diff options
299 files changed, 14419 insertions, 3038 deletions
diff --git a/Documentation/ABI/testing/sysfs-class-net-phydev b/Documentation/ABI/testing/sysfs-class-net-phydev index ac722dd5e694..31615c59bff9 100644 --- a/Documentation/ABI/testing/sysfs-class-net-phydev +++ b/Documentation/ABI/testing/sysfs-class-net-phydev @@ -26,6 +26,16 @@ Description: This ID is used to match the device with the appropriate driver. +What: /sys/class/mdio_bus/<bus>/<device>/c45_phy_ids/mmd<n>_device_id +Date: June 2025 +KernelVersion: 6.17 +Contact: netdev@vger.kernel.org +Description: + This attribute contains the 32-bit PHY Identifier as reported + by the device during bus enumeration, encoded in hexadecimal. + These C45 IDs are used to match the device with the appropriate + driver. These files are invisible to the C22 device. + What: /sys/class/mdio_bus/<bus>/<device>/phy_interface Date: February 2014 KernelVersion: 3.15 diff --git a/Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml b/Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml index fd4244fceced..ca61cc37a790 100644 --- a/Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml +++ b/Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml @@ -22,6 +22,12 @@ properties: reg: maxItems: 1 + vdd-supply: + description: Regulator that provides 3.3V VDD power supply. + + vdda-supply: + description: Regulator that provides 3.3V VDDA power supply. + managers: type: object additionalProperties: false @@ -68,6 +74,15 @@ properties: "#size-cells": const: 0 + vmain-supply: + description: Regulator that provides 44-57V VMAIN power supply. + + vaux5-supply: + description: Regulator that provides 5V VAUX5 power supply. + + vaux3p3-supply: + description: Regulator that provides 3.3V VAUX3P3 power supply. + patternProperties: '^port@[0-7]$': type: object @@ -106,10 +121,11 @@ examples: #address-cells = <1>; #size-cells = <0>; - manager@0 { + manager0: manager@0 { reg = <0>; #address-cells = <1>; #size-cells = <0>; + vmain-supply = <&pse1_supply>; phys0: port@0 { reg = <0>; @@ -161,7 +177,7 @@ examples: pairset-names = "alternative-a", "alternative-b"; pairsets = <&phys0>, <&phys1>; polarity-supported = "MDI", "S"; - vpwr-supply = <&vpwr1>; + vpwr-supply = <&manager0>; }; pse_pi1: pse-pi@1 { reg = <1>; @@ -169,7 +185,7 @@ examples: pairset-names = "alternative-a"; pairsets = <&phys2>; polarity-supported = "MDI"; - vpwr-supply = <&vpwr2>; + vpwr-supply = <&manager0>; }; }; }; diff --git a/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml b/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml index d08abcb01211..3a5f960d8489 100644 --- a/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml +++ b/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml @@ -20,6 +20,9 @@ properties: reg: maxItems: 1 + interrupts: + maxItems: 1 + '#pse-cells': const: 1 @@ -62,9 +65,12 @@ unevaluatedProperties: false required: - compatible - reg + - interrupts examples: - | + #include <dt-bindings/interrupt-controller/irq.h> + i2c { #address-cells = <1>; #size-cells = <0>; @@ -72,6 +78,8 @@ examples: ethernet-pse@20 { compatible = "ti,tps23881"; reg = <0x20>; + interrupts = <8 IRQ_TYPE_LEVEL_HIGH>; + interrupt-parent = <&gpiog>; channels { #address-cells = <1>; diff --git a/Documentation/driver-api/dpll.rst b/Documentation/driver-api/dpll.rst index e6855cd37e85..195e1e5d9a58 100644 --- a/Documentation/driver-api/dpll.rst +++ b/Documentation/driver-api/dpll.rst @@ -214,6 +214,24 @@ offset values are fractional with 3-digit decimal places and shell be divided with ``DPLL_PIN_PHASE_OFFSET_DIVIDER`` to get integer part and modulo divided to get fractional part. +Phase offset monitor +==================== + +Phase offset measurement is typically performed against the current active +source. However, some DPLL (Digital Phase-Locked Loop) devices may offer +the capability to monitor phase offsets across all available inputs. +The attribute and current feature state shall be included in the response +message of the ``DPLL_CMD_DEVICE_GET`` command for supported DPLL devices. +In such cases, users can also control the feature using the +``DPLL_CMD_DEVICE_SET`` command by setting the ``enum dpll_feature_state`` +values for the attribute. +Once enabled the phase offset measurements for the input shall be returned +in the ``DPLL_A_PIN_PHASE_OFFSET`` attribute. + + =============================== ======================== + ``DPLL_A_PHASE_OFFSET_MONITOR`` attr state of a feature + =============================== ======================== + Embedded SYNC ============= diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index 115d1a8f50bd..3bd6851c1d3c 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -240,6 +240,20 @@ definitions: integer part of a measured phase offset value. Value of (DPLL_A_PHASE_OFFSET % DPLL_PHASE_OFFSET_DIVIDER) is a fractional part of a measured phase offset value. + - + type: enum + name: feature-state + doc: | + Allow control (enable/disable) and status checking over features. + entries: + - + name: disable + doc: | + feature shall be disabled + - + name: enable + doc: | + feature shall be enabled attribute-sets: - @@ -293,6 +307,14 @@ attribute-sets: be put to message multiple times to indicate possible parallel quality levels (e.g. one specified by ITU option 1 and another one specified by option 2). + - + name: phase-offset-monitor + type: u32 + enum: feature-state + doc: Receive or request state of phase offset monitor feature. + If enabled, dpll device shall monitor and notify all currently + available inputs for changes of their phase offset against the + dpll device. - name: pin enum-name: dpll_a_pin @@ -483,6 +505,7 @@ operations: - temp - clock-id - type + - phase-offset-monitor dump: reply: *dev-attrs @@ -499,6 +522,7 @@ operations: request: attributes: - id + - phase-offset-monitor - name: device-create-ntf doc: Notification about device appearing diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index ed9bcdec01cc..e6a77e8053a0 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -118,6 +118,43 @@ definitions: doc: | Hardware timestamp comes from one PHY device of the network topology + - + name: pse-event + doc: PSE event list for the PSE controller + type: flags + name-prefix: ethtool- + entries: + - + name: pse-event-over-current + doc: PSE output current is too high + - + name: pse-event-over-temp + doc: PSE in over temperature state + - + name: c33-pse-event-detection + doc: | + detection process occur on the PSE. IEEE 802.3-2022 33.2.5 and + 145.2.6 PSE detection of PDs. IEEE 802.3-202 30.9.1.1.5 + aPSEPowerDetectionStatus + - + name: c33-pse-event-classification + doc: | + classification process occur on the PSE. IEEE 802.3-2022 33.2.6 + and 145.2.8 classification of PDs mutual identification. + IEEE 802.3-2022 30.9.1.1.8 aPSEPowerClassification. + - + name: c33-pse-event-disconnection + doc: | + PD has been disconnected on the PSE. IEEE 802.3-2022 33.3.8 + and 145.3.9 PD Maintain Power Signature. IEEE 802.3-2022 + 33.5.1.2.9 MPS Absent. IEEE 802.3-2022 30.9.1.1.20 + aPSEMPSAbsentCounter. + - + name: pse-event-over-budget + doc: PSE turned off due to over budget situation + - + name: pse-event-sw-pw-control-error + doc: PSE faced an error managing the power control from software attribute-sets: - @@ -1395,6 +1432,18 @@ attribute-sets: type: nest multi-attr: true nested-attributes: c33-pse-pw-limit + - + name: pse-pw-d-id + type: u32 + name-prefix: ethtool-a- + - + name: pse-prio-max + type: u32 + name-prefix: ethtool-a- + - + name: pse-prio + type: u32 + name-prefix: ethtool-a- - name: rss attr-cnt-name: __ethtool-a-rss-cnt @@ -1555,6 +1604,19 @@ attribute-sets: name: hwtstamp-flags type: nest nested-attributes: bitset + - + name: pse-ntf + attr-cnt-name: --ethtool-a-pse-ntf-cnt + attributes: + - + name: header + type: nest + nested-attributes: header + - + name: events + type: uint + enum: pse-event + doc: List of events reported by the PSE controller operations: enum-model: directional @@ -2205,6 +2267,9 @@ operations: - c33-pse-ext-substate - c33-pse-avail-pw-limit - c33-pse-pw-limit-ranges + - pse-pw-d-id + - pse-prio-max + - pse-prio dump: *pse-get-op - name: pse-set @@ -2219,6 +2284,7 @@ operations: - podl-pse-admin-control - c33-pse-admin-control - c33-pse-avail-pw-limit + - pse-prio - name: rss-get doc: Get RSS params. @@ -2413,3 +2479,13 @@ operations: attributes: *tsconfig reply: attributes: *tsconfig + - + name: pse-ntf + doc: Notification for PSE events. + + attribute-set: pse-ntf + + event: + attributes: + - header + - events diff --git a/Documentation/networking/device_drivers/ethernet/amazon/ena.rst b/Documentation/networking/device_drivers/ethernet/amazon/ena.rst index 4561e8ab9e08..14784a0a6a8a 100644 --- a/Documentation/networking/device_drivers/ethernet/amazon/ena.rst +++ b/Documentation/networking/device_drivers/ethernet/amazon/ena.rst @@ -56,6 +56,9 @@ ena_netdev.[ch] Main Linux kernel driver. ena_ethtool.c ethtool callbacks. ena_xdp.[ch] XDP files ena_pci_id_tbl.h Supported device IDs. +ena_phc.[ch] PTP hardware clock infrastructure (see `PHC`_ for more info) +ena_devlink.[ch] devlink files. +ena_debugfs.[ch] debugfs files. ================= ====================================================== Management Interface: @@ -221,6 +224,99 @@ descriptor it was received on would be recycled. When a packet smaller than RX copybreak bytes is received, it is copied into a new memory buffer and the RX descriptor is returned to HW. +.. _`PHC`: + +PTP Hardware Clock (PHC) +======================== +.. _`ptp-userspace-api`: https://docs.kernel.org/driver-api/ptp.html#ptp-hardware-clock-user-space-api +.. _`testptp`: https://elixir.bootlin.com/linux/latest/source/tools/testing/selftests/ptp/testptp.c + +ENA Linux driver supports PTP hardware clock providing timestamp reference to achieve nanosecond resolution. + +**PHC support** + +PHC depends on the PTP module, which needs to be either loaded as a module or compiled into the kernel. + +Verify if the PTP module is present: + +.. code-block:: shell + + grep -w '^CONFIG_PTP_1588_CLOCK=[ym]' /boot/config-`uname -r` + +- If no output is provided, the ENA driver cannot be loaded with PHC support. + +**PHC activation** + +The feature is turned off by default, in order to turn the feature on, the ENA driver +can be loaded in the following way: + +- devlink: + +.. code-block:: shell + + sudo devlink dev param set pci/<domain:bus:slot.function> name enable_phc value true cmode driverinit + sudo devlink dev reload pci/<domain:bus:slot.function> + # for example: + sudo devlink dev param set pci/0000:00:06.0 name enable_phc value true cmode driverinit + sudo devlink dev reload pci/0000:00:06.0 + +All available PTP clock sources can be tracked here: + +.. code-block:: shell + + ls /sys/class/ptp + +PHC support and capabilities can be verified using ethtool: + +.. code-block:: shell + + ethtool -T <interface> + +**PHC timestamp** + +To retrieve PHC timestamp, use `ptp-userspace-api`_, usage example using `testptp`_: + +.. code-block:: shell + + testptp -d /dev/ptp$(ethtool -T <interface> | awk '/PTP Hardware Clock:/ {print $NF}') -k 1 + +PHC get time requests should be within reasonable bounds, +avoid excessive utilization to ensure optimal performance and efficiency. +The ENA device restricts the frequency of PHC get time requests to a maximum +of 125 requests per second. If this limit is surpassed, the get time request +will fail, leading to an increment in the phc_err_ts statistic. + +**PHC statistics** + +PHC can be monitored using debugfs (if mounted): + +.. code-block:: shell + + sudo cat /sys/kernel/debug/<domain:bus:slot.function>/phc_stats + + # for example: + sudo cat /sys/kernel/debug/0000:00:06.0/phc_stats + +PHC errors must remain below 1% of all PHC requests to maintain the desired level of accuracy and reliability + +================= ====================================================== +**phc_cnt** | Number of successful retrieved timestamps (below expire timeout). +**phc_exp** | Number of expired retrieved timestamps (above expire timeout). +**phc_skp** | Number of skipped get time attempts (during block period). +**phc_err_dv** | Number of failed get time attempts due to device errors (entering into block state). +**phc_err_ts** | Number of failed get time attempts due to timestamp errors (entering into block state), + | This occurs if driver exceeded the request limit or device received an invalid timestamp. +================= ====================================================== + +PHC timeouts: + +================= ====================================================== +**expire** | Max time for a valid timestamp retrieval, passing this threshold will fail + | the get time request and block new requests until block timeout. +**block** | Blocking period starts once get time request expires or fails, + | all get time requests during block period will be skipped. +================= ====================================================== + Statistics ========== @@ -268,6 +364,18 @@ RSS - The user can provide a hash key, hash function, and configure the indirection table through `ethtool(8)`. +DEVLINK SUPPORT +=============== +.. _`devlink`: https://www.kernel.org/doc/html/latest/networking/devlink/index.html + +`devlink`_ supports reloading the driver and initiating re-negotiation with the ENA device + +.. code-block:: shell + + sudo devlink dev reload pci/<domain:bus:slot.function> + # for example: + sudo devlink dev reload pci/0000:00:06.0 + DATA PATH ========= diff --git a/Documentation/networking/devlink/devlink-params.rst b/Documentation/networking/devlink/devlink-params.rst index 4e01dc32bc08..3da8f4ef2417 100644 --- a/Documentation/networking/devlink/devlink-params.rst +++ b/Documentation/networking/devlink/devlink-params.rst @@ -137,3 +137,6 @@ own name. * - ``event_eq_size`` - u32 - Control the size of asynchronous control events EQ. + * - ``enable_phc`` + - Boolean + - Enable PHC (PTP Hardware Clock) functionality in the device. diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index b6e9af4d0f1b..e45bb555e909 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -290,6 +290,7 @@ Kernel to userspace: ``ETHTOOL_MSG_PHY_NTF`` Ethernet PHY information change ``ETHTOOL_MSG_TSCONFIG_GET_REPLY`` hw timestamping configuration ``ETHTOOL_MSG_TSCONFIG_SET_REPLY`` new hw timestamping configuration + ``ETHTOOL_MSG_PSE_NTF`` PSE events notification ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -1788,6 +1789,11 @@ Kernel response contents: limit of the PoE PSE. ``ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES`` nested Supported power limit configuration ranges. + ``ETHTOOL_A_PSE_PW_D_ID`` u32 Index of the PSE power domain + ``ETHTOOL_A_PSE_PRIO_MAX`` u32 Priority maximum configurable + on the PoE PSE + ``ETHTOOL_A_PSE_PRIO`` u32 Priority of the PoE PSE + currently configured ========================================== ====== ============================= When set, the optional ``ETHTOOL_A_PODL_PSE_ADMIN_STATE`` attribute identifies @@ -1861,6 +1867,15 @@ identifies the C33 PSE power limit ranges through If the controller works with fixed classes, the min and max values will be equal. +The ``ETHTOOL_A_PSE_PW_D_ID`` attribute identifies the index of PSE power +domain. + +When set, the optional ``ETHTOOL_A_PSE_PRIO_MAX`` attribute identifies +the PSE maximum priority value. +When set, the optional ``ETHTOOL_A_PSE_PRIO`` attributes is used to +identifies the currently configured PSE priority. +For a description of PSE priority attributes, see ``PSE_SET``. + PSE_SET ======= @@ -1874,6 +1889,8 @@ Request contents: ``ETHTOOL_A_C33_PSE_ADMIN_CONTROL`` u32 Control PSE Admin state ``ETHTOOL_A_C33_PSE_AVAIL_PWR_LIMIT`` u32 Control PoE PSE available power limit + ``ETHTOOL_A_PSE_PRIO`` u32 Control priority of the + PoE PSE ====================================== ====== ============================= When set, the optional ``ETHTOOL_A_PODL_PSE_ADMIN_CONTROL`` attribute is used @@ -1896,6 +1913,38 @@ various existing products that document power consumption in watts rather than classes. If power limit configuration based on classes is needed, the conversion can be done in user space, for example by ethtool. +When set, the optional ``ETHTOOL_A_PSE_PRIO`` attributes is used to +control the PSE priority. Allowed priority value are between zero and +the value of ``ETHTOOL_A_PSE_PRIO_MAX`` attribute. + +A lower value indicates a higher priority, meaning that a priority value +of 0 corresponds to the highest port priority. +Port priority serves two functions: + + - Power-up Order: After a reset, ports are powered up in order of their + priority from highest to lowest. Ports with higher priority + (lower values) power up first. + - Shutdown Order: When the power budget is exceeded, ports with lower + priority (higher values) are turned off first. + +PSE_NTF +======= + +Notify PSE events. + +Notification contents: + + =============================== ====== ======================== + ``ETHTOOL_A_PSE_HEADER`` nested request header + ``ETHTOOL_A_PSE_EVENTS`` bitset PSE events + =============================== ====== ======================== + +When set, the optional ``ETHTOOL_A_PSE_EVENTS`` attribute identifies the +PSE events. + +.. kernel-doc:: include/uapi/linux/ethtool_netlink_generated.h + :identifiers: ethtool_pse_event + RSS_GET ======= diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 0f1251cce314..466bc3f5186e 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -645,9 +645,11 @@ tcp_recovery - INTEGER features. ========= ============================================================= - RACK: 0x1 enables the RACK loss detection for fast detection of lost - retransmissions and tail drops. It also subsumes and disables - RFC6675 recovery for SACK connections. + RACK: 0x1 enables RACK loss detection, for fast detection of lost + retransmissions and tail drops, and resilience to + reordering. currently, setting this bit to 0 has no + effect, since RACK is the only supported loss detection + algorithm. RACK: 0x2 makes RACK's reordering window static (min_rtt/4). diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst index bc9b2131bf7a..7bbda5944ee2 100644 --- a/Documentation/networking/net_cachelines/tcp_sock.rst +++ b/Documentation/networking/net_cachelines/tcp_sock.rst @@ -115,7 +115,6 @@ u32 lost_out read_mostly read_m u32 sacked_out read_mostly read_mostly tcp_left_out(tx);tcp_packets_in_flight(tx/rx);tcp_clean_rtx_queue(rx) struct hrtimer pacing_timer struct hrtimer compressed_ack_timer -struct sk_buff* lost_skb_hint read_mostly tcp_clean_rtx_queue struct sk_buff* retransmit_skb_hint read_mostly tcp_clean_rtx_queue struct rb_root out_of_order_queue read_mostly tcp_data_queue,tcp_fast_path_check struct sk_buff* ooo_last_skb @@ -123,7 +122,6 @@ struct tcp_sack_block[1] duplicate_sack struct tcp_sack_block[4] selective_acks struct tcp_sack_block[4] recv_sack_cache struct sk_buff* highest_sack read_write tcp_event_new_data_sent -int lost_cnt_hint u32 prior_ssthresh u32 high_seq u32 retrans_stamp diff --git a/Documentation/networking/netconsole.rst b/Documentation/networking/netconsole.rst index a0076b542e9c..59cb9982afe6 100644 --- a/Documentation/networking/netconsole.rst +++ b/Documentation/networking/netconsole.rst @@ -340,6 +340,38 @@ In this example, the message was sent by CPU 42. cpu=42 # kernel-populated value +Message ID auto population in userdata +-------------------------------------- + +Within the netconsole configfs hierarchy, there is a file named `msgid_enabled` +located in the `userdata` directory. This file controls the message ID +auto-population feature, which assigns a numeric id to each message sent to a +given target and appends the ID to userdata dictionary in every message sent. + +The message ID is generated using a per-target 32 bit counter that is +incremented for every message sent to the target. Note that this counter will +eventually wrap around after reaching uint32_t max value, so the message ID is +not globally unique over time. However, it can still be used by the target to +detect if messages were dropped before reaching the target by identifying gaps +in the sequence of IDs. + +It is important to distinguish message IDs from the message <sequnum> field. +Some kernel messages may never reach netconsole (for example, due to printk +rate limiting). Thus, a gap in <sequnum> cannot be solely relied upon to +indicate that a message was dropped during transmission, as it may never have +been sent via netconsole. The message ID, on the other hand, is only assigned +to messages that are actually transmitted via netconsole. + +Example:: + + echo "This is message #1" > /dev/kmsg + echo "This is message #2" > /dev/kmsg + 13,434,54928466,-;This is message #1 + msgid=1 + 13,435,54934019,-;This is message #2 + msgid=2 + + Extended console: ================= diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h index d529bcb03775..062def303dce 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h @@ -18,9 +18,8 @@ #define OTX2_CPT_MAX_VFS_NUM 128 #define OTX2_CPT_RVU_FUNC_ADDR_S(blk, slot, offs) \ (((blk) << 20) | ((slot) << 12) | (offs)) -#define OTX2_CPT_RVU_PFFUNC(pf, func) \ - ((((pf) & RVU_PFVF_PF_MASK) << RVU_PFVF_PF_SHIFT) | \ - (((func) & RVU_PFVF_FUNC_MASK) << RVU_PFVF_FUNC_SHIFT)) + +#define OTX2_CPT_RVU_PFFUNC(pdev, pf, func) rvu_make_pcifunc(pdev, pf, func) #define OTX2_CPT_INVALID_CRYPTO_ENG_GRP 0xFF #define OTX2_CPT_NAME_LENGTH 64 diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c index 12c0e966fa65..b4b2d3d1cbc2 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c @@ -142,7 +142,7 @@ static int send_inline_ipsec_inbound_msg(struct otx2_cptpf_dev *cptpf, memset(req, 0, sizeof(*req)); req->hdr.id = MBOX_MSG_CPT_INLINE_IPSEC_CFG; req->hdr.sig = OTX2_MBOX_REQ_SIG; - req->hdr.pcifunc = OTX2_CPT_RVU_PFFUNC(cptpf->pf_id, 0); + req->hdr.pcifunc = OTX2_CPT_RVU_PFFUNC(cptpf->pdev, cptpf->pf_id, 0); req->dir = CPT_INLINE_INBOUND; req->slot = slot; req->sso_pf_func_ovrd = cptpf->sso_pf_func_ovrd; @@ -184,7 +184,8 @@ static int rx_inline_ipsec_lf_cfg(struct otx2_cptpf_dev *cptpf, u8 egrp, nix_req->gen_cfg.opcode = cpt_inline_rx_opcode(pdev); nix_req->gen_cfg.param1 = req->param1; nix_req->gen_cfg.param2 = req->param2; - nix_req->inst_qsel.cpt_pf_func = OTX2_CPT_RVU_PFFUNC(cptpf->pf_id, 0); + nix_req->inst_qsel.cpt_pf_func = + OTX2_CPT_RVU_PFFUNC(cptpf->pdev, cptpf->pf_id, 0); nix_req->inst_qsel.cpt_slot = 0; ret = otx2_cpt_send_mbox_msg(&cptpf->afpf_mbox, pdev); if (ret) @@ -392,9 +393,8 @@ void otx2_cptpf_vfpf_mbox_handler(struct work_struct *work) msg = (struct mbox_msghdr *)(mdev->mbase + offset); /* Set which VF sent this message based on mbox IRQ */ - msg->pcifunc = ((u16)cptpf->pf_id << RVU_PFVF_PF_SHIFT) | - ((vf->vf_id + 1) & RVU_PFVF_FUNC_MASK); - + msg->pcifunc = rvu_make_pcifunc(cptpf->pdev, cptpf->pf_id, + (vf->vf_id + 1)); err = cptpf_handle_vf_req(cptpf, vf, msg, msg->next_msgoff - offset); /* @@ -469,8 +469,7 @@ static void process_afpf_mbox_msg(struct otx2_cptpf_dev *cptpf, switch (msg->id) { case MBOX_MSG_READY: - cptpf->pf_id = (msg->pcifunc >> RVU_PFVF_PF_SHIFT) & - RVU_PFVF_PF_MASK; + cptpf->pf_id = rvu_get_pf(cptpf->pdev, msg->pcifunc); break; case MBOX_MSG_MSIX_OFFSET: rsp_msix = (struct msix_offset_rsp *) msg; diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c index 78367849c3d5..7180944ece50 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c @@ -176,7 +176,9 @@ static int cptx_set_ucode_base(struct otx2_cpt_eng_grp_info *eng_grp, /* Set PF number for microcode fetches */ ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev, CPT_AF_PF_FUNC, - cptpf->pf_id << RVU_PFVF_PF_SHIFT, blkaddr); + rvu_make_pcifunc(cptpf->pdev, + cptpf->pf_id, 0), + blkaddr); if (ret) return ret; diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c index 931b72580fd9..92e49babd79a 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c @@ -189,7 +189,7 @@ int otx2_cptvf_send_eng_grp_num_msg(struct otx2_cptvf_dev *cptvf, int eng_type) } req->hdr.id = MBOX_MSG_GET_ENG_GRP_NUM; req->hdr.sig = OTX2_MBOX_REQ_SIG; - req->hdr.pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->vf_id, 0); + req->hdr.pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->pdev, cptvf->vf_id, 0); req->eng_type = eng_type; return otx2_cpt_send_mbox_msg(mbox, pdev); @@ -210,7 +210,7 @@ int otx2_cptvf_send_kvf_limits_msg(struct otx2_cptvf_dev *cptvf) } req->id = MBOX_MSG_GET_KVF_LIMITS; req->sig = OTX2_MBOX_REQ_SIG; - req->pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->vf_id, 0); + req->pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->pdev, cptvf->vf_id, 0); return otx2_cpt_send_mbox_msg(mbox, pdev); } @@ -230,7 +230,7 @@ int otx2_cptvf_send_caps_msg(struct otx2_cptvf_dev *cptvf) } req->id = MBOX_MSG_GET_CAPS; req->sig = OTX2_MBOX_REQ_SIG; - req->pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->vf_id, 0); + req->pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->pdev, cptvf->vf_id, 0); return otx2_cpt_send_mbox_msg(mbox, pdev); } diff --git a/drivers/dpll/dpll_core.h b/drivers/dpll/dpll_core.h index 2b6d8ef1cdf3..9b11e637397b 100644 --- a/drivers/dpll/dpll_core.h +++ b/drivers/dpll/dpll_core.h @@ -45,7 +45,6 @@ struct dpll_device { * @dpll_refs: hold referencees to dplls pin was registered with * @parent_refs: hold references to parent pins pin was registered with * @prop: pin properties copied from the registerer - * @rclk_dev_name: holds name of device when pin can recover clock from it * @refcount: refcount * @rcu: rcu_head for kfree_rcu() **/ diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index c130f87147fa..4619aaa18b9c 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -127,6 +127,26 @@ dpll_msg_add_mode_supported(struct sk_buff *msg, struct dpll_device *dpll, } static int +dpll_msg_add_phase_offset_monitor(struct sk_buff *msg, struct dpll_device *dpll, + struct netlink_ext_ack *extack) +{ + const struct dpll_device_ops *ops = dpll_device_ops(dpll); + enum dpll_feature_state state; + int ret; + + if (ops->phase_offset_monitor_set && ops->phase_offset_monitor_get) { + ret = ops->phase_offset_monitor_get(dpll, dpll_priv(dpll), + &state, extack); + if (ret) + return ret; + if (nla_put_u32(msg, DPLL_A_PHASE_OFFSET_MONITOR, state)) + return -EMSGSIZE; + } + + return 0; +} + +static int dpll_msg_add_lock_status(struct sk_buff *msg, struct dpll_device *dpll, struct netlink_ext_ack *extack) { @@ -591,6 +611,9 @@ dpll_device_get_one(struct dpll_device *dpll, struct sk_buff *msg, return ret; if (nla_put_u32(msg, DPLL_A_TYPE, dpll->type)) return -EMSGSIZE; + ret = dpll_msg_add_phase_offset_monitor(msg, dpll, extack); + if (ret) + return ret; return 0; } @@ -747,6 +770,31 @@ int dpll_pin_change_ntf(struct dpll_pin *pin) EXPORT_SYMBOL_GPL(dpll_pin_change_ntf); static int +dpll_phase_offset_monitor_set(struct dpll_device *dpll, struct nlattr *a, + struct netlink_ext_ack *extack) +{ + const struct dpll_device_ops *ops = dpll_device_ops(dpll); + enum dpll_feature_state state = nla_get_u32(a), old_state; + int ret; + + if (!(ops->phase_offset_monitor_set && ops->phase_offset_monitor_get)) { + NL_SET_ERR_MSG_ATTR(extack, a, "dpll device not capable of phase offset monitor"); + return -EOPNOTSUPP; + } + ret = ops->phase_offset_monitor_get(dpll, dpll_priv(dpll), &old_state, + extack); + if (ret) { + NL_SET_ERR_MSG(extack, "unable to get current state of phase offset monitor"); + return ret; + } + if (state == old_state) + return 0; + + return ops->phase_offset_monitor_set(dpll, dpll_priv(dpll), state, + extack); +} + +static int dpll_pin_freq_set(struct dpll_pin *pin, struct nlattr *a, struct netlink_ext_ack *extack) { @@ -1533,12 +1581,29 @@ int dpll_nl_device_get_doit(struct sk_buff *skb, struct genl_info *info) return genlmsg_reply(msg, info); } -int dpll_nl_device_set_doit(struct sk_buff *skb, struct genl_info *info) +static int +dpll_set_from_nlattr(struct dpll_device *dpll, struct genl_info *info) { - /* placeholder for set command */ + int ret; + + if (info->attrs[DPLL_A_PHASE_OFFSET_MONITOR]) { + struct nlattr *a = info->attrs[DPLL_A_PHASE_OFFSET_MONITOR]; + + ret = dpll_phase_offset_monitor_set(dpll, a, info->extack); + if (ret) + return ret; + } + return 0; } +int dpll_nl_device_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct dpll_device *dpll = info->user_ptr[0]; + + return dpll_set_from_nlattr(dpll, info); +} + int dpll_nl_device_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct dpll_dump_ctx *ctx = dpll_dump_context(cb); diff --git a/drivers/dpll/dpll_nl.c b/drivers/dpll/dpll_nl.c index fe9b6893d261..8de90310c3be 100644 --- a/drivers/dpll/dpll_nl.c +++ b/drivers/dpll/dpll_nl.c @@ -37,8 +37,9 @@ static const struct nla_policy dpll_device_get_nl_policy[DPLL_A_ID + 1] = { }; /* DPLL_CMD_DEVICE_SET - do */ -static const struct nla_policy dpll_device_set_nl_policy[DPLL_A_ID + 1] = { +static const struct nla_policy dpll_device_set_nl_policy[DPLL_A_PHASE_OFFSET_MONITOR + 1] = { [DPLL_A_ID] = { .type = NLA_U32, }, + [DPLL_A_PHASE_OFFSET_MONITOR] = NLA_POLICY_MAX(NLA_U32, 1), }; /* DPLL_CMD_PIN_ID_GET - do */ @@ -105,7 +106,7 @@ static const struct genl_split_ops dpll_nl_ops[] = { .doit = dpll_nl_device_set_doit, .post_doit = dpll_post_doit, .policy = dpll_device_set_nl_policy, - .maxattr = DPLL_A_ID, + .maxattr = DPLL_A_PHASE_OFFSET_MONITOR, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, { diff --git a/drivers/net/amt.c b/drivers/net/amt.c index 734a0b3242a9..ed86537b2f61 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -979,7 +979,7 @@ static void amt_event_send_request(struct amt_dev *amt) amt->req_cnt++; out: exp = min_t(u32, (1 * (1 << amt->req_cnt)), AMT_MAX_REQ_TIMEOUT); - mod_delayed_work(amt_wq, &amt->req_wq, msecs_to_jiffies(exp * 1000)); + mod_delayed_work(amt_wq, &amt->req_wq, secs_to_jiffies(exp)); } static void amt_req_work(struct work_struct *work) @@ -1046,7 +1046,8 @@ static bool amt_send_membership_update(struct amt_dev *amt, amt->gw_port, amt->relay_port, false, - false); + false, + 0); amt_update_gw_status(amt, AMT_STATUS_SENT_UPDATE, true); return false; } @@ -1103,7 +1104,8 @@ static void amt_send_multicast_data(struct amt_dev *amt, amt->relay_port, tunnel->source_port, false, - false); + false, + 0); } static bool amt_send_membership_query(struct amt_dev *amt, @@ -1161,7 +1163,8 @@ static bool amt_send_membership_query(struct amt_dev *amt, amt->relay_port, tunnel->source_port, false, - false); + false, + 0); amt_update_relay_status(tunnel, AMT_STATUS_SENT_QUERY, true); return false; } diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index a9dffdcac805..0df3208783ad 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -362,8 +362,8 @@ static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev, udp_tunnel_xmit_skb(rt, sock->sk, skb, saddr, info->key.u.ipv4.dst, tos, ttl, df, sport, bareudp->port, !net_eq(bareudp->net, dev_net(bareudp->dev)), - !test_bit(IP_TUNNEL_CSUM_BIT, - info->key.tun_flags)); + !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags), + 0); return 0; free_dst: @@ -431,7 +431,8 @@ static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev, &saddr, &daddr, prio, ttl, info->key.label, sport, bareudp->port, !test_bit(IP_TUNNEL_CSUM_BIT, - info->key.tun_flags)); + info->key.tun_flags), + 0); return 0; free_dst: diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index ec5c64006a16..5a95877b7419 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -388,8 +388,8 @@ static void mcp251x_write_2regs(struct spi_device *spi, u8 reg, u8 v1, u8 v2) mcp251x_spi_write(spi, 4); } -static void mcp251x_write_bits(struct spi_device *spi, u8 reg, - u8 mask, u8 val) +static int mcp251x_write_bits(struct spi_device *spi, u8 reg, + u8 mask, u8 val) { struct mcp251x_priv *priv = spi_get_drvdata(spi); @@ -398,7 +398,7 @@ static void mcp251x_write_bits(struct spi_device *spi, u8 reg, priv->spi_tx_buf[2] = mask; priv->spi_tx_buf[3] = val; - mcp251x_spi_write(spi, 4); + return mcp251x_spi_write(spi, 4); } static u8 mcp251x_read_stat(struct spi_device *spi) @@ -441,6 +441,7 @@ static int mcp251x_gpio_request(struct gpio_chip *chip, unsigned int offset) { struct mcp251x_priv *priv = gpiochip_get_data(chip); + int ret; u8 val; /* nothing to be done for inputs */ @@ -450,8 +451,10 @@ static int mcp251x_gpio_request(struct gpio_chip *chip, val = BFPCTRL_BFE(offset - MCP251X_GPIO_RX0BF); mutex_lock(&priv->mcp_lock); - mcp251x_write_bits(priv->spi, BFPCTRL, val, val); + ret = mcp251x_write_bits(priv->spi, BFPCTRL, val, val); mutex_unlock(&priv->mcp_lock); + if (ret) + return ret; priv->reg_bfpctrl |= val; @@ -530,29 +533,35 @@ static int mcp251x_gpio_get_multiple(struct gpio_chip *chip, return 0; } -static void mcp251x_gpio_set(struct gpio_chip *chip, unsigned int offset, - int value) +static int mcp251x_gpio_set(struct gpio_chip *chip, unsigned int offset, + int value) { struct mcp251x_priv *priv = gpiochip_get_data(chip); u8 mask, val; + int ret; mask = BFPCTRL_BFS(offset - MCP251X_GPIO_RX0BF); val = value ? mask : 0; mutex_lock(&priv->mcp_lock); - mcp251x_write_bits(priv->spi, BFPCTRL, mask, val); + ret = mcp251x_write_bits(priv->spi, BFPCTRL, mask, val); mutex_unlock(&priv->mcp_lock); + if (ret) + return ret; priv->reg_bfpctrl &= ~mask; priv->reg_bfpctrl |= val; + + return 0; } -static void +static int mcp251x_gpio_set_multiple(struct gpio_chip *chip, unsigned long *maskp, unsigned long *bitsp) { struct mcp251x_priv *priv = gpiochip_get_data(chip); u8 mask, val; + int ret; mask = FIELD_GET(MCP251X_GPIO_OUTPUT_MASK, maskp[0]); mask = FIELD_PREP(BFPCTRL_BFS_MASK, mask); @@ -561,14 +570,18 @@ mcp251x_gpio_set_multiple(struct gpio_chip *chip, val = FIELD_PREP(BFPCTRL_BFS_MASK, val); if (!mask) - return; + return 0; mutex_lock(&priv->mcp_lock); - mcp251x_write_bits(priv->spi, BFPCTRL, mask, val); + ret = mcp251x_write_bits(priv->spi, BFPCTRL, mask, val); mutex_unlock(&priv->mcp_lock); + if (ret) + return ret; priv->reg_bfpctrl &= ~mask; priv->reg_bfpctrl |= val; + + return 0; } static void mcp251x_gpio_restore(struct spi_device *spi) @@ -594,8 +607,8 @@ static int mcp251x_gpio_setup(struct mcp251x_priv *priv) gpio->get_direction = mcp251x_gpio_get_direction; gpio->get = mcp251x_gpio_get; gpio->get_multiple = mcp251x_gpio_get_multiple; - gpio->set = mcp251x_gpio_set; - gpio->set_multiple = mcp251x_gpio_set_multiple; + gpio->set_rv = mcp251x_gpio_set; + gpio->set_multiple_rv = mcp251x_gpio_set_multiple; gpio->base = -1; gpio->ngpio = ARRAY_SIZE(mcp251x_gpio_names); gpio->names = mcp251x_gpio_names; diff --git a/drivers/net/dsa/b53/Kconfig b/drivers/net/dsa/b53/Kconfig index ebaa4a80d544..915008e8eff5 100644 --- a/drivers/net/dsa/b53/Kconfig +++ b/drivers/net/dsa/b53/Kconfig @@ -5,6 +5,7 @@ menuconfig B53 select NET_DSA_TAG_NONE select NET_DSA_TAG_BRCM select NET_DSA_TAG_BRCM_LEGACY + select NET_DSA_TAG_BRCM_LEGACY_FCS select NET_DSA_TAG_BRCM_PREPEND help This driver adds support for Broadcom managed switch chips. It supports diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index dc2f4adac9bc..46978757c972 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -361,18 +361,23 @@ static void b53_set_forwarding(struct b53_device *dev, int enable) b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, mgmt); - /* Include IMP port in dumb forwarding mode - */ - b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, &mgmt); - mgmt |= B53_MII_DUMB_FWDG_EN; - b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, mgmt); - - /* Look at B53_UC_FWD_EN and B53_MC_FWD_EN to decide whether - * frames should be flooded or not. - */ - b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt); - mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN | B53_IPMC_FWD_EN; - b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt); + if (!is5325(dev)) { + /* Include IMP port in dumb forwarding mode */ + b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, &mgmt); + mgmt |= B53_MII_DUMB_FWDG_EN; + b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, mgmt); + + /* Look at B53_UC_FWD_EN and B53_MC_FWD_EN to decide whether + * frames should be flooded or not. + */ + b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt); + mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN | B53_IPMC_FWD_EN; + b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt); + } else { + b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt); + mgmt |= B53_IP_MCAST_25; + b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt); + } } static void b53_enable_vlan(struct b53_device *dev, int port, bool enable, @@ -487,6 +492,9 @@ static int b53_flush_arl(struct b53_device *dev, u8 mask) { unsigned int i; + if (is5325(dev)) + return 0; + b53_write8(dev, B53_CTRL_PAGE, B53_FAST_AGE_CTRL, FAST_AGE_DONE | FAST_AGE_DYNAMIC | mask); @@ -511,6 +519,9 @@ out: static int b53_fast_age_port(struct b53_device *dev, int port) { + if (is5325(dev)) + return 0; + b53_write8(dev, B53_CTRL_PAGE, B53_FAST_AGE_PORT_CTRL, port); return b53_flush_arl(dev, FAST_AGE_PORT); @@ -518,6 +529,9 @@ static int b53_fast_age_port(struct b53_device *dev, int port) static int b53_fast_age_vlan(struct b53_device *dev, u16 vid) { + if (is5325(dev)) + return 0; + b53_write16(dev, B53_CTRL_PAGE, B53_FAST_AGE_VID_CTRL, vid); return b53_flush_arl(dev, FAST_AGE_VLAN); @@ -529,6 +543,10 @@ void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port) unsigned int i; u16 pvlan; + /* BCM5325 CPU port is at 8 */ + if ((is5325(dev) || is5365(dev)) && cpu_port == B53_CPU_PORT_25) + cpu_port = B53_CPU_PORT; + /* Enable the IMP port to be in the same VLAN as the other ports * on a per-port basis such that we only have Port i and IMP in * the same VLAN. @@ -546,12 +564,24 @@ static void b53_port_set_ucast_flood(struct b53_device *dev, int port, { u16 uc; - b53_read16(dev, B53_CTRL_PAGE, B53_UC_FLOOD_MASK, &uc); - if (unicast) - uc |= BIT(port); - else - uc &= ~BIT(port); - b53_write16(dev, B53_CTRL_PAGE, B53_UC_FLOOD_MASK, uc); + if (is5325(dev)) { + if (port == B53_CPU_PORT_25) + port = B53_CPU_PORT; + + b53_read16(dev, B53_IEEE_PAGE, B53_IEEE_UCAST_DLF, &uc); + if (unicast) + uc |= BIT(port) | B53_IEEE_UCAST_DROP_EN; + else + uc &= ~BIT(port); + b53_write16(dev, B53_IEEE_PAGE, B53_IEEE_UCAST_DLF, uc); + } else { + b53_read16(dev, B53_CTRL_PAGE, B53_UC_FLOOD_MASK, &uc); + if (unicast) + uc |= BIT(port); + else + uc &= ~BIT(port); + b53_write16(dev, B53_CTRL_PAGE, B53_UC_FLOOD_MASK, uc); + } } static void b53_port_set_mcast_flood(struct b53_device *dev, int port, @@ -559,19 +589,31 @@ static void b53_port_set_mcast_flood(struct b53_device *dev, int port, { u16 mc; - b53_read16(dev, B53_CTRL_PAGE, B53_MC_FLOOD_MASK, &mc); - if (multicast) - mc |= BIT(port); - else - mc &= ~BIT(port); - b53_write16(dev, B53_CTRL_PAGE, B53_MC_FLOOD_MASK, mc); + if (is5325(dev)) { + if (port == B53_CPU_PORT_25) + port = B53_CPU_PORT; - b53_read16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, &mc); - if (multicast) - mc |= BIT(port); - else - mc &= ~BIT(port); - b53_write16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, mc); + b53_read16(dev, B53_IEEE_PAGE, B53_IEEE_MCAST_DLF, &mc); + if (multicast) + mc |= BIT(port) | B53_IEEE_MCAST_DROP_EN; + else + mc &= ~BIT(port); + b53_write16(dev, B53_IEEE_PAGE, B53_IEEE_MCAST_DLF, mc); + } else { + b53_read16(dev, B53_CTRL_PAGE, B53_MC_FLOOD_MASK, &mc); + if (multicast) + mc |= BIT(port); + else + mc &= ~BIT(port); + b53_write16(dev, B53_CTRL_PAGE, B53_MC_FLOOD_MASK, mc); + + b53_read16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, &mc); + if (multicast) + mc |= BIT(port); + else + mc &= ~BIT(port); + b53_write16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, mc); + } } static void b53_port_set_learning(struct b53_device *dev, int port, @@ -579,6 +621,9 @@ static void b53_port_set_learning(struct b53_device *dev, int port, { u16 reg; + if (is5325(dev)) + return; + b53_read16(dev, B53_CTRL_PAGE, B53_DIS_LEARNING, ®); if (learning) reg &= ~BIT(port); @@ -615,6 +660,19 @@ int b53_setup_port(struct dsa_switch *ds, int port) if (dsa_is_user_port(ds, port)) b53_set_eap_mode(dev, port, EAP_MODE_SIMPLIFIED); + if (is5325(dev) && + in_range(port, 1, 4)) { + u8 reg; + + b53_read8(dev, B53_CTRL_PAGE, B53_PD_MODE_CTRL_25, ®); + reg &= ~PD_MODE_POWER_DOWN_PORT(0); + if (dsa_is_unused_port(ds, port)) + reg |= PD_MODE_POWER_DOWN_PORT(port); + else + reg &= ~PD_MODE_POWER_DOWN_PORT(port); + b53_write8(dev, B53_CTRL_PAGE, B53_PD_MODE_CTRL_25, reg); + } + return 0; } EXPORT_SYMBOL(b53_setup_port); @@ -713,6 +771,11 @@ void b53_brcm_hdr_setup(struct dsa_switch *ds, int port) hdr_ctl |= GC_FRM_MGMT_PORT_M; b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, hdr_ctl); + /* B53_BRCM_HDR not present on devices with legacy tags */ + if (dev->tag_protocol == DSA_TAG_PROTO_BRCM_LEGACY || + dev->tag_protocol == DSA_TAG_PROTO_BRCM_LEGACY_FCS) + return; + /* Enable Broadcom tags for IMP port */ b53_read8(dev, B53_MGMT_PAGE, B53_BRCM_HDR, &hdr_ctl); if (tag_en) @@ -1257,6 +1320,8 @@ static void b53_force_link(struct b53_device *dev, int port, int link) if (port == dev->imp_port) { off = B53_PORT_OVERRIDE_CTRL; val = PORT_OVERRIDE_EN; + } else if (is5325(dev)) { + return; } else { off = B53_GMII_PORT_OVERRIDE_CTRL(port); val = GMII_PO_EN; @@ -1281,6 +1346,8 @@ static void b53_force_port_config(struct b53_device *dev, int port, if (port == dev->imp_port) { off = B53_PORT_OVERRIDE_CTRL; val = PORT_OVERRIDE_EN; + } else if (is5325(dev)) { + return; } else { off = B53_GMII_PORT_OVERRIDE_CTRL(port); val = GMII_PO_EN; @@ -1311,10 +1378,19 @@ static void b53_force_port_config(struct b53_device *dev, int port, return; } - if (rx_pause) - reg |= PORT_OVERRIDE_RX_FLOW; - if (tx_pause) - reg |= PORT_OVERRIDE_TX_FLOW; + if (rx_pause) { + if (is5325(dev)) + reg |= PORT_OVERRIDE_LP_FLOW_25; + else + reg |= PORT_OVERRIDE_RX_FLOW; + } + + if (tx_pause) { + if (is5325(dev)) + reg |= PORT_OVERRIDE_LP_FLOW_25; + else + reg |= PORT_OVERRIDE_TX_FLOW; + } b53_write8(dev, B53_CTRL_PAGE, off, reg); } @@ -1764,6 +1840,45 @@ static int b53_arl_read(struct b53_device *dev, u64 mac, return *idx >= dev->num_arl_bins ? -ENOSPC : -ENOENT; } +static int b53_arl_read_25(struct b53_device *dev, u64 mac, + u16 vid, struct b53_arl_entry *ent, u8 *idx) +{ + DECLARE_BITMAP(free_bins, B53_ARLTBL_MAX_BIN_ENTRIES); + unsigned int i; + int ret; + + ret = b53_arl_op_wait(dev); + if (ret) + return ret; + + bitmap_zero(free_bins, dev->num_arl_bins); + + /* Read the bins */ + for (i = 0; i < dev->num_arl_bins; i++) { + u64 mac_vid; + + b53_read64(dev, B53_ARLIO_PAGE, + B53_ARLTBL_MAC_VID_ENTRY(i), &mac_vid); + + b53_arl_to_entry_25(ent, mac_vid); + + if (!(mac_vid & ARLTBL_VALID_25)) { + set_bit(i, free_bins); + continue; + } + if ((mac_vid & ARLTBL_MAC_MASK) != mac) + continue; + if (dev->vlan_enabled && + ((mac_vid >> ARLTBL_VID_S_65) & ARLTBL_VID_MASK_25) != vid) + continue; + *idx = i; + return 0; + } + + *idx = find_first_bit(free_bins, dev->num_arl_bins); + return *idx >= dev->num_arl_bins ? -ENOSPC : -ENOENT; +} + static int b53_arl_op(struct b53_device *dev, int op, int port, const unsigned char *addr, u16 vid, bool is_valid) { @@ -1778,14 +1893,18 @@ static int b53_arl_op(struct b53_device *dev, int op, int port, /* Perform a read for the given MAC and VID */ b53_write48(dev, B53_ARLIO_PAGE, B53_MAC_ADDR_IDX, mac); - b53_write16(dev, B53_ARLIO_PAGE, B53_VLAN_ID_IDX, vid); + if (!is5325m(dev)) + b53_write16(dev, B53_ARLIO_PAGE, B53_VLAN_ID_IDX, vid); /* Issue a read operation for this MAC */ ret = b53_arl_rw_op(dev, 1); if (ret) return ret; - ret = b53_arl_read(dev, mac, vid, &ent, &idx); + if (is5325(dev) || is5365(dev)) + ret = b53_arl_read_25(dev, mac, vid, &ent, &idx); + else + ret = b53_arl_read(dev, mac, vid, &ent, &idx); /* If this is a read, just finish now */ if (op) @@ -1829,12 +1948,17 @@ static int b53_arl_op(struct b53_device *dev, int op, int port, ent.is_static = true; ent.is_age = false; memcpy(ent.mac, addr, ETH_ALEN); - b53_arl_from_entry(&mac_vid, &fwd_entry, &ent); + if (is5325(dev) || is5365(dev)) + b53_arl_from_entry_25(&mac_vid, &ent); + else + b53_arl_from_entry(&mac_vid, &fwd_entry, &ent); b53_write64(dev, B53_ARLIO_PAGE, B53_ARLTBL_MAC_VID_ENTRY(idx), mac_vid); - b53_write32(dev, B53_ARLIO_PAGE, - B53_ARLTBL_DATA_ENTRY(idx), fwd_entry); + + if (!is5325(dev) && !is5365(dev)) + b53_write32(dev, B53_ARLIO_PAGE, + B53_ARLTBL_DATA_ENTRY(idx), fwd_entry); return b53_arl_rw_op(dev, 0); } @@ -1846,12 +1970,6 @@ int b53_fdb_add(struct dsa_switch *ds, int port, struct b53_device *priv = ds->priv; int ret; - /* 5325 and 5365 require some more massaging, but could - * be supported eventually - */ - if (is5325(priv) || is5365(priv)) - return -EOPNOTSUPP; - mutex_lock(&priv->arl_mutex); ret = b53_arl_op(priv, 0, port, addr, vid, true); mutex_unlock(&priv->arl_mutex); @@ -1878,10 +1996,15 @@ EXPORT_SYMBOL(b53_fdb_del); static int b53_arl_search_wait(struct b53_device *dev) { unsigned int timeout = 1000; - u8 reg; + u8 reg, offset; + + if (is5325(dev) || is5365(dev)) + offset = B53_ARL_SRCH_CTL_25; + else + offset = B53_ARL_SRCH_CTL; do { - b53_read8(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_CTL, ®); + b53_read8(dev, B53_ARLIO_PAGE, offset, ®); if (!(reg & ARL_SRCH_STDN)) return 0; @@ -1898,13 +2021,24 @@ static void b53_arl_search_rd(struct b53_device *dev, u8 idx, struct b53_arl_entry *ent) { u64 mac_vid; - u32 fwd_entry; - b53_read64(dev, B53_ARLIO_PAGE, - B53_ARL_SRCH_RSTL_MACVID(idx), &mac_vid); - b53_read32(dev, B53_ARLIO_PAGE, - B53_ARL_SRCH_RSTL(idx), &fwd_entry); - b53_arl_to_entry(ent, mac_vid, fwd_entry); + if (is5325(dev)) { + b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL_0_MACVID_25, + &mac_vid); + b53_arl_to_entry_25(ent, mac_vid); + } else if (is5365(dev)) { + b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL_0_MACVID_65, + &mac_vid); + b53_arl_to_entry_25(ent, mac_vid); + } else { + u32 fwd_entry; + + b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL_MACVID(idx), + &mac_vid); + b53_read32(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL(idx), + &fwd_entry); + b53_arl_to_entry(ent, mac_vid, fwd_entry); + } } static int b53_fdb_copy(int port, const struct b53_arl_entry *ent, @@ -1925,14 +2059,20 @@ int b53_fdb_dump(struct dsa_switch *ds, int port, struct b53_device *priv = ds->priv; struct b53_arl_entry results[2]; unsigned int count = 0; + u8 offset; int ret; u8 reg; mutex_lock(&priv->arl_mutex); + if (is5325(priv) || is5365(priv)) + offset = B53_ARL_SRCH_CTL_25; + else + offset = B53_ARL_SRCH_CTL; + /* Start search operation */ reg = ARL_SRCH_STDN; - b53_write8(priv, B53_ARLIO_PAGE, B53_ARL_SRCH_CTL, reg); + b53_write8(priv, offset, B53_ARL_SRCH_CTL, reg); do { ret = b53_arl_search_wait(priv); @@ -2165,7 +2305,13 @@ int b53_br_flags_pre(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack) { - if (flags.mask & ~(BR_FLOOD | BR_MCAST_FLOOD | BR_LEARNING)) + struct b53_device *dev = ds->priv; + unsigned long mask = (BR_FLOOD | BR_MCAST_FLOOD); + + if (!is5325(dev)) + mask |= BR_LEARNING; + + if (flags.mask & ~mask) return -EINVAL; return 0; @@ -2241,8 +2387,11 @@ enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds, int port, goto out; } - /* Older models require a different 6 byte tag */ - if (is5325(dev) || is5365(dev) || is63xx(dev)) { + /* Older models require different 6 byte tags */ + if (is5325(dev) || is5365(dev)) { + dev->tag_protocol = DSA_TAG_PROTO_BRCM_LEGACY_FCS; + goto out; + } else if (is63xx(dev)) { dev->tag_protocol = DSA_TAG_PROTO_BRCM_LEGACY; goto out; } @@ -2830,6 +2979,9 @@ static int b53_switch_init(struct b53_device *dev) } } + if (is5325e(dev)) + dev->num_arl_buckets = 512; + dev->num_ports = fls(dev->enabled_ports); dev->ds->num_ports = min_t(unsigned int, dev->num_ports, DSA_MAX_PORTS); @@ -2931,10 +3083,24 @@ int b53_switch_detect(struct b53_device *dev) b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_TABLE_ACCESS_25, 0xf); b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_TABLE_ACCESS_25, &tmp); - if (tmp == 0xf) + if (tmp == 0xf) { + u32 phy_id; + int val; + dev->chip_id = BCM5325_DEVICE_ID; - else + + val = b53_phy_read16(dev->ds, 0, MII_PHYSID1); + phy_id = (val & 0xffff) << 16; + val = b53_phy_read16(dev->ds, 0, MII_PHYSID2); + phy_id |= (val & 0xfff0); + + if (phy_id == 0x00406330) + dev->variant_id = B53_VARIANT_5325M; + else if (phy_id == 0x0143bc30) + dev->variant_id = B53_VARIANT_5325E; + } else { dev->chip_id = BCM5365_DEVICE_ID; + } break; case BCM5389_DEVICE_ID: case BCM5395_DEVICE_ID: diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index a5ef7071ba07..b1b9e8882ba4 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -84,6 +84,12 @@ enum { BCM53134_DEVICE_ID = 0x5075, }; +enum b53_variant_id { + B53_VARIANT_NONE = 0, + B53_VARIANT_5325E, + B53_VARIANT_5325M, +}; + struct b53_pcs { struct phylink_pcs pcs; struct b53_device *dev; @@ -118,6 +124,7 @@ struct b53_device { /* chip specific data */ u32 chip_id; + enum b53_variant_id variant_id; u8 core_rev; u8 vta_regs[3]; u8 duplex_reg; @@ -165,6 +172,18 @@ static inline int is5325(struct b53_device *dev) return dev->chip_id == BCM5325_DEVICE_ID; } +static inline int is5325e(struct b53_device *dev) +{ + return is5325(dev) && + dev->variant_id == B53_VARIANT_5325E; +} + +static inline int is5325m(struct b53_device *dev) +{ + return is5325(dev) && + dev->variant_id == B53_VARIANT_5325M; +} + static inline int is5365(struct b53_device *dev) { #ifdef CONFIG_BCM47XX @@ -298,6 +317,19 @@ static inline void b53_arl_to_entry(struct b53_arl_entry *ent, ent->vid = mac_vid >> ARLTBL_VID_S; } +static inline void b53_arl_to_entry_25(struct b53_arl_entry *ent, + u64 mac_vid) +{ + memset(ent, 0, sizeof(*ent)); + ent->port = (mac_vid >> ARLTBL_DATA_PORT_ID_S_25) & + ARLTBL_DATA_PORT_ID_MASK_25; + ent->is_valid = !!(mac_vid & ARLTBL_VALID_25); + ent->is_age = !!(mac_vid & ARLTBL_AGE_25); + ent->is_static = !!(mac_vid & ARLTBL_STATIC_25); + u64_to_ether_addr(mac_vid, ent->mac); + ent->vid = mac_vid >> ARLTBL_VID_S_65; +} + static inline void b53_arl_from_entry(u64 *mac_vid, u32 *fwd_entry, const struct b53_arl_entry *ent) { @@ -312,6 +344,22 @@ static inline void b53_arl_from_entry(u64 *mac_vid, u32 *fwd_entry, *fwd_entry |= ARLTBL_AGE; } +static inline void b53_arl_from_entry_25(u64 *mac_vid, + const struct b53_arl_entry *ent) +{ + *mac_vid = ether_addr_to_u64(ent->mac); + *mac_vid |= (u64)(ent->port & ARLTBL_DATA_PORT_ID_MASK_25) << + ARLTBL_DATA_PORT_ID_S_25; + *mac_vid |= (u64)(ent->vid & ARLTBL_VID_MASK_25) << + ARLTBL_VID_S_65; + if (ent->is_valid) + *mac_vid |= ARLTBL_VALID_25; + if (ent->is_static) + *mac_vid |= ARLTBL_STATIC_25; + if (ent->is_age) + *mac_vid |= ARLTBL_AGE_25; +} + #ifdef CONFIG_BCM47XX #include <linux/bcm47xx_nvram.h> diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h index 1fbc5a204bc7..309fe0e46dad 100644 --- a/drivers/net/dsa/b53/b53_regs.h +++ b/drivers/net/dsa/b53/b53_regs.h @@ -29,6 +29,7 @@ #define B53_ARLIO_PAGE 0x05 /* ARL Access */ #define B53_FRAMEBUF_PAGE 0x06 /* Management frame access */ #define B53_MEM_ACCESS_PAGE 0x08 /* Memory access */ +#define B53_IEEE_PAGE 0x0a /* IEEE 802.1X */ /* PHY Registers */ #define B53_PORT_MII_PAGE(i) (0x10 + (i)) /* Port i MII Registers */ @@ -95,17 +96,22 @@ #define PORT_OVERRIDE_SPEED_10M (0 << PORT_OVERRIDE_SPEED_S) #define PORT_OVERRIDE_SPEED_100M (1 << PORT_OVERRIDE_SPEED_S) #define PORT_OVERRIDE_SPEED_1000M (2 << PORT_OVERRIDE_SPEED_S) +#define PORT_OVERRIDE_LP_FLOW_25 BIT(3) /* BCM5325 only */ #define PORT_OVERRIDE_RV_MII_25 BIT(4) /* BCM5325 only */ #define PORT_OVERRIDE_RX_FLOW BIT(4) #define PORT_OVERRIDE_TX_FLOW BIT(5) #define PORT_OVERRIDE_SPEED_2000M BIT(6) /* BCM5301X only, requires setting 1000M */ #define PORT_OVERRIDE_EN BIT(7) /* Use the register contents */ -/* Power-down mode control */ +/* Power-down mode control (8 bit) */ #define B53_PD_MODE_CTRL_25 0x0f +#define PD_MODE_PORT_MASK 0x1f +/* Bit 0 also powers down the switch. */ +#define PD_MODE_POWER_DOWN_PORT(i) BIT(i) /* IP Multicast control (8 bit) */ #define B53_IP_MULTICAST_CTRL 0x21 +#define B53_IP_MCAST_25 BIT(0) #define B53_IPMC_FWD_EN BIT(1) #define B53_UC_FWD_EN BIT(6) #define B53_MC_FWD_EN BIT(7) @@ -324,9 +330,10 @@ #define ARLTBL_VID_MASK 0xfff #define ARLTBL_DATA_PORT_ID_S_25 48 #define ARLTBL_DATA_PORT_ID_MASK_25 0xf -#define ARLTBL_AGE_25 BIT(61) -#define ARLTBL_STATIC_25 BIT(62) -#define ARLTBL_VALID_25 BIT(63) +#define ARLTBL_VID_S_65 53 +#define ARLTBL_AGE_25 BIT_ULL(61) +#define ARLTBL_STATIC_25 BIT_ULL(62) +#define ARLTBL_VALID_25 BIT_ULL(63) /* ARL Table Data Entry N Registers (32 bit) */ #define B53_ARLTBL_DATA_ENTRY(n) ((0x10 * (n)) + 0x18) @@ -366,6 +373,18 @@ #define B53_ARL_SRCH_RSTL(x) (B53_ARL_SRCH_RSTL_0 + ((x) * 0x10)) /************************************************************************* + * IEEE 802.1X Registers + *************************************************************************/ + +/* Multicast DLF Drop Control register (16 bit) */ +#define B53_IEEE_MCAST_DLF 0x94 +#define B53_IEEE_MCAST_DROP_EN BIT(11) + +/* Unicast DLF Drop Control register (16 bit) */ +#define B53_IEEE_UCAST_DLF 0x96 +#define B53_IEEE_UCAST_DROP_EN BIT(11) + +/************************************************************************* * Port VLAN Registers *************************************************************************/ diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index df213c37b4fe..e5bed4237ff4 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -2112,7 +2112,7 @@ mt7530_gpio_get(struct gpio_chip *gc, unsigned int offset) return !!(mt7530_read(priv, MT7530_LED_GPIO_DATA) & bit); } -static void +static int mt7530_gpio_set(struct gpio_chip *gc, unsigned int offset, int value) { struct mt7530_priv *priv = gpiochip_get_data(gc); @@ -2122,6 +2122,8 @@ mt7530_gpio_set(struct gpio_chip *gc, unsigned int offset, int value) mt7530_set(priv, MT7530_LED_GPIO_DATA, bit); else mt7530_clear(priv, MT7530_LED_GPIO_DATA, bit); + + return 0; } static int @@ -2185,7 +2187,7 @@ mt7530_setup_gpio(struct mt7530_priv *priv) gc->direction_input = mt7530_gpio_direction_input; gc->direction_output = mt7530_gpio_direction_output; gc->get = mt7530_gpio_get; - gc->set = mt7530_gpio_set; + gc->set_rv = mt7530_gpio_set; gc->base = -1; gc->ngpio = 15; gc->can_sleep = true; diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index f18aa321053d..4f9687ab3b2b 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -2258,14 +2258,14 @@ static int vsc73xx_gpio_get(struct gpio_chip *chip, unsigned int offset) return !!(val & BIT(offset)); } -static void vsc73xx_gpio_set(struct gpio_chip *chip, unsigned int offset, - int val) +static int vsc73xx_gpio_set(struct gpio_chip *chip, unsigned int offset, + int val) { struct vsc73xx *vsc = gpiochip_get_data(chip); u32 tmp = val ? BIT(offset) : 0; - vsc73xx_update_bits(vsc, VSC73XX_BLOCK_SYSTEM, 0, - VSC73XX_GPIO, BIT(offset), tmp); + return vsc73xx_update_bits(vsc, VSC73XX_BLOCK_SYSTEM, 0, + VSC73XX_GPIO, BIT(offset), tmp); } static int vsc73xx_gpio_direction_output(struct gpio_chip *chip, @@ -2317,7 +2317,7 @@ static int vsc73xx_gpio_probe(struct vsc73xx *vsc) vsc->gc.parent = vsc->dev; vsc->gc.base = -1; vsc->gc.get = vsc73xx_gpio_get; - vsc->gc.set = vsc73xx_gpio_set; + vsc->gc.set_rv = vsc73xx_gpio_set; vsc->gc.direction_input = vsc73xx_gpio_direction_input; vsc->gc.direction_output = vsc73xx_gpio_direction_output; vsc->gc.get_direction = vsc73xx_gpio_get_direction; diff --git a/drivers/net/ethernet/amazon/Kconfig b/drivers/net/ethernet/amazon/Kconfig index c37fa393b99e..95dcc3969f0c 100644 --- a/drivers/net/ethernet/amazon/Kconfig +++ b/drivers/net/ethernet/amazon/Kconfig @@ -19,7 +19,9 @@ if NET_VENDOR_AMAZON config ENA_ETHERNET tristate "Elastic Network Adapter (ENA) support" depends on PCI_MSI && !CPU_BIG_ENDIAN + depends on PTP_1588_CLOCK_OPTIONAL select DIMLIB + select NET_DEVLINK help This driver supports Elastic Network Adapter (ENA)" diff --git a/drivers/net/ethernet/amazon/ena/Makefile b/drivers/net/ethernet/amazon/ena/Makefile index 6ab615365172..6d8036bc1823 100644 --- a/drivers/net/ethernet/amazon/ena/Makefile +++ b/drivers/net/ethernet/amazon/ena/Makefile @@ -5,4 +5,4 @@ obj-$(CONFIG_ENA_ETHERNET) += ena.o -ena-y := ena_netdev.o ena_com.o ena_eth_com.o ena_ethtool.o ena_xdp.o +ena-y := ena_netdev.o ena_com.o ena_eth_com.o ena_ethtool.o ena_xdp.o ena_phc.o ena_devlink.o ena_debugfs.o diff --git a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h index 9d9fa6559354..562869a0fdba 100644 --- a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h +++ b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h @@ -60,6 +60,7 @@ enum ena_admin_aq_feature_id { ENA_ADMIN_AENQ_CONFIG = 26, ENA_ADMIN_LINK_CONFIG = 27, ENA_ADMIN_HOST_ATTR_CONFIG = 28, + ENA_ADMIN_PHC_CONFIG = 29, ENA_ADMIN_FEATURES_OPCODE_NUM = 32, }; @@ -127,6 +128,14 @@ enum ena_admin_get_stats_scope { ENA_ADMIN_ETH_TRAFFIC = 1, }; +enum ena_admin_phc_type { + ENA_ADMIN_PHC_TYPE_READLESS = 0, +}; + +enum ena_admin_phc_error_flags { + ENA_ADMIN_PHC_ERROR_FLAG_TIMESTAMP = BIT(0), +}; + /* ENA SRD configuration for ENI */ enum ena_admin_ena_srd_flags { /* Feature enabled */ @@ -943,7 +952,9 @@ struct ena_admin_host_info { * 4 : rss_configurable_function_key * 5 : reserved * 6 : rx_page_reuse - * 31:7 : reserved + * 7 : reserved + * 8 : phc + * 31:9 : reserved */ u32 driver_supported_features; }; @@ -1023,6 +1034,43 @@ struct ena_admin_queue_ext_feature_desc { }; }; +struct ena_admin_feature_phc_desc { + /* PHC type as defined in enum ena_admin_get_phc_type, + * used only for GET command. + */ + u8 type; + + /* Reserved - MBZ */ + u8 reserved1[3]; + + /* PHC doorbell address as an offset to PCIe MMIO REG BAR, + * used only for GET command. + */ + u32 doorbell_offset; + + /* Max time for valid PHC retrieval, passing this threshold will + * fail the get-time request and block PHC requests for + * block_timeout_usec, used only for GET command. + */ + u32 expire_timeout_usec; + + /* PHC requests block period, blocking starts if PHC request expired + * in order to prevent floods on busy device, + * used only for GET command. + */ + u32 block_timeout_usec; + + /* Shared PHC physical address (ena_admin_phc_resp), + * used only for SET command. + */ + struct ena_common_mem_addr output_address; + + /* Shared PHC Size (ena_admin_phc_resp), + * used only for SET command. + */ + u32 output_length; +}; + struct ena_admin_get_feat_resp { struct ena_admin_acq_common_desc acq_common_desc; @@ -1052,6 +1100,8 @@ struct ena_admin_get_feat_resp { struct ena_admin_feature_intr_moder_desc intr_moderation; struct ena_admin_ena_hw_hints hw_hints; + + struct ena_admin_feature_phc_desc phc; } u; }; @@ -1085,6 +1135,9 @@ struct ena_admin_set_feat_cmd { /* LLQ configuration */ struct ena_admin_feature_llq_desc llq; + + /* PHC configuration */ + struct ena_admin_feature_phc_desc phc; } u; }; @@ -1162,6 +1215,23 @@ struct ena_admin_ena_mmio_req_read_less_resp { u32 reg_val; }; +struct ena_admin_phc_resp { + /* Request Id, received from DB register */ + u16 req_id; + + u8 reserved1[6]; + + /* PHC timestamp (nsec) */ + u64 timestamp; + + u8 reserved2[12]; + + /* Bit field of enum ena_admin_phc_error_flags */ + u32 error_flags; + + u8 reserved3[32]; +}; + /* aq_common_desc */ #define ENA_ADMIN_AQ_COMMON_DESC_COMMAND_ID_MASK GENMASK(11, 0) #define ENA_ADMIN_AQ_COMMON_DESC_PHASE_MASK BIT(0) @@ -1260,6 +1330,8 @@ struct ena_admin_ena_mmio_req_read_less_resp { #define ENA_ADMIN_HOST_INFO_RSS_CONFIGURABLE_FUNCTION_KEY_MASK BIT(4) #define ENA_ADMIN_HOST_INFO_RX_PAGE_REUSE_SHIFT 6 #define ENA_ADMIN_HOST_INFO_RX_PAGE_REUSE_MASK BIT(6) +#define ENA_ADMIN_HOST_INFO_PHC_SHIFT 8 +#define ENA_ADMIN_HOST_INFO_PHC_MASK BIT(8) /* aenq_common_desc */ #define ENA_ADMIN_AENQ_COMMON_DESC_PHASE_MASK BIT(0) diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 66445617fbfb..e67b592e5697 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -41,6 +41,12 @@ #define ENA_MAX_ADMIN_POLL_US 5000 +/* PHC definitions */ +#define ENA_PHC_DEFAULT_EXPIRE_TIMEOUT_USEC 10 +#define ENA_PHC_DEFAULT_BLOCK_TIMEOUT_USEC 1000 +#define ENA_PHC_REQ_ID_OFFSET 0xDEAD +#define ENA_PHC_ERROR_FLAGS (ENA_ADMIN_PHC_ERROR_FLAG_TIMESTAMP) + /*****************************************************************************/ /*****************************************************************************/ /*****************************************************************************/ @@ -1641,6 +1647,267 @@ void ena_com_set_admin_polling_mode(struct ena_com_dev *ena_dev, bool polling) ena_dev->admin_queue.polling = polling; } +bool ena_com_phc_supported(struct ena_com_dev *ena_dev) +{ + return ena_com_check_supported_feature_id(ena_dev, ENA_ADMIN_PHC_CONFIG); +} + +int ena_com_phc_init(struct ena_com_dev *ena_dev) +{ + struct ena_com_phc_info *phc = &ena_dev->phc; + + memset(phc, 0x0, sizeof(*phc)); + + /* Allocate shared mem used PHC timestamp retrieved from device */ + phc->virt_addr = dma_alloc_coherent(ena_dev->dmadev, + sizeof(*phc->virt_addr), + &phc->phys_addr, + GFP_KERNEL); + if (unlikely(!phc->virt_addr)) + return -ENOMEM; + + spin_lock_init(&phc->lock); + + phc->virt_addr->req_id = 0; + phc->virt_addr->timestamp = 0; + + return 0; +} + +int ena_com_phc_config(struct ena_com_dev *ena_dev) +{ + struct ena_com_phc_info *phc = &ena_dev->phc; + struct ena_admin_get_feat_resp get_feat_resp; + struct ena_admin_set_feat_resp set_feat_resp; + struct ena_admin_set_feat_cmd set_feat_cmd; + int ret = 0; + + /* Get device PHC default configuration */ + ret = ena_com_get_feature(ena_dev, + &get_feat_resp, + ENA_ADMIN_PHC_CONFIG, + 0); + if (unlikely(ret)) { + netdev_err(ena_dev->net_device, + "Failed to get PHC feature configuration, error: %d\n", + ret); + return ret; + } + + /* Supporting only readless PHC retrieval */ + if (get_feat_resp.u.phc.type != ENA_ADMIN_PHC_TYPE_READLESS) { + netdev_err(ena_dev->net_device, + "Unsupported PHC type, error: %d\n", + -EOPNOTSUPP); + return -EOPNOTSUPP; + } + + /* Update PHC doorbell offset according to device value, + * used to write req_id to PHC bar + */ + phc->doorbell_offset = get_feat_resp.u.phc.doorbell_offset; + + /* Update PHC expire timeout according to device + * or default driver value + */ + phc->expire_timeout_usec = (get_feat_resp.u.phc.expire_timeout_usec) ? + get_feat_resp.u.phc.expire_timeout_usec : + ENA_PHC_DEFAULT_EXPIRE_TIMEOUT_USEC; + + /* Update PHC block timeout according to device + * or default driver value + */ + phc->block_timeout_usec = (get_feat_resp.u.phc.block_timeout_usec) ? + get_feat_resp.u.phc.block_timeout_usec : + ENA_PHC_DEFAULT_BLOCK_TIMEOUT_USEC; + + /* Sanity check - expire timeout must not exceed block timeout */ + if (phc->expire_timeout_usec > phc->block_timeout_usec) + phc->expire_timeout_usec = phc->block_timeout_usec; + + /* Prepare PHC feature command */ + memset(&set_feat_cmd, 0x0, sizeof(set_feat_cmd)); + set_feat_cmd.aq_common_descriptor.opcode = ENA_ADMIN_SET_FEATURE; + set_feat_cmd.feat_common.feature_id = ENA_ADMIN_PHC_CONFIG; + set_feat_cmd.u.phc.output_length = sizeof(*phc->virt_addr); + ret = ena_com_mem_addr_set(ena_dev, + &set_feat_cmd.u.phc.output_address, + phc->phys_addr); + if (unlikely(ret)) { + netdev_err(ena_dev->net_device, + "Failed setting PHC output address, error: %d\n", + ret); + return ret; + } + + /* Send PHC feature command to the device */ + ret = ena_com_execute_admin_command(&ena_dev->admin_queue, + (struct ena_admin_aq_entry *)&set_feat_cmd, + sizeof(set_feat_cmd), + (struct ena_admin_acq_entry *)&set_feat_resp, + sizeof(set_feat_resp)); + + if (unlikely(ret)) { + netdev_err(ena_dev->net_device, + "Failed to enable PHC, error: %d\n", + ret); + return ret; + } + + phc->active = true; + netdev_dbg(ena_dev->net_device, "PHC is active in the device\n"); + + return ret; +} + +void ena_com_phc_destroy(struct ena_com_dev *ena_dev) +{ + struct ena_com_phc_info *phc = &ena_dev->phc; + unsigned long flags = 0; + + /* In case PHC is not supported by the device, silently exiting */ + if (!phc->virt_addr) + return; + + spin_lock_irqsave(&phc->lock, flags); + phc->active = false; + spin_unlock_irqrestore(&phc->lock, flags); + + dma_free_coherent(ena_dev->dmadev, + sizeof(*phc->virt_addr), + phc->virt_addr, + phc->phys_addr); + phc->virt_addr = NULL; +} + +int ena_com_phc_get_timestamp(struct ena_com_dev *ena_dev, u64 *timestamp) +{ + volatile struct ena_admin_phc_resp *resp = ena_dev->phc.virt_addr; + const ktime_t zero_system_time = ktime_set(0, 0); + struct ena_com_phc_info *phc = &ena_dev->phc; + ktime_t expire_time; + ktime_t block_time; + unsigned long flags = 0; + int ret = 0; + + if (!phc->active) { + netdev_err(ena_dev->net_device, "PHC feature is not active in the device\n"); + return -EOPNOTSUPP; + } + + spin_lock_irqsave(&phc->lock, flags); + + /* Check if PHC is in blocked state */ + if (unlikely(ktime_compare(phc->system_time, zero_system_time))) { + /* Check if blocking time expired */ + block_time = ktime_add_us(phc->system_time, phc->block_timeout_usec); + if (!ktime_after(ktime_get(), block_time)) { + /* PHC is still in blocked state, skip PHC request */ + phc->stats.phc_skp++; + ret = -EBUSY; + goto skip; + } + + /* PHC is in active state, update statistics according + * to req_id and error_flags + */ + if (READ_ONCE(resp->req_id) != phc->req_id) { + /* Device didn't update req_id during blocking time, + * this indicates on a device error + */ + netdev_err(ena_dev->net_device, + "PHC get time request 0x%x failed (device error)\n", + phc->req_id); + phc->stats.phc_err_dv++; + } else if (resp->error_flags & ENA_PHC_ERROR_FLAGS) { + /* Device updated req_id during blocking time but got + * a PHC error, this occurs if device: + * - exceeded the get time request limit + * - received an invalid timestamp + */ + netdev_err(ena_dev->net_device, + "PHC get time request 0x%x failed (error 0x%x)\n", + phc->req_id, + resp->error_flags); + phc->stats.phc_err_ts += !!(resp->error_flags & + ENA_ADMIN_PHC_ERROR_FLAG_TIMESTAMP); + } else { + /* Device updated req_id during blocking time + * with valid timestamp + */ + phc->stats.phc_exp++; + } + } + + /* Setting relative timeouts */ + phc->system_time = ktime_get(); + block_time = ktime_add_us(phc->system_time, phc->block_timeout_usec); + expire_time = ktime_add_us(phc->system_time, phc->expire_timeout_usec); + + /* We expect the device to return this req_id once + * the new PHC timestamp is updated + */ + phc->req_id++; + + /* Initialize PHC shared memory with different req_id value + * to be able to identify once the device changes it to req_id + */ + resp->req_id = phc->req_id + ENA_PHC_REQ_ID_OFFSET; + + /* Writing req_id to PHC bar */ + writel(phc->req_id, ena_dev->reg_bar + phc->doorbell_offset); + + /* Stalling until the device updates req_id */ + while (1) { + if (unlikely(ktime_after(ktime_get(), expire_time))) { + /* Gave up waiting for updated req_id, PHC enters into + * blocked state until passing blocking time, + * during this time any get PHC timestamp will fail with + * device busy error + */ + ret = -EBUSY; + break; + } + + /* Check if req_id was updated by the device */ + if (READ_ONCE(resp->req_id) != phc->req_id) { + /* req_id was not updated by the device yet, + * check again on next loop + */ + continue; + } + + /* req_id was updated by the device which indicates that + * PHC timestamp and error_flags are updated too, + * checking errors before retrieving timestamp + */ + if (unlikely(resp->error_flags & ENA_PHC_ERROR_FLAGS)) { + /* Retrieved invalid PHC timestamp, PHC enters into + * blocked state until passing blocking time, + * during this time any get PHC timestamp requests + * will fail with device busy error + */ + ret = -EBUSY; + break; + } + + /* PHC timestamp value is returned to the caller */ + *timestamp = resp->timestamp; + + /* Update statistic on valid PHC timestamp retrieval */ + phc->stats.phc_cnt++; + + /* This indicates PHC state is active */ + phc->system_time = zero_system_time; + break; + } + +skip: + spin_unlock_irqrestore(&phc->lock, flags); + + return ret; +} + int ena_com_mmio_reg_read_request_init(struct ena_com_dev *ena_dev) { struct ena_com_mmio_read *mmio_read = &ena_dev->mmio_read; diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h index 9414e93d107b..64df2c48c9a6 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.h +++ b/drivers/net/ethernet/amazon/ena/ena_com.h @@ -210,6 +210,14 @@ struct ena_com_stats_admin { u64 no_completion; }; +struct ena_com_stats_phc { + u64 phc_cnt; + u64 phc_exp; + u64 phc_skp; + u64 phc_err_dv; + u64 phc_err_ts; +}; + struct ena_com_admin_queue { void *q_dmadev; struct ena_com_dev *ena_dev; @@ -258,6 +266,47 @@ struct ena_com_mmio_read { spinlock_t lock; }; +/* PTP hardware clock (PHC) MMIO read data info */ +struct ena_com_phc_info { + /* Internal PHC statistics */ + struct ena_com_stats_phc stats; + + /* PHC shared memory - virtual address */ + struct ena_admin_phc_resp *virt_addr; + + /* System time of last PHC request */ + ktime_t system_time; + + /* Spin lock to ensure a single outstanding PHC read */ + spinlock_t lock; + + /* PHC doorbell address as an offset to PCIe MMIO REG BAR */ + u32 doorbell_offset; + + /* Shared memory read expire timeout (usec) + * Max time for valid PHC retrieval, passing this threshold will fail + * the get time request and block new PHC requests for block_timeout_usec + * in order to prevent floods on busy device + */ + u32 expire_timeout_usec; + + /* Shared memory read abort timeout (usec) + * PHC requests block period, blocking starts once PHC request expired + * in order to prevent floods on busy device, + * any PHC requests during block period will be skipped + */ + u32 block_timeout_usec; + + /* PHC shared memory - physical address */ + dma_addr_t phys_addr; + + /* Request id sent to the device */ + u16 req_id; + + /* True if PHC is active in the device */ + bool active; +}; + struct ena_rss { /* Indirect table */ u16 *host_rss_ind_tbl; @@ -317,6 +366,7 @@ struct ena_com_dev { u32 ena_min_poll_delay_us; struct ena_com_mmio_read mmio_read; + struct ena_com_phc_info phc; struct ena_rss rss; u32 supported_features; @@ -382,6 +432,40 @@ struct ena_aenq_handlers { */ int ena_com_mmio_reg_read_request_init(struct ena_com_dev *ena_dev); +/* ena_com_phc_init - Allocate and initialize PHC feature + * @ena_dev: ENA communication layer struct + * @note: This method assumes PHC is supported by the device + * @return - 0 on success, negative value on failure + */ +int ena_com_phc_init(struct ena_com_dev *ena_dev); + +/* ena_com_phc_supported - Return if PHC feature is supported by the device + * @ena_dev: ENA communication layer struct + * @note: This method must be called after getting supported features + * @return - supported or not + */ +bool ena_com_phc_supported(struct ena_com_dev *ena_dev); + +/* ena_com_phc_config - Configure PHC feature + * @ena_dev: ENA communication layer struct + * Configure PHC feature in driver and device + * @note: This method assumes PHC is supported by the device + * @return - 0 on success, negative value on failure + */ +int ena_com_phc_config(struct ena_com_dev *ena_dev); + +/* ena_com_phc_destroy - Destroy PHC feature + * @ena_dev: ENA communication layer struct + */ +void ena_com_phc_destroy(struct ena_com_dev *ena_dev); + +/* ena_com_phc_get_timestamp - Retrieve PHC timestamp + * @ena_dev: ENA communication layer struct + * @timestamp: Retrieved PHC timestamp + * @return - 0 on success, negative value on failure + */ +int ena_com_phc_get_timestamp(struct ena_com_dev *ena_dev, u64 *timestamp); + /* ena_com_set_mmio_read_mode - Enable/disable the indirect mmio reg read mechanism * @ena_dev: ENA communication layer struct * @readless_supported: readless mode (enable/disable) diff --git a/drivers/net/ethernet/amazon/ena/ena_debugfs.c b/drivers/net/ethernet/amazon/ena/ena_debugfs.c new file mode 100644 index 000000000000..46ed80986724 --- /dev/null +++ b/drivers/net/ethernet/amazon/ena/ena_debugfs.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) Amazon.com, Inc. or its affiliates. + * All rights reserved. + */ + +#ifdef CONFIG_DEBUG_FS + +#include <linux/seq_file.h> +#include <linux/pci.h> +#include "ena_debugfs.h" +#include "ena_phc.h" + +static int phc_stats_show(struct seq_file *file, void *priv) +{ + struct ena_adapter *adapter = file->private; + + if (!ena_phc_is_active(adapter)) + return 0; + + seq_printf(file, + "phc_cnt: %llu\n", + adapter->ena_dev->phc.stats.phc_cnt); + seq_printf(file, + "phc_exp: %llu\n", + adapter->ena_dev->phc.stats.phc_exp); + seq_printf(file, + "phc_skp: %llu\n", + adapter->ena_dev->phc.stats.phc_skp); + seq_printf(file, + "phc_err_dv: %llu\n", + adapter->ena_dev->phc.stats.phc_err_dv); + seq_printf(file, + "phc_err_ts: %llu\n", + adapter->ena_dev->phc.stats.phc_err_ts); + + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(phc_stats); + +void ena_debugfs_init(struct net_device *dev) +{ + struct ena_adapter *adapter = netdev_priv(dev); + + adapter->debugfs_base = + debugfs_create_dir(dev_name(&adapter->pdev->dev), NULL); + + debugfs_create_file("phc_stats", + 0400, + adapter->debugfs_base, + adapter, + &phc_stats_fops); +} + +void ena_debugfs_terminate(struct net_device *dev) +{ + struct ena_adapter *adapter = netdev_priv(dev); + + debugfs_remove_recursive(adapter->debugfs_base); +} + +#endif /* CONFIG_DEBUG_FS */ diff --git a/drivers/net/ethernet/amazon/ena/ena_debugfs.h b/drivers/net/ethernet/amazon/ena/ena_debugfs.h new file mode 100644 index 000000000000..dc61dd998867 --- /dev/null +++ b/drivers/net/ethernet/amazon/ena/ena_debugfs.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) Amazon.com, Inc. or its affiliates. + * All rights reserved. + */ + +#ifndef __ENA_DEBUGFS_H__ +#define __ENA_DEBUGFS_H__ + +#include <linux/debugfs.h> +#include <linux/netdevice.h> +#include "ena_netdev.h" + +#ifdef CONFIG_DEBUG_FS + +void ena_debugfs_init(struct net_device *dev); + +void ena_debugfs_terminate(struct net_device *dev); + +#else /* CONFIG_DEBUG_FS */ + +static inline void ena_debugfs_init(struct net_device *dev) {} + +static inline void ena_debugfs_terminate(struct net_device *dev) {} + +#endif /* CONFIG_DEBUG_FS */ + +#endif /* __ENA_DEBUGFS_H__ */ diff --git a/drivers/net/ethernet/amazon/ena/ena_devlink.c b/drivers/net/ethernet/amazon/ena/ena_devlink.c new file mode 100644 index 000000000000..ac81c24016dd --- /dev/null +++ b/drivers/net/ethernet/amazon/ena/ena_devlink.c @@ -0,0 +1,210 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) Amazon.com, Inc. or its affiliates. + * All rights reserved. + */ + +#include "linux/pci.h" +#include "ena_devlink.h" +#include "ena_phc.h" + +static int ena_devlink_enable_phc_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct ena_adapter *adapter = ENA_DEVLINK_PRIV(devlink); + + if (!val.vbool) + return 0; + + if (!ena_com_phc_supported(adapter->ena_dev)) { + NL_SET_ERR_MSG_MOD(extack, "Device doesn't support PHC"); + return -EOPNOTSUPP; + } + + return 0; +} + +static const struct devlink_param ena_devlink_params[] = { + DEVLINK_PARAM_GENERIC(ENABLE_PHC, + BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, + NULL, + ena_devlink_enable_phc_validate), +}; + +void ena_devlink_params_get(struct devlink *devlink) +{ + struct ena_adapter *adapter = ENA_DEVLINK_PRIV(devlink); + union devlink_param_value val; + int err; + + err = devl_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_PHC, + &val); + if (err) { + netdev_err(adapter->netdev, "Failed to query PHC param\n"); + return; + } + + ena_phc_enable(adapter, val.vbool); +} + +void ena_devlink_disable_phc_param(struct devlink *devlink) +{ + union devlink_param_value value; + + value.vbool = false; + devl_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_PHC, + value); +} + +static void ena_devlink_port_register(struct devlink *devlink) +{ + struct ena_adapter *adapter = ENA_DEVLINK_PRIV(devlink); + struct devlink_port_attrs attrs = {}; + + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + devlink_port_attrs_set(&adapter->devlink_port, &attrs); + devl_port_register(devlink, &adapter->devlink_port, 0); +} + +static void ena_devlink_port_unregister(struct devlink *devlink) +{ + struct ena_adapter *adapter = ENA_DEVLINK_PRIV(devlink); + + devl_port_unregister(&adapter->devlink_port); +} + +static int ena_devlink_reload_down(struct devlink *devlink, + bool netns_change, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + struct netlink_ext_ack *extack) +{ + struct ena_adapter *adapter = ENA_DEVLINK_PRIV(devlink); + + if (netns_change) { + NL_SET_ERR_MSG_MOD(extack, + "Namespace change is not supported"); + return -EOPNOTSUPP; + } + + ena_devlink_port_unregister(devlink); + + rtnl_lock(); + ena_destroy_device(adapter, false); + rtnl_unlock(); + + return 0; +} + +static int ena_devlink_reload_up(struct devlink *devlink, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + u32 *actions_performed, + struct netlink_ext_ack *extack) +{ + struct ena_adapter *adapter = ENA_DEVLINK_PRIV(devlink); + int err = 0; + + rtnl_lock(); + /* Check that no other routine initialized the device (e.g. + * ena_fw_reset_device()). Also we're under devlink_mutex here, + * so devlink isn't freed under our feet. + */ + if (!test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags)) + err = ena_restore_device(adapter); + + rtnl_unlock(); + + ena_devlink_port_register(devlink); + + if (!err) + *actions_performed = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT); + + return err; +} + +static const struct devlink_ops ena_devlink_ops = { + .reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT), + .reload_down = ena_devlink_reload_down, + .reload_up = ena_devlink_reload_up, +}; + +static int ena_devlink_configure_params(struct devlink *devlink) +{ + struct ena_adapter *adapter = ENA_DEVLINK_PRIV(devlink); + union devlink_param_value value; + int rc; + + rc = devlink_params_register(devlink, ena_devlink_params, + ARRAY_SIZE(ena_devlink_params)); + if (rc) { + netdev_err(adapter->netdev, "Failed to register devlink params\n"); + return rc; + } + + value.vbool = ena_phc_is_enabled(adapter); + devl_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_PHC, + value); + + return 0; +} + +struct devlink *ena_devlink_alloc(struct ena_adapter *adapter) +{ + struct device *dev = &adapter->pdev->dev; + struct devlink *devlink; + + devlink = devlink_alloc(&ena_devlink_ops, + sizeof(struct ena_adapter *), + dev); + if (!devlink) { + netdev_err(adapter->netdev, + "Failed to allocate devlink struct\n"); + return NULL; + } + + ENA_DEVLINK_PRIV(devlink) = adapter; + adapter->devlink = devlink; + + if (ena_devlink_configure_params(devlink)) + goto free_devlink; + + return devlink; + +free_devlink: + devlink_free(devlink); + return NULL; +} + +static void ena_devlink_configure_params_clean(struct devlink *devlink) +{ + devlink_params_unregister(devlink, ena_devlink_params, + ARRAY_SIZE(ena_devlink_params)); +} + +void ena_devlink_free(struct devlink *devlink) +{ + ena_devlink_configure_params_clean(devlink); + + devlink_free(devlink); +} + +void ena_devlink_register(struct devlink *devlink, struct device *dev) +{ + devl_lock(devlink); + ena_devlink_port_register(devlink); + devl_register(devlink); + devl_unlock(devlink); +} + +void ena_devlink_unregister(struct devlink *devlink) +{ + devl_lock(devlink); + ena_devlink_port_unregister(devlink); + devl_unregister(devlink); + devl_unlock(devlink); +} diff --git a/drivers/net/ethernet/amazon/ena/ena_devlink.h b/drivers/net/ethernet/amazon/ena/ena_devlink.h new file mode 100644 index 000000000000..7a19ce4830d9 --- /dev/null +++ b/drivers/net/ethernet/amazon/ena/ena_devlink.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) Amazon.com, Inc. or its affiliates. + * All rights reserved. + */ +#ifndef DEVLINK_H +#define DEVLINK_H + +#include "ena_netdev.h" +#include <net/devlink.h> + +#define ENA_DEVLINK_PRIV(devlink) \ + (*(struct ena_adapter **)devlink_priv(devlink)) + +struct devlink *ena_devlink_alloc(struct ena_adapter *adapter); +void ena_devlink_free(struct devlink *devlink); +void ena_devlink_register(struct devlink *devlink, struct device *dev); +void ena_devlink_unregister(struct devlink *devlink); +void ena_devlink_params_get(struct devlink *devlink); +void ena_devlink_disable_phc_param(struct devlink *devlink); + +#endif /* DEVLINK_H */ diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index a3c934c3de71..a81d3a7a3bb9 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -5,9 +5,11 @@ #include <linux/ethtool.h> #include <linux/pci.h> +#include <linux/net_tstamp.h> #include "ena_netdev.h" #include "ena_xdp.h" +#include "ena_phc.h" struct ena_stats { char name[ETH_GSTRING_LEN]; @@ -298,6 +300,18 @@ static void ena_get_ethtool_stats(struct net_device *netdev, ena_get_stats(adapter, data, true); } +static int ena_get_ts_info(struct net_device *netdev, + struct kernel_ethtool_ts_info *info) +{ + struct ena_adapter *adapter = netdev_priv(netdev); + + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE; + + info->phc_index = ena_phc_get_index(adapter); + + return 0; +} + static int ena_get_sw_stats_count(struct ena_adapter *adapter) { return adapter->num_io_queues * (ENA_STATS_ARRAY_TX + ENA_STATS_ARRAY_RX) @@ -721,9 +735,11 @@ static u16 ena_flow_data_to_flow_hash(u32 hash_fields) return data; } -static int ena_get_rss_hash(struct ena_com_dev *ena_dev, - struct ethtool_rxnfc *cmd) +static int ena_get_rxfh_fields(struct net_device *netdev, + struct ethtool_rxfh_fields *cmd) { + struct ena_adapter *adapter = netdev_priv(netdev); + struct ena_com_dev *ena_dev = adapter->ena_dev; enum ena_admin_flow_hash_proto proto; u16 hash_fields; int rc; @@ -772,9 +788,12 @@ static int ena_get_rss_hash(struct ena_com_dev *ena_dev, return 0; } -static int ena_set_rss_hash(struct ena_com_dev *ena_dev, - struct ethtool_rxnfc *cmd) +static int ena_set_rxfh_fields(struct net_device *netdev, + const struct ethtool_rxfh_fields *cmd, + struct netlink_ext_ack *extack) { + struct ena_adapter *adapter = netdev_priv(netdev); + struct ena_com_dev *ena_dev = adapter->ena_dev; enum ena_admin_flow_hash_proto proto; u16 hash_fields; @@ -816,26 +835,6 @@ static int ena_set_rss_hash(struct ena_com_dev *ena_dev, return ena_com_fill_hash_ctrl(ena_dev, proto, hash_fields); } -static int ena_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *info) -{ - struct ena_adapter *adapter = netdev_priv(netdev); - int rc = 0; - - switch (info->cmd) { - case ETHTOOL_SRXFH: - rc = ena_set_rss_hash(adapter->ena_dev, info); - break; - case ETHTOOL_SRXCLSRLDEL: - case ETHTOOL_SRXCLSRLINS: - default: - netif_err(adapter, drv, netdev, - "Command parameter %d is not supported\n", info->cmd); - rc = -EOPNOTSUPP; - } - - return rc; -} - static int ena_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *info, u32 *rules) { @@ -847,9 +846,6 @@ static int ena_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *info, info->data = adapter->num_io_queues; rc = 0; break; - case ETHTOOL_GRXFH: - rc = ena_get_rss_hash(adapter->ena_dev, info); - break; case ETHTOOL_GRXCLSRLCNT: case ETHTOOL_GRXCLSRULE: case ETHTOOL_GRXCLSRLALL: @@ -1098,16 +1094,17 @@ static const struct ethtool_ops ena_ethtool_ops = { .get_strings = ena_get_ethtool_strings, .get_ethtool_stats = ena_get_ethtool_stats, .get_rxnfc = ena_get_rxnfc, - .set_rxnfc = ena_set_rxnfc, .get_rxfh_indir_size = ena_get_rxfh_indir_size, .get_rxfh_key_size = ena_get_rxfh_key_size, .get_rxfh = ena_get_rxfh, .set_rxfh = ena_set_rxfh, + .get_rxfh_fields = ena_get_rxfh_fields, + .set_rxfh_fields = ena_set_rxfh_fields, .get_channels = ena_get_channels, .set_channels = ena_set_channels, .get_tunable = ena_get_tunable, .set_tunable = ena_set_tunable, - .get_ts_info = ethtool_op_get_ts_info, + .get_ts_info = ena_get_ts_info, }; void ena_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 86fd08f375df..92d149d4f091 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -19,6 +19,12 @@ #include "ena_pci_id_tbl.h" #include "ena_xdp.h" +#include "ena_phc.h" + +#include "ena_devlink.h" + +#include "ena_debugfs.h" + MODULE_AUTHOR("Amazon.com, Inc. or its affiliates"); MODULE_DESCRIPTION(DEVICE_NAME); MODULE_LICENSE("GPL"); @@ -39,8 +45,6 @@ MODULE_DEVICE_TABLE(pci, ena_pci_tbl); static int ena_rss_init_default(struct ena_adapter *adapter); static void check_for_admin_com_state(struct ena_adapter *adapter); -static int ena_destroy_device(struct ena_adapter *adapter, bool graceful); -static int ena_restore_device(struct ena_adapter *adapter); static void ena_tx_timeout(struct net_device *dev, unsigned int txqueue) { @@ -2743,7 +2747,8 @@ static void ena_config_host_info(struct ena_com_dev *ena_dev, struct pci_dev *pd ENA_ADMIN_HOST_INFO_INTERRUPT_MODERATION_MASK | ENA_ADMIN_HOST_INFO_RX_BUF_MIRRORING_MASK | ENA_ADMIN_HOST_INFO_RSS_CONFIGURABLE_FUNCTION_KEY_MASK | - ENA_ADMIN_HOST_INFO_RX_PAGE_REUSE_MASK; + ENA_ADMIN_HOST_INFO_RX_PAGE_REUSE_MASK | + ENA_ADMIN_HOST_INFO_PHC_MASK; rc = ena_com_set_host_attributes(ena_dev); if (rc) { @@ -3135,6 +3140,8 @@ static int ena_device_init(struct ena_adapter *adapter, struct pci_dev *pdev, goto err_mmio_read_less; } + ena_devlink_params_get(adapter->devlink); + /* ENA admin level init */ rc = ena_com_admin_init(ena_dev, &aenq_handlers); if (rc) { @@ -3188,6 +3195,10 @@ static int ena_device_init(struct ena_adapter *adapter, struct pci_dev *pdev, if (unlikely(rc)) goto err_admin_init; + rc = ena_phc_init(adapter); + if (unlikely(rc && (rc != -EOPNOTSUPP))) + netdev_err(netdev, "Failed initializing PHC, error: %d\n", rc); + return 0; err_admin_init: @@ -3233,7 +3244,7 @@ err_disable_msix: return rc; } -static int ena_destroy_device(struct ena_adapter *adapter, bool graceful) +int ena_destroy_device(struct ena_adapter *adapter, bool graceful) { struct net_device *netdev = adapter->netdev; struct ena_com_dev *ena_dev = adapter->ena_dev; @@ -3271,6 +3282,8 @@ static int ena_destroy_device(struct ena_adapter *adapter, bool graceful) ena_com_admin_destroy(ena_dev); + ena_phc_destroy(adapter); + ena_com_mmio_reg_read_request_destroy(ena_dev); /* return reset reason to default value */ @@ -3282,7 +3295,7 @@ static int ena_destroy_device(struct ena_adapter *adapter, bool graceful) return rc; } -static int ena_restore_device(struct ena_adapter *adapter) +int ena_restore_device(struct ena_adapter *adapter) { struct ena_com_dev_get_features_ctx get_feat_ctx; struct ena_com_dev *ena_dev = adapter->ena_dev; @@ -3344,6 +3357,7 @@ err_device_destroy: ena_com_wait_for_abort_completion(ena_dev); ena_com_admin_destroy(ena_dev); ena_com_dev_reset(ena_dev, ENA_REGS_RESET_DRIVER_INVALID_STATE); + ena_phc_destroy(adapter); ena_com_mmio_reg_read_request_destroy(ena_dev); err: clear_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags); @@ -3867,6 +3881,7 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct ena_adapter *adapter; struct net_device *netdev; static int adapters_found; + struct devlink *devlink; u32 max_num_io_queues; bool wd_state; int bars, rc; @@ -3932,10 +3947,16 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, adapter); + rc = ena_phc_alloc(adapter); + if (rc) { + netdev_err(netdev, "ena_phc_alloc failed\n"); + goto err_netdev_destroy; + } + rc = ena_com_allocate_customer_metrics_buffer(ena_dev); if (rc) { netdev_err(netdev, "ena_com_allocate_customer_metrics_buffer failed\n"); - goto err_netdev_destroy; + goto err_free_phc; } rc = ena_map_llq_mem_bar(pdev, ena_dev, bars); @@ -3944,12 +3965,20 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_metrics_destroy; } + /* Need to do this before ena_device_init */ + devlink = ena_devlink_alloc(adapter); + if (!devlink) { + netdev_err(netdev, "ena_devlink_alloc failed\n"); + rc = -ENOMEM; + goto err_metrics_destroy; + } + rc = ena_device_init(adapter, pdev, &get_feat_ctx, &wd_state); if (rc) { dev_err(&pdev->dev, "ENA device init failed\n"); if (rc == -ETIME) rc = -EPROBE_DEFER; - goto err_metrics_destroy; + goto ena_devlink_destroy; } /* Initial TX and RX interrupt delay. Assumes 1 usec granularity. @@ -4033,6 +4062,8 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_rss; } + ena_debugfs_init(netdev); + INIT_WORK(&adapter->reset_task, ena_fw_reset_device); adapter->last_keep_alive_jiffies = jiffies; @@ -4054,6 +4085,12 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapters_found++; + /* From this point, the devlink device is visible to users. + * Perform the registration last to ensure that all the resources + * are available and that the netdevice is registered. + */ + ena_devlink_register(devlink, &pdev->dev); + return 0; err_rss: @@ -4070,8 +4107,12 @@ err_worker_destroy: err_device_destroy: ena_com_delete_host_info(ena_dev); ena_com_admin_destroy(ena_dev); +ena_devlink_destroy: + ena_devlink_free(devlink); err_metrics_destroy: ena_com_delete_customer_metrics_buffer(ena_dev); +err_free_phc: + ena_phc_free(adapter); err_netdev_destroy: free_netdev(netdev); err_free_region: @@ -4102,6 +4143,8 @@ static void __ena_shutoff(struct pci_dev *pdev, bool shutdown) ena_dev = adapter->ena_dev; netdev = adapter->netdev; + ena_debugfs_terminate(netdev); + /* Make sure timer and reset routine won't be called after * freeing device resources. */ @@ -4112,6 +4155,11 @@ static void __ena_shutoff(struct pci_dev *pdev, bool shutdown) adapter->reset_reason = ENA_REGS_RESET_SHUTDOWN; ena_destroy_device(adapter, true); + ena_phc_free(adapter); + + ena_devlink_unregister(adapter->devlink); + ena_devlink_free(adapter->devlink); + if (shutdown) { netif_device_detach(netdev); dev_close(netdev); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index 6e12ae3b12e5..006f9a3acea6 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -16,6 +16,7 @@ #include <linux/skbuff.h> #include <net/xdp.h> #include <uapi/linux/bpf.h> +#include <net/devlink.h> #include "ena_com.h" #include "ena_eth_com.h" @@ -110,6 +111,8 @@ #define ENA_MMIO_DISABLE_REG_READ BIT(0) +struct ena_phc_info; + struct ena_irq { irq_handler_t handler; void *data; @@ -348,6 +351,8 @@ struct ena_adapter { char name[ENA_NAME_MAX_LEN]; + struct ena_phc_info *phc_info; + unsigned long flags; /* TX */ struct ena_ring tx_ring[ENA_MAX_NUM_IO_QUEUES] @@ -383,6 +388,13 @@ struct ena_adapter { struct bpf_prog *xdp_bpf_prog; u32 xdp_first_ring; u32 xdp_num_queues; + + struct devlink *devlink; + struct devlink_port devlink_port; +#ifdef CONFIG_DEBUG_FS + + struct dentry *debugfs_base; +#endif /* CONFIG_DEBUG_FS */ }; void ena_set_ethtool_ops(struct net_device *netdev); @@ -412,6 +424,8 @@ static inline void ena_reset_device(struct ena_adapter *adapter, set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); } +int ena_destroy_device(struct ena_adapter *adapter, bool graceful); +int ena_restore_device(struct ena_adapter *adapter); int handle_invalid_req_id(struct ena_ring *ring, u16 req_id, struct ena_tx_buffer *tx_info, bool is_xdp); diff --git a/drivers/net/ethernet/amazon/ena/ena_phc.c b/drivers/net/ethernet/amazon/ena/ena_phc.c new file mode 100644 index 000000000000..7867e893fd15 --- /dev/null +++ b/drivers/net/ethernet/amazon/ena/ena_phc.c @@ -0,0 +1,233 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* + * Copyright 2015-2022 Amazon.com, Inc. or its affiliates. All rights reserved. + */ + +#include <linux/pci.h> +#include "ena_netdev.h" +#include "ena_phc.h" +#include "ena_devlink.h" + +static int ena_phc_adjtime(struct ptp_clock_info *clock_info, s64 delta) +{ + return -EOPNOTSUPP; +} + +static int ena_phc_adjfine(struct ptp_clock_info *clock_info, long scaled_ppm) +{ + return -EOPNOTSUPP; +} + +static int ena_phc_feature_enable(struct ptp_clock_info *clock_info, + struct ptp_clock_request *rq, + int on) +{ + return -EOPNOTSUPP; +} + +static int ena_phc_gettimex64(struct ptp_clock_info *clock_info, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct ena_phc_info *phc_info = + container_of(clock_info, struct ena_phc_info, clock_info); + unsigned long flags; + u64 timestamp_nsec; + int rc; + + spin_lock_irqsave(&phc_info->lock, flags); + + ptp_read_system_prets(sts); + + rc = ena_com_phc_get_timestamp(phc_info->adapter->ena_dev, + ×tamp_nsec); + + ptp_read_system_postts(sts); + + spin_unlock_irqrestore(&phc_info->lock, flags); + + *ts = ns_to_timespec64(timestamp_nsec); + + return rc; +} + +static int ena_phc_settime64(struct ptp_clock_info *clock_info, + const struct timespec64 *ts) +{ + return -EOPNOTSUPP; +} + +static struct ptp_clock_info ena_ptp_clock_info = { + .owner = THIS_MODULE, + .n_alarm = 0, + .n_ext_ts = 0, + .n_per_out = 0, + .pps = 0, + .adjtime = ena_phc_adjtime, + .adjfine = ena_phc_adjfine, + .gettimex64 = ena_phc_gettimex64, + .settime64 = ena_phc_settime64, + .enable = ena_phc_feature_enable, +}; + +/* Enable/Disable PHC by the kernel, affects on the next init flow */ +void ena_phc_enable(struct ena_adapter *adapter, bool enable) +{ + struct ena_phc_info *phc_info = adapter->phc_info; + + if (!phc_info) { + netdev_err(adapter->netdev, "phc_info is not allocated\n"); + return; + } + + phc_info->enabled = enable; +} + +/* Check if PHC is enabled by the kernel */ +bool ena_phc_is_enabled(struct ena_adapter *adapter) +{ + struct ena_phc_info *phc_info = adapter->phc_info; + + return (phc_info && phc_info->enabled); +} + +/* PHC is activated if ptp clock is registered in the kernel */ +bool ena_phc_is_active(struct ena_adapter *adapter) +{ + struct ena_phc_info *phc_info = adapter->phc_info; + + return (phc_info && phc_info->clock); +} + +static int ena_phc_register(struct ena_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct ptp_clock_info *clock_info; + struct ena_phc_info *phc_info; + int rc = 0; + + phc_info = adapter->phc_info; + clock_info = &phc_info->clock_info; + + /* PHC may already be registered in case of a reset */ + if (ena_phc_is_active(adapter)) + return 0; + + phc_info->adapter = adapter; + + spin_lock_init(&phc_info->lock); + + /* Fill the ptp_clock_info struct and register PTP clock */ + *clock_info = ena_ptp_clock_info; + snprintf(clock_info->name, + sizeof(clock_info->name), + "ena-ptp-%02x", + PCI_SLOT(pdev->devfn)); + + phc_info->clock = ptp_clock_register(clock_info, &pdev->dev); + if (IS_ERR(phc_info->clock)) { + rc = PTR_ERR(phc_info->clock); + netdev_err(adapter->netdev, "Failed registering ptp clock, error: %d\n", + rc); + phc_info->clock = NULL; + } + + return rc; +} + +static void ena_phc_unregister(struct ena_adapter *adapter) +{ + struct ena_phc_info *phc_info = adapter->phc_info; + + /* During reset flow, PHC must stay registered + * to keep kernel's PHC index + */ + if (ena_phc_is_active(adapter) && + !test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags)) { + ptp_clock_unregister(phc_info->clock); + phc_info->clock = NULL; + } +} + +int ena_phc_alloc(struct ena_adapter *adapter) +{ + /* Allocate driver specific PHC info */ + adapter->phc_info = vzalloc(sizeof(*adapter->phc_info)); + if (unlikely(!adapter->phc_info)) { + netdev_err(adapter->netdev, "Failed to alloc phc_info\n"); + return -ENOMEM; + } + + return 0; +} + +void ena_phc_free(struct ena_adapter *adapter) +{ + if (adapter->phc_info) { + vfree(adapter->phc_info); + adapter->phc_info = NULL; + } +} + +int ena_phc_init(struct ena_adapter *adapter) +{ + struct ena_com_dev *ena_dev = adapter->ena_dev; + struct net_device *netdev = adapter->netdev; + int rc = -EOPNOTSUPP; + + /* Validate PHC feature is supported in the device */ + if (!ena_com_phc_supported(ena_dev)) { + netdev_dbg(netdev, "PHC feature is not supported by the device\n"); + goto err_ena_com_phc_init; + } + + /* Validate PHC feature is enabled by the kernel */ + if (!ena_phc_is_enabled(adapter)) { + netdev_dbg(netdev, "PHC feature is not enabled by the kernel\n"); + goto err_ena_com_phc_init; + } + + /* Initialize device specific PHC info */ + rc = ena_com_phc_init(ena_dev); + if (unlikely(rc)) { + netdev_err(netdev, "Failed to init phc, error: %d\n", rc); + goto err_ena_com_phc_init; + } + + /* Configure PHC feature in driver and device */ + rc = ena_com_phc_config(ena_dev); + if (unlikely(rc)) { + netdev_err(netdev, "Failed to config phc, error: %d\n", rc); + goto err_ena_com_phc_config; + } + + /* Register to PTP class driver */ + rc = ena_phc_register(adapter); + if (unlikely(rc)) { + netdev_err(netdev, "Failed to register phc, error: %d\n", rc); + goto err_ena_com_phc_config; + } + + return 0; + +err_ena_com_phc_config: + ena_com_phc_destroy(ena_dev); +err_ena_com_phc_init: + ena_phc_enable(adapter, false); + ena_devlink_disable_phc_param(adapter->devlink); + return rc; +} + +void ena_phc_destroy(struct ena_adapter *adapter) +{ + ena_phc_unregister(adapter); + ena_com_phc_destroy(adapter->ena_dev); +} + +int ena_phc_get_index(struct ena_adapter *adapter) +{ + if (ena_phc_is_active(adapter)) + return ptp_clock_index(adapter->phc_info->clock); + + return -1; +} diff --git a/drivers/net/ethernet/amazon/ena/ena_phc.h b/drivers/net/ethernet/amazon/ena/ena_phc.h new file mode 100644 index 000000000000..7364fe714e44 --- /dev/null +++ b/drivers/net/ethernet/amazon/ena/ena_phc.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* + * Copyright 2015-2022 Amazon.com, Inc. or its affiliates. All rights reserved. + */ + +#ifndef ENA_PHC_H +#define ENA_PHC_H + +#include <linux/ptp_clock_kernel.h> + +struct ena_phc_info { + /* PTP hardware capabilities */ + struct ptp_clock_info clock_info; + + /* Registered PTP clock device */ + struct ptp_clock *clock; + + /* Adapter specific private data structure */ + struct ena_adapter *adapter; + + /* PHC lock */ + spinlock_t lock; + + /* Enabled by kernel */ + bool enabled; +}; + +void ena_phc_enable(struct ena_adapter *adapter, bool enable); +bool ena_phc_is_enabled(struct ena_adapter *adapter); +bool ena_phc_is_active(struct ena_adapter *adapter); +int ena_phc_get_index(struct ena_adapter *adapter); +int ena_phc_init(struct ena_adapter *adapter); +void ena_phc_destroy(struct ena_adapter *adapter); +int ena_phc_alloc(struct ena_adapter *adapter); +void ena_phc_free(struct ena_adapter *adapter); + +#endif /* ENA_PHC_H */ diff --git a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h index a2efebafd686..51068dc1cc2a 100644 --- a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h +++ b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h @@ -53,6 +53,11 @@ enum ena_regs_reset_reason_types { #define ENA_REGS_MMIO_RESP_HI_OFF 0x64 #define ENA_REGS_RSS_IND_ENTRY_UPDATE_OFF 0x68 +/* phc_registers offsets */ + +/* 100 base */ +#define ENA_REGS_PHC_DB_OFF 0x100 + /* version register */ #define ENA_REGS_VERSION_MINOR_VERSION_MASK 0xff #define ENA_REGS_VERSION_MAJOR_VERSION_SHIFT 8 @@ -129,4 +134,7 @@ enum ena_regs_reset_reason_types { #define ENA_REGS_RSS_IND_ENTRY_UPDATE_CQ_IDX_SHIFT 16 #define ENA_REGS_RSS_IND_ENTRY_UPDATE_CQ_IDX_MASK 0xffff0000 +/* phc_db_req_id register */ +#define ENA_REGS_PHC_DB_REQ_ID_MASK 0xffff + #endif /* _ENA_REGS_H_ */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 44199855ebfb..528ce9ca4f54 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -3318,8 +3318,11 @@ static int bnx2x_set_phys_id(struct net_device *dev, return 0; } -static int bnx2x_get_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info) +static int bnx2x_get_rxfh_fields(struct net_device *dev, + struct ethtool_rxfh_fields *info) { + struct bnx2x *bp = netdev_priv(dev); + switch (info->flow_type) { case TCP_V4_FLOW: case TCP_V6_FLOW: @@ -3361,20 +3364,21 @@ static int bnx2x_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, case ETHTOOL_GRXRINGS: info->data = BNX2X_NUM_ETH_QUEUES(bp); return 0; - case ETHTOOL_GRXFH: - return bnx2x_get_rss_flags(bp, info); default: DP(BNX2X_MSG_ETHTOOL, "Command parameters not supported\n"); return -EOPNOTSUPP; } } -static int bnx2x_set_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info) +static int bnx2x_set_rxfh_fields(struct net_device *dev, + const struct ethtool_rxfh_fields *info, + struct netlink_ext_ack *extack) { + struct bnx2x *bp = netdev_priv(dev); int udp_rss_requested; DP(BNX2X_MSG_ETHTOOL, - "Set rss flags command parameters: flow type = %d, data = %llu\n", + "Set rss flags command parameters: flow type = %d, data = %u\n", info->flow_type, info->data); switch (info->flow_type) { @@ -3460,19 +3464,6 @@ static int bnx2x_set_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info) } } -static int bnx2x_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info) -{ - struct bnx2x *bp = netdev_priv(dev); - - switch (info->cmd) { - case ETHTOOL_SRXFH: - return bnx2x_set_rss_flags(bp, info); - default: - DP(BNX2X_MSG_ETHTOOL, "Command parameters not supported\n"); - return -EOPNOTSUPP; - } -} - static u32 bnx2x_get_rxfh_indir_size(struct net_device *dev) { return T_ETH_INDIRECTION_TABLE_SIZE; @@ -3684,10 +3675,11 @@ static const struct ethtool_ops bnx2x_ethtool_ops = { .set_phys_id = bnx2x_set_phys_id, .get_ethtool_stats = bnx2x_get_ethtool_stats, .get_rxnfc = bnx2x_get_rxnfc, - .set_rxnfc = bnx2x_set_rxnfc, .get_rxfh_indir_size = bnx2x_get_rxfh_indir_size, .get_rxfh = bnx2x_get_rxfh, .set_rxfh = bnx2x_set_rxfh, + .get_rxfh_fields = bnx2x_get_rxfh_fields, + .set_rxfh_fields = bnx2x_set_rxfh_fields, .get_channels = bnx2x_get_channels, .set_channels = bnx2x_set_channels, .get_module_info = bnx2x_get_module_info, @@ -3711,10 +3703,11 @@ static const struct ethtool_ops bnx2x_vf_ethtool_ops = { .get_strings = bnx2x_get_strings, .get_ethtool_stats = bnx2x_get_ethtool_stats, .get_rxnfc = bnx2x_get_rxnfc, - .set_rxnfc = bnx2x_set_rxnfc, .get_rxfh_indir_size = bnx2x_get_rxfh_indir_size, .get_rxfh = bnx2x_get_rxfh, .set_rxfh = bnx2x_set_rxfh, + .get_rxfh_fields = bnx2x_get_rxfh_fields, + .set_rxfh_fields = bnx2x_set_rxfh_fields, .get_channels = bnx2x_get_channels, .set_channels = bnx2x_set_channels, .get_link_ksettings = bnx2x_get_vf_link_ksettings, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index c9a1a1d504c0..3ee4b848ef53 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -10219,8 +10219,7 @@ static int bnx2x_udp_tunnel_sync(struct net_device *netdev, unsigned int table) static const struct udp_tunnel_nic_info bnx2x_udp_tunnels = { .sync_table = bnx2x_udp_tunnel_sync, - .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP | - UDP_TUNNEL_NIC_INFO_OPEN_ONLY, + .flags = UDP_TUNNEL_NIC_INFO_OPEN_ONLY, .tables = { { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, }, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 869580b6f70d..d93b0a661ccb 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1810,7 +1810,7 @@ static struct net_device *bnxt_get_pkt_dev(struct bnxt *bp, u16 cfa_code) { struct net_device *dev = bnxt_get_vf_rep(bp, cfa_code); - /* if vf-rep dev is NULL, the must belongs to the PF */ + /* if vf-rep dev is NULL, it must belong to the PF */ return dev ? dev : bp->dev; } @@ -7116,7 +7116,7 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp, default: netdev_err(bp->dev, "hwrm alloc invalid ring type %d\n", ring_type); - return -1; + return -EINVAL; } resp = hwrm_req_hold(bp, req); @@ -14055,28 +14055,13 @@ static void bnxt_unlock_sp(struct bnxt *bp) netdev_unlock(bp->dev); } -/* Same as bnxt_lock_sp() with additional rtnl_lock */ -static void bnxt_rtnl_lock_sp(struct bnxt *bp) -{ - clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state); - rtnl_lock(); - netdev_lock(bp->dev); -} - -static void bnxt_rtnl_unlock_sp(struct bnxt *bp) -{ - set_bit(BNXT_STATE_IN_SP_TASK, &bp->state); - netdev_unlock(bp->dev); - rtnl_unlock(); -} - /* Only called from bnxt_sp_task() */ static void bnxt_reset(struct bnxt *bp, bool silent) { - bnxt_rtnl_lock_sp(bp); + bnxt_lock_sp(bp); if (test_bit(BNXT_STATE_OPEN, &bp->state)) bnxt_reset_task(bp, silent); - bnxt_rtnl_unlock_sp(bp); + bnxt_unlock_sp(bp); } /* Only called from bnxt_sp_task() */ @@ -14084,9 +14069,9 @@ static void bnxt_rx_ring_reset(struct bnxt *bp) { int i; - bnxt_rtnl_lock_sp(bp); + bnxt_lock_sp(bp); if (!test_bit(BNXT_STATE_OPEN, &bp->state)) { - bnxt_rtnl_unlock_sp(bp); + bnxt_unlock_sp(bp); return; } /* Disable and flush TPA before resetting the RX ring */ @@ -14125,7 +14110,7 @@ static void bnxt_rx_ring_reset(struct bnxt *bp) } if (bp->flags & BNXT_FLAG_TPA) bnxt_set_tpa(bp, true); - bnxt_rtnl_unlock_sp(bp); + bnxt_unlock_sp(bp); } static void bnxt_fw_fatal_close(struct bnxt *bp) @@ -15017,17 +15002,15 @@ static void bnxt_fw_reset_task(struct work_struct *work) bp->fw_reset_state = BNXT_FW_RESET_STATE_OPENING; fallthrough; case BNXT_FW_RESET_STATE_OPENING: - while (!rtnl_trylock()) { + while (!netdev_trylock(bp->dev)) { bnxt_queue_fw_reset_work(bp, HZ / 10); return; } - netdev_lock(bp->dev); rc = bnxt_open(bp->dev); if (rc) { netdev_err(bp->dev, "bnxt_open() failed during FW reset\n"); bnxt_fw_reset_abort(bp, rc); netdev_unlock(bp->dev); - rtnl_unlock(); goto ulp_start; } @@ -15047,7 +15030,6 @@ static void bnxt_fw_reset_task(struct work_struct *work) bnxt_dl_health_fw_status_update(bp, true); } netdev_unlock(bp->dev); - rtnl_unlock(); bnxt_ulp_start(bp, 0); bnxt_reenable_sriov(bp); netdev_lock(bp->dev); @@ -15573,8 +15555,7 @@ static int bnxt_udp_tunnel_unset_port(struct net_device *netdev, unsigned int ta static const struct udp_tunnel_nic_info bnxt_udp_tunnels = { .set_port = bnxt_udp_tunnel_set_port, .unset_port = bnxt_udp_tunnel_unset_port, - .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP | - UDP_TUNNEL_NIC_INFO_OPEN_ONLY, + .flags = UDP_TUNNEL_NIC_INFO_OPEN_ONLY, .tables = { { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, }, @@ -15582,8 +15563,7 @@ static const struct udp_tunnel_nic_info bnxt_udp_tunnels = { }, bnxt_udp_tunnels_p7 = { .set_port = bnxt_udp_tunnel_set_port, .unset_port = bnxt_udp_tunnel_unset_port, - .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP | - UDP_TUNNEL_NIC_INFO_OPEN_ONLY, + .flags = UDP_TUNNEL_NIC_INFO_OPEN_ONLY, .tables = { { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, }, @@ -15998,7 +15978,7 @@ err_reset: rc); napi_enable_locked(&bnapi->napi); bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons); - netif_close(dev); + bnxt_reset_task(bp, true); return rc; } @@ -16814,7 +16794,6 @@ static int bnxt_resume(struct device *device) struct bnxt *bp = netdev_priv(dev); int rc = 0; - rtnl_lock(); netdev_lock(dev); rc = pci_enable_device(bp->pdev); if (rc) { @@ -16859,7 +16838,6 @@ static int bnxt_resume(struct device *device) resume_exit: netdev_unlock(bp->dev); - rtnl_unlock(); bnxt_ulp_start(bp, rc); if (!rc) bnxt_reenable_sriov(bp); @@ -17025,7 +17003,6 @@ static void bnxt_io_resume(struct pci_dev *pdev) int err; netdev_info(bp->dev, "PCI Slot Resume\n"); - rtnl_lock(); netdev_lock(netdev); err = bnxt_hwrm_func_qcaps(bp); @@ -17043,7 +17020,6 @@ static void bnxt_io_resume(struct pci_dev *pdev) netif_device_attach(netdev); netdev_unlock(netdev); - rtnl_unlock(); bnxt_ulp_start(bp, err); if (!err) bnxt_reenable_sriov(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index f5d490bf997e..4c10373abffd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -1587,8 +1587,11 @@ static u64 get_ethtool_ipv6_rss(struct bnxt *bp) return 0; } -static int bnxt_grxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd) +static int bnxt_get_rxfh_fields(struct net_device *dev, + struct ethtool_rxfh_fields *cmd) { + struct bnxt *bp = netdev_priv(dev); + cmd->data = 0; switch (cmd->flow_type) { case TCP_V4_FLOW: @@ -1647,10 +1650,15 @@ static int bnxt_grxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd) #define RXH_4TUPLE (RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3) #define RXH_2TUPLE (RXH_IP_SRC | RXH_IP_DST) -static int bnxt_srxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd) +static int bnxt_set_rxfh_fields(struct net_device *dev, + const struct ethtool_rxfh_fields *cmd, + struct netlink_ext_ack *extack) { - u32 rss_hash_cfg = bp->rss_hash_cfg; + struct bnxt *bp = netdev_priv(dev); int tuple, rc = 0; + u32 rss_hash_cfg; + + rss_hash_cfg = bp->rss_hash_cfg; if (cmd->data == RXH_4TUPLE) tuple = 4; @@ -1768,10 +1776,6 @@ static int bnxt_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, rc = bnxt_grxclsrule(bp, cmd); break; - case ETHTOOL_GRXFH: - rc = bnxt_grxfh(bp, cmd); - break; - default: rc = -EOPNOTSUPP; break; @@ -1786,10 +1790,6 @@ static int bnxt_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) int rc; switch (cmd->cmd) { - case ETHTOOL_SRXFH: - rc = bnxt_srxfh(bp, cmd); - break; - case ETHTOOL_SRXCLSRLINS: rc = bnxt_srxclsrlins(bp, cmd); break; @@ -5521,6 +5521,8 @@ const struct ethtool_ops bnxt_ethtool_ops = { .get_rxfh_key_size = bnxt_get_rxfh_key_size, .get_rxfh = bnxt_get_rxfh, .set_rxfh = bnxt_set_rxfh, + .get_rxfh_fields = bnxt_get_rxfh_fields, + .set_rxfh_fields = bnxt_set_rxfh_fields, .create_rxfh_context = bnxt_create_rxfh_context, .modify_rxfh_context = bnxt_modify_rxfh_context, .remove_rxfh_context = bnxt_remove_rxfh_context, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 5ddddd89052f..bc0d80356568 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -823,7 +823,7 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs) int tx_ok = 0, rx_ok = 0, rss_ok = 0; int avail_cp, avail_stat; - /* Check if we can enable requested num of vf's. At a mininum + /* Check if we can enable requested num of vf's. At a minimum * we require 1 RX 1 TX rings for each VF. In this minimum conf * features like TPA will not be available. */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index d2ca90407cce..0599d3016224 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -1316,7 +1316,7 @@ static int bnxt_tc_get_decap_handle(struct bnxt *bp, struct bnxt_tc_flow *flow, /* Check if there's another flow using the same tunnel decap. * If not, add this tunnel to the table and resolve the other - * tunnel header fileds. Ignore src_port in the tunnel_key, + * tunnel header fields. Ignore src_port in the tunnel_key, * since it is not required for decap filters. */ decap_key->tp_src = 0; @@ -1410,7 +1410,7 @@ static int bnxt_tc_get_encap_handle(struct bnxt *bp, struct bnxt_tc_flow *flow, /* Check if there's another flow using the same tunnel encap. * If not, add this tunnel to the table and resolve the other - * tunnel header fileds + * tunnel header fields */ encap_node = bnxt_tc_get_tunnel_node(bp, &tc_info->encap_table, &tc_info->encap_ht_params, diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index b6437ba7a2eb..573e8b279e52 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -169,10 +169,15 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable) reg &= ~EXT_GPHY_RESET; } else { + reg |= EXT_GPHY_RESET; + bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); + mdelay(1); + reg |= EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN | - EXT_GPHY_RESET | EXT_CFG_IDDQ_GLOBAL_PWR; + EXT_CFG_IDDQ_GLOBAL_PWR; bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); mdelay(1); + reg |= EXT_CK25_DIS; } bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c index ff8f2f9f9cae..75f22f74774c 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c @@ -1208,45 +1208,6 @@ int setup_cn23xx_octeon_pf_device(struct octeon_device *oct) } EXPORT_SYMBOL_GPL(setup_cn23xx_octeon_pf_device); -int validate_cn23xx_pf_config_info(struct octeon_device *oct, - struct octeon_config *conf23xx) -{ - if (CFG_GET_IQ_MAX_Q(conf23xx) > CN23XX_MAX_INPUT_QUEUES) { - dev_err(&oct->pci_dev->dev, "%s: Num IQ (%d) exceeds Max (%d)\n", - __func__, CFG_GET_IQ_MAX_Q(conf23xx), - CN23XX_MAX_INPUT_QUEUES); - return 1; - } - - if (CFG_GET_OQ_MAX_Q(conf23xx) > CN23XX_MAX_OUTPUT_QUEUES) { - dev_err(&oct->pci_dev->dev, "%s: Num OQ (%d) exceeds Max (%d)\n", - __func__, CFG_GET_OQ_MAX_Q(conf23xx), - CN23XX_MAX_OUTPUT_QUEUES); - return 1; - } - - if (CFG_GET_IQ_INSTR_TYPE(conf23xx) != OCTEON_32BYTE_INSTR && - CFG_GET_IQ_INSTR_TYPE(conf23xx) != OCTEON_64BYTE_INSTR) { - dev_err(&oct->pci_dev->dev, "%s: Invalid instr type for IQ\n", - __func__); - return 1; - } - - if (!CFG_GET_OQ_REFILL_THRESHOLD(conf23xx)) { - dev_err(&oct->pci_dev->dev, "%s: Invalid parameter for OQ\n", - __func__); - return 1; - } - - if (!(CFG_GET_OQ_INTR_TIME(conf23xx))) { - dev_err(&oct->pci_dev->dev, "%s: Invalid parameter for OQ\n", - __func__); - return 1; - } - - return 0; -} - int cn23xx_fw_loaded(struct octeon_device *oct) { u64 val; diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h index 234b96b4f488..bbe9f3133b07 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h @@ -54,9 +54,6 @@ struct oct_vf_stats { int setup_cn23xx_octeon_pf_device(struct octeon_device *oct); -int validate_cn23xx_pf_config_info(struct octeon_device *oct, - struct octeon_config *conf23xx); - u32 cn23xx_pf_get_oq_ticks(struct octeon_device *oct, u32 time_intr_in_us); int cn23xx_sriov_config(struct octeon_device *oct); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c index d0ff0c170b1a..fc6053414b7d 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c @@ -516,8 +516,8 @@ static int nicvf_set_ringparam(struct net_device *netdev, return 0; } -static int nicvf_get_rss_hash_opts(struct nicvf *nic, - struct ethtool_rxnfc *info) +static int nicvf_get_rxfh_fields(struct net_device *dev, + struct ethtool_rxfh_fields *info) { info->data = 0; @@ -552,25 +552,28 @@ static int nicvf_get_rxnfc(struct net_device *dev, info->data = nic->rx_queues; ret = 0; break; - case ETHTOOL_GRXFH: - return nicvf_get_rss_hash_opts(nic, info); default: break; } return ret; } -static int nicvf_set_rss_hash_opts(struct nicvf *nic, - struct ethtool_rxnfc *info) +static int nicvf_set_rxfh_fields(struct net_device *dev, + const struct ethtool_rxfh_fields *info, + struct netlink_ext_ack *extack) { - struct nicvf_rss_info *rss = &nic->rss_info; - u64 rss_cfg = nicvf_reg_read(nic, NIC_VNIC_RSS_CFG); + struct nicvf *nic = netdev_priv(dev); + struct nicvf_rss_info *rss; + u64 rss_cfg; + + rss = &nic->rss_info; + rss_cfg = nicvf_reg_read(nic, NIC_VNIC_RSS_CFG); if (!rss->enable) netdev_err(nic->netdev, "RSS is disabled, hash cannot be set\n"); - netdev_info(nic->netdev, "Set RSS flow type = %d, data = %lld\n", + netdev_info(nic->netdev, "Set RSS flow type = %d, data = %u\n", info->flow_type, info->data); if (!(info->data & RXH_IP_SRC) || !(info->data & RXH_IP_DST)) @@ -628,19 +631,6 @@ static int nicvf_set_rss_hash_opts(struct nicvf *nic, return 0; } -static int nicvf_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info) -{ - struct nicvf *nic = netdev_priv(dev); - - switch (info->cmd) { - case ETHTOOL_SRXFH: - return nicvf_set_rss_hash_opts(nic, info); - default: - break; - } - return -EOPNOTSUPP; -} - static u32 nicvf_get_rxfh_key_size(struct net_device *netdev) { return RSS_HASH_KEY_SIZE * sizeof(u64); @@ -872,11 +862,12 @@ static const struct ethtool_ops nicvf_ethtool_ops = { .get_ringparam = nicvf_get_ringparam, .set_ringparam = nicvf_set_ringparam, .get_rxnfc = nicvf_get_rxnfc, - .set_rxnfc = nicvf_set_rxnfc, .get_rxfh_key_size = nicvf_get_rxfh_key_size, .get_rxfh_indir_size = nicvf_get_rxfh_indir_size, .get_rxfh = nicvf_get_rxfh, .set_rxfh = nicvf_set_rxfh, + .get_rxfh_fields = nicvf_get_rxfh_fields, + .set_rxfh_fields = nicvf_set_rxfh_fields, .get_channels = nicvf_get_channels, .set_channels = nicvf_set_channels, .get_pauseparam = nicvf_get_pauseparam, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 1546c3db08f0..23326235d4ab 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -1730,6 +1730,60 @@ static int cxgb4_ntuple_get_filter(struct net_device *dev, return 0; } +static int cxgb4_get_rxfh_fields(struct net_device *dev, + struct ethtool_rxfh_fields *info) +{ + const struct port_info *pi = netdev_priv(dev); + unsigned int v = pi->rss_mode; + + info->data = 0; + switch (info->flow_type) { + case TCP_V4_FLOW: + if (v & FW_RSS_VI_CONFIG_CMD_IP4FOURTUPEN_F) + info->data = RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3; + else if (v & FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F) + info->data = RXH_IP_SRC | RXH_IP_DST; + break; + case UDP_V4_FLOW: + if ((v & FW_RSS_VI_CONFIG_CMD_IP4FOURTUPEN_F) && + (v & FW_RSS_VI_CONFIG_CMD_UDPEN_F)) + info->data = RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3; + else if (v & FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F) + info->data = RXH_IP_SRC | RXH_IP_DST; + break; + case SCTP_V4_FLOW: + case AH_ESP_V4_FLOW: + case IPV4_FLOW: + if (v & FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F) + info->data = RXH_IP_SRC | RXH_IP_DST; + break; + case TCP_V6_FLOW: + if (v & FW_RSS_VI_CONFIG_CMD_IP6FOURTUPEN_F) + info->data = RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3; + else if (v & FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F) + info->data = RXH_IP_SRC | RXH_IP_DST; + break; + case UDP_V6_FLOW: + if ((v & FW_RSS_VI_CONFIG_CMD_IP6FOURTUPEN_F) && + (v & FW_RSS_VI_CONFIG_CMD_UDPEN_F)) + info->data = RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3; + else if (v & FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F) + info->data = RXH_IP_SRC | RXH_IP_DST; + break; + case SCTP_V6_FLOW: + case AH_ESP_V6_FLOW: + case IPV6_FLOW: + if (v & FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F) + info->data = RXH_IP_SRC | RXH_IP_DST; + break; + } + return 0; +} + static int get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rules) { @@ -1739,56 +1793,6 @@ static int get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, int ret = 0; switch (info->cmd) { - case ETHTOOL_GRXFH: { - unsigned int v = pi->rss_mode; - - info->data = 0; - switch (info->flow_type) { - case TCP_V4_FLOW: - if (v & FW_RSS_VI_CONFIG_CMD_IP4FOURTUPEN_F) - info->data = RXH_IP_SRC | RXH_IP_DST | - RXH_L4_B_0_1 | RXH_L4_B_2_3; - else if (v & FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F) - info->data = RXH_IP_SRC | RXH_IP_DST; - break; - case UDP_V4_FLOW: - if ((v & FW_RSS_VI_CONFIG_CMD_IP4FOURTUPEN_F) && - (v & FW_RSS_VI_CONFIG_CMD_UDPEN_F)) - info->data = RXH_IP_SRC | RXH_IP_DST | - RXH_L4_B_0_1 | RXH_L4_B_2_3; - else if (v & FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F) - info->data = RXH_IP_SRC | RXH_IP_DST; - break; - case SCTP_V4_FLOW: - case AH_ESP_V4_FLOW: - case IPV4_FLOW: - if (v & FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F) - info->data = RXH_IP_SRC | RXH_IP_DST; - break; - case TCP_V6_FLOW: - if (v & FW_RSS_VI_CONFIG_CMD_IP6FOURTUPEN_F) - info->data = RXH_IP_SRC | RXH_IP_DST | - RXH_L4_B_0_1 | RXH_L4_B_2_3; - else if (v & FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F) - info->data = RXH_IP_SRC | RXH_IP_DST; - break; - case UDP_V6_FLOW: - if ((v & FW_RSS_VI_CONFIG_CMD_IP6FOURTUPEN_F) && - (v & FW_RSS_VI_CONFIG_CMD_UDPEN_F)) - info->data = RXH_IP_SRC | RXH_IP_DST | - RXH_L4_B_0_1 | RXH_L4_B_2_3; - else if (v & FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F) - info->data = RXH_IP_SRC | RXH_IP_DST; - break; - case SCTP_V6_FLOW: - case AH_ESP_V6_FLOW: - case IPV6_FLOW: - if (v & FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F) - info->data = RXH_IP_SRC | RXH_IP_DST; - break; - } - return 0; - } case ETHTOOL_GRXRINGS: info->data = pi->nqsets; return 0; @@ -2199,6 +2203,7 @@ static const struct ethtool_ops cxgb_ethtool_ops = { .get_rxfh_indir_size = get_rss_table_size, .get_rxfh = get_rss_table, .set_rxfh = set_rss_table, + .get_rxfh_fields = cxgb4_get_rxfh_fields, .self_test = cxgb4_self_test, .flash_device = set_flash, .get_ts_info = get_ts_info, diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c index 529160926a96..a50f5dad34d5 100644 --- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c +++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c @@ -528,8 +528,10 @@ static int enic_grxclsrule(struct enic *enic, struct ethtool_rxnfc *cmd) return 0; } -static int enic_get_rx_flow_hash(struct enic *enic, struct ethtool_rxnfc *cmd) +static int enic_get_rx_flow_hash(struct net_device *dev, + struct ethtool_rxfh_fields *cmd) { + struct enic *enic = netdev_priv(dev); u8 rss_hash_type = 0; cmd->data = 0; @@ -597,9 +599,6 @@ static int enic_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, ret = enic_grxclsrule(enic, cmd); spin_unlock_bh(&enic->rfs_h.lock); break; - case ETHTOOL_GRXFH: - ret = enic_get_rx_flow_hash(enic, cmd); - break; default: ret = -EOPNOTSUPP; break; @@ -693,6 +692,7 @@ static const struct ethtool_ops enic_ethtool_ops = { .get_rxfh_key_size = enic_get_rxfh_key_size, .get_rxfh = enic_get_rxfh, .set_rxfh = enic_set_rxfh, + .get_rxfh_fields = enic_get_rx_flow_hash, .get_link_ksettings = enic_get_ksettings, .get_ts_info = enic_get_ts_info, .get_channels = enic_get_channels, diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 3d2e21592119..f49400ba9729 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4031,8 +4031,7 @@ static int be_vxlan_unset_port(struct net_device *netdev, unsigned int table, static const struct udp_tunnel_nic_info be_udp_tunnels = { .set_port = be_vxlan_set_port, .unset_port = be_vxlan_unset_port, - .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP | - UDP_TUNNEL_NIC_INFO_OPEN_ONLY, + .flags = UDP_TUNNEL_NIC_INFO_OPEN_ONLY, .tables = { { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, }, diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 23c23cca2620..3edc8d142dd5 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -28,7 +28,6 @@ #include <linux/percpu.h> #include <linux/dma-mapping.h> #include <linux/sort.h> -#include <linux/phy_fixed.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <soc/fsl/bman.h> @@ -3150,7 +3149,6 @@ static const struct net_device_ops dpaa_ops = { .ndo_stop = dpaa_eth_stop, .ndo_tx_timeout = dpaa_tx_timeout, .ndo_get_stats64 = dpaa_get_stats64, - .ndo_change_carrier = fixed_phy_change_carrier, .ndo_set_mac_address = dpaa_set_mac_address, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = dpaa_set_rx_mode, diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index 9986f6e1f587..0c588e03b15e 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -263,8 +263,8 @@ static void dpaa_get_strings(struct net_device *net_dev, u32 stringset, ethtool_puts(&data, dpaa_stats_global[i]); } -static int dpaa_get_hash_opts(struct net_device *dev, - struct ethtool_rxnfc *cmd) +static int dpaa_get_rxfh_fields(struct net_device *dev, + struct ethtool_rxfh_fields *cmd) { struct dpaa_priv *priv = netdev_priv(dev); @@ -299,22 +299,6 @@ static int dpaa_get_hash_opts(struct net_device *dev, return 0; } -static int dpaa_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, - u32 *unused) -{ - int ret = -EOPNOTSUPP; - - switch (cmd->cmd) { - case ETHTOOL_GRXFH: - ret = dpaa_get_hash_opts(dev, cmd); - break; - default: - break; - } - - return ret; -} - static void dpaa_set_hash(struct net_device *net_dev, bool enable) { struct mac_device *mac_dev; @@ -329,8 +313,9 @@ static void dpaa_set_hash(struct net_device *net_dev, bool enable) priv->keygen_in_use = enable; } -static int dpaa_set_hash_opts(struct net_device *dev, - struct ethtool_rxnfc *nfc) +static int dpaa_set_rxfh_fields(struct net_device *dev, + const struct ethtool_rxfh_fields *nfc, + struct netlink_ext_ack *extack) { int ret = -EINVAL; @@ -364,21 +349,6 @@ static int dpaa_set_hash_opts(struct net_device *dev, return ret; } -static int dpaa_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) -{ - int ret = -EOPNOTSUPP; - - switch (cmd->cmd) { - case ETHTOOL_SRXFH: - ret = dpaa_set_hash_opts(dev, cmd); - break; - default: - break; - } - - return ret; -} - static int dpaa_get_ts_info(struct net_device *net_dev, struct kernel_ethtool_ts_info *info) { @@ -510,8 +480,8 @@ const struct ethtool_ops dpaa_ethtool_ops = { .get_strings = dpaa_get_strings, .get_link_ksettings = dpaa_get_link_ksettings, .set_link_ksettings = dpaa_set_link_ksettings, - .get_rxnfc = dpaa_get_rxnfc, - .set_rxnfc = dpaa_set_rxnfc, + .get_rxfh_fields = dpaa_get_rxfh_fields, + .set_rxfh_fields = dpaa_set_rxfh_fields, .get_ts_info = dpaa_get_ts_info, .get_coalesce = dpaa_get_coalesce, .set_coalesce = dpaa_set_coalesce, diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index 74ef77cb7078..00474ed11d53 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -719,13 +719,6 @@ static int dpaa2_eth_get_rxnfc(struct net_device *net_dev, int i, j = 0; switch (rxnfc->cmd) { - case ETHTOOL_GRXFH: - /* we purposely ignore cmd->flow_type for now, because the - * classifier only supports a single set of fields for all - * protocols - */ - rxnfc->data = priv->rx_hash_fields; - break; case ETHTOOL_GRXRINGS: rxnfc->data = dpaa2_eth_queue_count(priv); break; @@ -767,11 +760,6 @@ static int dpaa2_eth_set_rxnfc(struct net_device *net_dev, int err = 0; switch (rxnfc->cmd) { - case ETHTOOL_SRXFH: - if ((rxnfc->data & DPAA2_RXH_SUPPORTED) != rxnfc->data) - return -EOPNOTSUPP; - err = dpaa2_eth_set_hash(net_dev, rxnfc->data); - break; case ETHTOOL_SRXCLSRLINS: err = dpaa2_eth_update_cls_rule(net_dev, &rxnfc->fs, rxnfc->fs.location); break; @@ -785,6 +773,28 @@ static int dpaa2_eth_set_rxnfc(struct net_device *net_dev, return err; } +static int dpaa2_eth_get_rxfh_fields(struct net_device *net_dev, + struct ethtool_rxfh_fields *rxnfc) +{ + struct dpaa2_eth_priv *priv = netdev_priv(net_dev); + + /* we purposely ignore cmd->flow_type for now, because the + * classifier only supports a single set of fields for all + * protocols + */ + rxnfc->data = priv->rx_hash_fields; + return 0; +} + +static int dpaa2_eth_set_rxfh_fields(struct net_device *net_dev, + const struct ethtool_rxfh_fields *rxnfc, + struct netlink_ext_ack *extack) +{ + if ((rxnfc->data & DPAA2_RXH_SUPPORTED) != rxnfc->data) + return -EOPNOTSUPP; + return dpaa2_eth_set_hash(net_dev, rxnfc->data); +} + int dpaa2_phc_index = -1; EXPORT_SYMBOL(dpaa2_phc_index); @@ -939,6 +949,8 @@ const struct ethtool_ops dpaa2_ethtool_ops = { .get_strings = dpaa2_eth_get_strings, .get_rxnfc = dpaa2_eth_get_rxnfc, .set_rxnfc = dpaa2_eth_set_rxnfc, + .get_rxfh_fields = dpaa2_eth_get_rxfh_fields, + .set_rxfh_fields = dpaa2_eth_set_rxfh_fields, .get_ts_info = dpaa2_eth_get_ts_info, .get_tunable = dpaa2_eth_get_tunable, .set_tunable = dpaa2_eth_set_tunable, diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index dcc3fbac3481..e4287725832e 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1375,6 +1375,7 @@ static void enetc_get_offloads(struct enetc_bdr *rx_ring, } if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_VLAN) { + struct enetc_hw *hw = &priv->si->hw; __be16 tpid = 0; switch (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_TPID) { @@ -1385,15 +1386,12 @@ static void enetc_get_offloads(struct enetc_bdr *rx_ring, tpid = htons(ETH_P_8021AD); break; case 2: - tpid = htons(enetc_port_rd(&priv->si->hw, - ENETC_PCVLANR1)); + tpid = htons(enetc_rd_hot(hw, ENETC_SICVLANR1) & + SICVLANR_ETYPE); break; case 3: - tpid = htons(enetc_port_rd(&priv->si->hw, - ENETC_PCVLANR2)); - break; - default: - break; + tpid = htons(enetc_rd_hot(hw, ENETC_SICVLANR2) & + SICVLANR_ETYPE); } __vlan_hwaccel_put_tag(skb, tpid, le16_to_cpu(rxbd->r.vlan_opt)); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index d38cd36be4a6..2e5cef646741 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -467,7 +467,8 @@ static void enetc_get_rmon_stats(struct net_device *ndev, #define ENETC_RSSHASH_L3 (RXH_L2DA | RXH_VLAN | RXH_L3_PROTO | RXH_IP_SRC | \ RXH_IP_DST) #define ENETC_RSSHASH_L4 (ENETC_RSSHASH_L3 | RXH_L4_B_0_1 | RXH_L4_B_2_3) -static int enetc_get_rsshash(struct ethtool_rxnfc *rxnfc) +static int enetc_get_rxfh_fields(struct net_device *netdev, + struct ethtool_rxfh_fields *rxnfc) { static const u32 rsshash[] = { [TCP_V4_FLOW] = ENETC_RSSHASH_L4, @@ -584,9 +585,6 @@ static int enetc_get_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *rxnfc, case ETHTOOL_GRXRINGS: rxnfc->data = priv->num_rx_rings; break; - case ETHTOOL_GRXFH: - /* get RSS hash config */ - return enetc_get_rsshash(rxnfc); case ETHTOOL_GRXCLSRLCNT: /* total number of entries */ rxnfc->data = priv->si->num_fs_entries; @@ -639,8 +637,6 @@ static int enetc4_get_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *rxnfc case ETHTOOL_GRXRINGS: rxnfc->data = priv->num_rx_rings; break; - case ETHTOOL_GRXFH: - return enetc_get_rsshash(rxnfc); default: return -EOPNOTSUPP; } @@ -1228,6 +1224,7 @@ const struct ethtool_ops enetc_pf_ethtool_ops = { .get_rxfh_indir_size = enetc_get_rxfh_indir_size, .get_rxfh = enetc_get_rxfh, .set_rxfh = enetc_set_rxfh, + .get_rxfh_fields = enetc_get_rxfh_fields, .get_ringparam = enetc_get_ringparam, .get_coalesce = enetc_get_coalesce, .set_coalesce = enetc_set_coalesce, @@ -1258,6 +1255,7 @@ const struct ethtool_ops enetc_vf_ethtool_ops = { .get_rxfh_indir_size = enetc_get_rxfh_indir_size, .get_rxfh = enetc_get_rxfh, .set_rxfh = enetc_set_rxfh, + .get_rxfh_fields = enetc_get_rxfh_fields, .get_ringparam = enetc_get_ringparam, .get_coalesce = enetc_get_coalesce, .set_coalesce = enetc_set_coalesce, @@ -1284,6 +1282,7 @@ const struct ethtool_ops enetc4_pf_ethtool_ops = { .get_rxfh_indir_size = enetc_get_rxfh_indir_size, .get_rxfh = enetc_get_rxfh, .set_rxfh = enetc_set_rxfh, + .get_rxfh_fields = enetc_get_rxfh_fields, }; void enetc_set_ethtool_ops(struct net_device *ndev) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 4098f01479bc..cb26f185f52f 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -43,6 +43,9 @@ #define ENETC_SIPMAR0 0x80 #define ENETC_SIPMAR1 0x84 +#define ENETC_SICVLANR1 0x90 +#define ENETC_SICVLANR2 0x94 +#define SICVLANR_ETYPE GENMASK(15, 0) /* VF-PF Message passing */ #define ENETC_DEFAULT_MSG_SIZE 1024 /* and max size */ diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index 781d92e703cb..28f53cf2a174 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -781,14 +781,26 @@ err: return ret; } -static int gfar_set_hash_opts(struct gfar_private *priv, - struct ethtool_rxnfc *cmd) +static int gfar_set_rxfh_fields(struct net_device *dev, + const struct ethtool_rxfh_fields *cmd, + struct netlink_ext_ack *extack) { + struct gfar_private *priv = netdev_priv(dev); + int ret; + + if (test_bit(GFAR_RESETTING, &priv->state)) + return -EBUSY; + + mutex_lock(&priv->rx_queue_access); + + ret = 0; /* write the filer rules here */ if (!gfar_ethflow_to_filer_table(priv, cmd->data, cmd->flow_type)) - return -EINVAL; + ret = -EINVAL; - return 0; + mutex_unlock(&priv->rx_queue_access); + + return ret; } static int gfar_check_filer_hardware(struct gfar_private *priv) @@ -1398,9 +1410,6 @@ static int gfar_set_nfc(struct net_device *dev, struct ethtool_rxnfc *cmd) mutex_lock(&priv->rx_queue_access); switch (cmd->cmd) { - case ETHTOOL_SRXFH: - ret = gfar_set_hash_opts(priv, cmd); - break; case ETHTOOL_SRXCLSRLINS: if ((cmd->fs.ring_cookie != RX_CLS_FLOW_DISC && cmd->fs.ring_cookie >= priv->num_rx_queues) || @@ -1508,6 +1517,7 @@ const struct ethtool_ops gfar_ethtool_ops = { #endif .set_rxnfc = gfar_set_nfc, .get_rxnfc = gfar_get_nfc, + .set_rxfh_fields = gfar_set_rxfh_fields, .get_ts_info = gfar_get_ts_info, .get_link_ksettings = phy_ethtool_get_link_ksettings, .set_link_ksettings = phy_ethtool_set_link_ksettings, diff --git a/drivers/net/ethernet/google/Kconfig b/drivers/net/ethernet/google/Kconfig index 564862a57124..14c9431e15e5 100644 --- a/drivers/net/ethernet/google/Kconfig +++ b/drivers/net/ethernet/google/Kconfig @@ -18,6 +18,7 @@ if NET_VENDOR_GOOGLE config GVE tristate "Google Virtual NIC (gVNIC) support" depends on (PCI_MSI && (X86 || CPU_LITTLE_ENDIAN)) + depends on PTP_1588_CLOCK_OPTIONAL select PAGE_POOL help This driver supports Google Virtual NIC (gVNIC)" diff --git a/drivers/net/ethernet/google/gve/Makefile b/drivers/net/ethernet/google/gve/Makefile index 4520f1c07a63..e0ec227a50f7 100644 --- a/drivers/net/ethernet/google/gve/Makefile +++ b/drivers/net/ethernet/google/gve/Makefile @@ -1,5 +1,7 @@ # Makefile for the Google virtual Ethernet (gve) driver obj-$(CONFIG_GVE) += gve.o -gve-objs := gve_main.o gve_tx.o gve_tx_dqo.o gve_rx.o gve_rx_dqo.o gve_ethtool.o gve_adminq.o gve_utils.o gve_flow_rule.o \ +gve-y := gve_main.o gve_tx.o gve_tx_dqo.o gve_rx.o gve_rx_dqo.o gve_ethtool.o gve_adminq.o gve_utils.o gve_flow_rule.o \ gve_buffer_mgmt_dqo.o + +gve-$(CONFIG_PTP_1588_CLOCK) += gve_ptp.o diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 2fab38c8ee78..4469442d4940 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -11,7 +11,9 @@ #include <linux/dmapool.h> #include <linux/ethtool_netlink.h> #include <linux/netdevice.h> +#include <linux/net_tstamp.h> #include <linux/pci.h> +#include <linux/ptp_clock_kernel.h> #include <linux/u64_stats_sync.h> #include <net/page_pool/helpers.h> #include <net/xdp.h> @@ -750,6 +752,12 @@ struct gve_rss_config { u32 *hash_lut; }; +struct gve_ptp { + struct ptp_clock_info info; + struct ptp_clock *clock; + struct gve_priv *priv; +}; + struct gve_priv { struct net_device *dev; struct gve_tx_ring *tx; /* array of tx_cfg.num_queues */ @@ -781,7 +789,7 @@ struct gve_priv { struct gve_tx_queue_config tx_cfg; struct gve_rx_queue_config rx_cfg; - u32 num_ntfy_blks; /* spilt between TX and RX so must be even */ + u32 num_ntfy_blks; /* split between TX and RX so must be even */ struct gve_registers __iomem *reg_bar0; /* see gve_register.h */ __be32 __iomem *db_bar2; /* "array" of doorbells */ @@ -813,6 +821,7 @@ struct gve_priv { u32 adminq_set_driver_parameter_cnt; u32 adminq_report_stats_cnt; u32 adminq_report_link_speed_cnt; + u32 adminq_report_nic_timestamp_cnt; u32 adminq_get_ptype_map_cnt; u32 adminq_verify_driver_compatibility_cnt; u32 adminq_query_flow_rules_cnt; @@ -870,6 +879,14 @@ struct gve_priv { u16 rss_lut_size; bool cache_rss_config; struct gve_rss_config rss_config; + + /* True if the device supports reading the nic clock */ + bool nic_timestamp_supported; + struct gve_ptp *ptp; + struct kernel_hwtstamp_config ts_config; + struct gve_nic_ts_report *nic_ts_report; + dma_addr_t nic_ts_report_bus; + u64 last_sync_nic_counter; /* Clock counter from last NIC TS report */ }; enum gve_service_task_flags_bit { @@ -1249,6 +1266,24 @@ int gve_del_flow_rule(struct gve_priv *priv, struct ethtool_rxnfc *cmd); int gve_flow_rules_reset(struct gve_priv *priv); /* RSS config */ int gve_init_rss_config(struct gve_priv *priv, u16 num_queues); +/* PTP and timestamping */ +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) +int gve_clock_nic_ts_read(struct gve_priv *priv); +int gve_init_clock(struct gve_priv *priv); +void gve_teardown_clock(struct gve_priv *priv); +#else /* CONFIG_PTP_1588_CLOCK */ +static inline int gve_clock_nic_ts_read(struct gve_priv *priv) +{ + return -EOPNOTSUPP; +} + +static inline int gve_init_clock(struct gve_priv *priv) +{ + return 0; +} + +static inline void gve_teardown_clock(struct gve_priv *priv) { } +#endif /* CONFIG_PTP_1588_CLOCK */ /* report stats handling */ void gve_handle_report_stats(struct gve_priv *priv); /* exported by ethtool.c */ diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index 3e8fc33cc11f..4f33d094a2ef 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -46,6 +46,7 @@ void gve_parse_device_option(struct gve_priv *priv, struct gve_device_option_buffer_sizes **dev_op_buffer_sizes, struct gve_device_option_flow_steering **dev_op_flow_steering, struct gve_device_option_rss_config **dev_op_rss_config, + struct gve_device_option_nic_timestamp **dev_op_nic_timestamp, struct gve_device_option_modify_ring **dev_op_modify_ring) { u32 req_feat_mask = be32_to_cpu(option->required_features_mask); @@ -225,6 +226,23 @@ void gve_parse_device_option(struct gve_priv *priv, "RSS config"); *dev_op_rss_config = (void *)(option + 1); break; + case GVE_DEV_OPT_ID_NIC_TIMESTAMP: + if (option_length < sizeof(**dev_op_nic_timestamp) || + req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_NIC_TIMESTAMP) { + dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT, + "Nic Timestamp", + (int)sizeof(**dev_op_nic_timestamp), + GVE_DEV_OPT_REQ_FEAT_MASK_NIC_TIMESTAMP, + option_length, req_feat_mask); + break; + } + + if (option_length > sizeof(**dev_op_nic_timestamp)) + dev_warn(&priv->pdev->dev, + GVE_DEVICE_OPTION_TOO_BIG_FMT, + "Nic Timestamp"); + *dev_op_nic_timestamp = (void *)(option + 1); + break; default: /* If we don't recognize the option just continue * without doing anything. @@ -246,6 +264,7 @@ gve_process_device_options(struct gve_priv *priv, struct gve_device_option_buffer_sizes **dev_op_buffer_sizes, struct gve_device_option_flow_steering **dev_op_flow_steering, struct gve_device_option_rss_config **dev_op_rss_config, + struct gve_device_option_nic_timestamp **dev_op_nic_timestamp, struct gve_device_option_modify_ring **dev_op_modify_ring) { const int num_options = be16_to_cpu(descriptor->num_device_options); @@ -269,6 +288,7 @@ gve_process_device_options(struct gve_priv *priv, dev_op_dqo_rda, dev_op_jumbo_frames, dev_op_dqo_qpl, dev_op_buffer_sizes, dev_op_flow_steering, dev_op_rss_config, + dev_op_nic_timestamp, dev_op_modify_ring); dev_opt = next_opt; } @@ -306,6 +326,7 @@ int gve_adminq_alloc(struct device *dev, struct gve_priv *priv) priv->adminq_set_driver_parameter_cnt = 0; priv->adminq_report_stats_cnt = 0; priv->adminq_report_link_speed_cnt = 0; + priv->adminq_report_nic_timestamp_cnt = 0; priv->adminq_get_ptype_map_cnt = 0; priv->adminq_query_flow_rules_cnt = 0; priv->adminq_cfg_flow_rule_cnt = 0; @@ -442,6 +463,8 @@ static int gve_adminq_kick_and_wait(struct gve_priv *priv) int tail, head; int i; + lockdep_assert_held(&priv->adminq_lock); + tail = ioread32be(&priv->reg_bar0->adminq_event_counter); head = priv->adminq_prod_cnt; @@ -467,9 +490,6 @@ static int gve_adminq_kick_and_wait(struct gve_priv *priv) return 0; } -/* This function is not threadsafe - the caller is responsible for any - * necessary locks. - */ static int gve_adminq_issue_cmd(struct gve_priv *priv, union gve_adminq_command *cmd_orig) { @@ -477,6 +497,8 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv, u32 opcode; u32 tail; + lockdep_assert_held(&priv->adminq_lock); + tail = ioread32be(&priv->reg_bar0->adminq_event_counter); // Check if next command will overflow the buffer. @@ -544,6 +566,9 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv, case GVE_ADMINQ_REPORT_LINK_SPEED: priv->adminq_report_link_speed_cnt++; break; + case GVE_ADMINQ_REPORT_NIC_TIMESTAMP: + priv->adminq_report_nic_timestamp_cnt++; + break; case GVE_ADMINQ_GET_PTYPE_MAP: priv->adminq_get_ptype_map_cnt++; break; @@ -564,6 +589,7 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv, break; default: dev_err(&priv->pdev->dev, "unknown AQ command opcode %d\n", opcode); + return -EINVAL; } return 0; @@ -625,7 +651,7 @@ static int gve_adminq_execute_extended_cmd(struct gve_priv *priv, u32 opcode, /* The device specifies that the management vector can either be the first irq * or the last irq. ntfy_blk_msix_base_idx indicates the first irq assigned to - * the ntfy blks. It if is 0 then the management vector is last, if it is 1 then + * the ntfy blks. If it is 0 then the management vector is last, if it is 1 then * the management vector is first. * * gve arranges the msix vectors so that the management vector is last. @@ -709,13 +735,19 @@ int gve_adminq_create_tx_queues(struct gve_priv *priv, u32 start_id, u32 num_que int err; int i; + mutex_lock(&priv->adminq_lock); + for (i = start_id; i < start_id + num_queues; i++) { err = gve_adminq_create_tx_queue(priv, i); if (err) - return err; + goto out; } - return gve_adminq_kick_and_wait(priv); + err = gve_adminq_kick_and_wait(priv); + +out: + mutex_unlock(&priv->adminq_lock); + return err; } static void gve_adminq_get_create_rx_queue_cmd(struct gve_priv *priv, @@ -788,13 +820,19 @@ int gve_adminq_create_rx_queues(struct gve_priv *priv, u32 num_queues) int err; int i; + mutex_lock(&priv->adminq_lock); + for (i = 0; i < num_queues; i++) { err = gve_adminq_create_rx_queue(priv, i); if (err) - return err; + goto out; } - return gve_adminq_kick_and_wait(priv); + err = gve_adminq_kick_and_wait(priv); + +out: + mutex_unlock(&priv->adminq_lock); + return err; } static int gve_adminq_destroy_tx_queue(struct gve_priv *priv, u32 queue_index) @@ -820,13 +858,19 @@ int gve_adminq_destroy_tx_queues(struct gve_priv *priv, u32 start_id, u32 num_qu int err; int i; + mutex_lock(&priv->adminq_lock); + for (i = start_id; i < start_id + num_queues; i++) { err = gve_adminq_destroy_tx_queue(priv, i); if (err) - return err; + goto out; } - return gve_adminq_kick_and_wait(priv); + err = gve_adminq_kick_and_wait(priv); + +out: + mutex_unlock(&priv->adminq_lock); + return err; } static void gve_adminq_make_destroy_rx_queue_cmd(union gve_adminq_command *cmd, @@ -861,13 +905,19 @@ int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 num_queues) int err; int i; + mutex_lock(&priv->adminq_lock); + for (i = 0; i < num_queues; i++) { err = gve_adminq_destroy_rx_queue(priv, i); if (err) - return err; + goto out; } - return gve_adminq_kick_and_wait(priv); + err = gve_adminq_kick_and_wait(priv); + +out: + mutex_unlock(&priv->adminq_lock); + return err; } static void gve_set_default_desc_cnt(struct gve_priv *priv, @@ -904,6 +954,8 @@ static void gve_enable_supported_features(struct gve_priv *priv, *dev_op_flow_steering, const struct gve_device_option_rss_config *dev_op_rss_config, + const struct gve_device_option_nic_timestamp + *dev_op_nic_timestamp, const struct gve_device_option_modify_ring *dev_op_modify_ring) { @@ -980,10 +1032,15 @@ static void gve_enable_supported_features(struct gve_priv *priv, "RSS device option enabled with key size of %u, lut size of %u.\n", priv->rss_key_size, priv->rss_lut_size); } + + if (dev_op_nic_timestamp && + (supported_features_mask & GVE_SUP_NIC_TIMESTAMP_MASK)) + priv->nic_timestamp_supported = true; } int gve_adminq_describe_device(struct gve_priv *priv) { + struct gve_device_option_nic_timestamp *dev_op_nic_timestamp = NULL; struct gve_device_option_flow_steering *dev_op_flow_steering = NULL; struct gve_device_option_buffer_sizes *dev_op_buffer_sizes = NULL; struct gve_device_option_jumbo_frames *dev_op_jumbo_frames = NULL; @@ -1024,6 +1081,7 @@ int gve_adminq_describe_device(struct gve_priv *priv) &dev_op_buffer_sizes, &dev_op_flow_steering, &dev_op_rss_config, + &dev_op_nic_timestamp, &dev_op_modify_ring); if (err) goto free_device_descriptor; @@ -1088,7 +1146,8 @@ int gve_adminq_describe_device(struct gve_priv *priv) gve_enable_supported_features(priv, supported_features_mask, dev_op_jumbo_frames, dev_op_dqo_qpl, dev_op_buffer_sizes, dev_op_flow_steering, - dev_op_rss_config, dev_op_modify_ring); + dev_op_rss_config, dev_op_nic_timestamp, + dev_op_modify_ring); free_device_descriptor: dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus); @@ -1200,6 +1259,22 @@ int gve_adminq_report_link_speed(struct gve_priv *priv) return err; } +int gve_adminq_report_nic_ts(struct gve_priv *priv, + dma_addr_t nic_ts_report_addr) +{ + union gve_adminq_command cmd; + + memset(&cmd, 0, sizeof(cmd)); + cmd.opcode = cpu_to_be32(GVE_ADMINQ_REPORT_NIC_TIMESTAMP); + cmd.report_nic_ts = (struct gve_adminq_report_nic_ts) { + .nic_ts_report_len = + cpu_to_be64(sizeof(struct gve_nic_ts_report)), + .nic_ts_report_addr = cpu_to_be64(nic_ts_report_addr), + }; + + return gve_adminq_execute_cmd(priv, &cmd); +} + int gve_adminq_get_ptype_map_dqo(struct gve_priv *priv, struct gve_ptype_lut *ptype_lut) { diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h index 228217458275..22a74b6aa17e 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.h +++ b/drivers/net/ethernet/google/gve/gve_adminq.h @@ -27,6 +27,7 @@ enum gve_adminq_opcodes { GVE_ADMINQ_GET_PTYPE_MAP = 0xE, GVE_ADMINQ_VERIFY_DRIVER_COMPATIBILITY = 0xF, GVE_ADMINQ_QUERY_FLOW_RULES = 0x10, + GVE_ADMINQ_REPORT_NIC_TIMESTAMP = 0x11, GVE_ADMINQ_QUERY_RSS = 0x12, /* For commands that are larger than 56 bytes */ @@ -174,6 +175,12 @@ struct gve_device_option_rss_config { static_assert(sizeof(struct gve_device_option_rss_config) == 8); +struct gve_device_option_nic_timestamp { + __be32 supported_features_mask; +}; + +static_assert(sizeof(struct gve_device_option_nic_timestamp) == 4); + /* Terminology: * * RDA - Raw DMA Addressing - Buffers associated with SKBs are directly DMA @@ -192,6 +199,7 @@ enum gve_dev_opt_id { GVE_DEV_OPT_ID_JUMBO_FRAMES = 0x8, GVE_DEV_OPT_ID_BUFFER_SIZES = 0xa, GVE_DEV_OPT_ID_FLOW_STEERING = 0xb, + GVE_DEV_OPT_ID_NIC_TIMESTAMP = 0xd, GVE_DEV_OPT_ID_RSS_CONFIG = 0xe, }; @@ -206,6 +214,7 @@ enum gve_dev_opt_req_feat_mask { GVE_DEV_OPT_REQ_FEAT_MASK_MODIFY_RING = 0x0, GVE_DEV_OPT_REQ_FEAT_MASK_FLOW_STEERING = 0x0, GVE_DEV_OPT_REQ_FEAT_MASK_RSS_CONFIG = 0x0, + GVE_DEV_OPT_REQ_FEAT_MASK_NIC_TIMESTAMP = 0x0, }; enum gve_sup_feature_mask { @@ -214,6 +223,7 @@ enum gve_sup_feature_mask { GVE_SUP_BUFFER_SIZES_MASK = 1 << 4, GVE_SUP_FLOW_STEERING_MASK = 1 << 5, GVE_SUP_RSS_CONFIG_MASK = 1 << 7, + GVE_SUP_NIC_TIMESTAMP_MASK = 1 << 8, }; #define GVE_DEV_OPT_LEN_GQI_RAW_ADDRESSING 0x0 @@ -392,6 +402,21 @@ struct gve_adminq_report_link_speed { static_assert(sizeof(struct gve_adminq_report_link_speed) == 8); +struct gve_adminq_report_nic_ts { + __be64 nic_ts_report_len; + __be64 nic_ts_report_addr; +}; + +static_assert(sizeof(struct gve_adminq_report_nic_ts) == 16); + +struct gve_nic_ts_report { + __be64 nic_timestamp; /* NIC clock in nanoseconds */ + __be64 reserved1; + __be64 reserved2; + __be64 reserved3; + __be64 reserved4; +}; + struct stats { __be32 stat_name; __be32 queue_id; @@ -451,7 +476,7 @@ struct gve_ptype_entry { }; struct gve_ptype_map { - struct gve_ptype_entry ptypes[1 << 10]; /* PTYPES are always 10 bits. */ + struct gve_ptype_entry ptypes[GVE_NUM_PTYPES]; /* PTYPES are always 10 bits. */ }; struct gve_adminq_get_ptype_map { @@ -585,6 +610,7 @@ union gve_adminq_command { struct gve_adminq_query_flow_rules query_flow_rules; struct gve_adminq_configure_rss configure_rss; struct gve_adminq_query_rss query_rss; + struct gve_adminq_report_nic_ts report_nic_ts; struct gve_adminq_extended_command extended_command; }; }; @@ -624,6 +650,8 @@ int gve_adminq_reset_flow_rules(struct gve_priv *priv); int gve_adminq_query_flow_rules(struct gve_priv *priv, u16 query_opcode, u32 starting_loc); int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh); int gve_adminq_query_rss_config(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh); +int gve_adminq_report_nic_ts(struct gve_priv *priv, + dma_addr_t nic_ts_report_addr); struct gve_ptype_lut; int gve_adminq_get_ptype_map_dqo(struct gve_priv *priv, diff --git a/drivers/net/ethernet/google/gve/gve_desc_dqo.h b/drivers/net/ethernet/google/gve/gve_desc_dqo.h index f79cd0591110..d17da841b5a0 100644 --- a/drivers/net/ethernet/google/gve/gve_desc_dqo.h +++ b/drivers/net/ethernet/google/gve/gve_desc_dqo.h @@ -247,7 +247,8 @@ struct gve_rx_compl_desc_dqo { }; __le32 hash; __le32 reserved6; - __le64 reserved7; + __le32 reserved7; + __le32 ts; /* timestamp in nanosecs */ } __packed; static_assert(sizeof(struct gve_rx_compl_desc_dqo) == 32); diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index a6d0089ecd7b..d0a223250845 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -76,7 +76,7 @@ static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] __nonstring_array "adminq_dcfg_device_resources_cnt", "adminq_set_driver_parameter_cnt", "adminq_report_stats_cnt", "adminq_report_link_speed_cnt", "adminq_get_ptype_map_cnt", "adminq_query_flow_rules", "adminq_cfg_flow_rule", "adminq_cfg_rss_cnt", - "adminq_query_rss_cnt", + "adminq_query_rss_cnt", "adminq_report_nic_timestamp_cnt", }; static const char gve_gstrings_priv_flags[][ETH_GSTRING_LEN] = { @@ -456,6 +456,7 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = priv->adminq_cfg_flow_rule_cnt; data[i++] = priv->adminq_cfg_rss_cnt; data[i++] = priv->adminq_query_rss_cnt; + data[i++] = priv->adminq_report_nic_timestamp_cnt; } static void gve_get_channels(struct net_device *netdev, @@ -667,7 +668,7 @@ static u32 gve_get_priv_flags(struct net_device *netdev) struct gve_priv *priv = netdev_priv(netdev); u32 ret_flags = 0; - /* Only 1 flag exists currently: report-stats (BIT(O)), so set that flag. */ + /* Only 1 flag exists currently: report-stats (BIT(0)), so set that flag. */ if (priv->ethtool_flags & BIT(0)) ret_flags |= BIT(0); return ret_flags; @@ -922,6 +923,27 @@ static int gve_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rx return 0; } +static int gve_get_ts_info(struct net_device *netdev, + struct kernel_ethtool_ts_info *info) +{ + struct gve_priv *priv = netdev_priv(netdev); + + ethtool_op_get_ts_info(netdev, info); + + if (priv->nic_timestamp_supported) { + info->so_timestamping |= SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + info->rx_filters |= BIT(HWTSTAMP_FILTER_NONE) | + BIT(HWTSTAMP_FILTER_ALL); + + if (priv->ptp) + info->phc_index = ptp_clock_index(priv->ptp->clock); + } + + return 0; +} + const struct ethtool_ops gve_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS, .supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT, @@ -950,5 +972,5 @@ const struct ethtool_ops gve_ethtool_ops = { .get_priv_flags = gve_get_priv_flags, .set_priv_flags = gve_set_priv_flags, .get_link_ksettings = gve_get_link_ksettings, - .get_ts_info = ethtool_op_get_ts_info, + .get_ts_info = gve_get_ts_info, }; diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index dc35a23ec47f..28e4795f5f40 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -619,9 +619,12 @@ static int gve_setup_device_resources(struct gve_priv *priv) err = gve_alloc_counter_array(priv); if (err) goto abort_with_rss_config_cache; - err = gve_alloc_notify_blocks(priv); + err = gve_init_clock(priv); if (err) goto abort_with_counter; + err = gve_alloc_notify_blocks(priv); + if (err) + goto abort_with_clock; err = gve_alloc_stats_report(priv); if (err) goto abort_with_ntfy_blocks; @@ -674,6 +677,8 @@ abort_with_stats_report: gve_free_stats_report(priv); abort_with_ntfy_blocks: gve_free_notify_blocks(priv); +abort_with_clock: + gve_teardown_clock(priv); abort_with_counter: gve_free_counter_array(priv); abort_with_rss_config_cache: @@ -722,6 +727,7 @@ static void gve_teardown_device_resources(struct gve_priv *priv) gve_free_counter_array(priv); gve_free_notify_blocks(priv); gve_free_stats_report(priv); + gve_teardown_clock(priv); gve_clear_device_resources_ok(priv); } @@ -1727,7 +1733,7 @@ int gve_adjust_config(struct gve_priv *priv, { int err; - /* Allocate resources for the new confiugration */ + /* Allocate resources for the new configuration */ err = gve_queues_mem_alloc(priv, tx_alloc_cfg, rx_alloc_cfg); if (err) { netif_err(priv, drv, priv->dev, @@ -2042,6 +2048,46 @@ revert_features: return err; } +static int gve_get_ts_config(struct net_device *dev, + struct kernel_hwtstamp_config *kernel_config) +{ + struct gve_priv *priv = netdev_priv(dev); + + *kernel_config = priv->ts_config; + return 0; +} + +static int gve_set_ts_config(struct net_device *dev, + struct kernel_hwtstamp_config *kernel_config, + struct netlink_ext_ack *extack) +{ + struct gve_priv *priv = netdev_priv(dev); + + if (kernel_config->tx_type != HWTSTAMP_TX_OFF) { + NL_SET_ERR_MSG_MOD(extack, "TX timestamping is not supported"); + return -ERANGE; + } + + if (kernel_config->rx_filter != HWTSTAMP_FILTER_NONE) { + if (!priv->nic_ts_report) { + NL_SET_ERR_MSG_MOD(extack, + "RX timestamping is not supported"); + kernel_config->rx_filter = HWTSTAMP_FILTER_NONE; + return -EOPNOTSUPP; + } + + kernel_config->rx_filter = HWTSTAMP_FILTER_ALL; + gve_clock_nic_ts_read(priv); + ptp_schedule_worker(priv->ptp->clock, 0); + } else { + ptp_cancel_worker_sync(priv->ptp->clock); + } + + priv->ts_config.rx_filter = kernel_config->rx_filter; + + return 0; +} + static const struct net_device_ops gve_netdev_ops = { .ndo_start_xmit = gve_start_xmit, .ndo_features_check = gve_features_check, @@ -2053,6 +2099,8 @@ static const struct net_device_ops gve_netdev_ops = { .ndo_bpf = gve_xdp, .ndo_xdp_xmit = gve_xdp_xmit, .ndo_xsk_wakeup = gve_xsk_wakeup, + .ndo_hwtstamp_get = gve_get_ts_config, + .ndo_hwtstamp_set = gve_set_ts_config, }; static void gve_handle_status(struct gve_priv *priv, u32 status) @@ -2236,7 +2284,7 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) goto err; } - /* Big TCP is only supported on DQ*/ + /* Big TCP is only supported on DQO */ if (!gve_is_gqi(priv)) netif_set_tso_max_size(priv->dev, GVE_DQO_TX_MAX); @@ -2272,6 +2320,9 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) priv->rx_coalesce_usecs = GVE_RX_IRQ_RATELIMIT_US_DQO; } + priv->ts_config.tx_type = HWTSTAMP_TX_OFF; + priv->ts_config.rx_filter = HWTSTAMP_FILTER_NONE; + setup_device: gve_set_netdev_xdp_features(priv); err = gve_setup_device_resources(priv); diff --git a/drivers/net/ethernet/google/gve/gve_ptp.c b/drivers/net/ethernet/google/gve/gve_ptp.c new file mode 100644 index 000000000000..e96247c9d68d --- /dev/null +++ b/drivers/net/ethernet/google/gve/gve_ptp.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Google virtual Ethernet (gve) driver + * + * Copyright (C) 2025 Google LLC + */ + +#include "gve.h" +#include "gve_adminq.h" + +/* Interval to schedule a nic timestamp calibration, 250ms. */ +#define GVE_NIC_TS_SYNC_INTERVAL_MS 250 + +/* Read the nic timestamp from hardware via the admin queue. */ +int gve_clock_nic_ts_read(struct gve_priv *priv) +{ + u64 nic_raw; + int err; + + err = gve_adminq_report_nic_ts(priv, priv->nic_ts_report_bus); + if (err) + return err; + + nic_raw = be64_to_cpu(priv->nic_ts_report->nic_timestamp); + WRITE_ONCE(priv->last_sync_nic_counter, nic_raw); + + return 0; +} + +static long gve_ptp_do_aux_work(struct ptp_clock_info *info) +{ + const struct gve_ptp *ptp = container_of(info, struct gve_ptp, info); + struct gve_priv *priv = ptp->priv; + int err; + + if (gve_get_reset_in_progress(priv) || !gve_get_admin_queue_ok(priv)) + goto out; + + err = gve_clock_nic_ts_read(priv); + if (err && net_ratelimit()) + dev_err(&priv->pdev->dev, + "%s read err %d\n", __func__, err); + +out: + return msecs_to_jiffies(GVE_NIC_TS_SYNC_INTERVAL_MS); +} + +static const struct ptp_clock_info gve_ptp_caps = { + .owner = THIS_MODULE, + .name = "gve clock", + .do_aux_work = gve_ptp_do_aux_work, +}; + +static int gve_ptp_init(struct gve_priv *priv) +{ + struct gve_ptp *ptp; + int err; + + if (!priv->nic_timestamp_supported) { + dev_dbg(&priv->pdev->dev, "Device does not support PTP\n"); + return -EOPNOTSUPP; + } + + priv->ptp = kzalloc(sizeof(*priv->ptp), GFP_KERNEL); + if (!priv->ptp) + return -ENOMEM; + + ptp = priv->ptp; + ptp->info = gve_ptp_caps; + ptp->clock = ptp_clock_register(&ptp->info, &priv->pdev->dev); + + if (IS_ERR(ptp->clock)) { + dev_err(&priv->pdev->dev, "PTP clock registration failed\n"); + err = PTR_ERR(ptp->clock); + goto free_ptp; + } + + ptp->priv = priv; + return 0; + +free_ptp: + kfree(ptp); + priv->ptp = NULL; + return err; +} + +static void gve_ptp_release(struct gve_priv *priv) +{ + struct gve_ptp *ptp = priv->ptp; + + if (!ptp) + return; + + if (ptp->clock) + ptp_clock_unregister(ptp->clock); + + kfree(ptp); + priv->ptp = NULL; +} + +int gve_init_clock(struct gve_priv *priv) +{ + int err; + + if (!priv->nic_timestamp_supported) + return 0; + + err = gve_ptp_init(priv); + if (err) + return err; + + priv->nic_ts_report = + dma_alloc_coherent(&priv->pdev->dev, + sizeof(struct gve_nic_ts_report), + &priv->nic_ts_report_bus, + GFP_KERNEL); + if (!priv->nic_ts_report) { + dev_err(&priv->pdev->dev, "%s dma alloc error\n", __func__); + err = -ENOMEM; + goto release_ptp; + } + + return 0; + +release_ptp: + gve_ptp_release(priv); + return err; +} + +void gve_teardown_clock(struct gve_priv *priv) +{ + gve_ptp_release(priv); + + if (priv->nic_ts_report) { + dma_free_coherent(&priv->pdev->dev, + sizeof(struct gve_nic_ts_report), + priv->nic_ts_report, priv->nic_ts_report_bus); + priv->nic_ts_report = NULL; + } +} diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index dcb0545baa50..0be41a0cdd15 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -437,6 +437,29 @@ static void gve_rx_skb_hash(struct sk_buff *skb, skb_set_hash(skb, le32_to_cpu(compl_desc->hash), hash_type); } +/* Expand the hardware timestamp to the full 64 bits of width, and add it to the + * skb. + * + * This algorithm works by using the passed hardware timestamp to generate a + * diff relative to the last read of the nic clock. This diff can be positive or + * negative, as it is possible that we have read the clock more recently than + * the hardware has received this packet. To detect this, we use the high bit of + * the diff, and assume that the read is more recent if the high bit is set. In + * this case we invert the process. + * + * Note that this means if the time delta between packet reception and the last + * clock read is greater than ~2 seconds, this will provide invalid results. + */ +static void gve_rx_skb_hwtstamp(struct gve_rx_ring *rx, u32 hwts) +{ + u64 last_read = READ_ONCE(rx->gve->last_sync_nic_counter); + struct sk_buff *skb = rx->ctx.skb_head; + u32 low = (u32)last_read; + s32 diff = hwts - low; + + skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(last_read + diff); +} + static void gve_rx_free_skb(struct napi_struct *napi, struct gve_rx_ring *rx) { if (!rx->ctx.skb_head) @@ -767,6 +790,9 @@ static int gve_rx_complete_skb(struct gve_rx_ring *rx, struct napi_struct *napi, if (feat & NETIF_F_RXCSUM) gve_rx_skb_csum(rx->ctx.skb_head, desc, ptype); + if (rx->gve->ts_config.rx_filter == HWTSTAMP_FILTER_ALL) + gve_rx_skb_hwtstamp(rx, le32_to_cpu(desc->ts)); + /* RSC packets must set gso_size otherwise the TCP stack will complain * that packets are larger than MTU. */ diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 9364bc2b4eb1..c0bbb12eed2e 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -2096,54 +2096,47 @@ static void e1000_get_strings(struct net_device __always_unused *netdev, } } -static int e1000_get_rxnfc(struct net_device *netdev, - struct ethtool_rxnfc *info, - u32 __always_unused *rule_locs) +static int e1000_get_rxfh_fields(struct net_device *netdev, + struct ethtool_rxfh_fields *info) { - info->data = 0; + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 mrqc; - switch (info->cmd) { - case ETHTOOL_GRXFH: { - struct e1000_adapter *adapter = netdev_priv(netdev); - struct e1000_hw *hw = &adapter->hw; - u32 mrqc; + info->data = 0; - mrqc = er32(MRQC); + mrqc = er32(MRQC); - if (!(mrqc & E1000_MRQC_RSS_FIELD_MASK)) - return 0; - - switch (info->flow_type) { - case TCP_V4_FLOW: - if (mrqc & E1000_MRQC_RSS_FIELD_IPV4_TCP) - info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; - fallthrough; - case UDP_V4_FLOW: - case SCTP_V4_FLOW: - case AH_ESP_V4_FLOW: - case IPV4_FLOW: - if (mrqc & E1000_MRQC_RSS_FIELD_IPV4) - info->data |= RXH_IP_SRC | RXH_IP_DST; - break; - case TCP_V6_FLOW: - if (mrqc & E1000_MRQC_RSS_FIELD_IPV6_TCP) - info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; - fallthrough; - case UDP_V6_FLOW: - case SCTP_V6_FLOW: - case AH_ESP_V6_FLOW: - case IPV6_FLOW: - if (mrqc & E1000_MRQC_RSS_FIELD_IPV6) - info->data |= RXH_IP_SRC | RXH_IP_DST; - break; - default: - break; - } + if (!(mrqc & E1000_MRQC_RSS_FIELD_MASK)) return 0; - } + + switch (info->flow_type) { + case TCP_V4_FLOW: + if (mrqc & E1000_MRQC_RSS_FIELD_IPV4_TCP) + info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + fallthrough; + case UDP_V4_FLOW: + case SCTP_V4_FLOW: + case AH_ESP_V4_FLOW: + case IPV4_FLOW: + if (mrqc & E1000_MRQC_RSS_FIELD_IPV4) + info->data |= RXH_IP_SRC | RXH_IP_DST; + break; + case TCP_V6_FLOW: + if (mrqc & E1000_MRQC_RSS_FIELD_IPV6_TCP) + info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + fallthrough; + case UDP_V6_FLOW: + case SCTP_V6_FLOW: + case AH_ESP_V6_FLOW: + case IPV6_FLOW: + if (mrqc & E1000_MRQC_RSS_FIELD_IPV6) + info->data |= RXH_IP_SRC | RXH_IP_DST; + break; default: - return -EOPNOTSUPP; + break; } + return 0; } static int e1000e_get_eee(struct net_device *netdev, struct ethtool_keee *edata) @@ -2352,7 +2345,7 @@ static const struct ethtool_ops e1000_ethtool_ops = { .get_sset_count = e1000e_get_sset_count, .get_coalesce = e1000_get_coalesce, .set_coalesce = e1000_set_coalesce, - .get_rxnfc = e1000_get_rxnfc, + .get_rxfh_fields = e1000_get_rxfh_fields, .get_ts_info = e1000e_get_ts_info, .get_eee = e1000e_get_eee, .set_eee = e1000e_set_eee, diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index 1bc5b6c0b897..1954a04460d1 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -691,9 +691,11 @@ static int fm10k_set_coalesce(struct net_device *dev, return 0; } -static int fm10k_get_rss_hash_opts(struct fm10k_intfc *interface, - struct ethtool_rxnfc *cmd) +static int fm10k_get_rssh_fields(struct net_device *dev, + struct ethtool_rxfh_fields *cmd) { + struct fm10k_intfc *interface = netdev_priv(dev); + cmd->data = 0; /* Report default options for RSS on fm10k */ @@ -743,9 +745,6 @@ static int fm10k_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, cmd->data = interface->num_rx_queues; ret = 0; break; - case ETHTOOL_GRXFH: - ret = fm10k_get_rss_hash_opts(interface, cmd); - break; default: break; } @@ -753,9 +752,11 @@ static int fm10k_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, return ret; } -static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface, - struct ethtool_rxnfc *nfc) +static int fm10k_set_rssh_fields(struct net_device *dev, + const struct ethtool_rxfh_fields *nfc, + struct netlink_ext_ack *extack) { + struct fm10k_intfc *interface = netdev_priv(dev); int rss_ipv4_udp = test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, interface->flags); int rss_ipv6_udp = test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, @@ -871,22 +872,6 @@ static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface, return 0; } -static int fm10k_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) -{ - struct fm10k_intfc *interface = netdev_priv(dev); - int ret = -EOPNOTSUPP; - - switch (cmd->cmd) { - case ETHTOOL_SRXFH: - ret = fm10k_set_rss_hash_opt(interface, cmd); - break; - default: - break; - } - - return ret; -} - static int fm10k_mbx_test(struct fm10k_intfc *interface, u64 *data) { struct fm10k_hw *hw = &interface->hw; @@ -1176,7 +1161,6 @@ static const struct ethtool_ops fm10k_ethtool_ops = { .get_coalesce = fm10k_get_coalesce, .set_coalesce = fm10k_set_coalesce, .get_rxnfc = fm10k_get_rxnfc, - .set_rxnfc = fm10k_set_rxnfc, .get_regs = fm10k_get_regs, .get_regs_len = fm10k_get_regs_len, .self_test = fm10k_self_test, @@ -1186,6 +1170,8 @@ static const struct ethtool_ops fm10k_ethtool_ops = { .get_rxfh_key_size = fm10k_get_rssrk_size, .get_rxfh = fm10k_get_rssh, .set_rxfh = fm10k_set_rssh, + .get_rxfh_fields = fm10k_get_rssh_fields, + .set_rxfh_fields = fm10k_set_rssh_fields, .get_channels = fm10k_get_channels, .set_channels = fm10k_set_channels, .get_ts_info = ethtool_op_get_ts_info, diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index c7f2d85eafcd..2ff17d50135c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -3139,15 +3139,12 @@ static int i40e_set_per_queue_coalesce(struct net_device *netdev, u32 queue, return __i40e_set_coalesce(netdev, ec, queue); } -/** - * i40e_get_rss_hash_opts - Get RSS hash Input Set for each flow type - * @pf: pointer to the physical function struct - * @cmd: ethtool rxnfc command - * - * Returns Success if the flow is supported, else Invalid Input. - **/ -static int i40e_get_rss_hash_opts(struct i40e_pf *pf, struct ethtool_rxnfc *cmd) +static int i40e_get_rxfh_fields(struct net_device *netdev, + struct ethtool_rxfh_fields *cmd) { + struct i40e_netdev_priv *np = netdev_priv(netdev); + struct i40e_vsi *vsi = np->vsi; + struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; u8 flow_pctype = 0; u64 i_set = 0; @@ -3545,9 +3542,6 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, cmd->data = vsi->rss_size; ret = 0; break; - case ETHTOOL_GRXFH: - ret = i40e_get_rss_hash_opts(pf, cmd); - break; case ETHTOOL_GRXCLSRLCNT: cmd->rule_cnt = pf->fdir_pf_active_filters; /* report total rule count */ @@ -3576,7 +3570,7 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, * Returns value of bits to be set per user request **/ static u64 i40e_get_rss_hash_bits(struct i40e_hw *hw, - struct ethtool_rxnfc *nfc, + const struct ethtool_rxfh_fields *nfc, u64 i_setc) { u64 i_set = i_setc; @@ -3621,15 +3615,13 @@ static u64 i40e_get_rss_hash_bits(struct i40e_hw *hw, } #define FLOW_PCTYPES_SIZE 64 -/** - * i40e_set_rss_hash_opt - Enable/Disable flow types for RSS hash - * @pf: pointer to the physical function struct - * @nfc: ethtool rxnfc command - * - * Returns Success if the flow input set is supported. - **/ -static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc) +static int i40e_set_rxfh_fields(struct net_device *netdev, + const struct ethtool_rxfh_fields *nfc, + struct netlink_ext_ack *extack) { + struct i40e_netdev_priv *np = netdev_priv(netdev); + struct i40e_vsi *vsi = np->vsi; + struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; u64 hena = (u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(0)) | ((u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(1)) << 32); @@ -4964,13 +4956,9 @@ static int i40e_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; - struct i40e_pf *pf = vsi->back; int ret = -EOPNOTSUPP; switch (cmd->cmd) { - case ETHTOOL_SRXFH: - ret = i40e_set_rss_hash_opt(pf, cmd); - break; case ETHTOOL_SRXCLSRLINS: ret = i40e_add_fdir_ethtool(vsi, cmd); break; @@ -5846,6 +5834,8 @@ static const struct ethtool_ops i40e_ethtool_ops = { .get_rxfh_indir_size = i40e_get_rxfh_indir_size, .get_rxfh = i40e_get_rxfh, .set_rxfh = i40e_set_rxfh, + .get_rxfh_fields = i40e_get_rxfh_fields, + .set_rxfh_fields = i40e_set_rxfh_fields, .get_channels = i40e_get_channels, .set_channels = i40e_set_channels, .get_module_info = i40e_get_module_info, diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 1156a5b3055c..3b4f59d978a5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -15895,7 +15895,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) 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 | diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 2b2b315205b5..05d72be3fe80 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -1307,14 +1307,7 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx return iavf_fdir_del_fltr(adapter, false, fsp->location); } -/** - * iavf_adv_rss_parse_hdrs - parses headers from RSS hash input - * @cmd: ethtool rxnfc command - * - * This function parses the rxnfc command and returns intended - * header types for RSS configuration - */ -static u32 iavf_adv_rss_parse_hdrs(struct ethtool_rxnfc *cmd) +static u32 iavf_adv_rss_parse_hdrs(const struct ethtool_rxfh_fields *cmd) { u32 hdrs = IAVF_ADV_RSS_FLOW_SEG_HDR_NONE; @@ -1350,15 +1343,8 @@ static u32 iavf_adv_rss_parse_hdrs(struct ethtool_rxnfc *cmd) return hdrs; } -/** - * iavf_adv_rss_parse_hash_flds - parses hash fields from RSS hash input - * @cmd: ethtool rxnfc command - * @symm: true if Symmetric Topelitz is set - * - * This function parses the rxnfc command and returns intended hash fields for - * RSS configuration - */ -static u64 iavf_adv_rss_parse_hash_flds(struct ethtool_rxnfc *cmd, bool symm) +static u64 +iavf_adv_rss_parse_hash_flds(const struct ethtool_rxfh_fields *cmd, bool symm) { u64 hfld = IAVF_ADV_RSS_HASH_INVALID; @@ -1416,17 +1402,12 @@ static u64 iavf_adv_rss_parse_hash_flds(struct ethtool_rxnfc *cmd, bool symm) return hfld; } -/** - * iavf_set_adv_rss_hash_opt - Enable/Disable flow types for RSS hash - * @adapter: pointer to the VF adapter structure - * @cmd: ethtool rxnfc command - * - * Returns Success if the flow input set is supported. - */ static int -iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter, - struct ethtool_rxnfc *cmd) +iavf_set_rxfh_fields(struct net_device *netdev, + const struct ethtool_rxfh_fields *cmd, + struct netlink_ext_ack *extack) { + struct iavf_adapter *adapter = netdev_priv(netdev); struct iavf_adv_rss *rss_old, *rss_new; bool rss_new_add = false; bool symm = false; @@ -1493,17 +1474,10 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter, return err; } -/** - * iavf_get_adv_rss_hash_opt - Retrieve hash fields for a given flow-type - * @adapter: pointer to the VF adapter structure - * @cmd: ethtool rxnfc command - * - * Returns Success if the flow input set is supported. - */ static int -iavf_get_adv_rss_hash_opt(struct iavf_adapter *adapter, - struct ethtool_rxnfc *cmd) +iavf_get_rxfh_fields(struct net_device *netdev, struct ethtool_rxfh_fields *cmd) { + struct iavf_adapter *adapter = netdev_priv(netdev); struct iavf_adv_rss *rss; u64 hash_flds; u32 hdrs; @@ -1568,9 +1542,6 @@ static int iavf_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd) case ETHTOOL_SRXCLSRLDEL: ret = iavf_del_fdir_ethtool(adapter, cmd); break; - case ETHTOOL_SRXFH: - ret = iavf_set_adv_rss_hash_opt(adapter, cmd); - break; default: break; } @@ -1612,9 +1583,6 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, case ETHTOOL_GRXCLSRLALL: ret = iavf_get_fdir_fltr_ids(adapter, cmd, (u32 *)rule_locs); break; - case ETHTOOL_GRXFH: - ret = iavf_get_adv_rss_hash_opt(adapter, cmd); - break; default: break; } @@ -1812,6 +1780,8 @@ static const struct ethtool_ops iavf_ethtool_ops = { .get_rxfh_indir_size = iavf_get_rxfh_indir_size, .get_rxfh = iavf_get_rxfh, .set_rxfh = iavf_set_rxfh, + .get_rxfh_fields = iavf_get_rxfh_fields, + .set_rxfh_fields = iavf_set_rxfh_fields, .get_channels = iavf_get_channels, .set_channels = iavf_set_channels, .get_rxfh_key_size = iavf_get_rxfh_key_size, diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index 23e786b9793d..aaf70c625655 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -723,7 +723,7 @@ static void iavf_clean_rx_ring(struct iavf_ring *rx_ring) for (u32 i = rx_ring->next_to_clean; i != rx_ring->next_to_use; ) { const struct libeth_fqe *rx_fqes = &rx_ring->rx_fqes[i]; - page_pool_put_full_page(rx_ring->pp, rx_fqes->page, false); + libeth_rx_recycle_slow(rx_fqes->netmem); if (unlikely(++i == rx_ring->count)) i = 0; @@ -1197,10 +1197,11 @@ static void iavf_add_rx_frag(struct sk_buff *skb, const struct libeth_fqe *rx_buffer, unsigned int size) { - u32 hr = rx_buffer->page->pp->p.offset; + u32 hr = netmem_get_pp(rx_buffer->netmem)->p.offset; - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, - rx_buffer->offset + hr, size, rx_buffer->truesize); + skb_add_rx_frag_netmem(skb, skb_shinfo(skb)->nr_frags, + rx_buffer->netmem, rx_buffer->offset + hr, + size, rx_buffer->truesize); } /** @@ -1214,12 +1215,13 @@ static void iavf_add_rx_frag(struct sk_buff *skb, static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer, unsigned int size) { - u32 hr = rx_buffer->page->pp->p.offset; + struct page *buf_page = __netmem_to_page(rx_buffer->netmem); + u32 hr = buf_page->pp->p.offset; struct sk_buff *skb; void *va; /* prefetch first cache line of first page */ - va = page_address(rx_buffer->page) + rx_buffer->offset; + va = page_address(buf_page) + rx_buffer->offset; net_prefetch(va + hr); /* build an skb around the page buffer */ diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index bdee499f991a..0ae7387e0599 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -2272,6 +2272,22 @@ struct ice_aqc_get_pkg_info_resp { struct ice_aqc_get_pkg_info pkg_info[]; }; +#define ICE_CGU_INPUT_PHASE_OFFSET_BYTES 6 + +struct ice_cgu_input_measure { + u8 phase_offset[ICE_CGU_INPUT_PHASE_OFFSET_BYTES]; + __le32 freq; +} __packed __aligned(sizeof(__le16)); + +#define ICE_AQC_GET_CGU_IN_MEAS_DPLL_IDX_M ICE_M(0xf, 0) + +/* Get CGU input measure command response data structure (indirect 0x0C59) */ +struct ice_aqc_get_cgu_input_measure { + u8 dpll_idx_opt; + u8 length; + u8 rsvd[6]; +}; + #define ICE_AQC_GET_CGU_MAX_PHASE_ADJ GENMASK(30, 0) /* Get CGU abilities command response data structure (indirect 0x0C61) */ @@ -2721,6 +2737,7 @@ struct ice_aq_desc { struct ice_aqc_add_get_update_free_vsi vsi_cmd; struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res; struct ice_aqc_download_pkg download_pkg; + struct ice_aqc_get_cgu_input_measure get_cgu_input_measure; struct ice_aqc_set_cgu_input_config set_cgu_input_config; struct ice_aqc_get_cgu_input_config get_cgu_input_config; struct ice_aqc_set_cgu_output_config set_cgu_output_config; @@ -2772,6 +2789,8 @@ enum ice_aq_err { ICE_AQ_RC_OK = 0, /* Success */ ICE_AQ_RC_EPERM = 1, /* Operation not permitted */ ICE_AQ_RC_ENOENT = 2, /* No such element */ + ICE_AQ_RC_ESRCH = 3, /* Bad opcode */ + ICE_AQ_RC_EAGAIN = 8, /* Try again */ ICE_AQ_RC_ENOMEM = 9, /* Out of memory */ ICE_AQ_RC_EBUSY = 12, /* Device or resource busy */ ICE_AQ_RC_EEXIST = 13, /* Object already exists */ @@ -2927,6 +2946,7 @@ enum ice_adminq_opc { ice_aqc_opc_get_pkg_info_list = 0x0C43, /* 1588/SyncE commands/events */ + ice_aqc_opc_get_cgu_input_measure = 0x0C59, ice_aqc_opc_get_cgu_abilities = 0x0C61, ice_aqc_opc_set_cgu_input_config = 0x0C62, ice_aqc_opc_get_cgu_input_config = 0x0C63, diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 4fedf0181c4e..48ff515d7c61 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -4971,6 +4971,32 @@ ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid, } /** + * ice_aq_get_cgu_input_pin_measure - get input pin signal measurements + * @hw: pointer to the HW struct + * @dpll_idx: index of dpll to be measured + * @meas: array to be filled with results + * @meas_num: max number of results array can hold + * + * Get CGU measurements (0x0C59) of phase and frequency offsets for input + * pins on given dpll. + * + * Return: 0 on success or negative value on failure. + */ +int ice_aq_get_cgu_input_pin_measure(struct ice_hw *hw, u8 dpll_idx, + struct ice_cgu_input_measure *meas, + u16 meas_num) +{ + struct ice_aqc_get_cgu_input_measure *cmd; + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_input_measure); + cmd = &desc.params.get_cgu_input_measure; + cmd->dpll_idx_opt = dpll_idx & ICE_AQC_GET_CGU_IN_MEAS_DPLL_IDX_M; + + return ice_aq_send_cmd(hw, &desc, meas, meas_num * sizeof(*meas), NULL); +} + +/** * ice_aq_get_cgu_abilities - get cgu abilities * @hw: pointer to the HW struct * @abilities: CGU abilities diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 64c530b39191..c70f56d897dc 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -229,6 +229,9 @@ void ice_replay_post(struct ice_hw *hw); struct ice_q_ctx * ice_get_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 q_handle); int ice_sbq_rw_reg(struct ice_hw *hw, struct ice_sbq_msg_input *in, u16 flag); +int ice_aq_get_cgu_input_pin_measure(struct ice_hw *hw, u8 dpll_idx, + struct ice_cgu_input_measure *meas, + u16 meas_num); int ice_aq_get_cgu_abilities(struct ice_hw *hw, struct ice_aqc_get_cgu_abilities *abilities); diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index 9fc50bb3f35a..d6190d9e32ba 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -12,6 +12,8 @@ #define ICE_DPLL_PIN_ESYNC_PULSE_HIGH_PERCENT 25 #define ICE_DPLL_PIN_GEN_RCLK_FREQ 1953125 #define ICE_DPLL_PIN_PRIO_OUTPUT 0xff +#define ICE_DPLL_INPUT_REF_NUM 10 +#define ICE_DPLL_PHASE_OFFSET_PERIOD 2 #define ICE_DPLL_SW_PIN_INPUT_BASE_SFP 4 #define ICE_DPLL_SW_PIN_INPUT_BASE_QSFP 6 #define ICE_DPLL_SW_PIN_OUTPUT_BASE 0 @@ -793,6 +795,67 @@ static int ice_dpll_mode_get(const struct dpll_device *dpll, void *dpll_priv, } /** + * ice_dpll_phase_offset_monitor_set - set phase offset monitor state + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @state: feature state to be set + * @extack: error reporting + * + * Dpll subsystem callback. Enable/disable phase offset monitor feature of dpll. + * + * Context: Acquires and releases pf->dplls.lock + * Return: 0 - success + */ +static int ice_dpll_phase_offset_monitor_set(const struct dpll_device *dpll, + void *dpll_priv, + enum dpll_feature_state state, + struct netlink_ext_ack *extack) +{ + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + mutex_lock(&pf->dplls.lock); + if (state == DPLL_FEATURE_STATE_ENABLE) + d->phase_offset_monitor_period = ICE_DPLL_PHASE_OFFSET_PERIOD; + else + d->phase_offset_monitor_period = 0; + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** + * ice_dpll_phase_offset_monitor_get - get phase offset monitor state + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @state: on success holds current state of phase offset monitor + * @extack: error reporting + * + * Dpll subsystem callback. Provides current state of phase offset monitor + * features on dpll device. + * + * Context: Acquires and releases pf->dplls.lock + * Return: 0 - success + */ +static int ice_dpll_phase_offset_monitor_get(const struct dpll_device *dpll, + void *dpll_priv, + enum dpll_feature_state *state, + struct netlink_ext_ack *extack) +{ + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + mutex_lock(&pf->dplls.lock); + if (d->phase_offset_monitor_period) + *state = DPLL_FEATURE_STATE_ENABLE; + else + *state = DPLL_FEATURE_STATE_DISABLE; + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** * ice_dpll_pin_state_set - set pin's state on dpll * @pin: pointer to a pin * @pin_priv: private data pointer passed on pin registration @@ -1757,6 +1820,8 @@ ice_dpll_phase_offset_get(const struct dpll_pin *pin, void *pin_priv, if (d->active_input == pin || (p->input && d->active_input == p->input->pin)) *phase_offset = d->phase_offset * ICE_DPLL_PHASE_OFFSET_FACTOR; + else if (d->phase_offset_monitor_period) + *phase_offset = p->phase_offset * ICE_DPLL_PHASE_OFFSET_FACTOR; else *phase_offset = 0; mutex_unlock(&pf->dplls.lock); @@ -2216,6 +2281,13 @@ static const struct dpll_device_ops ice_dpll_ops = { .mode_get = ice_dpll_mode_get, }; +static const struct dpll_device_ops ice_dpll_pom_ops = { + .lock_status_get = ice_dpll_lock_status_get, + .mode_get = ice_dpll_mode_get, + .phase_offset_monitor_set = ice_dpll_phase_offset_monitor_set, + .phase_offset_monitor_get = ice_dpll_phase_offset_monitor_get, +}; + /** * ice_generate_clock_id - generates unique clock_id for registering dpll. * @pf: board private structure @@ -2261,6 +2333,110 @@ static void ice_dpll_notify_changes(struct ice_dpll *d) } /** + * ice_dpll_is_pps_phase_monitor - check if dpll capable of phase offset monitor + * @pf: pf private structure + * + * Check if firmware is capable of supporting admin command to provide + * phase offset monitoring on all the input pins on PPS dpll. + * + * Returns: + * * true - PPS dpll phase offset monitoring is supported + * * false - PPS dpll phase offset monitoring is not supported + */ +static bool ice_dpll_is_pps_phase_monitor(struct ice_pf *pf) +{ + struct ice_cgu_input_measure meas[ICE_DPLL_INPUT_REF_NUM]; + int ret = ice_aq_get_cgu_input_pin_measure(&pf->hw, DPLL_TYPE_PPS, meas, + ARRAY_SIZE(meas)); + + if (ret && pf->hw.adminq.sq_last_status == ICE_AQ_RC_ESRCH) + return false; + + return true; +} + +/** + * ice_dpll_pins_notify_mask - notify dpll subsystem about bulk pin changes + * @pins: array of ice_dpll_pin pointers registered within dpll subsystem + * @pin_num: number of pins + * @phase_offset_ntf_mask: bitmask of pin indexes to notify + * + * Iterate over array of pins and call dpll subsystem pin notify if + * corresponding pin index within bitmask is set. + * + * Context: Must be called while pf->dplls.lock is released. + */ +static void ice_dpll_pins_notify_mask(struct ice_dpll_pin *pins, + u8 pin_num, + u32 phase_offset_ntf_mask) +{ + int i = 0; + + for (i = 0; i < pin_num; i++) + if (phase_offset_ntf_mask & (1 << i)) + dpll_pin_change_ntf(pins[i].pin); +} + +/** + * ice_dpll_pps_update_phase_offsets - update phase offset measurements + * @pf: pf private structure + * @phase_offset_pins_updated: returns mask of updated input pin indexes + * + * Read phase offset measurements for PPS dpll device and store values in + * input pins array. On success phase_offset_pins_updated - fills bitmask of + * updated input pin indexes, pins shall be notified. + * + * Context: Shall be called with pf->dplls.lock being locked. + * Returns: + * * 0 - success or no data available + * * negative - AQ failure + */ +static int ice_dpll_pps_update_phase_offsets(struct ice_pf *pf, + u32 *phase_offset_pins_updated) +{ + struct ice_cgu_input_measure meas[ICE_DPLL_INPUT_REF_NUM]; + struct ice_dpll_pin *p; + s64 phase_offset, tmp; + int i, j, ret; + + *phase_offset_pins_updated = 0; + ret = ice_aq_get_cgu_input_pin_measure(&pf->hw, DPLL_TYPE_PPS, meas, + ARRAY_SIZE(meas)); + if (ret && pf->hw.adminq.sq_last_status == ICE_AQ_RC_EAGAIN) { + return 0; + } else if (ret) { + dev_err(ice_pf_to_dev(pf), + "failed to get input pin measurements dpll=%d, ret=%d %s\n", + DPLL_TYPE_PPS, ret, + ice_aq_str(pf->hw.adminq.sq_last_status)); + return ret; + } + for (i = 0; i < pf->dplls.num_inputs; i++) { + p = &pf->dplls.inputs[i]; + phase_offset = 0; + for (j = 0; j < ICE_CGU_INPUT_PHASE_OFFSET_BYTES; j++) { + tmp = meas[i].phase_offset[j]; +#ifdef __LITTLE_ENDIAN + phase_offset += tmp << 8 * j; +#else + phase_offset += tmp << 8 * + (ICE_CGU_INPUT_PHASE_OFFSET_BYTES - 1 - j); +#endif + } + phase_offset = sign_extend64(phase_offset, 47); + if (p->phase_offset != phase_offset) { + dev_dbg(ice_pf_to_dev(pf), + "phase offset changed for pin:%d old:%llx, new:%llx\n", + p->idx, p->phase_offset, phase_offset); + p->phase_offset = phase_offset; + *phase_offset_pins_updated |= (1 << i); + } + } + + return 0; +} + +/** * ice_dpll_update_state - update dpll state * @pf: pf private structure * @d: pointer to queried dpll device @@ -2346,14 +2522,19 @@ static void ice_dpll_periodic_work(struct kthread_work *work) struct ice_pf *pf = container_of(d, struct ice_pf, dplls); struct ice_dpll *de = &pf->dplls.eec; struct ice_dpll *dp = &pf->dplls.pps; + u32 phase_offset_ntf = 0; int ret = 0; if (ice_is_reset_in_progress(pf->state)) goto resched; mutex_lock(&pf->dplls.lock); + d->periodic_counter++; ret = ice_dpll_update_state(pf, de, false); if (!ret) ret = ice_dpll_update_state(pf, dp, false); + if (!ret && dp->phase_offset_monitor_period && + d->periodic_counter % dp->phase_offset_monitor_period == 0) + ret = ice_dpll_pps_update_phase_offsets(pf, &phase_offset_ntf); if (ret) { d->cgu_state_acq_err_num++; /* stop rescheduling this worker */ @@ -2368,6 +2549,9 @@ static void ice_dpll_periodic_work(struct kthread_work *work) mutex_unlock(&pf->dplls.lock); ice_dpll_notify_changes(de); ice_dpll_notify_changes(dp); + if (phase_offset_ntf) + ice_dpll_pins_notify_mask(d->inputs, d->num_inputs, + phase_offset_ntf); resched: /* Run twice a second or reschedule if update failed */ @@ -2782,7 +2966,7 @@ static void ice_dpll_deinit_dpll(struct ice_pf *pf, struct ice_dpll *d, bool cgu) { if (cgu) - dpll_device_unregister(d->dpll, &ice_dpll_ops, d); + dpll_device_unregister(d->dpll, d->ops, d); dpll_device_put(d->dpll); } @@ -2816,12 +3000,17 @@ ice_dpll_init_dpll(struct ice_pf *pf, struct ice_dpll *d, bool cgu, } d->pf = pf; if (cgu) { + const struct dpll_device_ops *ops = &ice_dpll_ops; + + if (type == DPLL_TYPE_PPS && ice_dpll_is_pps_phase_monitor(pf)) + ops = &ice_dpll_pom_ops; ice_dpll_update_state(pf, d, true); - ret = dpll_device_register(d->dpll, type, &ice_dpll_ops, d); + ret = dpll_device_register(d->dpll, type, ops, d); if (ret) { dpll_device_put(d->dpll); return ret; } + d->ops = ops; } return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.h b/drivers/net/ethernet/intel/ice/ice_dpll.h index 10cd12d70972..a5a5b61c5115 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.h +++ b/drivers/net/ethernet/intel/ice/ice_dpll.h @@ -31,6 +31,7 @@ enum ice_dpll_pin_sw { * @prop: pin properties * @freq: current frequency of a pin * @phase_adjust: current phase adjust value + * @phase_offset: monitored phase offset value */ struct ice_dpll_pin { struct dpll_pin *pin; @@ -46,6 +47,7 @@ struct ice_dpll_pin { struct ice_dpll_pin *input; struct ice_dpll_pin *output; enum dpll_pin_direction direction; + s64 phase_offset; u8 status; bool active; bool hidden; @@ -64,8 +66,10 @@ struct ice_dpll_pin { * @input_prio: priorities of each input * @dpll_state: current dpll sync state * @prev_dpll_state: last dpll sync state + * @phase_offset_monitor_period: period for phase offset monitor read frequency * @active_input: pointer to active input pin * @prev_input: pointer to previous active input pin + * @ops: holds the registered ops */ struct ice_dpll { struct dpll_device *dpll; @@ -81,8 +85,10 @@ struct ice_dpll { enum dpll_lock_status dpll_state; enum dpll_lock_status prev_dpll_state; enum dpll_mode mode; + u32 phase_offset_monitor_period; struct dpll_pin *active_input; struct dpll_pin *prev_input; + const struct dpll_device_ops *ops; }; /** ice_dplls - store info required for CCU (clock controlling unit) @@ -101,6 +107,7 @@ struct ice_dpll { * @clock_id: clock_id of dplls * @input_phase_adj_max: max phase adjust value for an input pins * @output_phase_adj_max: max phase adjust value for an output pins + * @periodic_counter: counter of periodic work executions */ struct ice_dplls { struct kthread_worker *kworker; @@ -121,6 +128,7 @@ struct ice_dplls { u64 clock_id; s32 input_phase_adj_max; s32 output_phase_adj_max; + u32 periodic_counter; bool generic; }; diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 5863a86482f5..ea7e8b879b48 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -2797,14 +2797,7 @@ done: return err; } -/** - * ice_parse_hdrs - parses headers from RSS hash input - * @nfc: ethtool rxnfc command - * - * This function parses the rxnfc command and returns intended - * header types for RSS configuration - */ -static u32 ice_parse_hdrs(struct ethtool_rxnfc *nfc) +static u32 ice_parse_hdrs(const struct ethtool_rxfh_fields *nfc) { u32 hdrs = ICE_FLOW_SEG_HDR_NONE; @@ -2869,15 +2862,7 @@ static u32 ice_parse_hdrs(struct ethtool_rxnfc *nfc) return hdrs; } -/** - * ice_parse_hash_flds - parses hash fields from RSS hash input - * @nfc: ethtool rxnfc command - * @symm: true if Symmetric Topelitz is set - * - * This function parses the rxnfc command and returns intended - * hash fields for RSS configuration - */ -static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc, bool symm) +static u64 ice_parse_hash_flds(const struct ethtool_rxfh_fields *nfc, bool symm) { u64 hfld = ICE_HASH_INVALID; @@ -2974,16 +2959,13 @@ static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc, bool symm) return hfld; } -/** - * ice_set_rss_hash_opt - Enable/Disable flow types for RSS hash - * @vsi: the VSI being configured - * @nfc: ethtool rxnfc command - * - * Returns Success if the flow input set is supported. - */ static int -ice_set_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc) +ice_set_rxfh_fields(struct net_device *netdev, + const struct ethtool_rxfh_fields *nfc, + struct netlink_ext_ack *extack) { + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; struct ice_rss_hash_cfg cfg; struct device *dev; @@ -3029,14 +3011,11 @@ ice_set_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc) return 0; } -/** - * ice_get_rss_hash_opt - Retrieve hash fields for a given flow-type - * @vsi: the VSI being configured - * @nfc: ethtool rxnfc command - */ -static void -ice_get_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc) +static int +ice_get_rxfh_fields(struct net_device *netdev, struct ethtool_rxfh_fields *nfc) { + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; struct device *dev; u64 hash_flds; @@ -3049,21 +3028,21 @@ ice_get_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc) if (ice_is_safe_mode(pf)) { dev_dbg(dev, "Advanced RSS disabled. Package download failed, vsi num = %d\n", vsi->vsi_num); - return; + return 0; } hdrs = ice_parse_hdrs(nfc); if (hdrs == ICE_FLOW_SEG_HDR_NONE) { dev_dbg(dev, "Header type is not valid, vsi num = %d\n", vsi->vsi_num); - return; + return 0; } hash_flds = ice_get_rss_cfg(&pf->hw, vsi->idx, hdrs, &symm); if (hash_flds == ICE_HASH_INVALID) { dev_dbg(dev, "No hash fields found for the given header type, vsi num = %d\n", vsi->vsi_num); - return; + return 0; } if (hash_flds & ICE_FLOW_HASH_FLD_IPV4_SA || @@ -3090,6 +3069,8 @@ ice_get_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc) hash_flds & ICE_FLOW_HASH_FLD_GTPU_UP_TEID || hash_flds & ICE_FLOW_HASH_FLD_GTPU_DWN_TEID) nfc->data |= (u64)RXH_GTP_TEID; + + return 0; } /** @@ -3109,8 +3090,6 @@ static int ice_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd) return ice_add_fdir_ethtool(vsi, cmd); case ETHTOOL_SRXCLSRLDEL: return ice_del_fdir_ethtool(vsi, cmd); - case ETHTOOL_SRXFH: - return ice_set_rss_hash_opt(vsi, cmd); default: break; } @@ -3153,10 +3132,6 @@ ice_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, case ETHTOOL_GRXCLSRLALL: ret = ice_get_fdir_fltr_ids(hw, cmd, (u32 *)rule_locs); break; - case ETHTOOL_GRXFH: - ice_get_rss_hash_opt(vsi, cmd); - ret = 0; - break; default: break; } @@ -4816,6 +4791,8 @@ static const struct ethtool_ops ice_ethtool_ops = { .get_rxfh_indir_size = ice_get_rxfh_indir_size, .get_rxfh = ice_get_rxfh, .set_rxfh = ice_set_rxfh, + .get_rxfh_fields = ice_get_rxfh_fields, + .set_rxfh_fields = ice_set_rxfh_fields, .get_channels = ice_get_channels, .set_channels = ice_set_channels, .get_ts_info = ice_get_ts_info, diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 7a4b302d356b..f8ef80069e3d 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4767,7 +4767,6 @@ int ice_init_dev(struct ice_pf *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; if (pf->hw.tnl.valid_count[TNL_VXLAN]) { pf->hw.udp_tunnel_nic.tables[0].n_entries = @@ -7936,6 +7935,10 @@ const char *ice_aq_str(enum ice_aq_err aq_err) return "ICE_AQ_RC_EPERM"; case ICE_AQ_RC_ENOENT: return "ICE_AQ_RC_ENOENT"; + case ICE_AQ_RC_ESRCH: + return "ICE_AQ_RC_ESRCH"; + case ICE_AQ_RC_EAGAIN: + return "ICE_AQ_RC_EAGAIN"; case ICE_AQ_RC_ENOMEM: return "ICE_AQ_RC_ENOMEM"; case ICE_AQ_RC_EBUSY: diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c index 993c354aa27a..555879b1248d 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c @@ -1006,7 +1006,7 @@ static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget) break; skip_data: - rx_buf->page = NULL; + rx_buf->netmem = 0; IDPF_SINGLEQ_BUMP_RING_IDX(rx_q, ntc); cleaned_count++; diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 5cf440e09d0a..cef9dfb877e8 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -383,12 +383,12 @@ err_out: */ static void idpf_rx_page_rel(struct libeth_fqe *rx_buf) { - if (unlikely(!rx_buf->page)) + if (unlikely(!rx_buf->netmem)) return; - page_pool_put_full_page(rx_buf->page->pp, rx_buf->page, false); + libeth_rx_recycle_slow(rx_buf->netmem); - rx_buf->page = NULL; + rx_buf->netmem = 0; rx_buf->offset = 0; } @@ -3240,10 +3240,10 @@ idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb, void idpf_rx_add_frag(struct idpf_rx_buf *rx_buf, struct sk_buff *skb, unsigned int size) { - u32 hr = rx_buf->page->pp->p.offset; + u32 hr = netmem_get_pp(rx_buf->netmem)->p.offset; - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buf->page, - rx_buf->offset + hr, size, rx_buf->truesize); + skb_add_rx_frag_netmem(skb, skb_shinfo(skb)->nr_frags, rx_buf->netmem, + rx_buf->offset + hr, size, rx_buf->truesize); } /** @@ -3266,16 +3266,20 @@ static u32 idpf_rx_hsplit_wa(const struct libeth_fqe *hdr, struct libeth_fqe *buf, u32 data_len) { u32 copy = data_len <= L1_CACHE_BYTES ? data_len : ETH_HLEN; + struct page *hdr_page, *buf_page; const void *src; void *dst; - if (!libeth_rx_sync_for_cpu(buf, copy)) + if (unlikely(netmem_is_net_iov(buf->netmem)) || + !libeth_rx_sync_for_cpu(buf, copy)) return 0; - dst = page_address(hdr->page) + hdr->offset + hdr->page->pp->p.offset; - src = page_address(buf->page) + buf->offset + buf->page->pp->p.offset; - memcpy(dst, src, LARGEST_ALIGN(copy)); + hdr_page = __netmem_to_page(hdr->netmem); + buf_page = __netmem_to_page(buf->netmem); + dst = page_address(hdr_page) + hdr->offset + hdr_page->pp->p.offset; + src = page_address(buf_page) + buf->offset + buf_page->pp->p.offset; + memcpy(dst, src, LARGEST_ALIGN(copy)); buf->offset += copy; return copy; @@ -3291,11 +3295,12 @@ static u32 idpf_rx_hsplit_wa(const struct libeth_fqe *hdr, */ struct sk_buff *idpf_rx_build_skb(const struct libeth_fqe *buf, u32 size) { - u32 hr = buf->page->pp->p.offset; + struct page *buf_page = __netmem_to_page(buf->netmem); + u32 hr = buf_page->pp->p.offset; struct sk_buff *skb; void *va; - va = page_address(buf->page) + buf->offset; + va = page_address(buf_page) + buf->offset; prefetch(va + hr); skb = napi_build_skb(va, buf->truesize); @@ -3429,7 +3434,8 @@ static int idpf_rx_splitq_clean(struct idpf_rx_queue *rxq, int budget) if (unlikely(!hdr_len && !skb)) { hdr_len = idpf_rx_hsplit_wa(hdr, rx_buf, pkt_len); - pkt_len -= hdr_len; + /* If failed, drop both buffers by setting len to 0 */ + pkt_len -= hdr_len ? : pkt_len; u64_stats_update_begin(&rxq->stats_sync); u64_stats_inc(&rxq->q_stats.hsplit_buf_ovf); @@ -3446,7 +3452,7 @@ static int idpf_rx_splitq_clean(struct idpf_rx_queue *rxq, int budget) u64_stats_update_end(&rxq->stats_sync); } - hdr->page = NULL; + hdr->netmem = 0; payload: if (!libeth_rx_sync_for_cpu(rx_buf, pkt_len)) @@ -3462,7 +3468,7 @@ payload: break; skip_data: - rx_buf->page = NULL; + rx_buf->netmem = 0; idpf_rx_post_buf_refill(refillq, buf_id); IDPF_RX_BUMP_NTC(rxq, ntc); diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index ca6ccbc13954..92ef33459aec 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2500,9 +2500,11 @@ static int igb_get_ethtool_nfc_all(struct igb_adapter *adapter, return 0; } -static int igb_get_rss_hash_opts(struct igb_adapter *adapter, - struct ethtool_rxnfc *cmd) +static int igb_get_rxfh_fields(struct net_device *dev, + struct ethtool_rxfh_fields *cmd) { + struct igb_adapter *adapter = netdev_priv(dev); + cmd->data = 0; /* Report default options for RSS on igb */ @@ -2563,9 +2565,6 @@ static int igb_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, case ETHTOOL_GRXCLSRLALL: ret = igb_get_ethtool_nfc_all(adapter, cmd, rule_locs); break; - case ETHTOOL_GRXFH: - ret = igb_get_rss_hash_opts(adapter, cmd); - break; default: break; } @@ -2575,9 +2574,11 @@ static int igb_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, #define UDP_RSS_FLAGS (IGB_FLAG_RSS_FIELD_IPV4_UDP | \ IGB_FLAG_RSS_FIELD_IPV6_UDP) -static int igb_set_rss_hash_opt(struct igb_adapter *adapter, - struct ethtool_rxnfc *nfc) +static int igb_set_rxfh_fields(struct net_device *dev, + const struct ethtool_rxfh_fields *nfc, + struct netlink_ext_ack *extack) { + struct igb_adapter *adapter = netdev_priv(dev); u32 flags = adapter->flags; /* RSS does not support anything other than hashing @@ -3005,9 +3006,6 @@ static int igb_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) int ret = -EOPNOTSUPP; switch (cmd->cmd) { - case ETHTOOL_SRXFH: - ret = igb_set_rss_hash_opt(adapter, cmd); - break; case ETHTOOL_SRXCLSRLINS: ret = igb_add_ethtool_nfc_entry(adapter, cmd); break; @@ -3485,6 +3483,8 @@ static const struct ethtool_ops igb_ethtool_ops = { .get_rxfh_indir_size = igb_get_rxfh_indir_size, .get_rxfh = igb_get_rxfh, .set_rxfh = igb_set_rxfh, + .get_rxfh_fields = igb_get_rxfh_fields, + .set_rxfh_fields = igb_set_rxfh_fields, .get_channels = igb_get_channels, .set_channels = igb_set_channels, .get_priv_flags = igb_get_priv_flags, diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 859a15e4ccba..1525ae25fd3e 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -43,6 +43,7 @@ void igc_ethtool_set_ops(struct net_device *); struct igc_fpe_t { struct ethtool_mmsv mmsv; u32 tx_min_frag_size; + bool tx_enabled; }; enum igc_mac_filter_type { @@ -163,6 +164,7 @@ struct igc_ring { bool launchtime_enable; /* true if LaunchTime is enabled */ ktime_t last_tx_cycle; /* end of the cycle with a launchtime transmission */ ktime_t last_ff_cycle; /* Last cycle with an active first flag */ + bool preemptible; /* True if preemptible queue, false if express queue */ u32 start_time; u32 end_time; @@ -395,6 +397,7 @@ extern char igc_driver_name[]; #define IGC_FLAG_TSN_QBV_ENABLED BIT(17) #define IGC_FLAG_TSN_QAV_ENABLED BIT(18) #define IGC_FLAG_TSN_PREEMPT_ENABLED BIT(19) +#define IGC_FLAG_TSN_REVERSE_TXQ_PRIO BIT(20) #define IGC_FLAG_TSN_ANY_ENABLED \ (IGC_FLAG_TSN_QBV_ENABLED | IGC_FLAG_TSN_QAV_ENABLED | \ @@ -485,12 +488,30 @@ static inline u32 igc_rss_type(const union igc_adv_rx_desc *rx_desc) * descriptors until either it has this many to write back, or the * ITR timer expires. */ -#define IGC_RX_PTHRESH 8 -#define IGC_RX_HTHRESH 8 -#define IGC_TX_PTHRESH 8 -#define IGC_TX_HTHRESH 1 -#define IGC_RX_WTHRESH 4 -#define IGC_TX_WTHRESH 16 +#define IGC_RXDCTL_PTHRESH 8 +#define IGC_RXDCTL_HTHRESH 8 +#define IGC_RXDCTL_WTHRESH 4 +/* Ena specific Rx Queue */ +#define IGC_RXDCTL_QUEUE_ENABLE 0x02000000 +/* Receive Software Flush */ +#define IGC_RXDCTL_SWFLUSH 0x04000000 + +#define IGC_TXDCTL_PTHRESH_MASK GENMASK(4, 0) +#define IGC_TXDCTL_HTHRESH_MASK GENMASK(12, 8) +#define IGC_TXDCTL_WTHRESH_MASK GENMASK(20, 16) +#define IGC_TXDCTL_QUEUE_ENABLE_MASK GENMASK(25, 25) +#define IGC_TXDCTL_SWFLUSH_MASK GENMASK(26, 26) +#define IGC_TXDCTL_PRIORITY_MASK GENMASK(27, 27) + +#define IGC_TXDCTL_PTHRESH(x) FIELD_PREP(IGC_TXDCTL_PTHRESH_MASK, (x)) +#define IGC_TXDCTL_HTHRESH(x) FIELD_PREP(IGC_TXDCTL_HTHRESH_MASK, (x)) +#define IGC_TXDCTL_WTHRESH(x) FIELD_PREP(IGC_TXDCTL_WTHRESH_MASK, (x)) +/* Ena specific Tx Queue */ +#define IGC_TXDCTL_QUEUE_ENABLE FIELD_PREP(IGC_TXDCTL_QUEUE_ENABLE_MASK, 1) +/* Transmit Software Flush */ +#define IGC_TXDCTL_SWFLUSH FIELD_PREP(IGC_TXDCTL_SWFLUSH_MASK, 1) +#define IGC_TXDCTL_PRIORITY(x) FIELD_PREP(IGC_TXDCTL_PRIORITY_MASK, (x)) +#define IGC_TXDCTL_PRIORITY_HIGH IGC_TXDCTL_PRIORITY(1) #define IGC_RX_DMA_ATTR \ (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h index 6320eabb72fe..eaf17cd031c3 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.h +++ b/drivers/net/ethernet/intel/igc/igc_base.h @@ -86,14 +86,6 @@ union igc_adv_rx_desc { } wb; /* writeback */ }; -/* Additional Transmit Descriptor Control definitions */ -#define IGC_TXDCTL_QUEUE_ENABLE 0x02000000 /* Ena specific Tx Queue */ -#define IGC_TXDCTL_SWFLUSH 0x04000000 /* Transmit Software Flush */ - -/* Additional Receive Descriptor Control definitions */ -#define IGC_RXDCTL_QUEUE_ENABLE 0x02000000 /* Ena specific Rx Queue */ -#define IGC_RXDCTL_SWFLUSH 0x04000000 /* Receive Software Flush */ - /* SRRCTL bit definitions */ #define IGC_SRRCTL_BSIZEPKT_MASK GENMASK(6, 0) #define IGC_SRRCTL_BSIZEPKT(x) FIELD_PREP(IGC_SRRCTL_BSIZEPKT_MASK, \ diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 7189dfc389ad..86b346687196 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -588,6 +588,7 @@ #define IGC_TXQCTL_QUEUE_MODE_LAUNCHT 0x00000001 #define IGC_TXQCTL_STRICT_CYCLE 0x00000002 #define IGC_TXQCTL_STRICT_END 0x00000004 +#define IGC_TXQCTL_PREEMPTIBLE 0x00000008 #define IGC_TXQCTL_QAV_SEL_MASK 0x000000C0 #define IGC_TXQCTL_QAV_SEL_CBS0 0x00000080 #define IGC_TXQCTL_QAV_SEL_CBS1 0x000000C0 diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 3fc1eded9605..a7f397b58cd6 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -122,9 +122,11 @@ static const char igc_gstrings_test[][ETH_GSTRING_LEN] = { #define IGC_STATS_LEN \ (IGC_GLOBAL_STATS_LEN + IGC_NETDEV_STATS_LEN + IGC_QUEUE_STATS_LEN) +#define IGC_PRIV_FLAGS_LEGACY_RX BIT(0) +#define IGC_PRIV_FLAGS_REVERSE_TSN_TXQ_PRIO BIT(1) static const char igc_priv_flags_strings[][ETH_GSTRING_LEN] = { -#define IGC_PRIV_FLAGS_LEGACY_RX BIT(0) "legacy-rx", + "reverse-tsn-txq-prio", }; #define IGC_PRIV_FLAGS_STR_LEN ARRAY_SIZE(igc_priv_flags_strings) @@ -1045,9 +1047,11 @@ static int igc_ethtool_get_nfc_rules(struct igc_adapter *adapter, return 0; } -static int igc_ethtool_get_rss_hash_opts(struct igc_adapter *adapter, - struct ethtool_rxnfc *cmd) +static int igc_ethtool_get_rxfh_fields(struct net_device *dev, + struct ethtool_rxfh_fields *cmd) { + struct igc_adapter *adapter = netdev_priv(dev); + cmd->data = 0; /* Report default options for RSS on igc */ @@ -1103,8 +1107,6 @@ static int igc_ethtool_get_rxnfc(struct net_device *dev, return igc_ethtool_get_nfc_rule(adapter, cmd); case ETHTOOL_GRXCLSRLALL: return igc_ethtool_get_nfc_rules(adapter, cmd, rule_locs); - case ETHTOOL_GRXFH: - return igc_ethtool_get_rss_hash_opts(adapter, cmd); default: return -EOPNOTSUPP; } @@ -1112,9 +1114,11 @@ static int igc_ethtool_get_rxnfc(struct net_device *dev, #define UDP_RSS_FLAGS (IGC_FLAG_RSS_FIELD_IPV4_UDP | \ IGC_FLAG_RSS_FIELD_IPV6_UDP) -static int igc_ethtool_set_rss_hash_opt(struct igc_adapter *adapter, - struct ethtool_rxnfc *nfc) +static int igc_ethtool_set_rxfh_fields(struct net_device *dev, + const struct ethtool_rxfh_fields *nfc, + struct netlink_ext_ack *extack) { + struct igc_adapter *adapter = netdev_priv(dev); u32 flags = adapter->flags; /* RSS does not support anything other than hashing @@ -1425,8 +1429,6 @@ static int igc_ethtool_set_rxnfc(struct net_device *dev, struct igc_adapter *adapter = netdev_priv(dev); switch (cmd->cmd) { - case ETHTOOL_SRXFH: - return igc_ethtool_set_rss_hash_opt(adapter, cmd); case ETHTOOL_SRXCLSRLINS: return igc_ethtool_add_nfc_rule(adapter, cmd); case ETHTOOL_SRXCLSRLDEL: @@ -1600,6 +1602,9 @@ static u32 igc_ethtool_get_priv_flags(struct net_device *netdev) if (adapter->flags & IGC_FLAG_RX_LEGACY) priv_flags |= IGC_PRIV_FLAGS_LEGACY_RX; + if (adapter->flags & IGC_FLAG_TSN_REVERSE_TXQ_PRIO) + priv_flags |= IGC_PRIV_FLAGS_REVERSE_TSN_TXQ_PRIO; + return priv_flags; } @@ -1608,10 +1613,13 @@ static int igc_ethtool_set_priv_flags(struct net_device *netdev, u32 priv_flags) struct igc_adapter *adapter = netdev_priv(netdev); unsigned int flags = adapter->flags; - flags &= ~IGC_FLAG_RX_LEGACY; + flags &= ~(IGC_FLAG_RX_LEGACY | IGC_FLAG_TSN_REVERSE_TXQ_PRIO); if (priv_flags & IGC_PRIV_FLAGS_LEGACY_RX) flags |= IGC_FLAG_RX_LEGACY; + if (priv_flags & IGC_PRIV_FLAGS_REVERSE_TSN_TXQ_PRIO) + flags |= IGC_FLAG_TSN_REVERSE_TXQ_PRIO; + if (flags != adapter->flags) { adapter->flags = flags; @@ -2144,6 +2152,8 @@ static const struct ethtool_ops igc_ethtool_ops = { .get_rxfh_indir_size = igc_ethtool_get_rxfh_indir_size, .get_rxfh = igc_ethtool_get_rxfh, .set_rxfh = igc_ethtool_set_rxfh, + .get_rxfh_fields = igc_ethtool_get_rxfh_fields, + .set_rxfh_fields = igc_ethtool_set_rxfh_fields, .get_ts_info = igc_ethtool_get_ts_info, .get_channels = igc_ethtool_get_channels, .set_channels = igc_ethtool_set_channels, diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 686793c539f2..2e12915b42a9 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -683,9 +683,9 @@ static void igc_configure_rx_ring(struct igc_adapter *adapter, wr32(IGC_SRRCTL(reg_idx), srrctl); - rxdctl |= IGC_RX_PTHRESH; - rxdctl |= IGC_RX_HTHRESH << 8; - rxdctl |= IGC_RX_WTHRESH << 16; + rxdctl |= IGC_RXDCTL_PTHRESH; + rxdctl |= IGC_RXDCTL_HTHRESH << 8; + rxdctl |= IGC_RXDCTL_WTHRESH << 16; /* initialize rx_buffer_info */ memset(ring->rx_buffer_info, 0, @@ -749,11 +749,9 @@ static void igc_configure_tx_ring(struct igc_adapter *adapter, wr32(IGC_TDH(reg_idx), 0); writel(0, ring->tail); - txdctl |= IGC_TX_PTHRESH; - txdctl |= IGC_TX_HTHRESH << 8; - txdctl |= IGC_TX_WTHRESH << 16; + txdctl |= IGC_TXDCTL_PTHRESH(8) | IGC_TXDCTL_HTHRESH(1) | + IGC_TXDCTL_WTHRESH(16) | IGC_TXDCTL_QUEUE_ENABLE; - txdctl |= IGC_TXDCTL_QUEUE_ENABLE; wr32(IGC_TXDCTL(reg_idx), txdctl); } @@ -1687,6 +1685,15 @@ done: first->tx_flags = tx_flags; first->protocol = protocol; + /* For preemptible queue, manually pad the skb so that HW includes + * padding bytes in mCRC calculation + */ + if (tx_ring->preemptible && skb->len < ETH_ZLEN) { + if (skb_padto(skb, ETH_ZLEN)) + goto out_drop; + skb_put(skb, ETH_ZLEN - skb->len); + } + tso = igc_tso(tx_ring, first, launch_time, first_flag, &hdr_len); if (tso < 0) goto out_drop; @@ -6423,6 +6430,7 @@ static int igc_qbv_clear_schedule(struct igc_adapter *adapter) ring->start_time = 0; ring->end_time = NSEC_PER_SEC; ring->max_sdu = 0; + ring->preemptible = false; } spin_lock_irqsave(&adapter->qbv_tx_lock, flags); @@ -6488,9 +6496,12 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, if (!validate_schedule(adapter, qopt)) return -EINVAL; - /* preemptible isn't supported yet */ - if (qopt->mqprio.preemptible_tcs) - return -EOPNOTSUPP; + if (qopt->mqprio.preemptible_tcs && + !(adapter->flags & IGC_FLAG_TSN_REVERSE_TXQ_PRIO)) { + NL_SET_ERR_MSG_MOD(qopt->extack, + "reverse-tsn-txq-prio private flag must be enabled before setting preemptible tc"); + return -ENODEV; + } igc_ptp_read(adapter, &now); @@ -6583,6 +6594,8 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, ring->max_sdu = 0; } + igc_fpe_save_preempt_queue(adapter, &qopt->mqprio); + return 0; } @@ -6702,7 +6715,8 @@ static int igc_tc_query_caps(struct igc_adapter *adapter, case TC_SETUP_QDISC_TAPRIO: { struct tc_taprio_caps *caps = base->caps; - caps->broken_mqprio = true; + if (!(adapter->flags & IGC_FLAG_TSN_REVERSE_TXQ_PRIO)) + caps->broken_mqprio = true; if (hw->mac.type == igc_i225) { caps->supports_queue_max_sdu = true; @@ -6728,6 +6742,20 @@ static void igc_save_mqprio_params(struct igc_adapter *adapter, u8 num_tc, adapter->queue_per_tc[i] = offset[i]; } +static bool +igc_tsn_is_tc_to_queue_priority_ordered(struct tc_mqprio_qopt_offload *mqprio) +{ + int num_tc = mqprio->qopt.num_tc; + int i; + + for (i = 1; i < num_tc; i++) { + if (mqprio->qopt.offset[i - 1] > mqprio->qopt.offset[i]) + return false; + } + + return true; +} + static int igc_tsn_enable_mqprio(struct igc_adapter *adapter, struct tc_mqprio_qopt_offload *mqprio) { @@ -6739,6 +6767,7 @@ static int igc_tsn_enable_mqprio(struct igc_adapter *adapter, if (!mqprio->qopt.num_tc) { adapter->strict_priority_enable = false; + igc_fpe_clear_preempt_queue(adapter); netdev_reset_tc(adapter->netdev); goto apply; } @@ -6760,10 +6789,9 @@ static int igc_tsn_enable_mqprio(struct igc_adapter *adapter, } } - /* Preemption is not supported yet. */ - if (mqprio->preemptible_tcs) { + if (!igc_tsn_is_tc_to_queue_priority_ordered(mqprio)) { NL_SET_ERR_MSG_MOD(mqprio->extack, - "Preemption is not supported yet"); + "tc to queue mapping must preserve increasing priority (higher tc -> higher queue)"); return -EOPNOTSUPP; } @@ -6786,6 +6814,7 @@ static int igc_tsn_enable_mqprio(struct igc_adapter *adapter, adapter->queue_per_tc[i] = i; mqprio->qopt.hw = TC_MQPRIO_HW_OFFLOAD_TCS; + igc_fpe_save_preempt_queue(adapter, mqprio); apply: return igc_tsn_offload_apply(adapter); diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index f22cc4d4f459..b23b9ca451a7 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -13,6 +13,13 @@ #define TX_MAX_FRAG_SIZE (TX_MIN_FRAG_SIZE * \ (MAX_MULTPLIER_TX_MIN_FRAG + 1)) +enum tx_queue { + TX_QUEUE_0 = 0, + TX_QUEUE_1, + TX_QUEUE_2, + TX_QUEUE_3, +}; + DEFINE_STATIC_KEY_FALSE(igc_fpe_enabled); static int igc_fpe_init_smd_frame(struct igc_ring *ring, @@ -109,6 +116,18 @@ static int igc_fpe_xmit_smd_frame(struct igc_adapter *adapter, return err; } +static void igc_fpe_configure_tx(struct ethtool_mmsv *mmsv, bool tx_enable) +{ + struct igc_fpe_t *fpe = container_of(mmsv, struct igc_fpe_t, mmsv); + struct igc_adapter *adapter; + + adapter = container_of(fpe, struct igc_adapter, fpe); + adapter->fpe.tx_enabled = tx_enable; + + /* Update config since tx_enabled affects preemptible queue configuration */ + igc_tsn_offload_apply(adapter); +} + static void igc_fpe_send_mpacket(struct ethtool_mmsv *mmsv, enum ethtool_mpacket type) { @@ -130,15 +149,59 @@ static void igc_fpe_send_mpacket(struct ethtool_mmsv *mmsv, } static const struct ethtool_mmsv_ops igc_mmsv_ops = { + .configure_tx = igc_fpe_configure_tx, .send_mpacket = igc_fpe_send_mpacket, }; void igc_fpe_init(struct igc_adapter *adapter) { adapter->fpe.tx_min_frag_size = TX_MIN_FRAG_SIZE; + adapter->fpe.tx_enabled = false; ethtool_mmsv_init(&adapter->fpe.mmsv, adapter->netdev, &igc_mmsv_ops); } +void igc_fpe_clear_preempt_queue(struct igc_adapter *adapter) +{ + for (int i = 0; i < adapter->num_tx_queues; i++) { + struct igc_ring *tx_ring = adapter->tx_ring[i]; + + tx_ring->preemptible = false; + } +} + +static u32 igc_fpe_map_preempt_tc_to_queue(const struct igc_adapter *adapter, + unsigned long preemptible_tcs) +{ + struct net_device *dev = adapter->netdev; + u32 i, queue = 0; + + for (i = 0; i < dev->num_tc; i++) { + u32 offset, count; + + if (!(preemptible_tcs & BIT(i))) + continue; + + offset = dev->tc_to_txq[i].offset; + count = dev->tc_to_txq[i].count; + queue |= GENMASK(offset + count - 1, offset); + } + + return queue; +} + +void igc_fpe_save_preempt_queue(struct igc_adapter *adapter, + const struct tc_mqprio_qopt_offload *mqprio) +{ + u32 preemptible_queue = igc_fpe_map_preempt_tc_to_queue(adapter, + mqprio->preemptible_tcs); + + for (int i = 0; i < adapter->num_tx_queues; i++) { + struct igc_ring *tx_ring = adapter->tx_ring[i]; + + tx_ring->preemptible = !!(preemptible_queue & BIT(i)); + } +} + static bool is_any_launchtime(struct igc_adapter *adapter) { int i; @@ -238,7 +301,7 @@ bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter) adapter->taprio_offload_enable; } -static void igc_tsn_tx_arb(struct igc_adapter *adapter, u16 *queue_per_tc) +static void igc_tsn_tx_arb(struct igc_adapter *adapter, bool reverse_prio) { struct igc_hw *hw = &adapter->hw; u32 txarb; @@ -250,10 +313,17 @@ static void igc_tsn_tx_arb(struct igc_adapter *adapter, u16 *queue_per_tc) IGC_TXARB_TXQ_PRIO_2_MASK | IGC_TXARB_TXQ_PRIO_3_MASK); - txarb |= IGC_TXARB_TXQ_PRIO_0(queue_per_tc[3]); - txarb |= IGC_TXARB_TXQ_PRIO_1(queue_per_tc[2]); - txarb |= IGC_TXARB_TXQ_PRIO_2(queue_per_tc[1]); - txarb |= IGC_TXARB_TXQ_PRIO_3(queue_per_tc[0]); + if (reverse_prio) { + txarb |= IGC_TXARB_TXQ_PRIO_0(TX_QUEUE_3); + txarb |= IGC_TXARB_TXQ_PRIO_1(TX_QUEUE_2); + txarb |= IGC_TXARB_TXQ_PRIO_2(TX_QUEUE_1); + txarb |= IGC_TXARB_TXQ_PRIO_3(TX_QUEUE_0); + } else { + txarb |= IGC_TXARB_TXQ_PRIO_0(TX_QUEUE_0); + txarb |= IGC_TXARB_TXQ_PRIO_1(TX_QUEUE_1); + txarb |= IGC_TXARB_TXQ_PRIO_2(TX_QUEUE_2); + txarb |= IGC_TXARB_TXQ_PRIO_3(TX_QUEUE_3); + } wr32(IGC_TXARB, txarb); } @@ -286,7 +356,6 @@ static void igc_tsn_set_rxpbsize(struct igc_adapter *adapter, */ static int igc_tsn_disable_offload(struct igc_adapter *adapter) { - u16 queue_per_tc[4] = { 3, 2, 1, 0 }; struct igc_hw *hw = &adapter->hw; u32 tqavctrl; int i; @@ -308,9 +377,16 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) wr32(IGC_TQAVCTRL, tqavctrl); for (i = 0; i < adapter->num_tx_queues; i++) { + int reg_idx = adapter->tx_ring[i]->reg_idx; + u32 txdctl; + wr32(IGC_TXQCTL(i), 0); wr32(IGC_STQT(i), 0); wr32(IGC_ENDQT(i), NSEC_PER_SEC); + + txdctl = rd32(IGC_TXDCTL(reg_idx)); + txdctl &= ~IGC_TXDCTL_PRIORITY_HIGH; + wr32(IGC_TXDCTL(reg_idx), txdctl); } wr32(IGC_QBVCYCLET_S, 0); @@ -319,7 +395,7 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) /* Restore the default Tx arbitration: Priority 0 has the highest * priority and is assigned to queue 0 and so on and so forth. */ - igc_tsn_tx_arb(adapter, queue_per_tc); + igc_tsn_tx_arb(adapter, false); adapter->flags &= ~IGC_FLAG_TSN_QBV_ENABLED; @@ -385,15 +461,13 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) if (igc_is_device_id_i226(hw)) igc_tsn_set_retx_qbvfullthreshold(adapter); - if (adapter->strict_priority_enable) { - /* Configure queue priorities according to the user provided - * mapping. - */ - igc_tsn_tx_arb(adapter, adapter->queue_per_tc); - } + if (adapter->strict_priority_enable || + adapter->flags & IGC_FLAG_TSN_REVERSE_TXQ_PRIO) + igc_tsn_tx_arb(adapter, true); for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; + u32 txdctl = rd32(IGC_TXDCTL(ring->reg_idx)); u32 txqctl = 0; u16 cbs_value; u32 tqavcc; @@ -427,6 +501,22 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) if (ring->launchtime_enable) txqctl |= IGC_TXQCTL_QUEUE_MODE_LAUNCHT; + if (!adapter->fpe.tx_enabled) { + /* fpe inactive: clear both flags */ + txqctl &= ~IGC_TXQCTL_PREEMPTIBLE; + txdctl &= ~IGC_TXDCTL_PRIORITY_HIGH; + } else if (ring->preemptible) { + /* fpe active + preemptible: enable preemptible queue + set low priority */ + txqctl |= IGC_TXQCTL_PREEMPTIBLE; + txdctl &= ~IGC_TXDCTL_PRIORITY_HIGH; + } else { + /* fpe active + express: enable express queue + set high priority */ + txqctl &= ~IGC_TXQCTL_PREEMPTIBLE; + txdctl |= IGC_TXDCTL_PRIORITY_HIGH; + } + + wr32(IGC_TXDCTL(ring->reg_idx), txdctl); + /* Skip configuring CBS for Q2 and Q3 */ if (i > 1) goto skip_cbs; diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h index c2a77229207b..a95b893459d7 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.h +++ b/drivers/net/ethernet/intel/igc/igc_tsn.h @@ -4,6 +4,8 @@ #ifndef _IGC_TSN_H_ #define _IGC_TSN_H_ +#include <net/pkt_sched.h> + #define IGC_RX_MIN_FRAG_SIZE 60 #define SMD_FRAME_SIZE 60 @@ -15,6 +17,9 @@ enum igc_txd_popts_type { DECLARE_STATIC_KEY_FALSE(igc_fpe_enabled); void igc_fpe_init(struct igc_adapter *adapter); +void igc_fpe_clear_preempt_queue(struct igc_adapter *adapter); +void igc_fpe_save_preempt_queue(struct igc_adapter *adapter, + const struct tc_mqprio_qopt_offload *mqprio); u32 igc_fpe_get_supported_frag_size(u32 frag_size); int igc_tsn_offload_apply(struct igc_adapter *adapter); int igc_tsn_reset(struct igc_adapter *adapter); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 1dc1c6e611a4..25c3a09ad7f1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -2753,9 +2753,11 @@ static int ixgbe_get_ethtool_fdir_all(struct ixgbe_adapter *adapter, return 0; } -static int ixgbe_get_rss_hash_opts(struct ixgbe_adapter *adapter, - struct ethtool_rxnfc *cmd) +static int ixgbe_get_rxfh_fields(struct net_device *dev, + struct ethtool_rxfh_fields *cmd) { + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); + cmd->data = 0; /* Report default options for RSS on ixgbe */ @@ -2825,9 +2827,6 @@ static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, case ETHTOOL_GRXCLSRLALL: ret = ixgbe_get_ethtool_fdir_all(adapter, cmd, rule_locs); break; - case ETHTOOL_GRXFH: - ret = ixgbe_get_rss_hash_opts(adapter, cmd); - break; default: break; } @@ -3079,9 +3078,11 @@ static int ixgbe_del_ethtool_fdir_entry(struct ixgbe_adapter *adapter, #define UDP_RSS_FLAGS (IXGBE_FLAG2_RSS_FIELD_IPV4_UDP | \ IXGBE_FLAG2_RSS_FIELD_IPV6_UDP) -static int ixgbe_set_rss_hash_opt(struct ixgbe_adapter *adapter, - struct ethtool_rxnfc *nfc) +static int ixgbe_set_rxfh_fields(struct net_device *dev, + const struct ethtool_rxfh_fields *nfc, + struct netlink_ext_ack *extack) { + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); u32 flags2 = adapter->flags2; /* @@ -3204,9 +3205,6 @@ static int ixgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) case ETHTOOL_SRXCLSRLDEL: ret = ixgbe_del_ethtool_fdir_entry(adapter, cmd); break; - case ETHTOOL_SRXFH: - ret = ixgbe_set_rss_hash_opt(adapter, cmd); - break; default: break; } @@ -3751,6 +3749,8 @@ static const struct ethtool_ops ixgbe_ethtool_ops = { .get_rxfh_key_size = ixgbe_get_rxfh_key_size, .get_rxfh = ixgbe_get_rxfh, .set_rxfh = ixgbe_set_rxfh, + .get_rxfh_fields = ixgbe_get_rxfh_fields, + .set_rxfh_fields = ixgbe_set_rxfh_fields, .get_eee = ixgbe_get_eee, .set_eee = ixgbe_set_eee, .get_channels = ixgbe_get_channels, @@ -3797,6 +3797,8 @@ static const struct ethtool_ops ixgbe_ethtool_ops_e610 = { .get_rxfh_key_size = ixgbe_get_rxfh_key_size, .get_rxfh = ixgbe_get_rxfh, .set_rxfh = ixgbe_set_rxfh, + .get_rxfh_fields = ixgbe_get_rxfh_fields, + .set_rxfh_fields = ixgbe_set_rxfh_fields, .get_eee = ixgbe_get_eee, .set_eee = ixgbe_set_eee, .get_channels = ixgbe_get_channels, diff --git a/drivers/net/ethernet/intel/libeth/Kconfig b/drivers/net/ethernet/intel/libeth/Kconfig index 480293b71dbc..2445b979c499 100644 --- a/drivers/net/ethernet/intel/libeth/Kconfig +++ b/drivers/net/ethernet/intel/libeth/Kconfig @@ -1,9 +1,15 @@ # SPDX-License-Identifier: GPL-2.0-only -# Copyright (C) 2024 Intel Corporation +# Copyright (C) 2024-2025 Intel Corporation config LIBETH - tristate + tristate "Common Ethernet library (libeth)" if COMPILE_TEST select PAGE_POOL help libeth is a common library containing routines shared between several drivers, but not yet promoted to the generic kernel API. + +config LIBETH_XDP + tristate "Common XDP library (libeth_xdp)" if COMPILE_TEST + select LIBETH + help + XDP and XSk helpers based on libeth hotpath management. diff --git a/drivers/net/ethernet/intel/libeth/Makefile b/drivers/net/ethernet/intel/libeth/Makefile index 52492b081132..350bc0b38bad 100644 --- a/drivers/net/ethernet/intel/libeth/Makefile +++ b/drivers/net/ethernet/intel/libeth/Makefile @@ -1,6 +1,12 @@ # SPDX-License-Identifier: GPL-2.0-only -# Copyright (C) 2024 Intel Corporation +# Copyright (C) 2024-2025 Intel Corporation obj-$(CONFIG_LIBETH) += libeth.o libeth-y := rx.o +libeth-y += tx.o + +obj-$(CONFIG_LIBETH_XDP) += libeth_xdp.o + +libeth_xdp-y += xdp.o +libeth_xdp-y += xsk.o diff --git a/drivers/net/ethernet/intel/libeth/priv.h b/drivers/net/ethernet/intel/libeth/priv.h new file mode 100644 index 000000000000..9b811d31015c --- /dev/null +++ b/drivers/net/ethernet/intel/libeth/priv.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2025 Intel Corporation */ + +#ifndef __LIBETH_PRIV_H +#define __LIBETH_PRIV_H + +#include <linux/types.h> + +/* XDP */ + +enum xdp_action; +struct libeth_xdp_buff; +struct libeth_xdp_tx_frame; +struct skb_shared_info; +struct xdp_frame_bulk; + +extern const struct xsk_tx_metadata_ops libeth_xsktmo_slow; + +void libeth_xsk_tx_return_bulk(const struct libeth_xdp_tx_frame *bq, + u32 count); +u32 libeth_xsk_prog_exception(struct libeth_xdp_buff *xdp, enum xdp_action act, + int ret); + +struct libeth_xdp_ops { + void (*bulk)(const struct skb_shared_info *sinfo, + struct xdp_frame_bulk *bq, bool frags); + void (*xsk)(struct libeth_xdp_buff *xdp); +}; + +void libeth_attach_xdp(const struct libeth_xdp_ops *ops); + +static inline void libeth_detach_xdp(void) +{ + libeth_attach_xdp(NULL); +} + +#endif /* __LIBETH_PRIV_H */ diff --git a/drivers/net/ethernet/intel/libeth/rx.c b/drivers/net/ethernet/intel/libeth/rx.c index 66d1d23b8ad2..62521a1f4ec9 100644 --- a/drivers/net/ethernet/intel/libeth/rx.c +++ b/drivers/net/ethernet/intel/libeth/rx.c @@ -1,5 +1,9 @@ // SPDX-License-Identifier: GPL-2.0-only -/* Copyright (C) 2024 Intel Corporation */ +/* Copyright (C) 2024-2025 Intel Corporation */ + +#define DEFAULT_SYMBOL_NAMESPACE "LIBETH" + +#include <linux/export.h> #include <net/libeth/rx.h> @@ -68,7 +72,7 @@ static u32 libeth_rx_hw_len_truesize(const struct page_pool_params *pp, static bool libeth_rx_page_pool_params(struct libeth_fq *fq, struct page_pool_params *pp) { - pp->offset = LIBETH_SKB_HEADROOM; + pp->offset = fq->xdp ? LIBETH_XDP_HEADROOM : LIBETH_SKB_HEADROOM; /* HW-writeable / syncable length per one page */ pp->max_len = LIBETH_RX_PAGE_LEN(pp->offset); @@ -155,11 +159,12 @@ int libeth_rx_fq_create(struct libeth_fq *fq, struct napi_struct *napi) .dev = napi->dev->dev.parent, .netdev = napi->dev, .napi = napi, - .dma_dir = DMA_FROM_DEVICE, }; struct libeth_fqe *fqes; struct page_pool *pool; - bool ret; + int ret; + + pp.dma_dir = fq->xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; if (!fq->hsplit) ret = libeth_rx_page_pool_params(fq, &pp); @@ -173,20 +178,28 @@ int libeth_rx_fq_create(struct libeth_fq *fq, struct napi_struct *napi) return PTR_ERR(pool); fqes = kvcalloc_node(fq->count, sizeof(*fqes), GFP_KERNEL, fq->nid); - if (!fqes) + if (!fqes) { + ret = -ENOMEM; goto err_buf; + } + + ret = xdp_reg_page_pool(pool); + if (ret) + goto err_mem; fq->fqes = fqes; fq->pp = pool; return 0; +err_mem: + kvfree(fqes); err_buf: page_pool_destroy(pool); - return -ENOMEM; + return ret; } -EXPORT_SYMBOL_NS_GPL(libeth_rx_fq_create, "LIBETH"); +EXPORT_SYMBOL_GPL(libeth_rx_fq_create); /** * libeth_rx_fq_destroy - destroy a &page_pool created by libeth @@ -194,22 +207,23 @@ EXPORT_SYMBOL_NS_GPL(libeth_rx_fq_create, "LIBETH"); */ void libeth_rx_fq_destroy(struct libeth_fq *fq) { + xdp_unreg_page_pool(fq->pp); kvfree(fq->fqes); page_pool_destroy(fq->pp); } -EXPORT_SYMBOL_NS_GPL(libeth_rx_fq_destroy, "LIBETH"); +EXPORT_SYMBOL_GPL(libeth_rx_fq_destroy); /** - * libeth_rx_recycle_slow - recycle a libeth page from the NAPI context - * @page: page to recycle + * libeth_rx_recycle_slow - recycle libeth netmem + * @netmem: network memory to recycle * * To be used on exceptions or rare cases not requiring fast inline recycling. */ -void libeth_rx_recycle_slow(struct page *page) +void __cold libeth_rx_recycle_slow(netmem_ref netmem) { - page_pool_recycle_direct(page->pp, page); + page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, false); } -EXPORT_SYMBOL_NS_GPL(libeth_rx_recycle_slow, "LIBETH"); +EXPORT_SYMBOL_GPL(libeth_rx_recycle_slow); /* Converting abstract packet type numbers into a software structure with * the packet parameters to do O(1) lookup on Rx. @@ -251,7 +265,7 @@ void libeth_rx_pt_gen_hash_type(struct libeth_rx_pt *pt) pt->hash_type |= libeth_rx_pt_xdp_iprot[pt->inner_prot]; pt->hash_type |= libeth_rx_pt_xdp_pl[pt->payload_layer]; } -EXPORT_SYMBOL_NS_GPL(libeth_rx_pt_gen_hash_type, "LIBETH"); +EXPORT_SYMBOL_GPL(libeth_rx_pt_gen_hash_type); /* Module */ diff --git a/drivers/net/ethernet/intel/libeth/tx.c b/drivers/net/ethernet/intel/libeth/tx.c new file mode 100644 index 000000000000..e0167f43d2a8 --- /dev/null +++ b/drivers/net/ethernet/intel/libeth/tx.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2025 Intel Corporation */ + +#define DEFAULT_SYMBOL_NAMESPACE "LIBETH" + +#include <net/libeth/xdp.h> + +#include "priv.h" + +/* Tx buffer completion */ + +DEFINE_STATIC_CALL_NULL(bulk, libeth_xdp_return_buff_bulk); +DEFINE_STATIC_CALL_NULL(xsk, libeth_xsk_buff_free_slow); + +/** + * libeth_tx_complete_any - perform Tx completion for one SQE of any type + * @sqe: Tx buffer to complete + * @cp: polling params + * + * Can be used to complete both regular and XDP SQEs, for example when + * destroying queues. + * When libeth_xdp is not loaded, XDPSQEs won't be handled. + */ +void libeth_tx_complete_any(struct libeth_sqe *sqe, struct libeth_cq_pp *cp) +{ + if (sqe->type >= __LIBETH_SQE_XDP_START) + __libeth_xdp_complete_tx(sqe, cp, static_call(bulk), + static_call(xsk)); + else + libeth_tx_complete(sqe, cp); +} +EXPORT_SYMBOL_GPL(libeth_tx_complete_any); + +/* Module */ + +void libeth_attach_xdp(const struct libeth_xdp_ops *ops) +{ + static_call_update(bulk, ops ? ops->bulk : NULL); + static_call_update(xsk, ops ? ops->xsk : NULL); +} +EXPORT_SYMBOL_GPL(libeth_attach_xdp); diff --git a/drivers/net/ethernet/intel/libeth/xdp.c b/drivers/net/ethernet/intel/libeth/xdp.c new file mode 100644 index 000000000000..d4ac027d9584 --- /dev/null +++ b/drivers/net/ethernet/intel/libeth/xdp.c @@ -0,0 +1,451 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2025 Intel Corporation */ + +#define DEFAULT_SYMBOL_NAMESPACE "LIBETH_XDP" + +#include <linux/export.h> + +#include <net/libeth/xdp.h> + +#include "priv.h" + +/* XDPSQ sharing */ + +DEFINE_STATIC_KEY_FALSE(libeth_xdpsq_share); +EXPORT_SYMBOL_GPL(libeth_xdpsq_share); + +void __libeth_xdpsq_get(struct libeth_xdpsq_lock *lock, + const struct net_device *dev) +{ + bool warn; + + spin_lock_init(&lock->lock); + lock->share = true; + + warn = !static_key_enabled(&libeth_xdpsq_share); + static_branch_inc(&libeth_xdpsq_share); + + if (warn && net_ratelimit()) + netdev_warn(dev, "XDPSQ sharing enabled, possible XDP Tx slowdown\n"); +} +EXPORT_SYMBOL_GPL(__libeth_xdpsq_get); + +void __libeth_xdpsq_put(struct libeth_xdpsq_lock *lock, + const struct net_device *dev) +{ + static_branch_dec(&libeth_xdpsq_share); + + if (!static_key_enabled(&libeth_xdpsq_share) && net_ratelimit()) + netdev_notice(dev, "XDPSQ sharing disabled\n"); + + lock->share = false; +} +EXPORT_SYMBOL_GPL(__libeth_xdpsq_put); + +void __acquires(&lock->lock) +__libeth_xdpsq_lock(struct libeth_xdpsq_lock *lock) +{ + spin_lock(&lock->lock); +} +EXPORT_SYMBOL_GPL(__libeth_xdpsq_lock); + +void __releases(&lock->lock) +__libeth_xdpsq_unlock(struct libeth_xdpsq_lock *lock) +{ + spin_unlock(&lock->lock); +} +EXPORT_SYMBOL_GPL(__libeth_xdpsq_unlock); + +/* XDPSQ clean-up timers */ + +/** + * libeth_xdpsq_init_timer - initialize an XDPSQ clean-up timer + * @timer: timer to initialize + * @xdpsq: queue this timer belongs to + * @lock: corresponding XDPSQ lock + * @poll: queue polling/completion function + * + * XDPSQ clean-up timers must be set up before using at the queue configuration + * time. Set the required pointers and the cleaning callback. + */ +void libeth_xdpsq_init_timer(struct libeth_xdpsq_timer *timer, void *xdpsq, + struct libeth_xdpsq_lock *lock, + void (*poll)(struct work_struct *work)) +{ + timer->xdpsq = xdpsq; + timer->lock = lock; + + INIT_DELAYED_WORK(&timer->dwork, poll); +} +EXPORT_SYMBOL_GPL(libeth_xdpsq_init_timer); + +/* ``XDP_TX`` bulking */ + +static void __cold +libeth_xdp_tx_return_one(const struct libeth_xdp_tx_frame *frm) +{ + if (frm->len_fl & LIBETH_XDP_TX_MULTI) + libeth_xdp_return_frags(frm->data + frm->soff, true); + + libeth_xdp_return_va(frm->data, true); +} + +static void __cold +libeth_xdp_tx_return_bulk(const struct libeth_xdp_tx_frame *bq, u32 count) +{ + for (u32 i = 0; i < count; i++) { + const struct libeth_xdp_tx_frame *frm = &bq[i]; + + if (!(frm->len_fl & LIBETH_XDP_TX_FIRST)) + continue; + + libeth_xdp_tx_return_one(frm); + } +} + +static void __cold libeth_trace_xdp_exception(const struct net_device *dev, + const struct bpf_prog *prog, + u32 act) +{ + trace_xdp_exception(dev, prog, act); +} + +/** + * libeth_xdp_tx_exception - handle Tx exceptions of XDP frames + * @bq: XDP Tx frame bulk + * @sent: number of frames sent successfully (from this bulk) + * @flags: internal libeth_xdp flags (XSk, .ndo_xdp_xmit etc.) + * + * Cold helper used by __libeth_xdp_tx_flush_bulk(), do not call directly. + * Reports XDP Tx exceptions, frees the frames that won't be sent or adjust + * the Tx bulk to try again later. + */ +void __cold libeth_xdp_tx_exception(struct libeth_xdp_tx_bulk *bq, u32 sent, + u32 flags) +{ + const struct libeth_xdp_tx_frame *pos = &bq->bulk[sent]; + u32 left = bq->count - sent; + + if (!(flags & LIBETH_XDP_TX_NDO)) + libeth_trace_xdp_exception(bq->dev, bq->prog, XDP_TX); + + if (!(flags & LIBETH_XDP_TX_DROP)) { + memmove(bq->bulk, pos, left * sizeof(*bq->bulk)); + bq->count = left; + + return; + } + + if (flags & LIBETH_XDP_TX_XSK) + libeth_xsk_tx_return_bulk(pos, left); + else if (!(flags & LIBETH_XDP_TX_NDO)) + libeth_xdp_tx_return_bulk(pos, left); + else + libeth_xdp_xmit_return_bulk(pos, left, bq->dev); + + bq->count = 0; +} +EXPORT_SYMBOL_GPL(libeth_xdp_tx_exception); + +/* .ndo_xdp_xmit() implementation */ + +u32 __cold libeth_xdp_xmit_return_bulk(const struct libeth_xdp_tx_frame *bq, + u32 count, const struct net_device *dev) +{ + u32 n = 0; + + for (u32 i = 0; i < count; i++) { + const struct libeth_xdp_tx_frame *frm = &bq[i]; + dma_addr_t dma; + + if (frm->flags & LIBETH_XDP_TX_FIRST) + dma = *libeth_xdp_xmit_frame_dma(frm->xdpf); + else + dma = dma_unmap_addr(frm, dma); + + dma_unmap_page(dev->dev.parent, dma, dma_unmap_len(frm, len), + DMA_TO_DEVICE); + + /* Actual xdp_frames are freed by the core */ + n += !!(frm->flags & LIBETH_XDP_TX_FIRST); + } + + return n; +} +EXPORT_SYMBOL_GPL(libeth_xdp_xmit_return_bulk); + +/* Rx polling path */ + +/** + * libeth_xdp_load_stash - recreate an &xdp_buff from libeth_xdp buffer stash + * @dst: target &libeth_xdp_buff to initialize + * @src: source stash + * + * External helper used by libeth_xdp_init_buff(), do not call directly. + * Recreate an onstack &libeth_xdp_buff using the stash saved earlier. + * The only field untouched (rxq) is initialized later in the + * abovementioned function. + */ +void libeth_xdp_load_stash(struct libeth_xdp_buff *dst, + const struct libeth_xdp_buff_stash *src) +{ + dst->data = src->data; + dst->base.data_end = src->data + src->len; + dst->base.data_meta = src->data; + dst->base.data_hard_start = src->data - src->headroom; + + dst->base.frame_sz = src->frame_sz; + dst->base.flags = src->flags; +} +EXPORT_SYMBOL_GPL(libeth_xdp_load_stash); + +/** + * libeth_xdp_save_stash - convert &xdp_buff to a libeth_xdp buffer stash + * @dst: target &libeth_xdp_buff_stash to initialize + * @src: source XDP buffer + * + * External helper used by libeth_xdp_save_buff(), do not call directly. + * Use the fields from the passed XDP buffer to initialize the stash on the + * queue, so that a partially received frame can be finished later during + * the next NAPI poll. + */ +void libeth_xdp_save_stash(struct libeth_xdp_buff_stash *dst, + const struct libeth_xdp_buff *src) +{ + dst->data = src->data; + dst->headroom = src->data - src->base.data_hard_start; + dst->len = src->base.data_end - src->data; + + dst->frame_sz = src->base.frame_sz; + dst->flags = src->base.flags; + + WARN_ON_ONCE(dst->flags != src->base.flags); +} +EXPORT_SYMBOL_GPL(libeth_xdp_save_stash); + +void __libeth_xdp_return_stash(struct libeth_xdp_buff_stash *stash) +{ + LIBETH_XDP_ONSTACK_BUFF(xdp); + + libeth_xdp_load_stash(xdp, stash); + libeth_xdp_return_buff_slow(xdp); + + stash->data = NULL; +} +EXPORT_SYMBOL_GPL(__libeth_xdp_return_stash); + +/** + * libeth_xdp_return_buff_slow - free &libeth_xdp_buff + * @xdp: buffer to free/return + * + * Slowpath version of libeth_xdp_return_buff() to be called on exceptions, + * queue clean-ups etc., without unwanted inlining. + */ +void __cold libeth_xdp_return_buff_slow(struct libeth_xdp_buff *xdp) +{ + __libeth_xdp_return_buff(xdp, false); +} +EXPORT_SYMBOL_GPL(libeth_xdp_return_buff_slow); + +/** + * libeth_xdp_buff_add_frag - add frag to XDP buffer + * @xdp: head XDP buffer + * @fqe: Rx buffer containing the frag + * @len: frag length reported by HW + * + * External helper used by libeth_xdp_process_buff(), do not call directly. + * Frees both head and frag buffers on error. + * + * Return: true success, false on error (no space for a new frag). + */ +bool libeth_xdp_buff_add_frag(struct libeth_xdp_buff *xdp, + const struct libeth_fqe *fqe, + u32 len) +{ + netmem_ref netmem = fqe->netmem; + + if (!xdp_buff_add_frag(&xdp->base, netmem, + fqe->offset + netmem_get_pp(netmem)->p.offset, + len, fqe->truesize)) + goto recycle; + + return true; + +recycle: + libeth_rx_recycle_slow(netmem); + libeth_xdp_return_buff_slow(xdp); + + return false; +} +EXPORT_SYMBOL_GPL(libeth_xdp_buff_add_frag); + +/** + * libeth_xdp_prog_exception - handle XDP prog exceptions + * @bq: XDP Tx bulk + * @xdp: buffer to process + * @act: original XDP prog verdict + * @ret: error code if redirect failed + * + * External helper used by __libeth_xdp_run_prog() and + * __libeth_xsk_run_prog_slow(), do not call directly. + * Reports invalid @act, XDP exception trace event and frees the buffer. + * + * Return: libeth_xdp XDP prog verdict. + */ +u32 __cold libeth_xdp_prog_exception(const struct libeth_xdp_tx_bulk *bq, + struct libeth_xdp_buff *xdp, + enum xdp_action act, int ret) +{ + if (act > XDP_REDIRECT) + bpf_warn_invalid_xdp_action(bq->dev, bq->prog, act); + + libeth_trace_xdp_exception(bq->dev, bq->prog, act); + + if (xdp->base.rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) + return libeth_xsk_prog_exception(xdp, act, ret); + + libeth_xdp_return_buff_slow(xdp); + + return LIBETH_XDP_DROP; +} +EXPORT_SYMBOL_GPL(libeth_xdp_prog_exception); + +/* Tx buffer completion */ + +static void libeth_xdp_put_netmem_bulk(netmem_ref netmem, + struct xdp_frame_bulk *bq) +{ + if (unlikely(bq->count == XDP_BULK_QUEUE_SIZE)) + xdp_flush_frame_bulk(bq); + + bq->q[bq->count++] = netmem; +} + +/** + * libeth_xdp_return_buff_bulk - free &xdp_buff as part of a bulk + * @sinfo: shared info corresponding to the buffer + * @bq: XDP frame bulk to store the buffer + * @frags: whether the buffer has frags + * + * Same as xdp_return_frame_bulk(), but for &libeth_xdp_buff, speeds up Tx + * completion of ``XDP_TX`` buffers and allows to free them in same bulks + * with &xdp_frame buffers. + */ +void libeth_xdp_return_buff_bulk(const struct skb_shared_info *sinfo, + struct xdp_frame_bulk *bq, bool frags) +{ + if (!frags) + goto head; + + for (u32 i = 0; i < sinfo->nr_frags; i++) + libeth_xdp_put_netmem_bulk(skb_frag_netmem(&sinfo->frags[i]), + bq); + +head: + libeth_xdp_put_netmem_bulk(virt_to_netmem(sinfo), bq); +} +EXPORT_SYMBOL_GPL(libeth_xdp_return_buff_bulk); + +/* Misc */ + +/** + * libeth_xdp_queue_threshold - calculate XDP queue clean/refill threshold + * @count: number of descriptors in the queue + * + * The threshold is the limit at which RQs start to refill (when the number of + * empty buffers exceeds it) and SQs get cleaned up (when the number of free + * descriptors goes below it). To speed up hotpath processing, threshold is + * always pow-2, closest to 1/4 of the queue length. + * Don't call it on hotpath, calculate and cache the threshold during the + * queue initialization. + * + * Return: the calculated threshold. + */ +u32 libeth_xdp_queue_threshold(u32 count) +{ + u32 quarter, low, high; + + if (likely(is_power_of_2(count))) + return count >> 2; + + quarter = DIV_ROUND_CLOSEST(count, 4); + low = rounddown_pow_of_two(quarter); + high = roundup_pow_of_two(quarter); + + return high - quarter <= quarter - low ? high : low; +} +EXPORT_SYMBOL_GPL(libeth_xdp_queue_threshold); + +/** + * __libeth_xdp_set_features - set XDP features for netdev + * @dev: &net_device to configure + * @xmo: XDP metadata ops (Rx hints) + * @zc_segs: maximum number of S/G frags the HW can transmit + * @tmo: XSk Tx metadata ops (Tx hints) + * + * Set all the features libeth_xdp supports. Only the first argument is + * necessary; without the third one (zero), XSk support won't be advertised. + * Use the non-underscored versions in drivers instead. + */ +void __libeth_xdp_set_features(struct net_device *dev, + const struct xdp_metadata_ops *xmo, + u32 zc_segs, + const struct xsk_tx_metadata_ops *tmo) +{ + xdp_set_features_flag(dev, + NETDEV_XDP_ACT_BASIC | + NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | + (zc_segs ? NETDEV_XDP_ACT_XSK_ZEROCOPY : 0) | + NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG); + dev->xdp_metadata_ops = xmo; + + tmo = tmo == libeth_xsktmo ? &libeth_xsktmo_slow : tmo; + + dev->xdp_zc_max_segs = zc_segs ? : 1; + dev->xsk_tx_metadata_ops = zc_segs ? tmo : NULL; +} +EXPORT_SYMBOL_GPL(__libeth_xdp_set_features); + +/** + * libeth_xdp_set_redirect - toggle the XDP redirect feature + * @dev: &net_device to configure + * @enable: whether XDP is enabled + * + * Use this when XDPSQs are not always available to dynamically enable + * and disable redirect feature. + */ +void libeth_xdp_set_redirect(struct net_device *dev, bool enable) +{ + if (enable) + xdp_features_set_redirect_target(dev, true); + else + xdp_features_clear_redirect_target(dev); +} +EXPORT_SYMBOL_GPL(libeth_xdp_set_redirect); + +/* Module */ + +static const struct libeth_xdp_ops xdp_ops __initconst = { + .bulk = libeth_xdp_return_buff_bulk, + .xsk = libeth_xsk_buff_free_slow, +}; + +static int __init libeth_xdp_module_init(void) +{ + libeth_attach_xdp(&xdp_ops); + + return 0; +} +module_init(libeth_xdp_module_init); + +static void __exit libeth_xdp_module_exit(void) +{ + libeth_detach_xdp(); +} +module_exit(libeth_xdp_module_exit); + +MODULE_DESCRIPTION("Common Ethernet library - XDP infra"); +MODULE_IMPORT_NS("LIBETH"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/intel/libeth/xsk.c b/drivers/net/ethernet/intel/libeth/xsk.c new file mode 100644 index 000000000000..846e902e31b6 --- /dev/null +++ b/drivers/net/ethernet/intel/libeth/xsk.c @@ -0,0 +1,271 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2025 Intel Corporation */ + +#define DEFAULT_SYMBOL_NAMESPACE "LIBETH_XDP" + +#include <linux/export.h> + +#include <net/libeth/xsk.h> + +#include "priv.h" + +/* ``XDP_TX`` bulking */ + +void __cold libeth_xsk_tx_return_bulk(const struct libeth_xdp_tx_frame *bq, + u32 count) +{ + for (u32 i = 0; i < count; i++) + libeth_xsk_buff_free_slow(bq[i].xsk); +} + +/* XSk TMO */ + +const struct xsk_tx_metadata_ops libeth_xsktmo_slow = { + .tmo_request_checksum = libeth_xsktmo_req_csum, +}; + +/* Rx polling path */ + +/** + * libeth_xsk_buff_free_slow - free an XSk Rx buffer + * @xdp: buffer to free + * + * Slowpath version of xsk_buff_free() to be used on exceptions, cleanups etc. + * to avoid unwanted inlining. + */ +void libeth_xsk_buff_free_slow(struct libeth_xdp_buff *xdp) +{ + xsk_buff_free(&xdp->base); +} +EXPORT_SYMBOL_GPL(libeth_xsk_buff_free_slow); + +/** + * libeth_xsk_buff_add_frag - add frag to XSk Rx buffer + * @head: head buffer + * @xdp: frag buffer + * + * External helper used by libeth_xsk_process_buff(), do not call directly. + * Frees both main and frag buffers on error. + * + * Return: main buffer with attached frag on success, %NULL on error (no space + * for a new frag). + */ +struct libeth_xdp_buff *libeth_xsk_buff_add_frag(struct libeth_xdp_buff *head, + struct libeth_xdp_buff *xdp) +{ + if (!xsk_buff_add_frag(&head->base, &xdp->base)) + goto free; + + return head; + +free: + libeth_xsk_buff_free_slow(xdp); + libeth_xsk_buff_free_slow(head); + + return NULL; +} +EXPORT_SYMBOL_GPL(libeth_xsk_buff_add_frag); + +/** + * libeth_xsk_buff_stats_frags - update onstack RQ stats with XSk frags info + * @rs: onstack stats to update + * @xdp: buffer to account + * + * External helper used by __libeth_xsk_run_pass(), do not call directly. + * Adds buffer's frags count and total len to the onstack stats. + */ +void libeth_xsk_buff_stats_frags(struct libeth_rq_napi_stats *rs, + const struct libeth_xdp_buff *xdp) +{ + libeth_xdp_buff_stats_frags(rs, xdp); +} +EXPORT_SYMBOL_GPL(libeth_xsk_buff_stats_frags); + +/** + * __libeth_xsk_run_prog_slow - process the non-``XDP_REDIRECT`` verdicts + * @xdp: buffer to process + * @bq: Tx bulk for queueing on ``XDP_TX`` + * @act: verdict to process + * @ret: error code if ``XDP_REDIRECT`` failed + * + * External helper used by __libeth_xsk_run_prog(), do not call directly. + * ``XDP_REDIRECT`` is the most common and hottest verdict on XSk, thus + * it is processed inline. The rest goes here for out-of-line processing, + * together with redirect errors. + * + * Return: libeth_xdp XDP prog verdict. + */ +u32 __libeth_xsk_run_prog_slow(struct libeth_xdp_buff *xdp, + const struct libeth_xdp_tx_bulk *bq, + enum xdp_action act, int ret) +{ + switch (act) { + case XDP_DROP: + xsk_buff_free(&xdp->base); + + return LIBETH_XDP_DROP; + case XDP_TX: + return LIBETH_XDP_TX; + case XDP_PASS: + return LIBETH_XDP_PASS; + default: + break; + } + + return libeth_xdp_prog_exception(bq, xdp, act, ret); +} +EXPORT_SYMBOL_GPL(__libeth_xsk_run_prog_slow); + +/** + * libeth_xsk_prog_exception - handle XDP prog exceptions on XSk + * @xdp: buffer to process + * @act: verdict returned by the prog + * @ret: error code if ``XDP_REDIRECT`` failed + * + * Internal. Frees the buffer and, if the queue uses XSk wakeups, stop the + * current NAPI poll when there are no free buffers left. + * + * Return: libeth_xdp's XDP prog verdict. + */ +u32 __cold libeth_xsk_prog_exception(struct libeth_xdp_buff *xdp, + enum xdp_action act, int ret) +{ + const struct xdp_buff_xsk *xsk; + u32 __ret = LIBETH_XDP_DROP; + + if (act != XDP_REDIRECT) + goto drop; + + xsk = container_of(&xdp->base, typeof(*xsk), xdp); + if (xsk_uses_need_wakeup(xsk->pool) && ret == -ENOBUFS) + __ret = LIBETH_XDP_ABORTED; + +drop: + libeth_xsk_buff_free_slow(xdp); + + return __ret; +} + +/* Refill */ + +/** + * libeth_xskfq_create - create an XSkFQ + * @fq: fill queue to initialize + * + * Allocates the FQEs and initializes the fields used by libeth_xdp: number + * of buffers to refill, refill threshold and buffer len. + * + * Return: %0 on success, -errno otherwise. + */ +int libeth_xskfq_create(struct libeth_xskfq *fq) +{ + fq->fqes = kvcalloc_node(fq->count, sizeof(*fq->fqes), GFP_KERNEL, + fq->nid); + if (!fq->fqes) + return -ENOMEM; + + fq->pending = fq->count; + fq->thresh = libeth_xdp_queue_threshold(fq->count); + fq->buf_len = xsk_pool_get_rx_frame_size(fq->pool); + + return 0; +} +EXPORT_SYMBOL_GPL(libeth_xskfq_create); + +/** + * libeth_xskfq_destroy - destroy an XSkFQ + * @fq: fill queue to destroy + * + * Zeroes the used fields and frees the FQEs array. + */ +void libeth_xskfq_destroy(struct libeth_xskfq *fq) +{ + fq->buf_len = 0; + fq->thresh = 0; + fq->pending = 0; + + kvfree(fq->fqes); +} +EXPORT_SYMBOL_GPL(libeth_xskfq_destroy); + +/* .ndo_xsk_wakeup */ + +static void libeth_xsk_napi_sched(void *info) +{ + __napi_schedule_irqoff(info); +} + +/** + * libeth_xsk_init_wakeup - initialize libeth XSk wakeup structure + * @csd: struct to initialize + * @napi: NAPI corresponding to this queue + * + * libeth_xdp uses inter-processor interrupts to perform XSk wakeups. In order + * to do that, the corresponding CSDs must be initialized when creating the + * queues. + */ +void libeth_xsk_init_wakeup(call_single_data_t *csd, struct napi_struct *napi) +{ + INIT_CSD(csd, libeth_xsk_napi_sched, napi); +} +EXPORT_SYMBOL_GPL(libeth_xsk_init_wakeup); + +/** + * libeth_xsk_wakeup - perform an XSk wakeup + * @csd: CSD corresponding to the queue + * @qid: the stack queue index + * + * Try to mark the NAPI as missed first, so that it could be rescheduled. + * If it's not, schedule it on the corresponding CPU using IPIs (or directly + * if already running on it). + */ +void libeth_xsk_wakeup(call_single_data_t *csd, u32 qid) +{ + struct napi_struct *napi = csd->info; + + if (napi_if_scheduled_mark_missed(napi) || + unlikely(!napi_schedule_prep(napi))) + return; + + if (unlikely(qid >= nr_cpu_ids)) + qid %= nr_cpu_ids; + + if (qid != raw_smp_processor_id() && cpu_online(qid)) + smp_call_function_single_async(qid, csd); + else + __napi_schedule(napi); +} +EXPORT_SYMBOL_GPL(libeth_xsk_wakeup); + +/* Pool setup */ + +#define LIBETH_XSK_DMA_ATTR \ + (DMA_ATTR_WEAK_ORDERING | DMA_ATTR_SKIP_CPU_SYNC) + +/** + * libeth_xsk_setup_pool - setup or destroy an XSk pool for a queue + * @dev: target &net_device + * @qid: stack queue index to configure + * @enable: whether to enable or disable the pool + * + * Check that @qid is valid and then map or unmap the pool. + * + * Return: %0 on success, -errno otherwise. + */ +int libeth_xsk_setup_pool(struct net_device *dev, u32 qid, bool enable) +{ + struct xsk_buff_pool *pool; + + pool = xsk_get_pool_from_qid(dev, qid); + if (!pool) + return -EINVAL; + + if (enable) + return xsk_pool_dma_map(pool, dev->dev.parent, + LIBETH_XSK_DMA_ATTR); + else + xsk_pool_dma_unmap(pool, LIBETH_XSK_DMA_ATTR); + + return 0; +} +EXPORT_SYMBOL_GPL(libeth_xsk_setup_pool); diff --git a/drivers/net/ethernet/intel/libie/rx.c b/drivers/net/ethernet/intel/libie/rx.c index 66a9825fe11f..6fda656afa9c 100644 --- a/drivers/net/ethernet/intel/libie/rx.c +++ b/drivers/net/ethernet/intel/libie/rx.c @@ -1,6 +1,9 @@ // SPDX-License-Identifier: GPL-2.0-only -/* Copyright (C) 2024 Intel Corporation */ +/* Copyright (C) 2024-2025 Intel Corporation */ +#define DEFAULT_SYMBOL_NAMESPACE "LIBIE" + +#include <linux/export.h> #include <linux/net/intel/libie/rx.h> /* O(1) converting i40e/ice/iavf's 8/10-bit hardware packet type to a parsed @@ -116,7 +119,7 @@ const struct libeth_rx_pt libie_rx_pt_lut[LIBIE_RX_PT_NUM] = { LIBIE_RX_PT_IP(4), LIBIE_RX_PT_IP(6), }; -EXPORT_SYMBOL_NS_GPL(libie_rx_pt_lut, "LIBIE"); +EXPORT_SYMBOL_GPL(libie_rx_pt_lut); MODULE_DESCRIPTION("Intel(R) Ethernet common library"); MODULE_IMPORT_NS("LIBETH"); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c index 8ed83fb98862..44b201817d94 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c @@ -1618,7 +1618,8 @@ int mvpp22_port_rss_ctx_indir_get(struct mvpp2_port *port, u32 port_ctx, return 0; } -int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info) +int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, + const struct ethtool_rxfh_fields *info) { u16 hash_opts = 0; u32 flow_type; @@ -1656,7 +1657,8 @@ int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info) return mvpp2_port_rss_hash_opts_set(port, flow_type, hash_opts); } -int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port, struct ethtool_rxnfc *info) +int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port, + struct ethtool_rxfh_fields *info) { unsigned long hash_opts; u32 flow_type; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h index 85c9c6e80678..caadf3aea95d 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h @@ -272,8 +272,10 @@ int mvpp22_port_rss_ctx_indir_set(struct mvpp2_port *port, u32 rss_ctx, int mvpp22_port_rss_ctx_indir_get(struct mvpp2_port *port, u32 rss_ctx, u32 *indir); -int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port, struct ethtool_rxnfc *info); -int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info); +int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port, + struct ethtool_rxfh_fields *info); +int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, + const struct ethtool_rxfh_fields *info); void mvpp2_cls_init(struct mvpp2 *priv); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index a7872d14a49d..8ebb985d2573 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5588,9 +5588,6 @@ static int mvpp2_ethtool_get_rxnfc(struct net_device *dev, return -EOPNOTSUPP; switch (info->cmd) { - case ETHTOOL_GRXFH: - ret = mvpp2_ethtool_rxfh_get(port, info); - break; case ETHTOOL_GRXRINGS: info->data = port->nrxqs; break; @@ -5628,9 +5625,6 @@ static int mvpp2_ethtool_set_rxnfc(struct net_device *dev, return -EOPNOTSUPP; switch (info->cmd) { - case ETHTOOL_SRXFH: - ret = mvpp2_ethtool_rxfh_set(port, info); - break; case ETHTOOL_SRXCLSRLINS: ret = mvpp2_ethtool_cls_rule_ins(port, info); break; @@ -5747,6 +5741,29 @@ static int mvpp2_ethtool_set_rxfh(struct net_device *dev, return mvpp2_modify_rxfh_context(dev, NULL, rxfh, extack); } +static int mvpp2_ethtool_get_rxfh_fields(struct net_device *dev, + struct ethtool_rxfh_fields *info) +{ + struct mvpp2_port *port = netdev_priv(dev); + + if (!mvpp22_rss_is_supported(port)) + return -EOPNOTSUPP; + + return mvpp2_ethtool_rxfh_get(port, info); +} + +static int mvpp2_ethtool_set_rxfh_fields(struct net_device *dev, + const struct ethtool_rxfh_fields *info, + struct netlink_ext_ack *extack) +{ + struct mvpp2_port *port = netdev_priv(dev); + + if (!mvpp22_rss_is_supported(port)) + return -EOPNOTSUPP; + + return mvpp2_ethtool_rxfh_set(port, info); +} + static int mvpp2_ethtool_get_eee(struct net_device *dev, struct ethtool_keee *eee) { @@ -5813,6 +5830,8 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = { .get_rxfh_indir_size = mvpp2_ethtool_get_rxfh_indir_size, .get_rxfh = mvpp2_ethtool_get_rxfh, .set_rxfh = mvpp2_ethtool_set_rxfh, + .get_rxfh_fields = mvpp2_ethtool_get_rxfh_fields, + .set_rxfh_fields = mvpp2_ethtool_set_rxfh_fields, .create_rxfh_context = mvpp2_create_rxfh_context, .modify_rxfh_context = mvpp2_modify_rxfh_context, .remove_rxfh_context = mvpp2_remove_rxfh_context, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/Makefile b/drivers/net/ethernet/marvell/octeontx2/af/Makefile index ccea37847df8..532813d8d028 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/af/Makefile @@ -12,4 +12,4 @@ rvu_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 rvu_npc_fs.o \ rvu_cpt.o rvu_devlink.o rpm.o rvu_cn10k.o rvu_switch.o \ rvu_sdp.o rvu_npc_hash.o mcs.o mcs_rvu_if.o mcs_cnf10kb.o \ - rvu_rep.o + rvu_rep.o cn20k/mbox_init.o diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/api.h b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/api.h new file mode 100644 index 000000000000..4285b5d6a6a2 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/api.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell RVU Admin Function driver + * + * Copyright (C) 2024 Marvell. + * + */ + +#ifndef CN20K_API_H +#define CN20K_API_H + +#include "../rvu.h" + +struct ng_rvu { + struct mbox_ops *rvu_mbox_ops; + struct qmem *pf_mbox_addr; + struct qmem *vf_mbox_addr; +}; + +/* Mbox related APIs */ +int cn20k_rvu_mbox_init(struct rvu *rvu, int type, int num); +int cn20k_rvu_get_mbox_regions(struct rvu *rvu, void **mbox_addr, + int num, int type, unsigned long *pf_bmap); +void cn20k_free_mbox_memory(struct rvu *rvu); +int cn20k_register_afpf_mbox_intr(struct rvu *rvu); +int cn20k_register_afvf_mbox_intr(struct rvu *rvu, int pf_vec_start); +void cn20k_rvu_enable_mbox_intr(struct rvu *rvu); +void cn20k_rvu_unregister_interrupts(struct rvu *rvu); +int cn20k_mbox_setup(struct otx2_mbox *mbox, struct pci_dev *pdev, + void *reg_base, int direction, int ndevs); +void cn20k_rvu_enable_afvf_intr(struct rvu *rvu, int vfs); +void cn20k_rvu_disable_afvf_intr(struct rvu *rvu, int vfs); +#endif /* CN20K_API_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/mbox_init.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/mbox_init.c new file mode 100644 index 000000000000..bd3aab7770dd --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/mbox_init.c @@ -0,0 +1,424 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell RVU Admin Function driver + * + * Copyright (C) 2024 Marvell. + * + */ + +#include <linux/interrupt.h> +#include <linux/irq.h> + +#include "rvu_trace.h" +#include "mbox.h" +#include "reg.h" +#include "api.h" + +static irqreturn_t cn20k_afvf_mbox_intr_handler(int irq, void *rvu_irq) +{ + struct rvu_irq_data *rvu_irq_data = rvu_irq; + struct rvu *rvu = rvu_irq_data->rvu; + u64 intr; + + /* Sync with mbox memory region */ + rmb(); + + /* Clear interrupts */ + intr = rvupf_read64(rvu, rvu_irq_data->intr_status); + rvupf_write64(rvu, rvu_irq_data->intr_status, intr); + + if (intr) + trace_otx2_msg_interrupt(rvu->pdev, "VF(s) to AF", intr); + + rvu_irq_data->afvf_queue_work_hdlr(&rvu->afvf_wq_info, rvu_irq_data->start, + rvu_irq_data->mdevs, intr); + + return IRQ_HANDLED; +} + +int cn20k_register_afvf_mbox_intr(struct rvu *rvu, int pf_vec_start) +{ + struct rvu_irq_data *irq_data; + int intr_vec, offset, vec = 0; + int err; + + /* irq data for 4 VFPF intr vectors */ + irq_data = devm_kcalloc(rvu->dev, 4, + sizeof(struct rvu_irq_data), GFP_KERNEL); + if (!irq_data) + return -ENOMEM; + + for (intr_vec = RVU_MBOX_PF_INT_VEC_VFPF_MBOX0; intr_vec <= + RVU_MBOX_PF_INT_VEC_VFPF1_MBOX1; + intr_vec++, vec++) { + switch (intr_vec) { + case RVU_MBOX_PF_INT_VEC_VFPF_MBOX0: + irq_data[vec].intr_status = + RVU_MBOX_PF_VFPF_INTX(0); + irq_data[vec].start = 0; + irq_data[vec].mdevs = 64; + break; + case RVU_MBOX_PF_INT_VEC_VFPF_MBOX1: + irq_data[vec].intr_status = + RVU_MBOX_PF_VFPF_INTX(1); + irq_data[vec].start = 64; + irq_data[vec].mdevs = 64; + break; + case RVU_MBOX_PF_INT_VEC_VFPF1_MBOX0: + irq_data[vec].intr_status = + RVU_MBOX_PF_VFPF1_INTX(0); + irq_data[vec].start = 0; + irq_data[vec].mdevs = 64; + break; + case RVU_MBOX_PF_INT_VEC_VFPF1_MBOX1: + irq_data[vec].intr_status = RVU_MBOX_PF_VFPF1_INTX(1); + irq_data[vec].start = 64; + irq_data[vec].mdevs = 64; + break; + } + irq_data[vec].afvf_queue_work_hdlr = + rvu_queue_work; + offset = pf_vec_start + intr_vec; + irq_data[vec].vec_num = offset; + irq_data[vec].rvu = rvu; + + sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAF VFAF%d Mbox%d", + vec / 2, vec % 2); + err = request_irq(pci_irq_vector(rvu->pdev, offset), + rvu->ng_rvu->rvu_mbox_ops->afvf_intr_handler, 0, + &rvu->irq_name[offset * NAME_SIZE], + &irq_data[vec]); + if (err) { + dev_err(rvu->dev, + "RVUAF: IRQ registration failed for AFVF mbox irq\n"); + return err; + } + rvu->irq_allocated[offset] = true; + } + + return 0; +} + +/* CN20K mbox PFx => AF irq handler */ +static irqreturn_t cn20k_mbox_pf_common_intr_handler(int irq, void *rvu_irq) +{ + struct rvu_irq_data *rvu_irq_data = rvu_irq; + struct rvu *rvu = rvu_irq_data->rvu; + u64 intr; + + /* Clear interrupts */ + intr = rvu_read64(rvu, BLKADDR_RVUM, rvu_irq_data->intr_status); + rvu_write64(rvu, BLKADDR_RVUM, rvu_irq_data->intr_status, intr); + + if (intr) + trace_otx2_msg_interrupt(rvu->pdev, "PF(s) to AF", intr); + + /* Sync with mbox memory region */ + rmb(); + + rvu_irq_data->rvu_queue_work_hdlr(&rvu->afpf_wq_info, + rvu_irq_data->start, + rvu_irq_data->mdevs, intr); + + return IRQ_HANDLED; +} + +void cn20k_rvu_enable_mbox_intr(struct rvu *rvu) +{ + struct rvu_hwinfo *hw = rvu->hw; + + /* Clear spurious irqs, if any */ + rvu_write64(rvu, BLKADDR_RVUM, + RVU_MBOX_AF_PFAF_INT(0), INTR_MASK(hw->total_pfs)); + + rvu_write64(rvu, BLKADDR_RVUM, + RVU_MBOX_AF_PFAF_INT(1), INTR_MASK(hw->total_pfs - 64)); + + rvu_write64(rvu, BLKADDR_RVUM, + RVU_MBOX_AF_PFAF1_INT(0), INTR_MASK(hw->total_pfs)); + + rvu_write64(rvu, BLKADDR_RVUM, + RVU_MBOX_AF_PFAF1_INT(1), INTR_MASK(hw->total_pfs - 64)); + + /* Enable mailbox interrupt for all PFs except PF0 i.e AF itself */ + rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFAF_INT_ENA_W1S(0), + INTR_MASK(hw->total_pfs) & ~1ULL); + + rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFAF_INT_ENA_W1S(1), + INTR_MASK(hw->total_pfs - 64)); + + rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFAF1_INT_ENA_W1S(0), + INTR_MASK(hw->total_pfs) & ~1ULL); + + rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFAF1_INT_ENA_W1S(1), + INTR_MASK(hw->total_pfs - 64)); +} + +void cn20k_rvu_unregister_interrupts(struct rvu *rvu) +{ + rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFAF_INT_ENA_W1C(0), + INTR_MASK(rvu->hw->total_pfs) & ~1ULL); + + rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFAF_INT_ENA_W1C(1), + INTR_MASK(rvu->hw->total_pfs - 64)); + + rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFAF1_INT_ENA_W1C(0), + INTR_MASK(rvu->hw->total_pfs) & ~1ULL); + + rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFAF1_INT_ENA_W1C(1), + INTR_MASK(rvu->hw->total_pfs - 64)); +} + +int cn20k_register_afpf_mbox_intr(struct rvu *rvu) +{ + struct rvu_irq_data *irq_data; + int intr_vec, ret, vec = 0; + + /* irq data for 4 PF intr vectors */ + irq_data = devm_kcalloc(rvu->dev, 4, + sizeof(struct rvu_irq_data), GFP_KERNEL); + if (!irq_data) + return -ENOMEM; + + for (intr_vec = RVU_AF_CN20K_INT_VEC_PFAF_MBOX0; intr_vec <= + RVU_AF_CN20K_INT_VEC_PFAF1_MBOX1; intr_vec++, + vec++) { + switch (intr_vec) { + case RVU_AF_CN20K_INT_VEC_PFAF_MBOX0: + irq_data[vec].intr_status = + RVU_MBOX_AF_PFAF_INT(0); + irq_data[vec].start = 0; + irq_data[vec].mdevs = 64; + break; + case RVU_AF_CN20K_INT_VEC_PFAF_MBOX1: + irq_data[vec].intr_status = + RVU_MBOX_AF_PFAF_INT(1); + irq_data[vec].start = 64; + irq_data[vec].mdevs = 96; + break; + case RVU_AF_CN20K_INT_VEC_PFAF1_MBOX0: + irq_data[vec].intr_status = + RVU_MBOX_AF_PFAF1_INT(0); + irq_data[vec].start = 0; + irq_data[vec].mdevs = 64; + break; + case RVU_AF_CN20K_INT_VEC_PFAF1_MBOX1: + irq_data[vec].intr_status = + RVU_MBOX_AF_PFAF1_INT(1); + irq_data[vec].start = 64; + irq_data[vec].mdevs = 96; + break; + } + irq_data[vec].rvu_queue_work_hdlr = rvu_queue_work; + irq_data[vec].vec_num = intr_vec; + irq_data[vec].rvu = rvu; + + /* Register mailbox interrupt handler */ + sprintf(&rvu->irq_name[intr_vec * NAME_SIZE], + "RVUAF PFAF%d Mbox%d", + vec / 2, vec % 2); + ret = request_irq(pci_irq_vector(rvu->pdev, intr_vec), + rvu->ng_rvu->rvu_mbox_ops->pf_intr_handler, 0, + &rvu->irq_name[intr_vec * NAME_SIZE], + &irq_data[vec]); + if (ret) + return ret; + + rvu->irq_allocated[intr_vec] = true; + } + + return 0; +} + +int cn20k_rvu_get_mbox_regions(struct rvu *rvu, void **mbox_addr, + int num, int type, unsigned long *pf_bmap) +{ + int region; + u64 bar; + + if (type == TYPE_AFVF) { + for (region = 0; region < num; region++) { + if (!test_bit(region, pf_bmap)) + continue; + + bar = (u64)phys_to_virt((u64)rvu->ng_rvu->vf_mbox_addr->base); + bar += region * MBOX_SIZE; + mbox_addr[region] = (void *)bar; + + if (!mbox_addr[region]) + return -ENOMEM; + } + return 0; + } + + for (region = 0; region < num; region++) { + if (!test_bit(region, pf_bmap)) + continue; + + bar = (u64)phys_to_virt((u64)rvu->ng_rvu->pf_mbox_addr->base); + bar += region * MBOX_SIZE; + + mbox_addr[region] = (void *)bar; + + if (!mbox_addr[region]) + return -ENOMEM; + } + return 0; +} + +static int rvu_alloc_mbox_memory(struct rvu *rvu, int type, + int ndevs, int mbox_size) +{ + struct qmem *mbox_addr; + dma_addr_t iova; + int pf, err; + + /* Allocate contiguous memory for mailbox communication. + * eg: AF <=> PFx mbox memory + * This allocated memory is split into chunks of MBOX_SIZE + * and setup into each of the RVU PFs. In HW this memory will + * get aliased to an offset within BAR2 of those PFs. + * + * AF will access mbox memory using direct physical addresses + * and PFs will access the same shared memory from BAR2. + * + * PF <=> VF mbox memory also works in the same fashion. + * AFPF, PFVF requires IOVA to be used to maintain the mailbox msgs + */ + + err = qmem_alloc(rvu->dev, &mbox_addr, ndevs, mbox_size); + if (err) + return -ENOMEM; + + switch (type) { + case TYPE_AFPF: + rvu->ng_rvu->pf_mbox_addr = mbox_addr; + iova = (u64)mbox_addr->iova; + for (pf = 0; pf < ndevs; pf++) { + rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_AF_PFX_ADDR(pf), + (u64)iova); + iova += mbox_size; + } + break; + case TYPE_AFVF: + rvu->ng_rvu->vf_mbox_addr = mbox_addr; + rvupf_write64(rvu, RVU_PF_VF_MBOX_ADDR, (u64)mbox_addr->iova); + break; + default: + return 0; + } + + return 0; +} + +static struct mbox_ops cn20k_mbox_ops = { + .pf_intr_handler = cn20k_mbox_pf_common_intr_handler, + .afvf_intr_handler = cn20k_afvf_mbox_intr_handler, +}; + +int cn20k_rvu_mbox_init(struct rvu *rvu, int type, int ndevs) +{ + int dev; + + if (!is_cn20k(rvu->pdev)) + return 0; + + rvu->ng_rvu->rvu_mbox_ops = &cn20k_mbox_ops; + + if (type == TYPE_AFVF) { + rvu_write64(rvu, BLKADDR_RVUM, RVU_MBOX_PF_VF_CFG, ilog2(MBOX_SIZE)); + } else { + for (dev = 0; dev < ndevs; dev++) + rvu_write64(rvu, BLKADDR_RVUM, + RVU_MBOX_AF_PFX_CFG(dev), ilog2(MBOX_SIZE)); + } + + return rvu_alloc_mbox_memory(rvu, type, ndevs, MBOX_SIZE); +} + +void cn20k_free_mbox_memory(struct rvu *rvu) +{ + if (!is_cn20k(rvu->pdev)) + return; + + qmem_free(rvu->dev, rvu->ng_rvu->pf_mbox_addr); + qmem_free(rvu->dev, rvu->ng_rvu->vf_mbox_addr); +} + +void cn20k_rvu_disable_afvf_intr(struct rvu *rvu, int vfs) +{ + rvupf_write64(rvu, RVU_MBOX_PF_VFPF_INT_ENA_W1CX(0), INTR_MASK(vfs)); + rvupf_write64(rvu, RVU_MBOX_PF_VFPF1_INT_ENA_W1CX(0), INTR_MASK(vfs)); + rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1CX(0), INTR_MASK(vfs)); + rvupf_write64(rvu, RVU_PF_VFME_INT_ENA_W1CX(0), INTR_MASK(vfs)); + + if (vfs <= 64) + return; + + rvupf_write64(rvu, RVU_MBOX_PF_VFPF_INT_ENA_W1CX(1), INTR_MASK(vfs - 64)); + rvupf_write64(rvu, RVU_MBOX_PF_VFPF1_INT_ENA_W1CX(1), INTR_MASK(vfs - 64)); + rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1CX(1), INTR_MASK(vfs - 64)); + rvupf_write64(rvu, RVU_PF_VFME_INT_ENA_W1CX(1), INTR_MASK(vfs - 64)); +} + +void cn20k_rvu_enable_afvf_intr(struct rvu *rvu, int vfs) +{ + /* Clear any pending interrupts and enable AF VF interrupts for + * the first 64 VFs. + */ + rvupf_write64(rvu, RVU_MBOX_PF_VFPF_INTX(0), INTR_MASK(vfs)); + rvupf_write64(rvu, RVU_MBOX_PF_VFPF_INT_ENA_W1SX(0), INTR_MASK(vfs)); + rvupf_write64(rvu, RVU_MBOX_PF_VFPF1_INTX(0), INTR_MASK(vfs)); + rvupf_write64(rvu, RVU_MBOX_PF_VFPF1_INT_ENA_W1SX(0), INTR_MASK(vfs)); + + /* FLR */ + rvupf_write64(rvu, RVU_PF_VFFLR_INTX(0), INTR_MASK(vfs)); + rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1SX(0), INTR_MASK(vfs)); + + /* Same for remaining VFs, if any. */ + if (vfs <= 64) + return; + + rvupf_write64(rvu, RVU_MBOX_PF_VFPF_INTX(1), INTR_MASK(vfs - 64)); + rvupf_write64(rvu, RVU_MBOX_PF_VFPF_INT_ENA_W1SX(1), INTR_MASK(vfs - 64)); + rvupf_write64(rvu, RVU_MBOX_PF_VFPF1_INTX(1), INTR_MASK(vfs - 64)); + rvupf_write64(rvu, RVU_MBOX_PF_VFPF1_INT_ENA_W1SX(1), INTR_MASK(vfs - 64)); + + rvupf_write64(rvu, RVU_PF_VFFLR_INTX(1), INTR_MASK(vfs - 64)); + rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1SX(1), INTR_MASK(vfs - 64)); + rvupf_write64(rvu, RVU_PF_VFME_INT_ENA_W1SX(1), INTR_MASK(vfs - 64)); +} + +int rvu_alloc_cint_qint_mem(struct rvu *rvu, struct rvu_pfvf *pfvf, + int blkaddr, int nixlf) +{ + int qints, hwctx_size, err; + u64 cfg, ctx_cfg; + + if (is_rvu_otx2(rvu) || is_cn20k(rvu->pdev)) + return 0; + + ctx_cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST3); + /* Alloc memory for CQINT's HW contexts */ + cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST2); + qints = (cfg >> 24) & 0xFFF; + hwctx_size = 1UL << ((ctx_cfg >> 24) & 0xF); + err = qmem_alloc(rvu->dev, &pfvf->cq_ints_ctx, qints, hwctx_size); + if (err) + return -ENOMEM; + + rvu_write64(rvu, blkaddr, NIX_AF_LFX_CINTS_BASE(nixlf), + (u64)pfvf->cq_ints_ctx->iova); + + /* Alloc memory for QINT's HW contexts */ + cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST2); + qints = (cfg >> 12) & 0xFFF; + hwctx_size = 1UL << ((ctx_cfg >> 20) & 0xF); + err = qmem_alloc(rvu->dev, &pfvf->nix_qints_ctx, qints, hwctx_size); + if (err) + return -ENOMEM; + + rvu_write64(rvu, blkaddr, NIX_AF_LFX_QINTS_BASE(nixlf), + (u64)pfvf->nix_qints_ctx->iova); + + return 0; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/reg.h b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/reg.h new file mode 100644 index 000000000000..affb39803120 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/reg.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell RVU Admin Function driver + * + * Copyright (C) 2024 Marvell. + * + */ + +#ifndef RVU_MBOX_REG_H +#define RVU_MBOX_REG_H +#include "../rvu.h" +#include "../rvu_reg.h" + +/* RVUM block registers */ +#define RVU_PF_DISC (0x0) +#define RVU_PRIV_PFX_DISC(a) (0x8000208 | (a) << 16) +#define RVU_PRIV_HWVFX_DISC(a) (0xD000000 | (a) << 12) + +/* Mbox Registers */ +/* RVU AF BAR0 Mbox registers for AF => PFx */ +#define RVU_MBOX_AF_PFX_ADDR(a) (0x5000 | (a) << 4) +#define RVU_MBOX_AF_PFX_CFG(a) (0x6000 | (a) << 4) +#define RVU_MBOX_AF_AFPFX_TRIGX(a) (0x9000 | (a) << 3) +#define RVU_MBOX_AF_PFAF_INT(a) (0x2980 | (a) << 6) +#define RVU_MBOX_AF_PFAF_INT_W1S(a) (0x2988 | (a) << 6) +#define RVU_MBOX_AF_PFAF_INT_ENA_W1S(a) (0x2990 | (a) << 6) +#define RVU_MBOX_AF_PFAF_INT_ENA_W1C(a) (0x2998 | (a) << 6) +#define RVU_MBOX_AF_PFAF1_INT(a) (0x29A0 | (a) << 6) +#define RVU_MBOX_AF_PFAF1_INT_W1S(a) (0x29A8 | (a) << 6) +#define RVU_MBOX_AF_PFAF1_INT_ENA_W1S(a) (0x29B0 | (a) << 6) +#define RVU_MBOX_AF_PFAF1_INT_ENA_W1C(a) (0x29B8 | (a) << 6) + +/* RVU PF => AF mbox registers */ +#define RVU_MBOX_PF_PFAF_TRIGX(a) (0xC00 | (a) << 3) +#define RVU_MBOX_PF_INT (0xC20) +#define RVU_MBOX_PF_INT_W1S (0xC28) +#define RVU_MBOX_PF_INT_ENA_W1S (0xC30) +#define RVU_MBOX_PF_INT_ENA_W1C (0xC38) + +#define RVU_AF_BAR2_SEL (0x9000000) +#define RVU_AF_BAR2_PFID (0x16400) +#define NIX_CINTX_INT_W1S(a) (0xd30 | (a) << 12) +#define NIX_QINTX_CNT(a) (0xc00 | (a) << 12) + +#define RVU_MBOX_AF_VFAF_INT(a) (0x3000 | (a) << 6) +#define RVU_MBOX_AF_VFAF_INT_W1S(a) (0x3008 | (a) << 6) +#define RVU_MBOX_AF_VFAF_INT_ENA_W1S(a) (0x3010 | (a) << 6) +#define RVU_MBOX_AF_VFAF_INT_ENA_W1C(a) (0x3018 | (a) << 6) +#define RVU_MBOX_AF_VFAF_INT_ENA_W1C(a) (0x3018 | (a) << 6) +#define RVU_MBOX_AF_VFAF1_INT(a) (0x3020 | (a) << 6) +#define RVU_MBOX_AF_VFAF1_INT_W1S(a) (0x3028 | (a) << 6) +#define RVU_MBOX_AF_VFAF1_IN_ENA_W1S(a) (0x3030 | (a) << 6) +#define RVU_MBOX_AF_VFAF1_IN_ENA_W1C(a) (0x3038 | (a) << 6) + +#define RVU_MBOX_AF_AFVFX_TRIG(a, b) (0x10000 | (a) << 4 | (b) << 3) +#define RVU_MBOX_AF_VFX_ADDR(a) (0x20000 | (a) << 4) +#define RVU_MBOX_AF_VFX_CFG(a) (0x28000 | (a) << 4) + +#define RVU_MBOX_PF_VFX_PFVF_TRIGX(a) (0x2000 | (a) << 3) + +#define RVU_MBOX_PF_VFPF_INTX(a) (0x1000 | (a) << 3) +#define RVU_MBOX_PF_VFPF_INT_W1SX(a) (0x1020 | (a) << 3) +#define RVU_MBOX_PF_VFPF_INT_ENA_W1SX(a) (0x1040 | (a) << 3) +#define RVU_MBOX_PF_VFPF_INT_ENA_W1CX(a) (0x1060 | (a) << 3) + +#define RVU_MBOX_PF_VFPF1_INTX(a) (0x1080 | (a) << 3) +#define RVU_MBOX_PF_VFPF1_INT_W1SX(a) (0x10a0 | (a) << 3) +#define RVU_MBOX_PF_VFPF1_INT_ENA_W1SX(a) (0x10c0 | (a) << 3) +#define RVU_MBOX_PF_VFPF1_INT_ENA_W1CX(a) (0x10e0 | (a) << 3) + +#define RVU_MBOX_PF_VF_ADDR (0xC40) +#define RVU_MBOX_PF_LMTLINE_ADDR (0xC48) +#define RVU_MBOX_PF_VF_CFG (0xC60) + +#define RVU_MBOX_VF_VFPF_TRIGX(a) (0x3000 | (a) << 3) +#define RVU_MBOX_VF_INT (0x20) +#define RVU_MBOX_VF_INT_W1S (0x28) +#define RVU_MBOX_VF_INT_ENA_W1S (0x30) +#define RVU_MBOX_VF_INT_ENA_W1C (0x38) + +#define RVU_MBOX_VF_VFAF_TRIGX(a) (0x2000 | (a) << 3) +#endif /* RVU_MBOX_REG_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/struct.h b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/struct.h new file mode 100644 index 000000000000..76ce3ec6da9c --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/struct.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell RVU Admin Function driver + * + * Copyright (C) 2024 Marvell. + * + */ + +#ifndef STRUCT_H +#define STRUCT_H + +/* + * CN20k RVU PF MBOX Interrupt Vector Enumeration + * + * Vectors 0 - 3 are compatible with pre cn20k and hence + * existing macros are being reused. + */ +enum rvu_mbox_pf_int_vec_e { + RVU_MBOX_PF_INT_VEC_VFPF_MBOX0 = 0x4, + RVU_MBOX_PF_INT_VEC_VFPF_MBOX1 = 0x5, + RVU_MBOX_PF_INT_VEC_VFPF1_MBOX0 = 0x6, + RVU_MBOX_PF_INT_VEC_VFPF1_MBOX1 = 0x7, + RVU_MBOX_PF_INT_VEC_AFPF_MBOX = 0x8, + RVU_MBOX_PF_INT_VEC_CNT = 0x9, +}; + +/* RVU Admin function Interrupt Vector Enumeration */ +enum rvu_af_cn20k_int_vec_e { + RVU_AF_CN20K_INT_VEC_POISON = 0x0, + RVU_AF_CN20K_INT_VEC_PFFLR0 = 0x1, + RVU_AF_CN20K_INT_VEC_PFFLR1 = 0x2, + RVU_AF_CN20K_INT_VEC_PFME0 = 0x3, + RVU_AF_CN20K_INT_VEC_PFME1 = 0x4, + RVU_AF_CN20K_INT_VEC_GEN = 0x5, + RVU_AF_CN20K_INT_VEC_PFAF_MBOX0 = 0x6, + RVU_AF_CN20K_INT_VEC_PFAF_MBOX1 = 0x7, + RVU_AF_CN20K_INT_VEC_PFAF1_MBOX0 = 0x8, + RVU_AF_CN20K_INT_VEC_PFAF1_MBOX1 = 0x9, + RVU_AF_CN20K_INT_VEC_CNT = 0xa, +}; +#endif diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h index 406c59100a35..8a08bebf08c2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h @@ -39,7 +39,7 @@ struct qmem { void *base; dma_addr_t iova; int alloc_sz; - u16 entry_sz; + u32 entry_sz; u8 align; u32 qsize; }; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c index 7d21905deed8..75872d257eca 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c @@ -10,8 +10,11 @@ #include <linux/pci.h> #include "rvu_reg.h" +#include "cn20k/reg.h" +#include "cn20k/api.h" #include "mbox.h" #include "rvu_trace.h" +#include "rvu.h" static const u16 msgs_offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN); @@ -28,8 +31,10 @@ void __otx2_mbox_reset(struct otx2_mbox *mbox, int devid) mdev->rsp_size = 0; tx_hdr->num_msgs = 0; tx_hdr->msg_size = 0; + tx_hdr->sig = 0; rx_hdr->num_msgs = 0; rx_hdr->msg_size = 0; + rx_hdr->sig = 0; } EXPORT_SYMBOL(__otx2_mbox_reset); @@ -53,9 +58,98 @@ void otx2_mbox_destroy(struct otx2_mbox *mbox) } EXPORT_SYMBOL(otx2_mbox_destroy); +int cn20k_mbox_setup(struct otx2_mbox *mbox, struct pci_dev *pdev, + void *reg_base, int direction, int ndevs) +{ + switch (direction) { + case MBOX_DIR_AFPF: + case MBOX_DIR_PFVF: + mbox->tx_start = MBOX_DOWN_TX_START; + mbox->rx_start = MBOX_DOWN_RX_START; + mbox->tx_size = MBOX_DOWN_TX_SIZE; + mbox->rx_size = MBOX_DOWN_RX_SIZE; + break; + case MBOX_DIR_PFAF: + case MBOX_DIR_VFPF: + mbox->tx_start = MBOX_DOWN_RX_START; + mbox->rx_start = MBOX_DOWN_TX_START; + mbox->tx_size = MBOX_DOWN_RX_SIZE; + mbox->rx_size = MBOX_DOWN_TX_SIZE; + break; + case MBOX_DIR_AFPF_UP: + case MBOX_DIR_PFVF_UP: + mbox->tx_start = MBOX_UP_TX_START; + mbox->rx_start = MBOX_UP_RX_START; + mbox->tx_size = MBOX_UP_TX_SIZE; + mbox->rx_size = MBOX_UP_RX_SIZE; + break; + case MBOX_DIR_PFAF_UP: + case MBOX_DIR_VFPF_UP: + mbox->tx_start = MBOX_UP_RX_START; + mbox->rx_start = MBOX_UP_TX_START; + mbox->tx_size = MBOX_UP_RX_SIZE; + mbox->rx_size = MBOX_UP_TX_SIZE; + break; + default: + return -ENODEV; + } + + switch (direction) { + case MBOX_DIR_AFPF: + mbox->trigger = RVU_MBOX_AF_AFPFX_TRIGX(1); + mbox->tr_shift = 4; + break; + case MBOX_DIR_AFPF_UP: + mbox->trigger = RVU_MBOX_AF_AFPFX_TRIGX(0); + mbox->tr_shift = 4; + break; + case MBOX_DIR_PFAF: + mbox->trigger = RVU_MBOX_PF_PFAF_TRIGX(0); + mbox->tr_shift = 0; + break; + case MBOX_DIR_PFAF_UP: + mbox->trigger = RVU_MBOX_PF_PFAF_TRIGX(1); + mbox->tr_shift = 0; + break; + case MBOX_DIR_PFVF: + mbox->trigger = RVU_MBOX_PF_VFX_PFVF_TRIGX(1); + mbox->tr_shift = 4; + break; + case MBOX_DIR_PFVF_UP: + mbox->trigger = RVU_MBOX_PF_VFX_PFVF_TRIGX(0); + mbox->tr_shift = 4; + break; + case MBOX_DIR_VFPF: + mbox->trigger = RVU_MBOX_VF_VFPF_TRIGX(0); + mbox->tr_shift = 0; + break; + case MBOX_DIR_VFPF_UP: + mbox->trigger = RVU_MBOX_VF_VFPF_TRIGX(1); + mbox->tr_shift = 0; + break; + default: + return -ENODEV; + } + mbox->reg_base = reg_base; + mbox->pdev = pdev; + + mbox->dev = kcalloc(ndevs, sizeof(struct otx2_mbox_dev), GFP_KERNEL); + if (!mbox->dev) { + otx2_mbox_destroy(mbox); + return -ENOMEM; + } + mbox->ndevs = ndevs; + + return 0; +} + static int otx2_mbox_setup(struct otx2_mbox *mbox, struct pci_dev *pdev, void *reg_base, int direction, int ndevs) { + if (is_cn20k(pdev)) + return cn20k_mbox_setup(mbox, pdev, reg_base, + direction, ndevs); + switch (direction) { case MBOX_DIR_AFPF: case MBOX_DIR_PFVF: @@ -234,7 +328,10 @@ static void otx2_mbox_msg_send_data(struct otx2_mbox *mbox, int devid, u64 data) spin_lock(&mdev->mbox_lock); - tx_hdr->msg_size = mdev->msg_size; + if (!tx_hdr->sig) { + tx_hdr->msg_size = mdev->msg_size; + tx_hdr->num_msgs = mdev->num_msgs; + } /* Reset header for next messages */ mdev->msg_size = 0; @@ -248,7 +345,6 @@ static void otx2_mbox_msg_send_data(struct otx2_mbox *mbox, int devid, u64 data) * messages. So this should be written after writing all the messages * to the shared memory. */ - tx_hdr->num_msgs = mdev->num_msgs; rx_hdr->num_msgs = 0; msg = (struct mbox_msghdr *)(hw_mbase + mbox->tx_start + msgs_offset); @@ -309,6 +405,7 @@ struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid, { struct otx2_mbox_dev *mdev = &mbox->dev[devid]; struct mbox_msghdr *msghdr = NULL; + struct mbox_hdr *mboxhdr = NULL; spin_lock(&mdev->mbox_lock); size = ALIGN(size, MBOX_MSG_ALIGN); @@ -332,6 +429,11 @@ struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid, mdev->msg_size += size; mdev->rsp_size += size_rsp; msghdr->next_msgoff = mdev->msg_size + msgs_offset; + + mboxhdr = mdev->mbase + mbox->tx_start; + /* Clear the msg header region */ + memset(mboxhdr, 0, msgs_offset); + exit: spin_unlock(&mdev->mbox_lock); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index a213b2663583..b3562d658d45 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -13,6 +13,7 @@ #include "rvu_struct.h" #include "common.h" +#include "cn20k/struct.h" #define MBOX_SIZE SZ_64K @@ -50,6 +51,11 @@ #define MBOX_DIR_PFVF_UP 6 /* PF sends messages to VF */ #define MBOX_DIR_VFPF_UP 7 /* VF replies to PF */ +enum { + TYPE_AFVF, + TYPE_AFPF, +}; + struct otx2_mbox_dev { void *mbase; /* This dev's mbox region */ void *hwbase; @@ -78,6 +84,8 @@ struct otx2_mbox { struct mbox_hdr { u64 msg_size; /* Total msgs size embedded */ u16 num_msgs; /* No of msgs embedded */ + u16 opt_msg; + u8 sig; }; /* Header which precedes every msg and is also part of it */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c index 0277d226293e..d7030dfa5dad 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c @@ -97,7 +97,7 @@ int mcs_add_intr_wq_entry(struct mcs *mcs, struct mcs_intr_event *event) if (pcifunc & RVU_PFVF_FUNC_MASK) pfvf = &mcs->vf[rvu_get_hwvf(rvu, pcifunc)]; else - pfvf = &mcs->pf[rvu_get_pf(pcifunc)]; + pfvf = &mcs->pf[rvu_get_pf(rvu->pdev, pcifunc)]; event->intr_mask &= pfvf->intr_mask; @@ -123,7 +123,7 @@ static int mcs_notify_pfvf(struct mcs_intr_event *event, struct rvu *rvu) struct mcs_intr_info *req; int pf; - pf = rvu_get_pf(event->pcifunc); + pf = rvu_get_pf(rvu->pdev, event->pcifunc); mutex_lock(&rvu->mbox_lock); @@ -193,7 +193,7 @@ int rvu_mbox_handler_mcs_intr_cfg(struct rvu *rvu, if (pcifunc & RVU_PFVF_FUNC_MASK) pfvf = &mcs->vf[rvu_get_hwvf(rvu, pcifunc)]; else - pfvf = &mcs->pf[rvu_get_pf(pcifunc)]; + pfvf = &mcs->pf[rvu_get_pf(rvu->pdev, pcifunc)]; mcs->pf_map[0] = pcifunc; pfvf->intr_mask = req->intr_mask; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 43eea74bf541..bfee71f4cddc 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_trace.h" #include "rvu_npc_hash.h" +#include "cn20k/reg.h" +#include "cn20k/api.h" #define DRV_NAME "rvu_af" #define DRV_STRING "Marvell OcteonTX2 RVU Admin Function Driver" @@ -34,10 +36,8 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, int type, int num, void (mbox_handler)(struct work_struct *), void (mbox_up_handler)(struct work_struct *)); -enum { - TYPE_AFVF, - TYPE_AFPF, -}; +static irqreturn_t rvu_mbox_pf_intr_handler(int irq, void *rvu_irq); +static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq); /* Supported devices */ static const struct pci_device_id rvu_id_table[] = { @@ -294,7 +294,7 @@ int rvu_get_blkaddr(struct rvu *rvu, int blktype, u16 pcifunc) devnum = rvu_get_hwvf(rvu, pcifunc); } else { is_pf = true; - devnum = rvu_get_pf(pcifunc); + devnum = rvu_get_pf(rvu->pdev, pcifunc); } /* Check if the 'pcifunc' has a NIX LF from 'BLKADDR_NIX0' or @@ -359,7 +359,7 @@ static void rvu_update_rsrc_map(struct rvu *rvu, struct rvu_pfvf *pfvf, devnum = rvu_get_hwvf(rvu, pcifunc); } else { is_pf = true; - devnum = rvu_get_pf(pcifunc); + devnum = rvu_get_pf(rvu->pdev, pcifunc); } block->fn_map[lf] = attach ? pcifunc : 0; @@ -400,11 +400,6 @@ static void rvu_update_rsrc_map(struct rvu *rvu, struct rvu_pfvf *pfvf, rvu_write64(rvu, BLKADDR_RVUM, reg | (devnum << 16), num_lfs); } -inline int rvu_get_pf(u16 pcifunc) -{ - return (pcifunc >> RVU_PFVF_PF_SHIFT) & RVU_PFVF_PF_MASK; -} - void rvu_get_pf_numvfs(struct rvu *rvu, int pf, int *numvfs, int *hwvf) { u64 cfg; @@ -422,7 +417,7 @@ int rvu_get_hwvf(struct rvu *rvu, int pcifunc) int pf, func; u64 cfg; - pf = rvu_get_pf(pcifunc); + pf = rvu_get_pf(rvu->pdev, pcifunc); func = pcifunc & RVU_PFVF_FUNC_MASK; /* Get first HWVF attached to this PF */ @@ -437,7 +432,7 @@ struct rvu_pfvf *rvu_get_pfvf(struct rvu *rvu, int pcifunc) if (pcifunc & RVU_PFVF_FUNC_MASK) return &rvu->hwvf[rvu_get_hwvf(rvu, pcifunc)]; else - return &rvu->pf[rvu_get_pf(pcifunc)]; + return &rvu->pf[rvu_get_pf(rvu->pdev, pcifunc)]; } static bool is_pf_func_valid(struct rvu *rvu, u16 pcifunc) @@ -445,7 +440,7 @@ static bool is_pf_func_valid(struct rvu *rvu, u16 pcifunc) int pf, vf, nvfs; u64 cfg; - pf = rvu_get_pf(pcifunc); + pf = rvu_get_pf(rvu->pdev, pcifunc); if (pf >= rvu->hw->total_pfs) return false; @@ -760,6 +755,11 @@ static void rvu_free_hw_resources(struct rvu *rvu) rvu_reset_msix(rvu); mutex_destroy(&rvu->rsrc_lock); + + /* Free the QINT/CINT memory */ + pfvf = &rvu->pf[RVU_AFPF]; + qmem_free(rvu->dev, pfvf->nix_qints_ctx); + qmem_free(rvu->dev, pfvf->cq_ints_ctx); } static void rvu_setup_pfvf_macaddress(struct rvu *rvu) @@ -1487,7 +1487,7 @@ int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc) pf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK); /* All CGX mapped PFs are set with assigned NIX block during init */ - if (is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) { + if (is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc))) { blkaddr = pf->nix_blkaddr; } else if (is_lbk_vf(rvu, pcifunc)) { vf = pcifunc - 1; @@ -1501,7 +1501,7 @@ int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc) } /* if SDP1 then the blkaddr is NIX1 */ - if (is_sdp_pfvf(pcifunc) && pf->sdp_info->node_id == 1) + if (is_sdp_pfvf(rvu, pcifunc) && pf->sdp_info->node_id == 1) blkaddr = BLKADDR_NIX1; switch (blkaddr) { @@ -2006,7 +2006,7 @@ int rvu_mbox_handler_vf_flr(struct rvu *rvu, struct msg_req *req, vf = pcifunc & RVU_PFVF_FUNC_MASK; cfg = rvu_read64(rvu, BLKADDR_RVUM, - RVU_PRIV_PFX_CFG(rvu_get_pf(pcifunc))); + RVU_PRIV_PFX_CFG(rvu_get_pf(rvu->pdev, pcifunc))); numvfs = (cfg >> 12) & 0xFF; if (vf && vf <= numvfs) @@ -2223,15 +2223,30 @@ static void __rvu_mbox_handler(struct rvu_work *mwork, int type, bool poll) offset = mbox->rx_start + ALIGN(sizeof(*req_hdr), MBOX_MSG_ALIGN); + if (req_hdr->sig && !(is_rvu_otx2(rvu) || is_cn20k(rvu->pdev))) { + req_hdr->opt_msg = mw->mbox_wrk[devid].num_msgs; + rvu_write64(rvu, BLKADDR_NIX0, RVU_AF_BAR2_SEL, + RVU_AF_BAR2_PFID); + if (type == TYPE_AFPF) + rvu_write64(rvu, BLKADDR_NIX0, + AF_BAR2_ALIASX(0, NIX_CINTX_INT_W1S(devid)), + 0x1); + else + rvu_write64(rvu, BLKADDR_NIX0, + AF_BAR2_ALIASX(0, NIX_QINTX_CNT(devid)), + 0x1); + usleep_range(5000, 6000); + goto done; + } + for (id = 0; id < mw->mbox_wrk[devid].num_msgs; id++) { msg = mdev->mbase + offset; /* Set which PF/VF sent this message based on mbox IRQ */ switch (type) { case TYPE_AFPF: - msg->pcifunc &= - ~(RVU_PFVF_PF_MASK << RVU_PFVF_PF_SHIFT); - msg->pcifunc |= (devid << RVU_PFVF_PF_SHIFT); + msg->pcifunc &= rvu_pcifunc_pf_mask(rvu->pdev); + msg->pcifunc |= rvu_make_pcifunc(rvu->pdev, devid, 0); break; case TYPE_AFVF: msg->pcifunc &= @@ -2249,16 +2264,17 @@ static void __rvu_mbox_handler(struct rvu_work *mwork, int type, bool poll) if (msg->pcifunc & RVU_PFVF_FUNC_MASK) dev_warn(rvu->dev, "Error %d when processing message %s (0x%x) from PF%d:VF%d\n", err, otx2_mbox_id2name(msg->id), - msg->id, rvu_get_pf(msg->pcifunc), + msg->id, rvu_get_pf(rvu->pdev, msg->pcifunc), (msg->pcifunc & RVU_PFVF_FUNC_MASK) - 1); else dev_warn(rvu->dev, "Error %d when processing message %s (0x%x) from PF%d\n", err, otx2_mbox_id2name(msg->id), msg->id, devid); } +done: mw->mbox_wrk[devid].num_msgs = 0; - if (poll) + if (!is_cn20k(mbox->pdev) && poll) otx2_mbox_wait_for_zero(mbox, devid); /* Send mbox responses to VF/PF */ @@ -2371,6 +2387,14 @@ static int rvu_get_mbox_regions(struct rvu *rvu, void __iomem **mbox_addr, int region; u64 bar4; + /* For cn20k platform AF mailbox region is allocated by software + * and the corresponding IOVA is programmed in hardware unlike earlier + * silicons where software uses the hardware region after ioremap. + */ + if (is_cn20k(rvu->pdev)) + return cn20k_rvu_get_mbox_regions(rvu, (void *)mbox_addr, + num, type, pf_bmap); + /* For cn10k platform VF mailbox regions of a PF follows after the * PF <-> AF mailbox region. Whereas for Octeontx2 it is read from * RVU_PF_VF_BAR4_ADDR register. @@ -2424,6 +2448,11 @@ error: return -ENOMEM; } +static struct mbox_ops rvu_mbox_ops = { + .pf_intr_handler = rvu_mbox_pf_intr_handler, + .afvf_intr_handler = rvu_mbox_intr_handler, +}; + static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, int type, int num, void (mbox_handler)(struct work_struct *), @@ -2431,6 +2460,7 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, { int err = -EINVAL, i, dir, dir_up; void __iomem **mbox_regions; + struct ng_rvu *ng_rvu_mbox; void __iomem *reg_base; struct rvu_work *mwork; unsigned long *pf_bmap; @@ -2441,6 +2471,12 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, if (!pf_bmap) return -ENOMEM; + ng_rvu_mbox = kzalloc(sizeof(*ng_rvu_mbox), GFP_KERNEL); + if (!ng_rvu_mbox) { + err = -ENOMEM; + goto free_bitmap; + } + /* RVU VFs */ if (type == TYPE_AFVF) bitmap_set(pf_bmap, 0, num); @@ -2454,12 +2490,20 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, } } + rvu->ng_rvu = ng_rvu_mbox; + + rvu->ng_rvu->rvu_mbox_ops = &rvu_mbox_ops; + + err = cn20k_rvu_mbox_init(rvu, type, num); + if (err) + goto free_mem; + mutex_init(&rvu->mbox_lock); mbox_regions = kcalloc(num, sizeof(void __iomem *), GFP_KERNEL); if (!mbox_regions) { err = -ENOMEM; - goto free_bitmap; + goto free_qmem; } switch (type) { @@ -2486,7 +2530,7 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, } mw->mbox_wq = alloc_workqueue("%s", - WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM, + WQ_HIGHPRI | WQ_MEM_RECLAIM, num, name); if (!mw->mbox_wq) { err = -ENOMEM; @@ -2538,6 +2582,10 @@ unmap_regions: iounmap((void __iomem *)mbox_regions[num]); free_regions: kfree(mbox_regions); +free_qmem: + cn20k_free_mbox_memory(rvu); +free_mem: + kfree(rvu->ng_rvu); free_bitmap: bitmap_free(pf_bmap); return err; @@ -2564,8 +2612,8 @@ static void rvu_mbox_destroy(struct mbox_wq_info *mw) otx2_mbox_destroy(&mw->mbox_up); } -static void rvu_queue_work(struct mbox_wq_info *mw, int first, - int mdevs, u64 intr) +void rvu_queue_work(struct mbox_wq_info *mw, int first, + int mdevs, u64 intr) { struct otx2_mbox_dev *mdev; struct otx2_mbox *mbox; @@ -2656,6 +2704,11 @@ static void rvu_enable_mbox_intr(struct rvu *rvu) { struct rvu_hwinfo *hw = rvu->hw; + if (is_cn20k(rvu->pdev)) { + cn20k_rvu_enable_mbox_intr(rvu); + return; + } + /* Clear spurious irqs, if any */ rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT, INTR_MASK(hw->total_pfs)); @@ -2773,7 +2826,7 @@ static void rvu_flr_handler(struct work_struct *work) cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf)); numvfs = (cfg >> 12) & 0xFF; - pcifunc = pf << RVU_PFVF_PF_SHIFT; + pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0); for (vf = 0; vf < numvfs; vf++) __rvu_flr_handler(rvu, (pcifunc | (vf + 1))); @@ -2909,9 +2962,12 @@ static void rvu_unregister_interrupts(struct rvu *rvu) rvu_cpt_unregister_interrupts(rvu); - /* Disable the Mbox interrupt */ - rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT_ENA_W1C, - INTR_MASK(rvu->hw->total_pfs) & ~1ULL); + if (!is_cn20k(rvu->pdev)) + /* Disable the Mbox interrupt */ + rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT_ENA_W1C, + INTR_MASK(rvu->hw->total_pfs) & ~1ULL); + else + cn20k_rvu_unregister_interrupts(rvu); /* Disable the PF FLR interrupt */ rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT_ENA_W1C, @@ -2944,6 +3000,10 @@ static int rvu_afvf_msix_vectors_num_ok(struct rvu *rvu) * VF interrupts can be handled. Offset equal to zero means * that PF vectors are not configured and overlapping AF vectors. */ + if (is_cn20k(rvu->pdev)) + return (pfvf->msix.max >= RVU_AF_CN20K_INT_VEC_CNT + + RVU_MBOX_PF_INT_VEC_CNT) && offset; + return (pfvf->msix.max >= RVU_AF_INT_VEC_CNT + RVU_PF_INT_VEC_CNT) && offset; } @@ -2974,18 +3034,30 @@ static int rvu_register_interrupts(struct rvu *rvu) return ret; } - /* Register mailbox interrupt handler */ - sprintf(&rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], "RVUAF Mbox"); - ret = request_irq(pci_irq_vector(rvu->pdev, RVU_AF_INT_VEC_MBOX), - rvu_mbox_pf_intr_handler, 0, - &rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], rvu); - if (ret) { - dev_err(rvu->dev, - "RVUAF: IRQ registration failed for mbox irq\n"); - goto fail; - } + if (!is_cn20k(rvu->pdev)) { + /* Register mailbox interrupt handler */ + sprintf(&rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], + "RVUAF Mbox"); + ret = request_irq(pci_irq_vector + (rvu->pdev, RVU_AF_INT_VEC_MBOX), + rvu->ng_rvu->rvu_mbox_ops->pf_intr_handler, 0, + &rvu->irq_name[RVU_AF_INT_VEC_MBOX * + NAME_SIZE], rvu); + if (ret) { + dev_err(rvu->dev, + "RVUAF: IRQ registration failed for mbox\n"); + goto fail; + } - rvu->irq_allocated[RVU_AF_INT_VEC_MBOX] = true; + rvu->irq_allocated[RVU_AF_INT_VEC_MBOX] = true; + } else { + ret = cn20k_register_afpf_mbox_intr(rvu); + if (ret) { + dev_err(rvu->dev, + "RVUAF: IRQ registration failed for mbox\n"); + goto fail; + } + } /* Enable mailbox interrupts from all PFs */ rvu_enable_mbox_intr(rvu); @@ -3040,34 +3112,40 @@ static int rvu_register_interrupts(struct rvu *rvu) /* Get PF MSIX vectors offset. */ pf_vec_start = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_INT_CFG(0)) & 0x3ff; + if (!is_cn20k(rvu->pdev)) { + /* Register MBOX0 interrupt. */ + offset = pf_vec_start + RVU_PF_INT_VEC_VFPF_MBOX0; + sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF Mbox0"); + ret = request_irq(pci_irq_vector(rvu->pdev, offset), + rvu->ng_rvu->rvu_mbox_ops->afvf_intr_handler, 0, + &rvu->irq_name[offset * NAME_SIZE], + rvu); + if (ret) + dev_err(rvu->dev, + "RVUAF: IRQ registration failed for Mbox0\n"); - /* Register MBOX0 interrupt. */ - offset = pf_vec_start + RVU_PF_INT_VEC_VFPF_MBOX0; - sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF Mbox0"); - ret = request_irq(pci_irq_vector(rvu->pdev, offset), - rvu_mbox_intr_handler, 0, - &rvu->irq_name[offset * NAME_SIZE], - rvu); - if (ret) - dev_err(rvu->dev, - "RVUAF: IRQ registration failed for Mbox0\n"); - - rvu->irq_allocated[offset] = true; + rvu->irq_allocated[offset] = true; - /* Register MBOX1 interrupt. MBOX1 IRQ number follows MBOX0 so - * simply increment current offset by 1. - */ - offset = pf_vec_start + RVU_PF_INT_VEC_VFPF_MBOX1; - sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF Mbox1"); - ret = request_irq(pci_irq_vector(rvu->pdev, offset), - rvu_mbox_intr_handler, 0, - &rvu->irq_name[offset * NAME_SIZE], - rvu); - if (ret) - dev_err(rvu->dev, - "RVUAF: IRQ registration failed for Mbox1\n"); + /* Register MBOX1 interrupt. MBOX1 IRQ number follows MBOX0 so + * simply increment current offset by 1. + */ + offset = pf_vec_start + RVU_PF_INT_VEC_VFPF_MBOX1; + sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF Mbox1"); + ret = request_irq(pci_irq_vector(rvu->pdev, offset), + rvu->ng_rvu->rvu_mbox_ops->afvf_intr_handler, 0, + &rvu->irq_name[offset * NAME_SIZE], + rvu); + if (ret) + dev_err(rvu->dev, + "RVUAF: IRQ registration failed for Mbox1\n"); - rvu->irq_allocated[offset] = true; + rvu->irq_allocated[offset] = true; + } else { + ret = cn20k_register_afvf_mbox_intr(rvu, pf_vec_start); + if (ret) + dev_err(rvu->dev, + "RVUAF: IRQ registration failed for Mbox\n"); + } /* Register FLR interrupt handler for AF's VFs */ offset = pf_vec_start + RVU_PF_INT_VEC_VFFLR0; @@ -3178,6 +3256,9 @@ static void rvu_disable_afvf_intr(struct rvu *rvu) { int vfs = rvu->vfs; + if (is_cn20k(rvu->pdev)) + return cn20k_rvu_disable_afvf_intr(rvu, vfs); + rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(0), INTR_MASK(vfs)); rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1CX(0), INTR_MASK(vfs)); rvupf_write64(rvu, RVU_PF_VFME_INT_ENA_W1CX(0), INTR_MASK(vfs)); @@ -3194,6 +3275,9 @@ static void rvu_enable_afvf_intr(struct rvu *rvu) { int vfs = rvu->vfs; + if (is_cn20k(rvu->pdev)) + return cn20k_rvu_enable_afvf_intr(rvu, vfs); + /* Clear any pending interrupts and enable AF VF interrupts for * the first 64 VFs. */ @@ -3438,6 +3522,9 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id) ptp_start(rvu, rvu->fwdata->sclk, rvu->fwdata->ptp_ext_clk_rate, rvu->fwdata->ptp_ext_tstamp); + /* Alloc CINT and QINT memory */ + rvu_alloc_cint_qint_mem(rvu, &rvu->pf[RVU_AFPF], BLKADDR_NIX0, + (rvu->hw->block[BLKADDR_NIX0].lf.max)); return 0; err_dl: rvu_unregister_dl(rvu); @@ -3489,6 +3576,9 @@ static void rvu_remove(struct pci_dev *pdev) pci_set_drvdata(pdev, NULL); devm_kfree(&pdev->dev, rvu->hw); + if (is_cn20k(rvu->pdev)) + cn20k_free_mbox_memory(rvu); + kfree(rvu->ng_rvu); devm_kfree(&pdev->dev, rvu); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 48f66292ad5c..7ee1fdeb5295 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -10,6 +10,7 @@ #include <linux/pci.h> #include <net/devlink.h> +#include <linux/soc/marvell/silicons.h> #include "rvu_struct.h" #include "rvu_devlink.h" @@ -43,12 +44,39 @@ #define MAX_CPT_BLKS 2 /* PF_FUNC */ -#define RVU_PFVF_PF_SHIFT 10 -#define RVU_PFVF_PF_MASK 0x3F -#define RVU_PFVF_FUNC_SHIFT 0 -#define RVU_PFVF_FUNC_MASK 0x3FF +#define RVU_OTX2_PFVF_PF_SHIFT 10 +#define RVU_OTX2_PFVF_PF_MASK 0x3F +#define RVU_PFVF_FUNC_SHIFT 0 +#define RVU_PFVF_FUNC_MASK 0x3FF +#define RVU_CN20K_PFVF_PF_SHIFT 9 +#define RVU_CN20K_PFVF_PF_MASK 0x7F + +static inline u16 rvu_make_pcifunc(struct pci_dev *pdev, int pf, int func) +{ + if (is_cn20k(pdev)) + return ((pf & RVU_CN20K_PFVF_PF_MASK) << + RVU_CN20K_PFVF_PF_SHIFT) | + ((func & RVU_PFVF_FUNC_MASK) << + RVU_PFVF_FUNC_SHIFT); + else + return ((pf & RVU_OTX2_PFVF_PF_MASK) << + RVU_OTX2_PFVF_PF_SHIFT) | + ((func & RVU_PFVF_FUNC_MASK) << + RVU_PFVF_FUNC_SHIFT); +} + +static inline int rvu_pcifunc_pf_mask(struct pci_dev *pdev) +{ + if (is_cn20k(pdev)) + return ~(RVU_CN20K_PFVF_PF_MASK << RVU_CN20K_PFVF_PF_SHIFT); + else + return ~(RVU_OTX2_PFVF_PF_MASK << RVU_OTX2_PFVF_PF_SHIFT); +} + +#define RVU_AFPF 25 #ifdef CONFIG_DEBUG_FS + struct dump_ctx { int lf; int id; @@ -446,6 +474,23 @@ struct mbox_wq_info { struct workqueue_struct *mbox_wq; }; +struct rvu_irq_data { + u64 intr_status; + void (*rvu_queue_work_hdlr)(struct mbox_wq_info *mw, int first, + int mdevs, u64 intr); + void (*afvf_queue_work_hdlr)(struct mbox_wq_info *mw, int first, + int mdevs, u64 intr); + struct rvu *rvu; + int vec_num; + int start; + int mdevs; +}; + +struct mbox_ops { + irqreturn_t (*pf_intr_handler)(int irq, void *rvu_irq); + irqreturn_t (*afvf_intr_handler)(int irq, void *rvu_irq); +}; + struct channel_fwdata { struct sdp_node_info info; u8 valid; @@ -611,6 +656,8 @@ struct rvu { struct list_head rep_evtq_head; /* Representor event lock */ spinlock_t rep_evtq_lock; + + struct ng_rvu *ng_rvu; }; static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val) @@ -836,7 +883,6 @@ int rvu_alloc_rsrc_contig(struct rsrc_bmap *rsrc, int nrsrc); void rvu_free_rsrc_contig(struct rsrc_bmap *rsrc, int nrsrc, int start); bool rvu_rsrc_check_contig(struct rsrc_bmap *rsrc, int nrsrc); u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blkaddr); -int rvu_get_pf(u16 pcifunc); struct rvu_pfvf *rvu_get_pfvf(struct rvu *rvu, int pcifunc); void rvu_get_pf_numvfs(struct rvu *rvu, int pf, int *numvfs, int *hwvf); bool is_block_implemented(struct rvu_hwinfo *hw, int blkaddr); @@ -865,8 +911,8 @@ void rvu_aq_free(struct rvu *rvu, struct admin_queue *aq); /* SDP APIs */ int rvu_sdp_init(struct rvu *rvu); -bool is_sdp_pfvf(u16 pcifunc); -bool is_sdp_pf(u16 pcifunc); +bool is_sdp_pfvf(struct rvu *rvu, u16 pcifunc); +bool is_sdp_pf(struct rvu *rvu, u16 pcifunc); bool is_sdp_vf(struct rvu *rvu, u16 pcifunc); static inline bool is_rep_dev(struct rvu *rvu, u16 pcifunc) @@ -877,11 +923,21 @@ static inline bool is_rep_dev(struct rvu *rvu, u16 pcifunc) return false; } +static inline int rvu_get_pf(struct pci_dev *pdev, u16 pcifunc) +{ + if (is_cn20k(pdev)) + return (pcifunc >> RVU_CN20K_PFVF_PF_SHIFT) & + RVU_CN20K_PFVF_PF_MASK; + else + return (pcifunc >> RVU_OTX2_PFVF_PF_SHIFT) & + RVU_OTX2_PFVF_PF_MASK; +} + /* CGX APIs */ static inline bool is_pf_cgxmapped(struct rvu *rvu, u8 pf) { return (pf >= PF_CGXMAP_BASE && pf <= rvu->cgx_mapped_pfs) && - !is_sdp_pf(pf << RVU_PFVF_PF_SHIFT); + !is_sdp_pf(rvu, rvu_make_pcifunc(rvu->pdev, pf, 0)); } static inline void rvu_get_cgx_lmac_id(u8 map, u8 *cgx_id, u8 *lmac_id) @@ -893,7 +949,7 @@ static inline void rvu_get_cgx_lmac_id(u8 map, u8 *cgx_id, u8 *lmac_id) static inline bool is_cgx_vf(struct rvu *rvu, u16 pcifunc) { return ((pcifunc & RVU_PFVF_FUNC_MASK) && - is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))); + is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc))); } #define M(_name, _id, fn_name, req, rsp) \ @@ -901,6 +957,10 @@ int rvu_mbox_handler_ ## fn_name(struct rvu *, struct req *, struct rsp *); MBOX_MESSAGES #undef M +/* Mbox APIs */ +void rvu_queue_work(struct mbox_wq_info *mw, int first, + int mdevs, u64 intr); + int rvu_cgx_init(struct rvu *rvu); int rvu_cgx_exit(struct rvu *rvu); void *rvu_cgx_pdata(u8 cgx_id, struct rvu *rvu); @@ -955,7 +1015,8 @@ int rvu_nix_mcast_get_mce_index(struct rvu *rvu, u16 pcifunc, int rvu_nix_mcast_update_mcam_entry(struct rvu *rvu, u16 pcifunc, u32 mcast_grp_idx, u16 mcam_index); void rvu_nix_flr_free_bpids(struct rvu *rvu, u16 pcifunc); - +int rvu_alloc_cint_qint_mem(struct rvu *rvu, struct rvu_pfvf *pfvf, + int blkaddr, int nixlf); /* NPC APIs */ void rvu_npc_freemem(struct rvu *rvu); int rvu_npc_get_pkind(struct rvu *rvu, u16 pf); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index d0331b0e0bfd..b79db887ab9b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -457,7 +457,7 @@ int rvu_cgx_exit(struct rvu *rvu) inline bool is_cgx_config_permitted(struct rvu *rvu, u16 pcifunc) { if ((pcifunc & RVU_PFVF_FUNC_MASK) || - !is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) + !is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc))) return false; return true; } @@ -484,7 +484,7 @@ void rvu_cgx_enadis_rx_bp(struct rvu *rvu, int pf, bool enable) int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start) { - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); struct mac_ops *mac_ops; u8 cgx_id, lmac_id; void *cgxd; @@ -501,7 +501,7 @@ int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start) int rvu_cgx_tx_enable(struct rvu *rvu, u16 pcifunc, bool enable) { - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); struct mac_ops *mac_ops; u8 cgx_id, lmac_id; void *cgxd; @@ -526,7 +526,7 @@ int rvu_cgx_config_tx(void *cgxd, int lmac_id, bool enable) void rvu_cgx_disable_dmac_entries(struct rvu *rvu, u16 pcifunc) { - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); int i = 0, lmac_count = 0; struct mac_ops *mac_ops; u8 max_dmac_filters; @@ -577,7 +577,7 @@ int rvu_mbox_handler_cgx_stop_rxtx(struct rvu *rvu, struct msg_req *req, static int rvu_lmac_get_stats(struct rvu *rvu, struct msg_req *req, void *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); struct mac_ops *mac_ops; int stat = 0, err = 0; u64 tx_stat, rx_stat; @@ -633,7 +633,7 @@ int rvu_mbox_handler_rpm_stats(struct rvu *rvu, struct msg_req *req, int rvu_mbox_handler_cgx_stats_rst(struct rvu *rvu, struct msg_req *req, struct msg_rsp *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); struct rvu_pfvf *parent_pf; struct mac_ops *mac_ops; u8 cgx_idx, lmac; @@ -663,7 +663,7 @@ int rvu_mbox_handler_cgx_fec_stats(struct rvu *rvu, struct msg_req *req, struct cgx_fec_stats_rsp *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); struct mac_ops *mac_ops; u8 cgx_idx, lmac; void *cgxd; @@ -681,7 +681,7 @@ int rvu_mbox_handler_cgx_mac_addr_set(struct rvu *rvu, struct cgx_mac_addr_set_or_get *req, struct cgx_mac_addr_set_or_get *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); u8 cgx_id, lmac_id; if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) @@ -701,7 +701,7 @@ int rvu_mbox_handler_cgx_mac_addr_add(struct rvu *rvu, struct cgx_mac_addr_add_req *req, struct cgx_mac_addr_add_rsp *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); u8 cgx_id, lmac_id; int rc = 0; @@ -725,7 +725,7 @@ int rvu_mbox_handler_cgx_mac_addr_del(struct rvu *rvu, struct cgx_mac_addr_del_req *req, struct msg_rsp *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); u8 cgx_id, lmac_id; if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) @@ -743,7 +743,7 @@ int rvu_mbox_handler_cgx_mac_max_entries_get(struct rvu *rvu, struct cgx_max_dmac_entries_get_rsp *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); u8 cgx_id, lmac_id; /* If msg is received from PFs(which are not mapped to CGX LMACs) @@ -769,7 +769,7 @@ int rvu_mbox_handler_cgx_mac_addr_get(struct rvu *rvu, struct cgx_mac_addr_set_or_get *req, struct cgx_mac_addr_set_or_get *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); u8 cgx_id, lmac_id; int rc = 0; u64 cfg; @@ -790,7 +790,7 @@ int rvu_mbox_handler_cgx_promisc_enable(struct rvu *rvu, struct msg_req *req, struct msg_rsp *rsp) { u16 pcifunc = req->hdr.pcifunc; - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); u8 cgx_id, lmac_id; if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) @@ -809,7 +809,7 @@ int rvu_mbox_handler_cgx_promisc_enable(struct rvu *rvu, struct msg_req *req, int rvu_mbox_handler_cgx_promisc_disable(struct rvu *rvu, struct msg_req *req, struct msg_rsp *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); u8 cgx_id, lmac_id; if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) @@ -828,7 +828,7 @@ int rvu_mbox_handler_cgx_promisc_disable(struct rvu *rvu, struct msg_req *req, static int rvu_cgx_ptp_rx_cfg(struct rvu *rvu, u16 pcifunc, bool enable) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); struct mac_ops *mac_ops; u8 cgx_id, lmac_id; void *cgxd; @@ -864,7 +864,7 @@ static int rvu_cgx_ptp_rx_cfg(struct rvu *rvu, u16 pcifunc, bool enable) int rvu_mbox_handler_cgx_ptp_rx_enable(struct rvu *rvu, struct msg_req *req, struct msg_rsp *rsp) { - if (!is_pf_cgxmapped(rvu, rvu_get_pf(req->hdr.pcifunc))) + if (!is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, req->hdr.pcifunc))) return -EPERM; return rvu_cgx_ptp_rx_cfg(rvu, req->hdr.pcifunc, true); @@ -878,7 +878,7 @@ int rvu_mbox_handler_cgx_ptp_rx_disable(struct rvu *rvu, struct msg_req *req, static int rvu_cgx_config_linkevents(struct rvu *rvu, u16 pcifunc, bool en) { - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); u8 cgx_id, lmac_id; if (!is_cgx_config_permitted(rvu, pcifunc)) @@ -917,7 +917,7 @@ int rvu_mbox_handler_cgx_get_linkinfo(struct rvu *rvu, struct msg_req *req, u8 cgx_id, lmac_id; int pf, err; - pf = rvu_get_pf(req->hdr.pcifunc); + pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); if (!is_pf_cgxmapped(rvu, pf)) return -ENODEV; @@ -933,7 +933,7 @@ int rvu_mbox_handler_cgx_features_get(struct rvu *rvu, struct msg_req *req, struct cgx_features_info_msg *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); u8 cgx_idx, lmac; void *cgxd; @@ -975,7 +975,7 @@ u32 rvu_cgx_get_lmac_fifolen(struct rvu *rvu, int cgx, int lmac) static int rvu_cgx_config_intlbk(struct rvu *rvu, u16 pcifunc, bool en) { - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); struct mac_ops *mac_ops; u8 cgx_id, lmac_id; @@ -1005,7 +1005,7 @@ int rvu_mbox_handler_cgx_intlbk_disable(struct rvu *rvu, struct msg_req *req, int rvu_cgx_cfg_pause_frm(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause) { - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); u8 rx_pfc = 0, tx_pfc = 0; struct mac_ops *mac_ops; u8 cgx_id, lmac_id; @@ -1046,7 +1046,7 @@ int rvu_mbox_handler_cgx_cfg_pause_frm(struct rvu *rvu, struct cgx_pause_frm_cfg *req, struct cgx_pause_frm_cfg *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); struct mac_ops *mac_ops; u8 cgx_id, lmac_id; int err = 0; @@ -1073,7 +1073,7 @@ int rvu_mbox_handler_cgx_cfg_pause_frm(struct rvu *rvu, int rvu_mbox_handler_cgx_get_phy_fec_stats(struct rvu *rvu, struct msg_req *req, struct msg_rsp *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); u8 cgx_id, lmac_id; if (!is_pf_cgxmapped(rvu, pf)) @@ -1106,7 +1106,7 @@ int rvu_cgx_nix_cuml_stats(struct rvu *rvu, void *cgxd, int lmac_id, /* Assumes LF of a PF and all of its VF belongs to the same * NIX block */ - pcifunc = pf << RVU_PFVF_PF_SHIFT; + pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0); blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); if (blkaddr < 0) return 0; @@ -1133,10 +1133,10 @@ int rvu_cgx_start_stop_io(struct rvu *rvu, u16 pcifunc, bool start) struct rvu_pfvf *parent_pf, *pfvf; int cgx_users, err = 0; - if (!is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) + if (!is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc))) return 0; - parent_pf = &rvu->pf[rvu_get_pf(pcifunc)]; + parent_pf = &rvu->pf[rvu_get_pf(rvu->pdev, pcifunc)]; pfvf = rvu_get_pfvf(rvu, pcifunc); mutex_lock(&rvu->cgx_cfg_lock); @@ -1179,7 +1179,7 @@ int rvu_mbox_handler_cgx_set_fec_param(struct rvu *rvu, struct fec_mode *req, struct fec_mode *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); u8 cgx_id, lmac_id; if (!is_pf_cgxmapped(rvu, pf)) @@ -1195,7 +1195,7 @@ int rvu_mbox_handler_cgx_set_fec_param(struct rvu *rvu, int rvu_mbox_handler_cgx_get_aux_link_info(struct rvu *rvu, struct msg_req *req, struct cgx_fw_data *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); u8 cgx_id, lmac_id; if (!rvu->fwdata) @@ -1222,7 +1222,7 @@ int rvu_mbox_handler_cgx_set_link_mode(struct rvu *rvu, struct cgx_set_link_mode_req *req, struct cgx_set_link_mode_rsp *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); u8 cgx_idx, lmac; void *cgxd; @@ -1238,7 +1238,7 @@ int rvu_mbox_handler_cgx_set_link_mode(struct rvu *rvu, int rvu_mbox_handler_cgx_mac_addr_reset(struct rvu *rvu, struct cgx_mac_addr_reset_req *req, struct msg_rsp *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); u8 cgx_id, lmac_id; if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) @@ -1256,7 +1256,7 @@ int rvu_mbox_handler_cgx_mac_addr_update(struct rvu *rvu, struct cgx_mac_addr_update_req *req, struct cgx_mac_addr_update_rsp *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); u8 cgx_id, lmac_id; if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) @@ -1272,7 +1272,7 @@ int rvu_mbox_handler_cgx_mac_addr_update(struct rvu *rvu, int rvu_cgx_prio_flow_ctrl_cfg(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause, u16 pfc_en) { - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); u8 rx_8023 = 0, tx_8023 = 0; struct mac_ops *mac_ops; u8 cgx_id, lmac_id; @@ -1310,7 +1310,7 @@ int rvu_mbox_handler_cgx_prio_flow_ctrl_cfg(struct rvu *rvu, struct cgx_pfc_cfg *req, struct cgx_pfc_rsp *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); struct mac_ops *mac_ops; u8 cgx_id, lmac_id; void *cgxd; @@ -1335,7 +1335,7 @@ int rvu_mbox_handler_cgx_prio_flow_ctrl_cfg(struct rvu *rvu, void rvu_mac_reset(struct rvu *rvu, u16 pcifunc) { - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); struct mac_ops *mac_ops; struct cgx *cgxd; u8 cgx, lmac; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c index 4a3370a40dd8..05adc54535eb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c @@ -66,7 +66,7 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val, #define LMT_MAP_TBL_W1_OFF 8 static u32 rvu_get_lmtst_tbl_index(struct rvu *rvu, u16 pcifunc) { - return ((rvu_get_pf(pcifunc) * LMT_MAX_VFS) + + return ((rvu_get_pf(rvu->pdev, pcifunc) * LMT_MAX_VFS) + (pcifunc & RVU_PFVF_FUNC_MASK)) * LMT_MAPTBL_ENTRY_SIZE; } @@ -83,7 +83,7 @@ static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc, mutex_lock(&rvu->rsrc_lock); rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_REQ, iova); - pf = rvu_get_pf(pcifunc) & RVU_PFVF_PF_MASK; + pf = rvu_get_pf(rvu->pdev, pcifunc) & RVU_OTX2_PFVF_PF_MASK; val = BIT_ULL(63) | BIT_ULL(14) | BIT_ULL(13) | pf << 8 | ((pcifunc & RVU_PFVF_FUNC_MASK) & 0xFF); rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TXN_REQ, val); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c index 3c5bbaf12e59..f404117bf6c8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c @@ -410,7 +410,7 @@ static bool is_cpt_pf(struct rvu *rvu, u16 pcifunc) { int cpt_pf_num = rvu->cpt_pf_num; - if (rvu_get_pf(pcifunc) != cpt_pf_num) + if (rvu_get_pf(rvu->pdev, pcifunc) != cpt_pf_num) return false; if (pcifunc & RVU_PFVF_FUNC_MASK) return false; @@ -422,7 +422,7 @@ static bool is_cpt_vf(struct rvu *rvu, u16 pcifunc) { int cpt_pf_num = rvu->cpt_pf_num; - if (rvu_get_pf(pcifunc) != cpt_pf_num) + if (rvu_get_pf(rvu->pdev, pcifunc) != cpt_pf_num) return false; if (!(pcifunc & RVU_PFVF_FUNC_MASK)) return false; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index c827da626471..0c20642f81b9 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -688,7 +688,7 @@ static int get_max_column_width(struct rvu *rvu) for (pf = 0; pf < rvu->hw->total_pfs; pf++) { for (vf = 0; vf <= rvu->hw->total_vfs; vf++) { - pcifunc = pf << 10 | vf; + pcifunc = rvu_make_pcifunc(rvu->pdev, pf, vf); if (!pcifunc) continue; @@ -759,7 +759,7 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, for (vf = 0; vf <= rvu->hw->total_vfs; vf++) { off = 0; flag = 0; - pcifunc = pf << 10 | vf; + pcifunc = rvu_make_pcifunc(rvu->pdev, pf, vf); if (!pcifunc) continue; @@ -842,7 +842,7 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused) cgx[0] = 0; lmac[0] = 0; - pcifunc = pf << 10; + pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0); pfvf = rvu_get_pfvf(rvu, pcifunc); if (pfvf->nix_blkaddr == BLKADDR_NIX0) @@ -2623,10 +2623,10 @@ static int rvu_dbg_nix_band_prof_ctx_display(struct seq_file *m, void *unused) pcifunc = ipolicer->pfvf_map[idx]; if (!(pcifunc & RVU_PFVF_FUNC_MASK)) seq_printf(m, "Allocated to :: PF %d\n", - rvu_get_pf(pcifunc)); + rvu_get_pf(rvu->pdev, pcifunc)); else seq_printf(m, "Allocated to :: PF %d VF %d\n", - rvu_get_pf(pcifunc), + rvu_get_pf(rvu->pdev, pcifunc), (pcifunc & RVU_PFVF_FUNC_MASK) - 1); print_band_prof_ctx(m, &aq_rsp.prof); } @@ -2983,10 +2983,10 @@ static void rvu_print_npc_mcam_info(struct seq_file *s, if (!(pcifunc & RVU_PFVF_FUNC_MASK)) seq_printf(s, "\n\t\t Device \t\t: PF%d\n", - rvu_get_pf(pcifunc)); + rvu_get_pf(rvu->pdev, pcifunc)); else seq_printf(s, "\n\t\t Device \t\t: PF%d VF%d\n", - rvu_get_pf(pcifunc), + rvu_get_pf(rvu->pdev, pcifunc), (pcifunc & RVU_PFVF_FUNC_MASK) - 1); if (entry_acnt) { @@ -3049,13 +3049,13 @@ static int rvu_dbg_npc_mcam_info_display(struct seq_file *filp, void *unsued) seq_puts(filp, "\n\t\t Current allocation\n"); seq_puts(filp, "\t\t====================\n"); for (pf = 0; pf < rvu->hw->total_pfs; pf++) { - pcifunc = (pf << RVU_PFVF_PF_SHIFT); + pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0); rvu_print_npc_mcam_info(filp, pcifunc, blkaddr); cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf)); numvfs = (cfg >> 12) & 0xFF; for (vf = 0; vf < numvfs; vf++) { - pcifunc = (pf << RVU_PFVF_PF_SHIFT) | (vf + 1); + pcifunc = rvu_make_pcifunc(rvu->pdev, pf, (vf + 1)); rvu_print_npc_mcam_info(filp, pcifunc, blkaddr); } } @@ -3326,7 +3326,7 @@ static int rvu_dbg_npc_mcam_show_rules(struct seq_file *s, void *unused) mutex_lock(&mcam->lock); list_for_each_entry(iter, &mcam->mcam_rules, list) { - pf = (iter->owner >> RVU_PFVF_PF_SHIFT) & RVU_PFVF_PF_MASK; + pf = rvu_get_pf(rvu->pdev, iter->owner); seq_printf(s, "\n\tInstalled by: PF%d ", pf); if (iter->owner & RVU_PFVF_FUNC_MASK) { @@ -3344,7 +3344,7 @@ static int rvu_dbg_npc_mcam_show_rules(struct seq_file *s, void *unused) rvu_dbg_npc_mcam_show_flows(s, iter); if (is_npc_intf_rx(iter->intf)) { target = iter->rx_action.pf_func; - pf = (target >> RVU_PFVF_PF_SHIFT) & RVU_PFVF_PF_MASK; + pf = rvu_get_pf(rvu->pdev, target); seq_printf(s, "\tForward to: PF%d ", pf); if (target & RVU_PFVF_FUNC_MASK) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 613655fcd34f..bdf4d852c15d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -315,7 +315,8 @@ static bool is_valid_txschq(struct rvu *rvu, int blkaddr, if (lvl >= hw->cap.nix_tx_aggr_lvl) { if ((nix_get_tx_link(rvu, map_func) != nix_get_tx_link(rvu, pcifunc)) && - (rvu_get_pf(map_func) != rvu_get_pf(pcifunc))) + (rvu_get_pf(rvu->pdev, map_func) != + rvu_get_pf(rvu->pdev, pcifunc))) return false; else return true; @@ -339,7 +340,7 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf, bool from_vf; int err; - pf = rvu_get_pf(pcifunc); + pf = rvu_get_pf(rvu->pdev, pcifunc); if (!is_pf_cgxmapped(rvu, pf) && type != NIX_INTF_TYPE_LBK && type != NIX_INTF_TYPE_SDP) return 0; @@ -416,7 +417,7 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf, break; case NIX_INTF_TYPE_SDP: from_vf = !!(pcifunc & RVU_PFVF_FUNC_MASK); - parent_pf = &rvu->pf[rvu_get_pf(pcifunc)]; + parent_pf = &rvu->pf[rvu_get_pf(rvu->pdev, pcifunc)]; sdp_info = parent_pf->sdp_info; if (!sdp_info) { dev_err(rvu->dev, "Invalid sdp_info pointer\n"); @@ -590,12 +591,12 @@ static int nix_bp_disable(struct rvu *rvu, u16 chan_v; u64 cfg; - pf = rvu_get_pf(pcifunc); + pf = rvu_get_pf(rvu->pdev, pcifunc); type = is_lbk_vf(rvu, pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX; if (!is_pf_cgxmapped(rvu, pf) && type != NIX_INTF_TYPE_LBK) return 0; - if (is_sdp_pfvf(pcifunc)) + if (is_sdp_pfvf(rvu, pcifunc)) type = NIX_INTF_TYPE_SDP; if (cpt_link && !rvu->hw->cpt_links) @@ -736,9 +737,9 @@ static int nix_bp_enable(struct rvu *rvu, u16 chan_v; u64 cfg; - pf = rvu_get_pf(pcifunc); + pf = rvu_get_pf(rvu->pdev, pcifunc); type = is_lbk_vf(rvu, pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX; - if (is_sdp_pfvf(pcifunc)) + if (is_sdp_pfvf(rvu, pcifunc)) type = NIX_INTF_TYPE_SDP; /* Enable backpressure only for CGX mapped PFs and LBK/SDP interface */ @@ -1674,7 +1675,7 @@ int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu, } intf = is_lbk_vf(rvu, pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX; - if (is_sdp_pfvf(pcifunc)) + if (is_sdp_pfvf(rvu, pcifunc)) intf = NIX_INTF_TYPE_SDP; err = nix_interface_init(rvu, pcifunc, intf, nixlf, rsp, @@ -1798,7 +1799,8 @@ int rvu_mbox_handler_nix_mark_format_cfg(struct rvu *rvu, rc = rvu_nix_reserve_mark_format(rvu, nix_hw, blkaddr, cfg); if (rc < 0) { dev_err(rvu->dev, "No mark_format_ctl for (pf:%d, vf:%d)", - rvu_get_pf(pcifunc), pcifunc & RVU_PFVF_FUNC_MASK); + rvu_get_pf(rvu->pdev, pcifunc), + pcifunc & RVU_PFVF_FUNC_MASK); return NIX_AF_ERR_MARK_CFG_FAIL; } @@ -2050,7 +2052,7 @@ static void nix_clear_tx_xoff(struct rvu *rvu, int blkaddr, static int nix_get_tx_link(struct rvu *rvu, u16 pcifunc) { struct rvu_hwinfo *hw = rvu->hw; - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); u8 cgx_id = 0, lmac_id = 0; if (is_lbk_vf(rvu, pcifunc)) {/* LBK links */ @@ -2068,7 +2070,7 @@ static void nix_get_txschq_range(struct rvu *rvu, u16 pcifunc, int link, int *start, int *end) { struct rvu_hwinfo *hw = rvu->hw; - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); /* LBK links */ if (is_lbk_vf(rvu, pcifunc) || is_rep_dev(rvu, pcifunc)) { @@ -2426,7 +2428,7 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr, { struct nix_smq_flush_ctx *smq_flush_ctx; int err, restore_tx_en = 0, i; - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); u8 cgx_id = 0, lmac_id = 0; u16 tl2_tl3_link_schq; u8 link, link_level; @@ -2820,7 +2822,7 @@ void rvu_nix_tx_tl2_cfg(struct rvu *rvu, int blkaddr, u16 pcifunc, { struct rvu_hwinfo *hw = rvu->hw; int lbk_link_start, lbk_links; - u8 pf = rvu_get_pf(pcifunc); + u8 pf = rvu_get_pf(rvu->pdev, pcifunc); int schq; u64 cfg; @@ -3190,7 +3192,8 @@ static int nix_blk_setup_mce(struct rvu *rvu, struct nix_hw *nix_hw, err = rvu_nix_blk_aq_enq_inst(rvu, nix_hw, &aq_req, NULL); if (err) { dev_err(rvu->dev, "Failed to setup Bcast MCE for PF%d:VF%d\n", - rvu_get_pf(pcifunc), pcifunc & RVU_PFVF_FUNC_MASK); + rvu_get_pf(rvu->pdev, pcifunc), + pcifunc & RVU_PFVF_FUNC_MASK); return err; } return 0; @@ -3458,7 +3461,7 @@ int nix_update_mce_list(struct rvu *rvu, u16 pcifunc, dev_err(rvu->dev, "%s: Idx %d > max MCE idx %d, for PF%d bcast list\n", __func__, idx, mce_list->max, - pcifunc >> RVU_PFVF_PF_SHIFT); + rvu_get_pf(rvu->pdev, pcifunc)); return -EINVAL; } @@ -3510,7 +3513,8 @@ void nix_get_mce_list(struct rvu *rvu, u16 pcifunc, int type, struct rvu_pfvf *pfvf; if (!hw->cap.nix_rx_multicast || - !is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc & ~RVU_PFVF_FUNC_MASK))) { + !is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, + pcifunc & ~RVU_PFVF_FUNC_MASK))) { *mce_list = NULL; *mce_idx = 0; return; @@ -3544,13 +3548,13 @@ static int nix_update_mce_rule(struct rvu *rvu, u16 pcifunc, int pf; /* skip multicast pkt replication for AF's VFs & SDP links */ - if (is_lbk_vf(rvu, pcifunc) || is_sdp_pfvf(pcifunc)) + if (is_lbk_vf(rvu, pcifunc) || is_sdp_pfvf(rvu, pcifunc)) return 0; if (!hw->cap.nix_rx_multicast) return 0; - pf = rvu_get_pf(pcifunc); + pf = rvu_get_pf(rvu->pdev, pcifunc); if (!is_pf_cgxmapped(rvu, pf)) return 0; @@ -3619,7 +3623,7 @@ static int nix_setup_mce_tables(struct rvu *rvu, struct nix_hw *nix_hw) for (idx = 0; idx < (numvfs + 1); idx++) { /* idx-0 is for PF, followed by VFs */ - pcifunc = (pf << RVU_PFVF_PF_SHIFT); + pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0); pcifunc |= idx; /* Add dummy entries now, so that we don't have to check * for whether AQ_OP should be INIT/WRITE later on. @@ -4554,7 +4558,7 @@ int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req, static void nix_find_link_frs(struct rvu *rvu, struct nix_frs_cfg *req, u16 pcifunc) { - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); struct rvu_pfvf *pfvf; int maxlen, minlen; int numvfs, hwvf; @@ -4601,7 +4605,7 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req, { struct rvu_hwinfo *hw = rvu->hw; u16 pcifunc = req->hdr.pcifunc; - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); int blkaddr, link = -1; struct nix_hw *nix_hw; struct rvu_pfvf *pfvf; @@ -5251,7 +5255,7 @@ int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req, rvu_switch_update_rules(rvu, pcifunc, true); - pf = rvu_get_pf(pcifunc); + pf = rvu_get_pf(rvu->pdev, pcifunc); if (is_pf_cgxmapped(rvu, pf) && rvu->rep_mode) rvu_rep_notify_pfvf_state(rvu, pcifunc, true); @@ -5284,7 +5288,7 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req, rvu_switch_update_rules(rvu, pcifunc, false); rvu_cgx_tx_enable(rvu, pcifunc, true); - pf = rvu_get_pf(pcifunc); + pf = rvu_get_pf(rvu->pdev, pcifunc); if (is_pf_cgxmapped(rvu, pf) && rvu->rep_mode) rvu_rep_notify_pfvf_state(rvu, pcifunc, false); return 0; @@ -5296,7 +5300,7 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); struct hwctx_disable_req ctx_req; - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); struct mac_ops *mac_ops; u8 cgx_id, lmac_id; u64 sa_base; @@ -5385,7 +5389,7 @@ static int rvu_nix_lf_ptp_tx_cfg(struct rvu *rvu, u16 pcifunc, bool enable) int nixlf; u64 cfg; - pf = rvu_get_pf(pcifunc); + pf = rvu_get_pf(rvu->pdev, pcifunc); if (!is_mac_feature_supported(rvu, pf, RVU_LMAC_FEAT_PTP)) return 0; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index da15bb451178..c7c70429eb6c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -147,7 +147,9 @@ static int npc_get_ucast_mcam_index(struct npc_mcam *mcam, u16 pcifunc, int npc_get_nixlf_mcam_index(struct npc_mcam *mcam, u16 pcifunc, int nixlf, int type) { - int pf = rvu_get_pf(pcifunc); + struct rvu_hwinfo *hw = container_of(mcam, struct rvu_hwinfo, mcam); + struct rvu *rvu = hw->rvu; + int pf = rvu_get_pf(rvu->pdev, pcifunc); int index; /* Check if this is for a PF */ @@ -698,7 +700,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, /* RX_ACTION set to MCAST for CGX PF's */ if (hw->cap.nix_rx_multicast && pfvf->use_mce_list && - is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) { + is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc))) { *(u64 *)&action = 0; action.op = NIX_RX_ACTIONOP_MCAST; pfvf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK); @@ -3434,7 +3436,7 @@ int rvu_npc_set_parse_mode(struct rvu *rvu, u16 pcifunc, u64 mode, u8 dir, { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); int blkaddr, nixlf, rc, intf_mode; - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); u64 rxpkind, txpkind; u8 cgx_id, lmac_id; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c index d2661e7fabdb..999f6d93c7fe 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c @@ -1465,7 +1465,7 @@ static int rvu_npc_exact_update_table_entry(struct rvu *rvu, u8 cgx_id, u8 lmac_ int rvu_npc_exact_promisc_disable(struct rvu *rvu, u16 pcifunc) { struct npc_exact_table *table; - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); u8 cgx_id, lmac_id; u32 drop_mcam_idx; bool *promisc; @@ -1512,7 +1512,7 @@ int rvu_npc_exact_promisc_disable(struct rvu *rvu, u16 pcifunc) int rvu_npc_exact_promisc_enable(struct rvu *rvu, u16 pcifunc) { struct npc_exact_table *table; - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(rvu->pdev, pcifunc); u8 cgx_id, lmac_id; u32 drop_mcam_idx; bool *promisc; @@ -1560,7 +1560,7 @@ int rvu_npc_exact_promisc_enable(struct rvu *rvu, u16 pcifunc) int rvu_npc_exact_mac_addr_reset(struct rvu *rvu, struct cgx_mac_addr_reset_req *req, struct msg_rsp *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); u32 seq_id = req->index; struct rvu_pfvf *pfvf; u8 cgx_id, lmac_id; @@ -1593,7 +1593,7 @@ int rvu_npc_exact_mac_addr_update(struct rvu *rvu, struct cgx_mac_addr_update_req *req, struct cgx_mac_addr_update_rsp *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); struct npc_exact_table_entry *entry; struct npc_exact_table *table; struct rvu_pfvf *pfvf; @@ -1675,7 +1675,7 @@ int rvu_npc_exact_mac_addr_add(struct rvu *rvu, struct cgx_mac_addr_add_req *req, struct cgx_mac_addr_add_rsp *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); struct rvu_pfvf *pfvf; u8 cgx_id, lmac_id; int rc = 0; @@ -1711,7 +1711,7 @@ int rvu_npc_exact_mac_addr_del(struct rvu *rvu, struct cgx_mac_addr_del_req *req, struct msg_rsp *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); int rc; rc = rvu_npc_exact_del_table_entry_by_id(rvu, req->index); @@ -1736,7 +1736,7 @@ int rvu_npc_exact_mac_addr_del(struct rvu *rvu, int rvu_npc_exact_mac_addr_set(struct rvu *rvu, struct cgx_mac_addr_set_or_get *req, struct cgx_mac_addr_set_or_get *rsp) { - int pf = rvu_get_pf(req->hdr.pcifunc); + int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); u32 seq_id = req->index; struct rvu_pfvf *pfvf; u8 cgx_id, lmac_id; @@ -2001,7 +2001,7 @@ int rvu_npc_exact_init(struct rvu *rvu) } /* Filter rules are only for PF */ - pcifunc = RVU_PFFUNC(i, 0); + pcifunc = RVU_PFFUNC(rvu->pdev, i, 0); dev_dbg(rvu->dev, "%s:Drop rule cgx=%d lmac=%d chan(val=0x%llx, mask=0x%llx\n", diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h index 57a09328d46b..cb25cf478f1f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h @@ -139,9 +139,7 @@ static struct npc_mcam_kex_hash npc_mkex_hash_default __maybe_unused = { #define NPC_MCAM_DROP_RULE_MAX 30 #define NPC_MCAM_SDP_DROP_RULE_IDX 0 -#define RVU_PFFUNC(pf, func) \ - ((((pf) & RVU_PFVF_PF_MASK) << RVU_PFVF_PF_SHIFT) | \ - (((func) & RVU_PFVF_FUNC_MASK) << RVU_PFVF_FUNC_SHIFT)) +#define RVU_PFFUNC(pdev, pf, func) rvu_make_pcifunc(pdev, pf, func) enum npc_exact_opc_type { NPC_EXACT_OPC_MEM, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c index 32953cca108c..03099bc570bd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c @@ -39,7 +39,7 @@ static int rvu_rep_up_notify(struct rvu *rvu, struct rep_event *event) struct rep_event *msg; int pf; - pf = rvu_get_pf(event->pcifunc); + pf = rvu_get_pf(rvu->pdev, event->pcifunc); if (event->event & RVU_EVENT_MAC_ADDR_CHANGE) ether_addr_copy(pfvf->mac_addr, event->evt_data.mac); @@ -114,10 +114,10 @@ int rvu_rep_notify_pfvf_state(struct rvu *rvu, u16 pcifunc, bool enable) struct rep_event *req; int pf; - if (!is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) + if (!is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc))) return 0; - pf = rvu_get_pf(rvu->rep_pcifunc); + pf = rvu_get_pf(rvu->pdev, rvu->rep_pcifunc); mutex_lock(&rvu->mbox_lock); req = otx2_mbox_alloc_msg_rep_event_up_notify(rvu, pf); @@ -325,7 +325,7 @@ int rvu_rep_install_mcam_rules(struct rvu *rvu) if (!is_pf_cgxmapped(rvu, pf)) continue; - pcifunc = pf << RVU_PFVF_PF_SHIFT; + pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0); rvu_get_nix_blkaddr(rvu, pcifunc); rep = true; for (i = 0; i < 2; i++) { @@ -345,8 +345,7 @@ int rvu_rep_install_mcam_rules(struct rvu *rvu) rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL); for (vf = 0; vf < numvfs; vf++) { - pcifunc = pf << RVU_PFVF_PF_SHIFT | - ((vf + 1) & RVU_PFVF_FUNC_MASK); + pcifunc = rvu_make_pcifunc(rvu->pdev, pf, vf + 1); rvu_get_nix_blkaddr(rvu, pcifunc); /* Skip installimg rules if nixlf is not attached */ @@ -454,7 +453,7 @@ int rvu_mbox_handler_get_rep_cnt(struct rvu *rvu, struct msg_req *req, for (pf = 0; pf < rvu->hw->total_pfs; pf++) { if (!is_pf_cgxmapped(rvu, pf)) continue; - pcifunc = pf << RVU_PFVF_PF_SHIFT; + pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0); rvu->rep2pfvf_map[rep] = pcifunc; rsp->rep_pf_map[rep] = pcifunc; rep++; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c index 38cfe148f4b7..e4a5f9fa6fd4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c @@ -17,9 +17,9 @@ /* SDP PF number */ static int sdp_pf_num[MAX_SDP] = {-1, -1}; -bool is_sdp_pfvf(u16 pcifunc) +bool is_sdp_pfvf(struct rvu *rvu, u16 pcifunc) { - u16 pf = rvu_get_pf(pcifunc); + u16 pf = rvu_get_pf(rvu->pdev, pcifunc); u32 found = 0, i = 0; while (i < MAX_SDP) { @@ -34,9 +34,9 @@ bool is_sdp_pfvf(u16 pcifunc) return true; } -bool is_sdp_pf(u16 pcifunc) +bool is_sdp_pf(struct rvu *rvu, u16 pcifunc) { - return (is_sdp_pfvf(pcifunc) && + return (is_sdp_pfvf(rvu, pcifunc) && !(pcifunc & RVU_PFVF_FUNC_MASK)); } @@ -46,7 +46,7 @@ bool is_sdp_vf(struct rvu *rvu, u16 pcifunc) if (!(pcifunc & ~RVU_PFVF_FUNC_MASK)) return (rvu->vf_devid == RVU_SDP_VF_DEVID); - return (is_sdp_pfvf(pcifunc) && + return (is_sdp_pfvf(rvu, pcifunc) && !!(pcifunc & RVU_PFVF_FUNC_MASK)); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h index 77ac94cb2ec4..0596a3ac4c12 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h @@ -33,7 +33,8 @@ enum rvu_block_addr_e { BLKADDR_NDC_NIX1_RX = 0x10ULL, BLKADDR_NDC_NIX1_TX = 0x11ULL, BLKADDR_APR = 0x16ULL, - BLK_COUNT = 0x17ULL, + BLKADDR_MBOX = 0x1bULL, + BLK_COUNT = 0x1cULL, }; /* RVU Block Type Enumeration */ @@ -49,7 +50,8 @@ enum rvu_block_type_e { BLKTYPE_TIM = 0x8, BLKTYPE_CPT = 0x9, BLKTYPE_NDC = 0xa, - BLKTYPE_MAX = 0xa, + BLKTYPE_MBOX = 0x13, + BLKTYPE_MAX = 0x13, }; /* RVU Admin function Interrupt Vector Enumeration */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c index 268efb7c1c15..49ce38685a7e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c @@ -93,7 +93,7 @@ static int rvu_switch_install_rules(struct rvu *rvu) if (!is_pf_cgxmapped(rvu, pf)) continue; - pcifunc = pf << 10; + pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0); /* rvu_get_nix_blkaddr sets up the corresponding NIX block * address and NIX RX and TX interfaces for a pcifunc. * Generally it is called during attach call of a pcifunc but it @@ -126,7 +126,7 @@ static int rvu_switch_install_rules(struct rvu *rvu) rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL); for (vf = 0; vf < numvfs; vf++) { - pcifunc = pf << 10 | ((vf + 1) & 0x3FF); + pcifunc = rvu_make_pcifunc(rvu->pdev, pf, (vf + 1)); rvu_get_nix_blkaddr(rvu, pcifunc); err = rvu_switch_install_rx_rule(rvu, pcifunc, 0x0); @@ -236,7 +236,7 @@ void rvu_switch_disable(struct rvu *rvu) if (!is_pf_cgxmapped(rvu, pf)) continue; - pcifunc = pf << 10; + pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0); err = rvu_switch_install_rx_rule(rvu, pcifunc, 0xFFF); if (err) dev_err(rvu->dev, @@ -248,7 +248,7 @@ void rvu_switch_disable(struct rvu *rvu) rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL); for (vf = 0; vf < numvfs; vf++) { - pcifunc = pf << 10 | ((vf + 1) & 0x3FF); + pcifunc = rvu_make_pcifunc(rvu->pdev, pf, (vf + 1)); err = rvu_switch_install_rx_rule(rvu, pcifunc, 0xFFF); if (err) dev_err(rvu->dev, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index 69e0778f9ac1..883e9f4d601c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -8,7 +8,7 @@ obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o obj-$(CONFIG_RVU_ESWITCH) += rvu_rep.o rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \ - otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \ + otx2_flows.o otx2_tc.o cn10k.o cn20k.o otx2_dmac_flt.o \ otx2_devlink.o qos_sq.o qos.o otx2_xsk.o rvu_nicvf-y := otx2_vf.o rvu_rep-y := rep.o diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c index 7f6a435ac680..bec7d5b4d7cc 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c @@ -14,6 +14,7 @@ static struct dev_hw_ops otx2_hw_ops = { .sqe_flush = otx2_sqe_flush, .aura_freeptr = otx2_aura_freeptr, .refill_pool_ptrs = otx2_refill_pool_ptrs, + .pfaf_mbox_intr_handler = otx2_pfaf_mbox_intr_handler, }; static struct dev_hw_ops cn10k_hw_ops = { @@ -21,8 +22,20 @@ static struct dev_hw_ops cn10k_hw_ops = { .sqe_flush = cn10k_sqe_flush, .aura_freeptr = cn10k_aura_freeptr, .refill_pool_ptrs = cn10k_refill_pool_ptrs, + .pfaf_mbox_intr_handler = otx2_pfaf_mbox_intr_handler, }; +void otx2_init_hw_ops(struct otx2_nic *pfvf) +{ + if (!test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) { + pfvf->hw_ops = &otx2_hw_ops; + return; + } + + pfvf->hw_ops = &cn10k_hw_ops; +} +EXPORT_SYMBOL(otx2_init_hw_ops); + int cn10k_lmtst_init(struct otx2_nic *pfvf) { @@ -30,12 +43,9 @@ int cn10k_lmtst_init(struct otx2_nic *pfvf) struct otx2_lmt_info *lmt_info; int err, cpu; - if (!test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) { - pfvf->hw_ops = &otx2_hw_ops; + if (!test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) return 0; - } - pfvf->hw_ops = &cn10k_hw_ops; /* Total LMTLINES = num_online_cpus() * 32 (For Burst flush).*/ pfvf->tot_lmt_lines = (num_online_cpus() * LMT_BURST_SIZE); pfvf->hw.lmt_info = alloc_percpu(struct otx2_lmt_info); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h index e3f0bce9908f..945ab10bd4ed 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h @@ -39,4 +39,5 @@ int cn10k_alloc_leaf_profile(struct otx2_nic *pfvf, u16 *leaf); int cn10k_set_ipolicer_rate(struct otx2_nic *pfvf, u16 profile, u32 burst, u64 rate, bool pps); int cn10k_free_leaf_profile(struct otx2_nic *pfvf, u16 leaf); +void otx2_init_hw_ops(struct otx2_nic *pfvf); #endif /* CN10K_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c index a6500e3673f2..c691f0722154 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c @@ -481,7 +481,7 @@ static int cn10k_outb_write_sa(struct otx2_nic *pf, struct qmem *sa_info) goto set_available; /* Trigger CTX flush to write dirty data back to DRAM */ - reg_val = FIELD_PREP(CPT_LF_CTX_FLUSH, sa_iova >> 7); + reg_val = FIELD_PREP(CPT_LF_CTX_FLUSH_CPTR, sa_iova >> 7); otx2_write64(pf, CN10K_CPT_LF_CTX_FLUSH, reg_val); set_available: diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h index 9965df0faa3e..43fbce0d6039 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h @@ -220,7 +220,7 @@ struct cpt_sg_s { #define CPT_LF_Q_SIZE_DIV40 GENMASK_ULL(14, 0) /* CPT LF CTX Flush Register */ -#define CPT_LF_CTX_FLUSH GENMASK_ULL(45, 0) +#define CPT_LF_CTX_FLUSH_CPTR GENMASK_ULL(45, 0) #ifdef CONFIG_XFRM_OFFLOAD int cn10k_ipsec_init(struct net_device *netdev); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c new file mode 100644 index 000000000000..ec8cde98076d --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c @@ -0,0 +1,252 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell RVU Ethernet driver + * + * Copyright (C) 2024 Marvell. + * + */ + +#include "otx2_common.h" +#include "otx2_reg.h" +#include "otx2_struct.h" +#include "cn10k.h" + +static struct dev_hw_ops cn20k_hw_ops = { + .pfaf_mbox_intr_handler = cn20k_pfaf_mbox_intr_handler, + .vfaf_mbox_intr_handler = cn20k_vfaf_mbox_intr_handler, + .pfvf_mbox_intr_handler = cn20k_pfvf_mbox_intr_handler, +}; + +void cn20k_init(struct otx2_nic *pfvf) +{ + pfvf->hw_ops = &cn20k_hw_ops; +} +EXPORT_SYMBOL(cn20k_init); +/* CN20K mbox AF => PFx irq handler */ +irqreturn_t cn20k_pfaf_mbox_intr_handler(int irq, void *pf_irq) +{ + struct otx2_nic *pf = pf_irq; + struct mbox *mw = &pf->mbox; + struct otx2_mbox_dev *mdev; + struct otx2_mbox *mbox; + struct mbox_hdr *hdr; + u64 pf_trig_val; + + pf_trig_val = otx2_read64(pf, RVU_PF_INT) & 0x3ULL; + + /* Clear the IRQ */ + otx2_write64(pf, RVU_PF_INT, pf_trig_val); + + if (pf_trig_val & BIT_ULL(0)) { + mbox = &mw->mbox_up; + mdev = &mbox->dev[0]; + otx2_sync_mbox_bbuf(mbox, 0); + + hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + if (hdr->num_msgs) + queue_work(pf->mbox_wq, &mw->mbox_up_wrk); + + trace_otx2_msg_interrupt(pf->pdev, "UP message from AF to PF", + BIT_ULL(0)); + } + + if (pf_trig_val & BIT_ULL(1)) { + mbox = &mw->mbox; + mdev = &mbox->dev[0]; + otx2_sync_mbox_bbuf(mbox, 0); + + hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + if (hdr->num_msgs) + queue_work(pf->mbox_wq, &mw->mbox_wrk); + trace_otx2_msg_interrupt(pf->pdev, "DOWN reply from AF to PF", + BIT_ULL(1)); + } + + return IRQ_HANDLED; +} + +irqreturn_t cn20k_vfaf_mbox_intr_handler(int irq, void *vf_irq) +{ + struct otx2_nic *vf = vf_irq; + struct otx2_mbox_dev *mdev; + struct otx2_mbox *mbox; + struct mbox_hdr *hdr; + u64 vf_trig_val; + + vf_trig_val = otx2_read64(vf, RVU_VF_INT) & 0x3ULL; + /* Clear the IRQ */ + otx2_write64(vf, RVU_VF_INT, vf_trig_val); + + /* Read latest mbox data */ + smp_rmb(); + + if (vf_trig_val & BIT_ULL(1)) { + /* Check for PF => VF response messages */ + mbox = &vf->mbox.mbox; + mdev = &mbox->dev[0]; + otx2_sync_mbox_bbuf(mbox, 0); + + hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + if (hdr->num_msgs) + queue_work(vf->mbox_wq, &vf->mbox.mbox_wrk); + + trace_otx2_msg_interrupt(mbox->pdev, "DOWN reply from PF0 to VF", + BIT_ULL(1)); + } + + if (vf_trig_val & BIT_ULL(0)) { + /* Check for PF => VF notification messages */ + mbox = &vf->mbox.mbox_up; + mdev = &mbox->dev[0]; + otx2_sync_mbox_bbuf(mbox, 0); + + hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + if (hdr->num_msgs) + queue_work(vf->mbox_wq, &vf->mbox.mbox_up_wrk); + + trace_otx2_msg_interrupt(mbox->pdev, "UP message from PF0 to VF", + BIT_ULL(0)); + } + + return IRQ_HANDLED; +} + +void cn20k_enable_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs) +{ + /* Clear PF <=> VF mailbox IRQ */ + otx2_write64(pf, RVU_MBOX_PF_VFPF_INTX(0), ~0ull); + otx2_write64(pf, RVU_MBOX_PF_VFPF_INTX(1), ~0ull); + otx2_write64(pf, RVU_MBOX_PF_VFPF1_INTX(0), ~0ull); + otx2_write64(pf, RVU_MBOX_PF_VFPF1_INTX(1), ~0ull); + + /* Enable PF <=> VF mailbox IRQ */ + otx2_write64(pf, RVU_MBOX_PF_VFPF_INT_ENA_W1SX(0), INTR_MASK(numvfs)); + otx2_write64(pf, RVU_MBOX_PF_VFPF1_INT_ENA_W1SX(0), INTR_MASK(numvfs)); + if (numvfs > 64) { + numvfs -= 64; + otx2_write64(pf, RVU_MBOX_PF_VFPF_INT_ENA_W1SX(1), + INTR_MASK(numvfs)); + otx2_write64(pf, RVU_MBOX_PF_VFPF1_INT_ENA_W1SX(1), + INTR_MASK(numvfs)); + } +} + +void cn20k_disable_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs) +{ + int vector, intr_vec, vec = 0; + + /* Disable PF <=> VF mailbox IRQ */ + otx2_write64(pf, RVU_MBOX_PF_VFPF_INT_ENA_W1CX(0), ~0ull); + otx2_write64(pf, RVU_MBOX_PF_VFPF_INT_ENA_W1CX(1), ~0ull); + otx2_write64(pf, RVU_MBOX_PF_VFPF1_INT_ENA_W1CX(0), ~0ull); + otx2_write64(pf, RVU_MBOX_PF_VFPF1_INT_ENA_W1CX(1), ~0ull); + + otx2_write64(pf, RVU_MBOX_PF_VFPF_INTX(0), ~0ull); + otx2_write64(pf, RVU_MBOX_PF_VFPF1_INTX(0), ~0ull); + + if (numvfs > 64) { + otx2_write64(pf, RVU_MBOX_PF_VFPF_INTX(1), ~0ull); + otx2_write64(pf, RVU_MBOX_PF_VFPF1_INTX(1), ~0ull); + } + + for (intr_vec = RVU_MBOX_PF_INT_VEC_VFPF_MBOX0; intr_vec <= + RVU_MBOX_PF_INT_VEC_VFPF1_MBOX1; intr_vec++, vec++) { + vector = pci_irq_vector(pf->pdev, intr_vec); + free_irq(vector, pf->hw.pfvf_irq_devid[vec]); + } +} + +irqreturn_t cn20k_pfvf_mbox_intr_handler(int irq, void *pf_irq) +{ + struct pf_irq_data *irq_data = pf_irq; + struct otx2_nic *pf = irq_data->pf; + struct mbox *mbox; + u64 intr; + + /* Sync with mbox memory region */ + rmb(); + + /* Clear interrupts */ + intr = otx2_read64(pf, irq_data->intr_status); + otx2_write64(pf, irq_data->intr_status, intr); + mbox = pf->mbox_pfvf; + + if (intr) + trace_otx2_msg_interrupt(pf->pdev, "VF(s) to PF", intr); + + irq_data->pf_queue_work_hdlr(mbox, pf->mbox_pfvf_wq, irq_data->start, + irq_data->mdevs, intr); + + return IRQ_HANDLED; +} + +int cn20k_register_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs) +{ + struct otx2_hw *hw = &pf->hw; + struct pf_irq_data *irq_data; + int intr_vec, ret, vec = 0; + char *irq_name; + + /* irq data for 4 PF intr vectors */ + irq_data = devm_kcalloc(pf->dev, 4, + sizeof(struct pf_irq_data), GFP_KERNEL); + if (!irq_data) + return -ENOMEM; + + for (intr_vec = RVU_MBOX_PF_INT_VEC_VFPF_MBOX0; intr_vec <= + RVU_MBOX_PF_INT_VEC_VFPF1_MBOX1; intr_vec++, vec++) { + switch (intr_vec) { + case RVU_MBOX_PF_INT_VEC_VFPF_MBOX0: + irq_data[vec].intr_status = + RVU_MBOX_PF_VFPF_INTX(0); + irq_data[vec].start = 0; + irq_data[vec].mdevs = 64; + break; + case RVU_MBOX_PF_INT_VEC_VFPF_MBOX1: + irq_data[vec].intr_status = + RVU_MBOX_PF_VFPF_INTX(1); + irq_data[vec].start = 64; + irq_data[vec].mdevs = 96; + break; + case RVU_MBOX_PF_INT_VEC_VFPF1_MBOX0: + irq_data[vec].intr_status = + RVU_MBOX_PF_VFPF1_INTX(0); + irq_data[vec].start = 0; + irq_data[vec].mdevs = 64; + break; + case RVU_MBOX_PF_INT_VEC_VFPF1_MBOX1: + irq_data[vec].intr_status = + RVU_MBOX_PF_VFPF1_INTX(1); + irq_data[vec].start = 64; + irq_data[vec].mdevs = 96; + break; + } + irq_data[vec].pf_queue_work_hdlr = otx2_queue_vf_work; + irq_data[vec].vec_num = intr_vec; + irq_data[vec].pf = pf; + + /* Register mailbox interrupt handler */ + irq_name = &hw->irq_name[intr_vec * NAME_SIZE]; + if (pf->pcifunc) + snprintf(irq_name, NAME_SIZE, + "RVUPF%d_VF%d Mbox%d", rvu_get_pf(pf->pdev, + pf->pcifunc), vec / 2, vec % 2); + else + snprintf(irq_name, NAME_SIZE, "RVUPF_VF%d Mbox%d", + vec / 2, vec % 2); + + hw->pfvf_irq_devid[vec] = &irq_data[vec]; + ret = request_irq(pci_irq_vector(pf->pdev, intr_vec), + pf->hw_ops->pfvf_mbox_intr_handler, 0, + irq_name, + &irq_data[vec]); + if (ret) { + dev_err(pf->dev, + "RVUPF: IRQ registration failed for PFVF mbox0 irq\n"); + return ret; + } + } + + cn20k_enable_pfvf_mbox_intr(pf, numvfs); + + return 0; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.h new file mode 100644 index 000000000000..832adaf8c57f --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell RVU Ethernet driver + * + * Copyright (C) 2024 Marvell. + * + */ + +#ifndef CN20K_H +#define CN20K_H + +#include "otx2_common.h" + +void cn20k_init(struct otx2_nic *pfvf); +int cn20k_register_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs); +void cn20k_disable_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs); +void cn20k_enable_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs); +#endif /* CN20K_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index a2a7fc99695d..6b59881f78e0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -28,10 +28,12 @@ #include "otx2_reg.h" #include "otx2_txrx.h" #include "otx2_devlink.h" +#include <rvu.h> #include <rvu_trace.h> #include "qos.h" #include "rep.h" #include "cn10k_ipsec.h" +#include "cn20k.h" /* IPv4 flag more fragment bit */ #define IPV4_FLAG_MORE 0x20 @@ -61,6 +63,12 @@ /* Number of segments per SG structure */ #define MAX_SEGS_PER_SG 3 +irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq); +irqreturn_t cn20k_pfaf_mbox_intr_handler(int irq, void *pf_irq); +irqreturn_t cn20k_vfaf_mbox_intr_handler(int irq, void *vf_irq); +irqreturn_t cn20k_pfvf_mbox_intr_handler(int irq, void *pf_irq); +irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq); + enum arua_mapped_qtypes { AURA_NIX_RQ, AURA_NIX_SQ, @@ -245,6 +253,7 @@ struct otx2_hw { u16 nix_msixoff; /* Offset of NIX vectors */ char *irq_name; cpumask_var_t *affinity_mask; + struct pf_irq_data *pfvf_irq_devid[4]; /* Stats */ struct otx2_dev_stats dev_stats; @@ -366,6 +375,9 @@ struct dev_hw_ops { int size, int qidx); int (*refill_pool_ptrs)(void *dev, struct otx2_cq_queue *cq); void (*aura_freeptr)(void *dev, int aura, u64 buf); + irqreturn_t (*pfaf_mbox_intr_handler)(int irq, void *pf_irq); + irqreturn_t (*vfaf_mbox_intr_handler)(int irq, void *pf_irq); + irqreturn_t (*pfvf_mbox_intr_handler)(int irq, void *pf_irq); }; #define CN10K_MCS_SA_PER_SC 4 @@ -433,6 +445,16 @@ struct cn10k_mcs_cfg { struct list_head rxsc_list; }; +struct pf_irq_data { + u64 intr_status; + void (*pf_queue_work_hdlr)(struct mbox *mb, struct workqueue_struct *mw, + int first, int mdevs, u64 intr); + struct otx2_nic *pf; + int vec_num; + int start; + int mdevs; +}; + struct otx2_nic { void __iomem *reg_base; struct net_device *netdev; @@ -476,6 +498,7 @@ struct otx2_nic { struct mbox *mbox_pfvf; struct workqueue_struct *mbox_wq; struct workqueue_struct *mbox_pfvf_wq; + struct qmem *pfvf_mbox_addr; u8 total_vfs; u16 pcifunc; /* RVU PF_FUNC */ @@ -904,21 +927,11 @@ MBOX_UP_MCS_MESSAGES /* Time to wait before watchdog kicks off */ #define OTX2_TX_TIMEOUT (100 * HZ) -#define RVU_PFVF_PF_SHIFT 10 -#define RVU_PFVF_PF_MASK 0x3F -#define RVU_PFVF_FUNC_SHIFT 0 -#define RVU_PFVF_FUNC_MASK 0x3FF - static inline bool is_otx2_vf(u16 pcifunc) { return !!(pcifunc & RVU_PFVF_FUNC_MASK); } -static inline int rvu_get_pf(u16 pcifunc) -{ - return (pcifunc >> RVU_PFVF_PF_SHIFT) & RVU_PFVF_PF_MASK; -} - static inline dma_addr_t otx2_dma_map_page(struct otx2_nic *pfvf, struct page *page, size_t offset, size_t size, @@ -1196,4 +1209,6 @@ dma_addr_t otx2_dma_map_skb_frag(struct otx2_nic *pfvf, struct sk_buff *skb, int seg, int *len); void otx2_dma_unmap_skb_frags(struct otx2_nic *pfvf, struct sg_list *sg); int otx2_read_free_sqe(struct otx2_nic *pfvf, u16 qidx); +void otx2_queue_vf_work(struct mbox *mw, struct workqueue_struct *mbox_wq, + int first, int mdevs, u64 intr); #endif /* OTX2_COMMON_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index 45b8c9230184..9b7f847b9c22 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -559,10 +559,13 @@ static int otx2_set_coalesce(struct net_device *netdev, return 0; } -static int otx2_get_rss_hash_opts(struct otx2_nic *pfvf, - struct ethtool_rxnfc *nfc) +static int otx2_get_rss_hash_opts(struct net_device *dev, + struct ethtool_rxfh_fields *nfc) { - struct otx2_rss_info *rss = &pfvf->hw.rss_info; + struct otx2_nic *pfvf = netdev_priv(dev); + struct otx2_rss_info *rss; + + rss = &pfvf->hw.rss_info; if (!(rss->flowkey_cfg & (NIX_FLOW_KEY_TYPE_IPV4 | NIX_FLOW_KEY_TYPE_IPV6))) @@ -609,12 +612,17 @@ static int otx2_get_rss_hash_opts(struct otx2_nic *pfvf, return 0; } -static int otx2_set_rss_hash_opts(struct otx2_nic *pfvf, - struct ethtool_rxnfc *nfc) +static int otx2_set_rss_hash_opts(struct net_device *dev, + const struct ethtool_rxfh_fields *nfc, + struct netlink_ext_ack *extack) { - struct otx2_rss_info *rss = &pfvf->hw.rss_info; + struct otx2_nic *pfvf = netdev_priv(dev); u32 rxh_l4 = RXH_L4_B_0_1 | RXH_L4_B_2_3; - u32 rss_cfg = rss->flowkey_cfg; + struct otx2_rss_info *rss; + u32 rss_cfg; + + rss = &pfvf->hw.rss_info; + rss_cfg = rss->flowkey_cfg; if (!rss->enable) { netdev_err(pfvf->netdev, @@ -743,8 +751,6 @@ static int otx2_get_rxnfc(struct net_device *dev, if (netif_running(dev) && ntuple) ret = otx2_get_all_flows(pfvf, nfc, rules); break; - case ETHTOOL_GRXFH: - return otx2_get_rss_hash_opts(pfvf, nfc); default: break; } @@ -759,9 +765,6 @@ static int otx2_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc) pfvf->flow_cfg->ntuple = ntuple; switch (nfc->cmd) { - case ETHTOOL_SRXFH: - ret = otx2_set_rss_hash_opts(pfvf, nfc); - break; case ETHTOOL_SRXCLSRLINS: if (netif_running(dev) && ntuple) ret = otx2_add_flow(pfvf, nfc); @@ -1329,6 +1332,8 @@ static const struct ethtool_ops otx2_ethtool_ops = { .get_rxfh_indir_size = otx2_get_rxfh_indir_size, .get_rxfh = otx2_get_rxfh, .set_rxfh = otx2_set_rxfh, + .get_rxfh_fields = otx2_get_rss_hash_opts, + .set_rxfh_fields = otx2_set_rss_hash_opts, .get_msglevel = otx2_get_msglevel, .set_msglevel = otx2_set_msglevel, .get_pauseparam = otx2_get_pauseparam, @@ -1442,6 +1447,8 @@ static const struct ethtool_ops otx2vf_ethtool_ops = { .get_rxfh_indir_size = otx2_get_rxfh_indir_size, .get_rxfh = otx2_get_rxfh, .set_rxfh = otx2_set_rxfh, + .get_rxfh_fields = otx2_get_rss_hash_opts, + .set_rxfh_fields = otx2_set_rss_hash_opts, .get_ringparam = otx2_get_ringparam, .set_ringparam = otx2_set_ringparam, .get_coalesce = otx2_get_coalesce, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 07da4d6dbbc9..4e2d1206e1b0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -206,7 +206,8 @@ static int otx2_register_flr_me_intr(struct otx2_nic *pf, int numvfs) /* Register ME interrupt handler*/ irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFME0 * NAME_SIZE]; - snprintf(irq_name, NAME_SIZE, "RVUPF%d_ME0", rvu_get_pf(pf->pcifunc)); + snprintf(irq_name, NAME_SIZE, "RVUPF%d_ME0", + rvu_get_pf(pf->pdev, pf->pcifunc)); ret = request_irq(pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFME0), otx2_pf_me_intr_handler, 0, irq_name, pf); if (ret) { @@ -216,7 +217,8 @@ static int otx2_register_flr_me_intr(struct otx2_nic *pf, int numvfs) /* Register FLR interrupt handler */ irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFFLR0 * NAME_SIZE]; - snprintf(irq_name, NAME_SIZE, "RVUPF%d_FLR0", rvu_get_pf(pf->pcifunc)); + snprintf(irq_name, NAME_SIZE, "RVUPF%d_FLR0", + rvu_get_pf(pf->pdev, pf->pcifunc)); ret = request_irq(pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFFLR0), otx2_pf_flr_intr_handler, 0, irq_name, pf); if (ret) { @@ -228,7 +230,7 @@ static int otx2_register_flr_me_intr(struct otx2_nic *pf, int numvfs) if (numvfs > 64) { irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFME1 * NAME_SIZE]; snprintf(irq_name, NAME_SIZE, "RVUPF%d_ME1", - rvu_get_pf(pf->pcifunc)); + rvu_get_pf(pf->pdev, pf->pcifunc)); ret = request_irq(pci_irq_vector (pf->pdev, RVU_PF_INT_VEC_VFME1), otx2_pf_me_intr_handler, 0, irq_name, pf); @@ -238,7 +240,7 @@ static int otx2_register_flr_me_intr(struct otx2_nic *pf, int numvfs) } irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFFLR1 * NAME_SIZE]; snprintf(irq_name, NAME_SIZE, "RVUPF%d_FLR1", - rvu_get_pf(pf->pcifunc)); + rvu_get_pf(pf->pdev, pf->pcifunc)); ret = request_irq(pci_irq_vector (pf->pdev, RVU_PF_INT_VEC_VFFLR1), otx2_pf_flr_intr_handler, 0, irq_name, pf); @@ -294,8 +296,8 @@ static int otx2_pf_flr_init(struct otx2_nic *pf, int num_vfs) return 0; } -static void otx2_queue_vf_work(struct mbox *mw, struct workqueue_struct *mbox_wq, - int first, int mdevs, u64 intr) +void otx2_queue_vf_work(struct mbox *mw, struct workqueue_struct *mbox_wq, + int first, int mdevs, u64 intr) { struct otx2_mbox_dev *mdev; struct otx2_mbox *mbox; @@ -545,7 +547,7 @@ end: } } -static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq) +irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq) { struct otx2_nic *pf = (struct otx2_nic *)(pf_irq); int vfs = pf->total_vfs; @@ -574,6 +576,23 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq) return IRQ_HANDLED; } +static void *cn20k_pfvf_mbox_alloc(struct otx2_nic *pf, int numvfs) +{ + struct qmem *mbox_addr; + int err; + + err = qmem_alloc(&pf->pdev->dev, &mbox_addr, numvfs, MBOX_SIZE); + if (err) { + dev_err(pf->dev, "qmem alloc fail\n"); + return ERR_PTR(-ENOMEM); + } + + otx2_write64(pf, RVU_PF_VF_MBOX_ADDR, (u64)mbox_addr->iova); + pf->pfvf_mbox_addr = mbox_addr; + + return mbox_addr->base; +} + static int otx2_pfvf_mbox_init(struct otx2_nic *pf, int numvfs) { void __iomem *hwbase; @@ -595,19 +614,27 @@ static int otx2_pfvf_mbox_init(struct otx2_nic *pf, int numvfs) if (!pf->mbox_pfvf_wq) return -ENOMEM; - /* On CN10K platform, PF <-> VF mailbox region follows after - * PF <-> AF mailbox region. + /* For CN20K, PF allocates mbox memory in DRAM and writes PF/VF + * regions/offsets in RVU_PF_VF_MBOX_ADDR, the RVU_PFX_FUNC_PFAF_MBOX + * gives the aliased address to access PF/VF mailbox regions. */ - if (test_bit(CN10K_MBOX, &pf->hw.cap_flag)) - base = pci_resource_start(pf->pdev, PCI_MBOX_BAR_NUM) + - MBOX_SIZE; - else - base = readq(pf->reg_base + RVU_PF_VF_BAR4_ADDR); + if (is_cn20k(pf->pdev)) { + hwbase = (void __iomem *)cn20k_pfvf_mbox_alloc(pf, numvfs); + } else { + /* On CN10K platform, PF <-> VF mailbox region follows after + * PF <-> AF mailbox region. + */ + if (test_bit(CN10K_MBOX, &pf->hw.cap_flag)) + base = pci_resource_start(pf->pdev, PCI_MBOX_BAR_NUM) + + MBOX_SIZE; + else + base = readq(pf->reg_base + RVU_PF_VF_BAR4_ADDR); - hwbase = ioremap_wc(base, MBOX_SIZE * pf->total_vfs); - if (!hwbase) { - err = -ENOMEM; - goto free_wq; + hwbase = ioremap_wc(base, MBOX_SIZE * pf->total_vfs); + if (!hwbase) { + err = -ENOMEM; + goto free_wq; + } } mbox = &pf->mbox_pfvf[0]; @@ -631,7 +658,7 @@ static int otx2_pfvf_mbox_init(struct otx2_nic *pf, int numvfs) return 0; free_iomem: - if (hwbase) + if (hwbase && !(is_cn20k(pf->pdev))) iounmap(hwbase); free_wq: destroy_workqueue(pf->mbox_pfvf_wq); @@ -650,8 +677,10 @@ static void otx2_pfvf_mbox_destroy(struct otx2_nic *pf) pf->mbox_pfvf_wq = NULL; } - if (mbox->mbox.hwbase) + if (mbox->mbox.hwbase && !is_cn20k(pf->pdev)) iounmap(mbox->mbox.hwbase); + else + qmem_free(&pf->pdev->dev, pf->pfvf_mbox_addr); otx2_mbox_destroy(&mbox->mbox); } @@ -675,6 +704,9 @@ static void otx2_disable_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs) { int vector; + if (is_cn20k(pf->pdev)) + return cn20k_disable_pfvf_mbox_intr(pf, numvfs); + /* Disable PF <=> VF mailbox IRQ */ otx2_write64(pf, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(0), ~0ull); otx2_write64(pf, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(1), ~0ull); @@ -696,11 +728,14 @@ static int otx2_register_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs) char *irq_name; int err; + if (is_cn20k(pf->pdev)) + return cn20k_register_pfvf_mbox_intr(pf, numvfs); + /* Register MBOX0 interrupt handler */ irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFPF_MBOX0 * NAME_SIZE]; if (pf->pcifunc) snprintf(irq_name, NAME_SIZE, - "RVUPF%d_VF Mbox0", rvu_get_pf(pf->pcifunc)); + "RVUPF%d_VF Mbox0", rvu_get_pf(pf->pdev, pf->pcifunc)); else snprintf(irq_name, NAME_SIZE, "RVUPF_VF Mbox0"); err = request_irq(pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFPF_MBOX0), @@ -716,7 +751,8 @@ static int otx2_register_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs) irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFPF_MBOX1 * NAME_SIZE]; if (pf->pcifunc) snprintf(irq_name, NAME_SIZE, - "RVUPF%d_VF Mbox1", rvu_get_pf(pf->pcifunc)); + "RVUPF%d_VF Mbox1", + rvu_get_pf(pf->pdev, pf->pcifunc)); else snprintf(irq_name, NAME_SIZE, "RVUPF_VF Mbox1"); err = request_irq(pci_irq_vector(pf->pdev, @@ -1005,7 +1041,7 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work) otx2_mbox_msg_send(mbox, 0); } -static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq) +irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq) { struct otx2_nic *pf = (struct otx2_nic *)pf_irq; struct mbox *mw = &pf->mbox; @@ -1063,10 +1099,18 @@ static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq) void otx2_disable_mbox_intr(struct otx2_nic *pf) { - int vector = pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_AFPF_MBOX); + int vector; /* Disable AF => PF mailbox IRQ */ - otx2_write64(pf, RVU_PF_INT_ENA_W1C, BIT_ULL(0)); + if (!is_cn20k(pf->pdev)) { + vector = pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_AFPF_MBOX); + otx2_write64(pf, RVU_PF_INT_ENA_W1C, BIT_ULL(0)); + } else { + vector = pci_irq_vector(pf->pdev, + RVU_MBOX_PF_INT_VEC_AFPF_MBOX); + otx2_write64(pf, RVU_PF_INT_ENA_W1C, + BIT_ULL(0) | BIT_ULL(1)); + } free_irq(vector, pf); } EXPORT_SYMBOL(otx2_disable_mbox_intr); @@ -1079,10 +1123,24 @@ int otx2_register_mbox_intr(struct otx2_nic *pf, bool probe_af) int err; /* Register mailbox interrupt handler */ - irq_name = &hw->irq_name[RVU_PF_INT_VEC_AFPF_MBOX * NAME_SIZE]; - snprintf(irq_name, NAME_SIZE, "RVUPFAF Mbox"); - err = request_irq(pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_AFPF_MBOX), - otx2_pfaf_mbox_intr_handler, 0, irq_name, pf); + if (!is_cn20k(pf->pdev)) { + irq_name = &hw->irq_name[RVU_PF_INT_VEC_AFPF_MBOX * NAME_SIZE]; + snprintf(irq_name, NAME_SIZE, "RVUPF%d AFPF Mbox", + rvu_get_pf(pf->pdev, pf->pcifunc)); + err = request_irq(pci_irq_vector + (pf->pdev, RVU_PF_INT_VEC_AFPF_MBOX), + pf->hw_ops->pfaf_mbox_intr_handler, + 0, irq_name, pf); + } else { + irq_name = &hw->irq_name[RVU_MBOX_PF_INT_VEC_AFPF_MBOX * + NAME_SIZE]; + snprintf(irq_name, NAME_SIZE, "RVUPF%d AFPF Mbox", + rvu_get_pf(pf->pdev, pf->pcifunc)); + err = request_irq(pci_irq_vector + (pf->pdev, RVU_MBOX_PF_INT_VEC_AFPF_MBOX), + pf->hw_ops->pfaf_mbox_intr_handler, + 0, irq_name, pf); + } if (err) { dev_err(pf->dev, "RVUPF: IRQ registration failed for PFAF mbox irq\n"); @@ -1092,8 +1150,14 @@ int otx2_register_mbox_intr(struct otx2_nic *pf, bool probe_af) /* Enable mailbox interrupt for msgs coming from AF. * First clear to avoid spurious interrupts, if any. */ - otx2_write64(pf, RVU_PF_INT, BIT_ULL(0)); - otx2_write64(pf, RVU_PF_INT_ENA_W1S, BIT_ULL(0)); + if (!is_cn20k(pf->pdev)) { + otx2_write64(pf, RVU_PF_INT, BIT_ULL(0)); + otx2_write64(pf, RVU_PF_INT_ENA_W1S, BIT_ULL(0)); + } else { + otx2_write64(pf, RVU_PF_INT, BIT_ULL(0) | BIT_ULL(1)); + otx2_write64(pf, RVU_PF_INT_ENA_W1S, BIT_ULL(0) | + BIT_ULL(1)); + } if (!probe_af) return 0; @@ -1124,7 +1188,7 @@ void otx2_pfaf_mbox_destroy(struct otx2_nic *pf) pf->mbox_wq = NULL; } - if (mbox->mbox.hwbase) + if (mbox->mbox.hwbase && !is_cn20k(pf->pdev)) iounmap((void __iomem *)mbox->mbox.hwbase); otx2_mbox_destroy(&mbox->mbox); @@ -1144,12 +1208,20 @@ int otx2_pfaf_mbox_init(struct otx2_nic *pf) if (!pf->mbox_wq) return -ENOMEM; - /* Mailbox is a reserved memory (in RAM) region shared between - * admin function (i.e AF) and this PF, shouldn't be mapped as - * device memory to allow unaligned accesses. + /* For CN20K, AF allocates mbox memory in DRAM and writes PF + * regions/offsets in RVU_MBOX_AF_PFX_ADDR, the RVU_PFX_FUNC_PFAF_MBOX + * gives the aliased address to access AF/PF mailbox regions. */ - hwbase = ioremap_wc(pci_resource_start(pf->pdev, PCI_MBOX_BAR_NUM), - MBOX_SIZE); + if (is_cn20k(pf->pdev)) + hwbase = pf->reg_base + RVU_PFX_FUNC_PFAF_MBOX + + ((u64)BLKADDR_MBOX << RVU_FUNC_BLKADDR_SHIFT); + else + /* Mailbox is a reserved memory (in RAM) region shared between + * admin function (i.e AF) and this PF, shouldn't be mapped as + * device memory to allow unaligned accesses. + */ + hwbase = ioremap_wc(pci_resource_start + (pf->pdev, PCI_MBOX_BAR_NUM), MBOX_SIZE); if (!hwbase) { dev_err(pf->dev, "Unable to map PFAF mailbox region\n"); err = -ENOMEM; @@ -1971,7 +2043,7 @@ int otx2_open(struct net_device *netdev) if (err) { dev_err(pf->dev, "RVUPF%d: IRQ registration failed for QERR\n", - rvu_get_pf(pf->pcifunc)); + rvu_get_pf(pf->pdev, pf->pcifunc)); goto err_disable_napi; } @@ -1989,7 +2061,7 @@ int otx2_open(struct net_device *netdev) if (name_len >= NAME_SIZE) { dev_err(pf->dev, "RVUPF%d: IRQ registration failed for CQ%d, irq name is too long\n", - rvu_get_pf(pf->pcifunc), qidx); + rvu_get_pf(pf->pdev, pf->pcifunc), qidx); err = -EINVAL; goto err_free_cints; } @@ -2000,7 +2072,7 @@ int otx2_open(struct net_device *netdev) if (err) { dev_err(pf->dev, "RVUPF%d: IRQ registration failed for CQ%d\n", - rvu_get_pf(pf->pcifunc), qidx); + rvu_get_pf(pf->pdev, pf->pcifunc), qidx); goto err_free_cints; } vec++; @@ -2997,8 +3069,13 @@ int otx2_init_rsrc(struct pci_dev *pdev, struct otx2_nic *pf) if (err) return err; - err = pci_alloc_irq_vectors(hw->pdev, RVU_PF_INT_VEC_CNT, - RVU_PF_INT_VEC_CNT, PCI_IRQ_MSIX); + if (!is_cn20k(pf->pdev)) + err = pci_alloc_irq_vectors(hw->pdev, RVU_PF_INT_VEC_CNT, + RVU_PF_INT_VEC_CNT, PCI_IRQ_MSIX); + else + err = pci_alloc_irq_vectors(hw->pdev, RVU_MBOX_PF_INT_VEC_CNT, + RVU_MBOX_PF_INT_VEC_CNT, + PCI_IRQ_MSIX); if (err < 0) { dev_err(dev, "%s: Failed to alloc %d IRQ vectors\n", __func__, num_vec); @@ -3007,6 +3084,11 @@ int otx2_init_rsrc(struct pci_dev *pdev, struct otx2_nic *pf) otx2_setup_dev_hw_settings(pf); + if (is_cn20k(pf->pdev)) + cn20k_init(pf); + else + otx2_init_hw_ops(pf); + /* Init PF <=> AF mailbox stuff */ err = otx2_pfaf_mbox_init(pf); if (err) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h index e3aee6e36215..1cd576fd09c5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h @@ -44,6 +44,17 @@ #define RVU_PF_VF_MBOX_ADDR (0xC40) #define RVU_PF_LMTLINE_ADDR (0xC48) +#define RVU_MBOX_PF_VFX_PFVF_TRIGX(a) (0x2000 | (a) << 3) +#define RVU_MBOX_PF_VFPF_INTX(a) (0x1000 | (a) << 3) +#define RVU_MBOX_PF_VFPF_INT_W1SX(a) (0x1020 | (a) << 3) +#define RVU_MBOX_PF_VFPF_INT_ENA_W1SX(a) (0x1040 | (a) << 3) +#define RVU_MBOX_PF_VFPF_INT_ENA_W1CX(a) (0x1060 | (a) << 3) + +#define RVU_MBOX_PF_VFPF1_INTX(a) (0x1080 | (a) << 3) +#define RVU_MBOX_PF_VFPF1_INT_W1SX(a) (0x10a0 | (a) << 3) +#define RVU_MBOX_PF_VFPF1_INT_ENA_W1SX(a) (0x10c0 | (a) << 3) +#define RVU_MBOX_PF_VFPF1_INT_ENA_W1CX(a) (0x10e0 | (a) << 3) + /* RVU VF registers */ #define RVU_VF_VFPF_MBOX0 (0x00000) #define RVU_VF_VFPF_MBOX1 (0x00008) @@ -58,6 +69,11 @@ #define RVU_VF_MSIX_PBAX(a) (0xF0000 | (a) << 3) #define RVU_VF_MBOX_REGION (0xC0000) +/* CN20K RVU_MBOX_E: RVU PF/VF MBOX Address Range Enumeration */ +#define RVU_MBOX_AF_PFX_ADDR(a) (0x5000 | (a) << 4) +#define RVU_PFX_FUNC_PFAF_MBOX (0x80000) +#define RVU_PFX_FUNCX_VFAF_MBOX (0x40000) + #define RVU_FUNC_BLKADDR_SHIFT 20 #define RVU_FUNC_BLKADDR_MASK 0x1FULL @@ -138,39 +154,12 @@ #define NIX_LF_CINTX_ENA_W1S(a) (NIX_LFBASE | 0xD40 | (a) << 12) #define NIX_LF_CINTX_ENA_W1C(a) (NIX_LFBASE | 0xD50 | (a) << 12) -/* NIX AF transmit scheduler registers */ -#define NIX_AF_SMQX_CFG(a) (0x700 | (u64)(a) << 16) -#define NIX_AF_TL4X_SDP_LINK_CFG(a) (0xB10 | (u64)(a) << 16) -#define NIX_AF_TL1X_SCHEDULE(a) (0xC00 | (u64)(a) << 16) -#define NIX_AF_TL1X_CIR(a) (0xC20 | (u64)(a) << 16) -#define NIX_AF_TL1X_TOPOLOGY(a) (0xC80 | (u64)(a) << 16) -#define NIX_AF_TL2X_PARENT(a) (0xE88 | (u64)(a) << 16) -#define NIX_AF_TL2X_SCHEDULE(a) (0xE00 | (u64)(a) << 16) -#define NIX_AF_TL2X_TOPOLOGY(a) (0xE80 | (u64)(a) << 16) -#define NIX_AF_TL2X_CIR(a) (0xE20 | (u64)(a) << 16) -#define NIX_AF_TL2X_PIR(a) (0xE30 | (u64)(a) << 16) -#define NIX_AF_TL3X_PARENT(a) (0x1088 | (u64)(a) << 16) -#define NIX_AF_TL3X_SCHEDULE(a) (0x1000 | (u64)(a) << 16) -#define NIX_AF_TL3X_SHAPE(a) (0x1010 | (u64)(a) << 16) -#define NIX_AF_TL3X_CIR(a) (0x1020 | (u64)(a) << 16) -#define NIX_AF_TL3X_PIR(a) (0x1030 | (u64)(a) << 16) -#define NIX_AF_TL3X_TOPOLOGY(a) (0x1080 | (u64)(a) << 16) -#define NIX_AF_TL4X_PARENT(a) (0x1288 | (u64)(a) << 16) -#define NIX_AF_TL4X_SCHEDULE(a) (0x1200 | (u64)(a) << 16) -#define NIX_AF_TL4X_SHAPE(a) (0x1210 | (u64)(a) << 16) -#define NIX_AF_TL4X_CIR(a) (0x1220 | (u64)(a) << 16) -#define NIX_AF_TL4X_PIR(a) (0x1230 | (u64)(a) << 16) -#define NIX_AF_TL4X_TOPOLOGY(a) (0x1280 | (u64)(a) << 16) -#define NIX_AF_MDQX_SCHEDULE(a) (0x1400 | (u64)(a) << 16) -#define NIX_AF_MDQX_SHAPE(a) (0x1410 | (u64)(a) << 16) -#define NIX_AF_MDQX_CIR(a) (0x1420 | (u64)(a) << 16) -#define NIX_AF_MDQX_PIR(a) (0x1430 | (u64)(a) << 16) -#define NIX_AF_MDQX_PARENT(a) (0x1480 | (u64)(a) << 16) -#define NIX_AF_TL3_TL2X_LINKX_CFG(a, b) (0x1700 | (u64)(a) << 16 | (b) << 3) - /* LMT LF registers */ #define LMT_LFBASE BIT_ULL(RVU_FUNC_BLKADDR_SHIFT) #define LMT_LF_LMTLINEX(a) (LMT_LFBASE | 0x000 | (a) << 12) #define LMT_LF_LMTCANCEL (LMT_LFBASE | 0x400) +/* CN20K registers */ +#define RVU_PF_DISC (0x0) + #endif /* OTX2_REG_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 9a226ca74425..5f80b23c5335 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -467,7 +467,8 @@ static int otx2_tc_parse_actions(struct otx2_nic *nic, target = act->dev; if (target->dev.parent) { priv = netdev_priv(target); - if (rvu_get_pf(nic->pcifunc) != rvu_get_pf(priv->pcifunc)) { + if (rvu_get_pf(nic->pdev, nic->pcifunc) != + rvu_get_pf(nic->pdev, priv->pcifunc)) { NL_SET_ERR_MSG_MOD(extack, "can't redirect to other pf/vf"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 8a8b598bd389..5589fccd370b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -240,6 +240,10 @@ static void otx2vf_disable_mbox_intr(struct otx2_nic *vf) /* Disable VF => PF mailbox IRQ */ otx2_write64(vf, RVU_VF_INT_ENA_W1C, BIT_ULL(0)); + + if (is_cn20k(vf->pdev)) + otx2_write64(vf, RVU_VF_INT_ENA_W1C, BIT_ULL(0) | BIT_ULL(1)); + free_irq(vector, vf); } @@ -252,9 +256,18 @@ static int otx2vf_register_mbox_intr(struct otx2_nic *vf, bool probe_pf) /* Register mailbox interrupt handler */ irq_name = &hw->irq_name[RVU_VF_INT_VEC_MBOX * NAME_SIZE]; - snprintf(irq_name, NAME_SIZE, "RVUVFAF Mbox"); - err = request_irq(pci_irq_vector(vf->pdev, RVU_VF_INT_VEC_MBOX), - otx2vf_vfaf_mbox_intr_handler, 0, irq_name, vf); + snprintf(irq_name, NAME_SIZE, "RVUVF%d AFVF Mbox", ((vf->pcifunc & + RVU_PFVF_FUNC_MASK) - 1)); + + if (!is_cn20k(vf->pdev)) { + err = request_irq(pci_irq_vector(vf->pdev, RVU_VF_INT_VEC_MBOX), + otx2vf_vfaf_mbox_intr_handler, 0, irq_name, vf); + } else { + err = request_irq(pci_irq_vector(vf->pdev, RVU_VF_INT_VEC_MBOX), + vf->hw_ops->vfaf_mbox_intr_handler, 0, irq_name, + vf); + } + if (err) { dev_err(vf->dev, "RVUPF: IRQ registration failed for VFAF mbox irq\n"); @@ -264,8 +277,15 @@ static int otx2vf_register_mbox_intr(struct otx2_nic *vf, bool probe_pf) /* Enable mailbox interrupt for msgs coming from PF. * First clear to avoid spurious interrupts, if any. */ - otx2_write64(vf, RVU_VF_INT, BIT_ULL(0)); - otx2_write64(vf, RVU_VF_INT_ENA_W1S, BIT_ULL(0)); + if (!is_cn20k(vf->pdev)) { + otx2_write64(vf, RVU_VF_INT, BIT_ULL(0)); + otx2_write64(vf, RVU_VF_INT_ENA_W1S, BIT_ULL(0)); + } else { + otx2_write64(vf, RVU_VF_INT, BIT_ULL(0) | BIT_ULL(1) | + BIT_ULL(2) | BIT_ULL(3)); + otx2_write64(vf, RVU_VF_INT_ENA_W1S, BIT_ULL(0) | + BIT_ULL(1) | BIT_ULL(2) | BIT_ULL(3)); + } if (!probe_pf) return 0; @@ -315,7 +335,13 @@ static int otx2vf_vfaf_mbox_init(struct otx2_nic *vf) if (!vf->mbox_wq) return -ENOMEM; - if (test_bit(CN10K_MBOX, &vf->hw.cap_flag)) { + /* For cn20k platform, VF mailbox region is in dram aliased from AF + * VF MBOX ADDR, MBOX is a separate RVU block. + */ + if (is_cn20k(vf->pdev)) { + hwbase = vf->reg_base + RVU_VF_MBOX_REGION + ((u64)BLKADDR_MBOX << + RVU_FUNC_BLKADDR_SHIFT); + } else if (test_bit(CN10K_MBOX, &vf->hw.cap_flag)) { /* For cn10k platform, VF mailbox region is in its BAR2 * register space */ @@ -616,6 +642,12 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) } otx2_setup_dev_hw_settings(vf); + + if (is_cn20k(vf->pdev)) + cn20k_init(vf); + else + otx2_init_hw_ops(vf); + /* Init VF <=> PF mailbox stuff */ err = otx2vf_vfaf_mbox_init(vf); if (err) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c index 2cd3da3b6843..25af98034e2e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c @@ -244,10 +244,10 @@ static int rvu_rep_devlink_port_register(struct rep_dev *rep) if (!(rep->pcifunc & RVU_PFVF_FUNC_MASK)) { attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; - attrs.phys.port_number = rvu_get_pf(rep->pcifunc); + attrs.phys.port_number = rvu_get_pf(priv->pdev, rep->pcifunc); } else { attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF; - attrs.pci_vf.pf = rvu_get_pf(rep->pcifunc); + attrs.pci_vf.pf = rvu_get_pf(priv->pdev, rep->pcifunc); attrs.pci_vf.vf = rep->pcifunc & RVU_PFVF_FUNC_MASK; } @@ -672,7 +672,8 @@ int rvu_rep_create(struct otx2_nic *priv, struct netlink_ext_ack *extack) rep->pcifunc = pcifunc; snprintf(ndev->name, sizeof(ndev->name), "Rpf%dvf%d", - rvu_get_pf(pcifunc), (pcifunc & RVU_PFVF_FUNC_MASK)); + rvu_get_pf(priv->pdev, pcifunc), + (pcifunc & RVU_PFVF_FUNC_MASK)); ndev->hw_features = (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXHASH | diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c index 752a72499b4f..be80da03a594 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c @@ -290,9 +290,6 @@ static int mlx4_en_dcbnl_ieee_getets(struct net_device *dev, struct mlx4_en_priv *priv = netdev_priv(dev); struct ieee_ets *my_ets = &priv->ets; - if (!my_ets) - return -EINVAL; - ets->ets_cap = IEEE_8021QAZ_MAX_TCS; ets->cbs = my_ets->cbs; memcpy(ets->tc_tx_bw, my_ets->tc_tx_bw, sizeof(ets->tc_tx_bw)); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 281b34af0bb4..d2071aff7b8f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2670,8 +2670,7 @@ static int mlx4_udp_tunnel_sync(struct net_device *dev, unsigned int table) static const struct udp_tunnel_nic_info mlx4_udp_tunnels = { .sync_table = mlx4_udp_tunnel_sync, - .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP | - UDP_TUNNEL_NIC_INFO_IPV4_ONLY, + .flags = UDP_TUNNEL_NIC_INFO_IPV4_ONLY, .tables = { { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, }, diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index febeadfdd5a5..03d2fc7d9b09 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -49,6 +49,8 @@ #include <linux/mlx4/device.h> #include <linux/mlx4/doorbell.h> +#include <rdma/ib_verbs.h> + #include "mlx4.h" #include "fw.h" #include "icm.h" @@ -1246,14 +1248,6 @@ err_out: return err ? err : count; } -enum ibta_mtu { - IB_MTU_256 = 1, - IB_MTU_512 = 2, - IB_MTU_1024 = 3, - IB_MTU_2048 = 4, - IB_MTU_4096 = 5 -}; - static inline int int_to_ibta_mtu(int mtu) { switch (mtu) { @@ -1266,7 +1260,7 @@ static inline int int_to_ibta_mtu(int mtu) } } -static inline int ibta_mtu_to_int(enum ibta_mtu mtu) +static inline int ibta_mtu_to_int(enum ib_mtu mtu) { switch (mtu) { case IB_MTU_256: return 256; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 5b0d03b3efe8..65a73913b9a2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -278,10 +278,6 @@ enum packet_merge { struct mlx5e_packet_merge_param { enum packet_merge type; u32 timeout; - struct { - u8 match_criteria_type; - u8 alignment_granularity; - } shampo; }; struct mlx5e_params { @@ -557,7 +553,7 @@ struct mlx5e_icosq { } ____cacheline_aligned_in_smp; struct mlx5e_frag_page { - struct page *page; + netmem_ref netmem; u16 frags; }; @@ -638,7 +634,6 @@ struct mlx5e_shampo_hd { struct mlx5e_frag_page *pages; u32 hd_per_wq; u16 hd_per_wqe; - u16 pages_per_wq; unsigned long *bitmap; u16 pi; u16 ci; @@ -721,7 +716,11 @@ struct mlx5e_rq { struct bpf_prog __rcu *xdp_prog; struct mlx5e_xdpsq *xdpsq; DECLARE_BITMAP(flags, 8); + + /* page pools */ struct page_pool *page_pool; + struct page_pool *hd_page_pool; + struct mlx5e_xdp_buff mxbuf; /* AF_XDP zero-copy */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 58ec5e44aa7a..fc945bce933a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -901,6 +901,7 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, { void *rqc = param->rqc; void *wq = MLX5_ADDR_OF(rqc, rqc, wq); + u32 lro_timeout; int ndsegs = 1; int err; @@ -926,22 +927,25 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, MLX5_SET(wq, wq, log_wqe_stride_size, log_wqe_stride_size - MLX5_MPWQE_LOG_STRIDE_SZ_BASE); MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(mdev, params, xsk)); - if (params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) { - MLX5_SET(wq, wq, shampo_enable, true); - MLX5_SET(wq, wq, log_reservation_size, - mlx5e_shampo_get_log_rsrv_size(mdev, params)); - MLX5_SET(wq, wq, - log_max_num_of_packets_per_reservation, - mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params)); - MLX5_SET(wq, wq, log_headers_entry_size, - mlx5e_shampo_get_log_hd_entry_size(mdev, params)); - MLX5_SET(rqc, rqc, reservation_timeout, - mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_SHAMPO_TIMEOUT)); - MLX5_SET(rqc, rqc, shampo_match_criteria_type, - params->packet_merge.shampo.match_criteria_type); - MLX5_SET(rqc, rqc, shampo_no_match_alignment_granularity, - params->packet_merge.shampo.alignment_granularity); - } + if (params->packet_merge.type != MLX5E_PACKET_MERGE_SHAMPO) + break; + + MLX5_SET(wq, wq, shampo_enable, true); + MLX5_SET(wq, wq, log_reservation_size, + mlx5e_shampo_get_log_rsrv_size(mdev, params)); + MLX5_SET(wq, wq, + log_max_num_of_packets_per_reservation, + mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params)); + MLX5_SET(wq, wq, log_headers_entry_size, + mlx5e_shampo_get_log_hd_entry_size(mdev, params)); + lro_timeout = + mlx5e_choose_lro_timeout(mdev, + MLX5E_DEFAULT_SHAMPO_TIMEOUT); + MLX5_SET(rqc, rqc, reservation_timeout, lro_timeout); + MLX5_SET(rqc, rqc, shampo_match_criteria_type, + MLX5_RQC_SHAMPO_MATCH_CRITERIA_TYPE_EXTENDED); + MLX5_SET(rqc, rqc, shampo_no_match_alignment_granularity, + MLX5_RQC_SHAMPO_NO_MATCH_ALIGNMENT_GRANULARITY_STRIDE); break; } default: /* MLX5_WQ_TYPE_CYCLIC */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index e837c21d3d21..6501252359b0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -362,7 +362,8 @@ mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma) dma_unmap_single(pdev, dma->addr, dma->size, DMA_TO_DEVICE); break; case MLX5E_DMA_MAP_PAGE: - dma_unmap_page(pdev, dma->addr, dma->size, DMA_TO_DEVICE); + netmem_dma_unmap_page_attrs(pdev, dma->addr, dma->size, + DMA_TO_DEVICE, 0); break; default: WARN_ONCE(true, "mlx5e_tx_dma_unmap unknown DMA type!\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 8b9ee8bac674..35479cbf98d5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -32,6 +32,7 @@ #include <linux/dim.h> #include <linux/ethtool_netlink.h> +#include <net/netdev_queues.h> #include "en.h" #include "en/channels.h" @@ -365,11 +366,6 @@ void mlx5e_ethtool_get_ringparam(struct mlx5e_priv *priv, param->tx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE; param->rx_pending = 1 << priv->channels.params.log_rq_mtu_frames; param->tx_pending = 1 << priv->channels.params.log_sq_size; - - kernel_param->tcp_data_split = - (priv->channels.params.packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) ? - ETHTOOL_TCP_DATA_SPLIT_ENABLED : - ETHTOOL_TCP_DATA_SPLIT_DISABLED; } static void mlx5e_get_ringparam(struct net_device *dev, @@ -382,6 +378,27 @@ static void mlx5e_get_ringparam(struct net_device *dev, mlx5e_ethtool_get_ringparam(priv, param, kernel_param); } +static bool mlx5e_ethtool_set_tcp_data_split(struct mlx5e_priv *priv, + u8 tcp_data_split, + struct netlink_ext_ack *extack) +{ + struct net_device *dev = priv->netdev; + + if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED && + !(dev->features & NETIF_F_GRO_HW)) { + NL_SET_ERR_MSG_MOD(extack, + "TCP-data-split is not supported when GRO HW is disabled"); + return false; + } + + /* Might need to disable HW-GRO if it was kept on due to hds. */ + if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_DISABLED && + dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED) + netdev_update_features(priv->netdev); + + return true; +} + int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv, struct ethtool_ringparam *param, struct netlink_ext_ack *extack) @@ -440,6 +457,11 @@ static int mlx5e_set_ringparam(struct net_device *dev, { struct mlx5e_priv *priv = netdev_priv(dev); + if (!mlx5e_ethtool_set_tcp_data_split(priv, + kernel_param->tcp_data_split, + extack)) + return -EINVAL; + return mlx5e_ethtool_set_ringparam(priv, param, extack); } @@ -2623,6 +2645,7 @@ const struct ethtool_ops mlx5e_ethtool_ops = { ETHTOOL_COALESCE_USE_ADAPTIVE | ETHTOOL_COALESCE_USE_CQE, .supported_input_xfrm = RXH_XFRM_SYM_OR_XOR, + .supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT, .get_drvinfo = mlx5e_get_drvinfo, .get_link = ethtool_op_get_link, .get_link_ext_state = mlx5e_get_link_ext_state, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index ea822c69d137..dca5ca51a470 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -41,6 +41,7 @@ #include <linux/filter.h> #include <net/netdev_lock.h> #include <net/netdev_queues.h> +#include <net/netdev_rx_queue.h> #include <net/page_pool/types.h> #include <net/pkt_sched.h> #include <net/xdp_sock_drv.h> @@ -78,7 +79,8 @@ static bool mlx5e_hw_gro_supported(struct mlx5_core_dev *mdev) { - if (!MLX5_CAP_GEN(mdev, shampo)) + if (!MLX5_CAP_GEN(mdev, shampo) || + !MLX5_CAP_SHAMPO(mdev, shampo_header_split_data_merge)) return false; /* Our HW-GRO implementation relies on "KSM Mkey" for @@ -331,47 +333,6 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, ucseg->mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE); } -static int mlx5e_rq_shampo_hd_alloc(struct mlx5e_rq *rq, int node) -{ - rq->mpwqe.shampo = kvzalloc_node(sizeof(*rq->mpwqe.shampo), - GFP_KERNEL, node); - if (!rq->mpwqe.shampo) - return -ENOMEM; - return 0; -} - -static void mlx5e_rq_shampo_hd_free(struct mlx5e_rq *rq) -{ - kvfree(rq->mpwqe.shampo); -} - -static int mlx5e_rq_shampo_hd_info_alloc(struct mlx5e_rq *rq, int node) -{ - struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; - - shampo->bitmap = bitmap_zalloc_node(shampo->hd_per_wq, GFP_KERNEL, - node); - shampo->pages = kvzalloc_node(array_size(shampo->hd_per_wq, - sizeof(*shampo->pages)), - GFP_KERNEL, node); - if (!shampo->bitmap || !shampo->pages) - goto err_nomem; - - return 0; - -err_nomem: - bitmap_free(shampo->bitmap); - kvfree(shampo->pages); - - return -ENOMEM; -} - -static void mlx5e_rq_shampo_hd_info_free(struct mlx5e_rq *rq) -{ - bitmap_free(rq->mpwqe.shampo->bitmap); - kvfree(rq->mpwqe.shampo->pages); -} - static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, int node) { int wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq); @@ -584,19 +545,18 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq } static int mlx5e_create_rq_hd_umr_mkey(struct mlx5_core_dev *mdev, - struct mlx5e_rq *rq) + u16 hd_per_wq, u32 *umr_mkey) { u32 max_ksm_size = BIT(MLX5_CAP_GEN(mdev, log_max_klm_list_size)); - if (max_ksm_size < rq->mpwqe.shampo->hd_per_wq) { + if (max_ksm_size < hd_per_wq) { mlx5_core_err(mdev, "max ksm list size 0x%x is smaller than shampo header buffer list size 0x%x\n", - max_ksm_size, rq->mpwqe.shampo->hd_per_wq); + max_ksm_size, hd_per_wq); return -EINVAL; } - - return mlx5e_create_umr_ksm_mkey(mdev, rq->mpwqe.shampo->hd_per_wq, + return mlx5e_create_umr_ksm_mkey(mdev, hd_per_wq, MLX5E_SHAMPO_LOG_HEADER_ENTRY_SIZE, - &rq->mpwqe.shampo->mkey); + umr_mkey); } static void mlx5e_init_frags_partition(struct mlx5e_rq *rq) @@ -758,6 +718,42 @@ static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param xdp_frag_size); } +static int mlx5e_rq_shampo_hd_info_alloc(struct mlx5e_rq *rq, u16 hd_per_wq, + int node) +{ + struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; + + shampo->hd_per_wq = hd_per_wq; + + shampo->bitmap = bitmap_zalloc_node(hd_per_wq, GFP_KERNEL, node); + shampo->pages = kvzalloc_node(array_size(hd_per_wq, + sizeof(*shampo->pages)), + GFP_KERNEL, node); + if (!shampo->bitmap || !shampo->pages) + goto err_nomem; + + return 0; + +err_nomem: + kvfree(shampo->pages); + bitmap_free(shampo->bitmap); + + return -ENOMEM; +} + +static void mlx5e_rq_shampo_hd_info_free(struct mlx5e_rq *rq) +{ + kvfree(rq->mpwqe.shampo->pages); + bitmap_free(rq->mpwqe.shampo->bitmap); +} + +static bool mlx5_rq_needs_separate_hd_pool(struct mlx5e_rq *rq) +{ + struct netdev_rx_queue *rxq = __netif_get_rx_queue(rq->netdev, rq->ix); + + return !!rxq->mp_params.mp_ops; +} + static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_rq_param *rqp, @@ -765,42 +761,81 @@ static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev, u32 *pool_size, int node) { + void *wqc = MLX5_ADDR_OF(rqc, rqp->rqc, wq); + u32 hd_pool_size; + u16 hd_per_wq; + int wq_size; int err; if (!test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) return 0; - err = mlx5e_rq_shampo_hd_alloc(rq, node); - if (err) - goto out; - rq->mpwqe.shampo->hd_per_wq = - mlx5e_shampo_hd_per_wq(mdev, params, rqp); - err = mlx5e_create_rq_hd_umr_mkey(mdev, rq); + + rq->mpwqe.shampo = kvzalloc_node(sizeof(*rq->mpwqe.shampo), + GFP_KERNEL, node); + if (!rq->mpwqe.shampo) + return -ENOMEM; + + /* split headers data structures */ + hd_per_wq = mlx5e_shampo_hd_per_wq(mdev, params, rqp); + err = mlx5e_rq_shampo_hd_info_alloc(rq, hd_per_wq, node); if (err) - goto err_shampo_hd; - err = mlx5e_rq_shampo_hd_info_alloc(rq, node); + goto err_shampo_hd_info_alloc; + + err = mlx5e_create_rq_hd_umr_mkey(mdev, hd_per_wq, + &rq->mpwqe.shampo->mkey); if (err) - goto err_shampo_info; + goto err_umr_mkey; + + rq->mpwqe.shampo->key = cpu_to_be32(rq->mpwqe.shampo->mkey); + rq->mpwqe.shampo->hd_per_wqe = + mlx5e_shampo_hd_per_wqe(mdev, params, rqp); + wq_size = BIT(MLX5_GET(wq, wqc, log_wq_sz)); + hd_pool_size = (rq->mpwqe.shampo->hd_per_wqe * wq_size) / + MLX5E_SHAMPO_WQ_HEADER_PER_PAGE; + + if (mlx5_rq_needs_separate_hd_pool(rq)) { + /* Separate page pool for shampo headers */ + struct page_pool_params pp_params = { }; + + pp_params.order = 0; + pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV; + pp_params.pool_size = hd_pool_size; + pp_params.nid = node; + pp_params.dev = rq->pdev; + pp_params.napi = rq->cq.napi; + pp_params.netdev = rq->netdev; + pp_params.dma_dir = rq->buff.map_dir; + pp_params.max_len = PAGE_SIZE; + + rq->hd_page_pool = page_pool_create(&pp_params); + if (IS_ERR(rq->hd_page_pool)) { + err = PTR_ERR(rq->hd_page_pool); + rq->hd_page_pool = NULL; + goto err_hds_page_pool; + } + } else { + /* Common page pool, reserve space for headers. */ + *pool_size += hd_pool_size; + rq->hd_page_pool = NULL; + } + + /* gro only data structures */ rq->hw_gro_data = kvzalloc_node(sizeof(*rq->hw_gro_data), GFP_KERNEL, node); if (!rq->hw_gro_data) { err = -ENOMEM; goto err_hw_gro_data; } - rq->mpwqe.shampo->key = - cpu_to_be32(rq->mpwqe.shampo->mkey); - rq->mpwqe.shampo->hd_per_wqe = - mlx5e_shampo_hd_per_wqe(mdev, params, rqp); - rq->mpwqe.shampo->pages_per_wq = - rq->mpwqe.shampo->hd_per_wq / MLX5E_SHAMPO_WQ_HEADER_PER_PAGE; - *pool_size += rq->mpwqe.shampo->pages_per_wq; + return 0; err_hw_gro_data: - mlx5e_rq_shampo_hd_info_free(rq); -err_shampo_info: + page_pool_destroy(rq->hd_page_pool); +err_hds_page_pool: mlx5_core_destroy_mkey(mdev, rq->mpwqe.shampo->mkey); -err_shampo_hd: - mlx5e_rq_shampo_hd_free(rq); -out: +err_umr_mkey: + mlx5e_rq_shampo_hd_info_free(rq); +err_shampo_hd_info_alloc: + kvfree(rq->mpwqe.shampo); return err; } @@ -810,9 +845,11 @@ static void mlx5e_rq_free_shampo(struct mlx5e_rq *rq) return; kvfree(rq->hw_gro_data); + if (rq->hd_page_pool != rq->page_pool) + page_pool_destroy(rq->hd_page_pool); mlx5e_rq_shampo_hd_info_free(rq); mlx5_core_destroy_mkey(rq->mdev, rq->mpwqe.shampo->mkey); - mlx5e_rq_shampo_hd_free(rq); + kvfree(rq->mpwqe.shampo); } static int mlx5e_alloc_rq(struct mlx5e_params *params, @@ -929,6 +966,11 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, pp_params.netdev = rq->netdev; pp_params.dma_dir = rq->buff.map_dir; pp_params.max_len = PAGE_SIZE; + pp_params.queue_idx = rq->ix; + + /* Shampo header data split allow for unreadable netmem */ + if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) + pp_params.flags |= PP_FLAG_ALLOW_UNREADABLE_NETMEM; /* page_pool can be used even when there is no rq->xdp_prog, * given page_pool does not handle DMA mapping there is no @@ -941,6 +983,8 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, rq->page_pool = NULL; goto err_free_by_rq_type; } + if (!rq->hd_page_pool) + rq->hd_page_pool = rq->page_pool; if (xdp_rxq_info_is_reg(&rq->xdp_rxq)) err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_PAGE_POOL, rq->page_pool); @@ -4043,10 +4087,6 @@ static int set_feature_hw_gro(struct net_device *netdev, bool enable) if (enable) { new_params.packet_merge.type = MLX5E_PACKET_MERGE_SHAMPO; - new_params.packet_merge.shampo.match_criteria_type = - MLX5_RQC_SHAMPO_MATCH_CRITERIA_TYPE_EXTENDED; - new_params.packet_merge.shampo.alignment_granularity = - MLX5_RQC_SHAMPO_NO_MATCH_ALIGNMENT_GRANULARITY_STRIDE; } else if (new_params.packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) { new_params.packet_merge.type = MLX5E_PACKET_MERGE_NONE; } else { @@ -4373,6 +4413,7 @@ static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev static netdev_features_t mlx5e_fix_features(struct net_device *netdev, netdev_features_t features) { + struct netdev_config *cfg = netdev->cfg_pending; struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_vlan_table *vlan; struct mlx5e_params *params; @@ -4439,6 +4480,13 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, } } + /* The header-data split ring param requires HW GRO to stay enabled. */ + if (cfg && cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED && + !(features & NETIF_F_GRO_HW)) { + netdev_warn(netdev, "Keeping HW-GRO enabled, TCP header-data split depends on it\n"); + features |= NETIF_F_GRO_HW; + } + if (mlx5e_is_uplink_rep(priv)) { features = mlx5e_fix_uplink_rep_features(netdev, features); netdev->netns_immutable = true; @@ -5303,8 +5351,7 @@ void mlx5e_vxlan_set_netdev_info(struct mlx5e_priv *priv) priv->nic_info.set_port = mlx5e_vxlan_set_port; priv->nic_info.unset_port = mlx5e_vxlan_unset_port; - priv->nic_info.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP | - UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN; + priv->nic_info.flags = UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN; priv->nic_info.tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN; /* Don't count the space hard-coded to the IANA port */ priv->nic_info.tables[0].n_entries = @@ -5454,6 +5501,103 @@ static const struct netdev_stat_ops mlx5e_stat_ops = { .get_base_stats = mlx5e_get_base_stats, }; +struct mlx5_qmgmt_data { + struct mlx5e_channel *c; + struct mlx5e_channel_param cparam; +}; + +static int mlx5e_queue_mem_alloc(struct net_device *dev, void *newq, + int queue_index) +{ + struct mlx5_qmgmt_data *new = (struct mlx5_qmgmt_data *)newq; + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_channels *chs = &priv->channels; + struct mlx5e_params params = chs->params; + struct mlx5_core_dev *mdev; + int err; + + mutex_lock(&priv->state_lock); + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { + err = -ENODEV; + goto unlock; + } + + if (queue_index >= chs->num) { + err = -ERANGE; + goto unlock; + } + + if (MLX5E_GET_PFLAG(&chs->params, MLX5E_PFLAG_TX_PORT_TS) || + chs->params.ptp_rx || + chs->params.xdp_prog || + priv->htb) { + netdev_err(priv->netdev, + "Cloning channels with Port/rx PTP, XDP or HTB is not supported\n"); + err = -EOPNOTSUPP; + goto unlock; + } + + mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, queue_index); + err = mlx5e_build_channel_param(mdev, ¶ms, &new->cparam); + if (err) + goto unlock; + + err = mlx5e_open_channel(priv, queue_index, ¶ms, NULL, &new->c); +unlock: + mutex_unlock(&priv->state_lock); + return err; +} + +static void mlx5e_queue_mem_free(struct net_device *dev, void *mem) +{ + struct mlx5_qmgmt_data *data = (struct mlx5_qmgmt_data *)mem; + + /* not supposed to happen since mlx5e_queue_start never fails + * but this is how this should be implemented just in case + */ + if (data->c) + mlx5e_close_channel(data->c); +} + +static int mlx5e_queue_stop(struct net_device *dev, void *oldq, int queue_index) +{ + /* In mlx5 a txq cannot be simply stopped in isolation, only restarted. + * mlx5e_queue_start does not fail, we stop the old queue there. + * TODO: Improve this. + */ + return 0; +} + +static int mlx5e_queue_start(struct net_device *dev, void *newq, + int queue_index) +{ + struct mlx5_qmgmt_data *new = (struct mlx5_qmgmt_data *)newq; + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_channel *old; + + mutex_lock(&priv->state_lock); + + /* stop and close the old */ + old = priv->channels.c[queue_index]; + mlx5e_deactivate_priv_channels(priv); + /* close old before activating new, to avoid napi conflict */ + mlx5e_close_channel(old); + + /* start the new */ + priv->channels.c[queue_index] = new->c; + mlx5e_activate_priv_channels(priv); + mutex_unlock(&priv->state_lock); + return 0; +} + +static const struct netdev_queue_mgmt_ops mlx5e_queue_mgmt_ops = { + .ndo_queue_mem_size = sizeof(struct mlx5_qmgmt_data), + .ndo_queue_mem_alloc = mlx5e_queue_mem_alloc, + .ndo_queue_mem_free = mlx5e_queue_mem_free, + .ndo_queue_start = mlx5e_queue_start, + .ndo_queue_stop = mlx5e_queue_stop, +}; + static void mlx5e_build_nic_netdev(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -5464,6 +5608,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) SET_NETDEV_DEV(netdev, mdev->device); netdev->netdev_ops = &mlx5e_netdev_ops; + netdev->queue_mgmt_ops = &mlx5e_queue_mgmt_ops; netdev->xdp_metadata_ops = &mlx5e_xdp_metadata_ops; netdev->xsk_tx_metadata_ops = &mlx5e_xsk_tx_metadata_ops; netdev->request_ops_lock = true; @@ -5506,17 +5651,17 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) MLX5E_MPWRQ_UMR_MODE_ALIGNED)) netdev->vlan_features |= NETIF_F_LRO; + if (mlx5e_hw_gro_supported(mdev) && + mlx5e_check_fragmented_striding_rq_cap(mdev, PAGE_SHIFT, + MLX5E_MPWRQ_UMR_MODE_ALIGNED)) + netdev->vlan_features |= NETIF_F_GRO_HW; + netdev->hw_features = netdev->vlan_features; netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX; netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX; netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; netdev->hw_features |= NETIF_F_HW_VLAN_STAG_TX; - if (mlx5e_hw_gro_supported(mdev) && - mlx5e_check_fragmented_striding_rq_cap(mdev, PAGE_SHIFT, - MLX5E_MPWRQ_UMR_MODE_ALIGNED)) - netdev->hw_features |= NETIF_F_GRO_HW; - if (mlx5e_tunnel_any_tx_proto_supported(mdev)) { netdev->hw_enc_features |= NETIF_F_HW_CSUM; netdev->hw_enc_features |= NETIF_F_TSO; @@ -5595,6 +5740,8 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->priv_flags |= IFF_UNICAST_FLT; + netdev->netmem_tx = true; + netif_set_tso_max_size(netdev, GSO_MAX_SIZE); mlx5e_set_xdp_feature(netdev); mlx5e_set_netdev_dev_addr(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 84b1ab8233b8..2bb32082bfcc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -273,33 +273,32 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq, #define MLX5E_PAGECNT_BIAS_MAX (PAGE_SIZE / 64) -static int mlx5e_page_alloc_fragmented(struct mlx5e_rq *rq, +static int mlx5e_page_alloc_fragmented(struct page_pool *pp, struct mlx5e_frag_page *frag_page) { - struct page *page; + netmem_ref netmem = page_pool_dev_alloc_netmems(pp); - page = page_pool_dev_alloc_pages(rq->page_pool); - if (unlikely(!page)) + if (unlikely(!netmem)) return -ENOMEM; - page_pool_fragment_page(page, MLX5E_PAGECNT_BIAS_MAX); + page_pool_fragment_netmem(netmem, MLX5E_PAGECNT_BIAS_MAX); *frag_page = (struct mlx5e_frag_page) { - .page = page, + .netmem = netmem, .frags = 0, }; return 0; } -static void mlx5e_page_release_fragmented(struct mlx5e_rq *rq, +static void mlx5e_page_release_fragmented(struct page_pool *pp, struct mlx5e_frag_page *frag_page) { u16 drain_count = MLX5E_PAGECNT_BIAS_MAX - frag_page->frags; - struct page *page = frag_page->page; + netmem_ref netmem = frag_page->netmem; - if (page_pool_unref_page(page, drain_count) == 0) - page_pool_put_unrefed_page(rq->page_pool, page, -1, true); + if (page_pool_unref_netmem(netmem, drain_count) == 0) + page_pool_put_unrefed_netmem(pp, netmem, -1, true); } static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq, @@ -313,7 +312,8 @@ static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq, * offset) should just use the new one without replenishing again * by themselves. */ - err = mlx5e_page_alloc_fragmented(rq, frag->frag_page); + err = mlx5e_page_alloc_fragmented(rq->page_pool, + frag->frag_page); return err; } @@ -332,7 +332,7 @@ static inline void mlx5e_put_rx_frag(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *frag) { if (mlx5e_frag_can_release(frag)) - mlx5e_page_release_fragmented(rq, frag->frag_page); + mlx5e_page_release_fragmented(rq->page_pool, frag->frag_page); } static inline struct mlx5e_wqe_frag_info *get_frag(struct mlx5e_rq *rq, u16 ix) @@ -358,7 +358,7 @@ static int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe_cyc *wqe, frag->flags &= ~BIT(MLX5E_WQE_FRAG_SKIP_RELEASE); headroom = i == 0 ? rq->buff.headroom : 0; - addr = page_pool_get_dma_addr(frag->frag_page->page); + addr = page_pool_get_dma_addr_netmem(frag->frag_page->netmem); wqe->data[i].addr = cpu_to_be64(addr + frag->offset + headroom); } @@ -499,9 +499,10 @@ mlx5e_add_skb_shared_info_frag(struct mlx5e_rq *rq, struct skb_shared_info *sinf struct xdp_buff *xdp, struct mlx5e_frag_page *frag_page, u32 frag_offset, u32 len) { + netmem_ref netmem = frag_page->netmem; skb_frag_t *frag; - dma_addr_t addr = page_pool_get_dma_addr(frag_page->page); + dma_addr_t addr = page_pool_get_dma_addr_netmem(netmem); dma_sync_single_for_cpu(rq->pdev, addr + frag_offset, len, rq->buff.map_dir); if (!xdp_buff_has_frags(xdp)) { @@ -514,9 +515,9 @@ mlx5e_add_skb_shared_info_frag(struct mlx5e_rq *rq, struct skb_shared_info *sinf } frag = &sinfo->frags[sinfo->nr_frags++]; - skb_frag_fill_page_desc(frag, frag_page->page, frag_offset, len); + skb_frag_fill_netmem_desc(frag, netmem, frag_offset, len); - if (page_is_pfmemalloc(frag_page->page)) + if (netmem_is_pfmemalloc(netmem)) xdp_buff_set_frag_pfmemalloc(xdp); sinfo->xdp_frags_size += len; } @@ -527,27 +528,29 @@ mlx5e_add_skb_frag(struct mlx5e_rq *rq, struct sk_buff *skb, u32 frag_offset, u32 len, unsigned int truesize) { - dma_addr_t addr = page_pool_get_dma_addr(frag_page->page); + dma_addr_t addr = page_pool_get_dma_addr_netmem(frag_page->netmem); u8 next_frag = skb_shinfo(skb)->nr_frags; + netmem_ref netmem = frag_page->netmem; dma_sync_single_for_cpu(rq->pdev, addr + frag_offset, len, rq->buff.map_dir); - if (skb_can_coalesce(skb, next_frag, frag_page->page, frag_offset)) { + if (skb_can_coalesce_netmem(skb, next_frag, netmem, frag_offset)) { skb_coalesce_rx_frag(skb, next_frag - 1, len, truesize); - } else { - frag_page->frags++; - skb_add_rx_frag(skb, next_frag, frag_page->page, - frag_offset, len, truesize); + return; } + + frag_page->frags++; + skb_add_rx_frag_netmem(skb, next_frag, netmem, + frag_offset, len, truesize); } static inline void mlx5e_copy_skb_header(struct mlx5e_rq *rq, struct sk_buff *skb, - struct page *page, dma_addr_t addr, + netmem_ref netmem, dma_addr_t addr, int offset_from, int dma_offset, u32 headlen) { - const void *from = page_address(page) + offset_from; + const void *from = netmem_address(netmem) + offset_from; /* Aligning len to sizeof(long) optimizes memcpy performance */ unsigned int len = ALIGN(headlen, sizeof(long)); @@ -584,7 +587,8 @@ mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi) struct mlx5e_frag_page *frag_page; frag_page = &wi->alloc_units.frag_pages[i]; - mlx5e_page_release_fragmented(rq, frag_page); + mlx5e_page_release_fragmented(rq->page_pool, + frag_page); } } } @@ -679,12 +683,11 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq, struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, index); u64 addr; - err = mlx5e_page_alloc_fragmented(rq, frag_page); + err = mlx5e_page_alloc_fragmented(rq->hd_page_pool, frag_page); if (unlikely(err)) goto err_unmap; - - addr = page_pool_get_dma_addr(frag_page->page); + addr = page_pool_get_dma_addr_netmem(frag_page->netmem); for (int j = 0; j < MLX5E_SHAMPO_WQ_HEADER_PER_PAGE; j++) { header_offset = mlx5e_shampo_hd_offset(index++); @@ -715,7 +718,8 @@ err_unmap: if (!header_offset) { struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, index); - mlx5e_page_release_fragmented(rq, frag_page); + mlx5e_page_release_fragmented(rq->hd_page_pool, + frag_page); } } @@ -791,10 +795,11 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) for (i = 0; i < rq->mpwqe.pages_per_wqe; i++, frag_page++) { dma_addr_t addr; - err = mlx5e_page_alloc_fragmented(rq, frag_page); + err = mlx5e_page_alloc_fragmented(rq->page_pool, frag_page); if (unlikely(err)) goto err_unmap; - addr = page_pool_get_dma_addr(frag_page->page); + + addr = page_pool_get_dma_addr_netmem(frag_page->netmem); umr_wqe->inline_mtts[i] = (struct mlx5_mtt) { .ptag = cpu_to_be64(addr | MLX5_EN_WR), }; @@ -836,7 +841,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) err_unmap: while (--i >= 0) { frag_page--; - mlx5e_page_release_fragmented(rq, frag_page); + mlx5e_page_release_fragmented(rq->page_pool, frag_page); } bitmap_fill(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe); @@ -855,7 +860,7 @@ mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index) if (((header_index + 1) & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) == 0) { struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, header_index); - mlx5e_page_release_fragmented(rq, frag_page); + mlx5e_page_release_fragmented(rq->hd_page_pool, frag_page); } clear_bit(header_index, shampo->bitmap); } @@ -1100,6 +1105,8 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) if (rq->page_pool) page_pool_nid_changed(rq->page_pool, numa_mem_id()); + if (rq->hd_page_pool) + page_pool_nid_changed(rq->hd_page_pool, numa_mem_id()); head = rq->mpwqe.actual_wq_head; i = missing; @@ -1212,7 +1219,7 @@ static void *mlx5e_shampo_get_packet_hd(struct mlx5e_rq *rq, u16 header_index) struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, header_index); u16 head_offset = mlx5e_shampo_hd_offset(header_index) + rq->buff.headroom; - return page_address(frag_page->page) + head_offset; + return netmem_address(frag_page->netmem) + head_offset; } static void mlx5e_shampo_update_ipv4_udp_hdr(struct mlx5e_rq *rq, struct iphdr *ipv4) @@ -1673,11 +1680,11 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi, dma_addr_t addr; u32 frag_size; - va = page_address(frag_page->page) + wi->offset; + va = netmem_address(frag_page->netmem) + wi->offset; data = va + rx_headroom; frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt); - addr = page_pool_get_dma_addr(frag_page->page); + addr = page_pool_get_dma_addr_netmem(frag_page->netmem); dma_sync_single_range_for_cpu(rq->pdev, addr, wi->offset, frag_size, rq->buff.map_dir); net_prefetch(data); @@ -1727,10 +1734,10 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi frag_page = wi->frag_page; - va = page_address(frag_page->page) + wi->offset; + va = netmem_address(frag_page->netmem) + wi->offset; frag_consumed_bytes = min_t(u32, frag_info->frag_size, cqe_bcnt); - addr = page_pool_get_dma_addr(frag_page->page); + addr = page_pool_get_dma_addr_netmem(frag_page->netmem); dma_sync_single_range_for_cpu(rq->pdev, addr, wi->offset, rq->buff.frame0_sz, rq->buff.map_dir); net_prefetchw(va); /* xdp_frame data area */ @@ -2003,12 +2010,14 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w if (prog) { /* area for bpf_xdp_[store|load]_bytes */ - net_prefetchw(page_address(frag_page->page) + frag_offset); - if (unlikely(mlx5e_page_alloc_fragmented(rq, &wi->linear_page))) { + net_prefetchw(netmem_address(frag_page->netmem) + frag_offset); + if (unlikely(mlx5e_page_alloc_fragmented(rq->page_pool, + &wi->linear_page))) { rq->stats->buff_alloc_err++; return NULL; } - va = page_address(wi->linear_page.page); + + va = netmem_address(wi->linear_page.netmem); net_prefetchw(va); /* xdp_frame data area */ linear_hr = XDP_PACKET_HEADROOM; linear_data_len = 0; @@ -2068,7 +2077,8 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w wi->linear_page.frags++; } - mlx5e_page_release_fragmented(rq, &wi->linear_page); + mlx5e_page_release_fragmented(rq->page_pool, + &wi->linear_page); return NULL; /* page/packet was consumed by XDP */ } @@ -2077,13 +2087,14 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w mxbuf->xdp.data - mxbuf->xdp.data_hard_start, 0, mxbuf->xdp.data - mxbuf->xdp.data_meta); if (unlikely(!skb)) { - mlx5e_page_release_fragmented(rq, &wi->linear_page); + mlx5e_page_release_fragmented(rq->page_pool, + &wi->linear_page); return NULL; } skb_mark_for_recycle(skb); wi->linear_page.frags++; - mlx5e_page_release_fragmented(rq, &wi->linear_page); + mlx5e_page_release_fragmented(rq->page_pool, &wi->linear_page); if (xdp_buff_has_frags(&mxbuf->xdp)) { struct mlx5e_frag_page *pagep; @@ -2117,8 +2128,8 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w while (++pagep < frag_page); } /* copy header */ - addr = page_pool_get_dma_addr(head_page->page); - mlx5e_copy_skb_header(rq, skb, head_page->page, addr, + addr = page_pool_get_dma_addr_netmem(head_page->netmem); + mlx5e_copy_skb_header(rq, skb, head_page->netmem, addr, head_offset, head_offset, headlen); /* skb linear part was allocated with headlen and aligned to long */ skb->tail += headlen; @@ -2148,11 +2159,11 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, return NULL; } - va = page_address(frag_page->page) + head_offset; + va = netmem_address(frag_page->netmem) + head_offset; data = va + rx_headroom; frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt); - addr = page_pool_get_dma_addr(frag_page->page); + addr = page_pool_get_dma_addr_netmem(frag_page->netmem); dma_sync_single_range_for_cpu(rq->pdev, addr, head_offset, frag_size, rq->buff.map_dir); net_prefetch(data); @@ -2191,16 +2202,19 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, struct mlx5_cqe64 *cqe, u16 header_index) { struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, header_index); - dma_addr_t page_dma_addr = page_pool_get_dma_addr(frag_page->page); u16 head_offset = mlx5e_shampo_hd_offset(header_index); - dma_addr_t dma_addr = page_dma_addr + head_offset; u16 head_size = cqe->shampo.header_size; u16 rx_headroom = rq->buff.headroom; struct sk_buff *skb = NULL; + dma_addr_t page_dma_addr; + dma_addr_t dma_addr; void *hdr, *data; u32 frag_size; - hdr = page_address(frag_page->page) + head_offset; + page_dma_addr = page_pool_get_dma_addr_netmem(frag_page->netmem); + dma_addr = page_dma_addr + head_offset; + + hdr = netmem_address(frag_page->netmem) + head_offset; data = hdr + rx_headroom; frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + head_size); @@ -2225,7 +2239,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, } net_prefetchw(skb->data); - mlx5e_copy_skb_header(rq, skb, frag_page->page, dma_addr, + mlx5e_copy_skb_header(rq, skb, frag_page->netmem, dma_addr, head_offset + rx_headroom, rx_headroom, head_size); /* skb linear part was allocated with headlen and aligned to long */ @@ -2319,11 +2333,23 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq } if (!*skb) { - if (likely(head_size)) + if (likely(head_size)) { *skb = mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index); - else - *skb = mlx5e_skb_from_cqe_mpwrq_nonlinear(rq, wi, cqe, cqe_bcnt, - data_offset, page_idx); + } else { + struct mlx5e_frag_page *frag_page; + + frag_page = &wi->alloc_units.frag_pages[page_idx]; + /* Drop packets with header in unreadable data area to + * prevent the kernel from touching it. + */ + if (unlikely(netmem_is_net_iov(frag_page->netmem))) + goto free_hd_entry; + *skb = mlx5e_skb_from_cqe_mpwrq_nonlinear(rq, wi, cqe, + cqe_bcnt, + data_offset, + page_idx); + } + if (unlikely(!*skb)) goto free_hd_entry; diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c index 64a3b953cc17..40002d9fe274 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c @@ -913,23 +913,29 @@ static int lan743x_ethtool_get_sset_count(struct net_device *netdev, int sset) } } +static int lan743x_ethtool_get_rxfh_fields(struct net_device *netdev, + struct ethtool_rxfh_fields *fields) +{ + fields->data = 0; + + switch (fields->flow_type) { + case TCP_V4_FLOW:case UDP_V4_FLOW: + case TCP_V6_FLOW:case UDP_V6_FLOW: + fields->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + fallthrough; + case IPV4_FLOW: case IPV6_FLOW: + fields->data |= RXH_IP_SRC | RXH_IP_DST; + return 0; + } + + return 0; +} + static int lan743x_ethtool_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *rxnfc, u32 *rule_locs) { switch (rxnfc->cmd) { - case ETHTOOL_GRXFH: - rxnfc->data = 0; - switch (rxnfc->flow_type) { - case TCP_V4_FLOW:case UDP_V4_FLOW: - case TCP_V6_FLOW:case UDP_V6_FLOW: - rxnfc->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; - fallthrough; - case IPV4_FLOW: case IPV6_FLOW: - rxnfc->data |= RXH_IP_SRC | RXH_IP_DST; - return 0; - } - break; case ETHTOOL_GRXRINGS: rxnfc->data = LAN743X_USED_RX_CHANNELS; return 0; @@ -1368,6 +1374,7 @@ const struct ethtool_ops lan743x_ethtool_ops = { .get_rxfh_indir_size = lan743x_ethtool_get_rxfh_indir_size, .get_rxfh = lan743x_ethtool_get_rxfh, .set_rxfh = lan743x_ethtool_set_rxfh, + .get_rxfh_fields = lan743x_ethtool_get_rxfh_fields, .get_ts_info = lan743x_ethtool_get_ts_info, .get_eee = lan743x_ethtool_get_eee, .set_eee = lan743x_ethtool_set_eee, diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 3504507477c6..ac2f39853bf4 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -6,6 +6,8 @@ #include <linux/pci.h> #include <linux/utsname.h> #include <linux/version.h> +#include <linux/msi.h> +#include <linux/irqdomain.h> #include <net/mana/mana.h> @@ -80,8 +82,15 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev) return err ? err : -EPROTO; } - if (gc->num_msix_usable > resp.max_msix) - gc->num_msix_usable = resp.max_msix; + if (!pci_msix_can_alloc_dyn(pdev)) { + if (gc->num_msix_usable > resp.max_msix) + gc->num_msix_usable = resp.max_msix; + } else { + /* If dynamic allocation is enabled we have already allocated + * hwc msi + */ + gc->num_msix_usable = min(resp.max_msix, num_online_cpus() + 1); + } if (gc->num_msix_usable <= 1) return -ENOSPC; @@ -352,11 +361,59 @@ void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit) } EXPORT_SYMBOL_NS(mana_gd_ring_cq, "NET_MANA"); +#define MANA_SERVICE_PERIOD 10 + +struct mana_serv_work { + struct work_struct serv_work; + struct pci_dev *pdev; +}; + +static void mana_serv_func(struct work_struct *w) +{ + struct mana_serv_work *mns_wk; + struct pci_bus *bus, *parent; + struct pci_dev *pdev; + + mns_wk = container_of(w, struct mana_serv_work, serv_work); + pdev = mns_wk->pdev; + + pci_lock_rescan_remove(); + + if (!pdev) + goto out; + + bus = pdev->bus; + if (!bus) { + dev_err(&pdev->dev, "MANA service: no bus\n"); + goto out; + } + + parent = bus->parent; + if (!parent) { + dev_err(&pdev->dev, "MANA service: no parent bus\n"); + goto out; + } + + pci_stop_and_remove_bus_device(bus->self); + + msleep(MANA_SERVICE_PERIOD * 1000); + + pci_rescan_bus(parent); + +out: + pci_unlock_rescan_remove(); + + pci_dev_put(pdev); + kfree(mns_wk); + module_put(THIS_MODULE); +} + static void mana_gd_process_eqe(struct gdma_queue *eq) { u32 head = eq->head % (eq->queue_size / GDMA_EQE_SIZE); struct gdma_context *gc = eq->gdma_dev->gdma_context; struct gdma_eqe *eq_eqe_ptr = eq->queue_mem_ptr; + struct mana_serv_work *mns_wk; union gdma_eqe_info eqe_info; enum gdma_eqe_type type; struct gdma_event event; @@ -401,6 +458,33 @@ static void mana_gd_process_eqe(struct gdma_queue *eq) eq->eq.callback(eq->eq.context, eq, &event); break; + case GDMA_EQE_HWC_FPGA_RECONFIG: + dev_info(gc->dev, "Recv MANA service type:%d\n", type); + + if (gc->in_service) { + dev_info(gc->dev, "Already in service\n"); + break; + } + + if (!try_module_get(THIS_MODULE)) { + dev_info(gc->dev, "Module is unloading\n"); + break; + } + + mns_wk = kzalloc(sizeof(*mns_wk), GFP_ATOMIC); + if (!mns_wk) { + module_put(THIS_MODULE); + break; + } + + dev_info(gc->dev, "Start MANA service type:%d\n", type); + gc->in_service = true; + mns_wk->pdev = to_pci_dev(gc->dev); + pci_dev_get(mns_wk->pdev); + INIT_WORK(&mns_wk->serv_work, mana_serv_func); + schedule_work(&mns_wk->serv_work); + break; + default: break; } @@ -483,7 +567,9 @@ static int mana_gd_register_irq(struct gdma_queue *queue, } queue->eq.msix_index = msi_index; - gic = &gc->irq_contexts[msi_index]; + gic = xa_load(&gc->irq_contexts, msi_index); + if (WARN_ON(!gic)) + return -EINVAL; spin_lock_irqsave(&gic->lock, flags); list_add_rcu(&queue->entry, &gic->eq_list); @@ -508,7 +594,10 @@ static void mana_gd_deregiser_irq(struct gdma_queue *queue) if (WARN_ON(msix_index >= gc->num_msix_usable)) return; - gic = &gc->irq_contexts[msix_index]; + gic = xa_load(&gc->irq_contexts, msix_index); + if (WARN_ON(!gic)) + return; + spin_lock_irqsave(&gic->lock, flags); list_for_each_entry_rcu(eq, &gic->eq_list, entry) { if (queue == eq) { @@ -1288,7 +1377,49 @@ void mana_gd_free_res_map(struct gdma_resource *r) r->size = 0; } -static int irq_setup(unsigned int *irqs, unsigned int len, int node) +/* + * Spread on CPUs with the following heuristics: + * + * 1. No more than one IRQ per CPU, if possible; + * 2. NUMA locality is the second priority; + * 3. Sibling dislocality is the last priority. + * + * Let's consider this topology: + * + * Node 0 1 + * Core 0 1 2 3 + * CPU 0 1 2 3 4 5 6 7 + * + * The most performant IRQ distribution based on the above topology + * and heuristics may look like this: + * + * IRQ Nodes Cores CPUs + * 0 1 0 0-1 + * 1 1 1 2-3 + * 2 1 0 0-1 + * 3 1 1 2-3 + * 4 2 2 4-5 + * 5 2 3 6-7 + * 6 2 2 4-5 + * 7 2 3 6-7 + * + * The heuristics is implemented as follows. + * + * The outer for_each() loop resets the 'weight' to the actual number + * of CPUs in the hop. Then inner for_each() loop decrements it by the + * number of sibling groups (cores) while assigning first set of IRQs + * to each group. IRQs 0 and 1 above are distributed this way. + * + * Now, because NUMA locality is more important, we should walk the + * same set of siblings and assign 2nd set of IRQs (2 and 3), and it's + * implemented by the medium while() loop. We do like this unless the + * number of IRQs assigned on this hop will not become equal to number + * of CPUs in the hop (weight == 0). Then we switch to the next hop and + * do the same thing. + */ + +static int irq_setup(unsigned int *irqs, unsigned int len, int node, + bool skip_first_cpu) { const struct cpumask *next, *prev = cpu_none_mask; cpumask_var_t cpus __free(free_cpumask_var); @@ -1303,11 +1434,18 @@ static int irq_setup(unsigned int *irqs, unsigned int len, int node) while (weight > 0) { cpumask_andnot(cpus, next, prev); for_each_cpu(cpu, cpus) { + cpumask_andnot(cpus, cpus, topology_sibling_cpumask(cpu)); + --weight; + + if (unlikely(skip_first_cpu)) { + skip_first_cpu = false; + continue; + } + if (len-- == 0) goto done; + irq_set_affinity_and_hint(*irqs++, topology_sibling_cpumask(cpu)); - cpumask_andnot(cpus, cpus, topology_sibling_cpumask(cpu)); - --weight; } } prev = next; @@ -1317,47 +1455,108 @@ done: return 0; } -static int mana_gd_setup_irqs(struct pci_dev *pdev) +static int mana_gd_setup_dyn_irqs(struct pci_dev *pdev, int nvec) { struct gdma_context *gc = pci_get_drvdata(pdev); - unsigned int max_queues_per_port; struct gdma_irq_context *gic; - unsigned int max_irqs, cpu; - int start_irq_index = 1; - int nvec, *irqs, irq; - int err, i = 0, j; + bool skip_first_cpu = false; + int *irqs, irq, err, i; - cpus_read_lock(); - max_queues_per_port = num_online_cpus(); - if (max_queues_per_port > MANA_MAX_NUM_QUEUES) - max_queues_per_port = MANA_MAX_NUM_QUEUES; + irqs = kmalloc_array(nvec, sizeof(int), GFP_KERNEL); + if (!irqs) + return -ENOMEM; - /* Need 1 interrupt for the Hardware communication Channel (HWC) */ - max_irqs = max_queues_per_port + 1; + /* + * While processing the next pci irq vector, we start with index 1, + * as IRQ vector at index 0 is already processed for HWC. + * However, the population of irqs array starts with index 0, to be + * further used in irq_setup() + */ + for (i = 1; i <= nvec; i++) { + gic = kzalloc(sizeof(*gic), GFP_KERNEL); + if (!gic) { + err = -ENOMEM; + goto free_irq; + } + gic->handler = mana_gd_process_eq_events; + INIT_LIST_HEAD(&gic->eq_list); + spin_lock_init(&gic->lock); - nvec = pci_alloc_irq_vectors(pdev, 2, max_irqs, PCI_IRQ_MSIX); - if (nvec < 0) { - cpus_read_unlock(); - return nvec; + snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_q%d@pci:%s", + i - 1, pci_name(pdev)); + + /* one pci vector is already allocated for HWC */ + irqs[i - 1] = pci_irq_vector(pdev, i); + if (irqs[i - 1] < 0) { + err = irqs[i - 1]; + goto free_current_gic; + } + + err = request_irq(irqs[i - 1], mana_gd_intr, 0, gic->name, gic); + if (err) + goto free_current_gic; + + xa_store(&gc->irq_contexts, i, gic, GFP_KERNEL); } - if (nvec <= num_online_cpus()) - start_irq_index = 0; - irqs = kmalloc_array((nvec - start_irq_index), sizeof(int), GFP_KERNEL); - if (!irqs) { - err = -ENOMEM; - goto free_irq_vector; + /* + * When calling irq_setup() for dynamically added IRQs, if number of + * CPUs is more than or equal to allocated MSI-X, we need to skip the + * first CPU sibling group since they are already affinitized to HWC IRQ + */ + cpus_read_lock(); + if (gc->num_msix_usable <= num_online_cpus()) + skip_first_cpu = true; + + err = irq_setup(irqs, nvec, gc->numa_node, skip_first_cpu); + if (err) { + cpus_read_unlock(); + goto free_irq; } - gc->irq_contexts = kcalloc(nvec, sizeof(struct gdma_irq_context), - GFP_KERNEL); - if (!gc->irq_contexts) { - err = -ENOMEM; - goto free_irq_array; + cpus_read_unlock(); + kfree(irqs); + return 0; + +free_current_gic: + kfree(gic); +free_irq: + for (i -= 1; i > 0; i--) { + irq = pci_irq_vector(pdev, i); + gic = xa_load(&gc->irq_contexts, i); + if (WARN_ON(!gic)) + continue; + + irq_update_affinity_hint(irq, NULL); + free_irq(irq, gic); + xa_erase(&gc->irq_contexts, i); + kfree(gic); } + kfree(irqs); + return err; +} + +static int mana_gd_setup_irqs(struct pci_dev *pdev, int nvec) +{ + struct gdma_context *gc = pci_get_drvdata(pdev); + struct gdma_irq_context *gic; + int *irqs, *start_irqs, irq; + unsigned int cpu; + int err, i; + + irqs = kmalloc_array(nvec, sizeof(int), GFP_KERNEL); + if (!irqs) + return -ENOMEM; + + start_irqs = irqs; for (i = 0; i < nvec; i++) { - gic = &gc->irq_contexts[i]; + gic = kzalloc(sizeof(*gic), GFP_KERNEL); + if (!gic) { + err = -ENOMEM; + goto free_irq; + } + gic->handler = mana_gd_process_eq_events; INIT_LIST_HEAD(&gic->eq_list); spin_lock_init(&gic->lock); @@ -1369,69 +1568,128 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_q%d@pci:%s", i - 1, pci_name(pdev)); - irq = pci_irq_vector(pdev, i); - if (irq < 0) { - err = irq; - goto free_irq; + irqs[i] = pci_irq_vector(pdev, i); + if (irqs[i] < 0) { + err = irqs[i]; + goto free_current_gic; } - if (!i) { - err = request_irq(irq, mana_gd_intr, 0, gic->name, gic); - if (err) - goto free_irq; - - /* If number of IRQ is one extra than number of online CPUs, - * then we need to assign IRQ0 (hwc irq) and IRQ1 to - * same CPU. - * Else we will use different CPUs for IRQ0 and IRQ1. - * Also we are using cpumask_local_spread instead of - * cpumask_first for the node, because the node can be - * mem only. - */ - if (start_irq_index) { - cpu = cpumask_local_spread(i, gc->numa_node); - irq_set_affinity_and_hint(irq, cpumask_of(cpu)); - } else { - irqs[start_irq_index] = irq; - } - } else { - irqs[i - start_irq_index] = irq; - err = request_irq(irqs[i - start_irq_index], mana_gd_intr, 0, - gic->name, gic); - if (err) - goto free_irq; - } + err = request_irq(irqs[i], mana_gd_intr, 0, gic->name, gic); + if (err) + goto free_current_gic; + + xa_store(&gc->irq_contexts, i, gic, GFP_KERNEL); } - err = irq_setup(irqs, (nvec - start_irq_index), gc->numa_node); - if (err) + /* If number of IRQ is one extra than number of online CPUs, + * then we need to assign IRQ0 (hwc irq) and IRQ1 to + * same CPU. + * Else we will use different CPUs for IRQ0 and IRQ1. + * Also we are using cpumask_local_spread instead of + * cpumask_first for the node, because the node can be + * mem only. + */ + cpus_read_lock(); + if (nvec > num_online_cpus()) { + cpu = cpumask_local_spread(0, gc->numa_node); + irq_set_affinity_and_hint(irqs[0], cpumask_of(cpu)); + irqs++; + nvec -= 1; + } + + err = irq_setup(irqs, nvec, gc->numa_node, false); + if (err) { + cpus_read_unlock(); goto free_irq; + } - gc->max_num_msix = nvec; - gc->num_msix_usable = nvec; cpus_read_unlock(); - kfree(irqs); + kfree(start_irqs); return 0; +free_current_gic: + kfree(gic); free_irq: - for (j = i - 1; j >= 0; j--) { - irq = pci_irq_vector(pdev, j); - gic = &gc->irq_contexts[j]; + for (i -= 1; i >= 0; i--) { + irq = pci_irq_vector(pdev, i); + gic = xa_load(&gc->irq_contexts, i); + if (WARN_ON(!gic)) + continue; irq_update_affinity_hint(irq, NULL); free_irq(irq, gic); + xa_erase(&gc->irq_contexts, i); + kfree(gic); } - kfree(gc->irq_contexts); - gc->irq_contexts = NULL; -free_irq_array: - kfree(irqs); -free_irq_vector: - cpus_read_unlock(); - pci_free_irq_vectors(pdev); + kfree(start_irqs); return err; } +static int mana_gd_setup_hwc_irqs(struct pci_dev *pdev) +{ + struct gdma_context *gc = pci_get_drvdata(pdev); + unsigned int max_irqs, min_irqs; + int nvec, err; + + if (pci_msix_can_alloc_dyn(pdev)) { + max_irqs = 1; + min_irqs = 1; + } else { + /* Need 1 interrupt for HWC */ + max_irqs = min(num_online_cpus(), MANA_MAX_NUM_QUEUES) + 1; + min_irqs = 2; + } + + nvec = pci_alloc_irq_vectors(pdev, min_irqs, max_irqs, PCI_IRQ_MSIX); + if (nvec < 0) + return nvec; + + err = mana_gd_setup_irqs(pdev, nvec); + if (err) { + pci_free_irq_vectors(pdev); + return err; + } + + gc->num_msix_usable = nvec; + gc->max_num_msix = nvec; + + return 0; +} + +static int mana_gd_setup_remaining_irqs(struct pci_dev *pdev) +{ + struct gdma_context *gc = pci_get_drvdata(pdev); + struct msi_map irq_map; + int max_irqs, i, err; + + if (!pci_msix_can_alloc_dyn(pdev)) + /* remain irqs are already allocated with HWC IRQ */ + return 0; + + /* allocate only remaining IRQs*/ + max_irqs = gc->num_msix_usable - 1; + + for (i = 1; i <= max_irqs; i++) { + irq_map = pci_msix_alloc_irq_at(pdev, i, NULL); + if (!irq_map.virq) { + err = irq_map.index; + /* caller will handle cleaning up all allocated + * irqs, after HWC is destroyed + */ + return err; + } + } + + err = mana_gd_setup_dyn_irqs(pdev, max_irqs); + if (err) + return err; + + gc->max_num_msix = gc->max_num_msix + max_irqs; + + return 0; +} + static void mana_gd_remove_irqs(struct pci_dev *pdev) { struct gdma_context *gc = pci_get_drvdata(pdev); @@ -1446,19 +1704,21 @@ static void mana_gd_remove_irqs(struct pci_dev *pdev) if (irq < 0) continue; - gic = &gc->irq_contexts[i]; + gic = xa_load(&gc->irq_contexts, i); + if (WARN_ON(!gic)) + continue; /* Need to clear the hint before free_irq */ irq_update_affinity_hint(irq, NULL); free_irq(irq, gic); + xa_erase(&gc->irq_contexts, i); + kfree(gic); } pci_free_irq_vectors(pdev); gc->max_num_msix = 0; gc->num_msix_usable = 0; - kfree(gc->irq_contexts); - gc->irq_contexts = NULL; } static int mana_gd_setup(struct pci_dev *pdev) @@ -1473,9 +1733,10 @@ static int mana_gd_setup(struct pci_dev *pdev) if (!gc->service_wq) return -ENOMEM; - err = mana_gd_setup_irqs(pdev); + err = mana_gd_setup_hwc_irqs(pdev); if (err) { - dev_err(gc->dev, "Failed to setup IRQs: %d\n", err); + dev_err(gc->dev, "Failed to setup IRQs for HWC creation: %d\n", + err); goto free_workqueue; } @@ -1491,6 +1752,12 @@ static int mana_gd_setup(struct pci_dev *pdev) if (err) goto destroy_hwc; + err = mana_gd_setup_remaining_irqs(pdev); + if (err) { + dev_err(gc->dev, "Failed to setup remaining IRQs: %d", err); + goto destroy_hwc; + } + err = mana_gd_detect_devices(pdev); if (err) goto destroy_hwc; @@ -1571,6 +1838,7 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) gc->is_pf = mana_is_pf(pdev->device); gc->bar0_va = bar0_va; gc->dev = &pdev->dev; + xa_init(&gc->irq_contexts); if (gc->is_pf) gc->mana_pci_debugfs = debugfs_create_dir("0", mana_debugfs_root); @@ -1605,6 +1873,7 @@ unmap_bar: */ debugfs_remove_recursive(gc->mana_pci_debugfs); gc->mana_pci_debugfs = NULL; + xa_destroy(&gc->irq_contexts); pci_iounmap(pdev, bar0_va); free_gc: pci_set_drvdata(pdev, NULL); @@ -1630,6 +1899,8 @@ static void mana_gd_remove(struct pci_dev *pdev) gc->mana_pci_debugfs = NULL; + xa_destroy(&gc->irq_contexts); + pci_iounmap(pdev, gc->bar0_va); vfree(gc); diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 3d3677c0d014..650d22654d49 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -891,6 +891,10 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, } if (ctx->status_code && ctx->status_code != GDMA_STATUS_MORE_ENTRIES) { + if (ctx->status_code == GDMA_STATUS_CMD_UNSUPPORTED) { + err = -EOPNOTSUPP; + goto out; + } if (req_msg->req.msg_type != MANA_QUERY_PHY_STAT) dev_err(hwc->dev, "HWC: Failed hw_channel req: 0x%x\n", ctx->status_code); diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index e68b8190bb7a..5aee7bda1504 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -719,6 +719,78 @@ out: return err; } +static int mana_shaper_set(struct net_shaper_binding *binding, + const struct net_shaper *shaper, + struct netlink_ext_ack *extack) +{ + struct mana_port_context *apc = netdev_priv(binding->netdev); + u32 old_speed, rate; + int err; + + if (shaper->handle.scope != NET_SHAPER_SCOPE_NETDEV) { + NL_SET_ERR_MSG_MOD(extack, "net shaper scope should be netdev"); + return -EINVAL; + } + + if (apc->handle.id && shaper->handle.id != apc->handle.id) { + NL_SET_ERR_MSG_MOD(extack, "Cannot create multiple shapers"); + return -EOPNOTSUPP; + } + + if (!shaper->bw_max || (shaper->bw_max % 100000000)) { + NL_SET_ERR_MSG_MOD(extack, "Please use multiples of 100Mbps for bandwidth"); + return -EINVAL; + } + + rate = div_u64(shaper->bw_max, 1000); /* Convert bps to Kbps */ + rate = div_u64(rate, 1000); /* Convert Kbps to Mbps */ + + /* Get current speed */ + err = mana_query_link_cfg(apc); + old_speed = (err) ? SPEED_UNKNOWN : apc->speed; + + if (!err) { + err = mana_set_bw_clamp(apc, rate, TRI_STATE_TRUE); + apc->speed = (err) ? old_speed : rate; + apc->handle = (err) ? apc->handle : shaper->handle; + } + + return err; +} + +static int mana_shaper_del(struct net_shaper_binding *binding, + const struct net_shaper_handle *handle, + struct netlink_ext_ack *extack) +{ + struct mana_port_context *apc = netdev_priv(binding->netdev); + int err; + + err = mana_set_bw_clamp(apc, 0, TRI_STATE_FALSE); + + if (!err) { + /* Reset mana port context parameters */ + apc->handle.id = 0; + apc->handle.scope = NET_SHAPER_SCOPE_UNSPEC; + apc->speed = 0; + } + + return err; +} + +static void mana_shaper_cap(struct net_shaper_binding *binding, + enum net_shaper_scope scope, + unsigned long *flags) +{ + *flags = BIT(NET_SHAPER_A_CAPS_SUPPORT_BW_MAX) | + BIT(NET_SHAPER_A_CAPS_SUPPORT_METRIC_BPS); +} + +static const struct net_shaper_ops mana_shaper_ops = { + .set = mana_shaper_set, + .delete = mana_shaper_del, + .capabilities = mana_shaper_cap, +}; + static const struct net_device_ops mana_devops = { .ndo_open = mana_open, .ndo_stop = mana_close, @@ -729,6 +801,7 @@ static const struct net_device_ops mana_devops = { .ndo_bpf = mana_bpf, .ndo_xdp_xmit = mana_xdp_xmit, .ndo_change_mtu = mana_change_mtu, + .net_shaper_ops = &mana_shaper_ops, }; static void mana_cleanup_port_context(struct mana_port_context *apc) @@ -774,6 +847,9 @@ static int mana_send_request(struct mana_context *ac, void *in_buf, err = mana_gd_send_request(gc, in_len, in_buf, out_len, out_buf); if (err || resp->status) { + if (err == -EOPNOTSUPP) + return err; + if (req->req.msg_type != MANA_QUERY_PHY_STAT) dev_err(dev, "Failed to send mana message: %d, 0x%x\n", err, resp->status); @@ -1162,6 +1238,95 @@ out: return err; } +int mana_query_link_cfg(struct mana_port_context *apc) +{ + struct net_device *ndev = apc->ndev; + struct mana_query_link_config_resp resp = {}; + struct mana_query_link_config_req req = {}; + int err; + + mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_LINK_CONFIG, + sizeof(req), sizeof(resp)); + + req.vport = apc->port_handle; + req.hdr.resp.msg_version = GDMA_MESSAGE_V2; + + err = mana_send_request(apc->ac, &req, sizeof(req), &resp, + sizeof(resp)); + + if (err) { + if (err == -EOPNOTSUPP) { + netdev_info_once(ndev, "MANA_QUERY_LINK_CONFIG not supported\n"); + return err; + } + netdev_err(ndev, "Failed to query link config: %d\n", err); + return err; + } + + err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_LINK_CONFIG, + sizeof(resp)); + + if (err || resp.hdr.status) { + netdev_err(ndev, "Failed to query link config: %d, 0x%x\n", err, + resp.hdr.status); + if (!err) + err = -EOPNOTSUPP; + return err; + } + + if (resp.qos_unconfigured) { + err = -EINVAL; + return err; + } + apc->speed = resp.link_speed_mbps; + apc->max_speed = resp.qos_speed_mbps; + return 0; +} + +int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed, + int enable_clamping) +{ + struct mana_set_bw_clamp_resp resp = {}; + struct mana_set_bw_clamp_req req = {}; + struct net_device *ndev = apc->ndev; + int err; + + mana_gd_init_req_hdr(&req.hdr, MANA_SET_BW_CLAMP, + sizeof(req), sizeof(resp)); + req.vport = apc->port_handle; + req.link_speed_mbps = speed; + req.enable_clamping = enable_clamping; + + err = mana_send_request(apc->ac, &req, sizeof(req), &resp, + sizeof(resp)); + + if (err) { + if (err == -EOPNOTSUPP) { + netdev_info_once(ndev, "MANA_SET_BW_CLAMP not supported\n"); + return err; + } + netdev_err(ndev, "Failed to set bandwidth clamp for speed %u, err = %d", + speed, err); + return err; + } + + err = mana_verify_resp_hdr(&resp.hdr, MANA_SET_BW_CLAMP, + sizeof(resp)); + + if (err || resp.hdr.status) { + netdev_err(ndev, "Failed to set bandwidth clamp: %d, 0x%x\n", err, + resp.hdr.status); + if (!err) + err = -EOPNOTSUPP; + return err; + } + + if (resp.qos_unconfigured) + netdev_info(ndev, "QoS is unconfigured\n"); + + return 0; +} + int mana_create_wq_obj(struct mana_port_context *apc, mana_handle_t vport, u32 wq_type, struct mana_obj_spec *wq_spec, @@ -1912,8 +2077,10 @@ static void mana_destroy_txq(struct mana_port_context *apc) napi = &apc->tx_qp[i].tx_cq.napi; if (apc->tx_qp[i].txq.napi_initialized) { napi_synchronize(napi); - napi_disable(napi); - netif_napi_del(napi); + netdev_lock_ops_to_full(napi->dev); + napi_disable_locked(napi); + netif_napi_del_locked(napi); + netdev_unlock_full_to_ops(napi->dev); apc->tx_qp[i].txq.napi_initialized = false; } mana_destroy_wq_obj(apc, GDMA_SQ, apc->tx_qp[i].tx_object); @@ -2065,8 +2232,11 @@ static int mana_create_txq(struct mana_port_context *apc, mana_create_txq_debugfs(apc, i); - netif_napi_add_tx(net, &cq->napi, mana_poll); - napi_enable(&cq->napi); + set_bit(NAPI_STATE_NO_BUSY_POLL, &cq->napi.state); + netdev_lock_ops_to_full(net); + netif_napi_add_locked(net, &cq->napi, mana_poll); + napi_enable_locked(&cq->napi); + netdev_unlock_full_to_ops(net); txq->napi_initialized = true; mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT); @@ -2102,9 +2272,10 @@ static void mana_destroy_rxq(struct mana_port_context *apc, if (napi_initialized) { napi_synchronize(napi); - napi_disable(napi); - - netif_napi_del(napi); + netdev_lock_ops_to_full(napi->dev); + napi_disable_locked(napi); + netif_napi_del_locked(napi); + netdev_unlock_full_to_ops(napi->dev); } xdp_rxq_info_unreg(&rxq->xdp_rxq); @@ -2355,14 +2526,18 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, gc->cq_table[cq->gdma_id] = cq->gdma_cq; - netif_napi_add_weight(ndev, &cq->napi, mana_poll, 1); + netdev_lock_ops_to_full(ndev); + netif_napi_add_weight_locked(ndev, &cq->napi, mana_poll, 1); + netdev_unlock_full_to_ops(ndev); WARN_ON(xdp_rxq_info_reg(&rxq->xdp_rxq, ndev, rxq_idx, cq->napi.napi_id)); WARN_ON(xdp_rxq_info_reg_mem_model(&rxq->xdp_rxq, MEM_TYPE_PAGE_POOL, rxq->page_pool)); - napi_enable(&cq->napi); + netdev_lock_ops_to_full(ndev); + napi_enable_locked(&cq->napi); + netdev_unlock_full_to_ops(ndev); mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT); out: @@ -3001,6 +3176,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, goto free_indir; } + debugfs_create_u32("current_speed", 0400, apc->mana_port_debugfs, &apc->speed); + return 0; free_indir: diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index 4fb3a04994a2..a1afa75a9463 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -495,6 +495,12 @@ out: static int mana_get_link_ksettings(struct net_device *ndev, struct ethtool_link_ksettings *cmd) { + struct mana_port_context *apc = netdev_priv(ndev); + int err; + + err = mana_query_link_cfg(apc); + cmd->base.speed = (err) ? SPEED_UNKNOWN : apc->max_speed; + cmd->base.duplex = DUPLEX_FULL; cmd->base.port = PORT_OTHER; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 932f59d70f41..132626a3f9f7 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -2394,8 +2394,7 @@ static int nfp_udp_tunnel_sync(struct net_device *netdev, unsigned int table) static const struct udp_tunnel_nic_info nfp_udp_tunnels = { .sync_table = nfp_udp_tunnel_sync, - .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP | - UDP_TUNNEL_NIC_INFO_OPEN_ONLY, + .flags = UDP_TUNNEL_NIC_INFO_OPEN_ONLY, .tables = { { .n_entries = NFP_NET_N_VXLAN_PORTS, diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c index 4c377bdc62c8..136bfa3516d0 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c @@ -409,6 +409,7 @@ static void ionic_remove(struct pci_dev *pdev) timer_shutdown_sync(&ionic->watchdog_timer); if (ionic->lif) { + cancel_work_sync(&ionic->lif->deferred.work); /* prevent adminq cmds if already known as down */ if (test_and_clear_bit(IONIC_LIF_F_FW_RESET, ionic->lif->state)) set_bit(IONIC_LIF_F_FW_STOPPING, ionic->lif->state); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 18b9c8a810ae..093c5358b6e8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -424,9 +424,9 @@ do_check_time: if (fw_hb_ready != idev->fw_hb_ready) { idev->fw_hb_ready = fw_hb_ready; if (!fw_hb_ready) - dev_info(ionic->dev, "FW heartbeat stalled at %d\n", fw_hb); + dev_info(ionic->dev, "FW heartbeat stalled at %u\n", fw_hb); else - dev_info(ionic->dev, "FW heartbeat restored at %d\n", fw_hb); + dev_info(ionic->dev, "FW heartbeat restored at %u\n", fw_hb); } if (!fw_hb_ready) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 7707a9e53c43..48cb5d30b5f6 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -3526,10 +3526,6 @@ void ionic_lif_free(struct ionic_lif *lif) lif->info = NULL; lif->info_pa = 0; - /* unmap doorbell page */ - ionic_bus_unmap_dbpage(lif->ionic, lif->kern_dbpage); - lif->kern_dbpage = NULL; - mutex_destroy(&lif->config_lock); mutex_destroy(&lif->queue_lock); @@ -3555,6 +3551,9 @@ void ionic_lif_deinit(struct ionic_lif *lif) ionic_lif_qcq_deinit(lif, lif->notifyqcq); ionic_lif_qcq_deinit(lif, lif->adminqcq); + ionic_bus_unmap_dbpage(lif->ionic, lif->kern_dbpage); + lif->kern_dbpage = NULL; + ionic_lif_reset(lif); } diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index 985026dd816f..7e341e026489 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -987,20 +987,17 @@ static int qede_udp_tunnel_sync(struct net_device *dev, unsigned int table) static const struct udp_tunnel_nic_info qede_udp_tunnels_both = { .sync_table = qede_udp_tunnel_sync, - .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP, .tables = { { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, }, }, }, qede_udp_tunnels_vxlan = { .sync_table = qede_udp_tunnel_sync, - .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP, .tables = { { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, }, }, qede_udp_tunnels_geneve = { .sync_table = qede_udp_tunnel_sync, - .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP, .tables = { { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, }, }, diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index eb69121df726..53cdd36c4123 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -486,7 +486,6 @@ static int qlcnic_udp_tunnel_sync(struct net_device *dev, unsigned int table) static const struct udp_tunnel_nic_info qlcnic_udp_tunnels = { .sync_table = qlcnic_udp_tunnel_sync, - .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP, .tables = { { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, }, diff --git a/drivers/net/ethernet/realtek/rtase/rtase.h b/drivers/net/ethernet/realtek/rtase/rtase.h index 498cfe4d0cac..20decdeb9fdb 100644 --- a/drivers/net/ethernet/realtek/rtase/rtase.h +++ b/drivers/net/ethernet/realtek/rtase/rtase.h @@ -288,6 +288,7 @@ struct rtase_ring { u32 cur_idx; u32 dirty_idx; u16 index; + u8 type; struct sk_buff *skbuff[RTASE_NUM_DESC]; void *data_buf[RTASE_NUM_DESC]; diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c index 4d37217e9a14..ef13109c49cf 100644 --- a/drivers/net/ethernet/realtek/rtase/rtase_main.c +++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c @@ -326,6 +326,7 @@ static void rtase_tx_desc_init(struct rtase_private *tp, u16 idx) ring->cur_idx = 0; ring->dirty_idx = 0; ring->index = idx; + ring->type = NETDEV_QUEUE_TYPE_TX; ring->alloc_fail = 0; for (i = 0; i < RTASE_NUM_DESC; i++) { @@ -345,6 +346,9 @@ static void rtase_tx_desc_init(struct rtase_private *tp, u16 idx) ring->ivec = &tp->int_vector[0]; list_add_tail(&ring->ring_entry, &tp->int_vector[0].ring_list); } + + netif_queue_set_napi(tp->dev, ring->index, + ring->type, &ring->ivec->napi); } static void rtase_map_to_asic(union rtase_rx_desc *desc, dma_addr_t mapping, @@ -590,6 +594,7 @@ static void rtase_rx_desc_init(struct rtase_private *tp, u16 idx) ring->cur_idx = 0; ring->dirty_idx = 0; ring->index = idx; + ring->type = NETDEV_QUEUE_TYPE_RX; ring->alloc_fail = 0; for (i = 0; i < RTASE_NUM_DESC; i++) @@ -597,6 +602,8 @@ static void rtase_rx_desc_init(struct rtase_private *tp, u16 idx) ring->ring_handler = rx_handler; ring->ivec = &tp->int_vector[idx]; + netif_queue_set_napi(tp->dev, ring->index, + ring->type, &ring->ivec->napi); list_add_tail(&ring->ring_entry, &tp->int_vector[idx].ring_list); } @@ -1161,8 +1168,12 @@ static void rtase_down(struct net_device *dev) ivec = &tp->int_vector[i]; napi_disable(&ivec->napi); list_for_each_entry_safe(ring, tmp, &ivec->ring_list, - ring_entry) + ring_entry) { + netif_queue_set_napi(tp->dev, ring->index, + ring->type, NULL); + list_del(&ring->ring_entry); + } } netif_tx_disable(dev); @@ -1518,8 +1529,12 @@ static void rtase_sw_reset(struct net_device *dev) for (i = 0; i < tp->int_nums; i++) { ivec = &tp->int_vector[i]; list_for_each_entry_safe(ring, tmp, &ivec->ring_list, - ring_entry) + ring_entry) { + netif_queue_set_napi(tp->dev, ring->index, + ring->type, NULL); + list_del(&ring->ring_entry); + } } ret = rtase_init_ring(dev); @@ -1871,6 +1886,18 @@ static void rtase_init_netdev_ops(struct net_device *dev) dev->ethtool_ops = &rtase_ethtool_ops; } +static void rtase_init_napi(struct rtase_private *tp) +{ + u16 i; + + for (i = 0; i < tp->int_nums; i++) { + netif_napi_add_config(tp->dev, &tp->int_vector[i].napi, + tp->int_vector[i].poll, i); + netif_napi_set_irq(&tp->int_vector[i].napi, + tp->int_vector[i].irq); + } +} + static void rtase_reset_interrupt(struct pci_dev *pdev, const struct rtase_private *tp) { @@ -1956,9 +1983,6 @@ static void rtase_init_int_vector(struct rtase_private *tp) memset(tp->int_vector[0].name, 0x0, sizeof(tp->int_vector[0].name)); INIT_LIST_HEAD(&tp->int_vector[0].ring_list); - netif_napi_add(tp->dev, &tp->int_vector[0].napi, - tp->int_vector[0].poll); - /* interrupt vector 1 ~ 3 */ for (i = 1; i < tp->int_nums; i++) { tp->int_vector[i].tp = tp; @@ -1972,9 +1996,6 @@ static void rtase_init_int_vector(struct rtase_private *tp) memset(tp->int_vector[i].name, 0x0, sizeof(tp->int_vector[0].name)); INIT_LIST_HEAD(&tp->int_vector[i].ring_list); - - netif_napi_add(tp->dev, &tp->int_vector[i].napi, - tp->int_vector[i].poll); } } @@ -2206,6 +2227,8 @@ static int rtase_init_one(struct pci_dev *pdev, goto err_out_del_napi; } + rtase_init_napi(tp); + rtase_init_netdev_ops(dev); dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c index 4a439b34114d..ad73733644f9 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c @@ -308,8 +308,8 @@ static int sxgbe_set_coalesce(struct net_device *dev, return 0; } -static int sxgbe_get_rss_hash_opts(struct sxgbe_priv_data *priv, - struct ethtool_rxnfc *cmd) +static int sxgbe_get_rxfh_fields(struct net_device *dev, + struct ethtool_rxfh_fields *cmd) { cmd->data = 0; @@ -344,26 +344,11 @@ static int sxgbe_get_rss_hash_opts(struct sxgbe_priv_data *priv, return 0; } -static int sxgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, - u32 *rule_locs) +static int sxgbe_set_rxfh_fields(struct net_device *dev, + const struct ethtool_rxfh_fields *cmd, + struct netlink_ext_ack *extack) { struct sxgbe_priv_data *priv = netdev_priv(dev); - int ret = -EOPNOTSUPP; - - switch (cmd->cmd) { - case ETHTOOL_GRXFH: - ret = sxgbe_get_rss_hash_opts(priv, cmd); - break; - default: - break; - } - - return ret; -} - -static int sxgbe_set_rss_hash_opt(struct sxgbe_priv_data *priv, - struct ethtool_rxnfc *cmd) -{ u32 reg_val = 0; /* RSS does not support anything other than hashing @@ -421,22 +406,6 @@ static int sxgbe_set_rss_hash_opt(struct sxgbe_priv_data *priv, return 0; } -static int sxgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) -{ - struct sxgbe_priv_data *priv = netdev_priv(dev); - int ret = -EOPNOTSUPP; - - switch (cmd->cmd) { - case ETHTOOL_SRXFH: - ret = sxgbe_set_rss_hash_opt(priv, cmd); - break; - default: - break; - } - - return ret; -} - static void sxgbe_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *space) { @@ -489,8 +458,8 @@ static const struct ethtool_ops sxgbe_ethtool_ops = { .get_channels = sxgbe_get_channels, .get_coalesce = sxgbe_get_coalesce, .set_coalesce = sxgbe_set_coalesce, - .get_rxnfc = sxgbe_get_rxnfc, - .set_rxnfc = sxgbe_set_rxnfc, + .get_rxfh_fields = sxgbe_get_rxfh_fields, + .set_rxfh_fields = sxgbe_set_rxfh_fields, .get_regs = sxgbe_get_regs, .get_regs_len = sxgbe_get_regs_len, .get_eee = sxgbe_get_eee, diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 47349c148c0c..fcec81f862ec 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -3985,7 +3985,6 @@ static int efx_ef10_udp_tnl_unset_port(struct net_device *dev, static const struct udp_tunnel_nic_info efx_ef10_udp_tunnels = { .set_port = efx_ef10_udp_tnl_set_port, .unset_port = efx_ef10_udp_tnl_unset_port, - .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP, .tables = { { .n_entries = 16, diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index ea5da5793362..cbffccb3b9af 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -396,17 +396,6 @@ enum request_irq_err { #define CORE_IRQ_MTL_RX_OVERFLOW BIT(8) -/* Physical Coding Sublayer */ -struct rgmii_adv { - unsigned int pause; - unsigned int duplex; - unsigned int lp_pause; - unsigned int lp_duplex; -}; - -#define STMMAC_PCS_PAUSE 1 -#define STMMAC_PCS_ASYM_PAUSE 2 - /* DMA HW capabilities */ struct dma_features { unsigned int mbps_10_100; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index e30bdf72331a..2e398574c7a7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -622,6 +622,11 @@ static void ethqos_set_serdes_speed(struct qcom_ethqos *ethqos, int speed) } } +static void ethqos_pcs_set_inband(struct stmmac_priv *priv, bool enable) +{ + stmmac_pcs_ctrl_ane(priv, priv->ioaddr, enable, 0, 0); +} + /* On interface toggle MAC registers gets reset. * Configure MAC block for SGMII on ethernet phy link up */ @@ -640,7 +645,7 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos, int speed) RGMII_CONFIG2_RGMII_CLK_SEL_CFG, RGMII_IO_MACRO_CONFIG2); ethqos_set_serdes_speed(ethqos, SPEED_2500); - stmmac_pcs_ctrl_ane(priv, priv->ioaddr, 0, 0, 0); + ethqos_pcs_set_inband(priv, false); break; case SPEED_1000: val &= ~ETHQOS_MAC_CTRL_PORT_SEL; @@ -648,12 +653,12 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos, int speed) RGMII_CONFIG2_RGMII_CLK_SEL_CFG, RGMII_IO_MACRO_CONFIG2); ethqos_set_serdes_speed(ethqos, SPEED_1000); - stmmac_pcs_ctrl_ane(priv, priv->ioaddr, 1, 0, 0); + ethqos_pcs_set_inband(priv, true); break; case SPEED_100: val |= ETHQOS_MAC_CTRL_PORT_SEL | ETHQOS_MAC_CTRL_SPEED_MODE; ethqos_set_serdes_speed(ethqos, SPEED_1000); - stmmac_pcs_ctrl_ane(priv, priv->ioaddr, 1, 0, 0); + ethqos_pcs_set_inband(priv, true); break; case SPEED_10: val |= ETHQOS_MAC_CTRL_PORT_SEL; @@ -663,7 +668,7 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos, int speed) SGMII_10M_RX_CLK_DVDR), RGMII_IO_MACRO_CONFIG); ethqos_set_serdes_speed(ethqos, SPEED_1000); - stmmac_pcs_ctrl_ane(priv, priv->ioaddr, 1, 0, 0); + ethqos_pcs_set_inband(priv, true); break; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 700858ff6f7c..79b92130a03f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -24,12 +24,21 @@ #include "stmmac_platform.h" struct rk_priv_data; + +struct rk_reg_speed_data { + unsigned int rgmii_10; + unsigned int rgmii_100; + unsigned int rgmii_1000; + unsigned int rmii_10; + unsigned int rmii_100; +}; + struct rk_gmac_ops { void (*set_to_rgmii)(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay); void (*set_to_rmii)(struct rk_priv_data *bsp_priv); - void (*set_rgmii_speed)(struct rk_priv_data *bsp_priv, int speed); - void (*set_rmii_speed)(struct rk_priv_data *bsp_priv, int speed); + int (*set_speed)(struct rk_priv_data *bsp_priv, + phy_interface_t interface, int speed); void (*set_clock_selection)(struct rk_priv_data *bsp_priv, bool input, bool enable); void (*integrated_phy_powerup)(struct rk_priv_data *bsp_priv); @@ -58,7 +67,7 @@ enum rk_clocks_index { }; struct rk_priv_data { - struct platform_device *pdev; + struct device *dev; phy_interface_t phy_iface; int id; struct regulator *regulator; @@ -71,7 +80,6 @@ struct rk_priv_data { struct clk_bulk_data *clks; int num_clks; - struct clk *clk_mac; struct clk *clk_phy; struct reset_control *phy_reset; @@ -83,6 +91,64 @@ struct rk_priv_data { struct regmap *php_grf; }; +static int rk_set_reg_speed(struct rk_priv_data *bsp_priv, + const struct rk_reg_speed_data *rsd, + unsigned int reg, phy_interface_t interface, + int speed) +{ + unsigned int val; + + if (phy_interface_mode_is_rgmii(interface)) { + if (speed == SPEED_10) { + val = rsd->rgmii_10; + } else if (speed == SPEED_100) { + val = rsd->rgmii_100; + } else if (speed == SPEED_1000) { + val = rsd->rgmii_1000; + } else { + /* Phylink will not allow inappropriate speeds for + * interface modes, so this should never happen. + */ + return -EINVAL; + } + } else if (interface == PHY_INTERFACE_MODE_RMII) { + if (speed == SPEED_10) { + val = rsd->rmii_10; + } else if (speed == SPEED_100) { + val = rsd->rmii_100; + } else { + /* Phylink will not allow inappropriate speeds for + * interface modes, so this should never happen. + */ + return -EINVAL; + } + } else { + /* This should never happen, as .get_interfaces() limits + * the interface modes that are supported to RGMII and/or + * RMII. + */ + return -EINVAL; + } + + regmap_write(bsp_priv->grf, reg, val); + + return 0; + +} + +static int rk_set_clk_mac_speed(struct rk_priv_data *bsp_priv, + phy_interface_t interface, int speed) +{ + struct clk *clk_mac_speed = bsp_priv->clks[RK_CLK_MAC_SPEED].clk; + long rate; + + rate = rgmii_clock(speed); + if (rate < 0) + return rate; + + return clk_set_rate(clk_mac_speed, rate); +} + #define HIWORD_UPDATE(val, mask, shift) \ ((val) << (shift) | (mask) << ((shift) + 16)) @@ -177,42 +243,38 @@ static void px30_set_to_rmii(struct rk_priv_data *bsp_priv) PX30_GMAC_PHY_INTF_SEL_RMII); } -static void px30_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) +static int px30_set_speed(struct rk_priv_data *bsp_priv, + phy_interface_t interface, int speed) { struct clk *clk_mac_speed = bsp_priv->clks[RK_CLK_MAC_SPEED].clk; - struct device *dev = &bsp_priv->pdev->dev; - int ret; + struct device *dev = bsp_priv->dev; + unsigned int con1; + long rate; if (!clk_mac_speed) { dev_err(dev, "%s: Missing clk_mac_speed clock\n", __func__); - return; + return -EINVAL; } if (speed == 10) { - regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1, - PX30_GMAC_SPEED_10M); - - ret = clk_set_rate(clk_mac_speed, 2500000); - if (ret) - dev_err(dev, "%s: set clk_mac_speed rate 2500000 failed: %d\n", - __func__, ret); + con1 = PX30_GMAC_SPEED_10M; + rate = 2500000; } else if (speed == 100) { - regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1, - PX30_GMAC_SPEED_100M); - - ret = clk_set_rate(clk_mac_speed, 25000000); - if (ret) - dev_err(dev, "%s: set clk_mac_speed rate 25000000 failed: %d\n", - __func__, ret); - + con1 = PX30_GMAC_SPEED_100M; + rate = 25000000; } else { dev_err(dev, "unknown speed value for RMII! speed=%d", speed); + return -EINVAL; } + + regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1, con1); + + return clk_set_rate(clk_mac_speed, rate); } static const struct rk_gmac_ops px30_ops = { .set_to_rmii = px30_set_to_rmii, - .set_rmii_speed = px30_set_rmii_speed, + .set_speed = px30_set_speed, }; #define RK3128_GRF_MAC_CON0 0x0168 @@ -261,45 +323,25 @@ static void rk3128_set_to_rmii(struct rk_priv_data *bsp_priv) RK3128_GMAC_PHY_INTF_SEL_RMII | RK3128_GMAC_RMII_MODE); } -static void rk3128_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed) -{ - struct device *dev = &bsp_priv->pdev->dev; - - if (speed == 10) - regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, - RK3128_GMAC_CLK_2_5M); - else if (speed == 100) - regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, - RK3128_GMAC_CLK_25M); - else if (speed == 1000) - regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, - RK3128_GMAC_CLK_125M); - else - dev_err(dev, "unknown speed value for RGMII! speed=%d", speed); -} +static const struct rk_reg_speed_data rk3128_reg_speed_data = { + .rgmii_10 = RK3128_GMAC_CLK_2_5M, + .rgmii_100 = RK3128_GMAC_CLK_25M, + .rgmii_1000 = RK3128_GMAC_CLK_125M, + .rmii_10 = RK3128_GMAC_RMII_CLK_2_5M | RK3128_GMAC_SPEED_10M, + .rmii_100 = RK3128_GMAC_RMII_CLK_25M | RK3128_GMAC_SPEED_100M, +}; -static void rk3128_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) +static int rk3128_set_speed(struct rk_priv_data *bsp_priv, + phy_interface_t interface, int speed) { - struct device *dev = &bsp_priv->pdev->dev; - - if (speed == 10) { - regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, - RK3128_GMAC_RMII_CLK_2_5M | - RK3128_GMAC_SPEED_10M); - } else if (speed == 100) { - regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, - RK3128_GMAC_RMII_CLK_25M | - RK3128_GMAC_SPEED_100M); - } else { - dev_err(dev, "unknown speed value for RMII! speed=%d", speed); - } + return rk_set_reg_speed(bsp_priv, &rk3128_reg_speed_data, + RK3128_GRF_MAC_CON1, interface, speed); } static const struct rk_gmac_ops rk3128_ops = { .set_to_rgmii = rk3128_set_to_rgmii, .set_to_rmii = rk3128_set_to_rmii, - .set_rgmii_speed = rk3128_set_rgmii_speed, - .set_rmii_speed = rk3128_set_rmii_speed, + .set_speed = rk3128_set_speed, }; #define RK3228_GRF_MAC_CON0 0x0900 @@ -358,37 +400,19 @@ static void rk3228_set_to_rmii(struct rk_priv_data *bsp_priv) regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1, GRF_BIT(11)); } -static void rk3228_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed) -{ - struct device *dev = &bsp_priv->pdev->dev; - - if (speed == 10) - regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1, - RK3228_GMAC_CLK_2_5M); - else if (speed == 100) - regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1, - RK3228_GMAC_CLK_25M); - else if (speed == 1000) - regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1, - RK3228_GMAC_CLK_125M); - else - dev_err(dev, "unknown speed value for RGMII! speed=%d", speed); -} +static const struct rk_reg_speed_data rk3228_reg_speed_data = { + .rgmii_10 = RK3228_GMAC_CLK_2_5M, + .rgmii_100 = RK3228_GMAC_CLK_25M, + .rgmii_1000 = RK3228_GMAC_CLK_125M, + .rmii_10 = RK3228_GMAC_RMII_CLK_2_5M | RK3228_GMAC_SPEED_10M, + .rmii_100 = RK3228_GMAC_RMII_CLK_25M | RK3228_GMAC_SPEED_100M, +}; -static void rk3228_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) +static int rk3228_set_speed(struct rk_priv_data *bsp_priv, + phy_interface_t interface, int speed) { - struct device *dev = &bsp_priv->pdev->dev; - - if (speed == 10) - regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1, - RK3228_GMAC_RMII_CLK_2_5M | - RK3228_GMAC_SPEED_10M); - else if (speed == 100) - regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1, - RK3228_GMAC_RMII_CLK_25M | - RK3228_GMAC_SPEED_100M); - else - dev_err(dev, "unknown speed value for RMII! speed=%d", speed); + return rk_set_reg_speed(bsp_priv, &rk3228_reg_speed_data, + RK3228_GRF_MAC_CON1, interface, speed); } static void rk3228_integrated_phy_powerup(struct rk_priv_data *priv) @@ -402,8 +426,7 @@ static void rk3228_integrated_phy_powerup(struct rk_priv_data *priv) static const struct rk_gmac_ops rk3228_ops = { .set_to_rgmii = rk3228_set_to_rgmii, .set_to_rmii = rk3228_set_to_rmii, - .set_rgmii_speed = rk3228_set_rgmii_speed, - .set_rmii_speed = rk3228_set_rmii_speed, + .set_speed = rk3228_set_speed, .integrated_phy_powerup = rk3228_integrated_phy_powerup, .integrated_phy_powerdown = rk_gmac_integrated_ephy_powerdown, }; @@ -454,45 +477,25 @@ static void rk3288_set_to_rmii(struct rk_priv_data *bsp_priv) RK3288_GMAC_PHY_INTF_SEL_RMII | RK3288_GMAC_RMII_MODE); } -static void rk3288_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed) -{ - struct device *dev = &bsp_priv->pdev->dev; - - if (speed == 10) - regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1, - RK3288_GMAC_CLK_2_5M); - else if (speed == 100) - regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1, - RK3288_GMAC_CLK_25M); - else if (speed == 1000) - regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1, - RK3288_GMAC_CLK_125M); - else - dev_err(dev, "unknown speed value for RGMII! speed=%d", speed); -} +static const struct rk_reg_speed_data rk3288_reg_speed_data = { + .rgmii_10 = RK3288_GMAC_CLK_2_5M, + .rgmii_100 = RK3288_GMAC_CLK_25M, + .rgmii_1000 = RK3288_GMAC_CLK_125M, + .rmii_10 = RK3288_GMAC_RMII_CLK_2_5M | RK3288_GMAC_SPEED_10M, + .rmii_100 = RK3288_GMAC_RMII_CLK_25M | RK3288_GMAC_SPEED_100M, +}; -static void rk3288_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) +static int rk3288_set_speed(struct rk_priv_data *bsp_priv, + phy_interface_t interface, int speed) { - struct device *dev = &bsp_priv->pdev->dev; - - if (speed == 10) { - regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1, - RK3288_GMAC_RMII_CLK_2_5M | - RK3288_GMAC_SPEED_10M); - } else if (speed == 100) { - regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1, - RK3288_GMAC_RMII_CLK_25M | - RK3288_GMAC_SPEED_100M); - } else { - dev_err(dev, "unknown speed value for RMII! speed=%d", speed); - } + return rk_set_reg_speed(bsp_priv, &rk3288_reg_speed_data, + RK3288_GRF_SOC_CON1, interface, speed); } static const struct rk_gmac_ops rk3288_ops = { .set_to_rgmii = rk3288_set_to_rgmii, .set_to_rmii = rk3288_set_to_rmii, - .set_rgmii_speed = rk3288_set_rgmii_speed, - .set_rmii_speed = rk3288_set_rmii_speed, + .set_speed = rk3288_set_speed, }; #define RK3308_GRF_MAC_CON0 0x04a0 @@ -511,24 +514,21 @@ static void rk3308_set_to_rmii(struct rk_priv_data *bsp_priv) RK3308_GMAC_PHY_INTF_SEL_RMII); } -static void rk3308_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) -{ - struct device *dev = &bsp_priv->pdev->dev; +static const struct rk_reg_speed_data rk3308_reg_speed_data = { + .rmii_10 = RK3308_GMAC_SPEED_10M, + .rmii_100 = RK3308_GMAC_SPEED_100M, +}; - if (speed == 10) { - regmap_write(bsp_priv->grf, RK3308_GRF_MAC_CON0, - RK3308_GMAC_SPEED_10M); - } else if (speed == 100) { - regmap_write(bsp_priv->grf, RK3308_GRF_MAC_CON0, - RK3308_GMAC_SPEED_100M); - } else { - dev_err(dev, "unknown speed value for RMII! speed=%d", speed); - } +static int rk3308_set_speed(struct rk_priv_data *bsp_priv, + phy_interface_t interface, int speed) +{ + return rk_set_reg_speed(bsp_priv, &rk3308_reg_speed_data, + RK3308_GRF_MAC_CON0, interface, speed); } static const struct rk_gmac_ops rk3308_ops = { .set_to_rmii = rk3308_set_to_rmii, - .set_rmii_speed = rk3308_set_rmii_speed, + .set_speed = rk3308_set_speed, }; #define RK3328_GRF_MAC_CON0 0x0900 @@ -590,41 +590,26 @@ static void rk3328_set_to_rmii(struct rk_priv_data *bsp_priv) RK3328_GMAC_RMII_MODE); } -static void rk3328_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed) -{ - struct device *dev = &bsp_priv->pdev->dev; - - if (speed == 10) - regmap_write(bsp_priv->grf, RK3328_GRF_MAC_CON1, - RK3328_GMAC_CLK_2_5M); - else if (speed == 100) - regmap_write(bsp_priv->grf, RK3328_GRF_MAC_CON1, - RK3328_GMAC_CLK_25M); - else if (speed == 1000) - regmap_write(bsp_priv->grf, RK3328_GRF_MAC_CON1, - RK3328_GMAC_CLK_125M); - else - dev_err(dev, "unknown speed value for RGMII! speed=%d", speed); -} +static const struct rk_reg_speed_data rk3328_reg_speed_data = { + .rgmii_10 = RK3328_GMAC_CLK_2_5M, + .rgmii_100 = RK3328_GMAC_CLK_25M, + .rgmii_1000 = RK3328_GMAC_CLK_125M, + .rmii_10 = RK3328_GMAC_RMII_CLK_2_5M | RK3328_GMAC_SPEED_10M, + .rmii_100 = RK3328_GMAC_RMII_CLK_25M | RK3328_GMAC_SPEED_100M, +}; -static void rk3328_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) +static int rk3328_set_speed(struct rk_priv_data *bsp_priv, + phy_interface_t interface, int speed) { - struct device *dev = &bsp_priv->pdev->dev; unsigned int reg; - reg = bsp_priv->integrated_phy ? RK3328_GRF_MAC_CON2 : - RK3328_GRF_MAC_CON1; - - if (speed == 10) - regmap_write(bsp_priv->grf, reg, - RK3328_GMAC_RMII_CLK_2_5M | - RK3328_GMAC_SPEED_10M); - else if (speed == 100) - regmap_write(bsp_priv->grf, reg, - RK3328_GMAC_RMII_CLK_25M | - RK3328_GMAC_SPEED_100M); + if (interface == PHY_INTERFACE_MODE_RMII && bsp_priv->integrated_phy) + reg = RK3328_GRF_MAC_CON2; else - dev_err(dev, "unknown speed value for RMII! speed=%d", speed); + reg = RK3328_GRF_MAC_CON1; + + return rk_set_reg_speed(bsp_priv, &rk3328_reg_speed_data, reg, + interface, speed); } static void rk3328_integrated_phy_powerup(struct rk_priv_data *priv) @@ -638,8 +623,7 @@ static void rk3328_integrated_phy_powerup(struct rk_priv_data *priv) static const struct rk_gmac_ops rk3328_ops = { .set_to_rgmii = rk3328_set_to_rgmii, .set_to_rmii = rk3328_set_to_rmii, - .set_rgmii_speed = rk3328_set_rgmii_speed, - .set_rmii_speed = rk3328_set_rmii_speed, + .set_speed = rk3328_set_speed, .integrated_phy_powerup = rk3328_integrated_phy_powerup, .integrated_phy_powerdown = rk_gmac_integrated_ephy_powerdown, }; @@ -690,45 +674,25 @@ static void rk3366_set_to_rmii(struct rk_priv_data *bsp_priv) RK3366_GMAC_PHY_INTF_SEL_RMII | RK3366_GMAC_RMII_MODE); } -static void rk3366_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed) -{ - struct device *dev = &bsp_priv->pdev->dev; - - if (speed == 10) - regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6, - RK3366_GMAC_CLK_2_5M); - else if (speed == 100) - regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6, - RK3366_GMAC_CLK_25M); - else if (speed == 1000) - regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6, - RK3366_GMAC_CLK_125M); - else - dev_err(dev, "unknown speed value for RGMII! speed=%d", speed); -} +static const struct rk_reg_speed_data rk3366_reg_speed_data = { + .rgmii_10 = RK3366_GMAC_CLK_2_5M, + .rgmii_100 = RK3366_GMAC_CLK_25M, + .rgmii_1000 = RK3366_GMAC_CLK_125M, + .rmii_10 = RK3366_GMAC_RMII_CLK_2_5M | RK3366_GMAC_SPEED_10M, + .rmii_100 = RK3366_GMAC_RMII_CLK_25M | RK3366_GMAC_SPEED_100M, +}; -static void rk3366_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) +static int rk3366_set_speed(struct rk_priv_data *bsp_priv, + phy_interface_t interface, int speed) { - struct device *dev = &bsp_priv->pdev->dev; - - if (speed == 10) { - regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6, - RK3366_GMAC_RMII_CLK_2_5M | - RK3366_GMAC_SPEED_10M); - } else if (speed == 100) { - regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6, - RK3366_GMAC_RMII_CLK_25M | - RK3366_GMAC_SPEED_100M); - } else { - dev_err(dev, "unknown speed value for RMII! speed=%d", speed); - } + return rk_set_reg_speed(bsp_priv, &rk3366_reg_speed_data, + RK3366_GRF_SOC_CON6, interface, speed); } static const struct rk_gmac_ops rk3366_ops = { .set_to_rgmii = rk3366_set_to_rgmii, .set_to_rmii = rk3366_set_to_rmii, - .set_rgmii_speed = rk3366_set_rgmii_speed, - .set_rmii_speed = rk3366_set_rmii_speed, + .set_speed = rk3366_set_speed, }; #define RK3368_GRF_SOC_CON15 0x043c @@ -777,45 +741,25 @@ static void rk3368_set_to_rmii(struct rk_priv_data *bsp_priv) RK3368_GMAC_PHY_INTF_SEL_RMII | RK3368_GMAC_RMII_MODE); } -static void rk3368_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed) -{ - struct device *dev = &bsp_priv->pdev->dev; - - if (speed == 10) - regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15, - RK3368_GMAC_CLK_2_5M); - else if (speed == 100) - regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15, - RK3368_GMAC_CLK_25M); - else if (speed == 1000) - regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15, - RK3368_GMAC_CLK_125M); - else - dev_err(dev, "unknown speed value for RGMII! speed=%d", speed); -} +static const struct rk_reg_speed_data rk3368_reg_speed_data = { + .rgmii_10 = RK3368_GMAC_CLK_2_5M, + .rgmii_100 = RK3368_GMAC_CLK_25M, + .rgmii_1000 = RK3368_GMAC_CLK_125M, + .rmii_10 = RK3368_GMAC_RMII_CLK_2_5M | RK3368_GMAC_SPEED_10M, + .rmii_100 = RK3368_GMAC_RMII_CLK_25M | RK3368_GMAC_SPEED_100M, +}; -static void rk3368_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) +static int rk3368_set_speed(struct rk_priv_data *bsp_priv, + phy_interface_t interface, int speed) { - struct device *dev = &bsp_priv->pdev->dev; - - if (speed == 10) { - regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15, - RK3368_GMAC_RMII_CLK_2_5M | - RK3368_GMAC_SPEED_10M); - } else if (speed == 100) { - regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15, - RK3368_GMAC_RMII_CLK_25M | - RK3368_GMAC_SPEED_100M); - } else { - dev_err(dev, "unknown speed value for RMII! speed=%d", speed); - } + return rk_set_reg_speed(bsp_priv, &rk3368_reg_speed_data, + RK3368_GRF_SOC_CON15, interface, speed); } static const struct rk_gmac_ops rk3368_ops = { .set_to_rgmii = rk3368_set_to_rgmii, .set_to_rmii = rk3368_set_to_rmii, - .set_rgmii_speed = rk3368_set_rgmii_speed, - .set_rmii_speed = rk3368_set_rmii_speed, + .set_speed = rk3368_set_speed, }; #define RK3399_GRF_SOC_CON5 0xc214 @@ -864,45 +808,25 @@ static void rk3399_set_to_rmii(struct rk_priv_data *bsp_priv) RK3399_GMAC_PHY_INTF_SEL_RMII | RK3399_GMAC_RMII_MODE); } -static void rk3399_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed) -{ - struct device *dev = &bsp_priv->pdev->dev; - - if (speed == 10) - regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5, - RK3399_GMAC_CLK_2_5M); - else if (speed == 100) - regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5, - RK3399_GMAC_CLK_25M); - else if (speed == 1000) - regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5, - RK3399_GMAC_CLK_125M); - else - dev_err(dev, "unknown speed value for RGMII! speed=%d", speed); -} +static const struct rk_reg_speed_data rk3399_reg_speed_data = { + .rgmii_10 = RK3399_GMAC_CLK_2_5M, + .rgmii_100 = RK3399_GMAC_CLK_25M, + .rgmii_1000 = RK3399_GMAC_CLK_125M, + .rmii_10 = RK3399_GMAC_RMII_CLK_2_5M | RK3399_GMAC_SPEED_10M, + .rmii_100 = RK3399_GMAC_RMII_CLK_25M | RK3399_GMAC_SPEED_100M, +}; -static void rk3399_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) +static int rk3399_set_speed(struct rk_priv_data *bsp_priv, + phy_interface_t interface, int speed) { - struct device *dev = &bsp_priv->pdev->dev; - - if (speed == 10) { - regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5, - RK3399_GMAC_RMII_CLK_2_5M | - RK3399_GMAC_SPEED_10M); - } else if (speed == 100) { - regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5, - RK3399_GMAC_RMII_CLK_25M | - RK3399_GMAC_SPEED_100M); - } else { - dev_err(dev, "unknown speed value for RMII! speed=%d", speed); - } + return rk_set_reg_speed(bsp_priv, &rk3399_reg_speed_data, + RK3399_GRF_SOC_CON5, interface, speed); } static const struct rk_gmac_ops rk3399_ops = { .set_to_rgmii = rk3399_set_to_rgmii, .set_to_rmii = rk3399_set_to_rmii, - .set_rgmii_speed = rk3399_set_rgmii_speed, - .set_rmii_speed = rk3399_set_rmii_speed, + .set_speed = rk3399_set_speed, }; #define RK3528_VO_GRF_GMAC_CON 0x0018 @@ -965,43 +889,34 @@ static void rk3528_set_to_rmii(struct rk_priv_data *bsp_priv) RK3528_GMAC0_CLK_RMII_DIV2); } -static void rk3528_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed) -{ - struct device *dev = &bsp_priv->pdev->dev; +static const struct rk_reg_speed_data rk3528_gmac0_reg_speed_data = { + .rmii_10 = RK3528_GMAC0_CLK_RMII_DIV20, + .rmii_100 = RK3528_GMAC0_CLK_RMII_DIV2, +}; - if (speed == 10) - regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5, - RK3528_GMAC1_CLK_RGMII_DIV50); - else if (speed == 100) - regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5, - RK3528_GMAC1_CLK_RGMII_DIV5); - else if (speed == 1000) - regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5, - RK3528_GMAC1_CLK_RGMII_DIV1); - else - dev_err(dev, "unknown speed value for RGMII! speed=%d", speed); -} +static const struct rk_reg_speed_data rk3528_gmac1_reg_speed_data = { + .rgmii_10 = RK3528_GMAC1_CLK_RGMII_DIV50, + .rgmii_100 = RK3528_GMAC1_CLK_RGMII_DIV5, + .rgmii_1000 = RK3528_GMAC1_CLK_RGMII_DIV1, + .rmii_10 = RK3528_GMAC1_CLK_RMII_DIV20, + .rmii_100 = RK3528_GMAC1_CLK_RMII_DIV2, +}; -static void rk3528_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) +static int rk3528_set_speed(struct rk_priv_data *bsp_priv, + phy_interface_t interface, int speed) { - struct device *dev = &bsp_priv->pdev->dev; - unsigned int reg, val; + const struct rk_reg_speed_data *rsd; + unsigned int reg; - if (speed == 10) - val = bsp_priv->id == 1 ? RK3528_GMAC1_CLK_RMII_DIV20 : - RK3528_GMAC0_CLK_RMII_DIV20; - else if (speed == 100) - val = bsp_priv->id == 1 ? RK3528_GMAC1_CLK_RMII_DIV2 : - RK3528_GMAC0_CLK_RMII_DIV2; - else { - dev_err(dev, "unknown speed value for RMII! speed=%d", speed); - return; + if (bsp_priv->id == 1) { + rsd = &rk3528_gmac1_reg_speed_data; + reg = RK3528_VPU_GRF_GMAC_CON5; + } else { + rsd = &rk3528_gmac0_reg_speed_data; + reg = RK3528_VO_GRF_GMAC_CON; } - reg = bsp_priv->id == 1 ? RK3528_VPU_GRF_GMAC_CON5 : - RK3528_VO_GRF_GMAC_CON; - - regmap_write(bsp_priv->grf, reg, val); + return rk_set_reg_speed(bsp_priv, rsd, reg, interface, speed); } static void rk3528_set_clock_selection(struct rk_priv_data *bsp_priv, @@ -1035,8 +950,7 @@ static void rk3528_integrated_phy_powerdown(struct rk_priv_data *bsp_priv) static const struct rk_gmac_ops rk3528_ops = { .set_to_rgmii = rk3528_set_to_rgmii, .set_to_rmii = rk3528_set_to_rmii, - .set_rgmii_speed = rk3528_set_rgmii_speed, - .set_rmii_speed = rk3528_set_rmii_speed, + .set_speed = rk3528_set_speed, .set_clock_selection = rk3528_set_clock_selection, .integrated_phy_powerup = rk3528_integrated_phy_powerup, .integrated_phy_powerdown = rk3528_integrated_phy_powerdown, @@ -1098,30 +1012,10 @@ static void rk3568_set_to_rmii(struct rk_priv_data *bsp_priv) regmap_write(bsp_priv->grf, con1, RK3568_GMAC_PHY_INTF_SEL_RMII); } -static void rk3568_set_gmac_speed(struct rk_priv_data *bsp_priv, int speed) -{ - struct clk *clk_mac_speed = bsp_priv->clks[RK_CLK_MAC_SPEED].clk; - struct device *dev = &bsp_priv->pdev->dev; - long rate; - int ret; - - rate = rgmii_clock(speed); - if (rate < 0) { - dev_err(dev, "unknown speed value for GMAC speed=%d", speed); - return; - } - - ret = clk_set_rate(clk_mac_speed, rate); - if (ret) - dev_err(dev, "%s: set clk_mac_speed rate %ld failed %d\n", - __func__, rate, ret); -} - static const struct rk_gmac_ops rk3568_ops = { .set_to_rgmii = rk3568_set_to_rgmii, .set_to_rmii = rk3568_set_to_rmii, - .set_rgmii_speed = rk3568_set_gmac_speed, - .set_rmii_speed = rk3568_set_gmac_speed, + .set_speed = rk_set_clk_mac_speed, .regs_valid = true, .regs = { 0xfe2a0000, /* gmac0 */ @@ -1205,42 +1099,24 @@ static void rk3576_set_to_rmii(struct rk_priv_data *bsp_priv) regmap_write(bsp_priv->grf, offset_con, RK3576_GMAC_RMII_MODE); } -static void rk3576_set_gmac_speed(struct rk_priv_data *bsp_priv, int speed) -{ - struct device *dev = &bsp_priv->pdev->dev; - unsigned int val = 0, offset_con; +static const struct rk_reg_speed_data rk3578_reg_speed_data = { + .rgmii_10 = RK3576_GMAC_CLK_RGMII_DIV50, + .rgmii_100 = RK3576_GMAC_CLK_RGMII_DIV5, + .rgmii_1000 = RK3576_GMAC_CLK_RGMII_DIV1, + .rmii_10 = RK3576_GMAC_CLK_RMII_DIV20, + .rmii_100 = RK3576_GMAC_CLK_RMII_DIV2, +}; - switch (speed) { - case 10: - if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII) - val = RK3576_GMAC_CLK_RMII_DIV20; - else - val = RK3576_GMAC_CLK_RGMII_DIV50; - break; - case 100: - if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII) - val = RK3576_GMAC_CLK_RMII_DIV2; - else - val = RK3576_GMAC_CLK_RGMII_DIV5; - break; - case 1000: - if (bsp_priv->phy_iface != PHY_INTERFACE_MODE_RMII) - val = RK3576_GMAC_CLK_RGMII_DIV1; - else - goto err; - break; - default: - goto err; - } +static int rk3576_set_gmac_speed(struct rk_priv_data *bsp_priv, + phy_interface_t interface, int speed) +{ + unsigned int offset_con; offset_con = bsp_priv->id == 1 ? RK3576_GRF_GMAC_CON1 : RK3576_GRF_GMAC_CON0; - regmap_write(bsp_priv->grf, offset_con, val); - - return; -err: - dev_err(dev, "unknown speed value for GMAC speed=%d", speed); + return rk_set_reg_speed(bsp_priv, &rk3578_reg_speed_data, offset_con, + interface, speed); } static void rk3576_set_clock_selection(struct rk_priv_data *bsp_priv, bool input, @@ -1262,8 +1138,7 @@ static void rk3576_set_clock_selection(struct rk_priv_data *bsp_priv, bool input static const struct rk_gmac_ops rk3576_ops = { .set_to_rgmii = rk3576_set_to_rgmii, .set_to_rmii = rk3576_set_to_rmii, - .set_rgmii_speed = rk3576_set_gmac_speed, - .set_rmii_speed = rk3576_set_gmac_speed, + .set_speed = rk3576_set_gmac_speed, .set_clock_selection = rk3576_set_clock_selection, .php_grf_required = true, .regs_valid = true, @@ -1347,26 +1222,26 @@ static void rk3588_set_to_rmii(struct rk_priv_data *bsp_priv) RK3588_GMAC_CLK_RMII_MODE(bsp_priv->id)); } -static void rk3588_set_gmac_speed(struct rk_priv_data *bsp_priv, int speed) +static int rk3588_set_gmac_speed(struct rk_priv_data *bsp_priv, + phy_interface_t interface, int speed) { - struct device *dev = &bsp_priv->pdev->dev; unsigned int val = 0, id = bsp_priv->id; switch (speed) { case 10: - if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII) + if (interface == PHY_INTERFACE_MODE_RMII) val = RK3588_GMA_CLK_RMII_DIV20(id); else val = RK3588_GMAC_CLK_RGMII_DIV50(id); break; case 100: - if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII) + if (interface == PHY_INTERFACE_MODE_RMII) val = RK3588_GMA_CLK_RMII_DIV2(id); else val = RK3588_GMAC_CLK_RGMII_DIV5(id); break; case 1000: - if (bsp_priv->phy_iface != PHY_INTERFACE_MODE_RMII) + if (interface != PHY_INTERFACE_MODE_RMII) val = RK3588_GMAC_CLK_RGMII_DIV1(id); else goto err; @@ -1377,9 +1252,9 @@ static void rk3588_set_gmac_speed(struct rk_priv_data *bsp_priv, int speed) regmap_write(bsp_priv->php_grf, RK3588_GRF_CLK_CON1, val); - return; + return 0; err: - dev_err(dev, "unknown speed value for GMAC speed=%d", speed); + return -EINVAL; } static void rk3588_set_clock_selection(struct rk_priv_data *bsp_priv, bool input, @@ -1397,8 +1272,7 @@ static void rk3588_set_clock_selection(struct rk_priv_data *bsp_priv, bool input static const struct rk_gmac_ops rk3588_ops = { .set_to_rgmii = rk3588_set_to_rgmii, .set_to_rmii = rk3588_set_to_rmii, - .set_rgmii_speed = rk3588_set_gmac_speed, - .set_rmii_speed = rk3588_set_gmac_speed, + .set_speed = rk3588_set_gmac_speed, .set_clock_selection = rk3588_set_clock_selection, .php_grf_required = true, .regs_valid = true, @@ -1427,26 +1301,21 @@ static void rv1108_set_to_rmii(struct rk_priv_data *bsp_priv) RV1108_GMAC_PHY_INTF_SEL_RMII); } -static void rv1108_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) -{ - struct device *dev = &bsp_priv->pdev->dev; +static const struct rk_reg_speed_data rv1108_reg_speed_data = { + .rmii_10 = RV1108_GMAC_RMII_CLK_2_5M | RV1108_GMAC_SPEED_10M, + .rmii_100 = RV1108_GMAC_RMII_CLK_25M | RV1108_GMAC_SPEED_100M, +}; - if (speed == 10) { - regmap_write(bsp_priv->grf, RV1108_GRF_GMAC_CON0, - RV1108_GMAC_RMII_CLK_2_5M | - RV1108_GMAC_SPEED_10M); - } else if (speed == 100) { - regmap_write(bsp_priv->grf, RV1108_GRF_GMAC_CON0, - RV1108_GMAC_RMII_CLK_25M | - RV1108_GMAC_SPEED_100M); - } else { - dev_err(dev, "unknown speed value for RMII! speed=%d", speed); - } +static int rv1108_set_speed(struct rk_priv_data *bsp_priv, + phy_interface_t interface, int speed) +{ + return rk_set_reg_speed(bsp_priv, &rv1108_reg_speed_data, + RV1108_GRF_GMAC_CON0, interface, speed); } static const struct rk_gmac_ops rv1108_ops = { .set_to_rmii = rv1108_set_to_rmii, - .set_rmii_speed = rv1108_set_rmii_speed, + .set_speed = rv1108_set_speed, }; #define RV1126_GRF_GMAC_CON0 0X0070 @@ -1501,62 +1370,17 @@ static void rv1126_set_to_rmii(struct rk_priv_data *bsp_priv) RV1126_GMAC_PHY_INTF_SEL_RMII); } -static void rv1126_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed) -{ - struct clk *clk_mac_speed = bsp_priv->clks[RK_CLK_MAC_SPEED].clk; - struct device *dev = &bsp_priv->pdev->dev; - long rate; - int ret; - - rate = rgmii_clock(speed); - if (rate < 0) { - dev_err(dev, "unknown speed value for RGMII speed=%d", speed); - return; - } - - ret = clk_set_rate(clk_mac_speed, rate); - if (ret) - dev_err(dev, "%s: set clk_mac_speed rate %ld failed %d\n", - __func__, rate, ret); -} - -static void rv1126_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) -{ - struct clk *clk_mac_speed = bsp_priv->clks[RK_CLK_MAC_SPEED].clk; - struct device *dev = &bsp_priv->pdev->dev; - unsigned long rate; - int ret; - - switch (speed) { - case 10: - rate = 2500000; - break; - case 100: - rate = 25000000; - break; - default: - dev_err(dev, "unknown speed value for RGMII speed=%d", speed); - return; - } - - ret = clk_set_rate(clk_mac_speed, rate); - if (ret) - dev_err(dev, "%s: set clk_mac_speed rate %ld failed %d\n", - __func__, rate, ret); -} - static const struct rk_gmac_ops rv1126_ops = { .set_to_rgmii = rv1126_set_to_rgmii, .set_to_rmii = rv1126_set_to_rmii, - .set_rgmii_speed = rv1126_set_rgmii_speed, - .set_rmii_speed = rv1126_set_rmii_speed, + .set_speed = rk_set_clk_mac_speed, }; static int rk_gmac_clk_init(struct plat_stmmacenet_data *plat) { struct rk_priv_data *bsp_priv = plat->bsp_priv; - struct device *dev = &bsp_priv->pdev->dev; int phy_iface = bsp_priv->phy_iface; + struct device *dev = bsp_priv->dev; int i, j, ret; bsp_priv->clk_enabled = false; @@ -1583,16 +1407,10 @@ static int rk_gmac_clk_init(struct plat_stmmacenet_data *plat) if (ret) return dev_err_probe(dev, ret, "Failed to get clocks\n"); - /* "stmmaceth" will be enabled by the core */ - bsp_priv->clk_mac = devm_clk_get(dev, "stmmaceth"); - ret = PTR_ERR_OR_ZERO(bsp_priv->clk_mac); - if (ret) - return dev_err_probe(dev, ret, "Cannot get stmmaceth clock\n"); - if (bsp_priv->clock_input) { dev_info(dev, "clock input from PHY\n"); } else if (phy_iface == PHY_INTERFACE_MODE_RMII) { - clk_set_rate(bsp_priv->clk_mac, 50000000); + clk_set_rate(plat->stmmac_clk, 50000000); } if (plat->phy_node && bsp_priv->integrated_phy) { @@ -1648,8 +1466,8 @@ static int gmac_clk_enable(struct rk_priv_data *bsp_priv, bool enable) static int phy_power_on(struct rk_priv_data *bsp_priv, bool enable) { struct regulator *ldo = bsp_priv->regulator; + struct device *dev = bsp_priv->dev; int ret; - struct device *dev = &bsp_priv->pdev->dev; if (enable) { ret = regulator_enable(ldo); @@ -1773,7 +1591,7 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev, dev_info(dev, "integrated PHY? (%s).\n", bsp_priv->integrated_phy ? "yes" : "no"); - bsp_priv->pdev = pdev; + bsp_priv->dev = dev; return bsp_priv; } @@ -1793,7 +1611,7 @@ static int rk_gmac_check_ops(struct rk_priv_data *bsp_priv) return -EINVAL; break; default: - dev_err(&bsp_priv->pdev->dev, + dev_err(bsp_priv->dev, "unsupported interface %d", bsp_priv->phy_iface); } return 0; @@ -1801,8 +1619,8 @@ static int rk_gmac_check_ops(struct rk_priv_data *bsp_priv) static int rk_gmac_powerup(struct rk_priv_data *bsp_priv) { + struct device *dev = bsp_priv->dev; int ret; - struct device *dev = &bsp_priv->pdev->dev; ret = rk_gmac_check_ops(bsp_priv); if (ret) @@ -1858,35 +1676,34 @@ static void rk_gmac_powerdown(struct rk_priv_data *gmac) if (gmac->integrated_phy && gmac->ops->integrated_phy_powerdown) gmac->ops->integrated_phy_powerdown(gmac); - pm_runtime_put_sync(&gmac->pdev->dev); + pm_runtime_put_sync(gmac->dev); phy_power_on(gmac, false); gmac_clk_enable(gmac, false); } +static void rk_get_interfaces(struct stmmac_priv *priv, void *bsp_priv, + unsigned long *interfaces) +{ + struct rk_priv_data *rk = bsp_priv; + + if (rk->ops->set_to_rgmii) + phy_interface_set_rgmii(interfaces); + + if (rk->ops->set_to_rmii) + __set_bit(PHY_INTERFACE_MODE_RMII, interfaces); +} + static int rk_set_clk_tx_rate(void *bsp_priv_, struct clk *clk_tx_i, phy_interface_t interface, int speed) { struct rk_priv_data *bsp_priv = bsp_priv_; - struct device *dev = &bsp_priv->pdev->dev; - switch (bsp_priv->phy_iface) { - case PHY_INTERFACE_MODE_RGMII: - case PHY_INTERFACE_MODE_RGMII_ID: - case PHY_INTERFACE_MODE_RGMII_RXID: - case PHY_INTERFACE_MODE_RGMII_TXID: - if (bsp_priv->ops->set_rgmii_speed) - bsp_priv->ops->set_rgmii_speed(bsp_priv, speed); - break; - case PHY_INTERFACE_MODE_RMII: - if (bsp_priv->ops->set_rmii_speed) - bsp_priv->ops->set_rmii_speed(bsp_priv, speed); - break; - default: - dev_err(dev, "unsupported interface %d", bsp_priv->phy_iface); - } + if (bsp_priv->ops->set_speed) + return bsp_priv->ops->set_speed(bsp_priv, bsp_priv->phy_iface, + speed); - return 0; + return -EINVAL; } static int rk_gmac_probe(struct platform_device *pdev) @@ -1919,6 +1736,7 @@ static int rk_gmac_probe(struct platform_device *pdev) plat_dat->tx_fifo_size = 2048; } + plat_dat->get_interfaces = rk_get_interfaces; plat_dat->set_clk_tx_rate = rk_set_clk_tx_rate; plat_dat->bsp_priv = rk_gmac_setup(pdev, plat_dat, data); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c index 5e6ac82a89b9..bd65d4239054 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c @@ -48,7 +48,6 @@ struct visconti_eth { void __iomem *reg; - u32 phy_intf_sel; struct clk *phy_ref_clk; struct device *dev; }; @@ -57,42 +56,35 @@ static int visconti_eth_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i, phy_interface_t interface, int speed) { struct visconti_eth *dwmac = bsp_priv; - struct net_device *netdev = dev_get_drvdata(dwmac->dev); - unsigned int val, clk_sel_val = 0; - - switch (speed) { - case SPEED_1000: - if (dwmac->phy_intf_sel == ETHER_CONFIG_INTF_RGMII) - clk_sel_val = ETHER_CLK_SEL_FREQ_SEL_125M; - break; - case SPEED_100: - if (dwmac->phy_intf_sel == ETHER_CONFIG_INTF_RGMII) - clk_sel_val = ETHER_CLK_SEL_FREQ_SEL_25M; - if (dwmac->phy_intf_sel == ETHER_CONFIG_INTF_RMII) - clk_sel_val = ETHER_CLK_SEL_DIV_SEL_2; - break; - case SPEED_10: - if (dwmac->phy_intf_sel == ETHER_CONFIG_INTF_RGMII) - clk_sel_val = ETHER_CLK_SEL_FREQ_SEL_2P5M; - if (dwmac->phy_intf_sel == ETHER_CONFIG_INTF_RMII) - clk_sel_val = ETHER_CLK_SEL_DIV_SEL_20; - break; - default: - /* No bit control */ - netdev_err(netdev, "Unsupported speed request (%d)", speed); - return -EINVAL; - } - - /* Stop internal clock */ - val = readl(dwmac->reg + REG_ETHER_CLOCK_SEL); - val &= ~(ETHER_CLK_SEL_RMII_CLK_EN | ETHER_CLK_SEL_RX_TX_CLK_EN); - val |= ETHER_CLK_SEL_TX_O_E_N_IN; - writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); + unsigned long clk_sel, val; + + if (phy_interface_mode_is_rgmii(interface)) { + switch (speed) { + case SPEED_1000: + clk_sel = ETHER_CLK_SEL_FREQ_SEL_125M; + break; + + case SPEED_100: + clk_sel = ETHER_CLK_SEL_FREQ_SEL_25M; + break; + + case SPEED_10: + clk_sel = ETHER_CLK_SEL_FREQ_SEL_2P5M; + break; + + default: + return -EINVAL; + } + + /* Stop internal clock */ + val = readl(dwmac->reg + REG_ETHER_CLOCK_SEL); + val &= ~(ETHER_CLK_SEL_RMII_CLK_EN | + ETHER_CLK_SEL_RX_TX_CLK_EN); + val |= ETHER_CLK_SEL_TX_O_E_N_IN; + writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); - /* Set Clock-Mux, Start clock, Set TX_O direction */ - switch (dwmac->phy_intf_sel) { - case ETHER_CONFIG_INTF_RGMII: - val = clk_sel_val | ETHER_CLK_SEL_RX_CLK_EXT_SEL_RXC; + /* Set Clock-Mux, Start clock, Set TX_O direction */ + val = clk_sel | ETHER_CLK_SEL_RX_CLK_EXT_SEL_RXC; writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); val |= ETHER_CLK_SEL_RX_TX_CLK_EN; @@ -100,11 +92,32 @@ static int visconti_eth_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i, val &= ~ETHER_CLK_SEL_TX_O_E_N_IN; writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); - break; - case ETHER_CONFIG_INTF_RMII: - val = clk_sel_val | ETHER_CLK_SEL_RX_CLK_EXT_SEL_DIV | - ETHER_CLK_SEL_TX_CLK_EXT_SEL_DIV | ETHER_CLK_SEL_TX_O_E_N_IN | - ETHER_CLK_SEL_RMII_CLK_SEL_RX_C; + } else if (interface == PHY_INTERFACE_MODE_RMII) { + switch (speed) { + case SPEED_100: + clk_sel = ETHER_CLK_SEL_DIV_SEL_2; + break; + + case SPEED_10: + clk_sel = ETHER_CLK_SEL_DIV_SEL_20; + break; + + default: + return -EINVAL; + } + + /* Stop internal clock */ + val = readl(dwmac->reg + REG_ETHER_CLOCK_SEL); + val &= ~(ETHER_CLK_SEL_RMII_CLK_EN | + ETHER_CLK_SEL_RX_TX_CLK_EN); + val |= ETHER_CLK_SEL_TX_O_E_N_IN; + writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); + + /* Set Clock-Mux, Start clock, Set TX_O direction */ + val = clk_sel | ETHER_CLK_SEL_RX_CLK_EXT_SEL_DIV | + ETHER_CLK_SEL_TX_CLK_EXT_SEL_DIV | + ETHER_CLK_SEL_TX_O_E_N_IN | + ETHER_CLK_SEL_RMII_CLK_SEL_RX_C; writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); val |= ETHER_CLK_SEL_RMII_CLK_RST; @@ -112,16 +125,22 @@ static int visconti_eth_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i, val |= ETHER_CLK_SEL_RMII_CLK_EN | ETHER_CLK_SEL_RX_TX_CLK_EN; writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); - break; - case ETHER_CONFIG_INTF_MII: - default: - val = clk_sel_val | ETHER_CLK_SEL_RX_CLK_EXT_SEL_RXC | - ETHER_CLK_SEL_TX_CLK_EXT_SEL_TXC | ETHER_CLK_SEL_TX_O_E_N_IN; + } else { + /* Stop internal clock */ + val = readl(dwmac->reg + REG_ETHER_CLOCK_SEL); + val &= ~(ETHER_CLK_SEL_RMII_CLK_EN | + ETHER_CLK_SEL_RX_TX_CLK_EN); + val |= ETHER_CLK_SEL_TX_O_E_N_IN; + writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); + + /* Set Clock-Mux, Start clock, Set TX_O direction */ + val = ETHER_CLK_SEL_RX_CLK_EXT_SEL_RXC | + ETHER_CLK_SEL_TX_CLK_EXT_SEL_TXC | + ETHER_CLK_SEL_TX_O_E_N_IN; writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); val |= ETHER_CLK_SEL_RX_TX_CLK_EN; writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); - break; } return 0; @@ -130,28 +149,28 @@ static int visconti_eth_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i, static int visconti_eth_init_hw(struct platform_device *pdev, struct plat_stmmacenet_data *plat_dat) { struct visconti_eth *dwmac = plat_dat->bsp_priv; - unsigned int reg_val, clk_sel_val; + unsigned int clk_sel_val; + u32 phy_intf_sel; switch (plat_dat->phy_interface) { case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_TXID: - dwmac->phy_intf_sel = ETHER_CONFIG_INTF_RGMII; + phy_intf_sel = ETHER_CONFIG_INTF_RGMII; break; case PHY_INTERFACE_MODE_MII: - dwmac->phy_intf_sel = ETHER_CONFIG_INTF_MII; + phy_intf_sel = ETHER_CONFIG_INTF_MII; break; case PHY_INTERFACE_MODE_RMII: - dwmac->phy_intf_sel = ETHER_CONFIG_INTF_RMII; + phy_intf_sel = ETHER_CONFIG_INTF_RMII; break; default: dev_err(&pdev->dev, "Unsupported phy-mode (%d)\n", plat_dat->phy_interface); return -EOPNOTSUPP; } - reg_val = dwmac->phy_intf_sel; - writel(reg_val, dwmac->reg + REG_ETHER_CONTROL); + writel(phy_intf_sel, dwmac->reg + REG_ETHER_CONTROL); /* Enable TX/RX clock */ clk_sel_val = ETHER_CLK_SEL_FREQ_SEL_125M; @@ -161,8 +180,8 @@ static int visconti_eth_init_hw(struct platform_device *pdev, struct plat_stmmac dwmac->reg + REG_ETHER_CLOCK_SEL); /* release internal-reset */ - reg_val |= ETHER_ETH_CONTROL_RESET; - writel(reg_val, dwmac->reg + REG_ETHER_CONTROL); + phy_intf_sel |= ETHER_ETH_CONTROL_RESET; + writel(phy_intf_sel, dwmac->reg + REG_ETHER_CONTROL); return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index 56b76aaa58f0..38875c832bb8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -399,11 +399,6 @@ static void dwmac1000_ctrl_ane(void __iomem *ioaddr, bool ane, bool srgmi_ral, dwmac_ctrl_ane(ioaddr, GMAC_PCS_BASE, ane, srgmi_ral, loopback); } -static void dwmac1000_get_adv_lp(void __iomem *ioaddr, struct rgmii_adv *adv) -{ - dwmac_get_adv_lp(ioaddr, GMAC_PCS_BASE, adv); -} - static void dwmac1000_debug(struct stmmac_priv *priv, void __iomem *ioaddr, struct stmmac_extra_stats *x, u32 rx_queues, u32 tx_queues) @@ -508,7 +503,6 @@ const struct stmmac_ops dwmac1000_ops = { .set_eee_pls = dwmac1000_set_eee_pls, .debug = dwmac1000_debug, .pcs_ctrl_ane = dwmac1000_ctrl_ane, - .pcs_get_adv_lp = dwmac1000_get_adv_lp, .set_mac_loopback = dwmac1000_set_mac_loopback, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 9c2549d4100f..bc06b24fc611 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -589,11 +589,6 @@ static void dwmac4_ctrl_ane(void __iomem *ioaddr, bool ane, bool srgmi_ral, dwmac_ctrl_ane(ioaddr, GMAC_PCS_BASE, ane, srgmi_ral, loopback); } -static void dwmac4_get_adv_lp(void __iomem *ioaddr, struct rgmii_adv *adv) -{ - dwmac_get_adv_lp(ioaddr, GMAC_PCS_BASE, adv); -} - /* RGMII or SMII interface */ static void dwmac4_phystatus(void __iomem *ioaddr, struct stmmac_extra_stats *x) { @@ -958,7 +953,6 @@ const struct stmmac_ops dwmac4_ops = { .set_eee_timer = dwmac4_set_eee_timer, .set_eee_pls = dwmac4_set_eee_pls, .pcs_ctrl_ane = dwmac4_ctrl_ane, - .pcs_get_adv_lp = dwmac4_get_adv_lp, .debug = dwmac4_debug, .set_filter = dwmac4_set_filter, .set_mac_loopback = dwmac4_set_mac_loopback, @@ -993,7 +987,6 @@ const struct stmmac_ops dwmac410_ops = { .set_eee_timer = dwmac4_set_eee_timer, .set_eee_pls = dwmac4_set_eee_pls, .pcs_ctrl_ane = dwmac4_ctrl_ane, - .pcs_get_adv_lp = dwmac4_get_adv_lp, .debug = dwmac4_debug, .set_filter = dwmac4_set_filter, .flex_pps_config = dwmac5_flex_pps_config, @@ -1030,7 +1023,6 @@ const struct stmmac_ops dwmac510_ops = { .set_eee_timer = dwmac4_set_eee_timer, .set_eee_pls = dwmac4_set_eee_pls, .pcs_ctrl_ane = dwmac4_ctrl_ane, - .pcs_get_adv_lp = dwmac4_get_adv_lp, .debug = dwmac4_debug, .set_filter = dwmac4_set_filter, .safety_feat_config = dwmac5_safety_feat_config, diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index ae4efffb785f..e1ac9a245bfe 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -300,7 +300,6 @@ struct stmmac_dma_ops { struct mac_device_info; struct net_device; -struct rgmii_adv; struct stmmac_tc_entry; struct stmmac_pps_cfg; struct stmmac_rss; @@ -377,7 +376,6 @@ struct stmmac_ops { /* PCS calls */ void (*pcs_ctrl_ane)(void __iomem *ioaddr, bool ane, bool srgmi_ral, bool loopback); - void (*pcs_get_adv_lp)(void __iomem *ioaddr, struct rgmii_adv *adv); /* Safety Features */ int (*safety_feat_config)(void __iomem *ioaddr, unsigned int asp, struct stmmac_safety_feature_cfg *safety_cfg); @@ -467,8 +465,6 @@ struct stmmac_ops { stmmac_do_void_callback(__priv, mac, debug, __priv, __args) #define stmmac_pcs_ctrl_ane(__priv, __args...) \ stmmac_do_void_callback(__priv, mac, pcs_ctrl_ane, __args) -#define stmmac_pcs_get_adv_lp(__priv, __args...) \ - stmmac_do_void_callback(__priv, mac, pcs_get_adv_lp, __args) #define stmmac_safety_feat_config(__priv, __args...) \ stmmac_do_callback(__priv, mac, safety_feat_config, __args) #define stmmac_safety_feat_irq_status(__priv, __args...) \ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index f702f7b7bf9f..72f1724af037 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -325,7 +325,6 @@ static int stmmac_ethtool_get_link_ksettings(struct net_device *dev, if (!(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS) && (priv->hw->pcs & STMMAC_PCS_RGMII || priv->hw->pcs & STMMAC_PCS_SGMII)) { - struct rgmii_adv adv; u32 supported, advertising, lp_advertising; if (!priv->xstats.pcs_link) { @@ -337,10 +336,6 @@ static int stmmac_ethtool_get_link_ksettings(struct net_device *dev, cmd->base.speed = priv->xstats.pcs_speed; - /* Get and convert ADV/LP_ADV from the HW AN registers */ - if (stmmac_pcs_get_adv_lp(priv, priv->ioaddr, &adv)) - return -EOPNOTSUPP; /* should never happen indeed */ - /* Encoding of PSE bits is defined in 802.3z, 37.2.1.4 */ ethtool_convert_link_mode_to_legacy_u32( @@ -350,44 +345,12 @@ static int stmmac_ethtool_get_link_ksettings(struct net_device *dev, ethtool_convert_link_mode_to_legacy_u32( &lp_advertising, cmd->link_modes.lp_advertising); - if (adv.pause & STMMAC_PCS_PAUSE) - advertising |= ADVERTISED_Pause; - if (adv.pause & STMMAC_PCS_ASYM_PAUSE) - advertising |= ADVERTISED_Asym_Pause; - if (adv.lp_pause & STMMAC_PCS_PAUSE) - lp_advertising |= ADVERTISED_Pause; - if (adv.lp_pause & STMMAC_PCS_ASYM_PAUSE) - lp_advertising |= ADVERTISED_Asym_Pause; - /* Reg49[3] always set because ANE is always supported */ cmd->base.autoneg = ADVERTISED_Autoneg; supported |= SUPPORTED_Autoneg; advertising |= ADVERTISED_Autoneg; lp_advertising |= ADVERTISED_Autoneg; - if (adv.duplex) { - supported |= (SUPPORTED_1000baseT_Full | - SUPPORTED_100baseT_Full | - SUPPORTED_10baseT_Full); - advertising |= (ADVERTISED_1000baseT_Full | - ADVERTISED_100baseT_Full | - ADVERTISED_10baseT_Full); - } else { - supported |= (SUPPORTED_1000baseT_Half | - SUPPORTED_100baseT_Half | - SUPPORTED_10baseT_Half); - advertising |= (ADVERTISED_1000baseT_Half | - ADVERTISED_100baseT_Half | - ADVERTISED_10baseT_Half); - } - if (adv.lp_duplex) - lp_advertising |= (ADVERTISED_1000baseT_Full | - ADVERTISED_100baseT_Full | - ADVERTISED_10baseT_Full); - else - lp_advertising |= (ADVERTISED_1000baseT_Half | - ADVERTISED_100baseT_Half | - ADVERTISED_10baseT_Half); cmd->base.port = PORT_OTHER; ethtool_convert_legacy_u32_to_link_mode( @@ -515,12 +478,9 @@ stmmac_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) { struct stmmac_priv *priv = netdev_priv(netdev); - struct rgmii_adv adv_lp; - if (priv->hw->pcs && !stmmac_pcs_get_adv_lp(priv, priv->ioaddr, &adv_lp)) { + if (priv->hw->pcs) { pause->autoneg = 1; - if (!adv_lp.pause) - return; } else { phylink_ethtool_get_pauseparam(priv->phylink, pause); } @@ -531,12 +491,9 @@ stmmac_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) { struct stmmac_priv *priv = netdev_priv(netdev); - struct rgmii_adv adv_lp; - if (priv->hw->pcs && !stmmac_pcs_get_adv_lp(priv, priv->ioaddr, &adv_lp)) { + if (priv->hw->pcs) { pause->autoneg = 1; - if (!adv_lp.pause) - return -EOPNOTSUPP; return 0; } else { return phylink_ethtool_set_pauseparam(priv->phylink, pause); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index b948df1bff9a..c3845ec62fbd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1062,8 +1062,8 @@ static void stmmac_mac_link_up(struct phylink_config *config, interface, speed); if (ret < 0) netdev_err(priv->dev, - "failed to configure transmit clock for %dMbps: %pe\n", - speed, ERR_PTR(ret)); + "failed to configure %s transmit clock for %dMbps: %pe\n", + phy_modes(interface), speed, ERR_PTR(ret)); } stmmac_mac_set(priv, priv->ioaddr, true); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h index 1bdf87b237c4..4a684c97dfae 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h @@ -16,6 +16,8 @@ /* PCS registers (AN/TBI/SGMII/RGMII) offsets */ #define GMAC_AN_CTRL(x) (x) /* AN control */ #define GMAC_AN_STATUS(x) (x + 0x4) /* AN status */ + +/* ADV, LPA and EXP are only available for the TBI and RTBI interfaces */ #define GMAC_ANE_ADV(x) (x + 0x8) /* ANE Advertisement */ #define GMAC_ANE_LPA(x) (x + 0xc) /* ANE link partener ability */ #define GMAC_ANE_EXP(x) (x + 0x10) /* ANE expansion */ @@ -107,34 +109,4 @@ static inline void dwmac_ctrl_ane(void __iomem *ioaddr, u32 reg, bool ane, writel(value, ioaddr + GMAC_AN_CTRL(reg)); } - -/** - * dwmac_get_adv_lp - Get ADV and LP cap - * @ioaddr: IO registers pointer - * @reg: Base address of the AN Control Register. - * @adv_lp: structure to store the adv,lp status - * Description: this is to expose the ANE advertisement and Link partner ability - * status to ethtool support. - */ -static inline void dwmac_get_adv_lp(void __iomem *ioaddr, u32 reg, - struct rgmii_adv *adv_lp) -{ - u32 value = readl(ioaddr + GMAC_ANE_ADV(reg)); - - if (value & GMAC_ANE_FD) - adv_lp->duplex = DUPLEX_FULL; - if (value & GMAC_ANE_HD) - adv_lp->duplex |= DUPLEX_HALF; - - adv_lp->pause = (value & GMAC_ANE_PSE) >> GMAC_ANE_PSE_SHIFT; - - value = readl(ioaddr + GMAC_ANE_LPA(reg)); - - if (value & GMAC_ANE_FD) - adv_lp->lp_duplex = DUPLEX_FULL; - if (value & GMAC_ANE_HD) - adv_lp->lp_duplex = DUPLEX_HALF; - - adv_lp->lp_pause = (value & GMAC_ANE_PSE) >> GMAC_ANE_PSE_SHIFT; -} #endif /* __STMMAC_PCS_H__ */ diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index ddca8fc7883e..75d7e10944d4 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -7077,8 +7077,10 @@ static int niu_ethflow_to_flowkey(u64 ethflow, u64 *flow_key) } -static int niu_get_hash_opts(struct niu *np, struct ethtool_rxnfc *nfc) +static int niu_get_rxfh_fields(struct net_device *dev, + struct ethtool_rxfh_fields *nfc) { + struct niu *np = netdev_priv(dev); u64 class; nfc->data = 0; @@ -7290,9 +7292,6 @@ static int niu_get_nfc(struct net_device *dev, struct ethtool_rxnfc *cmd, int ret = 0; switch (cmd->cmd) { - case ETHTOOL_GRXFH: - ret = niu_get_hash_opts(np, cmd); - break; case ETHTOOL_GRXRINGS: cmd->data = np->num_rx_rings; break; @@ -7313,8 +7312,11 @@ static int niu_get_nfc(struct net_device *dev, struct ethtool_rxnfc *cmd, return ret; } -static int niu_set_hash_opts(struct niu *np, struct ethtool_rxnfc *nfc) +static int niu_set_rxfh_fields(struct net_device *dev, + const struct ethtool_rxfh_fields *nfc, + struct netlink_ext_ack *extack) { + struct niu *np = netdev_priv(dev); u64 class; u64 flow_key = 0; unsigned long flags; @@ -7656,9 +7658,6 @@ static int niu_set_nfc(struct net_device *dev, struct ethtool_rxnfc *cmd) int ret = 0; switch (cmd->cmd) { - case ETHTOOL_SRXFH: - ret = niu_set_hash_opts(np, cmd); - break; case ETHTOOL_SRXCLSRLINS: ret = niu_add_ethtool_tcam_entry(np, cmd); break; @@ -7912,6 +7911,8 @@ static const struct ethtool_ops niu_ethtool_ops = { .set_phys_id = niu_set_phys_id, .get_rxnfc = niu_get_nfc, .set_rxnfc = niu_set_nfc, + .get_rxfh_fields = niu_get_rxfh_fields, + .set_rxfh_fields = niu_set_rxfh_fields, .get_link_ksettings = niu_get_link_ksettings, .set_link_ksettings = niu_set_link_ksettings, }; diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 86fc1278127c..a1e013b0a0eb 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -125,45 +125,6 @@ static irqreturn_t prueth_tx_ts_irq(int irq, void *dev_id) return IRQ_HANDLED; } -static struct icssg_firmwares icssg_hsr_firmwares[] = { - { - .pru = "ti-pruss/am65x-sr2-pru0-pruhsr-fw.elf", - .rtu = "ti-pruss/am65x-sr2-rtu0-pruhsr-fw.elf", - .txpru = "ti-pruss/am65x-sr2-txpru0-pruhsr-fw.elf", - }, - { - .pru = "ti-pruss/am65x-sr2-pru1-pruhsr-fw.elf", - .rtu = "ti-pruss/am65x-sr2-rtu1-pruhsr-fw.elf", - .txpru = "ti-pruss/am65x-sr2-txpru1-pruhsr-fw.elf", - } -}; - -static struct icssg_firmwares icssg_switch_firmwares[] = { - { - .pru = "ti-pruss/am65x-sr2-pru0-prusw-fw.elf", - .rtu = "ti-pruss/am65x-sr2-rtu0-prusw-fw.elf", - .txpru = "ti-pruss/am65x-sr2-txpru0-prusw-fw.elf", - }, - { - .pru = "ti-pruss/am65x-sr2-pru1-prusw-fw.elf", - .rtu = "ti-pruss/am65x-sr2-rtu1-prusw-fw.elf", - .txpru = "ti-pruss/am65x-sr2-txpru1-prusw-fw.elf", - } -}; - -static struct icssg_firmwares icssg_emac_firmwares[] = { - { - .pru = "ti-pruss/am65x-sr2-pru0-prueth-fw.elf", - .rtu = "ti-pruss/am65x-sr2-rtu0-prueth-fw.elf", - .txpru = "ti-pruss/am65x-sr2-txpru0-prueth-fw.elf", - }, - { - .pru = "ti-pruss/am65x-sr2-pru1-prueth-fw.elf", - .rtu = "ti-pruss/am65x-sr2-rtu1-prueth-fw.elf", - .txpru = "ti-pruss/am65x-sr2-txpru1-prueth-fw.elf", - } -}; - static int prueth_start(struct rproc *rproc, const char *fw_name) { int ret; @@ -186,11 +147,11 @@ static int prueth_emac_start(struct prueth *prueth) int ret, slice; if (prueth->is_switch_mode) - firmwares = icssg_switch_firmwares; + firmwares = prueth->icssg_switch_firmwares; else if (prueth->is_hsr_offload_mode) - firmwares = icssg_hsr_firmwares; + firmwares = prueth->icssg_hsr_firmwares; else - firmwares = icssg_emac_firmwares; + firmwares = prueth->icssg_emac_firmwares; for (slice = 0; slice < PRUETH_NUM_MACS; slice++) { ret = prueth_start(prueth->pru[slice], firmwares[slice].pru); @@ -1632,6 +1593,87 @@ static void prueth_unregister_notifiers(struct prueth *prueth) unregister_netdevice_notifier(&prueth->prueth_netdevice_nb); } +static void icssg_read_firmware_names(struct device_node *np, + struct icssg_firmwares *fw) +{ + int i; + + for (i = 0; i < PRUETH_NUM_MACS; i++) { + of_property_read_string_index(np, "firmware-name", i * 3 + 0, + &fw[i].pru); + of_property_read_string_index(np, "firmware-name", i * 3 + 1, + &fw[i].rtu); + of_property_read_string_index(np, "firmware-name", i * 3 + 2, + &fw[i].txpru); + } +} + +/* icssg_firmware_name_replace - Replace a substring in firmware name + * @dev: device pointer for memory allocation + * @src: source firmware name string + * @from: substring to replace + * @to: replacement substring + * + * Return: a newly allocated string with the replacement, or the original + * string if replacement is not possible. + */ +static const char *icssg_firmware_name_replace(struct device *dev, + const char *src, + const char *from, + const char *to) +{ + size_t prefix, from_len, to_len, total; + const char *p = strstr(src, from); + char *buf; + + if (!p) + return src; /* fallback: no replacement, use original */ + + prefix = p - src; + from_len = strlen(from); + to_len = strlen(to); + total = strlen(src) - from_len + to_len + 1; + + buf = devm_kzalloc(dev, total, GFP_KERNEL); + if (!buf) + return src; /* fallback: allocation failed, use original */ + + strscpy(buf, src, prefix + 1); + strscpy(buf + prefix, to, to_len + 1); + strscpy(buf + prefix + to_len, p + from_len, total - prefix - to_len); + + return buf; +} + +/** + * icssg_mode_firmware_names - Generate firmware names for a specific mode + * @dev: device pointer for logging and context + * @src: source array of firmware name structures + * @dst: destination array to store updated firmware name structures + * @from: substring in firmware names to be replaced + * @to: substring to replace @from in firmware names + * + * Iterates over all MACs and replaces occurrences of the @from substring + * with @to in the firmware names (pru, rtu, txpru) for each MAC. The + * updated firmware names are stored in the @dst array. + */ +static void icssg_mode_firmware_names(struct device *dev, + struct icssg_firmwares *src, + struct icssg_firmwares *dst, + const char *from, const char *to) +{ + int i; + + for (i = 0; i < PRUETH_NUM_MACS; i++) { + dst[i].pru = icssg_firmware_name_replace(dev, src[i].pru, + from, to); + dst[i].rtu = icssg_firmware_name_replace(dev, src[i].rtu, + from, to); + dst[i].txpru = icssg_firmware_name_replace(dev, src[i].txpru, + from, to); + } +} + static int prueth_probe(struct platform_device *pdev) { struct device_node *eth_node, *eth_ports_node; @@ -1808,6 +1850,15 @@ static int prueth_probe(struct platform_device *pdev) icss_iep_init_fw(prueth->iep1); } + /* Read EMAC firmware names from device tree */ + icssg_read_firmware_names(np, prueth->icssg_emac_firmwares); + + /* Generate other mode firmware names based on EMAC firmware names */ + icssg_mode_firmware_names(dev, prueth->icssg_emac_firmwares, + prueth->icssg_switch_firmwares, "eth", "sw"); + icssg_mode_firmware_names(dev, prueth->icssg_emac_firmwares, + prueth->icssg_hsr_firmwares, "eth", "hsr"); + spin_lock_init(&prueth->vtbl_lock); spin_lock_init(&prueth->stats_lock); /* setup netdev interfaces */ diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index 23c465f1ce7f..c03e3b3626c1 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -259,9 +259,9 @@ struct prueth_pdata { }; struct icssg_firmwares { - char *pru; - char *rtu; - char *txpru; + const char *pru; + const char *rtu; + const char *txpru; }; /** @@ -300,6 +300,9 @@ struct icssg_firmwares { * @is_switchmode_supported: indicates platform support for switch mode * @switch_id: ID for mapping switch ports to bridge * @default_vlan: Default VLAN for host + * @icssg_emac_firmwares: Firmware names for EMAC mode, indexed per MAC + * @icssg_switch_firmwares: Firmware names for SWITCH mode, indexed per MAC + * @icssg_hsr_firmwares: Firmware names for HSR mode, indexed per MAC */ struct prueth { struct device *dev; @@ -343,6 +346,9 @@ struct prueth { spinlock_t vtbl_lock; /** @stats_lock: Lock for reading icssg stats */ spinlock_t stats_lock; + struct icssg_firmwares icssg_emac_firmwares[PRUETH_NUM_MACS]; + struct icssg_firmwares icssg_switch_firmwares[PRUETH_NUM_MACS]; + struct icssg_firmwares icssg_hsr_firmwares[PRUETH_NUM_MACS]; }; struct emac_tx_ts_response { diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index ffc15a432689..54384f9b3872 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -41,6 +41,7 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); /* per-network namespace private data for this module */ struct geneve_net { struct list_head geneve_list; + /* sock_list is protected by rtnl lock */ struct list_head sock_list; }; @@ -921,8 +922,8 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, udp_tunnel_xmit_skb(rt, gs4->sock->sk, skb, saddr, info->key.u.ipv4.dst, tos, ttl, df, sport, geneve->cfg.info.key.tp_dst, !net_eq(geneve->net, dev_net(geneve->dev)), - !test_bit(IP_TUNNEL_CSUM_BIT, - info->key.tun_flags)); + !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags), + 0); return 0; } @@ -1014,7 +1015,8 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, &saddr, &key->u.ipv6.dst, prio, ttl, info->key.label, sport, geneve->cfg.info.key.tp_dst, !test_bit(IP_TUNNEL_CSUM_BIT, - info->key.tun_flags)); + info->key.tun_flags), + 0); return 0; } #endif @@ -1179,8 +1181,9 @@ static void geneve_offload_rx_ports(struct net_device *dev, bool push) struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_sock *gs; - rcu_read_lock(); - list_for_each_entry_rcu(gs, &gn->sock_list, list) { + ASSERT_RTNL(); + + list_for_each_entry(gs, &gn->sock_list, list) { if (push) { udp_tunnel_push_rx_port(dev, gs->sock, UDP_TUNNEL_TYPE_GENEVE); @@ -1189,7 +1192,6 @@ static void geneve_offload_rx_ports(struct net_device *dev, bool push) UDP_TUNNEL_TYPE_GENEVE); } } - rcu_read_unlock(); } /* Initialize the device structure. */ diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index d4dec741c7f4..4b668ebaa0f7 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -446,7 +446,8 @@ static int gtp0_send_echo_resp_ip(struct gtp_dev *gtp, struct sk_buff *skb) htons(GTP0_PORT), htons(GTP0_PORT), !net_eq(sock_net(gtp->sk1u), dev_net(gtp->dev)), - false); + false, + 0); return 0; } @@ -704,7 +705,8 @@ static int gtp1u_send_echo_resp(struct gtp_dev *gtp, struct sk_buff *skb) htons(GTP1U_PORT), htons(GTP1U_PORT), !net_eq(sock_net(gtp->sk1u), dev_net(gtp->dev)), - false); + false, + 0); return 0; } @@ -1304,7 +1306,7 @@ static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev) pktinfo.gtph_port, pktinfo.gtph_port, !net_eq(sock_net(pktinfo.pctx->sk), dev_net(dev)), - false); + false, 0); break; case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) @@ -1314,7 +1316,7 @@ static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev) ip6_dst_hoplimit(&pktinfo.rt->dst), 0, pktinfo.gtph_port, pktinfo.gtph_port, - false); + false, 0); #else goto tx_err; #endif @@ -2405,7 +2407,7 @@ static int gtp_genl_send_echo_req(struct sk_buff *skb, struct genl_info *info) port, port, !net_eq(sock_net(sk), dev_net(gtp->dev)), - false); + false, 0); return 0; } diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c index aea0f0357568..9b41d4697a40 100644 --- a/drivers/net/mdio/fwnode_mdio.c +++ b/drivers/net/mdio/fwnode_mdio.c @@ -18,7 +18,8 @@ MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("FWNODE MDIO bus (Ethernet PHY) accessors"); static struct pse_control * -fwnode_find_pse_control(struct fwnode_handle *fwnode) +fwnode_find_pse_control(struct fwnode_handle *fwnode, + struct phy_device *phydev) { struct pse_control *psec; struct device_node *np; @@ -30,7 +31,7 @@ fwnode_find_pse_control(struct fwnode_handle *fwnode) if (!np) return NULL; - psec = of_pse_control_get(np); + psec = of_pse_control_get(np, phydev); if (PTR_ERR(psec) == -ENOENT) return NULL; @@ -128,15 +129,9 @@ int fwnode_mdiobus_register_phy(struct mii_bus *bus, u32 phy_id; int rc; - psec = fwnode_find_pse_control(child); - if (IS_ERR(psec)) - return PTR_ERR(psec); - mii_ts = fwnode_find_mii_timestamper(child); - if (IS_ERR(mii_ts)) { - rc = PTR_ERR(mii_ts); - goto clean_pse; - } + if (IS_ERR(mii_ts)) + return PTR_ERR(mii_ts); is_c45 = fwnode_device_is_compatible(child, "ethernet-phy-ieee802.3-c45"); if (is_c45 || fwnode_get_phy_id(child, &phy_id)) @@ -169,6 +164,12 @@ int fwnode_mdiobus_register_phy(struct mii_bus *bus, goto clean_phy; } + psec = fwnode_find_pse_control(child, phy); + if (IS_ERR(psec)) { + rc = PTR_ERR(psec); + goto unregister_phy; + } + phy->psec = psec; /* phy->mii_ts may already be defined by the PHY driver. A @@ -180,12 +181,13 @@ int fwnode_mdiobus_register_phy(struct mii_bus *bus, return 0; +unregister_phy: + if (is_acpi_node(child) || is_of_node(child)) + phy_device_remove(phy); clean_phy: phy_device_free(phy); clean_mii_ts: unregister_mii_timestamper(mii_ts); -clean_pse: - pse_control_put(psec); return rc; } diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 1eb678e07dd0..e3722de08ea9 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -113,6 +113,8 @@ enum sysdata_feature { SYSDATA_TASKNAME = BIT(1), /* Kernel release/version as part of sysdata */ SYSDATA_RELEASE = BIT(2), + /* Include a per-target message ID as part of sysdata */ + SYSDATA_MSGID = BIT(3), }; /** @@ -123,6 +125,7 @@ enum sysdata_feature { * @extradata_complete: Cached, formatted string of append * @userdata_length: String length of usedata in extradata_complete. * @sysdata_fields: Sysdata features enabled. + * @msgcounter: Message sent counter. * @stats: Packet send stats for the target. Used for debugging. * @enabled: On / off knob to enable / disable target. * Visible from userspace (read-write). @@ -153,6 +156,8 @@ struct netconsole_target { size_t userdata_length; /* bit-wise with sysdata_feature bits */ u32 sysdata_fields; + /* protected by target_list_lock */ + u32 msgcounter; #endif struct netconsole_target_stats stats; bool enabled; @@ -278,6 +283,23 @@ static void netconsole_process_cleanups_core(void) mutex_unlock(&target_cleanup_list_lock); } +static void netconsole_print_banner(struct netpoll *np) +{ + np_info(np, "local port %d\n", np->local_port); + if (np->ipv6) + np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6); + else + np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip); + np_info(np, "interface name '%s'\n", np->dev_name); + np_info(np, "local ethernet address '%pM'\n", np->dev_mac); + np_info(np, "remote port %d\n", np->remote_port); + if (np->ipv6) + np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6); + else + np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip); + np_info(np, "remote ethernet address %pM\n", np->remote_mac); +} + #ifdef CONFIG_NETCONSOLE_DYNAMIC /* @@ -487,6 +509,19 @@ static void unregister_netcons_consoles(void) unregister_console(&netconsole); } +static ssize_t sysdata_msgid_enabled_show(struct config_item *item, + char *buf) +{ + struct netconsole_target *nt = to_target(item->ci_parent); + bool msgid_enabled; + + mutex_lock(&dynamic_netconsole_mutex); + msgid_enabled = !!(nt->sysdata_fields & SYSDATA_MSGID); + mutex_unlock(&dynamic_netconsole_mutex); + + return sysfs_emit(buf, "%d\n", msgid_enabled); +} + /* * This one is special -- targets created through the configfs interface * are not enabled (and the corresponding netpoll activated) by default. @@ -534,10 +569,10 @@ static ssize_t enabled_store(struct config_item *item, } /* - * Skip netpoll_parse_options() -- all the attributes are + * Skip netconsole_parser_cmdline() -- all the attributes are * already configured via configfs. Just print them out. */ - netpoll_print_options(&nt->np); + netconsole_print_banner(&nt->np); ret = netpoll_setup(&nt->np); if (ret) @@ -782,6 +817,8 @@ static size_t count_extradata_entries(struct netconsole_target *nt) entries += 1; if (nt->sysdata_fields & SYSDATA_RELEASE) entries += 1; + if (nt->sysdata_fields & SYSDATA_MSGID) + entries += 1; return entries; } @@ -918,6 +955,40 @@ static void disable_sysdata_feature(struct netconsole_target *nt, nt->extradata_complete[nt->userdata_length] = 0; } +static ssize_t sysdata_msgid_enabled_store(struct config_item *item, + const char *buf, size_t count) +{ + struct netconsole_target *nt = to_target(item->ci_parent); + bool msgid_enabled, curr; + ssize_t ret; + + ret = kstrtobool(buf, &msgid_enabled); + if (ret) + return ret; + + mutex_lock(&dynamic_netconsole_mutex); + curr = !!(nt->sysdata_fields & SYSDATA_MSGID); + if (msgid_enabled == curr) + goto unlock_ok; + + if (msgid_enabled && + count_extradata_entries(nt) >= MAX_EXTRADATA_ITEMS) { + ret = -ENOSPC; + goto unlock; + } + + if (msgid_enabled) + nt->sysdata_fields |= SYSDATA_MSGID; + else + disable_sysdata_feature(nt, SYSDATA_MSGID); + +unlock_ok: + ret = strnlen(buf, count); +unlock: + mutex_unlock(&dynamic_netconsole_mutex); + return ret; +} + static ssize_t sysdata_release_enabled_store(struct config_item *item, const char *buf, size_t count) { @@ -1033,6 +1104,7 @@ CONFIGFS_ATTR(userdatum_, value); CONFIGFS_ATTR(sysdata_, cpu_nr_enabled); CONFIGFS_ATTR(sysdata_, taskname_enabled); CONFIGFS_ATTR(sysdata_, release_enabled); +CONFIGFS_ATTR(sysdata_, msgid_enabled); static struct configfs_attribute *userdatum_attrs[] = { &userdatum_attr_value, @@ -1095,6 +1167,7 @@ static struct configfs_attribute *userdata_attrs[] = { &sysdata_attr_cpu_nr_enabled, &sysdata_attr_taskname_enabled, &sysdata_attr_release_enabled, + &sysdata_attr_msgid_enabled, NULL, }; @@ -1292,6 +1365,14 @@ static int sysdata_append_release(struct netconsole_target *nt, int offset) init_utsname()->release); } +static int sysdata_append_msgid(struct netconsole_target *nt, int offset) +{ + wrapping_assign_add(nt->msgcounter, 1); + return scnprintf(&nt->extradata_complete[offset], + MAX_EXTRADATA_ENTRY_LEN, " msgid=%u\n", + nt->msgcounter); +} + /* * prepare_extradata - append sysdata at extradata_complete in runtime * @nt: target to send message to @@ -1314,6 +1395,8 @@ static int prepare_extradata(struct netconsole_target *nt) extradata_len += sysdata_append_taskname(nt, extradata_len); if (nt->sysdata_fields & SYSDATA_RELEASE) extradata_len += sysdata_append_release(nt, extradata_len); + if (nt->sysdata_fields & SYSDATA_MSGID) + extradata_len += sysdata_append_msgid(nt, extradata_len); WARN_ON_ONCE(extradata_len > MAX_EXTRADATA_ENTRY_LEN * MAX_EXTRADATA_ITEMS); @@ -1659,6 +1742,120 @@ static void write_msg(struct console *con, const char *msg, unsigned int len) spin_unlock_irqrestore(&target_list_lock, flags); } +static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr) +{ + const char *end; + + if (!strchr(str, ':') && + in4_pton(str, -1, (void *)addr, -1, &end) > 0) { + if (!*end) + return 0; + } + if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) { +#if IS_ENABLED(CONFIG_IPV6) + if (!*end) + return 1; +#else + return -1; +#endif + } + return -1; +} + +static int netconsole_parser_cmdline(struct netpoll *np, char *opt) +{ + bool ipversion_set = false; + char *cur = opt; + char *delim; + int ipv6; + + if (*cur != '@') { + delim = strchr(cur, '@'); + if (!delim) + goto parse_failed; + *delim = 0; + if (kstrtou16(cur, 10, &np->local_port)) + goto parse_failed; + cur = delim; + } + cur++; + + if (*cur != '/') { + ipversion_set = true; + delim = strchr(cur, '/'); + if (!delim) + goto parse_failed; + *delim = 0; + ipv6 = netpoll_parse_ip_addr(cur, &np->local_ip); + if (ipv6 < 0) + goto parse_failed; + else + np->ipv6 = (bool)ipv6; + cur = delim; + } + cur++; + + if (*cur != ',') { + /* parse out dev_name or dev_mac */ + delim = strchr(cur, ','); + if (!delim) + goto parse_failed; + *delim = 0; + + np->dev_name[0] = '\0'; + eth_broadcast_addr(np->dev_mac); + if (!strchr(cur, ':')) + strscpy(np->dev_name, cur, sizeof(np->dev_name)); + else if (!mac_pton(cur, np->dev_mac)) + goto parse_failed; + + cur = delim; + } + cur++; + + if (*cur != '@') { + /* dst port */ + delim = strchr(cur, '@'); + if (!delim) + goto parse_failed; + *delim = 0; + if (*cur == ' ' || *cur == '\t') + np_info(np, "warning: whitespace is not allowed\n"); + if (kstrtou16(cur, 10, &np->remote_port)) + goto parse_failed; + cur = delim; + } + cur++; + + /* dst ip */ + delim = strchr(cur, '/'); + if (!delim) + goto parse_failed; + *delim = 0; + ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip); + if (ipv6 < 0) + goto parse_failed; + else if (ipversion_set && np->ipv6 != (bool)ipv6) + goto parse_failed; + else + np->ipv6 = (bool)ipv6; + cur = delim + 1; + + if (*cur != 0) { + /* MAC address */ + if (!mac_pton(cur, np->remote_mac)) + goto parse_failed; + } + + netconsole_print_banner(np); + + return 0; + + parse_failed: + np_info(np, "couldn't parse config at '%s'!\n", cur); + return -1; +} + /* Allocate new target (from boot/module param) and setup netpoll for it */ static struct netconsole_target *alloc_param_target(char *target_config, int cmdline_count) @@ -1688,7 +1885,7 @@ static struct netconsole_target *alloc_param_target(char *target_config, } /* Parse parameters and setup netpoll */ - err = netpoll_parse_options(&nt->np, target_config); + err = netconsole_parser_cmdline(&nt->np, target_config); if (err) goto fail; diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index d04401f0bdf7..511ed72a93ce 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -131,7 +131,6 @@ struct netdevsim { struct nsim_macsec macsec; struct { u32 inject_error; - u32 sleep; u32 __ports[2][NSIM_UDP_TUNNEL_N_PORTS]; u32 (*ports)[NSIM_UDP_TUNNEL_N_PORTS]; struct dentry *ddir; @@ -342,7 +341,6 @@ struct nsim_dev { bool ipv4_only; bool shared; bool static_iana_vxlan; - u32 sleep; } udp_ports; struct nsim_dev_psample *psample; u16 esw_mode; diff --git a/drivers/net/netdevsim/udp_tunnels.c b/drivers/net/netdevsim/udp_tunnels.c index 640b4983a9a0..89fff76e51cf 100644 --- a/drivers/net/netdevsim/udp_tunnels.c +++ b/drivers/net/netdevsim/udp_tunnels.c @@ -18,9 +18,6 @@ nsim_udp_tunnel_set_port(struct net_device *dev, unsigned int table, ret = -ns->udp_ports.inject_error; ns->udp_ports.inject_error = 0; - if (ns->udp_ports.sleep) - msleep(ns->udp_ports.sleep); - if (!ret) { if (ns->udp_ports.ports[table][entry]) { WARN(1, "entry already in use\n"); @@ -47,8 +44,6 @@ nsim_udp_tunnel_unset_port(struct net_device *dev, unsigned int table, ret = -ns->udp_ports.inject_error; ns->udp_ports.inject_error = 0; - if (ns->udp_ports.sleep) - msleep(ns->udp_ports.sleep); if (!ret) { u32 val = be16_to_cpu(ti->port) << 16 | ti->type; @@ -112,12 +107,10 @@ 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); - rtnl_lock(); if (dev->reg_state == NETREG_REGISTERED) { memset(ns->udp_ports.ports, 0, sizeof(ns->udp_ports.__ports)); udp_tunnel_nic_reset_ntf(dev); } - rtnl_unlock(); return count; } @@ -172,7 +165,6 @@ int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev, GFP_KERNEL); if (!info) return -ENOMEM; - ns->udp_ports.sleep = nsim_dev->udp_ports.sleep; if (nsim_dev->udp_ports.sync_all) { info->set_port = NULL; @@ -181,8 +173,6 @@ int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev, info->sync_table = NULL; } - if (ns->udp_ports.sleep) - info->flags |= UDP_TUNNEL_NIC_INFO_MAY_SLEEP; if (nsim_dev->udp_ports.open_only) info->flags |= UDP_TUNNEL_NIC_INFO_OPEN_ONLY; if (nsim_dev->udp_ports.ipv4_only) @@ -217,6 +207,4 @@ void nsim_udp_tunnels_debugfs_create(struct nsim_dev *nsim_dev) &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/ovpn/udp.c b/drivers/net/ovpn/udp.c index bff00946eae2..254cc94c4617 100644 --- a/drivers/net/ovpn/udp.c +++ b/drivers/net/ovpn/udp.c @@ -199,7 +199,7 @@ static int ovpn_udp4_output(struct ovpn_peer *peer, struct ovpn_bind *bind, transmit: udp_tunnel_xmit_skb(rt, sk, skb, fl.saddr, fl.daddr, 0, ip4_dst_hoplimit(&rt->dst), 0, fl.fl4_sport, - fl.fl4_dport, false, sk->sk_no_check_tx); + fl.fl4_dport, false, sk->sk_no_check_tx, 0); ret = 0; err: local_bh_enable(); @@ -274,7 +274,7 @@ transmit: skb->ignore_df = 1; udp_tunnel6_xmit_skb(dst, sk, skb, skb->dev, &fl.saddr, &fl.daddr, 0, ip6_dst_hoplimit(dst), 0, fl.fl6_sport, - fl.fl6_dport, udp_get_no_check6_tx(sk)); + fl.fl6_dport, udp_get_no_check6_tx(sk), 0); ret = 0; err: local_bh_enable(); diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 53dad2482026..28acc6392cfc 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -25,6 +25,9 @@ if PHYLIB config SWPHY bool +config PHY_PACKAGE + tristate + config LED_TRIGGER_PHY bool "Support LED triggers for tracking link state" depends on LEDS_TRIGGERS @@ -157,6 +160,7 @@ config BCM54140_PHY tristate "Broadcom BCM54140 PHY" depends on HWMON || HWMON=n select BCM_NET_PHYLIB + select PHY_PACKAGE help Support the Broadcom BCM54140 Quad SGMII/QSGMII PHY. @@ -292,6 +296,7 @@ source "drivers/net/phy/mediatek/Kconfig" config MICREL_PHY tristate "Micrel PHYs" depends on PTP_1588_CLOCK_OPTIONAL + select PHY_PACKAGE help Supports the KSZ9021, VSC8201, KS8001 PHYs. @@ -323,6 +328,7 @@ config MICROSEMI_PHY depends on MACSEC || MACSEC=n depends on PTP_1588_CLOCK_OPTIONAL || !NETWORK_PHY_TIMESTAMPING select CRYPTO_LIB_AES if MACSEC + select PHY_PACKAGE help Currently supports VSC8514, VSC8530, VSC8531, VSC8540 and VSC8541 PHYs diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 7827609e9032..b4795aaf9c1c 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -3,7 +3,7 @@ libphy-y := phy.o phy-c45.o phy-core.o phy_device.o \ linkmode.o phy_link_topology.o \ - phy_package.o phy_caps.o mdio_bus_provider.o + phy_caps.o mdio_bus_provider.o mdio-bus-y += mdio_bus.o mdio_device.o ifdef CONFIG_PHYLIB @@ -19,6 +19,7 @@ obj-$(CONFIG_MDIO_BUS) += mdio-bus.o obj-$(CONFIG_PHYLINK) += phylink.o obj-$(CONFIG_PHYLIB) += libphy.o obj-$(CONFIG_PHYLIB) += mdio_devres.o +obj-$(CONFIG_PHY_PACKAGE) += phy_package.o obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += mii_timestamper.o diff --git a/drivers/net/phy/dp83tg720.c b/drivers/net/phy/dp83tg720.c index 7e76323409c4..391c1d868808 100644 --- a/drivers/net/phy/dp83tg720.c +++ b/drivers/net/phy/dp83tg720.c @@ -13,21 +13,92 @@ #include "open_alliance_helpers.h" /* + * DP83TG720 PHY Limitations and Workarounds + * + * The DP83TG720 1000BASE-T1 PHY has several limitations that require + * software-side mitigations. These workarounds are implemented throughout + * this driver. This section documents the known issues and their corresponding + * mitigation strategies. + * + * 1. Unreliable Link Detection and Synchronized Reset Deadlock + * ------------------------------------------------------------ + * After a link loss or during link establishment, the DP83TG720 PHY may fail + * to detect or report link status correctly. As of June 2025, no public + * errata sheet for the DP83TG720 PHY documents this behavior. + * The "DP83TC81x, DP83TG72x Software Implementation Guide" application note + * (SNLA404, available at https://www.ti.com/lit/an/snla404/snla404.pdf) + * recommends performing a soft restart if polling for a link fails to establish + * a connection after 100ms. This procedure is adopted as the workaround for the + * observed link detection issue. + * + * However, in point-to-point setups where both link partners use the same + * driver (e.g. Linux on both sides), a synchronized reset pattern may emerge. + * This leads to a deadlock, where both PHYs reset at the same time and + * continuously miss each other during auto-negotiation. + * + * To address this, the reset procedure includes two components: + * + * - A **fixed minimum delay of 1ms** after a hardware reset. The datasheet + * "DP83TG720S-Q1 1000BASE-T1 Automotive Ethernet PHY with SGMII and RGMII" + * specifies this as the "Post reset stabilization-time prior to MDC preamble + * for register access" (T6.2), ensuring the PHY is ready for MDIO + * operations. + * + * - An **additional asymmetric delay**, empirically chosen based on + * master/slave role. This reduces the risk of synchronized resets on both + * link partners. Values are selected to avoid periodic overlap and ensure + * the link is re-established within a few cycles. + * + * The functions that implement this logic are: + * - dp83tg720_soft_reset() + * - dp83tg720_get_next_update_time() + * + * 2. Polling-Based Link Detection and IRQ Support + * ----------------------------------------------- + * Due to the PHY-specific limitation described in section 1, link-up events + * cannot be reliably detected via interrupts on the DP83TG720. Therefore, + * polling is required to detect transitions from link-down to link-up. + * + * While link-down events *can* be detected via IRQs on this PHY, this driver + * currently does **not** implement interrupt support. As a result, all link + * state changes must be detected using polling. + * + * Polling behavior: + * - When the link is up: slow polling (e.g. 1s). + * - When the link just went down: fast polling for a short time. + * - When the link stays down: fallback to slow polling. + * + * This design balances responsiveness and CPU usage. It sacrifices fast link-up + * times in cases where the link is expected to remain down for extended periods, + * assuming that such systems do not require immediate reactivity. + */ + +/* * DP83TG720S_POLL_ACTIVE_LINK - Polling interval in milliseconds when the link * is active. - * DP83TG720S_POLL_NO_LINK_MIN - Minimum polling interval in milliseconds when - * the link is down. - * DP83TG720S_POLL_NO_LINK_MAX - Maximum polling interval in milliseconds when - * the link is down. + * DP83TG720S_POLL_NO_LINK - Polling interval in milliseconds when the + * link is down. + * DP83TG720S_FAST_POLL_DURATION_MS - Timeout in milliseconds for no-link + * polling after which polling interval is + * increased. + * DP83TG720S_POLL_SLOW - Slow polling interval when there is no + * link for a prolongued period. + * DP83TG720S_RESET_DELAY_MS_MASTER - Delay after a reset before attempting + * to establish a link again for master phy. + * DP83TG720S_RESET_DELAY_MS_SLAVE - Delay after a reset before attempting + * to establish a link again for slave phy. * * These values are not documented or officially recommended by the vendor but * were determined through empirical testing. They achieve a good balance in * minimizing the number of reset retries while ensuring reliable link recovery * within a reasonable timeframe. */ -#define DP83TG720S_POLL_ACTIVE_LINK 1000 -#define DP83TG720S_POLL_NO_LINK_MIN 100 -#define DP83TG720S_POLL_NO_LINK_MAX 1000 +#define DP83TG720S_POLL_ACTIVE_LINK 421 +#define DP83TG720S_POLL_NO_LINK 149 +#define DP83TG720S_FAST_POLL_DURATION_MS 6000 +#define DP83TG720S_POLL_SLOW 1117 +#define DP83TG720S_RESET_DELAY_MS_MASTER 97 +#define DP83TG720S_RESET_DELAY_MS_SLAVE 149 #define DP83TG720S_PHY_ID 0x2000a284 @@ -124,6 +195,7 @@ struct dp83tg720_stats { struct dp83tg720_priv { struct dp83tg720_stats stats; + unsigned long last_link_down_jiffies; }; /** @@ -201,6 +273,26 @@ static int dp83tg720_update_stats(struct phy_device *phydev) return 0; } +static int dp83tg720_soft_reset(struct phy_device *phydev) +{ + int ret; + + ret = phy_write(phydev, DP83TG720S_PHY_RESET, DP83TG720S_HW_RESET); + if (ret) + return ret; + + /* Include mandatory MDC-access delay (1ms) + extra asymmetric delay to + * avoid synchronized reset deadlock. See section 1 in the top-of-file + * comment block. + */ + if (phydev->master_slave_state == MASTER_SLAVE_STATE_SLAVE) + msleep(DP83TG720S_RESET_DELAY_MS_SLAVE); + else + msleep(DP83TG720S_RESET_DELAY_MS_MASTER); + + return ret; +} + static void dp83tg720_get_link_stats(struct phy_device *phydev, struct ethtool_link_ext_stats *link_stats) { @@ -382,21 +474,11 @@ static int dp83tg720_read_status(struct phy_device *phydev) /* According to the "DP83TC81x, DP83TG72x Software * Implementation Guide", the PHY needs to be reset after a * link loss or if no link is created after at least 100ms. - * - * Currently we are polling with the PHY_STATE_TIME (1000ms) - * interval, which is still enough for not automotive use cases. */ ret = phy_init_hw(phydev); if (ret) return ret; - /* Sleep 600ms for PHY stabilization post-reset. - * Empirically chosen value (not documented). - * Helps reduce reset bounces with link partners having similar - * issues. - */ - msleep(600); - /* After HW reset we need to restore master/slave configuration. * genphy_c45_pma_baset1_read_master_slave() call will be done * by the dp83tg720_config_aneg() function. @@ -477,19 +559,11 @@ static int dp83tg720_config_init(struct phy_device *phydev) { int ret; - /* Software Restart is not enough to recover from a link failure. - * Using Hardware Reset instead. - */ - ret = phy_write(phydev, DP83TG720S_PHY_RESET, DP83TG720S_HW_RESET); + /* Reset the PHY to recover from a link failure */ + ret = dp83tg720_soft_reset(phydev); if (ret) return ret; - /* Wait until MDC can be used again. - * The wait value of one 1ms is documented in "DP83TG720S-Q1 1000BASE-T1 - * Automotive Ethernet PHY with SGMII and RGMII" datasheet. - */ - usleep_range(1000, 2000); - if (phy_interface_is_rgmii(phydev)) { ret = dp83tg720_config_rgmii_delay(phydev); if (ret) @@ -525,50 +599,42 @@ static int dp83tg720_probe(struct phy_device *phydev) } /** - * dp83tg720_get_next_update_time - Determine the next update time for PHY - * state + * dp83tg720_get_next_update_time - Return next polling interval for PHY state * @phydev: Pointer to the phy_device structure * - * This function addresses a limitation of the DP83TG720 PHY, which cannot - * reliably detect or report a stable link state. To recover from such - * scenarios, the PHY must be periodically reset when the link is down. However, - * if the link partner also runs Linux with the same driver, synchronized reset - * intervals can lead to a deadlock where the link never establishes due to - * simultaneous resets on both sides. - * - * To avoid this, the function implements randomized polling intervals when the - * link is down. It ensures that reset intervals are desynchronized by - * introducing a random delay between a configured minimum and maximum range. - * When the link is up, a fixed polling interval is used to minimize overhead. - * - * This mechanism guarantees that the link will reestablish within 10 seconds - * in the worst-case scenario. + * Implements adaptive polling interval logic depending on link state and + * downtime duration. See the "2. Polling-Based Link Detection and IRQ Support" + * section at the top of this file for details. * - * Return: Time (in jiffies) until the next update event for the PHY state - * machine. + * Return: Time (in jiffies) until the next poll */ static unsigned int dp83tg720_get_next_update_time(struct phy_device *phydev) { + struct dp83tg720_priv *priv = phydev->priv; unsigned int next_time_jiffies; if (phydev->link) { - /* When the link is up, use a fixed 1000ms interval - * (in jiffies) - */ + priv->last_link_down_jiffies = 0; + + /* When the link is up, use a slower interval (in jiffies) */ next_time_jiffies = msecs_to_jiffies(DP83TG720S_POLL_ACTIVE_LINK); } else { - unsigned int min_jiffies, max_jiffies, rand_jiffies; - - /* When the link is down, randomize interval between min/max - * (in jiffies) - */ - min_jiffies = msecs_to_jiffies(DP83TG720S_POLL_NO_LINK_MIN); - max_jiffies = msecs_to_jiffies(DP83TG720S_POLL_NO_LINK_MAX); - - rand_jiffies = min_jiffies + - get_random_u32_below(max_jiffies - min_jiffies + 1); - next_time_jiffies = rand_jiffies; + unsigned long now = jiffies; + + if (!priv->last_link_down_jiffies) + priv->last_link_down_jiffies = now; + + if (time_before(now, priv->last_link_down_jiffies + + msecs_to_jiffies(DP83TG720S_FAST_POLL_DURATION_MS))) { + /* Link recently went down: fast polling */ + next_time_jiffies = + msecs_to_jiffies(DP83TG720S_POLL_NO_LINK); + } else { + /* Link has been down for a while: slow polling */ + next_time_jiffies = + msecs_to_jiffies(DP83TG720S_POLL_SLOW); + } } /* Ensure the polling time is at least one jiffy */ @@ -582,6 +648,7 @@ static struct phy_driver dp83tg720_driver[] = { .flags = PHY_POLL_CABLE_TEST, .probe = dp83tg720_probe, + .soft_reset = dp83tg720_soft_reset, .config_aneg = dp83tg720_config_aneg, .read_status = dp83tg720_read_status, .get_features = genphy_c45_pma_read_ext_abilities, diff --git a/drivers/net/phy/mdio-boardinfo.c b/drivers/net/phy/mdio-boardinfo.c index 2de679a68115..d3184e8f12ec 100644 --- a/drivers/net/phy/mdio-boardinfo.c +++ b/drivers/net/phy/mdio-boardinfo.c @@ -3,17 +3,23 @@ * mdio-boardinfo - Collect pre-declarations for MDIO devices */ -#include <linux/kernel.h> -#include <linux/slab.h> #include <linux/export.h> -#include <linux/mutex.h> +#include <linux/kernel.h> #include <linux/list.h> +#include <linux/mutex.h> +#include <linux/phy.h> +#include <linux/slab.h> #include "mdio-boardinfo.h" static LIST_HEAD(mdio_board_list); static DEFINE_MUTEX(mdio_board_lock); +struct mdio_board_entry { + struct list_head list; + struct mdio_board_info board_info; +}; + /** * mdiobus_setup_mdiodev_from_board_info - create and setup MDIO devices * from pre-collected board specific MDIO information @@ -26,24 +32,18 @@ void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus, (struct mii_bus *bus, struct mdio_board_info *bi)) { - struct mdio_board_entry *be; - struct mdio_board_entry *tmp; - struct mdio_board_info *bi; - int ret; + struct mdio_board_entry *be, *tmp; mutex_lock(&mdio_board_lock); list_for_each_entry_safe(be, tmp, &mdio_board_list, list) { - bi = &be->board_info; + struct mdio_board_info *bi = &be->board_info; if (strcmp(bus->id, bi->bus_id)) continue; mutex_unlock(&mdio_board_lock); - ret = cb(bus, bi); + cb(bus, bi); mutex_lock(&mdio_board_lock); - if (ret) - continue; - } mutex_unlock(&mdio_board_lock); } @@ -62,14 +62,13 @@ int mdiobus_register_board_info(const struct mdio_board_info *info, unsigned int n) { struct mdio_board_entry *be; - unsigned int i; be = kcalloc(n, sizeof(*be), GFP_KERNEL); if (!be) return -ENOMEM; - for (i = 0; i < n; i++, be++, info++) { - memcpy(&be->board_info, info, sizeof(*info)); + for (int i = 0; i < n; i++, be++) { + be->board_info = info[i]; mutex_lock(&mdio_board_lock); list_add_tail(&be->list, &mdio_board_list); mutex_unlock(&mdio_board_lock); diff --git a/drivers/net/phy/mdio-boardinfo.h b/drivers/net/phy/mdio-boardinfo.h index 773bb51399be..0878b77878d4 100644 --- a/drivers/net/phy/mdio-boardinfo.h +++ b/drivers/net/phy/mdio-boardinfo.h @@ -7,13 +7,8 @@ #ifndef __MDIO_BOARD_INFO_H #define __MDIO_BOARD_INFO_H -#include <linux/phy.h> -#include <linux/mutex.h> - -struct mdio_board_entry { - struct list_head list; - struct mdio_board_info board_info; -}; +struct mii_bus; +struct mdio_board_info; void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus, int (*cb) diff --git a/drivers/net/phy/mediatek/Kconfig b/drivers/net/phy/mediatek/Kconfig index 9f30a91be8dd..bb7dc876271e 100644 --- a/drivers/net/phy/mediatek/Kconfig +++ b/drivers/net/phy/mediatek/Kconfig @@ -27,6 +27,7 @@ config MEDIATEK_GE_SOC_PHY depends on ARCH_AIROHA || (ARCH_MEDIATEK && NVMEM_MTK_EFUSE) || \ COMPILE_TEST select MTK_NET_PHYLIB + select PHY_PACKAGE help Supports MediaTek SoC built-in Gigabit Ethernet PHYs. diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index e177037f9110..27f1833563ab 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -375,8 +375,8 @@ static void mmd_phy_indirect(struct mii_bus *bus, int phy_addr, int devad, devad | MII_MMD_CTRL_NOINCR); } -static int mmd_phy_read(struct mii_bus *bus, int phy_addr, bool is_c45, - int devad, u32 regnum) +int mmd_phy_read(struct mii_bus *bus, int phy_addr, bool is_c45, + int devad, u32 regnum) { if (is_c45) return __mdiobus_c45_read(bus, phy_addr, devad, regnum); @@ -385,9 +385,10 @@ static int mmd_phy_read(struct mii_bus *bus, int phy_addr, bool is_c45, /* Read the content of the MMD's selected register */ return __mdiobus_read(bus, phy_addr, MII_MMD_DATA); } +EXPORT_SYMBOL_GPL(mmd_phy_read); -static int mmd_phy_write(struct mii_bus *bus, int phy_addr, bool is_c45, - int devad, u32 regnum, u16 val) +int mmd_phy_write(struct mii_bus *bus, int phy_addr, bool is_c45, + int devad, u32 regnum, u16 val) { if (is_c45) return __mdiobus_c45_write(bus, phy_addr, devad, regnum, val); @@ -396,6 +397,7 @@ static int mmd_phy_write(struct mii_bus *bus, int phy_addr, bool is_c45, /* Write the data into MMD's selected register */ return __mdiobus_write(bus, phy_addr, MII_MMD_DATA, val); } +EXPORT_SYMBOL_GPL(mmd_phy_write); /** * __phy_read_mmd - Convenience function for reading a register @@ -486,71 +488,6 @@ int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) EXPORT_SYMBOL(phy_write_mmd); /** - * __phy_package_read_mmd - read MMD reg relative to PHY package base addr - * @phydev: The phy_device struct - * @addr_offset: The offset to be added to PHY package base_addr - * @devad: The MMD to read from - * @regnum: The register on the MMD to read - * - * Convenience helper for reading a register of an MMD on a given PHY - * using the PHY package base address. The base address is added to - * the addr_offset value. - * - * Same calling rules as for __phy_read(); - * - * NOTE: It's assumed that the entire PHY package is either C22 or C45. - */ -int __phy_package_read_mmd(struct phy_device *phydev, - unsigned int addr_offset, int devad, - u32 regnum) -{ - int addr = phy_package_address(phydev, addr_offset); - - if (addr < 0) - return addr; - - if (regnum > (u16)~0 || devad > 32) - return -EINVAL; - - return mmd_phy_read(phydev->mdio.bus, addr, phydev->is_c45, devad, - regnum); -} -EXPORT_SYMBOL(__phy_package_read_mmd); - -/** - * __phy_package_write_mmd - write MMD reg relative to PHY package base addr - * @phydev: The phy_device struct - * @addr_offset: The offset to be added to PHY package base_addr - * @devad: The MMD to write to - * @regnum: The register on the MMD to write - * @val: value to write to @regnum - * - * Convenience helper for writing a register of an MMD on a given PHY - * using the PHY package base address. The base address is added to - * the addr_offset value. - * - * Same calling rules as for __phy_write(); - * - * NOTE: It's assumed that the entire PHY package is either C22 or C45. - */ -int __phy_package_write_mmd(struct phy_device *phydev, - unsigned int addr_offset, int devad, - u32 regnum, u16 val) -{ - int addr = phy_package_address(phydev, addr_offset); - - if (addr < 0) - return addr; - - if (regnum > (u16)~0 || devad > 32) - return -EINVAL; - - return mmd_phy_write(phydev->mdio.bus, addr, phydev->is_c45, devad, - regnum, val); -} -EXPORT_SYMBOL(__phy_package_write_mmd); - -/** * phy_modify_changed - Function for modifying a PHY register * @phydev: the phy_device struct * @regnum: register number to modify diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 509078344020..90951681523c 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -652,11 +652,119 @@ static struct attribute *phy_dev_attrs[] = { &dev_attr_phy_dev_flags.attr, NULL, }; -ATTRIBUTE_GROUPS(phy_dev); + +static const struct attribute_group phy_dev_group = { + .attrs = phy_dev_attrs, +}; + +#define MMD_DEVICE_ID_ATTR(n) \ +static ssize_t mmd##n##_device_id_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ \ + struct phy_device *phydev = to_phy_device(dev); \ + return sysfs_emit(buf, "0x%.8lx\n", \ + (unsigned long)phydev->c45_ids.device_ids[n]); \ +} \ +static DEVICE_ATTR_RO(mmd##n##_device_id) + +MMD_DEVICE_ID_ATTR(1); +MMD_DEVICE_ID_ATTR(2); +MMD_DEVICE_ID_ATTR(3); +MMD_DEVICE_ID_ATTR(4); +MMD_DEVICE_ID_ATTR(5); +MMD_DEVICE_ID_ATTR(6); +MMD_DEVICE_ID_ATTR(7); +MMD_DEVICE_ID_ATTR(8); +MMD_DEVICE_ID_ATTR(9); +MMD_DEVICE_ID_ATTR(10); +MMD_DEVICE_ID_ATTR(11); +MMD_DEVICE_ID_ATTR(12); +MMD_DEVICE_ID_ATTR(13); +MMD_DEVICE_ID_ATTR(14); +MMD_DEVICE_ID_ATTR(15); +MMD_DEVICE_ID_ATTR(16); +MMD_DEVICE_ID_ATTR(17); +MMD_DEVICE_ID_ATTR(18); +MMD_DEVICE_ID_ATTR(19); +MMD_DEVICE_ID_ATTR(20); +MMD_DEVICE_ID_ATTR(21); +MMD_DEVICE_ID_ATTR(22); +MMD_DEVICE_ID_ATTR(23); +MMD_DEVICE_ID_ATTR(24); +MMD_DEVICE_ID_ATTR(25); +MMD_DEVICE_ID_ATTR(26); +MMD_DEVICE_ID_ATTR(27); +MMD_DEVICE_ID_ATTR(28); +MMD_DEVICE_ID_ATTR(29); +MMD_DEVICE_ID_ATTR(30); +MMD_DEVICE_ID_ATTR(31); + +static struct attribute *phy_mmd_attrs[] = { + &dev_attr_mmd1_device_id.attr, + &dev_attr_mmd2_device_id.attr, + &dev_attr_mmd3_device_id.attr, + &dev_attr_mmd4_device_id.attr, + &dev_attr_mmd5_device_id.attr, + &dev_attr_mmd6_device_id.attr, + &dev_attr_mmd7_device_id.attr, + &dev_attr_mmd8_device_id.attr, + &dev_attr_mmd9_device_id.attr, + &dev_attr_mmd10_device_id.attr, + &dev_attr_mmd11_device_id.attr, + &dev_attr_mmd12_device_id.attr, + &dev_attr_mmd13_device_id.attr, + &dev_attr_mmd14_device_id.attr, + &dev_attr_mmd15_device_id.attr, + &dev_attr_mmd16_device_id.attr, + &dev_attr_mmd17_device_id.attr, + &dev_attr_mmd18_device_id.attr, + &dev_attr_mmd19_device_id.attr, + &dev_attr_mmd20_device_id.attr, + &dev_attr_mmd21_device_id.attr, + &dev_attr_mmd22_device_id.attr, + &dev_attr_mmd23_device_id.attr, + &dev_attr_mmd24_device_id.attr, + &dev_attr_mmd25_device_id.attr, + &dev_attr_mmd26_device_id.attr, + &dev_attr_mmd27_device_id.attr, + &dev_attr_mmd28_device_id.attr, + &dev_attr_mmd29_device_id.attr, + &dev_attr_mmd30_device_id.attr, + &dev_attr_mmd31_device_id.attr, + NULL +}; + +static umode_t phy_mmd_is_visible(struct kobject *kobj, + struct attribute *attr, int index) +{ + struct device *dev = kobj_to_dev(kobj); + struct phy_device *phydev = to_phy_device(dev); + const int i = index + 1; + + if (!phydev->is_c45) + return 0; + if (i >= ARRAY_SIZE(phydev->c45_ids.device_ids) || + phydev->c45_ids.device_ids[i] == 0xffffffff) + return 0; + + return attr->mode; +} + +static const struct attribute_group phy_mmd_group = { + .name = "c45_phy_ids", + .attrs = phy_mmd_attrs, + .is_visible = phy_mmd_is_visible, +}; + +static const struct attribute_group *phy_device_groups[] = { + &phy_dev_group, + &phy_mmd_group, + NULL, +}; static const struct device_type mdio_bus_phy_type = { .name = "PHY", - .groups = phy_dev_groups, + .groups = phy_device_groups, .release = phy_device_release, .pm = pm_ptr(&mdio_bus_phy_pm_ops), }; @@ -1522,7 +1630,6 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, struct mii_bus *bus = phydev->mdio.bus; struct device *d = &phydev->mdio.dev; struct module *ndev_owner = NULL; - bool using_genphy = false; int err; /* For Ethernet device drivers that register their own MDIO bus, we @@ -1548,7 +1655,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, else d->driver = &genphy_driver.mdiodrv.driver; - using_genphy = true; + phydev->is_genphy_driven = 1; } if (!try_module_get(d->driver->owner)) { @@ -1557,7 +1664,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, goto error_put_device; } - if (using_genphy) { + if (phydev->is_genphy_driven) { err = d->driver->probe(d); if (err >= 0) err = device_bind_driver(d); @@ -1627,7 +1734,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, * the generic PHY driver we can't figure it out, thus set the old * legacy PORT_MII value. */ - if (using_genphy) + if (phydev->is_genphy_driven) phydev->port = PORT_MII; /* Initial carrier state is off as the phy is about to be @@ -1666,6 +1773,7 @@ error: error_module_put: module_put(d->driver->owner); + phydev->is_genphy_driven = 0; d->driver = NULL; error_put_device: put_device(d); @@ -1713,36 +1821,6 @@ struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, } EXPORT_SYMBOL(phy_attach); -static bool phy_driver_is_genphy_kind(struct phy_device *phydev, - struct device_driver *driver) -{ - struct device *d = &phydev->mdio.dev; - bool ret = false; - - if (!phydev->drv) - return ret; - - get_device(d); - ret = d->driver == driver; - put_device(d); - - return ret; -} - -bool phy_driver_is_genphy(struct phy_device *phydev) -{ - return phy_driver_is_genphy_kind(phydev, - &genphy_driver.mdiodrv.driver); -} -EXPORT_SYMBOL_GPL(phy_driver_is_genphy); - -bool phy_driver_is_genphy_10g(struct phy_device *phydev) -{ - return phy_driver_is_genphy_kind(phydev, - &genphy_c45_driver.mdiodrv.driver); -} -EXPORT_SYMBOL_GPL(phy_driver_is_genphy_10g); - /** * phy_detach - detach a PHY device from its network device * @phydev: target phy_device struct @@ -1799,9 +1877,10 @@ void phy_detach(struct phy_device *phydev) * from the generic driver so that there's a chance a * real driver could be loaded */ - if (phy_driver_is_genphy(phydev) || - phy_driver_is_genphy_10g(phydev)) + if (phydev->is_genphy_driven) { device_release_driver(&phydev->mdio.dev); + phydev->is_genphy_driven = 0; + } /* Assert the reset signal */ phy_device_reset(phydev, 1); diff --git a/drivers/net/phy/phy_package.c b/drivers/net/phy/phy_package.c index c738f76e8664..3024da0bbf7b 100644 --- a/drivers/net/phy/phy_package.c +++ b/drivers/net/phy/phy_package.c @@ -52,7 +52,8 @@ void *phy_package_get_priv(struct phy_device *phydev) } EXPORT_SYMBOL_GPL(phy_package_get_priv); -int phy_package_address(struct phy_device *phydev, unsigned int addr_offset) +static int phy_package_address(struct phy_device *phydev, + unsigned int addr_offset) { struct phy_package_shared *shared = phydev->shared; u8 base_addr = shared->base_addr; @@ -90,6 +91,71 @@ int __phy_package_write(struct phy_device *phydev, unsigned int addr_offset, } EXPORT_SYMBOL_GPL(__phy_package_write); +/** + * __phy_package_read_mmd - read MMD reg relative to PHY package base addr + * @phydev: The phy_device struct + * @addr_offset: The offset to be added to PHY package base_addr + * @devad: The MMD to read from + * @regnum: The register on the MMD to read + * + * Convenience helper for reading a register of an MMD on a given PHY + * using the PHY package base address. The base address is added to + * the addr_offset value. + * + * Same calling rules as for __phy_read(); + * + * NOTE: It's assumed that the entire PHY package is either C22 or C45. + */ +int __phy_package_read_mmd(struct phy_device *phydev, + unsigned int addr_offset, int devad, + u32 regnum) +{ + int addr = phy_package_address(phydev, addr_offset); + + if (addr < 0) + return addr; + + if (regnum > (u16)~0 || devad > 32) + return -EINVAL; + + return mmd_phy_read(phydev->mdio.bus, addr, phydev->is_c45, devad, + regnum); +} +EXPORT_SYMBOL(__phy_package_read_mmd); + +/** + * __phy_package_write_mmd - write MMD reg relative to PHY package base addr + * @phydev: The phy_device struct + * @addr_offset: The offset to be added to PHY package base_addr + * @devad: The MMD to write to + * @regnum: The register on the MMD to write + * @val: value to write to @regnum + * + * Convenience helper for writing a register of an MMD on a given PHY + * using the PHY package base address. The base address is added to + * the addr_offset value. + * + * Same calling rules as for __phy_write(); + * + * NOTE: It's assumed that the entire PHY package is either C22 or C45. + */ +int __phy_package_write_mmd(struct phy_device *phydev, + unsigned int addr_offset, int devad, + u32 regnum, u16 val) +{ + int addr = phy_package_address(phydev, addr_offset); + + if (addr < 0) + return addr; + + if (regnum > (u16)~0 || devad > 32) + return -EINVAL; + + return mmd_phy_write(phydev->mdio.bus, addr, phydev->is_c45, devad, + regnum, val); +} +EXPORT_SYMBOL(__phy_package_write_mmd); + static bool __phy_package_set_once(struct phy_device *phydev, unsigned int b) { struct phy_package_shared *shared = phydev->shared; @@ -348,3 +414,6 @@ int devm_of_phy_package_join(struct device *dev, struct phy_device *phydev, return ret; } EXPORT_SYMBOL_GPL(devm_of_phy_package_join); + +MODULE_DESCRIPTION("PHY package support"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/phy/phylib-internal.h b/drivers/net/phy/phylib-internal.h index afac2bd15b50..ebda74eb60a5 100644 --- a/drivers/net/phy/phylib-internal.h +++ b/drivers/net/phy/phylib-internal.h @@ -7,6 +7,7 @@ #define __PHYLIB_INTERNAL_H struct phy_device; +struct mii_bus; /* * phy_supported_speeds - return all speeds currently supported by a PHY device @@ -20,7 +21,10 @@ void of_set_phy_timing_role(struct phy_device *phydev); int phy_speed_down_core(struct phy_device *phydev); void phy_check_downshift(struct phy_device *phydev); -int phy_package_address(struct phy_device *phydev, unsigned int addr_offset); +int mmd_phy_read(struct mii_bus *bus, int phy_addr, bool is_c45, + int devad, u32 regnum); +int mmd_phy_write(struct mii_bus *bus, int phy_addr, bool is_c45, + int devad, u32 regnum, u16 val); int genphy_c45_read_eee_adv(struct phy_device *phydev, unsigned long *adv); diff --git a/drivers/net/phy/qcom/Kconfig b/drivers/net/phy/qcom/Kconfig index 570626cc8e14..bba14be8da2f 100644 --- a/drivers/net/phy/qcom/Kconfig +++ b/drivers/net/phy/qcom/Kconfig @@ -24,6 +24,7 @@ config QCA808X_PHY config QCA807X_PHY tristate "Qualcomm QCA807x PHYs" select QCOM_NET_PHYLIB + select PHY_PACKAGE depends on OF_MDIO help Currently supports the Qualcomm QCA8072, QCA8075 and the PSGMII diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c index 1af6b5ead74b..6d10ef7e9a8a 100644 --- a/drivers/net/phy/qcom/qca807x.c +++ b/drivers/net/phy/qcom/qca807x.c @@ -377,7 +377,7 @@ static int qca807x_gpio_get(struct gpio_chip *gc, unsigned int offset) return FIELD_GET(QCA807X_GPIO_FORCE_MODE_MASK, val); } -static void qca807x_gpio_set(struct gpio_chip *gc, unsigned int offset, int value) +static int qca807x_gpio_set(struct gpio_chip *gc, unsigned int offset, int value) { struct qca807x_gpio_priv *priv = gpiochip_get_data(gc); u16 reg; @@ -386,18 +386,19 @@ static void qca807x_gpio_set(struct gpio_chip *gc, unsigned int offset, int valu reg = QCA807X_MMD7_LED_FORCE_CTRL(offset); val = phy_read_mmd(priv->phy, MDIO_MMD_AN, reg); + if (val < 0) + return val; + val &= ~QCA807X_GPIO_FORCE_MODE_MASK; val |= QCA807X_GPIO_FORCE_EN; val |= FIELD_PREP(QCA807X_GPIO_FORCE_MODE_MASK, value); - phy_write_mmd(priv->phy, MDIO_MMD_AN, reg, val); + return phy_write_mmd(priv->phy, MDIO_MMD_AN, reg, val); } static int qca807x_gpio_dir_out(struct gpio_chip *gc, unsigned int offset, int value) { - qca807x_gpio_set(gc, offset, value); - - return 0; + return qca807x_gpio_set(gc, offset, value); } static int qca807x_gpio(struct phy_device *phydev) @@ -425,7 +426,7 @@ static int qca807x_gpio(struct phy_device *phydev) gc->get_direction = qca807x_gpio_get_direction; gc->direction_output = qca807x_gpio_dir_out; gc->get = qca807x_gpio_get; - gc->set = qca807x_gpio_set; + gc->set_rv = qca807x_gpio_set; return devm_gpiochip_add_data(dev, gc, priv); } diff --git a/drivers/net/pse-pd/pd692x0.c b/drivers/net/pse-pd/pd692x0.c index 7d60a714ca53..4de004813560 100644 --- a/drivers/net/pse-pd/pd692x0.c +++ b/drivers/net/pse-pd/pd692x0.c @@ -12,6 +12,8 @@ #include <linux/of.h> #include <linux/platform_device.h> #include <linux/pse-pd/pse.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/machine.h> #define PD692X0_PSE_NAME "pd692x0_pse" @@ -76,6 +78,8 @@ enum { PD692X0_MSG_GET_PORT_CLASS, PD692X0_MSG_GET_PORT_MEAS, PD692X0_MSG_GET_PORT_PARAM, + PD692X0_MSG_GET_POWER_BANK, + PD692X0_MSG_SET_POWER_BANK, /* add new message above here */ PD692X0_MSG_CNT @@ -95,6 +99,8 @@ struct pd692x0_priv { unsigned long last_cmd_key_time; enum ethtool_c33_pse_admin_state admin_state[PD692X0_MAX_PIS]; + struct regulator_dev *manager_reg[PD692X0_MAX_MANAGERS]; + int manager_pw_budget[PD692X0_MAX_MANAGERS]; }; /* Template list of communication messages. The non-null bytes defined here @@ -170,6 +176,16 @@ static const struct pd692x0_msg pd692x0_msg_template_list[PD692X0_MSG_CNT] = { .data = {0x4e, 0x4e, 0x4e, 0x4e, 0x4e, 0x4e, 0x4e, 0x4e}, }, + [PD692X0_MSG_GET_POWER_BANK] = { + .key = PD692X0_KEY_REQ, + .sub = {0x07, 0x0b, 0x57}, + .data = { 0, 0x4e, 0x4e, 0x4e, + 0x4e, 0x4e, 0x4e, 0x4e}, + }, + [PD692X0_MSG_SET_POWER_BANK] = { + .key = PD692X0_KEY_CMD, + .sub = {0x07, 0x0b, 0x57}, + }, }; static u8 pd692x0_build_msg(struct pd692x0_msg *msg, u8 echo) @@ -739,6 +755,29 @@ pd692x0_pi_get_actual_pw(struct pse_controller_dev *pcdev, int id) return (buf.data[0] << 4 | buf.data[1]) * 100; } +static int +pd692x0_pi_get_prio(struct pse_controller_dev *pcdev, int id) +{ + struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); + struct pd692x0_msg msg, buf = {0}; + int ret; + + ret = pd692x0_fw_unavailable(priv); + if (ret) + return ret; + + msg = pd692x0_msg_template_list[PD692X0_MSG_GET_PORT_PARAM]; + msg.sub[2] = id; + ret = pd692x0_sendrecv_msg(priv, &msg, &buf); + if (ret < 0) + return ret; + if (!buf.data[2] || buf.data[2] > pcdev->pis_prio_max + 1) + return -ERANGE; + + /* PSE core priority start at 0 */ + return buf.data[2] - 1; +} + static struct pd692x0_msg_ver pd692x0_get_sw_version(struct pd692x0_priv *priv) { struct device *dev = &priv->client->dev; @@ -766,6 +805,7 @@ static struct pd692x0_msg_ver pd692x0_get_sw_version(struct pd692x0_priv *priv) struct pd692x0_manager { struct device_node *port_node[PD692X0_MAX_MANAGER_PORTS]; + struct device_node *node; int nports; }; @@ -857,6 +897,8 @@ pd692x0_of_get_managers(struct pd692x0_priv *priv, if (ret) goto out; + of_node_get(node); + manager[manager_id].node = node; nmanagers++; } @@ -869,6 +911,8 @@ out: of_node_put(manager[i].port_node[j]); manager[i].port_node[j] = NULL; } + of_node_put(manager[i].node); + manager[i].node = NULL; } of_node_put(node); @@ -876,6 +920,143 @@ out: return ret; } +static const struct regulator_ops dummy_ops; + +static struct regulator_dev * +pd692x0_register_manager_regulator(struct device *dev, char *reg_name, + struct device_node *node) +{ + struct regulator_init_data *rinit_data; + struct regulator_config rconfig = {0}; + struct regulator_desc *rdesc; + struct regulator_dev *rdev; + + rinit_data = devm_kzalloc(dev, sizeof(*rinit_data), + GFP_KERNEL); + if (!rinit_data) + return ERR_PTR(-ENOMEM); + + rdesc = devm_kzalloc(dev, sizeof(*rdesc), GFP_KERNEL); + if (!rdesc) + return ERR_PTR(-ENOMEM); + + rdesc->name = reg_name; + rdesc->type = REGULATOR_VOLTAGE; + rdesc->ops = &dummy_ops; + rdesc->owner = THIS_MODULE; + + rinit_data->supply_regulator = "vmain"; + + rconfig.dev = dev; + rconfig.init_data = rinit_data; + rconfig.of_node = node; + + rdev = devm_regulator_register(dev, rdesc, &rconfig); + if (IS_ERR(rdev)) { + dev_err_probe(dev, PTR_ERR(rdev), + "Failed to register regulator\n"); + return rdev; + } + + return rdev; +} + +static int +pd692x0_register_managers_regulator(struct pd692x0_priv *priv, + const struct pd692x0_manager *manager, + int nmanagers) +{ + struct device *dev = &priv->client->dev; + size_t reg_name_len; + int i; + + /* Each regulator name len is dev name + 12 char + + * int max digit number (10) + 1 + */ + reg_name_len = strlen(dev_name(dev)) + 23; + + for (i = 0; i < nmanagers; i++) { + static const char * const regulators[] = { "vaux5", "vaux3p3" }; + struct regulator_dev *rdev; + char *reg_name; + int ret; + + reg_name = devm_kzalloc(dev, reg_name_len, GFP_KERNEL); + if (!reg_name) + return -ENOMEM; + snprintf(reg_name, 26, "pse-%s-manager%d", dev_name(dev), i); + rdev = pd692x0_register_manager_regulator(dev, reg_name, + manager[i].node); + if (IS_ERR(rdev)) + return PTR_ERR(rdev); + + /* VMAIN is described as main supply for the manager. + * Add other VAUX power supplies and link them to the + * virtual device rdev->dev. + */ + ret = devm_regulator_bulk_get_enable(&rdev->dev, + ARRAY_SIZE(regulators), + regulators); + if (ret) + return dev_err_probe(&rdev->dev, ret, + "Failed to enable regulators\n"); + + priv->manager_reg[i] = rdev; + } + + return 0; +} + +static int +pd692x0_conf_manager_power_budget(struct pd692x0_priv *priv, int id, int pw) +{ + struct pd692x0_msg msg, buf; + int ret, pw_mW = pw / 1000; + + msg = pd692x0_msg_template_list[PD692X0_MSG_GET_POWER_BANK]; + msg.data[0] = id; + ret = pd692x0_sendrecv_msg(priv, &msg, &buf); + if (ret < 0) + return ret; + + msg = pd692x0_msg_template_list[PD692X0_MSG_SET_POWER_BANK]; + msg.data[0] = id; + msg.data[1] = pw_mW >> 8; + msg.data[2] = pw_mW & 0xff; + msg.data[3] = buf.sub[2]; + msg.data[4] = buf.data[0]; + msg.data[5] = buf.data[1]; + msg.data[6] = buf.data[2]; + msg.data[7] = buf.data[3]; + return pd692x0_sendrecv_msg(priv, &msg, &buf); +} + +static int +pd692x0_configure_managers(struct pd692x0_priv *priv, int nmanagers) +{ + int i, ret; + + for (i = 0; i < nmanagers; i++) { + struct regulator *supply = priv->manager_reg[i]->supply; + int pw_budget; + + pw_budget = regulator_get_unclaimed_power_budget(supply); + /* Max power budget per manager */ + if (pw_budget > 6000000) + pw_budget = 6000000; + ret = regulator_request_power_budget(supply, pw_budget); + if (ret < 0) + return ret; + + priv->manager_pw_budget[i] = pw_budget; + ret = pd692x0_conf_manager_power_budget(priv, i, pw_budget); + if (ret < 0) + return ret; + } + + return 0; +} + static int pd692x0_set_port_matrix(const struct pse_pi_pairset *pairset, const struct pd692x0_manager *manager, @@ -998,6 +1179,14 @@ static int pd692x0_setup_pi_matrix(struct pse_controller_dev *pcdev) return ret; nmanagers = ret; + ret = pd692x0_register_managers_regulator(priv, manager, nmanagers); + if (ret) + goto out; + + ret = pd692x0_configure_managers(priv, nmanagers); + if (ret) + goto out; + ret = pd692x0_set_ports_matrix(priv, manager, nmanagers, port_matrix); if (ret) goto out; @@ -1008,8 +1197,14 @@ static int pd692x0_setup_pi_matrix(struct pse_controller_dev *pcdev) out: for (i = 0; i < nmanagers; i++) { + struct regulator *supply = priv->manager_reg[i]->supply; + + regulator_free_power_budget(supply, + priv->manager_pw_budget[i]); + for (j = 0; j < manager[i].nports; j++) of_node_put(manager[i].port_node[j]); + of_node_put(manager[i].node); } return ret; } @@ -1071,6 +1266,25 @@ static int pd692x0_pi_set_pw_limit(struct pse_controller_dev *pcdev, return pd692x0_sendrecv_msg(priv, &msg, &buf); } +static int pd692x0_pi_set_prio(struct pse_controller_dev *pcdev, int id, + unsigned int prio) +{ + struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); + struct pd692x0_msg msg, buf = {0}; + int ret; + + ret = pd692x0_fw_unavailable(priv); + if (ret) + return ret; + + msg = pd692x0_msg_template_list[PD692X0_MSG_SET_PORT_PARAM]; + msg.sub[2] = id; + /* Controller priority from 1 to 3 */ + msg.data[4] = prio + 1; + + return pd692x0_sendrecv_msg(priv, &msg, &buf); +} + static const struct pse_controller_ops pd692x0_ops = { .setup_pi_matrix = pd692x0_setup_pi_matrix, .pi_get_admin_state = pd692x0_pi_get_admin_state, @@ -1084,6 +1298,8 @@ static const struct pse_controller_ops pd692x0_ops = { .pi_get_pw_limit = pd692x0_pi_get_pw_limit, .pi_set_pw_limit = pd692x0_pi_set_pw_limit, .pi_get_pw_limit_ranges = pd692x0_pi_get_pw_limit_ranges, + .pi_get_prio = pd692x0_pi_get_prio, + .pi_set_prio = pd692x0_pi_set_prio, }; #define PD692X0_FW_LINE_MAX_SZ 0xff @@ -1437,6 +1653,7 @@ static const struct fw_upload_ops pd692x0_fw_ops = { static int pd692x0_i2c_probe(struct i2c_client *client) { + static const char * const regulators[] = { "vdd", "vdda" }; struct pd692x0_msg msg, buf = {0}, zero = {0}; struct device *dev = &client->dev; struct pd692x0_msg_ver ver; @@ -1444,6 +1661,12 @@ static int pd692x0_i2c_probe(struct i2c_client *client) struct fw_upload *fwl; int ret; + ret = devm_regulator_bulk_get_enable(dev, ARRAY_SIZE(regulators), + regulators); + if (ret) + return dev_err_probe(dev, ret, + "Failed to enable regulators\n"); + if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { dev_err(dev, "i2c check functionality failed\n"); return -ENXIO; @@ -1500,6 +1723,8 @@ static int pd692x0_i2c_probe(struct i2c_client *client) priv->pcdev.ops = &pd692x0_ops; priv->pcdev.dev = dev; priv->pcdev.types = ETHTOOL_PSE_C33; + priv->pcdev.supp_budget_eval_strategies = PSE_BUDGET_EVAL_STRAT_DYNAMIC; + priv->pcdev.pis_prio_max = 2; ret = devm_pse_controller_register(dev, &priv->pcdev); if (ret) return dev_err_probe(dev, ret, diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c index 4602e26eb8c8..23eb3c9d0bcd 100644 --- a/drivers/net/pse-pd/pse_core.c +++ b/drivers/net/pse-pd/pse_core.c @@ -7,13 +7,21 @@ #include <linux/device.h> #include <linux/ethtool.h> +#include <linux/ethtool_netlink.h> #include <linux/of.h> +#include <linux/phy.h> #include <linux/pse-pd/pse.h> #include <linux/regulator/driver.h> #include <linux/regulator/machine.h> +#include <linux/rtnetlink.h> +#include <net/net_trackers.h> + +#define PSE_PW_D_LIMIT INT_MAX static DEFINE_MUTEX(pse_list_mutex); static LIST_HEAD(pse_controller_list); +static DEFINE_XARRAY_ALLOC(pse_pw_d_map); +static DEFINE_MUTEX(pse_pw_d_mutex); /** * struct pse_control - a PSE control @@ -23,6 +31,7 @@ static LIST_HEAD(pse_controller_list); * @list: list entry for the pcdev's PSE controller list * @id: ID of the PSE line in the PSE controller device * @refcnt: Number of gets of this pse_control + * @attached_phydev: PHY device pointer attached by the PSE control */ struct pse_control { struct pse_controller_dev *pcdev; @@ -30,6 +39,22 @@ struct pse_control { struct list_head list; unsigned int id; struct kref refcnt; + struct phy_device *attached_phydev; +}; + +/** + * struct pse_power_domain - a PSE power domain + * @id: ID of the power domain + * @supply: Power supply the Power Domain + * @refcnt: Number of gets of this pse_power_domain + * @budget_eval_strategy: Current power budget evaluation strategy of the + * power domain + */ +struct pse_power_domain { + int id; + struct regulator *supply; + struct kref refcnt; + u32 budget_eval_strategy; }; static int of_load_single_pse_pi_pairset(struct device_node *node, @@ -208,10 +233,185 @@ out: return ret; } +/** + * pse_control_find_net_by_id - Find net attached to the pse control id + * @pcdev: a pointer to the PSE + * @id: index of the PSE control + * + * Return: pse_control pointer or NULL. The device returned has had a + * reference added and the pointer is safe until the user calls + * pse_control_put() to indicate they have finished with it. + */ +static struct pse_control * +pse_control_find_by_id(struct pse_controller_dev *pcdev, int id) +{ + struct pse_control *psec; + + mutex_lock(&pse_list_mutex); + list_for_each_entry(psec, &pcdev->pse_control_head, list) { + if (psec->id == id) { + kref_get(&psec->refcnt); + mutex_unlock(&pse_list_mutex); + return psec; + } + } + mutex_unlock(&pse_list_mutex); + return NULL; +} + +/** + * pse_control_get_netdev - Return netdev associated to a PSE control + * @psec: PSE control pointer + * + * Return: netdev pointer or NULL + */ +static struct net_device *pse_control_get_netdev(struct pse_control *psec) +{ + ASSERT_RTNL(); + + if (!psec || !psec->attached_phydev) + return NULL; + + return psec->attached_phydev->attached_dev; +} + +/** + * pse_pi_is_hw_enabled - Is PI enabled at the hardware level + * @pcdev: a pointer to the PSE controller device + * @id: Index of the PI + * + * Return: 1 if the PI is enabled at the hardware level, 0 if not, and + * a failure value on error + */ +static int pse_pi_is_hw_enabled(struct pse_controller_dev *pcdev, int id) +{ + struct pse_admin_state admin_state = {0}; + int ret; + + ret = pcdev->ops->pi_get_admin_state(pcdev, id, &admin_state); + if (ret < 0) + return ret; + + /* PI is well enabled at the hardware level */ + if (admin_state.podl_admin_state == ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED || + admin_state.c33_admin_state == ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED) + return 1; + + return 0; +} + +/** + * pse_pi_is_admin_enable_pending - Check if PI is in admin enable pending state + * which mean the power is not yet being + * delivered + * @pcdev: a pointer to the PSE controller device + * @id: Index of the PI + * + * Detects if a PI is enabled in software with a PD detected, but the hardware + * admin state hasn't been applied yet. + * + * This function is used in the power delivery and retry mechanisms to determine + * which PIs need to have power delivery attempted again. + * + * Return: true if the PI has admin enable flag set in software but not yet + * reflected in the hardware admin state, false otherwise. + */ +static bool +pse_pi_is_admin_enable_pending(struct pse_controller_dev *pcdev, int id) +{ + int ret; + + /* PI not enabled or nothing is plugged */ + if (!pcdev->pi[id].admin_state_enabled || + !pcdev->pi[id].isr_pd_detected) + return false; + + ret = pse_pi_is_hw_enabled(pcdev, id); + /* PSE PI is already enabled at hardware level */ + if (ret == 1) + return false; + + return true; +} + +static int _pse_pi_delivery_power_sw_pw_ctrl(struct pse_controller_dev *pcdev, + int id, + struct netlink_ext_ack *extack); + +/** + * pse_pw_d_retry_power_delivery - Retry power delivery for pending ports in a + * PSE power domain + * @pcdev: a pointer to the PSE controller device + * @pw_d: a pointer to the PSE power domain + * + * Scans all ports in the specified power domain and attempts to enable power + * delivery to any ports that have admin enable state set but don't yet have + * hardware power enabled. Used when there are changes in connection status, + * admin state, or priority that might allow previously unpowered ports to + * receive power, especially in over-budget conditions. + */ +static void pse_pw_d_retry_power_delivery(struct pse_controller_dev *pcdev, + struct pse_power_domain *pw_d) +{ + int i, ret = 0; + + for (i = 0; i < pcdev->nr_lines; i++) { + int prio_max = pcdev->nr_lines; + struct netlink_ext_ack extack; + + if (pcdev->pi[i].pw_d != pw_d) + continue; + + if (!pse_pi_is_admin_enable_pending(pcdev, i)) + continue; + + /* Do not try to enable PI with a lower prio (higher value) + * than one which already can't be enabled. + */ + if (pcdev->pi[i].prio > prio_max) + continue; + + ret = _pse_pi_delivery_power_sw_pw_ctrl(pcdev, i, &extack); + if (ret == -ERANGE) + prio_max = pcdev->pi[i].prio; + } +} + +/** + * pse_pw_d_is_sw_pw_control - Determine if power control is software managed + * @pcdev: a pointer to the PSE controller device + * @pw_d: a pointer to the PSE power domain + * + * This function determines whether the power control for a specific power + * domain is managed by software in the interrupt handler rather than directly + * by hardware. + * + * Software power control is active in the following cases: + * - When the budget evaluation strategy is set to static + * - When the budget evaluation strategy is disabled but the PSE controller + * has an interrupt handler that can report if a Powered Device is connected + * + * Return: true if the power control of the power domain is managed by software, + * false otherwise + */ +static bool pse_pw_d_is_sw_pw_control(struct pse_controller_dev *pcdev, + struct pse_power_domain *pw_d) +{ + if (!pw_d) + return false; + + if (pw_d->budget_eval_strategy == PSE_BUDGET_EVAL_STRAT_STATIC) + return true; + if (pw_d->budget_eval_strategy == PSE_BUDGET_EVAL_STRAT_DISABLED && + pcdev->ops->pi_enable && pcdev->irq) + return true; + + return false; +} + static int pse_pi_is_enabled(struct regulator_dev *rdev) { struct pse_controller_dev *pcdev = rdev_get_drvdata(rdev); - struct pse_admin_state admin_state = {0}; const struct pse_controller_ops *ops; int id, ret; @@ -221,13 +421,12 @@ static int pse_pi_is_enabled(struct regulator_dev *rdev) id = rdev_get_id(rdev); mutex_lock(&pcdev->lock); - ret = ops->pi_get_admin_state(pcdev, id, &admin_state); - if (ret) + if (pse_pw_d_is_sw_pw_control(pcdev, pcdev->pi[id].pw_d)) { + ret = pcdev->pi[id].admin_state_enabled; goto out; + } - if (admin_state.podl_admin_state == ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED || - admin_state.c33_admin_state == ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED) - ret = 1; + ret = pse_pi_is_hw_enabled(pcdev, id); out: mutex_unlock(&pcdev->lock); @@ -235,11 +434,239 @@ out: return ret; } +/** + * pse_pi_deallocate_pw_budget - Deallocate power budget of the PI + * @pi: a pointer to the PSE PI + */ +static void pse_pi_deallocate_pw_budget(struct pse_pi *pi) +{ + if (!pi->pw_d || !pi->pw_allocated_mW) + return; + + regulator_free_power_budget(pi->pw_d->supply, pi->pw_allocated_mW); + pi->pw_allocated_mW = 0; +} + +/** + * _pse_pi_disable - Call disable operation. Assumes the PSE lock has been + * acquired. + * @pcdev: a pointer to the PSE + * @id: index of the PSE control + * + * Return: 0 on success and failure value on error + */ +static int _pse_pi_disable(struct pse_controller_dev *pcdev, int id) +{ + const struct pse_controller_ops *ops = pcdev->ops; + int ret; + + if (!ops->pi_disable) + return -EOPNOTSUPP; + + ret = ops->pi_disable(pcdev, id); + if (ret) + return ret; + + pse_pi_deallocate_pw_budget(&pcdev->pi[id]); + + if (pse_pw_d_is_sw_pw_control(pcdev, pcdev->pi[id].pw_d)) + pse_pw_d_retry_power_delivery(pcdev, pcdev->pi[id].pw_d); + + return 0; +} + +/** + * pse_disable_pi_pol - Disable a PI on a power budget policy + * @pcdev: a pointer to the PSE + * @id: index of the PSE PI + * + * Return: 0 on success and failure value on error + */ +static int pse_disable_pi_pol(struct pse_controller_dev *pcdev, int id) +{ + unsigned long notifs = ETHTOOL_PSE_EVENT_OVER_BUDGET; + struct pse_ntf ntf = {}; + int ret; + + dev_dbg(pcdev->dev, "Disabling PI %d to free power budget\n", id); + + ret = _pse_pi_disable(pcdev, id); + if (ret) + notifs |= ETHTOOL_PSE_EVENT_SW_PW_CONTROL_ERROR; + + ntf.notifs = notifs; + ntf.id = id; + kfifo_in_spinlocked(&pcdev->ntf_fifo, &ntf, 1, &pcdev->ntf_fifo_lock); + schedule_work(&pcdev->ntf_work); + + return ret; +} + +/** + * pse_disable_pi_prio - Disable all PIs of a given priority inside a PSE + * power domain + * @pcdev: a pointer to the PSE + * @pw_d: a pointer to the PSE power domain + * @prio: priority + * + * Return: 0 on success and failure value on error + */ +static int pse_disable_pi_prio(struct pse_controller_dev *pcdev, + struct pse_power_domain *pw_d, + int prio) +{ + int i; + + for (i = 0; i < pcdev->nr_lines; i++) { + int ret; + + if (pcdev->pi[i].prio != prio || + pcdev->pi[i].pw_d != pw_d || + pse_pi_is_hw_enabled(pcdev, i) <= 0) + continue; + + ret = pse_disable_pi_pol(pcdev, i); + if (ret) + return ret; + } + + return 0; +} + +/** + * pse_pi_allocate_pw_budget_static_prio - Allocate power budget for the PI + * when the budget eval strategy is + * static + * @pcdev: a pointer to the PSE + * @id: index of the PSE control + * @pw_req: power requested in mW + * @extack: extack for error reporting + * + * Allocates power using static budget evaluation strategy, where allocation + * is based on PD classification. When insufficient budget is available, + * lower-priority ports (higher priority numbers) are turned off first. + * + * Return: 0 on success and failure value on error + */ +static int +pse_pi_allocate_pw_budget_static_prio(struct pse_controller_dev *pcdev, int id, + int pw_req, struct netlink_ext_ack *extack) +{ + struct pse_pi *pi = &pcdev->pi[id]; + int ret, _prio; + + _prio = pcdev->nr_lines; + while (regulator_request_power_budget(pi->pw_d->supply, pw_req) == -ERANGE) { + if (_prio <= pi->prio) { + NL_SET_ERR_MSG_FMT(extack, + "PI %d: not enough power budget available", + id); + return -ERANGE; + } + + ret = pse_disable_pi_prio(pcdev, pi->pw_d, _prio); + if (ret < 0) + return ret; + + _prio--; + } + + pi->pw_allocated_mW = pw_req; + return 0; +} + +/** + * pse_pi_allocate_pw_budget - Allocate power budget for the PI + * @pcdev: a pointer to the PSE + * @id: index of the PSE control + * @pw_req: power requested in mW + * @extack: extack for error reporting + * + * Return: 0 on success and failure value on error + */ +static int pse_pi_allocate_pw_budget(struct pse_controller_dev *pcdev, int id, + int pw_req, struct netlink_ext_ack *extack) +{ + struct pse_pi *pi = &pcdev->pi[id]; + + if (!pi->pw_d) + return 0; + + /* PSE_BUDGET_EVAL_STRAT_STATIC */ + if (pi->pw_d->budget_eval_strategy == PSE_BUDGET_EVAL_STRAT_STATIC) + return pse_pi_allocate_pw_budget_static_prio(pcdev, id, pw_req, + extack); + + return 0; +} + +/** + * _pse_pi_delivery_power_sw_pw_ctrl - Enable PSE PI in case of software power + * control. Assumes the PSE lock has been + * acquired. + * @pcdev: a pointer to the PSE + * @id: index of the PSE control + * @extack: extack for error reporting + * + * Return: 0 on success and failure value on error + */ +static int _pse_pi_delivery_power_sw_pw_ctrl(struct pse_controller_dev *pcdev, + int id, + struct netlink_ext_ack *extack) +{ + const struct pse_controller_ops *ops = pcdev->ops; + struct pse_pi *pi = &pcdev->pi[id]; + int ret, pw_req; + + if (!ops->pi_get_pw_req) { + /* No power allocation management */ + ret = ops->pi_enable(pcdev, id); + if (ret) + NL_SET_ERR_MSG_FMT(extack, + "PI %d: enable error %d", + id, ret); + return ret; + } + + ret = ops->pi_get_pw_req(pcdev, id); + if (ret < 0) + return ret; + + pw_req = ret; + + /* Compare requested power with port power limit and use the lowest + * one. + */ + if (ops->pi_get_pw_limit) { + ret = ops->pi_get_pw_limit(pcdev, id); + if (ret < 0) + return ret; + + if (ret < pw_req) + pw_req = ret; + } + + ret = pse_pi_allocate_pw_budget(pcdev, id, pw_req, extack); + if (ret) + return ret; + + ret = ops->pi_enable(pcdev, id); + if (ret) { + pse_pi_deallocate_pw_budget(pi); + NL_SET_ERR_MSG_FMT(extack, + "PI %d: enable error %d", + id, ret); + return ret; + } + + return 0; +} + static int pse_pi_enable(struct regulator_dev *rdev) { struct pse_controller_dev *pcdev = rdev_get_drvdata(rdev); const struct pse_controller_ops *ops; - int id, ret; + int id, ret = 0; ops = pcdev->ops; if (!ops->pi_enable) @@ -247,6 +674,23 @@ static int pse_pi_enable(struct regulator_dev *rdev) id = rdev_get_id(rdev); mutex_lock(&pcdev->lock); + if (pse_pw_d_is_sw_pw_control(pcdev, pcdev->pi[id].pw_d)) { + /* Manage enabled status by software. + * Real enable process will happen if a port is connected. + */ + if (pcdev->pi[id].isr_pd_detected) { + struct netlink_ext_ack extack; + + ret = _pse_pi_delivery_power_sw_pw_ctrl(pcdev, id, &extack); + } + if (!ret || ret == -ERANGE) { + pcdev->pi[id].admin_state_enabled = 1; + ret = 0; + } + mutex_unlock(&pcdev->lock); + return ret; + } + ret = ops->pi_enable(pcdev, id); if (!ret) pcdev->pi[id].admin_state_enabled = 1; @@ -258,21 +702,18 @@ static int pse_pi_enable(struct regulator_dev *rdev) static int pse_pi_disable(struct regulator_dev *rdev) { struct pse_controller_dev *pcdev = rdev_get_drvdata(rdev); - const struct pse_controller_ops *ops; + struct pse_pi *pi; int id, ret; - ops = pcdev->ops; - if (!ops->pi_disable) - return -EOPNOTSUPP; - id = rdev_get_id(rdev); + pi = &pcdev->pi[id]; mutex_lock(&pcdev->lock); - ret = ops->pi_disable(pcdev, id); + ret = _pse_pi_disable(pcdev, id); if (!ret) - pcdev->pi[id].admin_state_enabled = 0; - mutex_unlock(&pcdev->lock); + pi->admin_state_enabled = 0; - return ret; + mutex_unlock(&pcdev->lock); + return 0; } static int _pse_pi_get_voltage(struct regulator_dev *rdev) @@ -437,6 +878,158 @@ devm_pse_pi_regulator_register(struct pse_controller_dev *pcdev, return 0; } +static void __pse_pw_d_release(struct kref *kref) +{ + struct pse_power_domain *pw_d = container_of(kref, + struct pse_power_domain, + refcnt); + + regulator_put(pw_d->supply); + xa_erase(&pse_pw_d_map, pw_d->id); + mutex_unlock(&pse_pw_d_mutex); +} + +/** + * pse_flush_pw_ds - flush all PSE power domains of a PSE + * @pcdev: a pointer to the initialized PSE controller device + */ +static void pse_flush_pw_ds(struct pse_controller_dev *pcdev) +{ + struct pse_power_domain *pw_d; + int i; + + for (i = 0; i < pcdev->nr_lines; i++) { + if (!pcdev->pi[i].pw_d) + continue; + + pw_d = xa_load(&pse_pw_d_map, pcdev->pi[i].pw_d->id); + if (!pw_d) + continue; + + kref_put_mutex(&pw_d->refcnt, __pse_pw_d_release, + &pse_pw_d_mutex); + } +} + +/** + * devm_pse_alloc_pw_d - allocate a new PSE power domain for a device + * @dev: device that is registering this PSE power domain + * + * Return: Pointer to the newly allocated PSE power domain or error pointers + */ +static struct pse_power_domain *devm_pse_alloc_pw_d(struct device *dev) +{ + struct pse_power_domain *pw_d; + int index, ret; + + pw_d = devm_kzalloc(dev, sizeof(*pw_d), GFP_KERNEL); + if (!pw_d) + return ERR_PTR(-ENOMEM); + + ret = xa_alloc(&pse_pw_d_map, &index, pw_d, XA_LIMIT(1, PSE_PW_D_LIMIT), + GFP_KERNEL); + if (ret) + return ERR_PTR(ret); + + kref_init(&pw_d->refcnt); + pw_d->id = index; + return pw_d; +} + +/** + * pse_register_pw_ds - register the PSE power domains for a PSE + * @pcdev: a pointer to the PSE controller device + * + * Return: 0 on success and failure value on error + */ +static int pse_register_pw_ds(struct pse_controller_dev *pcdev) +{ + int i, ret = 0; + + mutex_lock(&pse_pw_d_mutex); + for (i = 0; i < pcdev->nr_lines; i++) { + struct regulator_dev *rdev = pcdev->pi[i].rdev; + struct pse_power_domain *pw_d; + struct regulator *supply; + bool present = false; + unsigned long index; + + /* No regulator or regulator parent supply registered. + * We need a regulator parent to register a PSE power domain + */ + if (!rdev || !rdev->supply) + continue; + + xa_for_each(&pse_pw_d_map, index, pw_d) { + /* Power supply already registered as a PSE power + * domain. + */ + if (regulator_is_equal(pw_d->supply, rdev->supply)) { + present = true; + pcdev->pi[i].pw_d = pw_d; + break; + } + } + if (present) { + kref_get(&pw_d->refcnt); + continue; + } + + pw_d = devm_pse_alloc_pw_d(pcdev->dev); + if (IS_ERR(pw_d)) { + ret = PTR_ERR(pw_d); + goto out; + } + + supply = regulator_get(&rdev->dev, rdev->supply_name); + if (IS_ERR(supply)) { + xa_erase(&pse_pw_d_map, pw_d->id); + ret = PTR_ERR(supply); + goto out; + } + + pw_d->supply = supply; + if (pcdev->supp_budget_eval_strategies) + pw_d->budget_eval_strategy = pcdev->supp_budget_eval_strategies; + else + pw_d->budget_eval_strategy = PSE_BUDGET_EVAL_STRAT_DISABLED; + kref_init(&pw_d->refcnt); + pcdev->pi[i].pw_d = pw_d; + } + +out: + mutex_unlock(&pse_pw_d_mutex); + return ret; +} + +/** + * pse_send_ntf_worker - Worker to send PSE notifications + * @work: work object + * + * Manage and send PSE netlink notifications using a workqueue to avoid + * deadlock between pcdev_lock and pse_list_mutex. + */ +static void pse_send_ntf_worker(struct work_struct *work) +{ + struct pse_controller_dev *pcdev; + struct pse_ntf ntf; + + pcdev = container_of(work, struct pse_controller_dev, ntf_work); + + while (kfifo_out(&pcdev->ntf_fifo, &ntf, 1)) { + struct net_device *netdev; + struct pse_control *psec; + + psec = pse_control_find_by_id(pcdev, ntf.id); + rtnl_lock(); + netdev = pse_control_get_netdev(psec); + if (netdev) + ethnl_pse_send_ntf(netdev, ntf.notifs); + rtnl_unlock(); + pse_control_put(psec); + } +} + /** * pse_controller_register - register a PSE controller device * @pcdev: a pointer to the initialized PSE controller device @@ -450,6 +1043,13 @@ int pse_controller_register(struct pse_controller_dev *pcdev) mutex_init(&pcdev->lock); INIT_LIST_HEAD(&pcdev->pse_control_head); + spin_lock_init(&pcdev->ntf_fifo_lock); + ret = kfifo_alloc(&pcdev->ntf_fifo, pcdev->nr_lines, GFP_KERNEL); + if (ret) { + dev_err(pcdev->dev, "failed to allocate kfifo notifications\n"); + return ret; + } + INIT_WORK(&pcdev->ntf_work, pse_send_ntf_worker); if (!pcdev->nr_lines) pcdev->nr_lines = 1; @@ -496,6 +1096,10 @@ int pse_controller_register(struct pse_controller_dev *pcdev) return ret; } + ret = pse_register_pw_ds(pcdev); + if (ret) + return ret; + mutex_lock(&pse_list_mutex); list_add(&pcdev->list, &pse_controller_list); mutex_unlock(&pse_list_mutex); @@ -510,7 +1114,12 @@ EXPORT_SYMBOL_GPL(pse_controller_register); */ void pse_controller_unregister(struct pse_controller_dev *pcdev) { + pse_flush_pw_ds(pcdev); pse_release_pis(pcdev); + if (pcdev->irq) + disable_irq(pcdev->irq); + cancel_work_sync(&pcdev->ntf_work); + kfifo_free(&pcdev->ntf_fifo); mutex_lock(&pse_list_mutex); list_del(&pcdev->list); mutex_unlock(&pse_list_mutex); @@ -557,6 +1166,191 @@ int devm_pse_controller_register(struct device *dev, } EXPORT_SYMBOL_GPL(devm_pse_controller_register); +struct pse_irq { + struct pse_controller_dev *pcdev; + struct pse_irq_desc desc; + unsigned long *notifs; +}; + +/** + * pse_to_regulator_notifs - Convert PSE notifications to Regulator + * notifications + * @notifs: PSE notifications + * + * Return: Regulator notifications + */ +static unsigned long pse_to_regulator_notifs(unsigned long notifs) +{ + unsigned long rnotifs = 0; + + if (notifs & ETHTOOL_PSE_EVENT_OVER_CURRENT) + rnotifs |= REGULATOR_EVENT_OVER_CURRENT; + if (notifs & ETHTOOL_PSE_EVENT_OVER_TEMP) + rnotifs |= REGULATOR_EVENT_OVER_TEMP; + + return rnotifs; +} + +/** + * pse_set_config_isr - Set PSE control config according to the PSE + * notifications + * @pcdev: a pointer to the PSE + * @id: index of the PSE control + * @notifs: PSE event notifications + * + * Return: 0 on success and failure value on error + */ +static int pse_set_config_isr(struct pse_controller_dev *pcdev, int id, + unsigned long notifs) +{ + int ret = 0; + + if (notifs & PSE_BUDGET_EVAL_STRAT_DYNAMIC) + return 0; + + if ((notifs & ETHTOOL_C33_PSE_EVENT_DISCONNECTION) && + ((notifs & ETHTOOL_C33_PSE_EVENT_DETECTION) || + (notifs & ETHTOOL_C33_PSE_EVENT_CLASSIFICATION))) { + dev_dbg(pcdev->dev, + "PI %d: error, connection and disconnection reported simultaneously", + id); + return -EINVAL; + } + + if (notifs & ETHTOOL_C33_PSE_EVENT_CLASSIFICATION) { + struct netlink_ext_ack extack; + + pcdev->pi[id].isr_pd_detected = true; + if (pcdev->pi[id].admin_state_enabled) { + ret = _pse_pi_delivery_power_sw_pw_ctrl(pcdev, id, + &extack); + if (ret == -ERANGE) + ret = 0; + } + } else if (notifs & ETHTOOL_C33_PSE_EVENT_DISCONNECTION) { + if (pcdev->pi[id].admin_state_enabled && + pcdev->pi[id].isr_pd_detected) + ret = _pse_pi_disable(pcdev, id); + pcdev->pi[id].isr_pd_detected = false; + } + + return ret; +} + +/** + * pse_isr - IRQ handler for PSE + * @irq: irq number + * @data: pointer to user interrupt structure + * + * Return: irqreturn_t - status of IRQ + */ +static irqreturn_t pse_isr(int irq, void *data) +{ + struct pse_controller_dev *pcdev; + unsigned long notifs_mask = 0; + struct pse_irq_desc *desc; + struct pse_irq *h = data; + int ret, i; + + desc = &h->desc; + pcdev = h->pcdev; + + /* Clear notifs mask */ + memset(h->notifs, 0, pcdev->nr_lines * sizeof(*h->notifs)); + mutex_lock(&pcdev->lock); + ret = desc->map_event(irq, pcdev, h->notifs, ¬ifs_mask); + if (ret || !notifs_mask) { + mutex_unlock(&pcdev->lock); + return IRQ_NONE; + } + + for_each_set_bit(i, ¬ifs_mask, pcdev->nr_lines) { + unsigned long notifs, rnotifs; + struct pse_ntf ntf = {}; + + /* Do nothing PI not described */ + if (!pcdev->pi[i].rdev) + continue; + + notifs = h->notifs[i]; + if (pse_pw_d_is_sw_pw_control(pcdev, pcdev->pi[i].pw_d)) { + ret = pse_set_config_isr(pcdev, i, notifs); + if (ret) + notifs |= ETHTOOL_PSE_EVENT_SW_PW_CONTROL_ERROR; + } + + dev_dbg(h->pcdev->dev, + "Sending PSE notification EVT 0x%lx\n", notifs); + + ntf.notifs = notifs; + ntf.id = i; + kfifo_in_spinlocked(&pcdev->ntf_fifo, &ntf, 1, + &pcdev->ntf_fifo_lock); + schedule_work(&pcdev->ntf_work); + + rnotifs = pse_to_regulator_notifs(notifs); + regulator_notifier_call_chain(pcdev->pi[i].rdev, rnotifs, + NULL); + } + + mutex_unlock(&pcdev->lock); + + return IRQ_HANDLED; +} + +/** + * devm_pse_irq_helper - Register IRQ based PSE event notifier + * @pcdev: a pointer to the PSE + * @irq: the irq value to be passed to request_irq + * @irq_flags: the flags to be passed to request_irq + * @d: PSE interrupt description + * + * Return: 0 on success and errno on failure + */ +int devm_pse_irq_helper(struct pse_controller_dev *pcdev, int irq, + int irq_flags, const struct pse_irq_desc *d) +{ + struct device *dev = pcdev->dev; + size_t irq_name_len; + struct pse_irq *h; + char *irq_name; + int ret; + + if (!d || !d->map_event || !d->name) + return -EINVAL; + + h = devm_kzalloc(dev, sizeof(*h), GFP_KERNEL); + if (!h) + return -ENOMEM; + + h->pcdev = pcdev; + h->desc = *d; + + /* IRQ name len is pcdev dev name + 5 char + irq desc name + 1 */ + irq_name_len = strlen(dev_name(pcdev->dev)) + 5 + strlen(d->name) + 1; + irq_name = devm_kzalloc(dev, irq_name_len, GFP_KERNEL); + if (!irq_name) + return -ENOMEM; + + snprintf(irq_name, irq_name_len, "pse-%s:%s", dev_name(pcdev->dev), + d->name); + + h->notifs = devm_kcalloc(dev, pcdev->nr_lines, + sizeof(*h->notifs), GFP_KERNEL); + if (!h->notifs) + return -ENOMEM; + + ret = devm_request_threaded_irq(dev, irq, NULL, pse_isr, + IRQF_ONESHOT | irq_flags, + irq_name, h); + if (ret) + dev_err(pcdev->dev, "Failed to request IRQ %d\n", irq); + + pcdev->irq = irq; + return ret; +} +EXPORT_SYMBOL_GPL(devm_pse_irq_helper); + /* PSE control section */ static void __pse_control_release(struct kref *kref) @@ -599,7 +1393,8 @@ void pse_control_put(struct pse_control *psec) EXPORT_SYMBOL_GPL(pse_control_put); static struct pse_control * -pse_control_get_internal(struct pse_controller_dev *pcdev, unsigned int index) +pse_control_get_internal(struct pse_controller_dev *pcdev, unsigned int index, + struct phy_device *phydev) { struct pse_control *psec; int ret; @@ -622,6 +1417,20 @@ pse_control_get_internal(struct pse_controller_dev *pcdev, unsigned int index) goto free_psec; } + if (!pcdev->ops->pi_get_admin_state) { + ret = -EOPNOTSUPP; + goto free_psec; + } + + /* Initialize admin_state_enabled before the regulator_get. This + * aims to have the right value reported in the first is_enabled + * call in case of control managed by software. + */ + ret = pse_pi_is_hw_enabled(pcdev, index); + if (ret < 0) + goto free_psec; + + pcdev->pi[index].admin_state_enabled = ret; psec->ps = devm_regulator_get_exclusive(pcdev->dev, rdev_get_name(pcdev->pi[index].rdev)); if (IS_ERR(psec->ps)) { @@ -629,21 +1438,14 @@ pse_control_get_internal(struct pse_controller_dev *pcdev, unsigned int index) goto put_module; } - ret = regulator_is_enabled(psec->ps); - if (ret < 0) - goto regulator_put; - - pcdev->pi[index].admin_state_enabled = ret; - psec->pcdev = pcdev; list_add(&psec->list, &pcdev->pse_control_head); psec->id = index; + psec->attached_phydev = phydev; kref_init(&psec->refcnt); return psec; -regulator_put: - devm_regulator_put(psec->ps); put_module: module_put(pcdev->owner); free_psec: @@ -693,7 +1495,8 @@ static int psec_id_xlate(struct pse_controller_dev *pcdev, return pse_spec->args[0]; } -struct pse_control *of_pse_control_get(struct device_node *node) +struct pse_control *of_pse_control_get(struct device_node *node, + struct phy_device *phydev) { struct pse_controller_dev *r, *pcdev; struct of_phandle_args args; @@ -743,7 +1546,7 @@ struct pse_control *of_pse_control_get(struct device_node *node) } /* pse_list_mutex also protects the pcdev's pse_control list */ - psec = pse_control_get_internal(pcdev, psec_id); + psec = pse_control_get_internal(pcdev, psec_id, phydev); out: mutex_unlock(&pse_list_mutex); @@ -754,6 +1557,35 @@ out: EXPORT_SYMBOL_GPL(of_pse_control_get); /** + * pse_get_sw_admin_state - Convert the software admin state to c33 or podl + * admin state value used in the standard + * @psec: PSE control pointer + * @admin_state: a pointer to the admin_state structure + */ +static void pse_get_sw_admin_state(struct pse_control *psec, + struct pse_admin_state *admin_state) +{ + struct pse_pi *pi = &psec->pcdev->pi[psec->id]; + + if (pse_has_podl(psec)) { + if (pi->admin_state_enabled) + admin_state->podl_admin_state = + ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED; + else + admin_state->podl_admin_state = + ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED; + } + if (pse_has_c33(psec)) { + if (pi->admin_state_enabled) + admin_state->c33_admin_state = + ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED; + else + admin_state->c33_admin_state = + ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED; + } +} + +/** * pse_ethtool_get_status - get status of PSE control * @psec: PSE control pointer * @extack: extack for reporting useful error messages @@ -769,16 +1601,46 @@ int pse_ethtool_get_status(struct pse_control *psec, struct pse_pw_status pw_status = {0}; const struct pse_controller_ops *ops; struct pse_controller_dev *pcdev; + struct pse_pi *pi; int ret; pcdev = psec->pcdev; ops = pcdev->ops; + + pi = &pcdev->pi[psec->id]; mutex_lock(&pcdev->lock); - ret = ops->pi_get_admin_state(pcdev, psec->id, &admin_state); - if (ret) - goto out; - status->podl_admin_state = admin_state.podl_admin_state; - status->c33_admin_state = admin_state.c33_admin_state; + if (pi->pw_d) { + status->pw_d_id = pi->pw_d->id; + if (pse_pw_d_is_sw_pw_control(pcdev, pi->pw_d)) { + pse_get_sw_admin_state(psec, &admin_state); + } else { + ret = ops->pi_get_admin_state(pcdev, psec->id, + &admin_state); + if (ret) + goto out; + } + status->podl_admin_state = admin_state.podl_admin_state; + status->c33_admin_state = admin_state.c33_admin_state; + + switch (pi->pw_d->budget_eval_strategy) { + case PSE_BUDGET_EVAL_STRAT_STATIC: + status->prio_max = pcdev->nr_lines - 1; + status->prio = pi->prio; + break; + case PSE_BUDGET_EVAL_STRAT_DYNAMIC: + status->prio_max = pcdev->pis_prio_max; + if (ops->pi_get_prio) { + ret = ops->pi_get_prio(pcdev, psec->id); + if (ret < 0) + goto out; + + status->prio = ret; + } + break; + default: + break; + } + } ret = ops->pi_get_pw_status(pcdev, psec->id, &pw_status); if (ret) @@ -928,6 +1790,52 @@ int pse_ethtool_set_config(struct pse_control *psec, EXPORT_SYMBOL_GPL(pse_ethtool_set_config); /** + * pse_pi_update_pw_budget - Update PSE power budget allocated with new + * power in mW + * @pcdev: a pointer to the PSE controller device + * @id: index of the PSE PI + * @pw_req: power requested + * @extack: extack for reporting useful error messages + * + * Return: Previous power allocated on success and failure value on error + */ +static int pse_pi_update_pw_budget(struct pse_controller_dev *pcdev, int id, + const unsigned int pw_req, + struct netlink_ext_ack *extack) +{ + struct pse_pi *pi = &pcdev->pi[id]; + int previous_pw_allocated; + int pw_diff, ret = 0; + + /* We don't want pw_allocated_mW value change in the middle of an + * power budget update + */ + mutex_lock(&pcdev->lock); + previous_pw_allocated = pi->pw_allocated_mW; + pw_diff = pw_req - previous_pw_allocated; + if (!pw_diff) { + goto out; + } else if (pw_diff > 0) { + ret = regulator_request_power_budget(pi->pw_d->supply, pw_diff); + if (ret) { + NL_SET_ERR_MSG_FMT(extack, + "PI %d: not enough power budget available", + id); + goto out; + } + + } else { + regulator_free_power_budget(pi->pw_d->supply, -pw_diff); + } + pi->pw_allocated_mW = pw_req; + ret = previous_pw_allocated; + +out: + mutex_unlock(&pcdev->lock); + return ret; +} + +/** * pse_ethtool_set_pw_limit - set PSE control power limit * @psec: PSE control pointer * @extack: extack for reporting useful error messages @@ -939,7 +1847,7 @@ int pse_ethtool_set_pw_limit(struct pse_control *psec, struct netlink_ext_ack *extack, const unsigned int pw_limit) { - int uV, uA, ret; + int uV, uA, ret, previous_pw_allocated = 0; s64 tmp_64; if (pw_limit > MAX_PI_PW) @@ -963,10 +1871,100 @@ int pse_ethtool_set_pw_limit(struct pse_control *psec, /* uA = mW * 1000000000 / uV */ uA = DIV_ROUND_CLOSEST_ULL(tmp_64, uV); - return regulator_set_current_limit(psec->ps, 0, uA); + /* Update power budget only in software power control case and + * if a Power Device is powered. + */ + if (pse_pw_d_is_sw_pw_control(psec->pcdev, + psec->pcdev->pi[psec->id].pw_d) && + psec->pcdev->pi[psec->id].admin_state_enabled && + psec->pcdev->pi[psec->id].isr_pd_detected) { + ret = pse_pi_update_pw_budget(psec->pcdev, psec->id, + pw_limit, extack); + if (ret < 0) + return ret; + previous_pw_allocated = ret; + } + + ret = regulator_set_current_limit(psec->ps, 0, uA); + if (ret < 0 && previous_pw_allocated) { + pse_pi_update_pw_budget(psec->pcdev, psec->id, + previous_pw_allocated, extack); + } + + return ret; } EXPORT_SYMBOL_GPL(pse_ethtool_set_pw_limit); +/** + * pse_ethtool_set_prio - Set PSE PI priority according to the budget + * evaluation strategy + * @psec: PSE control pointer + * @extack: extack for reporting useful error messages + * @prio: priovity value + * + * Return: 0 on success and failure value on error + */ +int pse_ethtool_set_prio(struct pse_control *psec, + struct netlink_ext_ack *extack, + unsigned int prio) +{ + struct pse_controller_dev *pcdev = psec->pcdev; + const struct pse_controller_ops *ops; + int ret = 0; + + if (!pcdev->pi[psec->id].pw_d) { + NL_SET_ERR_MSG(extack, "no power domain attached"); + return -EOPNOTSUPP; + } + + /* We don't want priority change in the middle of an + * enable/disable call or a priority mode change + */ + mutex_lock(&pcdev->lock); + switch (pcdev->pi[psec->id].pw_d->budget_eval_strategy) { + case PSE_BUDGET_EVAL_STRAT_STATIC: + if (prio >= pcdev->nr_lines) { + NL_SET_ERR_MSG_FMT(extack, + "priority %d exceed priority max %d", + prio, pcdev->nr_lines); + ret = -ERANGE; + goto out; + } + + pcdev->pi[psec->id].prio = prio; + pse_pw_d_retry_power_delivery(pcdev, pcdev->pi[psec->id].pw_d); + break; + + case PSE_BUDGET_EVAL_STRAT_DYNAMIC: + ops = psec->pcdev->ops; + if (!ops->pi_set_prio) { + NL_SET_ERR_MSG(extack, + "pse driver does not support setting port priority"); + ret = -EOPNOTSUPP; + goto out; + } + + if (prio > pcdev->pis_prio_max) { + NL_SET_ERR_MSG_FMT(extack, + "priority %d exceed priority max %d", + prio, pcdev->pis_prio_max); + ret = -ERANGE; + goto out; + } + + ret = ops->pi_set_prio(pcdev, psec->id, prio); + break; + + default: + ret = -EOPNOTSUPP; + } + +out: + mutex_unlock(&pcdev->lock); + return ret; +} +EXPORT_SYMBOL_GPL(pse_ethtool_set_prio); + bool pse_has_podl(struct pse_control *psec) { return psec->pcdev->types & ETHTOOL_PSE_PODL; diff --git a/drivers/net/pse-pd/tps23881.c b/drivers/net/pse-pd/tps23881.c index 5e9dda2c0eac..63f8f43062bc 100644 --- a/drivers/net/pse-pd/tps23881.c +++ b/drivers/net/pse-pd/tps23881.c @@ -16,15 +16,34 @@ #include <linux/pse-pd/pse.h> #define TPS23881_MAX_CHANS 8 - +#define TPS23881_MAX_IRQ_RETRIES 10 + +#define TPS23881_REG_IT 0x0 +#define TPS23881_REG_IT_MASK 0x1 +#define TPS23881_REG_IT_DISF BIT(2) +#define TPS23881_REG_IT_DETC BIT(3) +#define TPS23881_REG_IT_CLASC BIT(4) +#define TPS23881_REG_IT_IFAULT BIT(5) +#define TPS23881_REG_IT_SUPF BIT(7) +#define TPS23881_REG_DET_EVENT 0x5 +#define TPS23881_REG_FAULT 0x7 +#define TPS23881_REG_SUPF_EVENT 0xb +#define TPS23881_REG_TSD BIT(7) +#define TPS23881_REG_DISC 0xc #define TPS23881_REG_PW_STATUS 0x10 #define TPS23881_REG_OP_MODE 0x12 +#define TPS23881_REG_DISC_EN 0x13 #define TPS23881_OP_MODE_SEMIAUTO 0xaaaa #define TPS23881_REG_DIS_EN 0x13 #define TPS23881_REG_DET_CLA_EN 0x14 #define TPS23881_REG_GEN_MASK 0x17 +#define TPS23881_REG_CLCHE BIT(2) +#define TPS23881_REG_DECHE BIT(3) #define TPS23881_REG_NBITACC BIT(5) +#define TPS23881_REG_INTEN BIT(7) #define TPS23881_REG_PW_EN 0x19 +#define TPS23881_REG_RESET 0x1a +#define TPS23881_REG_CLRAIN BIT(7) #define TPS23881_REG_2PAIR_POL1 0x1e #define TPS23881_REG_PORT_MAP 0x26 #define TPS23881_REG_PORT_POWER 0x29 @@ -51,6 +70,7 @@ struct tps23881_port_desc { u8 chan[2]; bool is_4p; int pw_pol; + bool exist; }; struct tps23881_priv { @@ -168,6 +188,7 @@ static int tps23881_pi_enable(struct pse_controller_dev *pcdev, int id) struct i2c_client *client = priv->client; u8 chan; u16 val; + int ret; if (id >= TPS23881_MAX_CHANS) return -ERANGE; @@ -181,7 +202,22 @@ static int tps23881_pi_enable(struct pse_controller_dev *pcdev, int id) BIT(chan % 4)); } - return i2c_smbus_write_word_data(client, TPS23881_REG_PW_EN, val); + ret = i2c_smbus_write_word_data(client, TPS23881_REG_PW_EN, val); + if (ret) + return ret; + + /* Enable DC disconnect*/ + chan = priv->port[id].chan[0]; + ret = i2c_smbus_read_word_data(client, TPS23881_REG_DISC_EN); + if (ret < 0) + return ret; + + val = tps23881_set_val(ret, chan, 0, BIT(chan % 4), BIT(chan % 4)); + ret = i2c_smbus_write_word_data(client, TPS23881_REG_DISC_EN, val); + if (ret) + return ret; + + return 0; } static int tps23881_pi_disable(struct pse_controller_dev *pcdev, int id) @@ -214,6 +250,17 @@ static int tps23881_pi_disable(struct pse_controller_dev *pcdev, int id) */ mdelay(5); + /* Disable DC disconnect*/ + chan = priv->port[id].chan[0]; + ret = i2c_smbus_read_word_data(client, TPS23881_REG_DISC_EN); + if (ret < 0) + return ret; + + val = tps23881_set_val(ret, chan, 0, 0, BIT(chan % 4)); + ret = i2c_smbus_write_word_data(client, TPS23881_REG_DISC_EN, val); + if (ret) + return ret; + /* Enable detection and classification */ ret = i2c_smbus_read_word_data(client, TPS23881_REG_DET_CLA_EN); if (ret < 0) @@ -782,8 +829,10 @@ tps23881_write_port_matrix(struct tps23881_priv *priv, hw_chan = port_matrix[i].hw_chan[0] % 4; /* Set software port matrix for existing ports */ - if (port_matrix[i].exist) + if (port_matrix[i].exist) { priv->port[pi_id].chan[0] = lgcl_chan; + priv->port[pi_id].exist = true; + } /* Initialize power policy internal value */ priv->port[pi_id].pw_pol = -1; @@ -907,6 +956,47 @@ static int tps23881_setup_pi_matrix(struct pse_controller_dev *pcdev) return ret; } +static int tps23881_power_class_table[] = { + -ERANGE, + 4000, + 7000, + 15500, + 30000, + 15500, + 15500, + -ERANGE, + 45000, + 60000, + 75000, + 90000, + 15500, + 45000, + -ERANGE, + -ERANGE, +}; + +static int tps23881_pi_get_pw_req(struct pse_controller_dev *pcdev, int id) +{ + struct tps23881_priv *priv = to_tps23881_priv(pcdev); + struct i2c_client *client = priv->client; + u8 reg, chan; + int ret; + u16 val; + + /* For a 4-pair the classification need 5ms to be completed */ + if (priv->port[id].is_4p) + mdelay(5); + + chan = priv->port[id].chan[0]; + reg = TPS23881_REG_DISC + (chan % 4); + ret = i2c_smbus_read_word_data(client, reg); + if (ret < 0) + return ret; + + val = tps23881_calc_val(ret, chan, 4, 0xf); + return tps23881_power_class_table[val]; +} + static const struct pse_controller_ops tps23881_ops = { .setup_pi_matrix = tps23881_setup_pi_matrix, .pi_enable = tps23881_pi_enable, @@ -919,6 +1009,7 @@ static const struct pse_controller_ops tps23881_ops = { .pi_get_pw_limit = tps23881_pi_get_pw_limit, .pi_set_pw_limit = tps23881_pi_set_pw_limit, .pi_get_pw_limit_ranges = tps23881_pi_get_pw_limit_ranges, + .pi_get_pw_req = tps23881_pi_get_pw_req, }; static const char fw_parity_name[] = "ti/tps23881/tps23881-parity-14.bin"; @@ -1017,6 +1108,307 @@ static int tps23881_flash_sram_fw(struct i2c_client *client) return 0; } +/* Convert interrupt events to 0xff to be aligned with the chan + * number. + */ +static u8 tps23881_irq_export_chans_helper(u16 reg_val, u8 field_offset) +{ + u8 val; + + val = (reg_val >> (4 + field_offset) & 0xf0) | + (reg_val >> field_offset & 0x0f); + + return val; +} + +/* Convert chan number to port number */ +static void tps23881_set_notifs_helper(struct tps23881_priv *priv, + u8 chans, + unsigned long *notifs, + unsigned long *notifs_mask, + enum ethtool_pse_event event) +{ + u8 chan; + int i; + + if (!chans) + return; + + for (i = 0; i < TPS23881_MAX_CHANS; i++) { + if (!priv->port[i].exist) + continue; + /* No need to look at the 2nd channel in case of PoE4 as + * both registers are set. + */ + chan = priv->port[i].chan[0]; + + if (BIT(chan) & chans) { + *notifs_mask |= BIT(i); + notifs[i] |= event; + } + } +} + +static void tps23881_irq_event_over_temp(struct tps23881_priv *priv, + u16 reg_val, + unsigned long *notifs, + unsigned long *notifs_mask) +{ + int i; + + if (reg_val & TPS23881_REG_TSD) { + for (i = 0; i < TPS23881_MAX_CHANS; i++) { + if (!priv->port[i].exist) + continue; + + *notifs_mask |= BIT(i); + notifs[i] |= ETHTOOL_PSE_EVENT_OVER_TEMP; + } + } +} + +static int tps23881_irq_event_over_current(struct tps23881_priv *priv, + u16 reg_val, + unsigned long *notifs, + unsigned long *notifs_mask) +{ + int i, ret; + u8 chans; + + chans = tps23881_irq_export_chans_helper(reg_val, 0); + if (!chans) + return 0; + + tps23881_set_notifs_helper(priv, chans, notifs, notifs_mask, + ETHTOOL_PSE_EVENT_OVER_CURRENT | + ETHTOOL_C33_PSE_EVENT_DISCONNECTION); + + /* Over Current event resets the power limit registers so we need + * to configured it again. + */ + for_each_set_bit(i, notifs_mask, priv->pcdev.nr_lines) { + if (priv->port[i].pw_pol < 0) + continue; + + ret = tps23881_pi_enable_manual_pol(priv, i); + if (ret < 0) + return ret; + + /* Set power policy */ + ret = tps23881_pi_set_pw_pol_limit(priv, i, + priv->port[i].pw_pol, + priv->port[i].is_4p); + if (ret < 0) + return ret; + } + + return 0; +} + +static void tps23881_irq_event_disconnection(struct tps23881_priv *priv, + u16 reg_val, + unsigned long *notifs, + unsigned long *notifs_mask) +{ + u8 chans; + + chans = tps23881_irq_export_chans_helper(reg_val, 4); + if (chans) + tps23881_set_notifs_helper(priv, chans, notifs, notifs_mask, + ETHTOOL_C33_PSE_EVENT_DISCONNECTION); +} + +static int tps23881_irq_event_detection(struct tps23881_priv *priv, + u16 reg_val, + unsigned long *notifs, + unsigned long *notifs_mask) +{ + enum ethtool_pse_event event; + int reg, ret, i, val; + unsigned long chans; + + chans = tps23881_irq_export_chans_helper(reg_val, 0); + for_each_set_bit(i, &chans, TPS23881_MAX_CHANS) { + reg = TPS23881_REG_DISC + (i % 4); + ret = i2c_smbus_read_word_data(priv->client, reg); + if (ret < 0) + return ret; + + val = tps23881_calc_val(ret, i, 0, 0xf); + /* If detection valid */ + if (val == 0x4) + event = ETHTOOL_C33_PSE_EVENT_DETECTION; + else + event = ETHTOOL_C33_PSE_EVENT_DISCONNECTION; + + tps23881_set_notifs_helper(priv, BIT(i), notifs, + notifs_mask, event); + } + + return 0; +} + +static int tps23881_irq_event_classification(struct tps23881_priv *priv, + u16 reg_val, + unsigned long *notifs, + unsigned long *notifs_mask) +{ + int reg, ret, val, i; + unsigned long chans; + + chans = tps23881_irq_export_chans_helper(reg_val, 4); + for_each_set_bit(i, &chans, TPS23881_MAX_CHANS) { + reg = TPS23881_REG_DISC + (i % 4); + ret = i2c_smbus_read_word_data(priv->client, reg); + if (ret < 0) + return ret; + + val = tps23881_calc_val(ret, i, 4, 0xf); + /* Do not report classification event for unknown class */ + if (!val || val == 0x8 || val == 0xf) + continue; + + tps23881_set_notifs_helper(priv, BIT(i), notifs, + notifs_mask, + ETHTOOL_C33_PSE_EVENT_CLASSIFICATION); + } + + return 0; +} + +static int tps23881_irq_event_handler(struct tps23881_priv *priv, u16 reg, + unsigned long *notifs, + unsigned long *notifs_mask) +{ + struct i2c_client *client = priv->client; + int ret, val; + + /* The Supply event bit is repeated twice so we only need to read + * the one from the first byte. + */ + if (reg & TPS23881_REG_IT_SUPF) { + ret = i2c_smbus_read_word_data(client, TPS23881_REG_SUPF_EVENT); + if (ret < 0) + return ret; + tps23881_irq_event_over_temp(priv, ret, notifs, notifs_mask); + } + + if (reg & (TPS23881_REG_IT_IFAULT | TPS23881_REG_IT_IFAULT << 8 | + TPS23881_REG_IT_DISF | TPS23881_REG_IT_DISF << 8)) { + ret = i2c_smbus_read_word_data(client, TPS23881_REG_FAULT); + if (ret < 0) + return ret; + ret = tps23881_irq_event_over_current(priv, ret, notifs, + notifs_mask); + if (ret) + return ret; + + tps23881_irq_event_disconnection(priv, ret, notifs, notifs_mask); + } + + if (reg & (TPS23881_REG_IT_DETC | TPS23881_REG_IT_DETC << 8 | + TPS23881_REG_IT_CLASC | TPS23881_REG_IT_CLASC << 8)) { + ret = i2c_smbus_read_word_data(client, TPS23881_REG_DET_EVENT); + if (ret < 0) + return ret; + + val = ret; + ret = tps23881_irq_event_detection(priv, val, notifs, + notifs_mask); + if (ret) + return ret; + + ret = tps23881_irq_event_classification(priv, val, notifs, + notifs_mask); + if (ret) + return ret; + } + return 0; +} + +static int tps23881_irq_handler(int irq, struct pse_controller_dev *pcdev, + unsigned long *notifs, + unsigned long *notifs_mask) +{ + struct tps23881_priv *priv = to_tps23881_priv(pcdev); + struct i2c_client *client = priv->client; + int ret, it_mask, retry; + + /* Get interruption mask */ + ret = i2c_smbus_read_word_data(client, TPS23881_REG_IT_MASK); + if (ret < 0) + return ret; + it_mask = ret; + + /* Read interrupt register until it frees the interruption pin. */ + retry = 0; + while (true) { + if (retry > TPS23881_MAX_IRQ_RETRIES) { + dev_err(&client->dev, "interrupt never freed"); + return -ETIMEDOUT; + } + + ret = i2c_smbus_read_word_data(client, TPS23881_REG_IT); + if (ret < 0) + return ret; + + /* No more relevant interruption */ + if (!(ret & it_mask)) + return 0; + + ret = tps23881_irq_event_handler(priv, (u16)ret, notifs, + notifs_mask); + if (ret) + return ret; + + retry++; + } + return 0; +} + +static int tps23881_setup_irq(struct tps23881_priv *priv, int irq) +{ + struct i2c_client *client = priv->client; + struct pse_irq_desc irq_desc = { + .name = "tps23881-irq", + .map_event = tps23881_irq_handler, + }; + int ret; + u16 val; + + if (!irq) { + dev_err(&client->dev, "interrupt is missing"); + return -EINVAL; + } + + val = TPS23881_REG_IT_IFAULT | TPS23881_REG_IT_SUPF | + TPS23881_REG_IT_DETC | TPS23881_REG_IT_CLASC | + TPS23881_REG_IT_DISF; + val |= val << 8; + ret = i2c_smbus_write_word_data(client, TPS23881_REG_IT_MASK, val); + if (ret) + return ret; + + ret = i2c_smbus_read_word_data(client, TPS23881_REG_GEN_MASK); + if (ret < 0) + return ret; + + val = TPS23881_REG_INTEN | TPS23881_REG_CLCHE | TPS23881_REG_DECHE; + val |= val << 8; + val |= (u16)ret; + ret = i2c_smbus_write_word_data(client, TPS23881_REG_GEN_MASK, val); + if (ret < 0) + return ret; + + /* Reset interrupts registers */ + ret = i2c_smbus_write_word_data(client, TPS23881_REG_RESET, + TPS23881_REG_CLRAIN); + if (ret < 0) + return ret; + + return devm_pse_irq_helper(&priv->pcdev, irq, 0, &irq_desc); +} + static int tps23881_i2c_probe(struct i2c_client *client) { struct device *dev = &client->dev; @@ -1091,12 +1483,17 @@ static int tps23881_i2c_probe(struct i2c_client *client) priv->pcdev.dev = dev; priv->pcdev.types = ETHTOOL_PSE_C33; priv->pcdev.nr_lines = TPS23881_MAX_CHANS; + priv->pcdev.supp_budget_eval_strategies = PSE_BUDGET_EVAL_STRAT_STATIC; ret = devm_pse_controller_register(dev, &priv->pcdev); if (ret) { return dev_err_probe(dev, ret, "failed to register PSE controller\n"); } + ret = tps23881_setup_irq(priv, client->irq); + if (ret) + return ret; + return ret; } diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 97792de896b7..bcde95cb2a2e 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -1485,21 +1485,18 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev, static bool __vxlan_sock_release_prep(struct vxlan_sock *vs) { - struct vxlan_net *vn; + ASSERT_RTNL(); if (!vs) return false; if (!refcount_dec_and_test(&vs->refcnt)) return false; - vn = net_generic(sock_net(vs->sock->sk), vxlan_net_id); - spin_lock(&vn->sock_lock); hlist_del_rcu(&vs->hlist); udp_tunnel_notify_del_rx_port(vs->sock, (vs->flags & VXLAN_F_GPE) ? UDP_TUNNEL_TYPE_VXLAN_GPE : UDP_TUNNEL_TYPE_VXLAN); - spin_unlock(&vn->sock_lock); return true; } @@ -2451,6 +2448,7 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, rcu_read_lock(); if (addr_family == AF_INET) { struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); + u16 ipcb_flags = 0; struct rtable *rt; __be16 df = 0; __be32 saddr; @@ -2467,6 +2465,9 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto tx_error; } + if (flags & VXLAN_F_MC_ROUTE) + ipcb_flags |= IPSKB_MCROUTE; + if (!info) { /* Bypass encapsulation if the destination is local */ err = encap_bypass_if_local(skb, dev, vxlan, AF_INET, @@ -2522,11 +2523,13 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, udp_tunnel_xmit_skb(rt, sock4->sock->sk, skb, saddr, pkey->u.ipv4.dst, tos, ttl, df, - src_port, dst_port, xnet, !udp_sum); + src_port, dst_port, xnet, !udp_sum, + ipcb_flags); #if IS_ENABLED(CONFIG_IPV6) } else { struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock); struct in6_addr saddr; + u16 ip6cb_flags = 0; if (!ifindex) ifindex = sock6->sock->sk->sk_bound_dev_if; @@ -2542,6 +2545,9 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto tx_error; } + if (flags & VXLAN_F_MC_ROUTE) + ip6cb_flags |= IP6SKB_MCROUTE; + if (!info) { u32 rt6i_flags = dst_rt6_info(ndst)->rt6i_flags; @@ -2586,7 +2592,8 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, udp_tunnel6_xmit_skb(ndst, sock6->sock->sk, skb, dev, &saddr, &pkey->u.ipv6.dst, tos, ttl, - pkey->label, src_port, dst_port, !udp_sum); + pkey->label, src_port, dst_port, !udp_sum, + ip6cb_flags); #endif } vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX, pkt_len); @@ -2847,26 +2854,23 @@ static void vxlan_cleanup(struct timer_list *t) static void vxlan_vs_del_dev(struct vxlan_dev *vxlan) { - struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + ASSERT_RTNL(); - spin_lock(&vn->sock_lock); hlist_del_init_rcu(&vxlan->hlist4.hlist); #if IS_ENABLED(CONFIG_IPV6) hlist_del_init_rcu(&vxlan->hlist6.hlist); #endif - spin_unlock(&vn->sock_lock); } static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan, struct vxlan_dev_node *node) { - struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); __be32 vni = vxlan->default_dst.remote_vni; + ASSERT_RTNL(); + node->vxlan = vxlan; - spin_lock(&vn->sock_lock); hlist_add_head_rcu(&node->hlist, vni_head(vs, vni)); - spin_unlock(&vn->sock_lock); } /* Setup stats when device is created */ @@ -3291,9 +3295,10 @@ static void vxlan_offload_rx_ports(struct net_device *dev, bool push) struct vxlan_net *vn = net_generic(net, vxlan_net_id); unsigned int i; - spin_lock(&vn->sock_lock); + ASSERT_RTNL(); + for (i = 0; i < PORT_HASH_SIZE; ++i) { - hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist) { + hlist_for_each_entry(vs, &vn->sock_list[i], hlist) { unsigned short type; if (vs->flags & VXLAN_F_GPE) @@ -3307,7 +3312,6 @@ static void vxlan_offload_rx_ports(struct net_device *dev, bool push) udp_tunnel_drop_rx_port(dev, vs->sock, type); } } - spin_unlock(&vn->sock_lock); } /* Initialize the device structure. */ @@ -3401,6 +3405,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_LOCALBYPASS] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_VXLAN_LABEL_POLICY] = NLA_POLICY_MAX(NLA_U32, VXLAN_LABEL_MAX), [IFLA_VXLAN_RESERVED_BITS] = NLA_POLICY_EXACT_LEN(sizeof(struct vxlanhdr)), + [IFLA_VXLAN_MC_ROUTE] = NLA_POLICY_MAX(NLA_U8, 1), }; static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[], @@ -3537,12 +3542,13 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6, __be16 port, u32 flags, int ifindex) { - struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_sock *vs; struct socket *sock; unsigned int h; struct udp_tunnel_sock_cfg tunnel_cfg; + ASSERT_RTNL(); + vs = kzalloc(sizeof(*vs), GFP_KERNEL); if (!vs) return ERR_PTR(-ENOMEM); @@ -3560,13 +3566,11 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6, refcount_set(&vs->refcnt, 1); vs->flags = (flags & VXLAN_F_RCV_FLAGS); - spin_lock(&vn->sock_lock); hlist_add_head_rcu(&vs->hlist, vs_head(net, port)); udp_tunnel_notify_add_rx_port(sock, (vs->flags & VXLAN_F_GPE) ? UDP_TUNNEL_TYPE_VXLAN_GPE : UDP_TUNNEL_TYPE_VXLAN); - spin_unlock(&vn->sock_lock); /* Mark socket as an encapsulation socket. */ memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); @@ -3590,26 +3594,27 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6, static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6) { - struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); bool metadata = vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA; struct vxlan_sock *vs = NULL; struct vxlan_dev_node *node; int l3mdev_index = 0; + ASSERT_RTNL(); + if (vxlan->cfg.remote_ifindex) l3mdev_index = l3mdev_master_upper_ifindex_by_index( vxlan->net, vxlan->cfg.remote_ifindex); if (!vxlan->cfg.no_share) { - spin_lock(&vn->sock_lock); + rcu_read_lock(); vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET, vxlan->cfg.dst_port, vxlan->cfg.flags, l3mdev_index); if (vs && !refcount_inc_not_zero(&vs->refcnt)) { - spin_unlock(&vn->sock_lock); + rcu_read_unlock(); return -EBUSY; } - spin_unlock(&vn->sock_lock); + rcu_read_unlock(); } if (!vs) vs = vxlan_socket_create(vxlan->net, ipv6, @@ -4314,6 +4319,14 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], return err; } + if (data[IFLA_VXLAN_MC_ROUTE]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_MC_ROUTE, + VXLAN_F_MC_ROUTE, changelink, + true, extack); + if (err) + return err; + } + if (tb[IFLA_MTU]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_MTU], @@ -4875,7 +4888,6 @@ static __net_init int vxlan_init_net(struct net *net) unsigned int h; INIT_LIST_HEAD(&vn->vxlan_list); - spin_lock_init(&vn->sock_lock); vn->nexthop_notifier_block.notifier_call = vxlan_nexthop_event; for (h = 0; h < PORT_HASH_SIZE; ++h) diff --git a/drivers/net/vxlan/vxlan_private.h b/drivers/net/vxlan/vxlan_private.h index d328aed9feef..6c625fb29c6c 100644 --- a/drivers/net/vxlan/vxlan_private.h +++ b/drivers/net/vxlan/vxlan_private.h @@ -19,8 +19,8 @@ extern const struct rhashtable_params vxlan_vni_rht_params; /* per-network namespace private data for this module */ struct vxlan_net { struct list_head vxlan_list; + /* sock_list is protected by rtnl lock */ struct hlist_head sock_list[PORT_HASH_SIZE]; - spinlock_t sock_lock; struct notifier_block nexthop_notifier_block; }; diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c index 186d0660669a..4ff56d9f8f28 100644 --- a/drivers/net/vxlan/vxlan_vnifilter.c +++ b/drivers/net/vxlan/vxlan_vnifilter.c @@ -40,11 +40,11 @@ static void vxlan_vs_add_del_vninode(struct vxlan_dev *vxlan, struct vxlan_vni_node *v, bool del) { - struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); struct vxlan_dev_node *node; struct vxlan_sock *vs; - spin_lock(&vn->sock_lock); + ASSERT_RTNL(); + if (del) { if (!hlist_unhashed(&v->hlist4.hlist)) hlist_del_init_rcu(&v->hlist4.hlist); @@ -52,7 +52,7 @@ static void vxlan_vs_add_del_vninode(struct vxlan_dev *vxlan, if (!hlist_unhashed(&v->hlist6.hlist)) hlist_del_init_rcu(&v->hlist6.hlist); #endif - goto out; + return; } #if IS_ENABLED(CONFIG_IPV6) @@ -67,23 +67,21 @@ static void vxlan_vs_add_del_vninode(struct vxlan_dev *vxlan, node = &v->hlist4; hlist_add_head_rcu(&node->hlist, vni_head(vs, v->vni)); } -out: - spin_unlock(&vn->sock_lock); } void vxlan_vs_add_vnigrp(struct vxlan_dev *vxlan, struct vxlan_sock *vs, bool ipv6) { - struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); struct vxlan_vni_group *vg = rtnl_dereference(vxlan->vnigrp); struct vxlan_vni_node *v, *tmp; struct vxlan_dev_node *node; + ASSERT_RTNL(); + if (!vg) return; - spin_lock(&vn->sock_lock); list_for_each_entry_safe(v, tmp, &vg->vni_list, vlist) { #if IS_ENABLED(CONFIG_IPV6) if (ipv6) @@ -94,26 +92,24 @@ void vxlan_vs_add_vnigrp(struct vxlan_dev *vxlan, node->vxlan = vxlan; hlist_add_head_rcu(&node->hlist, vni_head(vs, v->vni)); } - spin_unlock(&vn->sock_lock); } void vxlan_vs_del_vnigrp(struct vxlan_dev *vxlan) { struct vxlan_vni_group *vg = rtnl_dereference(vxlan->vnigrp); - struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); struct vxlan_vni_node *v, *tmp; + ASSERT_RTNL(); + if (!vg) return; - spin_lock(&vn->sock_lock); list_for_each_entry_safe(v, tmp, &vg->vni_list, vlist) { hlist_del_init_rcu(&v->hlist4.hlist); #if IS_ENABLED(CONFIG_IPV6) hlist_del_init_rcu(&v->hlist6.hlist); #endif } - spin_unlock(&vn->sock_lock); } static void vxlan_vnifilter_stats_get(const struct vxlan_vni_node *vninode, diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c index 0414d7a6ce74..253488f8c00f 100644 --- a/drivers/net/wireguard/socket.c +++ b/drivers/net/wireguard/socket.c @@ -84,7 +84,7 @@ static int send4(struct wg_device *wg, struct sk_buff *skb, skb->ignore_df = 1; udp_tunnel_xmit_skb(rt, sock, skb, fl.saddr, fl.daddr, ds, ip4_dst_hoplimit(&rt->dst), 0, fl.fl4_sport, - fl.fl4_dport, false, false); + fl.fl4_dport, false, false, 0); goto out; err: @@ -151,7 +151,7 @@ static int send6(struct wg_device *wg, struct sk_buff *skb, skb->ignore_df = 1; udp_tunnel6_xmit_skb(dst, sock, skb, skb->dev, &fl.saddr, &fl.daddr, ds, ip6_dst_hoplimit(dst), 0, fl.fl6_sport, - fl.fl6_dport, false); + fl.fl6_dport, false, 0); goto out; err: diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index ef5d655a0052..86ca041bf74a 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -2119,6 +2119,7 @@ static struct irq_chip hv_msi_irq_chip = { static struct msi_domain_ops hv_msi_ops = { .msi_prepare = hv_msi_prepare, .msi_free = hv_msi_free, + .prepare_desc = pci_msix_prepare_desc, }; /** @@ -2140,7 +2141,7 @@ static int hv_pcie_init_irq_domain(struct hv_pcibus_device *hbus) hbus->msi_info.ops = &hv_msi_ops; hbus->msi_info.flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | MSI_FLAG_MULTI_PCI_MSI | - MSI_FLAG_PCI_MSIX); + MSI_FLAG_PCI_MSIX | MSI_FLAG_PCI_MSIX_ALLOC_DYN); hbus->msi_info.handler = FLOW_HANDLER; hbus->msi_info.handler_name = FLOW_NAME; hbus->msi_info.data = hbus; diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index c05152733993..765312c92d9b 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -222,13 +222,14 @@ static void pci_irq_unmask_msix(struct irq_data *data) pci_msix_unmask(irq_data_get_msi_desc(data)); } -static void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg, - struct msi_desc *desc) +void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg, + struct msi_desc *desc) { /* Don't fiddle with preallocated MSI descriptors */ if (!desc->pci.mask_base) msix_prepare_msi_desc(to_pci_dev(desc->dev), desc); } +EXPORT_SYMBOL_GPL(pci_msix_prepare_desc); static const struct msi_domain_template pci_msix_template = { .chip = { diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 35a5994bf64f..335e88d3ebdf 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -96,7 +96,7 @@ static int ptp_clock_settime(struct posix_clock *pc, const struct timespec64 *tp struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock); if (ptp_clock_freerun(ptp)) { - pr_err("ptp: physical clock is free running\n"); + pr_err_ratelimited("ptp: physical clock is free running\n"); return -EBUSY; } diff --git a/include/linux/dpll.h b/include/linux/dpll.h index 5e4f9ab1cf75..6ad6c2968a28 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -30,6 +30,14 @@ struct dpll_device_ops { void *dpll_priv, unsigned long *qls, struct netlink_ext_ack *extack); + int (*phase_offset_monitor_set)(const struct dpll_device *dpll, + void *dpll_priv, + enum dpll_feature_state state, + struct netlink_ext_ack *extack); + int (*phase_offset_monitor_get)(const struct dpll_device *dpll, + void *dpll_priv, + enum dpll_feature_state *state, + struct netlink_ext_ack *extack); }; struct dpll_pin_ops { diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index aba91335273a..1dcc4059b5ab 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -43,6 +43,8 @@ void ethtool_aggregate_rmon_stats(struct net_device *dev, struct ethtool_rmon_stats *rmon_stats); bool ethtool_dev_mm_supported(struct net_device *dev); +void ethnl_pse_send_ntf(struct net_device *netdev, unsigned long notif); + #else static inline int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd) { @@ -120,6 +122,11 @@ static inline bool ethtool_dev_mm_supported(struct net_device *dev) return false; } +static inline void ethnl_pse_send_ntf(struct phy_device *phydev, + unsigned long notif) +{ +} + #endif /* IS_ENABLED(CONFIG_ETHTOOL_NETLINK) */ static inline int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 38456b42cdb5..15e01935d3fa 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -79,11 +79,6 @@ static inline struct vlan_ethhdr *skb_vlan_eth_hdr(const struct sk_buff *skb) /* found in socket.c */ extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *)); -static inline bool is_vlan_dev(const struct net_device *dev) -{ - return dev->priv_flags & IFF_802_1Q_VLAN; -} - #define skb_vlan_tag_present(__skb) (!!(__skb)->vlan_all) #define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci) #define skb_vlan_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK) @@ -136,7 +131,7 @@ struct vlan_pcpu_stats { u32 tx_dropped; }; -#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) +#if IS_ENABLED(CONFIG_VLAN_8021Q) extern struct net_device *__vlan_find_dev_deep_rcu(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id); @@ -200,6 +195,11 @@ struct vlan_dev_priv { #endif }; +static inline bool is_vlan_dev(const struct net_device *dev) +{ + return dev->priv_flags & IFF_802_1Q_VLAN; +} + static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev) { return netdev_priv(dev); @@ -237,6 +237,11 @@ extern void vlan_vids_del_by_dev(struct net_device *dev, extern bool vlan_uses_dev(const struct net_device *dev); #else +static inline bool is_vlan_dev(const struct net_device *dev) +{ + return false; +} + static inline struct net_device * __vlan_find_dev_deep_rcu(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id) @@ -254,19 +259,19 @@ vlan_for_each(struct net_device *dev, static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev) { - BUG(); + WARN_ON_ONCE(1); return NULL; } static inline u16 vlan_dev_vlan_id(const struct net_device *dev) { - BUG(); + WARN_ON_ONCE(1); return 0; } static inline __be16 vlan_dev_vlan_proto(const struct net_device *dev) { - BUG(); + WARN_ON_ONCE(1); return 0; } diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 5aeeed22f35b..db0eb0d86b64 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -156,6 +156,7 @@ struct inet6_skb_parm { #define IP6SKB_SEG6 256 #define IP6SKB_FAKEJUMBO 512 #define IP6SKB_MULTIPATH 1024 +#define IP6SKB_MCROUTE 2048 }; #if defined(CONFIG_NET_L3_MASTER_DEV) diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index 63ef5191cc57..fddafdc168f7 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -31,6 +31,7 @@ extern int ip6_mroute_getsockopt(struct sock *, int, sockptr_t, sockptr_t); extern int ip6_mr_input(struct sk_buff *skb); extern int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); extern int ip6_mr_init(void); +extern int ip6_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb); extern void ip6_mr_cleanup(void); int ip6mr_ioctl(struct sock *sk, int cmd, void *arg); #else @@ -58,6 +59,12 @@ static inline int ip6_mr_init(void) return 0; } +static inline int +ip6_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + return ip6_output(net, sk, skb); +} + static inline void ip6_mr_cleanup(void) { return; diff --git a/include/linux/msi.h b/include/linux/msi.h index 6863540f4b71..7f254bde5426 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -706,6 +706,8 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, struct irq_domain *parent); u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev); struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev); +void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg, + struct msi_desc *desc); #else /* CONFIG_PCI_MSI */ static inline struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev) { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index adb14db25798..9cbc4e54b7e4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2388,7 +2388,7 @@ struct net_device { struct dm_hw_stat_delta __rcu *dm_private; #endif struct device dev; - const struct attribute_group *sysfs_groups[4]; + const struct attribute_group *sysfs_groups[5]; const struct attribute_group *sysfs_rx_queue_group; const struct rtnl_link_ops *rtnl_link_ops; diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 0477208ed9ff..735e65c3cc11 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -42,6 +42,13 @@ struct netpoll { struct work_struct refill_wq; }; +#define np_info(np, fmt, ...) \ + pr_info("%s: " fmt, np->name, ##__VA_ARGS__) +#define np_err(np, fmt, ...) \ + pr_err("%s: " fmt, np->name, ##__VA_ARGS__) +#define np_notice(np, fmt, ...) \ + pr_notice("%s: " fmt, np->name, ##__VA_ARGS__) + struct netpoll_info { refcount_t refcnt; @@ -65,11 +72,8 @@ static inline void netpoll_poll_enable(struct net_device *dev) { return; } #endif int netpoll_send_udp(struct netpoll *np, const char *msg, int len); -void netpoll_print_options(struct netpoll *np); -int netpoll_parse_options(struct netpoll *np, char *opt); int __netpoll_setup(struct netpoll *np, struct net_device *ndev); int netpoll_setup(struct netpoll *np); -void __netpoll_cleanup(struct netpoll *np); void __netpoll_free(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); void do_netpoll_cleanup(struct netpoll *np); diff --git a/include/linux/phy.h b/include/linux/phy.h index c4d8f7c82627..b037aab7b71d 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -269,8 +269,10 @@ static inline const char *phy_modes(phy_interface_t interface) * rgmii_clock - map link speed to the clock rate * @speed: link speed value * - * Description: maps RGMII supported link speeds - * into the clock rates. + * Description: maps RGMII supported link speeds into the clock rates. + * This can also be used for MII, GMII, and RMII interface modes as the + * clock rates are indentical, but the caller must be aware that errors + * for unsupported clock rates will not be signalled. * * Returns: clock rate or negative errno */ @@ -526,6 +528,7 @@ struct macsec_ops; * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY * @wol_enabled: Set to true if the PHY or the attached MAC have Wake-on-LAN * enabled. + * @is_genphy_driven: PHY is driven by one of the generic PHY drivers * @state: State of the PHY for management purposes * @dev_flags: Device-specific flags used by the PHY driver. * @@ -629,6 +632,7 @@ struct phy_device { unsigned is_on_sfp_module:1; unsigned mac_managed_pm:1; unsigned wol_enabled:1; + unsigned is_genphy_driven:1; unsigned autoneg:1; /* The most recently read link state */ @@ -1292,6 +1296,17 @@ static inline bool phy_is_started(struct phy_device *phydev) } /** + * phy_driver_is_genphy - Convenience function to check whether PHY is driven + * by one of the generic PHY drivers + * @phydev: The phy_device struct + * Return: true if PHY is driven by one of the genphy drivers + */ +static inline bool phy_driver_is_genphy(struct phy_device *phydev) +{ + return phydev->is_genphy_driven; +} + +/** * phy_disable_eee_mode - Don't advertise an EEE mode. * @phydev: The phy_device struct * @link_mode: The EEE mode to be disabled @@ -2093,7 +2108,4 @@ module_exit(phy_module_exit) #define module_phy_driver(__phy_drivers) \ phy_module_driver(__phy_drivers, ARRAY_SIZE(__phy_drivers)) -bool phy_driver_is_genphy(struct phy_device *phydev); -bool phy_driver_is_genphy_10g(struct phy_device *phydev); - #endif /* __PHY_H */ diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index c773eeb92d04..e5f305cef82e 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -6,13 +6,18 @@ #define _LINUX_PSE_CONTROLLER_H #include <linux/list.h> +#include <linux/netlink.h> +#include <linux/kfifo.h> #include <uapi/linux/ethtool.h> +#include <uapi/linux/ethtool_netlink_generated.h> +#include <linux/regulator/driver.h> /* Maximum current in uA according to IEEE 802.3-2022 Table 145-1 */ #define MAX_PI_CURRENT 1920000 /* Maximum power in mW according to IEEE 802.3-2022 Table 145-16 */ #define MAX_PI_PW 99900 +struct net_device; struct phy_device; struct pse_controller_dev; struct netlink_ext_ack; @@ -38,6 +43,19 @@ struct ethtool_c33_pse_pw_limit_range { }; /** + * struct pse_irq_desc - notification sender description for IRQ based events. + * + * @name: the visible name for the IRQ + * @map_event: driver callback to map IRQ status into PSE devices with events. + */ +struct pse_irq_desc { + const char *name; + int (*map_event)(int irq, struct pse_controller_dev *pcdev, + unsigned long *notifs, + unsigned long *notifs_mask); +}; + +/** * struct pse_control_config - PSE control/channel configuration. * * @podl_admin_control: set PoDL PSE admin control as described in @@ -98,6 +116,7 @@ struct pse_pw_limit_ranges { /** * struct ethtool_pse_control_status - PSE control/channel status. * + * @pw_d_id: PSE power domain index. * @podl_admin_state: operational state of the PoDL PSE * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState * @podl_pw_status: power detection status of the PoDL PSE. @@ -117,8 +136,12 @@ struct pse_pw_limit_ranges { * is in charge of the memory allocation * @c33_pw_limit_nb_ranges: number of supported power limit configuration * ranges + * @prio_max: max priority allowed for the c33_prio variable value. + * @prio: priority of the PSE. Managed by PSE core in case of static budget + * evaluation strategy. */ struct ethtool_pse_control_status { + u32 pw_d_id; enum ethtool_podl_pse_admin_state podl_admin_state; enum ethtool_podl_pse_pw_d_status podl_pw_status; enum ethtool_c33_pse_admin_state c33_admin_state; @@ -129,6 +152,8 @@ struct ethtool_pse_control_status { u32 c33_avail_pw_limit; struct ethtool_c33_pse_pw_limit_range *c33_pw_limit_ranges; u32 c33_pw_limit_nb_ranges; + u32 prio_max; + u32 prio; }; /** @@ -152,6 +177,11 @@ struct ethtool_pse_control_status { * range. The driver is in charge of the memory * allocation and should return the number of * ranges. + * @pi_get_prio: Get the PSE PI priority. + * @pi_set_prio: Configure the PSE PI priority. + * @pi_get_pw_req: Get the power requested by a PD before enabling the PSE PI. + * This is only relevant when an interrupt is registered using + * devm_pse_irq_helper helper. */ struct pse_controller_ops { int (*setup_pi_matrix)(struct pse_controller_dev *pcdev); @@ -172,6 +202,10 @@ struct pse_controller_ops { int id, int max_mW); int (*pi_get_pw_limit_ranges)(struct pse_controller_dev *pcdev, int id, struct pse_pw_limit_ranges *pw_limit_ranges); + int (*pi_get_prio)(struct pse_controller_dev *pcdev, int id); + int (*pi_set_prio)(struct pse_controller_dev *pcdev, int id, + unsigned int prio); + int (*pi_get_pw_req)(struct pse_controller_dev *pcdev, int id); }; struct module; @@ -206,12 +240,35 @@ struct pse_pi_pairset { * @np: device node pointer of the PSE PI node * @rdev: regulator represented by the PSE PI * @admin_state_enabled: PI enabled state + * @pw_d: Power domain of the PSE PI + * @prio: Priority of the PSE PI. Used in static budget evaluation strategy + * @isr_pd_detected: PSE PI detection status managed by the interruption + * handler. This variable is relevant when the power enabled + * management is managed in software like the static + * budget evaluation strategy. + * @pw_allocated_mW: Power allocated to a PSE PI to manage power budget in + * static budget evaluation strategy. */ struct pse_pi { struct pse_pi_pairset pairset[2]; struct device_node *np; struct regulator_dev *rdev; bool admin_state_enabled; + struct pse_power_domain *pw_d; + int prio; + bool isr_pd_detected; + int pw_allocated_mW; +}; + +/** + * struct pse_ntf - PSE notification element + * + * @id: ID of the PSE control + * @notifs: PSE notifications to be reported + */ +struct pse_ntf { + int id; + unsigned long notifs; }; /** @@ -228,6 +285,13 @@ struct pse_pi { * @types: types of the PSE controller * @pi: table of PSE PIs described in this controller device * @no_of_pse_pi: flag set if the pse_pis devicetree node is not used + * @irq: PSE interrupt + * @pis_prio_max: Maximum value allowed for the PSE PIs priority + * @supp_budget_eval_strategies: budget evaluation strategies supported + * by the PSE + * @ntf_work: workqueue for PSE notification management + * @ntf_fifo: PSE notifications FIFO + * @ntf_fifo_lock: protect @ntf_fifo writer */ struct pse_controller_dev { const struct pse_controller_ops *ops; @@ -241,6 +305,30 @@ struct pse_controller_dev { enum ethtool_pse_types types; struct pse_pi *pi; bool no_of_pse_pi; + int irq; + unsigned int pis_prio_max; + u32 supp_budget_eval_strategies; + struct work_struct ntf_work; + DECLARE_KFIFO_PTR(ntf_fifo, struct pse_ntf); + spinlock_t ntf_fifo_lock; /* Protect @ntf_fifo writer */ +}; + +/** + * enum pse_budget_eval_strategies - PSE budget evaluation strategies. + * @PSE_BUDGET_EVAL_STRAT_DISABLED: Budget evaluation strategy disabled. + * @PSE_BUDGET_EVAL_STRAT_STATIC: PSE static budget evaluation strategy. + * Budget evaluation strategy based on the power requested during PD + * classification. This strategy is managed by the PSE core. + * @PSE_BUDGET_EVAL_STRAT_DYNAMIC: PSE dynamic budget evaluation + * strategy. Budget evaluation strategy based on the current consumption + * per ports compared to the total power budget. This mode is managed by + * the PSE controller. + */ + +enum pse_budget_eval_strategies { + PSE_BUDGET_EVAL_STRAT_DISABLED = 1 << 0, + PSE_BUDGET_EVAL_STRAT_STATIC = 1 << 1, + PSE_BUDGET_EVAL_STRAT_DYNAMIC = 1 << 2, }; #if IS_ENABLED(CONFIG_PSE_CONTROLLER) @@ -249,8 +337,11 @@ void pse_controller_unregister(struct pse_controller_dev *pcdev); struct device; int devm_pse_controller_register(struct device *dev, struct pse_controller_dev *pcdev); +int devm_pse_irq_helper(struct pse_controller_dev *pcdev, int irq, + int irq_flags, const struct pse_irq_desc *d); -struct pse_control *of_pse_control_get(struct device_node *node); +struct pse_control *of_pse_control_get(struct device_node *node, + struct phy_device *phydev); void pse_control_put(struct pse_control *psec); int pse_ethtool_get_status(struct pse_control *psec, @@ -262,13 +353,17 @@ int pse_ethtool_set_config(struct pse_control *psec, int pse_ethtool_set_pw_limit(struct pse_control *psec, struct netlink_ext_ack *extack, const unsigned int pw_limit); +int pse_ethtool_set_prio(struct pse_control *psec, + struct netlink_ext_ack *extack, + unsigned int prio); bool pse_has_podl(struct pse_control *psec); bool pse_has_c33(struct pse_control *psec); #else -static inline struct pse_control *of_pse_control_get(struct device_node *node) +static inline struct pse_control *of_pse_control_get(struct device_node *node, + struct phy_device *phydev) { return ERR_PTR(-ENOENT); } @@ -298,6 +393,13 @@ static inline int pse_ethtool_set_pw_limit(struct pse_control *psec, return -EOPNOTSUPP; } +static inline int pse_ethtool_set_prio(struct pse_control *psec, + struct netlink_ext_ack *extack, + unsigned int prio) +{ + return -EOPNOTSUPP; +} + static inline bool pse_has_podl(struct pse_control *psec) { return false; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5520524c93bf..9508968cb300 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3873,20 +3873,26 @@ static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int l bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) __must_check; -static inline bool skb_can_coalesce(struct sk_buff *skb, int i, - const struct page *page, int off) +static inline bool skb_can_coalesce_netmem(struct sk_buff *skb, int i, + netmem_ref netmem, int off) { if (skb_zcopy(skb)) return false; if (i) { const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; - return page == skb_frag_page(frag) && + return netmem == skb_frag_netmem(frag) && off == skb_frag_off(frag) + skb_frag_size(frag); } return false; } +static inline bool skb_can_coalesce(struct sk_buff *skb, int i, + const struct page *page, int off) +{ + return skb_can_coalesce_netmem(skb, i, page_to_netmem(page), off); +} + static inline int __skb_linearize(struct sk_buff *skb) { return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM; diff --git a/include/linux/soc/marvell/silicons.h b/include/linux/soc/marvell/silicons.h new file mode 100644 index 000000000000..66bb9bfaf17d --- /dev/null +++ b/include/linux/soc/marvell/silicons.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * Copyright (C) 2024 Marvell. + */ + +#ifndef __SOC_SILICON_H +#define __SOC_SILICON_H + +#include <linux/types.h> +#include <linux/pci.h> + +#if defined(CONFIG_ARM64) + +#define CN20K_CHIPID 0x20 +/* + * Silicon check for CN20K family + */ +static inline bool is_cn20k(struct pci_dev *pdev) +{ + return (pdev->subsystem_device & 0xFF) == CN20K_CHIPID; +} +#else +#define is_cn20k(pdev) ((void)(pdev), 0) +#endif + +#endif /* __SOC_SILICON_H */ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 29f59d50dc73..1a5737b3753d 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -208,7 +208,6 @@ struct tcp_sock { u32 notsent_lowat; /* TCP_NOTSENT_LOWAT */ u16 gso_segs; /* Max number of segs per GSO packet */ /* from STCP, retrans queue hinting */ - struct sk_buff *lost_skb_hint; struct sk_buff *retransmit_skb_hint; __cacheline_group_end(tcp_sock_read_tx); @@ -419,8 +418,6 @@ struct tcp_sock { struct tcp_sack_block recv_sack_cache[4]; - int lost_cnt_hint; - u32 prior_ssthresh; /* ssthresh saved at recovery start */ u32 high_seq; /* snd_nxt at onset of congestion */ diff --git a/include/net/devlink.h b/include/net/devlink.h index 0091f23a40f7..63517646a497 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -520,6 +520,7 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_ENABLE_IWARP, DEVLINK_PARAM_GENERIC_ID_IO_EQ_SIZE, DEVLINK_PARAM_GENERIC_ID_EVENT_EQ_SIZE, + DEVLINK_PARAM_GENERIC_ID_ENABLE_PHC, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, @@ -578,6 +579,9 @@ enum devlink_param_generic_id { #define DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_NAME "event_eq_size" #define DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_TYPE DEVLINK_PARAM_TYPE_U32 +#define DEVLINK_PARAM_GENERIC_ENABLE_PHC_NAME "enable_phc" +#define DEVLINK_PARAM_GENERIC_ENABLE_PHC_TYPE DEVLINK_PARAM_TYPE_BOOL + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ diff --git a/include/net/dsa.h b/include/net/dsa.h index 55e2d97f247e..d73ea0880066 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -54,11 +54,13 @@ struct tc_action; #define DSA_TAG_PROTO_RZN1_A5PSW_VALUE 26 #define DSA_TAG_PROTO_LAN937X_VALUE 27 #define DSA_TAG_PROTO_VSC73XX_8021Q_VALUE 28 +#define DSA_TAG_PROTO_BRCM_LEGACY_FCS_VALUE 29 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, DSA_TAG_PROTO_BRCM = DSA_TAG_PROTO_BRCM_VALUE, DSA_TAG_PROTO_BRCM_LEGACY = DSA_TAG_PROTO_BRCM_LEGACY_VALUE, + DSA_TAG_PROTO_BRCM_LEGACY_FCS = DSA_TAG_PROTO_BRCM_LEGACY_FCS_VALUE, DSA_TAG_PROTO_BRCM_PREPEND = DSA_TAG_PROTO_BRCM_PREPEND_VALUE, DSA_TAG_PROTO_DSA = DSA_TAG_PROTO_DSA_VALUE, DSA_TAG_PROTO_EDSA = DSA_TAG_PROTO_EDSA_VALUE, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 4564b5d348b1..ae09e91398a5 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -202,12 +202,6 @@ static inline spinlock_t *inet_ehash_lockp( int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo); -static inline void inet_hashinfo2_free_mod(struct inet_hashinfo *h) -{ - kfree(h->lhash2); - h->lhash2 = NULL; -} - static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo) { kvfree(hashinfo->ehash_locks); diff --git a/include/net/ip.h b/include/net/ip.h index 47ed6d23853d..375304bb99f6 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -59,6 +59,7 @@ struct inet_skb_parm { #define IPSKB_L3SLAVE BIT(7) #define IPSKB_NOPOLICY BIT(8) #define IPSKB_MULTIPATH BIT(9) +#define IPSKB_MCROUTE BIT(10) u16 frag_max_size; }; @@ -167,6 +168,7 @@ void ip_list_rcv(struct list_head *head, struct packet_type *pt, int ip_local_deliver(struct sk_buff *skb); void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int proto); int ip_mr_input(struct sk_buff *skb); +int ip_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 399592405c72..dd163495f353 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -152,11 +152,12 @@ int ip6_tnl_get_iflink(const struct net_device *dev); int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu); static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, - struct net_device *dev) + struct net_device *dev, u16 ip6cb_flags) { int pkt_len, err; memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); + IP6CB(skb)->flags = ip6cb_flags; pkt_len = skb->len - skb_inner_network_offset(skb); err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb); diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 0c3d571a04a1..8cf1380f3656 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -603,7 +603,7 @@ static inline int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, u8 proto, - u8 tos, u8 ttl, __be16 df, bool xnet); + u8 tos, u8 ttl, __be16 df, bool xnet, u16 ipcb_flags); struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags); int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst, diff --git a/include/net/libeth/rx.h b/include/net/libeth/rx.h index ab05024be518..5d991404845e 100644 --- a/include/net/libeth/rx.h +++ b/include/net/libeth/rx.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/* Copyright (C) 2024 Intel Corporation */ +/* Copyright (C) 2024-2025 Intel Corporation */ #ifndef __LIBETH_RX_H #define __LIBETH_RX_H @@ -13,8 +13,10 @@ /* Space reserved in front of each frame */ #define LIBETH_SKB_HEADROOM (NET_SKB_PAD + NET_IP_ALIGN) +#define LIBETH_XDP_HEADROOM (ALIGN(XDP_PACKET_HEADROOM, NET_SKB_PAD) + \ + NET_IP_ALIGN) /* Maximum headroom for worst-case calculations */ -#define LIBETH_MAX_HEADROOM LIBETH_SKB_HEADROOM +#define LIBETH_MAX_HEADROOM LIBETH_XDP_HEADROOM /* Link layer / L2 overhead: Ethernet, 2 VLAN tags (C + S), FCS */ #define LIBETH_RX_LL_LEN (ETH_HLEN + 2 * VLAN_HLEN + ETH_FCS_LEN) /* Maximum supported L2-L4 header length */ @@ -31,7 +33,7 @@ /** * struct libeth_fqe - structure representing an Rx buffer (fill queue element) - * @page: page holding the buffer + * @netmem: network memory reference holding the buffer * @offset: offset from the page start (to the headroom) * @truesize: total space occupied by the buffer (w/ headroom and tailroom) * @@ -40,7 +42,7 @@ * former, @offset is always 0 and @truesize is always ```PAGE_SIZE```. */ struct libeth_fqe { - struct page *page; + netmem_ref netmem; u32 offset; u32 truesize; } __aligned_largest; @@ -66,6 +68,7 @@ enum libeth_fqe_type { * @count: number of descriptors/buffers the queue has * @type: type of the buffers this queue has * @hsplit: flag whether header split is enabled + * @xdp: flag indicating whether XDP is enabled * @buf_len: HW-writeable length per each buffer * @nid: ID of the closest NUMA node with memory */ @@ -81,6 +84,7 @@ struct libeth_fq { /* Cold fields */ enum libeth_fqe_type type:2; bool hsplit:1; + bool xdp:1; u32 buf_len; int nid; @@ -102,15 +106,16 @@ static inline dma_addr_t libeth_rx_alloc(const struct libeth_fq_fp *fq, u32 i) struct libeth_fqe *buf = &fq->fqes[i]; buf->truesize = fq->truesize; - buf->page = page_pool_dev_alloc(fq->pp, &buf->offset, &buf->truesize); - if (unlikely(!buf->page)) + buf->netmem = page_pool_dev_alloc_netmem(fq->pp, &buf->offset, + &buf->truesize); + if (unlikely(!buf->netmem)) return DMA_MAPPING_ERROR; - return page_pool_get_dma_addr(buf->page) + buf->offset + + return page_pool_get_dma_addr_netmem(buf->netmem) + buf->offset + fq->pp->p.offset; } -void libeth_rx_recycle_slow(struct page *page); +void libeth_rx_recycle_slow(netmem_ref netmem); /** * libeth_rx_sync_for_cpu - synchronize or recycle buffer post DMA @@ -126,18 +131,19 @@ void libeth_rx_recycle_slow(struct page *page); static inline bool libeth_rx_sync_for_cpu(const struct libeth_fqe *fqe, u32 len) { - struct page *page = fqe->page; + netmem_ref netmem = fqe->netmem; /* Very rare, but possible case. The most common reason: * the last fragment contained FCS only, which was then * stripped by the HW. */ if (unlikely(!len)) { - libeth_rx_recycle_slow(page); + libeth_rx_recycle_slow(netmem); return false; } - page_pool_dma_sync_for_cpu(page->pp, page, fqe->offset, len); + page_pool_dma_sync_netmem_for_cpu(netmem_get_pp(netmem), netmem, + fqe->offset, len); return true; } diff --git a/include/net/libeth/tx.h b/include/net/libeth/tx.h index 35614f9523f6..c3db5c6f1641 100644 --- a/include/net/libeth/tx.h +++ b/include/net/libeth/tx.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/* Copyright (C) 2024 Intel Corporation */ +/* Copyright (C) 2024-2025 Intel Corporation */ #ifndef __LIBETH_TX_H #define __LIBETH_TX_H @@ -12,11 +12,17 @@ /** * enum libeth_sqe_type - type of &libeth_sqe to act on Tx completion - * @LIBETH_SQE_EMPTY: unused/empty, no action required + * @LIBETH_SQE_EMPTY: unused/empty OR XDP_TX/XSk frame, no action required * @LIBETH_SQE_CTX: context descriptor with empty SQE, no action required * @LIBETH_SQE_SLAB: kmalloc-allocated buffer, unmap and kfree() * @LIBETH_SQE_FRAG: mapped skb frag, only unmap DMA * @LIBETH_SQE_SKB: &sk_buff, unmap and napi_consume_skb(), update stats + * @__LIBETH_SQE_XDP_START: separator between skb and XDP types + * @LIBETH_SQE_XDP_TX: &skb_shared_info, libeth_xdp_return_buff_bulk(), stats + * @LIBETH_SQE_XDP_XMIT: &xdp_frame, unmap and xdp_return_frame_bulk(), stats + * @LIBETH_SQE_XDP_XMIT_FRAG: &xdp_frame frag, only unmap DMA + * @LIBETH_SQE_XSK_TX: &libeth_xdp_buff on XSk queue, xsk_buff_free(), stats + * @LIBETH_SQE_XSK_TX_FRAG: &libeth_xdp_buff frag on XSk queue, xsk_buff_free() */ enum libeth_sqe_type { LIBETH_SQE_EMPTY = 0U, @@ -24,6 +30,13 @@ enum libeth_sqe_type { LIBETH_SQE_SLAB, LIBETH_SQE_FRAG, LIBETH_SQE_SKB, + + __LIBETH_SQE_XDP_START, + LIBETH_SQE_XDP_TX = __LIBETH_SQE_XDP_START, + LIBETH_SQE_XDP_XMIT, + LIBETH_SQE_XDP_XMIT_FRAG, + LIBETH_SQE_XSK_TX, + LIBETH_SQE_XSK_TX_FRAG, }; /** @@ -32,6 +45,9 @@ enum libeth_sqe_type { * @rs_idx: index of the last buffer from the batch this one was sent in * @raw: slab buffer to free via kfree() * @skb: &sk_buff to consume + * @sinfo: skb shared info of an XDP_TX frame + * @xdpf: XDP frame from ::ndo_xdp_xmit() + * @xsk: XSk Rx frame from XDP_TX action * @dma: DMA address to unmap * @len: length of the mapped region to unmap * @nr_frags: number of frags in the frame this buffer belongs to @@ -46,6 +62,9 @@ struct libeth_sqe { union { void *raw; struct sk_buff *skb; + struct skb_shared_info *sinfo; + struct xdp_frame *xdpf; + struct libeth_xdp_buff *xsk; }; DEFINE_DMA_UNMAP_ADDR(dma); @@ -71,7 +90,10 @@ struct libeth_sqe { /** * struct libeth_cq_pp - completion queue poll params * @dev: &device to perform DMA unmapping + * @bq: XDP frame bulk to combine return operations * @ss: onstack NAPI stats to fill + * @xss: onstack XDPSQ NAPI stats to fill + * @xdp_tx: number of XDP-not-XSk frames processed * @napi: whether it's called from the NAPI context * * libeth uses this structure to access objects needed for performing full @@ -80,7 +102,13 @@ struct libeth_sqe { */ struct libeth_cq_pp { struct device *dev; - struct libeth_sq_napi_stats *ss; + struct xdp_frame_bulk *bq; + + union { + struct libeth_sq_napi_stats *ss; + struct libeth_xdpsq_napi_stats *xss; + }; + u32 xdp_tx; bool napi; }; @@ -126,4 +154,6 @@ static inline void libeth_tx_complete(struct libeth_sqe *sqe, sqe->type = LIBETH_SQE_EMPTY; } +void libeth_tx_complete_any(struct libeth_sqe *sqe, struct libeth_cq_pp *cp); + #endif /* __LIBETH_TX_H */ diff --git a/include/net/libeth/types.h b/include/net/libeth/types.h index 603825e45133..cf1d78a9dc38 100644 --- a/include/net/libeth/types.h +++ b/include/net/libeth/types.h @@ -1,10 +1,32 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/* Copyright (C) 2024 Intel Corporation */ +/* Copyright (C) 2024-2025 Intel Corporation */ #ifndef __LIBETH_TYPES_H #define __LIBETH_TYPES_H -#include <linux/types.h> +#include <linux/workqueue.h> + +/* Stats */ + +/** + * struct libeth_rq_napi_stats - "hot" counters to update in Rx polling loop + * @packets: received frames counter + * @bytes: sum of bytes of received frames above + * @fragments: sum of fragments of received S/G frames + * @hsplit: number of frames the device performed the header split for + * @raw: alias to access all the fields as an array + */ +struct libeth_rq_napi_stats { + union { + struct { + u32 packets; + u32 bytes; + u32 fragments; + u32 hsplit; + }; + DECLARE_FLEX_ARRAY(u32, raw); + }; +}; /** * struct libeth_sq_napi_stats - "hot" counters to update in Tx completion loop @@ -22,4 +44,84 @@ struct libeth_sq_napi_stats { }; }; +/** + * struct libeth_xdpsq_napi_stats - "hot" counters to update in XDP Tx + * completion loop + * @packets: completed frames counter + * @bytes: sum of bytes of completed frames above + * @fragments: sum of fragments of completed S/G frames + * @raw: alias to access all the fields as an array + */ +struct libeth_xdpsq_napi_stats { + union { + struct { + u32 packets; + u32 bytes; + u32 fragments; + }; + DECLARE_FLEX_ARRAY(u32, raw); + }; +}; + +/* XDP */ + +/* + * The following structures should be embedded into driver's queue structure + * and passed to the libeth_xdp helpers, never used directly. + */ + +/* XDPSQ sharing */ + +/** + * struct libeth_xdpsq_lock - locking primitive for sharing XDPSQs + * @lock: spinlock for locking the queue + * @share: whether this particular queue is shared + */ +struct libeth_xdpsq_lock { + spinlock_t lock; + bool share; +}; + +/* XDPSQ clean-up timers */ + +/** + * struct libeth_xdpsq_timer - timer for cleaning up XDPSQs w/o interrupts + * @xdpsq: queue this timer belongs to + * @lock: lock for the queue + * @dwork: work performing cleanups + * + * XDPSQs not using interrupts but lazy cleaning, i.e. only when there's no + * space for sending the current queued frame/bulk, must fire up timers to + * make sure there are no stale buffers to free. + */ +struct libeth_xdpsq_timer { + void *xdpsq; + struct libeth_xdpsq_lock *lock; + + struct delayed_work dwork; +}; + +/* Rx polling path */ + +/** + * struct libeth_xdp_buff_stash - struct for stashing &xdp_buff onto a queue + * @data: pointer to the start of the frame, xdp_buff.data + * @headroom: frame headroom, xdp_buff.data - xdp_buff.data_hard_start + * @len: frame linear space length, xdp_buff.data_end - xdp_buff.data + * @frame_sz: truesize occupied by the frame, xdp_buff.frame_sz + * @flags: xdp_buff.flags + * + * &xdp_buff is 56 bytes long on x64, &libeth_xdp_buff is 64 bytes. This + * structure carries only necessary fields to save/restore a partially built + * frame on the queue structure to finish it during the next NAPI poll. + */ +struct libeth_xdp_buff_stash { + void *data; + u16 headroom; + u16 len; + + u32 frame_sz:24; + u32 flags:8; +} __aligned_largest; + #endif /* __LIBETH_TYPES_H */ diff --git a/include/net/libeth/xdp.h b/include/net/libeth/xdp.h new file mode 100644 index 000000000000..6ce6aec6884c --- /dev/null +++ b/include/net/libeth/xdp.h @@ -0,0 +1,1879 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2025 Intel Corporation */ + +#ifndef __LIBETH_XDP_H +#define __LIBETH_XDP_H + +#include <linux/bpf_trace.h> +#include <linux/unroll.h> + +#include <net/libeth/rx.h> +#include <net/libeth/tx.h> +#include <net/xsk_buff_pool.h> + +/* + * Defined as bits to be able to use them as a mask on Rx. + * Also used as internal return values on Tx. + */ +enum { + LIBETH_XDP_PASS = 0U, + LIBETH_XDP_DROP = BIT(0), + LIBETH_XDP_ABORTED = BIT(1), + LIBETH_XDP_TX = BIT(2), + LIBETH_XDP_REDIRECT = BIT(3), +}; + +/* + * &xdp_buff_xsk is the largest structure &libeth_xdp_buff gets casted to, + * pick maximum pointer-compatible alignment. + */ +#define __LIBETH_XDP_BUFF_ALIGN \ + (IS_ALIGNED(sizeof(struct xdp_buff_xsk), 16) ? 16 : \ + IS_ALIGNED(sizeof(struct xdp_buff_xsk), 8) ? 8 : \ + sizeof(long)) + +/** + * struct libeth_xdp_buff - libeth extension over &xdp_buff + * @base: main &xdp_buff + * @data: shortcut for @base.data + * @desc: RQ descriptor containing metadata for this buffer + * @priv: driver-private scratchspace + * + * The main reason for this is to have a pointer to the descriptor to be able + * to quickly get frame metadata from xdpmo and driver buff-to-xdp callbacks + * (as well as bigger alignment). + * Pointer/layout-compatible with &xdp_buff and &xdp_buff_xsk. + */ +struct libeth_xdp_buff { + union { + struct xdp_buff base; + void *data; + }; + + const void *desc; + unsigned long priv[] + __aligned(__LIBETH_XDP_BUFF_ALIGN); +} __aligned(__LIBETH_XDP_BUFF_ALIGN); +static_assert(offsetof(struct libeth_xdp_buff, data) == + offsetof(struct xdp_buff_xsk, xdp.data)); +static_assert(offsetof(struct libeth_xdp_buff, desc) == + offsetof(struct xdp_buff_xsk, cb)); +static_assert(IS_ALIGNED(sizeof(struct xdp_buff_xsk), + __alignof(struct libeth_xdp_buff))); + +/** + * __LIBETH_XDP_ONSTACK_BUFF - declare a &libeth_xdp_buff on the stack + * @name: name of the variable to declare + * @...: sizeof() of the driver-private data + */ +#define __LIBETH_XDP_ONSTACK_BUFF(name, ...) \ + ___LIBETH_XDP_ONSTACK_BUFF(name, ##__VA_ARGS__) +/** + * LIBETH_XDP_ONSTACK_BUFF - declare a &libeth_xdp_buff on the stack + * @name: name of the variable to declare + * @...: type or variable name of the driver-private data + */ +#define LIBETH_XDP_ONSTACK_BUFF(name, ...) \ + __LIBETH_XDP_ONSTACK_BUFF(name, __libeth_xdp_priv_sz(__VA_ARGS__)) + +#define ___LIBETH_XDP_ONSTACK_BUFF(name, ...) \ + __DEFINE_FLEX(struct libeth_xdp_buff, name, priv, \ + LIBETH_XDP_PRIV_SZ(__VA_ARGS__ + 0), \ + __uninitialized); \ + LIBETH_XDP_ASSERT_PRIV_SZ(__VA_ARGS__ + 0) + +#define __libeth_xdp_priv_sz(...) \ + CONCATENATE(__libeth_xdp_psz, COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__) + +#define __libeth_xdp_psz0(...) +#define __libeth_xdp_psz1(...) sizeof(__VA_ARGS__) + +#define LIBETH_XDP_PRIV_SZ(sz) \ + (ALIGN(sz, __alignof(struct libeth_xdp_buff)) / sizeof(long)) + +/* Performs XSK_CHECK_PRIV_TYPE() */ +#define LIBETH_XDP_ASSERT_PRIV_SZ(sz) \ + static_assert(offsetofend(struct xdp_buff_xsk, cb) >= \ + struct_size_t(struct libeth_xdp_buff, priv, \ + LIBETH_XDP_PRIV_SZ(sz))) + +/* XDPSQ sharing */ + +DECLARE_STATIC_KEY_FALSE(libeth_xdpsq_share); + +/** + * libeth_xdpsq_num - calculate optimal number of XDPSQs for this device + sys + * @rxq: current number of active Rx queues + * @txq: current number of active Tx queues + * @max: maximum number of Tx queues + * + * Each RQ must have its own XDPSQ for XSk pairs, each CPU must have own XDPSQ + * for lockless sending (``XDP_TX``, .ndo_xdp_xmit()). Cap the maximum of these + * two with the number of SQs the device can have (minus used ones). + * + * Return: number of XDP Tx queues the device needs to use. + */ +static inline u32 libeth_xdpsq_num(u32 rxq, u32 txq, u32 max) +{ + return min(max(nr_cpu_ids, rxq), max - txq); +} + +/** + * libeth_xdpsq_shared - whether XDPSQs can be shared between several CPUs + * @num: number of active XDPSQs + * + * Return: true if there's no 1:1 XDPSQ/CPU association, false otherwise. + */ +static inline bool libeth_xdpsq_shared(u32 num) +{ + return num < nr_cpu_ids; +} + +/** + * libeth_xdpsq_id - get XDPSQ index corresponding to this CPU + * @num: number of active XDPSQs + * + * Helper for libeth_xdp routines, do not use in drivers directly. + * + * Return: XDPSQ index needs to be used on this CPU. + */ +static inline u32 libeth_xdpsq_id(u32 num) +{ + u32 ret = raw_smp_processor_id(); + + if (static_branch_unlikely(&libeth_xdpsq_share) && + libeth_xdpsq_shared(num)) + ret %= num; + + return ret; +} + +void __libeth_xdpsq_get(struct libeth_xdpsq_lock *lock, + const struct net_device *dev); +void __libeth_xdpsq_put(struct libeth_xdpsq_lock *lock, + const struct net_device *dev); + +/** + * libeth_xdpsq_get - initialize &libeth_xdpsq_lock + * @lock: lock to initialize + * @dev: netdev which this lock belongs to + * @share: whether XDPSQs can be shared + * + * Tracks the current XDPSQ association and enables the static lock + * if needed. + */ +static inline void libeth_xdpsq_get(struct libeth_xdpsq_lock *lock, + const struct net_device *dev, + bool share) +{ + if (unlikely(share)) + __libeth_xdpsq_get(lock, dev); +} + +/** + * libeth_xdpsq_put - deinitialize &libeth_xdpsq_lock + * @lock: lock to deinitialize + * @dev: netdev which this lock belongs to + * + * Tracks the current XDPSQ association and disables the static lock + * if needed. + */ +static inline void libeth_xdpsq_put(struct libeth_xdpsq_lock *lock, + const struct net_device *dev) +{ + if (static_branch_unlikely(&libeth_xdpsq_share) && lock->share) + __libeth_xdpsq_put(lock, dev); +} + +void __libeth_xdpsq_lock(struct libeth_xdpsq_lock *lock); +void __libeth_xdpsq_unlock(struct libeth_xdpsq_lock *lock); + +/** + * libeth_xdpsq_lock - grab &libeth_xdpsq_lock if needed + * @lock: lock to take + * + * Touches the underlying spinlock only if the static key is enabled + * and the queue itself is marked as shareable. + */ +static inline void libeth_xdpsq_lock(struct libeth_xdpsq_lock *lock) +{ + if (static_branch_unlikely(&libeth_xdpsq_share) && lock->share) + __libeth_xdpsq_lock(lock); +} + +/** + * libeth_xdpsq_unlock - free &libeth_xdpsq_lock if needed + * @lock: lock to free + * + * Touches the underlying spinlock only if the static key is enabled + * and the queue itself is marked as shareable. + */ +static inline void libeth_xdpsq_unlock(struct libeth_xdpsq_lock *lock) +{ + if (static_branch_unlikely(&libeth_xdpsq_share) && lock->share) + __libeth_xdpsq_unlock(lock); +} + +/* XDPSQ clean-up timers */ + +void libeth_xdpsq_init_timer(struct libeth_xdpsq_timer *timer, void *xdpsq, + struct libeth_xdpsq_lock *lock, + void (*poll)(struct work_struct *work)); + +/** + * libeth_xdpsq_deinit_timer - deinitialize &libeth_xdpsq_timer + * @timer: timer to deinitialize + * + * Flush and disable the underlying workqueue. + */ +static inline void libeth_xdpsq_deinit_timer(struct libeth_xdpsq_timer *timer) +{ + cancel_delayed_work_sync(&timer->dwork); +} + +/** + * libeth_xdpsq_queue_timer - run &libeth_xdpsq_timer + * @timer: timer to queue + * + * Should be called after the queue was filled and the transmission was run + * to complete the pending buffers if no further sending will be done in a + * second (-> lazy cleaning won't happen). + * If the timer was already run, it will be requeued back to one second + * timeout again. + */ +static inline void libeth_xdpsq_queue_timer(struct libeth_xdpsq_timer *timer) +{ + mod_delayed_work_on(raw_smp_processor_id(), system_bh_highpri_wq, + &timer->dwork, HZ); +} + +/** + * libeth_xdpsq_run_timer - wrapper to run a queue clean-up on a timer event + * @work: workqueue belonging to the corresponding timer + * @poll: driver-specific completion queue poll function + * + * Run the polling function on the locked queue and requeue the timer if + * there's more work to do. + * Designed to be used via LIBETH_XDP_DEFINE_TIMER() below. + */ +static __always_inline void +libeth_xdpsq_run_timer(struct work_struct *work, + u32 (*poll)(void *xdpsq, u32 budget)) +{ + struct libeth_xdpsq_timer *timer = container_of(work, typeof(*timer), + dwork.work); + + libeth_xdpsq_lock(timer->lock); + + if (poll(timer->xdpsq, U32_MAX)) + libeth_xdpsq_queue_timer(timer); + + libeth_xdpsq_unlock(timer->lock); +} + +/* Common Tx bits */ + +/** + * enum - libeth_xdp internal Tx flags + * @LIBETH_XDP_TX_BULK: one bulk size at which it will be flushed to the queue + * @LIBETH_XDP_TX_BATCH: batch size for which the queue fill loop is unrolled + * @LIBETH_XDP_TX_DROP: indicates the send function must drop frames not sent + * @LIBETH_XDP_TX_NDO: whether the send function is called from .ndo_xdp_xmit() + * @LIBETH_XDP_TX_XSK: whether the function is called for ``XDP_TX`` for XSk + */ +enum { + LIBETH_XDP_TX_BULK = DEV_MAP_BULK_SIZE, + LIBETH_XDP_TX_BATCH = 8, + + LIBETH_XDP_TX_DROP = BIT(0), + LIBETH_XDP_TX_NDO = BIT(1), + LIBETH_XDP_TX_XSK = BIT(2), +}; + +/** + * enum - &libeth_xdp_tx_frame and &libeth_xdp_tx_desc flags + * @LIBETH_XDP_TX_LEN: only for ``XDP_TX``, [15:0] of ::len_fl is actual length + * @LIBETH_XDP_TX_CSUM: for XSk xmit, enable checksum offload + * @LIBETH_XDP_TX_XSKMD: for XSk xmit, mask of the metadata bits + * @LIBETH_XDP_TX_FIRST: indicates the frag is the first one of the frame + * @LIBETH_XDP_TX_LAST: whether the frag is the last one of the frame + * @LIBETH_XDP_TX_MULTI: whether the frame contains several frags + * @LIBETH_XDP_TX_FLAGS: only for ``XDP_TX``, [31:16] of ::len_fl is flags + */ +enum { + LIBETH_XDP_TX_LEN = GENMASK(15, 0), + + LIBETH_XDP_TX_CSUM = XDP_TXMD_FLAGS_CHECKSUM, + LIBETH_XDP_TX_XSKMD = LIBETH_XDP_TX_LEN, + + LIBETH_XDP_TX_FIRST = BIT(16), + LIBETH_XDP_TX_LAST = BIT(17), + LIBETH_XDP_TX_MULTI = BIT(18), + + LIBETH_XDP_TX_FLAGS = GENMASK(31, 16), +}; + +/** + * struct libeth_xdp_tx_frame - represents one XDP Tx element + * @data: frame start pointer for ``XDP_TX`` + * @len_fl: ``XDP_TX``, combined flags [31:16] and len [15:0] field for speed + * @soff: ``XDP_TX``, offset from @data to the start of &skb_shared_info + * @frag: one (non-head) frag for ``XDP_TX`` + * @xdpf: &xdp_frame for the head frag for .ndo_xdp_xmit() + * @dma: DMA address of the non-head frag for .ndo_xdp_xmit() + * @xsk: ``XDP_TX`` for XSk, XDP buffer for any frag + * @len: frag length for XSk ``XDP_TX`` and .ndo_xdp_xmit() + * @flags: Tx flags for the above + * @opts: combined @len + @flags for the above for speed + * @desc: XSk xmit descriptor for direct casting + */ +struct libeth_xdp_tx_frame { + union { + /* ``XDP_TX`` */ + struct { + void *data; + u32 len_fl; + u32 soff; + }; + + /* ``XDP_TX`` frag */ + skb_frag_t frag; + + /* .ndo_xdp_xmit(), XSk ``XDP_TX`` */ + struct { + union { + struct xdp_frame *xdpf; + dma_addr_t dma; + + struct libeth_xdp_buff *xsk; + }; + union { + struct { + u32 len; + u32 flags; + }; + aligned_u64 opts; + }; + }; + + /* XSk xmit */ + struct xdp_desc desc; + }; +} __aligned(sizeof(struct xdp_desc)); +static_assert(offsetof(struct libeth_xdp_tx_frame, frag.len) == + offsetof(struct libeth_xdp_tx_frame, len_fl)); +static_assert(sizeof(struct libeth_xdp_tx_frame) == sizeof(struct xdp_desc)); + +/** + * struct libeth_xdp_tx_bulk - XDP Tx frame bulk for bulk sending + * @prog: corresponding active XDP program, %NULL for .ndo_xdp_xmit() + * @dev: &net_device which the frames are transmitted on + * @xdpsq: shortcut to the corresponding driver-specific XDPSQ structure + * @act_mask: Rx only, mask of all the XDP prog verdicts for that NAPI session + * @count: current number of frames in @bulk + * @bulk: array of queued frames for bulk Tx + * + * All XDP Tx operations except XSk xmit queue each frame to the bulk first + * and flush it when @count reaches the array end. Bulk is always placed on + * the stack for performance. One bulk element contains all the data necessary + * for sending a frame and then freeing it on completion. + * For XSk xmit, Tx descriptor array from &xsk_buff_pool is casted directly + * to &libeth_xdp_tx_frame as they are compatible and the bulk structure is + * not used. + */ +struct libeth_xdp_tx_bulk { + const struct bpf_prog *prog; + struct net_device *dev; + void *xdpsq; + + u32 act_mask; + u32 count; + struct libeth_xdp_tx_frame bulk[LIBETH_XDP_TX_BULK]; +} __aligned(sizeof(struct libeth_xdp_tx_frame)); + +/** + * LIBETH_XDP_ONSTACK_BULK - declare &libeth_xdp_tx_bulk on the stack + * @bq: name of the variable to declare + * + * Helper to declare a bulk on the stack with a compiler hint that it should + * not be initialized automatically (with `CONFIG_INIT_STACK_ALL_*`) for + * performance reasons. + */ +#define LIBETH_XDP_ONSTACK_BULK(bq) \ + struct libeth_xdp_tx_bulk bq __uninitialized + +/** + * struct libeth_xdpsq - abstraction for an XDPSQ + * @pool: XSk buffer pool for XSk ``XDP_TX`` and xmit + * @sqes: array of Tx buffers from the actual queue struct + * @descs: opaque pointer to the HW descriptor array + * @ntu: pointer to the next free descriptor index + * @count: number of descriptors on that queue + * @pending: pointer to the number of sent-not-completed descs on that queue + * @xdp_tx: pointer to the above, but only for non-XSk-xmit frames + * @lock: corresponding XDPSQ lock + * + * Abstraction for driver-independent implementation of Tx. Placed on the stack + * and filled by the driver before the transmission, so that the generic + * functions can access and modify driver-specific resources. + */ +struct libeth_xdpsq { + struct xsk_buff_pool *pool; + struct libeth_sqe *sqes; + void *descs; + + u32 *ntu; + u32 count; + + u32 *pending; + u32 *xdp_tx; + struct libeth_xdpsq_lock *lock; +}; + +/** + * struct libeth_xdp_tx_desc - abstraction for an XDP Tx descriptor + * @addr: DMA address of the frame + * @len: length of the frame + * @flags: XDP Tx flags + * @opts: combined @len + @flags for speed + * + * Filled by the generic functions and then passed to driver-specific functions + * to fill a HW Tx descriptor, always placed on the [function] stack. + */ +struct libeth_xdp_tx_desc { + dma_addr_t addr; + union { + struct { + u32 len; + u32 flags; + }; + aligned_u64 opts; + }; +} __aligned_largest; + +/** + * libeth_xdp_ptr_to_priv - convert pointer to a libeth_xdp u64 priv + * @ptr: pointer to convert + * + * The main sending function passes private data as the largest scalar, u64. + * Use this helper when you want to pass a pointer there. + */ +#define libeth_xdp_ptr_to_priv(ptr) ({ \ + typecheck_pointer(ptr); \ + ((u64)(uintptr_t)(ptr)); \ +}) +/** + * libeth_xdp_priv_to_ptr - convert libeth_xdp u64 priv to a pointer + * @priv: private data to convert + * + * The main sending function passes private data as the largest scalar, u64. + * Use this helper when your callback takes this u64 and you want to convert + * it back to a pointer. + */ +#define libeth_xdp_priv_to_ptr(priv) ({ \ + static_assert(__same_type(priv, u64)); \ + ((const void *)(uintptr_t)(priv)); \ +}) + +/* + * On 64-bit systems, assigning one u64 is faster than two u32s. When ::len + * occupies lowest 32 bits (LE), whole ::opts can be assigned directly instead. + */ +#ifdef __LITTLE_ENDIAN +#define __LIBETH_WORD_ACCESS 1 +#endif +#ifdef __LIBETH_WORD_ACCESS +#define __libeth_xdp_tx_len(flen, ...) \ + .opts = ((flen) | FIELD_PREP(GENMASK_ULL(63, 32), (__VA_ARGS__ + 0))) +#else +#define __libeth_xdp_tx_len(flen, ...) \ + .len = (flen), .flags = (__VA_ARGS__ + 0) +#endif + +/** + * libeth_xdp_tx_xmit_bulk - main XDP Tx function + * @bulk: array of frames to send + * @xdpsq: pointer to the driver-specific XDPSQ struct + * @n: number of frames to send + * @unroll: whether to unroll the queue filling loop for speed + * @priv: driver-specific private data + * @prep: callback for cleaning the queue and filling abstract &libeth_xdpsq + * @fill: internal callback for filling &libeth_sqe and &libeth_xdp_tx_desc + * @xmit: callback for filling a HW descriptor with the frame info + * + * Internal abstraction for placing @n XDP Tx frames on the HW XDPSQ. Used for + * all types of frames: ``XDP_TX``, .ndo_xdp_xmit(), XSk ``XDP_TX``, and XSk + * xmit. + * @prep must lock the queue as this function releases it at the end. @unroll + * greatly increases the object code size, but also greatly increases XSk xmit + * performance; for other types of frames, it's not enabled. + * The compilers inline all those onstack abstractions to direct data accesses. + * + * Return: number of frames actually placed on the queue, <= @n. The function + * can't fail, but can send less frames if there's no enough free descriptors + * available. The actual free space is returned by @prep from the driver. + */ +static __always_inline u32 +libeth_xdp_tx_xmit_bulk(const struct libeth_xdp_tx_frame *bulk, void *xdpsq, + u32 n, bool unroll, u64 priv, + u32 (*prep)(void *xdpsq, struct libeth_xdpsq *sq), + struct libeth_xdp_tx_desc + (*fill)(struct libeth_xdp_tx_frame frm, u32 i, + const struct libeth_xdpsq *sq, u64 priv), + void (*xmit)(struct libeth_xdp_tx_desc desc, u32 i, + const struct libeth_xdpsq *sq, u64 priv)) +{ + struct libeth_xdpsq sq __uninitialized; + u32 this, batched, off = 0; + u32 ntu, i = 0; + + n = min(n, prep(xdpsq, &sq)); + if (unlikely(!n)) + goto unlock; + + ntu = *sq.ntu; + + this = sq.count - ntu; + if (likely(this > n)) + this = n; + +again: + if (!unroll) + goto linear; + + batched = ALIGN_DOWN(this, LIBETH_XDP_TX_BATCH); + + for ( ; i < off + batched; i += LIBETH_XDP_TX_BATCH) { + u32 base = ntu + i - off; + + unrolled_count(LIBETH_XDP_TX_BATCH) + for (u32 j = 0; j < LIBETH_XDP_TX_BATCH; j++) + xmit(fill(bulk[i + j], base + j, &sq, priv), + base + j, &sq, priv); + } + + if (batched < this) { +linear: + for ( ; i < off + this; i++) + xmit(fill(bulk[i], ntu + i - off, &sq, priv), + ntu + i - off, &sq, priv); + } + + ntu += this; + if (likely(ntu < sq.count)) + goto out; + + ntu = 0; + + if (i < n) { + this = n - i; + off = i; + + goto again; + } + +out: + *sq.ntu = ntu; + *sq.pending += n; + if (sq.xdp_tx) + *sq.xdp_tx += n; + +unlock: + libeth_xdpsq_unlock(sq.lock); + + return n; +} + +/* ``XDP_TX`` bulking */ + +void libeth_xdp_return_buff_slow(struct libeth_xdp_buff *xdp); + +/** + * libeth_xdp_tx_queue_head - internal helper for queueing one ``XDP_TX`` head + * @bq: XDP Tx bulk to queue the head frag to + * @xdp: XDP buffer with the head to queue + * + * Return: false if it's the only frag of the frame, true if it's an S/G frame. + */ +static inline bool libeth_xdp_tx_queue_head(struct libeth_xdp_tx_bulk *bq, + const struct libeth_xdp_buff *xdp) +{ + const struct xdp_buff *base = &xdp->base; + + bq->bulk[bq->count++] = (typeof(*bq->bulk)){ + .data = xdp->data, + .len_fl = (base->data_end - xdp->data) | LIBETH_XDP_TX_FIRST, + .soff = xdp_data_hard_end(base) - xdp->data, + }; + + if (!xdp_buff_has_frags(base)) + return false; + + bq->bulk[bq->count - 1].len_fl |= LIBETH_XDP_TX_MULTI; + + return true; +} + +/** + * libeth_xdp_tx_queue_frag - internal helper for queueing one ``XDP_TX`` frag + * @bq: XDP Tx bulk to queue the frag to + * @frag: frag to queue + */ +static inline void libeth_xdp_tx_queue_frag(struct libeth_xdp_tx_bulk *bq, + const skb_frag_t *frag) +{ + bq->bulk[bq->count++].frag = *frag; +} + +/** + * libeth_xdp_tx_queue_bulk - internal helper for queueing one ``XDP_TX`` frame + * @bq: XDP Tx bulk to queue the frame to + * @xdp: XDP buffer to queue + * @flush_bulk: driver callback to flush the bulk to the HW queue + * + * Return: true on success, false on flush error. + */ +static __always_inline bool +libeth_xdp_tx_queue_bulk(struct libeth_xdp_tx_bulk *bq, + struct libeth_xdp_buff *xdp, + bool (*flush_bulk)(struct libeth_xdp_tx_bulk *bq, + u32 flags)) +{ + const struct skb_shared_info *sinfo; + bool ret = true; + u32 nr_frags; + + if (unlikely(bq->count == LIBETH_XDP_TX_BULK) && + unlikely(!flush_bulk(bq, 0))) { + libeth_xdp_return_buff_slow(xdp); + return false; + } + + if (!libeth_xdp_tx_queue_head(bq, xdp)) + goto out; + + sinfo = xdp_get_shared_info_from_buff(&xdp->base); + nr_frags = sinfo->nr_frags; + + for (u32 i = 0; i < nr_frags; i++) { + if (unlikely(bq->count == LIBETH_XDP_TX_BULK) && + unlikely(!flush_bulk(bq, 0))) { + ret = false; + break; + } + + libeth_xdp_tx_queue_frag(bq, &sinfo->frags[i]); + } + +out: + bq->bulk[bq->count - 1].len_fl |= LIBETH_XDP_TX_LAST; + xdp->data = NULL; + + return ret; +} + +/** + * libeth_xdp_tx_fill_stats - fill &libeth_sqe with ``XDP_TX`` frame stats + * @sqe: SQ element to fill + * @desc: libeth_xdp Tx descriptor + * @sinfo: &skb_shared_info for this frame + * + * Internal helper for filling an SQE with the frame stats, do not use in + * drivers. Fills the number of frags and bytes for this frame. + */ +#define libeth_xdp_tx_fill_stats(sqe, desc, sinfo) \ + __libeth_xdp_tx_fill_stats(sqe, desc, sinfo, __UNIQUE_ID(sqe_), \ + __UNIQUE_ID(desc_), __UNIQUE_ID(sinfo_)) + +#define __libeth_xdp_tx_fill_stats(sqe, desc, sinfo, ue, ud, us) do { \ + const struct libeth_xdp_tx_desc *ud = (desc); \ + const struct skb_shared_info *us; \ + struct libeth_sqe *ue = (sqe); \ + \ + ue->nr_frags = 1; \ + ue->bytes = ud->len; \ + \ + if (ud->flags & LIBETH_XDP_TX_MULTI) { \ + us = (sinfo); \ + ue->nr_frags += us->nr_frags; \ + ue->bytes += us->xdp_frags_size; \ + } \ +} while (0) + +/** + * libeth_xdp_tx_fill_buf - internal helper to fill one ``XDP_TX`` &libeth_sqe + * @frm: XDP Tx frame from the bulk + * @i: index on the HW queue + * @sq: XDPSQ abstraction for the queue + * @priv: private data + * + * Return: XDP Tx descriptor with the synced DMA and other info to pass to + * the driver callback. + */ +static inline struct libeth_xdp_tx_desc +libeth_xdp_tx_fill_buf(struct libeth_xdp_tx_frame frm, u32 i, + const struct libeth_xdpsq *sq, u64 priv) +{ + struct libeth_xdp_tx_desc desc; + struct skb_shared_info *sinfo; + skb_frag_t *frag = &frm.frag; + struct libeth_sqe *sqe; + netmem_ref netmem; + + if (frm.len_fl & LIBETH_XDP_TX_FIRST) { + sinfo = frm.data + frm.soff; + skb_frag_fill_netmem_desc(frag, virt_to_netmem(frm.data), + offset_in_page(frm.data), + frm.len_fl); + } else { + sinfo = NULL; + } + + netmem = skb_frag_netmem(frag); + desc = (typeof(desc)){ + .addr = page_pool_get_dma_addr_netmem(netmem) + + skb_frag_off(frag), + .len = skb_frag_size(frag) & LIBETH_XDP_TX_LEN, + .flags = skb_frag_size(frag) & LIBETH_XDP_TX_FLAGS, + }; + + dma_sync_single_for_device(__netmem_get_pp(netmem)->p.dev, desc.addr, + desc.len, DMA_BIDIRECTIONAL); + + if (!sinfo) + return desc; + + sqe = &sq->sqes[i]; + sqe->type = LIBETH_SQE_XDP_TX; + sqe->sinfo = sinfo; + libeth_xdp_tx_fill_stats(sqe, &desc, sinfo); + + return desc; +} + +void libeth_xdp_tx_exception(struct libeth_xdp_tx_bulk *bq, u32 sent, + u32 flags); + +/** + * __libeth_xdp_tx_flush_bulk - internal helper to flush one XDP Tx bulk + * @bq: bulk to flush + * @flags: XDP TX flags (.ndo_xdp_xmit(), XSk etc.) + * @prep: driver-specific callback to prepare the queue for sending + * @fill: libeth_xdp callback to fill &libeth_sqe and &libeth_xdp_tx_desc + * @xmit: driver callback to fill a HW descriptor + * + * Internal abstraction to create bulk flush functions for drivers. Used for + * everything except XSk xmit. + * + * Return: true if anything was sent, false otherwise. + */ +static __always_inline bool +__libeth_xdp_tx_flush_bulk(struct libeth_xdp_tx_bulk *bq, u32 flags, + u32 (*prep)(void *xdpsq, struct libeth_xdpsq *sq), + struct libeth_xdp_tx_desc + (*fill)(struct libeth_xdp_tx_frame frm, u32 i, + const struct libeth_xdpsq *sq, u64 priv), + void (*xmit)(struct libeth_xdp_tx_desc desc, u32 i, + const struct libeth_xdpsq *sq, + u64 priv)) +{ + u32 sent, drops; + int err = 0; + + sent = libeth_xdp_tx_xmit_bulk(bq->bulk, bq->xdpsq, + min(bq->count, LIBETH_XDP_TX_BULK), + false, 0, prep, fill, xmit); + drops = bq->count - sent; + + if (unlikely(drops)) { + libeth_xdp_tx_exception(bq, sent, flags); + err = -ENXIO; + } else { + bq->count = 0; + } + + trace_xdp_bulk_tx(bq->dev, sent, drops, err); + + return likely(sent); +} + +/** + * libeth_xdp_tx_flush_bulk - wrapper to define flush of one ``XDP_TX`` bulk + * @bq: bulk to flush + * @flags: Tx flags, see above + * @prep: driver callback to prepare the queue + * @xmit: driver callback to fill a HW descriptor + * + * Use via LIBETH_XDP_DEFINE_FLUSH_TX() to define an ``XDP_TX`` driver + * callback. + */ +#define libeth_xdp_tx_flush_bulk(bq, flags, prep, xmit) \ + __libeth_xdp_tx_flush_bulk(bq, flags, prep, libeth_xdp_tx_fill_buf, \ + xmit) + +/* .ndo_xdp_xmit() implementation */ + +/** + * libeth_xdp_xmit_init_bulk - internal helper to initialize bulk for XDP xmit + * @bq: bulk to initialize + * @dev: target &net_device + * @xdpsqs: array of driver-specific XDPSQ structs + * @num: number of active XDPSQs (the above array length) + */ +#define libeth_xdp_xmit_init_bulk(bq, dev, xdpsqs, num) \ + __libeth_xdp_xmit_init_bulk(bq, dev, (xdpsqs)[libeth_xdpsq_id(num)]) + +static inline void __libeth_xdp_xmit_init_bulk(struct libeth_xdp_tx_bulk *bq, + struct net_device *dev, + void *xdpsq) +{ + bq->dev = dev; + bq->xdpsq = xdpsq; + bq->count = 0; +} + +/** + * libeth_xdp_xmit_frame_dma - internal helper to access DMA of an &xdp_frame + * @xf: pointer to the XDP frame + * + * There's no place in &libeth_xdp_tx_frame to store DMA address for an + * &xdp_frame head. The headroom is used then, the address is placed right + * after the frame struct, naturally aligned. + * + * Return: pointer to the DMA address to use. + */ +#define libeth_xdp_xmit_frame_dma(xf) \ + _Generic((xf), \ + const struct xdp_frame *: \ + (const dma_addr_t *)__libeth_xdp_xmit_frame_dma(xf), \ + struct xdp_frame *: \ + (dma_addr_t *)__libeth_xdp_xmit_frame_dma(xf) \ + ) + +static inline void *__libeth_xdp_xmit_frame_dma(const struct xdp_frame *xdpf) +{ + void *addr = (void *)(xdpf + 1); + + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && + __alignof(*xdpf) < sizeof(dma_addr_t)) + addr = PTR_ALIGN(addr, sizeof(dma_addr_t)); + + return addr; +} + +/** + * libeth_xdp_xmit_queue_head - internal helper for queueing one XDP xmit head + * @bq: XDP Tx bulk to queue the head frag to + * @xdpf: XDP frame with the head to queue + * @dev: device to perform DMA mapping + * + * Return: ``LIBETH_XDP_DROP`` on DMA mapping error, + * ``LIBETH_XDP_PASS`` if it's the only frag in the frame, + * ``LIBETH_XDP_TX`` if it's an S/G frame. + */ +static inline u32 libeth_xdp_xmit_queue_head(struct libeth_xdp_tx_bulk *bq, + struct xdp_frame *xdpf, + struct device *dev) +{ + dma_addr_t dma; + + dma = dma_map_single(dev, xdpf->data, xdpf->len, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma)) + return LIBETH_XDP_DROP; + + *libeth_xdp_xmit_frame_dma(xdpf) = dma; + + bq->bulk[bq->count++] = (typeof(*bq->bulk)){ + .xdpf = xdpf, + __libeth_xdp_tx_len(xdpf->len, LIBETH_XDP_TX_FIRST), + }; + + if (!xdp_frame_has_frags(xdpf)) + return LIBETH_XDP_PASS; + + bq->bulk[bq->count - 1].flags |= LIBETH_XDP_TX_MULTI; + + return LIBETH_XDP_TX; +} + +/** + * libeth_xdp_xmit_queue_frag - internal helper for queueing one XDP xmit frag + * @bq: XDP Tx bulk to queue the frag to + * @frag: frag to queue + * @dev: device to perform DMA mapping + * + * Return: true on success, false on DMA mapping error. + */ +static inline bool libeth_xdp_xmit_queue_frag(struct libeth_xdp_tx_bulk *bq, + const skb_frag_t *frag, + struct device *dev) +{ + dma_addr_t dma; + + dma = skb_frag_dma_map(dev, frag); + if (dma_mapping_error(dev, dma)) + return false; + + bq->bulk[bq->count++] = (typeof(*bq->bulk)){ + .dma = dma, + __libeth_xdp_tx_len(skb_frag_size(frag)), + }; + + return true; +} + +/** + * libeth_xdp_xmit_queue_bulk - internal helper for queueing one XDP xmit frame + * @bq: XDP Tx bulk to queue the frame to + * @xdpf: XDP frame to queue + * @flush_bulk: driver callback to flush the bulk to the HW queue + * + * Return: ``LIBETH_XDP_TX`` on success, + * ``LIBETH_XDP_DROP`` if the frame should be dropped by the stack, + * ``LIBETH_XDP_ABORTED`` if the frame will be dropped by libeth_xdp. + */ +static __always_inline u32 +libeth_xdp_xmit_queue_bulk(struct libeth_xdp_tx_bulk *bq, + struct xdp_frame *xdpf, + bool (*flush_bulk)(struct libeth_xdp_tx_bulk *bq, + u32 flags)) +{ + u32 head, nr_frags, i, ret = LIBETH_XDP_TX; + struct device *dev = bq->dev->dev.parent; + const struct skb_shared_info *sinfo; + + if (unlikely(bq->count == LIBETH_XDP_TX_BULK) && + unlikely(!flush_bulk(bq, LIBETH_XDP_TX_NDO))) + return LIBETH_XDP_DROP; + + head = libeth_xdp_xmit_queue_head(bq, xdpf, dev); + if (head == LIBETH_XDP_PASS) + goto out; + else if (head == LIBETH_XDP_DROP) + return LIBETH_XDP_DROP; + + sinfo = xdp_get_shared_info_from_frame(xdpf); + nr_frags = sinfo->nr_frags; + + for (i = 0; i < nr_frags; i++) { + if (unlikely(bq->count == LIBETH_XDP_TX_BULK) && + unlikely(!flush_bulk(bq, LIBETH_XDP_TX_NDO))) + break; + + if (!libeth_xdp_xmit_queue_frag(bq, &sinfo->frags[i], dev)) + break; + } + + if (unlikely(i < nr_frags)) + ret = LIBETH_XDP_ABORTED; + +out: + bq->bulk[bq->count - 1].flags |= LIBETH_XDP_TX_LAST; + + return ret; +} + +/** + * libeth_xdp_xmit_fill_buf - internal helper to fill one XDP xmit &libeth_sqe + * @frm: XDP Tx frame from the bulk + * @i: index on the HW queue + * @sq: XDPSQ abstraction for the queue + * @priv: private data + * + * Return: XDP Tx descriptor with the mapped DMA and other info to pass to + * the driver callback. + */ +static inline struct libeth_xdp_tx_desc +libeth_xdp_xmit_fill_buf(struct libeth_xdp_tx_frame frm, u32 i, + const struct libeth_xdpsq *sq, u64 priv) +{ + struct libeth_xdp_tx_desc desc; + struct libeth_sqe *sqe; + struct xdp_frame *xdpf; + + if (frm.flags & LIBETH_XDP_TX_FIRST) { + xdpf = frm.xdpf; + desc.addr = *libeth_xdp_xmit_frame_dma(xdpf); + } else { + xdpf = NULL; + desc.addr = frm.dma; + } + desc.opts = frm.opts; + + sqe = &sq->sqes[i]; + dma_unmap_addr_set(sqe, dma, desc.addr); + dma_unmap_len_set(sqe, len, desc.len); + + if (!xdpf) { + sqe->type = LIBETH_SQE_XDP_XMIT_FRAG; + return desc; + } + + sqe->type = LIBETH_SQE_XDP_XMIT; + sqe->xdpf = xdpf; + libeth_xdp_tx_fill_stats(sqe, &desc, + xdp_get_shared_info_from_frame(xdpf)); + + return desc; +} + +/** + * libeth_xdp_xmit_flush_bulk - wrapper to define flush of one XDP xmit bulk + * @bq: bulk to flush + * @flags: Tx flags, see __libeth_xdp_tx_flush_bulk() + * @prep: driver callback to prepare the queue + * @xmit: driver callback to fill a HW descriptor + * + * Use via LIBETH_XDP_DEFINE_FLUSH_XMIT() to define an XDP xmit driver + * callback. + */ +#define libeth_xdp_xmit_flush_bulk(bq, flags, prep, xmit) \ + __libeth_xdp_tx_flush_bulk(bq, (flags) | LIBETH_XDP_TX_NDO, prep, \ + libeth_xdp_xmit_fill_buf, xmit) + +u32 libeth_xdp_xmit_return_bulk(const struct libeth_xdp_tx_frame *bq, + u32 count, const struct net_device *dev); + +/** + * __libeth_xdp_xmit_do_bulk - internal function to implement .ndo_xdp_xmit() + * @bq: XDP Tx bulk to queue frames to + * @frames: XDP frames passed by the stack + * @n: number of frames + * @flags: flags passed by the stack + * @flush_bulk: driver callback to flush an XDP xmit bulk + * @finalize: driver callback to finalize sending XDP Tx frames on the queue + * + * Perform common checks, map the frags and queue them to the bulk, then flush + * the bulk to the XDPSQ. If requested by the stack, finalize the queue. + * + * Return: number of frames send or -errno on error. + */ +static __always_inline int +__libeth_xdp_xmit_do_bulk(struct libeth_xdp_tx_bulk *bq, + struct xdp_frame **frames, u32 n, u32 flags, + bool (*flush_bulk)(struct libeth_xdp_tx_bulk *bq, + u32 flags), + void (*finalize)(void *xdpsq, bool sent, bool flush)) +{ + u32 nxmit = 0; + + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) + return -EINVAL; + + for (u32 i = 0; likely(i < n); i++) { + u32 ret; + + ret = libeth_xdp_xmit_queue_bulk(bq, frames[i], flush_bulk); + if (unlikely(ret != LIBETH_XDP_TX)) { + nxmit += ret == LIBETH_XDP_ABORTED; + break; + } + + nxmit++; + } + + if (bq->count) { + flush_bulk(bq, LIBETH_XDP_TX_NDO); + if (unlikely(bq->count)) + nxmit -= libeth_xdp_xmit_return_bulk(bq->bulk, + bq->count, + bq->dev); + } + + finalize(bq->xdpsq, nxmit, flags & XDP_XMIT_FLUSH); + + return nxmit; +} + +/** + * libeth_xdp_xmit_do_bulk - implement full .ndo_xdp_xmit() in driver + * @dev: target &net_device + * @n: number of frames to send + * @fr: XDP frames to send + * @f: flags passed by the stack + * @xqs: array of XDPSQs driver structs + * @nqs: number of active XDPSQs, the above array length + * @fl: driver callback to flush an XDP xmit bulk + * @fin: driver cabback to finalize the queue + * + * If the driver has active XDPSQs, perform common checks and send the frames. + * Finalize the queue, if requested. + * + * Return: number of frames sent or -errno on error. + */ +#define libeth_xdp_xmit_do_bulk(dev, n, fr, f, xqs, nqs, fl, fin) \ + _libeth_xdp_xmit_do_bulk(dev, n, fr, f, xqs, nqs, fl, fin, \ + __UNIQUE_ID(bq_), __UNIQUE_ID(ret_), \ + __UNIQUE_ID(nqs_)) + +#define _libeth_xdp_xmit_do_bulk(d, n, fr, f, xqs, nqs, fl, fin, ub, ur, un) \ +({ \ + u32 un = (nqs); \ + int ur; \ + \ + if (likely(un)) { \ + LIBETH_XDP_ONSTACK_BULK(ub); \ + \ + libeth_xdp_xmit_init_bulk(&ub, d, xqs, un); \ + ur = __libeth_xdp_xmit_do_bulk(&ub, fr, n, f, fl, fin); \ + } else { \ + ur = -ENXIO; \ + } \ + \ + ur; \ +}) + +/* Rx polling path */ + +/** + * libeth_xdp_tx_init_bulk - initialize an XDP Tx bulk for Rx NAPI poll + * @bq: bulk to initialize + * @prog: RCU pointer to the XDP program (can be %NULL) + * @dev: target &net_device + * @xdpsqs: array of driver XDPSQ structs + * @num: number of active XDPSQs, the above array length + * + * Should be called on an onstack XDP Tx bulk before the NAPI polling loop. + * Initializes all the needed fields to run libeth_xdp functions. If @num == 0, + * assumes XDP is not enabled. + * Do not use for XSk, it has its own optimized helper. + */ +#define libeth_xdp_tx_init_bulk(bq, prog, dev, xdpsqs, num) \ + __libeth_xdp_tx_init_bulk(bq, prog, dev, xdpsqs, num, false, \ + __UNIQUE_ID(bq_), __UNIQUE_ID(nqs_)) + +#define __libeth_xdp_tx_init_bulk(bq, pr, d, xdpsqs, num, xsk, ub, un) do { \ + typeof(bq) ub = (bq); \ + u32 un = (num); \ + \ + rcu_read_lock(); \ + \ + if (un || (xsk)) { \ + ub->prog = rcu_dereference(pr); \ + ub->dev = (d); \ + ub->xdpsq = (xdpsqs)[libeth_xdpsq_id(un)]; \ + } else { \ + ub->prog = NULL; \ + } \ + \ + ub->act_mask = 0; \ + ub->count = 0; \ +} while (0) + +void libeth_xdp_load_stash(struct libeth_xdp_buff *dst, + const struct libeth_xdp_buff_stash *src); +void libeth_xdp_save_stash(struct libeth_xdp_buff_stash *dst, + const struct libeth_xdp_buff *src); +void __libeth_xdp_return_stash(struct libeth_xdp_buff_stash *stash); + +/** + * libeth_xdp_init_buff - initialize a &libeth_xdp_buff for Rx NAPI poll + * @dst: onstack buffer to initialize + * @src: XDP buffer stash placed on the queue + * @rxq: registered &xdp_rxq_info corresponding to this queue + * + * Should be called before the main NAPI polling loop. Loads the content of + * the previously saved stash or initializes the buffer from scratch. + * Do not use for XSk. + */ +static inline void +libeth_xdp_init_buff(struct libeth_xdp_buff *dst, + const struct libeth_xdp_buff_stash *src, + struct xdp_rxq_info *rxq) +{ + if (likely(!src->data)) + dst->data = NULL; + else + libeth_xdp_load_stash(dst, src); + + dst->base.rxq = rxq; +} + +/** + * libeth_xdp_save_buff - save a partially built buffer on a queue + * @dst: XDP buffer stash placed on the queue + * @src: onstack buffer to save + * + * Should be called after the main NAPI polling loop. If the loop exited before + * the buffer was finished, saves its content on the queue, so that it can be + * completed during the next poll. Otherwise, clears the stash. + */ +static inline void libeth_xdp_save_buff(struct libeth_xdp_buff_stash *dst, + const struct libeth_xdp_buff *src) +{ + if (likely(!src->data)) + dst->data = NULL; + else + libeth_xdp_save_stash(dst, src); +} + +/** + * libeth_xdp_return_stash - free an XDP buffer stash from a queue + * @stash: stash to free + * + * If the queue is about to be destroyed, but it still has an incompleted + * buffer stash, this helper should be called to free it. + */ +static inline void libeth_xdp_return_stash(struct libeth_xdp_buff_stash *stash) +{ + if (stash->data) + __libeth_xdp_return_stash(stash); +} + +static inline void libeth_xdp_return_va(const void *data, bool napi) +{ + netmem_ref netmem = virt_to_netmem(data); + + page_pool_put_full_netmem(__netmem_get_pp(netmem), netmem, napi); +} + +static inline void libeth_xdp_return_frags(const struct skb_shared_info *sinfo, + bool napi) +{ + for (u32 i = 0; i < sinfo->nr_frags; i++) { + netmem_ref netmem = skb_frag_netmem(&sinfo->frags[i]); + + page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, napi); + } +} + +/** + * libeth_xdp_return_buff - free/recycle &libeth_xdp_buff + * @xdp: buffer to free + * + * Hotpath helper to free &libeth_xdp_buff. Comparing to xdp_return_buff(), + * it's faster as it gets inlined and always assumes order-0 pages and safe + * direct recycling. Zeroes @xdp->data to avoid UAFs. + */ +#define libeth_xdp_return_buff(xdp) __libeth_xdp_return_buff(xdp, true) + +static inline void __libeth_xdp_return_buff(struct libeth_xdp_buff *xdp, + bool napi) +{ + if (!xdp_buff_has_frags(&xdp->base)) + goto out; + + libeth_xdp_return_frags(xdp_get_shared_info_from_buff(&xdp->base), + napi); + +out: + libeth_xdp_return_va(xdp->data, napi); + xdp->data = NULL; +} + +bool libeth_xdp_buff_add_frag(struct libeth_xdp_buff *xdp, + const struct libeth_fqe *fqe, + u32 len); + +/** + * libeth_xdp_prepare_buff - fill &libeth_xdp_buff with head FQE data + * @xdp: XDP buffer to attach the head to + * @fqe: FQE containing the head buffer + * @len: buffer len passed from HW + * + * Internal, use libeth_xdp_process_buff() instead. Initializes XDP buffer + * head with the Rx buffer data: data pointer, length, headroom, and + * truesize/tailroom. Zeroes the flags. + * Uses faster single u64 write instead of per-field access. + */ +static inline void libeth_xdp_prepare_buff(struct libeth_xdp_buff *xdp, + const struct libeth_fqe *fqe, + u32 len) +{ + const struct page *page = __netmem_to_page(fqe->netmem); + +#ifdef __LIBETH_WORD_ACCESS + static_assert(offsetofend(typeof(xdp->base), flags) - + offsetof(typeof(xdp->base), frame_sz) == + sizeof(u64)); + + *(u64 *)&xdp->base.frame_sz = fqe->truesize; +#else + xdp_init_buff(&xdp->base, fqe->truesize, xdp->base.rxq); +#endif + xdp_prepare_buff(&xdp->base, page_address(page) + fqe->offset, + page->pp->p.offset, len, true); +} + +/** + * libeth_xdp_process_buff - attach Rx buffer to &libeth_xdp_buff + * @xdp: XDP buffer to attach the Rx buffer to + * @fqe: Rx buffer to process + * @len: received data length from the descriptor + * + * If the XDP buffer is empty, attaches the Rx buffer as head and initializes + * the required fields. Otherwise, attaches the buffer as a frag. + * Already performs DMA sync-for-CPU and frame start prefetch + * (for head buffers only). + * + * Return: true on success, false if the descriptor must be skipped (empty or + * no space for a new frag). + */ +static inline bool libeth_xdp_process_buff(struct libeth_xdp_buff *xdp, + const struct libeth_fqe *fqe, + u32 len) +{ + if (!libeth_rx_sync_for_cpu(fqe, len)) + return false; + + if (xdp->data) + return libeth_xdp_buff_add_frag(xdp, fqe, len); + + libeth_xdp_prepare_buff(xdp, fqe, len); + + prefetch(xdp->data); + + return true; +} + +/** + * libeth_xdp_buff_stats_frags - update onstack RQ stats with XDP frags info + * @ss: onstack stats to update + * @xdp: buffer to account + * + * Internal helper used by __libeth_xdp_run_pass(), do not call directly. + * Adds buffer's frags count and total len to the onstack stats. + */ +static inline void +libeth_xdp_buff_stats_frags(struct libeth_rq_napi_stats *ss, + const struct libeth_xdp_buff *xdp) +{ + const struct skb_shared_info *sinfo; + + sinfo = xdp_get_shared_info_from_buff(&xdp->base); + ss->bytes += sinfo->xdp_frags_size; + ss->fragments += sinfo->nr_frags + 1; +} + +u32 libeth_xdp_prog_exception(const struct libeth_xdp_tx_bulk *bq, + struct libeth_xdp_buff *xdp, + enum xdp_action act, int ret); + +/** + * __libeth_xdp_run_prog - run XDP program on an XDP buffer + * @xdp: XDP buffer to run the prog on + * @bq: buffer bulk for ``XDP_TX`` queueing + * + * Internal inline abstraction to run XDP program. Handles ``XDP_DROP`` + * and ``XDP_REDIRECT`` only, the rest is processed levels up. + * Reports an XDP prog exception on errors. + * + * Return: libeth_xdp prog verdict depending on the prog's verdict. + */ +static __always_inline u32 +__libeth_xdp_run_prog(struct libeth_xdp_buff *xdp, + const struct libeth_xdp_tx_bulk *bq) +{ + enum xdp_action act; + + act = bpf_prog_run_xdp(bq->prog, &xdp->base); + if (unlikely(act < XDP_DROP || act > XDP_REDIRECT)) + goto out; + + switch (act) { + case XDP_PASS: + return LIBETH_XDP_PASS; + case XDP_DROP: + libeth_xdp_return_buff(xdp); + + return LIBETH_XDP_DROP; + case XDP_TX: + return LIBETH_XDP_TX; + case XDP_REDIRECT: + if (unlikely(xdp_do_redirect(bq->dev, &xdp->base, bq->prog))) + break; + + xdp->data = NULL; + + return LIBETH_XDP_REDIRECT; + default: + break; + } + +out: + return libeth_xdp_prog_exception(bq, xdp, act, 0); +} + +/** + * __libeth_xdp_run_flush - run XDP program and handle ``XDP_TX`` verdict + * @xdp: XDP buffer to run the prog on + * @bq: buffer bulk for ``XDP_TX`` queueing + * @run: internal callback for running XDP program + * @queue: internal callback for queuing ``XDP_TX`` frame + * @flush_bulk: driver callback for flushing a bulk + * + * Internal inline abstraction to run XDP program and additionally handle + * ``XDP_TX`` verdict. Used by both XDP and XSk, hence @run and @queue. + * Do not use directly. + * + * Return: libeth_xdp prog verdict depending on the prog's verdict. + */ +static __always_inline u32 +__libeth_xdp_run_flush(struct libeth_xdp_buff *xdp, + struct libeth_xdp_tx_bulk *bq, + u32 (*run)(struct libeth_xdp_buff *xdp, + const struct libeth_xdp_tx_bulk *bq), + bool (*queue)(struct libeth_xdp_tx_bulk *bq, + struct libeth_xdp_buff *xdp, + bool (*flush_bulk) + (struct libeth_xdp_tx_bulk *bq, + u32 flags)), + bool (*flush_bulk)(struct libeth_xdp_tx_bulk *bq, + u32 flags)) +{ + u32 act; + + act = run(xdp, bq); + if (act == LIBETH_XDP_TX && unlikely(!queue(bq, xdp, flush_bulk))) + act = LIBETH_XDP_DROP; + + bq->act_mask |= act; + + return act; +} + +/** + * libeth_xdp_run_prog - run XDP program (non-XSk path) and handle all verdicts + * @xdp: XDP buffer to process + * @bq: XDP Tx bulk to queue ``XDP_TX`` buffers + * @fl: driver ``XDP_TX`` bulk flush callback + * + * Run the attached XDP program and handle all possible verdicts. XSk has its + * own version. + * Prefer using it via LIBETH_XDP_DEFINE_RUN{,_PASS,_PROG}(). + * + * Return: true if the buffer should be passed up the stack, false if the poll + * should go to the next buffer. + */ +#define libeth_xdp_run_prog(xdp, bq, fl) \ + (__libeth_xdp_run_flush(xdp, bq, __libeth_xdp_run_prog, \ + libeth_xdp_tx_queue_bulk, \ + fl) == LIBETH_XDP_PASS) + +/** + * __libeth_xdp_run_pass - helper to run XDP program and handle the result + * @xdp: XDP buffer to process + * @bq: XDP Tx bulk to queue ``XDP_TX`` frames + * @napi: NAPI to build an skb and pass it up the stack + * @rs: onstack libeth RQ stats + * @md: metadata that should be filled to the XDP buffer + * @prep: callback for filling the metadata + * @run: driver wrapper to run XDP program + * @populate: driver callback to populate an skb with the HW descriptor data + * + * Inline abstraction that does the following (non-XSk path): + * 1) adds frame size and frag number (if needed) to the onstack stats; + * 2) fills the descriptor metadata to the onstack &libeth_xdp_buff + * 3) runs XDP program if present; + * 4) handles all possible verdicts; + * 5) on ``XDP_PASS`, builds an skb from the buffer; + * 6) populates it with the descriptor metadata; + * 7) passes it up the stack. + * + * In most cases, number 2 means just writing the pointer to the HW descriptor + * to the XDP buffer. If so, please use LIBETH_XDP_DEFINE_RUN{,_PASS}() + * wrappers to build a driver function. + */ +static __always_inline void +__libeth_xdp_run_pass(struct libeth_xdp_buff *xdp, + struct libeth_xdp_tx_bulk *bq, struct napi_struct *napi, + struct libeth_rq_napi_stats *rs, const void *md, + void (*prep)(struct libeth_xdp_buff *xdp, + const void *md), + bool (*run)(struct libeth_xdp_buff *xdp, + struct libeth_xdp_tx_bulk *bq), + bool (*populate)(struct sk_buff *skb, + const struct libeth_xdp_buff *xdp, + struct libeth_rq_napi_stats *rs)) +{ + struct sk_buff *skb; + + rs->bytes += xdp->base.data_end - xdp->data; + rs->packets++; + + if (xdp_buff_has_frags(&xdp->base)) + libeth_xdp_buff_stats_frags(rs, xdp); + + if (prep && (!__builtin_constant_p(!!md) || md)) + prep(xdp, md); + + if (!bq || !run || !bq->prog) + goto build; + + if (!run(xdp, bq)) + return; + +build: + skb = xdp_build_skb_from_buff(&xdp->base); + if (unlikely(!skb)) { + libeth_xdp_return_buff_slow(xdp); + return; + } + + xdp->data = NULL; + + if (unlikely(!populate(skb, xdp, rs))) { + napi_consume_skb(skb, true); + return; + } + + napi_gro_receive(napi, skb); +} + +static inline void libeth_xdp_prep_desc(struct libeth_xdp_buff *xdp, + const void *desc) +{ + xdp->desc = desc; +} + +/** + * libeth_xdp_run_pass - helper to run XDP program and handle the result + * @xdp: XDP buffer to process + * @bq: XDP Tx bulk to queue ``XDP_TX`` frames + * @napi: NAPI to build an skb and pass it up the stack + * @ss: onstack libeth RQ stats + * @desc: pointer to the HW descriptor for that frame + * @run: driver wrapper to run XDP program + * @populate: driver callback to populate an skb with the HW descriptor data + * + * Wrapper around the underscored version when "fill the descriptor metadata" + * means just writing the pointer to the HW descriptor as @xdp->desc. + */ +#define libeth_xdp_run_pass(xdp, bq, napi, ss, desc, run, populate) \ + __libeth_xdp_run_pass(xdp, bq, napi, ss, desc, libeth_xdp_prep_desc, \ + run, populate) + +/** + * libeth_xdp_finalize_rx - finalize XDPSQ after a NAPI polling loop (non-XSk) + * @bq: ``XDP_TX`` frame bulk + * @flush: driver callback to flush the bulk + * @finalize: driver callback to start sending the frames and run the timer + * + * Flush the bulk if there are frames left to send, kick the queue and flush + * the XDP maps. + */ +#define libeth_xdp_finalize_rx(bq, flush, finalize) \ + __libeth_xdp_finalize_rx(bq, 0, flush, finalize) + +static __always_inline void +__libeth_xdp_finalize_rx(struct libeth_xdp_tx_bulk *bq, u32 flags, + bool (*flush_bulk)(struct libeth_xdp_tx_bulk *bq, + u32 flags), + void (*finalize)(void *xdpsq, bool sent, bool flush)) +{ + if (bq->act_mask & LIBETH_XDP_TX) { + if (bq->count) + flush_bulk(bq, flags | LIBETH_XDP_TX_DROP); + finalize(bq->xdpsq, true, true); + } + if (bq->act_mask & LIBETH_XDP_REDIRECT) + xdp_do_flush(); + + rcu_read_unlock(); +} + +/* + * Helpers to reduce boilerplate code in drivers. + * + * Typical driver Rx flow would be (excl. bulk and buff init, frag attach): + * + * LIBETH_XDP_DEFINE_START(); + * LIBETH_XDP_DEFINE_FLUSH_TX(static driver_xdp_flush_tx, driver_xdp_tx_prep, + * driver_xdp_xmit); + * LIBETH_XDP_DEFINE_RUN(static driver_xdp_run, driver_xdp_run_prog, + * driver_xdp_flush_tx, driver_populate_skb); + * LIBETH_XDP_DEFINE_FINALIZE(static driver_xdp_finalize_rx, + * driver_xdp_flush_tx, driver_xdp_finalize_sq); + * LIBETH_XDP_DEFINE_END(); + * + * This will build a set of 4 static functions. The compiler is free to decide + * whether to inline them. + * Then, in the NAPI polling function: + * + * while (packets < budget) { + * // ... + * driver_xdp_run(xdp, &bq, napi, &rs, desc); + * } + * driver_xdp_finalize_rx(&bq); + */ + +#define LIBETH_XDP_DEFINE_START() \ + __diag_push(); \ + __diag_ignore(GCC, 8, "-Wold-style-declaration", \ + "Allow specifying \'static\' after the return type") + +/** + * LIBETH_XDP_DEFINE_TIMER - define a driver XDPSQ cleanup timer callback + * @name: name of the function to define + * @poll: Tx polling/completion function + */ +#define LIBETH_XDP_DEFINE_TIMER(name, poll) \ +void name(struct work_struct *work) \ +{ \ + libeth_xdpsq_run_timer(work, poll); \ +} + +/** + * LIBETH_XDP_DEFINE_FLUSH_TX - define a driver ``XDP_TX`` bulk flush function + * @name: name of the function to define + * @prep: driver callback to clean an XDPSQ + * @xmit: driver callback to write a HW Tx descriptor + */ +#define LIBETH_XDP_DEFINE_FLUSH_TX(name, prep, xmit) \ + __LIBETH_XDP_DEFINE_FLUSH_TX(name, prep, xmit, xdp) + +#define __LIBETH_XDP_DEFINE_FLUSH_TX(name, prep, xmit, pfx) \ +bool name(struct libeth_xdp_tx_bulk *bq, u32 flags) \ +{ \ + return libeth_##pfx##_tx_flush_bulk(bq, flags, prep, xmit); \ +} + +/** + * LIBETH_XDP_DEFINE_FLUSH_XMIT - define a driver XDP xmit bulk flush function + * @name: name of the function to define + * @prep: driver callback to clean an XDPSQ + * @xmit: driver callback to write a HW Tx descriptor + */ +#define LIBETH_XDP_DEFINE_FLUSH_XMIT(name, prep, xmit) \ +bool name(struct libeth_xdp_tx_bulk *bq, u32 flags) \ +{ \ + return libeth_xdp_xmit_flush_bulk(bq, flags, prep, xmit); \ +} + +/** + * LIBETH_XDP_DEFINE_RUN_PROG - define a driver XDP program run function + * @name: name of the function to define + * @flush: driver callback to flush an ``XDP_TX`` bulk + */ +#define LIBETH_XDP_DEFINE_RUN_PROG(name, flush) \ + bool __LIBETH_XDP_DEFINE_RUN_PROG(name, flush, xdp) + +#define __LIBETH_XDP_DEFINE_RUN_PROG(name, flush, pfx) \ +name(struct libeth_xdp_buff *xdp, struct libeth_xdp_tx_bulk *bq) \ +{ \ + return libeth_##pfx##_run_prog(xdp, bq, flush); \ +} + +/** + * LIBETH_XDP_DEFINE_RUN_PASS - define a driver buffer process + pass function + * @name: name of the function to define + * @run: driver callback to run XDP program (above) + * @populate: driver callback to fill an skb with HW descriptor info + */ +#define LIBETH_XDP_DEFINE_RUN_PASS(name, run, populate) \ + void __LIBETH_XDP_DEFINE_RUN_PASS(name, run, populate, xdp) + +#define __LIBETH_XDP_DEFINE_RUN_PASS(name, run, populate, pfx) \ +name(struct libeth_xdp_buff *xdp, struct libeth_xdp_tx_bulk *bq, \ + struct napi_struct *napi, struct libeth_rq_napi_stats *ss, \ + const void *desc) \ +{ \ + return libeth_##pfx##_run_pass(xdp, bq, napi, ss, desc, run, \ + populate); \ +} + +/** + * LIBETH_XDP_DEFINE_RUN - define a driver buffer process, run + pass function + * @name: name of the function to define + * @run: name of the XDP prog run function to define + * @flush: driver callback to flush an ``XDP_TX`` bulk + * @populate: driver callback to fill an skb with HW descriptor info + */ +#define LIBETH_XDP_DEFINE_RUN(name, run, flush, populate) \ + __LIBETH_XDP_DEFINE_RUN(name, run, flush, populate, XDP) + +#define __LIBETH_XDP_DEFINE_RUN(name, run, flush, populate, pfx) \ + LIBETH_##pfx##_DEFINE_RUN_PROG(static run, flush); \ + LIBETH_##pfx##_DEFINE_RUN_PASS(name, run, populate) + +/** + * LIBETH_XDP_DEFINE_FINALIZE - define a driver Rx NAPI poll finalize function + * @name: name of the function to define + * @flush: driver callback to flush an ``XDP_TX`` bulk + * @finalize: driver callback to finalize an XDPSQ and run the timer + */ +#define LIBETH_XDP_DEFINE_FINALIZE(name, flush, finalize) \ + __LIBETH_XDP_DEFINE_FINALIZE(name, flush, finalize, xdp) + +#define __LIBETH_XDP_DEFINE_FINALIZE(name, flush, finalize, pfx) \ +void name(struct libeth_xdp_tx_bulk *bq) \ +{ \ + libeth_##pfx##_finalize_rx(bq, flush, finalize); \ +} + +#define LIBETH_XDP_DEFINE_END() __diag_pop() + +/* XMO */ + +/** + * libeth_xdp_buff_to_rq - get RQ pointer from an XDP buffer pointer + * @xdp: &libeth_xdp_buff corresponding to the queue + * @type: typeof() of the driver Rx queue structure + * @member: name of &xdp_rxq_info inside @type + * + * Often times, pointer to the RQ is needed when reading/filling metadata from + * HW descriptors. The helper can be used to quickly jump from an XDP buffer + * to the queue corresponding to its &xdp_rxq_info without introducing + * additional fields (&libeth_xdp_buff is precisely 1 cacheline long on x64). + */ +#define libeth_xdp_buff_to_rq(xdp, type, member) \ + container_of_const((xdp)->base.rxq, type, member) + +/** + * libeth_xdpmo_rx_hash - convert &libeth_rx_pt to an XDP RSS hash metadata + * @hash: pointer to the variable to write the hash to + * @rss_type: pointer to the variable to write the hash type to + * @val: hash value from the HW descriptor + * @pt: libeth parsed packet type + * + * Handle zeroed/non-available hash and convert libeth parsed packet type to + * the corresponding XDP RSS hash type. To be called at the end of + * xdp_metadata_ops idpf_xdpmo::xmo_rx_hash() implementation. + * Note that if the driver doesn't use a constant packet type lookup table but + * generates it at runtime, it must call libeth_rx_pt_gen_hash_type(pt) to + * generate XDP RSS hash type for each packet type. + * + * Return: 0 on success, -ENODATA when the hash is not available. + */ +static inline int libeth_xdpmo_rx_hash(u32 *hash, + enum xdp_rss_hash_type *rss_type, + u32 val, struct libeth_rx_pt pt) +{ + if (unlikely(!val)) + return -ENODATA; + + *hash = val; + *rss_type = pt.hash_type; + + return 0; +} + +/* Tx buffer completion */ + +void libeth_xdp_return_buff_bulk(const struct skb_shared_info *sinfo, + struct xdp_frame_bulk *bq, bool frags); +void libeth_xsk_buff_free_slow(struct libeth_xdp_buff *xdp); + +/** + * __libeth_xdp_complete_tx - complete sent XDPSQE + * @sqe: SQ element / Tx buffer to complete + * @cp: Tx polling/completion params + * @bulk: internal callback to bulk-free ``XDP_TX`` buffers + * @xsk: internal callback to free XSk ``XDP_TX`` buffers + * + * Use the non-underscored version in drivers instead. This one is shared + * internally with libeth_tx_complete_any(). + * Complete an XDPSQE of any type of XDP frame. This includes DMA unmapping + * when needed, buffer freeing, stats update, and SQE invalidation. + */ +static __always_inline void +__libeth_xdp_complete_tx(struct libeth_sqe *sqe, struct libeth_cq_pp *cp, + typeof(libeth_xdp_return_buff_bulk) bulk, + typeof(libeth_xsk_buff_free_slow) xsk) +{ + enum libeth_sqe_type type = sqe->type; + + switch (type) { + case LIBETH_SQE_EMPTY: + return; + case LIBETH_SQE_XDP_XMIT: + case LIBETH_SQE_XDP_XMIT_FRAG: + dma_unmap_page(cp->dev, dma_unmap_addr(sqe, dma), + dma_unmap_len(sqe, len), DMA_TO_DEVICE); + break; + default: + break; + } + + switch (type) { + case LIBETH_SQE_XDP_TX: + bulk(sqe->sinfo, cp->bq, sqe->nr_frags != 1); + break; + case LIBETH_SQE_XDP_XMIT: + xdp_return_frame_bulk(sqe->xdpf, cp->bq); + break; + case LIBETH_SQE_XSK_TX: + case LIBETH_SQE_XSK_TX_FRAG: + xsk(sqe->xsk); + break; + default: + break; + } + + switch (type) { + case LIBETH_SQE_XDP_TX: + case LIBETH_SQE_XDP_XMIT: + case LIBETH_SQE_XSK_TX: + cp->xdp_tx -= sqe->nr_frags; + + cp->xss->packets++; + cp->xss->bytes += sqe->bytes; + break; + default: + break; + } + + sqe->type = LIBETH_SQE_EMPTY; +} + +static inline void libeth_xdp_complete_tx(struct libeth_sqe *sqe, + struct libeth_cq_pp *cp) +{ + __libeth_xdp_complete_tx(sqe, cp, libeth_xdp_return_buff_bulk, + libeth_xsk_buff_free_slow); +} + +/* Misc */ + +u32 libeth_xdp_queue_threshold(u32 count); + +void __libeth_xdp_set_features(struct net_device *dev, + const struct xdp_metadata_ops *xmo, + u32 zc_segs, + const struct xsk_tx_metadata_ops *tmo); +void libeth_xdp_set_redirect(struct net_device *dev, bool enable); + +/** + * libeth_xdp_set_features - set XDP features for netdev + * @dev: &net_device to configure + * @...: optional params, see __libeth_xdp_set_features() + * + * Set all the features libeth_xdp supports, including .ndo_xdp_xmit(). That + * said, it should be used only when XDPSQs are always available regardless + * of whether an XDP prog is attached to @dev. + */ +#define libeth_xdp_set_features(dev, ...) \ + CONCATENATE(__libeth_xdp_feat, \ + COUNT_ARGS(__VA_ARGS__))(dev, ##__VA_ARGS__) + +#define __libeth_xdp_feat0(dev) \ + __libeth_xdp_set_features(dev, NULL, 0, NULL) +#define __libeth_xdp_feat1(dev, xmo) \ + __libeth_xdp_set_features(dev, xmo, 0, NULL) +#define __libeth_xdp_feat2(dev, xmo, zc_segs) \ + __libeth_xdp_set_features(dev, xmo, zc_segs, NULL) +#define __libeth_xdp_feat3(dev, xmo, zc_segs, tmo) \ + __libeth_xdp_set_features(dev, xmo, zc_segs, tmo) + +/** + * libeth_xdp_set_features_noredir - enable all libeth_xdp features w/o redir + * @dev: target &net_device + * @...: optional params, see __libeth_xdp_set_features() + * + * Enable everything except the .ndo_xdp_xmit() feature, use when XDPSQs are + * not available right after netdev registration. + */ +#define libeth_xdp_set_features_noredir(dev, ...) \ + __libeth_xdp_set_features_noredir(dev, __UNIQUE_ID(dev_), \ + ##__VA_ARGS__) + +#define __libeth_xdp_set_features_noredir(dev, ud, ...) do { \ + struct net_device *ud = (dev); \ + \ + libeth_xdp_set_features(ud, ##__VA_ARGS__); \ + libeth_xdp_set_redirect(ud, false); \ +} while (0) + +#define libeth_xsktmo ((const void *)GOLDEN_RATIO_PRIME) + +#endif /* __LIBETH_XDP_H */ diff --git a/include/net/libeth/xsk.h b/include/net/libeth/xsk.h new file mode 100644 index 000000000000..481a7b28e6f2 --- /dev/null +++ b/include/net/libeth/xsk.h @@ -0,0 +1,685 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2025 Intel Corporation */ + +#ifndef __LIBETH_XSK_H +#define __LIBETH_XSK_H + +#include <net/libeth/xdp.h> +#include <net/xdp_sock_drv.h> + +/* ``XDP_TXMD_FLAGS_VALID`` is defined only under ``CONFIG_XDP_SOCKETS`` */ +#ifdef XDP_TXMD_FLAGS_VALID +static_assert(XDP_TXMD_FLAGS_VALID <= LIBETH_XDP_TX_XSKMD); +#endif + +/* ``XDP_TX`` bulking */ + +/** + * libeth_xsk_tx_queue_head - internal helper for queueing XSk ``XDP_TX`` head + * @bq: XDP Tx bulk to queue the head frag to + * @xdp: XSk buffer with the head to queue + * + * Return: false if it's the only frag of the frame, true if it's an S/G frame. + */ +static inline bool libeth_xsk_tx_queue_head(struct libeth_xdp_tx_bulk *bq, + struct libeth_xdp_buff *xdp) +{ + bq->bulk[bq->count++] = (typeof(*bq->bulk)){ + .xsk = xdp, + __libeth_xdp_tx_len(xdp->base.data_end - xdp->data, + LIBETH_XDP_TX_FIRST), + }; + + if (likely(!xdp_buff_has_frags(&xdp->base))) + return false; + + bq->bulk[bq->count - 1].flags |= LIBETH_XDP_TX_MULTI; + + return true; +} + +/** + * libeth_xsk_tx_queue_frag - internal helper for queueing XSk ``XDP_TX`` frag + * @bq: XDP Tx bulk to queue the frag to + * @frag: XSk frag to queue + */ +static inline void libeth_xsk_tx_queue_frag(struct libeth_xdp_tx_bulk *bq, + struct libeth_xdp_buff *frag) +{ + bq->bulk[bq->count++] = (typeof(*bq->bulk)){ + .xsk = frag, + __libeth_xdp_tx_len(frag->base.data_end - frag->data), + }; +} + +/** + * libeth_xsk_tx_queue_bulk - internal helper for queueing XSk ``XDP_TX`` frame + * @bq: XDP Tx bulk to queue the frame to + * @xdp: XSk buffer to queue + * @flush_bulk: driver callback to flush the bulk to the HW queue + * + * Return: true on success, false on flush error. + */ +static __always_inline bool +libeth_xsk_tx_queue_bulk(struct libeth_xdp_tx_bulk *bq, + struct libeth_xdp_buff *xdp, + bool (*flush_bulk)(struct libeth_xdp_tx_bulk *bq, + u32 flags)) +{ + bool ret = true; + + if (unlikely(bq->count == LIBETH_XDP_TX_BULK) && + unlikely(!flush_bulk(bq, LIBETH_XDP_TX_XSK))) { + libeth_xsk_buff_free_slow(xdp); + return false; + } + + if (!libeth_xsk_tx_queue_head(bq, xdp)) + goto out; + + for (const struct libeth_xdp_buff *head = xdp; ; ) { + xdp = container_of(xsk_buff_get_frag(&head->base), + typeof(*xdp), base); + if (!xdp) + break; + + if (unlikely(bq->count == LIBETH_XDP_TX_BULK) && + unlikely(!flush_bulk(bq, LIBETH_XDP_TX_XSK))) { + ret = false; + break; + } + + libeth_xsk_tx_queue_frag(bq, xdp); + } + +out: + bq->bulk[bq->count - 1].flags |= LIBETH_XDP_TX_LAST; + + return ret; +} + +/** + * libeth_xsk_tx_fill_buf - internal helper to fill XSk ``XDP_TX`` &libeth_sqe + * @frm: XDP Tx frame from the bulk + * @i: index on the HW queue + * @sq: XDPSQ abstraction for the queue + * @priv: private data + * + * Return: XDP Tx descriptor with the synced DMA and other info to pass to + * the driver callback. + */ +static inline struct libeth_xdp_tx_desc +libeth_xsk_tx_fill_buf(struct libeth_xdp_tx_frame frm, u32 i, + const struct libeth_xdpsq *sq, u64 priv) +{ + struct libeth_xdp_buff *xdp = frm.xsk; + struct libeth_xdp_tx_desc desc = { + .addr = xsk_buff_xdp_get_dma(&xdp->base), + .opts = frm.opts, + }; + struct libeth_sqe *sqe; + + xsk_buff_raw_dma_sync_for_device(sq->pool, desc.addr, desc.len); + + sqe = &sq->sqes[i]; + sqe->xsk = xdp; + + if (!(desc.flags & LIBETH_XDP_TX_FIRST)) { + sqe->type = LIBETH_SQE_XSK_TX_FRAG; + return desc; + } + + sqe->type = LIBETH_SQE_XSK_TX; + libeth_xdp_tx_fill_stats(sqe, &desc, + xdp_get_shared_info_from_buff(&xdp->base)); + + return desc; +} + +/** + * libeth_xsk_tx_flush_bulk - wrapper to define flush of XSk ``XDP_TX`` bulk + * @bq: bulk to flush + * @flags: Tx flags, see __libeth_xdp_tx_flush_bulk() + * @prep: driver callback to prepare the queue + * @xmit: driver callback to fill a HW descriptor + * + * Use via LIBETH_XSK_DEFINE_FLUSH_TX() to define an XSk ``XDP_TX`` driver + * callback. + */ +#define libeth_xsk_tx_flush_bulk(bq, flags, prep, xmit) \ + __libeth_xdp_tx_flush_bulk(bq, (flags) | LIBETH_XDP_TX_XSK, prep, \ + libeth_xsk_tx_fill_buf, xmit) + +/* XSk TMO */ + +/** + * libeth_xsktmo_req_csum - XSk Tx metadata op to request checksum offload + * @csum_start: unused + * @csum_offset: unused + * @priv: &libeth_xdp_tx_desc from the filling helper + * + * Generic implementation of ::tmo_request_checksum. Works only when HW doesn't + * require filling checksum offsets and other parameters beside the checksum + * request bit. + * Consider using within @libeth_xsktmo unless the driver requires HW-specific + * callbacks. + */ +static inline void libeth_xsktmo_req_csum(u16 csum_start, u16 csum_offset, + void *priv) +{ + ((struct libeth_xdp_tx_desc *)priv)->flags |= LIBETH_XDP_TX_CSUM; +} + +/* Only to inline the callbacks below, use @libeth_xsktmo in drivers instead */ +static const struct xsk_tx_metadata_ops __libeth_xsktmo = { + .tmo_request_checksum = libeth_xsktmo_req_csum, +}; + +/** + * __libeth_xsk_xmit_fill_buf_md - internal helper to prepare XSk xmit w/meta + * @xdesc: &xdp_desc from the XSk buffer pool + * @sq: XDPSQ abstraction for the queue + * @priv: XSk Tx metadata ops + * + * Same as __libeth_xsk_xmit_fill_buf(), but requests metadata pointer and + * fills additional fields in &libeth_xdp_tx_desc to ask for metadata offload. + * + * Return: XDP Tx descriptor with the DMA, metadata request bits, and other + * info to pass to the driver callback. + */ +static __always_inline struct libeth_xdp_tx_desc +__libeth_xsk_xmit_fill_buf_md(const struct xdp_desc *xdesc, + const struct libeth_xdpsq *sq, + u64 priv) +{ + const struct xsk_tx_metadata_ops *tmo = libeth_xdp_priv_to_ptr(priv); + struct libeth_xdp_tx_desc desc; + struct xdp_desc_ctx ctx; + + ctx = xsk_buff_raw_get_ctx(sq->pool, xdesc->addr); + desc = (typeof(desc)){ + .addr = ctx.dma, + __libeth_xdp_tx_len(xdesc->len), + }; + + BUILD_BUG_ON(!__builtin_constant_p(tmo == libeth_xsktmo)); + tmo = tmo == libeth_xsktmo ? &__libeth_xsktmo : tmo; + + xsk_tx_metadata_request(ctx.meta, tmo, &desc); + + return desc; +} + +/* XSk xmit implementation */ + +/** + * __libeth_xsk_xmit_fill_buf - internal helper to prepare XSk xmit w/o meta + * @xdesc: &xdp_desc from the XSk buffer pool + * @sq: XDPSQ abstraction for the queue + * + * Return: XDP Tx descriptor with the DMA and other info to pass to + * the driver callback. + */ +static inline struct libeth_xdp_tx_desc +__libeth_xsk_xmit_fill_buf(const struct xdp_desc *xdesc, + const struct libeth_xdpsq *sq) +{ + return (struct libeth_xdp_tx_desc){ + .addr = xsk_buff_raw_get_dma(sq->pool, xdesc->addr), + __libeth_xdp_tx_len(xdesc->len), + }; +} + +/** + * libeth_xsk_xmit_fill_buf - internal helper to prepare an XSk xmit + * @frm: &xdp_desc from the XSk buffer pool + * @i: index on the HW queue + * @sq: XDPSQ abstraction for the queue + * @priv: XSk Tx metadata ops + * + * Depending on the metadata ops presence (determined at compile time), calls + * the quickest helper to build a libeth XDP Tx descriptor. + * + * Return: XDP Tx descriptor with the synced DMA, metadata request bits, + * and other info to pass to the driver callback. + */ +static __always_inline struct libeth_xdp_tx_desc +libeth_xsk_xmit_fill_buf(struct libeth_xdp_tx_frame frm, u32 i, + const struct libeth_xdpsq *sq, u64 priv) +{ + struct libeth_xdp_tx_desc desc; + + if (priv) + desc = __libeth_xsk_xmit_fill_buf_md(&frm.desc, sq, priv); + else + desc = __libeth_xsk_xmit_fill_buf(&frm.desc, sq); + + desc.flags |= xsk_is_eop_desc(&frm.desc) ? LIBETH_XDP_TX_LAST : 0; + + xsk_buff_raw_dma_sync_for_device(sq->pool, desc.addr, desc.len); + + return desc; +} + +/** + * libeth_xsk_xmit_do_bulk - send XSk xmit frames + * @pool: XSk buffer pool containing the frames to send + * @xdpsq: opaque pointer to driver's XDPSQ struct + * @budget: maximum number of frames can be sent + * @tmo: optional XSk Tx metadata ops + * @prep: driver callback to build a &libeth_xdpsq + * @xmit: driver callback to put frames to a HW queue + * @finalize: driver callback to start a transmission + * + * Implements generic XSk xmit. Always turns on XSk Tx wakeup as it's assumed + * lazy cleaning is used and interrupts are disabled for the queue. + * HW descriptor filling is unrolled by ``LIBETH_XDP_TX_BATCH`` to optimize + * writes. + * Note that unlike other XDP Tx ops, the queue must be locked and cleaned + * prior to calling this function to already know available @budget. + * @prepare must only build a &libeth_xdpsq and return ``U32_MAX``. + * + * Return: false if @budget was exhausted, true otherwise. + */ +static __always_inline bool +libeth_xsk_xmit_do_bulk(struct xsk_buff_pool *pool, void *xdpsq, u32 budget, + const struct xsk_tx_metadata_ops *tmo, + u32 (*prep)(void *xdpsq, struct libeth_xdpsq *sq), + void (*xmit)(struct libeth_xdp_tx_desc desc, u32 i, + const struct libeth_xdpsq *sq, u64 priv), + void (*finalize)(void *xdpsq, bool sent, bool flush)) +{ + const struct libeth_xdp_tx_frame *bulk; + bool wake; + u32 n; + + wake = xsk_uses_need_wakeup(pool); + if (wake) + xsk_clear_tx_need_wakeup(pool); + + n = xsk_tx_peek_release_desc_batch(pool, budget); + bulk = container_of(&pool->tx_descs[0], typeof(*bulk), desc); + + libeth_xdp_tx_xmit_bulk(bulk, xdpsq, n, true, + libeth_xdp_ptr_to_priv(tmo), prep, + libeth_xsk_xmit_fill_buf, xmit); + finalize(xdpsq, n, true); + + if (wake) + xsk_set_tx_need_wakeup(pool); + + return n < budget; +} + +/* Rx polling path */ + +/** + * libeth_xsk_tx_init_bulk - initialize XDP Tx bulk for an XSk Rx NAPI poll + * @bq: bulk to initialize + * @prog: RCU pointer to the XDP program (never %NULL) + * @dev: target &net_device + * @xdpsqs: array of driver XDPSQ structs + * @num: number of active XDPSQs, the above array length + * + * Should be called on an onstack XDP Tx bulk before the XSk NAPI polling loop. + * Initializes all the needed fields to run libeth_xdp functions. + * Never checks if @prog is %NULL or @num == 0 as XDP must always be enabled + * when hitting this path. + */ +#define libeth_xsk_tx_init_bulk(bq, prog, dev, xdpsqs, num) \ + __libeth_xdp_tx_init_bulk(bq, prog, dev, xdpsqs, num, true, \ + __UNIQUE_ID(bq_), __UNIQUE_ID(nqs_)) + +struct libeth_xdp_buff *libeth_xsk_buff_add_frag(struct libeth_xdp_buff *head, + struct libeth_xdp_buff *xdp); + +/** + * libeth_xsk_process_buff - attach XSk Rx buffer to &libeth_xdp_buff + * @head: head XSk buffer to attach the XSk buffer to (or %NULL) + * @xdp: XSk buffer to process + * @len: received data length from the descriptor + * + * If @head == %NULL, treats the XSk buffer as head and initializes + * the required fields. Otherwise, attaches the buffer as a frag. + * Already performs DMA sync-for-CPU and frame start prefetch + * (for head buffers only). + * + * Return: head XSk buffer on success or if the descriptor must be skipped + * (empty), %NULL if there is no space for a new frag. + */ +static inline struct libeth_xdp_buff * +libeth_xsk_process_buff(struct libeth_xdp_buff *head, + struct libeth_xdp_buff *xdp, u32 len) +{ + if (unlikely(!len)) { + libeth_xsk_buff_free_slow(xdp); + return head; + } + + xsk_buff_set_size(&xdp->base, len); + xsk_buff_dma_sync_for_cpu(&xdp->base); + + if (head) + return libeth_xsk_buff_add_frag(head, xdp); + + prefetch(xdp->data); + + return xdp; +} + +void libeth_xsk_buff_stats_frags(struct libeth_rq_napi_stats *rs, + const struct libeth_xdp_buff *xdp); + +u32 __libeth_xsk_run_prog_slow(struct libeth_xdp_buff *xdp, + const struct libeth_xdp_tx_bulk *bq, + enum xdp_action act, int ret); + +/** + * __libeth_xsk_run_prog - run XDP program on XSk buffer + * @xdp: XSk buffer to run the prog on + * @bq: buffer bulk for ``XDP_TX`` queueing + * + * Internal inline abstraction to run XDP program on XSk Rx path. Handles + * only the most common ``XDP_REDIRECT`` inline, the rest is processed + * externally. + * Reports an XDP prog exception on errors. + * + * Return: libeth_xdp prog verdict depending on the prog's verdict. + */ +static __always_inline u32 +__libeth_xsk_run_prog(struct libeth_xdp_buff *xdp, + const struct libeth_xdp_tx_bulk *bq) +{ + enum xdp_action act; + int ret = 0; + + act = bpf_prog_run_xdp(bq->prog, &xdp->base); + if (unlikely(act != XDP_REDIRECT)) +rest: + return __libeth_xsk_run_prog_slow(xdp, bq, act, ret); + + ret = xdp_do_redirect(bq->dev, &xdp->base, bq->prog); + if (unlikely(ret)) + goto rest; + + return LIBETH_XDP_REDIRECT; +} + +/** + * libeth_xsk_run_prog - run XDP program on XSk path and handle all verdicts + * @xdp: XSk buffer to process + * @bq: XDP Tx bulk to queue ``XDP_TX`` buffers + * @fl: driver ``XDP_TX`` bulk flush callback + * + * Run the attached XDP program and handle all possible verdicts. + * Prefer using it via LIBETH_XSK_DEFINE_RUN{,_PASS,_PROG}(). + * + * Return: libeth_xdp prog verdict depending on the prog's verdict. + */ +#define libeth_xsk_run_prog(xdp, bq, fl) \ + __libeth_xdp_run_flush(xdp, bq, __libeth_xsk_run_prog, \ + libeth_xsk_tx_queue_bulk, fl) + +/** + * __libeth_xsk_run_pass - helper to run XDP program and handle the result + * @xdp: XSk buffer to process + * @bq: XDP Tx bulk to queue ``XDP_TX`` frames + * @napi: NAPI to build an skb and pass it up the stack + * @rs: onstack libeth RQ stats + * @md: metadata that should be filled to the XSk buffer + * @prep: callback for filling the metadata + * @run: driver wrapper to run XDP program + * @populate: driver callback to populate an skb with the HW descriptor data + * + * Inline abstraction, XSk's counterpart of __libeth_xdp_run_pass(), see its + * doc for details. + * + * Return: false if the polling loop must be exited due to lack of free + * buffers, true otherwise. + */ +static __always_inline bool +__libeth_xsk_run_pass(struct libeth_xdp_buff *xdp, + struct libeth_xdp_tx_bulk *bq, struct napi_struct *napi, + struct libeth_rq_napi_stats *rs, const void *md, + void (*prep)(struct libeth_xdp_buff *xdp, + const void *md), + u32 (*run)(struct libeth_xdp_buff *xdp, + struct libeth_xdp_tx_bulk *bq), + bool (*populate)(struct sk_buff *skb, + const struct libeth_xdp_buff *xdp, + struct libeth_rq_napi_stats *rs)) +{ + struct sk_buff *skb; + u32 act; + + rs->bytes += xdp->base.data_end - xdp->data; + rs->packets++; + + if (unlikely(xdp_buff_has_frags(&xdp->base))) + libeth_xsk_buff_stats_frags(rs, xdp); + + if (prep && (!__builtin_constant_p(!!md) || md)) + prep(xdp, md); + + act = run(xdp, bq); + if (likely(act == LIBETH_XDP_REDIRECT)) + return true; + + if (act != LIBETH_XDP_PASS) + return act != LIBETH_XDP_ABORTED; + + skb = xdp_build_skb_from_zc(&xdp->base); + if (unlikely(!skb)) { + libeth_xsk_buff_free_slow(xdp); + return true; + } + + if (unlikely(!populate(skb, xdp, rs))) { + napi_consume_skb(skb, true); + return true; + } + + napi_gro_receive(napi, skb); + + return true; +} + +/** + * libeth_xsk_run_pass - helper to run XDP program and handle the result + * @xdp: XSk buffer to process + * @bq: XDP Tx bulk to queue ``XDP_TX`` frames + * @napi: NAPI to build an skb and pass it up the stack + * @rs: onstack libeth RQ stats + * @desc: pointer to the HW descriptor for that frame + * @run: driver wrapper to run XDP program + * @populate: driver callback to populate an skb with the HW descriptor data + * + * Wrapper around the underscored version when "fill the descriptor metadata" + * means just writing the pointer to the HW descriptor as @xdp->desc. + */ +#define libeth_xsk_run_pass(xdp, bq, napi, rs, desc, run, populate) \ + __libeth_xsk_run_pass(xdp, bq, napi, rs, desc, libeth_xdp_prep_desc, \ + run, populate) + +/** + * libeth_xsk_finalize_rx - finalize XDPSQ after an XSk NAPI polling loop + * @bq: ``XDP_TX`` frame bulk + * @flush: driver callback to flush the bulk + * @finalize: driver callback to start sending the frames and run the timer + * + * Flush the bulk if there are frames left to send, kick the queue and flush + * the XDP maps. + */ +#define libeth_xsk_finalize_rx(bq, flush, finalize) \ + __libeth_xdp_finalize_rx(bq, LIBETH_XDP_TX_XSK, flush, finalize) + +/* + * Helpers to reduce boilerplate code in drivers. + * + * Typical driver XSk Rx flow would be (excl. bulk and buff init, frag attach): + * + * LIBETH_XDP_DEFINE_START(); + * LIBETH_XSK_DEFINE_FLUSH_TX(static driver_xsk_flush_tx, driver_xsk_tx_prep, + * driver_xdp_xmit); + * LIBETH_XSK_DEFINE_RUN(static driver_xsk_run, driver_xsk_run_prog, + * driver_xsk_flush_tx, driver_populate_skb); + * LIBETH_XSK_DEFINE_FINALIZE(static driver_xsk_finalize_rx, + * driver_xsk_flush_tx, driver_xdp_finalize_sq); + * LIBETH_XDP_DEFINE_END(); + * + * This will build a set of 4 static functions. The compiler is free to decide + * whether to inline them. + * Then, in the NAPI polling function: + * + * while (packets < budget) { + * // ... + * if (!driver_xsk_run(xdp, &bq, napi, &rs, desc)) + * break; + * } + * driver_xsk_finalize_rx(&bq); + */ + +/** + * LIBETH_XSK_DEFINE_FLUSH_TX - define a driver XSk ``XDP_TX`` flush function + * @name: name of the function to define + * @prep: driver callback to clean an XDPSQ + * @xmit: driver callback to write a HW Tx descriptor + */ +#define LIBETH_XSK_DEFINE_FLUSH_TX(name, prep, xmit) \ + __LIBETH_XDP_DEFINE_FLUSH_TX(name, prep, xmit, xsk) + +/** + * LIBETH_XSK_DEFINE_RUN_PROG - define a driver XDP program run function + * @name: name of the function to define + * @flush: driver callback to flush an XSk ``XDP_TX`` bulk + */ +#define LIBETH_XSK_DEFINE_RUN_PROG(name, flush) \ + u32 __LIBETH_XDP_DEFINE_RUN_PROG(name, flush, xsk) + +/** + * LIBETH_XSK_DEFINE_RUN_PASS - define a driver buffer process + pass function + * @name: name of the function to define + * @run: driver callback to run XDP program (above) + * @populate: driver callback to fill an skb with HW descriptor info + */ +#define LIBETH_XSK_DEFINE_RUN_PASS(name, run, populate) \ + bool __LIBETH_XDP_DEFINE_RUN_PASS(name, run, populate, xsk) + +/** + * LIBETH_XSK_DEFINE_RUN - define a driver buffer process, run + pass function + * @name: name of the function to define + * @run: name of the XDP prog run function to define + * @flush: driver callback to flush an XSk ``XDP_TX`` bulk + * @populate: driver callback to fill an skb with HW descriptor info + */ +#define LIBETH_XSK_DEFINE_RUN(name, run, flush, populate) \ + __LIBETH_XDP_DEFINE_RUN(name, run, flush, populate, XSK) + +/** + * LIBETH_XSK_DEFINE_FINALIZE - define a driver XSk NAPI poll finalize function + * @name: name of the function to define + * @flush: driver callback to flush an XSk ``XDP_TX`` bulk + * @finalize: driver callback to finalize an XDPSQ and run the timer + */ +#define LIBETH_XSK_DEFINE_FINALIZE(name, flush, finalize) \ + __LIBETH_XDP_DEFINE_FINALIZE(name, flush, finalize, xsk) + +/* Refilling */ + +/** + * struct libeth_xskfq - structure representing an XSk buffer (fill) queue + * @fp: hotpath part of the structure + * @pool: &xsk_buff_pool for buffer management + * @fqes: array of XSk buffer pointers + * @descs: opaque pointer to the HW descriptor array + * @ntu: index of the next buffer to poll + * @count: number of descriptors/buffers the queue has + * @pending: current number of XSkFQEs to refill + * @thresh: threshold below which the queue is refilled + * @buf_len: HW-writeable length per each buffer + * @nid: ID of the closest NUMA node with memory + */ +struct libeth_xskfq { + struct_group_tagged(libeth_xskfq_fp, fp, + struct xsk_buff_pool *pool; + struct libeth_xdp_buff **fqes; + void *descs; + + u32 ntu; + u32 count; + ); + + /* Cold fields */ + u32 pending; + u32 thresh; + + u32 buf_len; + int nid; +}; + +int libeth_xskfq_create(struct libeth_xskfq *fq); +void libeth_xskfq_destroy(struct libeth_xskfq *fq); + +/** + * libeth_xsk_buff_xdp_get_dma - get DMA address of XSk &libeth_xdp_buff + * @xdp: buffer to get the DMA addr for + */ +#define libeth_xsk_buff_xdp_get_dma(xdp) \ + xsk_buff_xdp_get_dma(&(xdp)->base) + +/** + * libeth_xskfqe_alloc - allocate @n XSk Rx buffers + * @fq: hotpath part of the XSkFQ, usually onstack + * @n: number of buffers to allocate + * @fill: driver callback to write DMA addresses to HW descriptors + * + * Note that @fq->ntu gets updated, but ::pending must be recalculated + * by the caller. + * + * Return: number of buffers refilled. + */ +static __always_inline u32 +libeth_xskfqe_alloc(struct libeth_xskfq_fp *fq, u32 n, + void (*fill)(const struct libeth_xskfq_fp *fq, u32 i)) +{ + u32 this, ret, done = 0; + struct xdp_buff **xskb; + + this = fq->count - fq->ntu; + if (likely(this > n)) + this = n; + +again: + xskb = (typeof(xskb))&fq->fqes[fq->ntu]; + ret = xsk_buff_alloc_batch(fq->pool, xskb, this); + + for (u32 i = 0, ntu = fq->ntu; likely(i < ret); i++) + fill(fq, ntu + i); + + done += ret; + fq->ntu += ret; + + if (likely(fq->ntu < fq->count) || unlikely(ret < this)) + goto out; + + fq->ntu = 0; + + if (this < n) { + this = n - this; + goto again; + } + +out: + return done; +} + +/* .ndo_xsk_wakeup */ + +void libeth_xsk_init_wakeup(call_single_data_t *csd, struct napi_struct *napi); +void libeth_xsk_wakeup(call_single_data_t *csd, u32 qid); + +/* Pool setup */ + +int libeth_xsk_setup_pool(struct net_device *dev, u32 qid, bool enable); + +#endif /* __LIBETH_XSK_H */ diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 3ce56a816425..92ab85061df0 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -10,6 +10,7 @@ #include "shm_channel.h" #define GDMA_STATUS_MORE_ENTRIES 0x00000105 +#define GDMA_STATUS_CMD_UNSUPPORTED 0xffffffff /* Structures labeled with "HW DATA" are exchanged with the hardware. All of * them are naturally aligned and hence don't need __packed. @@ -58,7 +59,7 @@ enum gdma_eqe_type { GDMA_EQE_HWC_INIT_EQ_ID_DB = 129, GDMA_EQE_HWC_INIT_DATA = 130, GDMA_EQE_HWC_INIT_DONE = 131, - GDMA_EQE_HWC_SOC_RECONFIG = 132, + GDMA_EQE_HWC_FPGA_RECONFIG = 132, GDMA_EQE_HWC_SOC_RECONFIG_DATA = 133, GDMA_EQE_HWC_SOC_SERVICE = 134, GDMA_EQE_RNIC_QP_FATAL = 176, @@ -388,7 +389,7 @@ struct gdma_context { unsigned int max_num_queues; unsigned int max_num_msix; unsigned int num_msix_usable; - struct gdma_irq_context *irq_contexts; + struct xarray irq_contexts; /* L2 MTU */ u16 adapter_mtu; @@ -403,6 +404,8 @@ struct gdma_context { u32 test_event_eq_id; bool is_pf; + bool in_service; + phys_addr_t bar0_pa; void __iomem *bar0_va; void __iomem *shm_base; @@ -578,12 +581,20 @@ enum { /* Driver can handle holes (zeros) in the device list */ #define GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP BIT(11) +/* Driver supports dynamic MSI-X vector allocation */ +#define GDMA_DRV_CAP_FLAG_1_DYNAMIC_IRQ_ALLOC_SUPPORT BIT(13) + +/* Driver can self reset on FPGA Reconfig EQE notification */ +#define GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE BIT(17) + #define GDMA_DRV_CAP_FLAGS1 \ (GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \ GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \ GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG | \ GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT | \ - GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP) + GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP | \ + GDMA_DRV_CAP_FLAG_1_DYNAMIC_IRQ_ALLOC_SUPPORT | \ + GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE) #define GDMA_DRV_CAP_FLAGS2 0 diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 4176edf1be71..e1030a7d2daa 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -5,6 +5,7 @@ #define _MANA_H #include <net/xdp.h> +#include <net/net_shaper.h> #include "gdma.h" #include "hw_channel.h" @@ -526,7 +527,14 @@ struct mana_port_context { struct mutex vport_mutex; int vport_use_count; + /* Net shaper handle*/ + struct net_shaper_handle handle; + u16 port_idx; + /* Currently configured speed (mbps) */ + u32 speed; + /* Maximum speed supported by the SKU (mbps) */ + u32 max_speed; bool port_is_up; bool port_st_save; /* Saved port state */ @@ -562,6 +570,9 @@ struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog); int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf); void mana_query_gf_stats(struct mana_port_context *apc); +int mana_query_link_cfg(struct mana_port_context *apc); +int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed, + int enable_clamping); void mana_query_phy_stats(struct mana_port_context *apc); int mana_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu, int num_queues); void mana_pre_dealloc_rxbufs(struct mana_port_context *apc); @@ -589,6 +600,8 @@ enum mana_command_code { MANA_FENCE_RQ = 0x20006, MANA_CONFIG_VPORT_RX = 0x20007, MANA_QUERY_VPORT_CONFIG = 0x20008, + MANA_QUERY_LINK_CONFIG = 0x2000A, + MANA_SET_BW_CLAMP = 0x2000B, MANA_QUERY_PHY_STAT = 0x2000c, /* Privileged commands for the PF mode */ @@ -598,6 +611,35 @@ enum mana_command_code { MANA_DEREGISTER_HW_PORT = 0x28004, }; +/* Query Link Configuration*/ +struct mana_query_link_config_req { + struct gdma_req_hdr hdr; + mana_handle_t vport; +}; /* HW DATA */ + +struct mana_query_link_config_resp { + struct gdma_resp_hdr hdr; + u32 qos_speed_mbps; + u8 qos_unconfigured; + u8 reserved1[3]; + u32 link_speed_mbps; + u8 reserved2[4]; +}; /* HW DATA */ + +/* Set Bandwidth Clamp*/ +struct mana_set_bw_clamp_req { + struct gdma_req_hdr hdr; + mana_handle_t vport; + enum TRI_STATE enable_clamping; + u32 link_speed_mbps; +}; /* HW DATA */ + +struct mana_set_bw_clamp_resp { + struct gdma_resp_hdr hdr; + u8 qos_unconfigured; + u8 reserved[7]; +}; /* HW DATA */ + /* Query Device Configuration */ struct mana_query_device_cfg_req { struct gdma_req_hdr hdr; diff --git a/include/net/netmem.h b/include/net/netmem.h index 386164fb9c18..7a1dafa3f080 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -89,8 +89,7 @@ static inline unsigned int net_iov_idx(const struct net_iov *niov) * typedef netmem_ref - a nonexistent type marking a reference to generic * network memory. * - * A netmem_ref currently is always a reference to a struct page. This - * abstraction is introduced so support for new memory types can be added. + * A netmem_ref can be a struct page* or a struct net_iov* underneath. * * Use the supplied helpers to obtain the underlying memory pointer and fields. */ @@ -117,9 +116,6 @@ static inline struct page *__netmem_to_page(netmem_ref netmem) return (__force struct page *)netmem; } -/* This conversion fails (returns NULL) if the netmem_ref is not struct page - * backed. - */ static inline struct page *netmem_to_page(netmem_ref netmem) { if (WARN_ON_ONCE(netmem_is_net_iov(netmem))) @@ -143,7 +139,7 @@ static inline netmem_ref net_iov_to_netmem(struct net_iov *niov) return (__force netmem_ref)((unsigned long)niov | NET_IOV); } -static inline netmem_ref page_to_netmem(struct page *page) +static inline netmem_ref page_to_netmem(const struct page *page) { return (__force netmem_ref)page; } @@ -178,6 +174,21 @@ static inline unsigned long netmem_pfn_trace(netmem_ref netmem) return page_to_pfn(netmem_to_page(netmem)); } +/* __netmem_clear_lsb - convert netmem_ref to struct net_iov * for access to + * common fields. + * @netmem: netmem reference to extract as net_iov. + * + * All the sub types of netmem_ref (page, net_iov) have the same pp, pp_magic, + * dma_addr, and pp_ref_count fields at the same offsets. Thus, we can access + * these fields without a type check to make sure that the underlying mem is + * net_iov or page. + * + * The resulting value of this function can only be used to access the fields + * that are NET_IOV_ASSERT_OFFSET'd. Accessing any other fields will result in + * undefined behavior. + * + * Return: the netmem_ref cast to net_iov* regardless of its underlying type. + */ static inline struct net_iov *__netmem_clear_lsb(netmem_ref netmem) { return (struct net_iov *)((__force unsigned long)netmem & ~NET_IOV); diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 93f2c31baf9b..773fc65780b5 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -153,6 +153,13 @@ static inline netmem_ref page_pool_dev_alloc_netmem(struct page_pool *pool, return page_pool_alloc_netmem(pool, offset, size, gfp); } +static inline netmem_ref page_pool_dev_alloc_netmems(struct page_pool *pool) +{ + gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; + + return page_pool_alloc_netmems(pool, gfp); +} + static inline struct page *page_pool_alloc(struct page_pool *pool, unsigned int *offset, unsigned int *size, gfp_t gfp) diff --git a/include/net/pfcp.h b/include/net/pfcp.h index af14f970b80e..639553797d3e 100644 --- a/include/net/pfcp.h +++ b/include/net/pfcp.h @@ -45,7 +45,7 @@ struct pfcphdr_session { reserved:4; #elif defined(__BIG_ENDIAN_BITFIELD) u8 reserved:4, - message_priprity:4; + message_priority:4; #else #error "Please fix <asm/byteorder>" #endif diff --git a/include/net/sock.h b/include/net/sock.h index 70c0b570a21f..ca532227cbfd 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2677,6 +2677,10 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); +bool skb_has_tx_timestamp(struct sk_buff *skb, const struct sock *sk); +int skb_get_tx_timestamp(struct sk_buff *skb, struct sock *sk, + struct timespec64 *ts); + static inline void sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { diff --git a/include/net/tcp.h b/include/net/tcp.h index 5078ad868fee..761c4a0ad386 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -321,7 +321,7 @@ extern struct proto tcp_prot; #define TCP_DEC_STATS(net, field) SNMP_DEC_STATS((net)->mib.tcp_statistics, field) #define TCP_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val) -void tcp_tasklet_init(void); +void tcp_tsq_work_init(void); int tcp_v4_err(struct sk_buff *skb, u32); @@ -1811,14 +1811,8 @@ static inline void tcp_mib_init(struct net *net) } /* from STCP */ -static inline void tcp_clear_retrans_hints_partial(struct tcp_sock *tp) -{ - tp->lost_skb_hint = NULL; -} - static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp) { - tcp_clear_retrans_hints_partial(tp); tp->retransmit_skb_hint = NULL; } diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 2df3b8344eb5..cbd3a43074bd 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -130,35 +130,20 @@ void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock, void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type); void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type); -static inline void udp_tunnel_get_rx_info(struct net_device *dev) -{ - ASSERT_RTNL(); - if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) - return; - call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev); -} - -static inline void udp_tunnel_drop_rx_info(struct net_device *dev) -{ - ASSERT_RTNL(); - if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) - return; - call_netdevice_notifiers(NETDEV_UDP_TUNNEL_DROP_INFO, dev); -} - /* Transmit the skb using UDP encapsulation. */ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, - bool xnet, bool nocheck); + bool xnet, bool nocheck, u16 ipcb_flags); -int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, - struct net_device *dev, - const struct in6_addr *saddr, - const struct in6_addr *daddr, - __u8 prio, __u8 ttl, __be32 label, - __be16 src_port, __be16 dst_port, bool nocheck); +void udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, + struct net_device *dev, + const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u8 prio, __u8 ttl, __be32 label, + __be16 src_port, __be16 dst_port, bool nocheck, + u16 ip6cb_flags); void udp_tunnel_sock_release(struct socket *sock); @@ -221,19 +206,17 @@ static inline void udp_tunnel_encap_enable(struct sock *sk) #define UDP_TUNNEL_NIC_MAX_TABLES 4 enum udp_tunnel_nic_info_flags { - /* Device callbacks may sleep */ - UDP_TUNNEL_NIC_INFO_MAY_SLEEP = BIT(0), /* Device only supports offloads when it's open, all ports * will be removed before close and re-added after open. */ - UDP_TUNNEL_NIC_INFO_OPEN_ONLY = BIT(1), + UDP_TUNNEL_NIC_INFO_OPEN_ONLY = BIT(0), /* Device supports only IPv4 tunnels */ - UDP_TUNNEL_NIC_INFO_IPV4_ONLY = BIT(2), + UDP_TUNNEL_NIC_INFO_IPV4_ONLY = BIT(1), /* Device has hard-coded the IANA VXLAN port (4789) as VXLAN. * This port must not be counted towards n_entries of any table. * Driver will not receive any callback associated with port 4789. */ - UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN = BIT(3), + UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN = BIT(2), }; struct udp_tunnel_nic; @@ -324,6 +307,9 @@ struct udp_tunnel_nic_ops { size_t (*dump_size)(struct net_device *dev, unsigned int table); int (*dump_write)(struct net_device *dev, unsigned int table, struct sk_buff *skb); + void (*assert_locked)(struct net_device *dev); + void (*lock)(struct net_device *dev); + void (*unlock)(struct net_device *dev); }; #ifdef CONFIG_INET @@ -352,8 +338,29 @@ static inline void udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv) { - if (udp_tunnel_nic_ops) + if (udp_tunnel_nic_ops) { + udp_tunnel_nic_ops->lock(dev); udp_tunnel_nic_ops->set_port_priv(dev, table, idx, priv); + udp_tunnel_nic_ops->unlock(dev); + } +} + +static inline void udp_tunnel_nic_assert_locked(struct net_device *dev) +{ + if (udp_tunnel_nic_ops) + udp_tunnel_nic_ops->assert_locked(dev); +} + +static inline void udp_tunnel_nic_lock(struct net_device *dev) +{ + if (udp_tunnel_nic_ops) + udp_tunnel_nic_ops->lock(dev); +} + +static inline void udp_tunnel_nic_unlock(struct net_device *dev) +{ + if (udp_tunnel_nic_ops) + udp_tunnel_nic_ops->unlock(dev); } static inline void @@ -395,17 +402,50 @@ static inline void udp_tunnel_nic_reset_ntf(struct net_device *dev) static inline size_t udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table) { + size_t ret; + if (!udp_tunnel_nic_ops) return 0; - return udp_tunnel_nic_ops->dump_size(dev, table); + + udp_tunnel_nic_ops->lock(dev); + ret = udp_tunnel_nic_ops->dump_size(dev, table); + udp_tunnel_nic_ops->unlock(dev); + + return ret; } static inline int udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, struct sk_buff *skb) { + int ret; + if (!udp_tunnel_nic_ops) return 0; - return udp_tunnel_nic_ops->dump_write(dev, table, skb); + + udp_tunnel_nic_ops->lock(dev); + ret = udp_tunnel_nic_ops->dump_write(dev, table, skb); + udp_tunnel_nic_ops->unlock(dev); + + return ret; +} + +static inline void udp_tunnel_get_rx_info(struct net_device *dev) +{ + ASSERT_RTNL(); + if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) + return; + udp_tunnel_nic_assert_locked(dev); + call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev); } + +static inline void udp_tunnel_drop_rx_info(struct net_device *dev) +{ + ASSERT_RTNL(); + if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) + return; + udp_tunnel_nic_assert_locked(dev); + call_netdevice_notifiers(NETDEV_UDP_TUNNEL_DROP_INFO, dev); +} + #endif diff --git a/include/net/vxlan.h b/include/net/vxlan.h index e2f7ca045d3e..0ee50785f4f1 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -332,6 +332,7 @@ struct vxlan_dev { #define VXLAN_F_VNIFILTER 0x20000 #define VXLAN_F_MDB 0x40000 #define VXLAN_F_LOCALBYPASS 0x80000 +#define VXLAN_F_MC_ROUTE 0x100000 /* Flags that are used in the receive path. These flags must match in * order for a socket to be shareable @@ -353,7 +354,9 @@ struct vxlan_dev { VXLAN_F_UDP_ZERO_CSUM6_RX | \ VXLAN_F_COLLECT_METADATA | \ VXLAN_F_VNIFILTER | \ - VXLAN_F_LOCALBYPASS) + VXLAN_F_LOCALBYPASS | \ + VXLAN_F_MC_ROUTE | \ + 0) struct net_device *vxlan_dev_create(struct net *net, const char *name, u8 name_assign_type, struct vxlan_config *conf); diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 95f59c1a6f57..54e60c6009e3 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -692,6 +692,7 @@ DEFINE_EVENT(tcp_ao_event, tcp_ao_handshake_failure, TP_ARGS(sk, skb, keyid, rnext, maclen) ); +#ifdef CONFIG_TCP_AO DEFINE_EVENT(tcp_ao_event, tcp_ao_wrong_maclen, TP_PROTO(const struct sock *sk, const struct sk_buff *skb, const __u8 keyid, const __u8 rnext, const __u8 maclen), @@ -830,6 +831,7 @@ DEFINE_EVENT(tcp_ao_event_sne, tcp_ao_rcv_sne_update, TP_PROTO(const struct sock *sk, __u32 new_sne), TP_ARGS(sk, new_sne) ); +#endif /* CONFIG_TCP_AO */ #endif /* _TRACE_TCP_H */ diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index bf97d4b6d51f..349e1b3ca1ae 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -192,6 +192,17 @@ enum dpll_pin_capabilities { #define DPLL_PHASE_OFFSET_DIVIDER 1000 +/** + * enum dpll_feature_state - Allow control (enable/disable) and status checking + * over features. + * @DPLL_FEATURE_STATE_DISABLE: feature shall be disabled + * @DPLL_FEATURE_STATE_ENABLE: feature shall be enabled + */ +enum dpll_feature_state { + DPLL_FEATURE_STATE_DISABLE, + DPLL_FEATURE_STATE_ENABLE, +}; + enum dpll_a { DPLL_A_ID = 1, DPLL_A_MODULE_NAME, @@ -204,6 +215,7 @@ enum dpll_a { DPLL_A_TYPE, DPLL_A_LOCK_STATUS_ERROR, DPLL_A_CLOCK_QUALITY_LEVEL, + DPLL_A_PHASE_OFFSET_MONITOR, __DPLL_A_MAX, DPLL_A_MAX = (__DPLL_A_MAX - 1) diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h index 9a02f579de22..8e5d067e7ddf 100644 --- a/include/uapi/linux/ethtool_netlink_generated.h +++ b/include/uapi/linux/ethtool_netlink_generated.h @@ -49,6 +49,34 @@ enum hwtstamp_source { HWTSTAMP_SOURCE_PHYLIB, }; +/** + * enum ethtool_pse_event - PSE event list for the PSE controller + * @ETHTOOL_PSE_EVENT_OVER_CURRENT: PSE output current is too high + * @ETHTOOL_PSE_EVENT_OVER_TEMP: PSE in over temperature state + * @ETHTOOL_C33_PSE_EVENT_DETECTION: detection process occur on the PSE. IEEE + * 802.3-2022 33.2.5 and 145.2.6 PSE detection of PDs. IEEE 802.3-202 + * 30.9.1.1.5 aPSEPowerDetectionStatus + * @ETHTOOL_C33_PSE_EVENT_CLASSIFICATION: classification process occur on the + * PSE. IEEE 802.3-2022 33.2.6 and 145.2.8 classification of PDs mutual + * identification. IEEE 802.3-2022 30.9.1.1.8 aPSEPowerClassification. + * @ETHTOOL_C33_PSE_EVENT_DISCONNECTION: PD has been disconnected on the PSE. + * IEEE 802.3-2022 33.3.8 and 145.3.9 PD Maintain Power Signature. IEEE + * 802.3-2022 33.5.1.2.9 MPS Absent. IEEE 802.3-2022 30.9.1.1.20 + * aPSEMPSAbsentCounter. + * @ETHTOOL_PSE_EVENT_OVER_BUDGET: PSE turned off due to over budget situation + * @ETHTOOL_PSE_EVENT_SW_PW_CONTROL_ERROR: PSE faced an error managing the + * power control from software + */ +enum ethtool_pse_event { + ETHTOOL_PSE_EVENT_OVER_CURRENT = 1, + ETHTOOL_PSE_EVENT_OVER_TEMP = 2, + ETHTOOL_C33_PSE_EVENT_DETECTION = 4, + ETHTOOL_C33_PSE_EVENT_CLASSIFICATION = 8, + ETHTOOL_C33_PSE_EVENT_DISCONNECTION = 16, + ETHTOOL_PSE_EVENT_OVER_BUDGET = 32, + ETHTOOL_PSE_EVENT_SW_PW_CONTROL_ERROR = 64, +}; + enum { ETHTOOL_A_HEADER_UNSPEC, ETHTOOL_A_HEADER_DEV_INDEX, @@ -642,6 +670,9 @@ enum { ETHTOOL_A_C33_PSE_EXT_SUBSTATE, ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT, ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES, + ETHTOOL_A_PSE_PW_D_ID, + ETHTOOL_A_PSE_PRIO_MAX, + ETHTOOL_A_PSE_PRIO, __ETHTOOL_A_PSE_CNT, ETHTOOL_A_PSE_MAX = (__ETHTOOL_A_PSE_CNT - 1) @@ -719,6 +750,14 @@ enum { }; enum { + ETHTOOL_A_PSE_NTF_HEADER = 1, + ETHTOOL_A_PSE_NTF_EVENTS, + + __ETHTOOL_A_PSE_NTF_CNT, + ETHTOOL_A_PSE_NTF_MAX = (__ETHTOOL_A_PSE_NTF_CNT - 1) +}; + +enum { ETHTOOL_MSG_USER_NONE = 0, ETHTOOL_MSG_STRSET_GET = 1, ETHTOOL_MSG_LINKINFO_GET, @@ -822,6 +861,7 @@ enum { ETHTOOL_MSG_PHY_NTF, ETHTOOL_MSG_TSCONFIG_GET_REPLY, ETHTOOL_MSG_TSCONFIG_SET_REPLY, + ETHTOOL_MSG_PSE_NTF, __ETHTOOL_MSG_KERNEL_CNT, ETHTOOL_MSG_KERNEL_MAX = (__ETHTOOL_MSG_KERNEL_CNT - 1) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 3ad2d5d98034..873c285996fe 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1398,6 +1398,7 @@ enum { IFLA_VXLAN_LOCALBYPASS, IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */ IFLA_VXLAN_RESERVED_BITS, + IFLA_VXLAN_MC_ROUTE, __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) diff --git a/net/core/dev.c b/net/core/dev.c index 5baa4691074f..df1678b1fe24 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3179,7 +3179,6 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) if (dev->reg_state == NETREG_REGISTERED || dev->reg_state == NETREG_UNREGISTERING) { - ASSERT_RTNL(); netdev_ops_assert_locked(dev); rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues, @@ -3229,7 +3228,6 @@ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) return -EINVAL; if (dev->reg_state == NETREG_REGISTERED) { - ASSERT_RTNL(); netdev_ops_assert_locked(dev); rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues, @@ -10771,12 +10769,14 @@ sync_lower: * *before* calling udp_tunnel_get_rx_info, * but *after* calling udp_tunnel_drop_rx_info. */ + udp_tunnel_nic_lock(dev); if (features & NETIF_F_RX_UDP_TUNNEL_PORT) { dev->features = features; udp_tunnel_get_rx_info(dev); } else { udp_tunnel_drop_rx_info(dev); } + udp_tunnel_nic_unlock(dev); } if (diff & NETIF_F_HW_VLAN_CTAG_FILTER) { diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 1ace0cd01adc..c9b969386399 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -641,12 +641,6 @@ static ssize_t phys_port_id_show(struct device *dev, struct netdev_phys_item_id ppid; ssize_t ret; - /* The check is also done in dev_get_phys_port_id; this helps returning - * early without hitting the locking section below. - */ - if (!netdev->netdev_ops->ndo_get_phys_port_id) - return -EOPNOTSUPP; - ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; @@ -668,13 +662,6 @@ static ssize_t phys_port_name_show(struct device *dev, char name[IFNAMSIZ]; ssize_t ret; - /* The checks are also done in dev_get_phys_port_name; this helps - * returning early without hitting the locking section below. - */ - if (!netdev->netdev_ops->ndo_get_phys_port_name && - !netdev->devlink_port) - return -EOPNOTSUPP; - ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; @@ -696,14 +683,6 @@ static ssize_t phys_switch_id_show(struct device *dev, struct netdev_phys_item_id ppid = { }; ssize_t ret; - /* The checks are also done in dev_get_phys_port_name; this helps - * returning early without hitting the locking section below. This works - * because recurse is false when calling dev_get_port_parent_id. - */ - if (!netdev->netdev_ops->ndo_get_port_parent_id && - !netdev->devlink_port) - return -EOPNOTSUPP; - ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; @@ -718,6 +697,40 @@ static ssize_t phys_switch_id_show(struct device *dev, } static DEVICE_ATTR_RO(phys_switch_id); +static struct attribute *netdev_phys_attrs[] __ro_after_init = { + &dev_attr_phys_port_id.attr, + &dev_attr_phys_port_name.attr, + &dev_attr_phys_switch_id.attr, + NULL, +}; + +static umode_t netdev_phys_is_visible(struct kobject *kobj, + struct attribute *attr, int index) +{ + struct device *dev = kobj_to_dev(kobj); + struct net_device *netdev = to_net_dev(dev); + + if (attr == &dev_attr_phys_port_id.attr) { + if (!netdev->netdev_ops->ndo_get_phys_port_id) + return 0; + } else if (attr == &dev_attr_phys_port_name.attr) { + if (!netdev->netdev_ops->ndo_get_phys_port_name && + !netdev->devlink_port) + return 0; + } else if (attr == &dev_attr_phys_switch_id.attr) { + if (!netdev->netdev_ops->ndo_get_port_parent_id && + !netdev->devlink_port) + return 0; + } + + return attr->mode; +} + +static const struct attribute_group netdev_phys_group = { + .attrs = netdev_phys_attrs, + .is_visible = netdev_phys_is_visible, +}; + static ssize_t threaded_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -783,9 +796,6 @@ static struct attribute *net_class_attrs[] __ro_after_init = { &dev_attr_tx_queue_len.attr, &dev_attr_gro_flush_timeout.attr, &dev_attr_napi_defer_hard_irqs.attr, - &dev_attr_phys_port_id.attr, - &dev_attr_phys_port_name.attr, - &dev_attr_phys_switch_id.attr, &dev_attr_proto_down.attr, &dev_attr_carrier_up_count.attr, &dev_attr_carrier_down_count.attr, @@ -2328,6 +2338,7 @@ int netdev_register_kobject(struct net_device *ndev) groups++; *groups++ = &netstat_group; + *groups++ = &netdev_phys_group; if (wireless_group_needed(ndev)) *groups++ = &wireless_group; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 4ddb7490df4b..07c453864a7d 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -58,13 +58,6 @@ static void zap_completion_queue(void); static unsigned int carrier_timeout = 4; module_param(carrier_timeout, uint, 0644); -#define np_info(np, fmt, ...) \ - pr_info("%s: " fmt, np->name, ##__VA_ARGS__) -#define np_err(np, fmt, ...) \ - pr_err("%s: " fmt, np->name, ##__VA_ARGS__) -#define np_notice(np, fmt, ...) \ - pr_notice("%s: " fmt, np->name, ##__VA_ARGS__) - static netdev_tx_t netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) @@ -499,43 +492,6 @@ int netpoll_send_udp(struct netpoll *np, const char *msg, int len) } EXPORT_SYMBOL(netpoll_send_udp); -void netpoll_print_options(struct netpoll *np) -{ - np_info(np, "local port %d\n", np->local_port); - if (np->ipv6) - np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6); - else - np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip); - np_info(np, "interface name '%s'\n", np->dev_name); - np_info(np, "local ethernet address '%pM'\n", np->dev_mac); - np_info(np, "remote port %d\n", np->remote_port); - if (np->ipv6) - np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6); - else - np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip); - np_info(np, "remote ethernet address %pM\n", np->remote_mac); -} -EXPORT_SYMBOL(netpoll_print_options); - -static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr) -{ - const char *end; - - if (!strchr(str, ':') && - in4_pton(str, -1, (void *)addr, -1, &end) > 0) { - if (!*end) - return 0; - } - if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) { -#if IS_ENABLED(CONFIG_IPV6) - if (!*end) - return 1; -#else - return -1; -#endif - } - return -1; -} static void skb_pool_flush(struct netpoll *np) { @@ -546,95 +502,6 @@ static void skb_pool_flush(struct netpoll *np) skb_queue_purge_reason(skb_pool, SKB_CONSUMED); } -int netpoll_parse_options(struct netpoll *np, char *opt) -{ - char *cur=opt, *delim; - int ipv6; - bool ipversion_set = false; - - if (*cur != '@') { - if ((delim = strchr(cur, '@')) == NULL) - goto parse_failed; - *delim = 0; - if (kstrtou16(cur, 10, &np->local_port)) - goto parse_failed; - cur = delim; - } - cur++; - - if (*cur != '/') { - ipversion_set = true; - if ((delim = strchr(cur, '/')) == NULL) - goto parse_failed; - *delim = 0; - ipv6 = netpoll_parse_ip_addr(cur, &np->local_ip); - if (ipv6 < 0) - goto parse_failed; - else - np->ipv6 = (bool)ipv6; - cur = delim; - } - cur++; - - if (*cur != ',') { - /* parse out dev_name or dev_mac */ - if ((delim = strchr(cur, ',')) == NULL) - goto parse_failed; - *delim = 0; - - np->dev_name[0] = '\0'; - eth_broadcast_addr(np->dev_mac); - if (!strchr(cur, ':')) - strscpy(np->dev_name, cur, sizeof(np->dev_name)); - else if (!mac_pton(cur, np->dev_mac)) - goto parse_failed; - - cur = delim; - } - cur++; - - if (*cur != '@') { - /* dst port */ - if ((delim = strchr(cur, '@')) == NULL) - goto parse_failed; - *delim = 0; - if (*cur == ' ' || *cur == '\t') - np_info(np, "warning: whitespace is not allowed\n"); - if (kstrtou16(cur, 10, &np->remote_port)) - goto parse_failed; - cur = delim; - } - cur++; - - /* dst ip */ - if ((delim = strchr(cur, '/')) == NULL) - goto parse_failed; - *delim = 0; - ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip); - if (ipv6 < 0) - goto parse_failed; - else if (ipversion_set && np->ipv6 != (bool)ipv6) - goto parse_failed; - else - np->ipv6 = (bool)ipv6; - cur = delim + 1; - - if (*cur != 0) { - /* MAC address */ - if (!mac_pton(cur, np->remote_mac)) - goto parse_failed; - } - - netpoll_print_options(np); - - return 0; - - parse_failed: - np_info(np, "couldn't parse config at '%s'!\n", cur); - return -1; -} -EXPORT_SYMBOL(netpoll_parse_options); - static void refill_skbs_work_handler(struct work_struct *work) { struct netpoll *np = @@ -863,7 +730,7 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head) kfree(npinfo); } -void __netpoll_cleanup(struct netpoll *np) +static void __netpoll_cleanup(struct netpoll *np) { struct netpoll_info *npinfo; @@ -885,7 +752,6 @@ void __netpoll_cleanup(struct netpoll *np) skb_pool_flush(np); } -EXPORT_SYMBOL_GPL(__netpoll_cleanup); void __netpoll_free(struct netpoll *np) { diff --git a/net/devlink/param.c b/net/devlink/param.c index b29abf8d3ed4..396b8a7f6013 100644 --- a/net/devlink/param.c +++ b/net/devlink/param.c @@ -92,6 +92,11 @@ static const struct devlink_param devlink_param_generic[] = { .name = DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_NAME, .type = DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_TYPE, }, + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_PHC, + .name = DEVLINK_PARAM_GENERIC_ENABLE_PHC_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_PHC_TYPE, + }, }; static int devlink_param_generic_verify(const struct devlink_param *param) diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 2dfe9063613f..869cbe57162f 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -42,12 +42,24 @@ config NET_DSA_TAG_BRCM Broadcom switches which place the tag after the MAC source address. config NET_DSA_TAG_BRCM_LEGACY - tristate "Tag driver for Broadcom legacy switches using in-frame headers" + tristate "Tag driver for BCM63xx legacy switches using in-frame headers" select NET_DSA_TAG_BRCM_COMMON help Say Y if you want to enable support for tagging frames for the - Broadcom legacy switches which place the tag after the MAC source + BCM63xx legacy switches which place the tag after the MAC source address. + This tag is used in BCM63xx legacy switches which work without the + original FCS and length before the tag insertion. + +config NET_DSA_TAG_BRCM_LEGACY_FCS + tristate "Tag driver for BCM53xx legacy switches using in-frame headers" + select NET_DSA_TAG_BRCM_COMMON + help + Say Y if you want to enable support for tagging frames for the + BCM53xx legacy switches which place the tag after the MAC source + address. + This tag is used in BCM53xx legacy switches which expect original + FCS and length before the tag insertion to be present. config NET_DSA_TAG_BRCM_PREPEND tristate "Tag driver for Broadcom switches using prepended headers" diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index fe75821623a4..26bb657ceac3 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -15,6 +15,7 @@ #define BRCM_NAME "brcm" #define BRCM_LEGACY_NAME "brcm-legacy" +#define BRCM_LEGACY_FCS_NAME "brcm-legacy-fcs" #define BRCM_PREPEND_NAME "brcm-prepend" /* Legacy Broadcom tag (6 bytes) */ @@ -32,6 +33,10 @@ #define BRCM_LEG_MULTICAST (1 << 5) #define BRCM_LEG_EGRESS (2 << 5) #define BRCM_LEG_INGRESS (3 << 5) +#define BRCM_LEG_LEN_HI(x) (((x) >> 8) & 0x7) + +/* 4th byte in the tag */ +#define BRCM_LEG_LEN_LO(x) ((x) & 0xff) /* 6th byte in the tag */ #define BRCM_LEG_PORT_ID (0xf) @@ -212,6 +217,41 @@ DSA_TAG_DRIVER(brcm_netdev_ops); MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM, BRCM_NAME); #endif +#if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_LEGACY) || \ + IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_LEGACY_FCS) +static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, + struct net_device *dev) +{ + int len = BRCM_LEG_TAG_LEN; + int source_port; + u8 *brcm_tag; + + if (unlikely(!pskb_may_pull(skb, BRCM_LEG_TAG_LEN + VLAN_HLEN))) + return NULL; + + brcm_tag = dsa_etype_header_pos_rx(skb); + + source_port = brcm_tag[5] & BRCM_LEG_PORT_ID; + + skb->dev = dsa_conduit_find_user(dev, 0, source_port); + if (!skb->dev) + return NULL; + + /* VLAN tag is added by BCM63xx internal switch */ + if (netdev_uses_dsa(skb->dev)) + len += VLAN_HLEN; + + /* Remove Broadcom tag and update checksum */ + skb_pull_rcsum(skb, len); + + dsa_default_offload_fwd_mark(skb); + + dsa_strip_etype_header(skb, len); + + return skb; +} +#endif /* CONFIG_NET_DSA_TAG_BRCM_LEGACY || CONFIG_NET_DSA_TAG_BRCM_LEGACY_FCS */ + #if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_LEGACY) static struct sk_buff *brcm_leg_tag_xmit(struct sk_buff *skb, struct net_device *dev) @@ -250,49 +290,77 @@ static struct sk_buff *brcm_leg_tag_xmit(struct sk_buff *skb, return skb; } -static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, - struct net_device *dev) +static const struct dsa_device_ops brcm_legacy_netdev_ops = { + .name = BRCM_LEGACY_NAME, + .proto = DSA_TAG_PROTO_BRCM_LEGACY, + .xmit = brcm_leg_tag_xmit, + .rcv = brcm_leg_tag_rcv, + .needed_headroom = BRCM_LEG_TAG_LEN, +}; + +DSA_TAG_DRIVER(brcm_legacy_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM_LEGACY, BRCM_LEGACY_NAME); +#endif /* CONFIG_NET_DSA_TAG_BRCM_LEGACY */ + +#if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_LEGACY_FCS) +static struct sk_buff *brcm_leg_fcs_tag_xmit(struct sk_buff *skb, + struct net_device *dev) { - int len = BRCM_LEG_TAG_LEN; - int source_port; + struct dsa_port *dp = dsa_user_to_port(dev); + unsigned int fcs_len; + __le32 fcs_val; u8 *brcm_tag; - if (unlikely(!pskb_may_pull(skb, BRCM_LEG_TAG_LEN + VLAN_HLEN))) + /* The Ethernet switch we are interfaced with needs packets to be at + * least 64 bytes (including FCS) otherwise they will be discarded when + * they enter the switch port logic. When Broadcom tags are enabled, we + * need to make sure that packets are at least 70 bytes (including FCS + * and tag) because the length verification is done after the Broadcom + * tag is stripped off the ingress packet. + * + * Let dsa_user_xmit() free the SKB. + */ + if (__skb_put_padto(skb, ETH_ZLEN + BRCM_LEG_TAG_LEN, false)) return NULL; - brcm_tag = dsa_etype_header_pos_rx(skb); + fcs_len = skb->len; + fcs_val = cpu_to_le32(crc32_le(~0, skb->data, fcs_len) ^ ~0); - source_port = brcm_tag[5] & BRCM_LEG_PORT_ID; + skb_push(skb, BRCM_LEG_TAG_LEN); - skb->dev = dsa_conduit_find_user(dev, 0, source_port); - if (!skb->dev) - return NULL; + dsa_alloc_etype_header(skb, BRCM_LEG_TAG_LEN); - /* VLAN tag is added by BCM63xx internal switch */ - if (netdev_uses_dsa(skb->dev)) - len += VLAN_HLEN; + brcm_tag = skb->data + 2 * ETH_ALEN; - /* Remove Broadcom tag and update checksum */ - skb_pull_rcsum(skb, len); + /* Broadcom tag type */ + brcm_tag[0] = BRCM_LEG_TYPE_HI; + brcm_tag[1] = BRCM_LEG_TYPE_LO; - dsa_default_offload_fwd_mark(skb); + /* Broadcom tag value */ + brcm_tag[2] = BRCM_LEG_EGRESS | BRCM_LEG_LEN_HI(fcs_len); + brcm_tag[3] = BRCM_LEG_LEN_LO(fcs_len); + brcm_tag[4] = 0; + brcm_tag[5] = dp->index & BRCM_LEG_PORT_ID; - dsa_strip_etype_header(skb, len); + /* Original FCS value */ + if (__skb_pad(skb, ETH_FCS_LEN, false)) + return NULL; + skb_put_data(skb, &fcs_val, ETH_FCS_LEN); return skb; } -static const struct dsa_device_ops brcm_legacy_netdev_ops = { - .name = BRCM_LEGACY_NAME, - .proto = DSA_TAG_PROTO_BRCM_LEGACY, - .xmit = brcm_leg_tag_xmit, +static const struct dsa_device_ops brcm_legacy_fcs_netdev_ops = { + .name = BRCM_LEGACY_FCS_NAME, + .proto = DSA_TAG_PROTO_BRCM_LEGACY_FCS, + .xmit = brcm_leg_fcs_tag_xmit, .rcv = brcm_leg_tag_rcv, .needed_headroom = BRCM_LEG_TAG_LEN, }; -DSA_TAG_DRIVER(brcm_legacy_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM_LEGACY, BRCM_LEGACY_NAME); -#endif /* CONFIG_NET_DSA_TAG_BRCM_LEGACY */ +DSA_TAG_DRIVER(brcm_legacy_fcs_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM_LEGACY_FCS, BRCM_LEGACY_FCS_NAME); +#endif /* CONFIG_NET_DSA_TAG_BRCM_LEGACY_FCS */ #if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_PREPEND) static struct sk_buff *brcm_tag_xmit_prepend(struct sk_buff *skb, @@ -328,6 +396,9 @@ static struct dsa_tag_driver *dsa_tag_driver_array[] = { #if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_LEGACY) &DSA_TAG_DRIVER_NAME(brcm_legacy_netdev_ops), #endif +#if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_LEGACY_FCS) + &DSA_TAG_DRIVER_NAME(brcm_legacy_fcs_netdev_ops), +#endif #if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_PREPEND) &DSA_TAG_DRIVER_NAME(brcm_prepend_netdev_ops), #endif diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c index 4f6b99eab2a6..6c536dfe52da 100644 --- a/net/ethtool/pse-pd.c +++ b/net/ethtool/pse-pd.c @@ -83,6 +83,8 @@ static int pse_reply_size(const struct ethnl_req_info *req_base, const struct ethtool_pse_control_status *st = &data->status; int len = 0; + if (st->pw_d_id) + len += nla_total_size(sizeof(u32)); /* _PSE_PW_D_ID */ if (st->podl_admin_state > 0) len += nla_total_size(sizeof(u32)); /* _PODL_PSE_ADMIN_STATE */ if (st->podl_pw_status > 0) @@ -109,6 +111,9 @@ static int pse_reply_size(const struct ethnl_req_info *req_base, len += st->c33_pw_limit_nb_ranges * (nla_total_size(0) + nla_total_size(sizeof(u32)) * 2); + if (st->prio_max) + /* _PSE_PRIO_MAX + _PSE_PRIO */ + len += nla_total_size(sizeof(u32)) * 2; return len; } @@ -148,6 +153,11 @@ static int pse_fill_reply(struct sk_buff *skb, const struct pse_reply_data *data = PSE_REPDATA(reply_base); const struct ethtool_pse_control_status *st = &data->status; + if (st->pw_d_id && + nla_put_u32(skb, ETHTOOL_A_PSE_PW_D_ID, + st->pw_d_id)) + return -EMSGSIZE; + if (st->podl_admin_state > 0 && nla_put_u32(skb, ETHTOOL_A_PODL_PSE_ADMIN_STATE, st->podl_admin_state)) @@ -198,6 +208,11 @@ static int pse_fill_reply(struct sk_buff *skb, pse_put_pw_limit_ranges(skb, st)) return -EMSGSIZE; + if (st->prio_max && + (nla_put_u32(skb, ETHTOOL_A_PSE_PRIO_MAX, st->prio_max) || + nla_put_u32(skb, ETHTOOL_A_PSE_PRIO, st->prio))) + return -EMSGSIZE; + return 0; } @@ -219,6 +234,7 @@ const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1] = { NLA_POLICY_RANGE(NLA_U32, ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED, ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED), [ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT] = { .type = NLA_U32 }, + [ETHTOOL_A_PSE_PRIO] = { .type = NLA_U32 }, }; static int @@ -267,6 +283,15 @@ ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info) if (ret) return ret; + if (tb[ETHTOOL_A_PSE_PRIO]) { + unsigned int prio; + + prio = nla_get_u32(tb[ETHTOOL_A_PSE_PRIO]); + ret = pse_ethtool_set_prio(phydev->psec, info->extack, prio); + if (ret) + return ret; + } + if (tb[ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT]) { unsigned int pw_limit; @@ -315,3 +340,42 @@ const struct ethnl_request_ops ethnl_pse_request_ops = { .set = ethnl_set_pse, /* PSE has no notification */ }; + +void ethnl_pse_send_ntf(struct net_device *netdev, unsigned long notifs) +{ + void *reply_payload; + struct sk_buff *skb; + int reply_len; + int ret; + + ASSERT_RTNL(); + + if (!netdev || !notifs) + return; + + reply_len = ethnl_reply_header_size() + + nla_total_size(sizeof(u32)); /* _PSE_NTF_EVENTS */ + + skb = genlmsg_new(reply_len, GFP_KERNEL); + if (!skb) + return; + + reply_payload = ethnl_bcastmsg_put(skb, ETHTOOL_MSG_PSE_NTF); + if (!reply_payload) + goto err_skb; + + ret = ethnl_fill_reply_header(skb, netdev, ETHTOOL_A_PSE_NTF_HEADER); + if (ret < 0) + goto err_skb; + + if (nla_put_uint(skb, ETHTOOL_A_PSE_NTF_EVENTS, notifs)) + goto err_skb; + + genlmsg_end(skb, reply_payload); + ethnl_multicast(skb, netdev); + return; + +err_skb: + nlmsg_free(skb); +} +EXPORT_SYMBOL_GPL(ethnl_pse_send_ntf); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index a648fff71ea7..c0440d61cf2f 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -966,6 +966,7 @@ static int arp_is_multicast(const void *pkey) static int arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { + enum skb_drop_reason drop_reason; const struct arphdr *arp; /* do not tweak dropwatch on an ARP we will ignore */ @@ -979,12 +980,15 @@ static int arp_rcv(struct sk_buff *skb, struct net_device *dev, goto out_of_mem; /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ - if (!pskb_may_pull(skb, arp_hdr_len(dev))) + drop_reason = pskb_may_pull_reason(skb, arp_hdr_len(dev)); + if (drop_reason != SKB_NOT_DROPPED_YET) goto freeskb; arp = arp_hdr(skb); - if (arp->ar_hln != dev->addr_len || arp->ar_pln != 4) + if (arp->ar_hln != dev->addr_len || arp->ar_pln != 4) { + drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; goto freeskb; + } memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); @@ -996,7 +1000,7 @@ consumeskb: consume_skb(skb); return NET_RX_SUCCESS; freeskb: - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); out_of_mem: return NET_RX_DROP; } diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 678b8f96e3e9..aaeb5d16f0c9 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -668,7 +668,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ip_tunnel_adj_headroom(dev, headroom); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl, - df, !net_eq(tunnel->net, dev_net(dev))); + df, !net_eq(tunnel->net, dev_net(dev)), 0); return; tx_error: DEV_STATS_INC(dev, tx_errors); @@ -857,7 +857,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ip_tunnel_adj_headroom(dev, max_headroom); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, - df, !net_eq(tunnel->net, dev_net(dev))); + df, !net_eq(tunnel->net, dev_net(dev)), 0); return; #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index f65d2f727381..cc9915543637 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -49,7 +49,8 @@ EXPORT_SYMBOL(ip6tun_encaps); void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, __u8 proto, - __u8 tos, __u8 ttl, __be16 df, bool xnet) + __u8 tos, __u8 ttl, __be16 df, bool xnet, + u16 ipcb_flags) { int pkt_len = skb->len - skb_inner_network_offset(skb); struct net *net = dev_net(rt->dst.dev); @@ -62,6 +63,7 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, skb_clear_hash_if_not_l4(skb); skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + IPCB(skb)->flags = ipcb_flags; /* Push down and install the IP header. */ skb_push(skb, sizeof(struct iphdr)); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a7d09ae9d761..f78c4e53dc8c 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1853,20 +1853,19 @@ static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt, /* Processing handlers for ipmr_forward, under rcu_read_lock() */ -static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, - int in_vifi, struct sk_buff *skb, int vifi) +static int ipmr_prepare_xmit(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, int vifi) { const struct iphdr *iph = ip_hdr(skb); struct vif_device *vif = &mrt->vif_table[vifi]; struct net_device *vif_dev; - struct net_device *dev; struct rtable *rt; struct flowi4 fl4; int encap = 0; vif_dev = vif_dev_read(vif); if (!vif_dev) - goto out_free; + return -1; if (vif->flags & VIFF_REGISTER) { WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); @@ -1874,12 +1873,9 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); DEV_STATS_INC(vif_dev, tx_packets); ipmr_cache_report(mrt, skb, vifi, IGMPMSG_WHOLEPKT); - goto out_free; + return -1; } - if (ipmr_forward_offloaded(skb, mrt, in_vifi, vifi)) - goto out_free; - if (vif->flags & VIFF_TUNNEL) { rt = ip_route_output_ports(net, &fl4, NULL, vif->remote, vif->local, @@ -1887,7 +1883,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, IPPROTO_IPIP, iph->tos & INET_DSCP_MASK, vif->link); if (IS_ERR(rt)) - goto out_free; + return -1; encap = sizeof(struct iphdr); } else { rt = ip_route_output_ports(net, &fl4, NULL, iph->daddr, 0, @@ -1895,11 +1891,9 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, IPPROTO_IPIP, iph->tos & INET_DSCP_MASK, vif->link); if (IS_ERR(rt)) - goto out_free; + return -1; } - dev = rt->dst.dev; - if (skb->len+encap > dst_mtu(&rt->dst) && (ntohs(iph->frag_off) & IP_DF)) { /* Do not fragment multicasts. Alas, IPv4 does not * allow to send ICMP, so that packets will disappear @@ -1907,14 +1901,14 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, */ IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); ip_rt_put(rt); - goto out_free; + return -1; } - encap += LL_RESERVED_SPACE(dev) + rt->dst.header_len; + encap += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; if (skb_cow(skb, encap)) { ip_rt_put(rt); - goto out_free; + return -1; } WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); @@ -1934,6 +1928,22 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); } + return 0; +} + +static void ipmr_queue_fwd_xmit(struct net *net, struct mr_table *mrt, + int in_vifi, struct sk_buff *skb, int vifi) +{ + struct rtable *rt; + + if (ipmr_forward_offloaded(skb, mrt, in_vifi, vifi)) + goto out_free; + + if (ipmr_prepare_xmit(net, mrt, skb, vifi)) + goto out_free; + + rt = skb_rtable(skb); + IPCB(skb)->flags |= IPSKB_FORWARDED; /* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally @@ -1947,7 +1957,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, * result in receiving multiple packets. */ NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, - net, NULL, skb, skb->dev, dev, + net, NULL, skb, skb->dev, rt->dst.dev, ipmr_forward_finish); return; @@ -1955,6 +1965,19 @@ out_free: kfree_skb(skb); } +static void ipmr_queue_output_xmit(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, int vifi) +{ + if (ipmr_prepare_xmit(net, mrt, skb, vifi)) + goto out_free; + + ip_mc_output(net, NULL, skb); + return; + +out_free: + kfree_skb(skb); +} + /* Called with mrt_lock or rcu_read_lock() */ static int ipmr_find_vif(const struct mr_table *mrt, struct net_device *dev) { @@ -2065,8 +2088,8 @@ forward: struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ipmr_queue_xmit(net, mrt, true_vifi, - skb2, psend); + ipmr_queue_fwd_xmit(net, mrt, true_vifi, + skb2, psend); } psend = ct; } @@ -2077,10 +2100,10 @@ last_forward: struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ipmr_queue_xmit(net, mrt, true_vifi, skb2, - psend); + ipmr_queue_fwd_xmit(net, mrt, true_vifi, skb2, + psend); } else { - ipmr_queue_xmit(net, mrt, true_vifi, skb, psend); + ipmr_queue_fwd_xmit(net, mrt, true_vifi, skb, psend); return; } } @@ -2214,6 +2237,110 @@ dont_forward: return 0; } +static void ip_mr_output_finish(struct net *net, struct mr_table *mrt, + struct net_device *dev, struct sk_buff *skb, + struct mfc_cache *c) +{ + int psend = -1; + int ct; + + atomic_long_inc(&c->_c.mfc_un.res.pkt); + atomic_long_add(skb->len, &c->_c.mfc_un.res.bytes); + WRITE_ONCE(c->_c.mfc_un.res.lastuse, jiffies); + + /* Forward the frame */ + if (c->mfc_origin == htonl(INADDR_ANY) && + c->mfc_mcastgrp == htonl(INADDR_ANY)) { + if (ip_hdr(skb)->ttl > + c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) { + /* It's an (*,*) entry and the packet is not coming from + * the upstream: forward the packet to the upstream + * only. + */ + psend = c->_c.mfc_parent; + goto last_xmit; + } + goto dont_xmit; + } + + for (ct = c->_c.mfc_un.res.maxvif - 1; + ct >= c->_c.mfc_un.res.minvif; ct--) { + if (ip_hdr(skb)->ttl > c->_c.mfc_un.res.ttls[ct]) { + if (psend != -1) { + struct sk_buff *skb2; + + skb2 = skb_clone(skb, GFP_ATOMIC); + if (skb2) + ipmr_queue_output_xmit(net, mrt, + skb2, psend); + } + psend = ct; + } + } + +last_xmit: + if (psend != -1) { + ipmr_queue_output_xmit(net, mrt, skb, psend); + return; + } + +dont_xmit: + kfree_skb(skb); +} + +/* Multicast packets for forwarding arrive here + * Called with rcu_read_lock(); + */ +int ip_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + struct rtable *rt = skb_rtable(skb); + struct mfc_cache *cache; + struct net_device *dev; + struct mr_table *mrt; + int vif; + + WARN_ON_ONCE(!rcu_read_lock_held()); + dev = rt->dst.dev; + + if (IPCB(skb)->flags & IPSKB_FORWARDED) + goto mc_output; + if (!(IPCB(skb)->flags & IPSKB_MCROUTE)) + goto mc_output; + + skb->dev = dev; + + mrt = ipmr_rt_fib_lookup(net, skb); + if (IS_ERR(mrt)) + goto mc_output; + + /* already under rcu_read_lock() */ + cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); + if (!cache) { + vif = ipmr_find_vif(mrt, dev); + if (vif >= 0) + cache = ipmr_cache_find_any(mrt, ip_hdr(skb)->daddr, + vif); + } + + /* No usable cache entry */ + if (!cache) { + vif = ipmr_find_vif(mrt, dev); + if (vif >= 0) + return ipmr_cache_unresolved(mrt, vif, skb, dev); + goto mc_output; + } + + vif = cache->_c.mfc_parent; + if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev) + goto mc_output; + + ip_mr_output_finish(net, mrt, dev, skb, cache); + return 0; + +mc_output: + return ip_mc_output(net, sk, skb); +} + #ifdef CONFIG_IP_PIMSM_V1 /* Handle IGMP messages of PIMv1 */ int pim_rcv_v1(struct sk_buff *skb) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index fccb05fb3a79..3ddf6bf40357 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2660,7 +2660,7 @@ add: if (IN_DEV_MFORWARD(in_dev) && !ipv4_is_local_multicast(fl4->daddr)) { rth->dst.input = ip_mr_input; - rth->dst.output = ip_mc_output; + rth->dst.output = ip_mr_output; } } #endif diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f64f8276a73c..8a3c99246d2e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -5053,9 +5053,8 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, reordering); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, notsent_lowat); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, gso_segs); - CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, lost_skb_hint); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, retransmit_skb_hint); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_tx, 40); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_tx, 32); /* TXRX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, tsoffset); @@ -5243,6 +5242,6 @@ void __init tcp_init(void) tcp_v4_init(); tcp_metrics_init(); BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0); - tcp_tasklet_init(); + tcp_tsq_work_init(); mptcp_init(); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8ec92dec321a..05b9571c9c92 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1451,11 +1451,6 @@ static u8 tcp_sacktag_one(struct sock *sk, tp->sacked_out += pcount; /* Out-of-order packets delivered */ state->sack_delivered += pcount; - - /* Lost marker hint past SACKed? Tweak RFC3517 cnt */ - if (tp->lost_skb_hint && - before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq)) - tp->lost_cnt_hint += pcount; } /* D-SACK. We can detect redundant retransmission in S|R and plain R @@ -1496,9 +1491,6 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev, tcp_skb_timestamp_us(skb)); tcp_rate_skb_delivered(sk, skb, state->rate); - if (skb == tp->lost_skb_hint) - tp->lost_cnt_hint += pcount; - TCP_SKB_CB(prev)->end_seq += shifted; TCP_SKB_CB(skb)->seq += shifted; @@ -1531,10 +1523,6 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev, if (skb == tp->retransmit_skb_hint) tp->retransmit_skb_hint = prev; - if (skb == tp->lost_skb_hint) { - tp->lost_skb_hint = prev; - tp->lost_cnt_hint -= tcp_skb_pcount(prev); - } TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; TCP_SKB_CB(prev)->eor = TCP_SKB_CB(skb)->eor; @@ -2151,12 +2139,6 @@ static inline void tcp_init_undo(struct tcp_sock *tp) tp->undo_retrans = -1; } -static bool tcp_is_rack(const struct sock *sk) -{ - return READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) & - TCP_RACK_LOSS_DETECTION; -} - /* If we detect SACK reneging, forget all SACK information * and reset tags completely, otherwise preserve SACKs. If receiver * dropped its ofo queue, we will know this due to reneging detection. @@ -2182,8 +2164,7 @@ static void tcp_timeout_mark_lost(struct sock *sk) skb_rbtree_walk_from(skb) { if (is_reneg) TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED; - else if (tcp_is_rack(sk) && skb != head && - tcp_rack_skb_timeout(tp, skb, 0) > 0) + else if (skb != head && tcp_rack_skb_timeout(tp, skb, 0) > 0) continue; /* Don't mark recently sent ones lost yet */ tcp_mark_skb_lost(sk, skb); } @@ -2264,22 +2245,6 @@ static bool tcp_check_sack_reneging(struct sock *sk, int *ack_flag) return false; } -/* Heurestics to calculate number of duplicate ACKs. There's no dupACKs - * counter when SACK is enabled (without SACK, sacked_out is used for - * that purpose). - * - * With reordering, holes may still be in flight, so RFC3517 recovery - * uses pure sacked_out (total number of SACKed segments) even though - * it violates the RFC that uses duplicate ACKs, often these are equal - * but when e.g. out-of-window ACKs or packet duplication occurs, - * they differ. Since neither occurs due to loss, TCP should really - * ignore them. - */ -static inline int tcp_dupack_heuristics(const struct tcp_sock *tp) -{ - return tp->sacked_out + 1; -} - /* Linux NewReno/SACK/ECN state machine. * -------------------------------------- * @@ -2332,13 +2297,7 @@ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp) * * If the receiver supports SACK: * - * RFC6675/3517: It is the conventional algorithm. A packet is - * considered lost if the number of higher sequence packets - * SACKed is greater than or equal the DUPACK thoreshold - * (reordering). This is implemented in tcp_mark_head_lost and - * tcp_update_scoreboard. - * - * RACK (draft-ietf-tcpm-rack-01): it is a newer algorithm + * RACK (RFC8985): RACK is a newer loss detection algorithm * (2017-) that checks timing instead of counting DUPACKs. * Essentially a packet is considered lost if it's not S/ACKed * after RTT + reordering_window, where both metrics are @@ -2353,8 +2312,8 @@ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp) * is lost (NewReno). This heuristics are the same in NewReno * and SACK. * - * Really tricky (and requiring careful tuning) part of algorithm - * is hidden in functions tcp_time_to_recover() and tcp_xmit_retransmit_queue(). + * The really tricky (and requiring careful tuning) part of the algorithm + * is hidden in the RACK code in tcp_recovery.c and tcp_xmit_retransmit_queue(). * The first determines the moment _when_ we should reduce CWND and, * hence, slow down forward transmission. In fact, it determines the moment * when we decide that hole is caused by loss, rather than by a reorder. @@ -2381,79 +2340,8 @@ static bool tcp_time_to_recover(struct sock *sk, int flag) { struct tcp_sock *tp = tcp_sk(sk); - /* Trick#1: The loss is proven. */ - if (tp->lost_out) - return true; - - /* Not-A-Trick#2 : Classic rule... */ - if (!tcp_is_rack(sk) && tcp_dupack_heuristics(tp) > tp->reordering) - return true; - - return false; -} - -/* Detect loss in event "A" above by marking head of queue up as lost. - * For RFC3517 SACK, a segment is considered lost if it - * has at least tp->reordering SACKed seqments above it; "packets" refers to - * the maximum SACKed segments to pass before reaching this limit. - */ -static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) -{ - struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - int cnt; - /* Use SACK to deduce losses of new sequences sent during recovery */ - const u32 loss_high = tp->snd_nxt; - - WARN_ON(packets > tp->packets_out); - skb = tp->lost_skb_hint; - if (skb) { - /* Head already handled? */ - if (mark_head && after(TCP_SKB_CB(skb)->seq, tp->snd_una)) - return; - cnt = tp->lost_cnt_hint; - } else { - skb = tcp_rtx_queue_head(sk); - cnt = 0; - } - - skb_rbtree_walk_from(skb) { - /* TODO: do this better */ - /* this is not the most efficient way to do this... */ - tp->lost_skb_hint = skb; - tp->lost_cnt_hint = cnt; - - if (after(TCP_SKB_CB(skb)->end_seq, loss_high)) - break; - - if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) - cnt += tcp_skb_pcount(skb); - - if (cnt > packets) - break; - - if (!(TCP_SKB_CB(skb)->sacked & TCPCB_LOST)) - tcp_mark_skb_lost(sk, skb); - - if (mark_head) - break; - } - tcp_verify_left_out(tp); -} - -/* Account newly detected lost packet(s) */ - -static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit) -{ - struct tcp_sock *tp = tcp_sk(sk); - - if (tcp_is_sack(tp)) { - int sacked_upto = tp->sacked_out - tp->reordering; - if (sacked_upto >= 0) - tcp_mark_head_lost(sk, sacked_upto, 0); - else if (fast_rexmit) - tcp_mark_head_lost(sk, 1, 1); - } + /* Has loss detection marked at least one packet lost? */ + return tp->lost_out != 0; } static bool tcp_tsopt_ecr_before(const struct tcp_sock *tp, u32 when) @@ -2881,8 +2769,6 @@ void tcp_simple_retransmit(struct sock *sk) tcp_mark_skb_lost(sk, skb); } - tcp_clear_retrans_hints_partial(tp); - if (!tp->lost_out) return; @@ -2990,17 +2876,8 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack, *rexmit = REXMIT_LOST; } -static bool tcp_force_fast_retransmit(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - return after(tcp_highest_sack_seq(tp), - tp->snd_una + tp->reordering * tp->mss_cache); -} - /* Undo during fast recovery after partial ACK. */ -static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una, - bool *do_lost) +static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una) { struct tcp_sock *tp = tcp_sk(sk); @@ -3025,9 +2902,6 @@ static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una, tcp_undo_cwnd_reduction(sk, true); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO); tcp_try_keep_open(sk); - } else { - /* Partial ACK arrived. Force fast retransmit. */ - *do_lost = tcp_force_fast_retransmit(sk); } return false; } @@ -3041,7 +2915,7 @@ static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag) if (unlikely(tcp_is_reno(tp))) { tcp_newreno_mark_lost(sk, *ack_flag & FLAG_SND_UNA_ADVANCED); - } else if (tcp_is_rack(sk)) { + } else { u32 prior_retrans = tp->retrans_out; if (tcp_rack_mark_lost(sk)) @@ -3068,10 +2942,8 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - int fast_rexmit = 0, flag = *ack_flag; + int flag = *ack_flag; bool ece_ack = flag & FLAG_ECE; - bool do_lost = num_dupack || ((flag & FLAG_DATA_SACKED) && - tcp_force_fast_retransmit(sk)); if (!tp->packets_out && tp->sacked_out) tp->sacked_out = 0; @@ -3120,7 +2992,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, if (!(flag & FLAG_SND_UNA_ADVANCED)) { if (tcp_is_reno(tp)) tcp_add_reno_sack(sk, num_dupack, ece_ack); - } else if (tcp_try_undo_partial(sk, prior_snd_una, &do_lost)) + } else if (tcp_try_undo_partial(sk, prior_snd_una)) return; if (tcp_try_undo_dsack(sk)) @@ -3175,11 +3047,8 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, /* Otherwise enter Recovery state */ tcp_enter_recovery(sk, ece_ack); - fast_rexmit = 1; } - if (!tcp_is_rack(sk) && do_lost) - tcp_update_scoreboard(sk, fast_rexmit); *rexmit = REXMIT_LOST; } @@ -3435,8 +3304,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb, next = skb_rb_next(skb); if (unlikely(skb == tp->retransmit_skb_hint)) tp->retransmit_skb_hint = NULL; - if (unlikely(skb == tp->lost_skb_hint)) - tp->lost_skb_hint = NULL; tcp_highest_sack_replace(sk, skb, next); tcp_rtx_queue_unlink_and_free(skb, sk); } @@ -3494,14 +3361,9 @@ static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb, if (flag & FLAG_RETRANS_DATA_ACKED) flag &= ~FLAG_ORIG_SACK_ACKED; } else { - int delta; - /* Non-retransmitted hole got filled? That's reordering */ if (before(reord, prior_fack)) tcp_check_sack_reordering(sk, reord, 0); - - delta = prior_sacked - tp->sacked_out; - tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta); } } else if (skb && rtt_update && sack_rtt_us >= 0 && sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 3ac8d2d17e1f..28f840724fe8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1066,15 +1066,15 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb * needs to be reallocated in a driver. * The invariant being skb->truesize subtracted from sk->sk_wmem_alloc * - * Since transmit from skb destructor is forbidden, we use a tasklet + * Since transmit from skb destructor is forbidden, we use a BH work item * to process all sockets that eventually need to send more skbs. - * We use one tasklet per cpu, with its own queue of sockets. + * We use one work item per cpu, with its own queue of sockets. */ -struct tsq_tasklet { - struct tasklet_struct tasklet; +struct tsq_work { + struct work_struct work; struct list_head head; /* queue of tcp sockets */ }; -static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet); +static DEFINE_PER_CPU(struct tsq_work, tsq_work); static void tcp_tsq_write(struct sock *sk) { @@ -1104,14 +1104,14 @@ static void tcp_tsq_handler(struct sock *sk) bh_unlock_sock(sk); } /* - * One tasklet per cpu tries to send more skbs. - * We run in tasklet context but need to disable irqs when + * One work item per cpu tries to send more skbs. + * We run in BH context but need to disable irqs when * transferring tsq->head because tcp_wfree() might * interrupt us (non NAPI drivers) */ -static void tcp_tasklet_func(struct tasklet_struct *t) +static void tcp_tsq_workfn(struct work_struct *work) { - struct tsq_tasklet *tsq = from_tasklet(tsq, t, tasklet); + struct tsq_work *tsq = container_of(work, struct tsq_work, work); LIST_HEAD(list); unsigned long flags; struct list_head *q, *n; @@ -1181,15 +1181,15 @@ void tcp_release_cb(struct sock *sk) } EXPORT_IPV6_MOD(tcp_release_cb); -void __init tcp_tasklet_init(void) +void __init tcp_tsq_work_init(void) { int i; for_each_possible_cpu(i) { - struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i); + struct tsq_work *tsq = &per_cpu(tsq_work, i); INIT_LIST_HEAD(&tsq->head); - tasklet_setup(&tsq->tasklet, tcp_tasklet_func); + INIT_WORK(&tsq->work, tcp_tsq_workfn); } } @@ -1203,11 +1203,11 @@ void tcp_wfree(struct sk_buff *skb) struct sock *sk = skb->sk; struct tcp_sock *tp = tcp_sk(sk); unsigned long flags, nval, oval; - struct tsq_tasklet *tsq; + struct tsq_work *tsq; bool empty; /* Keep one reference on sk_wmem_alloc. - * Will be released by sk_free() from here or tcp_tasklet_func() + * Will be released by sk_free() from here or tcp_tsq_workfn() */ WARN_ON(refcount_sub_and_test(skb->truesize - 1, &sk->sk_wmem_alloc)); @@ -1229,13 +1229,13 @@ void tcp_wfree(struct sk_buff *skb) nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED; } while (!try_cmpxchg(&sk->sk_tsq_flags, &oval, nval)); - /* queue this socket to tasklet queue */ + /* queue this socket to BH workqueue */ local_irq_save(flags); - tsq = this_cpu_ptr(&tsq_tasklet); + tsq = this_cpu_ptr(&tsq_work); empty = list_empty(&tsq->head); list_add(&tp->tsq_node, &tsq->head); if (empty) - tasklet_schedule(&tsq->tasklet); + queue_work(system_bh_wq, &tsq->work); local_irq_restore(flags); return; out: @@ -1554,11 +1554,6 @@ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int de if (tcp_is_reno(tp) && decr > 0) tp->sacked_out -= min_t(u32, tp->sacked_out, decr); - if (tp->lost_skb_hint && - before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) && - (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) - tp->lost_cnt_hint -= decr; - tcp_verify_left_out(tp); } @@ -2639,7 +2634,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, if (refcount_read(&sk->sk_wmem_alloc) > limit) { /* Always send skb if rtx queue is empty or has one skb. * No need to wait for TX completion to call us back, - * after softirq/tasklet schedule. + * after softirq schedule. * This helps when TX completions are delayed too much. */ if (tcp_rtx_queue_empty_or_single_skb(sk)) @@ -3252,7 +3247,6 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->eor = TCP_SKB_CB(next_skb)->eor; /* changed transmit queue under us so clear hints */ - tcp_clear_retrans_hints_partial(tp); if (next_skb == tp->retransmit_skb_hint) tp->retransmit_skb_hint = skb; diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 2326548997d3..fce945f23069 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -134,15 +134,17 @@ void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type) struct udp_tunnel_info ti; struct net_device *dev; + ASSERT_RTNL(); + ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; - rcu_read_lock(); - for_each_netdev_rcu(net, dev) { + for_each_netdev(net, dev) { + udp_tunnel_nic_lock(dev); udp_tunnel_nic_add_port(dev, &ti); + udp_tunnel_nic_unlock(dev); } - rcu_read_unlock(); } EXPORT_SYMBOL_GPL(udp_tunnel_notify_add_rx_port); @@ -154,22 +156,24 @@ void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type) struct udp_tunnel_info ti; struct net_device *dev; + ASSERT_RTNL(); + ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; - rcu_read_lock(); - for_each_netdev_rcu(net, dev) { + for_each_netdev(net, dev) { + udp_tunnel_nic_lock(dev); udp_tunnel_nic_del_port(dev, &ti); + udp_tunnel_nic_unlock(dev); } - rcu_read_unlock(); } EXPORT_SYMBOL_GPL(udp_tunnel_notify_del_rx_port); void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, - bool xnet, bool nocheck) + bool xnet, bool nocheck, u16 ipcb_flags) { struct udphdr *uh; @@ -185,7 +189,8 @@ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb udp_set_csum(nocheck, skb, src, dst, skb->len); - iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet); + iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet, + ipcb_flags); } EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb); diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c index b6d2d16189c0..ff66db48453c 100644 --- a/net/ipv4/udp_tunnel_nic.c +++ b/net/ipv4/udp_tunnel_nic.c @@ -29,6 +29,7 @@ struct udp_tunnel_nic_table_entry { * struct udp_tunnel_nic - UDP tunnel port offload state * @work: async work for talking to hardware from process context * @dev: netdev pointer + * @lock: protects all fields * @need_sync: at least one port start changed * @need_replay: space was freed, we need a replay of all ports * @work_pending: @work is currently scheduled @@ -41,6 +42,8 @@ struct udp_tunnel_nic { struct net_device *dev; + struct mutex lock; + u8 need_sync:1; u8 need_replay:1; u8 work_pending:1; @@ -298,22 +301,11 @@ __udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) static void udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) { - const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; - bool may_sleep; - if (!utn->need_sync) return; - /* Drivers which sleep in the callback need to update from - * the workqueue, if we come from the tunnel driver's notification. - */ - may_sleep = info->flags & UDP_TUNNEL_NIC_INFO_MAY_SLEEP; - if (!may_sleep) - __udp_tunnel_nic_device_sync(dev, utn); - if (may_sleep || utn->need_replay) { - queue_work(udp_tunnel_nic_workqueue, &utn->work); - utn->work_pending = 1; - } + queue_work(udp_tunnel_nic_workqueue, &utn->work); + utn->work_pending = 1; } static bool @@ -554,12 +546,12 @@ static void __udp_tunnel_nic_reset_ntf(struct net_device *dev) struct udp_tunnel_nic *utn; unsigned int i, j; - ASSERT_RTNL(); - utn = dev->udp_tunnel_nic; if (!utn) return; + mutex_lock(&utn->lock); + utn->need_sync = false; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { @@ -569,7 +561,7 @@ static void __udp_tunnel_nic_reset_ntf(struct net_device *dev) entry->flags &= ~(UDP_TUNNEL_NIC_ENTRY_DEL | UDP_TUNNEL_NIC_ENTRY_OP_FAIL); - /* We don't release rtnl across ops */ + /* We don't release utn lock across ops */ WARN_ON(entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN); if (!entry->use_cnt) continue; @@ -579,6 +571,8 @@ static void __udp_tunnel_nic_reset_ntf(struct net_device *dev) } __udp_tunnel_nic_device_sync(dev, utn); + + mutex_unlock(&utn->lock); } static size_t @@ -643,6 +637,33 @@ err_cancel: return -EMSGSIZE; } +static void __udp_tunnel_nic_assert_locked(struct net_device *dev) +{ + struct udp_tunnel_nic *utn; + + utn = dev->udp_tunnel_nic; + if (utn) + lockdep_assert_held(&utn->lock); +} + +static void __udp_tunnel_nic_lock(struct net_device *dev) +{ + struct udp_tunnel_nic *utn; + + utn = dev->udp_tunnel_nic; + if (utn) + mutex_lock(&utn->lock); +} + +static void __udp_tunnel_nic_unlock(struct net_device *dev) +{ + struct udp_tunnel_nic *utn; + + utn = dev->udp_tunnel_nic; + if (utn) + mutex_unlock(&utn->lock); +} + static const struct udp_tunnel_nic_ops __udp_tunnel_nic_ops = { .get_port = __udp_tunnel_nic_get_port, .set_port_priv = __udp_tunnel_nic_set_port_priv, @@ -651,6 +672,9 @@ static const struct udp_tunnel_nic_ops __udp_tunnel_nic_ops = { .reset_ntf = __udp_tunnel_nic_reset_ntf, .dump_size = __udp_tunnel_nic_dump_size, .dump_write = __udp_tunnel_nic_dump_write, + .assert_locked = __udp_tunnel_nic_assert_locked, + .lock = __udp_tunnel_nic_lock, + .unlock = __udp_tunnel_nic_unlock, }; static void @@ -710,11 +734,15 @@ static void udp_tunnel_nic_device_sync_work(struct work_struct *work) container_of(work, struct udp_tunnel_nic, work); rtnl_lock(); + mutex_lock(&utn->lock); + utn->work_pending = 0; __udp_tunnel_nic_device_sync(utn->dev, utn); if (utn->need_replay) udp_tunnel_nic_replay(utn->dev, utn); + + mutex_unlock(&utn->lock); rtnl_unlock(); } @@ -730,6 +758,7 @@ udp_tunnel_nic_alloc(const struct udp_tunnel_nic_info *info, return NULL; utn->n_tables = n_tables; INIT_WORK(&utn->work, udp_tunnel_nic_device_sync_work); + mutex_init(&utn->lock); for (i = 0; i < n_tables; i++) { utn->entries[i] = kcalloc(info->tables[i].n_entries, @@ -821,8 +850,11 @@ static int udp_tunnel_nic_register(struct net_device *dev) dev_hold(dev); dev->udp_tunnel_nic = utn; - if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) + if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) { + udp_tunnel_nic_lock(dev); udp_tunnel_get_rx_info(dev); + udp_tunnel_nic_unlock(dev); + } return 0; } @@ -832,6 +864,8 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + udp_tunnel_nic_lock(dev); + /* For a shared table remove this dev from the list of sharing devices * and if there are other devices just detach. */ @@ -841,8 +875,10 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) list_for_each_entry(node, &info->shared->devices, list) if (node->dev == dev) break; - if (list_entry_is_head(node, &info->shared->devices, list)) + if (list_entry_is_head(node, &info->shared->devices, list)) { + udp_tunnel_nic_unlock(dev); return; + } list_del(&node->list); kfree(node); @@ -852,6 +888,7 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) if (first) { udp_tunnel_drop_rx_info(dev); utn->dev = first->dev; + udp_tunnel_nic_unlock(dev); goto release_dev; } @@ -862,6 +899,7 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) * from the work which we will boot immediately. */ udp_tunnel_nic_flush(dev, utn); + udp_tunnel_nic_unlock(dev); /* Wait for the work to be done using the state, netdev core will * retry unregister until we give up our reference on this device. @@ -910,12 +948,16 @@ udp_tunnel_nic_netdevice_event(struct notifier_block *unused, return NOTIFY_DONE; if (event == NETDEV_UP) { + udp_tunnel_nic_lock(dev); WARN_ON(!udp_tunnel_nic_is_empty(dev, utn)); udp_tunnel_get_rx_info(dev); + udp_tunnel_nic_unlock(dev); return NOTIFY_OK; } if (event == NETDEV_GOING_DOWN) { + udp_tunnel_nic_lock(dev); udp_tunnel_nic_flush(dev, utn); + udp_tunnel_nic_unlock(dev); return NOTIFY_OK; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ba2ec7c870cc..9c297974d3a6 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3208,7 +3208,7 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, } } -#if IS_ENABLED(CONFIG_IPV6_SIT) || IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) +#if IS_ENABLED(CONFIG_IPV6_SIT) || IS_ENABLED(CONFIG_NET_IPGRE) static void add_v4_addrs(struct inet6_dev *idev) { struct in6_addr addr; @@ -3463,6 +3463,7 @@ static void addrconf_dev_config(struct net_device *dev) (dev->type != ARPHRD_IEEE1394) && (dev->type != ARPHRD_TUNNEL6) && (dev->type != ARPHRD_6LOWPAN) && + (dev->type != ARPHRD_IP6GRE) && (dev->type != ARPHRD_TUNNEL) && (dev->type != ARPHRD_NONE) && (dev->type != ARPHRD_RAWIP)) { @@ -3518,7 +3519,7 @@ static void addrconf_sit_config(struct net_device *dev) } #endif -#if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) +#if IS_ENABLED(CONFIG_NET_IPGRE) static void addrconf_gre_config(struct net_device *dev) { struct inet6_dev *idev; @@ -3536,7 +3537,7 @@ static void addrconf_gre_config(struct net_device *dev) * which is in EUI64 mode (as __ipv6_isatap_ifid() would fail in this * case). Such devices fall back to add_v4_addrs() instead. */ - if (!(dev->type == ARPHRD_IPGRE && *(__be32 *)dev->dev_addr == 0 && + if (!(*(__be32 *)dev->dev_addr == 0 && idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)) { addrconf_addr_gen(idev, true); return; @@ -3557,8 +3558,7 @@ static void addrconf_init_auto_addrs(struct net_device *dev) addrconf_sit_config(dev); break; #endif -#if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) - case ARPHRD_IP6GRE: +#if IS_ENABLED(CONFIG_NET_IPGRE) case ARPHRD_IPGRE: addrconf_gre_config(dev); break; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 894d3158a6f0..a885bb5c98ea 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1278,7 +1278,7 @@ route_lookup: ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; ipv6h->daddr = fl6->daddr; - ip6tunnel_xmit(NULL, skb, dev); + ip6tunnel_xmit(NULL, skb, dev, 0); return 0; tx_err_link_failure: DEV_STATS_INC(dev, tx_carrier_errors); diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index c99053189ea8..8ebe17a6058a 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -74,13 +74,14 @@ error: } EXPORT_SYMBOL_GPL(udp_sock_create6); -int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, - struct net_device *dev, - const struct in6_addr *saddr, - const struct in6_addr *daddr, - __u8 prio, __u8 ttl, __be32 label, - __be16 src_port, __be16 dst_port, bool nocheck) +void udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, + struct net_device *dev, + const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u8 prio, __u8 ttl, __be32 label, + __be16 src_port, __be16 dst_port, bool nocheck, + u16 ip6cb_flags) { struct udphdr *uh; struct ipv6hdr *ip6h; @@ -108,8 +109,7 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, ip6h->daddr = *daddr; ip6h->saddr = *saddr; - ip6tunnel_xmit(sk, skb, dev); - return 0; + ip6tunnel_xmit(sk, skb, dev, ip6cb_flags); } EXPORT_SYMBOL_GPL(udp_tunnel6_xmit_skb); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 9db31e5b998c..a35f4f1c6589 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2035,8 +2035,8 @@ static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct * Processing handlers for ip6mr_forward */ -static int ip6mr_forward2(struct net *net, struct mr_table *mrt, - struct sk_buff *skb, int vifi) +static int ip6mr_prepare_xmit(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, int vifi) { struct vif_device *vif = &mrt->vif_table[vifi]; struct net_device *vif_dev; @@ -2046,7 +2046,7 @@ static int ip6mr_forward2(struct net *net, struct mr_table *mrt, vif_dev = vif_dev_read(vif); if (!vif_dev) - goto out_free; + return -1; #ifdef CONFIG_IPV6_PIMSM_V2 if (vif->flags & MIFF_REGISTER) { @@ -2055,7 +2055,7 @@ static int ip6mr_forward2(struct net *net, struct mr_table *mrt, DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); DEV_STATS_INC(vif_dev, tx_packets); ip6mr_cache_report(mrt, skb, vifi, MRT6MSG_WHOLEPKT); - goto out_free; + return -1; } #endif @@ -2069,7 +2069,7 @@ static int ip6mr_forward2(struct net *net, struct mr_table *mrt, dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { dst_release(dst); - goto out_free; + return -1; } skb_dst_drop(skb); @@ -2093,20 +2093,43 @@ static int ip6mr_forward2(struct net *net, struct mr_table *mrt, /* We are about to write */ /* XXX: extension headers? */ if (skb_cow(skb, sizeof(*ipv6h) + LL_RESERVED_SPACE(vif_dev))) - goto out_free; + return -1; ipv6h = ipv6_hdr(skb); ipv6h->hop_limit--; + return 0; +} + +static void ip6mr_forward2(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, int vifi) +{ + struct net_device *indev = skb->dev; + + if (ip6mr_prepare_xmit(net, mrt, skb, vifi)) + goto out_free; IP6CB(skb)->flags |= IP6SKB_FORWARDED; - return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, - net, NULL, skb, skb->dev, vif_dev, - ip6mr_forward2_finish); + NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, + net, NULL, skb, indev, skb->dev, + ip6mr_forward2_finish); + return; + +out_free: + kfree_skb(skb); +} + +static void ip6mr_output2(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, int vifi) +{ + if (ip6mr_prepare_xmit(net, mrt, skb, vifi)) + goto out_free; + + ip6_output(net, NULL, skb); + return; out_free: kfree_skb(skb); - return 0; } /* Called with rcu_read_lock() */ @@ -2221,6 +2244,56 @@ dont_forward: kfree_skb(skb); } +/* Called under rcu_read_lock() */ +static void ip6_mr_output_finish(struct net *net, struct mr_table *mrt, + struct net_device *dev, struct sk_buff *skb, + struct mfc6_cache *c) +{ + int psend = -1; + int ct; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + atomic_long_inc(&c->_c.mfc_un.res.pkt); + atomic_long_add(skb->len, &c->_c.mfc_un.res.bytes); + WRITE_ONCE(c->_c.mfc_un.res.lastuse, jiffies); + + /* Forward the frame */ + if (ipv6_addr_any(&c->mf6c_origin) && + ipv6_addr_any(&c->mf6c_mcastgrp)) { + if (ipv6_hdr(skb)->hop_limit > + c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) { + /* It's an (*,*) entry and the packet is not coming from + * the upstream: forward the packet to the upstream + * only. + */ + psend = c->_c.mfc_parent; + goto last_forward; + } + goto dont_forward; + } + for (ct = c->_c.mfc_un.res.maxvif - 1; + ct >= c->_c.mfc_un.res.minvif; ct--) { + if (ipv6_hdr(skb)->hop_limit > c->_c.mfc_un.res.ttls[ct]) { + if (psend != -1) { + struct sk_buff *skb2; + + skb2 = skb_clone(skb, GFP_ATOMIC); + if (skb2) + ip6mr_output2(net, mrt, skb2, psend); + } + psend = ct; + } + } +last_forward: + if (psend != -1) { + ip6mr_output2(net, mrt, skb, psend); + return; + } + +dont_forward: + kfree_skb(skb); +} /* * Multicast packets for forwarding arrive here @@ -2288,6 +2361,61 @@ int ip6_mr_input(struct sk_buff *skb) return 0; } +int ip6_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + struct net_device *dev = skb_dst(skb)->dev; + struct flowi6 fl6 = (struct flowi6) { + .flowi6_iif = LOOPBACK_IFINDEX, + .flowi6_mark = skb->mark, + }; + struct mfc6_cache *cache; + struct mr_table *mrt; + int err; + int vif; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + if (IP6CB(skb)->flags & IP6SKB_FORWARDED) + goto ip6_output; + if (!(IP6CB(skb)->flags & IP6SKB_MCROUTE)) + goto ip6_output; + + err = ip6mr_fib_lookup(net, &fl6, &mrt); + if (err < 0) { + kfree_skb(skb); + return err; + } + + cache = ip6mr_cache_find(mrt, + &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); + if (!cache) { + vif = ip6mr_find_vif(mrt, dev); + if (vif >= 0) + cache = ip6mr_cache_find_any(mrt, + &ipv6_hdr(skb)->daddr, + vif); + } + + /* No usable cache entry */ + if (!cache) { + vif = ip6mr_find_vif(mrt, dev); + if (vif >= 0) + return ip6mr_cache_unresolved(mrt, vif, skb, dev); + goto ip6_output; + } + + /* Wrong interface */ + vif = cache->_c.mfc_parent; + if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev) + goto ip6_output; + + ip6_mr_output_finish(net, mrt, dev, skb, cache); + return 0; + +ip6_output: + return ip6_output(net, sk, skb); +} + int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, u32 portid) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 79c8f1acf8a3..df0caffefb38 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1145,6 +1145,7 @@ static void ip6_rt_init_dst(struct rt6_info *rt, const struct fib6_result *res) rt->dst.input = ip6_input; } else if (ipv6_addr_type(&f6i->fib6_dst.addr) & IPV6_ADDR_MULTICAST) { rt->dst.input = ip6_mc_input; + rt->dst.output = ip6_mr_output; } else { rt->dst.input = ip6_forward; } diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index a11a02b4ba95..dfa825ee870e 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -270,7 +270,7 @@ static void advance_nextseg(struct ipv6_sr_hdr *srh, struct in6_addr *daddr) static int seg6_lookup_any_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, - u32 tbl_id, bool local_delivery) + u32 tbl_id, bool local_delivery, int oif) { struct net *net = dev_net(skb->dev); struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -282,6 +282,7 @@ seg6_lookup_any_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_iif = skb->dev->ifindex; + fl6.flowi6_oif = oif; fl6.daddr = nhaddr ? *nhaddr : hdr->daddr; fl6.saddr = hdr->saddr; fl6.flowlabel = ip6_flowinfo(hdr); @@ -291,17 +292,19 @@ seg6_lookup_any_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, if (nhaddr) fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH; - if (!tbl_id) { + if (!tbl_id && !oif) { dst = ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags); - } else { + } else if (tbl_id) { struct fib6_table *table; table = fib6_get_table(net, tbl_id); if (!table) goto out; - rt = ip6_pol_route(net, table, 0, &fl6, skb, flags); + rt = ip6_pol_route(net, table, oif, &fl6, skb, flags); dst = &rt->dst; + } else { + dst = ip6_route_output(net, NULL, &fl6); } /* we want to discard traffic destined for local packet processing, @@ -330,7 +333,7 @@ out: int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, u32 tbl_id) { - return seg6_lookup_any_nexthop(skb, nhaddr, tbl_id, false); + return seg6_lookup_any_nexthop(skb, nhaddr, tbl_id, false, 0); } static __u8 seg6_flv_lcblock_octects(const struct seg6_flavors_info *finfo) @@ -418,7 +421,7 @@ static int end_next_csid_core(struct sk_buff *skb, struct seg6_local_lwt *slwt) static int input_action_end_x_finish(struct sk_buff *skb, struct seg6_local_lwt *slwt) { - seg6_lookup_nexthop(skb, &slwt->nh6, 0); + seg6_lookup_any_nexthop(skb, &slwt->nh6, 0, false, slwt->oif); return dst_input(skb); } @@ -1277,7 +1280,7 @@ static int input_action_end_dt6(struct sk_buff *skb, /* note: this time we do not need to specify the table because the VRF * takes care of selecting the correct table. */ - seg6_lookup_any_nexthop(skb, NULL, 0, true); + seg6_lookup_any_nexthop(skb, NULL, 0, true, 0); return dst_input(skb); @@ -1285,7 +1288,7 @@ legacy_mode: #endif skb_set_transport_header(skb, sizeof(struct ipv6hdr)); - seg6_lookup_any_nexthop(skb, NULL, slwt->table, true); + seg6_lookup_any_nexthop(skb, NULL, slwt->table, true, 0); return dst_input(skb); @@ -1477,7 +1480,8 @@ static struct seg6_action_desc seg6_action_table[] = { .action = SEG6_LOCAL_ACTION_END_X, .attrs = SEG6_F_ATTR(SEG6_LOCAL_NH6), .optattrs = SEG6_F_LOCAL_COUNTERS | - SEG6_F_LOCAL_FLAVORS, + SEG6_F_LOCAL_FLAVORS | + SEG6_F_ATTR(SEG6_LOCAL_OIF), .input = input_action_end_x, }, { diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index a72dbca9e8fc..12496ba1b7d4 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1035,7 +1035,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, skb_set_inner_ipproto(skb, IPPROTO_IPV6); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, - df, !net_eq(tunnel->net, dev_net(dev))); + df, !net_eq(tunnel->net, dev_net(dev)), 0); return NETDEV_TX_OK; tx_error_icmp: diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 6a40b8d0350d..a18e2c503da6 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1192,7 +1192,7 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) continue; uri = nla_data(sdp_attrs[NFC_SDP_ATTR_URI]); - if (uri == NULL || *uri == 0) + if (*uri == 0) continue; tid = local->sdreq_next_tid++; @@ -1540,10 +1540,6 @@ static int nfc_genl_se_io(struct sk_buff *skb, struct genl_info *info) } apdu = nla_data(info->attrs[NFC_ATTR_SE_APDU]); - if (!apdu) { - rc = -EINVAL; - goto put_dev; - } ctx = kzalloc(sizeof(struct se_io_ctx), GFP_KERNEL); if (!ctx) { diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index a9ed2ccab1bd..3336dcfb4515 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -261,9 +261,10 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *t) skb_set_inner_ipproto(skb, IPPROTO_SCTP); label = ip6_make_flowlabel(sock_net(sk), skb, fl6->flowlabel, true, fl6); - return udp_tunnel6_xmit_skb(dst, sk, skb, NULL, &fl6->saddr, - &fl6->daddr, tclass, ip6_dst_hoplimit(dst), - label, sctp_sk(sk)->udp_port, t->encap_port, false); + udp_tunnel6_xmit_skb(dst, sk, skb, NULL, &fl6->saddr, &fl6->daddr, + tclass, ip6_dst_hoplimit(dst), label, + sctp_sk(sk)->udp_port, t->encap_port, false, 0); + return 0; } /* Returns the dst cache entry for the given source and destination ip diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index f402f90eb6b6..a5ccada55f2b 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1103,7 +1103,8 @@ static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *t) skb_set_inner_ipproto(skb, IPPROTO_SCTP); udp_tunnel_xmit_skb(dst_rtable(dst), sk, skb, fl4->saddr, fl4->daddr, dscp, ip4_dst_hoplimit(dst), df, - sctp_sk(sk)->udp_port, t->encap_port, false, false); + sctp_sk(sk)->udp_port, t->encap_port, false, false, + 0); return 0; } diff --git a/net/socket.c b/net/socket.c index 9a0e720f0859..2cab805943c0 100644 --- a/net/socket.c +++ b/net/socket.c @@ -843,6 +843,52 @@ static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb, sizeof(ts_pktinfo), &ts_pktinfo); } +bool skb_has_tx_timestamp(struct sk_buff *skb, const struct sock *sk) +{ + const struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); + u32 tsflags = READ_ONCE(sk->sk_tsflags); + + if (serr->ee.ee_errno != ENOMSG || + serr->ee.ee_origin != SO_EE_ORIGIN_TIMESTAMPING) + return false; + + /* software time stamp available and wanted */ + if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) && skb->tstamp) + return true; + /* hardware time stamps available and wanted */ + return (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && + skb_hwtstamps(skb)->hwtstamp; +} + +int skb_get_tx_timestamp(struct sk_buff *skb, struct sock *sk, + struct timespec64 *ts) +{ + u32 tsflags = READ_ONCE(sk->sk_tsflags); + ktime_t hwtstamp; + int if_index = 0; + + if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) && + ktime_to_timespec64_cond(skb->tstamp, ts)) + return SOF_TIMESTAMPING_TX_SOFTWARE; + + if (!(tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) || + skb_is_swtx_tstamp(skb, false)) + return -ENOENT; + + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV) + hwtstamp = get_timestamp(sk, skb, &if_index); + else + hwtstamp = skb_hwtstamps(skb)->hwtstamp; + + if (tsflags & SOF_TIMESTAMPING_BIND_PHC) + hwtstamp = ptp_convert_timestamp(&hwtstamp, + READ_ONCE(sk->sk_bind_phc)); + if (!ktime_to_timespec64_cond(hwtstamp, ts)) + return -ENOENT; + + return SOF_TIMESTAMPING_TX_HARDWARE; +} + /* * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP) */ diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 108a4cc2e001..a024fcc8c0cb 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -172,7 +172,7 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb, struct udp_media_addr *dst, struct dst_cache *cache) { struct dst_entry *ndst; - int ttl, err = 0; + int ttl, err; local_bh_disable(); ndst = dst_cache_get(cache); @@ -197,7 +197,7 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb, ttl = ip4_dst_hoplimit(&rt->dst); udp_tunnel_xmit_skb(rt, ub->ubsock->sk, skb, src->ipv4.s_addr, dst->ipv4.s_addr, 0, ttl, 0, src->port, - dst->port, false, true); + dst->port, false, true, 0); #if IS_ENABLED(CONFIG_IPV6) } else { if (!ndst) { @@ -217,13 +217,13 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb, dst_cache_set_ip6(cache, ndst, &fl6.saddr); } ttl = ip6_dst_hoplimit(ndst); - err = udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, skb, NULL, - &src->ipv6, &dst->ipv6, 0, ttl, 0, - src->port, dst->port, false); + udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, skb, NULL, + &src->ipv6, &dst->ipv6, 0, ttl, 0, + src->port, dst->port, false, 0); #endif } local_bh_enable(); - return err; + return 0; tx_error: local_bh_enable(); diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index be780bcb73a3..bd309b2d3909 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -12,6 +12,7 @@ TEST_GEN_FILES := \ TEST_PROGS := \ napi_id.py \ netcons_basic.sh \ + netcons_cmdline.sh \ netcons_fragmented_msg.sh \ netcons_overflow.sh \ netcons_sysdata.sh \ diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py index 7947650210a0..baa2f24240ba 100755 --- a/tools/testing/selftests/drivers/net/hw/devmem.py +++ b/tools/testing/selftests/drivers/net/hw/devmem.py @@ -51,15 +51,14 @@ def check_tx(cfg) -> None: @ksft_disruptive def check_tx_chunks(cfg) -> None: - cfg.require_ipver("6") require_devmem(cfg) port = rand_port() - listen_cmd = f"socat -U - TCP6-LISTEN:{port}" + listen_cmd = f"socat -U - TCP{cfg.addr_ipver}-LISTEN:{port}" with bkg(listen_cmd, exit_wait=True) as socat: wait_port_listen(port) - cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_remote} -f {cfg.ifname} -s {cfg.addr_v['6']} -p {port} -z 3", host=cfg.remote, shell=True) + cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_remote} -f {cfg.ifname} -s {cfg.addr} -p {port} -z 3", host=cfg.remote, shell=True) ksft_eq(socat.stdout.strip(), "hello\nworld") diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c index 02e4d3d7ded2..cc9b40d9c5d5 100644 --- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c +++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c @@ -852,7 +852,6 @@ static int do_client(struct memory_buffer *mem) ssize_t line_size = 0; struct cmsghdr *cmsg; char *line = NULL; - unsigned long mid; size_t len = 0; int socket_fd; __u32 ddmabuf; diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh index 71a5a8b1712c..3fcf85a34596 100644 --- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh +++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh @@ -121,6 +121,17 @@ function create_dynamic_target() { echo 1 > "${NETCONS_PATH}"/enabled } +# Generate the command line argument for netconsole following: +# netconsole=[+][src-port]@[src-ip]/[<dev>],[tgt-port]@<tgt-ip>/[tgt-macaddr] +function create_cmdline_str() { + DSTMAC=$(ip netns exec "${NAMESPACE}" \ + ip link show "${DSTIF}" | awk '/ether/ {print $2}') + SRCPORT="1514" + TGTPORT="6666" + + echo "netconsole=\"+${SRCPORT}@${SRCIP}/${SRCIF},${TGTPORT}@${DSTIP}/${DSTMAC}\"" +} + # Do not append the release to the header of the message function disable_release_append() { echo 0 > "${NETCONS_PATH}"/enabled @@ -128,16 +139,9 @@ function disable_release_append() { echo 1 > "${NETCONS_PATH}"/enabled } -function cleanup() { +function do_cleanup() { local NSIM_DEV_SYS_DEL="/sys/bus/netdevsim/del_device" - # delete netconsole dynamic reconfiguration - echo 0 > "${NETCONS_PATH}"/enabled - # Remove all the keys that got created during the selftest - find "${NETCONS_PATH}/userdata/" -mindepth 1 -type d -delete - # Remove the configfs entry - rmdir "${NETCONS_PATH}" - # Delete netdevsim devices echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_DEL" echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_DEL" @@ -149,6 +153,17 @@ function cleanup() { echo "${DEFAULT_PRINTK_VALUES}" > /proc/sys/kernel/printk } +function cleanup() { + # delete netconsole dynamic reconfiguration + echo 0 > "${NETCONS_PATH}"/enabled + # Remove all the keys that got created during the selftest + find "${NETCONS_PATH}/userdata/" -mindepth 1 -type d -delete + # Remove the configfs entry + rmdir "${NETCONS_PATH}" + + do_cleanup +} + function set_user_data() { if [[ ! -d "${NETCONS_PATH}""/userdata" ]] then @@ -169,13 +184,9 @@ function listen_port_and_save_to() { socat UDP-LISTEN:"${PORT}",fork "${OUTPUT}" } -function validate_result() { +# Only validate that the message arrived properly +function validate_msg() { local TMPFILENAME="$1" - local FORMAT=${2:-"extended"} - - # TMPFILENAME will contain something like: - # 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM - # key=value # Check if the file exists if [ ! -f "$TMPFILENAME" ]; then @@ -188,6 +199,17 @@ function validate_result() { cat "${TMPFILENAME}" >&2 exit "${ksft_fail}" fi +} + +# Validate the message and userdata +function validate_result() { + local TMPFILENAME="$1" + + # TMPFILENAME will contain something like: + # 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM + # key=value + + validate_msg "${TMPFILENAME}" # userdata is not supported on basic format target, # thus, do not validate it. @@ -263,3 +285,12 @@ function pkill_socat() { pkill -f "${PROCESS_NAME}" set -e } + +# Check if netconsole was compiled as a module, otherwise exit +function check_netconsole_module() { + if modinfo netconsole | grep filename: | grep -q builtin + then + echo "SKIP: netconsole should be compiled as a module" >&2 + exit "${ksft_skip}" + fi +} diff --git a/tools/testing/selftests/drivers/net/netcons_cmdline.sh b/tools/testing/selftests/drivers/net/netcons_cmdline.sh new file mode 100755 index 000000000000..ad2fb8b1c463 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netcons_cmdline.sh @@ -0,0 +1,52 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 + +# This is a selftest to test cmdline arguments on netconsole. +# It exercises loading of netconsole from cmdline instead of the dynamic +# reconfiguration. This includes parsing the long netconsole= line and all the +# flow through init_netconsole(). +# +# Author: Breno Leitao <leitao@debian.org> + +set -euo pipefail + +SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh + +check_netconsole_module + +modprobe netdevsim 2> /dev/null || true +rmmod netconsole 2> /dev/null || true + +# The content of kmsg will be save to the following file +OUTPUT_FILE="/tmp/${TARGET}" + +# Check for basic system dependency and exit if not found +# check_for_dependencies +# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5) +echo "6 5" > /proc/sys/kernel/printk +# Remove the namespace and network interfaces +trap do_cleanup EXIT +# Create one namespace and two interfaces +set_network +# Create the command line for netconsole, with the configuration from the +# function above +CMDLINE="$(create_cmdline_str)" + +# Load the module, with the cmdline set +modprobe netconsole "${CMDLINE}" + +# Listed for netconsole port inside the namespace and destination interface +listen_port_and_save_to "${OUTPUT_FILE}" & +# Wait for socat to start and listen to the port. +wait_local_port_listen "${NAMESPACE}" "${PORT}" udp +# Send the message +echo "${MSG}: ${TARGET}" > /dev/kmsg +# Wait until socat saves the file to disk +busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" +# Make sure the message was received in the dst part +# and exit +validate_msg "${OUTPUT_FILE}" + +exit "${ksft_pass}" diff --git a/tools/testing/selftests/drivers/net/netcons_sysdata.sh b/tools/testing/selftests/drivers/net/netcons_sysdata.sh index a737e377bf08..baf69031089e 100755 --- a/tools/testing/selftests/drivers/net/netcons_sysdata.sh +++ b/tools/testing/selftests/drivers/net/netcons_sysdata.sh @@ -53,6 +53,17 @@ function set_release() { echo 1 > "${NETCONS_PATH}/userdata/release_enabled" } +# Enable the msgid to be appended to sysdata +function set_msgid() { + if [[ ! -f "${NETCONS_PATH}/userdata/msgid_enabled" ]] + then + echo "Not able to enable msgid sysdata append. Configfs not available in ${NETCONS_PATH}/userdata/msgid_enabled" >&2 + exit "${ksft_skip}" + fi + + echo 1 > "${NETCONS_PATH}/userdata/msgid_enabled" +} + # Disable the sysdata cpu_nr feature function unset_cpu_nr() { echo 0 > "${NETCONS_PATH}/userdata/cpu_nr_enabled" @@ -67,6 +78,10 @@ function unset_release() { echo 0 > "${NETCONS_PATH}/userdata/release_enabled" } +function unset_msgid() { + echo 0 > "${NETCONS_PATH}/userdata/msgid_enabled" +} + # Test if MSG contains sysdata function validate_sysdata() { # OUTPUT_FILE will contain something like: @@ -74,6 +89,7 @@ function validate_sysdata() { # userdatakey=userdatavalue # cpu=X # taskname=<taskname> + # msgid=<id> # Echo is what this test uses to create the message. See runtest() # function @@ -104,6 +120,12 @@ function validate_sysdata() { exit "${ksft_fail}" fi + if ! grep -q "msgid=[0-9]\+$" "${OUTPUT_FILE}"; then + echo "FAIL: 'msgid=<id>' not found in ${OUTPUT_FILE}" >&2 + cat "${OUTPUT_FILE}" >&2 + exit "${ksft_fail}" + fi + rm "${OUTPUT_FILE}" pkill_socat } @@ -155,6 +177,12 @@ function validate_no_sysdata() { exit "${ksft_fail}" fi + if grep -q "msgid=" "${OUTPUT_FILE}"; then + echo "FAIL: 'msgid= found in ${OUTPUT_FILE}" >&2 + cat "${OUTPUT_FILE}" >&2 + exit "${ksft_fail}" + fi + rm "${OUTPUT_FILE}" } @@ -206,6 +234,7 @@ set_cpu_nr # Enable taskname to be appended to sysdata set_taskname set_release +set_msgid runtest # Make sure the message was received in the dst part # and exit @@ -235,6 +264,7 @@ MSG="Test #3 from CPU${CPU}" unset_cpu_nr unset_taskname unset_release +unset_msgid runtest # At this time, cpu= shouldn't be present in the msg validate_no_sysdata 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 92c2f0376c08..4c859ecdad94 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh @@ -266,7 +266,6 @@ for port in 0 1; do echo $NSIM_ID > /sys/bus/netdevsim/new_device else echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep echo 1 > $NSIM_DEV_SYS/new_port fi NSIM_NETDEV=`get_netdev_name old_netdevs` @@ -350,23 +349,11 @@ old_netdevs=$(ls /sys/class/net) port=0 echo $NSIM_ID > /sys/bus/netdevsim/new_device echo 0 > $NSIM_DEV_SYS/del_port -echo 1000 > $NSIM_DEV_DFS/udp_ports_sleep echo 0 > $NSIM_DEV_SYS/new_port NSIM_NETDEV=`get_netdev_name old_netdevs` msg="create VxLANs" -exp0=( 0 0 0 0 ) # sleep is longer than out wait -new_vxlan vxlan0 10000 $NSIM_NETDEV - -modprobe -r vxlan -modprobe -r udp_tunnel - -msg="remove tunnels" -exp0=( 0 0 0 0 ) -check_tables - -msg="create VxLANs" -exp0=( 0 0 0 0 ) # sleep is longer than out wait +exp0=( `mke 10000 1` 0 0 0 ) new_vxlan vxlan0 10000 $NSIM_NETDEV exp0=( 0 0 0 0 ) @@ -428,7 +415,6 @@ echo 0 > $NSIM_DEV_SYS/del_port for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port @@ -486,7 +472,6 @@ echo 1 > $NSIM_DEV_DFS/udp_ports_sync_all for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port @@ -543,7 +528,6 @@ echo 0 > $NSIM_DEV_SYS/del_port for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port @@ -573,7 +557,6 @@ echo 1 > $NSIM_DEV_DFS/udp_ports_ipv4_only for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port @@ -634,7 +617,6 @@ echo 0 > $NSIM_DEV_SYS/del_port for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port @@ -690,7 +672,6 @@ echo 0 > $NSIM_DEV_SYS/del_port for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port @@ -750,7 +731,6 @@ echo 0 > $NSIM_DEV_SYS/del_port for port in 0 1; do if [ $port -ne 0 ]; then echo 1 > $NSIM_DEV_DFS/udp_ports_open_only - echo 1 > $NSIM_DEV_DFS/udp_ports_sleep fi echo $port > $NSIM_DEV_SYS/new_port @@ -809,7 +789,6 @@ 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) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index ab996bd22a5f..3abb74d563a7 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -41,6 +41,7 @@ TEST_PROGS += netns-name.sh TEST_PROGS += link_netns.py TEST_PROGS += nl_netdev.py TEST_PROGS += rtnetlink.py +TEST_PROGS += rtnetlink_notification.sh TEST_PROGS += srv6_end_dt46_l3vpn_test.sh TEST_PROGS += srv6_end_dt4_l3vpn_test.sh TEST_PROGS += srv6_end_dt6_l3vpn_test.sh diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 00bde7b6f39e..d7bb2e80e88c 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -102,6 +102,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \ vxlan_bridge_1d_port_8472.sh \ vxlan_bridge_1d.sh \ vxlan_bridge_1q_ipv6.sh \ + vxlan_bridge_1q_mc_ul.sh \ vxlan_bridge_1q_port_8472_ipv6.sh \ vxlan_bridge_1q_port_8472.sh \ vxlan_bridge_1q.sh \ diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 508f3c700d71..83ee6a07e072 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -37,6 +37,7 @@ declare -A NETIFS=( : "${TEAMD:=teamd}" : "${MCD:=smcrouted}" : "${MC_CLI:=smcroutectl}" +: "${MCD_TABLE_NAME:=selftests}" # Constants for netdevice bring-up: # Default time in seconds to wait for an interface to come up before giving up @@ -1757,6 +1758,51 @@ mc_send() msend -g $groups -I $if_name -c 1 > /dev/null 2>&1 } +adf_mcd_start() +{ + local ifs=("$@") + + local table_name="$MCD_TABLE_NAME" + local smcroutedir + local pid + local if + local i + + check_command "$MCD" || return 1 + check_command "$MC_CLI" || return 1 + + smcroutedir=$(mktemp -d) + defer rm -rf "$smcroutedir" + + for ((i = 1; i <= NUM_NETIFS; ++i)); do + echo "phyint ${NETIFS[p$i]} enable" >> \ + "$smcroutedir/$table_name.conf" + done + + for if in "${ifs[@]}"; do + if ! ip_link_has_flag "$if" MULTICAST; then + ip link set dev "$if" multicast on + defer ip link set dev "$if" multicast off + fi + + echo "phyint $if enable" >> \ + "$smcroutedir/$table_name.conf" + done + + "$MCD" -N -I "$table_name" -f "$smcroutedir/$table_name.conf" \ + -P "$smcroutedir/$table_name.pid" + busywait "$BUSYWAIT_TIMEOUT" test -e "$smcroutedir/$table_name.pid" + pid=$(cat "$smcroutedir/$table_name.pid") + defer kill_process "$pid" +} + +mc_cli() +{ + local table_name="$MCD_TABLE_NAME" + + "$MC_CLI" -I "$table_name" "$@" +} + start_ip_monitor() { local mtype=$1; shift diff --git a/tools/testing/selftests/net/forwarding/router_multicast.sh b/tools/testing/selftests/net/forwarding/router_multicast.sh index 5a58b1ec8aef..83e52abdbc2e 100755 --- a/tools/testing/selftests/net/forwarding/router_multicast.sh +++ b/tools/testing/selftests/net/forwarding/router_multicast.sh @@ -33,10 +33,6 @@ NUM_NETIFS=6 source lib.sh source tc_common.sh -require_command $MCD -require_command $MC_CLI -table_name=selftests - h1_create() { simple_if_init $h1 198.51.100.2/28 2001:db8:1::2/64 @@ -149,25 +145,6 @@ router_destroy() ip link set dev $rp1 down } -start_mcd() -{ - SMCROUTEDIR="$(mktemp -d)" - - for ((i = 1; i <= $NUM_NETIFS; ++i)); do - echo "phyint ${NETIFS[p$i]} enable" >> \ - $SMCROUTEDIR/$table_name.conf - done - - $MCD -N -I $table_name -f $SMCROUTEDIR/$table_name.conf \ - -P $SMCROUTEDIR/$table_name.pid -} - -kill_mcd() -{ - pkill $MCD - rm -rf $SMCROUTEDIR -} - setup_prepare() { h1=${NETIFS[p1]} @@ -179,7 +156,7 @@ setup_prepare() rp3=${NETIFS[p5]} h3=${NETIFS[p6]} - start_mcd + adf_mcd_start || exit "$EXIT_STATUS" vrf_prepare @@ -206,7 +183,7 @@ cleanup() vrf_cleanup - kill_mcd + defer_scopes_cleanup } create_mcast_sg() @@ -214,9 +191,9 @@ create_mcast_sg() local if_name=$1; shift local s_addr=$1; shift local mcast=$1; shift - local dest_ifs=${@} + local dest_ifs=("${@}") - $MC_CLI -I $table_name add $if_name $s_addr $mcast $dest_ifs + mc_cli add "$if_name" "$s_addr" "$mcast" "${dest_ifs[@]}" } delete_mcast_sg() @@ -224,9 +201,9 @@ delete_mcast_sg() local if_name=$1; shift local s_addr=$1; shift local mcast=$1; shift - local dest_ifs=${@} + local dest_ifs=("${@}") - $MC_CLI -I $table_name remove $if_name $s_addr $mcast $dest_ifs + mc_cli remove "$if_name" "$s_addr" "$mcast" "${dest_ifs[@]}" } mcast_v4() diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh new file mode 100755 index 000000000000..7ec58b6b1128 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh @@ -0,0 +1,771 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +-----------------------------------------+ +# | + $h1.10 + $h1.20 | +# | | 192.0.2.1/28 | 2001:db8:1::1/64 | +# | \________ ________/ | +# | \ / | +# | + $h1 H1 (vrf) | +# +-----------|-----------------------------+ +# | +# +-----------|----------------------------------------------------------------+ +# | +---------|--------------------------------------+ SWITCH (main vrf) | +# | | + $swp1 BR1 (802.1q) | | +# | | vid 10 20 | | +# | | | | +# | | + vx10 (vxlan) + vx20 (vxlan) | + lo10 (dummy) | +# | | local 192.0.2.100 local 2001:db8:4::1 | 192.0.2.100/28 | +# | | group 233.252.0.1 group ff0e::1:2:3 | 2001:db8:4::1/64 | +# | | id 1000 id 2000 | | +# | | vid 10 pvid untagged vid 20 pvid untagged | | +# | +------------------------------------------------+ | +# | | +# | + $swp2 $swp3 + | +# | | 192.0.2.33/28 192.0.2.65/28 | | +# | | 2001:db8:2::1/64 2001:db8:3::1/64 | | +# | | | | +# +---|--------------------------------------------------------------------|---+ +# | | +# +---|--------------------------------+ +--------------------------------|---+ +# | | H2 (vrf) | | H3 (vrf) | | +# | +-|----------------------------+ | | +-----------------------------|-+ | +# | | + $h2 BR2 (802.1d) | | | | BR3 (802.1d) $h3 + | | +# | | | | | | | | +# | | + v1$h2 (veth) | | | | v1$h3 (veth) + | | +# | +-|----------------------------+ | | +-----------------------------|-+ | +# | | | | | | +# +---|--------------------------------+ +--------------------------------|---+ +# | | +# +---|--------------------------------+ +--------------------------------|---+ +# | + v2$h2 (veth) NS2 (netns) | | NS3 (netns) v2$h3 (veth) + | +# | 192.0.2.34/28 | | 192.0.2.66/28 | +# | 2001:db8:2::2/64 | | 2001:db8:3::2/64 | +# | | | | +# | +--------------------------------+ | | +--------------------------------+ | +# | | BR1 (802.1q) | | | | BR1 (802.1q) | | +# | | + vx10 (vxlan) | | | | + vx10 (vxlan) | | +# | | local 192.0.2.34 | | | | local 192.0.2.50 | | +# | | group 233.252.0.1 dev v2$h2 | | | | group 233.252.0.1 dev v2$h3 | | +# | | id 1000 dstport $VXPORT | | | | id 1000 dstport $VXPORT | | +# | | vid 10 pvid untagged | | | | vid 10 pvid untagged | | +# | | | | | | | | +# | | + vx20 (vxlan) | | | | + vx20 (vxlan) | | +# | | local 2001:db8:2::2 | | | | local 2001:db8:3::2 | | +# | | group ff0e::1:2:3 dev v2$h2 | | | | group ff0e::1:2:3 dev v2$h3 | | +# | | id 2000 dstport $VXPORT | | | | id 2000 dstport $VXPORT | | +# | | vid 20 pvid untagged | | | | vid 20 pvid untagged | | +# | | | | | | | | +# | | + w1 (veth) | | | | + w1 (veth) | | +# | | | vid 10 20 | | | | | vid 10 20 | | +# | +--|-----------------------------+ | | +--|-----------------------------+ | +# | | | | | | +# | +--|-----------------------------+ | | +--|-----------------------------+ | +# | | + w2 (veth) VW2 (vrf) | | | | + w2 (veth) VW2 (vrf) | | +# | | |\ | | | | |\ | | +# | | | + w2.10 | | | | | + w2.10 | | +# | | | 192.0.2.3/28 | | | | | 192.0.2.4/28 | | +# | | | | | | | | | | +# | | + w2.20 | | | | + w2.20 | | +# | | 2001:db8:1::3/64 | | | | 2001:db8:1::4/64 | | +# | +--------------------------------+ | | +--------------------------------+ | +# +------------------------------------+ +------------------------------------+ +# +#shellcheck disable=SC2317 # SC doesn't see our uses of functions. + +: "${VXPORT:=4789}" +export VXPORT + +: "${GROUP4:=233.252.0.1}" +export GROUP4 + +: "${GROUP6:=ff0e::1:2:3}" +export GROUP6 + +: "${IPMR:=lo10}" + +ALL_TESTS=" + ipv4_nomcroute + ipv4_mcroute + ipv4_mcroute_changelink + ipv4_mcroute_starg + ipv4_mcroute_noroute + ipv4_mcroute_fdb + ipv4_mcroute_fdb_oif0 + ipv4_mcroute_fdb_oif0_sep + + ipv6_nomcroute + ipv6_mcroute + ipv6_mcroute_changelink + ipv6_mcroute_starg + ipv6_mcroute_noroute + ipv6_mcroute_fdb + ipv6_mcroute_fdb_oif0 + + ipv4_nomcroute_rx + ipv4_mcroute_rx + ipv4_mcroute_starg_rx + ipv4_mcroute_fdb_oif0_sep_rx + ipv4_mcroute_fdb_sep_rx + + ipv6_nomcroute_rx + ipv6_mcroute_rx + ipv6_mcroute_starg_rx + ipv6_mcroute_fdb_sep_rx +" + +NUM_NETIFS=6 +source lib.sh + +h1_create() +{ + simple_if_init "$h1" + defer simple_if_fini "$h1" + + ip_link_add "$h1.10" master "v$h1" link "$h1" type vlan id 10 + ip_link_set_up "$h1.10" + ip_addr_add "$h1.10" 192.0.2.1/28 + + ip_link_add "$h1.20" master "v$h1" link "$h1" type vlan id 20 + ip_link_set_up "$h1.20" + ip_addr_add "$h1.20" 2001:db8:1::1/64 +} + +install_capture() +{ + local dev=$1; shift + + tc qdisc add dev "$dev" clsact + defer tc qdisc del dev "$dev" clsact + + tc filter add dev "$dev" ingress proto ip pref 104 \ + flower skip_hw ip_proto udp dst_port "$VXPORT" \ + action pass + defer tc filter del dev "$dev" ingress proto ip pref 104 + + tc filter add dev "$dev" ingress proto ipv6 pref 106 \ + flower skip_hw ip_proto udp dst_port "$VXPORT" \ + action pass + defer tc filter del dev "$dev" ingress proto ipv6 pref 106 +} + +h2_create() +{ + # $h2 + ip_link_set_up "$h2" + + # H2 + vrf_create "v$h2" + defer vrf_destroy "v$h2" + + ip_link_set_up "v$h2" + + # br2 + ip_link_add br2 type bridge vlan_filtering 0 mcast_snooping 0 + ip_link_set_master br2 "v$h2" + ip_link_set_up br2 + + # $h2 + ip_link_set_master "$h2" br2 + install_capture "$h2" + + # v1$h2 + ip_link_set_up "v1$h2" + ip_link_set_master "v1$h2" br2 +} + +h3_create() +{ + # $h3 + ip_link_set_up "$h3" + + # H3 + vrf_create "v$h3" + defer vrf_destroy "v$h3" + + ip_link_set_up "v$h3" + + # br3 + ip_link_add br3 type bridge vlan_filtering 0 mcast_snooping 0 + ip_link_set_master br3 "v$h3" + ip_link_set_up br3 + + # $h3 + ip_link_set_master "$h3" br3 + install_capture "$h3" + + # v1$h3 + ip_link_set_up "v1$h3" + ip_link_set_master "v1$h3" br3 +} + +switch_create() +{ + local swp1_mac + + # br1 + swp1_mac=$(mac_get "$swp1") + ip_link_add br1 type bridge vlan_filtering 1 \ + vlan_default_pvid 0 mcast_snooping 0 + ip_link_set_addr br1 "$swp1_mac" + ip_link_set_up br1 + + # A dummy to force the IPv6 OIF=0 test to install a suitable MC route on + # $IPMR to be deterministic. Also used for the IPv6 RX!=TX ping test. + ip_link_add "X$IPMR" up type dummy + + # IPMR + ip_link_add "$IPMR" up type dummy + ip_addr_add "$IPMR" 192.0.2.100/28 + ip_addr_add "$IPMR" 2001:db8:4::1/64 + + # $swp1 + ip_link_set_up "$swp1" + ip_link_set_master "$swp1" br1 + bridge_vlan_add vid 10 dev "$swp1" + bridge_vlan_add vid 20 dev "$swp1" + + # $swp2 + ip_link_set_up "$swp2" + ip_addr_add "$swp2" 192.0.2.33/28 + ip_addr_add "$swp2" 2001:db8:2::1/64 + + # $swp3 + ip_link_set_up "$swp3" + ip_addr_add "$swp3" 192.0.2.65/28 + ip_addr_add "$swp3" 2001:db8:3::1/64 +} + +vx_create() +{ + local name=$1; shift + local vid=$1; shift + + ip_link_add "$name" up type vxlan dstport "$VXPORT" \ + nolearning noudpcsum tos inherit ttl 16 \ + "$@" + ip_link_set_master "$name" br1 + bridge_vlan_add vid "$vid" dev "$name" pvid untagged +} +export -f vx_create + +vx_wait() +{ + # Wait for all the ARP, IGMP etc. noise to settle down so that the + # tunnel is clear for measurements. + sleep 10 +} + +vx10_create() +{ + vx_create vx10 10 id 1000 "$@" +} +export -f vx10_create + +vx20_create() +{ + vx_create vx20 20 id 2000 "$@" +} +export -f vx20_create + +vx10_create_wait() +{ + vx10_create "$@" + vx_wait +} + +vx20_create_wait() +{ + vx20_create "$@" + vx_wait +} + +ns_init_common() +{ + local ns=$1; shift + local if_in=$1; shift + local ipv4_in=$1; shift + local ipv6_in=$1; shift + local ipv4_host=$1; shift + local ipv6_host=$1; shift + + # v2$h2 / v2$h3 + ip_link_set_up "$if_in" + ip_addr_add "$if_in" "$ipv4_in" + ip_addr_add "$if_in" "$ipv6_in" + + # br1 + ip_link_add br1 type bridge vlan_filtering 1 \ + vlan_default_pvid 0 mcast_snooping 0 + ip_link_set_up br1 + + # vx10, vx20 + vx10_create local "${ipv4_in%/*}" group "$GROUP4" dev "$if_in" + vx20_create local "${ipv6_in%/*}" group "$GROUP6" dev "$if_in" + + # w1 + ip_link_add w1 type veth peer name w2 + ip_link_set_master w1 br1 + ip_link_set_up w1 + bridge_vlan_add vid 10 dev w1 + bridge_vlan_add vid 20 dev w1 + + # w2 + simple_if_init w2 + defer simple_if_fini w2 + + # w2.10 + ip_link_add w2.10 master vw2 link w2 type vlan id 10 + ip_link_set_up w2.10 + ip_addr_add w2.10 "$ipv4_host" + + # w2.20 + ip_link_add w2.20 master vw2 link w2 type vlan id 20 + ip_link_set_up w2.20 + ip_addr_add w2.20 "$ipv6_host" +} +export -f ns_init_common + +ns2_create() +{ + # NS2 + ip netns add ns2 + defer ip netns del ns2 + + # v2$h2 + ip link set dev "v2$h2" netns ns2 + defer ip -n ns2 link set dev "v2$h2" netns 1 + + in_ns ns2 \ + ns_init_common ns2 "v2$h2" \ + 192.0.2.34/28 2001:db8:2::2/64 \ + 192.0.2.3/28 2001:db8:1::3/64 +} + +ns3_create() +{ + # NS3 + ip netns add ns3 + defer ip netns del ns3 + + # v2$h3 + ip link set dev "v2$h3" netns ns3 + defer ip -n ns3 link set dev "v2$h3" netns 1 + + ip -n ns3 link set dev "v2$h3" up + + in_ns ns3 \ + ns_init_common ns3 "v2$h3" \ + 192.0.2.66/28 2001:db8:3::2/64 \ + 192.0.2.4/28 2001:db8:1::4/64 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + defer vrf_cleanup + + forwarding_enable + defer forwarding_restore + + ip_link_add "v1$h2" type veth peer name "v2$h2" + ip_link_add "v1$h3" type veth peer name "v2$h3" + + h1_create + h2_create + h3_create + switch_create + ns2_create + ns3_create +} + +adf_install_broken_sg() +{ + adf_mcd_start "$IPMR" || exit "$EXIT_STATUS" + + mc_cli add "$swp2" 192.0.2.100 "$GROUP4" "$swp1" "$swp3" + defer mc_cli remove "$swp2" 192.0.2.100 "$GROUP4" "$swp1" "$swp3" + + mc_cli add "$swp2" 2001:db8:4::1 "$GROUP6" "$swp1" "$swp3" + defer mc_cli remove "$swp2" 2001:db8:4::1 "$GROUP6" "$swp1" "$swp3" +} + +adf_install_rx() +{ + mc_cli add "$swp2" 0.0.0.0 "$GROUP4" "$IPMR" + defer mc_cli remove "$swp2" 0.0.0.0 "$GROUP4" lo10 + + mc_cli add "$swp3" 0.0.0.0 "$GROUP4" "$IPMR" + defer mc_cli remove "$swp3" 0.0.0.0 "$GROUP4" lo10 + + mc_cli add "$swp2" :: "$GROUP6" "$IPMR" + defer mc_cli remove "$swp2" :: "$GROUP6" lo10 + + mc_cli add "$swp3" :: "$GROUP6" "$IPMR" + defer mc_cli remove "$swp3" :: "$GROUP6" lo10 +} + +adf_install_sg() +{ + adf_mcd_start "$IPMR" || exit "$EXIT_STATUS" + + mc_cli add "$IPMR" 192.0.2.100 "$GROUP4" "$swp2" "$swp3" + defer mc_cli remove "$IPMR" 192.0.2.33 "$GROUP4" "$swp2" "$swp3" + + mc_cli add "$IPMR" 2001:db8:4::1 "$GROUP6" "$swp2" "$swp3" + defer mc_cli remove "$IPMR" 2001:db8:4::1 "$GROUP6" "$swp2" "$swp3" + + adf_install_rx +} + +adf_install_sg_sep() +{ + adf_mcd_start lo || exit "$EXIT_STATUS" + + mc_cli add lo 192.0.2.120 "$GROUP4" "$swp2" "$swp3" + defer mc_cli remove lo 192.0.2.120 "$GROUP4" "$swp2" "$swp3" + + mc_cli add lo 2001:db8:5::1 "$GROUP6" "$swp2" "$swp3" + defer mc_cli remove lo 2001:db8:5::1 "$GROUP6" "$swp2" "$swp3" +} + +adf_install_sg_sep_rx() +{ + local lo=$1; shift + + adf_mcd_start "$IPMR" "$lo" || exit "$EXIT_STATUS" + + mc_cli add "$lo" 192.0.2.120 "$GROUP4" "$swp2" "$swp3" + defer mc_cli remove "$lo" 192.0.2.120 "$GROUP4" "$swp2" "$swp3" + + mc_cli add "$lo" 2001:db8:5::1 "$GROUP6" "$swp2" "$swp3" + defer mc_cli remove "$lo" 2001:db8:5::1 "$GROUP6" "$swp2" "$swp3" + + adf_install_rx +} + +adf_install_starg() +{ + adf_mcd_start "$IPMR" || exit "$EXIT_STATUS" + + mc_cli add "$IPMR" 0.0.0.0 "$GROUP4" "$swp2" "$swp3" + defer mc_cli remove "$IPMR" 0.0.0.0 "$GROUP4" "$swp2" "$swp3" + + mc_cli add "$IPMR" :: "$GROUP6" "$swp2" "$swp3" + defer mc_cli remove "$IPMR" :: "$GROUP6" "$swp2" "$swp3" + + adf_install_rx +} + +do_packets_v4() +{ + local mac + + mac=$(mac_get "$h2") + "$MZ" "$h1" -Q 10 -c 10 -d 100msec -p 64 -a own -b "$mac" \ + -A 192.0.2.1 -B 192.0.2.2 -t udp sp=1234,dp=2345 -q +} + +do_packets_v6() +{ + local mac + + mac=$(mac_get "$h2") + "$MZ" -6 "$h1" -Q 20 -c 10 -d 100msec -p 64 -a own -b "$mac" \ + -A 2001:db8:1::1 -B 2001:db8:1::2 -t udp sp=1234,dp=2345 -q +} + +do_test() +{ + local ipv=$1; shift + local expect_h2=$1; shift + local expect_h3=$1; shift + local what=$1; shift + + local pref=$((100 + ipv)) + local t0_h2 + local t0_h3 + local t1_h2 + local t1_h3 + local d_h2 + local d_h3 + + RET=0 + + t0_h2=$(tc_rule_stats_get "$h2" "$pref" ingress) + t0_h3=$(tc_rule_stats_get "$h3" "$pref" ingress) + + "do_packets_v$ipv" + sleep 1 + + t1_h2=$(tc_rule_stats_get "$h2" "$pref" ingress) + t1_h3=$(tc_rule_stats_get "$h3" "$pref" ingress) + + d_h2=$((t1_h2 - t0_h2)) + d_h3=$((t1_h3 - t0_h3)) + + ((d_h2 == expect_h2)) + check_err $? "Expected $expect_h2 packets on H2, got $d_h2" + + ((d_h3 == expect_h3)) + check_err $? "Expected $expect_h3 packets on H3, got $d_h3" + + log_test "VXLAN MC flood $what" +} + +ipv4_do_test_rx() +{ + local h3_should_fail=$1; shift + local what=$1; shift + + RET=0 + + ping_do "$h1.10" 192.0.2.3 + check_err $? "H2 should respond" + + ping_do "$h1.10" 192.0.2.4 + check_err_fail "$h3_should_fail" $? "H3 responds" + + log_test "VXLAN MC flood $what" +} + +ipv6_do_test_rx() +{ + local h3_should_fail=$1; shift + local what=$1; shift + + RET=0 + + ping6_do "$h1.20" 2001:db8:1::3 + check_err $? "H2 should respond" + + ping6_do "$h1.20" 2001:db8:1::4 + check_err_fail "$h3_should_fail" $? "H3 responds" + + log_test "VXLAN MC flood $what" +} + +ipv4_nomcroute() +{ + # Install a misleading (S,G) rule to attempt to trick the system into + # pushing the packets elsewhere. + adf_install_broken_sg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$swp2" + do_test 4 10 0 "IPv4 nomcroute" +} + +ipv6_nomcroute() +{ + # Like for IPv4, install a misleading (S,G). + adf_install_broken_sg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$swp2" + do_test 6 10 0 "IPv6 nomcroute" +} + +ipv4_nomcroute_rx() +{ + vx10_create local 192.0.2.100 group "$GROUP4" dev "$swp2" + ipv4_do_test_rx 1 "IPv4 nomcroute ping" +} + +ipv6_nomcroute_rx() +{ + vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$swp2" + ipv6_do_test_rx 1 "IPv6 nomcroute ping" +} + +ipv4_mcroute() +{ + adf_install_sg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + do_test 4 10 10 "IPv4 mcroute" +} + +ipv6_mcroute() +{ + adf_install_sg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + do_test 6 10 10 "IPv6 mcroute" +} + +ipv4_mcroute_rx() +{ + adf_install_sg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + ipv4_do_test_rx 0 "IPv4 mcroute ping" +} + +ipv6_mcroute_rx() +{ + adf_install_sg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + ipv6_do_test_rx 0 "IPv6 mcroute ping" +} + +ipv4_mcroute_changelink() +{ + adf_install_sg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" + ip link set dev vx10 type vxlan mcroute + sleep 1 + do_test 4 10 10 "IPv4 mcroute changelink" +} + +ipv6_mcroute_changelink() +{ + adf_install_sg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + ip link set dev vx20 type vxlan mcroute + sleep 1 + do_test 6 10 10 "IPv6 mcroute changelink" +} + +ipv4_mcroute_starg() +{ + adf_install_starg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + do_test 4 10 10 "IPv4 mcroute (*,G)" +} + +ipv6_mcroute_starg() +{ + adf_install_starg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + do_test 6 10 10 "IPv6 mcroute (*,G)" +} + +ipv4_mcroute_starg_rx() +{ + adf_install_starg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + ipv4_do_test_rx 0 "IPv4 mcroute (*,G) ping" +} + +ipv6_mcroute_starg_rx() +{ + adf_install_starg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + ipv6_do_test_rx 0 "IPv6 mcroute (*,G) ping" +} + +ipv4_mcroute_noroute() +{ + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + do_test 4 0 0 "IPv4 mcroute, no route" +} + +ipv6_mcroute_noroute() +{ + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + do_test 6 0 0 "IPv6 mcroute, no route" +} + +ipv4_mcroute_fdb() +{ + adf_install_sg + vx10_create_wait local 192.0.2.100 dev "$IPMR" mcroute + bridge fdb add dev vx10 \ + 00:00:00:00:00:00 self static dst "$GROUP4" via "$IPMR" + do_test 4 10 10 "IPv4 mcroute FDB" +} + +ipv6_mcroute_fdb() +{ + adf_install_sg + vx20_create_wait local 2001:db8:4::1 dev "$IPMR" mcroute + bridge -6 fdb add dev vx20 \ + 00:00:00:00:00:00 self static dst "$GROUP6" via "$IPMR" + do_test 6 10 10 "IPv6 mcroute FDB" +} + +# Use FDB to configure VXLAN in a way where oif=0 for purposes of FIB lookup. +ipv4_mcroute_fdb_oif0() +{ + adf_install_sg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + bridge fdb del dev vx10 00:00:00:00:00:00 + bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" + do_test 4 10 10 "IPv4 mcroute oif=0" +} + +ipv6_mcroute_fdb_oif0() +{ + # The IPv6 tunnel lookup does not fall back to selection by source + # address. Instead it just does a FIB match, and that would find one of + # the several ff00::/8 multicast routes -- each device has one. In order + # to reliably force the $IPMR device, add a /128 route for the + # destination group address. + ip -6 route add table local multicast "$GROUP6/128" dev "$IPMR" + defer ip -6 route del table local multicast "$GROUP6/128" dev "$IPMR" + + adf_install_sg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + bridge -6 fdb del dev vx20 00:00:00:00:00:00 + bridge -6 fdb add dev vx20 00:00:00:00:00:00 self static dst "$GROUP6" + do_test 6 10 10 "IPv6 mcroute oif=0" +} + +# In oif=0 test as above, have FIB lookup resolve to loopback instead of IPMR. +# This doesn't work with IPv6 -- a MC route on lo would be marked as RTF_REJECT. +ipv4_mcroute_fdb_oif0_sep() +{ + adf_install_sg_sep + + ip_addr_add lo 192.0.2.120/28 + vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute + bridge fdb del dev vx10 00:00:00:00:00:00 + bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" + do_test 4 10 10 "IPv4 mcroute TX!=RX oif=0" +} + +ipv4_mcroute_fdb_oif0_sep_rx() +{ + adf_install_sg_sep_rx lo + + ip_addr_add lo 192.0.2.120/28 + vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute + bridge fdb del dev vx10 00:00:00:00:00:00 + bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" + ipv4_do_test_rx 0 "IPv4 mcroute TX!=RX oif=0 ping" +} + +ipv4_mcroute_fdb_sep_rx() +{ + adf_install_sg_sep_rx lo + + ip_addr_add lo 192.0.2.120/28 + vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute + bridge fdb del dev vx10 00:00:00:00:00:00 + bridge fdb add \ + dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" via lo + ipv4_do_test_rx 0 "IPv4 mcroute TX!=RX ping" +} + +ipv6_mcroute_fdb_sep_rx() +{ + adf_install_sg_sep_rx "X$IPMR" + + ip_addr_add "X$IPMR" 2001:db8:5::1/64 + vx20_create_wait local 2001:db8:5::1 group "$GROUP6" dev "$IPMR" mcroute + bridge -6 fdb del dev vx20 00:00:00:00:00:00 + bridge -6 fdb add dev vx20 00:00:00:00:00:00 \ + self static dst "$GROUP6" via "X$IPMR" + ipv6_do_test_rx 0 "IPv6 mcroute TX!=RX ping" +} + +trap cleanup EXIT + +setup_prepare +setup_wait "$NUM_NETIFS" +tests_run + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 006fdadcc4b9..ff0dbe23e8e0 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -547,13 +547,19 @@ ip_link_set_addr() defer ip link set dev "$name" address "$old_addr" } -ip_link_is_up() +ip_link_has_flag() { local name=$1; shift + local flag=$1; shift local state=$(ip -j link show "$name" | - jq -r '(.[].flags[] | select(. == "UP")) // "DOWN"') - [[ $state == "UP" ]] + jq --arg flag "$flag" 'any(.[].flags.[]; . == $flag)') + [[ $state == true ]] +} + +ip_link_is_up() +{ + ip_link_has_flag "$1" UP } ip_link_set_up() diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index cd8a58097448..1f5227f3d64d 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -385,7 +385,7 @@ static int get_bind_to_device(int sd, char *name, size_t len) name[0] = '\0'; rc = getsockopt(sd, SOL_SOCKET, SO_BINDTODEVICE, name, &optlen); if (rc < 0) - log_err_errno("setsockopt(SO_BINDTODEVICE)"); + log_err_errno("getsockopt(SO_BINDTODEVICE)"); return rc; } @@ -535,7 +535,7 @@ static int set_freebind(int sd, int version) break; case AF_INET6: if (setsockopt(sd, SOL_IPV6, IPV6_FREEBIND, &one, sizeof(one))) { - log_err_errno("setsockopt(IPV6_FREEBIND"); + log_err_errno("setsockopt(IPV6_FREEBIND)"); rc = -1; } break; @@ -812,7 +812,7 @@ static int convert_addr(struct sock_args *args, const char *_str, sep++; if (str_to_uint(sep, 1, pfx_len_max, &args->prefix_len) != 0) { - fprintf(stderr, "Invalid port\n"); + fprintf(stderr, "Invalid prefix length\n"); return 1; } } else { @@ -1272,7 +1272,7 @@ static int msg_loop(int client, int sd, void *addr, socklen_t alen, } } - nfds = interactive ? MAX(fileno(stdin), sd) + 1 : sd + 1; + nfds = interactive ? MAX(fileno(stdin), sd) + 1 : sd + 1; while (1) { FD_ZERO(&rfds); FD_SET(sd, &rfds); @@ -1492,7 +1492,7 @@ static int lsock_init(struct sock_args *args) sd = socket(args->version, args->type, args->protocol); if (sd < 0) { log_err_errno("Error opening socket"); - return -1; + return -1; } if (set_reuseaddr(sd) != 0) @@ -1912,7 +1912,7 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args) * waiting to be told when to continue */ if (read(fd, &buf, sizeof(buf)) <= 0) { - log_err_errno("Failed to read IPC status from status"); + log_err_errno("Failed to read IPC status from pipe"); return 1; } if (!buf) { diff --git a/tools/testing/selftests/net/rtnetlink_notification.sh b/tools/testing/selftests/net/rtnetlink_notification.sh new file mode 100755 index 000000000000..39c1b815bbe4 --- /dev/null +++ b/tools/testing/selftests/net/rtnetlink_notification.sh @@ -0,0 +1,70 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# This test is for checking rtnetlink notification callpaths, and get as much +# coverage as possible. +# +# set -e + +ALL_TESTS=" + kci_test_mcast_addr_notification +" + +source lib.sh + +kci_test_mcast_addr_notification() +{ + RET=0 + local tmpfile + local monitor_pid + local match_result + local test_dev="test-dummy1" + + tmpfile=$(mktemp) + defer rm "$tmpfile" + + ip monitor maddr > $tmpfile & + monitor_pid=$! + defer kill_process "$monitor_pid" + + sleep 1 + + if [ ! -e "/proc/$monitor_pid" ]; then + RET=$ksft_skip + log_test "mcast addr notification: iproute2 too old" + return $RET + fi + + ip link add name "$test_dev" type dummy + check_err $? "failed to add dummy interface" + ip link set "$test_dev" up + check_err $? "failed to set dummy interface up" + ip link del dev "$test_dev" + check_err $? "Failed to delete dummy interface" + sleep 1 + + # There should be 4 line matches as follows. + # 13: test-dummy1 inet6 mcast ff02::1 scope global + # 13: test-dummy1 inet mcast 224.0.0.1 scope global + # Deleted 13: test-dummy1 inet mcast 224.0.0.1 scope global + # Deleted 13: test-dummy1 inet6 mcast ff02::1 scope global + match_result=$(grep -cE "$test_dev.*(224.0.0.1|ff02::1)" "$tmpfile") + if [ "$match_result" -ne 4 ]; then + RET=$ksft_fail + fi + log_test "mcast addr notification: Expected 4 matches, got $match_result" + return $RET +} + +#check for needed privileges +if [ "$(id -u)" -ne 0 ];then + RET=$ksft_skip + log_test "need root privileges" + exit $RET +fi + +require_command ip + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh index 4b86040c58c6..bedf0ce885c2 100755 --- a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh @@ -72,6 +72,9 @@ # Every fcf0:0:x:y::/64 network interconnects the SRv6 routers rt-x with rt-y in # the selftest network. # +# In addition, every router interface connecting rt-x to rt-y is assigned an +# IPv6 link-local address fe80::x:y/64. +# # Local SID/C-SID table # ===================== # @@ -521,6 +524,9 @@ setup_rt_networking() ip -netns "${nsname}" addr \ add "${net_prefix}::${rt}/64" dev "${devname}" nodad + ip -netns "${nsname}" addr \ + add "fe80::${rt}:${neigh}/64" dev "${devname}" nodad + ip -netns "${nsname}" link set "${devname}" up done @@ -609,6 +615,27 @@ set_end_x_nextcsid() nflen "${LCNODEFUNC_BLEN}" dev "${DUMMY_DEVNAME}" } +set_end_x_ll_nextcsid() +{ + local rt="$1" + local adj="$2" + + eval nsname=\${$(get_rtname "${rt}")} + lcnode_func_prefix="$(build_lcnode_func_prefix "${rt}")" + nh6_ll_addr="fe80::${adj}:${rt}" + oifname="veth-rt-${rt}-${adj}" + + # enabled NEXT-C-SID SRv6 End.X behavior via an IPv6 link-local nexthop + # address (note that "dev" is the dummy dum0 device chosen for the sake + # of simplicity). + ip -netns "${nsname}" -6 route \ + replace "${lcnode_func_prefix}" \ + table "${LOCALSID_TABLE_ID}" \ + encap seg6local action End.X nh6 "${nh6_ll_addr}" \ + oif "${oifname}" flavors next-csid lblen "${LCBLOCK_BLEN}" \ + nflen "${LCNODEFUNC_BLEN}" dev "${DUMMY_DEVNAME}" +} + set_underlay_sids_reachability() { local rt="$1" @@ -1016,6 +1043,27 @@ host_vpn_tests() check_and_log_hs_ipv4_connectivity 1 2 check_and_log_hs_ipv4_connectivity 2 1 + + # Setup the adjacencies in the SRv6 aware routers using IPv6 link-local + # addresses. + # - rt-3 SRv6 End.X adjacency with rt-4 + # - rt-4 SRv6 End.X adjacency with rt-1 + set_end_x_ll_nextcsid 3 4 + set_end_x_ll_nextcsid 4 1 + + log_section "SRv6 VPN connectivity test hosts (h1 <-> h2, IPv6), link-local" + + check_and_log_hs_ipv6_connectivity 1 2 + check_and_log_hs_ipv6_connectivity 2 1 + + log_section "SRv6 VPN connectivity test hosts (h1 <-> h2, IPv4), link-local" + + check_and_log_hs_ipv4_connectivity 1 2 + check_and_log_hs_ipv4_connectivity 2 1 + + # Restore the previous adjacencies. + set_end_x_nextcsid 3 4 + set_end_x_nextcsid 4 1 } __nextcsid_end_x_behavior_test() diff --git a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh index 6127a78ee988..8deacc565afa 100755 --- a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh +++ b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh @@ -146,18 +146,17 @@ run_cmd() } check_hv_connectivity() { - ip netns exec $hv_1 ping -c 1 -W 1 $1 &>/dev/null - sleep 1 - ip netns exec $hv_1 ping -c 1 -W 1 $2 &>/dev/null + slowwait 5 ip netns exec $hv_1 ping -c 1 -W 1 $1 &>/dev/null + slowwait 5 ip netns exec $hv_1 ping -c 1 -W 1 $2 &>/dev/null return $? } check_vm_connectivity() { - run_cmd "ip netns exec $vm_11 ping -c 1 -W 1 10.0.10.12" + slowwait 5 run_cmd "ip netns exec $vm_11 ping -c 1 -W 1 10.0.10.12" log_test $? 0 "VM connectivity over $1 (ipv4 default rdst)" - run_cmd "ip netns exec $vm_21 ping -c 1 -W 1 10.0.10.22" + slowwait 5 run_cmd "ip netns exec $vm_21 ping -c 1 -W 1 10.0.10.22" log_test $? 0 "VM connectivity over $1 (ipv6 default rdst)" } diff --git a/tools/testing/selftests/net/vrf_route_leaking.sh b/tools/testing/selftests/net/vrf_route_leaking.sh index e9c2f71da207..ce34cb2e6e0b 100755 --- a/tools/testing/selftests/net/vrf_route_leaking.sh +++ b/tools/testing/selftests/net/vrf_route_leaking.sh @@ -275,7 +275,7 @@ setup_sym() # Wait for ip config to settle - sleep 2 + slowwait 5 ip netns exec $h1 "${ping6}" -c1 -w1 ${H2_N2_IP6} >/dev/null 2>&1 } setup_asym() @@ -370,7 +370,7 @@ setup_asym() ip -netns $r2 -6 addr add dev eth1 ${R2_N2_IP6}/64 nodad # Wait for ip config to settle - sleep 2 + slowwait 5 ip netns exec $h1 "${ping6}" -c1 -w1 ${H2_N2_IP6} >/dev/null 2>&1 } check_connectivity() diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json index 28c6ce6da7db..531a2f6e4900 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json @@ -264,5 +264,41 @@ "matchPattern": "sfq", "matchCount": "0", "teardown": [] + }, + { + "id": "cdc1", + "name": "Check that a negative perturb timer is rejected", + "category": [ + "qdisc", + "sfq" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq perturb -10", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "sfq", + "matchCount": "0", + "teardown": [] + }, + { + "id": "a9f0", + "name": "Check that a too big perturb timer is rejected", + "category": [ + "qdisc", + "sfq" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq perturb 1000000000", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "sfq", + "matchCount": "0", + "teardown": [] } ] diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index 0c7e9cbcbc85..803f1e075b62 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -7,6 +7,7 @@ * Author: Stefan Hajnoczi <stefanha@redhat.com> */ +#include <ctype.h> #include <errno.h> #include <stdio.h> #include <stdint.h> @@ -23,6 +24,9 @@ #include "control.h" #include "util.h" +#define KALLSYMS_PATH "/proc/kallsyms" +#define KALLSYMS_LINE_LEN 512 + /* Install signal handlers */ void init_signals(void) { @@ -121,15 +125,17 @@ bool vsock_wait_sent(int fd) return !ret; } -/* Create socket <type>, bind to <cid, port> and return the file descriptor. */ -int vsock_bind(unsigned int cid, unsigned int port, int type) +/* Create socket <type>, bind to <cid, port>. + * Return the file descriptor, or -1 on error. + */ +int vsock_bind_try(unsigned int cid, unsigned int port, int type) { struct sockaddr_vm sa = { .svm_family = AF_VSOCK, .svm_cid = cid, .svm_port = port, }; - int fd; + int fd, saved_errno; fd = socket(AF_VSOCK, type, 0); if (fd < 0) { @@ -138,6 +144,22 @@ int vsock_bind(unsigned int cid, unsigned int port, int type) } if (bind(fd, (struct sockaddr *)&sa, sizeof(sa))) { + saved_errno = errno; + close(fd); + errno = saved_errno; + fd = -1; + } + + return fd; +} + +/* Create socket <type>, bind to <cid, port> and return the file descriptor. */ +int vsock_bind(unsigned int cid, unsigned int port, int type) +{ + int fd; + + fd = vsock_bind_try(cid, port, type); + if (fd < 0) { perror("bind"); exit(EXIT_FAILURE); } @@ -836,3 +858,55 @@ void enable_so_linger(int fd, int timeout) exit(EXIT_FAILURE); } } + +static int __get_transports(void) +{ + char buf[KALLSYMS_LINE_LEN]; + const char *ksym; + int ret = 0; + FILE *f; + + f = fopen(KALLSYMS_PATH, "r"); + if (!f) { + perror("Can't open " KALLSYMS_PATH); + exit(EXIT_FAILURE); + } + + while (fgets(buf, sizeof(buf), f)) { + char *match; + int i; + + assert(buf[strlen(buf) - 1] == '\n'); + + for (i = 0; i < TRANSPORT_NUM; ++i) { + if (ret & BIT(i)) + continue; + + /* Match should be followed by '\t' or '\n'. + * See kallsyms.c:s_show(). + */ + ksym = transport_ksyms[i]; + match = strstr(buf, ksym); + if (match && isspace(match[strlen(ksym)])) { + ret |= BIT(i); + break; + } + } + } + + fclose(f); + return ret; +} + +/* Return integer with TRANSPORT_* bit set for every (known) registered vsock + * transport. + */ +int get_transports(void) +{ + static int tr = -1; + + if (tr == -1) + tr = __get_transports(); + + return tr; +} diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index 5e2db67072d5..71895192cc02 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -3,8 +3,36 @@ #define UTIL_H #include <sys/socket.h> +#include <linux/bitops.h> +#include <linux/kernel.h> #include <linux/vm_sockets.h> +/* All known vsock transports, see callers of vsock_core_register() */ +#define KNOWN_TRANSPORTS(x) \ + x(LOOPBACK, "loopback") \ + x(VIRTIO, "virtio") \ + x(VHOST, "vhost") \ + x(VMCI, "vmci") \ + x(HYPERV, "hvs") + +enum transport { + TRANSPORT_COUNTER_BASE = __COUNTER__ + 1, + #define x(name, symbol) \ + TRANSPORT_##name = BIT(__COUNTER__ - TRANSPORT_COUNTER_BASE), + KNOWN_TRANSPORTS(x) + TRANSPORT_NUM = __COUNTER__ - TRANSPORT_COUNTER_BASE, + #undef x +}; + +static const char * const transport_ksyms[] = { + #define x(name, symbol) "d " symbol "_transport", + KNOWN_TRANSPORTS(x) + #undef x +}; + +static_assert(ARRAY_SIZE(transport_ksyms) == TRANSPORT_NUM); +static_assert(BITS_PER_TYPE(int) >= TRANSPORT_NUM); + /* Tests can either run as the client or the server */ enum test_mode { TEST_MODE_UNSET, @@ -44,6 +72,7 @@ int vsock_connect(unsigned int cid, unsigned int port, int type); int vsock_accept(unsigned int cid, unsigned int port, struct sockaddr_vm *clientaddrp, int type); int vsock_stream_connect(unsigned int cid, unsigned int port); +int vsock_bind_try(unsigned int cid, unsigned int port, int type); int vsock_bind(unsigned int cid, unsigned int port, int type); int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type); @@ -81,4 +110,5 @@ void setsockopt_timeval_check(int fd, int level, int optname, struct timeval val, char const *errmsg); void enable_so_zerocopy_check(int fd); void enable_so_linger(int fd, int timeout); +int get_transports(void); #endif /* UTIL_H */ diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index f669baaa0dca..eb6f54378667 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -1718,16 +1718,27 @@ static void test_stream_msgzcopy_leak_zcskb_server(const struct test_opts *opts) #define MAX_PORT_RETRIES 24 /* net/vmw_vsock/af_vsock.c */ -/* Test attempts to trigger a transport release for an unbound socket. This can - * lead to a reference count mishandling. - */ -static void test_stream_transport_uaf_client(const struct test_opts *opts) +static bool test_stream_transport_uaf(int cid) { int sockets[MAX_PORT_RETRIES]; struct sockaddr_vm addr; - int fd, i, alen; + socklen_t alen; + int fd, i, c; + bool ret; + + /* Probe for a transport by attempting a local CID bind. Unavailable + * transport (or more specifically: an unsupported transport/CID + * combination) results in EADDRNOTAVAIL, other errnos are fatal. + */ + fd = vsock_bind_try(cid, VMADDR_PORT_ANY, SOCK_STREAM); + if (fd < 0) { + if (errno != EADDRNOTAVAIL) { + perror("Unexpected bind() errno"); + exit(EXIT_FAILURE); + } - fd = vsock_bind(VMADDR_CID_ANY, VMADDR_PORT_ANY, SOCK_STREAM); + return false; + } alen = sizeof(addr); if (getsockname(fd, (struct sockaddr *)&addr, &alen)) { @@ -1735,38 +1746,83 @@ static void test_stream_transport_uaf_client(const struct test_opts *opts) exit(EXIT_FAILURE); } + /* Drain the autobind pool; see __vsock_bind_connectible(). */ for (i = 0; i < MAX_PORT_RETRIES; ++i) - sockets[i] = vsock_bind(VMADDR_CID_ANY, ++addr.svm_port, - SOCK_STREAM); + sockets[i] = vsock_bind(cid, ++addr.svm_port, SOCK_STREAM); close(fd); - fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + /* Setting SOCK_NONBLOCK makes connect() return soon after + * (re-)assigning the transport. We are not connecting to anything + * anyway, so there is no point entering the main loop in + * vsock_connect(); waiting for timeout, checking for signals, etc. + */ + fd = socket(AF_VSOCK, SOCK_STREAM | SOCK_NONBLOCK, 0); if (fd < 0) { perror("socket"); exit(EXIT_FAILURE); } - if (!vsock_connect_fd(fd, addr.svm_cid, addr.svm_port)) { - perror("Unexpected connect() #1 success"); + /* Assign transport, while failing to autobind. Autobind pool was + * drained, so EADDRNOTAVAIL coming from __vsock_bind_connectible() is + * expected. + * + * One exception is ENODEV which is thrown by vsock_assign_transport(), + * i.e. before vsock_auto_bind(), when the only transport loaded is + * vhost. + */ + if (!connect(fd, (struct sockaddr *)&addr, alen)) { + fprintf(stderr, "Unexpected connect() success\n"); exit(EXIT_FAILURE); } - - /* Vulnerable system may crash now. */ - if (!vsock_connect_fd(fd, VMADDR_CID_HOST, VMADDR_PORT_ANY)) { - perror("Unexpected connect() #2 success"); + if (errno == ENODEV && cid == VMADDR_CID_HOST) { + ret = false; + goto cleanup; + } + if (errno != EADDRNOTAVAIL) { + perror("Unexpected connect() errno"); exit(EXIT_FAILURE); } + /* Reassign transport, triggering old transport release and + * (potentially) unbinding of an unbound socket. + * + * Vulnerable system may crash now. + */ + for (c = VMADDR_CID_HYPERVISOR; c <= VMADDR_CID_HOST + 1; ++c) { + if (c != cid) { + addr.svm_cid = c; + (void)connect(fd, (struct sockaddr *)&addr, alen); + } + } + + ret = true; +cleanup: close(fd); while (i--) close(sockets[i]); - control_writeln("DONE"); + return ret; } -static void test_stream_transport_uaf_server(const struct test_opts *opts) +/* Test attempts to trigger a transport release for an unbound socket. This can + * lead to a reference count mishandling. + */ +static void test_stream_transport_uaf_client(const struct test_opts *opts) { - control_expectln("DONE"); + bool tested = false; + int cid, tr; + + for (cid = VMADDR_CID_HYPERVISOR; cid <= VMADDR_CID_HOST + 1; ++cid) + tested |= test_stream_transport_uaf(cid); + + tr = get_transports(); + if (!tr) + fprintf(stderr, "No transports detected\n"); + else if (tr == TRANSPORT_VIRTIO) + fprintf(stderr, "Setup unsupported: sole virtio transport\n"); + else if (!tested) + fprintf(stderr, "No transports tested\n"); } static void test_stream_connect_retry_client(const struct test_opts *opts) @@ -2034,7 +2090,6 @@ static struct test_case test_cases[] = { { .name = "SOCK_STREAM transport release use-after-free", .run_client = test_stream_transport_uaf_client, - .run_server = test_stream_transport_uaf_server, }, { .name = "SOCK_STREAM retry failed connect()", |