diff options
502 files changed, 5400 insertions, 2439 deletions
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index ab8cd337f43a..8aed6d94c4cd 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -586,6 +586,7 @@ What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/srbds /sys/devices/system/cpu/vulnerabilities/tsa /sys/devices/system/cpu/vulnerabilities/tsx_async_abort + /sys/devices/system/cpu/vulnerabilities/vmscape Date: January 2018 Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> Description: Information about CPU vulnerabilities diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index 89ca636081b7..55d747511f83 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -26,3 +26,4 @@ are configurable at compile, boot or run time. rsb old_microcode indirect-target-selection + vmscape diff --git a/Documentation/admin-guide/hw-vuln/vmscape.rst b/Documentation/admin-guide/hw-vuln/vmscape.rst new file mode 100644 index 000000000000..d9b9a2b6c114 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/vmscape.rst @@ -0,0 +1,110 @@ +.. SPDX-License-Identifier: GPL-2.0 + +VMSCAPE +======= + +VMSCAPE is a vulnerability that may allow a guest to influence the branch +prediction in host userspace. It particularly affects hypervisors like QEMU. + +Even if a hypervisor may not have any sensitive data like disk encryption keys, +guest-userspace may be able to attack the guest-kernel using the hypervisor as +a confused deputy. + +Affected processors +------------------- + +The following CPU families are affected by VMSCAPE: + +**Intel processors:** + - Skylake generation (Parts without Enhanced-IBRS) + - Cascade Lake generation - (Parts affected by ITS guest/host separation) + - Alder Lake and newer (Parts affected by BHI) + +Note that, BHI affected parts that use BHB clearing software mitigation e.g. +Icelake are not vulnerable to VMSCAPE. + +**AMD processors:** + - Zen series (families 0x17, 0x19, 0x1a) + +** Hygon processors:** + - Family 0x18 + +Mitigation +---------- + +Conditional IBPB +---------------- + +Kernel tracks when a CPU has run a potentially malicious guest and issues an +IBPB before the first exit to userspace after VM-exit. If userspace did not run +between VM-exit and the next VM-entry, no IBPB is issued. + +Note that the existing userspace mitigation against Spectre-v2 is effective in +protecting the userspace. They are insufficient to protect the userspace VMMs +from a malicious guest. This is because Spectre-v2 mitigations are applied at +context switch time, while the userspace VMM can run after a VM-exit without a +context switch. + +Vulnerability enumeration and mitigation is not applied inside a guest. This is +because nested hypervisors should already be deploying IBPB to isolate +themselves from nested guests. + +SMT considerations +------------------ + +When Simultaneous Multi-Threading (SMT) is enabled, hypervisors can be +vulnerable to cross-thread attacks. For complete protection against VMSCAPE +attacks in SMT environments, STIBP should be enabled. + +The kernel will issue a warning if SMT is enabled without adequate STIBP +protection. Warning is not issued when: + +- SMT is disabled +- STIBP is enabled system-wide +- Intel eIBRS is enabled (which implies STIBP protection) + +System information and options +------------------------------ + +The sysfs file showing VMSCAPE mitigation status is: + + /sys/devices/system/cpu/vulnerabilities/vmscape + +The possible values in this file are: + + * 'Not affected': + + The processor is not vulnerable to VMSCAPE attacks. + + * 'Vulnerable': + + The processor is vulnerable and no mitigation has been applied. + + * 'Mitigation: IBPB before exit to userspace': + + Conditional IBPB mitigation is enabled. The kernel tracks when a CPU has + run a potentially malicious guest and issues an IBPB before the first + exit to userspace after VM-exit. + + * 'Mitigation: IBPB on VMEXIT': + + IBPB is issued on every VM-exit. This occurs when other mitigations like + RETBLEED or SRSO are already issuing IBPB on VM-exit. + +Mitigation control on the kernel command line +---------------------------------------------- + +The mitigation can be controlled via the ``vmscape=`` command line parameter: + + * ``vmscape=off``: + + Disable the VMSCAPE mitigation. + + * ``vmscape=ibpb``: + + Enable conditional IBPB mitigation (default when CONFIG_MITIGATION_VMSCAPE=y). + + * ``vmscape=force``: + + Force vulnerability detection and mitigation even on processors that are + not known to be affected. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 747a55abf494..5a7a83c411e9 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3829,6 +3829,7 @@ srbds=off [X86,INTEL] ssbd=force-off [ARM64] tsx_async_abort=off [X86] + vmscape=off [X86] Exceptions: This does not have any effect on @@ -8041,6 +8042,16 @@ vmpoff= [KNL,S390] Perform z/VM CP command after power off. Format: <command> + vmscape= [X86] Controls mitigation for VMscape attacks. + VMscape attacks can leak information from a userspace + hypervisor to a guest via speculative side-channels. + + off - disable the mitigation + ibpb - use Indirect Branch Prediction Barrier + (IBPB) mitigation (default) + force - force vulnerability detection even on + unaffected processors + vsyscall= [X86-64,EARLY] Controls the behavior of vsyscalls (i.e. calls to fixed addresses of 0xffffffffff600x00 from legacy diff --git a/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml b/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml index f2f87f0f545b..6493a6968bb4 100644 --- a/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml +++ b/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml @@ -92,8 +92,12 @@ required: anyOf: - required: - qcom,powered-remotely + - num-channels + - qcom,num-ees - required: - qcom,controlled-remotely + - num-channels + - qcom,num-ees - required: - clocks - clock-names diff --git a/Documentation/devicetree/bindings/phy/marvell,comphy-cp110.yaml b/Documentation/devicetree/bindings/phy/marvell,comphy-cp110.yaml index d9501df42886..c35d31642805 100644 --- a/Documentation/devicetree/bindings/phy/marvell,comphy-cp110.yaml +++ b/Documentation/devicetree/bindings/phy/marvell,comphy-cp110.yaml @@ -47,21 +47,19 @@ properties: const: 0 clocks: + minItems: 1 maxItems: 3 - description: Reference clocks for CP110; MG clock, MG Core clock, AXI clock clock-names: - items: - - const: mg_clk - - const: mg_core_clk - - const: axi_clk + minItems: 1 + maxItems: 3 marvell,system-controller: description: Phandle to the Marvell system controller (CP110 only) $ref: /schemas/types.yaml#/definitions/phandle patternProperties: - '^phy@[0-2]$': + '^phy@[0-5]$': description: A COMPHY lane child node type: object additionalProperties: false @@ -69,10 +67,14 @@ patternProperties: properties: reg: description: COMPHY lane number + maximum: 5 '#phy-cells': const: 1 + connector: + type: object + required: - reg - '#phy-cells' @@ -91,13 +93,24 @@ allOf: then: properties: - clocks: false - clock-names: false + clocks: + maxItems: 1 + clock-names: + const: xtal required: - reg-names else: + properties: + clocks: + minItems: 3 + clock-names: + items: + - const: mg_clk + - const: mg_core_clk + - const: axi_clk + required: - marvell,system-controller diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml index a1ae8c7988c8..b6f140bf5b3b 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml @@ -176,6 +176,8 @@ allOf: compatible: contains: enum: + - qcom,sa8775p-qmp-gen4x2-pcie-phy + - qcom,sa8775p-qmp-gen4x4-pcie-phy - qcom,sc8280xp-qmp-gen3x1-pcie-phy - qcom,sc8280xp-qmp-gen3x2-pcie-phy - qcom,sc8280xp-qmp-gen3x4-pcie-phy @@ -197,8 +199,6 @@ allOf: contains: enum: - qcom,qcs8300-qmp-gen4x2-pcie-phy - - qcom,sa8775p-qmp-gen4x2-pcie-phy - - qcom,sa8775p-qmp-gen4x4-pcie-phy then: properties: clocks: diff --git a/Documentation/devicetree/bindings/serial/8250.yaml b/Documentation/devicetree/bindings/serial/8250.yaml index e46bee8d25bf..b243afa69a1a 100644 --- a/Documentation/devicetree/bindings/serial/8250.yaml +++ b/Documentation/devicetree/bindings/serial/8250.yaml @@ -48,7 +48,6 @@ allOf: oneOf: - required: [ clock-frequency ] - required: [ clocks ] - - if: properties: compatible: @@ -60,12 +59,39 @@ allOf: items: - const: uartclk - const: reg - else: + - if: + properties: + compatible: + contains: + const: spacemit,k1-uart + then: properties: clock-names: items: - const: core - const: bus + - if: + properties: + compatible: + contains: + enum: + - spacemit,k1-uart + - nxp,lpc1850-uart + then: + required: + - clocks + - clock-names + properties: + clocks: + minItems: 2 + clock-names: + minItems: 2 + else: + properties: + clocks: + maxItems: 1 + clock-names: + maxItems: 1 properties: compatible: @@ -162,6 +188,9 @@ properties: minItems: 1 maxItems: 2 oneOf: + - enum: + - main + - uart - items: - const: core - const: bus @@ -264,29 +293,6 @@ required: - reg - interrupts -if: - properties: - compatible: - contains: - enum: - - spacemit,k1-uart - - nxp,lpc1850-uart -then: - required: - - clocks - - clock-names - properties: - clocks: - minItems: 2 - clock-names: - minItems: 2 -else: - properties: - clocks: - maxItems: 1 - clock-names: - maxItems: 1 - unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml b/Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml index 89c462653e2d..8cc848ae11cb 100644 --- a/Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml +++ b/Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml @@ -41,7 +41,7 @@ properties: - const: dma_intr2 clocks: - minItems: 1 + maxItems: 1 clock-names: const: sw_baud diff --git a/Documentation/netlink/specs/conntrack.yaml b/Documentation/netlink/specs/conntrack.yaml index c6832633ab7b..591e22a2ee43 100644 --- a/Documentation/netlink/specs/conntrack.yaml +++ b/Documentation/netlink/specs/conntrack.yaml @@ -575,8 +575,8 @@ operations: - nat-dst - timeout - mark - - counter-orig - - counter-reply + - counters-orig + - counters-reply - use - id - nat-dst @@ -591,7 +591,6 @@ operations: request: value: 0x101 attributes: - - nfgen-family - mark - filter - status @@ -608,8 +607,8 @@ operations: - nat-dst - timeout - mark - - counter-orig - - counter-reply + - counters-orig + - counters-reply - use - id - nat-dst diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml index 02f1ddcfbf1c..d1b4829b580a 100644 --- a/Documentation/netlink/specs/mptcp_pm.yaml +++ b/Documentation/netlink/specs/mptcp_pm.yaml @@ -28,13 +28,13 @@ definitions: traffic-patterns it can take a long time until the MPTCP_EVENT_ESTABLISHED is sent. Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, sport, - dport, server-side. + dport, server-side, [flags]. - name: established doc: >- A MPTCP connection is established (can start new subflows). Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, sport, - dport, server-side. + dport, server-side, [flags]. - name: closed doc: >- @@ -256,7 +256,7 @@ attribute-sets: type: u32 - name: if-idx - type: u32 + type: s32 - name: reset-reason type: u32 diff --git a/Documentation/networking/can.rst b/Documentation/networking/can.rst index bc1b585355f7..7650c4b5be5f 100644 --- a/Documentation/networking/can.rst +++ b/Documentation/networking/can.rst @@ -742,7 +742,7 @@ The broadcast manager sends responses to user space in the same form: struct timeval ival1, ival2; /* count and subsequent interval */ canid_t can_id; /* unique can_id for task */ __u32 nframes; /* number of can_frames following */ - struct can_frame frames[0]; + struct can_frame frames[]; }; The aligned payload 'frames' uses the same basic CAN frame structure defined diff --git a/Documentation/networking/mptcp.rst b/Documentation/networking/mptcp.rst index 17f2bab61164..2e31038d6462 100644 --- a/Documentation/networking/mptcp.rst +++ b/Documentation/networking/mptcp.rst @@ -60,10 +60,10 @@ address announcements. Typically, it is the client side that initiates subflows, and the server side that announces additional addresses via the ``ADD_ADDR`` and ``REMOVE_ADDR`` options. -Path managers are controlled by the ``net.mptcp.pm_type`` sysctl knob -- see -mptcp-sysctl.rst. There are two types: the in-kernel one (type ``0``) where the -same rules are applied for all the connections (see: ``ip mptcp``) ; and the -userspace one (type ``1``), controlled by a userspace daemon (i.e. `mptcpd +Path managers are controlled by the ``net.mptcp.path_manager`` sysctl knob -- +see mptcp-sysctl.rst. There are two types: the in-kernel one (``kernel``) where +the same rules are applied for all the connections (see: ``ip mptcp``) ; and the +userspace one (``userspace``), controlled by a userspace daemon (i.e. `mptcpd <https://mptcpd.mptcp.dev/>`_) where different rules can be applied for each connection. The path managers can be controlled via a Netlink API; see netlink_spec/mptcp_pm.rst. diff --git a/Documentation/sound/alsa-configuration.rst b/Documentation/sound/alsa-configuration.rst index 062b86522e4d..accaebbdd642 100644 --- a/Documentation/sound/alsa-configuration.rst +++ b/Documentation/sound/alsa-configuration.rst @@ -2293,7 +2293,7 @@ delayed_register notice the need. skip_validation Skip unit descriptor validation (default: no). - The option is used to ignores the validation errors with the hexdump + The option is used to ignore the validation errors with the hexdump of the unit descriptor instead of a driver probe error, so that we can check its details. quirk_flags diff --git a/MAINTAINERS b/MAINTAINERS index 17073c075bf7..520fb4e379a3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4683,7 +4683,6 @@ F: security/bpf/ BPF [SELFTESTS] (Test Runners & Infrastructure) M: Andrii Nakryiko <andrii@kernel.org> M: Eduard Zingerman <eddyz87@gmail.com> -R: Mykola Lysenko <mykolal@fb.com> L: bpf@vger.kernel.org S: Maintained F: tools/testing/selftests/bpf/ @@ -5259,7 +5258,6 @@ F: drivers/gpio/gpio-bt8xx.c BTRFS FILE SYSTEM M: Chris Mason <clm@fb.com> -M: Josef Bacik <josef@toxicpanda.com> M: David Sterba <dsterba@suse.com> L: linux-btrfs@vger.kernel.org S: Maintained @@ -7240,15 +7238,15 @@ F: include/linux/swiotlb.h F: kernel/dma/ DMA MAPPING HELPERS DEVICE DRIVER API [RUST] -M: Abdiel Janulgue <abdiel.janulgue@gmail.com> M: Danilo Krummrich <dakr@kernel.org> +R: Abdiel Janulgue <abdiel.janulgue@gmail.com> R: Daniel Almeida <daniel.almeida@collabora.com> R: Robin Murphy <robin.murphy@arm.com> R: Andreas Hindborg <a.hindborg@kernel.org> L: rust-for-linux@vger.kernel.org S: Supported W: https://rust-for-linux.com -T: git https://github.com/Rust-for-Linux/linux.git alloc-next +T: git git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core.git F: rust/helpers/dma.c F: rust/kernel/dma.rs F: samples/rust/rust_dma.rs @@ -7432,7 +7430,7 @@ S: Supported F: Documentation/devicetree/bindings/dpll/dpll-device.yaml F: Documentation/devicetree/bindings/dpll/dpll-pin.yaml F: Documentation/driver-api/dpll.rst -F: drivers/dpll/* +F: drivers/dpll/ F: include/linux/dpll.h F: include/uapi/linux/dpll.h @@ -8080,7 +8078,6 @@ F: Documentation/devicetree/bindings/gpu/ F: Documentation/gpu/ F: drivers/gpu/drm/ F: drivers/gpu/vga/ -F: rust/kernel/drm/ F: include/drm/drm F: include/linux/vga* F: include/uapi/drm/ @@ -8092,11 +8089,21 @@ X: drivers/gpu/drm/i915/ X: drivers/gpu/drm/kmb/ X: drivers/gpu/drm/mediatek/ X: drivers/gpu/drm/msm/ -X: drivers/gpu/drm/nouveau/ +X: drivers/gpu/drm/nova/ X: drivers/gpu/drm/radeon/ X: drivers/gpu/drm/tegra/ X: drivers/gpu/drm/xe/ +DRM DRIVERS AND COMMON INFRASTRUCTURE [RUST] +M: Danilo Krummrich <dakr@kernel.org> +M: Alice Ryhl <aliceryhl@google.com> +S: Supported +W: https://drm.pages.freedesktop.org/maintainer-tools/drm-rust.html +T: git https://gitlab.freedesktop.org/drm/rust/kernel.git +F: drivers/gpu/drm/nova/ +F: drivers/gpu/nova-core/ +F: rust/kernel/drm/ + DRM DRIVERS FOR ALLWINNER A10 M: Maxime Ripard <mripard@kernel.org> M: Chen-Yu Tsai <wens@csie.org> @@ -15741,13 +15748,6 @@ S: Supported W: http://www.melexis.com F: drivers/iio/temperature/mlx90635.c -MELFAS MIP4 TOUCHSCREEN DRIVER -M: Sangwon Jee <jeesw@melfas.com> -S: Supported -W: http://www.melfas.com -F: Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt -F: drivers/input/touchscreen/melfas_mip4.c - MELLANOX BLUEFIELD I2C DRIVER M: Khalil Blaiech <kblaiech@nvidia.com> M: Asmaa Mnebhi <asmaa@nvidia.com> @@ -16128,6 +16128,7 @@ M: Andrew Morton <akpm@linux-foundation.org> M: Mike Rapoport <rppt@kernel.org> L: linux-mm@kvack.org S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock.git F: include/linux/numa_memblks.h F: mm/numa.c F: mm/numa_emulation.c @@ -16195,6 +16196,7 @@ R: Rik van Riel <riel@surriel.com> R: Liam R. Howlett <Liam.Howlett@oracle.com> R: Vlastimil Babka <vbabka@suse.cz> R: Harry Yoo <harry.yoo@oracle.com> +R: Jann Horn <jannh@google.com> L: linux-mm@kvack.org S: Maintained F: include/linux/rmap.h @@ -16239,6 +16241,7 @@ R: Nico Pache <npache@redhat.com> R: Ryan Roberts <ryan.roberts@arm.com> R: Dev Jain <dev.jain@arm.com> R: Barry Song <baohua@kernel.org> +R: Lance Yang <lance.yang@linux.dev> L: linux-mm@kvack.org S: Maintained W: http://www.linux-mm.org @@ -17480,6 +17483,7 @@ NETFILTER M: Pablo Neira Ayuso <pablo@netfilter.org> M: Jozsef Kadlecsik <kadlec@netfilter.org> M: Florian Westphal <fw@strlen.de> +R: Phil Sutter <phil@nwl.cc> L: netfilter-devel@vger.kernel.org L: coreteam@netfilter.org S: Maintained @@ -24256,7 +24260,7 @@ F: Documentation/devicetree/bindings/input/allwinner,sun4i-a10-lradc-keys.yaml F: drivers/input/keyboard/sun4i-lradc-keys.c SUNDANCE NETWORK DRIVER -M: Denis Kirjanov <dkirjanov@suse.de> +M: Denis Kirjanov <kirjanov@gmail.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/dlink/sundance.c @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 17 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 2b07f0a27a7d..0ee4f6fa3a17 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -1369,6 +1369,7 @@ static inline bool kvm_system_needs_idmapped_vectors(void) } void kvm_init_host_debug_data(void); +void kvm_debug_init_vhe(void); void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu); void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu); void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 1246216616b5..2888b5d03757 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -355,11 +355,6 @@ static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walke return pteref; } -static inline kvm_pte_t *kvm_dereference_pteref_raw(kvm_pteref_t pteref) -{ - return pteref; -} - static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker) { /* @@ -389,11 +384,6 @@ static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walke return rcu_dereference_check(pteref, !(walker->flags & KVM_PGTABLE_WALK_SHARED)); } -static inline kvm_pte_t *kvm_dereference_pteref_raw(kvm_pteref_t pteref) -{ - return rcu_dereference_raw(pteref); -} - static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker) { if (walker->flags & KVM_PGTABLE_WALK_SHARED) @@ -562,26 +552,6 @@ static inline int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2 void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt); /** - * kvm_pgtable_stage2_destroy_range() - Destroy the unlinked range of addresses. - * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). - * @addr: Intermediate physical address at which to place the mapping. - * @size: Size of the mapping. - * - * The page-table is assumed to be unreachable by any hardware walkers prior - * to freeing and therefore no TLB invalidation is performed. - */ -void kvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt, - u64 addr, u64 size); - -/** - * kvm_pgtable_stage2_destroy_pgd() - Destroy the PGD of guest stage-2 page-table. - * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). - * - * It is assumed that the rest of the page-table is freed before this operation. - */ -void kvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt); - -/** * kvm_pgtable_stage2_free_unlinked() - Free an unlinked stage-2 paging structure. * @mm_ops: Memory management callbacks. * @pgtable: Unlinked stage-2 paging structure to be freed. diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h index 35f9d9478004..ea58282f59bb 100644 --- a/arch/arm64/include/asm/kvm_pkvm.h +++ b/arch/arm64/include/asm/kvm_pkvm.h @@ -179,9 +179,7 @@ struct pkvm_mapping { int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops); -void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt, - u64 addr, u64 size); -void pkvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt); +void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt); int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, enum kvm_pgtable_prot prot, void *mc, enum kvm_pgtable_walk_flags flags); diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index af1ca875c52c..410060ebd86d 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -94,7 +94,7 @@ int load_other_segments(struct kimage *image, char *initrd, unsigned long initrd_len, char *cmdline) { - struct kexec_buf kbuf; + struct kexec_buf kbuf = {}; void *dtb = NULL; unsigned long initrd_load_addr = 0, dtb_len, orig_segments = image->nr_segments; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 5bf101c869c9..bd6b6a620a09 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2113,8 +2113,10 @@ static void cpu_hyp_init_features(void) { cpu_set_hyp_vector(); - if (is_kernel_in_hyp_mode()) + if (is_kernel_in_hyp_mode()) { kvm_timer_init_vhe(); + kvm_debug_init_vhe(); + } if (vgic_present) kvm_vgic_init_cpu_hardware(); diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index 381382c19fe4..e027d9c32b0d 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -96,6 +96,13 @@ void kvm_init_host_debug_data(void) } } +void kvm_debug_init_vhe(void) +{ + /* Clear PMSCR_EL1.E{0,1}SPE which reset to UNKNOWN values. */ + if (SYS_FIELD_GET(ID_AA64DFR0_EL1, PMSVer, read_sysreg(id_aa64dfr0_el1))) + write_sysreg_el1(0, SYS_PMSCR); +} + /* * Configures the 'external' MDSCR_EL1 value for the guest, i.e. when the host * has taken over MDSCR_EL1. @@ -138,6 +145,9 @@ void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu) /* Must be called before kvm_vcpu_load_vhe() */ KVM_BUG_ON(vcpu_get_flag(vcpu, SYSREGS_ON_CPU), vcpu->kvm); + if (has_vhe()) + *host_data_ptr(host_debug_state.mdcr_el2) = read_sysreg(mdcr_el2); + /* * Determine which of the possible debug states we're in: * @@ -184,6 +194,9 @@ void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu) void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu) { + if (has_vhe()) + write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2); + if (likely(!(vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) return; diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 84ec4e100fbb..b6682202edf3 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -431,9 +431,6 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu) vcpu_set_flag(vcpu, PMUSERENR_ON_CPU); } - *host_data_ptr(host_debug_state.mdcr_el2) = read_sysreg(mdcr_el2); - write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); - if (cpus_have_final_cap(ARM64_HAS_HCX)) { u64 hcrx = vcpu->arch.hcrx_el2; if (is_nested_ctxt(vcpu)) { @@ -454,8 +451,6 @@ static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); - write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2); - write_sysreg(0, hstr_el2); if (system_supports_pmuv3()) { write_sysreg(ctxt_sys_reg(hctxt, PMUSERENR_EL0), pmuserenr_el0); diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index ccd575d5f6de..d3b9ec8a7c28 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -50,6 +50,10 @@ extern void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc); static void __activate_traps(struct kvm_vcpu *vcpu) { ___activate_traps(vcpu, vcpu->arch.hcr_el2); + + *host_data_ptr(host_debug_state.mdcr_el2) = read_sysreg(mdcr_el2); + write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); + __activate_traps_common(vcpu); __activate_cptr_traps(vcpu); @@ -93,6 +97,8 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) isb(); } + write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2); + __deactivate_traps_common(vcpu); write_sysreg_hcr(this_cpu_ptr(&kvm_init_params)->hcr_el2); diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 71d2fc97f004..82da9b03692d 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -253,7 +253,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu) *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); *vcpu_cpsr(vcpu) = read_sysreg_el2(SYS_SPSR); - __vcpu_assign_sys_reg(vcpu, read_sysreg_el1(SYS_VBAR), VBAR_EL1); + __vcpu_assign_sys_reg(vcpu, VBAR_EL1, read_sysreg_el1(SYS_VBAR)); kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index c36f282a175d..c351b4abd5db 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -1551,38 +1551,21 @@ static int stage2_free_walker(const struct kvm_pgtable_visit_ctx *ctx, return 0; } -void kvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt, - u64 addr, u64 size) +void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) { + size_t pgd_sz; struct kvm_pgtable_walker walker = { .cb = stage2_free_walker, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; - WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker)); -} - -void kvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt) -{ - size_t pgd_sz; - + WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker)); pgd_sz = kvm_pgd_pages(pgt->ia_bits, pgt->start_level) * PAGE_SIZE; - - /* - * Since the pgtable is unlinked at this point, and not shared with - * other walkers, safely deference pgd with kvm_dereference_pteref_raw() - */ - pgt->mm_ops->free_pages_exact(kvm_dereference_pteref_raw(pgt->pgd), pgd_sz); + pgt->mm_ops->free_pages_exact(kvm_dereference_pteref(&walker, pgt->pgd), pgd_sz); pgt->pgd = NULL; } -void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) -{ - kvm_pgtable_stage2_destroy_range(pgt, 0, BIT(pgt->ia_bits)); - kvm_pgtable_stage2_destroy_pgd(pgt); -} - void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level) { kvm_pteref_t ptep = (kvm_pteref_t)pgtable; diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 86f3d80daf37..736394292503 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -904,38 +904,6 @@ static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type) return 0; } -/* - * Assume that @pgt is valid and unlinked from the KVM MMU to free the - * page-table without taking the kvm_mmu_lock and without performing any - * TLB invalidations. - * - * Also, the range of addresses can be large enough to cause need_resched - * warnings, for instance on CONFIG_PREEMPT_NONE kernels. Hence, invoke - * cond_resched() periodically to prevent hogging the CPU for a long time - * and schedule something else, if required. - */ -static void stage2_destroy_range(struct kvm_pgtable *pgt, phys_addr_t addr, - phys_addr_t end) -{ - u64 next; - - do { - next = stage2_range_addr_end(addr, end); - KVM_PGT_FN(kvm_pgtable_stage2_destroy_range)(pgt, addr, - next - addr); - if (next != end) - cond_resched(); - } while (addr = next, addr != end); -} - -static void kvm_stage2_destroy(struct kvm_pgtable *pgt) -{ - unsigned int ia_bits = VTCR_EL2_IPA(pgt->mmu->vtcr); - - stage2_destroy_range(pgt, 0, BIT(ia_bits)); - KVM_PGT_FN(kvm_pgtable_stage2_destroy_pgd)(pgt); -} - /** * kvm_init_stage2_mmu - Initialise a S2 MMU structure * @kvm: The pointer to the KVM structure @@ -1012,7 +980,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t return 0; out_destroy_pgtable: - kvm_stage2_destroy(pgt); + KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt); out_free_pgtable: kfree(pgt); return err; @@ -1106,10 +1074,14 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu) mmu->pgt = NULL; free_percpu(mmu->last_vcpu_ran); } + + if (kvm_is_nested_s2_mmu(kvm, mmu)) + kvm_init_nested_s2_mmu(mmu); + write_unlock(&kvm->mmu_lock); if (pgt) { - kvm_stage2_destroy(pgt); + KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt); kfree(pgt); } } @@ -1541,11 +1513,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu); VM_BUG_ON(write_fault && exec_fault); - if (fault_is_perm && !write_fault && !exec_fault) { - kvm_err("Unexpected L2 read permission error\n"); - return -EFAULT; - } - if (!is_protected_kvm_enabled()) memcache = &vcpu->arch.mmu_page_cache; else diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 77db81bae86f..50d559248a1f 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -847,7 +847,7 @@ static void kvm_invalidate_vncr_ipa(struct kvm *kvm, u64 start, u64 end) ipa_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift, vt->wr.level)); - ipa_start = vt->wr.pa & (ipa_size - 1); + ipa_start = vt->wr.pa & ~(ipa_size - 1); ipa_end = ipa_start + ipa_size; if (ipa_end <= start || ipa_start >= end) @@ -887,7 +887,7 @@ static void invalidate_vncr_va(struct kvm *kvm, va_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift, vt->wr.level)); - va_start = vt->gva & (va_size - 1); + va_start = vt->gva & ~(va_size - 1); va_end = va_start + va_size; switch (scope->type) { @@ -1276,7 +1276,7 @@ static bool kvm_vncr_tlb_lookup(struct kvm_vcpu *vcpu) !(tcr & TCR_ASID16)) asid &= GENMASK(7, 0); - return asid != vt->wr.asid; + return asid == vt->wr.asid; } return true; diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c index 61827cf6fea4..fcd70bfe44fb 100644 --- a/arch/arm64/kvm/pkvm.c +++ b/arch/arm64/kvm/pkvm.c @@ -316,16 +316,9 @@ static int __pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 start, u64 e return 0; } -void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt, - u64 addr, u64 size) +void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) { - __pkvm_pgtable_stage2_unmap(pgt, addr, addr + size); -} - -void pkvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt) -{ - /* Expected to be called after all pKVM mappings have been released. */ - WARN_ON_ONCE(!RB_EMPTY_ROOT(&pgt->pkvm_mappings.rb_root)); + __pkvm_pgtable_stage2_unmap(pgt, 0, ~(0ULL)); } int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c index 2684f273d9e1..4c1209261b65 100644 --- a/arch/arm64/kvm/vgic/vgic-debug.c +++ b/arch/arm64/kvm/vgic/vgic-debug.c @@ -69,7 +69,7 @@ static int iter_mark_lpis(struct kvm *kvm) int nr_lpis = 0; xa_for_each(&dist->lpi_xa, intid, irq) { - if (!vgic_try_get_irq_kref(irq)) + if (!vgic_try_get_irq_ref(irq)) continue; xa_set_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 1e680ad6e863..4c3c0d82e476 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -53,7 +53,7 @@ void kvm_vgic_early_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - xa_init_flags(&dist->lpi_xa, XA_FLAGS_LOCK_IRQ); + xa_init(&dist->lpi_xa); } /* CREATION */ @@ -208,7 +208,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) raw_spin_lock_init(&irq->irq_lock); irq->vcpu = NULL; irq->target_vcpu = vcpu0; - kref_init(&irq->refcount); + refcount_set(&irq->refcount, 0); switch (dist->vgic_model) { case KVM_DEV_TYPE_ARM_VGIC_V2: irq->targets = 0; @@ -277,7 +277,7 @@ static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type) irq->intid = i; irq->vcpu = NULL; irq->target_vcpu = vcpu; - kref_init(&irq->refcount); + refcount_set(&irq->refcount, 0); if (vgic_irq_is_sgi(i)) { /* SGIs */ irq->enabled = 1; diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 7368c13f16b7..ce3e3ed3f29f 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -78,7 +78,6 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq = vgic_get_irq(kvm, intid), *oldirq; - unsigned long flags; int ret; /* In this case there is no put, since we keep the reference. */ @@ -89,7 +88,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, if (!irq) return ERR_PTR(-ENOMEM); - ret = xa_reserve_irq(&dist->lpi_xa, intid, GFP_KERNEL_ACCOUNT); + ret = xa_reserve(&dist->lpi_xa, intid, GFP_KERNEL_ACCOUNT); if (ret) { kfree(irq); return ERR_PTR(ret); @@ -99,19 +98,19 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, raw_spin_lock_init(&irq->irq_lock); irq->config = VGIC_CONFIG_EDGE; - kref_init(&irq->refcount); + refcount_set(&irq->refcount, 1); irq->intid = intid; irq->target_vcpu = vcpu; irq->group = 1; - xa_lock_irqsave(&dist->lpi_xa, flags); + xa_lock(&dist->lpi_xa); /* * There could be a race with another vgic_add_lpi(), so we need to * check that we don't add a second list entry with the same LPI. */ oldirq = xa_load(&dist->lpi_xa, intid); - if (vgic_try_get_irq_kref(oldirq)) { + if (vgic_try_get_irq_ref(oldirq)) { /* Someone was faster with adding this LPI, lets use that. */ kfree(irq); irq = oldirq; @@ -126,7 +125,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, } out_unlock: - xa_unlock_irqrestore(&dist->lpi_xa, flags); + xa_unlock(&dist->lpi_xa); if (ret) return ERR_PTR(ret); @@ -547,7 +546,7 @@ static struct vgic_irq *vgic_its_check_cache(struct kvm *kvm, phys_addr_t db, rcu_read_lock(); irq = xa_load(&its->translation_cache, cache_key); - if (!vgic_try_get_irq_kref(irq)) + if (!vgic_try_get_irq_ref(irq)) irq = NULL; rcu_read_unlock(); @@ -571,7 +570,7 @@ static void vgic_its_cache_translation(struct kvm *kvm, struct vgic_its *its, * its_lock, as the ITE (and the reference it holds) cannot be freed. */ lockdep_assert_held(&its->its_lock); - vgic_get_irq_kref(irq); + vgic_get_irq_ref(irq); old = xa_store(&its->translation_cache, cache_key, irq, GFP_KERNEL_ACCOUNT); diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index 4d9343d2b0b1..548aec9d5a72 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -518,7 +518,7 @@ static struct vgic_irq *__vgic_host_irq_get_vlpi(struct kvm *kvm, int host_irq) if (!irq->hw || irq->host_irq != host_irq) continue; - if (!vgic_try_get_irq_kref(irq)) + if (!vgic_try_get_irq_ref(irq)) return NULL; return irq; diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index f5148b38120a..6dd5a10081e2 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -28,8 +28,8 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = { * kvm->arch.config_lock (mutex) * its->cmd_lock (mutex) * its->its_lock (mutex) - * vgic_cpu->ap_list_lock must be taken with IRQs disabled - * vgic_dist->lpi_xa.xa_lock must be taken with IRQs disabled + * vgic_dist->lpi_xa.xa_lock + * vgic_cpu->ap_list_lock must be taken with IRQs disabled * vgic_irq->irq_lock must be taken with IRQs disabled * * As the ap_list_lock might be taken from the timer interrupt handler, @@ -71,7 +71,7 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid) rcu_read_lock(); irq = xa_load(&dist->lpi_xa, intid); - if (!vgic_try_get_irq_kref(irq)) + if (!vgic_try_get_irq_ref(irq)) irq = NULL; rcu_read_unlock(); @@ -114,37 +114,66 @@ struct vgic_irq *vgic_get_vcpu_irq(struct kvm_vcpu *vcpu, u32 intid) return vgic_get_irq(vcpu->kvm, intid); } -/* - * We can't do anything in here, because we lack the kvm pointer to - * lock and remove the item from the lpi_list. So we keep this function - * empty and use the return value of kref_put() to trigger the freeing. - */ -static void vgic_irq_release(struct kref *ref) +static void vgic_release_lpi_locked(struct vgic_dist *dist, struct vgic_irq *irq) +{ + lockdep_assert_held(&dist->lpi_xa.xa_lock); + __xa_erase(&dist->lpi_xa, irq->intid); + kfree_rcu(irq, rcu); +} + +static __must_check bool __vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) +{ + if (irq->intid < VGIC_MIN_LPI) + return false; + + return refcount_dec_and_test(&irq->refcount); +} + +static __must_check bool vgic_put_irq_norelease(struct kvm *kvm, struct vgic_irq *irq) { + if (!__vgic_put_irq(kvm, irq)) + return false; + + irq->pending_release = true; + return true; } void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) { struct vgic_dist *dist = &kvm->arch.vgic; - unsigned long flags; - if (irq->intid < VGIC_MIN_LPI) - return; + if (irq->intid >= VGIC_MIN_LPI) + might_lock(&dist->lpi_xa.xa_lock); - if (!kref_put(&irq->refcount, vgic_irq_release)) + if (!__vgic_put_irq(kvm, irq)) return; - xa_lock_irqsave(&dist->lpi_xa, flags); - __xa_erase(&dist->lpi_xa, irq->intid); - xa_unlock_irqrestore(&dist->lpi_xa, flags); + xa_lock(&dist->lpi_xa); + vgic_release_lpi_locked(dist, irq); + xa_unlock(&dist->lpi_xa); +} - kfree_rcu(irq, rcu); +static void vgic_release_deleted_lpis(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + unsigned long intid; + struct vgic_irq *irq; + + xa_lock(&dist->lpi_xa); + + xa_for_each(&dist->lpi_xa, intid, irq) { + if (irq->pending_release) + vgic_release_lpi_locked(dist, irq); + } + + xa_unlock(&dist->lpi_xa); } void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_irq *irq, *tmp; + bool deleted = false; unsigned long flags; raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags); @@ -155,11 +184,14 @@ void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu) list_del(&irq->ap_list); irq->vcpu = NULL; raw_spin_unlock(&irq->irq_lock); - vgic_put_irq(vcpu->kvm, irq); + deleted |= vgic_put_irq_norelease(vcpu->kvm, irq); } } raw_spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags); + + if (deleted) + vgic_release_deleted_lpis(vcpu->kvm); } void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending) @@ -399,7 +431,7 @@ retry: * now in the ap_list. This is safe as the caller must already hold a * reference on the irq. */ - vgic_get_irq_kref(irq); + vgic_get_irq_ref(irq); list_add_tail(&irq->ap_list, &vcpu->arch.vgic_cpu.ap_list_head); irq->vcpu = vcpu; @@ -630,6 +662,7 @@ static void vgic_prune_ap_list(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_irq *irq, *tmp; + bool deleted_lpis = false; DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); @@ -657,12 +690,12 @@ retry: /* * This vgic_put_irq call matches the - * vgic_get_irq_kref in vgic_queue_irq_unlock, + * vgic_get_irq_ref in vgic_queue_irq_unlock, * where we added the LPI to the ap_list. As * we remove the irq from the list, we drop * also drop the refcount. */ - vgic_put_irq(vcpu->kvm, irq); + deleted_lpis |= vgic_put_irq_norelease(vcpu->kvm, irq); continue; } @@ -725,6 +758,9 @@ retry: } raw_spin_unlock(&vgic_cpu->ap_list_lock); + + if (unlikely(deleted_lpis)) + vgic_release_deleted_lpis(vcpu->kvm); } static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu) @@ -818,7 +854,7 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu) * the AP list has been sorted already. */ if (multi_sgi && irq->priority > prio) { - _raw_spin_unlock(&irq->irq_lock); + raw_spin_unlock(&irq->irq_lock); break; } diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index de1c1d3261c3..ac5f9c5d2b98 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -267,7 +267,7 @@ void vgic_v2_put(struct kvm_vcpu *vcpu); void vgic_v2_save_state(struct kvm_vcpu *vcpu); void vgic_v2_restore_state(struct kvm_vcpu *vcpu); -static inline bool vgic_try_get_irq_kref(struct vgic_irq *irq) +static inline bool vgic_try_get_irq_ref(struct vgic_irq *irq) { if (!irq) return false; @@ -275,12 +275,12 @@ static inline bool vgic_try_get_irq_kref(struct vgic_irq *irq) if (irq->intid < VGIC_MIN_LPI) return true; - return kref_get_unless_zero(&irq->refcount); + return refcount_inc_not_zero(&irq->refcount); } -static inline void vgic_get_irq_kref(struct vgic_irq *irq) +static inline void vgic_get_irq_ref(struct vgic_irq *irq) { - WARN_ON_ONCE(!vgic_try_get_irq_kref(irq)); + WARN_ON_ONCE(!vgic_try_get_irq_ref(irq)); } void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu); diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index f0abc38c40ac..0631a6b11281 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -298,6 +298,10 @@ config AS_HAS_LVZ_EXTENSION config CC_HAS_ANNOTATE_TABLEJUMP def_bool $(cc-option,-mannotate-tablejump) +config RUSTC_HAS_ANNOTATE_TABLEJUMP + depends on RUST + def_bool $(rustc-option,-Cllvm-args=--loongarch-annotate-tablejump) + menu "Kernel type and options" source "kernel/Kconfig.hz" @@ -563,10 +567,14 @@ config ARCH_STRICT_ALIGN -mstrict-align build parameter to prevent unaligned accesses. CPUs with h/w unaligned access support: - Loongson-2K2000/2K3000/3A5000/3C5000/3D5000. + Loongson-2K2000/2K3000 and all of Loongson-3 series processors + based on LoongArch. CPUs without h/w unaligned access support: - Loongson-2K500/2K1000. + Loongson-2K0300/2K0500/2K1000. + + If you want to make sure whether to support unaligned memory access + on your hardware, please read the bit 20 (UAL) of CPUCFG1 register. This option is enabled by default to make the kernel be able to run on all LoongArch systems. But you can disable it manually if you want diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index a3a9759414f4..ae419e32f22e 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -102,16 +102,21 @@ KBUILD_CFLAGS += $(call cc-option,-mthin-add-sub) $(call cc-option,-Wa$(comma) ifdef CONFIG_OBJTOOL ifdef CONFIG_CC_HAS_ANNOTATE_TABLEJUMP +KBUILD_CFLAGS += -mannotate-tablejump +else +KBUILD_CFLAGS += -fno-jump-tables # keep compatibility with older compilers +endif +ifdef CONFIG_RUSTC_HAS_ANNOTATE_TABLEJUMP +KBUILD_RUSTFLAGS += -Cllvm-args=--loongarch-annotate-tablejump +else +KBUILD_RUSTFLAGS += -Zno-jump-tables # keep compatibility with older compilers +endif +ifdef CONFIG_LTO_CLANG # The annotate-tablejump option can not be passed to LLVM backend when LTO is enabled. # Ensure it is aware of linker with LTO, '--loongarch-annotate-tablejump' also needs to # be passed via '-mllvm' to ld.lld. -KBUILD_CFLAGS += -mannotate-tablejump -ifdef CONFIG_LTO_CLANG KBUILD_LDFLAGS += -mllvm --loongarch-annotate-tablejump endif -else -KBUILD_CFLAGS += -fno-jump-tables # keep compatibility with older compilers -endif endif KBUILD_RUSTFLAGS += --target=loongarch64-unknown-none-softfloat -Ccode-model=small diff --git a/arch/loongarch/include/asm/acenv.h b/arch/loongarch/include/asm/acenv.h index 52f298f7293b..483c955f2ae5 100644 --- a/arch/loongarch/include/asm/acenv.h +++ b/arch/loongarch/include/asm/acenv.h @@ -10,9 +10,8 @@ #ifndef _ASM_LOONGARCH_ACENV_H #define _ASM_LOONGARCH_ACENV_H -/* - * This header is required by ACPI core, but we have nothing to fill in - * right now. Will be updated later when needed. - */ +#ifdef CONFIG_ARCH_STRICT_ALIGN +#define ACPI_MISALIGNMENT_NOT_SUPPORTED +#endif /* CONFIG_ARCH_STRICT_ALIGN */ #endif /* _ASM_LOONGARCH_ACENV_H */ diff --git a/arch/loongarch/include/asm/kvm_mmu.h b/arch/loongarch/include/asm/kvm_mmu.h index 099bafc6f797..e36cc7e8ed20 100644 --- a/arch/loongarch/include/asm/kvm_mmu.h +++ b/arch/loongarch/include/asm/kvm_mmu.h @@ -16,6 +16,13 @@ */ #define KVM_MMU_CACHE_MIN_PAGES (CONFIG_PGTABLE_LEVELS - 1) +/* + * _PAGE_MODIFIED is a SW pte bit, it records page ever written on host + * kernel, on secondary MMU it records the page writeable attribute, in + * order for fast path handling. + */ +#define KVM_PAGE_WRITEABLE _PAGE_MODIFIED + #define _KVM_FLUSH_PGTABLE 0x1 #define _KVM_HAS_PGMASK 0x2 #define kvm_pfn_pte(pfn, prot) (((pfn) << PFN_PTE_SHIFT) | pgprot_val(prot)) @@ -52,10 +59,10 @@ static inline void kvm_set_pte(kvm_pte_t *ptep, kvm_pte_t val) WRITE_ONCE(*ptep, val); } -static inline int kvm_pte_write(kvm_pte_t pte) { return pte & _PAGE_WRITE; } -static inline int kvm_pte_dirty(kvm_pte_t pte) { return pte & _PAGE_DIRTY; } static inline int kvm_pte_young(kvm_pte_t pte) { return pte & _PAGE_ACCESSED; } static inline int kvm_pte_huge(kvm_pte_t pte) { return pte & _PAGE_HUGE; } +static inline int kvm_pte_dirty(kvm_pte_t pte) { return pte & __WRITEABLE; } +static inline int kvm_pte_writeable(kvm_pte_t pte) { return pte & KVM_PAGE_WRITEABLE; } static inline kvm_pte_t kvm_pte_mkyoung(kvm_pte_t pte) { @@ -69,12 +76,12 @@ static inline kvm_pte_t kvm_pte_mkold(kvm_pte_t pte) static inline kvm_pte_t kvm_pte_mkdirty(kvm_pte_t pte) { - return pte | _PAGE_DIRTY; + return pte | __WRITEABLE; } static inline kvm_pte_t kvm_pte_mkclean(kvm_pte_t pte) { - return pte & ~_PAGE_DIRTY; + return pte & ~__WRITEABLE; } static inline kvm_pte_t kvm_pte_mkhuge(kvm_pte_t pte) @@ -87,6 +94,11 @@ static inline kvm_pte_t kvm_pte_mksmall(kvm_pte_t pte) return pte & ~_PAGE_HUGE; } +static inline kvm_pte_t kvm_pte_mkwriteable(kvm_pte_t pte) +{ + return pte | KVM_PAGE_WRITEABLE; +} + static inline int kvm_need_flush(kvm_ptw_ctx *ctx) { return ctx->flag & _KVM_FLUSH_PGTABLE; diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c index c0a5dc9aeae2..23bd5ae2212c 100644 --- a/arch/loongarch/kernel/env.c +++ b/arch/loongarch/kernel/env.c @@ -86,7 +86,7 @@ late_initcall(fdt_cpu_clk_init); static ssize_t boardinfo_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, + return sysfs_emit(buf, "BIOS Information\n" "Vendor\t\t\t: %s\n" "Version\t\t\t: %s\n" @@ -109,6 +109,8 @@ static int __init boardinfo_init(void) struct kobject *loongson_kobj; loongson_kobj = kobject_create_and_add("loongson", firmware_kobj); + if (!loongson_kobj) + return -ENOMEM; return sysfs_create_file(loongson_kobj, &boardinfo_attr.attr); } diff --git a/arch/loongarch/kernel/stacktrace.c b/arch/loongarch/kernel/stacktrace.c index 9a038d1070d7..387dc4d3c486 100644 --- a/arch/loongarch/kernel/stacktrace.c +++ b/arch/loongarch/kernel/stacktrace.c @@ -51,12 +51,13 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, if (task == current) { regs->regs[3] = (unsigned long)__builtin_frame_address(0); regs->csr_era = (unsigned long)__builtin_return_address(0); + regs->regs[22] = 0; } else { regs->regs[3] = thread_saved_fp(task); regs->csr_era = thread_saved_ra(task); + regs->regs[22] = task->thread.reg22; } regs->regs[1] = 0; - regs->regs[22] = 0; for (unwind_start(&state, task, regs); !unwind_done(&state) && !unwind_error(&state); unwind_next_frame(&state)) { diff --git a/arch/loongarch/kernel/vdso.c b/arch/loongarch/kernel/vdso.c index 7b888d9085a0..dee1a15d7f4c 100644 --- a/arch/loongarch/kernel/vdso.c +++ b/arch/loongarch/kernel/vdso.c @@ -54,6 +54,9 @@ static int __init init_vdso(void) vdso_info.code_mapping.pages = kcalloc(vdso_info.size / PAGE_SIZE, sizeof(struct page *), GFP_KERNEL); + if (!vdso_info.code_mapping.pages) + return -ENOMEM; + pfn = __phys_to_pfn(__pa_symbol(vdso_info.vdso)); for (i = 0; i < vdso_info.size / PAGE_SIZE; i++) vdso_info.code_mapping.pages[i] = pfn_to_page(pfn + i); diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c index 2ce41f93b2a4..6c9c7de7226b 100644 --- a/arch/loongarch/kvm/exit.c +++ b/arch/loongarch/kvm/exit.c @@ -778,10 +778,8 @@ static long kvm_save_notify(struct kvm_vcpu *vcpu) return 0; default: return KVM_HCALL_INVALID_CODE; - }; - - return KVM_HCALL_INVALID_CODE; -}; + } +} /* * kvm_handle_lsx_disabled() - Guest used LSX while disabled in root. diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index 026b139dcff2..c32333695381 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -426,21 +426,26 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev, struct loongarch_eiointc *s = dev->kvm->arch.eiointc; data = (void __user *)attr->addr; - spin_lock_irqsave(&s->lock, flags); switch (type) { case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_NUM_CPU: + case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_FEATURE: if (copy_from_user(&val, data, 4)) - ret = -EFAULT; - else { - if (val >= EIOINTC_ROUTE_MAX_VCPUS) - ret = -EINVAL; - else - s->num_cpu = val; - } + return -EFAULT; + break; + default: + break; + } + + spin_lock_irqsave(&s->lock, flags); + switch (type) { + case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_NUM_CPU: + if (val >= EIOINTC_ROUTE_MAX_VCPUS) + ret = -EINVAL; + else + s->num_cpu = val; break; case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_FEATURE: - if (copy_from_user(&s->features, data, 4)) - ret = -EFAULT; + s->features = val; if (!(s->features & BIT(EIOINTC_HAS_VIRT_EXTENSION))) s->status |= BIT(EIOINTC_ENABLE); break; @@ -462,19 +467,17 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev, static int kvm_eiointc_regs_access(struct kvm_device *dev, struct kvm_device_attr *attr, - bool is_write) + bool is_write, int *data) { int addr, cpu, offset, ret = 0; unsigned long flags; void *p = NULL; - void __user *data; struct loongarch_eiointc *s; s = dev->kvm->arch.eiointc; addr = attr->attr; cpu = addr >> 16; addr &= 0xffff; - data = (void __user *)attr->addr; switch (addr) { case EIOINTC_NODETYPE_START ... EIOINTC_NODETYPE_END: offset = (addr - EIOINTC_NODETYPE_START) / 4; @@ -513,13 +516,10 @@ static int kvm_eiointc_regs_access(struct kvm_device *dev, } spin_lock_irqsave(&s->lock, flags); - if (is_write) { - if (copy_from_user(p, data, 4)) - ret = -EFAULT; - } else { - if (copy_to_user(data, p, 4)) - ret = -EFAULT; - } + if (is_write) + memcpy(p, data, 4); + else + memcpy(data, p, 4); spin_unlock_irqrestore(&s->lock, flags); return ret; @@ -527,19 +527,17 @@ static int kvm_eiointc_regs_access(struct kvm_device *dev, static int kvm_eiointc_sw_status_access(struct kvm_device *dev, struct kvm_device_attr *attr, - bool is_write) + bool is_write, int *data) { int addr, ret = 0; unsigned long flags; void *p = NULL; - void __user *data; struct loongarch_eiointc *s; s = dev->kvm->arch.eiointc; addr = attr->attr; addr &= 0xffff; - data = (void __user *)attr->addr; switch (addr) { case KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_NUM_CPU: if (is_write) @@ -561,13 +559,10 @@ static int kvm_eiointc_sw_status_access(struct kvm_device *dev, return -EINVAL; } spin_lock_irqsave(&s->lock, flags); - if (is_write) { - if (copy_from_user(p, data, 4)) - ret = -EFAULT; - } else { - if (copy_to_user(data, p, 4)) - ret = -EFAULT; - } + if (is_write) + memcpy(p, data, 4); + else + memcpy(data, p, 4); spin_unlock_irqrestore(&s->lock, flags); return ret; @@ -576,11 +571,27 @@ static int kvm_eiointc_sw_status_access(struct kvm_device *dev, static int kvm_eiointc_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { + int ret, data; + switch (attr->group) { case KVM_DEV_LOONGARCH_EXTIOI_GRP_REGS: - return kvm_eiointc_regs_access(dev, attr, false); + ret = kvm_eiointc_regs_access(dev, attr, false, &data); + if (ret) + return ret; + + if (copy_to_user((void __user *)attr->addr, &data, 4)) + ret = -EFAULT; + + return ret; case KVM_DEV_LOONGARCH_EXTIOI_GRP_SW_STATUS: - return kvm_eiointc_sw_status_access(dev, attr, false); + ret = kvm_eiointc_sw_status_access(dev, attr, false, &data); + if (ret) + return ret; + + if (copy_to_user((void __user *)attr->addr, &data, 4)) + ret = -EFAULT; + + return ret; default: return -EINVAL; } @@ -589,13 +600,21 @@ static int kvm_eiointc_get_attr(struct kvm_device *dev, static int kvm_eiointc_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { + int data; + switch (attr->group) { case KVM_DEV_LOONGARCH_EXTIOI_GRP_CTRL: return kvm_eiointc_ctrl_access(dev, attr); case KVM_DEV_LOONGARCH_EXTIOI_GRP_REGS: - return kvm_eiointc_regs_access(dev, attr, true); + if (copy_from_user(&data, (void __user *)attr->addr, 4)) + return -EFAULT; + + return kvm_eiointc_regs_access(dev, attr, true, &data); case KVM_DEV_LOONGARCH_EXTIOI_GRP_SW_STATUS: - return kvm_eiointc_sw_status_access(dev, attr, true); + if (copy_from_user(&data, (void __user *)attr->addr, 4)) + return -EFAULT; + + return kvm_eiointc_sw_status_access(dev, attr, true, &data); default: return -EINVAL; } diff --git a/arch/loongarch/kvm/intc/pch_pic.c b/arch/loongarch/kvm/intc/pch_pic.c index 119290bcea79..baf3b4faf7ea 100644 --- a/arch/loongarch/kvm/intc/pch_pic.c +++ b/arch/loongarch/kvm/intc/pch_pic.c @@ -348,6 +348,7 @@ static int kvm_pch_pic_regs_access(struct kvm_device *dev, struct kvm_device_attr *attr, bool is_write) { + char buf[8]; int addr, offset, len = 8, ret = 0; void __user *data; void *p = NULL; @@ -397,17 +398,23 @@ static int kvm_pch_pic_regs_access(struct kvm_device *dev, return -EINVAL; } - spin_lock(&s->lock); - /* write or read value according to is_write */ if (is_write) { - if (copy_from_user(p, data, len)) - ret = -EFAULT; - } else { - if (copy_to_user(data, p, len)) - ret = -EFAULT; + if (copy_from_user(buf, data, len)) + return -EFAULT; } + + spin_lock(&s->lock); + if (is_write) + memcpy(p, buf, len); + else + memcpy(buf, p, len); spin_unlock(&s->lock); + if (!is_write) { + if (copy_to_user(data, buf, len)) + return -EFAULT; + } + return ret; } diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c index ed956c5cf2cc..7c8143e79c12 100644 --- a/arch/loongarch/kvm/mmu.c +++ b/arch/loongarch/kvm/mmu.c @@ -569,7 +569,7 @@ static int kvm_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa, bool writ /* Track access to pages marked old */ new = kvm_pte_mkyoung(*ptep); if (write && !kvm_pte_dirty(new)) { - if (!kvm_pte_write(new)) { + if (!kvm_pte_writeable(new)) { ret = -EFAULT; goto out; } @@ -856,9 +856,9 @@ retry: prot_bits |= _CACHE_SUC; if (writeable) { - prot_bits |= _PAGE_WRITE; + prot_bits = kvm_pte_mkwriteable(prot_bits); if (write) - prot_bits |= __WRITEABLE; + prot_bits = kvm_pte_mkdirty(prot_bits); } /* Disable dirty logging on HugePages */ @@ -904,7 +904,7 @@ retry: kvm_release_faultin_page(kvm, page, false, writeable); spin_unlock(&kvm->mmu_lock); - if (prot_bits & _PAGE_DIRTY) + if (kvm_pte_dirty(prot_bits)) mark_page_dirty_in_slot(kvm, memslot, gfn); out: diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h index e5f57cfe1d45..025c6dcbf893 100644 --- a/arch/s390/include/asm/pci_insn.h +++ b/arch/s390/include/asm/pci_insn.h @@ -16,11 +16,11 @@ #define ZPCI_PCI_ST_FUNC_NOT_AVAIL 40 #define ZPCI_PCI_ST_ALREADY_IN_RQ_STATE 44 -/* Load/Store return codes */ -#define ZPCI_PCI_LS_OK 0 -#define ZPCI_PCI_LS_ERR 1 -#define ZPCI_PCI_LS_BUSY 2 -#define ZPCI_PCI_LS_INVAL_HANDLE 3 +/* PCI instruction condition codes */ +#define ZPCI_CC_OK 0 +#define ZPCI_CC_ERR 1 +#define ZPCI_CC_BUSY 2 +#define ZPCI_CC_INVAL_HANDLE 3 /* Load/Store address space identifiers */ #define ZPCI_PCIAS_MEMIO_0 0 diff --git a/arch/s390/kernel/kexec_elf.c b/arch/s390/kernel/kexec_elf.c index 4d364de43799..143e34a4eca5 100644 --- a/arch/s390/kernel/kexec_elf.c +++ b/arch/s390/kernel/kexec_elf.c @@ -16,7 +16,7 @@ static int kexec_file_add_kernel_elf(struct kimage *image, struct s390_load_data *data) { - struct kexec_buf buf; + struct kexec_buf buf = {}; const Elf_Ehdr *ehdr; const Elf_Phdr *phdr; Elf_Addr entry; diff --git a/arch/s390/kernel/kexec_image.c b/arch/s390/kernel/kexec_image.c index a32ce8bea745..9a439175723c 100644 --- a/arch/s390/kernel/kexec_image.c +++ b/arch/s390/kernel/kexec_image.c @@ -16,7 +16,7 @@ static int kexec_file_add_kernel_image(struct kimage *image, struct s390_load_data *data) { - struct kexec_buf buf; + struct kexec_buf buf = {}; buf.image = image; diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index c2bac14dd668..a36d7311c668 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -129,7 +129,7 @@ static int kexec_file_update_purgatory(struct kimage *image, static int kexec_file_add_purgatory(struct kimage *image, struct s390_load_data *data) { - struct kexec_buf buf; + struct kexec_buf buf = {}; int ret; buf.image = image; @@ -152,7 +152,7 @@ static int kexec_file_add_purgatory(struct kimage *image, static int kexec_file_add_initrd(struct kimage *image, struct s390_load_data *data) { - struct kexec_buf buf; + struct kexec_buf buf = {}; int ret; buf.image = image; @@ -184,7 +184,7 @@ static int kexec_file_add_ipl_report(struct kimage *image, { __u32 *lc_ipl_parmblock_ptr; unsigned int len, ncerts; - struct kexec_buf buf; + struct kexec_buf buf = {}; unsigned long addr; void *ptr, *end; int ret; diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 4d09954ebf49..04457d88e589 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -760,8 +760,6 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type) break; case PERF_TYPE_HARDWARE: - if (is_sampling_event(event)) /* No sampling support */ - return -ENOENT; ev = attr->config; if (!attr->exclude_user && attr->exclude_kernel) { /* @@ -859,6 +857,8 @@ static int cpumf_pmu_event_init(struct perf_event *event) unsigned int type = event->attr.type; int err = -ENOENT; + if (is_sampling_event(event)) /* No sampling support */ + return err; if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW) err = __hw_perf_event_init(event, type); else if (event->pmu->type == type) diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c index f373a1009c45..9455f213dc20 100644 --- a/arch/s390/kernel/perf_pai_crypto.c +++ b/arch/s390/kernel/perf_pai_crypto.c @@ -285,10 +285,10 @@ static int paicrypt_event_init(struct perf_event *event) /* PAI crypto PMU registered as PERF_TYPE_RAW, check event type */ if (a->type != PERF_TYPE_RAW && event->pmu->type != a->type) return -ENOENT; - /* PAI crypto event must be in valid range */ + /* PAI crypto event must be in valid range, try others if not */ if (a->config < PAI_CRYPTO_BASE || a->config > PAI_CRYPTO_BASE + paicrypt_cnt) - return -EINVAL; + return -ENOENT; /* Allow only CRYPTO_ALL for sampling */ if (a->sample_period && a->config != PAI_CRYPTO_BASE) return -EINVAL; diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c index d827473e7f87..7b32935273ce 100644 --- a/arch/s390/kernel/perf_pai_ext.c +++ b/arch/s390/kernel/perf_pai_ext.c @@ -265,7 +265,7 @@ static int paiext_event_valid(struct perf_event *event) event->hw.config_base = offsetof(struct paiext_cb, acc); return 0; } - return -EINVAL; + return -ENOENT; } /* Might be called on different CPU than the one the event is intended for. */ diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 2a92a8b9e4c2..9384572ffa7b 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2778,12 +2778,19 @@ static unsigned long get_ind_bit(__u64 addr, unsigned long bit_nr, bool swap) static struct page *get_map_page(struct kvm *kvm, u64 uaddr) { + struct mm_struct *mm = kvm->mm; struct page *page = NULL; + int locked = 1; + + if (mmget_not_zero(mm)) { + mmap_read_lock(mm); + get_user_pages_remote(mm, uaddr, 1, FOLL_WRITE, + &page, &locked); + if (locked) + mmap_read_unlock(mm); + mmput(mm); + } - mmap_read_lock(kvm->mm); - get_user_pages_remote(kvm->mm, uaddr, 1, FOLL_WRITE, - &page, NULL); - mmap_read_unlock(kvm->mm); return page; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index bf6fa8b9ca73..6d51aa5f66be 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4864,12 +4864,12 @@ static void kvm_s390_assert_primary_as(struct kvm_vcpu *vcpu) * @vcpu: the vCPU whose gmap is to be fixed up * @gfn: the guest frame number used for memslots (including fake memslots) * @gaddr: the gmap address, does not have to match @gfn for ucontrol gmaps - * @flags: FOLL_* flags + * @foll: FOLL_* flags * * Return: 0 on success, < 0 in case of error. * Context: The mm lock must not be held before calling. May sleep. */ -int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int flags) +int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int foll) { struct kvm_memory_slot *slot; unsigned int fault_flags; @@ -4883,13 +4883,13 @@ int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, u if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return vcpu_post_run_addressing_exception(vcpu); - fault_flags = flags & FOLL_WRITE ? FAULT_FLAG_WRITE : 0; + fault_flags = foll & FOLL_WRITE ? FAULT_FLAG_WRITE : 0; if (vcpu->arch.gmap->pfault_enabled) - flags |= FOLL_NOWAIT; + foll |= FOLL_NOWAIT; vmaddr = __gfn_to_hva_memslot(slot, gfn); try_again: - pfn = __kvm_faultin_pfn(slot, gfn, flags, &writable, &page); + pfn = __kvm_faultin_pfn(slot, gfn, foll, &writable, &page); /* Access outside memory, inject addressing exception */ if (is_noslot_pfn(pfn)) @@ -4905,7 +4905,7 @@ try_again: return 0; vcpu->stat.pfault_sync++; /* Could not setup async pfault, try again synchronously */ - flags &= ~FOLL_NOWAIT; + foll &= ~FOLL_NOWAIT; goto try_again; } /* Any other error */ @@ -4925,7 +4925,7 @@ try_again: return rc; } -static int vcpu_dat_fault_handler(struct kvm_vcpu *vcpu, unsigned long gaddr, unsigned int flags) +static int vcpu_dat_fault_handler(struct kvm_vcpu *vcpu, unsigned long gaddr, unsigned int foll) { unsigned long gaddr_tmp; gfn_t gfn; @@ -4950,18 +4950,18 @@ static int vcpu_dat_fault_handler(struct kvm_vcpu *vcpu, unsigned long gaddr, un } gfn = gpa_to_gfn(gaddr_tmp); } - return __kvm_s390_handle_dat_fault(vcpu, gfn, gaddr, flags); + return __kvm_s390_handle_dat_fault(vcpu, gfn, gaddr, foll); } static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) { - unsigned int flags = 0; + unsigned int foll = 0; unsigned long gaddr; int rc; gaddr = current->thread.gmap_teid.addr * PAGE_SIZE; if (kvm_s390_cur_gmap_fault_is_write()) - flags = FAULT_FLAG_WRITE; + foll = FOLL_WRITE; switch (current->thread.gmap_int_code & PGM_INT_CODE_MASK) { case 0: @@ -5003,7 +5003,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) send_sig(SIGSEGV, current, 0); if (rc != -ENXIO) break; - flags = FAULT_FLAG_WRITE; + foll = FOLL_WRITE; fallthrough; case PGM_PROTECTION: case PGM_SEGMENT_TRANSLATION: @@ -5013,7 +5013,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) case PGM_REGION_SECOND_TRANS: case PGM_REGION_THIRD_TRANS: kvm_s390_assert_primary_as(vcpu); - return vcpu_dat_fault_handler(vcpu, gaddr, flags); + return vcpu_dat_fault_handler(vcpu, gaddr, foll); default: KVM_BUG(1, vcpu->kvm, "Unexpected program interrupt 0x%x, TEID 0x%016lx", current->thread.gmap_int_code, current->thread.gmap_teid.val); diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 25ede8354514..6ba5a0305e25 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -624,6 +624,17 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) int cc, ret; u16 dummy; + /* Add the notifier only once. No races because we hold kvm->lock */ + if (kvm->arch.pv.mmu_notifier.ops != &kvm_s390_pv_mmu_notifier_ops) { + /* The notifier will be unregistered when the VM is destroyed */ + kvm->arch.pv.mmu_notifier.ops = &kvm_s390_pv_mmu_notifier_ops; + ret = mmu_notifier_register(&kvm->arch.pv.mmu_notifier, kvm->mm); + if (ret) { + kvm->arch.pv.mmu_notifier.ops = NULL; + return ret; + } + } + ret = kvm_s390_pv_alloc_vm(kvm); if (ret) return ret; @@ -659,11 +670,6 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) return -EIO; } kvm->arch.gmap->guest_handle = uvcb.guest_handle; - /* Add the notifier only once. No races because we hold kvm->lock */ - if (kvm->arch.pv.mmu_notifier.ops != &kvm_s390_pv_mmu_notifier_ops) { - kvm->arch.pv.mmu_notifier.ops = &kvm_s390_pv_mmu_notifier_ops; - mmu_notifier_register(&kvm->arch.pv.mmu_notifier, kvm->mm); - } return 0; } diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 60688be4e876..50eb57c976bc 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -335,7 +335,6 @@ pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, int nodat; struct mm_struct *mm = vma->vm_mm; - preempt_disable(); pgste = ptep_xchg_start(mm, addr, ptep); nodat = !!(pgste_val(pgste) & _PGSTE_GPS_NODAT); old = ptep_flush_lazy(mm, addr, ptep, nodat); @@ -360,7 +359,6 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, } else { set_pte(ptep, pte); } - preempt_enable(); } static inline void pmdp_idte_local(struct mm_struct *mm, diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c index ad8d78fb1d9a..de7867ae220d 100644 --- a/arch/um/drivers/virtio_uml.c +++ b/arch/um/drivers/virtio_uml.c @@ -1250,10 +1250,12 @@ static int virtio_uml_probe(struct platform_device *pdev) device_set_wakeup_capable(&vu_dev->vdev.dev, true); rc = register_virtio_device(&vu_dev->vdev); - if (rc) + if (rc) { put_device(&vu_dev->vdev.dev); + return rc; + } vu_dev->registered = 1; - return rc; + return 0; error_init: os_close_file(vu_dev->sock); diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c index 617886d1fb1e..21f0e50fb1df 100644 --- a/arch/um/os-Linux/file.c +++ b/arch/um/os-Linux/file.c @@ -535,7 +535,7 @@ ssize_t os_rcv_fd_msg(int fd, int *fds, unsigned int n_fds, cmsg->cmsg_type != SCM_RIGHTS) return n; - memcpy(fds, CMSG_DATA(cmsg), cmsg->cmsg_len); + memcpy(fds, CMSG_DATA(cmsg), cmsg->cmsg_len - CMSG_LEN(0)); return n; } diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c index 4193e04d7e4a..e3ad71a0d13c 100644 --- a/arch/um/os-Linux/util.c +++ b/arch/um/os-Linux/util.c @@ -20,8 +20,7 @@ void stack_protections(unsigned long address) { - if (mprotect((void *) address, UM_THREAD_SIZE, - PROT_READ | PROT_WRITE | PROT_EXEC) < 0) + if (mprotect((void *) address, UM_THREAD_SIZE, PROT_READ | PROT_WRITE) < 0) panic("protecting stack failed, errno = %d", errno); } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 58d890fe2100..52c8910ba2ef 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2701,6 +2701,15 @@ config MITIGATION_TSA security vulnerability on AMD CPUs which can lead to forwarding of invalid info to subsequent instructions and thus can affect their timing and thereby cause a leakage. + +config MITIGATION_VMSCAPE + bool "Mitigate VMSCAPE" + depends on KVM + default y + help + Enable mitigation for VMSCAPE attacks. VMSCAPE is a hardware security + vulnerability on Intel and AMD CPUs that may allow a guest to do + Spectre v2 style attacks on userspace hypervisor. endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 06fc0479a23f..751ca35386b0 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -495,6 +495,7 @@ #define X86_FEATURE_TSA_SQ_NO (21*32+11) /* AMD CPU not vulnerable to TSA-SQ */ #define X86_FEATURE_TSA_L1_NO (21*32+12) /* AMD CPU not vulnerable to TSA-L1 */ #define X86_FEATURE_CLEAR_CPU_BUF_VM (21*32+13) /* Clear CPU buffers using VERW before VMRUN */ +#define X86_FEATURE_IBPB_EXIT_TO_USER (21*32+14) /* Use IBPB on exit-to-userspace, see VMSCAPE bug */ /* * BUG word(s) @@ -551,4 +552,5 @@ #define X86_BUG_ITS X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */ #define X86_BUG_ITS_NATIVE_ONLY X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */ #define X86_BUG_TSA X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */ +#define X86_BUG_VMSCAPE X86_BUG( 1*32+10) /* "vmscape" CPU is affected by VMSCAPE attacks from guests */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index d535a97c7284..ce3eb6d5fdf9 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -93,6 +93,13 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, * 8 (ia32) bits. */ choose_random_kstack_offset(rdtsc()); + + /* Avoid unnecessary reads of 'x86_ibpb_exit_to_user' */ + if (cpu_feature_enabled(X86_FEATURE_IBPB_EXIT_TO_USER) && + this_cpu_read(x86_ibpb_exit_to_user)) { + indirect_branch_prediction_barrier(); + this_cpu_write(x86_ibpb_exit_to_user, false); + } } #define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 10f261678749..e29f82466f43 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -530,6 +530,8 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) : "memory"); } +DECLARE_PER_CPU(bool, x86_ibpb_exit_to_user); + static inline void indirect_branch_prediction_barrier(void) { asm_inline volatile(ALTERNATIVE("", "call write_ibpb", X86_FEATURE_IBPB) diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 02236962fdb1..465b19fd1a2d 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -562,6 +562,24 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, extern struct ghcb *boot_ghcb; +static inline void sev_evict_cache(void *va, int npages) +{ + volatile u8 val __always_unused; + u8 *bytes = va; + int page_idx; + + /* + * For SEV guests, a read from the first/last cache-lines of a 4K page + * using the guest key is sufficient to cause a flush of all cache-lines + * associated with that 4K page without incurring all the overhead of a + * full CLFLUSH sequence. + */ + for (page_idx = 0; page_idx < npages; page_idx++) { + val = bytes[page_idx * PAGE_SIZE]; + val = bytes[page_idx * PAGE_SIZE + PAGE_SIZE - 1]; + } +} + #else /* !CONFIG_AMD_MEM_ENCRYPT */ #define snp_vmpl 0 @@ -605,6 +623,7 @@ static inline int snp_send_guest_request(struct snp_msg_desc *mdesc, static inline int snp_svsm_vtpm_send_command(u8 *buffer) { return -ENODEV; } static inline void __init snp_secure_tsc_prepare(void) { } static inline void __init snp_secure_tsc_init(void) { } +static inline void sev_evict_cache(void *va, int npages) {} #endif /* CONFIG_AMD_MEM_ENCRYPT */ @@ -619,24 +638,6 @@ int rmp_make_shared(u64 pfn, enum pg_level level); void snp_leak_pages(u64 pfn, unsigned int npages); void kdump_sev_callback(void); void snp_fixup_e820_tables(void); - -static inline void sev_evict_cache(void *va, int npages) -{ - volatile u8 val __always_unused; - u8 *bytes = va; - int page_idx; - - /* - * For SEV guests, a read from the first/last cache-lines of a 4K page - * using the guest key is sufficient to cause a flush of all cache-lines - * associated with that 4K page without incurring all the overhead of a - * full CLFLUSH sequence. - */ - for (page_idx = 0; page_idx < npages; page_idx++) { - val = bytes[page_idx * PAGE_SIZE]; - val = bytes[page_idx * PAGE_SIZE + PAGE_SIZE - 1]; - } -} #else static inline bool snp_probe_rmptable_info(void) { return false; } static inline int snp_rmptable_init(void) { return -ENOSYS; } @@ -652,7 +653,6 @@ static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV static inline void snp_leak_pages(u64 pfn, unsigned int npages) {} static inline void kdump_sev_callback(void) { } static inline void snp_fixup_e820_tables(void) {} -static inline void sev_evict_cache(void *va, int npages) {} #endif #endif diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index af838b8d845c..36dcfc5105be 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -96,6 +96,9 @@ static void __init its_update_mitigation(void); static void __init its_apply_mitigation(void); static void __init tsa_select_mitigation(void); static void __init tsa_apply_mitigation(void); +static void __init vmscape_select_mitigation(void); +static void __init vmscape_update_mitigation(void); +static void __init vmscape_apply_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -105,6 +108,14 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); DEFINE_PER_CPU(u64, x86_spec_ctrl_current); EXPORT_PER_CPU_SYMBOL_GPL(x86_spec_ctrl_current); +/* + * Set when the CPU has run a potentially malicious guest. An IBPB will + * be needed to before running userspace. That IBPB will flush the branch + * predictor content. + */ +DEFINE_PER_CPU(bool, x86_ibpb_exit_to_user); +EXPORT_PER_CPU_SYMBOL_GPL(x86_ibpb_exit_to_user); + u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; static u64 __ro_after_init x86_arch_cap_msr; @@ -262,6 +273,7 @@ void __init cpu_select_mitigations(void) its_select_mitigation(); bhi_select_mitigation(); tsa_select_mitigation(); + vmscape_select_mitigation(); /* * After mitigations are selected, some may need to update their @@ -293,6 +305,7 @@ void __init cpu_select_mitigations(void) bhi_update_mitigation(); /* srso_update_mitigation() depends on retbleed_update_mitigation(). */ srso_update_mitigation(); + vmscape_update_mitigation(); spectre_v1_apply_mitigation(); spectre_v2_apply_mitigation(); @@ -310,6 +323,7 @@ void __init cpu_select_mitigations(void) its_apply_mitigation(); bhi_apply_mitigation(); tsa_apply_mitigation(); + vmscape_apply_mitigation(); } /* @@ -2538,88 +2552,6 @@ static void update_mds_branch_idle(void) } } -#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n" -#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" -#define MMIO_MSG_SMT "MMIO Stale Data CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/processor_mmio_stale_data.html for more details.\n" - -void cpu_bugs_smt_update(void) -{ - mutex_lock(&spec_ctrl_mutex); - - if (sched_smt_active() && unprivileged_ebpf_enabled() && - spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) - pr_warn_once(SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG); - - switch (spectre_v2_user_stibp) { - case SPECTRE_V2_USER_NONE: - break; - case SPECTRE_V2_USER_STRICT: - case SPECTRE_V2_USER_STRICT_PREFERRED: - update_stibp_strict(); - break; - case SPECTRE_V2_USER_PRCTL: - case SPECTRE_V2_USER_SECCOMP: - update_indir_branch_cond(); - break; - } - - switch (mds_mitigation) { - case MDS_MITIGATION_FULL: - case MDS_MITIGATION_AUTO: - case MDS_MITIGATION_VMWERV: - if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY)) - pr_warn_once(MDS_MSG_SMT); - update_mds_branch_idle(); - break; - case MDS_MITIGATION_OFF: - break; - } - - switch (taa_mitigation) { - case TAA_MITIGATION_VERW: - case TAA_MITIGATION_AUTO: - case TAA_MITIGATION_UCODE_NEEDED: - if (sched_smt_active()) - pr_warn_once(TAA_MSG_SMT); - break; - case TAA_MITIGATION_TSX_DISABLED: - case TAA_MITIGATION_OFF: - break; - } - - switch (mmio_mitigation) { - case MMIO_MITIGATION_VERW: - case MMIO_MITIGATION_AUTO: - case MMIO_MITIGATION_UCODE_NEEDED: - if (sched_smt_active()) - pr_warn_once(MMIO_MSG_SMT); - break; - case MMIO_MITIGATION_OFF: - break; - } - - switch (tsa_mitigation) { - case TSA_MITIGATION_USER_KERNEL: - case TSA_MITIGATION_VM: - case TSA_MITIGATION_AUTO: - case TSA_MITIGATION_FULL: - /* - * TSA-SQ can potentially lead to info leakage between - * SMT threads. - */ - if (sched_smt_active()) - static_branch_enable(&cpu_buf_idle_clear); - else - static_branch_disable(&cpu_buf_idle_clear); - break; - case TSA_MITIGATION_NONE: - case TSA_MITIGATION_UCODE_NEEDED: - break; - } - - mutex_unlock(&spec_ctrl_mutex); -} - #undef pr_fmt #define pr_fmt(fmt) "Speculative Store Bypass: " fmt @@ -3331,8 +3263,184 @@ static void __init srso_apply_mitigation(void) } #undef pr_fmt +#define pr_fmt(fmt) "VMSCAPE: " fmt + +enum vmscape_mitigations { + VMSCAPE_MITIGATION_NONE, + VMSCAPE_MITIGATION_AUTO, + VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER, + VMSCAPE_MITIGATION_IBPB_ON_VMEXIT, +}; + +static const char * const vmscape_strings[] = { + [VMSCAPE_MITIGATION_NONE] = "Vulnerable", + /* [VMSCAPE_MITIGATION_AUTO] */ + [VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER] = "Mitigation: IBPB before exit to userspace", + [VMSCAPE_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT", +}; + +static enum vmscape_mitigations vmscape_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_VMSCAPE) ? VMSCAPE_MITIGATION_AUTO : VMSCAPE_MITIGATION_NONE; + +static int __init vmscape_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) { + vmscape_mitigation = VMSCAPE_MITIGATION_NONE; + } else if (!strcmp(str, "ibpb")) { + vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER; + } else if (!strcmp(str, "force")) { + setup_force_cpu_bug(X86_BUG_VMSCAPE); + vmscape_mitigation = VMSCAPE_MITIGATION_AUTO; + } else { + pr_err("Ignoring unknown vmscape=%s option.\n", str); + } + + return 0; +} +early_param("vmscape", vmscape_parse_cmdline); + +static void __init vmscape_select_mitigation(void) +{ + if (cpu_mitigations_off() || + !boot_cpu_has_bug(X86_BUG_VMSCAPE) || + !boot_cpu_has(X86_FEATURE_IBPB)) { + vmscape_mitigation = VMSCAPE_MITIGATION_NONE; + return; + } + + if (vmscape_mitigation == VMSCAPE_MITIGATION_AUTO) + vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER; +} + +static void __init vmscape_update_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_VMSCAPE)) + return; + + if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB || + srso_mitigation == SRSO_MITIGATION_IBPB_ON_VMEXIT) + vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_ON_VMEXIT; + + pr_info("%s\n", vmscape_strings[vmscape_mitigation]); +} + +static void __init vmscape_apply_mitigation(void) +{ + if (vmscape_mitigation == VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER) + setup_force_cpu_cap(X86_FEATURE_IBPB_EXIT_TO_USER); +} + +#undef pr_fmt #define pr_fmt(fmt) fmt +#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n" +#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" +#define MMIO_MSG_SMT "MMIO Stale Data CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/processor_mmio_stale_data.html for more details.\n" +#define VMSCAPE_MSG_SMT "VMSCAPE: SMT on, STIBP is required for full protection. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/vmscape.html for more details.\n" + +void cpu_bugs_smt_update(void) +{ + mutex_lock(&spec_ctrl_mutex); + + if (sched_smt_active() && unprivileged_ebpf_enabled() && + spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) + pr_warn_once(SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG); + + switch (spectre_v2_user_stibp) { + case SPECTRE_V2_USER_NONE: + break; + case SPECTRE_V2_USER_STRICT: + case SPECTRE_V2_USER_STRICT_PREFERRED: + update_stibp_strict(); + break; + case SPECTRE_V2_USER_PRCTL: + case SPECTRE_V2_USER_SECCOMP: + update_indir_branch_cond(); + break; + } + + switch (mds_mitigation) { + case MDS_MITIGATION_FULL: + case MDS_MITIGATION_AUTO: + case MDS_MITIGATION_VMWERV: + if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY)) + pr_warn_once(MDS_MSG_SMT); + update_mds_branch_idle(); + break; + case MDS_MITIGATION_OFF: + break; + } + + switch (taa_mitigation) { + case TAA_MITIGATION_VERW: + case TAA_MITIGATION_AUTO: + case TAA_MITIGATION_UCODE_NEEDED: + if (sched_smt_active()) + pr_warn_once(TAA_MSG_SMT); + break; + case TAA_MITIGATION_TSX_DISABLED: + case TAA_MITIGATION_OFF: + break; + } + + switch (mmio_mitigation) { + case MMIO_MITIGATION_VERW: + case MMIO_MITIGATION_AUTO: + case MMIO_MITIGATION_UCODE_NEEDED: + if (sched_smt_active()) + pr_warn_once(MMIO_MSG_SMT); + break; + case MMIO_MITIGATION_OFF: + break; + } + + switch (tsa_mitigation) { + case TSA_MITIGATION_USER_KERNEL: + case TSA_MITIGATION_VM: + case TSA_MITIGATION_AUTO: + case TSA_MITIGATION_FULL: + /* + * TSA-SQ can potentially lead to info leakage between + * SMT threads. + */ + if (sched_smt_active()) + static_branch_enable(&cpu_buf_idle_clear); + else + static_branch_disable(&cpu_buf_idle_clear); + break; + case TSA_MITIGATION_NONE: + case TSA_MITIGATION_UCODE_NEEDED: + break; + } + + switch (vmscape_mitigation) { + case VMSCAPE_MITIGATION_NONE: + case VMSCAPE_MITIGATION_AUTO: + break; + case VMSCAPE_MITIGATION_IBPB_ON_VMEXIT: + case VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER: + /* + * Hypervisors can be attacked across-threads, warn for SMT when + * STIBP is not already enabled system-wide. + * + * Intel eIBRS (!AUTOIBRS) implies STIBP on. + */ + if (!sched_smt_active() || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED || + (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && + !boot_cpu_has(X86_FEATURE_AUTOIBRS))) + break; + pr_warn_once(VMSCAPE_MSG_SMT); + break; + } + + mutex_unlock(&spec_ctrl_mutex); +} + #ifdef CONFIG_SYSFS #define L1TF_DEFAULT_MSG "Mitigation: PTE Inversion" @@ -3578,6 +3686,11 @@ static ssize_t tsa_show_state(char *buf) return sysfs_emit(buf, "%s\n", tsa_strings[tsa_mitigation]); } +static ssize_t vmscape_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", vmscape_strings[vmscape_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -3644,6 +3757,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_TSA: return tsa_show_state(buf); + case X86_BUG_VMSCAPE: + return vmscape_show_state(buf); + default: break; } @@ -3735,6 +3851,11 @@ ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *bu { return cpu_show_common(dev, attr, buf, X86_BUG_TSA); } + +ssize_t cpu_show_vmscape(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_VMSCAPE); +} #endif void __warn_thunk(void) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 34a054181c4d..f98ec9c7fc07 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1236,55 +1236,71 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define ITS_NATIVE_ONLY BIT(9) /* CPU is affected by Transient Scheduler Attacks */ #define TSA BIT(10) +/* CPU is affected by VMSCAPE */ +#define VMSCAPE BIT(11) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { - VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS), - VULNBL_INTEL_STEPS(INTEL_HASWELL, X86_STEP_MAX, SRBDS), - VULNBL_INTEL_STEPS(INTEL_HASWELL_L, X86_STEP_MAX, SRBDS), - VULNBL_INTEL_STEPS(INTEL_HASWELL_G, X86_STEP_MAX, SRBDS), - VULNBL_INTEL_STEPS(INTEL_HASWELL_X, X86_STEP_MAX, MMIO), - VULNBL_INTEL_STEPS(INTEL_BROADWELL_D, X86_STEP_MAX, MMIO), - VULNBL_INTEL_STEPS(INTEL_BROADWELL_G, X86_STEP_MAX, SRBDS), - VULNBL_INTEL_STEPS(INTEL_BROADWELL_X, X86_STEP_MAX, MMIO), - VULNBL_INTEL_STEPS(INTEL_BROADWELL, X86_STEP_MAX, SRBDS), - VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, 0x5, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS), - VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPS(INTEL_SKYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, 0xb, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS), - VULNBL_INTEL_STEPS(INTEL_KABYLAKE, 0xc, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS), - VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L, X86_STEP_MAX, RETBLEED), + VULNBL_INTEL_STEPS(INTEL_SANDYBRIDGE_X, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_SANDYBRIDGE, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE_X, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_HASWELL, X86_STEP_MAX, SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_HASWELL_L, X86_STEP_MAX, SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_HASWELL_G, X86_STEP_MAX, SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_HASWELL_X, X86_STEP_MAX, MMIO | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_BROADWELL_D, X86_STEP_MAX, MMIO | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_BROADWELL_X, X86_STEP_MAX, MMIO | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_BROADWELL_G, X86_STEP_MAX, SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_BROADWELL, X86_STEP_MAX, SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, 0x5, MMIO | RETBLEED | GDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, 0xb, MMIO | RETBLEED | GDS | SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE, 0xc, MMIO | RETBLEED | GDS | SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L, X86_STEP_MAX, RETBLEED | VMSCAPE), VULNBL_INTEL_STEPS(INTEL_ICELAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY), VULNBL_INTEL_STEPS(INTEL_ICELAKE_D, X86_STEP_MAX, MMIO | GDS | ITS | ITS_NATIVE_ONLY), VULNBL_INTEL_STEPS(INTEL_ICELAKE_X, X86_STEP_MAX, MMIO | GDS | ITS | ITS_NATIVE_ONLY), - VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS), - VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED | ITS), - VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED | ITS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | VMSCAPE), VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L, X86_STEP_MAX, GDS | ITS | ITS_NATIVE_ONLY), VULNBL_INTEL_STEPS(INTEL_TIGERLAKE, X86_STEP_MAX, GDS | ITS | ITS_NATIVE_ONLY), VULNBL_INTEL_STEPS(INTEL_LAKEFIELD, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED), VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY), - VULNBL_INTEL_TYPE(INTEL_ALDERLAKE, ATOM, RFDS), - VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L, X86_STEP_MAX, RFDS), - VULNBL_INTEL_TYPE(INTEL_RAPTORLAKE, ATOM, RFDS), - VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_P, X86_STEP_MAX, RFDS), - VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_S, X86_STEP_MAX, RFDS), - VULNBL_INTEL_STEPS(INTEL_ATOM_GRACEMONT, X86_STEP_MAX, RFDS), + VULNBL_INTEL_TYPE(INTEL_ALDERLAKE, ATOM, RFDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_ALDERLAKE, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L, X86_STEP_MAX, RFDS | VMSCAPE), + VULNBL_INTEL_TYPE(INTEL_RAPTORLAKE, ATOM, RFDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_P, X86_STEP_MAX, RFDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_S, X86_STEP_MAX, RFDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_METEORLAKE_L, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_ARROWLAKE_H, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_ARROWLAKE, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_ARROWLAKE_U, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_LUNARLAKE_M, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_SAPPHIRERAPIDS_X, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_GRANITERAPIDS_X, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_EMERALDRAPIDS_X, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_ATOM_GRACEMONT, X86_STEP_MAX, RFDS | VMSCAPE), VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT, X86_STEP_MAX, MMIO | MMIO_SBDS | RFDS), VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT_D, X86_STEP_MAX, MMIO | RFDS), VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RFDS), VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT, X86_STEP_MAX, RFDS), VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT_D, X86_STEP_MAX, RFDS), VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT_PLUS, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_ATOM_CRESTMONT_X, X86_STEP_MAX, VMSCAPE), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), - VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO), - VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO), - VULNBL_AMD(0x19, SRSO | TSA), - VULNBL_AMD(0x1a, SRSO), + VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO | VMSCAPE), + VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO | VMSCAPE), + VULNBL_AMD(0x19, SRSO | TSA | VMSCAPE), + VULNBL_AMD(0x1a, SRSO | VMSCAPE), {} }; @@ -1543,6 +1559,14 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) } } + /* + * Set the bug only on bare-metal. A nested hypervisor should already be + * deploying IBPB to isolate itself from nested guests. + */ + if (cpu_matches(cpu_vuln_blacklist, VMSCAPE) && + !boot_cpu_has(X86_FEATURE_HYPERVISOR)) + setup_force_cpu_bug(X86_BUG_VMSCAPE); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c index 827dd0dbb6e9..c79ebbb639cb 100644 --- a/arch/x86/kernel/cpu/topology_amd.c +++ b/arch/x86/kernel/cpu/topology_amd.c @@ -175,27 +175,30 @@ static void topoext_fixup(struct topo_scan *tscan) static void parse_topology_amd(struct topo_scan *tscan) { - bool has_topoext = false; - /* - * If the extended topology leaf 0x8000_001e is available - * try to get SMT, CORE, TILE, and DIE shifts from extended + * Try to get SMT, CORE, TILE, and DIE shifts from extended * CPUID leaf 0x8000_0026 on supported processors first. If * extended CPUID leaf 0x8000_0026 is not supported, try to - * get SMT and CORE shift from leaf 0xb first, then try to - * get the CORE shift from leaf 0x8000_0008. + * get SMT and CORE shift from leaf 0xb. If either leaf is + * available, cpu_parse_topology_ext() will return true. */ - if (cpu_feature_enabled(X86_FEATURE_TOPOEXT)) - has_topoext = cpu_parse_topology_ext(tscan); + bool has_xtopology = cpu_parse_topology_ext(tscan); if (cpu_feature_enabled(X86_FEATURE_AMD_HTR_CORES)) tscan->c->topo.cpu_type = cpuid_ebx(0x80000026); - if (!has_topoext && !parse_8000_0008(tscan)) + /* + * If XTOPOLOGY leaves (0x26/0xb) are not available, try to + * get the CORE shift from leaf 0x8000_0008 first. + */ + if (!has_xtopology && !parse_8000_0008(tscan)) return; - /* Prefer leaf 0x8000001e if available */ - if (parse_8000_001e(tscan, has_topoext)) + /* + * Prefer leaf 0x8000001e if available to get the SMT shift and + * the initial APIC ID if XTOPOLOGY leaves are not available. + */ + if (parse_8000_001e(tscan, has_xtopology)) return; /* Try the NODEID MSR */ diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index d9931c6c4bc6..1bfebe40854f 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4046,8 +4046,7 @@ static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); u64 cr8; - if (nested_svm_virtualize_tpr(vcpu) || - kvm_vcpu_apicv_active(vcpu)) + if (nested_svm_virtualize_tpr(vcpu)) return; cr8 = kvm_get_cr8(vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 604490b1cb19..706b6fd56d3c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11011,6 +11011,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) wrmsrq(MSR_IA32_XFD_ERR, 0); /* + * Mark this CPU as needing a branch predictor flush before running + * userspace. Must be done before enabling preemption to ensure it gets + * set for the CPU that actually ran the guest, and not the CPU that it + * may migrate to. + */ + if (cpu_feature_enabled(X86_FEATURE_IBPB_EXIT_TO_USER)) + this_cpu_write(x86_ibpb_exit_to_user, true); + + /* * Consume any pending interrupts, including the possible source of * VM-Exit on SVM and any ticks that occur between VM-Exit and now. * An instruction is required after local_irq_enable() to fully unblock diff --git a/block/fops.c b/block/fops.c index 82451ac8ff25..ddbc69c0922b 100644 --- a/block/fops.c +++ b/block/fops.c @@ -7,6 +7,7 @@ #include <linux/init.h> #include <linux/mm.h> #include <linux/blkdev.h> +#include <linux/blk-integrity.h> #include <linux/buffer_head.h> #include <linux/mpage.h> #include <linux/uio.h> @@ -54,7 +55,6 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, struct bio bio; ssize_t ret; - WARN_ON_ONCE(iocb->ki_flags & IOCB_HAS_METADATA); if (nr_pages <= DIO_INLINE_BIO_VECS) vecs = inline_vecs; else { @@ -131,7 +131,7 @@ static void blkdev_bio_end_io(struct bio *bio) if (bio->bi_status && !dio->bio.bi_status) dio->bio.bi_status = bio->bi_status; - if (!is_sync && (dio->iocb->ki_flags & IOCB_HAS_METADATA)) + if (bio_integrity(bio)) bio_integrity_unmap_user(bio); if (atomic_dec_and_test(&dio->ref)) { @@ -233,7 +233,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, } bio->bi_opf |= REQ_NOWAIT; } - if (!is_sync && (iocb->ki_flags & IOCB_HAS_METADATA)) { + if (iocb->ki_flags & IOCB_HAS_METADATA) { ret = bio_integrity_map_iter(bio, iocb->private); if (unlikely(ret)) goto fail; @@ -301,7 +301,7 @@ static void blkdev_bio_end_io_async(struct bio *bio) ret = blk_status_to_errno(bio->bi_status); } - if (iocb->ki_flags & IOCB_HAS_METADATA) + if (bio_integrity(bio)) bio_integrity_unmap_user(bio); iocb->ki_complete(iocb, ret); @@ -422,7 +422,8 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1); - if (likely(nr_pages <= BIO_MAX_VECS)) { + if (likely(nr_pages <= BIO_MAX_VECS && + !(iocb->ki_flags & IOCB_HAS_METADATA))) { if (is_sync_kiocb(iocb)) return __blkdev_direct_IO_simple(iocb, iter, bdev, nr_pages); @@ -687,6 +688,8 @@ static int blkdev_open(struct inode *inode, struct file *filp) if (bdev_can_atomic_write(bdev)) filp->f_mode |= FMODE_CAN_ATOMIC_WRITE; + if (blk_get_integrity(bdev->bd_disk)) + filp->f_mode |= FMODE_HAS_METADATA; ret = bdev_open(bdev, mode, filp->private_data, NULL, filp); if (ret) diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 0da7c1ac778a..ca6fdcc6c54a 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -970,6 +970,12 @@ int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size, } lock_sock(sk); + if (ctx->write) { + release_sock(sk); + return -EBUSY; + } + ctx->write = true; + if (ctx->init && !ctx->more) { if (ctx->used) { err = -EINVAL; @@ -1019,6 +1025,8 @@ int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size, continue; } + ctx->merge = 0; + if (!af_alg_writable(sk)) { err = af_alg_wait_for_wmem(sk, msg->msg_flags); if (err) @@ -1058,7 +1066,6 @@ int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size, ctx->used += plen; copied += plen; size -= plen; - ctx->merge = 0; } else { do { struct page *pg; @@ -1104,6 +1111,7 @@ int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size, unlock: af_alg_data_wakeup(sk); + ctx->write = false; release_sock(sk); return copied ?: err; diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index efc575a00edd..008da0354fba 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -603,6 +603,7 @@ CPU_SHOW_VULN_FALLBACK(ghostwrite); CPU_SHOW_VULN_FALLBACK(old_microcode); CPU_SHOW_VULN_FALLBACK(indirect_target_selection); CPU_SHOW_VULN_FALLBACK(tsa); +CPU_SHOW_VULN_FALLBACK(vmscape); static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); @@ -622,6 +623,7 @@ static DEVICE_ATTR(ghostwrite, 0444, cpu_show_ghostwrite, NULL); static DEVICE_ATTR(old_microcode, 0444, cpu_show_old_microcode, NULL); static DEVICE_ATTR(indirect_target_selection, 0444, cpu_show_indirect_target_selection, NULL); static DEVICE_ATTR(tsa, 0444, cpu_show_tsa, NULL); +static DEVICE_ATTR(vmscape, 0444, cpu_show_vmscape, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -642,6 +644,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_old_microcode.attr, &dev_attr_indirect_target_selection.attr, &dev_attr_tsa.attr, + &dev_attr_vmscape.attr, NULL }; diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index e09930c2b226..91f3b8afb63c 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -1330,6 +1330,7 @@ void drbd_reconsider_queue_parameters(struct drbd_device *device, lim.max_write_zeroes_sectors = DRBD_MAX_BBIO_SECTORS; else lim.max_write_zeroes_sectors = 0; + lim.max_hw_wzeroes_unmap_sectors = 0; if ((lim.discard_granularity >> SECTOR_SHIFT) > lim.max_hw_discard_sectors) { diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 8acad3cc6e6e..f31652085adc 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1795,6 +1795,7 @@ static int write_same_filled_page(struct zram *zram, unsigned long fill, u32 index) { zram_slot_lock(zram, index); + zram_free_page(zram, index); zram_set_flag(zram, index, ZRAM_SAME); zram_set_handle(zram, index, fill); zram_slot_unlock(zram, index); @@ -1832,6 +1833,7 @@ static int write_incompressible_page(struct zram *zram, struct page *page, kunmap_local(src); zram_slot_lock(zram, index); + zram_free_page(zram, index); zram_set_flag(zram, index, ZRAM_HUGE); zram_set_handle(zram, index, handle); zram_set_obj_size(zram, index, PAGE_SIZE); @@ -1855,11 +1857,6 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index) unsigned long element; bool same_filled; - /* First, free memory allocated to this slot (if any) */ - zram_slot_lock(zram, index); - zram_free_page(zram, index); - zram_slot_unlock(zram, index); - mem = kmap_local_page(page); same_filled = page_same_filled(mem, &element); kunmap_local(mem); @@ -1901,6 +1898,7 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index) zcomp_stream_put(zstrm); zram_slot_lock(zram, index); + zram_free_page(zram, index); zram_set_handle(zram, index, handle); zram_set_obj_size(zram, index, comp_len); zram_slot_unlock(zram, index); diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index bbc27ef9edf7..b4c79fde1979 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -1554,13 +1554,15 @@ static void amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy) pr_debug("CPU %d exiting\n", policy->cpu); } -static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy) +static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy, bool policy_change) { struct amd_cpudata *cpudata = policy->driver_data; union perf_cached perf; u8 epp; - if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq) + if (policy_change || + policy->min != cpudata->min_limit_freq || + policy->max != cpudata->max_limit_freq) amd_pstate_update_min_max_limit(policy); if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) @@ -1584,7 +1586,7 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy) cpudata->policy = policy->policy; - ret = amd_pstate_epp_update_limit(policy); + ret = amd_pstate_epp_update_limit(policy, true); if (ret) return ret; @@ -1626,13 +1628,14 @@ static int amd_pstate_suspend(struct cpufreq_policy *policy) * min_perf value across kexec reboots. If this CPU is just resumed back without kexec, * the limits, epp and desired perf will get reset to the cached values in cpudata struct */ - ret = amd_pstate_update_perf(policy, perf.bios_min_perf, 0U, 0U, 0U, false); + ret = amd_pstate_update_perf(policy, perf.bios_min_perf, + FIELD_GET(AMD_CPPC_DES_PERF_MASK, cpudata->cppc_req_cached), + FIELD_GET(AMD_CPPC_MAX_PERF_MASK, cpudata->cppc_req_cached), + FIELD_GET(AMD_CPPC_EPP_PERF_MASK, cpudata->cppc_req_cached), + false); if (ret) return ret; - /* invalidate to ensure it's rewritten during resume */ - cpudata->cppc_req_cached = 0; - /* set this flag to avoid setting core offline*/ cpudata->suspended = true; @@ -1658,7 +1661,7 @@ static int amd_pstate_epp_resume(struct cpufreq_policy *policy) int ret; /* enable amd pstate from suspend state*/ - ret = amd_pstate_epp_update_limit(policy); + ret = amd_pstate_epp_update_limit(policy, false); if (ret) return ret; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index f366d35c5840..0d5d283a5429 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1034,8 +1034,8 @@ static bool hybrid_register_perf_domain(unsigned int cpu) if (!cpu_dev) return false; - if (em_dev_register_perf_domain(cpu_dev, HYBRID_EM_STATE_COUNT, &cb, - cpumask_of(cpu), false)) + if (em_dev_register_pd_no_update(cpu_dev, HYBRID_EM_STATE_COUNT, &cb, + cpumask_of(cpu), false)) return false; cpudata->pd_registered = true; diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index e058ba027792..9f5ccc1720cb 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -2430,7 +2430,7 @@ static void __sev_firmware_shutdown(struct sev_device *sev, bool panic) { int error; - __sev_platform_shutdown_locked(NULL); + __sev_platform_shutdown_locked(&error); if (sev_es_tmr) { /* diff --git a/drivers/dma/dw/rzn1-dmamux.c b/drivers/dma/dw/rzn1-dmamux.c index 4fb8508419db..deadf135681b 100644 --- a/drivers/dma/dw/rzn1-dmamux.c +++ b/drivers/dma/dw/rzn1-dmamux.c @@ -48,12 +48,16 @@ static void *rzn1_dmamux_route_allocate(struct of_phandle_args *dma_spec, u32 mask; int ret; - if (dma_spec->args_count != RNZ1_DMAMUX_NCELLS) - return ERR_PTR(-EINVAL); + if (dma_spec->args_count != RNZ1_DMAMUX_NCELLS) { + ret = -EINVAL; + goto put_device; + } map = kzalloc(sizeof(*map), GFP_KERNEL); - if (!map) - return ERR_PTR(-ENOMEM); + if (!map) { + ret = -ENOMEM; + goto put_device; + } chan = dma_spec->args[0]; map->req_idx = dma_spec->args[4]; @@ -94,12 +98,15 @@ static void *rzn1_dmamux_route_allocate(struct of_phandle_args *dma_spec, if (ret) goto clear_bitmap; + put_device(&pdev->dev); return map; clear_bitmap: clear_bit(map->req_idx, dmamux->used_chans); free_map: kfree(map); +put_device: + put_device(&pdev->dev); return ERR_PTR(ret); } diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 35bdefd3728b..8c4725ad1f64 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -189,27 +189,30 @@ static int idxd_setup_wqs(struct idxd_device *idxd) idxd->wq_enable_map = bitmap_zalloc_node(idxd->max_wqs, GFP_KERNEL, dev_to_node(dev)); if (!idxd->wq_enable_map) { rc = -ENOMEM; - goto err_bitmap; + goto err_free_wqs; } for (i = 0; i < idxd->max_wqs; i++) { wq = kzalloc_node(sizeof(*wq), GFP_KERNEL, dev_to_node(dev)); if (!wq) { rc = -ENOMEM; - goto err; + goto err_unwind; } idxd_dev_set_type(&wq->idxd_dev, IDXD_DEV_WQ); conf_dev = wq_confdev(wq); wq->id = i; wq->idxd = idxd; - device_initialize(wq_confdev(wq)); + device_initialize(conf_dev); conf_dev->parent = idxd_confdev(idxd); conf_dev->bus = &dsa_bus_type; conf_dev->type = &idxd_wq_device_type; rc = dev_set_name(conf_dev, "wq%d.%d", idxd->id, wq->id); - if (rc < 0) - goto err; + if (rc < 0) { + put_device(conf_dev); + kfree(wq); + goto err_unwind; + } mutex_init(&wq->wq_lock); init_waitqueue_head(&wq->err_queue); @@ -220,15 +223,20 @@ static int idxd_setup_wqs(struct idxd_device *idxd) wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES; wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev)); if (!wq->wqcfg) { + put_device(conf_dev); + kfree(wq); rc = -ENOMEM; - goto err; + goto err_unwind; } if (idxd->hw.wq_cap.op_config) { wq->opcap_bmap = bitmap_zalloc(IDXD_MAX_OPCAP_BITS, GFP_KERNEL); if (!wq->opcap_bmap) { + kfree(wq->wqcfg); + put_device(conf_dev); + kfree(wq); rc = -ENOMEM; - goto err_opcap_bmap; + goto err_unwind; } bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS); } @@ -239,13 +247,7 @@ static int idxd_setup_wqs(struct idxd_device *idxd) return 0; -err_opcap_bmap: - kfree(wq->wqcfg); - -err: - put_device(conf_dev); - kfree(wq); - +err_unwind: while (--i >= 0) { wq = idxd->wqs[i]; if (idxd->hw.wq_cap.op_config) @@ -254,11 +256,10 @@ err: conf_dev = wq_confdev(wq); put_device(conf_dev); kfree(wq); - } bitmap_free(idxd->wq_enable_map); -err_bitmap: +err_free_wqs: kfree(idxd->wqs); return rc; @@ -1291,10 +1292,12 @@ static void idxd_remove(struct pci_dev *pdev) device_unregister(idxd_confdev(idxd)); idxd_shutdown(pdev); idxd_device_remove_debugfs(idxd); - idxd_cleanup(idxd); + perfmon_pmu_remove(idxd); + idxd_cleanup_interrupts(idxd); + if (device_pasid_enabled(idxd)) + idxd_disable_system_pasid(idxd); pci_iounmap(pdev, idxd->reg_base); put_device(idxd_confdev(idxd)); - idxd_free(idxd); pci_disable_device(pdev); } diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c index bbc3276992bb..2cf060174795 100644 --- a/drivers/dma/qcom/bam_dma.c +++ b/drivers/dma/qcom/bam_dma.c @@ -1283,13 +1283,17 @@ static int bam_dma_probe(struct platform_device *pdev) if (!bdev->bamclk) { ret = of_property_read_u32(pdev->dev.of_node, "num-channels", &bdev->num_channels); - if (ret) + if (ret) { dev_err(bdev->dev, "num-channels unspecified in dt\n"); + return ret; + } ret = of_property_read_u32(pdev->dev.of_node, "qcom,num-ees", &bdev->num_ees); - if (ret) + if (ret) { dev_err(bdev->dev, "num-ees unspecified in dt\n"); + return ret; + } } ret = clk_prepare_enable(bdev->bamclk); diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c index 3ed406f08c44..552be71db6c4 100644 --- a/drivers/dma/ti/edma.c +++ b/drivers/dma/ti/edma.c @@ -2064,8 +2064,8 @@ static int edma_setup_from_hw(struct device *dev, struct edma_soc_info *pdata, * priority. So Q0 is the highest priority queue and the last queue has * the lowest priority. */ - queue_priority_map = devm_kcalloc(dev, ecc->num_tc + 1, sizeof(s8), - GFP_KERNEL); + queue_priority_map = devm_kcalloc(dev, ecc->num_tc + 1, + sizeof(*queue_priority_map), GFP_KERNEL); if (!queue_priority_map) return -ENOMEM; diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 036f21cac0a9..0a852011653c 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -211,8 +211,8 @@ static int dpll_msg_add_clock_quality_level(struct sk_buff *msg, struct dpll_device *dpll, struct netlink_ext_ack *extack) { + DECLARE_BITMAP(qls, DPLL_CLOCK_QUALITY_LEVEL_MAX + 1) = { 0 }; const struct dpll_device_ops *ops = dpll_device_ops(dpll); - DECLARE_BITMAP(qls, DPLL_CLOCK_QUALITY_LEVEL_MAX) = { 0 }; enum dpll_clock_quality_level ql; int ret; @@ -221,7 +221,7 @@ dpll_msg_add_clock_quality_level(struct sk_buff *msg, struct dpll_device *dpll, ret = ops->clock_quality_level_get(dpll, dpll_priv(dpll), qls, extack); if (ret) return ret; - for_each_set_bit(ql, qls, DPLL_CLOCK_QUALITY_LEVEL_MAX) + for_each_set_bit(ql, qls, DPLL_CLOCK_QUALITY_LEVEL_MAX + 1) if (nla_put_u32(msg, DPLL_A_CLOCK_QUALITY_LEVEL, ql)) return -EMSGSIZE; diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index 78b10c6ef7fe..2e93189d7142 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -41,7 +41,7 @@ /* * ABI version history is documented in linux/firewire-cdev.h. */ -#define FW_CDEV_KERNEL_VERSION 5 +#define FW_CDEV_KERNEL_VERSION 6 #define FW_CDEV_VERSION_EVENT_REQUEST2 4 #define FW_CDEV_VERSION_ALLOCATE_REGION_END 4 #define FW_CDEV_VERSION_AUTO_FLUSH_ISO_OVERFLOW 5 diff --git a/drivers/gpio/gpiolib-acpi-core.c b/drivers/gpio/gpiolib-acpi-core.c index 12b24a717e43..284e762d92c4 100644 --- a/drivers/gpio/gpiolib-acpi-core.c +++ b/drivers/gpio/gpiolib-acpi-core.c @@ -942,8 +942,9 @@ struct gpio_desc *acpi_find_gpio(struct fwnode_handle *fwnode, { struct acpi_device *adev = to_acpi_device_node(fwnode); bool can_fallback = acpi_can_fallback_to_crs(adev, con_id); - struct acpi_gpio_info info; + struct acpi_gpio_info info = {}; struct gpio_desc *desc; + int ret; desc = __acpi_find_gpio(fwnode, con_id, idx, can_fallback, &info); if (IS_ERR(desc)) @@ -957,6 +958,12 @@ struct gpio_desc *acpi_find_gpio(struct fwnode_handle *fwnode, acpi_gpio_update_gpiod_flags(dflags, &info); acpi_gpio_update_gpiod_lookup_flags(lookupflags, &info); + + /* ACPI uses hundredths of milliseconds units */ + ret = gpio_set_debounce_timeout(desc, info.debounce * 10); + if (ret) + return ERR_PTR(ret); + return desc; } @@ -992,7 +999,7 @@ int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *con_id, int ret; for (i = 0, idx = 0; idx <= index; i++) { - struct acpi_gpio_info info; + struct acpi_gpio_info info = {}; struct gpio_desc *desc; /* Ignore -EPROBE_DEFER, it only matters if idx matches */ diff --git a/drivers/gpio/gpiolib-acpi-quirks.c b/drivers/gpio/gpiolib-acpi-quirks.c index bfb04e67c4bc..7b95d1b03361 100644 --- a/drivers/gpio/gpiolib-acpi-quirks.c +++ b/drivers/gpio/gpiolib-acpi-quirks.c @@ -319,6 +319,18 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = { }, { /* + * Same as G1619-04. New model. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GPD"), + DMI_MATCH(DMI_PRODUCT_NAME, "G1619-05"), + }, + .driver_data = &(struct acpi_gpiolib_dmi_quirk) { + .ignore_wake = "PNP0C50:00@8", + }, + }, + { + /* * Spurious wakeups from GPIO 11 * Found in BIOS 1.04 * https://gitlab.freedesktop.org/drm/amd/-/issues/3954 diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index fbe7616555c8..a2879d2b7c8e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -250,16 +250,24 @@ void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev, void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool suspend_proc) { - if (adev->kfd.dev) - kgd2kfd_suspend(adev->kfd.dev, suspend_proc); + if (adev->kfd.dev) { + if (adev->in_s0ix) + kgd2kfd_stop_sched_all_nodes(adev->kfd.dev); + else + kgd2kfd_suspend(adev->kfd.dev, suspend_proc); + } } int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool resume_proc) { int r = 0; - if (adev->kfd.dev) - r = kgd2kfd_resume(adev->kfd.dev, resume_proc); + if (adev->kfd.dev) { + if (adev->in_s0ix) + r = kgd2kfd_start_sched_all_nodes(adev->kfd.dev); + else + r = kgd2kfd_resume(adev->kfd.dev, resume_proc); + } return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 33eb4826b58b..aa88bad7416b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -426,7 +426,9 @@ void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint64_t throttle_bitmask); int kgd2kfd_check_and_lock_kfd(struct kfd_dev *kfd); void kgd2kfd_unlock_kfd(struct kfd_dev *kfd); int kgd2kfd_start_sched(struct kfd_dev *kfd, uint32_t node_id); +int kgd2kfd_start_sched_all_nodes(struct kfd_dev *kfd); int kgd2kfd_stop_sched(struct kfd_dev *kfd, uint32_t node_id); +int kgd2kfd_stop_sched_all_nodes(struct kfd_dev *kfd); bool kgd2kfd_compute_active(struct kfd_dev *kfd, uint32_t node_id); bool kgd2kfd_vmfault_fast_path(struct amdgpu_device *adev, struct amdgpu_iv_entry *entry, bool retry_fault); @@ -516,11 +518,21 @@ static inline int kgd2kfd_start_sched(struct kfd_dev *kfd, uint32_t node_id) return 0; } +static inline int kgd2kfd_start_sched_all_nodes(struct kfd_dev *kfd) +{ + return 0; +} + static inline int kgd2kfd_stop_sched(struct kfd_dev *kfd, uint32_t node_id) { return 0; } +static inline int kgd2kfd_stop_sched_all_nodes(struct kfd_dev *kfd) +{ + return 0; +} + static inline bool kgd2kfd_compute_active(struct kfd_dev *kfd, uint32_t node_id) { return false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 260165bbe373..b16cce7c22c3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -213,19 +213,35 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev, spin_lock(&kfd_mem_limit.mem_limit_lock); if (kfd_mem_limit.system_mem_used + system_mem_needed > - kfd_mem_limit.max_system_mem_limit) + kfd_mem_limit.max_system_mem_limit) { pr_debug("Set no_system_mem_limit=1 if using shared memory\n"); + if (!no_system_mem_limit) { + ret = -ENOMEM; + goto release; + } + } - if ((kfd_mem_limit.system_mem_used + system_mem_needed > - kfd_mem_limit.max_system_mem_limit && !no_system_mem_limit) || - (kfd_mem_limit.ttm_mem_used + ttm_mem_needed > - kfd_mem_limit.max_ttm_mem_limit) || - (adev && xcp_id >= 0 && adev->kfd.vram_used[xcp_id] + vram_needed > - vram_size - reserved_for_pt - reserved_for_ras - atomic64_read(&adev->vram_pin_size))) { + if (kfd_mem_limit.ttm_mem_used + ttm_mem_needed > + kfd_mem_limit.max_ttm_mem_limit) { ret = -ENOMEM; goto release; } + /*if is_app_apu is false and apu_prefer_gtt is true, it is an APU with + * carve out < gtt. In that case, VRAM allocation will go to gtt domain, skip + * VRAM check since ttm_mem_limit check already cover this allocation + */ + + if (adev && xcp_id >= 0 && (!adev->apu_prefer_gtt || adev->gmc.is_app_apu)) { + uint64_t vram_available = + vram_size - reserved_for_pt - reserved_for_ras - + atomic64_read(&adev->vram_pin_size); + if (adev->kfd.vram_used[xcp_id] + vram_needed > vram_available) { + ret = -ENOMEM; + goto release; + } + } + /* Update memory accounting by decreasing available system * memory, TTM memory and GPU memory as computed above */ @@ -1626,11 +1642,15 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev, uint64_t vram_available, system_mem_available, ttm_mem_available; spin_lock(&kfd_mem_limit.mem_limit_lock); - vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id) - - adev->kfd.vram_used_aligned[xcp_id] - - atomic64_read(&adev->vram_pin_size) - - reserved_for_pt - - reserved_for_ras; + if (adev->apu_prefer_gtt && !adev->gmc.is_app_apu) + vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id) + - adev->kfd.vram_used_aligned[xcp_id]; + else + vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id) + - adev->kfd.vram_used_aligned[xcp_id] + - atomic64_read(&adev->vram_pin_size) + - reserved_for_pt + - reserved_for_ras; if (adev->apu_prefer_gtt) { system_mem_available = no_system_mem_limit ? diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 01d234cf8156..c8459337fcb8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5136,7 +5136,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients) adev->in_suspend = true; if (amdgpu_sriov_vf(adev)) { - if (!adev->in_s0ix && !adev->in_runpm) + if (!adev->in_runpm) amdgpu_amdkfd_suspend_process(adev); amdgpu_virt_fini_data_exchange(adev); r = amdgpu_virt_request_full_gpu(adev, false); @@ -5156,10 +5156,8 @@ int amdgpu_device_suspend(struct drm_device *dev, bool notify_clients) amdgpu_device_ip_suspend_phase1(adev); - if (!adev->in_s0ix) { - amdgpu_amdkfd_suspend(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm); - amdgpu_userq_suspend(adev); - } + amdgpu_amdkfd_suspend(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm); + amdgpu_userq_suspend(adev); r = amdgpu_device_evict_resources(adev); if (r) @@ -5254,15 +5252,13 @@ int amdgpu_device_resume(struct drm_device *dev, bool notify_clients) goto exit; } - if (!adev->in_s0ix) { - r = amdgpu_amdkfd_resume(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm); - if (r) - goto exit; + r = amdgpu_amdkfd_resume(adev, !amdgpu_sriov_vf(adev) && !adev->in_runpm); + if (r) + goto exit; - r = amdgpu_userq_resume(adev); - if (r) - goto exit; - } + r = amdgpu_userq_resume(adev); + if (r) + goto exit; r = amdgpu_device_ip_late_init(adev); if (r) @@ -5275,7 +5271,7 @@ exit: amdgpu_virt_init_data_exchange(adev); amdgpu_virt_release_full_gpu(adev, true); - if (!adev->in_s0ix && !r && !adev->in_runpm) + if (!r && !adev->in_runpm) r = amdgpu_amdkfd_resume_process(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 6379bb25bf5c..486c3646710c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -421,8 +421,6 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring) dma_fence_put(ring->vmid_wait); ring->vmid_wait = NULL; ring->me = 0; - - ring->adev->rings[ring->idx] = NULL; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index c85de8c8f6f5..c37527704d43 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -1654,6 +1654,21 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block) } } break; + case IP_VERSION(11, 0, 1): + case IP_VERSION(11, 0, 4): + adev->gfx.cleaner_shader_ptr = gfx_11_0_3_cleaner_shader_hex; + adev->gfx.cleaner_shader_size = sizeof(gfx_11_0_3_cleaner_shader_hex); + if (adev->gfx.pfp_fw_version >= 102 && + adev->gfx.mec_fw_version >= 66 && + adev->mes.fw_version[0] >= 128) { + adev->gfx.enable_cleaner_shader = true; + r = amdgpu_gfx_cleaner_shader_sw_init(adev, adev->gfx.cleaner_shader_size); + if (r) { + adev->gfx.enable_cleaner_shader = false; + dev_err(adev->dev, "Failed to initialize cleaner shader\n"); + } + } + break; case IP_VERSION(11, 5, 0): case IP_VERSION(11, 5, 1): adev->gfx.cleaner_shader_ptr = gfx_11_0_3_cleaner_shader_hex; diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c index a887df520414..4258d3e0b706 100644 --- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c +++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c @@ -29,6 +29,8 @@ #include "amdgpu.h" #include "isp_v4_1_1.h" +MODULE_FIRMWARE("amdgpu/isp_4_1_1.bin"); + #define ISP_PERFORMANCE_STATE_LOW 0 #define ISP_PERFORMANCE_STATE_HIGH 1 diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index 6cc05d36e359..64b240b51f1a 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -149,12 +149,12 @@ static int psp_v11_0_wait_for_bootloader(struct psp_context *psp) int ret; int retry_loop; - for (retry_loop = 0; retry_loop < 10; retry_loop++) { + for (retry_loop = 0; retry_loop < 20; retry_loop++) { /* Wait for bootloader to signify that is ready having bit 31 of C2PMSG_35 set to 1 */ ret = psp_wait_for( psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35), - 0x80000000, 0x80000000, PSP_WAITREG_NOVERBOSE); + 0x80000000, 0x8000FFFF, PSP_WAITREG_NOVERBOSE); if (ret == 0) return 0; @@ -397,18 +397,6 @@ static int psp_v11_0_mode1_reset(struct psp_context *psp) msleep(500); - offset = SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_33); - - ret = psp_wait_for(psp, offset, MBOX_TOS_RESP_FLAG, MBOX_TOS_RESP_MASK, - 0); - - if (ret) { - DRM_INFO("psp mode 1 reset failed!\n"); - return -EINVAL; - } - - DRM_INFO("psp mode1 reset succeed \n"); - return 0; } @@ -665,7 +653,8 @@ static const struct psp_funcs psp_v11_0_funcs = { .ring_get_wptr = psp_v11_0_ring_get_wptr, .ring_set_wptr = psp_v11_0_ring_set_wptr, .load_usbc_pd_fw = psp_v11_0_load_usbc_pd_fw, - .read_usbc_pd_fw = psp_v11_0_read_usbc_pd_fw + .read_usbc_pd_fw = psp_v11_0_read_usbc_pd_fw, + .wait_for_bootloader = psp_v11_0_wait_for_bootloader }; void psp_v11_0_set_psp_funcs(struct psp_context *psp) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 4b8f4407047f..2811226b0ea5 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -1888,15 +1888,19 @@ static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p, struct amdgpu_job *job) { struct drm_gpu_scheduler **scheds; - - /* The create msg must be in the first IB submitted */ - if (atomic_read(&job->base.entity->fence_seq)) - return -EINVAL; + struct dma_fence *fence; /* if VCN0 is harvested, we can't support AV1 */ if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) return -EINVAL; + /* wait for all jobs to finish before switching to instance 0 */ + fence = amdgpu_ctx_get_fence(p->ctx, job->base.entity, ~0ull); + if (fence) { + dma_fence_wait(fence, false); + dma_fence_put(fence); + } + scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_DEC] [AMDGPU_RING_PRIO_DEFAULT].sched; drm_sched_entity_modify_sched(job->base.entity, scheds, 1); diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 1924e075b66f..706f3b2f484f 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -1808,15 +1808,19 @@ static int vcn_v4_0_limit_sched(struct amdgpu_cs_parser *p, struct amdgpu_job *job) { struct drm_gpu_scheduler **scheds; - - /* The create msg must be in the first IB submitted */ - if (atomic_read(&job->base.entity->fence_seq)) - return -EINVAL; + struct dma_fence *fence; /* if VCN0 is harvested, we can't support AV1 */ if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) return -EINVAL; + /* wait for all jobs to finish before switching to instance 0 */ + fence = amdgpu_ctx_get_fence(p->ctx, job->base.entity, ~0ull); + if (fence) { + dma_fence_wait(fence, false); + dma_fence_put(fence); + } + scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_ENC] [AMDGPU_RING_PRIO_0].sched; drm_sched_entity_modify_sched(job->base.entity, scheds, 1); @@ -1907,22 +1911,16 @@ out: #define RADEON_VCN_ENGINE_TYPE_ENCODE (0x00000002) #define RADEON_VCN_ENGINE_TYPE_DECODE (0x00000003) - #define RADEON_VCN_ENGINE_INFO (0x30000001) -#define RADEON_VCN_ENGINE_INFO_MAX_OFFSET 16 - #define RENCODE_ENCODE_STANDARD_AV1 2 #define RENCODE_IB_PARAM_SESSION_INIT 0x00000003 -#define RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET 64 -/* return the offset in ib if id is found, -1 otherwise - * to speed up the searching we only search upto max_offset - */ -static int vcn_v4_0_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int max_offset) +/* return the offset in ib if id is found, -1 otherwise */ +static int vcn_v4_0_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int start) { int i; - for (i = 0; i < ib->length_dw && i < max_offset && ib->ptr[i] >= 8; i += ib->ptr[i]/4) { + for (i = start; i < ib->length_dw && ib->ptr[i] >= 8; i += ib->ptr[i] / 4) { if (ib->ptr[i + 1] == id) return i; } @@ -1937,33 +1935,29 @@ static int vcn_v4_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, struct amdgpu_vcn_decode_buffer *decode_buffer; uint64_t addr; uint32_t val; - int idx; + int idx = 0, sidx; /* The first instance can decode anything */ if (!ring->me) return 0; - /* RADEON_VCN_ENGINE_INFO is at the top of ib block */ - idx = vcn_v4_0_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, - RADEON_VCN_ENGINE_INFO_MAX_OFFSET); - if (idx < 0) /* engine info is missing */ - return 0; - - val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */ - if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { - decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6]; - - if (!(decode_buffer->valid_buf_flag & 0x1)) - return 0; - - addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | - decode_buffer->msg_buffer_address_lo; - return vcn_v4_0_dec_msg(p, job, addr); - } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) { - idx = vcn_v4_0_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, - RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET); - if (idx >= 0 && ib->ptr[idx + 2] == RENCODE_ENCODE_STANDARD_AV1) - return vcn_v4_0_limit_sched(p, job); + while ((idx = vcn_v4_0_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, idx)) >= 0) { + val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */ + if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { + decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6]; + + if (!(decode_buffer->valid_buf_flag & 0x1)) + return 0; + + addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | + decode_buffer->msg_buffer_address_lo; + return vcn_v4_0_dec_msg(p, job, addr); + } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) { + sidx = vcn_v4_0_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, idx); + if (sidx >= 0 && ib->ptr[sidx + 2] == RENCODE_ENCODE_STANDARD_AV1) + return vcn_v4_0_limit_sched(p, job); + } + idx += ib->ptr[idx] / 4; } return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 7e749f9b6d69..349c351e242b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -1550,6 +1550,25 @@ int kgd2kfd_start_sched(struct kfd_dev *kfd, uint32_t node_id) return ret; } +int kgd2kfd_start_sched_all_nodes(struct kfd_dev *kfd) +{ + struct kfd_node *node; + int i, r; + + if (!kfd->init_complete) + return 0; + + for (i = 0; i < kfd->num_nodes; i++) { + node = kfd->nodes[i]; + r = node->dqm->ops.unhalt(node->dqm); + if (r) { + dev_err(kfd_device, "Error in starting scheduler\n"); + return r; + } + } + return 0; +} + int kgd2kfd_stop_sched(struct kfd_dev *kfd, uint32_t node_id) { struct kfd_node *node; @@ -1567,6 +1586,23 @@ int kgd2kfd_stop_sched(struct kfd_dev *kfd, uint32_t node_id) return node->dqm->ops.halt(node->dqm); } +int kgd2kfd_stop_sched_all_nodes(struct kfd_dev *kfd) +{ + struct kfd_node *node; + int i, r; + + if (!kfd->init_complete) + return 0; + + for (i = 0; i < kfd->num_nodes; i++) { + node = kfd->nodes[i]; + r = node->dqm->ops.halt(node->dqm); + if (r) + return r; + } + return 0; +} + bool kgd2kfd_compute_active(struct kfd_dev *kfd, uint32_t node_id) { struct kfd_node *node; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 4ec73f33535e..720b20e842ba 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -1587,7 +1587,8 @@ static int kfd_dev_create_p2p_links(void) break; if (!dev->gpu || !dev->gpu->adev || (dev->gpu->kfd->hive_id && - dev->gpu->kfd->hive_id == new_dev->gpu->kfd->hive_id)) + dev->gpu->kfd->hive_id == new_dev->gpu->kfd->hive_id && + amdgpu_xgmi_get_is_sharing_enabled(dev->gpu->adev, new_dev->gpu->adev))) goto next; /* check if node(s) is/are peer accessible in one direction or bi-direction */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 7808a647a306..97d9eba17963 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2913,6 +2913,17 @@ static int dm_oem_i2c_hw_init(struct amdgpu_device *adev) return 0; } +static void dm_oem_i2c_hw_fini(struct amdgpu_device *adev) +{ + struct amdgpu_display_manager *dm = &adev->dm; + + if (dm->oem_i2c) { + i2c_del_adapter(&dm->oem_i2c->base); + kfree(dm->oem_i2c); + dm->oem_i2c = NULL; + } +} + /** * dm_hw_init() - Initialize DC device * @ip_block: Pointer to the amdgpu_ip_block for this hw instance. @@ -2963,7 +2974,7 @@ static int dm_hw_fini(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; - kfree(adev->dm.oem_i2c); + dm_oem_i2c_hw_fini(adev); amdgpu_dm_hpd_fini(adev); @@ -3127,25 +3138,6 @@ static void dm_destroy_cached_state(struct amdgpu_device *adev) dm->cached_state = NULL; } -static void dm_complete(struct amdgpu_ip_block *ip_block) -{ - struct amdgpu_device *adev = ip_block->adev; - - dm_destroy_cached_state(adev); -} - -static int dm_prepare_suspend(struct amdgpu_ip_block *ip_block) -{ - struct amdgpu_device *adev = ip_block->adev; - - if (amdgpu_in_reset(adev)) - return 0; - - WARN_ON(adev->dm.cached_state); - - return dm_cache_state(adev); -} - static int dm_suspend(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; @@ -3571,10 +3563,8 @@ static const struct amd_ip_funcs amdgpu_dm_funcs = { .early_fini = amdgpu_dm_early_fini, .hw_init = dm_hw_init, .hw_fini = dm_hw_fini, - .prepare_suspend = dm_prepare_suspend, .suspend = dm_suspend, .resume = dm_resume, - .complete = dm_complete, .is_idle = dm_is_idle, .wait_for_idle = dm_wait_for_idle, .check_soft_reset = dm_check_soft_reset, @@ -8727,7 +8717,16 @@ static int amdgpu_dm_encoder_init(struct drm_device *dev, static void manage_dm_interrupts(struct amdgpu_device *adev, struct amdgpu_crtc *acrtc, struct dm_crtc_state *acrtc_state) -{ +{ /* + * We cannot be sure that the frontend index maps to the same + * backend index - some even map to more than one. + * So we have to go through the CRTC to find the right IRQ. + */ + int irq_type = amdgpu_display_crtc_idx_to_irq_type( + adev, + acrtc->crtc_id); + struct drm_device *dev = adev_to_drm(adev); + struct drm_vblank_crtc_config config = {0}; struct dc_crtc_timing *timing; int offdelay; @@ -8780,7 +8779,35 @@ static void manage_dm_interrupts(struct amdgpu_device *adev, drm_crtc_vblank_on_config(&acrtc->base, &config); + /* Allow RX6xxx, RX7700, RX7800 GPUs to call amdgpu_irq_get.*/ + switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) { + case IP_VERSION(3, 0, 0): + case IP_VERSION(3, 0, 2): + case IP_VERSION(3, 0, 3): + case IP_VERSION(3, 2, 0): + if (amdgpu_irq_get(adev, &adev->pageflip_irq, irq_type)) + drm_err(dev, "DM_IRQ: Cannot get pageflip irq!\n"); +#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) + if (amdgpu_irq_get(adev, &adev->vline0_irq, irq_type)) + drm_err(dev, "DM_IRQ: Cannot get vline0 irq!\n"); +#endif + } + } else { + /* Allow RX6xxx, RX7700, RX7800 GPUs to call amdgpu_irq_put.*/ + switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) { + case IP_VERSION(3, 0, 0): + case IP_VERSION(3, 0, 2): + case IP_VERSION(3, 0, 3): + case IP_VERSION(3, 2, 0): +#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) + if (amdgpu_irq_put(adev, &adev->vline0_irq, irq_type)) + drm_err(dev, "DM_IRQ: Cannot put vline0 irq!\n"); +#endif + if (amdgpu_irq_put(adev, &adev->pageflip_irq, irq_type)) + drm_err(dev, "DM_IRQ: Cannot put pageflip irq!\n"); + } + drm_crtc_vblank_off(&acrtc->base); } } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 7187d5aedf0a..77a9d2c7d318 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -809,6 +809,7 @@ void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm, drm_dp_aux_init(&aconnector->dm_dp_aux.aux); drm_dp_cec_register_connector(&aconnector->dm_dp_aux.aux, &aconnector->base); + drm_dp_dpcd_set_probe(&aconnector->dm_dp_aux.aux, false); if (aconnector->base.connector_type == DRM_MODE_CONNECTOR_eDP) return; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 59c07756130d..f24e1da68269 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -1145,6 +1145,7 @@ struct dc_debug_options { bool enable_hblank_borrow; bool force_subvp_df_throttle; uint32_t acpi_transition_bitmasks[MAX_PIPES]; + bool enable_pg_cntl_debug_logs; }; diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c index 58c84f555c0f..0ce9489ac6b7 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c @@ -133,30 +133,34 @@ enum dsc_clk_source { }; -static void dccg35_set_dsc_clk_rcg(struct dccg *dccg, int inst, bool enable) +static void dccg35_set_dsc_clk_rcg(struct dccg *dccg, int inst, bool allow_rcg) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); - if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dsc && enable) + if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dsc && allow_rcg) return; switch (inst) { case 0: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 1: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 2: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 3: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; default: BREAK_TO_DEBUGGER(); return; } + + /* Wait for clock to ramp */ + if (!allow_rcg) + udelay(10); } static void dccg35_set_symclk32_se_rcg( @@ -385,35 +389,34 @@ static void dccg35_set_dtbclk_p_rcg(struct dccg *dccg, int inst, bool enable) } } -static void dccg35_set_dppclk_rcg(struct dccg *dccg, - int inst, bool enable) +static void dccg35_set_dppclk_rcg(struct dccg *dccg, int inst, bool allow_rcg) { - struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); - - if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && enable) + if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && allow_rcg) return; switch (inst) { case 0: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 1: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 2: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 3: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; default: BREAK_TO_DEBUGGER(); break; } - //DC_LOG_DEBUG("%s: inst(%d) DPPCLK rcg_disable: %d\n", __func__, inst, enable ? 0 : 1); + /* Wait for clock to ramp */ + if (!allow_rcg) + udelay(10); } static void dccg35_set_dpstreamclk_rcg( @@ -1177,32 +1180,34 @@ static void dccg35_update_dpp_dto(struct dccg *dccg, int dpp_inst, } static void dccg35_set_dppclk_root_clock_gating(struct dccg *dccg, - uint32_t dpp_inst, uint32_t enable) + uint32_t dpp_inst, uint32_t disallow_rcg) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); - if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp) + if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && !disallow_rcg) return; switch (dpp_inst) { case 0: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, enable); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, disallow_rcg); break; case 1: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, enable); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, disallow_rcg); break; case 2: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, enable); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, disallow_rcg); break; case 3: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, enable); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, disallow_rcg); break; default: break; } - //DC_LOG_DEBUG("%s: dpp_inst(%d) rcg: %d\n", __func__, dpp_inst, enable); + /* Wait for clock to ramp */ + if (disallow_rcg) + udelay(10); } static void dccg35_get_pixel_rate_div( @@ -1782,8 +1787,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) //Disable DTO switch (inst) { case 0: - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, 1); REG_UPDATE_2(DSCCLK0_DTO_PARAM, DSCCLK0_DTO_PHASE, 0, @@ -1791,8 +1795,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK0_EN, 1); break; case 1: - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, 1); REG_UPDATE_2(DSCCLK1_DTO_PARAM, DSCCLK1_DTO_PHASE, 0, @@ -1800,8 +1803,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK1_EN, 1); break; case 2: - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, 1); REG_UPDATE_2(DSCCLK2_DTO_PARAM, DSCCLK2_DTO_PHASE, 0, @@ -1809,8 +1811,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK2_EN, 1); break; case 3: - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, 1); REG_UPDATE_2(DSCCLK3_DTO_PARAM, DSCCLK3_DTO_PHASE, 0, @@ -1821,6 +1822,9 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) BREAK_TO_DEBUGGER(); return; } + + /* Wait for clock to ramp */ + udelay(10); } static void dccg35_disable_dscclk(struct dccg *dccg, @@ -1864,6 +1868,9 @@ static void dccg35_disable_dscclk(struct dccg *dccg, default: return; } + + /* Wait for clock ramp */ + udelay(10); } static void dccg35_enable_symclk_se(struct dccg *dccg, uint32_t stream_enc_inst, uint32_t link_enc_inst) @@ -2349,10 +2356,7 @@ static void dccg35_disable_symclk_se_cb( void dccg35_root_gate_disable_control(struct dccg *dccg, uint32_t pipe_idx, uint32_t disable_clock_gating) { - - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpp) { - dccg35_set_dppclk_root_clock_gating(dccg, pipe_idx, disable_clock_gating); - } + dccg35_set_dppclk_root_clock_gating(dccg, pipe_idx, disable_clock_gating); } static const struct dccg_funcs dccg35_funcs_new = { diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c index 3207addbd4eb..b7c2d3095b25 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c @@ -955,7 +955,7 @@ enum dc_status dcn20_enable_stream_timing( return DC_ERROR_UNEXPECTED; } - fsleep(stream->timing.v_total * (stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz)); + udelay(stream->timing.v_total * (stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz)); params.vertical_total_min = stream->adjust.v_total_min; params.vertical_total_max = stream->adjust.v_total_max; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c index a267f574b619..764eff6a4ec6 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c @@ -113,6 +113,14 @@ static void enable_memory_low_power(struct dc *dc) } #endif +static void print_pg_status(struct dc *dc, const char *debug_func, const char *debug_log) +{ + if (dc->debug.enable_pg_cntl_debug_logs && dc->res_pool->pg_cntl) { + if (dc->res_pool->pg_cntl->funcs->print_pg_status) + dc->res_pool->pg_cntl->funcs->print_pg_status(dc->res_pool->pg_cntl, debug_func, debug_log); + } +} + void dcn35_set_dmu_fgcg(struct dce_hwseq *hws, bool enable) { REG_UPDATE_3(DMU_CLK_CNTL, @@ -137,6 +145,8 @@ void dcn35_init_hw(struct dc *dc) uint32_t user_level = MAX_BACKLIGHT_LEVEL; int i; + print_pg_status(dc, __func__, ": start"); + if (dc->clk_mgr && dc->clk_mgr->funcs->init_clocks) dc->clk_mgr->funcs->init_clocks(dc->clk_mgr); @@ -200,10 +210,7 @@ void dcn35_init_hw(struct dc *dc) /* we want to turn off all dp displays before doing detection */ dc->link_srv->blank_all_dp_displays(dc); -/* - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); -*/ + if (res_pool->hubbub && res_pool->hubbub->funcs->dchubbub_init) res_pool->hubbub->funcs->dchubbub_init(dc->res_pool->hubbub); /* If taking control over from VBIOS, we may want to optimize our first @@ -236,6 +243,8 @@ void dcn35_init_hw(struct dc *dc) } hws->funcs.init_pipes(dc, dc->current_state); + print_pg_status(dc, __func__, ": after init_pipes"); + if (dc->res_pool->hubbub->funcs->allow_self_refresh_control && !dc->res_pool->hubbub->ctx->dc->debug.disable_stutter) dc->res_pool->hubbub->funcs->allow_self_refresh_control(dc->res_pool->hubbub, @@ -312,6 +321,7 @@ void dcn35_init_hw(struct dc *dc) if (dc->res_pool->pg_cntl->funcs->init_pg_status) dc->res_pool->pg_cntl->funcs->init_pg_status(dc->res_pool->pg_cntl); } + print_pg_status(dc, __func__, ": after init_pg_status"); } static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) @@ -500,97 +510,6 @@ void dcn35_physymclk_root_clock_control(struct dce_hwseq *hws, unsigned int phy_ } } -void dcn35_dsc_pg_control( - struct dce_hwseq *hws, - unsigned int dsc_inst, - bool power_on) -{ - uint32_t power_gate = power_on ? 0 : 1; - uint32_t pwr_status = power_on ? 0 : 2; - uint32_t org_ip_request_cntl = 0; - - if (hws->ctx->dc->debug.disable_dsc_power_gate) - return; - if (hws->ctx->dc->debug.ignore_pg) - return; - REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); - if (org_ip_request_cntl == 0) - REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); - - switch (dsc_inst) { - case 0: /* DSC0 */ - REG_UPDATE(DOMAIN16_PG_CONFIG, - DOMAIN_POWER_GATE, power_gate); - - REG_WAIT(DOMAIN16_PG_STATUS, - DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); - break; - case 1: /* DSC1 */ - REG_UPDATE(DOMAIN17_PG_CONFIG, - DOMAIN_POWER_GATE, power_gate); - - REG_WAIT(DOMAIN17_PG_STATUS, - DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); - break; - case 2: /* DSC2 */ - REG_UPDATE(DOMAIN18_PG_CONFIG, - DOMAIN_POWER_GATE, power_gate); - - REG_WAIT(DOMAIN18_PG_STATUS, - DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); - break; - case 3: /* DSC3 */ - REG_UPDATE(DOMAIN19_PG_CONFIG, - DOMAIN_POWER_GATE, power_gate); - - REG_WAIT(DOMAIN19_PG_STATUS, - DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); - break; - default: - BREAK_TO_DEBUGGER(); - break; - } - - if (org_ip_request_cntl == 0) - REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); -} - -void dcn35_enable_power_gating_plane(struct dce_hwseq *hws, bool enable) -{ - bool force_on = true; /* disable power gating */ - uint32_t org_ip_request_cntl = 0; - - if (hws->ctx->dc->debug.disable_hubp_power_gate) - return; - if (hws->ctx->dc->debug.ignore_pg) - return; - REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); - if (org_ip_request_cntl == 0) - REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); - /* DCHUBP0/1/2/3/4/5 */ - REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - /* DPP0/1/2/3/4/5 */ - REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - - force_on = true; /* disable power gating */ - if (enable && !hws->ctx->dc->debug.disable_dsc_power_gate) - force_on = false; - - /* DCS0/1/2/3/4 */ - REG_UPDATE(DOMAIN16_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN17_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN18_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN19_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - - -} - /* In headless boot cases, DIG may be turned * on which causes HW/SW discrepancies. * To avoid this, power down hardware on boot @@ -1453,6 +1372,8 @@ void dcn35_prepare_bandwidth( } dcn20_prepare_bandwidth(dc, context); + + print_pg_status(dc, __func__, ": after rcg and power up"); } void dcn35_optimize_bandwidth( @@ -1461,6 +1382,8 @@ void dcn35_optimize_bandwidth( { struct pg_block_update pg_update_state; + print_pg_status(dc, __func__, ": before rcg and power up"); + dcn20_optimize_bandwidth(dc, context); if (dc->hwss.calc_blocks_to_gate) { @@ -1472,6 +1395,8 @@ void dcn35_optimize_bandwidth( if (dc->hwss.root_clock_control) dc->hwss.root_clock_control(dc, &pg_update_state, false); } + + print_pg_status(dc, __func__, ": after rcg and power up"); } void dcn35_set_drr(struct pipe_ctx **pipe_ctx, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c index a3ccf805bd16..aefb7c473741 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c @@ -115,7 +115,6 @@ static const struct hw_sequencer_funcs dcn35_funcs = { .exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state, .update_visual_confirm_color = dcn10_update_visual_confirm_color, .apply_idle_power_optimizations = dcn35_apply_idle_power_optimizations, - .update_dsc_pg = dcn32_update_dsc_pg, .calc_blocks_to_gate = dcn35_calc_blocks_to_gate, .calc_blocks_to_ungate = dcn35_calc_blocks_to_ungate, .hw_block_power_up = dcn35_hw_block_power_up, @@ -150,7 +149,6 @@ static const struct hwseq_private_funcs dcn35_private_funcs = { .plane_atomic_disable = dcn35_plane_atomic_disable, //.plane_atomic_disable = dcn20_plane_atomic_disable,/*todo*/ //.hubp_pg_control = dcn35_hubp_pg_control, - .enable_power_gating_plane = dcn35_enable_power_gating_plane, .dpp_root_clock_control = dcn35_dpp_root_clock_control, .dpstream_root_clock_control = dcn35_dpstream_root_clock_control, .physymclk_root_clock_control = dcn35_physymclk_root_clock_control, @@ -165,7 +163,6 @@ static const struct hwseq_private_funcs dcn35_private_funcs = { .calculate_dccg_k1_k2_values = dcn32_calculate_dccg_k1_k2_values, .resync_fifo_dccg_dio = dcn314_resync_fifo_dccg_dio, .is_dp_dig_pixel_rate_div_policy = dcn35_is_dp_dig_pixel_rate_div_policy, - .dsc_pg_control = dcn35_dsc_pg_control, .dsc_pg_status = dcn32_dsc_pg_status, .enable_plane = dcn35_enable_plane, .wait_for_pipe_update_if_needed = dcn10_wait_for_pipe_update_if_needed, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c index 58f2be2a326b..a580a55695c3 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c @@ -114,7 +114,6 @@ static const struct hw_sequencer_funcs dcn351_funcs = { .exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state, .update_visual_confirm_color = dcn10_update_visual_confirm_color, .apply_idle_power_optimizations = dcn35_apply_idle_power_optimizations, - .update_dsc_pg = dcn32_update_dsc_pg, .calc_blocks_to_gate = dcn351_calc_blocks_to_gate, .calc_blocks_to_ungate = dcn351_calc_blocks_to_ungate, .hw_block_power_up = dcn351_hw_block_power_up, @@ -145,7 +144,6 @@ static const struct hwseq_private_funcs dcn351_private_funcs = { .plane_atomic_disable = dcn35_plane_atomic_disable, //.plane_atomic_disable = dcn20_plane_atomic_disable,/*todo*/ //.hubp_pg_control = dcn35_hubp_pg_control, - .enable_power_gating_plane = dcn35_enable_power_gating_plane, .dpp_root_clock_control = dcn35_dpp_root_clock_control, .dpstream_root_clock_control = dcn35_dpstream_root_clock_control, .physymclk_root_clock_control = dcn35_physymclk_root_clock_control, @@ -159,7 +157,6 @@ static const struct hwseq_private_funcs dcn351_private_funcs = { .setup_hpo_hw_control = dcn35_setup_hpo_hw_control, .calculate_dccg_k1_k2_values = dcn32_calculate_dccg_k1_k2_values, .is_dp_dig_pixel_rate_div_policy = dcn35_is_dp_dig_pixel_rate_div_policy, - .dsc_pg_control = dcn35_dsc_pg_control, .dsc_pg_status = dcn32_dsc_pg_status, .enable_plane = dcn35_enable_plane, .wait_for_pipe_update_if_needed = dcn10_wait_for_pipe_update_if_needed, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h b/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h index 44f86cc2d1d6..227e3f8d7e5f 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h @@ -49,6 +49,7 @@ struct pg_cntl_funcs { void (*mem_pg_control)(struct pg_cntl *pg_cntl, bool power_on); void (*dio_pg_control)(struct pg_cntl *pg_cntl, bool power_on); void (*init_pg_status)(struct pg_cntl *pg_cntl); + void (*print_pg_status)(struct pg_cntl *pg_cntl, const char *debug_func, const char *debug_log); }; #endif //__DC_PG_CNTL_H__ diff --git a/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c b/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c index af21c0a27f86..72bd43f9bbe2 100644 --- a/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c +++ b/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c @@ -79,16 +79,12 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo uint32_t power_gate = power_on ? 0 : 1; uint32_t pwr_status = power_on ? 0 : 2; uint32_t org_ip_request_cntl = 0; - bool block_enabled; - - /*need to enable dscclk regardless DSC_PG*/ - if (pg_cntl->ctx->dc->res_pool->dccg->funcs->enable_dsc && power_on) - pg_cntl->ctx->dc->res_pool->dccg->funcs->enable_dsc( - pg_cntl->ctx->dc->res_pool->dccg, dsc_inst); + bool block_enabled = false; + bool skip_pg = pg_cntl->ctx->dc->debug.ignore_pg || + pg_cntl->ctx->dc->debug.disable_dsc_power_gate || + pg_cntl->ctx->dc->idle_optimizations_allowed; - if (pg_cntl->ctx->dc->debug.ignore_pg || - pg_cntl->ctx->dc->debug.disable_dsc_power_gate || - pg_cntl->ctx->dc->idle_optimizations_allowed) + if (skip_pg && !power_on) return; block_enabled = pg_cntl35_dsc_pg_status(pg_cntl, dsc_inst); @@ -111,7 +107,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo REG_WAIT(DOMAIN16_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); + 1, 10000); break; case 1: /* DSC1 */ REG_UPDATE(DOMAIN17_PG_CONFIG, @@ -119,7 +115,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo REG_WAIT(DOMAIN17_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); + 1, 10000); break; case 2: /* DSC2 */ REG_UPDATE(DOMAIN18_PG_CONFIG, @@ -127,7 +123,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo REG_WAIT(DOMAIN18_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); + 1, 10000); break; case 3: /* DSC3 */ REG_UPDATE(DOMAIN19_PG_CONFIG, @@ -135,7 +131,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo REG_WAIT(DOMAIN19_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); + 1, 10000); break; default: BREAK_TO_DEBUGGER(); @@ -144,12 +140,6 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo if (dsc_inst < MAX_PIPES) pg_cntl->pg_pipe_res_enable[PG_DSC][dsc_inst] = power_on; - - if (pg_cntl->ctx->dc->res_pool->dccg->funcs->disable_dsc && !power_on) { - /*this is to disable dscclk*/ - pg_cntl->ctx->dc->res_pool->dccg->funcs->disable_dsc( - pg_cntl->ctx->dc->res_pool->dccg, dsc_inst); - } } static bool pg_cntl35_hubp_dpp_pg_status(struct pg_cntl *pg_cntl, unsigned int hubp_dpp_inst) @@ -189,11 +179,12 @@ void pg_cntl35_hubp_dpp_pg_control(struct pg_cntl *pg_cntl, unsigned int hubp_dp uint32_t pwr_status = power_on ? 0 : 2; uint32_t org_ip_request_cntl; bool block_enabled; + bool skip_pg = pg_cntl->ctx->dc->debug.ignore_pg || + pg_cntl->ctx->dc->debug.disable_hubp_power_gate || + pg_cntl->ctx->dc->debug.disable_dpp_power_gate || + pg_cntl->ctx->dc->idle_optimizations_allowed; - if (pg_cntl->ctx->dc->debug.ignore_pg || - pg_cntl->ctx->dc->debug.disable_hubp_power_gate || - pg_cntl->ctx->dc->debug.disable_dpp_power_gate || - pg_cntl->ctx->dc->idle_optimizations_allowed) + if (skip_pg && !power_on) return; block_enabled = pg_cntl35_hubp_dpp_pg_status(pg_cntl, hubp_dpp_inst); @@ -213,22 +204,22 @@ void pg_cntl35_hubp_dpp_pg_control(struct pg_cntl *pg_cntl, unsigned int hubp_dp case 0: /* DPP0 & HUBP0 */ REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_GATE, power_gate); - REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000); break; case 1: /* DPP1 & HUBP1 */ REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_GATE, power_gate); - REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000); break; case 2: /* DPP2 & HUBP2 */ REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_GATE, power_gate); - REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000); break; case 3: /* DPP3 & HUBP3 */ REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_GATE, power_gate); - REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000); break; default: BREAK_TO_DEBUGGER(); @@ -501,6 +492,36 @@ void pg_cntl35_init_pg_status(struct pg_cntl *pg_cntl) pg_cntl->pg_res_enable[PG_DWB] = block_enabled; } +static void pg_cntl35_print_pg_status(struct pg_cntl *pg_cntl, const char *debug_func, const char *debug_log) +{ + int i = 0; + bool block_enabled = false; + + DC_LOG_DEBUG("%s: %s", debug_func, debug_log); + + DC_LOG_DEBUG("PG_CNTL status:\n"); + + block_enabled = pg_cntl35_io_clk_status(pg_cntl); + DC_LOG_DEBUG("ONO0=%d (DCCG, DIO, DCIO)\n", block_enabled ? 1 : 0); + + block_enabled = pg_cntl35_mem_status(pg_cntl); + DC_LOG_DEBUG("ONO1=%d (DCHUBBUB, DCHVM, DCHUBBUBMEM)\n", block_enabled ? 1 : 0); + + block_enabled = pg_cntl35_plane_otg_status(pg_cntl); + DC_LOG_DEBUG("ONO2=%d (MPC, OPP, OPTC, DWB)\n", block_enabled ? 1 : 0); + + block_enabled = pg_cntl35_hpo_pg_status(pg_cntl); + DC_LOG_DEBUG("ONO3=%d (HPO)\n", block_enabled ? 1 : 0); + + for (i = 0; i < pg_cntl->ctx->dc->res_pool->pipe_count; i++) { + block_enabled = pg_cntl35_hubp_dpp_pg_status(pg_cntl, i); + DC_LOG_DEBUG("ONO%d=%d (DCHUBP%d, DPP%d)\n", 4 + i * 2, block_enabled ? 1 : 0, i, i); + + block_enabled = pg_cntl35_dsc_pg_status(pg_cntl, i); + DC_LOG_DEBUG("ONO%d=%d (DSC%d)\n", 5 + i * 2, block_enabled ? 1 : 0, i); + } +} + static const struct pg_cntl_funcs pg_cntl35_funcs = { .init_pg_status = pg_cntl35_init_pg_status, .dsc_pg_control = pg_cntl35_dsc_pg_control, @@ -511,7 +532,8 @@ static const struct pg_cntl_funcs pg_cntl35_funcs = { .mpcc_pg_control = pg_cntl35_mpcc_pg_control, .opp_pg_control = pg_cntl35_opp_pg_control, .optc_pg_control = pg_cntl35_optc_pg_control, - .dwb_pg_control = pg_cntl35_dwb_pg_control + .dwb_pg_control = pg_cntl35_dwb_pg_control, + .print_pg_status = pg_cntl35_print_pg_status }; struct pg_cntl *pg_cntl35_create( diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index b47cb4a5f488..408f05dfab90 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -2236,7 +2236,7 @@ static int smu_resume(struct amdgpu_ip_block *ip_block) return ret; } - if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) { + if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL && smu->od_enabled) { ret = smu_od_edit_dpm_table(smu, PP_OD_COMMIT_DPM_TABLE, NULL, 0); if (ret) return ret; diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c index c0ad8f59e483..8b3304dedcd9 100644 --- a/drivers/gpu/drm/bridge/analogix/anx7625.c +++ b/drivers/gpu/drm/bridge/analogix/anx7625.c @@ -2677,7 +2677,7 @@ static int anx7625_i2c_probe(struct i2c_client *client) ret = devm_request_threaded_irq(dev, platform->pdata.intp_irq, NULL, anx7625_intr_hpd_isr, IRQF_TRIGGER_FALLING | - IRQF_ONESHOT, + IRQF_ONESHOT | IRQF_NO_AUTOEN, "anx7625-intp", platform); if (ret) { DRM_DEV_ERROR(dev, "fail to request irq\n"); @@ -2746,8 +2746,10 @@ static int anx7625_i2c_probe(struct i2c_client *client) } /* Add work function */ - if (platform->pdata.intp_irq) + if (platform->pdata.intp_irq) { + enable_irq(platform->pdata.intp_irq); queue_work(platform->workqueue, &platform->work); + } if (platform->pdata.audio_en) anx7625_register_audio(dev, platform); diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c index a614d1384f71..38726ae1bf15 100644 --- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c @@ -1984,8 +1984,10 @@ static void cdns_mhdp_atomic_enable(struct drm_bridge *bridge, mhdp_state = to_cdns_mhdp_bridge_state(new_state); mhdp_state->current_mode = drm_mode_duplicate(bridge->dev, mode); - if (!mhdp_state->current_mode) - return; + if (!mhdp_state->current_mode) { + ret = -EINVAL; + goto out; + } drm_mode_set_name(mhdp_state->current_mode); diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c index db9b089ef62c..86853535fb7b 100644 --- a/drivers/gpu/drm/drm_gpuvm.c +++ b/drivers/gpu/drm/drm_gpuvm.c @@ -2432,8 +2432,6 @@ static const struct drm_gpuvm_ops lock_ops = { * * The expected usage is:: * - * .. code-block:: c - * * vm_bind { * struct drm_exec exec; * diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 273054c22325..c92f3e736228 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -1172,7 +1172,7 @@ static void icl_mbus_init(struct intel_display *display) if (DISPLAY_VER(display) == 12) abox_regs |= BIT(0); - for_each_set_bit(i, &abox_regs, sizeof(abox_regs)) + for_each_set_bit(i, &abox_regs, BITS_PER_TYPE(abox_regs)) intel_de_rmw(display, MBUS_ABOX_CTL(i), mask, val); } @@ -1629,11 +1629,11 @@ static void tgl_bw_buddy_init(struct intel_display *display) if (table[config].page_mask == 0) { drm_dbg_kms(display->drm, "Unknown memory configuration; disabling address buddy logic.\n"); - for_each_set_bit(i, &abox_mask, sizeof(abox_mask)) + for_each_set_bit(i, &abox_mask, BITS_PER_TYPE(abox_mask)) intel_de_write(display, BW_BUDDY_CTL(i), BW_BUDDY_DISABLE); } else { - for_each_set_bit(i, &abox_mask, sizeof(abox_mask)) { + for_each_set_bit(i, &abox_mask, BITS_PER_TYPE(abox_mask)) { intel_de_write(display, BW_BUDDY_PAGE_MASK(i), table[config].page_mask); diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c index 41228478b21c..0a3a3f6a5f9d 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c @@ -546,7 +546,7 @@ static int intel_dp_aux_vesa_setup_backlight(struct intel_connector *connector, luminance_range->max_luminance, panel->vbt.backlight.pwm_freq_hz, intel_dp->edp_dpcd, ¤t_level, ¤t_mode, - false); + panel->backlight.edp.vesa.luminance_control_support); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index f8a817689e16..eb5537f0ac90 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -387,19 +387,21 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev) of_id = of_match_node(mtk_drm_of_ids, node); if (!of_id) - goto next_put_node; + continue; pdev = of_find_device_by_node(node); if (!pdev) - goto next_put_node; + continue; drm_dev = device_find_child(&pdev->dev, NULL, mtk_drm_match); + put_device(&pdev->dev); if (!drm_dev) - goto next_put_device_pdev_dev; + continue; temp_drm_priv = dev_get_drvdata(drm_dev); + put_device(drm_dev); if (!temp_drm_priv) - goto next_put_device_drm_dev; + continue; if (temp_drm_priv->data->main_len) all_drm_priv[CRTC_MAIN] = temp_drm_priv; @@ -411,17 +413,10 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev) if (temp_drm_priv->mtk_drm_bound) cnt++; -next_put_device_drm_dev: - put_device(drm_dev); - -next_put_device_pdev_dev: - put_device(&pdev->dev); - -next_put_node: - of_node_put(node); - - if (cnt == MAX_CRTC) + if (cnt == MAX_CRTC) { + of_node_put(node); break; + } } if (drm_priv->data->mmsys_dev_num == cnt) { diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 9f345a008717..869d4335c0f4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -240,21 +240,6 @@ nouveau_fence_emit(struct nouveau_fence *fence) return ret; } -void -nouveau_fence_cancel(struct nouveau_fence *fence) -{ - struct nouveau_fence_chan *fctx = nouveau_fctx(fence); - unsigned long flags; - - spin_lock_irqsave(&fctx->lock, flags); - if (!dma_fence_is_signaled_locked(&fence->base)) { - dma_fence_set_error(&fence->base, -ECANCELED); - if (nouveau_fence_signal(fence)) - nvif_event_block(&fctx->event); - } - spin_unlock_irqrestore(&fctx->lock, flags); -} - bool nouveau_fence_done(struct nouveau_fence *fence) { diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h index 9957a919bd38..183dd43ecfff 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.h +++ b/drivers/gpu/drm/nouveau/nouveau_fence.h @@ -29,7 +29,6 @@ void nouveau_fence_unref(struct nouveau_fence **); int nouveau_fence_emit(struct nouveau_fence *); bool nouveau_fence_done(struct nouveau_fence *); -void nouveau_fence_cancel(struct nouveau_fence *fence); int nouveau_fence_wait(struct nouveau_fence *, bool lazy, bool intr); int nouveau_fence_sync(struct nouveau_bo *, struct nouveau_channel *, bool exclusive, bool intr); diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c index 0cc0bc9f9952..e60f7892f5ce 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sched.c +++ b/drivers/gpu/drm/nouveau/nouveau_sched.c @@ -11,7 +11,6 @@ #include "nouveau_exec.h" #include "nouveau_abi16.h" #include "nouveau_sched.h" -#include "nouveau_chan.h" #define NOUVEAU_SCHED_JOB_TIMEOUT_MS 10000 @@ -122,9 +121,11 @@ nouveau_job_done(struct nouveau_job *job) { struct nouveau_sched *sched = job->sched; - spin_lock(&sched->job_list.lock); + spin_lock(&sched->job.list.lock); list_del(&job->entry); - spin_unlock(&sched->job_list.lock); + spin_unlock(&sched->job.list.lock); + + wake_up(&sched->job.wq); } void @@ -305,9 +306,9 @@ nouveau_job_submit(struct nouveau_job *job) } /* Submit was successful; add the job to the schedulers job list. */ - spin_lock(&sched->job_list.lock); - list_add(&job->entry, &sched->job_list.head); - spin_unlock(&sched->job_list.lock); + spin_lock(&sched->job.list.lock); + list_add(&job->entry, &sched->job.list.head); + spin_unlock(&sched->job.list.lock); drm_sched_job_arm(&job->base); job->done_fence = dma_fence_get(&job->base.s_fence->finished); @@ -392,23 +393,10 @@ nouveau_sched_free_job(struct drm_sched_job *sched_job) nouveau_job_fini(job); } -static void -nouveau_sched_cancel_job(struct drm_sched_job *sched_job) -{ - struct nouveau_fence *fence; - struct nouveau_job *job; - - job = to_nouveau_job(sched_job); - fence = to_nouveau_fence(job->done_fence); - - nouveau_fence_cancel(fence); -} - static const struct drm_sched_backend_ops nouveau_sched_ops = { .run_job = nouveau_sched_run_job, .timedout_job = nouveau_sched_timedout_job, .free_job = nouveau_sched_free_job, - .cancel_job = nouveau_sched_cancel_job, }; static int @@ -458,8 +446,9 @@ nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm, goto fail_sched; mutex_init(&sched->mutex); - spin_lock_init(&sched->job_list.lock); - INIT_LIST_HEAD(&sched->job_list.head); + spin_lock_init(&sched->job.list.lock); + INIT_LIST_HEAD(&sched->job.list.head); + init_waitqueue_head(&sched->job.wq); return 0; @@ -493,12 +482,16 @@ nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm, return 0; } + static void nouveau_sched_fini(struct nouveau_sched *sched) { struct drm_gpu_scheduler *drm_sched = &sched->base; struct drm_sched_entity *entity = &sched->entity; + rmb(); /* for list_empty to work without lock */ + wait_event(sched->job.wq, list_empty(&sched->job.list.head)); + drm_sched_entity_fini(entity); drm_sched_fini(drm_sched); diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.h b/drivers/gpu/drm/nouveau/nouveau_sched.h index b98c3f0bef30..20cd1da8db73 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sched.h +++ b/drivers/gpu/drm/nouveau/nouveau_sched.h @@ -103,9 +103,12 @@ struct nouveau_sched { struct mutex mutex; struct { - struct list_head head; - spinlock_t lock; - } job_list; + struct { + struct list_head head; + spinlock_t lock; + } list; + struct wait_queue_head wq; + } job; }; int nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm, diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c index ddfc46bc1b3e..48f105239f42 100644 --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -1019,8 +1019,8 @@ bind_validate_map_sparse(struct nouveau_job *job, u64 addr, u64 range) u64 end = addr + range; again: - spin_lock(&sched->job_list.lock); - list_for_each_entry(__job, &sched->job_list.head, entry) { + spin_lock(&sched->job.list.lock); + list_for_each_entry(__job, &sched->job.list.head, entry) { struct nouveau_uvmm_bind_job *bind_job = to_uvmm_bind_job(__job); list_for_each_op(op, &bind_job->ops) { @@ -1030,7 +1030,7 @@ again: if (!(end <= op_addr || addr >= op_end)) { nouveau_uvmm_bind_job_get(bind_job); - spin_unlock(&sched->job_list.lock); + spin_unlock(&sched->job.list.lock); wait_for_completion(&bind_job->complete); nouveau_uvmm_bind_job_put(bind_job); goto again; @@ -1038,7 +1038,7 @@ again: } } } - spin_unlock(&sched->job_list.lock); + spin_unlock(&sched->job.list.lock); } static int diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c index 1116f2d2826e..4d8e9b34702a 100644 --- a/drivers/gpu/drm/panthor/panthor_drv.c +++ b/drivers/gpu/drm/panthor/panthor_drv.c @@ -1094,7 +1094,7 @@ static int panthor_ioctl_group_create(struct drm_device *ddev, void *data, struct drm_panthor_queue_create *queue_args; int ret; - if (!args->queues.count) + if (!args->queues.count || args->queues.count > MAX_CS_PER_CSG) return -EINVAL; ret = PANTHOR_UOBJ_GET_ARRAY(queue_args, &args->queues); diff --git a/drivers/gpu/drm/xe/abi/guc_actions_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_abi.h index 81eb046aeebf..b9f67d7a00d8 100644 --- a/drivers/gpu/drm/xe/abi/guc_actions_abi.h +++ b/drivers/gpu/drm/xe/abi/guc_actions_abi.h @@ -117,6 +117,7 @@ enum xe_guc_action { XE_GUC_ACTION_ENTER_S_STATE = 0x501, XE_GUC_ACTION_EXIT_S_STATE = 0x502, XE_GUC_ACTION_GLOBAL_SCHED_POLICY_CHANGE = 0x506, + XE_GUC_ACTION_UPDATE_SCHEDULING_POLICIES_KLV = 0x509, XE_GUC_ACTION_SCHED_CONTEXT = 0x1000, XE_GUC_ACTION_SCHED_CONTEXT_MODE_SET = 0x1001, XE_GUC_ACTION_SCHED_CONTEXT_MODE_DONE = 0x1002, diff --git a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h index 0366a9da5977..d7719d0e36ca 100644 --- a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h +++ b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h @@ -17,6 +17,7 @@ * | 0 | 31:16 | **KEY** - KLV key identifier | * | | | - `GuC Self Config KLVs`_ | * | | | - `GuC Opt In Feature KLVs`_ | + * | | | - `GuC Scheduling Policies KLVs`_ | * | | | - `GuC VGT Policy KLVs`_ | * | | | - `GuC VF Configuration KLVs`_ | * | | | | @@ -153,6 +154,30 @@ enum { #define GUC_KLV_OPT_IN_FEATURE_DYNAMIC_INHIBIT_CONTEXT_SWITCH_LEN 0u /** + * DOC: GuC Scheduling Policies KLVs + * + * `GuC KLV`_ keys available for use with UPDATE_SCHEDULING_POLICIES_KLV. + * + * _`GUC_KLV_SCHEDULING_POLICIES_RENDER_COMPUTE_YIELD` : 0x1001 + * Some platforms do not allow concurrent execution of RCS and CCS + * workloads from different address spaces. By default, the GuC prioritizes + * RCS submissions over CCS ones, which can lead to CCS workloads being + * significantly (or completely) starved of execution time. This KLV allows + * the driver to specify a quantum (in ms) and a ratio (percentage value + * between 0 and 100), and the GuC will prioritize the CCS for that + * percentage of each quantum. For example, specifying 100ms and 30% will + * make the GuC prioritize the CCS for 30ms of every 100ms. + * Note that this does not necessarly mean that RCS and CCS engines will + * only be active for their percentage of the quantum, as the restriction + * only kicks in if both classes are fully busy with non-compatible address + * spaces; i.e., if one engine is idle or running the same address space, + * a pending job on the other engine will still be submitted to the HW no + * matter what the ratio is + */ +#define GUC_KLV_SCHEDULING_POLICIES_RENDER_COMPUTE_YIELD_KEY 0x1001 +#define GUC_KLV_SCHEDULING_POLICIES_RENDER_COMPUTE_YIELD_LEN 2u + +/** * DOC: GuC VGT Policy KLVs * * `GuC KLV`_ keys available for use with PF2GUC_UPDATE_VGT_POLICY. diff --git a/drivers/gpu/drm/xe/tests/xe_bo.c b/drivers/gpu/drm/xe/tests/xe_bo.c index bb469096d072..7b40cc8be1c9 100644 --- a/drivers/gpu/drm/xe/tests/xe_bo.c +++ b/drivers/gpu/drm/xe/tests/xe_bo.c @@ -236,7 +236,7 @@ static int evict_test_run_tile(struct xe_device *xe, struct xe_tile *tile, struc } xe_bo_lock(external, false); - err = xe_bo_pin_external(external); + err = xe_bo_pin_external(external, false); xe_bo_unlock(external); if (err) { KUNIT_FAIL(test, "external bo pin err=%pe\n", diff --git a/drivers/gpu/drm/xe/tests/xe_dma_buf.c b/drivers/gpu/drm/xe/tests/xe_dma_buf.c index c53f67ce4b0a..121f17c112ec 100644 --- a/drivers/gpu/drm/xe/tests/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/tests/xe_dma_buf.c @@ -89,15 +89,7 @@ static void check_residency(struct kunit *test, struct xe_bo *exported, return; } - /* - * If on different devices, the exporter is kept in system if - * possible, saving a migration step as the transfer is just - * likely as fast from system memory. - */ - if (params->mem_mask & XE_BO_FLAG_SYSTEM) - KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, XE_PL_TT)); - else - KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, mem_type)); + KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, mem_type)); if (params->force_different_devices) KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(imported, XE_PL_TT)); diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 9954bb458ce1..bae7ff2e5927 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -186,6 +186,8 @@ static void try_add_system(struct xe_device *xe, struct xe_bo *bo, bo->placements[*c] = (struct ttm_place) { .mem_type = XE_PL_TT, + .flags = (bo_flags & XE_BO_FLAG_VRAM_MASK) ? + TTM_PL_FLAG_FALLBACK : 0, }; *c += 1; } @@ -2269,6 +2271,7 @@ uint64_t vram_region_gpu_offset(struct ttm_resource *res) /** * xe_bo_pin_external - pin an external BO * @bo: buffer object to be pinned + * @in_place: Pin in current placement, don't attempt to migrate. * * Pin an external (not tied to a VM, can be exported via dma-buf / prime FD) * BO. Unique call compared to xe_bo_pin as this function has it own set of @@ -2276,7 +2279,7 @@ uint64_t vram_region_gpu_offset(struct ttm_resource *res) * * Returns 0 for success, negative error code otherwise. */ -int xe_bo_pin_external(struct xe_bo *bo) +int xe_bo_pin_external(struct xe_bo *bo, bool in_place) { struct xe_device *xe = xe_bo_device(bo); int err; @@ -2285,9 +2288,11 @@ int xe_bo_pin_external(struct xe_bo *bo) xe_assert(xe, xe_bo_is_user(bo)); if (!xe_bo_is_pinned(bo)) { - err = xe_bo_validate(bo, NULL, false); - if (err) - return err; + if (!in_place) { + err = xe_bo_validate(bo, NULL, false); + if (err) + return err; + } spin_lock(&xe->pinned.lock); list_add_tail(&bo->pinned_link, &xe->pinned.late.external); @@ -2440,6 +2445,9 @@ int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict) }; int ret; + if (xe_bo_is_pinned(bo)) + return 0; + if (vm) { lockdep_assert_held(&vm->lock); xe_vm_assert_held(vm); diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index 02e8cde4c6b2..9ce94d252015 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -198,7 +198,7 @@ static inline void xe_bo_unlock_vm_held(struct xe_bo *bo) } } -int xe_bo_pin_external(struct xe_bo *bo); +int xe_bo_pin_external(struct xe_bo *bo, bool in_place); int xe_bo_pin(struct xe_bo *bo); void xe_bo_unpin_external(struct xe_bo *bo); void xe_bo_unpin(struct xe_bo *bo); diff --git a/drivers/gpu/drm/xe/xe_device_sysfs.c b/drivers/gpu/drm/xe/xe_device_sysfs.c index bd9015761aa0..3e3b2d9033a7 100644 --- a/drivers/gpu/drm/xe/xe_device_sysfs.c +++ b/drivers/gpu/drm/xe/xe_device_sysfs.c @@ -311,12 +311,16 @@ int xe_device_sysfs_init(struct xe_device *xe) if (xe->info.platform == XE_BATTLEMAGE) { ret = sysfs_create_files(&dev->kobj, auto_link_downgrade_attrs); if (ret) - return ret; + goto cleanup; ret = late_bind_create_files(dev); if (ret) - return ret; + goto cleanup; } return devm_add_action_or_reset(dev, xe_device_sysfs_fini, xe); + +cleanup: + xe_device_sysfs_fini(xe); + return ret; } diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index d4d2c6854790..7ceb0c90f391 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -553,6 +553,12 @@ struct xe_device { /** @pm_notifier: Our PM notifier to perform actions in response to various PM events. */ struct notifier_block pm_notifier; + /** @pm_block: Completion to block validating tasks on suspend / hibernate prepare */ + struct completion pm_block; + /** @rebind_resume_list: List of wq items to kick on resume. */ + struct list_head rebind_resume_list; + /** @rebind_resume_lock: Lock to protect the rebind_resume_list */ + struct mutex rebind_resume_lock; /** @pmt: Support the PMT driver callback interface */ struct { diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c index 346f857f3837..af64baf872ef 100644 --- a/drivers/gpu/drm/xe/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/xe_dma_buf.c @@ -72,7 +72,7 @@ static int xe_dma_buf_pin(struct dma_buf_attachment *attach) return ret; } - ret = xe_bo_pin_external(bo); + ret = xe_bo_pin_external(bo, true); xe_assert(xe, !ret); return 0; diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index 44364c042ad7..374c831e691b 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -237,6 +237,15 @@ retry: goto err_unlock_list; } + /* + * It's OK to block interruptible here with the vm lock held, since + * on task freezing during suspend / hibernate, the call will + * return -ERESTARTSYS and the IOCTL will be rerun. + */ + err = wait_for_completion_interruptible(&xe->pm_block); + if (err) + goto err_unlock_list; + vm_exec.vm = &vm->gpuvm; vm_exec.flags = DRM_EXEC_INTERRUPTIBLE_WAIT; if (xe_vm_in_lr_mode(vm)) { diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 8991b4aed440..c07edcda99c5 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -151,6 +151,16 @@ err_lrc: return err; } +static void __xe_exec_queue_fini(struct xe_exec_queue *q) +{ + int i; + + q->ops->fini(q); + + for (i = 0; i < q->width; ++i) + xe_lrc_put(q->lrc[i]); +} + struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *vm, u32 logical_mask, u16 width, struct xe_hw_engine *hwe, u32 flags, @@ -181,11 +191,13 @@ struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *v if (xe_exec_queue_uses_pxp(q)) { err = xe_pxp_exec_queue_add(xe->pxp, q); if (err) - goto err_post_alloc; + goto err_post_init; } return q; +err_post_init: + __xe_exec_queue_fini(q); err_post_alloc: __xe_exec_queue_free(q); return ERR_PTR(err); @@ -283,13 +295,11 @@ void xe_exec_queue_destroy(struct kref *ref) xe_exec_queue_put(eq); } - q->ops->fini(q); + q->ops->destroy(q); } void xe_exec_queue_fini(struct xe_exec_queue *q) { - int i; - /* * Before releasing our ref to lrc and xef, accumulate our run ticks * and wakeup any waiters. @@ -298,9 +308,7 @@ void xe_exec_queue_fini(struct xe_exec_queue *q) if (q->xef && atomic_dec_and_test(&q->xef->exec_queue.pending_removal)) wake_up_var(&q->xef->exec_queue.pending_removal); - for (i = 0; i < q->width; ++i) - xe_lrc_put(q->lrc[i]); - + __xe_exec_queue_fini(q); __xe_exec_queue_free(q); } diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index cc1cffb5c87f..1c9d03f2a3e5 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -166,8 +166,14 @@ struct xe_exec_queue_ops { int (*init)(struct xe_exec_queue *q); /** @kill: Kill inflight submissions for backend */ void (*kill)(struct xe_exec_queue *q); - /** @fini: Fini exec queue for submission backend */ + /** @fini: Undoes the init() for submission backend */ void (*fini)(struct xe_exec_queue *q); + /** + * @destroy: Destroy exec queue for submission backend. The backend + * function must call xe_exec_queue_fini() (which will in turn call the + * fini() backend function) to ensure the queue is properly cleaned up. + */ + void (*destroy)(struct xe_exec_queue *q); /** @set_priority: Set priority for exec queue */ int (*set_priority)(struct xe_exec_queue *q, enum xe_exec_queue_priority priority); diff --git a/drivers/gpu/drm/xe/xe_execlist.c b/drivers/gpu/drm/xe/xe_execlist.c index 788f56b066b6..f83d421ac9d3 100644 --- a/drivers/gpu/drm/xe/xe_execlist.c +++ b/drivers/gpu/drm/xe/xe_execlist.c @@ -385,10 +385,20 @@ err_free: return err; } -static void execlist_exec_queue_fini_async(struct work_struct *w) +static void execlist_exec_queue_fini(struct xe_exec_queue *q) +{ + struct xe_execlist_exec_queue *exl = q->execlist; + + drm_sched_entity_fini(&exl->entity); + drm_sched_fini(&exl->sched); + + kfree(exl); +} + +static void execlist_exec_queue_destroy_async(struct work_struct *w) { struct xe_execlist_exec_queue *ee = - container_of(w, struct xe_execlist_exec_queue, fini_async); + container_of(w, struct xe_execlist_exec_queue, destroy_async); struct xe_exec_queue *q = ee->q; struct xe_execlist_exec_queue *exl = q->execlist; struct xe_device *xe = gt_to_xe(q->gt); @@ -401,10 +411,6 @@ static void execlist_exec_queue_fini_async(struct work_struct *w) list_del(&exl->active_link); spin_unlock_irqrestore(&exl->port->lock, flags); - drm_sched_entity_fini(&exl->entity); - drm_sched_fini(&exl->sched); - kfree(exl); - xe_exec_queue_fini(q); } @@ -413,10 +419,10 @@ static void execlist_exec_queue_kill(struct xe_exec_queue *q) /* NIY */ } -static void execlist_exec_queue_fini(struct xe_exec_queue *q) +static void execlist_exec_queue_destroy(struct xe_exec_queue *q) { - INIT_WORK(&q->execlist->fini_async, execlist_exec_queue_fini_async); - queue_work(system_unbound_wq, &q->execlist->fini_async); + INIT_WORK(&q->execlist->destroy_async, execlist_exec_queue_destroy_async); + queue_work(system_unbound_wq, &q->execlist->destroy_async); } static int execlist_exec_queue_set_priority(struct xe_exec_queue *q, @@ -467,6 +473,7 @@ static const struct xe_exec_queue_ops execlist_exec_queue_ops = { .init = execlist_exec_queue_init, .kill = execlist_exec_queue_kill, .fini = execlist_exec_queue_fini, + .destroy = execlist_exec_queue_destroy, .set_priority = execlist_exec_queue_set_priority, .set_timeslice = execlist_exec_queue_set_timeslice, .set_preempt_timeout = execlist_exec_queue_set_preempt_timeout, diff --git a/drivers/gpu/drm/xe/xe_execlist_types.h b/drivers/gpu/drm/xe/xe_execlist_types.h index 415140936f11..92c4ba52db0c 100644 --- a/drivers/gpu/drm/xe/xe_execlist_types.h +++ b/drivers/gpu/drm/xe/xe_execlist_types.h @@ -42,7 +42,7 @@ struct xe_execlist_exec_queue { bool has_run; - struct work_struct fini_async; + struct work_struct destroy_async; enum xe_exec_queue_priority active_priority; struct list_head active_link; diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index c8eda36546d3..17634195cdc2 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -41,6 +41,7 @@ #include "xe_gt_topology.h" #include "xe_guc_exec_queue_types.h" #include "xe_guc_pc.h" +#include "xe_guc_submit.h" #include "xe_hw_fence.h" #include "xe_hw_engine_class_sysfs.h" #include "xe_irq.h" @@ -97,7 +98,7 @@ void xe_gt_sanitize(struct xe_gt *gt) * FIXME: if xe_uc_sanitize is called here, on TGL driver will not * reload */ - gt->uc.guc.submission_state.enabled = false; + xe_guc_submit_disable(>->uc.guc); } static void xe_gt_enable_host_l2_vram(struct xe_gt *gt) diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c index 494909f74eb2..d84831a03610 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c @@ -1632,7 +1632,6 @@ static u64 pf_estimate_fair_lmem(struct xe_gt *gt, unsigned int num_vfs) u64 fair; fair = div_u64(available, num_vfs); - fair = rounddown_pow_of_two(fair); /* XXX: ttm_vram_mgr & drm_buddy limitation */ fair = ALIGN_DOWN(fair, alignment); #ifdef MAX_FAIR_LMEM fair = min_t(u64, MAX_FAIR_LMEM, fair); diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c index b1d1d6da3758..270fc3792493 100644 --- a/drivers/gpu/drm/xe/xe_guc.c +++ b/drivers/gpu/drm/xe/xe_guc.c @@ -880,9 +880,7 @@ int xe_guc_post_load_init(struct xe_guc *guc) return ret; } - guc->submission_state.enabled = true; - - return 0; + return xe_guc_submit_enable(guc); } int xe_guc_reset(struct xe_guc *guc) @@ -1579,7 +1577,7 @@ void xe_guc_sanitize(struct xe_guc *guc) { xe_uc_fw_sanitize(&guc->fw); xe_guc_ct_disable(&guc->ct); - guc->submission_state.enabled = false; + xe_guc_submit_disable(guc); } int xe_guc_reset_prepare(struct xe_guc *guc) diff --git a/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h b/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h index a3f421e2adc0..c30c0e3ccbbb 100644 --- a/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h @@ -35,8 +35,8 @@ struct xe_guc_exec_queue { struct xe_sched_msg static_msgs[MAX_STATIC_MSG_TYPE]; /** @lr_tdr: long running TDR worker */ struct work_struct lr_tdr; - /** @fini_async: do final fini async from this worker */ - struct work_struct fini_async; + /** @destroy_async: do final destroy async from this worker */ + struct work_struct destroy_async; /** @resume_time: time of last resume */ u64 resume_time; /** @state: GuC specific state for this xe_exec_queue */ diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index cafb47711e9b..0104afbc941c 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -32,6 +32,7 @@ #include "xe_guc_ct.h" #include "xe_guc_exec_queue_types.h" #include "xe_guc_id_mgr.h" +#include "xe_guc_klv_helpers.h" #include "xe_guc_submit_types.h" #include "xe_hw_engine.h" #include "xe_hw_fence.h" @@ -316,6 +317,71 @@ int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids) return drmm_add_action_or_reset(&xe->drm, guc_submit_fini, guc); } +/* + * Given that we want to guarantee enough RCS throughput to avoid missing + * frames, we set the yield policy to 20% of each 80ms interval. + */ +#define RC_YIELD_DURATION 80 /* in ms */ +#define RC_YIELD_RATIO 20 /* in percent */ +static u32 *emit_render_compute_yield_klv(u32 *emit) +{ + *emit++ = PREP_GUC_KLV_TAG(SCHEDULING_POLICIES_RENDER_COMPUTE_YIELD); + *emit++ = RC_YIELD_DURATION; + *emit++ = RC_YIELD_RATIO; + + return emit; +} + +#define SCHEDULING_POLICY_MAX_DWORDS 16 +static int guc_init_global_schedule_policy(struct xe_guc *guc) +{ + u32 data[SCHEDULING_POLICY_MAX_DWORDS]; + u32 *emit = data; + u32 count = 0; + int ret; + + if (GUC_SUBMIT_VER(guc) < MAKE_GUC_VER(1, 1, 0)) + return 0; + + *emit++ = XE_GUC_ACTION_UPDATE_SCHEDULING_POLICIES_KLV; + + if (CCS_MASK(guc_to_gt(guc))) + emit = emit_render_compute_yield_klv(emit); + + count = emit - data; + if (count > 1) { + xe_assert(guc_to_xe(guc), count <= SCHEDULING_POLICY_MAX_DWORDS); + + ret = xe_guc_ct_send_block(&guc->ct, data, count); + if (ret < 0) { + xe_gt_err(guc_to_gt(guc), + "failed to enable GuC sheduling policies: %pe\n", + ERR_PTR(ret)); + return ret; + } + } + + return 0; +} + +int xe_guc_submit_enable(struct xe_guc *guc) +{ + int ret; + + ret = guc_init_global_schedule_policy(guc); + if (ret) + return ret; + + guc->submission_state.enabled = true; + + return 0; +} + +void xe_guc_submit_disable(struct xe_guc *guc) +{ + guc->submission_state.enabled = false; +} + static void __release_guc_id(struct xe_guc *guc, struct xe_exec_queue *q, u32 xa_count) { int i; @@ -1277,48 +1343,57 @@ rearm: return DRM_GPU_SCHED_STAT_NO_HANG; } -static void __guc_exec_queue_fini_async(struct work_struct *w) +static void guc_exec_queue_fini(struct xe_exec_queue *q) +{ + struct xe_guc_exec_queue *ge = q->guc; + struct xe_guc *guc = exec_queue_to_guc(q); + + release_guc_id(guc, q); + xe_sched_entity_fini(&ge->entity); + xe_sched_fini(&ge->sched); + + /* + * RCU free due sched being exported via DRM scheduler fences + * (timeline name). + */ + kfree_rcu(ge, rcu); +} + +static void __guc_exec_queue_destroy_async(struct work_struct *w) { struct xe_guc_exec_queue *ge = - container_of(w, struct xe_guc_exec_queue, fini_async); + container_of(w, struct xe_guc_exec_queue, destroy_async); struct xe_exec_queue *q = ge->q; struct xe_guc *guc = exec_queue_to_guc(q); xe_pm_runtime_get(guc_to_xe(guc)); trace_xe_exec_queue_destroy(q); - release_guc_id(guc, q); if (xe_exec_queue_is_lr(q)) cancel_work_sync(&ge->lr_tdr); /* Confirm no work left behind accessing device structures */ cancel_delayed_work_sync(&ge->sched.base.work_tdr); - xe_sched_entity_fini(&ge->entity); - xe_sched_fini(&ge->sched); - /* - * RCU free due sched being exported via DRM scheduler fences - * (timeline name). - */ - kfree_rcu(ge, rcu); xe_exec_queue_fini(q); + xe_pm_runtime_put(guc_to_xe(guc)); } -static void guc_exec_queue_fini_async(struct xe_exec_queue *q) +static void guc_exec_queue_destroy_async(struct xe_exec_queue *q) { struct xe_guc *guc = exec_queue_to_guc(q); struct xe_device *xe = guc_to_xe(guc); - INIT_WORK(&q->guc->fini_async, __guc_exec_queue_fini_async); + INIT_WORK(&q->guc->destroy_async, __guc_exec_queue_destroy_async); /* We must block on kernel engines so slabs are empty on driver unload */ if (q->flags & EXEC_QUEUE_FLAG_PERMANENT || exec_queue_wedged(q)) - __guc_exec_queue_fini_async(&q->guc->fini_async); + __guc_exec_queue_destroy_async(&q->guc->destroy_async); else - queue_work(xe->destroy_wq, &q->guc->fini_async); + queue_work(xe->destroy_wq, &q->guc->destroy_async); } -static void __guc_exec_queue_fini(struct xe_guc *guc, struct xe_exec_queue *q) +static void __guc_exec_queue_destroy(struct xe_guc *guc, struct xe_exec_queue *q) { /* * Might be done from within the GPU scheduler, need to do async as we @@ -1327,7 +1402,7 @@ static void __guc_exec_queue_fini(struct xe_guc *guc, struct xe_exec_queue *q) * this we and don't really care when everything is fini'd, just that it * is. */ - guc_exec_queue_fini_async(q); + guc_exec_queue_destroy_async(q); } static void __guc_exec_queue_process_msg_cleanup(struct xe_sched_msg *msg) @@ -1341,7 +1416,7 @@ static void __guc_exec_queue_process_msg_cleanup(struct xe_sched_msg *msg) if (exec_queue_registered(q)) disable_scheduling_deregister(guc, q); else - __guc_exec_queue_fini(guc, q); + __guc_exec_queue_destroy(guc, q); } static bool guc_exec_queue_allowed_to_change_state(struct xe_exec_queue *q) @@ -1574,14 +1649,14 @@ static bool guc_exec_queue_try_add_msg(struct xe_exec_queue *q, #define STATIC_MSG_CLEANUP 0 #define STATIC_MSG_SUSPEND 1 #define STATIC_MSG_RESUME 2 -static void guc_exec_queue_fini(struct xe_exec_queue *q) +static void guc_exec_queue_destroy(struct xe_exec_queue *q) { struct xe_sched_msg *msg = q->guc->static_msgs + STATIC_MSG_CLEANUP; if (!(q->flags & EXEC_QUEUE_FLAG_PERMANENT) && !exec_queue_wedged(q)) guc_exec_queue_add_msg(q, msg, CLEANUP); else - __guc_exec_queue_fini(exec_queue_to_guc(q), q); + __guc_exec_queue_destroy(exec_queue_to_guc(q), q); } static int guc_exec_queue_set_priority(struct xe_exec_queue *q, @@ -1711,6 +1786,7 @@ static const struct xe_exec_queue_ops guc_exec_queue_ops = { .init = guc_exec_queue_init, .kill = guc_exec_queue_kill, .fini = guc_exec_queue_fini, + .destroy = guc_exec_queue_destroy, .set_priority = guc_exec_queue_set_priority, .set_timeslice = guc_exec_queue_set_timeslice, .set_preempt_timeout = guc_exec_queue_set_preempt_timeout, @@ -1732,7 +1808,7 @@ static void guc_exec_queue_stop(struct xe_guc *guc, struct xe_exec_queue *q) if (exec_queue_extra_ref(q) || xe_exec_queue_is_lr(q)) xe_exec_queue_put(q); else if (exec_queue_destroyed(q)) - __guc_exec_queue_fini(guc, q); + __guc_exec_queue_destroy(guc, q); } if (q->guc->suspend_pending) { set_exec_queue_suspended(q); @@ -1989,7 +2065,7 @@ static void handle_deregister_done(struct xe_guc *guc, struct xe_exec_queue *q) if (exec_queue_extra_ref(q) || xe_exec_queue_is_lr(q)) xe_exec_queue_put(q); else - __guc_exec_queue_fini(guc, q); + __guc_exec_queue_destroy(guc, q); } int xe_guc_deregister_done_handler(struct xe_guc *guc, u32 *msg, u32 len) diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h index 9b71a986c6ca..0d126b807c10 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.h +++ b/drivers/gpu/drm/xe/xe_guc_submit.h @@ -13,6 +13,8 @@ struct xe_exec_queue; struct xe_guc; int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids); +int xe_guc_submit_enable(struct xe_guc *guc); +void xe_guc_submit_disable(struct xe_guc *guc); int xe_guc_submit_reset_prepare(struct xe_guc *guc); void xe_guc_submit_reset_wait(struct xe_guc *guc); diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c index c17ed1ae8649..c5b63e10bb91 100644 --- a/drivers/gpu/drm/xe/xe_hwmon.c +++ b/drivers/gpu/drm/xe/xe_hwmon.c @@ -286,7 +286,7 @@ static struct xe_reg xe_hwmon_get_reg(struct xe_hwmon *hwmon, enum xe_hwmon_reg */ static void xe_hwmon_power_max_read(struct xe_hwmon *hwmon, u32 attr, int channel, long *value) { - u64 reg_val = 0, min, max; + u32 reg_val = 0; struct xe_device *xe = hwmon->xe; struct xe_reg rapl_limit, pkg_power_sku; struct xe_mmio *mmio = xe_root_tile_mmio(xe); @@ -294,7 +294,7 @@ static void xe_hwmon_power_max_read(struct xe_hwmon *hwmon, u32 attr, int channe mutex_lock(&hwmon->hwmon_lock); if (hwmon->xe->info.has_mbx_power_limits) { - xe_hwmon_pcode_read_power_limit(hwmon, attr, channel, (u32 *)®_val); + xe_hwmon_pcode_read_power_limit(hwmon, attr, channel, ®_val); } else { rapl_limit = xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT, channel); pkg_power_sku = xe_hwmon_get_reg(hwmon, REG_PKG_POWER_SKU, channel); @@ -304,19 +304,21 @@ static void xe_hwmon_power_max_read(struct xe_hwmon *hwmon, u32 attr, int channe /* Check if PL limits are disabled. */ if (!(reg_val & PWR_LIM_EN)) { *value = PL_DISABLE; - drm_info(&hwmon->xe->drm, "%s disabled for channel %d, val 0x%016llx\n", + drm_info(&hwmon->xe->drm, "%s disabled for channel %d, val 0x%08x\n", PWR_ATTR_TO_STR(attr), channel, reg_val); goto unlock; } reg_val = REG_FIELD_GET(PWR_LIM_VAL, reg_val); - *value = mul_u64_u32_shr(reg_val, SF_POWER, hwmon->scl_shift_power); + *value = mul_u32_u32(reg_val, SF_POWER) >> hwmon->scl_shift_power; /* For platforms with mailbox power limit support clamping would be done by pcode. */ if (!hwmon->xe->info.has_mbx_power_limits) { - reg_val = xe_mmio_read64_2x32(mmio, pkg_power_sku); - min = REG_FIELD_GET(PKG_MIN_PWR, reg_val); - max = REG_FIELD_GET(PKG_MAX_PWR, reg_val); + u64 pkg_pwr, min, max; + + pkg_pwr = xe_mmio_read64_2x32(mmio, pkg_power_sku); + min = REG_FIELD_GET(PKG_MIN_PWR, pkg_pwr); + max = REG_FIELD_GET(PKG_MAX_PWR, pkg_pwr); min = mul_u64_u32_shr(min, SF_POWER, hwmon->scl_shift_power); max = mul_u64_u32_shr(max, SF_POWER, hwmon->scl_shift_power); if (min && max) @@ -493,8 +495,8 @@ xe_hwmon_power_max_interval_show(struct device *dev, struct device_attribute *at { struct xe_hwmon *hwmon = dev_get_drvdata(dev); struct xe_mmio *mmio = xe_root_tile_mmio(hwmon->xe); - u32 x, y, x_w = 2; /* 2 bits */ - u64 r, tau4, out; + u32 reg_val, x, y, x_w = 2; /* 2 bits */ + u64 tau4, out; int channel = (to_sensor_dev_attr(attr)->index % 2) ? CHANNEL_PKG : CHANNEL_CARD; u32 power_attr = (to_sensor_dev_attr(attr)->index > 1) ? PL2_HWMON_ATTR : PL1_HWMON_ATTR; @@ -505,23 +507,24 @@ xe_hwmon_power_max_interval_show(struct device *dev, struct device_attribute *at mutex_lock(&hwmon->hwmon_lock); if (hwmon->xe->info.has_mbx_power_limits) { - ret = xe_hwmon_pcode_read_power_limit(hwmon, power_attr, channel, (u32 *)&r); + ret = xe_hwmon_pcode_read_power_limit(hwmon, power_attr, channel, ®_val); if (ret) { drm_err(&hwmon->xe->drm, - "power interval read fail, ch %d, attr %d, r 0%llx, ret %d\n", - channel, power_attr, r, ret); - r = 0; + "power interval read fail, ch %d, attr %d, val 0x%08x, ret %d\n", + channel, power_attr, reg_val, ret); + reg_val = 0; } } else { - r = xe_mmio_read32(mmio, xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT, channel)); + reg_val = xe_mmio_read32(mmio, xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT, + channel)); } mutex_unlock(&hwmon->hwmon_lock); xe_pm_runtime_put(hwmon->xe); - x = REG_FIELD_GET(PWR_LIM_TIME_X, r); - y = REG_FIELD_GET(PWR_LIM_TIME_Y, r); + x = REG_FIELD_GET(PWR_LIM_TIME_X, reg_val); + y = REG_FIELD_GET(PWR_LIM_TIME_Y, reg_val); /* * tau = (1 + (x / 4)) * power(2,y), x = bits(23:22), y = bits(21:17) diff --git a/drivers/gpu/drm/xe/xe_nvm.c b/drivers/gpu/drm/xe/xe_nvm.c index 61b0a1531a53..2cfe9eb67391 100644 --- a/drivers/gpu/drm/xe/xe_nvm.c +++ b/drivers/gpu/drm/xe/xe_nvm.c @@ -35,6 +35,10 @@ static const struct intel_dg_nvm_region regions[INTEL_DG_NVM_REGIONS] = { static void xe_nvm_release_dev(struct device *dev) { + struct auxiliary_device *aux = container_of(dev, struct auxiliary_device, dev); + struct intel_dg_nvm_dev *nvm = container_of(aux, struct intel_dg_nvm_dev, aux_dev); + + kfree(nvm); } static bool xe_nvm_non_posted_erase(struct xe_device *xe) @@ -162,6 +166,5 @@ void xe_nvm_fini(struct xe_device *xe) auxiliary_device_delete(&nvm->aux_dev); auxiliary_device_uninit(&nvm->aux_dev); - kfree(nvm); xe->nvm = NULL; } diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c index e279b47ba03b..bb9b6ecad2af 100644 --- a/drivers/gpu/drm/xe/xe_pm.c +++ b/drivers/gpu/drm/xe/xe_pm.c @@ -24,6 +24,7 @@ #include "xe_pcode.h" #include "xe_pxp.h" #include "xe_trace.h" +#include "xe_vm.h" #include "xe_wa.h" /** @@ -290,6 +291,19 @@ static u32 vram_threshold_value(struct xe_device *xe) return DEFAULT_VRAM_THRESHOLD; } +static void xe_pm_wake_rebind_workers(struct xe_device *xe) +{ + struct xe_vm *vm, *next; + + mutex_lock(&xe->rebind_resume_lock); + list_for_each_entry_safe(vm, next, &xe->rebind_resume_list, + preempt.pm_activate_link) { + list_del_init(&vm->preempt.pm_activate_link); + xe_vm_resume_rebind_worker(vm); + } + mutex_unlock(&xe->rebind_resume_lock); +} + static int xe_pm_notifier_callback(struct notifier_block *nb, unsigned long action, void *data) { @@ -299,30 +313,30 @@ static int xe_pm_notifier_callback(struct notifier_block *nb, switch (action) { case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: + reinit_completion(&xe->pm_block); xe_pm_runtime_get(xe); err = xe_bo_evict_all_user(xe); - if (err) { + if (err) drm_dbg(&xe->drm, "Notifier evict user failed (%d)\n", err); - xe_pm_runtime_put(xe); - break; - } err = xe_bo_notifier_prepare_all_pinned(xe); - if (err) { + if (err) drm_dbg(&xe->drm, "Notifier prepare pin failed (%d)\n", err); - xe_pm_runtime_put(xe); - } + /* + * Keep the runtime pm reference until post hibernation / post suspend to + * avoid a runtime suspend interfering with evicted objects or backup + * allocations. + */ break; case PM_POST_HIBERNATION: case PM_POST_SUSPEND: + complete_all(&xe->pm_block); + xe_pm_wake_rebind_workers(xe); xe_bo_notifier_unprepare_all_pinned(xe); xe_pm_runtime_put(xe); break; } - if (err) - return NOTIFY_BAD; - return NOTIFY_DONE; } @@ -344,6 +358,14 @@ int xe_pm_init(struct xe_device *xe) if (err) return err; + err = drmm_mutex_init(&xe->drm, &xe->rebind_resume_lock); + if (err) + goto err_unregister; + + init_completion(&xe->pm_block); + complete_all(&xe->pm_block); + INIT_LIST_HEAD(&xe->rebind_resume_list); + /* For now suspend/resume is only allowed with GuC */ if (!xe_device_uc_enabled(xe)) return 0; diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c index 41705f5d52e3..8f7b0add2364 100644 --- a/drivers/gpu/drm/xe/xe_survivability_mode.c +++ b/drivers/gpu/drm/xe/xe_survivability_mode.c @@ -41,6 +41,8 @@ * * # echo 1 > /sys/kernel/config/xe/0000:03:00.0/survivability_mode * + * It is the responsibility of the user to clear the mode once firmware flash is complete. + * * Refer :ref:`xe_configfs` for more details on how to use configfs * * Survivability mode is indicated by the below admin-only readable sysfs which provides additional @@ -147,7 +149,6 @@ static void xe_survivability_mode_fini(void *arg) struct pci_dev *pdev = to_pci_dev(xe->drm.dev); struct device *dev = &pdev->dev; - xe_configfs_clear_survivability_mode(pdev); sysfs_remove_file(&dev->kobj, &dev_attr_survivability_mode.attr); } diff --git a/drivers/gpu/drm/xe/xe_tile_sysfs.c b/drivers/gpu/drm/xe/xe_tile_sysfs.c index b804234a6551..9e1236a9ec67 100644 --- a/drivers/gpu/drm/xe/xe_tile_sysfs.c +++ b/drivers/gpu/drm/xe/xe_tile_sysfs.c @@ -44,16 +44,18 @@ int xe_tile_sysfs_init(struct xe_tile *tile) kt->tile = tile; err = kobject_add(&kt->base, &dev->kobj, "tile%d", tile->id); - if (err) { - kobject_put(&kt->base); - return err; - } + if (err) + goto err_object; tile->sysfs = &kt->base; err = xe_vram_freq_sysfs_init(tile); if (err) - return err; + goto err_object; return devm_add_action_or_reset(xe->drm.dev, tile_sysfs_fini, tile); + +err_object: + kobject_put(&kt->base); + return err; } diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index d60c4b115304..5146999d27fa 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -240,8 +240,8 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q) pfence = xe_preempt_fence_create(q, q->lr.context, ++q->lr.seqno); - if (!pfence) { - err = -ENOMEM; + if (IS_ERR(pfence)) { + err = PTR_ERR(pfence); goto out_fini; } @@ -393,6 +393,9 @@ static int xe_gpuvm_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec) list_move_tail(&gpuva_to_vma(gpuva)->combined_links.rebind, &vm->rebind_list); + if (!try_wait_for_completion(&vm->xe->pm_block)) + return -EAGAIN; + ret = xe_bo_validate(gem_to_xe_bo(vm_bo->obj), vm, false); if (ret) return ret; @@ -479,6 +482,33 @@ static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm, return xe_vm_validate_rebind(vm, exec, vm->preempt.num_exec_queues); } +static bool vm_suspend_rebind_worker(struct xe_vm *vm) +{ + struct xe_device *xe = vm->xe; + bool ret = false; + + mutex_lock(&xe->rebind_resume_lock); + if (!try_wait_for_completion(&vm->xe->pm_block)) { + ret = true; + list_move_tail(&vm->preempt.pm_activate_link, &xe->rebind_resume_list); + } + mutex_unlock(&xe->rebind_resume_lock); + + return ret; +} + +/** + * xe_vm_resume_rebind_worker() - Resume the rebind worker. + * @vm: The vm whose preempt worker to resume. + * + * Resume a preempt worker that was previously suspended by + * vm_suspend_rebind_worker(). + */ +void xe_vm_resume_rebind_worker(struct xe_vm *vm) +{ + queue_work(vm->xe->ordered_wq, &vm->preempt.rebind_work); +} + static void preempt_rebind_work_func(struct work_struct *w) { struct xe_vm *vm = container_of(w, struct xe_vm, preempt.rebind_work); @@ -502,6 +532,11 @@ static void preempt_rebind_work_func(struct work_struct *w) } retry: + if (!try_wait_for_completion(&vm->xe->pm_block) && vm_suspend_rebind_worker(vm)) { + up_write(&vm->lock); + return; + } + if (xe_vm_userptr_check_repin(vm)) { err = xe_vm_userptr_pin(vm); if (err) @@ -1714,6 +1749,7 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef) if (flags & XE_VM_FLAG_LR_MODE) { INIT_WORK(&vm->preempt.rebind_work, preempt_rebind_work_func); xe_pm_runtime_get_noresume(xe); + INIT_LIST_HEAD(&vm->preempt.pm_activate_link); } if (flags & XE_VM_FLAG_FAULT_MODE) { @@ -1895,8 +1931,12 @@ void xe_vm_close_and_put(struct xe_vm *vm) xe_assert(xe, !vm->preempt.num_exec_queues); xe_vm_close(vm); - if (xe_vm_in_preempt_fence_mode(vm)) + if (xe_vm_in_preempt_fence_mode(vm)) { + mutex_lock(&xe->rebind_resume_lock); + list_del_init(&vm->preempt.pm_activate_link); + mutex_unlock(&xe->rebind_resume_lock); flush_work(&vm->preempt.rebind_work); + } if (xe_vm_in_fault_mode(vm)) xe_svm_close(vm); diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h index 2ecb417c19a2..82b112795807 100644 --- a/drivers/gpu/drm/xe/xe_vm.h +++ b/drivers/gpu/drm/xe/xe_vm.h @@ -273,6 +273,8 @@ struct dma_fence *xe_vm_bind_kernel_bo(struct xe_vm *vm, struct xe_bo *bo, struct xe_exec_queue *q, u64 addr, enum xe_cache_level cache_lvl); +void xe_vm_resume_rebind_worker(struct xe_vm *vm); + /** * xe_vm_resv() - Return's the vm's reservation object * @vm: The vm diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index 8a07feef503b..6058cf739388 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -293,6 +293,11 @@ struct xe_vm { * BOs */ struct work_struct rebind_work; + /** + * @preempt.pm_activate_link: Link to list of rebind workers to be + * kicked on resume. + */ + struct list_head pm_activate_link; } preempt; /** @um: unified memory state */ diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules index e990f20eccfe..710f4423726c 100644 --- a/drivers/gpu/drm/xe/xe_wa_oob.rules +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules @@ -30,7 +30,8 @@ 16022287689 GRAPHICS_VERSION(2001) GRAPHICS_VERSION(2004) 13011645652 GRAPHICS_VERSION(2004) - GRAPHICS_VERSION(3001) + GRAPHICS_VERSION_RANGE(3000, 3001) + GRAPHICS_VERSION(3003) 14022293748 GRAPHICS_VERSION_RANGE(2001, 2002) GRAPHICS_VERSION(2004) GRAPHICS_VERSION_RANGE(3000, 3001) diff --git a/drivers/gpu/nova-core/Kconfig b/drivers/gpu/nova-core/Kconfig index 8726d80d6ba4..20d3e6d0d796 100644 --- a/drivers/gpu/nova-core/Kconfig +++ b/drivers/gpu/nova-core/Kconfig @@ -1,5 +1,6 @@ config NOVA_CORE tristate "Nova Core GPU driver" + depends on 64BIT depends on PCI depends on RUST depends on RUST_FW_LOADER_ABSTRACTIONS diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 4c94297e17e6..d72e89c25e50 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -422,6 +422,7 @@ static const struct xpad_device { { 0x3537, 0x1010, "GameSir G7 SE", 0, XTYPE_XBOXONE }, { 0x366c, 0x0005, "ByoWave Proteus Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE, FLAG_DELAY_INIT }, { 0x3767, 0x0101, "Fanatec Speedster 3 Forceshock Wheel", 0, XTYPE_XBOX }, + { 0x37d7, 0x2501, "Flydigi Apex 5", 0, XTYPE_XBOX360 }, { 0x413d, 0x2104, "Black Shark Green Ghost Gamepad", 0, XTYPE_XBOX360 }, { 0xffff, 0xffff, "Chinese-made Xbox Controller", 0, XTYPE_XBOX }, { 0x0000, 0x0000, "Generic X-Box pad", 0, XTYPE_UNKNOWN } @@ -578,6 +579,7 @@ static const struct usb_device_id xpad_table[] = { XPAD_XBOX360_VENDOR(0x3537), /* GameSir Controllers */ XPAD_XBOXONE_VENDOR(0x3537), /* GameSir Controllers */ XPAD_XBOXONE_VENDOR(0x366c), /* ByoWave controllers */ + XPAD_XBOX360_VENDOR(0x37d7), /* Flydigi Controllers */ XPAD_XBOX360_VENDOR(0x413d), /* Black Shark Green Ghost Controller */ { } }; diff --git a/drivers/input/keyboard/mtk-pmic-keys.c b/drivers/input/keyboard/mtk-pmic-keys.c index 50e2e792c91d..c78d9f6d97c4 100644 --- a/drivers/input/keyboard/mtk-pmic-keys.c +++ b/drivers/input/keyboard/mtk-pmic-keys.c @@ -55,6 +55,7 @@ struct mtk_pmic_regs { const struct mtk_pmic_keys_regs keys_regs[MTK_PMIC_MAX_KEY_COUNT]; u32 pmic_rst_reg; u32 rst_lprst_mask; /* Long-press reset timeout bitmask */ + bool key_release_irq; }; static const struct mtk_pmic_regs mt6397_regs = { @@ -116,6 +117,7 @@ static const struct mtk_pmic_regs mt6358_regs = { MTK_PMIC_HOMEKEY_RST), .pmic_rst_reg = MT6358_TOP_RST_MISC, .rst_lprst_mask = MTK_PMIC_RST_DU_MASK, + .key_release_irq = true, }; static const struct mtk_pmic_regs mt6359_regs = { @@ -129,6 +131,7 @@ static const struct mtk_pmic_regs mt6359_regs = { MTK_PMIC_HOMEKEY_RST), .pmic_rst_reg = MT6359_TOP_RST_MISC, .rst_lprst_mask = MTK_PMIC_RST_DU_MASK, + .key_release_irq = true, }; struct mtk_pmic_keys_info { @@ -368,7 +371,7 @@ static int mtk_pmic_keys_probe(struct platform_device *pdev) if (keys->keys[index].irq < 0) return keys->keys[index].irq; - if (of_device_is_compatible(node, "mediatek,mt6358-keys")) { + if (mtk_pmic_regs->key_release_irq) { keys->keys[index].irq_r = platform_get_irq_byname(pdev, irqnames_r[index]); diff --git a/drivers/input/misc/iqs7222.c b/drivers/input/misc/iqs7222.c index 6fac31c0d99f..ff23219a582a 100644 --- a/drivers/input/misc/iqs7222.c +++ b/drivers/input/misc/iqs7222.c @@ -2427,6 +2427,9 @@ static int iqs7222_parse_chan(struct iqs7222_private *iqs7222, if (error) return error; + if (!iqs7222->kp_type[chan_index][i]) + continue; + if (!dev_desc->event_offset) continue; diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 6ed9fc34948c..1caa6c4ca435 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -1155,6 +1155,20 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "XxHP4NAx"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "XxKK4NAx_XxSP4NAx"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, /* * A lot of modern Clevo barebones have touchpad and/or keyboard issues * after suspend fixable with the forcenorestore quirk. diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 5219d7ddfdaa..95f63c5f6159 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -555,6 +555,7 @@ struct gcr3_tbl_info { }; struct amd_io_pgtable { + seqcount_t seqcount; /* Protects root/mode update */ struct io_pgtable pgtbl; int mode; u64 *root; diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 8de689b2c5ed..ba9e582a8bbe 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -1455,12 +1455,12 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, PCI_FUNC(e->devid)); devid = e->devid; - for (dev_i = devid_start; dev_i <= devid; ++dev_i) { - if (alias) + if (alias) { + for (dev_i = devid_start; dev_i <= devid; ++dev_i) pci_seg->alias_table[dev_i] = devid_to; + set_dev_entry_from_acpi(iommu, devid_to, flags, ext_flags); } set_dev_entry_from_acpi_range(iommu, devid_start, devid, flags, ext_flags); - set_dev_entry_from_acpi(iommu, devid_to, flags, ext_flags); break; case IVHD_DEV_SPECIAL: { u8 handle, type; @@ -3067,7 +3067,8 @@ static int __init early_amd_iommu_init(void) if (!boot_cpu_has(X86_FEATURE_CX16)) { pr_err("Failed to initialize. The CMPXCHG16B feature is required.\n"); - return -EINVAL; + ret = -EINVAL; + goto out; } /* diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c index a91e71f981ef..70c2f5b1631b 100644 --- a/drivers/iommu/amd/io_pgtable.c +++ b/drivers/iommu/amd/io_pgtable.c @@ -17,6 +17,7 @@ #include <linux/slab.h> #include <linux/types.h> #include <linux/dma-mapping.h> +#include <linux/seqlock.h> #include <asm/barrier.h> @@ -130,8 +131,11 @@ static bool increase_address_space(struct amd_io_pgtable *pgtable, *pte = PM_LEVEL_PDE(pgtable->mode, iommu_virt_to_phys(pgtable->root)); + write_seqcount_begin(&pgtable->seqcount); pgtable->root = pte; pgtable->mode += 1; + write_seqcount_end(&pgtable->seqcount); + amd_iommu_update_and_flush_device_table(domain); pte = NULL; @@ -153,6 +157,7 @@ static u64 *alloc_pte(struct amd_io_pgtable *pgtable, { unsigned long last_addr = address + (page_size - 1); struct io_pgtable_cfg *cfg = &pgtable->pgtbl.cfg; + unsigned int seqcount; int level, end_lvl; u64 *pte, *page; @@ -170,8 +175,14 @@ static u64 *alloc_pte(struct amd_io_pgtable *pgtable, } - level = pgtable->mode - 1; - pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + do { + seqcount = read_seqcount_begin(&pgtable->seqcount); + + level = pgtable->mode - 1; + pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + } while (read_seqcount_retry(&pgtable->seqcount, seqcount)); + + address = PAGE_SIZE_ALIGN(address, page_size); end_lvl = PAGE_SIZE_LEVEL(page_size); @@ -249,6 +260,7 @@ static u64 *fetch_pte(struct amd_io_pgtable *pgtable, unsigned long *page_size) { int level; + unsigned int seqcount; u64 *pte; *page_size = 0; @@ -256,8 +268,12 @@ static u64 *fetch_pte(struct amd_io_pgtable *pgtable, if (address > PM_LEVEL_SIZE(pgtable->mode)) return NULL; - level = pgtable->mode - 1; - pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + do { + seqcount = read_seqcount_begin(&pgtable->seqcount); + level = pgtable->mode - 1; + pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + } while (read_seqcount_retry(&pgtable->seqcount, seqcount)); + *page_size = PTE_LEVEL_PAGE_SIZE(level); while (level > 0) { @@ -541,6 +557,7 @@ static struct io_pgtable *v1_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo if (!pgtable->root) return NULL; pgtable->mode = PAGE_MODE_3_LEVEL; + seqcount_init(&pgtable->seqcount); cfg->pgsize_bitmap = amd_iommu_pgsize_bitmap; cfg->ias = IOMMU_IN_ADDR_BIT_SIZE; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 9c3ab9d9f69a..dff2d895b8ab 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1575,6 +1575,10 @@ static void switch_to_super_page(struct dmar_domain *domain, unsigned long lvl_pages = lvl_to_nr_pages(level); struct dma_pte *pte = NULL; + if (WARN_ON(!IS_ALIGNED(start_pfn, lvl_pages) || + !IS_ALIGNED(end_pfn + 1, lvl_pages))) + return; + while (start_pfn <= end_pfn) { if (!pte) pte = pfn_to_dma_pte(domain, start_pfn, &level, @@ -1650,7 +1654,8 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, unsigned long pages_to_remove; pteval |= DMA_PTE_LARGE_PAGE; - pages_to_remove = min_t(unsigned long, nr_pages, + pages_to_remove = min_t(unsigned long, + round_down(nr_pages, lvl_pages), nr_pte_to_next_page(pte) * lvl_pages); end_pfn = iov_pfn + pages_to_remove - 1; switch_to_super_page(domain, iov_pfn, end_pfn, largepage_lvl); diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index 9c80d61deb2c..aa576736d60b 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -612,6 +612,23 @@ static u64 get_iota_region_flag(struct s390_domain *domain) } } +static bool reg_ioat_propagate_error(int cc, u8 status) +{ + /* + * If the device is in the error state the reset routine + * will register the IOAT of the newly set domain on re-enable + */ + if (cc == ZPCI_CC_ERR && status == ZPCI_PCI_ST_FUNC_NOT_AVAIL) + return false; + /* + * If the device was removed treat registration as success + * and let the subsequent error event trigger tear down. + */ + if (cc == ZPCI_CC_INVAL_HANDLE) + return false; + return cc != ZPCI_CC_OK; +} + static int s390_iommu_domain_reg_ioat(struct zpci_dev *zdev, struct iommu_domain *domain, u8 *status) { @@ -696,7 +713,7 @@ static int s390_iommu_attach_device(struct iommu_domain *domain, /* If we fail now DMA remains blocked via blocking domain */ cc = s390_iommu_domain_reg_ioat(zdev, domain, &status); - if (cc && status != ZPCI_PCI_ST_FUNC_NOT_AVAIL) + if (reg_ioat_propagate_error(cc, status)) return -EIO; zdev->dma_table = s390_domain->dma_table; zdev_s390_domain_update(zdev, domain); @@ -1032,7 +1049,8 @@ struct zpci_iommu_ctrs *zpci_get_iommu_ctrs(struct zpci_dev *zdev) lockdep_assert_held(&zdev->dom_lock); - if (zdev->s390_domain->type == IOMMU_DOMAIN_BLOCKED) + if (zdev->s390_domain->type == IOMMU_DOMAIN_BLOCKED || + zdev->s390_domain->type == IOMMU_DOMAIN_IDENTITY) return NULL; s390_domain = to_s390_domain(zdev->s390_domain); @@ -1123,12 +1141,7 @@ static int s390_attach_dev_identity(struct iommu_domain *domain, /* If we fail now DMA remains blocked via blocking domain */ cc = s390_iommu_domain_reg_ioat(zdev, domain, &status); - - /* - * If the device is undergoing error recovery the reset code - * will re-establish the new domain. - */ - if (cc && status != ZPCI_PCI_ST_FUNC_NOT_AVAIL) + if (reg_ioat_propagate_error(cc, status)) return -EIO; zdev_s390_domain_update(zdev, domain); diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index efeee0a873c0..ab96b692e5a3 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -133,7 +133,7 @@ struct journal_sector { commit_id_t commit_id; }; -#define MAX_TAG_SIZE (JOURNAL_SECTOR_DATA - JOURNAL_MAC_PER_SECTOR - offsetof(struct journal_entry, last_bytes[MAX_SECTORS_PER_BLOCK])) +#define MAX_TAG_SIZE 255 #define METADATA_PADDING_SECTORS 8 diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 79ea85d18e24..f4b904e24328 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3813,8 +3813,10 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits) struct raid_set *rs = ti->private; unsigned int chunk_size_bytes = to_bytes(rs->md.chunk_sectors); - limits->io_min = chunk_size_bytes; - limits->io_opt = chunk_size_bytes * mddev_data_stripes(rs); + if (chunk_size_bytes) { + limits->io_min = chunk_size_bytes; + limits->io_opt = chunk_size_bytes * mddev_data_stripes(rs); + } } static void raid_presuspend(struct dm_target *ti) diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 58902091bf79..1461dc740dae 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -456,11 +456,15 @@ static void stripe_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct stripe_c *sc = ti->private; - unsigned int chunk_size = sc->chunk_size << SECTOR_SHIFT; + unsigned int io_min, io_opt; limits->chunk_sectors = sc->chunk_size; - limits->io_min = chunk_size; - limits->io_opt = chunk_size * sc->stripes; + + if (!check_shl_overflow(sc->chunk_size, SECTOR_SHIFT, &io_min) && + !check_mul_overflow(io_min, sc->stripes, &io_opt)) { + limits->io_min = io_min; + limits->io_opt = io_opt; + } } static struct target_type stripe_target = { diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index 5d9b08115375..3e1f165c2d20 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -73,6 +73,7 @@ static int linear_set_limits(struct mddev *mddev) md_init_stacking_limits(&lim); lim.max_hw_sectors = mddev->chunk_sectors; lim.max_write_zeroes_sectors = mddev->chunk_sectors; + lim.max_hw_wzeroes_unmap_sectors = mddev->chunk_sectors; lim.io_min = mddev->chunk_sectors << 9; err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); if (err) diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index f1d8811a542a..419139ad7663 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -382,6 +382,7 @@ static int raid0_set_limits(struct mddev *mddev) md_init_stacking_limits(&lim); lim.max_hw_sectors = mddev->chunk_sectors; lim.max_write_zeroes_sectors = mddev->chunk_sectors; + lim.max_hw_wzeroes_unmap_sectors = mddev->chunk_sectors; lim.io_min = mddev->chunk_sectors << 9; lim.io_opt = lim.io_min * mddev->raid_disks; lim.chunk_sectors = mddev->chunk_sectors; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index bf44878ec640..d30b82beeb92 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -3211,6 +3211,7 @@ static int raid1_set_limits(struct mddev *mddev) md_init_stacking_limits(&lim); lim.max_write_zeroes_sectors = 0; + lim.max_hw_wzeroes_unmap_sectors = 0; lim.features |= BLK_FEAT_ATOMIC_WRITES; err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); if (err) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index b60c30bfb6c7..9832eefb2f15 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -4008,6 +4008,7 @@ static int raid10_set_queue_limits(struct mddev *mddev) md_init_stacking_limits(&lim); lim.max_write_zeroes_sectors = 0; + lim.max_hw_wzeroes_unmap_sectors = 0; lim.io_min = mddev->chunk_sectors << 9; lim.chunk_sectors = mddev->chunk_sectors; lim.io_opt = lim.io_min * raid10_nr_stripes(conf); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 023649fe2476..e385ef1355e8 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -7732,6 +7732,7 @@ static int raid5_set_limits(struct mddev *mddev) lim.features |= BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE; lim.discard_granularity = stripe; lim.max_write_zeroes_sectors = 0; + lim.max_hw_wzeroes_unmap_sectors = 0; mddev_stack_rdev_limits(mddev, &lim, 0); rdev_for_each(rdev, mddev) queue_limits_stack_bdev(&lim, rdev->bdev, rdev->new_data_offset, diff --git a/drivers/mmc/host/mvsdio.c b/drivers/mmc/host/mvsdio.c index a9e6277789ba..79df2fa89a3f 100644 --- a/drivers/mmc/host/mvsdio.c +++ b/drivers/mmc/host/mvsdio.c @@ -292,7 +292,7 @@ static u32 mvsd_finish_data(struct mvsd_host *host, struct mmc_data *data, host->pio_ptr = NULL; host->pio_size = 0; } else { - dma_unmap_sg(mmc_dev(host->mmc), data->sg, host->sg_frags, + dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, mmc_get_dma_dir(data)); } diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c index 3a1de477e9af..b0f91cc9e40e 100644 --- a/drivers/mmc/host/sdhci-pci-gli.c +++ b/drivers/mmc/host/sdhci-pci-gli.c @@ -283,6 +283,8 @@ #define PCIE_GLI_9767_UHS2_CTL2_ZC_VALUE 0xb #define PCIE_GLI_9767_UHS2_CTL2_ZC_CTL BIT(6) #define PCIE_GLI_9767_UHS2_CTL2_ZC_CTL_VALUE 0x1 +#define PCIE_GLI_9767_UHS2_CTL2_FORCE_PHY_RESETN BIT(13) +#define PCIE_GLI_9767_UHS2_CTL2_FORCE_RESETN_VALUE BIT(14) #define GLI_MAX_TUNING_LOOP 40 @@ -1179,6 +1181,65 @@ static void gl9767_set_low_power_negotiation(struct pci_dev *pdev, bool enable) gl9767_vhs_read(pdev); } +static void sdhci_gl9767_uhs2_phy_reset(struct sdhci_host *host, bool assert) +{ + struct sdhci_pci_slot *slot = sdhci_priv(host); + struct pci_dev *pdev = slot->chip->pdev; + u32 value, set, clr; + + if (assert) { + /* Assert reset, set RESETN and clean RESETN_VALUE */ + set = PCIE_GLI_9767_UHS2_CTL2_FORCE_PHY_RESETN; + clr = PCIE_GLI_9767_UHS2_CTL2_FORCE_RESETN_VALUE; + } else { + /* De-assert reset, clean RESETN and set RESETN_VALUE */ + set = PCIE_GLI_9767_UHS2_CTL2_FORCE_RESETN_VALUE; + clr = PCIE_GLI_9767_UHS2_CTL2_FORCE_PHY_RESETN; + } + + gl9767_vhs_write(pdev); + pci_read_config_dword(pdev, PCIE_GLI_9767_UHS2_CTL2, &value); + value |= set; + pci_write_config_dword(pdev, PCIE_GLI_9767_UHS2_CTL2, value); + value &= ~clr; + pci_write_config_dword(pdev, PCIE_GLI_9767_UHS2_CTL2, value); + gl9767_vhs_read(pdev); +} + +static void __gl9767_uhs2_set_power(struct sdhci_host *host, unsigned char mode, unsigned short vdd) +{ + u8 pwr = 0; + + if (mode != MMC_POWER_OFF) { + pwr = sdhci_get_vdd_value(vdd); + if (!pwr) + WARN(1, "%s: Invalid vdd %#x\n", + mmc_hostname(host->mmc), vdd); + pwr |= SDHCI_VDD2_POWER_180; + } + + if (host->pwr == pwr) + return; + + host->pwr = pwr; + + if (pwr == 0) { + sdhci_writeb(host, 0, SDHCI_POWER_CONTROL); + } else { + sdhci_writeb(host, 0, SDHCI_POWER_CONTROL); + + pwr |= SDHCI_POWER_ON; + sdhci_writeb(host, pwr & 0xf, SDHCI_POWER_CONTROL); + usleep_range(5000, 6250); + + /* Assert reset */ + sdhci_gl9767_uhs2_phy_reset(host, true); + pwr |= SDHCI_VDD2_POWER_ON; + sdhci_writeb(host, pwr, SDHCI_POWER_CONTROL); + usleep_range(5000, 6250); + } +} + static void sdhci_gl9767_set_clock(struct sdhci_host *host, unsigned int clock) { struct sdhci_pci_slot *slot = sdhci_priv(host); @@ -1205,6 +1266,11 @@ static void sdhci_gl9767_set_clock(struct sdhci_host *host, unsigned int clock) } sdhci_enable_clk(host, clk); + + if (mmc_card_uhs2(host->mmc)) + /* De-assert reset */ + sdhci_gl9767_uhs2_phy_reset(host, false); + gl9767_set_low_power_negotiation(pdev, true); } @@ -1476,7 +1542,7 @@ static void sdhci_gl9767_set_power(struct sdhci_host *host, unsigned char mode, gl9767_vhs_read(pdev); sdhci_gli_overcurrent_event_enable(host, false); - sdhci_uhs2_set_power(host, mode, vdd); + __gl9767_uhs2_set_power(host, mode, vdd); sdhci_gli_overcurrent_event_enable(host, true); } else { gl9767_vhs_write(pdev); diff --git a/drivers/mmc/host/sdhci-uhs2.c b/drivers/mmc/host/sdhci-uhs2.c index 0efeb9d0c376..c459a08d01da 100644 --- a/drivers/mmc/host/sdhci-uhs2.c +++ b/drivers/mmc/host/sdhci-uhs2.c @@ -295,7 +295,8 @@ static void __sdhci_uhs2_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) else sdhci_uhs2_set_power(host, ios->power_mode, ios->vdd); - sdhci_set_clock(host, host->clock); + host->ops->set_clock(host, ios->clock); + host->clock = ios->clock; } static int sdhci_uhs2_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 3a17821efa5c..ac7e11f37af7 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -2367,23 +2367,6 @@ void sdhci_set_ios_common(struct mmc_host *mmc, struct mmc_ios *ios) (ios->power_mode == MMC_POWER_UP) && !(host->quirks2 & SDHCI_QUIRK2_PRESET_VALUE_BROKEN)) sdhci_enable_preset_value(host, false); - - if (!ios->clock || ios->clock != host->clock) { - host->ops->set_clock(host, ios->clock); - host->clock = ios->clock; - - if (host->quirks & SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK && - host->clock) { - host->timeout_clk = mmc->actual_clock ? - mmc->actual_clock / 1000 : - host->clock / 1000; - mmc->max_busy_timeout = - host->ops->get_max_timeout_count ? - host->ops->get_max_timeout_count(host) : - 1 << 27; - mmc->max_busy_timeout /= host->timeout_clk; - } - } } EXPORT_SYMBOL_GPL(sdhci_set_ios_common); @@ -2410,6 +2393,23 @@ void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) sdhci_set_ios_common(mmc, ios); + if (!ios->clock || ios->clock != host->clock) { + host->ops->set_clock(host, ios->clock); + host->clock = ios->clock; + + if (host->quirks & SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK && + host->clock) { + host->timeout_clk = mmc->actual_clock ? + mmc->actual_clock / 1000 : + host->clock / 1000; + mmc->max_busy_timeout = + host->ops->get_max_timeout_count ? + host->ops->get_max_timeout_count(host) : + 1 << 27; + mmc->max_busy_timeout /= host->timeout_clk; + } + } + if (host->ops->set_power) host->ops->set_power(host, ios->power_mode, ios->vdd); else diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig index 46cebde79f34..e518dfeee654 100644 --- a/drivers/mtd/devices/Kconfig +++ b/drivers/mtd/devices/Kconfig @@ -185,8 +185,8 @@ config MTD_POWERNV_FLASH config MTD_INTEL_DG tristate "Intel Discrete Graphics non-volatile memory driver" - depends on AUXILIARY_BUS - depends on MTD + depends on AUXILIARY_BUS && MTD + depends on DRM_I915!=n || DRM_XE!=n || COMPILE_TEST help This provides an MTD device to access Intel Discrete Graphics non-volatile memory. diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c index 84ab4a83cbd6..db94d14a3807 100644 --- a/drivers/mtd/nand/raw/atmel/nand-controller.c +++ b/drivers/mtd/nand/raw/atmel/nand-controller.c @@ -1378,13 +1378,23 @@ static int atmel_smc_nand_prepare_smcconf(struct atmel_nand *nand, return ret; /* + * Read setup timing depends on the operation done on the NAND: + * + * NRD_SETUP = max(tAR, tCLR) + */ + timeps = max(conf->timings.sdr.tAR_min, conf->timings.sdr.tCLR_min); + ncycles = DIV_ROUND_UP(timeps, mckperiodps); + totalcycles += ncycles; + ret = atmel_smc_cs_conf_set_setup(smcconf, ATMEL_SMC_NRD_SHIFT, ncycles); + if (ret) + return ret; + + /* * The read cycle timing is directly matching tRC, but is also * dependent on the setup and hold timings we calculated earlier, * which gives: * - * NRD_CYCLE = max(tRC, NRD_PULSE + NRD_HOLD) - * - * NRD_SETUP is always 0. + * NRD_CYCLE = max(tRC, NRD_SETUP + NRD_PULSE + NRD_HOLD) */ ncycles = DIV_ROUND_UP(conf->timings.sdr.tRC_min, mckperiodps); ncycles = max(totalcycles, ncycles); diff --git a/drivers/mtd/nand/raw/nuvoton-ma35d1-nand-controller.c b/drivers/mtd/nand/raw/nuvoton-ma35d1-nand-controller.c index c23b537948d5..1a285cd8fad6 100644 --- a/drivers/mtd/nand/raw/nuvoton-ma35d1-nand-controller.c +++ b/drivers/mtd/nand/raw/nuvoton-ma35d1-nand-controller.c @@ -935,10 +935,10 @@ static void ma35_chips_cleanup(struct ma35_nand_info *nand) static int ma35_nand_chips_init(struct device *dev, struct ma35_nand_info *nand) { - struct device_node *np = dev->of_node, *nand_np; + struct device_node *np = dev->of_node; int ret; - for_each_child_of_node(np, nand_np) { + for_each_child_of_node_scoped(np, nand_np) { ret = ma35_nand_chip_init(dev, nand, nand_np); if (ret) { ma35_chips_cleanup(nand); diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c index a960403081f1..d957327fb4fa 100644 --- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c +++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c @@ -272,6 +272,7 @@ struct stm32_fmc2_nfc { struct sg_table dma_data_sg; struct sg_table dma_ecc_sg; u8 *ecc_buf; + dma_addr_t dma_ecc_addr; int dma_ecc_len; u32 tx_dma_max_burst; u32 rx_dma_max_burst; @@ -902,17 +903,10 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf, if (!write_data && !raw) { /* Configure DMA ECC status */ - p = nfc->ecc_buf; for_each_sg(nfc->dma_ecc_sg.sgl, sg, eccsteps, s) { - sg_set_buf(sg, p, nfc->dma_ecc_len); - p += nfc->dma_ecc_len; - } - - ret = dma_map_sg(nfc->dev, nfc->dma_ecc_sg.sgl, - eccsteps, dma_data_dir); - if (!ret) { - ret = -EIO; - goto err_unmap_data; + sg_dma_address(sg) = nfc->dma_ecc_addr + + s * nfc->dma_ecc_len; + sg_dma_len(sg) = nfc->dma_ecc_len; } desc_ecc = dmaengine_prep_slave_sg(nfc->dma_ecc_ch, @@ -921,7 +915,7 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf, DMA_PREP_INTERRUPT); if (!desc_ecc) { ret = -ENOMEM; - goto err_unmap_ecc; + goto err_unmap_data; } reinit_completion(&nfc->dma_ecc_complete); @@ -929,7 +923,7 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf, desc_ecc->callback_param = &nfc->dma_ecc_complete; ret = dma_submit_error(dmaengine_submit(desc_ecc)); if (ret) - goto err_unmap_ecc; + goto err_unmap_data; dma_async_issue_pending(nfc->dma_ecc_ch); } @@ -949,7 +943,7 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf, if (!write_data && !raw) dmaengine_terminate_all(nfc->dma_ecc_ch); ret = -ETIMEDOUT; - goto err_unmap_ecc; + goto err_unmap_data; } /* Wait DMA data transfer completion */ @@ -969,11 +963,6 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf, } } -err_unmap_ecc: - if (!write_data && !raw) - dma_unmap_sg(nfc->dev, nfc->dma_ecc_sg.sgl, - eccsteps, dma_data_dir); - err_unmap_data: dma_unmap_sg(nfc->dev, nfc->dma_data_sg.sgl, eccsteps, dma_data_dir); @@ -996,9 +985,21 @@ static int stm32_fmc2_nfc_seq_write(struct nand_chip *chip, const u8 *buf, /* Write oob */ if (oob_required) { - ret = nand_change_write_column_op(chip, mtd->writesize, - chip->oob_poi, mtd->oobsize, - false); + unsigned int offset_in_page = mtd->writesize; + const void *buf = chip->oob_poi; + unsigned int len = mtd->oobsize; + + if (!raw) { + struct mtd_oob_region oob_free; + + mtd_ooblayout_free(mtd, 0, &oob_free); + offset_in_page += oob_free.offset; + buf += oob_free.offset; + len = oob_free.length; + } + + ret = nand_change_write_column_op(chip, offset_in_page, + buf, len, false); if (ret) return ret; } @@ -1610,7 +1611,8 @@ static int stm32_fmc2_nfc_dma_setup(struct stm32_fmc2_nfc *nfc) return ret; /* Allocate a buffer to store ECC status registers */ - nfc->ecc_buf = devm_kzalloc(nfc->dev, FMC2_MAX_ECC_BUF_LEN, GFP_KERNEL); + nfc->ecc_buf = dmam_alloc_coherent(nfc->dev, FMC2_MAX_ECC_BUF_LEN, + &nfc->dma_ecc_addr, GFP_KERNEL); if (!nfc->ecc_buf) return -ENOMEM; diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c index 87053389a1fc..4870b2d5edb2 100644 --- a/drivers/mtd/nand/spi/winbond.c +++ b/drivers/mtd/nand/spi/winbond.c @@ -176,6 +176,36 @@ static const struct mtd_ooblayout_ops w25n02kv_ooblayout = { .free = w25n02kv_ooblayout_free, }; +static int w25n01jw_ooblayout_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section > 3) + return -ERANGE; + + region->offset = (16 * section) + 12; + region->length = 4; + + return 0; +} + +static int w25n01jw_ooblayout_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section > 3) + return -ERANGE; + + region->offset = (16 * section); + region->length = 12; + + /* Extract BBM */ + if (!section) { + region->offset += 2; + region->length -= 2; + } + + return 0; +} + static int w35n01jw_ooblayout_ecc(struct mtd_info *mtd, int section, struct mtd_oob_region *region) { @@ -206,6 +236,11 @@ static int w35n01jw_ooblayout_free(struct mtd_info *mtd, int section, return 0; } +static const struct mtd_ooblayout_ops w25n01jw_ooblayout = { + .ecc = w25n01jw_ooblayout_ecc, + .free = w25n01jw_ooblayout_free, +}; + static const struct mtd_ooblayout_ops w35n01jw_ooblayout = { .ecc = w35n01jw_ooblayout_ecc, .free = w35n01jw_ooblayout_free, @@ -394,7 +429,7 @@ static const struct spinand_info winbond_spinand_table[] = { &write_cache_variants, &update_cache_variants), 0, - SPINAND_ECCINFO(&w25m02gv_ooblayout, NULL), + SPINAND_ECCINFO(&w25n01jw_ooblayout, NULL), SPINAND_CONFIGURE_CHIP(w25n0xjw_hs_cfg)), SPINAND_INFO("W25N01KV", /* 3.3V */ SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xae, 0x21), diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 257333c88710..57be04f6cb11 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2132,6 +2132,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len); } else if (bond->params.fail_over_mac == BOND_FOM_FOLLOW && BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP && + bond_has_slaves(bond) && memcmp(slave_dev->dev_addr, bond_dev->dev_addr, bond_dev->addr_len) == 0) { /* Set slave to random address to avoid duplicate mac * address in later fail over. @@ -3355,7 +3356,6 @@ static void bond_ns_send_all(struct bonding *bond, struct slave *slave) /* Find out through which dev should the packet go */ memset(&fl6, 0, sizeof(struct flowi6)); fl6.daddr = targets[i]; - fl6.flowi6_oif = bond->dev->ifindex; dst = ip6_route_output(dev_net(bond->dev), NULL, &fl6); if (dst->error) { diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c index 64e664f5adcc..87c134bcd48d 100644 --- a/drivers/net/can/rcar/rcar_can.c +++ b/drivers/net/can/rcar/rcar_can.c @@ -861,7 +861,6 @@ static int rcar_can_resume(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct rcar_can_priv *priv = netdev_priv(ndev); - u16 ctlr; int err; if (!netif_running(ndev)) @@ -873,12 +872,7 @@ static int rcar_can_resume(struct device *dev) return err; } - ctlr = readw(&priv->regs->ctlr); - ctlr &= ~RCAR_CAN_CTLR_SLPM; - writew(ctlr, &priv->regs->ctlr); - ctlr &= ~RCAR_CAN_CTLR_CANM; - writew(ctlr, &priv->regs->ctlr); - priv->can.state = CAN_STATE_ERROR_ACTIVE; + rcar_can_start(ndev); netif_device_attach(ndev); netif_start_queue(ndev); diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 81baec8eb1e5..a25a3ca62c12 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -690,14 +690,6 @@ static void xcan_write_frame(struct net_device *ndev, struct sk_buff *skb, dlc |= XCAN_DLCR_EDL_MASK; } - if (!(priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES) && - (priv->devtype.flags & XCAN_FLAG_TXFEMP)) - can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max, 0); - else - can_put_echo_skb(skb, ndev, 0, 0); - - priv->tx_head++; - priv->write_reg(priv, XCAN_FRAME_ID_OFFSET(frame_offset), id); /* If the CAN frame is RTR frame this write triggers transmission * (not on CAN FD) @@ -730,6 +722,14 @@ static void xcan_write_frame(struct net_device *ndev, struct sk_buff *skb, data[1]); } } + + if (!(priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES) && + (priv->devtype.flags & XCAN_FLAG_TXFEMP)) + can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max, 0); + else + can_put_echo_skb(skb, ndev, 0, 0); + + priv->tx_head++; } /** diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 829b1f087e9e..2f846381d5a7 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1273,9 +1273,15 @@ static int b53_setup(struct dsa_switch *ds) */ ds->untag_vlan_aware_bridge_pvid = true; - /* Ageing time is set in seconds */ - ds->ageing_time_min = 1 * 1000; - ds->ageing_time_max = AGE_TIME_MAX * 1000; + if (dev->chip_id == BCM53101_DEVICE_ID) { + /* BCM53101 uses 0.5 second increments */ + ds->ageing_time_min = 1 * 500; + ds->ageing_time_max = AGE_TIME_MAX * 500; + } else { + /* Everything else uses 1 second increments */ + ds->ageing_time_min = 1 * 1000; + ds->ageing_time_max = AGE_TIME_MAX * 1000; + } ret = b53_reset_switch(dev); if (ret) { @@ -2559,7 +2565,10 @@ int b53_set_ageing_time(struct dsa_switch *ds, unsigned int msecs) else reg = B53_AGING_TIME_CONTROL; - atc = DIV_ROUND_CLOSEST(msecs, 1000); + if (dev->chip_id == BCM53101_DEVICE_ID) + atc = DIV_ROUND_CLOSEST(msecs, 500); + else + atc = DIV_ROUND_CLOSEST(msecs, 1000); if (!is5325(dev) && !is5365(dev)) atc |= AGE_CHANGE; diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index a9040c42d2ff..6e97a5a7daaf 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -4230,8 +4230,7 @@ static void cnic_cm_stop_bnx2x_hw(struct cnic_dev *dev) cnic_bnx2x_delete_wait(dev, 0); - cancel_delayed_work(&cp->delete_task); - flush_workqueue(cnic_wq); + cancel_delayed_work_sync(&cp->delete_task); if (atomic_read(&cp->iscsi_conn) != 0) netdev_warn(dev->netdev, "%d iSCSI connections not destroyed\n", diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c index de8a6ce86ad7..12105ffb5dac 100644 --- a/drivers/net/ethernet/cavium/liquidio/request_manager.c +++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c @@ -126,7 +126,7 @@ int octeon_init_instr_queue(struct octeon_device *oct, oct->io_qmask.iq |= BIT_ULL(iq_no); /* Set the 32B/64B mode for each input queue */ - oct->io_qmask.iq64B |= ((conf->instr_type == 64) << iq_no); + oct->io_qmask.iq64B |= ((u64)(conf->instr_type == 64) << iq_no); iq->iqcmd_64B = (conf->instr_type == 64); oct->fn_list.setup_iq_regs(oct, iq_no); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index 4643a3380618..b1e1ad9e4b48 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -2736,7 +2736,7 @@ static int dpaa2_switch_setup_dpbp(struct ethsw_core *ethsw) dev_err(dev, "dpsw_ctrl_if_set_pools() failed\n"); goto err_get_attr; } - ethsw->bpid = dpbp_attrs.id; + ethsw->bpid = dpbp_attrs.bpid; return 0; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 1383918f8a3f..adf1f2bbcbb1 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2363,7 +2363,8 @@ static void fec_enet_phy_reset_after_clk_enable(struct net_device *ndev) */ phy_dev = of_phy_find_device(fep->phy_node); phy_reset_after_clk_enable(phy_dev); - put_device(&phy_dev->mdio.dev); + if (phy_dev) + put_device(&phy_dev->mdio.dev); } } diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 76d872b91a38..cc02a85ad42b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -1561,6 +1561,7 @@ I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config); struct i40e_aq_set_mac_config { __le16 max_frame_size; u8 params; +#define I40E_AQ_SET_MAC_CONFIG_CRC_EN BIT(2) u8 tx_timer_priority; /* bitmap */ __le16 tx_timer_value; __le16 fc_refresh_threshold; diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 270e7e8cf9cf..59f5c1e810eb 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1190,6 +1190,40 @@ int i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures, } /** + * i40e_aq_set_mac_config - Configure MAC settings + * @hw: pointer to the hw struct + * @max_frame_size: Maximum Frame Size to be supported by the port + * @cmd_details: pointer to command details structure or NULL + * + * Set MAC configuration (0x0603). Note that max_frame_size must be greater + * than zero. + * + * Return: 0 on success, or a negative error code on failure. + */ +int i40e_aq_set_mac_config(struct i40e_hw *hw, u16 max_frame_size, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_set_mac_config *cmd; + struct libie_aq_desc desc; + + cmd = libie_aq_raw(&desc); + + if (max_frame_size == 0) + return -EINVAL; + + i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_mac_config); + + cmd->max_frame_size = cpu_to_le16(max_frame_size); + cmd->params = I40E_AQ_SET_MAC_CONFIG_CRC_EN; + +#define I40E_AQ_SET_MAC_CONFIG_FC_DEFAULT_THRESHOLD 0x7FFF + cmd->fc_refresh_threshold = + cpu_to_le16(I40E_AQ_SET_MAC_CONFIG_FC_DEFAULT_THRESHOLD); + + return i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); +} + +/** * i40e_aq_clear_pxe_mode * @hw: pointer to the hw struct * @cmd_details: pointer to command details structure or NULL diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b83f823e4917..b14019d44b58 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4156,7 +4156,7 @@ free_queue_irqs: irq_num = pf->msix_entries[base + vector].vector; irq_set_affinity_notifier(irq_num, NULL); irq_update_affinity_hint(irq_num, NULL); - free_irq(irq_num, &vsi->q_vectors[vector]); + free_irq(irq_num, vsi->q_vectors[vector]); } return err; } @@ -16045,13 +16045,17 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_dbg(&pf->pdev->dev, "get supported phy types ret = %pe last_status = %s\n", ERR_PTR(err), libie_aq_str(pf->hw.aq.asq_last_status)); - /* make sure the MFS hasn't been set lower than the default */ #define MAX_FRAME_SIZE_DEFAULT 0x2600 - val = FIELD_GET(I40E_PRTGL_SAH_MFS_MASK, - rd32(&pf->hw, I40E_PRTGL_SAH)); - if (val < MAX_FRAME_SIZE_DEFAULT) - dev_warn(&pdev->dev, "MFS for port %x (%d) has been set below the default (%d)\n", - pf->hw.port, val, MAX_FRAME_SIZE_DEFAULT); + + err = i40e_aq_set_mac_config(hw, MAX_FRAME_SIZE_DEFAULT, NULL); + if (err) + dev_warn(&pdev->dev, "set mac config ret = %pe last_status = %s\n", + ERR_PTR(err), libie_aq_str(pf->hw.aq.asq_last_status)); + + /* Make sure the MFS is set to the expected value */ + val = rd32(hw, I40E_PRTGL_SAH); + FIELD_MODIFY(I40E_PRTGL_SAH_MFS_MASK, &val, MAX_FRAME_SIZE_DEFAULT); + wr32(hw, I40E_PRTGL_SAH, val); /* Add a filter to drop all Flow control frames from any VSI from being * transmitted. By doing so we stop a malicious VF from sending out diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index aef5de53ce3b..26bb7bffe361 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -98,6 +98,8 @@ int i40e_aq_set_mac_loopback(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details); int i40e_aq_set_phy_int_mask(struct i40e_hw *hw, u16 mask, struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_set_mac_config(struct i40e_hw *hw, u16 max_frame_size, + struct i40e_asq_cmd_details *cmd_details); int i40e_aq_clear_pxe_mode(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details); int i40e_aq_set_link_restart_an(struct i40e_hw *hw, diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 048c33039130..b194eae03208 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -948,9 +948,6 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, if (!eop_desc) break; - /* prevent any other reads prior to eop_desc */ - smp_rmb(); - i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf); /* we have caught up to head, no work left to do */ if (tx_head == tx_desc) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index d2871757ec94..41e7e29879a3 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -894,10 +894,6 @@ ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page, rx_buf->page_offset, size); sinfo->xdp_frags_size += size; - /* remember frag count before XDP prog execution; bpf_xdp_adjust_tail() - * can pop off frags but driver has to handle it on its own - */ - rx_ring->nr_frags = sinfo->nr_frags; if (page_is_pfmemalloc(rx_buf->page)) xdp_buff_set_frag_pfmemalloc(xdp); @@ -968,20 +964,20 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, /** * ice_get_pgcnts - grab page_count() for gathered fragments * @rx_ring: Rx descriptor ring to store the page counts on + * @ntc: the next to clean element (not included in this frame!) * * This function is intended to be called right before running XDP * program so that the page recycling mechanism will be able to take * a correct decision regarding underlying pages; this is done in such * way as XDP program can change the refcount of page */ -static void ice_get_pgcnts(struct ice_rx_ring *rx_ring) +static void ice_get_pgcnts(struct ice_rx_ring *rx_ring, unsigned int ntc) { - u32 nr_frags = rx_ring->nr_frags + 1; u32 idx = rx_ring->first_desc; struct ice_rx_buf *rx_buf; u32 cnt = rx_ring->count; - for (int i = 0; i < nr_frags; i++) { + while (idx != ntc) { rx_buf = &rx_ring->rx_buf[idx]; rx_buf->pgcnt = page_count(rx_buf->page); @@ -1154,62 +1150,51 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf) } /** - * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all frame frags + * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all buffers in frame * @rx_ring: Rx ring with all the auxiliary data * @xdp: XDP buffer carrying linear + frags part - * @xdp_xmit: XDP_TX/XDP_REDIRECT verdict storage - * @ntc: a current next_to_clean value to be stored at rx_ring + * @ntc: the next to clean element (not included in this frame!) * @verdict: return code from XDP program execution * - * Walk through gathered fragments and satisfy internal page - * recycle mechanism; we take here an action related to verdict - * returned by XDP program; + * Called after XDP program is completed, or on error with verdict set to + * ICE_XDP_CONSUMED. + * + * Walk through buffers from first_desc to the end of the frame, releasing + * buffers and satisfying internal page recycle mechanism. The action depends + * on verdict from XDP program. */ static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, - u32 *xdp_xmit, u32 ntc, u32 verdict) + u32 ntc, u32 verdict) { - u32 nr_frags = rx_ring->nr_frags + 1; u32 idx = rx_ring->first_desc; u32 cnt = rx_ring->count; - u32 post_xdp_frags = 1; struct ice_rx_buf *buf; - int i; + u32 xdp_frags = 0; + int i = 0; if (unlikely(xdp_buff_has_frags(xdp))) - post_xdp_frags += xdp_get_shared_info_from_buff(xdp)->nr_frags; + xdp_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags; - for (i = 0; i < post_xdp_frags; i++) { + while (idx != ntc) { buf = &rx_ring->rx_buf[idx]; + if (++idx == cnt) + idx = 0; - if (verdict & (ICE_XDP_TX | ICE_XDP_REDIR)) { + /* An XDP program could release fragments from the end of the + * buffer. For these, we need to keep the pagecnt_bias as-is. + * To do this, only adjust pagecnt_bias for fragments up to + * the total remaining after the XDP program has run. + */ + if (verdict != ICE_XDP_CONSUMED) ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); - *xdp_xmit |= verdict; - } else if (verdict & ICE_XDP_CONSUMED) { + else if (i++ <= xdp_frags) buf->pagecnt_bias++; - } else if (verdict == ICE_XDP_PASS) { - ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); - } ice_put_rx_buf(rx_ring, buf); - - if (++idx == cnt) - idx = 0; - } - /* handle buffers that represented frags released by XDP prog; - * for these we keep pagecnt_bias as-is; refcount from struct page - * has been decremented within XDP prog and we do not have to increase - * the biased refcnt - */ - for (; i < nr_frags; i++) { - buf = &rx_ring->rx_buf[idx]; - ice_put_rx_buf(rx_ring, buf); - if (++idx == cnt) - idx = 0; } xdp->data = NULL; rx_ring->first_desc = ntc; - rx_ring->nr_frags = 0; } /** @@ -1317,6 +1302,10 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) /* retrieve a buffer from the ring */ rx_buf = ice_get_rx_buf(rx_ring, size, ntc); + /* Increment ntc before calls to ice_put_rx_mbuf() */ + if (++ntc == cnt) + ntc = 0; + if (!xdp->data) { void *hard_start; @@ -1325,24 +1314,23 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) xdp_prepare_buff(xdp, hard_start, offset, size, !!offset); xdp_buff_clear_frags_flag(xdp); } else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) { - ice_put_rx_mbuf(rx_ring, xdp, NULL, ntc, ICE_XDP_CONSUMED); + ice_put_rx_mbuf(rx_ring, xdp, ntc, ICE_XDP_CONSUMED); break; } - if (++ntc == cnt) - ntc = 0; /* skip if it is NOP desc */ if (ice_is_non_eop(rx_ring, rx_desc)) continue; - ice_get_pgcnts(rx_ring); + ice_get_pgcnts(rx_ring, ntc); xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc); if (xdp_verdict == ICE_XDP_PASS) goto construct_skb; total_rx_bytes += xdp_get_buff_len(xdp); total_rx_pkts++; - ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict); + ice_put_rx_mbuf(rx_ring, xdp, ntc, xdp_verdict); + xdp_xmit |= xdp_verdict & (ICE_XDP_TX | ICE_XDP_REDIR); continue; construct_skb: @@ -1355,7 +1343,7 @@ construct_skb: rx_ring->ring_stats->rx_stats.alloc_buf_failed++; xdp_verdict = ICE_XDP_CONSUMED; } - ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict); + ice_put_rx_mbuf(rx_ring, xdp, ntc, xdp_verdict); if (!skb) break; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index fef750c5f288..2fd8e78178a2 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -358,7 +358,6 @@ struct ice_rx_ring { struct ice_tx_ring *xdp_ring; struct ice_rx_ring *next; /* pointer to next ring in q_vector */ struct xsk_buff_pool *xsk_pool; - u32 nr_frags; u16 max_frame; u16 rx_buf_len; dma_addr_t dma; /* physical address of ring */ diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 92ef33459aec..7b8f32c5169a 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2081,11 +2081,8 @@ static void igb_diag_test(struct net_device *netdev, } else { dev_info(&adapter->pdev->dev, "online testing starting\n"); - /* PHY is powered down when interface is down */ - if (if_running && igb_link_test(adapter, &data[TEST_LINK])) + if (igb_link_test(adapter, &data[TEST_LINK])) eth_test->flags |= ETH_TEST_FL_FAILED; - else - data[TEST_LINK] = 0; /* Online tests aren't run; pass by default */ data[TEST_REG] = 0; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index a9a7a94ae61e..453deb6d14b3 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4453,8 +4453,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) xdp_rxq_info_unreg(&rx_ring->xdp_rxq); res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->queue_index, - rx_ring->q_vector->napi.napi_id); + rx_ring->queue_index, 0); if (res < 0) { dev_err(dev, "Failed to register xdp_rxq index %u\n", rx_ring->queue_index); diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 266bfcf2a28f..a427f05814c1 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -345,6 +345,7 @@ struct igc_adapter { /* LEDs */ struct mutex led_mutex; struct igc_led_classdev *leds; + bool leds_available; }; void igc_up(struct igc_adapter *adapter); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index e79b14d50b24..728d7ca5338b 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -7335,8 +7335,14 @@ static int igc_probe(struct pci_dev *pdev, if (IS_ENABLED(CONFIG_IGC_LEDS)) { err = igc_led_setup(adapter); - if (err) - goto err_register; + if (err) { + netdev_warn_once(netdev, + "LED init failed (%d); continuing without LED support\n", + err); + adapter->leds_available = false; + } else { + adapter->leds_available = true; + } } return 0; @@ -7392,7 +7398,7 @@ static void igc_remove(struct pci_dev *pdev) cancel_work_sync(&adapter->watchdog_task); hrtimer_cancel(&adapter->hrtimer); - if (IS_ENABLED(CONFIG_IGC_LEDS)) + if (IS_ENABLED(CONFIG_IGC_LEDS) && adapter->leds_available) igc_led_free(adapter); /* Release control of h/w to f/w. If f/w is AMT enabled, this diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 80e6a2ef1350..6218bdb7f941 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6973,6 +6973,13 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, break; } + /* Make sure the SWFW semaphore is in a valid state */ + if (hw->mac.ops.init_swfw_sync) + hw->mac.ops.init_swfw_sync(hw); + + if (hw->mac.type == ixgbe_mac_e610) + mutex_init(&hw->aci.lock); + #ifdef IXGBE_FCOE /* FCoE support exists, always init the FCoE lock */ spin_lock_init(&adapter->fcoe.lock); @@ -11643,10 +11650,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_sw_init; - /* Make sure the SWFW semaphore is in a valid state */ - if (hw->mac.ops.init_swfw_sync) - hw->mac.ops.init_swfw_sync(hw); - if (ixgbe_check_fw_error(adapter)) return ixgbe_recovery_probe(adapter); @@ -11850,8 +11853,6 @@ skip_sriov: ether_addr_copy(hw->mac.addr, hw->mac.perm_addr); ixgbe_mac_set_default_filter(adapter); - if (hw->mac.type == ixgbe_mac_e610) - mutex_init(&hw->aci.lock); timer_setup(&adapter->service_timer, ixgbe_service_timer, 0); if (ixgbe_removed(hw->hw_addr)) { @@ -12007,9 +12008,9 @@ err_register: devl_unlock(adapter->devlink); ixgbe_release_hw_control(adapter); ixgbe_clear_interrupt_scheme(adapter); +err_sw_init: if (hw->mac.type == ixgbe_mac_e610) mutex_destroy(&adapter->hw.aci.lock); -err_sw_init: ixgbe_disable_sriov(adapter); adapter->flags2 &= ~IXGBE_FLAG2_SEARCH_FOR_SFP; iounmap(adapter->io_addr); @@ -12060,10 +12061,8 @@ static void ixgbe_remove(struct pci_dev *pdev) set_bit(__IXGBE_REMOVING, &adapter->state); cancel_work_sync(&adapter->service_task); - if (adapter->hw.mac.type == ixgbe_mac_e610) { + if (adapter->hw.mac.type == ixgbe_mac_e610) ixgbe_disable_link_status_events(adapter); - mutex_destroy(&adapter->hw.aci.lock); - } if (adapter->mii_bus) mdiobus_unregister(adapter->mii_bus); @@ -12123,6 +12122,9 @@ static void ixgbe_remove(struct pci_dev *pdev) disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); free_netdev(netdev); + if (adapter->hw.mac.type == ixgbe_mac_e610) + mutex_destroy(&adapter->hw.aci.lock); + if (disable_dev) pci_disable_device(pdev); } diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index 24499bb36c00..bcea3fc26a8c 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -1124,11 +1124,24 @@ static int octep_set_features(struct net_device *dev, netdev_features_t features return err; } +static bool octep_is_vf_valid(struct octep_device *oct, int vf) +{ + if (vf >= CFG_GET_ACTIVE_VFS(oct->conf)) { + netdev_err(oct->netdev, "Invalid VF ID %d\n", vf); + return false; + } + + return true; +} + static int octep_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi) { struct octep_device *oct = netdev_priv(dev); + if (!octep_is_vf_valid(oct, vf)) + return -EINVAL; + ivi->vf = vf; ether_addr_copy(ivi->mac, oct->vf_info[vf].mac_addr); ivi->spoofchk = true; @@ -1143,6 +1156,9 @@ static int octep_set_vf_mac(struct net_device *dev, int vf, u8 *mac) struct octep_device *oct = netdev_priv(dev); int err; + if (!octep_is_vf_valid(oct, vf)) + return -EINVAL; + if (!is_valid_ether_addr(mac)) { dev_err(&oct->pdev->dev, "Invalid MAC Address %pM\n", mac); return -EADDRNOTAVAIL; diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c index ebecdd29f3bd..0867fab61b19 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c @@ -196,6 +196,7 @@ static void octep_pfvf_get_mac_addr(struct octep_device *oct, u32 vf_id, vf_id); return; } + ether_addr_copy(oct->vf_info[vf_id].mac_addr, rsp->s_set_mac.mac_addr); rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK; } @@ -205,6 +206,8 @@ static void octep_pfvf_dev_remove(struct octep_device *oct, u32 vf_id, { int err; + /* Reset VF-specific information maintained by the PF */ + memset(&oct->vf_info[vf_id], 0, sizeof(struct octep_pfvf_info)); err = octep_ctrl_net_dev_remove(oct, vf_id); if (err) { rsp->s.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c index e52cc6b1a26c..dedd586ed310 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c @@ -491,7 +491,7 @@ void otx2_ptp_destroy(struct otx2_nic *pfvf) if (!ptp) return; - cancel_delayed_work(&pfvf->ptp->synctstamp_work); + cancel_delayed_work_sync(&pfvf->ptp->synctstamp_work); ptp_clock_unregister(ptp->ptp_clock); kfree(ptp); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index 9560fcba643f..ac65e3191480 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -92,6 +92,7 @@ enum { MLX5E_ACCEL_FS_ESP_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1, MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL, MLX5E_ACCEL_FS_POL_FT_LEVEL, + MLX5E_ACCEL_FS_POL_MISS_FT_LEVEL, MLX5E_ACCEL_FS_ESP_FT_ROCE_LEVEL, #endif }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index ffcd0cdeb775..23703f28386a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -185,6 +185,7 @@ struct mlx5e_ipsec_rx_create_attr { u32 family; int prio; int pol_level; + int pol_miss_level; int sa_level; int status_level; enum mlx5_flow_namespace_type chains_ns; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 98b6a3a623f9..65dc3529283b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -747,6 +747,7 @@ static void ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, attr->family = family; attr->prio = MLX5E_NIC_PRIO; attr->pol_level = MLX5E_ACCEL_FS_POL_FT_LEVEL; + attr->pol_miss_level = MLX5E_ACCEL_FS_POL_MISS_FT_LEVEL; attr->sa_level = MLX5E_ACCEL_FS_ESP_FT_LEVEL; attr->status_level = MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL; attr->chains_ns = MLX5_FLOW_NAMESPACE_KERNEL; @@ -833,7 +834,7 @@ static int ipsec_rx_chains_create_miss(struct mlx5e_ipsec *ipsec, ft_attr.max_fte = 1; ft_attr.autogroup.max_num_groups = 1; - ft_attr.level = attr->pol_level; + ft_attr.level = attr->pol_miss_level; ft_attr.prio = attr->prio; ft = mlx5_create_auto_grouped_flow_table(attr->ns, &ft_attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index e680673ffb72..15eded36b872 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -139,8 +139,6 @@ void mlx5e_update_carrier(struct mlx5e_priv *priv) if (up) { netdev_info(priv->netdev, "Link up\n"); netif_carrier_on(priv->netdev); - mlx5e_port_manual_buffer_config(priv, 0, priv->netdev->mtu, - NULL, NULL, NULL); } else { netdev_info(priv->netdev, "Link down\n"); netif_carrier_off(priv->netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 63a7a788fb0d..cd0242eb008c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1506,12 +1506,21 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = { static int mlx5e_vport_uplink_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) { - struct mlx5e_priv *priv = netdev_priv(mlx5_uplink_netdev_get(dev)); struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); + struct net_device *netdev; + struct mlx5e_priv *priv; + int err; + + netdev = mlx5_uplink_netdev_get(dev); + if (!netdev) + return 0; + priv = netdev_priv(netdev); rpriv->netdev = priv->netdev; - return mlx5e_netdev_change_profile(priv, &mlx5e_uplink_rep_profile, - rpriv); + err = mlx5e_netdev_change_profile(priv, &mlx5e_uplink_rep_profile, + rpriv); + mlx5_uplink_netdev_put(dev, netdev); + return err; } static void @@ -1638,8 +1647,16 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) { struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); struct net_device *netdev = rpriv->netdev; - struct mlx5e_priv *priv = netdev_priv(netdev); - void *ppriv = priv->ppriv; + struct mlx5e_priv *priv; + void *ppriv; + + if (!netdev) { + ppriv = rpriv; + goto free_ppriv; + } + + priv = netdev_priv(netdev); + ppriv = priv->ppriv; if (rep->vport == MLX5_VPORT_UPLINK) { mlx5e_vport_uplink_rep_unload(rpriv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 8b4977650183..5f2d6c35f1ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -1515,6 +1515,7 @@ static u32 mlx5_esw_qos_lag_link_speed_get_locked(struct mlx5_core_dev *mdev) speed = lksettings.base.speed; out: + mlx5_uplink_netdev_put(mdev, slave); return speed; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index cb165085a4c1..db552c012b4f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -114,9 +114,9 @@ #define ETHTOOL_NUM_PRIOS 11 #define ETHTOOL_MIN_LEVEL (KERNEL_MIN_LEVEL + ETHTOOL_NUM_PRIOS) /* Vlan, mac, ttc, inner ttc, {UDP/ANY/aRFS/accel/{esp, esp_err}}, IPsec policy, - * {IPsec RoCE MPV,Alias table},IPsec RoCE policy + * IPsec policy miss, {IPsec RoCE MPV,Alias table},IPsec RoCE policy */ -#define KERNEL_NIC_PRIO_NUM_LEVELS 10 +#define KERNEL_NIC_PRIO_NUM_LEVELS 11 #define KERNEL_NIC_NUM_PRIOS 1 /* One more level for tc, and one more for promisc */ #define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 2) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h index b111ccd03b02..74ea5da58b7e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h @@ -47,7 +47,20 @@ int mlx5_crdump_collect(struct mlx5_core_dev *dev, u32 *cr_data); static inline struct net_device *mlx5_uplink_netdev_get(struct mlx5_core_dev *mdev) { - return mdev->mlx5e_res.uplink_netdev; + struct mlx5e_resources *mlx5e_res = &mdev->mlx5e_res; + struct net_device *netdev; + + mutex_lock(&mlx5e_res->uplink_netdev_lock); + netdev = mlx5e_res->uplink_netdev; + netdev_hold(netdev, &mlx5e_res->tracker, GFP_KERNEL); + mutex_unlock(&mlx5e_res->uplink_netdev_lock); + return netdev; +} + +static inline void mlx5_uplink_netdev_put(struct mlx5_core_dev *mdev, + struct net_device *netdev) +{ + netdev_put(netdev, &mdev->mlx5e_res.tracker); } struct mlx5_sd; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 2d7adf7444ba..aa9f2b0a77d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -1170,7 +1170,11 @@ const struct mlx5_link_info *mlx5_port_ptys2info(struct mlx5_core_dev *mdev, mlx5e_port_get_link_mode_info_arr(mdev, &table, &max_size, force_legacy); i = find_first_bit(&temp, max_size); - if (i < max_size) + + /* mlx5e_link_info has holes. Check speed + * is not zero as indication of one. + */ + if (i < max_size && table[i].speed) return &table[i]; return NULL; diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c index 56d5464222d9..cdbf82affa7b 100644 --- a/drivers/net/ethernet/natsemi/ns83820.c +++ b/drivers/net/ethernet/natsemi/ns83820.c @@ -820,7 +820,7 @@ static void rx_irq(struct net_device *ndev) struct ns83820 *dev = PRIV(ndev); struct rx_info *info = &dev->rx_info; unsigned next_rx; - int rx_rc, len; + int len; u32 cmdsts; __le32 *desc; unsigned long flags; @@ -881,8 +881,10 @@ static void rx_irq(struct net_device *ndev) if (likely(CMDSTS_OK & cmdsts)) { #endif skb_put(skb, len); - if (unlikely(!skb)) + if (unlikely(!skb)) { + ndev->stats.rx_dropped++; goto netdev_mangle_me_harder_failed; + } if (cmdsts & CMDSTS_DEST_MULTI) ndev->stats.multicast++; ndev->stats.rx_packets++; @@ -901,15 +903,12 @@ static void rx_irq(struct net_device *ndev) __vlan_hwaccel_put_tag(skb, htons(ETH_P_IPV6), tag); } #endif - rx_rc = netif_rx(skb); - if (NET_RX_DROP == rx_rc) { -netdev_mangle_me_harder_failed: - ndev->stats.rx_dropped++; - } + netif_rx(skb); } else { dev_kfree_skb_irq(skb); } +netdev_mangle_me_harder_failed: nr++; next_rx = info->next_rx; desc = info->descs + (DESC_SIZE * next_rx); diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 9c3d3dd2f847..1f0cea3cae92 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -4462,10 +4462,11 @@ static enum dbg_status qed_protection_override_dump(struct qed_hwfn *p_hwfn, goto out; } - /* Add override window info to buffer */ + /* Add override window info to buffer, preventing buffer overflow */ override_window_dwords = - qed_rd(p_hwfn, p_ptt, GRC_REG_NUMBER_VALID_OVERRIDE_WINDOW) * - PROTECTION_OVERRIDE_ELEMENT_DWORDS; + min(qed_rd(p_hwfn, p_ptt, GRC_REG_NUMBER_VALID_OVERRIDE_WINDOW) * + PROTECTION_OVERRIDE_ELEMENT_DWORDS, + PROTECTION_OVERRIDE_DEPTH_DWORDS); if (override_window_dwords) { addr = BYTES_TO_DWORDS(GRC_REG_PROTECTION_OVERRIDE_WINDOW); offset += qed_grc_dump_addr_range(p_hwfn, diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index dadce6009791..e42d0fdefee1 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -654,7 +654,7 @@ static void icssg_prueth_hsr_fdb_add_del(struct prueth_emac *emac, static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr) { - struct net_device *real_dev; + struct net_device *real_dev, *port_dev; struct prueth_emac *emac; u8 vlan_id, i; @@ -663,11 +663,15 @@ static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr) if (is_hsr_master(real_dev)) { for (i = HSR_PT_SLAVE_A; i < HSR_PT_INTERLINK; i++) { - emac = netdev_priv(hsr_get_port_ndev(real_dev, i)); - if (!emac) + port_dev = hsr_get_port_ndev(real_dev, i); + emac = netdev_priv(port_dev); + if (!emac) { + dev_put(port_dev); return -EINVAL; + } icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id, true); + dev_put(port_dev); } } else { emac = netdev_priv(real_dev); @@ -679,7 +683,7 @@ static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr) static int icssg_prueth_hsr_del_mcast(struct net_device *ndev, const u8 *addr) { - struct net_device *real_dev; + struct net_device *real_dev, *port_dev; struct prueth_emac *emac; u8 vlan_id, i; @@ -688,11 +692,15 @@ static int icssg_prueth_hsr_del_mcast(struct net_device *ndev, const u8 *addr) if (is_hsr_master(real_dev)) { for (i = HSR_PT_SLAVE_A; i < HSR_PT_INTERLINK; i++) { - emac = netdev_priv(hsr_get_port_ndev(real_dev, i)); - if (!emac) + port_dev = hsr_get_port_ndev(real_dev, i); + emac = netdev_priv(port_dev); + if (!emac) { + dev_put(port_dev); return -EINVAL; + } icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id, false); + dev_put(port_dev); } } else { emac = netdev_priv(real_dev); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index bcd07a715752..5cb353a97d6d 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -2078,10 +2078,6 @@ static void wx_setup_mrqc(struct wx *wx) { u32 rss_field = 0; - /* VT, and RSS do not coexist at the same time */ - if (test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags)) - return; - /* Disable indicating checksum in descriptor, enables RSS hash */ wr32m(wx, WX_PSR_CTL, WX_PSR_CTL_PCSD, WX_PSR_CTL_PCSD); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 01329fe7451a..0eca96eeed58 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -4286,6 +4286,7 @@ static int macsec_newlink(struct net_device *dev, if (err < 0) goto del_dev; + netdev_update_features(dev); netif_stacked_transfer_operstate(real_dev, dev); linkwatch_fire_event(dev); diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 28acc6392cfc..392749aae54d 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -361,7 +361,7 @@ config NXP_TJA11XX_PHY tristate "NXP TJA11xx PHYs support" depends on HWMON help - Currently supports the NXP TJA1100 and TJA1101 PHY. + Currently supports the NXP TJA1100, TJA1101 and TJA1102 PHYs. config NCN26000_PHY tristate "Onsemi 10BASE-T1S Ethernet PHY" diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 13df28445f02..c02da57a4da5 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -1065,23 +1065,19 @@ EXPORT_SYMBOL_GPL(phy_inband_caps); */ int phy_config_inband(struct phy_device *phydev, unsigned int modes) { - int err; + lockdep_assert_held(&phydev->lock); if (!!(modes & LINK_INBAND_DISABLE) + !!(modes & LINK_INBAND_ENABLE) + !!(modes & LINK_INBAND_BYPASS) != 1) return -EINVAL; - mutex_lock(&phydev->lock); if (!phydev->drv) - err = -EIO; + return -EIO; else if (!phydev->drv->config_inband) - err = -EOPNOTSUPP; - else - err = phydev->drv->config_inband(phydev, modes); - mutex_unlock(&phydev->lock); + return -EOPNOTSUPP; - return err; + return phydev->drv->config_inband(phydev, modes); } EXPORT_SYMBOL(phy_config_inband); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 7556aa3dd7ee..c82c1997147b 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -287,8 +287,7 @@ static bool phy_uses_state_machine(struct phy_device *phydev) if (phydev->phy_link_change == phy_link_change) return phydev->attached_dev && phydev->adjust_link; - /* phydev->phy_link_change is implicitly phylink_phy_change() */ - return true; + return !!phydev->phy_link_change; } static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) @@ -1864,6 +1863,8 @@ void phy_detach(struct phy_device *phydev) phydev->attached_dev = NULL; phy_link_topo_del_phy(dev, phydev); } + + phydev->phy_link_change = NULL; phydev->phylink = NULL; if (!phydev->is_on_sfp_module) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index c7cb95aa8007..1988b7d2089a 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -67,6 +67,8 @@ struct phylink { struct timer_list link_poll; struct mutex state_mutex; + /* Serialize updates to pl->phydev with phylink_resolve() */ + struct mutex phydev_mutex; struct phylink_link_state phy_state; unsigned int phy_ib_mode; struct work_struct resolve; @@ -1432,6 +1434,7 @@ static void phylink_get_fixed_state(struct phylink *pl, static void phylink_mac_initial_config(struct phylink *pl, bool force_restart) { struct phylink_link_state link_state; + struct phy_device *phy = pl->phydev; switch (pl->req_link_an_mode) { case MLO_AN_PHY: @@ -1455,7 +1458,11 @@ static void phylink_mac_initial_config(struct phylink *pl, bool force_restart) link_state.link = false; phylink_apply_manual_flow(pl, &link_state); + if (phy) + mutex_lock(&phy->lock); phylink_major_config(pl, force_restart, &link_state); + if (phy) + mutex_unlock(&phy->lock); } static const char *phylink_pause_to_str(int pause) @@ -1591,8 +1598,13 @@ static void phylink_resolve(struct work_struct *w) struct phylink_link_state link_state; bool mac_config = false; bool retrigger = false; + struct phy_device *phy; bool cur_link_state; + mutex_lock(&pl->phydev_mutex); + phy = pl->phydev; + if (phy) + mutex_lock(&phy->lock); mutex_lock(&pl->state_mutex); cur_link_state = phylink_link_is_up(pl); @@ -1626,11 +1638,11 @@ static void phylink_resolve(struct work_struct *w) /* If we have a phy, the "up" state is the union of both the * PHY and the MAC */ - if (pl->phydev) + if (phy) link_state.link &= pl->phy_state.link; /* Only update if the PHY link is up */ - if (pl->phydev && pl->phy_state.link) { + if (phy && pl->phy_state.link) { /* If the interface has changed, force a link down * event if the link isn't already down, and re-resolve. */ @@ -1694,6 +1706,9 @@ static void phylink_resolve(struct work_struct *w) queue_work(system_power_efficient_wq, &pl->resolve); } mutex_unlock(&pl->state_mutex); + if (phy) + mutex_unlock(&phy->lock); + mutex_unlock(&pl->phydev_mutex); } static void phylink_run_resolve(struct phylink *pl) @@ -1829,6 +1844,7 @@ struct phylink *phylink_create(struct phylink_config *config, if (!pl) return ERR_PTR(-ENOMEM); + mutex_init(&pl->phydev_mutex); mutex_init(&pl->state_mutex); INIT_WORK(&pl->resolve, phylink_resolve); @@ -2089,6 +2105,7 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, dev_name(&phy->mdio.dev), phy->drv->name, irq_str); kfree(irq_str); + mutex_lock(&pl->phydev_mutex); mutex_lock(&phy->lock); mutex_lock(&pl->state_mutex); pl->phydev = phy; @@ -2134,6 +2151,7 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, mutex_unlock(&pl->state_mutex); mutex_unlock(&phy->lock); + mutex_unlock(&pl->phydev_mutex); phylink_dbg(pl, "phy: %s setting supported %*pb advertising %*pb\n", @@ -2312,6 +2330,7 @@ void phylink_disconnect_phy(struct phylink *pl) ASSERT_RTNL(); + mutex_lock(&pl->phydev_mutex); phy = pl->phydev; if (phy) { mutex_lock(&phy->lock); @@ -2321,8 +2340,11 @@ void phylink_disconnect_phy(struct phylink *pl) pl->mac_tx_clk_stop = false; mutex_unlock(&pl->state_mutex); mutex_unlock(&phy->lock); - flush_work(&pl->resolve); + } + mutex_unlock(&pl->phydev_mutex); + if (phy) { + flush_work(&pl->resolve); phy_disconnect(phy); } } diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index bd1ec3b2c084..3a3965b79942 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -4078,12 +4078,68 @@ static int ath12k_mac_fils_discovery(struct ath12k_link_vif *arvif, return ret; } +static void ath12k_mac_vif_setup_ps(struct ath12k_link_vif *arvif) +{ + struct ath12k *ar = arvif->ar; + struct ieee80211_vif *vif = arvif->ahvif->vif; + struct ieee80211_conf *conf = &ath12k_ar_to_hw(ar)->conf; + enum wmi_sta_powersave_param param; + struct ieee80211_bss_conf *info; + enum wmi_sta_ps_mode psmode; + int ret; + int timeout; + bool enable_ps; + + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + + if (vif->type != NL80211_IFTYPE_STATION) + return; + + enable_ps = arvif->ahvif->ps; + if (enable_ps) { + psmode = WMI_STA_PS_MODE_ENABLED; + param = WMI_STA_PS_PARAM_INACTIVITY_TIME; + + timeout = conf->dynamic_ps_timeout; + if (timeout == 0) { + info = ath12k_mac_get_link_bss_conf(arvif); + if (!info) { + ath12k_warn(ar->ab, "unable to access bss link conf in setup ps for vif %pM link %u\n", + vif->addr, arvif->link_id); + return; + } + + /* firmware doesn't like 0 */ + timeout = ieee80211_tu_to_usec(info->beacon_int) / 1000; + } + + ret = ath12k_wmi_set_sta_ps_param(ar, arvif->vdev_id, param, + timeout); + if (ret) { + ath12k_warn(ar->ab, "failed to set inactivity time for vdev %d: %i\n", + arvif->vdev_id, ret); + return; + } + } else { + psmode = WMI_STA_PS_MODE_DISABLED; + } + + ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac vdev %d psmode %s\n", + arvif->vdev_id, psmode ? "enable" : "disable"); + + ret = ath12k_wmi_pdev_set_ps_mode(ar, arvif->vdev_id, psmode); + if (ret) + ath12k_warn(ar->ab, "failed to set sta power save mode %d for vdev %d: %d\n", + psmode, arvif->vdev_id, ret); +} + static void ath12k_mac_op_vif_cfg_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u64 changed) { struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); unsigned long links = ahvif->links_map; + struct ieee80211_vif_cfg *vif_cfg; struct ieee80211_bss_conf *info; struct ath12k_link_vif *arvif; struct ieee80211_sta *sta; @@ -4147,61 +4203,24 @@ static void ath12k_mac_op_vif_cfg_changed(struct ieee80211_hw *hw, } } } -} - -static void ath12k_mac_vif_setup_ps(struct ath12k_link_vif *arvif) -{ - struct ath12k *ar = arvif->ar; - struct ieee80211_vif *vif = arvif->ahvif->vif; - struct ieee80211_conf *conf = &ath12k_ar_to_hw(ar)->conf; - enum wmi_sta_powersave_param param; - struct ieee80211_bss_conf *info; - enum wmi_sta_ps_mode psmode; - int ret; - int timeout; - bool enable_ps; - lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + if (changed & BSS_CHANGED_PS) { + links = ahvif->links_map; + vif_cfg = &vif->cfg; - if (vif->type != NL80211_IFTYPE_STATION) - return; + for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) { + arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]); + if (!arvif || !arvif->ar) + continue; - enable_ps = arvif->ahvif->ps; - if (enable_ps) { - psmode = WMI_STA_PS_MODE_ENABLED; - param = WMI_STA_PS_PARAM_INACTIVITY_TIME; + ar = arvif->ar; - timeout = conf->dynamic_ps_timeout; - if (timeout == 0) { - info = ath12k_mac_get_link_bss_conf(arvif); - if (!info) { - ath12k_warn(ar->ab, "unable to access bss link conf in setup ps for vif %pM link %u\n", - vif->addr, arvif->link_id); - return; + if (ar->ab->hw_params->supports_sta_ps) { + ahvif->ps = vif_cfg->ps; + ath12k_mac_vif_setup_ps(arvif); } - - /* firmware doesn't like 0 */ - timeout = ieee80211_tu_to_usec(info->beacon_int) / 1000; } - - ret = ath12k_wmi_set_sta_ps_param(ar, arvif->vdev_id, param, - timeout); - if (ret) { - ath12k_warn(ar->ab, "failed to set inactivity time for vdev %d: %i\n", - arvif->vdev_id, ret); - return; - } - } else { - psmode = WMI_STA_PS_MODE_DISABLED; } - - ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac vdev %d psmode %s\n", - arvif->vdev_id, psmode ? "enable" : "disable"); - - ret = ath12k_wmi_pdev_set_ps_mode(ar, arvif->vdev_id, psmode); - if (ret) - ath12k_warn(ar->ab, "failed to set sta power save mode %d for vdev %d: %d\n", - psmode, arvif->vdev_id, ret); } static bool ath12k_mac_supports_tpc(struct ath12k *ar, struct ath12k_vif *ahvif, @@ -4223,7 +4242,6 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar, { struct ath12k_vif *ahvif = arvif->ahvif; struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif); - struct ieee80211_vif_cfg *vif_cfg = &vif->cfg; struct cfg80211_chan_def def; u32 param_id, param_value; enum nl80211_band band; @@ -4510,12 +4528,6 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar, } ath12k_mac_fils_discovery(arvif, info); - - if (changed & BSS_CHANGED_PS && - ar->ab->hw_params->supports_sta_ps) { - ahvif->ps = vif_cfg->ps; - ath12k_mac_vif_setup_ps(arvif); - } } static struct ath12k_vif_cache *ath12k_ahvif_get_link_cache(struct ath12k_vif *ahvif, diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index 742ffeb48bce..29dadedefdd2 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -843,7 +843,7 @@ int ath12k_wmi_mgmt_send(struct ath12k_link_vif *arvif, u32 buf_id, cmd->tx_params_valid = 0; frame_tlv = (struct wmi_tlv *)(skb->data + sizeof(*cmd)); - frame_tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_BYTE, buf_len); + frame_tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_BYTE, buf_len_aligned); memcpy(frame_tlv->value, frame->data, buf_len); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index f9e2095d6490..7e56e4ff7642 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -124,13 +124,13 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x0082, 0x1304, iwl6005_mac_cfg)},/* low 5GHz active */ {IWL_PCI_DEVICE(0x0082, 0x1305, iwl6005_mac_cfg)},/* high 5GHz active */ -/* 6x30 Series */ - {IWL_PCI_DEVICE(0x008A, 0x5305, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x008A, 0x5307, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x008A, 0x5325, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x008A, 0x5327, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x008B, 0x5315, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x008B, 0x5317, iwl1000_mac_cfg)}, +/* 1030/6x30 Series */ + {IWL_PCI_DEVICE(0x008A, 0x5305, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x008A, 0x5307, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x008A, 0x5325, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x008A, 0x5327, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x008B, 0x5315, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x008B, 0x5317, iwl6030_mac_cfg)}, {IWL_PCI_DEVICE(0x0090, 0x5211, iwl6030_mac_cfg)}, {IWL_PCI_DEVICE(0x0090, 0x5215, iwl6030_mac_cfg)}, {IWL_PCI_DEVICE(0x0090, 0x5216, iwl6030_mac_cfg)}, @@ -181,12 +181,12 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x08AE, 0x1027, iwl1000_mac_cfg)}, /* 130 Series WiFi */ - {IWL_PCI_DEVICE(0x0896, 0x5005, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x0896, 0x5007, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x0897, 0x5015, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x0897, 0x5017, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x0896, 0x5025, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x0896, 0x5027, iwl1000_mac_cfg)}, + {IWL_PCI_DEVICE(0x0896, 0x5005, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x0896, 0x5007, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x0897, 0x5015, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x0897, 0x5017, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x0896, 0x5025, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x0896, 0x5027, iwl6030_mac_cfg)}, /* 2x00 Series */ {IWL_PCI_DEVICE(0x0890, 0x4022, iwl2000_mac_cfg)}, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c index d912e709a92c..bb03dad4a300 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c @@ -2092,7 +2092,7 @@ static void iwl_txq_gen1_update_byte_cnt_tbl(struct iwl_trans *trans, break; } - if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_9000 && + if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_7000 && trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210) len = DIV_ROUND_UP(len, 4); diff --git a/drivers/net/wireless/virtual/virt_wifi.c b/drivers/net/wireless/virtual/virt_wifi.c index 1fffeff2190c..4eae89376feb 100644 --- a/drivers/net/wireless/virtual/virt_wifi.c +++ b/drivers/net/wireless/virtual/virt_wifi.c @@ -277,7 +277,9 @@ static void virt_wifi_connect_complete(struct work_struct *work) priv->is_connected = true; /* Schedules an event that acquires the rtnl lock. */ - cfg80211_connect_result(priv->upperdev, requested_bss, NULL, 0, NULL, 0, + cfg80211_connect_result(priv->upperdev, + priv->is_connected ? fake_router_bssid : NULL, + NULL, 0, NULL, 0, status, GFP_KERNEL); netif_carrier_on(priv->upperdev); } diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c index 755651f33811..a72aa57591c0 100644 --- a/drivers/pci/controller/pci-mvebu.c +++ b/drivers/pci/controller/pci-mvebu.c @@ -1168,12 +1168,6 @@ static void __iomem *mvebu_pcie_map_registers(struct platform_device *pdev, return devm_ioremap_resource(&pdev->dev, &port->regs); } -#define DT_FLAGS_TO_TYPE(flags) (((flags) >> 24) & 0x03) -#define DT_TYPE_IO 0x1 -#define DT_TYPE_MEM32 0x2 -#define DT_CPUADDR_TO_TARGET(cpuaddr) (((cpuaddr) >> 56) & 0xFF) -#define DT_CPUADDR_TO_ATTR(cpuaddr) (((cpuaddr) >> 48) & 0xFF) - static int mvebu_get_tgt_attr(struct device_node *np, int devfn, unsigned long type, unsigned int *tgt, @@ -1189,19 +1183,12 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn, return -EINVAL; for_each_of_range(&parser, &range) { - unsigned long rtype; u32 slot = upper_32_bits(range.bus_addr); - if (DT_FLAGS_TO_TYPE(range.flags) == DT_TYPE_IO) - rtype = IORESOURCE_IO; - else if (DT_FLAGS_TO_TYPE(range.flags) == DT_TYPE_MEM32) - rtype = IORESOURCE_MEM; - else - continue; - - if (slot == PCI_SLOT(devfn) && type == rtype) { - *tgt = DT_CPUADDR_TO_TARGET(range.cpu_addr); - *attr = DT_CPUADDR_TO_ATTR(range.cpu_addr); + if (slot == PCI_SLOT(devfn) && + type == (range.flags & IORESOURCE_TYPE_BITS)) { + *tgt = (range.parent_bus_addr >> 56) & 0xFF; + *attr = (range.parent_bus_addr >> 48) & 0xFF; return 0; } } diff --git a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c index e0f2acc8109c..8fcbc312fd61 100644 --- a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c +++ b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c @@ -127,13 +127,13 @@ static int eusb2_repeater_init(struct phy *phy) rptr->cfg->init_tbl[i].value); /* Override registers from devicetree values */ - if (!of_property_read_u8(np, "qcom,tune-usb2-amplitude", &val)) + if (!of_property_read_u8(np, "qcom,tune-usb2-preem", &val)) regmap_write(regmap, base + EUSB2_TUNE_USB2_PREEM, val); if (!of_property_read_u8(np, "qcom,tune-usb2-disc-thres", &val)) regmap_write(regmap, base + EUSB2_TUNE_HSDISC, val); - if (!of_property_read_u8(np, "qcom,tune-usb2-preem", &val)) + if (!of_property_read_u8(np, "qcom,tune-usb2-amplitude", &val)) regmap_write(regmap, base + EUSB2_TUNE_IUSB2, val); /* Wait for status OK */ diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c index 95830dcfdec9..0fa63b734b67 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c @@ -3067,6 +3067,14 @@ struct qmp_pcie { struct clk_fixed_rate aux_clk_fixed; }; +static bool qphy_checkbits(const void __iomem *base, u32 offset, u32 val) +{ + u32 reg; + + reg = readl(base + offset); + return (reg & val) == val; +} + static inline void qphy_setbits(void __iomem *base, u32 offset, u32 val) { u32 reg; @@ -4339,16 +4347,21 @@ static int qmp_pcie_init(struct phy *phy) struct qmp_pcie *qmp = phy_get_drvdata(phy); const struct qmp_phy_cfg *cfg = qmp->cfg; void __iomem *pcs = qmp->pcs; - bool phy_initialized = !!(readl(pcs + cfg->regs[QPHY_START_CTRL])); int ret; - qmp->skip_init = qmp->nocsr_reset && phy_initialized; /* - * We need to check the existence of init sequences in two cases: - * 1. The PHY doesn't support no_csr reset. - * 2. The PHY supports no_csr reset but isn't initialized by bootloader. - * As we can't skip init in these two cases. + * We can skip PHY initialization if all of the following conditions + * are met: + * 1. The PHY supports the nocsr_reset that preserves the PHY config. + * 2. The PHY was started (and not powered down again) by the + * bootloader, with all of the expected bits set correctly. + * In this case, we can continue without having the init sequence + * defined in the driver. */ + qmp->skip_init = qmp->nocsr_reset && + qphy_checkbits(pcs, cfg->regs[QPHY_START_CTRL], SERDES_START | PCS_START) && + qphy_checkbits(pcs, cfg->regs[QPHY_PCS_POWER_DOWN_CONTROL], cfg->pwrdn_ctrl); + if (!qmp->skip_init && !cfg->tbls.serdes_num) { dev_err(qmp->dev, "Init sequence not available\n"); return -ENODATA; diff --git a/drivers/phy/tegra/xusb-tegra210.c b/drivers/phy/tegra/xusb-tegra210.c index ebc8a7e21a31..3409924498e9 100644 --- a/drivers/phy/tegra/xusb-tegra210.c +++ b/drivers/phy/tegra/xusb-tegra210.c @@ -3164,18 +3164,22 @@ tegra210_xusb_padctl_probe(struct device *dev, } pdev = of_find_device_by_node(np); + of_node_put(np); if (!pdev) { dev_warn(dev, "PMC device is not available\n"); goto out; } - if (!platform_get_drvdata(pdev)) + if (!platform_get_drvdata(pdev)) { + put_device(&pdev->dev); return ERR_PTR(-EPROBE_DEFER); + } padctl->regmap = dev_get_regmap(&pdev->dev, "usb_sleepwalk"); if (!padctl->regmap) dev_info(dev, "failed to find PMC regmap\n"); + put_device(&pdev->dev); out: return &padctl->base; } diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c index ff5d5e29629f..50adabb867cb 100644 --- a/drivers/phy/ti/phy-gmii-sel.c +++ b/drivers/phy/ti/phy-gmii-sel.c @@ -34,6 +34,7 @@ enum { PHY_GMII_SEL_PORT_MODE = 0, PHY_GMII_SEL_RGMII_ID_MODE, PHY_GMII_SEL_RMII_IO_CLK_EN, + PHY_GMII_SEL_FIXED_TX_DELAY, PHY_GMII_SEL_LAST, }; @@ -127,6 +128,11 @@ static int phy_gmii_sel_mode(struct phy *phy, enum phy_mode mode, int submode) goto unsupported; } + /* With a fixed delay, some modes are not supported at all. */ + if (soc_data->features & BIT(PHY_GMII_SEL_FIXED_TX_DELAY) && + rgmii_id != 0) + return -EINVAL; + if_phy->phy_if_mode = submode; dev_dbg(dev, "%s id:%u mode:%u rgmii_id:%d rmii_clk_ext:%d\n", @@ -210,25 +216,46 @@ struct phy_gmii_sel_soc_data phy_gmii_sel_soc_dm814 = { static const struct reg_field phy_gmii_sel_fields_am654[][PHY_GMII_SEL_LAST] = { - { [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x0, 0, 2), }, - { [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x4, 0, 2), }, - { [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x8, 0, 2), }, - { [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0xC, 0, 2), }, - { [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x10, 0, 2), }, - { [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x14, 0, 2), }, - { [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x18, 0, 2), }, - { [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x1C, 0, 2), }, + { + [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x0, 0, 2), + [PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x0, 4, 4), + }, { + [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x4, 0, 2), + [PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x4, 4, 4), + }, { + [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x8, 0, 2), + [PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x8, 4, 4), + }, { + [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0xC, 0, 2), + [PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0xC, 4, 4), + }, { + [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x10, 0, 2), + [PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x10, 4, 4), + }, { + [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x14, 0, 2), + [PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x14, 4, 4), + }, { + [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x18, 0, 2), + [PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x18, 4, 4), + }, { + [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x1C, 0, 2), + [PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x1C, 4, 4), + }, }; static const struct phy_gmii_sel_soc_data phy_gmii_sel_soc_am654 = { .use_of_data = true, + .features = BIT(PHY_GMII_SEL_RGMII_ID_MODE) | + BIT(PHY_GMII_SEL_FIXED_TX_DELAY), .regfields = phy_gmii_sel_fields_am654, }; static const struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw5g_soc_j7200 = { .use_of_data = true, + .features = BIT(PHY_GMII_SEL_RGMII_ID_MODE) | + BIT(PHY_GMII_SEL_FIXED_TX_DELAY), .regfields = phy_gmii_sel_fields_am654, .extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_SGMII) | BIT(PHY_INTERFACE_MODE_USXGMII), @@ -239,6 +266,8 @@ struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw5g_soc_j7200 = { static const struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw9g_soc_j721e = { .use_of_data = true, + .features = BIT(PHY_GMII_SEL_RGMII_ID_MODE) | + BIT(PHY_GMII_SEL_FIXED_TX_DELAY), .regfields = phy_gmii_sel_fields_am654, .extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_SGMII), .num_ports = 8, @@ -248,6 +277,8 @@ struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw9g_soc_j721e = { static const struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw9g_soc_j784s4 = { .use_of_data = true, + .features = BIT(PHY_GMII_SEL_RGMII_ID_MODE) | + BIT(PHY_GMII_SEL_FIXED_TX_DELAY), .regfields = phy_gmii_sel_fields_am654, .extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_SGMII) | BIT(PHY_INTERFACE_MODE_USXGMII), diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c index c1a0ef979142..c444bb2530ca 100644 --- a/drivers/phy/ti/phy-omap-usb2.c +++ b/drivers/phy/ti/phy-omap-usb2.c @@ -363,6 +363,13 @@ static void omap_usb2_init_errata(struct omap_usb *phy) phy->flags |= OMAP_USB2_DISABLE_CHRG_DET; } +static void omap_usb2_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + static int omap_usb2_probe(struct platform_device *pdev) { struct omap_usb *phy; @@ -373,6 +380,7 @@ static int omap_usb2_probe(struct platform_device *pdev) struct device_node *control_node; struct platform_device *control_pdev; const struct usb_phy_data *phy_data; + int ret; phy_data = device_get_match_data(&pdev->dev); if (!phy_data) @@ -423,6 +431,11 @@ static int omap_usb2_probe(struct platform_device *pdev) return -EINVAL; } phy->control_dev = &control_pdev->dev; + + ret = devm_add_action_or_reset(&pdev->dev, omap_usb2_put_device, + phy->control_dev); + if (ret) + return ret; } else { if (of_property_read_u32_index(node, "syscon-phy-power", 1, diff --git a/drivers/phy/ti/phy-ti-pipe3.c b/drivers/phy/ti/phy-ti-pipe3.c index da2cbacb982c..ae764d6524c9 100644 --- a/drivers/phy/ti/phy-ti-pipe3.c +++ b/drivers/phy/ti/phy-ti-pipe3.c @@ -667,12 +667,20 @@ static int ti_pipe3_get_clk(struct ti_pipe3 *phy) return 0; } +static void ti_pipe3_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + static int ti_pipe3_get_sysctrl(struct ti_pipe3 *phy) { struct device *dev = phy->dev; struct device_node *node = dev->of_node; struct device_node *control_node; struct platform_device *control_pdev; + int ret; phy->phy_power_syscon = syscon_regmap_lookup_by_phandle(node, "syscon-phy-power"); @@ -704,6 +712,11 @@ static int ti_pipe3_get_sysctrl(struct ti_pipe3 *phy) } phy->control_dev = &control_pdev->dev; + + ret = devm_add_action_or_reset(dev, ti_pipe3_put_device, + phy->control_dev); + if (ret) + return ret; } if (phy->mode == PIPE3_MODE_PCIE) { diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c index 18fb44139de2..4d0a38e06f08 100644 --- a/drivers/platform/x86/amd/pmc/pmc-quirks.c +++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c @@ -239,6 +239,14 @@ static const struct dmi_system_id fwbug_list[] = { DMI_MATCH(DMI_BOARD_NAME, "WUJIE14-GX4HRXL"), } }, + { + .ident = "MECHREVO Yilong15Pro Series GM5HG7A", + .driver_data = &quirk_spurious_8042, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MECHREVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "Yilong15Pro Series GM5HG7A"), + } + }, /* https://bugzilla.kernel.org/show_bug.cgi?id=220116 */ { .ident = "PCSpecialist Lafite Pro V 14M", diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index ef988605c4da..bc544a4a5266 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -403,6 +403,7 @@ static const struct acpi_device_id amd_pmf_acpi_ids[] = { {"AMDI0103", 0}, {"AMDI0105", 0}, {"AMDI0107", 0}, + {"AMDI0108", 0}, { } }; MODULE_DEVICE_TABLE(acpi, amd_pmf_acpi_ids); diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index 3a488cf9ca06..6a62bc5b02fd 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -673,6 +673,8 @@ static void asus_nb_wmi_key_filter(struct asus_wmi_driver *asus_wmi, int *code, if (atkbd_reports_vol_keys) *code = ASUS_WMI_KEY_IGNORE; break; + case 0x5D: /* Wireless console Toggle */ + case 0x5E: /* Wireless console Enable / Keyboard Attach, Detach */ case 0x5F: /* Wireless console Disable / Special Key */ if (quirks->key_wlan_event) *code = quirks->key_wlan_event; diff --git a/drivers/platform/x86/oxpec.c b/drivers/platform/x86/oxpec.c index eb076bb4099b..54377b282ff8 100644 --- a/drivers/platform/x86/oxpec.c +++ b/drivers/platform/x86/oxpec.c @@ -126,6 +126,13 @@ static const struct dmi_system_id dmi_table[] = { }, { .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "AOKZOE"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "AOKZOE A1X"), + }, + .driver_data = (void *)oxp_fly, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "AYANEO"), DMI_MATCH(DMI_BOARD_NAME, "AYANEO 2"), }, @@ -306,6 +313,13 @@ static const struct dmi_system_id dmi_table[] = { }, .driver_data = (void *)oxp_x1, }, + { + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "ONEXPLAYER X1Pro EVA-02"), + }, + .driver_data = (void *)oxp_x1, + }, {}, }; diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c index 0006ab3d0789..61c2277c9ce3 100644 --- a/drivers/pmdomain/core.c +++ b/drivers/pmdomain/core.c @@ -187,6 +187,7 @@ static const struct genpd_lock_ops genpd_raw_spin_ops = { #define genpd_is_opp_table_fw(genpd) (genpd->flags & GENPD_FLAG_OPP_TABLE_FW) #define genpd_is_dev_name_fw(genpd) (genpd->flags & GENPD_FLAG_DEV_NAME_FW) #define genpd_is_no_sync_state(genpd) (genpd->flags & GENPD_FLAG_NO_SYNC_STATE) +#define genpd_is_no_stay_on(genpd) (genpd->flags & GENPD_FLAG_NO_STAY_ON) static inline bool irq_safe_dev_in_sleep_domain(struct device *dev, const struct generic_pm_domain *genpd) @@ -1357,7 +1358,6 @@ err_poweroff: return ret; } -#ifndef CONFIG_PM_GENERIC_DOMAINS_OF static bool pd_ignore_unused; static int __init pd_ignore_unused_setup(char *__unused) { @@ -1382,9 +1382,6 @@ static int __init genpd_power_off_unused(void) mutex_lock(&gpd_list_lock); list_for_each_entry(genpd, &gpd_list, gpd_list_node) { - genpd_lock(genpd); - genpd->stay_on = false; - genpd_unlock(genpd); genpd_queue_power_off_work(genpd); } @@ -1393,7 +1390,6 @@ static int __init genpd_power_off_unused(void) return 0; } late_initcall_sync(genpd_power_off_unused); -#endif #ifdef CONFIG_PM_SLEEP @@ -2367,6 +2363,18 @@ static void genpd_lock_init(struct generic_pm_domain *genpd) } } +#ifdef CONFIG_PM_GENERIC_DOMAINS_OF +static void genpd_set_stay_on(struct generic_pm_domain *genpd, bool is_off) +{ + genpd->stay_on = !genpd_is_no_stay_on(genpd) && !is_off; +} +#else +static void genpd_set_stay_on(struct generic_pm_domain *genpd, bool is_off) +{ + genpd->stay_on = false; +} +#endif + /** * pm_genpd_init - Initialize a generic I/O PM domain object. * @genpd: PM domain object to initialize. @@ -2392,7 +2400,7 @@ int pm_genpd_init(struct generic_pm_domain *genpd, INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn); atomic_set(&genpd->sd_count, 0); genpd->status = is_off ? GENPD_STATE_OFF : GENPD_STATE_ON; - genpd->stay_on = !is_off; + genpd_set_stay_on(genpd, is_off); genpd->sync_state = GENPD_SYNC_STATE_OFF; genpd->device_count = 0; genpd->provider = NULL; diff --git a/drivers/pmdomain/renesas/rcar-gen4-sysc.c b/drivers/pmdomain/renesas/rcar-gen4-sysc.c index 5aa7fa1df8fe..7434bf42d215 100644 --- a/drivers/pmdomain/renesas/rcar-gen4-sysc.c +++ b/drivers/pmdomain/renesas/rcar-gen4-sysc.c @@ -251,6 +251,7 @@ static int __init rcar_gen4_sysc_pd_setup(struct rcar_gen4_sysc_pd *pd) genpd->detach_dev = cpg_mssr_detach_dev; } + genpd->flags |= GENPD_FLAG_NO_STAY_ON; genpd->power_off = rcar_gen4_sysc_pd_power_off; genpd->power_on = rcar_gen4_sysc_pd_power_on; diff --git a/drivers/pmdomain/renesas/rcar-sysc.c b/drivers/pmdomain/renesas/rcar-sysc.c index 4b310c1d35fa..d8a8ffcde38d 100644 --- a/drivers/pmdomain/renesas/rcar-sysc.c +++ b/drivers/pmdomain/renesas/rcar-sysc.c @@ -241,6 +241,7 @@ static int __init rcar_sysc_pd_setup(struct rcar_sysc_pd *pd) } } + genpd->flags |= GENPD_FLAG_NO_STAY_ON; genpd->power_off = rcar_sysc_pd_power_off; genpd->power_on = rcar_sysc_pd_power_on; @@ -342,7 +343,7 @@ struct rcar_pm_domains { }; static struct genpd_onecell_data *rcar_sysc_onecell_data; -static struct device_node *rcar_sysc_onecell_np; +static struct device_node *rcar_sysc_onecell_np __initdata = NULL; static int __init rcar_sysc_pd_init(void) { diff --git a/drivers/pmdomain/renesas/rmobile-sysc.c b/drivers/pmdomain/renesas/rmobile-sysc.c index 8eedc9a1d825..a6bf7295e909 100644 --- a/drivers/pmdomain/renesas/rmobile-sysc.c +++ b/drivers/pmdomain/renesas/rmobile-sysc.c @@ -100,7 +100,8 @@ static void rmobile_init_pm_domain(struct rmobile_pm_domain *rmobile_pd) struct generic_pm_domain *genpd = &rmobile_pd->genpd; struct dev_power_governor *gov = rmobile_pd->gov; - genpd->flags |= GENPD_FLAG_PM_CLK | GENPD_FLAG_ACTIVE_WAKEUP; + genpd->flags |= GENPD_FLAG_PM_CLK | GENPD_FLAG_ACTIVE_WAKEUP | + GENPD_FLAG_NO_STAY_ON; genpd->attach_dev = cpg_mstp_attach_dev; genpd->detach_dev = cpg_mstp_detach_dev; diff --git a/drivers/pmdomain/rockchip/pm-domains.c b/drivers/pmdomain/rockchip/pm-domains.c index 242570c505fb..1955c6d453e4 100644 --- a/drivers/pmdomain/rockchip/pm-domains.c +++ b/drivers/pmdomain/rockchip/pm-domains.c @@ -865,7 +865,7 @@ static int rockchip_pm_add_one_domain(struct rockchip_pmu *pmu, pd->genpd.power_on = rockchip_pd_power_on; pd->genpd.attach_dev = rockchip_pd_attach_dev; pd->genpd.detach_dev = rockchip_pd_detach_dev; - pd->genpd.flags = GENPD_FLAG_PM_CLK; + pd->genpd.flags = GENPD_FLAG_PM_CLK | GENPD_FLAG_NO_STAY_ON; if (pd_info->active_wakeup) pd->genpd.flags |= GENPD_FLAG_ACTIVE_WAKEUP; pm_genpd_init(&pd->genpd, NULL, diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 93dcebbe1141..ad2d9ecf32a5 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1919,8 +1919,8 @@ static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag); - if ((cache.flags & 0xff) == 0xff) - cache.flags = -1; /* read error */ + if (di->chip == BQ27000 && (cache.flags & 0xff) == 0xff) + cache.flags = -ENODEV; /* bq27000 hdq read error */ if (cache.flags >= 0) { cache.capacity = bq27xxx_battery_read_soc(di); diff --git a/drivers/regulator/sy7636a-regulator.c b/drivers/regulator/sy7636a-regulator.c index d1e7ba1fb3e1..27e3d939b7bb 100644 --- a/drivers/regulator/sy7636a-regulator.c +++ b/drivers/regulator/sy7636a-regulator.c @@ -83,9 +83,11 @@ static int sy7636a_regulator_probe(struct platform_device *pdev) if (!regmap) return -EPROBE_DEFER; - gdp = devm_gpiod_get(pdev->dev.parent, "epd-pwr-good", GPIOD_IN); + device_set_of_node_from_dev(&pdev->dev, pdev->dev.parent); + + gdp = devm_gpiod_get(&pdev->dev, "epd-pwr-good", GPIOD_IN); if (IS_ERR(gdp)) { - dev_err(pdev->dev.parent, "Power good GPIO fault %ld\n", PTR_ERR(gdp)); + dev_err(&pdev->dev, "Power good GPIO fault %ld\n", PTR_ERR(gdp)); return PTR_ERR(gdp); } @@ -105,7 +107,6 @@ static int sy7636a_regulator_probe(struct platform_device *pdev) } config.dev = &pdev->dev; - config.dev->of_node = pdev->dev.parent->of_node; config.regmap = regmap; rdev = devm_regulator_register(&pdev->dev, &desc, &config); diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c index cd1f657f782d..13c663a154c4 100644 --- a/drivers/tty/hvc/hvc_console.c +++ b/drivers/tty/hvc/hvc_console.c @@ -543,10 +543,10 @@ static ssize_t hvc_write(struct tty_struct *tty, const u8 *buf, size_t count) } /* - * Racy, but harmless, kick thread if there is still pending data. + * Kick thread to flush if there's still pending data + * or to wakeup the write queue. */ - if (hp->n_outbuf) - hvc_kick(); + hvc_kick(); return written; } diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 3f38fba8f6ea..a668e0bb26b3 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1177,17 +1177,6 @@ static int sc16is7xx_startup(struct uart_port *port) sc16is7xx_port_write(port, SC16IS7XX_FCR_REG, SC16IS7XX_FCR_FIFO_BIT); - /* Enable EFR */ - sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, - SC16IS7XX_LCR_CONF_MODE_B); - - regcache_cache_bypass(one->regmap, true); - - /* Enable write access to enhanced features and internal clock div */ - sc16is7xx_port_update(port, SC16IS7XX_EFR_REG, - SC16IS7XX_EFR_ENABLE_BIT, - SC16IS7XX_EFR_ENABLE_BIT); - /* Enable TCR/TLR */ sc16is7xx_port_update(port, SC16IS7XX_MCR_REG, SC16IS7XX_MCR_TCRTLR_BIT, @@ -1199,7 +1188,8 @@ static int sc16is7xx_startup(struct uart_port *port) SC16IS7XX_TCR_RX_RESUME(24) | SC16IS7XX_TCR_RX_HALT(48)); - regcache_cache_bypass(one->regmap, false); + /* Disable TCR/TLR access */ + sc16is7xx_port_update(port, SC16IS7XX_MCR_REG, SC16IS7XX_MCR_TCRTLR_BIT, 0); /* Now, initialize the UART */ sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, SC16IS7XX_LCR_WORD_LEN_8); diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index fe457bf1e15b..a66b44d21fba 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -33,7 +33,6 @@ #define CDNS_UART_MINOR 0 /* works best with devtmpfs */ #define CDNS_UART_NR_PORTS 16 #define CDNS_UART_FIFO_SIZE 64 /* FIFO size */ -#define CDNS_UART_REGISTER_SPACE 0x1000 #define TX_TIMEOUT 500000 /* Rx Trigger level */ @@ -1098,15 +1097,15 @@ static int cdns_uart_verify_port(struct uart_port *port, */ static int cdns_uart_request_port(struct uart_port *port) { - if (!request_mem_region(port->mapbase, CDNS_UART_REGISTER_SPACE, + if (!request_mem_region(port->mapbase, port->mapsize, CDNS_UART_NAME)) { return -ENOMEM; } - port->membase = ioremap(port->mapbase, CDNS_UART_REGISTER_SPACE); + port->membase = ioremap(port->mapbase, port->mapsize); if (!port->membase) { dev_err(port->dev, "Unable to map registers\n"); - release_mem_region(port->mapbase, CDNS_UART_REGISTER_SPACE); + release_mem_region(port->mapbase, port->mapsize); return -ENOMEM; } return 0; @@ -1121,7 +1120,7 @@ static int cdns_uart_request_port(struct uart_port *port) */ static void cdns_uart_release_port(struct uart_port *port) { - release_mem_region(port->mapbase, CDNS_UART_REGISTER_SPACE); + release_mem_region(port->mapbase, port->mapsize); iounmap(port->membase); port->membase = NULL; } @@ -1780,6 +1779,7 @@ static int cdns_uart_probe(struct platform_device *pdev) * and triggers invocation of the config_port() entry point. */ port->mapbase = res->start; + port->mapsize = resource_size(res); port->irq = irq; port->dev = &pdev->dev; port->uartclk = clk_get_rate(cdns_uart_data->uartclk); diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 1e50675772fe..cc88aaa106da 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -243,7 +243,7 @@ int ufshcd_mcq_memory_alloc(struct ufs_hba *hba) hwq->sqe_base_addr = dmam_alloc_coherent(hba->dev, utrdl_size, &hwq->sqe_dma_addr, GFP_KERNEL); - if (!hwq->sqe_dma_addr) { + if (!hwq->sqe_base_addr) { dev_err(hba->dev, "SQE allocation failed\n"); return -ENOMEM; } @@ -252,7 +252,7 @@ int ufshcd_mcq_memory_alloc(struct ufs_hba *hba) hwq->cqe_base_addr = dmam_alloc_coherent(hba->dev, cqe_size, &hwq->cqe_dma_addr, GFP_KERNEL); - if (!hwq->cqe_dma_addr) { + if (!hwq->cqe_base_addr) { dev_err(hba->dev, "CQE allocation failed\n"); return -ENOMEM; } diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index c3177034b779..f441958b0ef4 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -119,11 +119,11 @@ ssize_t usb_show_dynids(struct usb_dynids *dynids, char *buf) guard(mutex)(&usb_dynids_lock); list_for_each_entry(dynid, &dynids->list, node) if (dynid->id.bInterfaceClass != 0) - count += sysfs_emit_at(&buf[count], count, "%04x %04x %02x\n", + count += sysfs_emit_at(buf, count, "%04x %04x %02x\n", dynid->id.idVendor, dynid->id.idProduct, dynid->id.bInterfaceClass); else - count += sysfs_emit_at(&buf[count], count, "%04x %04x\n", + count += sysfs_emit_at(buf, count, "%04x %04x\n", dynid->id.idVendor, dynid->id.idProduct); return count; } diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c index 0a800ba53816..de16b02d857e 100644 --- a/drivers/usb/gadget/function/f_midi2.c +++ b/drivers/usb/gadget/function/f_midi2.c @@ -1599,6 +1599,7 @@ static int f_midi2_create_card(struct f_midi2 *midi2) strscpy(fb->info.name, ump_fb_name(b), sizeof(fb->info.name)); } + snd_ump_update_group_attrs(ump); } for (i = 0; i < midi2->num_eps; i++) { @@ -1736,9 +1737,12 @@ static int f_midi2_create_usb_configs(struct f_midi2 *midi2, case USB_SPEED_HIGH: midi2_midi1_ep_out_desc.wMaxPacketSize = cpu_to_le16(512); midi2_midi1_ep_in_desc.wMaxPacketSize = cpu_to_le16(512); - for (i = 0; i < midi2->num_eps; i++) + for (i = 0; i < midi2->num_eps; i++) { midi2_midi2_ep_out_desc[i].wMaxPacketSize = cpu_to_le16(512); + midi2_midi2_ep_in_desc[i].wMaxPacketSize = + cpu_to_le16(512); + } fallthrough; case USB_SPEED_FULL: midi1_in_eps = midi2_midi1_ep_in_descs; @@ -1747,9 +1751,12 @@ static int f_midi2_create_usb_configs(struct f_midi2 *midi2, case USB_SPEED_SUPER: midi2_midi1_ep_out_desc.wMaxPacketSize = cpu_to_le16(1024); midi2_midi1_ep_in_desc.wMaxPacketSize = cpu_to_le16(1024); - for (i = 0; i < midi2->num_eps; i++) + for (i = 0; i < midi2->num_eps; i++) { midi2_midi2_ep_out_desc[i].wMaxPacketSize = cpu_to_le16(1024); + midi2_midi2_ep_in_desc[i].wMaxPacketSize = + cpu_to_le16(1024); + } midi1_in_eps = midi2_midi1_ep_in_ss_descs; midi1_out_eps = midi2_midi1_ep_out_ss_descs; break; diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index 21dbfb0b3bac..1cefca660773 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -765,8 +765,7 @@ static int dummy_dequeue(struct usb_ep *_ep, struct usb_request *_req) if (!dum->driver) return -ESHUTDOWN; - local_irq_save(flags); - spin_lock(&dum->lock); + spin_lock_irqsave(&dum->lock, flags); list_for_each_entry(iter, &ep->queue, queue) { if (&iter->req != _req) continue; @@ -776,15 +775,16 @@ static int dummy_dequeue(struct usb_ep *_ep, struct usb_request *_req) retval = 0; break; } - spin_unlock(&dum->lock); if (retval == 0) { dev_dbg(udc_dev(dum), "dequeued req %p from %s, len %d buf %p\n", req, _ep->name, _req->length, _req->buf); + spin_unlock(&dum->lock); usb_gadget_giveback_request(_ep, _req); + spin_lock(&dum->lock); } - local_irq_restore(flags); + spin_unlock_irqrestore(&dum->lock, flags); return retval; } diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c index 06a2edb9e86e..63edf2d8f245 100644 --- a/drivers/usb/host/xhci-dbgcap.c +++ b/drivers/usb/host/xhci-dbgcap.c @@ -101,13 +101,34 @@ static u32 xhci_dbc_populate_strings(struct dbc_str_descs *strings) return string_length; } +static void xhci_dbc_init_ep_contexts(struct xhci_dbc *dbc) +{ + struct xhci_ep_ctx *ep_ctx; + unsigned int max_burst; + dma_addr_t deq; + + max_burst = DBC_CTRL_MAXBURST(readl(&dbc->regs->control)); + + /* Populate bulk out endpoint context: */ + ep_ctx = dbc_bulkout_ctx(dbc); + deq = dbc_bulkout_enq(dbc); + ep_ctx->ep_info = 0; + ep_ctx->ep_info2 = dbc_epctx_info2(BULK_OUT_EP, 1024, max_burst); + ep_ctx->deq = cpu_to_le64(deq | dbc->ring_out->cycle_state); + + /* Populate bulk in endpoint context: */ + ep_ctx = dbc_bulkin_ctx(dbc); + deq = dbc_bulkin_enq(dbc); + ep_ctx->ep_info = 0; + ep_ctx->ep_info2 = dbc_epctx_info2(BULK_IN_EP, 1024, max_burst); + ep_ctx->deq = cpu_to_le64(deq | dbc->ring_in->cycle_state); +} + static void xhci_dbc_init_contexts(struct xhci_dbc *dbc, u32 string_length) { struct dbc_info_context *info; - struct xhci_ep_ctx *ep_ctx; u32 dev_info; - dma_addr_t deq, dma; - unsigned int max_burst; + dma_addr_t dma; if (!dbc) return; @@ -121,20 +142,8 @@ static void xhci_dbc_init_contexts(struct xhci_dbc *dbc, u32 string_length) info->serial = cpu_to_le64(dma + DBC_MAX_STRING_LENGTH * 3); info->length = cpu_to_le32(string_length); - /* Populate bulk out endpoint context: */ - ep_ctx = dbc_bulkout_ctx(dbc); - max_burst = DBC_CTRL_MAXBURST(readl(&dbc->regs->control)); - deq = dbc_bulkout_enq(dbc); - ep_ctx->ep_info = 0; - ep_ctx->ep_info2 = dbc_epctx_info2(BULK_OUT_EP, 1024, max_burst); - ep_ctx->deq = cpu_to_le64(deq | dbc->ring_out->cycle_state); - - /* Populate bulk in endpoint context: */ - ep_ctx = dbc_bulkin_ctx(dbc); - deq = dbc_bulkin_enq(dbc); - ep_ctx->ep_info = 0; - ep_ctx->ep_info2 = dbc_epctx_info2(BULK_IN_EP, 1024, max_burst); - ep_ctx->deq = cpu_to_le64(deq | dbc->ring_in->cycle_state); + /* Populate bulk in and out endpoint contexts: */ + xhci_dbc_init_ep_contexts(dbc); /* Set DbC context and info registers: */ lo_hi_writeq(dbc->ctx->dma, &dbc->regs->dccp); @@ -436,6 +445,42 @@ dbc_alloc_ctx(struct device *dev, gfp_t flags) return ctx; } +static void xhci_dbc_ring_init(struct xhci_ring *ring) +{ + struct xhci_segment *seg = ring->first_seg; + + /* clear all trbs on ring in case of old ring */ + memset(seg->trbs, 0, TRB_SEGMENT_SIZE); + + /* Only event ring does not use link TRB */ + if (ring->type != TYPE_EVENT) { + union xhci_trb *trb = &seg->trbs[TRBS_PER_SEGMENT - 1]; + + trb->link.segment_ptr = cpu_to_le64(ring->first_seg->dma); + trb->link.control = cpu_to_le32(LINK_TOGGLE | TRB_TYPE(TRB_LINK)); + } + xhci_initialize_ring_info(ring); +} + +static int xhci_dbc_reinit_ep_rings(struct xhci_dbc *dbc) +{ + struct xhci_ring *in_ring = dbc->eps[BULK_IN].ring; + struct xhci_ring *out_ring = dbc->eps[BULK_OUT].ring; + + if (!in_ring || !out_ring || !dbc->ctx) { + dev_warn(dbc->dev, "Can't re-init unallocated endpoints\n"); + return -ENODEV; + } + + xhci_dbc_ring_init(in_ring); + xhci_dbc_ring_init(out_ring); + + /* set ep context enqueue, dequeue, and cycle to initial values */ + xhci_dbc_init_ep_contexts(dbc); + + return 0; +} + static struct xhci_ring * xhci_dbc_ring_alloc(struct device *dev, enum xhci_ring_type type, gfp_t flags) { @@ -464,15 +509,10 @@ xhci_dbc_ring_alloc(struct device *dev, enum xhci_ring_type type, gfp_t flags) seg->dma = dma; - /* Only event ring does not use link TRB */ - if (type != TYPE_EVENT) { - union xhci_trb *trb = &seg->trbs[TRBS_PER_SEGMENT - 1]; - - trb->link.segment_ptr = cpu_to_le64(dma); - trb->link.control = cpu_to_le32(LINK_TOGGLE | TRB_TYPE(TRB_LINK)); - } INIT_LIST_HEAD(&ring->td_list); - xhci_initialize_ring_info(ring); + + xhci_dbc_ring_init(ring); + return ring; dma_fail: kfree(seg); @@ -864,7 +904,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc) dev_info(dbc->dev, "DbC cable unplugged\n"); dbc->state = DS_ENABLED; xhci_dbc_flush_requests(dbc); - + xhci_dbc_reinit_ep_rings(dbc); return EVT_DISC; } @@ -874,7 +914,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc) writel(portsc, &dbc->regs->portsc); dbc->state = DS_ENABLED; xhci_dbc_flush_requests(dbc); - + xhci_dbc_reinit_ep_rings(dbc); return EVT_DISC; } diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 81eaad87a3d9..c4a6544aa107 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -962,7 +962,7 @@ static void xhci_free_virt_devices_depth_first(struct xhci_hcd *xhci, int slot_i out: /* we are now at a leaf device */ xhci_debugfs_remove_slot(xhci, slot_id); - xhci_free_virt_device(xhci, vdev, slot_id); + xhci_free_virt_device(xhci, xhci->devs[slot_id], slot_id); } int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id, diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index e5cd33093423..fc869b7f803f 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1322,7 +1322,18 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1033, 0xff), /* Telit LE910C1-EUX (ECM) */ .driver_info = NCTRL(0) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1034, 0xff), /* Telit LE910C4-WWX (rmnet) */ + .driver_info = RSVD(2) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1035, 0xff) }, /* Telit LE910C4-WWX (ECM) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1036, 0xff) }, /* Telit LE910C4-WWX */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1037, 0xff), /* Telit LE910C4-WWX (rmnet) */ + .driver_info = NCTRL(0) | NCTRL(1) | RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1038, 0xff), /* Telit LE910C4-WWX (rmnet) */ + .driver_info = NCTRL(0) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x103b, 0xff), /* Telit LE910C4-WWX */ + .driver_info = NCTRL(0) | NCTRL(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x103c, 0xff), /* Telit LE910C4-WWX */ + .driver_info = NCTRL(0) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG0), .driver_info = RSVD(0) | RSVD(1) | NCTRL(2) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG1), @@ -1369,6 +1380,12 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff), /* Telit FN990A (PCIe) */ .driver_info = RSVD(0) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1077, 0xff), /* Telit FN990A (rmnet + audio) */ + .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1078, 0xff), /* Telit FN990A (MBIM + audio) */ + .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1079, 0xff), /* Telit FN990A (RNDIS + audio) */ + .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1080, 0xff), /* Telit FE990A (rmnet) */ .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1081, 0xff), /* Telit FE990A (MBIM) */ diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 1f6fdfaa34bf..b2a568a5bc9b 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -2426,17 +2426,21 @@ static void tcpm_handle_vdm_request(struct tcpm_port *port, case ADEV_NONE: break; case ADEV_NOTIFY_USB_AND_QUEUE_VDM: - WARN_ON(typec_altmode_notify(adev, TYPEC_STATE_USB, NULL)); - typec_altmode_vdm(adev, p[0], &p[1], cnt); + if (rx_sop_type == TCPC_TX_SOP_PRIME) { + typec_cable_altmode_vdm(adev, TYPEC_PLUG_SOP_P, p[0], &p[1], cnt); + } else { + WARN_ON(typec_altmode_notify(adev, TYPEC_STATE_USB, NULL)); + typec_altmode_vdm(adev, p[0], &p[1], cnt); + } break; case ADEV_QUEUE_VDM: - if (response_tx_sop_type == TCPC_TX_SOP_PRIME) + if (rx_sop_type == TCPC_TX_SOP_PRIME) typec_cable_altmode_vdm(adev, TYPEC_PLUG_SOP_P, p[0], &p[1], cnt); else typec_altmode_vdm(adev, p[0], &p[1], cnt); break; case ADEV_QUEUE_VDM_SEND_EXIT_MODE_ON_FAIL: - if (response_tx_sop_type == TCPC_TX_SOP_PRIME) { + if (rx_sop_type == TCPC_TX_SOP_PRIME) { if (typec_cable_altmode_vdm(adev, TYPEC_PLUG_SOP_P, p[0], &p[1], cnt)) { int svdm_version = typec_get_cable_svdm_version( diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 9bf282d2453c..499a9edf0ca3 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1795,7 +1795,14 @@ static int reclaim_bgs_cmp(void *unused, const struct list_head *a, bg1 = list_entry(a, struct btrfs_block_group, bg_list); bg2 = list_entry(b, struct btrfs_block_group, bg_list); - return bg1->used > bg2->used; + /* + * Some other task may be updating the ->used field concurrently, but it + * is not serious if we get a stale value or load/store tearing issues, + * as sorting the list of block groups to reclaim is not critical and an + * occasional imperfect order is ok. So silence KCSAN and avoid the + * overhead of locking or any other synchronization. + */ + return data_race(bg1->used > bg2->used); } static inline bool btrfs_should_reclaim(const struct btrfs_fs_info *fs_info) diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index d09d622016ef..35e3071cec06 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -1616,25 +1616,29 @@ out: } /* - * Convert the compression suffix (eg. after "zlib" starting with ":") to - * level, unrecognized string will set the default level. Negative level - * numbers are allowed. + * Convert the compression suffix (eg. after "zlib" starting with ":") to level. + * + * If the resulting level exceeds the algo's supported levels, it will be clamped. + * + * Return <0 if no valid string can be found. + * Return 0 if everything is fine. */ -int btrfs_compress_str2level(unsigned int type, const char *str) +int btrfs_compress_str2level(unsigned int type, const char *str, int *level_ret) { int level = 0; int ret; - if (!type) + if (!type) { + *level_ret = btrfs_compress_set_level(type, level); return 0; + } if (str[0] == ':') { ret = kstrtoint(str + 1, 10, &level); if (ret) - level = 0; + return ret; } - level = btrfs_compress_set_level(type, level); - - return level; + *level_ret = btrfs_compress_set_level(type, level); + return 0; } diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h index 1b38e707bbd9..7b41b2b5ff44 100644 --- a/fs/btrfs/compression.h +++ b/fs/btrfs/compression.h @@ -102,7 +102,7 @@ void btrfs_submit_compressed_write(struct btrfs_ordered_extent *ordered, bool writeback); void btrfs_submit_compressed_read(struct btrfs_bio *bbio); -int btrfs_compress_str2level(unsigned int type, const char *str); +int btrfs_compress_str2level(unsigned int type, const char *str, int *level_ret); struct folio *btrfs_alloc_compr_folio(void); void btrfs_free_compr_folio(struct folio *folio); diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 0f8d8e275143..c0c1ddd46b67 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1843,7 +1843,6 @@ static void fill_stack_inode_item(struct btrfs_trans_handle *trans, int btrfs_fill_inode(struct btrfs_inode *inode, u32 *rdev) { - struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_delayed_node *delayed_node; struct btrfs_inode_item *inode_item; struct inode *vfs_inode = &inode->vfs_inode; @@ -1864,8 +1863,6 @@ int btrfs_fill_inode(struct btrfs_inode *inode, u32 *rdev) i_uid_write(vfs_inode, btrfs_stack_inode_uid(inode_item)); i_gid_write(vfs_inode, btrfs_stack_inode_gid(inode_item)); btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item)); - btrfs_inode_set_file_extent_range(inode, 0, - round_up(i_size_read(vfs_inode), fs_info->sectorsize)); vfs_inode->i_mode = btrfs_stack_inode_mode(inode_item); set_nlink(vfs_inode, btrfs_stack_inode_nlink(inode_item)); inode_set_bytes(vfs_inode, btrfs_stack_inode_nbytes(inode_item)); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index c953297aa89a..b21cb72835cc 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -111,6 +111,24 @@ struct btrfs_bio_ctrl { */ unsigned long submit_bitmap; struct readahead_control *ractl; + + /* + * The start offset of the last used extent map by a read operation. + * + * This is for proper compressed read merge. + * U64_MAX means we are starting the read and have made no progress yet. + * + * The current btrfs_bio_is_contig() only uses disk_bytenr as + * the condition to check if the read can be merged with previous + * bio, which is not correct. E.g. two file extents pointing to the + * same extent but with different offset. + * + * So here we need to do extra checks to only merge reads that are + * covered by the same extent map. + * Just extent_map::start will be enough, as they are unique + * inside the same inode. + */ + u64 last_em_start; }; static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl) @@ -909,7 +927,7 @@ static void btrfs_readahead_expand(struct readahead_control *ractl, * return 0 on success, otherwise return error */ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached, - struct btrfs_bio_ctrl *bio_ctrl, u64 *prev_em_start) + struct btrfs_bio_ctrl *bio_ctrl) { struct inode *inode = folio->mapping->host; struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); @@ -1019,12 +1037,11 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached, * non-optimal behavior (submitting 2 bios for the same extent). */ if (compress_type != BTRFS_COMPRESS_NONE && - prev_em_start && *prev_em_start != (u64)-1 && - *prev_em_start != em->start) + bio_ctrl->last_em_start != U64_MAX && + bio_ctrl->last_em_start != em->start) force_bio_submit = true; - if (prev_em_start) - *prev_em_start = em->start; + bio_ctrl->last_em_start = em->start; btrfs_free_extent_map(em); em = NULL; @@ -1238,12 +1255,15 @@ int btrfs_read_folio(struct file *file, struct folio *folio) const u64 start = folio_pos(folio); const u64 end = start + folio_size(folio) - 1; struct extent_state *cached_state = NULL; - struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ }; + struct btrfs_bio_ctrl bio_ctrl = { + .opf = REQ_OP_READ, + .last_em_start = U64_MAX, + }; struct extent_map *em_cached = NULL; int ret; lock_extents_for_read(inode, start, end, &cached_state); - ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl, NULL); + ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl); btrfs_unlock_extent(&inode->io_tree, start, end, &cached_state); btrfs_free_extent_map(em_cached); @@ -2583,7 +2603,8 @@ void btrfs_readahead(struct readahead_control *rac) { struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ | REQ_RAHEAD, - .ractl = rac + .ractl = rac, + .last_em_start = U64_MAX, }; struct folio *folio; struct btrfs_inode *inode = BTRFS_I(rac->mapping->host); @@ -2591,12 +2612,11 @@ void btrfs_readahead(struct readahead_control *rac) const u64 end = start + readahead_length(rac) - 1; struct extent_state *cached_state = NULL; struct extent_map *em_cached = NULL; - u64 prev_em_start = (u64)-1; lock_extents_for_read(inode, start, end, &cached_state); while ((folio = readahead_folio(rac)) != NULL) - btrfs_do_readpage(folio, &em_cached, &bio_ctrl, &prev_em_start); + btrfs_do_readpage(folio, &em_cached, &bio_ctrl); btrfs_unlock_extent(&inode->io_tree, start, end, &cached_state); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index dd82dcc7b2b7..18db1053cdf0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3885,10 +3885,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path bool filled = false; int first_xattr_slot; - ret = btrfs_init_file_extent_tree(inode); - if (ret) - goto out; - ret = btrfs_fill_inode(inode, &rdev); if (!ret) filled = true; @@ -3920,8 +3916,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path i_uid_write(vfs_inode, btrfs_inode_uid(leaf, inode_item)); i_gid_write(vfs_inode, btrfs_inode_gid(leaf, inode_item)); btrfs_i_size_write(inode, btrfs_inode_size(leaf, inode_item)); - btrfs_inode_set_file_extent_range(inode, 0, - round_up(i_size_read(vfs_inode), fs_info->sectorsize)); inode_set_atime(vfs_inode, btrfs_timespec_sec(leaf, &inode_item->atime), btrfs_timespec_nsec(leaf, &inode_item->atime)); @@ -3953,6 +3947,11 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path btrfs_set_inode_mapping_order(inode); cache_index: + ret = btrfs_init_file_extent_tree(inode); + if (ret) + goto out; + btrfs_inode_set_file_extent_range(inode, 0, + round_up(i_size_read(vfs_inode), fs_info->sectorsize)); /* * If we were modified in the current generation and evicted from memory * and then re-read we need to do a full sync since we don't have any @@ -5696,7 +5695,17 @@ static void btrfs_del_inode_from_root(struct btrfs_inode *inode) bool empty = false; xa_lock(&root->inodes); - entry = __xa_erase(&root->inodes, btrfs_ino(inode)); + /* + * This btrfs_inode is being freed and has already been unhashed at this + * point. It's possible that another btrfs_inode has already been + * allocated for the same inode and inserted itself into the root, so + * don't delete it in that case. + * + * Note that this shouldn't need to allocate memory, so the gfp flags + * don't really matter. + */ + entry = __xa_cmpxchg(&root->inodes, btrfs_ino(inode), inode, NULL, + GFP_ATOMIC); if (entry == inode) empty = xa_empty(&root->inodes); xa_unlock(&root->inodes); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index ccaa9a3cf1ce..da102da169fd 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1455,6 +1455,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root, struct btrfs_qgroup *qgroup; LIST_HEAD(qgroup_list); u64 num_bytes = src->excl; + u64 num_bytes_cmpr = src->excl_cmpr; int ret = 0; qgroup = find_qgroup_rb(fs_info, ref_root); @@ -1466,11 +1467,12 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root, struct btrfs_qgroup_list *glist; qgroup->rfer += sign * num_bytes; - qgroup->rfer_cmpr += sign * num_bytes; + qgroup->rfer_cmpr += sign * num_bytes_cmpr; WARN_ON(sign < 0 && qgroup->excl < num_bytes); + WARN_ON(sign < 0 && qgroup->excl_cmpr < num_bytes_cmpr); qgroup->excl += sign * num_bytes; - qgroup->excl_cmpr += sign * num_bytes; + qgroup->excl_cmpr += sign * num_bytes_cmpr; if (sign > 0) qgroup_rsv_add_by_qgroup(fs_info, qgroup, src); diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index 3871c3a6c743..9f1858b42c0e 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -980,11 +980,18 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info) if (!btrfs_test_opt(fs_info, REF_VERIFY)) return 0; + extent_root = btrfs_extent_root(fs_info, 0); + /* If the extent tree is damaged we cannot ignore it (IGNOREBADROOTS). */ + if (IS_ERR(extent_root)) { + btrfs_warn(fs_info, "ref-verify: extent tree not available, disabling"); + btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); + return 0; + } + path = btrfs_alloc_path(); if (!path) return -ENOMEM; - extent_root = btrfs_extent_root(fs_info, 0); eb = btrfs_read_lock_root_node(extent_root); level = btrfs_header_level(eb); path->nodes[level] = eb; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index a262b494a89f..b06b8f325537 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -276,6 +276,7 @@ static int btrfs_parse_compress(struct btrfs_fs_context *ctx, const struct fs_parameter *param, int opt) { const char *string = param->string; + int ret; /* * Provide the same semantics as older kernels that don't use fs @@ -294,21 +295,30 @@ static int btrfs_parse_compress(struct btrfs_fs_context *ctx, btrfs_clear_opt(ctx->mount_opt, NODATASUM); } else if (btrfs_match_compress_type(string, "zlib", true)) { ctx->compress_type = BTRFS_COMPRESS_ZLIB; - ctx->compress_level = btrfs_compress_str2level(BTRFS_COMPRESS_ZLIB, - string + 4); + ret = btrfs_compress_str2level(BTRFS_COMPRESS_ZLIB, string + 4, + &ctx->compress_level); + if (ret < 0) + goto error; btrfs_set_opt(ctx->mount_opt, COMPRESS); btrfs_clear_opt(ctx->mount_opt, NODATACOW); btrfs_clear_opt(ctx->mount_opt, NODATASUM); - } else if (btrfs_match_compress_type(string, "lzo", false)) { + } else if (btrfs_match_compress_type(string, "lzo", true)) { ctx->compress_type = BTRFS_COMPRESS_LZO; - ctx->compress_level = 0; + ret = btrfs_compress_str2level(BTRFS_COMPRESS_LZO, string + 3, + &ctx->compress_level); + if (ret < 0) + goto error; + if (string[3] == ':' && string[4]) + btrfs_warn(NULL, "Compression level ignored for LZO"); btrfs_set_opt(ctx->mount_opt, COMPRESS); btrfs_clear_opt(ctx->mount_opt, NODATACOW); btrfs_clear_opt(ctx->mount_opt, NODATASUM); } else if (btrfs_match_compress_type(string, "zstd", true)) { ctx->compress_type = BTRFS_COMPRESS_ZSTD; - ctx->compress_level = btrfs_compress_str2level(BTRFS_COMPRESS_ZSTD, - string + 4); + ret = btrfs_compress_str2level(BTRFS_COMPRESS_ZSTD, string + 4, + &ctx->compress_level); + if (ret < 0) + goto error; btrfs_set_opt(ctx->mount_opt, COMPRESS); btrfs_clear_opt(ctx->mount_opt, NODATACOW); btrfs_clear_opt(ctx->mount_opt, NODATASUM); @@ -319,10 +329,14 @@ static int btrfs_parse_compress(struct btrfs_fs_context *ctx, btrfs_clear_opt(ctx->mount_opt, COMPRESS); btrfs_clear_opt(ctx->mount_opt, FORCE_COMPRESS); } else { - btrfs_err(NULL, "unrecognized compression value %s", string); - return -EINVAL; + ret = -EINVAL; + goto error; } return 0; +error: + btrfs_err(NULL, "failed to parse compression option '%s'", string); + return ret; + } static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param) @@ -1079,7 +1093,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) seq_printf(seq, ",compress-force=%s", compress_type); else seq_printf(seq, ",compress=%s", compress_type); - if (info->compress_level) + if (info->compress_level && info->compress_type != BTRFS_COMPRESS_LZO) seq_printf(seq, ":%d", info->compress_level); } if (btrfs_test_opt(info, NOSSD)) diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 0f556f4de3f9..a997c7cc35a2 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1756,10 +1756,10 @@ static int check_inode_ref(struct extent_buffer *leaf, while (ptr < end) { u16 namelen; - if (unlikely(ptr + sizeof(iref) > end)) { + if (unlikely(ptr + sizeof(*iref) > end)) { inode_ref_err(leaf, slot, "inode ref overflow, ptr %lu end %lu inode_ref_size %zu", - ptr, end, sizeof(iref)); + ptr, end, sizeof(*iref)); return -EUCLEAN; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 7d5d90845ca9..7a63afedd01e 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1964,7 +1964,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, search_key.objectid = log_key.objectid; search_key.type = BTRFS_INODE_EXTREF_KEY; - search_key.offset = key->objectid; + search_key.offset = btrfs_extref_hash(key->objectid, name.name, name.len); ret = backref_in_log(root->log_root, &search_key, key->objectid, &name); if (ret < 0) { goto out; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index fa7a929a0461..c6e3efd6f602 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2722,6 +2722,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path goto error; } + if (bdev_nr_bytes(file_bdev(bdev_file)) <= BTRFS_DEVICE_RANGE_RESERVED) { + ret = -EINVAL; + goto error; + } + if (fs_devices->seeding) { seeding_dev = true; down_write(&sb->s_umount); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index ea662036f441..efc2a81f50e5 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -2582,9 +2582,9 @@ again: spin_lock(&space_info->lock); space_info->total_bytes -= bg->length; space_info->disk_total -= bg->length * factor; + space_info->disk_total -= bg->zone_unusable; /* There is no allocation ever happened. */ ASSERT(bg->used == 0); - ASSERT(bg->zone_unusable == 0); /* No super block in a block group on the zoned setup. */ ASSERT(bg->bytes_super == 0); spin_unlock(&space_info->lock); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 8b202d789e93..322ed268f14a 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1264,7 +1264,9 @@ static inline int move_dirty_folio_in_page_array(struct address_space *mapping, 0, gfp_flags); if (IS_ERR(pages[index])) { - if (PTR_ERR(pages[index]) == -EINVAL) { + int err = PTR_ERR(pages[index]); + + if (err == -EINVAL) { pr_err_client(cl, "inode->i_blkbits=%hhu\n", inode->i_blkbits); } @@ -1273,7 +1275,7 @@ static inline int move_dirty_folio_in_page_array(struct address_space *mapping, BUG_ON(ceph_wbc->locked_pages == 0); pages[index] = NULL; - return PTR_ERR(pages[index]); + return err; } } else { pages[index] = &folio->page; @@ -1687,6 +1689,7 @@ get_more_pages: process_folio_batch: rc = ceph_process_folio_batch(mapping, wbc, &ceph_wbc); + ceph_shift_unused_folios_left(&ceph_wbc.fbatch); if (rc) goto release_folios; @@ -1695,8 +1698,6 @@ process_folio_batch: goto release_folios; if (ceph_wbc.processed_in_fbatch) { - ceph_shift_unused_folios_left(&ceph_wbc.fbatch); - if (folio_batch_count(&ceph_wbc.fbatch) == 0 && ceph_wbc.locked_pages < ceph_wbc.max_pages) { doutc(cl, "reached end fbatch, trying for more\n"); diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index fdd404fc8112..f3fe786b4143 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -55,8 +55,6 @@ static int mdsc_show(struct seq_file *s, void *p) struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req; struct rb_node *rp; - int pathlen = 0; - u64 pathbase; char *path; mutex_lock(&mdsc->mutex); @@ -81,8 +79,8 @@ static int mdsc_show(struct seq_file *s, void *p) if (req->r_inode) { seq_printf(s, " #%llx", ceph_ino(req->r_inode)); } else if (req->r_dentry) { - path = ceph_mdsc_build_path(mdsc, req->r_dentry, &pathlen, - &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, req->r_dentry, &path_info, 0); if (IS_ERR(path)) path = NULL; spin_lock(&req->r_dentry->d_lock); @@ -91,7 +89,7 @@ static int mdsc_show(struct seq_file *s, void *p) req->r_dentry, path ? path : ""); spin_unlock(&req->r_dentry->d_lock); - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); } else if (req->r_path1) { seq_printf(s, " #%llx/%s", req->r_ino1.ino, req->r_path1); @@ -100,8 +98,8 @@ static int mdsc_show(struct seq_file *s, void *p) } if (req->r_old_dentry) { - path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &pathlen, - &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &path_info, 0); if (IS_ERR(path)) path = NULL; spin_lock(&req->r_old_dentry->d_lock); @@ -111,7 +109,7 @@ static int mdsc_show(struct seq_file *s, void *p) req->r_old_dentry, path ? path : ""); spin_unlock(&req->r_old_dentry->d_lock); - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); } else if (req->r_path2 && req->r_op != CEPH_MDS_OP_SYMLINK) { if (req->r_ino2.ino) seq_printf(s, " #%llx/%s", req->r_ino2.ino, diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 8478e7e75df6..32973c62c1a2 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1271,10 +1271,8 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc, /* If op failed, mark everyone involved for errors */ if (result) { - int pathlen = 0; - u64 base = 0; - char *path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, - &base, 0); + struct ceph_path_info path_info = {0}; + char *path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0); /* mark error on parent + clear complete */ mapping_set_error(req->r_parent->i_mapping, result); @@ -1288,8 +1286,8 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc, mapping_set_error(req->r_old_inode->i_mapping, result); pr_warn_client(cl, "failure path=(%llx)%s result=%d!\n", - base, IS_ERR(path) ? "<<bad>>" : path, result); - ceph_mdsc_free_path(path, pathlen); + path_info.vino.ino, IS_ERR(path) ? "<<bad>>" : path, result); + ceph_mdsc_free_path_info(&path_info); } out: iput(req->r_old_inode); @@ -1347,8 +1345,6 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) int err = -EROFS; int op; char *path; - int pathlen; - u64 pathbase; if (ceph_snap(dir) == CEPH_SNAPDIR) { /* rmdir .snap/foo is RMSNAP */ @@ -1367,14 +1363,15 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) if (!dn) { try_async = false; } else { - path = ceph_mdsc_build_path(mdsc, dn, &pathlen, &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0); if (IS_ERR(path)) { try_async = false; err = 0; } else { err = ceph_mds_check_access(mdsc, path, MAY_WRITE); } - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); dput(dn); /* For none EACCES cases will let the MDS do the mds auth check */ diff --git a/fs/ceph/file.c b/fs/ceph/file.c index c02f100f8552..978acd3d4b32 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -368,8 +368,6 @@ int ceph_open(struct inode *inode, struct file *file) int flags, fmode, wanted; struct dentry *dentry; char *path; - int pathlen; - u64 pathbase; bool do_sync = false; int mask = MAY_READ; @@ -399,14 +397,15 @@ int ceph_open(struct inode *inode, struct file *file) if (!dentry) { do_sync = true; } else { - path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0); if (IS_ERR(path)) { do_sync = true; err = 0; } else { err = ceph_mds_check_access(mdsc, path, mask); } - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); dput(dentry); /* For none EACCES cases will let the MDS do the mds auth check */ @@ -614,15 +613,13 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc, mapping_set_error(req->r_parent->i_mapping, result); if (result) { - int pathlen = 0; - u64 base = 0; - char *path = ceph_mdsc_build_path(mdsc, req->r_dentry, &pathlen, - &base, 0); + struct ceph_path_info path_info = {0}; + char *path = ceph_mdsc_build_path(mdsc, req->r_dentry, &path_info, 0); pr_warn_client(cl, "async create failure path=(%llx)%s result=%d!\n", - base, IS_ERR(path) ? "<<bad>>" : path, result); - ceph_mdsc_free_path(path, pathlen); + path_info.vino.ino, IS_ERR(path) ? "<<bad>>" : path, result); + ceph_mdsc_free_path_info(&path_info); ceph_dir_clear_complete(req->r_parent); if (!d_unhashed(dentry)) @@ -791,8 +788,6 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, int mask; int err; char *path; - int pathlen; - u64 pathbase; doutc(cl, "%p %llx.%llx dentry %p '%pd' %s flags %d mode 0%o\n", dir, ceph_vinop(dir), dentry, dentry, @@ -814,7 +809,8 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, if (!dn) { try_async = false; } else { - path = ceph_mdsc_build_path(mdsc, dn, &pathlen, &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0); if (IS_ERR(path)) { try_async = false; err = 0; @@ -826,7 +822,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, mask |= MAY_WRITE; err = ceph_mds_check_access(mdsc, path, mask); } - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); dput(dn); /* For none EACCES cases will let the MDS do the mds auth check */ diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index fc543075b827..f67025465de0 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -55,6 +55,52 @@ static int ceph_set_ino_cb(struct inode *inode, void *data) return 0; } +/* + * Check if the parent inode matches the vino from directory reply info + */ +static inline bool ceph_vino_matches_parent(struct inode *parent, + struct ceph_vino vino) +{ + return ceph_ino(parent) == vino.ino && ceph_snap(parent) == vino.snap; +} + +/* + * Validate that the directory inode referenced by @req->r_parent matches the + * inode number and snapshot id contained in the reply's directory record. If + * they do not match – which can theoretically happen if the parent dentry was + * moved between the time the request was issued and the reply arrived – fall + * back to looking up the correct inode in the inode cache. + * + * A reference is *always* returned. Callers that receive a different inode + * than the original @parent are responsible for dropping the extra reference + * once the reply has been processed. + */ +static struct inode *ceph_get_reply_dir(struct super_block *sb, + struct inode *parent, + struct ceph_mds_reply_info_parsed *rinfo) +{ + struct ceph_vino vino; + + if (unlikely(!rinfo->diri.in)) + return parent; /* nothing to compare against */ + + /* If we didn't have a cached parent inode to begin with, just bail out. */ + if (!parent) + return NULL; + + vino.ino = le64_to_cpu(rinfo->diri.in->ino); + vino.snap = le64_to_cpu(rinfo->diri.in->snapid); + + if (likely(ceph_vino_matches_parent(parent, vino))) + return parent; /* matches – use the original reference */ + + /* Mismatch – this should be rare. Emit a WARN and obtain the correct inode. */ + WARN_ONCE(1, "ceph: reply dir mismatch (parent valid %llx.%llx reply %llx.%llx)\n", + ceph_ino(parent), ceph_snap(parent), vino.ino, vino.snap); + + return ceph_get_inode(sb, vino, NULL); +} + /** * ceph_new_inode - allocate a new inode in advance of an expected create * @dir: parent directory for new inode @@ -1523,6 +1569,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) struct ceph_vino tvino, dvino; struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb); struct ceph_client *cl = fsc->client; + struct inode *parent_dir = NULL; int err = 0; doutc(cl, "%p is_dentry %d is_target %d\n", req, @@ -1536,10 +1583,17 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) } if (rinfo->head->is_dentry) { - struct inode *dir = req->r_parent; - - if (dir) { - err = ceph_fill_inode(dir, NULL, &rinfo->diri, + /* + * r_parent may be stale, in cases when R_PARENT_LOCKED is not set, + * so we need to get the correct inode + */ + parent_dir = ceph_get_reply_dir(sb, req->r_parent, rinfo); + if (unlikely(IS_ERR(parent_dir))) { + err = PTR_ERR(parent_dir); + goto done; + } + if (parent_dir) { + err = ceph_fill_inode(parent_dir, NULL, &rinfo->diri, rinfo->dirfrag, session, -1, &req->r_caps_reservation); if (err < 0) @@ -1548,14 +1602,14 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) WARN_ON_ONCE(1); } - if (dir && req->r_op == CEPH_MDS_OP_LOOKUPNAME && + if (parent_dir && req->r_op == CEPH_MDS_OP_LOOKUPNAME && test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) && !test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) { bool is_nokey = false; struct qstr dname; struct dentry *dn, *parent; struct fscrypt_str oname = FSTR_INIT(NULL, 0); - struct ceph_fname fname = { .dir = dir, + struct ceph_fname fname = { .dir = parent_dir, .name = rinfo->dname, .ctext = rinfo->altname, .name_len = rinfo->dname_len, @@ -1564,10 +1618,10 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) BUG_ON(!rinfo->head->is_target); BUG_ON(req->r_dentry); - parent = d_find_any_alias(dir); + parent = d_find_any_alias(parent_dir); BUG_ON(!parent); - err = ceph_fname_alloc_buffer(dir, &oname); + err = ceph_fname_alloc_buffer(parent_dir, &oname); if (err < 0) { dput(parent); goto done; @@ -1576,7 +1630,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) err = ceph_fname_to_usr(&fname, NULL, &oname, &is_nokey); if (err < 0) { dput(parent); - ceph_fname_free_buffer(dir, &oname); + ceph_fname_free_buffer(parent_dir, &oname); goto done; } dname.name = oname.name; @@ -1595,7 +1649,7 @@ retry_lookup: dname.len, dname.name, dn); if (!dn) { dput(parent); - ceph_fname_free_buffer(dir, &oname); + ceph_fname_free_buffer(parent_dir, &oname); err = -ENOMEM; goto done; } @@ -1610,12 +1664,12 @@ retry_lookup: ceph_snap(d_inode(dn)) != tvino.snap)) { doutc(cl, " dn %p points to wrong inode %p\n", dn, d_inode(dn)); - ceph_dir_clear_ordered(dir); + ceph_dir_clear_ordered(parent_dir); d_delete(dn); dput(dn); goto retry_lookup; } - ceph_fname_free_buffer(dir, &oname); + ceph_fname_free_buffer(parent_dir, &oname); req->r_dentry = dn; dput(parent); @@ -1794,6 +1848,9 @@ retry_lookup: &dvino, ptvino); } done: + /* Drop extra ref from ceph_get_reply_dir() if it returned a new inode */ + if (unlikely(!IS_ERR_OR_NULL(parent_dir) && parent_dir != req->r_parent)) + iput(parent_dir); doutc(cl, "done err=%d\n", err); return err; } @@ -2487,22 +2544,21 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode, int truncate_retry = 20; /* The RMW will take around 50ms */ struct dentry *dentry; char *path; - int pathlen; - u64 pathbase; bool do_sync = false; dentry = d_find_alias(inode); if (!dentry) { do_sync = true; } else { - path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0); if (IS_ERR(path)) { do_sync = true; err = 0; } else { err = ceph_mds_check_access(mdsc, path, MAY_WRITE); } - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); dput(dentry); /* For none EACCES cases will let the MDS do the mds auth check */ diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 0f497c39ff82..3bc72b47fe4d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2681,8 +2681,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen) * ceph_mdsc_build_path - build a path string to a given dentry * @mdsc: mds client * @dentry: dentry to which path should be built - * @plen: returned length of string - * @pbase: returned base inode number + * @path_info: output path, length, base ino+snap, and freepath ownership flag * @for_wire: is this path going to be sent to the MDS? * * Build a string that represents the path to the dentry. This is mostly called @@ -2700,7 +2699,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen) * foo/.snap/bar -> foo//bar */ char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry, - int *plen, u64 *pbase, int for_wire) + struct ceph_path_info *path_info, int for_wire) { struct ceph_client *cl = mdsc->fsc->client; struct dentry *cur; @@ -2810,16 +2809,28 @@ retry: return ERR_PTR(-ENAMETOOLONG); } - *pbase = base; - *plen = PATH_MAX - 1 - pos; + /* Initialize the output structure */ + memset(path_info, 0, sizeof(*path_info)); + + path_info->vino.ino = base; + path_info->pathlen = PATH_MAX - 1 - pos; + path_info->path = path + pos; + path_info->freepath = true; + + /* Set snap from dentry if available */ + if (d_inode(dentry)) + path_info->vino.snap = ceph_snap(d_inode(dentry)); + else + path_info->vino.snap = CEPH_NOSNAP; + doutc(cl, "on %p %d built %llx '%.*s'\n", dentry, d_count(dentry), - base, *plen, path + pos); + base, PATH_MAX - 1 - pos, path + pos); return path + pos; } static int build_dentry_path(struct ceph_mds_client *mdsc, struct dentry *dentry, - struct inode *dir, const char **ppath, int *ppathlen, - u64 *pino, bool *pfreepath, bool parent_locked) + struct inode *dir, struct ceph_path_info *path_info, + bool parent_locked) { char *path; @@ -2828,41 +2839,47 @@ static int build_dentry_path(struct ceph_mds_client *mdsc, struct dentry *dentry dir = d_inode_rcu(dentry->d_parent); if (dir && parent_locked && ceph_snap(dir) == CEPH_NOSNAP && !IS_ENCRYPTED(dir)) { - *pino = ceph_ino(dir); + path_info->vino.ino = ceph_ino(dir); + path_info->vino.snap = ceph_snap(dir); rcu_read_unlock(); - *ppath = dentry->d_name.name; - *ppathlen = dentry->d_name.len; + path_info->path = dentry->d_name.name; + path_info->pathlen = dentry->d_name.len; + path_info->freepath = false; return 0; } rcu_read_unlock(); - path = ceph_mdsc_build_path(mdsc, dentry, ppathlen, pino, 1); + path = ceph_mdsc_build_path(mdsc, dentry, path_info, 1); if (IS_ERR(path)) return PTR_ERR(path); - *ppath = path; - *pfreepath = true; + /* + * ceph_mdsc_build_path already fills path_info, including snap handling. + */ return 0; } -static int build_inode_path(struct inode *inode, - const char **ppath, int *ppathlen, u64 *pino, - bool *pfreepath) +static int build_inode_path(struct inode *inode, struct ceph_path_info *path_info) { struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb); struct dentry *dentry; char *path; if (ceph_snap(inode) == CEPH_NOSNAP) { - *pino = ceph_ino(inode); - *ppathlen = 0; + path_info->vino.ino = ceph_ino(inode); + path_info->vino.snap = ceph_snap(inode); + path_info->pathlen = 0; + path_info->freepath = false; return 0; } dentry = d_find_alias(inode); - path = ceph_mdsc_build_path(mdsc, dentry, ppathlen, pino, 1); + path = ceph_mdsc_build_path(mdsc, dentry, path_info, 1); dput(dentry); if (IS_ERR(path)) return PTR_ERR(path); - *ppath = path; - *pfreepath = true; + /* + * ceph_mdsc_build_path already fills path_info, including snap from dentry. + * Override with inode's snap since that's what this function is for. + */ + path_info->vino.snap = ceph_snap(inode); return 0; } @@ -2872,26 +2889,32 @@ static int build_inode_path(struct inode *inode, */ static int set_request_path_attr(struct ceph_mds_client *mdsc, struct inode *rinode, struct dentry *rdentry, struct inode *rdiri, - const char *rpath, u64 rino, const char **ppath, - int *pathlen, u64 *ino, bool *freepath, + const char *rpath, u64 rino, + struct ceph_path_info *path_info, bool parent_locked) { struct ceph_client *cl = mdsc->fsc->client; int r = 0; + /* Initialize the output structure */ + memset(path_info, 0, sizeof(*path_info)); + if (rinode) { - r = build_inode_path(rinode, ppath, pathlen, ino, freepath); + r = build_inode_path(rinode, path_info); doutc(cl, " inode %p %llx.%llx\n", rinode, ceph_ino(rinode), ceph_snap(rinode)); } else if (rdentry) { - r = build_dentry_path(mdsc, rdentry, rdiri, ppath, pathlen, ino, - freepath, parent_locked); - doutc(cl, " dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen, *ppath); + r = build_dentry_path(mdsc, rdentry, rdiri, path_info, parent_locked); + doutc(cl, " dentry %p %llx/%.*s\n", rdentry, path_info->vino.ino, + path_info->pathlen, path_info->path); } else if (rpath || rino) { - *ino = rino; - *ppath = rpath; - *pathlen = rpath ? strlen(rpath) : 0; - doutc(cl, " path %.*s\n", *pathlen, rpath); + path_info->vino.ino = rino; + path_info->vino.snap = CEPH_NOSNAP; + path_info->path = rpath; + path_info->pathlen = rpath ? strlen(rpath) : 0; + path_info->freepath = false; + + doutc(cl, " path %.*s\n", path_info->pathlen, rpath); } return r; @@ -2968,11 +2991,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, struct ceph_client *cl = mdsc->fsc->client; struct ceph_msg *msg; struct ceph_mds_request_head_legacy *lhead; - const char *path1 = NULL; - const char *path2 = NULL; - u64 ino1 = 0, ino2 = 0; - int pathlen1 = 0, pathlen2 = 0; - bool freepath1 = false, freepath2 = false; + struct ceph_path_info path_info1 = {0}; + struct ceph_path_info path_info2 = {0}; struct dentry *old_dentry = NULL; int len; u16 releases; @@ -2982,25 +3002,49 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, u16 request_head_version = mds_supported_head_version(session); kuid_t caller_fsuid = req->r_cred->fsuid; kgid_t caller_fsgid = req->r_cred->fsgid; + bool parent_locked = test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); ret = set_request_path_attr(mdsc, req->r_inode, req->r_dentry, - req->r_parent, req->r_path1, req->r_ino1.ino, - &path1, &pathlen1, &ino1, &freepath1, - test_bit(CEPH_MDS_R_PARENT_LOCKED, - &req->r_req_flags)); + req->r_parent, req->r_path1, req->r_ino1.ino, + &path_info1, parent_locked); if (ret < 0) { msg = ERR_PTR(ret); goto out; } + /* + * When the parent directory's i_rwsem is *not* locked, req->r_parent may + * have become stale (e.g. after a concurrent rename) between the time the + * dentry was looked up and now. If we detect that the stored r_parent + * does not match the inode number we just encoded for the request, switch + * to the correct inode so that the MDS receives a valid parent reference. + */ + if (!parent_locked && req->r_parent && path_info1.vino.ino && + ceph_ino(req->r_parent) != path_info1.vino.ino) { + struct inode *old_parent = req->r_parent; + struct inode *correct_dir = ceph_get_inode(mdsc->fsc->sb, path_info1.vino, NULL); + if (!IS_ERR(correct_dir)) { + WARN_ONCE(1, "ceph: r_parent mismatch (had %llx wanted %llx) - updating\n", + ceph_ino(old_parent), path_info1.vino.ino); + /* + * Transfer CEPH_CAP_PIN from the old parent to the new one. + * The pin was taken earlier in ceph_mdsc_submit_request(). + */ + ceph_put_cap_refs(ceph_inode(old_parent), CEPH_CAP_PIN); + iput(old_parent); + req->r_parent = correct_dir; + ceph_get_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN); + } + } + /* If r_old_dentry is set, then assume that its parent is locked */ if (req->r_old_dentry && !(req->r_old_dentry->d_flags & DCACHE_DISCONNECTED)) old_dentry = req->r_old_dentry; ret = set_request_path_attr(mdsc, NULL, old_dentry, - req->r_old_dentry_dir, - req->r_path2, req->r_ino2.ino, - &path2, &pathlen2, &ino2, &freepath2, true); + req->r_old_dentry_dir, + req->r_path2, req->r_ino2.ino, + &path_info2, true); if (ret < 0) { msg = ERR_PTR(ret); goto out_free1; @@ -3031,7 +3075,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, /* filepaths */ len += 2 * (1 + sizeof(u32) + sizeof(u64)); - len += pathlen1 + pathlen2; + len += path_info1.pathlen + path_info2.pathlen; /* cap releases */ len += sizeof(struct ceph_mds_request_release) * @@ -3039,9 +3083,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, !!req->r_old_inode_drop + !!req->r_old_dentry_drop); if (req->r_dentry_drop) - len += pathlen1; + len += path_info1.pathlen; if (req->r_old_dentry_drop) - len += pathlen2; + len += path_info2.pathlen; /* MClientRequest tail */ @@ -3154,8 +3198,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, lhead->ino = cpu_to_le64(req->r_deleg_ino); lhead->args = req->r_args; - ceph_encode_filepath(&p, end, ino1, path1); - ceph_encode_filepath(&p, end, ino2, path2); + ceph_encode_filepath(&p, end, path_info1.vino.ino, path_info1.path); + ceph_encode_filepath(&p, end, path_info2.vino.ino, path_info2.path); /* make note of release offset, in case we need to replay */ req->r_request_release_offset = p - msg->front.iov_base; @@ -3218,11 +3262,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, msg->hdr.data_off = cpu_to_le16(0); out_free2: - if (freepath2) - ceph_mdsc_free_path((char *)path2, pathlen2); + ceph_mdsc_free_path_info(&path_info2); out_free1: - if (freepath1) - ceph_mdsc_free_path((char *)path1, pathlen1); + ceph_mdsc_free_path_info(&path_info1); out: return msg; out_err: @@ -4579,24 +4621,20 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) struct ceph_pagelist *pagelist = recon_state->pagelist; struct dentry *dentry; struct ceph_cap *cap; - char *path; - int pathlen = 0, err; - u64 pathbase; + struct ceph_path_info path_info = {0}; + int err; u64 snap_follows; dentry = d_find_primary(inode); if (dentry) { /* set pathbase to parent dir when msg_version >= 2 */ - path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, + char *path = ceph_mdsc_build_path(mdsc, dentry, &path_info, recon_state->msg_version >= 2); dput(dentry); if (IS_ERR(path)) { err = PTR_ERR(path); goto out_err; } - } else { - path = NULL; - pathbase = 0; } spin_lock(&ci->i_ceph_lock); @@ -4629,7 +4667,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) rec.v2.wanted = cpu_to_le32(__ceph_caps_wanted(ci)); rec.v2.issued = cpu_to_le32(cap->issued); rec.v2.snaprealm = cpu_to_le64(ci->i_snap_realm->ino); - rec.v2.pathbase = cpu_to_le64(pathbase); + rec.v2.pathbase = cpu_to_le64(path_info.vino.ino); rec.v2.flock_len = (__force __le32) ((ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) ? 0 : 1); } else { @@ -4644,7 +4682,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) ts = inode_get_atime(inode); ceph_encode_timespec64(&rec.v1.atime, &ts); rec.v1.snaprealm = cpu_to_le64(ci->i_snap_realm->ino); - rec.v1.pathbase = cpu_to_le64(pathbase); + rec.v1.pathbase = cpu_to_le64(path_info.vino.ino); } if (list_empty(&ci->i_cap_snaps)) { @@ -4706,7 +4744,7 @@ encode_again: sizeof(struct ceph_filelock); rec.v2.flock_len = cpu_to_le32(struct_len); - struct_len += sizeof(u32) + pathlen + sizeof(rec.v2); + struct_len += sizeof(u32) + path_info.pathlen + sizeof(rec.v2); if (struct_v >= 2) struct_len += sizeof(u64); /* snap_follows */ @@ -4730,7 +4768,7 @@ encode_again: ceph_pagelist_encode_8(pagelist, 1); ceph_pagelist_encode_32(pagelist, struct_len); } - ceph_pagelist_encode_string(pagelist, path, pathlen); + ceph_pagelist_encode_string(pagelist, (char *)path_info.path, path_info.pathlen); ceph_pagelist_append(pagelist, &rec, sizeof(rec.v2)); ceph_locks_to_pagelist(flocks, pagelist, num_fcntl_locks, num_flock_locks); @@ -4741,17 +4779,17 @@ out_freeflocks: } else { err = ceph_pagelist_reserve(pagelist, sizeof(u64) + sizeof(u32) + - pathlen + sizeof(rec.v1)); + path_info.pathlen + sizeof(rec.v1)); if (err) goto out_err; ceph_pagelist_encode_64(pagelist, ceph_ino(inode)); - ceph_pagelist_encode_string(pagelist, path, pathlen); + ceph_pagelist_encode_string(pagelist, (char *)path_info.path, path_info.pathlen); ceph_pagelist_append(pagelist, &rec, sizeof(rec.v1)); } out_err: - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); if (!err) recon_state->nr_caps++; return err; diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 3e2a6fa7c19a..0428a5eaf28c 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -617,14 +617,24 @@ extern int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath, extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc); -static inline void ceph_mdsc_free_path(char *path, int len) +/* + * Structure to group path-related output parameters for build_*_path functions + */ +struct ceph_path_info { + const char *path; + int pathlen; + struct ceph_vino vino; + bool freepath; +}; + +static inline void ceph_mdsc_free_path_info(const struct ceph_path_info *path_info) { - if (!IS_ERR_OR_NULL(path)) - __putname(path - (PATH_MAX - 1 - len)); + if (path_info && path_info->freepath && !IS_ERR_OR_NULL(path_info->path)) + __putname((char *)path_info->path - (PATH_MAX - 1 - path_info->pathlen)); } extern char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, - struct dentry *dentry, int *plen, u64 *base, + struct dentry *dentry, struct ceph_path_info *path_info, int for_wire); extern void __ceph_mdsc_drop_dentry_lease(struct dentry *dentry); diff --git a/fs/coredump.c b/fs/coredump.c index 5dce257c67fc..60bc9685e149 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -1466,11 +1466,15 @@ static int proc_dostring_coredump(const struct ctl_table *table, int write, ssize_t retval; char old_core_pattern[CORENAME_MAX_SIZE]; + if (write) + return proc_dostring(table, write, buffer, lenp, ppos); + retval = strscpy(old_core_pattern, core_pattern, CORENAME_MAX_SIZE); error = proc_dostring(table, write, buffer, lenp, ppos); if (error) return error; + if (!check_coredump_socket()) { strscpy(core_pattern, old_core_pattern, retval + 1); return -EINVAL; diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h index 377ee12b8b96..3d5738f80072 100644 --- a/fs/erofs/erofs_fs.h +++ b/fs/erofs/erofs_fs.h @@ -12,10 +12,12 @@ /* to allow for x86 boot sectors and other oddities. */ #define EROFS_SUPER_OFFSET 1024 -#define EROFS_FEATURE_COMPAT_SB_CHKSUM 0x00000001 -#define EROFS_FEATURE_COMPAT_MTIME 0x00000002 -#define EROFS_FEATURE_COMPAT_XATTR_FILTER 0x00000004 +#define EROFS_FEATURE_COMPAT_SB_CHKSUM 0x00000001 +#define EROFS_FEATURE_COMPAT_MTIME 0x00000002 +#define EROFS_FEATURE_COMPAT_XATTR_FILTER 0x00000004 #define EROFS_FEATURE_COMPAT_SHARED_EA_IN_METABOX 0x00000008 +#define EROFS_FEATURE_COMPAT_PLAIN_XATTR_PFX 0x00000010 + /* * Any bits that aren't in EROFS_ALL_FEATURE_INCOMPAT should diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 4ccc5f0ee8df..9319c66e86c3 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -234,6 +234,7 @@ EROFS_FEATURE_FUNCS(metabox, incompat, INCOMPAT_METABOX) EROFS_FEATURE_FUNCS(sb_chksum, compat, COMPAT_SB_CHKSUM) EROFS_FEATURE_FUNCS(xattr_filter, compat, COMPAT_XATTR_FILTER) EROFS_FEATURE_FUNCS(shared_ea_in_metabox, compat, COMPAT_SHARED_EA_IN_METABOX) +EROFS_FEATURE_FUNCS(plain_xattr_pfx, compat, COMPAT_PLAIN_XATTR_PFX) static inline u64 erofs_nid_to_ino64(struct erofs_sb_info *sbi, erofs_nid_t nid) { diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 1b529ace4db0..db13b40a78e0 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -1018,10 +1018,22 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root) return 0; } +static void erofs_evict_inode(struct inode *inode) +{ +#ifdef CONFIG_FS_DAX + if (IS_DAX(inode)) + dax_break_layout_final(inode); +#endif + + truncate_inode_pages_final(&inode->i_data); + clear_inode(inode); +} + const struct super_operations erofs_sops = { .put_super = erofs_put_super, .alloc_inode = erofs_alloc_inode, .free_inode = erofs_free_inode, + .evict_inode = erofs_evict_inode, .statfs = erofs_statfs, .show_options = erofs_show_options, }; diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index eaa9efd766ee..396536d9a862 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -482,6 +482,7 @@ int erofs_xattr_prefixes_init(struct super_block *sb) erofs_off_t pos = (erofs_off_t)sbi->xattr_prefix_start << 2; struct erofs_xattr_prefix_item *pfs; int ret = 0, i, len; + bool plain = erofs_sb_has_plain_xattr_pfx(sbi); if (!sbi->xattr_prefix_count) return 0; @@ -490,9 +491,15 @@ int erofs_xattr_prefixes_init(struct super_block *sb) if (!pfs) return -ENOMEM; - if (sbi->packed_inode) - buf.mapping = sbi->packed_inode->i_mapping; - else + if (!plain) { + if (erofs_sb_has_metabox(sbi)) + (void)erofs_init_metabuf(&buf, sb, true); + else if (sbi->packed_inode) + buf.mapping = sbi->packed_inode->i_mapping; + else + plain = true; + } + if (plain) (void)erofs_init_metabuf(&buf, sb, false); for (i = 0; i < sbi->xattr_prefix_count; i++) { diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index a93efd95c555..798223e6da9c 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -394,10 +394,10 @@ static int z_erofs_map_blocks_fo(struct inode *inode, .map = map, .in_mbox = erofs_inode_in_metabox(inode), }; - int err = 0; - unsigned int endoff, afmt; + unsigned int endoff; unsigned long initial_lcn; unsigned long long ofs, end; + int err; ofs = flags & EROFS_GET_BLOCKS_FINDTAIL ? inode->i_size - 1 : map->m_la; if (fragment && !(flags & EROFS_GET_BLOCKS_FINDTAIL) && @@ -482,20 +482,15 @@ static int z_erofs_map_blocks_fo(struct inode *inode, err = -EFSCORRUPTED; goto unmap_out; } - afmt = vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER ? - Z_EROFS_COMPRESSION_INTERLACED : - Z_EROFS_COMPRESSION_SHIFTED; + if (vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER) + map->m_algorithmformat = Z_EROFS_COMPRESSION_INTERLACED; + else + map->m_algorithmformat = Z_EROFS_COMPRESSION_SHIFTED; + } else if (m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) { + map->m_algorithmformat = vi->z_algorithmtype[1]; } else { - afmt = m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2 ? - vi->z_algorithmtype[1] : vi->z_algorithmtype[0]; - if (!(EROFS_I_SB(inode)->available_compr_algs & (1 << afmt))) { - erofs_err(sb, "inconsistent algorithmtype %u for nid %llu", - afmt, vi->nid); - err = -EFSCORRUPTED; - goto unmap_out; - } + map->m_algorithmformat = vi->z_algorithmtype[0]; } - map->m_algorithmformat = afmt; if ((flags & EROFS_GET_BLOCKS_FIEMAP) || ((flags & EROFS_GET_BLOCKS_READMORE) && @@ -626,9 +621,9 @@ static int z_erofs_fill_inode(struct inode *inode, struct erofs_map_blocks *map) { struct erofs_inode *const vi = EROFS_I(inode); struct super_block *const sb = inode->i_sb; - int err, headnr; - erofs_off_t pos; struct z_erofs_map_header *h; + erofs_off_t pos; + int err = 0; if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) { /* @@ -642,7 +637,6 @@ static int z_erofs_fill_inode(struct inode *inode, struct erofs_map_blocks *map) if (wait_on_bit_lock(&vi->flags, EROFS_I_BL_Z_BIT, TASK_KILLABLE)) return -ERESTARTSYS; - err = 0; if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) goto out_unlock; @@ -679,15 +673,6 @@ static int z_erofs_fill_inode(struct inode *inode, struct erofs_map_blocks *map) else if (vi->z_advise & Z_EROFS_ADVISE_INLINE_PCLUSTER) vi->z_idata_size = le16_to_cpu(h->h_idata_size); - headnr = 0; - if (vi->z_algorithmtype[0] >= Z_EROFS_COMPRESSION_MAX || - vi->z_algorithmtype[++headnr] >= Z_EROFS_COMPRESSION_MAX) { - erofs_err(sb, "unknown HEAD%u format %u for nid %llu, please upgrade kernel", - headnr + 1, vi->z_algorithmtype[headnr], vi->nid); - err = -EOPNOTSUPP; - goto out_unlock; - } - if (!erofs_sb_has_big_pcluster(EROFS_SB(sb)) && vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 | Z_EROFS_ADVISE_BIG_PCLUSTER_2)) { @@ -726,6 +711,30 @@ out_unlock: return err; } +static int z_erofs_map_sanity_check(struct inode *inode, + struct erofs_map_blocks *map) +{ + struct erofs_sb_info *sbi = EROFS_I_SB(inode); + + if (!(map->m_flags & EROFS_MAP_ENCODED)) + return 0; + if (unlikely(map->m_algorithmformat >= Z_EROFS_COMPRESSION_RUNTIME_MAX)) { + erofs_err(inode->i_sb, "unknown algorithm %d @ pos %llu for nid %llu, please upgrade kernel", + map->m_algorithmformat, map->m_la, EROFS_I(inode)->nid); + return -EOPNOTSUPP; + } + if (unlikely(map->m_algorithmformat < Z_EROFS_COMPRESSION_MAX && + !(sbi->available_compr_algs & (1 << map->m_algorithmformat)))) { + erofs_err(inode->i_sb, "inconsistent algorithmtype %u for nid %llu", + map->m_algorithmformat, EROFS_I(inode)->nid); + return -EFSCORRUPTED; + } + if (unlikely(map->m_plen > Z_EROFS_PCLUSTER_MAX_SIZE || + map->m_llen > Z_EROFS_PCLUSTER_MAX_DSIZE)) + return -EOPNOTSUPP; + return 0; +} + int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map, int flags) { @@ -746,10 +755,8 @@ int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map, else err = z_erofs_map_blocks_fo(inode, map, flags); } - if (!err && (map->m_flags & EROFS_MAP_ENCODED) && - unlikely(map->m_plen > Z_EROFS_PCLUSTER_MAX_SIZE || - map->m_llen > Z_EROFS_PCLUSTER_MAX_DSIZE)) - err = -EOPNOTSUPP; + if (!err) + err = z_erofs_map_sanity_check(inode, map); if (err) map->m_llen = 0; } diff --git a/fs/exec.c b/fs/exec.c index 2a1e5e4042a1..e861a4b7ffda 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -2048,7 +2048,7 @@ static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int writ { int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (!error) + if (!error && !write) validate_coredump_safety(); return error; } diff --git a/fs/fhandle.c b/fs/fhandle.c index 68a7d2861c58..a907ddfac4d5 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -208,6 +208,14 @@ static int vfs_dentry_acceptable(void *context, struct dentry *dentry) return 1; /* + * Verify that the decoded dentry itself has a valid id mapping. + * In case the decoded dentry is the mountfd root itself, this + * verifies that the mountfd inode itself has a valid id mapping. + */ + if (!privileged_wrt_inode_uidgid(user_ns, idmap, d_inode(dentry))) + return 0; + + /* * It's racy as we're not taking rename_lock but we're able to ignore * permissions and we just need an approximation whether we were able * to follow a path to the file. diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index e80cd8f2c049..5150aa25e64b 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1893,7 +1893,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode, index = outarg->offset >> PAGE_SHIFT; - while (num) { + while (num && ap->num_folios < num_pages) { struct folio *folio; unsigned int folio_offset; unsigned int nr_bytes; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 2d817d7cab26..5c569c3cb53f 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1199,7 +1199,7 @@ static void fuse_fillattr(struct mnt_idmap *idmap, struct inode *inode, if (attr->blksize != 0) blkbits = ilog2(attr->blksize); else - blkbits = inode->i_sb->s_blocksize_bits; + blkbits = fc->blkbits; stat->blksize = 1 << blkbits; } @@ -1377,6 +1377,7 @@ retry: generic_fillattr(idmap, request_mask, inode, stat); stat->mode = fi->orig_i_mode; stat->ino = fi->orig_ino; + stat->blksize = 1 << fi->cached_i_blkbits; if (test_bit(FUSE_I_BTIME, &fi->state)) { stat->btime = fi->i_btime; stat->result_mask |= STATX_BTIME; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 5525a4520b0f..4adcf09d4b01 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2960,7 +2960,7 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in, .nodeid_out = ff_out->nodeid, .fh_out = ff_out->fh, .off_out = pos_out, - .len = len, + .len = min_t(size_t, len, UINT_MAX & PAGE_MASK), .flags = flags }; struct fuse_write_out outarg; @@ -3026,6 +3026,9 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in, fc->no_copy_file_range = 1; err = -EOPNOTSUPP; } + if (!err && outarg.size > len) + err = -EIO; + if (err) goto out; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index ec248d13c8bf..cc428d04be3e 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -210,6 +210,12 @@ struct fuse_inode { /** Reference to backing file in passthrough mode */ struct fuse_backing *fb; #endif + + /* + * The underlying inode->i_blkbits value will not be modified, + * so preserve the blocksize specified by the server. + */ + u8 cached_i_blkbits; }; /** FUSE inode state bits */ @@ -969,6 +975,14 @@ struct fuse_conn { /* Request timeout (in jiffies). 0 = no timeout */ unsigned int req_timeout; } timeout; + + /* + * This is a workaround until fuse uses iomap for reads. + * For fuseblk servers, this represents the blocksize passed in at + * mount time and for regular fuse servers, this is equivalent to + * inode->i_blkbits. + */ + u8 blkbits; }; /* diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 67c2318bfc42..7ddfd2b3cc9c 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -289,6 +289,11 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, } } + if (attr->blksize) + fi->cached_i_blkbits = ilog2(attr->blksize); + else + fi->cached_i_blkbits = fc->blkbits; + /* * Don't set the sticky bit in i_mode, unless we want the VFS * to check permissions. This prevents failures due to the @@ -1805,10 +1810,21 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx) err = -EINVAL; if (!sb_set_blocksize(sb, ctx->blksize)) goto err; + /* + * This is a workaround until fuse hooks into iomap for reads. + * Use PAGE_SIZE for the blocksize else if the writeback cache + * is enabled, buffered writes go through iomap and a read may + * overwrite partially written data if blocksize < PAGE_SIZE + */ + fc->blkbits = sb->s_blocksize_bits; + if (ctx->blksize != PAGE_SIZE && + !sb_set_blocksize(sb, PAGE_SIZE)) + goto err; #endif } else { sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; + fc->blkbits = sb->s_blocksize_bits; } sb->s_subtype = ctx->subtype; diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c index 607ef735ad4a..eb97ac009e75 100644 --- a/fs/fuse/passthrough.c +++ b/fs/fuse/passthrough.c @@ -237,6 +237,11 @@ int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map) if (!file) goto out; + /* read/write/splice/mmap passthrough only relevant for regular files */ + res = d_is_dir(file->f_path.dentry) ? -EISDIR : -EINVAL; + if (!d_is_reg(file->f_path.dentry)) + goto out_fput; + backing_sb = file_inode(file)->i_sb; res = -ELOOP; if (backing_sb->s_stack_depth >= fc->max_stack_depth) diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index c826e7ca49f5..76c8fd0bfc75 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -1016,7 +1016,7 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, if (kaddr) *kaddr = fs->window_kaddr + offset; if (pfn) - *pfn = fs->window_phys_addr + offset; + *pfn = PHYS_PFN(fs->window_phys_addr + offset); return nr_pages > max_nr_pages ? max_nr_pages : nr_pages; } diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index a6c692cac616..9adf36e6364b 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -70,6 +70,24 @@ static struct kernfs_open_node *of_on(struct kernfs_open_file *of) !list_empty(&of->list)); } +/* Get active reference to kernfs node for an open file */ +static struct kernfs_open_file *kernfs_get_active_of(struct kernfs_open_file *of) +{ + /* Skip if file was already released */ + if (unlikely(of->released)) + return NULL; + + if (!kernfs_get_active(of->kn)) + return NULL; + + return of; +} + +static void kernfs_put_active_of(struct kernfs_open_file *of) +{ + return kernfs_put_active(of->kn); +} + /** * kernfs_deref_open_node_locked - Get kernfs_open_node corresponding to @kn * @@ -139,7 +157,7 @@ static void kernfs_seq_stop_active(struct seq_file *sf, void *v) if (ops->seq_stop) ops->seq_stop(sf, v); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); } static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) @@ -152,7 +170,7 @@ static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return ERR_PTR(-ENODEV); ops = kernfs_ops(of->kn); @@ -238,7 +256,7 @@ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) { + if (!kernfs_get_active_of(of)) { len = -ENODEV; mutex_unlock(&of->mutex); goto out_free; @@ -252,7 +270,7 @@ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) else len = -EINVAL; - kernfs_put_active(of->kn); + kernfs_put_active_of(of); mutex_unlock(&of->mutex); if (len < 0) @@ -323,7 +341,7 @@ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) { + if (!kernfs_get_active_of(of)) { mutex_unlock(&of->mutex); len = -ENODEV; goto out_free; @@ -335,7 +353,7 @@ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) else len = -EINVAL; - kernfs_put_active(of->kn); + kernfs_put_active_of(of); mutex_unlock(&of->mutex); if (len > 0) @@ -357,13 +375,13 @@ static void kernfs_vma_open(struct vm_area_struct *vma) if (!of->vm_ops) return; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return; if (of->vm_ops->open) of->vm_ops->open(vma); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); } static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf) @@ -375,14 +393,14 @@ static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf) if (!of->vm_ops) return VM_FAULT_SIGBUS; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return VM_FAULT_SIGBUS; ret = VM_FAULT_SIGBUS; if (of->vm_ops->fault) ret = of->vm_ops->fault(vmf); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); return ret; } @@ -395,7 +413,7 @@ static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf) if (!of->vm_ops) return VM_FAULT_SIGBUS; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return VM_FAULT_SIGBUS; ret = 0; @@ -404,7 +422,7 @@ static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf) else file_update_time(file); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); return ret; } @@ -418,14 +436,14 @@ static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr, if (!of->vm_ops) return -EINVAL; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return -EINVAL; ret = -EINVAL; if (of->vm_ops->access) ret = of->vm_ops->access(vma, addr, buf, len, write); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); return ret; } @@ -455,7 +473,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) mutex_lock(&of->mutex); rc = -ENODEV; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) goto out_unlock; ops = kernfs_ops(of->kn); @@ -490,7 +508,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) } vma->vm_ops = &kernfs_vm_ops; out_put: - kernfs_put_active(of->kn); + kernfs_put_active_of(of); out_unlock: mutex_unlock(&of->mutex); @@ -852,7 +870,7 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); __poll_t ret; - if (!kernfs_get_active(kn)) + if (!kernfs_get_active_of(of)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; if (kn->attr.ops->poll) @@ -860,7 +878,7 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) else ret = kernfs_generic_poll(of, wait); - kernfs_put_active(kn); + kernfs_put_active_of(of); return ret; } @@ -875,7 +893,7 @@ static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) { + if (!kernfs_get_active_of(of)) { mutex_unlock(&of->mutex); return -ENODEV; } @@ -886,7 +904,7 @@ static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence) else ret = generic_file_llseek(file, offset, whence); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); mutex_unlock(&of->mutex); return ret; } diff --git a/fs/namespace.c b/fs/namespace.c index ae6d1312b184..51f77c65c0c6 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2455,7 +2455,7 @@ struct vfsmount *clone_private_mount(const struct path *path) return ERR_PTR(-EINVAL); } - if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN)) + if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); if (__has_locked_children(old_mnt, path->dentry)) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 8fb4a950dd55..4e3dcc157a83 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -888,6 +888,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, if (fsinfo->xattr_support) server->caps |= NFS_CAP_XATTR; + else + server->caps &= ~NFS_CAP_XATTR; #endif } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 86e36c630f09..8059ece82468 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -28,6 +28,7 @@ #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/gfp.h> +#include <linux/rmap.h> #include <linux/swap.h> #include <linux/compaction.h> @@ -280,6 +281,37 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) } EXPORT_SYMBOL_GPL(nfs_file_fsync); +void nfs_truncate_last_folio(struct address_space *mapping, loff_t from, + loff_t to) +{ + struct folio *folio; + + if (from >= to) + return; + + folio = filemap_lock_folio(mapping, from >> PAGE_SHIFT); + if (IS_ERR(folio)) + return; + + if (folio_mkclean(folio)) + folio_mark_dirty(folio); + + if (folio_test_uptodate(folio)) { + loff_t fpos = folio_pos(folio); + size_t offset = from - fpos; + size_t end = folio_size(folio); + + if (to - fpos < end) + end = to - fpos; + folio_zero_segment(folio, offset, end); + trace_nfs_size_truncate_folio(mapping->host, to); + } + + folio_unlock(folio); + folio_put(folio); +} +EXPORT_SYMBOL_GPL(nfs_truncate_last_folio); + /* * Decide whether a read/modify/write cycle may be more efficient * then a modify/write/read cycle when writing to a page in the @@ -356,6 +388,7 @@ static int nfs_write_begin(const struct kiocb *iocb, dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%lu), %u@%lld)\n", file, mapping->host->i_ino, len, (long long) pos); + nfs_truncate_last_folio(mapping, i_size_read(mapping->host), pos); fgp |= fgf_set_order(len); start: @@ -442,10 +475,11 @@ static void nfs_invalidate_folio(struct folio *folio, size_t offset, dfprintk(PAGECACHE, "NFS: invalidate_folio(%lu, %zu, %zu)\n", folio->index, offset, length); - if (offset != 0 || length < folio_size(folio)) - return; /* Cancel any unstarted writes on this page */ - nfs_wb_folio_cancel(inode, folio); + if (offset != 0 || length < folio_size(folio)) + nfs_wb_folio(inode, folio); + else + nfs_wb_folio_cancel(inode, folio); folio_wait_private_2(folio); /* [DEPRECATED] */ trace_nfs_invalidate_folio(inode, folio_pos(folio) + offset, length); } diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 8dc921d83538..9edb5f9b0c4e 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -293,7 +293,7 @@ ff_lseg_match_mirrors(struct pnfs_layout_segment *l1, struct pnfs_layout_segment *l2) { const struct nfs4_ff_layout_segment *fl1 = FF_LAYOUT_LSEG(l1); - const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l1); + const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l2); u32 i; if (fl1->mirror_array_cnt != fl2->mirror_array_cnt) @@ -773,8 +773,11 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg, continue; if (check_device && - nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node)) + nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node)) { + // reinitialize the error state in case if this is the last iteration + ds = ERR_PTR(-EINVAL); continue; + } *best_idx = idx; break; @@ -804,7 +807,7 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg, struct nfs4_pnfs_ds *ds; ds = ff_layout_choose_valid_ds_for_read(lseg, start_idx, best_idx); - if (ds) + if (!IS_ERR(ds)) return ds; return ff_layout_choose_any_ds_for_read(lseg, start_idx, best_idx); } @@ -818,7 +821,7 @@ ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio, ds = ff_layout_choose_best_ds_for_read(lseg, pgio->pg_mirror_idx, best_idx); - if (ds || !pgio->pg_mirror_idx) + if (!IS_ERR(ds) || !pgio->pg_mirror_idx) return ds; return ff_layout_choose_best_ds_for_read(lseg, 0, best_idx); } @@ -868,7 +871,7 @@ retry: req->wb_nio = 0; ds = ff_layout_get_ds_for_read(pgio, &ds_idx); - if (!ds) { + if (IS_ERR(ds)) { if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg)) goto out_mds; pnfs_generic_pg_cleanup(pgio); @@ -1072,11 +1075,13 @@ static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr) { u32 idx = hdr->pgio_mirror_idx + 1; u32 new_idx = 0; + struct nfs4_pnfs_ds *ds; - if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx)) - ff_layout_send_layouterror(hdr->lseg); - else + ds = ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx); + if (IS_ERR(ds)) pnfs_error_mark_layout_for_return(hdr->inode, hdr->lseg); + else + ff_layout_send_layouterror(hdr->lseg); pnfs_read_resend_pnfs(hdr, new_idx); } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 338ef77ae423..49df9debb1a6 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -716,6 +716,7 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, { struct inode *inode = d_inode(dentry); struct nfs_fattr *fattr; + loff_t oldsize = i_size_read(inode); int error = 0; nfs_inc_stats(inode, NFSIOS_VFSSETATTR); @@ -731,7 +732,7 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if (error) return error; - if (attr->ia_size == i_size_read(inode)) + if (attr->ia_size == oldsize) attr->ia_valid &= ~ATTR_SIZE; } @@ -767,8 +768,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, trace_nfs_setattr_enter(inode); /* Write all dirty data */ - if (S_ISREG(inode->i_mode)) + if (S_ISREG(inode->i_mode)) { + nfs_file_block_o_direct(NFS_I(inode)); nfs_sync_inode(inode); + } fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) { @@ -777,8 +780,12 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, } error = NFS_PROTO(inode)->setattr(dentry, fattr, attr); - if (error == 0) + if (error == 0) { + if (attr->ia_valid & ATTR_SIZE) + nfs_truncate_last_folio(inode->i_mapping, oldsize, + attr->ia_size); error = nfs_refresh_inode(inode, fattr); + } nfs_free_fattr(fattr); out: trace_nfs_setattr_exit(inode, error); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 74d712b58423..c0a44f389f8f 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -437,6 +437,8 @@ int nfs_file_release(struct inode *, struct file *); int nfs_lock(struct file *, int, struct file_lock *); int nfs_flock(struct file *, int, struct file_lock *); int nfs_check_flags(int); +void nfs_truncate_last_folio(struct address_space *mapping, loff_t from, + loff_t to); /* inode.c */ extern struct workqueue_struct *nfsiod_workqueue; @@ -530,6 +532,16 @@ static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi) return test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0; } +/* Must be called with exclusively locked inode->i_rwsem */ +static inline void nfs_file_block_o_direct(struct nfs_inode *nfsi) +{ + if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) { + clear_bit(NFS_INO_ODIRECT, &nfsi->flags); + inode_dio_wait(&nfsi->vfs_inode); + } +} + + /* namespace.c */ #define NFS_PATH_CANONICAL 1 extern char *nfs_path(char **p, struct dentry *dentry, diff --git a/fs/nfs/io.c b/fs/nfs/io.c index 3388faf2acb9..d275b0a250bf 100644 --- a/fs/nfs/io.c +++ b/fs/nfs/io.c @@ -14,15 +14,6 @@ #include "internal.h" -/* Call with exclusively locked inode->i_rwsem */ -static void nfs_block_o_direct(struct nfs_inode *nfsi, struct inode *inode) -{ - if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) { - clear_bit(NFS_INO_ODIRECT, &nfsi->flags); - inode_dio_wait(inode); - } -} - /** * nfs_start_io_read - declare the file is being used for buffered reads * @inode: file inode @@ -57,7 +48,7 @@ nfs_start_io_read(struct inode *inode) err = down_write_killable(&inode->i_rwsem); if (err) return err; - nfs_block_o_direct(nfsi, inode); + nfs_file_block_o_direct(nfsi); downgrade_write(&inode->i_rwsem); return 0; @@ -90,7 +81,7 @@ nfs_start_io_write(struct inode *inode) err = down_write_killable(&inode->i_rwsem); if (!err) - nfs_block_o_direct(NFS_I(inode), inode); + nfs_file_block_o_direct(NFS_I(inode)); return err; } diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c index bd5fca285899..97abf62f109d 100644 --- a/fs/nfs/localio.c +++ b/fs/nfs/localio.c @@ -180,10 +180,8 @@ static void nfs_local_probe(struct nfs_client *clp) return; } - if (nfs_client_is_local(clp)) { - /* If already enabled, disable and re-enable */ - nfs_localio_disable_client(clp); - } + if (nfs_client_is_local(clp)) + return; if (!nfs_uuid_begin(&clp->cl_uuid)) return; @@ -244,7 +242,8 @@ __nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, case -ENOMEM: case -ENXIO: case -ENOENT: - /* Revalidate localio, will disable if unsupported */ + /* Revalidate localio */ + nfs_localio_disable_client(clp); nfs_local_probe(clp); } } @@ -453,12 +452,13 @@ static void nfs_local_call_read(struct work_struct *work) nfs_local_iter_init(&iter, iocb, READ); status = filp->f_op->read_iter(&iocb->kiocb, &iter); + + revert_creds(save_cred); + if (status != -EIOCBQUEUED) { nfs_local_read_done(iocb, status); nfs_local_pgio_release(iocb); } - - revert_creds(save_cred); } static int @@ -648,14 +648,15 @@ static void nfs_local_call_write(struct work_struct *work) file_start_write(filp); status = filp->f_op->write_iter(&iocb->kiocb, &iter); file_end_write(filp); + + revert_creds(save_cred); + current->flags = old_flags; + if (status != -EIOCBQUEUED) { nfs_local_write_done(iocb, status); nfs_local_vfs_getattr(iocb); nfs_local_pgio_release(iocb); } - - revert_creds(save_cred); - current->flags = old_flags; } static int diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 01c01f45358b..6a0b5871ba3b 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -114,6 +114,7 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, exception.inode = inode; exception.state = lock->open_context->state; + nfs_file_block_o_direct(NFS_I(inode)); err = nfs_sync_inode(inode); if (err) goto out; @@ -137,6 +138,7 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE], }; struct inode *inode = file_inode(filep); + loff_t oldsize = i_size_read(inode); int err; if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE)) @@ -145,7 +147,11 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) inode_lock(inode); err = nfs42_proc_fallocate(&msg, filep, offset, len); - if (err == -EOPNOTSUPP) + + if (err == 0) + nfs_truncate_last_folio(inode->i_mapping, oldsize, + offset + len); + else if (err == -EOPNOTSUPP) NFS_SERVER(inode)->caps &= ~(NFS_CAP_ALLOCATE | NFS_CAP_ZERO_RANGE); @@ -183,6 +189,7 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len) .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ZERO_RANGE], }; struct inode *inode = file_inode(filep); + loff_t oldsize = i_size_read(inode); int err; if (!nfs_server_capable(inode, NFS_CAP_ZERO_RANGE)) @@ -191,9 +198,11 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len) inode_lock(inode); err = nfs42_proc_fallocate(&msg, filep, offset, len); - if (err == 0) + if (err == 0) { + nfs_truncate_last_folio(inode->i_mapping, oldsize, + offset + len); truncate_pagecache_range(inode, offset, (offset + len) -1); - if (err == -EOPNOTSUPP) + } else if (err == -EOPNOTSUPP) NFS_SERVER(inode)->caps &= ~NFS_CAP_ZERO_RANGE; inode_unlock(inode); @@ -354,22 +363,27 @@ out: /** * nfs42_copy_dest_done - perform inode cache updates after clone/copy offload - * @inode: pointer to destination inode + * @file: pointer to destination file * @pos: destination offset * @len: copy length + * @oldsize: length of the file prior to clone/copy * * Punch a hole in the inode page cache, so that the NFS client will * know to retrieve new data. * Update the file size if necessary, and then mark the inode as having * invalid cached values for change attribute, ctime, mtime and space used. */ -static void nfs42_copy_dest_done(struct inode *inode, loff_t pos, loff_t len) +static void nfs42_copy_dest_done(struct file *file, loff_t pos, loff_t len, + loff_t oldsize) { + struct inode *inode = file_inode(file); + struct address_space *mapping = file->f_mapping; loff_t newsize = pos + len; loff_t end = newsize - 1; - WARN_ON_ONCE(invalidate_inode_pages2_range(inode->i_mapping, - pos >> PAGE_SHIFT, end >> PAGE_SHIFT)); + nfs_truncate_last_folio(mapping, oldsize, pos); + WARN_ON_ONCE(invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, + end >> PAGE_SHIFT)); spin_lock(&inode->i_lock); if (newsize > i_size_read(inode)) @@ -402,6 +416,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, struct nfs_server *src_server = NFS_SERVER(src_inode); loff_t pos_src = args->src_pos; loff_t pos_dst = args->dst_pos; + loff_t oldsize_dst = i_size_read(dst_inode); size_t count = args->count; ssize_t status; @@ -430,6 +445,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, return status; } + nfs_file_block_o_direct(NFS_I(dst_inode)); status = nfs_sync_inode(dst_inode); if (status) return status; @@ -475,7 +491,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, goto out; } - nfs42_copy_dest_done(dst_inode, pos_dst, res->write_res.count); + nfs42_copy_dest_done(dst, pos_dst, res->write_res.count, oldsize_dst); nfs_invalidate_atime(src_inode); status = res->write_res.count; out: @@ -1242,6 +1258,7 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, struct nfs42_clone_res res = { .server = server, }; + loff_t oldsize_dst = i_size_read(dst_inode); int status; msg->rpc_argp = &args; @@ -1276,7 +1293,7 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, /* a zero-length count means clone to EOF in src */ if (count == 0 && res.dst_fattr->valid & NFS_ATTR_FATTR_SIZE) count = nfs_size_to_loff_t(res.dst_fattr->size) - dst_offset; - nfs42_copy_dest_done(dst_inode, dst_offset, count); + nfs42_copy_dest_done(dst_f, dst_offset, count, oldsize_dst); status = nfs_post_op_update_inode(dst_inode, res.dst_fattr); } diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 1d6b5f4230c9..c9a0d1e420c6 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -278,9 +278,11 @@ static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off, lock_two_nondirectories(src_inode, dst_inode); /* flush all pending writes on both src and dst so that server * has the latest data */ + nfs_file_block_o_direct(NFS_I(src_inode)); ret = nfs_sync_inode(src_inode); if (ret) goto out_unlock; + nfs_file_block_o_direct(NFS_I(dst_inode)); ret = nfs_sync_inode(dst_inode); if (ret) goto out_unlock; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 7d2b67e06cc3..ce61253efd45 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4013,8 +4013,10 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f res.attr_bitmask[2]; } memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask)); - server->caps &= ~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS | - NFS_CAP_SYMLINKS| NFS_CAP_SECURITY_LABEL); + server->caps &= + ~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS | + NFS_CAP_SECURITY_LABEL | NFS_CAP_FS_LOCATIONS | + NFS_CAP_OPEN_XOR | NFS_CAP_DELEGTIME); server->fattr_valid = NFS_ATTR_FATTR_V4; if (res.attr_bitmask[0] & FATTR4_WORD0_ACL && res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL) @@ -4092,7 +4094,6 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) }; int err; - nfs_server_set_init_caps(server); do { err = nfs4_handle_exception(server, _nfs4_server_capabilities(server, fhandle), diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 96b1323318c2..627115179795 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -272,6 +272,7 @@ DECLARE_EVENT_CLASS(nfs_update_size_class, TP_ARGS(inode, new_size)) DEFINE_NFS_UPDATE_SIZE_EVENT(truncate); +DEFINE_NFS_UPDATE_SIZE_EVENT(truncate_folio); DEFINE_NFS_UPDATE_SIZE_EVENT(wcc); DEFINE_NFS_UPDATE_SIZE_EVENT(update); DEFINE_NFS_UPDATE_SIZE_EVENT(grow); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 8b7c04737967..647c53d1418a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -237,59 +237,17 @@ static void nfs_mapping_set_error(struct folio *folio, int error) } /* - * nfs_page_group_search_locked - * @head - head request of page group - * @page_offset - offset into page + * nfs_page_covers_folio + * @req: struct nfs_page * - * Search page group with head @head to find a request that contains the - * page offset @page_offset. - * - * Returns a pointer to the first matching nfs request, or NULL if no - * match is found. - * - * Must be called with the page group lock held - */ -static struct nfs_page * -nfs_page_group_search_locked(struct nfs_page *head, unsigned int page_offset) -{ - struct nfs_page *req; - - req = head; - do { - if (page_offset >= req->wb_pgbase && - page_offset < (req->wb_pgbase + req->wb_bytes)) - return req; - - req = req->wb_this_page; - } while (req != head); - - return NULL; -} - -/* - * nfs_page_group_covers_page - * @head - head request of page group - * - * Return true if the page group with head @head covers the whole page, - * returns false otherwise + * Return true if the request covers the whole folio. + * Note that the caller should ensure all subrequests have been joined */ static bool nfs_page_group_covers_page(struct nfs_page *req) { unsigned int len = nfs_folio_length(nfs_page_to_folio(req)); - struct nfs_page *tmp; - unsigned int pos = 0; - - nfs_page_group_lock(req); - for (;;) { - tmp = nfs_page_group_search_locked(req->wb_head, pos); - if (!tmp) - break; - pos = tmp->wb_pgbase + tmp->wb_bytes; - } - - nfs_page_group_unlock(req); - return pos >= len; + return req->wb_pgbase == 0 && req->wb_bytes == len; } /* We can set the PG_uptodate flag if we see that a write request @@ -2045,6 +2003,7 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio) * release it */ nfs_inode_remove_request(req); nfs_unlock_and_release_request(req); + folio_cancel_dirty(folio); } return ret; diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c index 14868a3dd592..bc52afbfc5c7 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -1075,7 +1075,7 @@ void nilfs_sysfs_delete_device_group(struct the_nilfs *nilfs) ************************************************************************/ static ssize_t nilfs_feature_revision_show(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%d.%d\n", NILFS_CURRENT_REV, NILFS_MINOR_REV); @@ -1087,7 +1087,7 @@ static const char features_readme_str[] = "(1) revision\n\tshow current revision of NILFS file system driver.\n"; static ssize_t nilfs_feature_README_show(struct kobject *kobj, - struct attribute *attr, + struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, features_readme_str); diff --git a/fs/nilfs2/sysfs.h b/fs/nilfs2/sysfs.h index 78a87a016928..d370cd5cce3f 100644 --- a/fs/nilfs2/sysfs.h +++ b/fs/nilfs2/sysfs.h @@ -50,16 +50,16 @@ struct nilfs_sysfs_dev_subgroups { struct completion sg_segments_kobj_unregister; }; -#define NILFS_COMMON_ATTR_STRUCT(name) \ +#define NILFS_KOBJ_ATTR_STRUCT(name) \ struct nilfs_##name##_attr { \ struct attribute attr; \ - ssize_t (*show)(struct kobject *, struct attribute *, \ + ssize_t (*show)(struct kobject *, struct kobj_attribute *, \ char *); \ - ssize_t (*store)(struct kobject *, struct attribute *, \ + ssize_t (*store)(struct kobject *, struct kobj_attribute *, \ const char *, size_t); \ } -NILFS_COMMON_ATTR_STRUCT(feature); +NILFS_KOBJ_ATTR_STRUCT(feature); #define NILFS_DEV_ATTR_STRUCT(name) \ struct nilfs_##name##_attr { \ diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index 930150ed5db1..ef147e8b3271 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -706,6 +706,8 @@ out: * it not only handles the fiemap for inlined files, but also deals * with the fast symlink, cause they have no difference for extent * mapping per se. + * + * Must be called with ip_alloc_sem semaphore held. */ static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh, struct fiemap_extent_info *fieinfo, @@ -717,6 +719,7 @@ static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh, u64 phys; u32 flags = FIEMAP_EXTENT_DATA_INLINE|FIEMAP_EXTENT_LAST; struct ocfs2_inode_info *oi = OCFS2_I(inode); + lockdep_assert_held_read(&oi->ip_alloc_sem); di = (struct ocfs2_dinode *)di_bh->b_data; if (ocfs2_inode_is_fast_symlink(inode)) @@ -732,8 +735,11 @@ static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh, phys += offsetof(struct ocfs2_dinode, id2.i_data.id_data); + /* Release the ip_alloc_sem to prevent deadlock on page fault */ + up_read(&OCFS2_I(inode)->ip_alloc_sem); ret = fiemap_fill_next_extent(fieinfo, 0, phys, id_count, flags); + down_read(&OCFS2_I(inode)->ip_alloc_sem); if (ret < 0) return ret; } @@ -802,9 +808,11 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, len_bytes = (u64)le16_to_cpu(rec.e_leaf_clusters) << osb->s_clustersize_bits; phys_bytes = le64_to_cpu(rec.e_blkno) << osb->sb->s_blocksize_bits; virt_bytes = (u64)le32_to_cpu(rec.e_cpos) << osb->s_clustersize_bits; - + /* Release the ip_alloc_sem to prevent deadlock on page fault */ + up_read(&OCFS2_I(inode)->ip_alloc_sem); ret = fiemap_fill_next_extent(fieinfo, virt_bytes, phys_bytes, len_bytes, fe_flags); + down_read(&OCFS2_I(inode)->ip_alloc_sem); if (ret) break; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index bd0c099cfdd2..176281112273 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -393,7 +393,8 @@ struct proc_dir_entry *proc_register(struct proc_dir_entry *dir, if (proc_alloc_inum(&dp->low_ino)) goto out_free_entry; - pde_set_flags(dp); + if (!S_ISDIR(dp->mode)) + pde_set_flags(dp); write_lock(&proc_subdir_lock); dp->parent = dir; diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c index d98e0d2de09f..3c39cfacb251 100644 --- a/fs/resctrl/ctrlmondata.c +++ b/fs/resctrl/ctrlmondata.c @@ -625,11 +625,11 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) */ list_for_each_entry(d, &r->mon_domains, hdr.list) { if (d->ci_id == domid) { - rr.ci_id = d->ci_id; cpu = cpumask_any(&d->hdr.cpu_mask); ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); if (!ci) continue; + rr.ci = ci; mon_event_read(&rr, r, NULL, rdtgrp, &ci->shared_cpu_map, evtid, false); goto checkresult; diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index 0a1eedba2b03..9a8cf6f11151 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -98,7 +98,7 @@ struct mon_data { * domains in @r sharing L3 @ci.id * @evtid: Which monitor event to read. * @first: Initialize MBM counter when true. - * @ci_id: Cacheinfo id for L3. Only set when @d is NULL. Used when summing domains. + * @ci: Cacheinfo for L3. Only set when @d is NULL. Used when summing domains. * @err: Error encountered when reading counter. * @val: Returned value of event counter. If @rgrp is a parent resource group, * @val includes the sum of event counts from its child resource groups. @@ -112,7 +112,7 @@ struct rmid_read { struct rdt_mon_domain *d; enum resctrl_event_id evtid; bool first; - unsigned int ci_id; + struct cacheinfo *ci; int err; u64 val; void *arch_mon_ctx; diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index f5637855c3ac..7326c28a7908 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -361,7 +361,6 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) { int cpu = smp_processor_id(); struct rdt_mon_domain *d; - struct cacheinfo *ci; struct mbm_state *m; int err, ret; u64 tval = 0; @@ -389,8 +388,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) } /* Summing domains that share a cache, must be on a CPU for that cache. */ - ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); - if (!ci || ci->id != rr->ci_id) + if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map)) return -EINVAL; /* @@ -402,7 +400,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) */ ret = -EINVAL; list_for_each_entry(d, &rr->r->mon_domains, hdr.list) { - if (d->ci_id != rr->ci_id) + if (d->ci_id != rr->ci->id) continue; err = resctrl_arch_rmid_read(rr->r, d, closid, rmid, rr->evtid, &tval, rr->arch_mon_ctx); diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 1e64a4fb6af0..0fae95cf81c4 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -87,7 +87,7 @@ #define SMB_INTERFACE_POLL_INTERVAL 600 /* maximum number of PDUs in one compound */ -#define MAX_COMPOUND 7 +#define MAX_COMPOUND 10 /* * Default number of credits to keep available for SMB3. @@ -1882,9 +1882,12 @@ static inline bool is_replayable_error(int error) /* cifs_get_writable_file() flags */ -#define FIND_WR_ANY 0 -#define FIND_WR_FSUID_ONLY 1 -#define FIND_WR_WITH_DELETE 2 +enum cifs_writable_file_flags { + FIND_WR_ANY = 0U, + FIND_WR_FSUID_ONLY = (1U << 0), + FIND_WR_WITH_DELETE = (1U << 1), + FIND_WR_NO_PENDING_DELETE = (1U << 2), +}; #define MID_FREE 0 #define MID_REQUEST_ALLOCATED 1 @@ -2343,6 +2346,8 @@ struct smb2_compound_vars { struct kvec qi_iov; struct kvec io_iov[SMB2_IOCTL_IOV_SIZE]; struct kvec si_iov[SMB2_SET_INFO_IOV_SIZE]; + struct kvec unlink_iov[SMB2_SET_INFO_IOV_SIZE]; + struct kvec rename_iov[SMB2_SET_INFO_IOV_SIZE]; struct kvec close_iov; struct smb2_file_rename_info_hdr rename_info; struct smb2_file_link_info_hdr link_info; diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index c34c533b2efa..e8fba98690ce 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -312,8 +312,8 @@ extern void cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode); extern void cifs_close_all_deferred_files(struct cifs_tcon *cifs_tcon); -extern void cifs_close_deferred_file_under_dentry(struct cifs_tcon *cifs_tcon, - const char *path); +void cifs_close_deferred_file_under_dentry(struct cifs_tcon *cifs_tcon, + struct dentry *dentry); extern void cifs_mark_open_handles_for_deleted_file(struct inode *inode, const char *path); diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 186e061068be..cb907e18cc35 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -998,7 +998,10 @@ int cifs_open(struct inode *inode, struct file *file) /* Get the cached handle as SMB2 close is deferred */ if (OPEN_FMODE(file->f_flags) & FMODE_WRITE) { - rc = cifs_get_writable_path(tcon, full_path, FIND_WR_FSUID_ONLY, &cfile); + rc = cifs_get_writable_path(tcon, full_path, + FIND_WR_FSUID_ONLY | + FIND_WR_NO_PENDING_DELETE, + &cfile); } else { rc = cifs_get_readable_path(tcon, full_path, &cfile); } @@ -2530,6 +2533,9 @@ refind_writable: continue; if (with_delete && !(open_file->fid.access & DELETE)) continue; + if ((flags & FIND_WR_NO_PENDING_DELETE) && + open_file->status_file_deleted) + continue; if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) { if (!open_file->invalidHandle) { /* found a good writable file */ @@ -2647,6 +2653,16 @@ cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, spin_unlock(&tcon->open_file_lock); free_dentry_path(page); *ret_file = find_readable_file(cinode, 0); + if (*ret_file) { + spin_lock(&cinode->open_file_lock); + if ((*ret_file)->status_file_deleted) { + spin_unlock(&cinode->open_file_lock); + cifsFileInfo_put(*ret_file); + *ret_file = NULL; + } else { + spin_unlock(&cinode->open_file_lock); + } + } return *ret_file ? 0 : -ENOENT; } diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index fe453a4b3dc8..0f0d2dae6283 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -1931,7 +1931,7 @@ cifs_drop_nlink(struct inode *inode) * but will return the EACCES to the caller. Note that the VFS does not call * unlink on negative dentries currently. */ -int cifs_unlink(struct inode *dir, struct dentry *dentry) +static int __cifs_unlink(struct inode *dir, struct dentry *dentry, bool sillyrename) { int rc = 0; unsigned int xid; @@ -1984,7 +1984,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) } netfs_wait_for_outstanding_io(inode); - cifs_close_deferred_file_under_dentry(tcon, full_path); + cifs_close_deferred_file_under_dentry(tcon, dentry); #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))) { @@ -2003,7 +2003,24 @@ retry_std_delete: goto psx_del_no_retry; } - rc = server->ops->unlink(xid, tcon, full_path, cifs_sb, dentry); + /* For SMB2+, if the file is open, we always perform a silly rename. + * + * We check for d_count() right after calling + * cifs_close_deferred_file_under_dentry() to make sure that the + * dentry's refcount gets dropped in case the file had any deferred + * close. + */ + if (!sillyrename && server->vals->protocol_id > SMB10_PROT_ID) { + spin_lock(&dentry->d_lock); + if (d_count(dentry) > 1) + sillyrename = true; + spin_unlock(&dentry->d_lock); + } + + if (sillyrename) + rc = -EBUSY; + else + rc = server->ops->unlink(xid, tcon, full_path, cifs_sb, dentry); psx_del_no_retry: if (!rc) { @@ -2071,6 +2088,11 @@ unlink_out: return rc; } +int cifs_unlink(struct inode *dir, struct dentry *dentry) +{ + return __cifs_unlink(dir, dentry, false); +} + static int cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode, const char *full_path, struct cifs_sb_info *cifs_sb, @@ -2358,14 +2380,16 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry) rc = server->ops->rmdir(xid, tcon, full_path, cifs_sb); cifs_put_tlink(tlink); + cifsInode = CIFS_I(d_inode(direntry)); + if (!rc) { + set_bit(CIFS_INO_DELETE_PENDING, &cifsInode->flags); spin_lock(&d_inode(direntry)->i_lock); i_size_write(d_inode(direntry), 0); clear_nlink(d_inode(direntry)); spin_unlock(&d_inode(direntry)->i_lock); } - cifsInode = CIFS_I(d_inode(direntry)); /* force revalidate to go get info when needed */ cifsInode->time = 0; @@ -2458,8 +2482,11 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ do_rename_exit: - if (rc == 0) + if (rc == 0) { d_move(from_dentry, to_dentry); + /* Force a new lookup */ + d_drop(from_dentry); + } cifs_put_tlink(tlink); return rc; } @@ -2470,6 +2497,7 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, struct dentry *target_dentry, unsigned int flags) { const char *from_name, *to_name; + struct TCP_Server_Info *server; void *page1, *page2; struct cifs_sb_info *cifs_sb; struct tcon_link *tlink; @@ -2505,6 +2533,7 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, if (IS_ERR(tlink)) return PTR_ERR(tlink); tcon = tlink_tcon(tlink); + server = tcon->ses->server; page1 = alloc_dentry_path(); page2 = alloc_dentry_path(); @@ -2522,10 +2551,10 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, goto cifs_rename_exit; } - cifs_close_deferred_file_under_dentry(tcon, from_name); + cifs_close_deferred_file_under_dentry(tcon, source_dentry); if (d_inode(target_dentry) != NULL) { netfs_wait_for_outstanding_io(d_inode(target_dentry)); - cifs_close_deferred_file_under_dentry(tcon, to_name); + cifs_close_deferred_file_under_dentry(tcon, target_dentry); } rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, @@ -2591,19 +2620,53 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, unlink_target: #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ - - /* Try unlinking the target dentry if it's not negative */ - if (d_really_is_positive(target_dentry) && (rc == -EACCES || rc == -EEXIST)) { - if (d_is_dir(target_dentry)) - tmprc = cifs_rmdir(target_dir, target_dentry); - else - tmprc = cifs_unlink(target_dir, target_dentry); - if (tmprc) - goto cifs_rename_exit; - rc = cifs_do_rename(xid, source_dentry, from_name, - target_dentry, to_name); - if (!rc) - rehash = false; + if (d_really_is_positive(target_dentry)) { + if (!rc) { + struct inode *inode = d_inode(target_dentry); + /* + * Samba and ksmbd servers allow renaming a target + * directory that is open, so make sure to update + * ->i_nlink and then mark it as delete pending. + */ + if (S_ISDIR(inode->i_mode)) { + drop_cached_dir_by_name(xid, tcon, to_name, cifs_sb); + spin_lock(&inode->i_lock); + i_size_write(inode, 0); + clear_nlink(inode); + spin_unlock(&inode->i_lock); + set_bit(CIFS_INO_DELETE_PENDING, &CIFS_I(inode)->flags); + CIFS_I(inode)->time = 0; /* force reval */ + inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); + } + } else if (rc == -EACCES || rc == -EEXIST) { + /* + * Rename failed, possibly due to a busy target. + * Retry it by unliking the target first. + */ + if (d_is_dir(target_dentry)) { + tmprc = cifs_rmdir(target_dir, target_dentry); + } else { + tmprc = __cifs_unlink(target_dir, target_dentry, + server->vals->protocol_id > SMB10_PROT_ID); + } + if (tmprc) { + /* + * Some servers will return STATUS_ACCESS_DENIED + * or STATUS_DIRECTORY_NOT_EMPTY when failing to + * rename a non-empty directory. Make sure to + * propagate the appropriate error back to + * userspace. + */ + if (tmprc == -EEXIST || tmprc == -ENOTEMPTY) + rc = tmprc; + goto cifs_rename_exit; + } + rc = cifs_do_rename(xid, source_dentry, from_name, + target_dentry, to_name); + if (!rc) + rehash = false; + } } /* force revalidate to go get info when needed */ @@ -2629,6 +2692,8 @@ cifs_dentry_needs_reval(struct dentry *dentry) struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); struct cached_fid *cfid = NULL; + if (test_bit(CIFS_INO_DELETE_PENDING, &cifs_i->flags)) + return false; if (cifs_i->time == 0) return true; diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index da23cc12a52c..dda6dece802a 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -832,33 +832,28 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon) kfree(tmp_list); } } -void -cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, const char *path) + +void cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, + struct dentry *dentry) { - struct cifsFileInfo *cfile; struct file_list *tmp_list, *tmp_next_list; - void *page; - const char *full_path; + struct cifsFileInfo *cfile; LIST_HEAD(file_head); - page = alloc_dentry_path(); spin_lock(&tcon->open_file_lock); list_for_each_entry(cfile, &tcon->openFileList, tlist) { - full_path = build_path_from_dentry(cfile->dentry, page); - if (strstr(full_path, path)) { - if (delayed_work_pending(&cfile->deferred)) { - if (cancel_delayed_work(&cfile->deferred)) { - spin_lock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock); - cifs_del_deferred_close(cfile); - spin_unlock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock); - - tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); - if (tmp_list == NULL) - break; - tmp_list->cfile = cfile; - list_add_tail(&tmp_list->list, &file_head); - } - } + if ((cfile->dentry == dentry) && + delayed_work_pending(&cfile->deferred) && + cancel_delayed_work(&cfile->deferred)) { + spin_lock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock); + cifs_del_deferred_close(cfile); + spin_unlock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock); + + tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); + if (tmp_list == NULL) + break; + tmp_list->cfile = cfile; + list_add_tail(&tmp_list->list, &file_head); } } spin_unlock(&tcon->open_file_lock); @@ -868,7 +863,6 @@ cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, const char *path) list_del(&tmp_list->list); kfree(tmp_list); } - free_dentry_path(page); } /* diff --git a/fs/smb/client/smb2glob.h b/fs/smb/client/smb2glob.h index 224495322a05..e56e4d402f13 100644 --- a/fs/smb/client/smb2glob.h +++ b/fs/smb/client/smb2glob.h @@ -30,10 +30,9 @@ enum smb2_compound_ops { SMB2_OP_QUERY_DIR, SMB2_OP_MKDIR, SMB2_OP_RENAME, - SMB2_OP_DELETE, SMB2_OP_HARDLINK, SMB2_OP_SET_EOF, - SMB2_OP_RMDIR, + SMB2_OP_UNLINK, SMB2_OP_POSIX_QUERY_INFO, SMB2_OP_SET_REPARSE, SMB2_OP_GET_REPARSE, diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 31c13fb5b85b..7cadc8ca4f55 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -346,9 +346,6 @@ replay_again: trace_smb3_posix_query_info_compound_enter(xid, tcon->tid, ses->Suid, full_path); break; - case SMB2_OP_DELETE: - trace_smb3_delete_enter(xid, tcon->tid, ses->Suid, full_path); - break; case SMB2_OP_MKDIR: /* * Directories are created through parameters in the @@ -356,23 +353,40 @@ replay_again: */ trace_smb3_mkdir_enter(xid, tcon->tid, ses->Suid, full_path); break; - case SMB2_OP_RMDIR: - rqst[num_rqst].rq_iov = &vars->si_iov[0]; + case SMB2_OP_UNLINK: + rqst[num_rqst].rq_iov = vars->unlink_iov; rqst[num_rqst].rq_nvec = 1; size[0] = 1; /* sizeof __u8 See MS-FSCC section 2.4.11 */ data[0] = &delete_pending[0]; - rc = SMB2_set_info_init(tcon, server, - &rqst[num_rqst], COMPOUND_FID, - COMPOUND_FID, current->tgid, - FILE_DISPOSITION_INFORMATION, - SMB2_O_INFO_FILE, 0, data, size); - if (rc) + if (cfile) { + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], + cfile->fid.persistent_fid, + cfile->fid.volatile_fid, + current->tgid, + FILE_DISPOSITION_INFORMATION, + SMB2_O_INFO_FILE, 0, + data, size); + } else { + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], + COMPOUND_FID, + COMPOUND_FID, + current->tgid, + FILE_DISPOSITION_INFORMATION, + SMB2_O_INFO_FILE, 0, + data, size); + } + if (!rc && (!cfile || num_rqst > 1)) { + smb2_set_next_command(tcon, &rqst[num_rqst]); + smb2_set_related(&rqst[num_rqst]); + } else if (rc) { goto finished; - smb2_set_next_command(tcon, &rqst[num_rqst]); - smb2_set_related(&rqst[num_rqst++]); - trace_smb3_rmdir_enter(xid, tcon->tid, ses->Suid, full_path); + } + num_rqst++; + trace_smb3_unlink_enter(xid, tcon->tid, ses->Suid, full_path); break; case SMB2_OP_SET_EOF: rqst[num_rqst].rq_iov = &vars->si_iov[0]; @@ -442,7 +456,7 @@ replay_again: ses->Suid, full_path); break; case SMB2_OP_RENAME: - rqst[num_rqst].rq_iov = &vars->si_iov[0]; + rqst[num_rqst].rq_iov = vars->rename_iov; rqst[num_rqst].rq_nvec = 2; len = in_iov[i].iov_len; @@ -732,19 +746,6 @@ finished: trace_smb3_posix_query_info_compound_done(xid, tcon->tid, ses->Suid); break; - case SMB2_OP_DELETE: - if (rc) - trace_smb3_delete_err(xid, tcon->tid, ses->Suid, rc); - else { - /* - * If dentry (hence, inode) is NULL, lease break is going to - * take care of degrading leases on handles for deleted files. - */ - if (inode) - cifs_mark_open_handles_for_deleted_file(inode, full_path); - trace_smb3_delete_done(xid, tcon->tid, ses->Suid); - } - break; case SMB2_OP_MKDIR: if (rc) trace_smb3_mkdir_err(xid, tcon->tid, ses->Suid, rc); @@ -765,11 +766,11 @@ finished: trace_smb3_rename_done(xid, tcon->tid, ses->Suid); SMB2_set_info_free(&rqst[num_rqst++]); break; - case SMB2_OP_RMDIR: - if (rc) - trace_smb3_rmdir_err(xid, tcon->tid, ses->Suid, rc); + case SMB2_OP_UNLINK: + if (!rc) + trace_smb3_unlink_done(xid, tcon->tid, ses->Suid); else - trace_smb3_rmdir_done(xid, tcon->tid, ses->Suid); + trace_smb3_unlink_err(xid, tcon->tid, ses->Suid, rc); SMB2_set_info_free(&rqst[num_rqst++]); break; case SMB2_OP_SET_EOF: @@ -1166,7 +1167,7 @@ smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name, FILE_OPEN, CREATE_NOT_FILE, ACL_NO_MODE); return smb2_compound_op(xid, tcon, cifs_sb, name, &oparms, NULL, - &(int){SMB2_OP_RMDIR}, 1, + &(int){SMB2_OP_UNLINK}, 1, NULL, NULL, NULL, NULL); } @@ -1175,20 +1176,29 @@ smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name, struct cifs_sb_info *cifs_sb, struct dentry *dentry) { struct cifs_open_parms oparms; + struct inode *inode = NULL; + int rc; - oparms = CIFS_OPARMS(cifs_sb, tcon, name, - DELETE, FILE_OPEN, - CREATE_DELETE_ON_CLOSE | OPEN_REPARSE_POINT, - ACL_NO_MODE); - int rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms, - NULL, &(int){SMB2_OP_DELETE}, 1, - NULL, NULL, NULL, dentry); + if (dentry) + inode = d_inode(dentry); + + oparms = CIFS_OPARMS(cifs_sb, tcon, name, DELETE, + FILE_OPEN, OPEN_REPARSE_POINT, ACL_NO_MODE); + rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms, + NULL, &(int){SMB2_OP_UNLINK}, + 1, NULL, NULL, NULL, dentry); if (rc == -EINVAL) { cifs_dbg(FYI, "invalid lease key, resending request without lease"); rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms, - NULL, &(int){SMB2_OP_DELETE}, 1, - NULL, NULL, NULL, NULL); + NULL, &(int){SMB2_OP_UNLINK}, + 1, NULL, NULL, NULL, NULL); } + /* + * If dentry (hence, inode) is NULL, lease break is going to + * take care of degrading leases on handles for deleted files. + */ + if (!rc && inode) + cifs_mark_open_handles_for_deleted_file(inode, name); return rc; } @@ -1441,3 +1451,113 @@ out: cifs_free_open_info(&data); return rc; } + +static inline __le16 *utf16_smb2_path(struct cifs_sb_info *cifs_sb, + const char *name, size_t namelen) +{ + int len; + + if (*name == '\\' || + (cifs_sb_master_tlink(cifs_sb) && + cifs_sb_master_tcon(cifs_sb)->posix_extensions && *name == '/')) + name++; + return cifs_strndup_to_utf16(name, namelen, &len, + cifs_sb->local_nls, + cifs_remap(cifs_sb)); +} + +int smb2_rename_pending_delete(const char *full_path, + struct dentry *dentry, + const unsigned int xid) +{ + struct cifs_sb_info *cifs_sb = CIFS_SB(d_inode(dentry)->i_sb); + struct cifsInodeInfo *cinode = CIFS_I(d_inode(dentry)); + __le16 *utf16_path __free(kfree) = NULL; + __u32 co = file_create_options(dentry); + int cmds[] = { + SMB2_OP_SET_INFO, + SMB2_OP_RENAME, + SMB2_OP_UNLINK, + }; + const int num_cmds = ARRAY_SIZE(cmds); + char *to_name __free(kfree) = NULL; + __u32 attrs = cinode->cifsAttrs; + struct cifs_open_parms oparms; + static atomic_t sillycounter; + struct cifsFileInfo *cfile; + struct tcon_link *tlink; + struct cifs_tcon *tcon; + struct kvec iov[2]; + const char *ppath; + void *page; + size_t len; + int rc; + + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + tcon = tlink_tcon(tlink); + + page = alloc_dentry_path(); + + ppath = build_path_from_dentry(dentry->d_parent, page); + if (IS_ERR(ppath)) { + rc = PTR_ERR(ppath); + goto out; + } + + len = strlen(ppath) + strlen("/.__smb1234") + 1; + to_name = kmalloc(len, GFP_KERNEL); + if (!to_name) { + rc = -ENOMEM; + goto out; + } + + scnprintf(to_name, len, "%s%c.__smb%04X", ppath, CIFS_DIR_SEP(cifs_sb), + atomic_inc_return(&sillycounter) & 0xffff); + + utf16_path = utf16_smb2_path(cifs_sb, to_name, len); + if (!utf16_path) { + rc = -ENOMEM; + goto out; + } + + drop_cached_dir_by_name(xid, tcon, full_path, cifs_sb); + oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, + DELETE | FILE_WRITE_ATTRIBUTES, + FILE_OPEN, co, ACL_NO_MODE); + + attrs &= ~ATTR_READONLY; + if (!attrs) + attrs = ATTR_NORMAL; + if (d_inode(dentry)->i_nlink <= 1) + attrs |= ATTR_HIDDEN; + iov[0].iov_base = &(FILE_BASIC_INFO) { + .Attributes = cpu_to_le32(attrs), + }; + iov[0].iov_len = sizeof(FILE_BASIC_INFO); + iov[1].iov_base = utf16_path; + iov[1].iov_len = sizeof(*utf16_path) * UniStrlen((wchar_t *)utf16_path); + + cifs_get_writable_path(tcon, full_path, FIND_WR_WITH_DELETE, &cfile); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov, + cmds, num_cmds, cfile, NULL, NULL, dentry); + if (rc == -EINVAL) { + cifs_dbg(FYI, "invalid lease key, resending request without lease\n"); + cifs_get_writable_path(tcon, full_path, + FIND_WR_WITH_DELETE, &cfile); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov, + cmds, num_cmds, cfile, NULL, NULL, NULL); + } + if (!rc) { + set_bit(CIFS_INO_DELETE_PENDING, &cinode->flags); + } else { + cifs_tcon_dbg(FYI, "%s: failed to rename '%s' to '%s': %d\n", + __func__, full_path, to_name, rc); + rc = -EIO; + } +out: + cifs_put_tlink(tlink); + free_dentry_path(page); + return rc; +} diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 94b1d7a395d5..e586f3f4b5c9 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -2640,13 +2640,35 @@ smb2_set_next_command(struct cifs_tcon *tcon, struct smb_rqst *rqst) } /* SMB headers in a compound are 8 byte aligned. */ - if (!IS_ALIGNED(len, 8)) { - num_padding = 8 - (len & 7); + if (IS_ALIGNED(len, 8)) + goto out; + + num_padding = 8 - (len & 7); + if (smb3_encryption_required(tcon)) { + int i; + + /* + * Flatten request into a single buffer with required padding as + * the encryption layer can't handle the padding iovs. + */ + for (i = 1; i < rqst->rq_nvec; i++) { + memcpy(rqst->rq_iov[0].iov_base + + rqst->rq_iov[0].iov_len, + rqst->rq_iov[i].iov_base, + rqst->rq_iov[i].iov_len); + rqst->rq_iov[0].iov_len += rqst->rq_iov[i].iov_len; + } + memset(rqst->rq_iov[0].iov_base + rqst->rq_iov[0].iov_len, + 0, num_padding); + rqst->rq_iov[0].iov_len += num_padding; + rqst->rq_nvec = 1; + } else { rqst->rq_iov[rqst->rq_nvec].iov_base = smb2_padding; rqst->rq_iov[rqst->rq_nvec].iov_len = num_padding; rqst->rq_nvec++; - len += num_padding; } + len += num_padding; +out: shdr->NextCommand = cpu_to_le32(len); } @@ -5376,6 +5398,7 @@ struct smb_version_operations smb20_operations = { .llseek = smb3_llseek, .is_status_io_timeout = smb2_is_status_io_timeout, .is_network_name_deleted = smb2_is_network_name_deleted, + .rename_pending_delete = smb2_rename_pending_delete, }; #endif /* CIFS_ALLOW_INSECURE_LEGACY */ @@ -5481,6 +5504,7 @@ struct smb_version_operations smb21_operations = { .llseek = smb3_llseek, .is_status_io_timeout = smb2_is_status_io_timeout, .is_network_name_deleted = smb2_is_network_name_deleted, + .rename_pending_delete = smb2_rename_pending_delete, }; struct smb_version_operations smb30_operations = { @@ -5597,6 +5621,7 @@ struct smb_version_operations smb30_operations = { .llseek = smb3_llseek, .is_status_io_timeout = smb2_is_status_io_timeout, .is_network_name_deleted = smb2_is_network_name_deleted, + .rename_pending_delete = smb2_rename_pending_delete, }; struct smb_version_operations smb311_operations = { @@ -5713,6 +5738,7 @@ struct smb_version_operations smb311_operations = { .llseek = smb3_llseek, .is_status_io_timeout = smb2_is_status_io_timeout, .is_network_name_deleted = smb2_is_network_name_deleted, + .rename_pending_delete = smb2_rename_pending_delete, }; #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index 6e805ece6a7b..b3f1398c9f79 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -317,5 +317,8 @@ int posix_info_sid_size(const void *beg, const void *end); int smb2_make_nfs_node(unsigned int xid, struct inode *inode, struct dentry *dentry, struct cifs_tcon *tcon, const char *full_path, umode_t mode, dev_t dev); +int smb2_rename_pending_delete(const char *full_path, + struct dentry *dentry, + const unsigned int xid); #endif /* _SMB2PROTO_H */ diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 02d6db431fd4..e0fce5033004 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -453,9 +453,12 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) struct smbdirect_recv_io *response = container_of(wc->wr_cqe, struct smbdirect_recv_io, cqe); struct smbdirect_socket *sc = response->socket; + struct smbdirect_socket_parameters *sp = &sc->parameters; struct smbd_connection *info = container_of(sc, struct smbd_connection, socket); - int data_length = 0; + u32 data_offset = 0; + u32 data_length = 0; + u32 remaining_data_length = 0; log_rdma_recv(INFO, "response=0x%p type=%d wc status=%d wc opcode %d byte_len=%d pkey_index=%u\n", response, sc->recv_io.expected, wc->status, wc->opcode, @@ -487,7 +490,22 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) /* SMBD data transfer packet */ case SMBDIRECT_EXPECT_DATA_TRANSFER: data_transfer = smbdirect_recv_io_payload(response); + + if (wc->byte_len < + offsetof(struct smbdirect_data_transfer, padding)) + goto error; + + remaining_data_length = le32_to_cpu(data_transfer->remaining_data_length); + data_offset = le32_to_cpu(data_transfer->data_offset); data_length = le32_to_cpu(data_transfer->data_length); + if (wc->byte_len < data_offset || + (u64)wc->byte_len < (u64)data_offset + data_length) + goto error; + + if (remaining_data_length > sp->max_fragmented_recv_size || + data_length > sp->max_fragmented_recv_size || + (u64)remaining_data_length + (u64)data_length > (u64)sp->max_fragmented_recv_size) + goto error; if (data_length) { if (sc->recv_io.reassembly.full_packet_received) @@ -1090,8 +1108,10 @@ static int smbd_negotiate(struct smbd_connection *info) log_rdma_event(INFO, "smbd_post_recv rc=%d iov.addr=0x%llx iov.length=%u iov.lkey=0x%x\n", rc, response->sge.addr, response->sge.length, response->sge.lkey); - if (rc) + if (rc) { + put_receive_buffer(info, response); return rc; + } init_completion(&info->negotiate_completion); info->negotiate_done = false; @@ -1329,13 +1349,16 @@ void smbd_destroy(struct TCP_Server_Info *server) sc->status == SMBDIRECT_SOCKET_DISCONNECTED); } + log_rdma_event(INFO, "cancelling post_send_credits_work\n"); + disable_work_sync(&info->post_send_credits_work); + log_rdma_event(INFO, "destroying qp\n"); ib_drain_qp(sc->ib.qp); rdma_destroy_qp(sc->rdma.cm_id); sc->ib.qp = NULL; log_rdma_event(INFO, "cancelling idle timer\n"); - cancel_delayed_work_sync(&info->idle_timer_work); + disable_delayed_work_sync(&info->idle_timer_work); /* It's not possible for upper layer to get to reassembly */ log_rdma_event(INFO, "drain the reassembly queue\n"); @@ -1708,7 +1731,7 @@ allocate_mr_failed: return NULL; negotiation_failed: - cancel_delayed_work_sync(&info->idle_timer_work); + disable_delayed_work_sync(&info->idle_timer_work); destroy_caches_and_workqueue(info); sc->status = SMBDIRECT_SOCKET_NEGOTIATE_FAILED; rdma_disconnect(sc->rdma.cm_id); @@ -2067,7 +2090,7 @@ static void destroy_mr_list(struct smbd_connection *info) struct smbdirect_socket *sc = &info->socket; struct smbd_mr *mr, *tmp; - cancel_work_sync(&info->mr_recovery_work); + disable_work_sync(&info->mr_recovery_work); list_for_each_entry_safe(mr, tmp, &info->mr_list, list) { if (mr->state == MR_INVALIDATED) ib_dma_unmap_sg(sc->ib.dev, mr->sgt.sgl, diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index fe0e075bc63c..fd650e2afc76 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -669,13 +669,12 @@ DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(query_info_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(posix_query_info_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(hardlink_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(rename_enter); -DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(rmdir_enter); +DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(unlink_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_eof_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_info_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_reparse_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(get_reparse_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(query_wsl_ea_compound_enter); -DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(delete_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(mkdir_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(tdis_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(mknod_enter); @@ -710,13 +709,12 @@ DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(query_info_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(posix_query_info_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(hardlink_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(rename_done); -DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(rmdir_done); +DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(unlink_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_eof_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_info_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_reparse_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(get_reparse_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(query_wsl_ea_compound_done); -DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(delete_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(mkdir_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(tdis_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(mknod_done); @@ -756,14 +754,13 @@ DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(query_info_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(posix_query_info_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(hardlink_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(rename_err); -DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(rmdir_err); +DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(unlink_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_eof_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_info_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_reparse_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(get_reparse_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(query_wsl_ea_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(mkdir_err); -DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(delete_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(tdis_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(mknod_err); diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 5466aa8c39b1..6550bd9f002c 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -554,7 +554,7 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) case SMB_DIRECT_MSG_DATA_TRANSFER: { struct smb_direct_data_transfer *data_transfer = (struct smb_direct_data_transfer *)recvmsg->packet; - unsigned int data_length; + u32 remaining_data_length, data_offset, data_length; int avail_recvmsg_count, receive_credits; if (wc->byte_len < @@ -564,15 +564,25 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) return; } + remaining_data_length = le32_to_cpu(data_transfer->remaining_data_length); data_length = le32_to_cpu(data_transfer->data_length); - if (data_length) { - if (wc->byte_len < sizeof(struct smb_direct_data_transfer) + - (u64)data_length) { - put_recvmsg(t, recvmsg); - smb_direct_disconnect_rdma_connection(t); - return; - } + data_offset = le32_to_cpu(data_transfer->data_offset); + if (wc->byte_len < data_offset || + wc->byte_len < (u64)data_offset + data_length) { + put_recvmsg(t, recvmsg); + smb_direct_disconnect_rdma_connection(t); + return; + } + if (remaining_data_length > t->max_fragmented_recv_size || + data_length > t->max_fragmented_recv_size || + (u64)remaining_data_length + (u64)data_length > + (u64)t->max_fragmented_recv_size) { + put_recvmsg(t, recvmsg); + smb_direct_disconnect_rdma_connection(t); + return; + } + if (data_length) { if (t->full_packet_received) recvmsg->first_segment = true; @@ -1209,78 +1219,130 @@ static int smb_direct_writev(struct ksmbd_transport *t, bool need_invalidate, unsigned int remote_key) { struct smb_direct_transport *st = smb_trans_direct_transfort(t); - int remaining_data_length; - int start, i, j; - int max_iov_size = st->max_send_size - + size_t remaining_data_length; + size_t iov_idx; + size_t iov_ofs; + size_t max_iov_size = st->max_send_size - sizeof(struct smb_direct_data_transfer); int ret; - struct kvec vec; struct smb_direct_send_ctx send_ctx; + int error = 0; if (st->status != SMB_DIRECT_CS_CONNECTED) return -ENOTCONN; //FIXME: skip RFC1002 header.. + if (WARN_ON_ONCE(niovs <= 1 || iov[0].iov_len != 4)) + return -EINVAL; buflen -= 4; + iov_idx = 1; + iov_ofs = 0; remaining_data_length = buflen; ksmbd_debug(RDMA, "Sending smb (RDMA): smb_len=%u\n", buflen); smb_direct_send_ctx_init(st, &send_ctx, need_invalidate, remote_key); - start = i = 1; - buflen = 0; - while (true) { - buflen += iov[i].iov_len; - if (buflen > max_iov_size) { - if (i > start) { - remaining_data_length -= - (buflen - iov[i].iov_len); - ret = smb_direct_post_send_data(st, &send_ctx, - &iov[start], i - start, - remaining_data_length); - if (ret) + while (remaining_data_length) { + struct kvec vecs[SMB_DIRECT_MAX_SEND_SGES - 1]; /* minus smbdirect hdr */ + size_t possible_bytes = max_iov_size; + size_t possible_vecs; + size_t bytes = 0; + size_t nvecs = 0; + + /* + * For the last message remaining_data_length should be + * have been 0 already! + */ + if (WARN_ON_ONCE(iov_idx >= niovs)) { + error = -EINVAL; + goto done; + } + + /* + * We have 2 factors which limit the arguments we pass + * to smb_direct_post_send_data(): + * + * 1. The number of supported sges for the send, + * while one is reserved for the smbdirect header. + * And we currently need one SGE per page. + * 2. The number of negotiated payload bytes per send. + */ + possible_vecs = min_t(size_t, ARRAY_SIZE(vecs), niovs - iov_idx); + + while (iov_idx < niovs && possible_vecs && possible_bytes) { + struct kvec *v = &vecs[nvecs]; + int page_count; + + v->iov_base = ((u8 *)iov[iov_idx].iov_base) + iov_ofs; + v->iov_len = min_t(size_t, + iov[iov_idx].iov_len - iov_ofs, + possible_bytes); + page_count = get_buf_page_count(v->iov_base, v->iov_len); + if (page_count > possible_vecs) { + /* + * If the number of pages in the buffer + * is to much (because we currently require + * one SGE per page), we need to limit the + * length. + * + * We know possible_vecs is at least 1, + * so we always keep the first page. + * + * We need to calculate the number extra + * pages (epages) we can also keep. + * + * We calculate the number of bytes in the + * first page (fplen), this should never be + * larger than v->iov_len because page_count is + * at least 2, but adding a limitation feels + * better. + * + * Then we calculate the number of bytes (elen) + * we can keep for the extra pages. + */ + size_t epages = possible_vecs - 1; + size_t fpofs = offset_in_page(v->iov_base); + size_t fplen = min_t(size_t, PAGE_SIZE - fpofs, v->iov_len); + size_t elen = min_t(size_t, v->iov_len - fplen, epages*PAGE_SIZE); + + v->iov_len = fplen + elen; + page_count = get_buf_page_count(v->iov_base, v->iov_len); + if (WARN_ON_ONCE(page_count > possible_vecs)) { + /* + * Something went wrong in the above + * logic... + */ + error = -EINVAL; goto done; - } else { - /* iov[start] is too big, break it */ - int nvec = (buflen + max_iov_size - 1) / - max_iov_size; - - for (j = 0; j < nvec; j++) { - vec.iov_base = - (char *)iov[start].iov_base + - j * max_iov_size; - vec.iov_len = - min_t(int, max_iov_size, - buflen - max_iov_size * j); - remaining_data_length -= vec.iov_len; - ret = smb_direct_post_send_data(st, &send_ctx, &vec, 1, - remaining_data_length); - if (ret) - goto done; } - i++; - if (i == niovs) - break; } - start = i; - buflen = 0; - } else { - i++; - if (i == niovs) { - /* send out all remaining vecs */ - remaining_data_length -= buflen; - ret = smb_direct_post_send_data(st, &send_ctx, - &iov[start], i - start, - remaining_data_length); - if (ret) - goto done; - break; + possible_vecs -= page_count; + nvecs += 1; + possible_bytes -= v->iov_len; + bytes += v->iov_len; + + iov_ofs += v->iov_len; + if (iov_ofs >= iov[iov_idx].iov_len) { + iov_idx += 1; + iov_ofs = 0; } } + + remaining_data_length -= bytes; + + ret = smb_direct_post_send_data(st, &send_ctx, + vecs, nvecs, + remaining_data_length); + if (unlikely(ret)) { + error = ret; + goto done; + } } done: ret = smb_direct_flush_send_list(st, &send_ctx, true); + if (unlikely(!ret && error)) + ret = error; /* * As an optimization, we don't wait for individual I/O to finish @@ -1744,6 +1806,11 @@ static int smb_direct_init_params(struct smb_direct_transport *t, return -EINVAL; } + if (device->attrs.max_send_sge < SMB_DIRECT_MAX_SEND_SGES) { + pr_err("warning: device max_send_sge = %d too small\n", + device->attrs.max_send_sge); + return -EINVAL; + } if (device->attrs.max_recv_sge < SMB_DIRECT_MAX_RECV_SGES) { pr_err("warning: device max_recv_sge = %d too small\n", device->attrs.max_recv_sge); @@ -1767,7 +1834,7 @@ static int smb_direct_init_params(struct smb_direct_transport *t, cap->max_send_wr = max_send_wrs; cap->max_recv_wr = t->recv_credit_max; - cap->max_send_sge = max_sge_per_wr; + cap->max_send_sge = SMB_DIRECT_MAX_SEND_SGES; cap->max_recv_sge = SMB_DIRECT_MAX_RECV_SGES; cap->max_inline_data = 0; cap->max_rdma_ctxs = t->max_rw_credits; diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index f7b3b93f3a49..0c70f3a55575 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -135,6 +135,7 @@ struct af_alg_async_req { * SG? * @enc: Cryptographic operation to be performed when * recvmsg is invoked. + * @write: True if we are in the middle of a write. * @init: True if metadata has been sent. * @len: Length of memory allocated for this data structure. * @inflight: Non-zero when AIO requests are in flight. @@ -151,10 +152,11 @@ struct af_alg_ctx { size_t used; atomic_t rcvused; - bool more; - bool merge; - bool enc; - bool init; + u32 more:1, + merge:1, + enc:1, + write:1, + init:1; unsigned int len; diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 404883c7af6e..4000ff16f295 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -8,8 +8,8 @@ #include <linux/bits.h> #include <linux/kvm.h> #include <linux/irqreturn.h> -#include <linux/kref.h> #include <linux/mutex.h> +#include <linux/refcount.h> #include <linux/spinlock.h> #include <linux/static_key.h> #include <linux/types.h> @@ -139,10 +139,13 @@ struct vgic_irq { bool pending_latch; /* The pending latch state used to calculate * the pending state for both level * and edge triggered IRQs. */ - bool active; /* not used for LPIs */ + bool active; + bool pending_release; /* Used for LPIs only, unreferenced IRQ + * pending a release */ + bool enabled; bool hw; /* Tied to HW IRQ */ - struct kref refcount; /* Used for LPIs */ + refcount_t refcount; /* Used for LPIs */ u32 hwintid; /* HW INTID number */ unsigned int host_irq; /* linux irq corresponding to hwintid */ union { diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index fa4ffe037bc7..8720a0705900 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -18,23 +18,42 @@ #define KASAN_ABI_VERSION 5 /* + * Clang 22 added preprocessor macros to match GCC, in hopes of eventually + * dropping __has_feature support for sanitizers: + * https://github.com/llvm/llvm-project/commit/568c23bbd3303518c5056d7f03444dae4fdc8a9c + * Create these macros for older versions of clang so that it is easy to clean + * up once the minimum supported version of LLVM for building the kernel always + * creates these macros. + * * Note: Checking __has_feature(*_sanitizer) is only true if the feature is * enabled. Therefore it is not required to additionally check defined(CONFIG_*) * to avoid adding redundant attributes in other configurations. */ +#if __has_feature(address_sanitizer) && !defined(__SANITIZE_ADDRESS__) +#define __SANITIZE_ADDRESS__ +#endif +#if __has_feature(hwaddress_sanitizer) && !defined(__SANITIZE_HWADDRESS__) +#define __SANITIZE_HWADDRESS__ +#endif +#if __has_feature(thread_sanitizer) && !defined(__SANITIZE_THREAD__) +#define __SANITIZE_THREAD__ +#endif -#if __has_feature(address_sanitizer) || __has_feature(hwaddress_sanitizer) -/* Emulate GCC's __SANITIZE_ADDRESS__ flag */ +/* + * Treat __SANITIZE_HWADDRESS__ the same as __SANITIZE_ADDRESS__ in the kernel. + */ +#ifdef __SANITIZE_HWADDRESS__ #define __SANITIZE_ADDRESS__ +#endif + +#ifdef __SANITIZE_ADDRESS__ #define __no_sanitize_address \ __attribute__((no_sanitize("address", "hwaddress"))) #else #define __no_sanitize_address #endif -#if __has_feature(thread_sanitizer) -/* emulate gcc's __SANITIZE_THREAD__ flag */ -#define __SANITIZE_THREAD__ +#ifdef __SANITIZE_THREAD__ #define __no_sanitize_thread \ __attribute__((no_sanitize("thread"))) #else diff --git a/include/linux/cpu.h b/include/linux/cpu.h index b91b993f58ee..487b3bf2e1ea 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -83,6 +83,7 @@ extern ssize_t cpu_show_old_microcode(struct device *dev, extern ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_vmscape(struct device *dev, struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/damon.h b/include/linux/damon.h index f13664c62ddd..9e62b2a85538 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -636,6 +636,7 @@ struct damon_operations { * @data: Data that will be passed to @fn. * @repeat: Repeat invocations. * @return_code: Return code from @fn invocation. + * @dealloc_on_cancel: De-allocate when canceled. * * Control damon_call(), which requests specific kdamond to invoke a given * function. Refer to damon_call() for more details. @@ -645,6 +646,7 @@ struct damon_call_control { void *data; bool repeat; int return_code; + bool dealloc_on_cancel; /* private: internal use only */ /* informs if the kdamond finished handling of the request */ struct completion completion; diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 7fa1eb3cc823..61d50571ad88 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -171,6 +171,9 @@ int em_dev_update_perf_domain(struct device *dev, int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, const struct em_data_callback *cb, const cpumask_t *cpus, bool microwatts); +int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states, + const struct em_data_callback *cb, + const cpumask_t *cpus, bool microwatts); void em_dev_unregister_perf_domain(struct device *dev); struct em_perf_table *em_table_alloc(struct em_perf_domain *pd); void em_table_free(struct em_perf_table *table); @@ -350,6 +353,13 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, { return -EINVAL; } +static inline +int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states, + const struct em_data_callback *cb, + const cpumask_t *cpus, bool microwatts) +{ + return -EINVAL; +} static inline void em_dev_unregister_perf_domain(struct device *dev) { } diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index de5bd76a400c..d7d757e72554 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -856,8 +856,8 @@ struct kernel_ethtool_ts_info { enum hwtstamp_provider_qualifier phc_qualifier; enum hwtstamp_source phc_source; int phc_phyindex; - enum hwtstamp_tx_types tx_types; - enum hwtstamp_rx_filters rx_filters; + u32 tx_types; + u32 rx_filters; }; /** diff --git a/include/linux/fs.h b/include/linux/fs.h index d7ab4f96d705..601d036a6c78 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -149,7 +149,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)(1 << 12)) -/* FMODE_* bit 13 */ +/* Supports IOCB_HAS_METADATA */ +#define FMODE_HAS_METADATA ((__force fmode_t)(1 << 13)) /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)(1 << 14)) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 80a178f3d896..12f5ee43850e 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -420,9 +420,6 @@ struct io_ring_ctx { struct list_head defer_list; unsigned nr_drained; - struct io_alloc_cache msg_cache; - spinlock_t msg_lock; - #ifdef CONFIG_NET_RX_BUSY_POLL struct list_head napi_list; /* track busy poll napi_id */ spinlock_t napi_lock; /* napi_list lock */ diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 890011071f2b..fe5ce9215821 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -562,7 +562,7 @@ static inline void kasan_init_hw_tags(void) { } #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); -int kasan_populate_vmalloc(unsigned long addr, unsigned long size); +int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask); void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end, @@ -574,7 +574,7 @@ static inline void kasan_populate_early_vm_area_shadow(void *start, unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, - unsigned long size) + unsigned long size, gfp_t gfp_mask) { return 0; } @@ -610,7 +610,7 @@ static __always_inline void kasan_poison_vmalloc(const void *start, static inline void kasan_populate_early_vm_area_shadow(void *start, unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, - unsigned long size) + unsigned long size, gfp_t gfp_mask) { return 0; } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8c5fbfb85749..10fe492e1fed 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -663,6 +663,7 @@ struct mlx5e_resources { bool tisn_valid; } hw_objs; struct net_device *uplink_netdev; + netdevice_tracker tracker; struct mutex uplink_netdev_lock; struct mlx5_crypto_dek_priv *dek_priv; }; diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index c84edf217819..f67a2cb7d781 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -115,6 +115,12 @@ struct dev_pm_domain_list { * genpd provider specific way, likely through a * parent device node. This flag makes genpd to * skip its internal support for this. + * + * GENPD_FLAG_NO_STAY_ON: For genpd OF providers a powered-on PM domain at + * initialization is prevented from being + * powered-off until the ->sync_state() callback is + * invoked. This flag informs genpd to allow a + * power-off without waiting for ->sync_state(). */ #define GENPD_FLAG_PM_CLK (1U << 0) #define GENPD_FLAG_IRQ_SAFE (1U << 1) @@ -126,6 +132,7 @@ struct dev_pm_domain_list { #define GENPD_FLAG_OPP_TABLE_FW (1U << 7) #define GENPD_FLAG_DEV_NAME_FW (1U << 8) #define GENPD_FLAG_NO_SYNC_STATE (1U << 9) +#define GENPD_FLAG_NO_STAY_ON (1U << 10) enum gpd_status { GENPD_STATE_ON = 0, /* PM domain is on */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 2fe6ed2cc3fd..7012a0f758d8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -385,6 +385,16 @@ void folio_add_lru_vma(struct folio *, struct vm_area_struct *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); +static inline bool folio_may_be_lru_cached(struct folio *folio) +{ + /* + * Holding PMD-sized folios in per-CPU LRU cache unbalances accounting. + * Holding small numbers of low-order mTHP folios in per-CPU LRU cache + * will be sensible, but nobody has implemented and tested that yet. + */ + return !folio_test_large(folio); +} + extern atomic_t lru_disable_count; static inline bool lru_cache_disabled(void) diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 4160731dcb6e..1fc2fb03ce3f 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -3,6 +3,7 @@ #define __NET_DST_METADATA_H 1 #include <linux/skbuff.h> +#include <net/ip.h> #include <net/ip_tunnels.h> #include <net/macsec.h> #include <net/dst.h> @@ -220,9 +221,15 @@ static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, int md_size) { const struct iphdr *iph = ip_hdr(skb); + struct metadata_dst *tun_dst; + + tun_dst = __ip_tun_set_dst(iph->saddr, iph->daddr, iph->tos, iph->ttl, + 0, flags, tunnel_id, md_size); - return __ip_tun_set_dst(iph->saddr, iph->daddr, iph->tos, iph->ttl, - 0, flags, tunnel_id, md_size); + if (tun_dst && (iph->frag_off & htons(IP_DF))) + __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, + tun_dst->u.tun_info.key.tun_flags); + return tun_dst; } static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *saddr, diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 891e43a01bdc..3faa80f5d801 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1912,7 +1912,6 @@ struct nftables_pernet { struct mutex commit_mutex; u64 table_handle; u64 tstamp; - unsigned int base_seq; unsigned int gc_seq; u8 validate_state; struct work_struct destroy_work; diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 6c2f483d9828..656e784714f3 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -109,17 +109,11 @@ nft_hash_lookup_fast(const struct net *net, const struct nft_set *set, const struct nft_set_ext * nft_hash_lookup(const struct net *net, const struct nft_set *set, const u32 *key); +#endif + const struct nft_set_ext * nft_set_do_lookup(const struct net *net, const struct nft_set *set, const u32 *key); -#else -static inline const struct nft_set_ext * -nft_set_do_lookup(const struct net *net, const struct nft_set *set, - const u32 *key) -{ - return set->ops->lookup(net, set, key); -} -#endif /* called from nft_pipapo_avx2.c */ const struct nft_set_ext * diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index cc8060c017d5..99dd166c5d07 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -3,6 +3,7 @@ #define _NETNS_NFTABLES_H_ struct netns_nftables { + unsigned int base_seq; u8 gencursor; }; diff --git a/include/net/sock.h b/include/net/sock.h index fb13322a11fc..2e14283c5be1 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2061,6 +2061,9 @@ static inline void sk_set_socket(struct sock *sk, struct socket *sock) if (sock) { WRITE_ONCE(sk->sk_uid, SOCK_INODE(sock)->i_uid); WRITE_ONCE(sk->sk_ino, SOCK_INODE(sock)->i_ino); + } else { + /* Note: sk_uid is unchanged. */ + WRITE_ONCE(sk->sk_ino, 0); } } @@ -2082,8 +2085,6 @@ static inline void sock_orphan(struct sock *sk) sock_set_flag(sk, SOCK_DEAD); sk_set_socket(sk, NULL); sk->sk_wq = NULL; - /* Note: sk_uid is unchanged. */ - WRITE_ONCE(sk->sk_ino, 0); write_unlock_bh(&sk->sk_callback_lock); } diff --git a/include/sound/sdca.h b/include/sound/sdca.h index 5a5d6de78d72..9c6a351c9d47 100644 --- a/include/sound/sdca.h +++ b/include/sound/sdca.h @@ -46,6 +46,7 @@ struct sdca_device_data { enum sdca_quirk { SDCA_QUIRKS_RT712_VB, + SDCA_QUIRKS_SKIP_FUNC_TYPE_PATCHING, }; #if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_SND_SOC_SDCA) diff --git a/include/sound/sdca_function.h b/include/sound/sdca_function.h index 06ec126cdcc3..ea68856e4c8c 100644 --- a/include/sound/sdca_function.h +++ b/include/sound/sdca_function.h @@ -1063,27 +1063,30 @@ struct sdca_entity_ge { /** * struct sdca_entity_hide - information specific to HIDE Entities * @hid: HID device structure - * @hidtx_ids: HIDTx Report ID * @num_hidtx_ids: number of HIDTx Report ID - * @hidrx_ids: HIDRx Report ID * @num_hidrx_ids: number of HIDRx Report ID - * @hide_reside_function_num: indicating which Audio Function Numbers within this Device - * @max_delay: the maximum time in microseconds allowed for the Device to change the ownership from Device to Host - * @af_number_list: which Audio Function Numbers within this Device are sending/receiving the messages in this HIDE - * @hid_desc: HID descriptor for the HIDE Entity + * @hidtx_ids: HIDTx Report ID + * @hidrx_ids: HIDRx Report ID + * @af_number_list: which Audio Function Numbers within this Device are + * sending/receiving the messages in this HIDE + * @hide_reside_function_num: indicating which Audio Function Numbers + * within this Device + * @max_delay: the maximum time in microseconds allowed for the Device + * to change the ownership from Device to Host * @hid_report_desc: HID Report Descriptor for the HIDE Entity + * @hid_desc: HID descriptor for the HIDE Entity */ struct sdca_entity_hide { struct hid_device *hid; unsigned int *hidtx_ids; - int num_hidtx_ids; unsigned int *hidrx_ids; + int num_hidtx_ids; int num_hidrx_ids; + unsigned int af_number_list[SDCA_MAX_FUNCTION_COUNT]; unsigned int hide_reside_function_num; unsigned int max_delay; - unsigned int af_number_list[SDCA_MAX_FUNCTION_COUNT]; - struct hid_descriptor hid_desc; unsigned char *hid_report_desc; + struct hid_descriptor hid_desc; }; /** diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 67d015df8893..5fd5b4cf75ca 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -31,6 +31,8 @@ #define MPTCP_INFO_FLAG_FALLBACK _BITUL(0) #define MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED _BITUL(1) +#define MPTCP_PM_EV_FLAG_DENY_JOIN_ID0 _BITUL(0) + #define MPTCP_PM_ADDR_FLAG_SIGNAL (1 << 0) #define MPTCP_PM_ADDR_FLAG_SUBFLOW (1 << 1) #define MPTCP_PM_ADDR_FLAG_BACKUP (1 << 2) diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h index 6ac84b2f636c..7359d34da446 100644 --- a/include/uapi/linux/mptcp_pm.h +++ b/include/uapi/linux/mptcp_pm.h @@ -16,10 +16,10 @@ * good time to allocate memory and send ADD_ADDR if needed. Depending on the * traffic-patterns it can take a long time until the MPTCP_EVENT_ESTABLISHED * is sent. Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, server-side. + * sport, dport, server-side, [flags]. * @MPTCP_EVENT_ESTABLISHED: A MPTCP connection is established (can start new * subflows). Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, server-side. + * sport, dport, server-side, [flags]. * @MPTCP_EVENT_CLOSED: A MPTCP connection has stopped. Attribute: token. * @MPTCP_EVENT_ANNOUNCED: A new address has been announced by the peer. * Attributes: token, rem_id, family, daddr4 | daddr6 [, dport]. diff --git a/init/main.c b/init/main.c index 0ee0ee7b7c2c..5753e9539ae6 100644 --- a/init/main.c +++ b/init/main.c @@ -956,6 +956,7 @@ void start_kernel(void) sort_main_extable(); trap_init(); mm_core_init(); + maple_tree_init(); poking_init(); ftrace_init(); @@ -973,7 +974,6 @@ void start_kernel(void) "Interrupts were enabled *very* early, fixing it\n")) local_irq_disable(); radix_tree_init(); - maple_tree_init(); /* * Set up housekeeping before setting up workqueues to allow the unbound diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 17dfaa0395c4..1d03b2fc4b25 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -352,16 +352,16 @@ static void create_worker_cb(struct callback_head *cb) struct io_wq *wq; struct io_wq_acct *acct; - bool do_create = false; + bool activated_free_worker, do_create = false; worker = container_of(cb, struct io_worker, create_work); wq = worker->wq; acct = worker->acct; rcu_read_lock(); - do_create = !io_acct_activate_free_worker(acct); + activated_free_worker = io_acct_activate_free_worker(acct); rcu_read_unlock(); - if (!do_create) + if (activated_free_worker) goto no_need_create; raw_spin_lock(&acct->workers_lock); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 93633613a165..93665cebe9bd 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -290,7 +290,6 @@ static void io_free_alloc_caches(struct io_ring_ctx *ctx) io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free); io_alloc_cache_free(&ctx->rw_cache, io_rw_cache_free); io_alloc_cache_free(&ctx->cmd_cache, io_cmd_cache_free); - io_alloc_cache_free(&ctx->msg_cache, kfree); io_futex_cache_free(ctx); io_rsrc_cache_free(ctx); } @@ -337,9 +336,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) ret |= io_alloc_cache_init(&ctx->cmd_cache, IO_ALLOC_CACHE_MAX, sizeof(struct io_async_cmd), sizeof(struct io_async_cmd)); - spin_lock_init(&ctx->msg_lock); - ret |= io_alloc_cache_init(&ctx->msg_cache, IO_ALLOC_CACHE_MAX, - sizeof(struct io_kiocb), 0); ret |= io_futex_cache_init(ctx); ret |= io_rsrc_cache_init(ctx); if (ret) @@ -1406,8 +1402,10 @@ static void io_req_task_cancel(struct io_kiocb *req, io_tw_token_t tw) void io_req_task_submit(struct io_kiocb *req, io_tw_token_t tw) { - io_tw_lock(req->ctx, tw); - if (unlikely(io_should_terminate_tw())) + struct io_ring_ctx *ctx = req->ctx; + + io_tw_lock(ctx, tw); + if (unlikely(io_should_terminate_tw(ctx))) io_req_defer_failed(req, -EFAULT); else if (req->flags & REQ_F_FORCE_ASYNC) io_queue_iowq(req); diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index abc6de227f74..1880902be6fd 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -476,9 +476,9 @@ static inline bool io_allowed_run_tw(struct io_ring_ctx *ctx) * 2) PF_KTHREAD is set, in which case the invoker of the task_work is * our fallback task_work. */ -static inline bool io_should_terminate_tw(void) +static inline bool io_should_terminate_tw(struct io_ring_ctx *ctx) { - return current->flags & (PF_KTHREAD | PF_EXITING); + return (current->flags & (PF_KTHREAD | PF_EXITING)) || percpu_ref_is_dying(&ctx->refs); } static inline void io_req_queue_tw_complete(struct io_kiocb *req, s32 res) diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index 4c2578f2efcb..5e5b94236d72 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -11,7 +11,6 @@ #include "io_uring.h" #include "rsrc.h" #include "filetable.h" -#include "alloc_cache.h" #include "msg_ring.h" /* All valid masks for MSG_RING */ @@ -76,13 +75,7 @@ static void io_msg_tw_complete(struct io_kiocb *req, io_tw_token_t tw) struct io_ring_ctx *ctx = req->ctx; io_add_aux_cqe(ctx, req->cqe.user_data, req->cqe.res, req->cqe.flags); - if (spin_trylock(&ctx->msg_lock)) { - if (io_alloc_cache_put(&ctx->msg_cache, req)) - req = NULL; - spin_unlock(&ctx->msg_lock); - } - if (req) - kfree_rcu(req, rcu_head); + kfree_rcu(req, rcu_head); percpu_ref_put(&ctx->refs); } @@ -104,26 +97,13 @@ static int io_msg_remote_post(struct io_ring_ctx *ctx, struct io_kiocb *req, return 0; } -static struct io_kiocb *io_msg_get_kiocb(struct io_ring_ctx *ctx) -{ - struct io_kiocb *req = NULL; - - if (spin_trylock(&ctx->msg_lock)) { - req = io_alloc_cache_get(&ctx->msg_cache); - spin_unlock(&ctx->msg_lock); - if (req) - return req; - } - return kmem_cache_alloc(req_cachep, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); -} - static int io_msg_data_remote(struct io_ring_ctx *target_ctx, struct io_msg *msg) { struct io_kiocb *target; u32 flags = 0; - target = io_msg_get_kiocb(target_ctx); + target = kmem_cache_alloc(req_cachep, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO) ; if (unlikely(!target)) return -ENOMEM; diff --git a/io_uring/notif.c b/io_uring/notif.c index 9a6f6e92d742..ea9c0116cec2 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -85,7 +85,7 @@ static int io_link_skb(struct sk_buff *skb, struct ubuf_info *uarg) return -EEXIST; prev_nd = container_of(prev_uarg, struct io_notif_data, uarg); - prev_notif = cmd_to_io_kiocb(nd); + prev_notif = cmd_to_io_kiocb(prev_nd); /* make sure all noifications can be finished in the same task_work */ if (unlikely(notif->ctx != prev_notif->ctx || diff --git a/io_uring/poll.c b/io_uring/poll.c index c786e587563b..6090a26975d4 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -224,7 +224,7 @@ static int io_poll_check_events(struct io_kiocb *req, io_tw_token_t tw) { int v; - if (unlikely(io_should_terminate_tw())) + if (unlikely(io_should_terminate_tw(req->ctx))) return -ECANCELED; do { diff --git a/io_uring/rw.c b/io_uring/rw.c index 52a5b950b2e5..af5a54b5db12 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -886,6 +886,9 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type) if (req->flags & REQ_F_HAS_METADATA) { struct io_async_rw *io = req->async_data; + if (!(file->f_mode & FMODE_HAS_METADATA)) + return -EINVAL; + /* * We have a union of meta fields with wpq used for buffered-io * in io_async_rw, so fail it here. diff --git a/io_uring/timeout.c b/io_uring/timeout.c index 7f13bfa9f2b6..17e3aab0af36 100644 --- a/io_uring/timeout.c +++ b/io_uring/timeout.c @@ -324,7 +324,7 @@ static void io_req_task_link_timeout(struct io_kiocb *req, io_tw_token_t tw) int ret; if (prev) { - if (!io_should_terminate_tw()) { + if (!io_should_terminate_tw(req->ctx)) { struct io_cancel_data cd = { .ctx = req->ctx, .data = prev->cqe.user_data, diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 053bac89b6c0..213716e10d70 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -118,7 +118,7 @@ static void io_uring_cmd_work(struct io_kiocb *req, io_tw_token_t tw) struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); unsigned int flags = IO_URING_F_COMPLETE_DEFER; - if (io_should_terminate_tw()) + if (io_should_terminate_tw(req->ctx)) flags |= IO_URING_F_TASK_DEAD; /* task_work executor checks the deffered list completion */ diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 269c04a24664..f6cf8c2af5f7 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -62,3 +62,4 @@ CFLAGS_REMOVE_bpf_lru_list.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_queue_stack_maps.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_lpm_trie.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_ringbuf.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rqspinlock.o = $(CC_FLAGS_FTRACE) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 5d1650af899d..e4568d44e827 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2366,8 +2366,7 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx, const struct bpf_insn *insn) { /* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON - * is not working properly, or interpreter is being used when - * prog->jit_requested is not 0, so warn about it! + * is not working properly, so warn about it! */ WARN_ON_ONCE(1); return 0; @@ -2468,8 +2467,9 @@ out: return ret; } -static void bpf_prog_select_func(struct bpf_prog *fp) +static bool bpf_prog_select_interpreter(struct bpf_prog *fp) { + bool select_interpreter = false; #ifndef CONFIG_BPF_JIT_ALWAYS_ON u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1); u32 idx = (round_up(stack_depth, 32) / 32) - 1; @@ -2478,15 +2478,16 @@ static void bpf_prog_select_func(struct bpf_prog *fp) * But for non-JITed programs, we don't need bpf_func, so no bounds * check needed. */ - if (!fp->jit_requested && - !WARN_ON_ONCE(idx >= ARRAY_SIZE(interpreters))) { + if (idx < ARRAY_SIZE(interpreters)) { fp->bpf_func = interpreters[idx]; + select_interpreter = true; } else { fp->bpf_func = __bpf_prog_ret0_warn; } #else fp->bpf_func = __bpf_prog_ret0_warn; #endif + return select_interpreter; } /** @@ -2505,7 +2506,7 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) /* In case of BPF to BPF calls, verifier did all the prep * work with regards to JITing, etc. */ - bool jit_needed = fp->jit_requested; + bool jit_needed = false; if (fp->bpf_func) goto finalize; @@ -2514,7 +2515,8 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) bpf_prog_has_kfunc_call(fp)) jit_needed = true; - bpf_prog_select_func(fp); + if (!bpf_prog_select_interpreter(fp)) + jit_needed = true; /* eBPF JITs can rewrite the program in case constant * blinding is active. However, in case of error during @@ -3024,7 +3026,10 @@ EXPORT_SYMBOL_GPL(bpf_event_output); /* Always built-in helper functions. */ const struct bpf_func_proto bpf_tail_call_proto = { - .func = NULL, + /* func is unused for tail_call, we set it to pass the + * get_helper_proto check + */ + .func = BPF_PTR_POISON, .gpl_only = false, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_CTX, diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index b2b7b8ec2c2a..c46360b27871 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -186,7 +186,6 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, struct xdp_buff xdp; int i, nframes = 0; - xdp_set_return_frame_no_direct(); xdp.rxq = &rxq; for (i = 0; i < n; i++) { @@ -231,7 +230,6 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, } } - xdp_clear_return_frame_no_direct(); stats->pass += nframes; return nframes; @@ -255,6 +253,7 @@ static void cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, rcu_read_lock(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); + xdp_set_return_frame_no_direct(); ret->xdp_n = cpu_map_bpf_prog_run_xdp(rcpu, frames, ret->xdp_n, stats); if (unlikely(ret->skb_n)) @@ -264,6 +263,7 @@ static void cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, if (stats->redirect) xdp_do_flush(); + xdp_clear_return_frame_no_direct(); bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); diff --git a/kernel/bpf/crypto.c b/kernel/bpf/crypto.c index 94854cd9c4cc..83c4d9943084 100644 --- a/kernel/bpf/crypto.c +++ b/kernel/bpf/crypto.c @@ -278,7 +278,7 @@ static int bpf_crypto_crypt(const struct bpf_crypto_ctx *ctx, siv_len = siv ? __bpf_dynptr_size(siv) : 0; src_len = __bpf_dynptr_size(src); dst_len = __bpf_dynptr_size(dst); - if (!src_len || !dst_len) + if (!src_len || !dst_len || src_len > dst_len) return -EINVAL; if (siv_len != ctx->siv_len) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 6b4877e85a68..8af62cb243d9 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1274,8 +1274,11 @@ static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u goto out; } - /* allocate hrtimer via map_kmalloc to use memcg accounting */ - cb = bpf_map_kmalloc_node(map, size, GFP_ATOMIC, map->numa_node); + /* Allocate via bpf_map_kmalloc_node() for memcg accounting. Until + * kmalloc_nolock() is available, avoid locking issues by using + * __GFP_HIGH (GFP_ATOMIC & ~__GFP_RECLAIM). + */ + cb = bpf_map_kmalloc_node(map, size, __GFP_HIGH, map->numa_node); if (!cb) { ret = -ENOMEM; goto out; @@ -3664,10 +3667,17 @@ __bpf_kfunc int bpf_strnstr(const char *s1__ign, const char *s2__ign, size_t len guard(pagefault)(); for (i = 0; i < XATTR_SIZE_MAX; i++) { - for (j = 0; i + j < len && j < XATTR_SIZE_MAX; j++) { + for (j = 0; i + j <= len && j < XATTR_SIZE_MAX; j++) { __get_kernel_nofault(&c2, s2__ign + j, char, err_out); if (c2 == '\0') return i; + /* + * We allow reading an extra byte from s2 (note the + * `i + j <= len` above) to cover the case when s2 is + * a suffix of the first len chars of s1. + */ + if (i + j == len) + break; __get_kernel_nofault(&c1, s1__ign + j, char, err_out); if (c1 == '\0') return -ENOENT; diff --git a/kernel/bpf/rqspinlock.c b/kernel/bpf/rqspinlock.c index 5ab354d55d82..a00561b1d3e5 100644 --- a/kernel/bpf/rqspinlock.c +++ b/kernel/bpf/rqspinlock.c @@ -471,7 +471,7 @@ queue: * any MCS node. This is not the most elegant solution, but is * simple enough. */ - if (unlikely(idx >= _Q_MAX_NODES)) { + if (unlikely(idx >= _Q_MAX_NODES || in_nmi())) { lockevent_inc(lock_no_node); RES_RESET_TIMEOUT(ts, RES_DEF_TIMEOUT); while (!queued_spin_trylock(lock)) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c4f69a9e9af6..9fb1f957a093 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8547,6 +8547,10 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno, verifier_bug(env, "Two map pointers in a timer helper"); return -EFAULT; } + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + verbose(env, "bpf_timer cannot be used for PREEMPT_RT.\n"); + return -EOPNOTSUPP; + } meta->map_uid = reg->map_uid; meta->map_ptr = map; return 0; @@ -11354,7 +11358,7 @@ static int get_helper_proto(struct bpf_verifier_env *env, int func_id, return -EINVAL; *ptr = env->ops->get_func_proto(func_id, env->prog); - return *ptr ? 0 : -EINVAL; + return *ptr && (*ptr)->func ? 0 : -EINVAL; } static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn, diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 312c6a8b55bb..77d02f87f3f1 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -126,8 +126,31 @@ DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem); * of concurrent destructions. Use a separate workqueue so that cgroup * destruction work items don't end up filling up max_active of system_wq * which may lead to deadlock. + * + * A cgroup destruction should enqueue work sequentially to: + * cgroup_offline_wq: use for css offline work + * cgroup_release_wq: use for css release work + * cgroup_free_wq: use for free work + * + * Rationale for using separate workqueues: + * The cgroup root free work may depend on completion of other css offline + * operations. If all tasks were enqueued to a single workqueue, this could + * create a deadlock scenario where: + * - Free work waits for other css offline work to complete. + * - But other css offline work is queued after free work in the same queue. + * + * Example deadlock scenario with single workqueue (cgroup_destroy_wq): + * 1. umount net_prio + * 2. net_prio root destruction enqueues work to cgroup_destroy_wq (CPUx) + * 3. perf_event CSS A offline enqueues work to same cgroup_destroy_wq (CPUx) + * 4. net_prio cgroup_destroy_root->cgroup_lock_and_drain_offline. + * 5. net_prio root destruction blocks waiting for perf_event CSS A offline, + * which can never complete as it's behind in the same queue and + * workqueue's max_active is 1. */ -static struct workqueue_struct *cgroup_destroy_wq; +static struct workqueue_struct *cgroup_offline_wq; +static struct workqueue_struct *cgroup_release_wq; +static struct workqueue_struct *cgroup_free_wq; /* generate an array of cgroup subsystem pointers */ #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys, @@ -4159,6 +4182,7 @@ static void cgroup_file_release(struct kernfs_open_file *of) cft->release(of); put_cgroup_ns(ctx->ns); kfree(ctx); + of->priv = NULL; } static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, @@ -5558,7 +5582,7 @@ static void css_release_work_fn(struct work_struct *work) cgroup_unlock(); INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); - queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); + queue_rcu_work(cgroup_free_wq, &css->destroy_rwork); } static void css_release(struct percpu_ref *ref) @@ -5567,7 +5591,7 @@ static void css_release(struct percpu_ref *ref) container_of(ref, struct cgroup_subsys_state, refcnt); INIT_WORK(&css->destroy_work, css_release_work_fn); - queue_work(cgroup_destroy_wq, &css->destroy_work); + queue_work(cgroup_release_wq, &css->destroy_work); } static void init_and_link_css(struct cgroup_subsys_state *css, @@ -5701,7 +5725,7 @@ err_list_del: list_del_rcu(&css->sibling); err_free_css: INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); - queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); + queue_rcu_work(cgroup_free_wq, &css->destroy_rwork); return ERR_PTR(err); } @@ -5939,7 +5963,7 @@ static void css_killed_ref_fn(struct percpu_ref *ref) if (atomic_dec_and_test(&css->online_cnt)) { INIT_WORK(&css->destroy_work, css_killed_work_fn); - queue_work(cgroup_destroy_wq, &css->destroy_work); + queue_work(cgroup_offline_wq, &css->destroy_work); } } @@ -6325,8 +6349,14 @@ static int __init cgroup_wq_init(void) * We would prefer to do this in cgroup_init() above, but that * is called before init_workqueues(): so leave this until after. */ - cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); - BUG_ON(!cgroup_destroy_wq); + cgroup_offline_wq = alloc_workqueue("cgroup_offline", 0, 1); + BUG_ON(!cgroup_offline_wq); + + cgroup_release_wq = alloc_workqueue("cgroup_release", 0, 1); + BUG_ON(!cgroup_release_wq); + + cgroup_free_wq = alloc_workqueue("cgroup_free", 0, 1); + BUG_ON(!cgroup_free_wq); return 0; } core_initcall(cgroup_wq_init); diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index e43c6de2bce4..b82399437db0 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -39,6 +39,7 @@ enum { dma_debug_sg, dma_debug_coherent, dma_debug_resource, + dma_debug_noncoherent, }; enum map_err_types { @@ -141,6 +142,7 @@ static const char *type2name[] = { [dma_debug_sg] = "scatter-gather", [dma_debug_coherent] = "coherent", [dma_debug_resource] = "resource", + [dma_debug_noncoherent] = "noncoherent", }; static const char *dir2name[] = { @@ -993,7 +995,8 @@ static void check_unmap(struct dma_debug_entry *ref) "[mapped as %s] [unmapped as %s]\n", ref->dev_addr, ref->size, type2name[entry->type], type2name[ref->type]); - } else if (entry->type == dma_debug_coherent && + } else if ((entry->type == dma_debug_coherent || + entry->type == dma_debug_noncoherent) && ref->paddr != entry->paddr) { err_printk(ref->dev, entry, "device driver frees " "DMA memory with different CPU address " @@ -1581,6 +1584,49 @@ void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, } } +void debug_dma_alloc_pages(struct device *dev, struct page *page, + size_t size, int direction, + dma_addr_t dma_addr, + unsigned long attrs) +{ + struct dma_debug_entry *entry; + + if (unlikely(dma_debug_disabled())) + return; + + entry = dma_entry_alloc(); + if (!entry) + return; + + entry->type = dma_debug_noncoherent; + entry->dev = dev; + entry->paddr = page_to_phys(page); + entry->size = size; + entry->dev_addr = dma_addr; + entry->direction = direction; + + add_dma_entry(entry, attrs); +} + +void debug_dma_free_pages(struct device *dev, struct page *page, + size_t size, int direction, + dma_addr_t dma_addr) +{ + struct dma_debug_entry ref = { + .type = dma_debug_noncoherent, + .dev = dev, + .paddr = page_to_phys(page), + .dev_addr = dma_addr, + .size = size, + .direction = direction, + }; + + if (unlikely(dma_debug_disabled())) + return; + + check_unmap(&ref); +} + static int __init dma_debug_driver_setup(char *str) { int i; diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h index f525197d3cae..48757ca13f31 100644 --- a/kernel/dma/debug.h +++ b/kernel/dma/debug.h @@ -54,6 +54,13 @@ extern void debug_dma_sync_sg_for_cpu(struct device *dev, extern void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, int direction); +extern void debug_dma_alloc_pages(struct device *dev, struct page *page, + size_t size, int direction, + dma_addr_t dma_addr, + unsigned long attrs); +extern void debug_dma_free_pages(struct device *dev, struct page *page, + size_t size, int direction, + dma_addr_t dma_addr); #else /* CONFIG_DMA_API_DEBUG */ static inline void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, @@ -126,5 +133,18 @@ static inline void debug_dma_sync_sg_for_device(struct device *dev, int nelems, int direction) { } + +static inline void debug_dma_alloc_pages(struct device *dev, struct page *page, + size_t size, int direction, + dma_addr_t dma_addr, + unsigned long attrs) +{ +} + +static inline void debug_dma_free_pages(struct device *dev, struct page *page, + size_t size, int direction, + dma_addr_t dma_addr) +{ +} #endif /* CONFIG_DMA_API_DEBUG */ #endif /* _KERNEL_DMA_DEBUG_H */ diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 107e4a4d251d..56de28a3b179 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -712,7 +712,7 @@ struct page *dma_alloc_pages(struct device *dev, size_t size, if (page) { trace_dma_alloc_pages(dev, page_to_virt(page), *dma_handle, size, dir, gfp, 0); - debug_dma_map_page(dev, page, 0, size, dir, *dma_handle, 0); + debug_dma_alloc_pages(dev, page, size, dir, *dma_handle, 0); } else { trace_dma_alloc_pages(dev, NULL, 0, size, dir, gfp, 0); } @@ -738,7 +738,7 @@ void dma_free_pages(struct device *dev, size_t size, struct page *page, dma_addr_t dma_handle, enum dma_data_direction dir) { trace_dma_free_pages(dev, page_to_virt(page), dma_handle, size, dir, 0); - debug_dma_unmap_page(dev, dma_handle, size, dir); + debug_dma_free_pages(dev, page, size, dir, dma_handle); __dma_free_pages(dev, size, page, dma_handle, dir); } EXPORT_SYMBOL_GPL(dma_free_pages); diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index ea7995a25780..8df55397414a 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -553,6 +553,30 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, const struct em_data_callback *cb, const cpumask_t *cpus, bool microwatts) { + int ret = em_dev_register_pd_no_update(dev, nr_states, cb, cpus, microwatts); + + if (_is_cpu_device(dev)) + em_check_capacity_update(); + + return ret; +} +EXPORT_SYMBOL_GPL(em_dev_register_perf_domain); + +/** + * em_dev_register_pd_no_update() - Register a perf domain for a device + * @dev : Device to register the PD for + * @nr_states : Number of performance states in the new PD + * @cb : Callback functions for populating the energy model + * @cpus : CPUs to include in the new PD (mandatory if @dev is a CPU device) + * @microwatts : Whether or not the power values in the EM will be in uW + * + * Like em_dev_register_perf_domain(), but does not trigger a CPU capacity + * update after registering the PD, even if @dev is a CPU device. + */ +int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states, + const struct em_data_callback *cb, + const cpumask_t *cpus, bool microwatts) +{ struct em_perf_table *em_table; unsigned long cap, prev_cap = 0; unsigned long flags = 0; @@ -636,12 +660,9 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, unlock: mutex_unlock(&em_pd_mutex); - if (_is_cpu_device(dev)) - em_check_capacity_update(); - return ret; } -EXPORT_SYMBOL_GPL(em_dev_register_perf_domain); +EXPORT_SYMBOL_GPL(em_dev_register_pd_no_update); /** * em_dev_unregister_perf_domain() - Unregister Energy Model (EM) for a device diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 1f1f30cca573..2f66ab453823 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -449,6 +449,7 @@ int hibernation_snapshot(int platform_mode) shrink_shmem_memory(); console_suspend_all(); + pm_restrict_gfp_mask(); error = dpm_suspend(PMSG_FREEZE); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index be00629f0ba4..ccba6fc3c3fe 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9551,7 +9551,7 @@ static unsigned long tg_weight(struct task_group *tg) #ifdef CONFIG_FAIR_GROUP_SCHED return scale_load_down(tg->shares); #else - return sched_weight_from_cgroup(tg->scx_weight); + return sched_weight_from_cgroup(tg->scx.weight); #endif } diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 4ae32ef179dd..088ceff38c8a 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -6788,12 +6788,8 @@ __bpf_kfunc u32 scx_bpf_reenqueue_local(void) * CPUs disagree, they use %ENQUEUE_RESTORE which is bypassed to * the current local DSQ for running tasks and thus are not * visible to the BPF scheduler. - * - * Also skip re-enqueueing tasks that can only run on this - * CPU, as they would just be re-added to the same local - * DSQ without any benefit. */ - if (p->migration_pending || is_migration_disabled(p) || p->nr_cpus_allowed == 1) + if (p->migration_pending) continue; dispatch_dequeue(rq, p); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 30899a8cc52c..e8c479329282 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -787,10 +787,10 @@ static void retrigger_next_event(void *arg) * of the next expiring timer is enough. The return from the SMP * function call will take care of the reprogramming in case the * CPU was in a NOHZ idle sleep. + * + * In periodic low resolution mode, the next softirq expiration + * must also be updated. */ - if (!hrtimer_hres_active(base) && !tick_nohz_active) - return; - raw_spin_lock(&base->lock); hrtimer_update_base(base); if (hrtimer_hres_active(base)) @@ -2295,11 +2295,6 @@ int hrtimers_cpu_dying(unsigned int dying_cpu) &new_base->clock_base[i]); } - /* - * The migration might have changed the first expiring softirq - * timer on this CPU. Update it. - */ - __hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT); /* Tell the other CPU to retrigger the next event */ smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 2a42c1036ea8..1e3b32b1e82c 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -1397,7 +1397,8 @@ error: ftrace_graph_active--; gops->saved_func = NULL; fgraph_lru_release_index(i); - unregister_pm_notifier(&ftrace_suspend_notifier); + if (!ftrace_graph_active) + unregister_pm_notifier(&ftrace_suspend_notifier); } return ret; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1b7db732c0b1..b3c94fbaf002 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -834,7 +834,10 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, /* copy the current bits to the new max */ ret = trace_pid_list_first(filtered_pids, &pid); while (!ret) { - trace_pid_list_set(pid_list, pid); + ret = trace_pid_list_set(pid_list, pid); + if (ret < 0) + goto out; + ret = trace_pid_list_next(filtered_pids, pid + 1, &pid); nr_pids++; } @@ -871,6 +874,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, trace_parser_clear(&parser); ret = 0; } + out: trace_parser_put(&parser); if (ret < 0) { @@ -7209,7 +7213,7 @@ static ssize_t write_marker_to_buffer(struct trace_array *tr, const char __user entry = ring_buffer_event_data(event); entry->ip = ip; - len = __copy_from_user_inatomic(&entry->buf, ubuf, cnt); + len = copy_from_user_nofault(&entry->buf, ubuf, cnt); if (len) { memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE); cnt = FAULTED_SIZE; @@ -7306,7 +7310,7 @@ static ssize_t write_raw_marker_to_buffer(struct trace_array *tr, entry = ring_buffer_event_data(event); - len = __copy_from_user_inatomic(&entry->id, ubuf, cnt); + len = copy_from_user_nofault(&entry->id, ubuf, cnt); if (len) { entry->id = -1; memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE); diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index af42aaa3d172..2ab283fd3032 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -496,7 +496,7 @@ static bool user_event_enabler_queue_fault(struct user_event_mm *mm, { struct user_event_enabler_fault *fault; - fault = kmem_cache_zalloc(fault_cache, GFP_NOWAIT | __GFP_NOWARN); + fault = kmem_cache_zalloc(fault_cache, GFP_NOWAIT); if (!fault) return false; diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index ccae62d4fb91..fa60362a3f31 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -908,6 +908,8 @@ static int trace_kprobe_create_internal(int argc, const char *argv[], return -EINVAL; } buf = kmemdup(&argv[0][1], len + 1, GFP_KERNEL); + if (!buf) + return -ENOMEM; buf[len] = '\0'; ret = kstrtouint(buf, 0, &maxactive); if (ret || !maxactive) { diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index fd259da0aa64..337bc0eb5d71 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -2322,6 +2322,9 @@ osnoise_cpus_write(struct file *filp, const char __user *ubuf, size_t count, int running, err; char *buf __free(kfree) = NULL; + if (count < 1) + return 0; + buf = kmalloc(count, GFP_KERNEL); if (!buf) return -ENOMEM; diff --git a/mm/damon/core.c b/mm/damon/core.c index 106ee8b0f2d5..08065b363972 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -2111,6 +2111,10 @@ static void damos_adjust_quota(struct damon_ctx *c, struct damos *s) if (!quota->ms && !quota->sz && list_empty("a->goals)) return; + /* First charge window */ + if (!quota->total_charged_sz && !quota->charged_from) + quota->charged_from = jiffies; + /* New charge window starts */ if (time_after_eq(jiffies, quota->charged_from + msecs_to_jiffies(quota->reset_interval))) { @@ -2475,10 +2479,14 @@ static void kdamond_call(struct damon_ctx *ctx, bool cancel) mutex_lock(&ctx->call_controls_lock); list_del(&control->list); mutex_unlock(&ctx->call_controls_lock); - if (!control->repeat) + if (!control->repeat) { complete(&control->completion); - else + } else if (control->canceled && control->dealloc_on_cancel) { + kfree(control); + continue; + } else { list_add(&control->list, &repeat_controls); + } } control = list_first_entry_or_null(&repeat_controls, struct damon_call_control, list); diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c index 151a9de5ad8b..b5a5ed16a7a5 100644 --- a/mm/damon/lru_sort.c +++ b/mm/damon/lru_sort.c @@ -198,6 +198,11 @@ static int damon_lru_sort_apply_parameters(void) if (err) return err; + if (!damon_lru_sort_mon_attrs.sample_interval) { + err = -EINVAL; + goto out; + } + err = damon_set_attrs(ctx, &damon_lru_sort_mon_attrs); if (err) goto out; diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index 3c71b4596676..fb7c982a0018 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -194,6 +194,11 @@ static int damon_reclaim_apply_parameters(void) if (err) return err; + if (!damon_reclaim_mon_attrs.aggr_interval) { + err = -EINVAL; + goto out; + } + err = damon_set_attrs(param_ctx, &damon_reclaim_mon_attrs); if (err) goto out; diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index 6d2b0dab50cb..c96c2154128f 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -1260,14 +1260,18 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr, { struct damon_sysfs_kdamond *kdamond = container_of(kobj, struct damon_sysfs_kdamond, kobj); - struct damon_ctx *ctx = kdamond->damon_ctx; - bool running; + struct damon_ctx *ctx; + bool running = false; - if (!ctx) - running = false; - else + if (!mutex_trylock(&damon_sysfs_lock)) + return -EBUSY; + + ctx = kdamond->damon_ctx; + if (ctx) running = damon_is_running(ctx); + mutex_unlock(&damon_sysfs_lock); + return sysfs_emit(buf, "%s\n", running ? damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_ON] : damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_OFF]); @@ -1530,14 +1534,10 @@ static int damon_sysfs_repeat_call_fn(void *data) return 0; } -static struct damon_call_control damon_sysfs_repeat_call_control = { - .fn = damon_sysfs_repeat_call_fn, - .repeat = true, -}; - static int damon_sysfs_turn_damon_on(struct damon_sysfs_kdamond *kdamond) { struct damon_ctx *ctx; + struct damon_call_control *repeat_call_control; int err; if (damon_sysfs_kdamond_running(kdamond)) @@ -1550,18 +1550,29 @@ static int damon_sysfs_turn_damon_on(struct damon_sysfs_kdamond *kdamond) damon_destroy_ctx(kdamond->damon_ctx); kdamond->damon_ctx = NULL; + repeat_call_control = kmalloc(sizeof(*repeat_call_control), + GFP_KERNEL); + if (!repeat_call_control) + return -ENOMEM; + ctx = damon_sysfs_build_ctx(kdamond->contexts->contexts_arr[0]); - if (IS_ERR(ctx)) + if (IS_ERR(ctx)) { + kfree(repeat_call_control); return PTR_ERR(ctx); + } err = damon_start(&ctx, 1, false); if (err) { + kfree(repeat_call_control); damon_destroy_ctx(ctx); return err; } kdamond->damon_ctx = ctx; - damon_sysfs_repeat_call_control.data = kdamond; - damon_call(ctx, &damon_sysfs_repeat_call_control); + repeat_call_control->fn = damon_sysfs_repeat_call_fn; + repeat_call_control->data = kdamond; + repeat_call_control->repeat = true; + repeat_call_control->dealloc_on_cancel = true; + damon_call(ctx, repeat_call_control); return err; } @@ -2287,8 +2287,8 @@ static unsigned long collect_longterm_unpinnable_folios( struct pages_or_folios *pofs) { unsigned long collected = 0; - bool drain_allow = true; struct folio *folio; + int drained = 0; long i = 0; for (folio = pofs_get_folio(pofs, i); folio; @@ -2307,9 +2307,17 @@ static unsigned long collect_longterm_unpinnable_folios( continue; } - if (!folio_test_lru(folio) && drain_allow) { + if (drained == 0 && folio_may_be_lru_cached(folio) && + folio_ref_count(folio) != + folio_expected_ref_count(folio) + 1) { + lru_add_drain(); + drained = 1; + } + if (drained == 1 && folio_may_be_lru_cached(folio) && + folio_ref_count(folio) != + folio_expected_ref_count(folio) + 1) { lru_add_drain_all(); - drain_allow = false; + drained = 2; } if (!folio_isolate_lru(folio)) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 753f99b4c718..eed59cfb5d21 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5851,7 +5851,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, spinlock_t *ptl; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); - bool adjust_reservation = false; + bool adjust_reservation; unsigned long last_addr_mask; bool force_flush = false; @@ -5944,6 +5944,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, sz); hugetlb_count_sub(pages_per_huge_page(h), mm); hugetlb_remove_rmap(folio); + spin_unlock(ptl); /* * Restore the reservation for anonymous page, otherwise the @@ -5951,14 +5952,16 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, * If there we are freeing a surplus, do not set the restore * reservation bit. */ + adjust_reservation = false; + + spin_lock_irq(&hugetlb_lock); if (!h->surplus_huge_pages && __vma_private_lock(vma) && folio_test_anon(folio)) { folio_set_hugetlb_restore_reserve(folio); /* Reservation to be adjusted after the spin lock */ adjust_reservation = true; } - - spin_unlock(ptl); + spin_unlock_irq(&hugetlb_lock); /* * Adjust the reservation for the region that will have the diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index e2ceebf737ef..11d472a5c4e8 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -336,13 +336,13 @@ static void ___free_pages_bulk(struct page **pages, int nr_pages) } } -static int ___alloc_pages_bulk(struct page **pages, int nr_pages) +static int ___alloc_pages_bulk(struct page **pages, int nr_pages, gfp_t gfp_mask) { unsigned long nr_populated, nr_total = nr_pages; struct page **page_array = pages; while (nr_pages) { - nr_populated = alloc_pages_bulk(GFP_KERNEL, nr_pages, pages); + nr_populated = alloc_pages_bulk(gfp_mask, nr_pages, pages); if (!nr_populated) { ___free_pages_bulk(page_array, nr_total - nr_pages); return -ENOMEM; @@ -354,25 +354,42 @@ static int ___alloc_pages_bulk(struct page **pages, int nr_pages) return 0; } -static int __kasan_populate_vmalloc(unsigned long start, unsigned long end) +static int __kasan_populate_vmalloc(unsigned long start, unsigned long end, gfp_t gfp_mask) { unsigned long nr_pages, nr_total = PFN_UP(end - start); struct vmalloc_populate_data data; + unsigned int flags; int ret = 0; - data.pages = (struct page **)__get_free_page(GFP_KERNEL | __GFP_ZERO); + data.pages = (struct page **)__get_free_page(gfp_mask | __GFP_ZERO); if (!data.pages) return -ENOMEM; while (nr_total) { nr_pages = min(nr_total, PAGE_SIZE / sizeof(data.pages[0])); - ret = ___alloc_pages_bulk(data.pages, nr_pages); + ret = ___alloc_pages_bulk(data.pages, nr_pages, gfp_mask); if (ret) break; data.start = start; + + /* + * page tables allocations ignore external gfp mask, enforce it + * by the scope API + */ + if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) + flags = memalloc_nofs_save(); + else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) + flags = memalloc_noio_save(); + ret = apply_to_page_range(&init_mm, start, nr_pages * PAGE_SIZE, kasan_populate_vmalloc_pte, &data); + + if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) + memalloc_nofs_restore(flags); + else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) + memalloc_noio_restore(flags); + ___free_pages_bulk(data.pages, nr_pages); if (ret) break; @@ -386,7 +403,7 @@ static int __kasan_populate_vmalloc(unsigned long start, unsigned long end) return ret; } -int kasan_populate_vmalloc(unsigned long addr, unsigned long size) +int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask) { unsigned long shadow_start, shadow_end; int ret; @@ -415,7 +432,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size) shadow_start = PAGE_ALIGN_DOWN(shadow_start); shadow_end = PAGE_ALIGN(shadow_end); - ret = __kasan_populate_vmalloc(shadow_start, shadow_end); + ret = __kasan_populate_vmalloc(shadow_start, shadow_end, gfp_mask); if (ret) return ret; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 6b40bdfd224c..b486c1d19b2d 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1417,8 +1417,8 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, */ if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || - folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, - address))) + folio_test_referenced(folio) || + mmu_notifier_test_young(vma->vm_mm, _address))) referenced++; } if (!writable) { diff --git a/mm/memory-failure.c b/mm/memory-failure.c index fc30ca4804bf..df6ee59527dd 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -956,7 +956,7 @@ static const char * const action_page_types[] = { [MF_MSG_BUDDY] = "free buddy page", [MF_MSG_DAX] = "dax page", [MF_MSG_UNSPLIT_THP] = "unsplit thp", - [MF_MSG_ALREADY_POISONED] = "already poisoned", + [MF_MSG_ALREADY_POISONED] = "already poisoned page", [MF_MSG_UNKNOWN] = "unknown page", }; @@ -1349,9 +1349,10 @@ static int action_result(unsigned long pfn, enum mf_action_page_type type, { trace_memory_failure_event(pfn, type, result); - num_poisoned_pages_inc(pfn); - - update_per_node_mf_stats(pfn, result); + if (type != MF_MSG_ALREADY_POISONED) { + num_poisoned_pages_inc(pfn); + update_per_node_mf_stats(pfn, result); + } pr_err("%#lx: recovery action for %s: %s\n", pfn, action_page_types[type], action_name[result]); @@ -2094,12 +2095,11 @@ retry: *hugetlb = 0; return 0; } else if (res == -EHWPOISON) { - pr_err("%#lx: already hardware poisoned\n", pfn); if (flags & MF_ACTION_REQUIRED) { folio = page_folio(p); res = kill_accessing_process(current, folio_pfn(folio), flags); - action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED); } + action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED); return res; } else if (res == -EBUSY) { if (!(flags & MF_NO_RETRY)) { @@ -2285,7 +2285,6 @@ try_again: goto unlock_mutex; if (TestSetPageHWPoison(p)) { - pr_err("%#lx: already hardware poisoned\n", pfn); res = -EHWPOISON; if (flags & MF_ACTION_REQUIRED) res = kill_accessing_process(current, pfn, flags); @@ -2569,10 +2568,9 @@ int unpoison_memory(unsigned long pfn) static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); - if (!pfn_valid(pfn)) - return -ENXIO; - - p = pfn_to_page(pfn); + p = pfn_to_online_page(pfn); + if (!p) + return -EIO; folio = page_folio(p); mutex_lock(&mf_mutex); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 1f15af712bc3..74318c787715 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1815,8 +1815,14 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) pfn = folio_pfn(folio) + folio_nr_pages(folio) - 1; if (folio_contain_hwpoisoned_page(folio)) { - if (WARN_ON(folio_test_lru(folio))) - folio_isolate_lru(folio); + /* + * unmap_poisoned_folio() cannot handle large folios + * in all cases yet. + */ + if (folio_test_large(folio) && !folio_test_hugetlb(folio)) + goto put_folio; + if (folio_test_lru(folio) && !folio_isolate_lru(folio)) + goto put_folio; if (folio_mapped(folio)) { folio_lock(folio); unmap_poisoned_folio(folio, pfn, false); diff --git a/mm/mlock.c b/mm/mlock.c index a1d93ad33c6d..bb0776f5ef7c 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -255,7 +255,7 @@ void mlock_folio(struct folio *folio) folio_get(folio); if (!folio_batch_add(fbatch, mlock_lru(folio)) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } @@ -278,7 +278,7 @@ void mlock_new_folio(struct folio *folio) folio_get(folio); if (!folio_batch_add(fbatch, mlock_new(folio)) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } @@ -299,7 +299,7 @@ void munlock_folio(struct folio *folio) */ folio_get(folio); if (!folio_batch_add(fbatch, folio) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } diff --git a/mm/mremap.c b/mm/mremap.c index e618a706aff5..35de0a7b910e 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1774,15 +1774,18 @@ static unsigned long check_mremap_params(struct vma_remap_struct *vrm) if (!vrm->new_len) return -EINVAL; - /* Is the new length or address silly? */ - if (vrm->new_len > TASK_SIZE || - vrm->new_addr > TASK_SIZE - vrm->new_len) + /* Is the new length silly? */ + if (vrm->new_len > TASK_SIZE) return -EINVAL; /* Remainder of checks are for cases with specific new_addr. */ if (!vrm_implies_new_addr(vrm)) return 0; + /* Is the new address silly? */ + if (vrm->new_addr > TASK_SIZE - vrm->new_len) + return -EINVAL; + /* The new address must be page-aligned. */ if (offset_in_page(vrm->new_addr)) return -EINVAL; diff --git a/mm/percpu.c b/mm/percpu.c index a56f35dcc417..81462ce5866e 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1734,7 +1734,7 @@ void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved, bool is_atomic; bool do_warn; struct obj_cgroup *objcg = NULL; - static int warn_limit = 10; + static atomic_t warn_limit = ATOMIC_INIT(10); struct pcpu_chunk *chunk, *next; const char *err; int slot, off, cpu, ret; @@ -1904,13 +1904,17 @@ fail_unlock: fail: trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align); - if (do_warn && warn_limit) { - pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n", - size, align, is_atomic, err); - if (!is_atomic) - dump_stack(); - if (!--warn_limit) - pr_info("limit reached, disable warning\n"); + if (do_warn) { + int remaining = atomic_dec_if_positive(&warn_limit); + + if (remaining >= 0) { + pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n", + size, align, is_atomic, err); + if (!is_atomic) + dump_stack(); + if (remaining == 0) + pr_info("limit reached, disable warning\n"); + } } if (is_atomic) { diff --git a/mm/swap.c b/mm/swap.c index 3632dd061beb..b74ebe865dd9 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -164,6 +164,10 @@ static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; + /* block memcg migration while the folio moves between lru */ + if (move_fn != lru_add && !folio_test_clear_lru(folio)) + continue; + folio_lruvec_relock_irqsave(folio, &lruvec, &flags); move_fn(lruvec, folio); @@ -176,14 +180,10 @@ static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) } static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, - struct folio *folio, move_fn_t move_fn, - bool on_lru, bool disable_irq) + struct folio *folio, move_fn_t move_fn, bool disable_irq) { unsigned long flags; - if (on_lru && !folio_test_clear_lru(folio)) - return; - folio_get(folio); if (disable_irq) @@ -191,8 +191,8 @@ static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, else local_lock(&cpu_fbatches.lock); - if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || folio_test_large(folio) || - lru_cache_disabled()) + if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn); if (disable_irq) @@ -201,13 +201,13 @@ static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, local_unlock(&cpu_fbatches.lock); } -#define folio_batch_add_and_move(folio, op, on_lru) \ - __folio_batch_add_and_move( \ - &cpu_fbatches.op, \ - folio, \ - op, \ - on_lru, \ - offsetof(struct cpu_fbatches, op) >= offsetof(struct cpu_fbatches, lock_irq) \ +#define folio_batch_add_and_move(folio, op) \ + __folio_batch_add_and_move( \ + &cpu_fbatches.op, \ + folio, \ + op, \ + offsetof(struct cpu_fbatches, op) >= \ + offsetof(struct cpu_fbatches, lock_irq) \ ) static void lru_move_tail(struct lruvec *lruvec, struct folio *folio) @@ -231,10 +231,10 @@ static void lru_move_tail(struct lruvec *lruvec, struct folio *folio) void folio_rotate_reclaimable(struct folio *folio) { if (folio_test_locked(folio) || folio_test_dirty(folio) || - folio_test_unevictable(folio)) + folio_test_unevictable(folio) || !folio_test_lru(folio)) return; - folio_batch_add_and_move(folio, lru_move_tail, true); + folio_batch_add_and_move(folio, lru_move_tail); } void lru_note_cost_unlock_irq(struct lruvec *lruvec, bool file, @@ -328,10 +328,11 @@ static void folio_activate_drain(int cpu) void folio_activate(struct folio *folio) { - if (folio_test_active(folio) || folio_test_unevictable(folio)) + if (folio_test_active(folio) || folio_test_unevictable(folio) || + !folio_test_lru(folio)) return; - folio_batch_add_and_move(folio, lru_activate, true); + folio_batch_add_and_move(folio, lru_activate); } #else @@ -507,7 +508,7 @@ void folio_add_lru(struct folio *folio) lru_gen_in_fault() && !(current->flags & PF_MEMALLOC)) folio_set_active(folio); - folio_batch_add_and_move(folio, lru_add, false); + folio_batch_add_and_move(folio, lru_add); } EXPORT_SYMBOL(folio_add_lru); @@ -685,13 +686,13 @@ void lru_add_drain_cpu(int cpu) void deactivate_file_folio(struct folio *folio) { /* Deactivating an unevictable folio will not accelerate reclaim */ - if (folio_test_unevictable(folio)) + if (folio_test_unevictable(folio) || !folio_test_lru(folio)) return; if (lru_gen_enabled() && lru_gen_clear_refs(folio)) return; - folio_batch_add_and_move(folio, lru_deactivate_file, true); + folio_batch_add_and_move(folio, lru_deactivate_file); } /* @@ -704,13 +705,13 @@ void deactivate_file_folio(struct folio *folio) */ void folio_deactivate(struct folio *folio) { - if (folio_test_unevictable(folio)) + if (folio_test_unevictable(folio) || !folio_test_lru(folio)) return; if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio)) return; - folio_batch_add_and_move(folio, lru_deactivate, true); + folio_batch_add_and_move(folio, lru_deactivate); } /** @@ -723,10 +724,11 @@ void folio_deactivate(struct folio *folio) void folio_mark_lazyfree(struct folio *folio) { if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || + !folio_test_lru(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; - folio_batch_add_and_move(folio, lru_lazyfree, true); + folio_batch_add_and_move(folio, lru_lazyfree); } void lru_add_drain(void) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 6dbcdceecae1..5edd536ba9d2 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2026,6 +2026,8 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, if (unlikely(!vmap_initialized)) return ERR_PTR(-EBUSY); + /* Only reclaim behaviour flags are relevant. */ + gfp_mask = gfp_mask & GFP_RECLAIM_MASK; might_sleep(); /* @@ -2038,8 +2040,6 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, */ va = node_alloc(size, align, vstart, vend, &addr, &vn_id); if (!va) { - gfp_mask = gfp_mask & GFP_RECLAIM_MASK; - va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); if (unlikely(!va)) return ERR_PTR(-ENOMEM); @@ -2089,7 +2089,7 @@ retry: BUG_ON(va->va_start < vstart); BUG_ON(va->va_end > vend); - ret = kasan_populate_vmalloc(addr, size); + ret = kasan_populate_vmalloc(addr, size, gfp_mask); if (ret) { free_vmap_area(va); return ERR_PTR(ret); @@ -4826,7 +4826,7 @@ retry: /* populate the kasan shadow space */ for (area = 0; area < nr_vms; area++) { - if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area])) + if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area], GFP_KERNEL)) goto err_free_shadow; } diff --git a/mm/vmscan.c b/mm/vmscan.c index a48aec8bfd92..674999999cd0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4507,7 +4507,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c } /* ineligible */ - if (!folio_test_lru(folio) || zone > sc->reclaim_idx) { + if (zone > sc->reclaim_idx) { gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); return true; diff --git a/net/bridge/br.c b/net/bridge/br.c index 1885d0c315f0..c683baa3847f 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -324,6 +324,13 @@ int br_boolopt_multi_toggle(struct net_bridge *br, int err = 0; int opt_id; + opt_id = find_next_bit(&bitmap, BITS_PER_LONG, BR_BOOLOPT_MAX); + if (opt_id != BITS_PER_LONG) { + NL_SET_ERR_MSG_FMT_MOD(extack, "Unknown boolean option %d", + opt_id); + return -EINVAL; + } + for_each_set_bit(opt_id, &bitmap, BR_BOOLOPT_MAX) { bool on = !!(bm->optval & BIT(opt_id)); diff --git a/net/can/j1939/bus.c b/net/can/j1939/bus.c index 39844f14eed8..797719cb227e 100644 --- a/net/can/j1939/bus.c +++ b/net/can/j1939/bus.c @@ -290,8 +290,11 @@ int j1939_local_ecu_get(struct j1939_priv *priv, name_t name, u8 sa) if (!ecu) ecu = j1939_ecu_create_locked(priv, name); err = PTR_ERR_OR_ZERO(ecu); - if (err) + if (err) { + if (j1939_address_is_unicast(sa)) + priv->ents[sa].nusers--; goto done; + } ecu->nusers++; /* TODO: do we care if ecu->addr != sa? */ diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h index 31a93cae5111..81f58924b4ac 100644 --- a/net/can/j1939/j1939-priv.h +++ b/net/can/j1939/j1939-priv.h @@ -212,6 +212,7 @@ void j1939_priv_get(struct j1939_priv *priv); /* notify/alert all j1939 sockets bound to ifindex */ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv); +void j1939_sk_netdev_event_unregister(struct j1939_priv *priv); int j1939_cancel_active_session(struct j1939_priv *priv, struct sock *sk); void j1939_tp_init(struct j1939_priv *priv); diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index 7e8a20f2fc42..3706a872ecaf 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -377,6 +377,9 @@ static int j1939_netdev_notify(struct notifier_block *nb, j1939_sk_netdev_event_netdown(priv); j1939_ecu_unmap_all(priv); break; + case NETDEV_UNREGISTER: + j1939_sk_netdev_event_unregister(priv); + break; } j1939_priv_put(priv); diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 3d8b588822f9..88e7160d4248 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -521,6 +521,9 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) ret = j1939_local_ecu_get(priv, jsk->addr.src_name, jsk->addr.sa); if (ret) { j1939_netdev_stop(priv); + jsk->priv = NULL; + synchronize_rcu(); + j1939_priv_put(priv); goto out_release_sock; } @@ -1300,6 +1303,55 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) read_unlock_bh(&priv->j1939_socks_lock); } +void j1939_sk_netdev_event_unregister(struct j1939_priv *priv) +{ + struct sock *sk; + struct j1939_sock *jsk; + bool wait_rcu = false; + +rescan: /* The caller is holding a ref on this "priv" via j1939_priv_get_by_ndev(). */ + read_lock_bh(&priv->j1939_socks_lock); + list_for_each_entry(jsk, &priv->j1939_socks, list) { + /* Skip if j1939_jsk_add() is not called on this socket. */ + if (!(jsk->state & J1939_SOCK_BOUND)) + continue; + sk = &jsk->sk; + sock_hold(sk); + read_unlock_bh(&priv->j1939_socks_lock); + /* Check if j1939_jsk_del() is not yet called on this socket after holding + * socket's lock, for both j1939_sk_bind() and j1939_sk_release() call + * j1939_jsk_del() with socket's lock held. + */ + lock_sock(sk); + if (jsk->state & J1939_SOCK_BOUND) { + /* Neither j1939_sk_bind() nor j1939_sk_release() called j1939_jsk_del(). + * Make this socket no longer bound, by pretending as if j1939_sk_bind() + * dropped old references but did not get new references. + */ + j1939_jsk_del(priv, jsk); + j1939_local_ecu_put(priv, jsk->addr.src_name, jsk->addr.sa); + j1939_netdev_stop(priv); + /* Call j1939_priv_put() now and prevent j1939_sk_sock_destruct() from + * calling the corresponding j1939_priv_put(). + * + * j1939_sk_sock_destruct() is supposed to call j1939_priv_put() after + * an RCU grace period. But since the caller is holding a ref on this + * "priv", we can defer synchronize_rcu() until immediately before + * the caller calls j1939_priv_put(). + */ + j1939_priv_put(priv); + jsk->priv = NULL; + wait_rcu = true; + } + release_sock(sk); + sock_put(sk); + goto rescan; + } + read_unlock_bh(&priv->j1939_socks_lock); + if (wait_rcu) + synchronize_rcu(); +} + static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index d1b5705dc0c6..9f6d860411cb 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1524,7 +1524,7 @@ static void con_fault_finish(struct ceph_connection *con) * in case we faulted due to authentication, invalidate our * current tickets so that we can get new ones. */ - if (con->v1.auth_retry) { + if (!ceph_msgr2(from_msgr(con->msgr)) && con->v1.auth_retry) { dout("auth_retry %d, invalidating\n", con->v1.auth_retry); if (con->ops->invalidate_authorizer) con->ops->invalidate_authorizer(con); @@ -1714,9 +1714,10 @@ static void clear_standby(struct ceph_connection *con) { /* come back from STANDBY? */ if (con->state == CEPH_CON_S_STANDBY) { - dout("clear_standby %p and ++connect_seq\n", con); + dout("clear_standby %p\n", con); con->state = CEPH_CON_S_PREOPEN; - con->v1.connect_seq++; + if (!ceph_msgr2(from_msgr(con->msgr))) + con->v1.connect_seq++; WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_WRITE_PENDING)); WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_KEEPALIVE_PENDING)); } diff --git a/net/core/dev.c b/net/core/dev.c index 93a25d87b86b..8d49b2198d07 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6965,7 +6965,7 @@ static void napi_stop_kthread(struct napi_struct *napi) * the kthread. */ while (true) { - if (!test_bit(NAPIF_STATE_SCHED_THREADED, &napi->state)) + if (!test_bit(NAPI_STATE_SCHED_THREADED, &napi->state)) break; msleep(20); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 9c0ad7f4b5d8..ad54b12d4b4c 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -464,8 +464,15 @@ int generic_hwtstamp_get_lower(struct net_device *dev, if (!netif_device_present(dev)) return -ENODEV; - if (ops->ndo_hwtstamp_get) - return dev_get_hwtstamp_phylib(dev, kernel_cfg); + if (ops->ndo_hwtstamp_get) { + int err; + + netdev_lock_ops(dev); + err = dev_get_hwtstamp_phylib(dev, kernel_cfg); + netdev_unlock_ops(dev); + + return err; + } /* Legacy path: unconverted lower driver */ return generic_hwtstamp_ioctl_lower(dev, SIOCGHWTSTAMP, kernel_cfg); @@ -481,8 +488,15 @@ int generic_hwtstamp_set_lower(struct net_device *dev, if (!netif_device_present(dev)) return -ENODEV; - if (ops->ndo_hwtstamp_set) - return dev_set_hwtstamp_phylib(dev, kernel_cfg, extack); + if (ops->ndo_hwtstamp_set) { + int err; + + netdev_lock_ops(dev); + err = dev_set_hwtstamp_phylib(dev, kernel_cfg, extack); + netdev_unlock_ops(dev); + + return err; + } /* Legacy path: unconverted lower driver */ return generic_hwtstamp_ioctl_lower(dev, SIOCSHWTSTAMP, kernel_cfg); diff --git a/net/devlink/rate.c b/net/devlink/rate.c index 110b3fa8a0b1..264fb82cba19 100644 --- a/net/devlink/rate.c +++ b/net/devlink/rate.c @@ -34,7 +34,7 @@ devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info) static struct devlink_rate * devlink_rate_node_get_by_name(struct devlink *devlink, const char *node_name) { - static struct devlink_rate *devlink_rate; + struct devlink_rate *devlink_rate; list_for_each_entry(devlink_rate, &devlink->rate_list, list) { if (devlink_rate_is_node(devlink_rate) && @@ -819,8 +819,8 @@ EXPORT_SYMBOL_GPL(devl_rate_leaf_destroy); */ void devl_rate_nodes_destroy(struct devlink *devlink) { - static struct devlink_rate *devlink_rate, *tmp; const struct devlink_ops *ops = devlink->ops; + struct devlink_rate *devlink_rate, *tmp; devl_assert_locked(devlink); diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 4f58648a27ad..92e6a681c797 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -905,7 +905,7 @@ int ethtool_net_get_ts_info_by_phc(struct net_device *dev, int err; if (!ops->get_ts_info) - return -ENODEV; + return -EOPNOTSUPP; /* Does ptp comes from netdev */ ethtool_init_tsinfo(info); @@ -973,7 +973,7 @@ int ethtool_get_ts_info_by_phc(struct net_device *dev, int err; err = ethtool_net_get_ts_info_by_phc(dev, info, hwprov_desc); - if (err == -ENODEV) { + if (err == -ENODEV || err == -EOPNOTSUPP) { struct phy_device *phy; phy = ethtool_phy_get_ts_info_by_phc(dev, info, hwprov_desc); diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 88657255fec1..fbbc3ccf9df6 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -49,7 +49,7 @@ static bool hsr_check_carrier(struct hsr_port *master) ASSERT_RTNL(); - hsr_for_each_port(master->hsr, port) { + hsr_for_each_port_rtnl(master->hsr, port) { if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) { netif_carrier_on(master->dev); return true; @@ -105,7 +105,7 @@ int hsr_get_max_mtu(struct hsr_priv *hsr) struct hsr_port *port; mtu_max = ETH_DATA_LEN; - hsr_for_each_port(hsr, port) + hsr_for_each_port_rtnl(hsr, port) if (port->type != HSR_PT_MASTER) mtu_max = min(port->dev->mtu, mtu_max); @@ -139,7 +139,7 @@ static int hsr_dev_open(struct net_device *dev) hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { @@ -172,7 +172,7 @@ static int hsr_dev_close(struct net_device *dev) struct hsr_priv *hsr; hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { @@ -205,7 +205,7 @@ static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr, * may become enabled. */ features &= ~NETIF_F_ONE_FOR_ALL; - hsr_for_each_port(hsr, port) + hsr_for_each_port_rtnl(hsr, port) features = netdev_increment_features(features, port->dev->features, mask); @@ -226,6 +226,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct hsr_priv *hsr = netdev_priv(dev); struct hsr_port *master; + rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (master) { skb->dev = master->dev; @@ -238,6 +239,8 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); } + rcu_read_unlock(); + return NETDEV_TX_OK; } @@ -484,7 +487,7 @@ static void hsr_set_rx_mode(struct net_device *dev) hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { @@ -506,7 +509,7 @@ static void hsr_change_rx_flags(struct net_device *dev, int change) hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { @@ -534,7 +537,7 @@ static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev, hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER || port->type == HSR_PT_INTERLINK) continue; @@ -580,7 +583,7 @@ static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev, hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: @@ -672,9 +675,14 @@ struct net_device *hsr_get_port_ndev(struct net_device *ndev, struct hsr_priv *hsr = netdev_priv(ndev); struct hsr_port *port; + rcu_read_lock(); hsr_for_each_port(hsr, port) - if (port->type == pt) + if (port->type == pt) { + dev_hold(port->dev); + rcu_read_unlock(); return port->dev; + } + rcu_read_unlock(); return NULL; } EXPORT_SYMBOL(hsr_get_port_ndev); diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index 192893c3f2ec..bc94b07101d8 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -22,7 +22,7 @@ static bool hsr_slave_empty(struct hsr_priv *hsr) { struct hsr_port *port; - hsr_for_each_port(hsr, port) + hsr_for_each_port_rtnl(hsr, port) if (port->type != HSR_PT_MASTER) return false; return true; @@ -134,7 +134,7 @@ struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt) { struct hsr_port *port; - hsr_for_each_port(hsr, port) + hsr_for_each_port_rtnl(hsr, port) if (port->type == pt) return port; return NULL; diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 135ec5fce019..33b0d2460c9b 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -224,6 +224,9 @@ struct hsr_priv { #define hsr_for_each_port(hsr, port) \ list_for_each_entry_rcu((port), &(hsr)->ports, port_list) +#define hsr_for_each_port_rtnl(hsr, port) \ + list_for_each_entry_rcu((port), &(hsr)->ports, port_list, lockdep_rtnl_is_held()) + struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt); /* Caller must ensure skb is a valid HSR frame */ diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index cc9915543637..2e61ac137128 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -206,6 +206,9 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr))) return -EINVAL; + if (skb_is_gso(skb)) + skb_gso_reset(skb); + skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN); pskb_pull(skb, ETH_HLEN); skb_reset_network_header(skb); @@ -300,6 +303,9 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu) if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr))) return -EINVAL; + if (skb_is_gso(skb)) + skb_gso_reset(skb); + skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN); pskb_pull(skb, ETH_HLEN); skb_reset_network_header(skb); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 71a956fbfc55..ad76556800f2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3327,6 +3327,7 @@ int tcp_disconnect(struct sock *sk, int flags) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int old_state = sk->sk_state; + struct request_sock *req; u32 seq; if (old_state != TCP_CLOSE) @@ -3442,6 +3443,10 @@ int tcp_disconnect(struct sock *sk, int flags) /* Clean up fastopen related fields */ + req = rcu_dereference_protected(tp->fastopen_rsk, + lockdep_sock_is_held(sk)); + if (req) + reqsk_fastopen_remove(sk, req, false); tcp_free_fastopen_req(tp); inet_clear_bit(DEFER_CONNECT, sk); tp->fastopen_client_fail = 0; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index bbb8d5f0eae7..3338b6cc85c4 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -1178,7 +1178,9 @@ void tcp_ao_finish_connect(struct sock *sk, struct sk_buff *skb) if (!ao) return; - WRITE_ONCE(ao->risn, tcp_hdr(skb)->seq); + /* sk with TCP_REPAIR_ON does not have skb in tcp_finish_connect */ + if (skb) + WRITE_ONCE(ao->risn, tcp_hdr(skb)->seq); ao->rcv_sne = 0; hlist_for_each_entry_rcu(key, &ao->head, node, lockdep_sock_is_held(sk)) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index ba581785adb4..a268e1595b22 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -408,8 +408,11 @@ more_data: if (!psock->cork) { psock->cork = kzalloc(sizeof(*psock->cork), GFP_ATOMIC | __GFP_NOWARN); - if (!psock->cork) + if (!psock->cork) { + sk_msg_free(sk, msg); + *copied = 0; return -ENOMEM; + } } memcpy(psock->cork, msg, sizeof(*msg)); return 0; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 2a8ea28442b2..1103b3341a70 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -985,13 +985,13 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, return false; } - if (mp_opt->deny_join_id0) - WRITE_ONCE(msk->pm.remote_deny_join_id0, true); - if (unlikely(!READ_ONCE(msk->pm.server_side))) pr_warn_once("bogus mpc option on established client sk"); set_fully_established: + if (mp_opt->deny_join_id0) + WRITE_ONCE(msk->pm.remote_deny_join_id0, true); + mptcp_data_lock((struct sock *)msk); __mptcp_subflow_fully_established(msk, subflow, mp_opt); mptcp_data_unlock((struct sock *)msk); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 50aaf259959a..ce7d42d3bd00 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -408,6 +408,7 @@ static int mptcp_event_created(struct sk_buff *skb, const struct sock *ssk) { int err = nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token)); + u16 flags = 0; if (err) return err; @@ -415,6 +416,12 @@ static int mptcp_event_created(struct sk_buff *skb, if (nla_put_u8(skb, MPTCP_ATTR_SERVER_SIDE, READ_ONCE(msk->pm.server_side))) return -EMSGSIZE; + if (READ_ONCE(msk->pm.remote_deny_join_id0)) + flags |= MPTCP_PM_EV_FLAG_DENY_JOIN_ID0; + + if (flags && nla_put_u16(skb, MPTCP_ATTR_FLAGS, flags)) + return -EMSGSIZE; + return mptcp_event_add_subflow(skb, ssk); } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e6fd97b21e9e..5e497a83e967 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -371,6 +371,20 @@ static void mptcp_close_wake_up(struct sock *sk) sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); } +static void mptcp_shutdown_subflows(struct mptcp_sock *msk) +{ + struct mptcp_subflow_context *subflow; + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow; + + slow = lock_sock_fast(ssk); + tcp_shutdown(ssk, SEND_SHUTDOWN); + unlock_sock_fast(ssk, slow); + } +} + /* called under the msk socket lock */ static bool mptcp_pending_data_fin_ack(struct sock *sk) { @@ -395,6 +409,7 @@ static void mptcp_check_data_fin_ack(struct sock *sk) break; case TCP_CLOSING: case TCP_LAST_ACK: + mptcp_shutdown_subflows(msk); mptcp_set_state(sk, TCP_CLOSE); break; } @@ -563,6 +578,7 @@ static bool mptcp_check_data_fin(struct sock *sk) mptcp_set_state(sk, TCP_CLOSING); break; case TCP_FIN_WAIT2: + mptcp_shutdown_subflows(msk); mptcp_set_state(sk, TCP_CLOSE); break; default: diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 2c267aff95be..2abe6f1e9940 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -1532,13 +1532,12 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) { static const unsigned int tx_rx_locks = SOCK_RCVBUF_LOCK | SOCK_SNDBUF_LOCK; struct sock *sk = (struct sock *)msk; + bool keep_open; - if (ssk->sk_prot->keepalive) { - if (sock_flag(sk, SOCK_KEEPOPEN)) - ssk->sk_prot->keepalive(ssk, 1); - else - ssk->sk_prot->keepalive(ssk, 0); - } + keep_open = sock_flag(sk, SOCK_KEEPOPEN); + if (ssk->sk_prot->keepalive) + ssk->sk_prot->keepalive(ssk, keep_open); + sock_valbool_flag(ssk, SOCK_KEEPOPEN, keep_open); ssk->sk_priority = sk->sk_priority; ssk->sk_bound_dev_if = sk->sk_bound_dev_if; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 3f1b62a9fe88..f31a3a79531a 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -883,6 +883,10 @@ create_child: ctx->subflow_id = 1; owner = mptcp_sk(ctx->conn); + + if (mp_opt.deny_join_id0) + WRITE_ONCE(owner->pm.remote_deny_join_id0, true); + mptcp_pm_new_connection(owner, child, 1); /* with OoO packets we can reach here without ingress diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c1082de09656..c3c73411c40c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1131,11 +1131,14 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla, return ERR_PTR(-ENOENT); } -static __be16 nft_base_seq(const struct net *net) +static unsigned int nft_base_seq(const struct net *net) { - struct nftables_pernet *nft_net = nft_pernet(net); + return READ_ONCE(net->nft.base_seq); +} - return htons(nft_net->base_seq & 0xffff); +static __be16 nft_base_seq_be16(const struct net *net) +{ + return htons(nft_base_seq(net) & 0xffff); } static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = { @@ -1155,7 +1158,7 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), - flags, family, NFNETLINK_V0, nft_base_seq(net)); + flags, family, NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -1248,7 +1251,7 @@ static int nf_tables_dump_tables(struct sk_buff *skb, rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -2030,7 +2033,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), - flags, family, NFNETLINK_V0, nft_base_seq(net)); + flags, family, NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -2133,7 +2136,7 @@ static int nf_tables_dump_chains(struct sk_buff *skb, rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -3671,7 +3674,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, u16 type = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nfnl_msg_put(skb, portid, seq, type, flags, family, NFNETLINK_V0, - nft_base_seq(net)); + nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -3839,7 +3842,7 @@ static int nf_tables_dump_rules(struct sk_buff *skb, rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -4050,7 +4053,7 @@ static int nf_tables_getrule_reset(struct sk_buff *skb, buf = kasprintf(GFP_ATOMIC, "%.*s:%u", nla_len(nla[NFTA_RULE_TABLE]), (char *)nla_data(nla[NFTA_RULE_TABLE]), - nft_net->base_seq); + nft_base_seq(net)); audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, AUDIT_NFT_OP_RULE_RESET, GFP_ATOMIC); kfree(buf); @@ -4887,7 +4890,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), flags, ctx->family, NFNETLINK_V0, - nft_base_seq(ctx->net)); + nft_base_seq_be16(ctx->net)); if (!nlh) goto nla_put_failure; @@ -5032,7 +5035,7 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (ctx->family != NFPROTO_UNSPEC && @@ -6209,7 +6212,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (dump_ctx->ctx.family != NFPROTO_UNSPEC && @@ -6238,7 +6241,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) seq = cb->nlh->nlmsg_seq; nlh = nfnl_msg_put(skb, portid, seq, event, NLM_F_MULTI, - table->family, NFNETLINK_V0, nft_base_seq(net)); + table->family, NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -6331,7 +6334,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb, event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family, - NFNETLINK_V0, nft_base_seq(ctx->net)); + NFNETLINK_V0, nft_base_seq_be16(ctx->net)); if (!nlh) goto nla_put_failure; @@ -6630,7 +6633,7 @@ static int nf_tables_getsetelem_reset(struct sk_buff *skb, } nelems++; } - audit_log_nft_set_reset(dump_ctx.ctx.table, nft_net->base_seq, nelems); + audit_log_nft_set_reset(dump_ctx.ctx.table, nft_base_seq(info->net), nelems); out_unlock: rcu_read_unlock(); @@ -8381,7 +8384,7 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), - flags, family, NFNETLINK_V0, nft_base_seq(net)); + flags, family, NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -8446,7 +8449,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -8480,7 +8483,7 @@ cont: idx++; } if (ctx->reset && entries) - audit_log_obj_reset(table, nft_net->base_seq, entries); + audit_log_obj_reset(table, nft_base_seq(net), entries); if (rc < 0) break; } @@ -8649,7 +8652,7 @@ static int nf_tables_getobj_reset(struct sk_buff *skb, buf = kasprintf(GFP_ATOMIC, "%.*s:%u", nla_len(nla[NFTA_OBJ_TABLE]), (char *)nla_data(nla[NFTA_OBJ_TABLE]), - nft_net->base_seq); + nft_base_seq(net)); audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); kfree(buf); @@ -8754,9 +8757,8 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, u16 flags, int family, int report, gfp_t gfp) { - struct nftables_pernet *nft_net = nft_pernet(net); char *buf = kasprintf(gfp, "%s:%u", - table->name, nft_net->base_seq); + table->name, nft_base_seq(net)); audit_log_nfcfg(buf, family, @@ -9442,7 +9444,7 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), - flags, family, NFNETLINK_V0, nft_base_seq(net)); + flags, family, NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -9511,7 +9513,7 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb, rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -9696,17 +9698,16 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq) { - struct nftables_pernet *nft_net = nft_pernet(net); struct nlmsghdr *nlh; char buf[TASK_COMM_LEN]; int event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWGEN); nlh = nfnl_msg_put(skb, portid, seq, event, 0, AF_UNSPEC, - NFNETLINK_V0, nft_base_seq(net)); + NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_net->base_seq)) || + if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_base_seq(net))) || nla_put_be32(skb, NFTA_GEN_PROC_PID, htonl(task_pid_nr(current))) || nla_put_string(skb, NFTA_GEN_PROC_NAME, get_task_comm(buf, current))) goto nla_put_failure; @@ -10968,11 +10969,12 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) * Bump generation counter, invalidate any dump in progress. * Cannot fail after this point. */ - base_seq = READ_ONCE(nft_net->base_seq); + base_seq = nft_base_seq(net); while (++base_seq == 0) ; - WRITE_ONCE(nft_net->base_seq, base_seq); + /* pairs with smp_load_acquire in nft_lookup_eval */ + smp_store_release(&net->nft.base_seq, base_seq); gc_seq = nft_gc_seq_begin(nft_net); @@ -11181,7 +11183,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); - nf_tables_commit_audit_log(&adl, nft_net->base_seq); + nf_tables_commit_audit_log(&adl, nft_base_seq(net)); nft_gc_seq_end(nft_net, gc_seq); nft_net->validate_state = NFT_VALIDATE_SKIP; @@ -11506,7 +11508,7 @@ static bool nf_tables_valid_genid(struct net *net, u32 genid) mutex_lock(&nft_net->commit_mutex); nft_net->tstamp = get_jiffies_64(); - genid_ok = genid == 0 || nft_net->base_seq == genid; + genid_ok = genid == 0 || nft_base_seq(net) == genid; if (!genid_ok) mutex_unlock(&nft_net->commit_mutex); @@ -12143,7 +12145,7 @@ static int __net_init nf_tables_init_net(struct net *net) INIT_LIST_HEAD(&nft_net->module_list); INIT_LIST_HEAD(&nft_net->notify_list); mutex_init(&nft_net->commit_mutex); - nft_net->base_seq = 1; + net->nft.base_seq = 1; nft_net->gc_seq = 0; nft_net->validate_state = NFT_VALIDATE_SKIP; INIT_WORK(&nft_net->destroy_work, nf_tables_trans_destroy_work); diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 40c602ffbcba..58c5b14889c4 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -24,11 +24,11 @@ struct nft_lookup { struct nft_set_binding binding; }; -#ifdef CONFIG_MITIGATION_RETPOLINE -const struct nft_set_ext * -nft_set_do_lookup(const struct net *net, const struct nft_set *set, - const u32 *key) +static const struct nft_set_ext * +__nft_set_do_lookup(const struct net *net, const struct nft_set *set, + const u32 *key) { +#ifdef CONFIG_MITIGATION_RETPOLINE if (set->ops == &nft_set_hash_fast_type.ops) return nft_hash_lookup_fast(net, set, key); if (set->ops == &nft_set_hash_type.ops) @@ -51,10 +51,46 @@ nft_set_do_lookup(const struct net *net, const struct nft_set *set, return nft_rbtree_lookup(net, set, key); WARN_ON_ONCE(1); +#endif return set->ops->lookup(net, set, key); } + +static unsigned int nft_base_seq(const struct net *net) +{ + /* pairs with smp_store_release() in nf_tables_commit() */ + return smp_load_acquire(&net->nft.base_seq); +} + +static bool nft_lookup_should_retry(const struct net *net, unsigned int seq) +{ + return unlikely(seq != nft_base_seq(net)); +} + +const struct nft_set_ext * +nft_set_do_lookup(const struct net *net, const struct nft_set *set, + const u32 *key) +{ + const struct nft_set_ext *ext; + unsigned int base_seq; + + do { + base_seq = nft_base_seq(net); + + ext = __nft_set_do_lookup(net, set, key); + if (ext) + break; + /* No match? There is a small chance that lookup was + * performed in the old generation, but nf_tables_commit() + * already unlinked a (matching) element. + * + * We need to repeat the lookup to make sure that we didn't + * miss a matching element in the new generation. + */ + } while (nft_lookup_should_retry(net, base_seq)); + + return ext; +} EXPORT_SYMBOL_GPL(nft_set_do_lookup); -#endif void nft_lookup_eval(const struct nft_expr *expr, struct nft_regs *regs, diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index c24c922f895d..8d3f040a904a 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -226,7 +226,8 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx, const struct nft_bitmap *priv = nft_set_priv(set); struct nft_bitmap_elem *be; - list_for_each_entry_rcu(be, &priv->list, head) { + list_for_each_entry_rcu(be, &priv->list, head, + lockdep_is_held(&nft_pernet(ctx->net)->commit_mutex)) { if (iter->count < iter->skip) goto cont; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 9a10251228fd..793790d79d13 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -510,6 +510,23 @@ out: * * This function is called from the data path. It will search for * an element matching the given key in the current active copy. + * Unlike other set types, this uses NFT_GENMASK_ANY instead of + * nft_genmask_cur(). + * + * This is because new (future) elements are not reachable from + * priv->match, they get added to priv->clone instead. + * When the commit phase flips the generation bitmask, the + * 'now old' entries are skipped but without the 'now current' + * elements becoming visible. Using nft_genmask_cur() thus creates + * inconsistent state: matching old entries get skipped but thew + * newly matching entries are unreachable. + * + * GENMASK will still find the 'now old' entries which ensures consistent + * priv->match view. + * + * nft_pipapo_commit swaps ->clone and ->match shortly after the + * genbit flip. As ->clone doesn't contain the old entries in the first + * place, lookup will only find the now-current ones. * * Return: ntables API extension pointer or NULL if no match. */ @@ -518,12 +535,11 @@ nft_pipapo_lookup(const struct net *net, const struct nft_set *set, const u32 *key) { struct nft_pipapo *priv = nft_set_priv(set); - u8 genmask = nft_genmask_cur(net); const struct nft_pipapo_match *m; const struct nft_pipapo_elem *e; m = rcu_dereference(priv->match); - e = pipapo_get(m, (const u8 *)key, genmask, get_jiffies_64()); + e = pipapo_get(m, (const u8 *)key, NFT_GENMASK_ANY, get_jiffies_64()); return e ? &e->ext : NULL; } diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index 2f090e253caf..c0884fa68c79 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -1152,7 +1152,6 @@ nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, struct nft_pipapo *priv = nft_set_priv(set); const struct nft_set_ext *ext = NULL; struct nft_pipapo_scratch *scratch; - u8 genmask = nft_genmask_cur(net); const struct nft_pipapo_match *m; const struct nft_pipapo_field *f; const u8 *rp = (const u8 *)key; @@ -1248,8 +1247,7 @@ next_match: if (last) { const struct nft_set_ext *e = &f->mt[ret].e->ext; - if (unlikely(nft_set_elem_expired(e) || - !nft_set_elem_active(e, genmask))) + if (unlikely(nft_set_elem_expired(e))) goto next_match; ext = e; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 938a257c069e..b1f04168ec93 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -77,7 +77,9 @@ __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, nft_rbtree_interval_end(rbe) && nft_rbtree_interval_start(interval)) continue; - interval = rbe; + if (nft_set_elem_active(&rbe->ext, genmask) && + !nft_rbtree_elem_expired(rbe)) + interval = rbe; } else if (d > 0) parent = rcu_dereference_raw(parent->rb_right); else { @@ -102,8 +104,6 @@ __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, } if (set->flags & NFT_SET_INTERVAL && interval != NULL && - nft_set_elem_active(&interval->ext, genmask) && - !nft_rbtree_elem_expired(interval) && nft_rbtree_interval_start(interval)) return &interval->ext; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 104732d34543..978c129c6095 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1836,6 +1836,9 @@ static int genl_bind(struct net *net, int group) !ns_capable(net->user_ns, CAP_SYS_ADMIN)) ret = -EPERM; + if (ret) + break; + if (family->bind) family->bind(i); diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c index 28c1b0022178..bd861191157b 100644 --- a/net/rds/ib_frmr.c +++ b/net/rds/ib_frmr.c @@ -133,12 +133,15 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_dma_len, &off, PAGE_SIZE); - if (unlikely(ret != ibmr->sg_dma_len)) - return ret < 0 ? ret : -EINVAL; + if (unlikely(ret != ibmr->sg_dma_len)) { + ret = ret < 0 ? ret : -EINVAL; + goto out_inc; + } - if (cmpxchg(&frmr->fr_state, - FRMR_IS_FREE, FRMR_IS_INUSE) != FRMR_IS_FREE) - return -EBUSY; + if (cmpxchg(&frmr->fr_state, FRMR_IS_FREE, FRMR_IS_INUSE) != FRMR_IS_FREE) { + ret = -EBUSY; + goto out_inc; + } atomic_inc(&ibmr->ic->i_fastreg_inuse_count); @@ -166,11 +169,10 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) /* Failure here can be because of -ENOMEM as well */ rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_STALE); - atomic_inc(&ibmr->ic->i_fastreg_wrs); if (printk_ratelimit()) pr_warn("RDS/IB: %s returned error(%d)\n", __func__, ret); - goto out; + goto out_inc; } /* Wait for the registration to complete in order to prevent an invalid @@ -179,8 +181,10 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) */ wait_event(frmr->fr_reg_done, !frmr->fr_reg); -out: + return ret; +out_inc: + atomic_inc(&ibmr->ic->i_fastreg_wrs); return ret; } diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 41e657e97761..cf2dcec6ce5a 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -94,10 +94,10 @@ static const struct dmi_system_id rfkill_gpio_deny_table[] = { static int rfkill_gpio_probe(struct platform_device *pdev) { struct rfkill_gpio_data *rfkill; - struct gpio_desc *gpio; + const char *type_name = NULL; const char *name_property; const char *type_property; - const char *type_name; + struct gpio_desc *gpio; int ret; if (dmi_check_system(rfkill_gpio_deny_table)) diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c index 1e19c605bcc8..dce5a3d8a964 100644 --- a/net/rxrpc/rxgk.c +++ b/net/rxrpc/rxgk.c @@ -475,7 +475,7 @@ static int rxgk_verify_packet_integrity(struct rxrpc_call *call, struct krb5_buffer metadata; unsigned int offset = sp->offset, len = sp->len; size_t data_offset = 0, data_len = len; - u32 ac; + u32 ac = 0; int ret = -ENOMEM; _enter(""); @@ -499,9 +499,10 @@ static int rxgk_verify_packet_integrity(struct rxrpc_call *call, ret = rxgk_verify_mic_skb(gk->krb5, gk->rx_Kc, &metadata, skb, &offset, &len, &ac); kfree(hdr); - if (ret == -EPROTO) { - rxrpc_abort_eproto(call, skb, ac, - rxgk_abort_1_verify_mic_eproto); + if (ret < 0) { + if (ret != -ENOMEM) + rxrpc_abort_eproto(call, skb, ac, + rxgk_abort_1_verify_mic_eproto); } else { sp->offset = offset; sp->len = len; @@ -524,15 +525,16 @@ static int rxgk_verify_packet_encrypted(struct rxrpc_call *call, struct rxgk_header hdr; unsigned int offset = sp->offset, len = sp->len; int ret; - u32 ac; + u32 ac = 0; _enter(""); ret = rxgk_decrypt_skb(gk->krb5, gk->rx_enc, skb, &offset, &len, &ac); - if (ret == -EPROTO) - rxrpc_abort_eproto(call, skb, ac, rxgk_abort_2_decrypt_eproto); - if (ret < 0) + if (ret < 0) { + if (ret != -ENOMEM) + rxrpc_abort_eproto(call, skb, ac, rxgk_abort_2_decrypt_eproto); goto error; + } if (len < sizeof(hdr)) { ret = rxrpc_abort_eproto(call, skb, RXGK_PACKETSHORT, diff --git a/net/rxrpc/rxgk_app.c b/net/rxrpc/rxgk_app.c index b94b77a1c317..30275cb5ba3e 100644 --- a/net/rxrpc/rxgk_app.c +++ b/net/rxrpc/rxgk_app.c @@ -54,6 +54,10 @@ int rxgk_yfs_decode_ticket(struct rxrpc_connection *conn, struct sk_buff *skb, _enter(""); + if (ticket_len < 10 * sizeof(__be32)) + return rxrpc_abort_conn(conn, skb, RXGK_INCONSISTENCY, -EPROTO, + rxgk_abort_resp_short_yfs_tkt); + /* Get the session key length */ ret = skb_copy_bits(skb, ticket_offset, tmp, sizeof(tmp)); if (ret < 0) @@ -187,7 +191,7 @@ int rxgk_extract_token(struct rxrpc_connection *conn, struct sk_buff *skb, struct key *server_key; unsigned int ticket_offset, ticket_len; u32 kvno, enctype; - int ret, ec; + int ret, ec = 0; struct { __be32 kvno; @@ -195,22 +199,23 @@ int rxgk_extract_token(struct rxrpc_connection *conn, struct sk_buff *skb, __be32 token_len; } container; + if (token_len < sizeof(container)) + goto short_packet; + /* Decode the RXGK_TokenContainer object. This tells us which server * key we should be using. We can then fetch the key, get the secret * and set up the crypto to extract the token. */ if (skb_copy_bits(skb, token_offset, &container, sizeof(container)) < 0) - return rxrpc_abort_conn(conn, skb, RXGK_PACKETSHORT, -EPROTO, - rxgk_abort_resp_tok_short); + goto short_packet; kvno = ntohl(container.kvno); enctype = ntohl(container.enctype); ticket_len = ntohl(container.token_len); ticket_offset = token_offset + sizeof(container); - if (xdr_round_up(ticket_len) > token_len - 3 * 4) - return rxrpc_abort_conn(conn, skb, RXGK_PACKETSHORT, -EPROTO, - rxgk_abort_resp_tok_short); + if (xdr_round_up(ticket_len) > token_len - sizeof(container)) + goto short_packet; _debug("KVNO %u", kvno); _debug("ENC %u", enctype); @@ -236,9 +241,11 @@ int rxgk_extract_token(struct rxrpc_connection *conn, struct sk_buff *skb, &ticket_offset, &ticket_len, &ec); crypto_free_aead(token_enc); token_enc = NULL; - if (ret < 0) - return rxrpc_abort_conn(conn, skb, ec, ret, - rxgk_abort_resp_tok_dec); + if (ret < 0) { + if (ret != -ENOMEM) + return rxrpc_abort_conn(conn, skb, ec, ret, + rxgk_abort_resp_tok_dec); + } ret = conn->security->default_decode_ticket(conn, skb, ticket_offset, ticket_len, _key); @@ -283,4 +290,8 @@ temporary_error: * also come out this way if the ticket decryption fails. */ return ret; + +short_packet: + return rxrpc_abort_conn(conn, skb, RXGK_PACKETSHORT, -EPROTO, + rxgk_abort_resp_tok_short); } diff --git a/net/rxrpc/rxgk_common.h b/net/rxrpc/rxgk_common.h index 7370a5655985..80164d89e19c 100644 --- a/net/rxrpc/rxgk_common.h +++ b/net/rxrpc/rxgk_common.h @@ -88,11 +88,16 @@ int rxgk_decrypt_skb(const struct krb5_enctype *krb5, *_offset += offset; *_len = len; break; + case -EBADMSG: /* Checksum mismatch. */ case -EPROTO: - case -EBADMSG: *_error_code = RXGK_SEALEDINCON; break; + case -EMSGSIZE: + *_error_code = RXGK_PACKETSHORT; + break; + case -ENOPKG: /* Would prefer RXGK_BADETYPE, but not available for YFS. */ default: + *_error_code = RXGK_INCONSISTENCY; break; } @@ -127,11 +132,16 @@ int rxgk_verify_mic_skb(const struct krb5_enctype *krb5, *_offset += offset; *_len = len; break; + case -EBADMSG: /* Checksum mismatch */ case -EPROTO: - case -EBADMSG: *_error_code = RXGK_SEALEDINCON; break; + case -EMSGSIZE: + *_error_code = RXGK_PACKETSHORT; + break; + case -ENOPKG: /* Would prefer RXGK_BADETYPE, but not available for YFS. */ default: + *_error_code = RXGK_INCONSISTENCY; break; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 73bc39281ef5..9b45fbdc90ca 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -276,8 +276,6 @@ EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue); static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode) { - if (unlikely(current->flags & PF_EXITING)) - return -EINTR; schedule(); if (signal_pending_state(mode, current)) return -ERESTARTSYS; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index c5f7bbf5775f..3aa987e7f072 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -407,9 +407,9 @@ xs_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags, int flags) iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1, alert_kvec.iov_len); ret = sock_recvmsg(sock, &msg, flags); - if (ret > 0 && - tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) { - iov_iter_revert(&msg.msg_iter, ret); + if (ret > 0) { + if (tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) + iov_iter_revert(&msg.msg_iter, ret); ret = xs_sock_process_cmsg(sock, &msg, msg_flags, &u.cmsg, -EAGAIN); } diff --git a/net/tls/tls.h b/net/tls/tls.h index 4e077068e6d9..e4c42731ce39 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -141,6 +141,7 @@ void update_sk_prot(struct sock *sk, struct tls_context *ctx); int wait_on_pending_writer(struct sock *sk, long *timeo); void tls_err_abort(struct sock *sk, int err); +void tls_strp_abort_strp(struct tls_strparser *strp, int err); int init_prot_info(struct tls_prot_info *prot, const struct tls_crypto_info *crypto_info, diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index d71643b494a1..98e12f0ff57e 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -13,7 +13,7 @@ static struct workqueue_struct *tls_strp_wq; -static void tls_strp_abort_strp(struct tls_strparser *strp, int err) +void tls_strp_abort_strp(struct tls_strparser *strp, int err) { if (strp->stopped) return; @@ -211,11 +211,17 @@ static int tls_strp_copyin_frag(struct tls_strparser *strp, struct sk_buff *skb, struct sk_buff *in_skb, unsigned int offset, size_t in_len) { + unsigned int nfrag = skb->len / PAGE_SIZE; size_t len, chunk; skb_frag_t *frag; int sz; - frag = &skb_shinfo(skb)->frags[skb->len / PAGE_SIZE]; + if (unlikely(nfrag >= skb_shinfo(skb)->nr_frags)) { + DEBUG_NET_WARN_ON_ONCE(1); + return -EMSGSIZE; + } + + frag = &skb_shinfo(skb)->frags[nfrag]; len = in_len; /* First make sure we got the header */ @@ -520,10 +526,8 @@ static int tls_strp_read_sock(struct tls_strparser *strp) tls_strp_load_anchor_with_queue(strp, inq); if (!strp->stm.full_len) { sz = tls_rx_msg_size(strp, strp->anchor); - if (sz < 0) { - tls_strp_abort_strp(strp, sz); + if (sz < 0) return sz; - } strp->stm.full_len = sz; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index bac65d0d4e3e..daac9fd4be7e 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2474,8 +2474,7 @@ int tls_rx_msg_size(struct tls_strparser *strp, struct sk_buff *skb) return data_len + TLS_HEADER_SIZE; read_failure: - tls_err_abort(strp->sk, ret); - + tls_strp_abort_strp(strp, ret); return ret; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 89519aa52893..852573423e52 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -7062,7 +7062,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, u32 seq, int flags, struct cfg80211_registered_device *rdev, struct net_device *dev, - const u8 *mac_addr, struct station_info *sinfo) + const u8 *mac_addr, struct station_info *sinfo, + bool link_stats) { void *hdr; struct nlattr *sinfoattr, *bss_param; @@ -7283,7 +7284,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, goto nla_put_failure; } - if (sinfo->valid_links) { + if (link_stats && sinfo->valid_links) { links = nla_nest_start(msg, NL80211_ATTR_MLO_LINKS); if (!links) goto nla_put_failure; @@ -7574,7 +7575,7 @@ static int nl80211_dump_station(struct sk_buff *skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wdev->netdev, mac_addr, - &sinfo) < 0) + &sinfo, false) < 0) goto out; sta_idx++; @@ -7635,7 +7636,7 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) if (nl80211_send_station(msg, NL80211_CMD_NEW_STATION, info->snd_portid, info->snd_seq, 0, - rdev, dev, mac_addr, &sinfo) < 0) { + rdev, dev, mac_addr, &sinfo, false) < 0) { nlmsg_free(msg); return -ENOBUFS; } @@ -19680,7 +19681,7 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr, return; if (nl80211_send_station(msg, NL80211_CMD_NEW_STATION, 0, 0, 0, - rdev, dev, mac_addr, sinfo) < 0) { + rdev, dev, mac_addr, sinfo, false) < 0) { nlmsg_free(msg); return; } @@ -19710,7 +19711,7 @@ void cfg80211_del_sta_sinfo(struct net_device *dev, const u8 *mac_addr, } if (nl80211_send_station(msg, NL80211_CMD_DEL_STATION, 0, 0, 0, - rdev, dev, mac_addr, sinfo) < 0) { + rdev, dev, mac_addr, sinfo, false) < 0) { nlmsg_free(msg); return; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 9c3acecc14b1..72e34bd2d925 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -36,6 +36,20 @@ #define TX_BATCH_SIZE 32 #define MAX_PER_SOCKET_BUDGET 32 +struct xsk_addr_node { + u64 addr; + struct list_head addr_node; +}; + +struct xsk_addr_head { + u32 num_descs; + struct list_head addrs_list; +}; + +static struct kmem_cache *xsk_tx_generic_cache; + +#define XSKCB(skb) ((struct xsk_addr_head *)((skb)->cb)) + void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { if (pool->cached_need_wakeup & XDP_WAKEUP_RX) @@ -532,24 +546,43 @@ static int xsk_wakeup(struct xdp_sock *xs, u8 flags) return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags); } -static int xsk_cq_reserve_addr_locked(struct xsk_buff_pool *pool, u64 addr) +static int xsk_cq_reserve_locked(struct xsk_buff_pool *pool) { unsigned long flags; int ret; spin_lock_irqsave(&pool->cq_lock, flags); - ret = xskq_prod_reserve_addr(pool->cq, addr); + ret = xskq_prod_reserve(pool->cq); spin_unlock_irqrestore(&pool->cq_lock, flags); return ret; } -static void xsk_cq_submit_locked(struct xsk_buff_pool *pool, u32 n) +static void xsk_cq_submit_addr_locked(struct xsk_buff_pool *pool, + struct sk_buff *skb) { + struct xsk_addr_node *pos, *tmp; + u32 descs_processed = 0; unsigned long flags; + u32 idx; spin_lock_irqsave(&pool->cq_lock, flags); - xskq_prod_submit_n(pool->cq, n); + idx = xskq_get_prod(pool->cq); + + xskq_prod_write_addr(pool->cq, idx, + (u64)(uintptr_t)skb_shinfo(skb)->destructor_arg); + descs_processed++; + + if (unlikely(XSKCB(skb)->num_descs > 1)) { + list_for_each_entry_safe(pos, tmp, &XSKCB(skb)->addrs_list, addr_node) { + xskq_prod_write_addr(pool->cq, idx + descs_processed, + pos->addr); + descs_processed++; + list_del(&pos->addr_node); + kmem_cache_free(xsk_tx_generic_cache, pos); + } + } + xskq_prod_submit_n(pool->cq, descs_processed); spin_unlock_irqrestore(&pool->cq_lock, flags); } @@ -562,9 +595,14 @@ static void xsk_cq_cancel_locked(struct xsk_buff_pool *pool, u32 n) spin_unlock_irqrestore(&pool->cq_lock, flags); } +static void xsk_inc_num_desc(struct sk_buff *skb) +{ + XSKCB(skb)->num_descs++; +} + static u32 xsk_get_num_desc(struct sk_buff *skb) { - return skb ? (long)skb_shinfo(skb)->destructor_arg : 0; + return XSKCB(skb)->num_descs; } static void xsk_destruct_skb(struct sk_buff *skb) @@ -576,23 +614,33 @@ static void xsk_destruct_skb(struct sk_buff *skb) *compl->tx_timestamp = ktime_get_tai_fast_ns(); } - xsk_cq_submit_locked(xdp_sk(skb->sk)->pool, xsk_get_num_desc(skb)); + xsk_cq_submit_addr_locked(xdp_sk(skb->sk)->pool, skb); sock_wfree(skb); } -static void xsk_set_destructor_arg(struct sk_buff *skb) +static void xsk_set_destructor_arg(struct sk_buff *skb, u64 addr) { - long num = xsk_get_num_desc(xdp_sk(skb->sk)->skb) + 1; - - skb_shinfo(skb)->destructor_arg = (void *)num; + BUILD_BUG_ON(sizeof(struct xsk_addr_head) > sizeof(skb->cb)); + INIT_LIST_HEAD(&XSKCB(skb)->addrs_list); + XSKCB(skb)->num_descs = 0; + skb_shinfo(skb)->destructor_arg = (void *)(uintptr_t)addr; } static void xsk_consume_skb(struct sk_buff *skb) { struct xdp_sock *xs = xdp_sk(skb->sk); + u32 num_descs = xsk_get_num_desc(skb); + struct xsk_addr_node *pos, *tmp; + + if (unlikely(num_descs > 1)) { + list_for_each_entry_safe(pos, tmp, &XSKCB(skb)->addrs_list, addr_node) { + list_del(&pos->addr_node); + kmem_cache_free(xsk_tx_generic_cache, pos); + } + } skb->destructor = sock_wfree; - xsk_cq_cancel_locked(xs->pool, xsk_get_num_desc(skb)); + xsk_cq_cancel_locked(xs->pool, num_descs); /* Free skb without triggering the perf drop trace */ consume_skb(skb); xs->skb = NULL; @@ -609,6 +657,7 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, { struct xsk_buff_pool *pool = xs->pool; u32 hr, len, ts, offset, copy, copied; + struct xsk_addr_node *xsk_addr; struct sk_buff *skb = xs->skb; struct page *page; void *buffer; @@ -623,6 +672,19 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, return ERR_PTR(err); skb_reserve(skb, hr); + + xsk_set_destructor_arg(skb, desc->addr); + } else { + xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL); + if (!xsk_addr) + return ERR_PTR(-ENOMEM); + + /* in case of -EOVERFLOW that could happen below, + * xsk_consume_skb() will release this node as whole skb + * would be dropped, which implies freeing all list elements + */ + xsk_addr->addr = desc->addr; + list_add_tail(&xsk_addr->addr_node, &XSKCB(skb)->addrs_list); } addr = desc->addr; @@ -694,8 +756,11 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, err = skb_store_bits(skb, 0, buffer, len); if (unlikely(err)) goto free_err; + + xsk_set_destructor_arg(skb, desc->addr); } else { int nr_frags = skb_shinfo(skb)->nr_frags; + struct xsk_addr_node *xsk_addr; struct page *page; u8 *vaddr; @@ -710,12 +775,22 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, goto free_err; } + xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL); + if (!xsk_addr) { + __free_page(page); + err = -ENOMEM; + goto free_err; + } + vaddr = kmap_local_page(page); memcpy(vaddr, buffer, len); kunmap_local(vaddr); skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE); refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc); + + xsk_addr->addr = desc->addr; + list_add_tail(&xsk_addr->addr_node, &XSKCB(skb)->addrs_list); } if (first_frag && desc->options & XDP_TX_METADATA) { @@ -759,7 +834,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, skb->mark = READ_ONCE(xs->sk.sk_mark); skb->destructor = xsk_destruct_skb; xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta); - xsk_set_destructor_arg(skb); + xsk_inc_num_desc(skb); return skb; @@ -769,7 +844,7 @@ free_err: if (err == -EOVERFLOW) { /* Drop the packet */ - xsk_set_destructor_arg(xs->skb); + xsk_inc_num_desc(xs->skb); xsk_drop_skb(xs->skb); xskq_cons_release(xs->tx); } else { @@ -812,7 +887,7 @@ static int __xsk_generic_xmit(struct sock *sk) * if there is space in it. This avoids having to implement * any buffering in the Tx path. */ - err = xsk_cq_reserve_addr_locked(xs->pool, desc.addr); + err = xsk_cq_reserve_locked(xs->pool); if (err) { err = -EAGAIN; goto out; @@ -1815,8 +1890,18 @@ static int __init xsk_init(void) if (err) goto out_pernet; + xsk_tx_generic_cache = kmem_cache_create("xsk_generic_xmit_cache", + sizeof(struct xsk_addr_node), + 0, SLAB_HWCACHE_ALIGN, NULL); + if (!xsk_tx_generic_cache) { + err = -ENOMEM; + goto out_unreg_notif; + } + return 0; +out_unreg_notif: + unregister_netdevice_notifier(&xsk_netdev_notifier); out_pernet: unregister_pernet_subsys(&xsk_net_ops); out_sk: diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 46d87e961ad6..f16f390370dc 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -344,6 +344,11 @@ static inline u32 xskq_cons_present_entries(struct xsk_queue *q) /* Functions for producers */ +static inline u32 xskq_get_prod(struct xsk_queue *q) +{ + return READ_ONCE(q->ring->producer); +} + static inline u32 xskq_prod_nb_free(struct xsk_queue *q, u32 max) { u32 free_entries = q->nentries - (q->cached_prod - q->cached_cons); @@ -390,6 +395,13 @@ static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr) return 0; } +static inline void xskq_prod_write_addr(struct xsk_queue *q, u32 idx, u64 addr) +{ + struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; + + ring->desc[idx & q->ring_mask] = addr; +} + static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_desc *descs, u32 nb_entries) { diff --git a/rust/kernel/device.rs b/rust/kernel/device.rs index 5902b3714a16..a1db49eb159a 100644 --- a/rust/kernel/device.rs +++ b/rust/kernel/device.rs @@ -138,7 +138,9 @@ pub mod property; /// } /// ``` /// -/// An example for a class device implementation is [`drm::Device`]. +/// An example for a class device implementation is +#[cfg_attr(CONFIG_DRM = "y", doc = "[`drm::Device`](kernel::drm::Device).")] +#[cfg_attr(not(CONFIG_DRM = "y"), doc = "`drm::Device`.")] /// /// # Invariants /// @@ -151,7 +153,6 @@ pub mod property; /// dropped from any thread. /// /// [`AlwaysRefCounted`]: kernel::types::AlwaysRefCounted -/// [`drm::Device`]: kernel::drm::Device /// [`impl_device_context_deref`]: kernel::impl_device_context_deref /// [`pci::Device`]: kernel::pci::Device /// [`platform::Device`]: kernel::platform::Device diff --git a/samples/damon/mtier.c b/samples/damon/mtier.c index 7ebd352138e4..beaf36657dea 100644 --- a/samples/damon/mtier.c +++ b/samples/damon/mtier.c @@ -208,6 +208,9 @@ static int damon_sample_mtier_enable_store( if (enabled == is_enabled) return 0; + if (!init_called) + return 0; + if (enabled) { err = damon_sample_mtier_start(); if (err) diff --git a/samples/damon/prcl.c b/samples/damon/prcl.c index 1b839c06a612..0226652f94d5 100644 --- a/samples/damon/prcl.c +++ b/samples/damon/prcl.c @@ -137,6 +137,9 @@ static int damon_sample_prcl_enable_store( if (enabled == is_enabled) return 0; + if (!init_called) + return 0; + if (enabled) { err = damon_sample_prcl_start(); if (err) diff --git a/samples/damon/wsse.c b/samples/damon/wsse.c index da052023b099..21eaf15f987d 100644 --- a/samples/damon/wsse.c +++ b/samples/damon/wsse.c @@ -118,6 +118,9 @@ static int damon_sample_wsse_enable_store( return 0; if (enabled) { + if (!init_called) + return 0; + err = damon_sample_wsse_start(); if (err) enabled = false; diff --git a/samples/ftrace/ftrace-direct-modify.c b/samples/ftrace/ftrace-direct-modify.c index cfea7a38befb..da3a9f2091f5 100644 --- a/samples/ftrace/ftrace-direct-modify.c +++ b/samples/ftrace/ftrace-direct-modify.c @@ -75,8 +75,8 @@ asm ( CALL_DEPTH_ACCOUNT " call my_direct_func1\n" " leave\n" -" .size my_tramp1, .-my_tramp1\n" ASM_RET +" .size my_tramp1, .-my_tramp1\n" " .type my_tramp2, @function\n" " .globl my_tramp2\n" diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 85bb8c4d3b17..f267437c9698 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -3702,6 +3702,7 @@ enum { ALC236_FIXUP_DELL_DUAL_CODECS, ALC287_FIXUP_CS35L41_I2C_2_THINKPAD_ACPI, ALC287_FIXUP_TAS2781_I2C, + ALC295_FIXUP_DELL_TAS2781_I2C, ALC245_FIXUP_TAS2781_SPI_2, ALC287_FIXUP_TXNW2781_I2C, ALC287_FIXUP_YOGA7_14ARB7_I2C, @@ -5167,6 +5168,12 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc294_fixup_gx502_hp, }, + [ALC295_FIXUP_DELL_TAS2781_I2C] = { + .type = HDA_FIXUP_FUNC, + .v.func = tas2781_fixup_tias_i2c, + .chained = true, + .chain_id = ALC289_FIXUP_DUAL_SPK + }, [ALC294_FIXUP_ASUS_GU502_PINS] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -6289,8 +6296,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0c1e, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS), SND_PCI_QUIRK(0x1028, 0x0c28, "Dell Inspiron 16 Plus 7630", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), SND_PCI_QUIRK(0x1028, 0x0c4d, "Dell", ALC287_FIXUP_CS35L41_I2C_4), - SND_PCI_QUIRK(0x1028, 0x0c94, "Dell Polaris 3 metal", ALC287_FIXUP_TAS2781_I2C), - SND_PCI_QUIRK(0x1028, 0x0c96, "Dell Polaris 2in1", ALC287_FIXUP_TAS2781_I2C), + SND_PCI_QUIRK(0x1028, 0x0c94, "Dell Polaris 3 metal", ALC295_FIXUP_DELL_TAS2781_I2C), + SND_PCI_QUIRK(0x1028, 0x0c96, "Dell Polaris 2in1", ALC295_FIXUP_DELL_TAS2781_I2C), SND_PCI_QUIRK(0x1028, 0x0cbd, "Dell Oasis 13 CS MTL-U", ALC289_FIXUP_DELL_CS35L41_SPI_2), SND_PCI_QUIRK(0x1028, 0x0cbe, "Dell Oasis 13 2-IN-1 MTL-U", ALC289_FIXUP_DELL_CS35L41_SPI_2), SND_PCI_QUIRK(0x1028, 0x0cbf, "Dell Oasis 13 Low Weight MTU-L", ALC289_FIXUP_DELL_CS35L41_SPI_2), @@ -6469,6 +6476,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8992, "HP EliteBook 845 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8994, "HP EliteBook 855 G9", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8995, "HP EliteBook 855 G9", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x89a0, "HP Laptop 15-dw4xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x89a4, "HP ProBook 440 G9", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89a6, "HP ProBook 450 G9", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89aa, "HP EliteBook 630 G9", ALC236_FIXUP_HP_GPIO_LED), @@ -7071,8 +7079,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x38be, "Yoga S980-14.5 proX YC Dual", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38bf, "Yoga S980-14.5 proX LX Dual", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38c3, "Y980 DUAL", ALC287_FIXUP_TAS2781_I2C), - SND_PCI_QUIRK(0x17aa, 0x38c7, "Thinkbook 13x Gen 4", ALC287_FIXUP_CS35L41_I2C_4), - SND_PCI_QUIRK(0x17aa, 0x38c8, "Thinkbook 13x Gen 4", ALC287_FIXUP_CS35L41_I2C_4), + SND_PCI_QUIRK(0x17aa, 0x38c7, "Thinkbook 13x Gen 4", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), + SND_PCI_QUIRK(0x17aa, 0x38c8, "Thinkbook 13x Gen 4", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), SND_PCI_QUIRK(0x17aa, 0x38cb, "Y790 YG DUAL", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38cd, "Y790 VECO DUAL", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38d2, "Lenovo Yoga 9 14IMH9", ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN), @@ -7093,6 +7101,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3913, "Lenovo 145", ALC236_FIXUP_LENOVO_INV_DMIC), SND_PCI_QUIRK(0x17aa, 0x391f, "Yoga S990-16 pro Quad YC Quad", ALC287_FIXUP_TXNW2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3920, "Yoga S990-16 pro Quad VECO Quad", ALC287_FIXUP_TXNW2781_I2C), + SND_PCI_QUIRK(0x17aa, 0x3929, "Thinkbook 13x Gen 5", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), + SND_PCI_QUIRK(0x17aa, 0x392b, "Thinkbook 13x Gen 5", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K), diff --git a/sound/hda/codecs/side-codecs/cs35l41_hda_property.c b/sound/hda/codecs/side-codecs/cs35l41_hda_property.c index d8249d997c2a..16d5ea77192f 100644 --- a/sound/hda/codecs/side-codecs/cs35l41_hda_property.c +++ b/sound/hda/codecs/side-codecs/cs35l41_hda_property.c @@ -135,6 +135,8 @@ static const struct cs35l41_config cs35l41_config_table[] = { { "17AA38C8", 4, INTERNAL, { CS35L41_RIGHT, CS35L41_LEFT, CS35L41_RIGHT, CS35L41_LEFT }, 0, 2, -1, 1000, 4500, 24 }, { "17AA38F9", 2, EXTERNAL, { CS35L41_RIGHT, CS35L41_LEFT, 0, 0 }, 0, 2, -1, 0, 0, 0 }, { "17AA38FA", 2, EXTERNAL, { CS35L41_RIGHT, CS35L41_LEFT, 0, 0 }, 0, 2, -1, 0, 0, 0 }, + { "17AA3929", 4, INTERNAL, { CS35L41_RIGHT, CS35L41_LEFT, CS35L41_RIGHT, CS35L41_LEFT }, 0, 2, -1, 1000, 4500, 24 }, + { "17AA392B", 4, INTERNAL, { CS35L41_RIGHT, CS35L41_LEFT, CS35L41_RIGHT, CS35L41_LEFT }, 0, 2, -1, 1000, 4500, 24 }, {} }; @@ -558,6 +560,8 @@ static const struct cs35l41_prop_model cs35l41_prop_model_table[] = { { "CSC3551", "17AA38C8", generic_dsd_config }, { "CSC3551", "17AA38F9", generic_dsd_config }, { "CSC3551", "17AA38FA", generic_dsd_config }, + { "CSC3551", "17AA3929", generic_dsd_config }, + { "CSC3551", "17AA392B", generic_dsd_config }, {} }; diff --git a/sound/hda/codecs/side-codecs/tas2781_hda.c b/sound/hda/codecs/side-codecs/tas2781_hda.c index f46d2e06c64f..96e6d82dc69e 100644 --- a/sound/hda/codecs/side-codecs/tas2781_hda.c +++ b/sound/hda/codecs/side-codecs/tas2781_hda.c @@ -33,6 +33,23 @@ const efi_guid_t tasdev_fct_efi_guid[] = { }; EXPORT_SYMBOL_NS_GPL(tasdev_fct_efi_guid, "SND_HDA_SCODEC_TAS2781"); +/* + * The order of calibrated-data writing function is a bit different from the + * order in UEFI. Here is the conversion to match the order of calibrated-data + * writing function. + */ +static void cali_cnv(unsigned char *data, unsigned int base, int offset) +{ + struct cali_reg reg_data; + + memcpy(®_data, &data[base], sizeof(reg_data)); + /* the data order has to be swapped between r0_low_reg and inv0_reg */ + swap(reg_data.r0_low_reg, reg_data.invr0_reg); + + cpu_to_be32_array((__force __be32 *)(data + offset + 1), + (u32 *)®_data, TASDEV_CALIB_N); +} + static void tas2781_apply_calib(struct tasdevice_priv *p) { struct calidata *cali_data = &p->cali_data; @@ -103,8 +120,7 @@ static void tas2781_apply_calib(struct tasdevice_priv *p) data[l] = k; oft++; - for (i = 0; i < TASDEV_CALIB_N * 4; i++) - data[l + i + 1] = data[4 * oft + i]; + cali_cnv(data, 4 * oft, l); k++; } } @@ -130,9 +146,8 @@ static void tas2781_apply_calib(struct tasdevice_priv *p) for (j = p->ndev - 1; j >= 0; j--) { l = j * (cali_data->cali_dat_sz_per_dev + 1); - for (i = TASDEV_CALIB_N * 4; i > 0 ; i--) - data[l + i] = data[p->index * 5 + i]; - data[l+i] = j; + cali_cnv(data, cali_data->cali_dat_sz_per_dev * j, l); + data[l] = j; } } @@ -178,6 +193,11 @@ int tas2781_save_calibration(struct tas2781_hda *hda) efi_status_t status; int i; + if (!efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE)) { + dev_err(p->dev, "%s: NO EFI FOUND!\n", __func__); + return -EINVAL; + } + if (hda->catlog_id < LENOVO) efi_guid = tasdev_fct_efi_guid[hda->catlog_id]; diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c index 45a70fbf6205..b5b7a1e82b75 100644 --- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c +++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c @@ -315,6 +315,11 @@ static int tas2563_save_calibration(struct tas2781_hda *h) unsigned int attr; int ret, i, j, k; + if (!efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE)) { + dev_err(p->dev, "%s: NO EFI FOUND!\n", __func__); + return -EINVAL; + } + cd->cali_dat_sz_per_dev = TAS2563_CAL_DATA_SIZE * TASDEV_CALIB_N; /* extra byte for each device is the device number */ diff --git a/sound/hda/core/intel-dsp-config.c b/sound/hda/core/intel-dsp-config.c index c15284742899..2a9e35cddcf7 100644 --- a/sound/hda/core/intel-dsp-config.c +++ b/sound/hda/core/intel-dsp-config.c @@ -650,6 +650,8 @@ static int snd_intel_dsp_check_soundwire(struct pci_dev *pci) int ret; handle = ACPI_HANDLE(&pci->dev); + if (!handle) + return -ENODEV; ret = sdw_intel_acpi_scan(handle, &info); if (ret < 0) diff --git a/sound/soc/amd/acp/acp-i2s.c b/sound/soc/amd/acp/acp-i2s.c index 617690362ad7..4ba0a66981ea 100644 --- a/sound/soc/amd/acp/acp-i2s.c +++ b/sound/soc/amd/acp/acp-i2s.c @@ -73,7 +73,7 @@ static int acp_i2s_set_fmt(struct snd_soc_dai *cpu_dai, unsigned int fmt) { struct device *dev = cpu_dai->component->dev; - struct acp_chip_info *chip = dev_get_platdata(dev); + struct acp_chip_info *chip = dev_get_drvdata(dev->parent); int mode; mode = fmt & SND_SOC_DAIFMT_FORMAT_MASK; @@ -199,7 +199,7 @@ static int acp_i2s_hwparams(struct snd_pcm_substream *substream, struct snd_pcm_ u32 reg_val, fmt_reg, tdm_fmt; u32 lrclk_div_val, bclk_div_val; - chip = dev_get_platdata(dev); + chip = dev_get_drvdata(dev->parent); rsrc = chip->rsrc; /* These values are as per Hardware Spec */ @@ -386,7 +386,7 @@ static int acp_i2s_trigger(struct snd_pcm_substream *substream, int cmd, struct { struct acp_stream *stream = substream->runtime->private_data; struct device *dev = dai->component->dev; - struct acp_chip_info *chip = dev_get_platdata(dev); + struct acp_chip_info *chip = dev_get_drvdata(dev->parent); struct acp_resource *rsrc = chip->rsrc; u32 val, period_bytes, reg_val, ier_val, water_val, buf_size, buf_reg; @@ -516,14 +516,13 @@ static int acp_i2s_trigger(struct snd_pcm_substream *substream, int cmd, struct static int acp_i2s_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct device *dev = dai->component->dev; - struct acp_chip_info *chip = dev_get_platdata(dev); + struct acp_chip_info *chip = dev_get_drvdata(dev->parent); struct acp_resource *rsrc = chip->rsrc; struct acp_stream *stream = substream->runtime->private_data; u32 reg_dma_size = 0, reg_fifo_size = 0, reg_fifo_addr = 0; u32 phy_addr = 0, acp_fifo_addr = 0, ext_int_ctrl; unsigned int dir = substream->stream; - chip = dev_get_platdata(dev); switch (dai->driver->id) { case I2S_SP_INSTANCE: if (dir == SNDRV_PCM_STREAM_PLAYBACK) { @@ -632,7 +631,7 @@ static int acp_i2s_startup(struct snd_pcm_substream *substream, struct snd_soc_d { struct acp_stream *stream = substream->runtime->private_data; struct device *dev = dai->component->dev; - struct acp_chip_info *chip = dev_get_platdata(dev); + struct acp_chip_info *chip = dev_get_drvdata(dev->parent); struct acp_resource *rsrc = chip->rsrc; unsigned int dir = substream->stream; unsigned int irq_bit = 0; diff --git a/sound/soc/amd/acp/acp-sdw-legacy-mach.c b/sound/soc/amd/acp/acp-sdw-legacy-mach.c index c2197b75a7dd..5a3cfedacbaf 100644 --- a/sound/soc/amd/acp/acp-sdw-legacy-mach.c +++ b/sound/soc/amd/acp/acp-sdw-legacy-mach.c @@ -79,6 +79,22 @@ static const struct dmi_system_id soc_sdw_quirk_table[] = { }, .driver_data = (void *)(ASOC_SDW_CODEC_SPKR), }, + { + .callback = soc_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0DD3"), + }, + .driver_data = (void *)(ASOC_SDW_CODEC_SPKR), + }, + { + .callback = soc_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0DD4"), + }, + .driver_data = (void *)(ASOC_SDW_CODEC_SPKR), + }, {} }; diff --git a/sound/soc/amd/acp/amd.h b/sound/soc/amd/acp/amd.h index cb8d97122f95..73a028e67246 100644 --- a/sound/soc/amd/acp/amd.h +++ b/sound/soc/amd/acp/amd.h @@ -130,7 +130,7 @@ #define PDM_DMA_INTR_MASK 0x10000 #define PDM_DEC_64 0x2 #define PDM_CLK_FREQ_MASK 0x07 -#define PDM_MISC_CTRL_MASK 0x10 +#define PDM_MISC_CTRL_MASK 0x18 #define PDM_ENABLE 0x01 #define PDM_DISABLE 0x00 #define DMA_EN_MASK 0x02 diff --git a/sound/soc/codecs/lpass-rx-macro.c b/sound/soc/codecs/lpass-rx-macro.c index 238dbdb46c18..a8fc842cc94e 100644 --- a/sound/soc/codecs/lpass-rx-macro.c +++ b/sound/soc/codecs/lpass-rx-macro.c @@ -618,6 +618,7 @@ static struct interp_sample_rate sr_val_tbl[] = { {176400, 0xB}, {352800, 0xC}, }; +/* Matches also rx_macro_mux_text */ enum { RX_MACRO_AIF1_PB, RX_MACRO_AIF2_PB, @@ -722,6 +723,7 @@ static const char * const rx_int2_2_interp_mux_text[] = { "ZERO", "RX INT2_2 MUX", }; +/* Order must match RX_MACRO_MAX_DAIS enum (offset by 1) */ static const char *const rx_macro_mux_text[] = { "ZERO", "AIF1_PB", "AIF2_PB", "AIF3_PB", "AIF4_PB" }; @@ -2474,6 +2476,7 @@ static int rx_macro_mux_put(struct snd_kcontrol *kcontrol, struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; struct snd_soc_dapm_update *update = NULL; u32 rx_port_value = ucontrol->value.enumerated.item[0]; + unsigned int dai_id; u32 aif_rst; struct rx_macro *rx = snd_soc_component_get_drvdata(component); @@ -2490,19 +2493,24 @@ static int rx_macro_mux_put(struct snd_kcontrol *kcontrol, switch (rx_port_value) { case 0: - if (rx->active_ch_cnt[aif_rst]) { - clear_bit(widget->shift, - &rx->active_ch_mask[aif_rst]); - rx->active_ch_cnt[aif_rst]--; + /* + * active_ch_cnt and active_ch_mask use DAI IDs (RX_MACRO_MAX_DAIS). + * active_ch_cnt == 0 was tested in if() above. + */ + dai_id = aif_rst - 1; + if (rx->active_ch_cnt[dai_id]) { + clear_bit(widget->shift, &rx->active_ch_mask[dai_id]); + rx->active_ch_cnt[dai_id]--; } break; case 1: case 2: case 3: case 4: - set_bit(widget->shift, - &rx->active_ch_mask[rx_port_value]); - rx->active_ch_cnt[rx_port_value]++; + /* active_ch_cnt and active_ch_mask use DAI IDs (WSA_MACRO_MAX_DAIS). */ + dai_id = rx_port_value - 1; + set_bit(widget->shift, &rx->active_ch_mask[dai_id]); + rx->active_ch_cnt[dai_id]++; break; default: dev_err(component->dev, diff --git a/sound/soc/codecs/lpass-wsa-macro.c b/sound/soc/codecs/lpass-wsa-macro.c index da6adb3de21d..d7eec9fdaf9c 100644 --- a/sound/soc/codecs/lpass-wsa-macro.c +++ b/sound/soc/codecs/lpass-wsa-macro.c @@ -368,6 +368,7 @@ static struct interp_sample_rate int_mix_sample_rate_val[] = { {192000, 0x6}, /* 192K */ }; +/* Matches also rx_mux_text */ enum { WSA_MACRO_AIF1_PB, WSA_MACRO_AIF_MIX1_PB, @@ -465,6 +466,7 @@ static const char *const rx_mix_ec_text[] = { "ZERO", "RX_MIX_TX0", "RX_MIX_TX1" }; +/* Order must match WSA_MACRO_MAX_DAIS enum (offset by 1) */ static const char *const rx_mux_text[] = { "ZERO", "AIF1_PB", "AIF_MIX1_PB" }; @@ -2207,6 +2209,7 @@ static int wsa_macro_rx_mux_put(struct snd_kcontrol *kcontrol, u32 rx_port_value = ucontrol->value.integer.value[0]; u32 bit_input; u32 aif_rst; + unsigned int dai_id; struct wsa_macro *wsa = snd_soc_component_get_drvdata(component); aif_rst = wsa->rx_port_value[widget->shift]; @@ -2224,17 +2227,22 @@ static int wsa_macro_rx_mux_put(struct snd_kcontrol *kcontrol, switch (rx_port_value) { case 0: - if (wsa->active_ch_cnt[aif_rst]) { - clear_bit(bit_input, - &wsa->active_ch_mask[aif_rst]); - wsa->active_ch_cnt[aif_rst]--; + /* + * active_ch_cnt and active_ch_mask use DAI IDs (WSA_MACRO_MAX_DAIS). + * active_ch_cnt == 0 was tested in if() above. + */ + dai_id = aif_rst - 1; + if (wsa->active_ch_cnt[dai_id]) { + clear_bit(bit_input, &wsa->active_ch_mask[dai_id]); + wsa->active_ch_cnt[dai_id]--; } break; case 1: case 2: - set_bit(bit_input, - &wsa->active_ch_mask[rx_port_value]); - wsa->active_ch_cnt[rx_port_value]++; + /* active_ch_cnt and active_ch_mask use DAI IDs (WSA_MACRO_MAX_DAIS). */ + dai_id = rx_port_value - 1; + set_bit(bit_input, &wsa->active_ch_mask[dai_id]); + wsa->active_ch_cnt[dai_id]++; break; default: dev_err(component->dev, diff --git a/sound/soc/codecs/rt5682s.c b/sound/soc/codecs/rt5682s.c index 80b921695e7d..1d80a4b862e2 100644 --- a/sound/soc/codecs/rt5682s.c +++ b/sound/soc/codecs/rt5682s.c @@ -653,14 +653,15 @@ static void rt5682s_sar_power_mode(struct snd_soc_component *component, int mode switch (mode) { case SAR_PWR_SAVING: snd_soc_component_update_bits(component, RT5682S_CBJ_CTRL_3, - RT5682S_CBJ_IN_BUF_MASK, RT5682S_CBJ_IN_BUF_DIS); + RT5682S_CBJ_IN_BUF_MASK, RT5682S_CBJ_IN_BUF_EN); snd_soc_component_update_bits(component, RT5682S_CBJ_CTRL_1, - RT5682S_MB1_PATH_MASK | RT5682S_MB2_PATH_MASK, - RT5682S_CTRL_MB1_REG | RT5682S_CTRL_MB2_REG); + RT5682S_MB1_PATH_MASK | RT5682S_MB2_PATH_MASK | + RT5682S_VREF_POW_MASK, RT5682S_CTRL_MB1_FSM | + RT5682S_CTRL_MB2_FSM | RT5682S_VREF_POW_FSM); snd_soc_component_update_bits(component, RT5682S_SAR_IL_CMD_1, RT5682S_SAR_BUTDET_MASK | RT5682S_SAR_BUTDET_POW_MASK | RT5682S_SAR_SEL_MB1_2_CTL_MASK, RT5682S_SAR_BUTDET_DIS | - RT5682S_SAR_BUTDET_POW_SAV | RT5682S_SAR_SEL_MB1_2_MANU); + RT5682S_SAR_BUTDET_POW_NORM | RT5682S_SAR_SEL_MB1_2_MANU); usleep_range(5000, 5500); snd_soc_component_update_bits(component, RT5682S_SAR_IL_CMD_1, RT5682S_SAR_BUTDET_MASK, RT5682S_SAR_BUTDET_EN); @@ -688,7 +689,7 @@ static void rt5682s_sar_power_mode(struct snd_soc_component *component, int mode snd_soc_component_update_bits(component, RT5682S_SAR_IL_CMD_1, RT5682S_SAR_BUTDET_MASK | RT5682S_SAR_BUTDET_POW_MASK | RT5682S_SAR_SEL_MB1_2_CTL_MASK, RT5682S_SAR_BUTDET_DIS | - RT5682S_SAR_BUTDET_POW_SAV | RT5682S_SAR_SEL_MB1_2_MANU); + RT5682S_SAR_BUTDET_POW_NORM | RT5682S_SAR_SEL_MB1_2_MANU); break; default: dev_err(component->dev, "Invalid SAR Power mode: %d\n", mode); @@ -725,7 +726,7 @@ static void rt5682s_disable_push_button_irq(struct snd_soc_component *component) snd_soc_component_update_bits(component, RT5682S_SAR_IL_CMD_1, RT5682S_SAR_BUTDET_MASK | RT5682S_SAR_BUTDET_POW_MASK | RT5682S_SAR_SEL_MB1_2_CTL_MASK, RT5682S_SAR_BUTDET_DIS | - RT5682S_SAR_BUTDET_POW_SAV | RT5682S_SAR_SEL_MB1_2_MANU); + RT5682S_SAR_BUTDET_POW_NORM | RT5682S_SAR_SEL_MB1_2_MANU); } /** @@ -786,7 +787,7 @@ static int rt5682s_headset_detect(struct snd_soc_component *component, int jack_ jack_type = SND_JACK_HEADSET; snd_soc_component_write(component, RT5682S_SAR_IL_CMD_3, 0x024c); snd_soc_component_update_bits(component, RT5682S_CBJ_CTRL_1, - RT5682S_FAST_OFF_MASK, RT5682S_FAST_OFF_EN); + RT5682S_FAST_OFF_MASK, RT5682S_FAST_OFF_DIS); snd_soc_component_update_bits(component, RT5682S_SAR_IL_CMD_1, RT5682S_SAR_SEL_MB1_2_MASK, val << RT5682S_SAR_SEL_MB1_2_SFT); rt5682s_enable_push_button_irq(component); @@ -966,7 +967,7 @@ static int rt5682s_set_jack_detect(struct snd_soc_component *component, RT5682S_EMB_JD_MASK | RT5682S_DET_TYPE | RT5682S_POL_FAST_OFF_MASK | RT5682S_MIC_CAP_MASK, RT5682S_EMB_JD_EN | RT5682S_DET_TYPE | - RT5682S_POL_FAST_OFF_HIGH | RT5682S_MIC_CAP_HS); + RT5682S_POL_FAST_OFF_LOW | RT5682S_MIC_CAP_HS); regmap_update_bits(rt5682s->regmap, RT5682S_SAR_IL_CMD_1, RT5682S_SAR_POW_MASK, RT5682S_SAR_POW_EN); regmap_update_bits(rt5682s->regmap, RT5682S_GPIO_CTRL_1, diff --git a/sound/soc/codecs/rt712-sdca.c b/sound/soc/codecs/rt712-sdca.c index 5b298db5f0f6..0ebaae426e73 100644 --- a/sound/soc/codecs/rt712-sdca.c +++ b/sound/soc/codecs/rt712-sdca.c @@ -1890,11 +1890,9 @@ int rt712_sdca_io_init(struct device *dev, struct sdw_slave *slave) rt712_sdca_va_io_init(rt712); } else { - if (!rt712->dmic_function_found) { - dev_err(&slave->dev, "%s RT712 VB detected but no SMART_MIC function exposed in ACPI\n", + if (!rt712->dmic_function_found) + dev_warn(&slave->dev, "%s RT712 VB detected but no SMART_MIC function exposed in ACPI\n", __func__); - goto suspend; - } /* multilanes and DMIC are supported by rt712vb */ prop->lane_control_support = true; diff --git a/sound/soc/codecs/sma1307.c b/sound/soc/codecs/sma1307.c index 6a601e7134ea..b683e676640d 100644 --- a/sound/soc/codecs/sma1307.c +++ b/sound/soc/codecs/sma1307.c @@ -1737,9 +1737,10 @@ static void sma1307_setting_loaded(struct sma1307_priv *sma1307, const char *fil sma1307->set.checksum = data[sma1307->set.header_size - 2]; sma1307->set.num_mode = data[sma1307->set.header_size - 1]; num_mode = sma1307->set.num_mode; - sma1307->set.header = devm_kzalloc(sma1307->dev, - sma1307->set.header_size, - GFP_KERNEL); + sma1307->set.header = devm_kmalloc_array(sma1307->dev, + sma1307->set.header_size, + sizeof(int), + GFP_KERNEL); if (!sma1307->set.header) { sma1307->set.status = false; return; diff --git a/sound/soc/codecs/wm8940.c b/sound/soc/codecs/wm8940.c index 401ee20897b1..94873ea63014 100644 --- a/sound/soc/codecs/wm8940.c +++ b/sound/soc/codecs/wm8940.c @@ -220,7 +220,7 @@ static const struct snd_kcontrol_new wm8940_snd_controls[] = { SOC_SINGLE_TLV("Digital Capture Volume", WM8940_ADCVOL, 0, 255, 0, wm8940_adc_tlv), SOC_ENUM("Mic Bias Level", wm8940_mic_bias_level_enum), - SOC_SINGLE_TLV("Capture Boost Volue", WM8940_ADCBOOST, + SOC_SINGLE_TLV("Capture Boost Volume", WM8940_ADCBOOST, 8, 1, 0, wm8940_capture_boost_vol_tlv), SOC_SINGLE_TLV("Speaker Playback Volume", WM8940_SPKVOL, 0, 63, 0, wm8940_spk_vol_tlv), @@ -693,7 +693,12 @@ static int wm8940_update_clocks(struct snd_soc_dai *dai) f = wm8940_get_mclkdiv(priv->mclk, fs256, &mclkdiv); if (f != priv->mclk) { /* The PLL performs best around 90MHz */ - fpll = wm8940_get_mclkdiv(22500000, fs256, &mclkdiv); + if (fs256 % 8000) + f = 22579200; + else + f = 24576000; + + fpll = wm8940_get_mclkdiv(f, fs256, &mclkdiv); } wm8940_set_dai_pll(dai, 0, 0, priv->mclk, fpll); diff --git a/sound/soc/codecs/wm8974.c b/sound/soc/codecs/wm8974.c index bdf437a5403f..db16d893a235 100644 --- a/sound/soc/codecs/wm8974.c +++ b/sound/soc/codecs/wm8974.c @@ -419,10 +419,14 @@ static int wm8974_update_clocks(struct snd_soc_dai *dai) fs256 = 256 * priv->fs; f = wm8974_get_mclkdiv(priv->mclk, fs256, &mclkdiv); - if (f != priv->mclk) { /* The PLL performs best around 90MHz */ - fpll = wm8974_get_mclkdiv(22500000, fs256, &mclkdiv); + if (fs256 % 8000) + f = 22579200; + else + f = 24576000; + + fpll = wm8974_get_mclkdiv(f, fs256, &mclkdiv); } wm8974_set_dai_pll(dai, 0, 0, priv->mclk, fpll); diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index f997b2dc221b..28f03a5f29f7 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -761,7 +761,7 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { .callback = sof_sdw_quirk_cb, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Google"), - DMI_MATCH(DMI_PRODUCT_NAME, "Fatcat"), + DMI_MATCH(DMI_PRODUCT_FAMILY, "Google_Fatcat"), }, .driver_data = (void *)(SOC_SDW_PCH_DMIC | SOF_BT_OFFLOAD_SSP(2) | diff --git a/sound/soc/intel/boards/sof_ssp_amp.c b/sound/soc/intel/boards/sof_ssp_amp.c index 48ee5353bdf1..729c0cd7c19c 100644 --- a/sound/soc/intel/boards/sof_ssp_amp.c +++ b/sound/soc/intel/boards/sof_ssp_amp.c @@ -216,6 +216,12 @@ static const struct platform_device_id board_ids[] = { /* SSP 0 and SSP 2 are used for HDMI IN */ SOF_HDMI_PLAYBACK_PRESENT), }, + { + .name = "ptl_lt6911_hdmi_ssp", + .driver_data = (kernel_ulong_t)(SOF_SSP_MASK_HDMI_CAPTURE(0x5) | + /* SSP 0 and SSP 2 are used for HDMI IN */ + SOF_HDMI_PLAYBACK_PRESENT), + }, { } }; MODULE_DEVICE_TABLE(platform, board_ids); diff --git a/sound/soc/intel/catpt/pcm.c b/sound/soc/intel/catpt/pcm.c index 46acb7fdc547..bf734c69c4e0 100644 --- a/sound/soc/intel/catpt/pcm.c +++ b/sound/soc/intel/catpt/pcm.c @@ -568,8 +568,9 @@ static const struct snd_pcm_hardware catpt_pcm_hardware = { SNDRV_PCM_INFO_RESUME | SNDRV_PCM_INFO_NO_PERIOD_WAKEUP, .formats = SNDRV_PCM_FMTBIT_S16_LE | - SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_S32_LE, + .subformats = SNDRV_PCM_SUBFMTBIT_MSBITS_24 | + SNDRV_PCM_SUBFMTBIT_MSBITS_MAX, .period_bytes_min = PAGE_SIZE, .period_bytes_max = CATPT_BUFFER_MAX_SIZE / CATPT_PCM_PERIODS_MIN, .periods_min = CATPT_PCM_PERIODS_MIN, @@ -698,14 +699,18 @@ static struct snd_soc_dai_driver dai_drivers[] = { .channels_min = 2, .channels_max = 2, .rates = SNDRV_PCM_RATE_48000, - .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE, + .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S32_LE, + .subformats = SNDRV_PCM_SUBFMTBIT_MSBITS_24 | + SNDRV_PCM_SUBFMTBIT_MSBITS_MAX, }, .capture = { .stream_name = "Analog Capture", .channels_min = 2, .channels_max = 4, .rates = SNDRV_PCM_RATE_48000, - .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE, + .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S32_LE, + .subformats = SNDRV_PCM_SUBFMTBIT_MSBITS_24 | + SNDRV_PCM_SUBFMTBIT_MSBITS_MAX, }, }, { @@ -717,7 +722,9 @@ static struct snd_soc_dai_driver dai_drivers[] = { .channels_min = 2, .channels_max = 2, .rates = SNDRV_PCM_RATE_8000_192000, - .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE, + .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S32_LE, + .subformats = SNDRV_PCM_SUBFMTBIT_MSBITS_24 | + SNDRV_PCM_SUBFMTBIT_MSBITS_MAX, }, }, { @@ -729,7 +736,9 @@ static struct snd_soc_dai_driver dai_drivers[] = { .channels_min = 2, .channels_max = 2, .rates = SNDRV_PCM_RATE_8000_192000, - .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE, + .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S32_LE, + .subformats = SNDRV_PCM_SUBFMTBIT_MSBITS_24 | + SNDRV_PCM_SUBFMTBIT_MSBITS_MAX, }, }, { @@ -741,7 +750,9 @@ static struct snd_soc_dai_driver dai_drivers[] = { .channels_min = 2, .channels_max = 2, .rates = SNDRV_PCM_RATE_48000, - .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE, + .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S32_LE, + .subformats = SNDRV_PCM_SUBFMTBIT_MSBITS_24 | + SNDRV_PCM_SUBFMTBIT_MSBITS_MAX, }, }, { diff --git a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c index e292701dfcfe..3c8b10e21ceb 100644 --- a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c @@ -61,6 +61,12 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_ptl_machines[] = { SND_SOC_ACPI_TPLG_INTEL_SSP_MSB | SND_SOC_ACPI_TPLG_INTEL_DMIC_NUMBER, }, + /* place amp-only boards in the end of table */ + { + .id = "INTC10B0", + .drv_name = "ptl_lt6911_hdmi_ssp", + .sof_tplg_filename = "sof-ptl-hdmi-ssp02.tplg", + }, {}, }; EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_ptl_machines); diff --git a/sound/soc/qcom/qdsp6/audioreach.c b/sound/soc/qcom/qdsp6/audioreach.c index 4ebaaf736fb9..3f5eed5afce5 100644 --- a/sound/soc/qcom/qdsp6/audioreach.c +++ b/sound/soc/qcom/qdsp6/audioreach.c @@ -971,6 +971,7 @@ static int audioreach_i2s_set_media_format(struct q6apm_graph *graph, param_data->param_id = PARAM_ID_I2S_INTF_CFG; param_data->param_size = ic_sz - APM_MODULE_PARAM_DATA_SIZE; + intf_cfg->cfg.lpaif_type = module->hw_interface_type; intf_cfg->cfg.intf_idx = module->hw_interface_idx; intf_cfg->cfg.sd_line_idx = module->sd_line_idx; diff --git a/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c b/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c index a0d90462fd6a..528756f1332b 100644 --- a/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c +++ b/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c @@ -213,8 +213,10 @@ static int q6apm_lpass_dai_prepare(struct snd_pcm_substream *substream, struct s return 0; err: - q6apm_graph_close(dai_data->graph[dai->id]); - dai_data->graph[dai->id] = NULL; + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { + q6apm_graph_close(dai_data->graph[dai->id]); + dai_data->graph[dai->id] = NULL; + } return rc; } @@ -260,6 +262,7 @@ static const struct snd_soc_dai_ops q6i2s_ops = { .shutdown = q6apm_lpass_dai_shutdown, .set_channel_map = q6dma_set_channel_map, .hw_params = q6dma_hw_params, + .set_fmt = q6i2s_set_fmt, }; static const struct snd_soc_dai_ops q6hdmi_ops = { diff --git a/sound/soc/qcom/sc8280xp.c b/sound/soc/qcom/sc8280xp.c index 73f9f82c4e25..288ccd7f8866 100644 --- a/sound/soc/qcom/sc8280xp.c +++ b/sound/soc/qcom/sc8280xp.c @@ -32,6 +32,10 @@ static int sc8280xp_snd_init(struct snd_soc_pcm_runtime *rtd) int dp_pcm_id = 0; switch (cpu_dai->id) { + case PRIMARY_MI2S_RX...QUATERNARY_MI2S_TX: + case QUINARY_MI2S_RX...QUINARY_MI2S_TX: + snd_soc_dai_set_fmt(cpu_dai, SND_SOC_DAIFMT_BP_FP); + break; case WSA_CODEC_DMA_RX_0: case WSA_CODEC_DMA_RX_1: /* @@ -186,7 +190,7 @@ static int sc8280xp_platform_probe(struct platform_device *pdev) static const struct of_device_id snd_sc8280xp_dt_match[] = { {.compatible = "qcom,qcm6490-idp-sndcard", "qcm6490"}, {.compatible = "qcom,qcs6490-rb3gen2-sndcard", "qcs6490"}, - {.compatible = "qcom,qcs8275-sndcard", "qcs8275"}, + {.compatible = "qcom,qcs8275-sndcard", "qcs8300"}, {.compatible = "qcom,qcs9075-sndcard", "qcs9075"}, {.compatible = "qcom,qcs9100-sndcard", "qcs9100"}, {.compatible = "qcom,sc8280xp-sndcard", "sc8280xp"}, diff --git a/sound/soc/sdca/sdca_device.c b/sound/soc/sdca/sdca_device.c index 0244cdcdd109..4798ce2c8f0b 100644 --- a/sound/soc/sdca/sdca_device.c +++ b/sound/soc/sdca/sdca_device.c @@ -7,6 +7,7 @@ */ #include <linux/acpi.h> +#include <linux/dmi.h> #include <linux/module.h> #include <linux/property.h> #include <linux/soundwire/sdw.h> @@ -55,11 +56,30 @@ static bool sdca_device_quirk_rt712_vb(struct sdw_slave *slave) return false; } +static bool sdca_device_quirk_skip_func_type_patching(struct sdw_slave *slave) +{ + const char *vendor, *sku; + + vendor = dmi_get_system_info(DMI_SYS_VENDOR); + sku = dmi_get_system_info(DMI_PRODUCT_SKU); + + if (vendor && sku && + !strcmp(vendor, "Dell Inc.") && + (!strcmp(sku, "0C62") || !strcmp(sku, "0C63") || !strcmp(sku, "0C6B")) && + slave->sdca_data.interface_revision == 0x061c && + slave->id.mfg_id == 0x01fa && slave->id.part_id == 0x4243) + return true; + + return false; +} + bool sdca_device_quirk_match(struct sdw_slave *slave, enum sdca_quirk quirk) { switch (quirk) { case SDCA_QUIRKS_RT712_VB: return sdca_device_quirk_rt712_vb(slave); + case SDCA_QUIRKS_SKIP_FUNC_TYPE_PATCHING: + return sdca_device_quirk_skip_func_type_patching(slave); default: break; } diff --git a/sound/soc/sdca/sdca_functions.c b/sound/soc/sdca/sdca_functions.c index f26f597dca9e..13f68f7b6dd6 100644 --- a/sound/soc/sdca/sdca_functions.c +++ b/sound/soc/sdca/sdca_functions.c @@ -90,6 +90,7 @@ static int find_sdca_function(struct acpi_device *adev, void *data) { struct fwnode_handle *function_node = acpi_fwnode_handle(adev); struct sdca_device_data *sdca_data = data; + struct sdw_slave *slave = container_of(sdca_data, struct sdw_slave, sdca_data); struct device *dev = &adev->dev; struct fwnode_handle *control5; /* used to identify function type */ const char *function_name; @@ -137,11 +138,13 @@ static int find_sdca_function(struct acpi_device *adev, void *data) return ret; } - ret = patch_sdca_function_type(sdca_data->interface_revision, &function_type); - if (ret < 0) { - dev_err(dev, "SDCA version %#x invalid function type %d\n", - sdca_data->interface_revision, function_type); - return ret; + if (!sdca_device_quirk_match(slave, SDCA_QUIRKS_SKIP_FUNC_TYPE_PATCHING)) { + ret = patch_sdca_function_type(sdca_data->interface_revision, &function_type); + if (ret < 0) { + dev_err(dev, "SDCA version %#x invalid function type %d\n", + sdca_data->interface_revision, function_type); + return ret; + } } function_name = get_sdca_function_name(function_type); diff --git a/sound/soc/sdca/sdca_interrupts.c b/sound/soc/sdca/sdca_interrupts.c index 8018773ee426..79bf3042f57d 100644 --- a/sound/soc/sdca/sdca_interrupts.c +++ b/sound/soc/sdca/sdca_interrupts.c @@ -155,7 +155,7 @@ static irqreturn_t detected_mode_handler(int irq, void *data) SDCA_CTL_SELECTED_MODE_NAME); if (!name) - return -ENOMEM; + return IRQ_NONE; kctl = snd_soc_component_get_kcontrol(component, name); if (!kctl) { diff --git a/sound/soc/sdca/sdca_regmap.c b/sound/soc/sdca/sdca_regmap.c index 5cb3048ea8cf..72f893e00ff5 100644 --- a/sound/soc/sdca/sdca_regmap.c +++ b/sound/soc/sdca/sdca_regmap.c @@ -196,7 +196,7 @@ int sdca_regmap_mbq_size(struct sdca_function_data *function, unsigned int reg) control = function_find_control(function, reg); if (!control) - return false; + return -EINVAL; return clamp_val(control->nbits / BITS_PER_BYTE, sizeof(u8), sizeof(u32)); } diff --git a/sound/soc/sof/imx/imx-common.c b/sound/soc/sof/imx/imx-common.c index f00b381cec3b..d66c198b861a 100644 --- a/sound/soc/sof/imx/imx-common.c +++ b/sound/soc/sof/imx/imx-common.c @@ -316,9 +316,9 @@ static int imx_parse_ioremap_memory(struct snd_sof_dev *sdev) } sdev->bar[blk_type] = devm_ioremap_resource(sdev->dev, res); - if (!sdev->bar[blk_type]) + if (IS_ERR(sdev->bar[blk_type])) return dev_err_probe(sdev->dev, - -ENOMEM, + PTR_ERR(sdev->bar[blk_type]), "failed to ioremap %s region\n", chip_info->memory[i].name); } diff --git a/sound/soc/sof/intel/hda-stream.c b/sound/soc/sof/intel/hda-stream.c index aa6b0247d5c9..a34f472ef175 100644 --- a/sound/soc/sof/intel/hda-stream.c +++ b/sound/soc/sof/intel/hda-stream.c @@ -890,7 +890,7 @@ int hda_dsp_stream_init(struct snd_sof_dev *sdev) if (num_capture >= SOF_HDA_CAPTURE_STREAMS) { dev_err(sdev->dev, "error: too many capture streams %d\n", - num_playback); + num_capture); return -EINVAL; } diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c index a25c5a531690..9ad76fff741b 100644 --- a/sound/usb/qcom/qc_audio_offload.c +++ b/sound/usb/qcom/qc_audio_offload.c @@ -538,38 +538,33 @@ static void uaudio_iommu_unmap(enum mem_type mtype, unsigned long iova, umap_size, iova, mapped_iova_size); } +static int uaudio_iommu_map_prot(bool dma_coherent) +{ + int prot = IOMMU_READ | IOMMU_WRITE; + + if (dma_coherent) + prot |= IOMMU_CACHE; + return prot; +} + /** - * uaudio_iommu_map() - maps iommu memory for adsp + * uaudio_iommu_map_pa() - maps iommu memory for adsp * @mtype: ring type * @dma_coherent: dma coherent * @pa: physical address for ring/buffer * @size: size of memory region - * @sgt: sg table for memory region * * Maps the XHCI related resources to a memory region that is assigned to be * used by the adsp. This will be mapped to the domain, which is created by * the ASoC USB backend driver. * */ -static unsigned long uaudio_iommu_map(enum mem_type mtype, bool dma_coherent, - phys_addr_t pa, size_t size, - struct sg_table *sgt) +static unsigned long uaudio_iommu_map_pa(enum mem_type mtype, bool dma_coherent, + phys_addr_t pa, size_t size) { - struct scatterlist *sg; unsigned long iova = 0; - size_t total_len = 0; - unsigned long iova_sg; - phys_addr_t pa_sg; bool map = true; - size_t sg_len; - int prot; - int ret; - int i; - - prot = IOMMU_READ | IOMMU_WRITE; - - if (dma_coherent) - prot |= IOMMU_CACHE; + int prot = uaudio_iommu_map_prot(dma_coherent); switch (mtype) { case MEM_EVENT_RING: @@ -583,20 +578,41 @@ static unsigned long uaudio_iommu_map(enum mem_type mtype, bool dma_coherent, &uaudio_qdev->xfer_ring_iova_size, &uaudio_qdev->xfer_ring_list, size); break; - case MEM_XFER_BUF: - iova = uaudio_get_iova(&uaudio_qdev->curr_xfer_buf_iova, - &uaudio_qdev->xfer_buf_iova_size, - &uaudio_qdev->xfer_buf_list, size); - break; default: dev_err(uaudio_qdev->data->dev, "unknown mem type %d\n", mtype); } if (!iova || !map) - goto done; + return 0; + + iommu_map(uaudio_qdev->data->domain, iova, pa, size, prot, GFP_KERNEL); - if (!sgt) - goto skip_sgt_map; + return iova; +} + +static unsigned long uaudio_iommu_map_xfer_buf(bool dma_coherent, size_t size, + struct sg_table *sgt) +{ + struct scatterlist *sg; + unsigned long iova = 0; + size_t total_len = 0; + unsigned long iova_sg; + phys_addr_t pa_sg; + size_t sg_len; + int prot = uaudio_iommu_map_prot(dma_coherent); + int ret; + int i; + + prot = IOMMU_READ | IOMMU_WRITE; + + if (dma_coherent) + prot |= IOMMU_CACHE; + + iova = uaudio_get_iova(&uaudio_qdev->curr_xfer_buf_iova, + &uaudio_qdev->xfer_buf_iova_size, + &uaudio_qdev->xfer_buf_list, size); + if (!iova) + goto done; iova_sg = iova; for_each_sg(sgt->sgl, sg, sgt->nents, i) { @@ -618,11 +634,6 @@ static unsigned long uaudio_iommu_map(enum mem_type mtype, bool dma_coherent, uaudio_iommu_unmap(MEM_XFER_BUF, iova, size, total_len); iova = 0; } - return iova; - -skip_sgt_map: - iommu_map(uaudio_qdev->data->domain, iova, pa, size, prot, GFP_KERNEL); - done: return iova; } @@ -1020,7 +1031,6 @@ static int uaudio_transfer_buffer_setup(struct snd_usb_substream *subs, struct sg_table xfer_buf_sgt; dma_addr_t xfer_buf_dma; void *xfer_buf; - phys_addr_t xfer_buf_pa; u32 len = xfer_buf_len; bool dma_coherent; dma_addr_t xfer_buf_dma_sysdev; @@ -1051,18 +1061,12 @@ static int uaudio_transfer_buffer_setup(struct snd_usb_substream *subs, if (!xfer_buf) return -ENOMEM; - /* Remapping is not possible if xfer_buf is outside of linear map */ - xfer_buf_pa = virt_to_phys(xfer_buf); - if (WARN_ON(!page_is_ram(PFN_DOWN(xfer_buf_pa)))) { - ret = -ENXIO; - goto unmap_sync; - } dma_get_sgtable(subs->dev->bus->sysdev, &xfer_buf_sgt, xfer_buf, xfer_buf_dma, len); /* map the physical buffer into sysdev as well */ - xfer_buf_dma_sysdev = uaudio_iommu_map(MEM_XFER_BUF, dma_coherent, - xfer_buf_pa, len, &xfer_buf_sgt); + xfer_buf_dma_sysdev = uaudio_iommu_map_xfer_buf(dma_coherent, + len, &xfer_buf_sgt); if (!xfer_buf_dma_sysdev) { ret = -ENOMEM; goto unmap_sync; @@ -1143,8 +1147,8 @@ uaudio_endpoint_setup(struct snd_usb_substream *subs, sg_free_table(sgt); /* data transfer ring */ - iova = uaudio_iommu_map(MEM_XFER_RING, dma_coherent, tr_pa, - PAGE_SIZE, NULL); + iova = uaudio_iommu_map_pa(MEM_XFER_RING, dma_coherent, tr_pa, + PAGE_SIZE); if (!iova) { ret = -ENOMEM; goto clear_pa; @@ -1207,8 +1211,8 @@ static int uaudio_event_ring_setup(struct snd_usb_substream *subs, mem_info->dma = sg_dma_address(sgt->sgl); sg_free_table(sgt); - iova = uaudio_iommu_map(MEM_EVENT_RING, dma_coherent, er_pa, - PAGE_SIZE, NULL); + iova = uaudio_iommu_map_pa(MEM_EVENT_RING, dma_coherent, er_pa, + PAGE_SIZE); if (!iova) { ret = -ENOMEM; goto clear_pa; diff --git a/tools/arch/loongarch/include/asm/inst.h b/tools/arch/loongarch/include/asm/inst.h index c25b5853181d..d68fad63c8b7 100644 --- a/tools/arch/loongarch/include/asm/inst.h +++ b/tools/arch/loongarch/include/asm/inst.h @@ -51,6 +51,10 @@ enum reg2i16_op { bgeu_op = 0x1b, }; +enum reg3_op { + amswapw_op = 0x70c0, +}; + struct reg0i15_format { unsigned int immediate : 15; unsigned int opcode : 17; @@ -96,6 +100,13 @@ struct reg2i16_format { unsigned int opcode : 6; }; +struct reg3_format { + unsigned int rd : 5; + unsigned int rj : 5; + unsigned int rk : 5; + unsigned int opcode : 17; +}; + union loongarch_instruction { unsigned int word; struct reg0i15_format reg0i15_format; @@ -105,6 +116,7 @@ union loongarch_instruction { struct reg2i12_format reg2i12_format; struct reg2i14_format reg2i14_format; struct reg2i16_format reg2i16_format; + struct reg3_format reg3_format; }; #define LOONGARCH_INSN_SIZE sizeof(union loongarch_instruction) diff --git a/tools/lib/subcmd/help.c b/tools/lib/subcmd/help.c index 9ef569492560..ddaeb4eb3e24 100644 --- a/tools/lib/subcmd/help.c +++ b/tools/lib/subcmd/help.c @@ -75,6 +75,9 @@ void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes) size_t ci, cj, ei; int cmp; + if (!excludes->cnt) + return; + ci = cj = ei = 0; while (ci < cmds->cnt && ei < excludes->cnt) { cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name); diff --git a/tools/objtool/arch/loongarch/decode.c b/tools/objtool/arch/loongarch/decode.c index b6fdc68053cc..2e555c4060c5 100644 --- a/tools/objtool/arch/loongarch/decode.c +++ b/tools/objtool/arch/loongarch/decode.c @@ -278,6 +278,25 @@ static bool decode_insn_reg2i16_fomat(union loongarch_instruction inst, return true; } +static bool decode_insn_reg3_fomat(union loongarch_instruction inst, + struct instruction *insn) +{ + switch (inst.reg3_format.opcode) { + case amswapw_op: + if (inst.reg3_format.rd == LOONGARCH_GPR_ZERO && + inst.reg3_format.rk == LOONGARCH_GPR_RA && + inst.reg3_format.rj == LOONGARCH_GPR_ZERO) { + /* amswap.w $zero, $ra, $zero */ + insn->type = INSN_BUG; + } + break; + default: + return false; + } + + return true; +} + int arch_decode_instruction(struct objtool_file *file, const struct section *sec, unsigned long offset, unsigned int maxlen, struct instruction *insn) @@ -309,11 +328,19 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec return 0; if (decode_insn_reg2i16_fomat(inst, insn)) return 0; + if (decode_insn_reg3_fomat(inst, insn)) + return 0; - if (inst.word == 0) + if (inst.word == 0) { + /* andi $zero, $zero, 0x0 */ insn->type = INSN_NOP; - else if (inst.reg0i15_format.opcode == break_op) { - /* break */ + } else if (inst.reg0i15_format.opcode == break_op && + inst.reg0i15_format.immediate == 0x0) { + /* break 0x0 */ + insn->type = INSN_TRAP; + } else if (inst.reg0i15_format.opcode == break_op && + inst.reg0i15_format.immediate == 0x1) { + /* break 0x1 */ insn->type = INSN_BUG; } else if (inst.reg2_format.opcode == ertn_op) { /* ertn */ diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index fd49703021fd..078634461df2 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -2009,6 +2009,7 @@ static int __cmd_contention(int argc, const char **argv) .owner = show_lock_owner, .cgroups = RB_ROOT, }; + struct perf_env host_env; lockhash_table = calloc(LOCKHASH_SIZE, sizeof(*lockhash_table)); if (!lockhash_table) @@ -2024,7 +2025,10 @@ static int __cmd_contention(int argc, const char **argv) eops.mmap = perf_event__process_mmap; eops.tracing_data = perf_event__process_tracing_data; - session = perf_session__new(use_bpf ? NULL : &data, &eops); + perf_env__init(&host_env); + session = __perf_session__new(use_bpf ? NULL : &data, &eops, + /*trace_event_repipe=*/false, &host_env); + if (IS_ERR(session)) { pr_err("Initializing perf session failed\n"); err = PTR_ERR(session); @@ -2142,6 +2146,7 @@ out_delete: evlist__delete(con.evlist); lock_contention_finish(&con); perf_session__delete(session); + perf_env__exit(&host_env); zfree(&lockhash_table); return err; } diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 85b2a93a59ac..779f6230130a 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -477,6 +477,7 @@ static int __maps__insert(struct maps *maps, struct map *new) } /* Insert the value at the end. */ maps_by_address[nr_maps] = map__get(new); + map__set_kmap_maps(new, maps); if (maps_by_name) maps_by_name[nr_maps] = map__get(new); @@ -502,8 +503,6 @@ static int __maps__insert(struct maps *maps, struct map *new) if (map__end(new) < map__start(new)) RC_CHK_ACCESS(maps)->ends_broken = true; - map__set_kmap_maps(new, maps); - return 0; } @@ -891,6 +890,7 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) if (before) { map__put(maps_by_address[i]); maps_by_address[i] = before; + map__set_kmap_maps(before, maps); if (maps_by_name) { map__put(maps_by_name[ni]); @@ -918,6 +918,7 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) */ map__put(maps_by_address[i]); maps_by_address[i] = map__get(new); + map__set_kmap_maps(new, maps); if (maps_by_name) { map__put(maps_by_name[ni]); @@ -942,14 +943,13 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) */ map__put(maps_by_address[i]); maps_by_address[i] = map__get(new); + map__set_kmap_maps(new, maps); if (maps_by_name) { map__put(maps_by_name[ni]); maps_by_name[ni] = map__get(new); } - map__set_kmap_maps(new, maps); - check_invariants(maps); return err; } @@ -1019,6 +1019,7 @@ int maps__copy_from(struct maps *dest, struct maps *parent) err = unwind__prepare_access(dest, new, NULL); if (!err) { dest_maps_by_address[i] = new; + map__set_kmap_maps(new, dest); if (dest_maps_by_name) dest_maps_by_name[i] = map__get(new); RC_CHK_ACCESS(dest)->nr_maps = i + 1; diff --git a/tools/testing/selftests/bpf/prog_tests/free_timer.c b/tools/testing/selftests/bpf/prog_tests/free_timer.c index b7b77a6b2979..0de8facca4c5 100644 --- a/tools/testing/selftests/bpf/prog_tests/free_timer.c +++ b/tools/testing/selftests/bpf/prog_tests/free_timer.c @@ -124,6 +124,10 @@ void test_free_timer(void) int err; skel = free_timer__open_and_load(); + if (!skel && errno == EOPNOTSUPP) { + test__skip(); + return; + } if (!ASSERT_OK_PTR(skel, "open_load")) return; diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c index d66687f1ee6a..56f660ca567b 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer.c +++ b/tools/testing/selftests/bpf/prog_tests/timer.c @@ -86,6 +86,10 @@ void serial_test_timer(void) int err; timer_skel = timer__open_and_load(); + if (!timer_skel && errno == EOPNOTSUPP) { + test__skip(); + return; + } if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load")) return; diff --git a/tools/testing/selftests/bpf/prog_tests/timer_crash.c b/tools/testing/selftests/bpf/prog_tests/timer_crash.c index f74b82305da8..b841597c8a3a 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer_crash.c +++ b/tools/testing/selftests/bpf/prog_tests/timer_crash.c @@ -12,6 +12,10 @@ static void test_timer_crash_mode(int mode) struct timer_crash *skel; skel = timer_crash__open_and_load(); + if (!skel && errno == EOPNOTSUPP) { + test__skip(); + return; + } if (!ASSERT_OK_PTR(skel, "timer_crash__open_and_load")) return; skel->bss->pid = getpid(); diff --git a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c index 1a2f99596916..eb303fa1e09a 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c +++ b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c @@ -59,6 +59,10 @@ void test_timer_lockup(void) } skel = timer_lockup__open_and_load(); + if (!skel && errno == EOPNOTSUPP) { + test__skip(); + return; + } if (!ASSERT_OK_PTR(skel, "timer_lockup__open_and_load")) return; diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c index 9ff7843909e7..c930c7d7105b 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c +++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c @@ -65,6 +65,10 @@ void serial_test_timer_mim(void) goto cleanup; timer_skel = timer_mim__open_and_load(); + if (!timer_skel && errno == EOPNOTSUPP) { + test__skip(); + return; + } if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load")) goto cleanup; diff --git a/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h index d67466c1ff77..f90531cf3ee5 100644 --- a/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h +++ b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h @@ -302,7 +302,7 @@ int arena_spin_lock_slowpath(arena_spinlock_t __arena __arg_arena *lock, u32 val * barriers. */ if (val & _Q_LOCKED_MASK) - smp_cond_load_acquire_label(&lock->locked, !VAL, release_err); + (void)smp_cond_load_acquire_label(&lock->locked, !VAL, release_err); /* * take ownership and clear the pending bit. @@ -380,7 +380,7 @@ queue: /* Link @node into the waitqueue. */ WRITE_ONCE(prev->next, node); - arch_mcs_spin_lock_contended_label(&node->locked, release_node_err); + (void)arch_mcs_spin_lock_contended_label(&node->locked, release_node_err); /* * While waiting for the MCS lock, the next pointer may have diff --git a/tools/testing/selftests/bpf/progs/crypto_sanity.c b/tools/testing/selftests/bpf/progs/crypto_sanity.c index 645be6cddf36..dfd8a258f14a 100644 --- a/tools/testing/selftests/bpf/progs/crypto_sanity.c +++ b/tools/testing/selftests/bpf/progs/crypto_sanity.c @@ -14,7 +14,7 @@ unsigned char key[256] = {}; u16 udp_test_port = 7777; u32 authsize, key_len; char algo[128] = {}; -char dst[16] = {}; +char dst[16] = {}, dst_bad[8] = {}; int status; static int skb_dynptr_validate(struct __sk_buff *skb, struct bpf_dynptr *psrc) @@ -59,10 +59,9 @@ int skb_crypto_setup(void *ctx) .authsize = authsize, }; struct bpf_crypto_ctx *cctx; - int err = 0; + int err; status = 0; - if (key_len > 256) { status = -EINVAL; return 0; @@ -70,8 +69,8 @@ int skb_crypto_setup(void *ctx) __builtin_memcpy(¶ms.algo, algo, sizeof(algo)); __builtin_memcpy(¶ms.key, key, sizeof(key)); - cctx = bpf_crypto_ctx_create(¶ms, sizeof(params), &err); + cctx = bpf_crypto_ctx_create(¶ms, sizeof(params), &err); if (!cctx) { status = err; return 0; @@ -80,7 +79,6 @@ int skb_crypto_setup(void *ctx) err = crypto_ctx_insert(cctx); if (err && err != -EEXIST) status = err; - return 0; } @@ -92,6 +90,7 @@ int decrypt_sanity(struct __sk_buff *skb) struct bpf_dynptr psrc, pdst; int err; + status = 0; err = skb_dynptr_validate(skb, &psrc); if (err < 0) { status = err; @@ -110,13 +109,23 @@ int decrypt_sanity(struct __sk_buff *skb) return TC_ACT_SHOT; } - /* dst is a global variable to make testing part easier to check. In real - * production code, a percpu map should be used to store the result. + /* Check also bad case where the dst buffer is smaller than the + * skb's linear section. + */ + bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst); + status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL); + if (!status) + status = -EIO; + if (status != -EINVAL) + goto err; + + /* dst is a global variable to make testing part easier to check. + * In real production code, a percpu map should be used to store + * the result. */ bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst); - status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL); - +err: return TC_ACT_SHOT; } @@ -129,7 +138,6 @@ int encrypt_sanity(struct __sk_buff *skb) int err; status = 0; - err = skb_dynptr_validate(skb, &psrc); if (err < 0) { status = err; @@ -148,13 +156,23 @@ int encrypt_sanity(struct __sk_buff *skb) return TC_ACT_SHOT; } - /* dst is a global variable to make testing part easier to check. In real - * production code, a percpu map should be used to store the result. + /* Check also bad case where the dst buffer is smaller than the + * skb's linear section. + */ + bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst); + status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL); + if (!status) + status = -EIO; + if (status != -EINVAL) + goto err; + + /* dst is a global variable to make testing part easier to check. + * In real production code, a percpu map should be used to store + * the result. */ bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst); - status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL); - +err: return TC_ACT_SHOT; } diff --git a/tools/testing/selftests/bpf/progs/linked_list_fail.c b/tools/testing/selftests/bpf/progs/linked_list_fail.c index 6438982b928b..ddd26d1a083f 100644 --- a/tools/testing/selftests/bpf/progs/linked_list_fail.c +++ b/tools/testing/selftests/bpf/progs/linked_list_fail.c @@ -226,8 +226,7 @@ int obj_new_no_composite(void *ctx) SEC("?tc") int obj_new_no_struct(void *ctx) { - - bpf_obj_new(union { int data; unsigned udata; }); + (void)bpf_obj_new(union { int data; unsigned udata; }); return 0; } @@ -252,7 +251,7 @@ int new_null_ret(void *ctx) SEC("?tc") int obj_new_acq(void *ctx) { - bpf_obj_new(struct foo); + (void)bpf_obj_new(struct foo); return 0; } diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c index 46697f381878..a47690174e0e 100644 --- a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c +++ b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c @@ -30,8 +30,12 @@ __test(2) int test_strcspn(void *ctx) { return bpf_strcspn(str, "lo"); } __test(6) int test_strstr_found(void *ctx) { return bpf_strstr(str, "world"); } __test(-ENOENT) int test_strstr_notfound(void *ctx) { return bpf_strstr(str, "hi"); } __test(0) int test_strstr_empty(void *ctx) { return bpf_strstr(str, ""); } -__test(0) int test_strnstr_found(void *ctx) { return bpf_strnstr(str, "hello", 6); } -__test(-ENOENT) int test_strnstr_notfound(void *ctx) { return bpf_strnstr(str, "hi", 10); } +__test(0) int test_strnstr_found1(void *ctx) { return bpf_strnstr("", "", 0); } +__test(0) int test_strnstr_found2(void *ctx) { return bpf_strnstr(str, "hello", 5); } +__test(0) int test_strnstr_found3(void *ctx) { return bpf_strnstr(str, "hello", 6); } +__test(-ENOENT) int test_strnstr_notfound1(void *ctx) { return bpf_strnstr(str, "hi", 10); } +__test(-ENOENT) int test_strnstr_notfound2(void *ctx) { return bpf_strnstr(str, "hello", 4); } +__test(-ENOENT) int test_strnstr_notfound3(void *ctx) { return bpf_strnstr("", "a", 0); } __test(0) int test_strnstr_empty(void *ctx) { return bpf_strnstr(str, "", 1); } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh index 7bc148889ca7..187b478d0ddf 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -7,6 +7,8 @@ ALL_TESTS=" prio arp_validate num_grat_arp + fail_over_mac + vlan_over_bond " lib_dir=$(dirname "$0") @@ -352,8 +354,8 @@ garp_test() exp_num=$(echo "${param}" | cut -f6 -d ' ') active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") - slowwait_for_counter $((exp_num + 5)) $exp_num \ - tc_rule_handle_stats_get "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}" + slowwait_for_counter $((exp_num + 5)) $exp_num tc_rule_handle_stats_get \ + "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}" &> /dev/null # check result real_num=$(tc_rule_handle_stats_get "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}") @@ -376,6 +378,197 @@ num_grat_arp() done } +check_all_mac_same() +{ + RET=0 + # all slaves should have same mac address (with the first port's mac) + local bond_mac=$(ip -n "$s_ns" -j link show bond0 | jq -r '.[]["address"]') + local eth0_mac=$(ip -n "$s_ns" -j link show eth0 | jq -r '.[]["address"]') + local eth1_mac=$(ip -n "$s_ns" -j link show eth1 | jq -r '.[]["address"]') + local eth2_mac=$(ip -n "$s_ns" -j link show eth2 | jq -r '.[]["address"]') + if [ "$bond_mac" != "${mac[0]}" ] || [ "$eth0_mac" != "$bond_mac" ] || \ + [ "$eth1_mac" != "$bond_mac" ] || [ "$eth2_mac" != "$bond_mac" ]; then + RET=1 + fi +} + +check_bond_mac_same_with_first() +{ + RET=0 + # bond mac address should be same with the first added slave + local bond_mac=$(ip -n "$s_ns" -j link show bond0 | jq -r '.[]["address"]') + if [ "$bond_mac" != "${mac[0]}" ]; then + RET=1 + fi +} + +check_bond_mac_same_with_active() +{ + RET=0 + # bond mac address should be same with active slave + local bond_mac=$(ip -n "$s_ns" -j link show bond0 | jq -r '.[]["address"]') + local active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + local active_slave_mac=$(ip -n "$s_ns" -j link show "$active_slave" | jq -r '.[]["address"]') + if [ "$bond_mac" != "$active_slave_mac" ]; then + RET=1 + fi +} + +check_backup_slave_mac_not_change() +{ + RET=0 + # backup slave's mac address is not changed + if ip -n "$s_ns" -d -j link show type bond_slave | jq -e '.[] + | select(.linkinfo.info_slave_data.state=="BACKUP") + | select(.address != .linkinfo.info_slave_data.perm_hwaddr)' &> /dev/null; then + RET=1 + fi +} + +check_backup_slave_mac_inherit() +{ + local backup_mac + RET=0 + + # backup slaves should use mac[1] or mac[2] + local backup_macs=$(ip -n "$s_ns" -d -j link show type bond_slave | \ + jq -r '.[] | select(.linkinfo.info_slave_data.state=="BACKUP") | .address') + for backup_mac in $backup_macs; do + if [ "$backup_mac" != "${mac[1]}" ] && [ "$backup_mac" != "${mac[2]}" ]; then + RET=1 + fi + done +} + +check_first_slave_random_mac() +{ + RET=0 + # remove the first added slave and added it back + ip -n "$s_ns" link set eth0 nomaster + ip -n "$s_ns" link set eth0 master bond0 + + # the first slave should use random mac address + eth0_mac=$(ip -n "$s_ns" -j link show eth0 | jq -r '.[]["address"]') + [ "$eth0_mac" = "${mac[0]}" ] && RET=1 + log_test "bond fail_over_mac follow" "random first slave mac" + + # remove the first slave, the permanent MAC address should be restored back + ip -n "$s_ns" link set eth0 nomaster + eth0_mac=$(ip -n "$s_ns" -j link show eth0 | jq -r '.[]["address"]') + [ "$eth0_mac" != "${mac[0]}" ] && RET=1 +} + +do_active_backup_failover() +{ + local active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + ip -n ${s_ns} link set ${active_slave} down + slowwait 2 active_slave_changed $active_slave + ip -n ${s_ns} link set ${active_slave} up +} + +fail_over_mac() +{ + # Bring down the first interface on the switch to force the bond to + # select another active interface instead of the first one that joined. + ip -n "$g_ns" link set s0 down + + # fail_over_mac none + bond_reset "mode active-backup miimon 100 fail_over_mac 0" + check_all_mac_same + log_test "fail_over_mac 0" "all slaves have same mac" + do_active_backup_failover + check_all_mac_same + log_test "fail_over_mac 0" "failover: all slaves have same mac" + + # fail_over_mac active + bond_reset "mode active-backup miimon 100 fail_over_mac 1" + check_bond_mac_same_with_active + log_test "fail_over_mac 1" "bond mac is same with active slave mac" + check_backup_slave_mac_not_change + log_test "fail_over_mac 1" "backup slave mac is not changed" + do_active_backup_failover + check_bond_mac_same_with_active + log_test "fail_over_mac 1" "failover: bond mac is same with active slave mac" + check_backup_slave_mac_not_change + log_test "fail_over_mac 1" "failover: backup slave mac is not changed" + + # fail_over_mac follow + bond_reset "mode active-backup miimon 100 fail_over_mac 2" + check_bond_mac_same_with_first + log_test "fail_over_mac 2" "bond mac is same with first slave mac" + check_bond_mac_same_with_active + log_test "fail_over_mac 2" "bond mac is same with active slave mac" + check_backup_slave_mac_inherit + log_test "fail_over_mac 2" "backup slave mac inherit" + do_active_backup_failover + check_bond_mac_same_with_first + log_test "fail_over_mac 2" "failover: bond mac is same with first slave mac" + check_bond_mac_same_with_active + log_test "fail_over_mac 2" "failover: bond mac is same with active slave mac" + check_backup_slave_mac_inherit + log_test "fail_over_mac 2" "failover: backup slave mac inherit" + check_first_slave_random_mac + log_test "fail_over_mac 2" "first slave mac random" +} + +vlan_over_bond_arp() +{ + local mode="$1" + RET=0 + + bond_reset "mode $mode arp_interval 100 arp_ip_target 192.0.3.10" + ip -n "${s_ns}" link add bond0.3 link bond0 type vlan id 3 + ip -n "${s_ns}" link set bond0.3 up + ip -n "${s_ns}" addr add 192.0.3.1/24 dev bond0.3 + ip -n "${s_ns}" addr add 2001:db8::3:1/64 dev bond0.3 + + slowwait_for_counter 5 5 tc_rule_handle_stats_get \ + "dev eth0.3 ingress" 101 ".packets" "-n ${c_ns}" &> /dev/null || RET=1 + log_test "vlan over bond arp" "$mode" +} + +vlan_over_bond_ns() +{ + local mode="$1" + RET=0 + + if skip_ns; then + log_test_skip "vlan_over_bond ns" "$mode" + return 0 + fi + + bond_reset "mode $mode arp_interval 100 ns_ip6_target 2001:db8::3:10" + ip -n "${s_ns}" link add bond0.3 link bond0 type vlan id 3 + ip -n "${s_ns}" link set bond0.3 up + ip -n "${s_ns}" addr add 192.0.3.1/24 dev bond0.3 + ip -n "${s_ns}" addr add 2001:db8::3:1/64 dev bond0.3 + + slowwait_for_counter 5 5 tc_rule_handle_stats_get \ + "dev eth0.3 ingress" 102 ".packets" "-n ${c_ns}" &> /dev/null || RET=1 + log_test "vlan over bond ns" "$mode" +} + +vlan_over_bond() +{ + # add vlan 3 for client + ip -n "${c_ns}" link add eth0.3 link eth0 type vlan id 3 + ip -n "${c_ns}" link set eth0.3 up + ip -n "${c_ns}" addr add 192.0.3.10/24 dev eth0.3 + ip -n "${c_ns}" addr add 2001:db8::3:10/64 dev eth0.3 + + # Add tc rule to check the vlan pkts + tc -n "${c_ns}" qdisc add dev eth0.3 clsact + tc -n "${c_ns}" filter add dev eth0.3 ingress protocol arp \ + handle 101 flower skip_hw arp_op request \ + arp_sip 192.0.3.1 arp_tip 192.0.3.10 action pass + tc -n "${c_ns}" filter add dev eth0.3 ingress protocol ipv6 \ + handle 102 flower skip_hw ip_proto icmpv6 \ + type 135 src_ip 2001:db8::3:1 action pass + + vlan_over_bond_arp "active-backup" + vlan_over_bond_ns "active-backup" +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh index 195ef83cfbf1..167aa4a4a12a 100644 --- a/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh @@ -39,6 +39,8 @@ g_ip4="192.0.2.254" s_ip6="2001:db8::1" c_ip6="2001:db8::10" g_ip6="2001:db8::254" +mac[0]="00:0a:0b:0c:0d:01" +mac[1]="00:0a:0b:0c:0d:02" gateway_create() { @@ -62,6 +64,7 @@ server_create() for i in $(seq 0 1); do ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns} + ip -n "${s_ns}" link set "eth${i}" addr "${mac[$i]}" ip -n ${g_ns} link set s${i} up ip -n ${g_ns} link set s${i} master br0 diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh index 3a1333d9a85b..23a2932301cc 100644 --- a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh @@ -26,6 +26,7 @@ # +-------------------------------------+ source bond_topo_2d1c.sh +mac[2]="00:0a:0b:0c:0d:03" setup_prepare() { @@ -36,6 +37,7 @@ setup_prepare() # Add the extra device as we use 3 down links for bond0 local i=2 ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns} + ip -n "${s_ns}" link set "eth${i}" addr "${mac[$i]}" ip -n ${g_ns} link set s${i} up ip -n ${g_ns} link set s${i} master br0 ip -n ${s_ns} link set eth${i} master bond0 diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config index 4d16a69ffc65..832fa1caeb66 100644 --- a/tools/testing/selftests/drivers/net/bonding/config +++ b/tools/testing/selftests/drivers/net/bonding/config @@ -10,3 +10,4 @@ CONFIG_NET_CLS_MATCHALL=m CONFIG_NET_SCH_INGRESS=y CONFIG_NLMON=y CONFIG_VETH=y +CONFIG_VLAN_8021Q=m diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c index 63ce708d93ed..e4b7c2b457ee 100644 --- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c +++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c @@ -2,6 +2,13 @@ // Copyright (c) 2025 Miklos Szeredi <miklos@szeredi.hu> #define _GNU_SOURCE + +// Needed for linux/fanotify.h +typedef struct { + int val[2]; +} __kernel_fsid_t; +#define __kernel_fsid_t __kernel_fsid_t + #include <fcntl.h> #include <sched.h> #include <stdio.h> @@ -10,20 +17,12 @@ #include <sys/mount.h> #include <unistd.h> #include <sys/syscall.h> +#include <sys/fanotify.h> #include "../../kselftest_harness.h" #include "../statmount/statmount.h" #include "../utils.h" -// Needed for linux/fanotify.h -#ifndef __kernel_fsid_t -typedef struct { - int val[2]; -} __kernel_fsid_t; -#endif - -#include <sys/fanotify.h> - static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX"; static const int mark_cmds[] = { diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c index 090a5ca65004..9f57ca46e3af 100644 --- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c +++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c @@ -2,6 +2,13 @@ // Copyright (c) 2025 Miklos Szeredi <miklos@szeredi.hu> #define _GNU_SOURCE + +// Needed for linux/fanotify.h +typedef struct { + int val[2]; +} __kernel_fsid_t; +#define __kernel_fsid_t __kernel_fsid_t + #include <fcntl.h> #include <sched.h> #include <stdio.h> @@ -10,21 +17,12 @@ #include <sys/mount.h> #include <unistd.h> #include <sys/syscall.h> +#include <sys/fanotify.h> #include "../../kselftest_harness.h" -#include "../../pidfd/pidfd.h" #include "../statmount/statmount.h" #include "../utils.h" -// Needed for linux/fanotify.h -#ifndef __kernel_fsid_t -typedef struct { - int val[2]; -} __kernel_fsid_t; -#endif - -#include <sys/fanotify.h> - static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX"; static const int mark_types[] = { diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index c7e03e1d6f63..2b31d4a93ad7 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -116,6 +116,7 @@ TEST_PROGS += skf_net_off.sh TEST_GEN_FILES += skf_net_off TEST_GEN_FILES += tfo TEST_PROGS += tfo_passive.sh +TEST_PROGS += broadcast_ether_dst.sh TEST_PROGS += broadcast_pmtu.sh TEST_PROGS += ipv6_force_forwarding.sh diff --git a/tools/testing/selftests/net/broadcast_ether_dst.sh b/tools/testing/selftests/net/broadcast_ether_dst.sh new file mode 100755 index 000000000000..334a7eca8a80 --- /dev/null +++ b/tools/testing/selftests/net/broadcast_ether_dst.sh @@ -0,0 +1,83 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Author: Brett A C Sheffield <bacs@librecast.net> +# Author: Oscar Maes <oscmaes92@gmail.com> +# +# Ensure destination ethernet field is correctly set for +# broadcast packets + +source lib.sh + +CLIENT_IP4="192.168.0.1" +GW_IP4="192.168.0.2" + +setup() { + setup_ns CLIENT_NS SERVER_NS + + ip -net "${SERVER_NS}" link add link1 type veth \ + peer name link0 netns "${CLIENT_NS}" + + ip -net "${CLIENT_NS}" link set link0 up + ip -net "${CLIENT_NS}" addr add "${CLIENT_IP4}"/24 dev link0 + + ip -net "${SERVER_NS}" link set link1 up + + ip -net "${CLIENT_NS}" route add default via "${GW_IP4}" + ip netns exec "${CLIENT_NS}" arp -s "${GW_IP4}" 00:11:22:33:44:55 +} + +cleanup() { + rm -f "${CAPFILE}" "${OUTPUT}" + ip -net "${SERVER_NS}" link del link1 + cleanup_ns "${CLIENT_NS}" "${SERVER_NS}" +} + +test_broadcast_ether_dst() { + local rc=0 + CAPFILE=$(mktemp -u cap.XXXXXXXXXX) + OUTPUT=$(mktemp -u out.XXXXXXXXXX) + + echo "Testing ethernet broadcast destination" + + # start tcpdump listening for icmp + # tcpdump will exit after receiving a single packet + # timeout will kill tcpdump if it is still running after 2s + timeout 2s ip netns exec "${CLIENT_NS}" \ + tcpdump -i link0 -c 1 -w "${CAPFILE}" icmp &> "${OUTPUT}" & + pid=$! + slowwait 1 grep -qs "listening" "${OUTPUT}" + + # send broadcast ping + ip netns exec "${CLIENT_NS}" \ + ping -W0.01 -c1 -b 255.255.255.255 &> /dev/null + + # wait for tcpdump for exit after receiving packet + wait "${pid}" + + # compare ethernet destination field to ff:ff:ff:ff:ff:ff + ether_dst=$(tcpdump -r "${CAPFILE}" -tnne 2>/dev/null | \ + awk '{sub(/,/,"",$3); print $3}') + if [[ "${ether_dst}" == "ff:ff:ff:ff:ff:ff" ]]; then + echo "[ OK ]" + rc="${ksft_pass}" + else + echo "[FAIL] expected dst ether addr to be ff:ff:ff:ff:ff:ff," \ + "got ${ether_dst}" + rc="${ksft_fail}" + fi + + return "${rc}" +} + +if [ ! -x "$(command -v tcpdump)" ]; then + echo "SKIP: Could not run test without tcpdump tool" + exit "${ksft_skip}" +fi + +trap cleanup EXIT + +setup +test_broadcast_ether_dst + +exit $? diff --git a/tools/testing/selftests/net/can/config b/tools/testing/selftests/net/can/config new file mode 100644 index 000000000000..188f79796670 --- /dev/null +++ b/tools/testing/selftests/net/can/config @@ -0,0 +1,3 @@ +CONFIG_CAN=m +CONFIG_CAN_DEV=m +CONFIG_CAN_VCAN=m diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 7a3cb4c09e45..d847ff1737c3 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -28,7 +28,7 @@ flush_pids() } # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGKILL &>/dev/null diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 4f07ac9fa207..b148cadb96d0 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -1093,6 +1093,7 @@ int main_loop_s(int listensock) struct pollfd polls; socklen_t salen; int remotesock; + int err = 0; int fd = 0; again: @@ -1125,7 +1126,7 @@ again: SOCK_TEST_TCPULP(remotesock, 0); memset(&winfo, 0, sizeof(winfo)); - copyfd_io(fd, remotesock, 1, true, &winfo); + err = copyfd_io(fd, remotesock, 1, true, &winfo); } else { perror("accept"); return 1; @@ -1134,10 +1135,10 @@ again: if (cfg_input) close(fd); - if (--cfg_repeat > 0) + if (!err && --cfg_repeat > 0) goto again; - return 0; + return err; } static void init_rng(void) @@ -1247,7 +1248,7 @@ void xdisconnect(int fd) else xerror("bad family"); - strcpy(cmd, "ss -M | grep -q "); + strcpy(cmd, "ss -Mnt | grep -q "); cmdlen = strlen(cmd); if (!inet_ntop(addr.ss_family, raw_addr, &cmd[cmdlen], sizeof(cmd) - cmdlen)) @@ -1257,7 +1258,7 @@ void xdisconnect(int fd) /* * wait until the pending data is completely flushed and all - * the MPTCP sockets reached the closed status. + * the sockets reached the closed status. * disconnect will bypass/ignore/drop any pending data. */ for (i = 0; ; i += msec_sleep) { diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 5e3c56253274..47ecb5b3836e 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -134,7 +134,7 @@ ns4="" TEST_GROUP="" # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { rm -f "$cin_disconnect" @@ -211,6 +211,11 @@ if $checksum; then done fi +if $capture; then + rndh="${ns1:4}" + mptcp_lib_pr_info "Packet capture files will have this prefix: ${rndh}-" +fi + set_ethtool_flags() { local ns="$1" local dev="$2" @@ -361,7 +366,6 @@ do_transfer() if $capture; then local capuser - local rndh="${connector_ns:4}" if [ -z $SUDO_USER ] ; then capuser="" else diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 82cae37d9c20..7fd555b123b9 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -8,7 +8,7 @@ # ShellCheck incorrectly believes that most of the code here is unreachable # because it's invoked by variable name, see how the "tests" array is used -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 . "$(dirname "${0}")/mptcp_lib.sh" diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 09cd24b2ae46..d62e653d48b0 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -384,7 +384,7 @@ mptcp_lib_make_file() { mptcp_lib_print_file_err() { ls -l "${1}" 1>&2 echo "Trailing bytes are: " - tail -c 27 "${1}" + tail -c 32 "${1}" | od -x | head -n2 } # $1: input file ; $2: output file ; $3: what kind of file diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c index e934dd26a59d..112c07c4c37a 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -667,22 +667,26 @@ static void process_one_client(int fd, int pipefd) do_getsockopts(&s, fd, ret, ret2); if (s.mptcpi_rcv_delta != (uint64_t)ret + 1) - xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64, s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - ret); + xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64 ", diff %" PRId64, + s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - (ret + 1)); /* be nice when running on top of older kernel */ if (s.pkt_stats_avail) { if (s.last_sample.mptcpi_bytes_sent != ret2) - xerror("mptcpi_bytes_sent %" PRIu64 ", expect %" PRIu64, + xerror("mptcpi_bytes_sent %" PRIu64 ", expect %" PRIu64 + ", diff %" PRId64, s.last_sample.mptcpi_bytes_sent, ret2, s.last_sample.mptcpi_bytes_sent - ret2); if (s.last_sample.mptcpi_bytes_received != ret) - xerror("mptcpi_bytes_received %" PRIu64 ", expect %" PRIu64, + xerror("mptcpi_bytes_received %" PRIu64 ", expect %" PRIu64 + ", diff %" PRId64, s.last_sample.mptcpi_bytes_received, ret, s.last_sample.mptcpi_bytes_received - ret); if (s.last_sample.mptcpi_bytes_acked != ret) - xerror("mptcpi_bytes_acked %" PRIu64 ", expect %" PRIu64, - s.last_sample.mptcpi_bytes_acked, ret2, - s.last_sample.mptcpi_bytes_acked - ret2); + xerror("mptcpi_bytes_acked %" PRIu64 ", expect %" PRIu64 + ", diff %" PRId64, + s.last_sample.mptcpi_bytes_acked, ret, + s.last_sample.mptcpi_bytes_acked - ret); } close(fd); diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 418a903c3a4d..f01989be6e9b 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -95,7 +95,7 @@ init() } # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { mptcp_lib_ns_exit "${ns1}" "${ns2}" "${ns_sbox}" diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index ac7ec6f94023..ec6a87588191 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -32,7 +32,7 @@ ns1="" err=$(mktemp) # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { rm -f "${err}" @@ -70,8 +70,9 @@ format_endpoints() { mptcp_lib_pm_nl_format_endpoints "${@}" } +# This function is invoked indirectly +#shellcheck disable=SC2317,SC2329 get_endpoint() { - # shellcheck disable=SC2317 # invoked indirectly mptcp_lib_pm_nl_get_endpoint "${ns1}" "${@}" } diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c index 994a556f46c1..93fea3442216 100644 --- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -188,6 +188,13 @@ static int capture_events(int fd, int event_group) fprintf(stderr, ",error:%u", *(__u8 *)RTA_DATA(attrs)); else if (attrs->rta_type == MPTCP_ATTR_SERVER_SIDE) fprintf(stderr, ",server_side:%u", *(__u8 *)RTA_DATA(attrs)); + else if (attrs->rta_type == MPTCP_ATTR_FLAGS) { + __u16 flags = *(__u16 *)RTA_DATA(attrs); + + /* only print when present, easier */ + if (flags & MPTCP_PM_EV_FLAG_DENY_JOIN_ID0) + fprintf(stderr, ",deny_join_id0:1"); + } attrs = RTA_NEXT(attrs, msg_len); } diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 2329c2f8519b..1903e8e84a31 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -35,7 +35,7 @@ usage() { } # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { rm -f "$cout" "$sout" diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 333064b0b5ac..3d45991f24ed 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -94,7 +94,7 @@ test_fail() } # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { print_title "Cleanup" @@ -201,6 +201,9 @@ make_connection() is_v6="v4" fi + # set this on the client side only: will not affect the rest + ip netns exec "$ns2" sysctl -q net.mptcp.allow_join_initial_addr_port=0 + :>"$client_evts" :>"$server_evts" @@ -223,23 +226,28 @@ make_connection() local client_token local client_port local client_serverside + local client_nojoin local server_token local server_serverside + local server_nojoin client_token=$(mptcp_lib_evts_get_info token "$client_evts") client_port=$(mptcp_lib_evts_get_info sport "$client_evts") client_serverside=$(mptcp_lib_evts_get_info server_side "$client_evts") + client_nojoin=$(mptcp_lib_evts_get_info deny_join_id0 "$client_evts") server_token=$(mptcp_lib_evts_get_info token "$server_evts") server_serverside=$(mptcp_lib_evts_get_info server_side "$server_evts") + server_nojoin=$(mptcp_lib_evts_get_info deny_join_id0 "$server_evts") print_test "Established IP${is_v6} MPTCP Connection ns2 => ns1" - if [ "$client_token" != "" ] && [ "$server_token" != "" ] && [ "$client_serverside" = 0 ] && - [ "$server_serverside" = 1 ] + if [ "${client_token}" != "" ] && [ "${server_token}" != "" ] && + [ "${client_serverside}" = 0 ] && [ "${server_serverside}" = 1 ] && + [ "${client_nojoin:-0}" = 0 ] && [ "${server_nojoin:-0}" = 1 ] then test_pass print_title "Connection info: ${client_addr}:${client_port} -> ${connect_addr}:${app_port}" else - test_fail "Expected tokens (c:${client_token} - s:${server_token}) and server (c:${client_serverside} - s:${server_serverside})" + test_fail "Expected tokens (c:${client_token} - s:${server_token}), server (c:${client_serverside} - s:${server_serverside}), nojoin (c:${client_nojoin} - s:${server_nojoin})" mptcp_lib_result_print_all_tap exit ${KSFT_FAIL} fi diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index 3c8d3455d8e7..b327d3061ed5 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -25,6 +25,7 @@ tests=" nat_related_v4 ip4-nat-related: ICMP related matches work with SNAT netlink_checks ovsnl: validate netlink attrs and settings upcall_interfaces ovs: test the upcall interfaces + tunnel_metadata ovs: test extraction of tunnel metadata drop_reason drop: test drop reasons are emitted psample psample: Sampling packets with psample" @@ -113,13 +114,13 @@ ovs_add_dp () { } ovs_add_if () { - info "Adding IF to DP: br:$2 if:$3" - if [ "$4" != "-u" ]; then - ovs_sbx "$1" python3 $ovs_base/ovs-dpctl.py add-if "$2" "$3" \ - || return 1 + info "Adding IF to DP: br:$3 if:$4 ($2)" + if [ "$5" != "-u" ]; then + ovs_sbx "$1" python3 $ovs_base/ovs-dpctl.py add-if \ + -t "$2" "$3" "$4" || return 1 else python3 $ovs_base/ovs-dpctl.py add-if \ - -u "$2" "$3" >$ovs_dir/$3.out 2>$ovs_dir/$3.err & + -u -t "$2" "$3" "$4" >$ovs_dir/$4.out 2>$ovs_dir/$4.err & pid=$! on_exit "ovs_sbx $1 kill -TERM $pid 2>/dev/null" fi @@ -166,9 +167,9 @@ ovs_add_netns_and_veths () { fi if [ "$7" != "-u" ]; then - ovs_add_if "$1" "$2" "$4" || return 1 + ovs_add_if "$1" "netdev" "$2" "$4" || return 1 else - ovs_add_if "$1" "$2" "$4" -u || return 1 + ovs_add_if "$1" "netdev" "$2" "$4" -u || return 1 fi if [ $TRACING -eq 1 ]; then @@ -756,6 +757,79 @@ test_upcall_interfaces() { return 0 } +ovs_add_kernel_tunnel() { + local sbxname=$1; shift + local ns=$1; shift + local tnl_type=$1; shift + local name=$1; shift + local addr=$1; shift + + info "setting up kernel ${tnl_type} tunnel ${name}" + ovs_sbx "${sbxname}" ip -netns ${ns} link add dev ${name} type ${tnl_type} $* || return 1 + on_exit "ovs_sbx ${sbxname} ip -netns ${ns} link del ${name} >/dev/null 2>&1" + ovs_sbx "${sbxname}" ip -netns ${ns} addr add dev ${name} ${addr} || return 1 + ovs_sbx "${sbxname}" ip -netns ${ns} link set dev ${name} mtu 1450 up || return 1 +} + +test_tunnel_metadata() { + which arping >/dev/null 2>&1 || return $ksft_skip + + sbxname="test_tunnel_metadata" + sbx_add "${sbxname}" || return 1 + + info "setting up new DP" + ovs_add_dp "${sbxname}" tdp0 -V 2:1 || return 1 + + ovs_add_netns_and_veths "${sbxname}" tdp0 tns left0 l0 \ + 172.31.110.1/24 || return 1 + + info "removing veth interface from openvswitch and setting IP" + ovs_del_if "${sbxname}" tdp0 left0 || return 1 + ovs_sbx "${sbxname}" ip addr add 172.31.110.2/24 dev left0 || return 1 + ovs_sbx "${sbxname}" ip link set left0 up || return 1 + + info "setting up tunnel port in openvswitch" + ovs_add_if "${sbxname}" "vxlan" tdp0 ovs-vxlan0 -u || return 1 + on_exit "ovs_sbx ${sbxname} ip link del ovs-vxlan0" + ovs_wait ip link show ovs-vxlan0 &>/dev/null || return 1 + ovs_sbx "${sbxname}" ip link set ovs-vxlan0 up || return 1 + + configs=$(echo ' + 1 172.31.221.1/24 1155332 32 set udpcsum flags\(df\|csum\) + 2 172.31.222.1/24 1234567 45 set noudpcsum flags\(df\) + 3 172.31.223.1/24 1020304 23 unset udpcsum flags\(csum\) + 4 172.31.224.1/24 1357986 15 unset noudpcsum' | sed '/^$/d') + + while read -r i addr id ttl df csum flags; do + ovs_add_kernel_tunnel "${sbxname}" tns vxlan vxlan${i} ${addr} \ + remote 172.31.110.2 id ${id} dstport 4789 \ + ttl ${ttl} df ${df} ${csum} || return 1 + done <<< "${configs}" + + ovs_wait grep -q 'listening on upcall packet handler' \ + ${ovs_dir}/ovs-vxlan0.out || return 1 + + info "sending arping" + for i in 1 2 3 4; do + ovs_sbx "${sbxname}" ip netns exec tns \ + arping -I vxlan${i} 172.31.22${i}.2 -c 1 \ + >${ovs_dir}/arping.stdout 2>${ovs_dir}/arping.stderr + done + + info "checking that received decapsulated packets carry correct metadata" + while read -r i addr id ttl df csum flags; do + arp_hdr="arp\\(sip=172.31.22${i}.1,tip=172.31.22${i}.2,op=1,sha=" + addrs="src=172.31.110.1,dst=172.31.110.2" + ports="tp_src=[0-9]*,tp_dst=4789" + tnl_md="tunnel\\(tun_id=${id},${addrs},ttl=${ttl},${ports},${flags}\\)" + + ovs_sbx "${sbxname}" grep -qE "MISS upcall.*${tnl_md}.*${arp_hdr}" \ + ${ovs_dir}/ovs-vxlan0.out || return 1 + done <<< "${configs}" + + return 0 +} + run_test() { ( tname="$1" diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-after-disconnect.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-after-disconnect.pkt new file mode 100644 index 000000000000..26794e7ddfd5 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-after-disconnect.pkt @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +`./defaults.sh + ./set_sysctls.py /proc/sys/net/ipv4/tcp_fastopen=0x602 /proc/sys/net/ipv4/tcp_timestamps=0` + + 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:10(10) win 32792 <mss 1460,nop,nop,sackOK> + +0 > S. 0:0(0) ack 11 win 65535 <mss 1460,nop,nop,sackOK> + +// sk->sk_state is TCP_SYN_RECV + +.1 accept(3, ..., ...) = 4 + +// tcp_disconnect() sets sk->sk_state to TCP_CLOSE + +0 connect(4, AF_UNSPEC, ...) = 0 + +0 > R. 1:1(0) ack 11 win 65535 + +// connect() sets sk->sk_state to TCP_SYN_SENT + +0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + +0 connect(4, ..., ...) = -1 EINPROGRESS (Operation is now in progress) + +0 > S 0:0(0) win 65535 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +// tp->fastopen_rsk must be NULL + +1 > S 0:0(0) win 65535 <mss 1460,nop,nop,sackOK,nop,wscale 8> diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 0f5640d8dc7f..dd093f9df6f1 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -2770,6 +2770,22 @@ TEST_F(tls_err, poll_partial_rec_async) } } +/* Use OOB+large send to trigger copy mode due to memory pressure. + * OOB causes a short read. + */ +TEST_F(tls_err, oob_pressure) +{ + char buf[1<<16]; + int i; + + memrnd(buf, sizeof(buf)); + + EXPECT_EQ(send(self->fd2, buf, 5, MSG_OOB), 5); + EXPECT_EQ(send(self->fd2, buf, sizeof(buf), 0), sizeof(buf)); + for (i = 0; i < 64; i++) + EXPECT_EQ(send(self->fd2, buf, 5, MSG_OOB), 5); +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; |