diff options
453 files changed, 5045 insertions, 2923 deletions
@@ -327,6 +327,7 @@ Henrik Rydberg <rydberg@bitmath.org> Herbert Xu <herbert@gondor.apana.org.au> Huacai Chen <chenhuacai@kernel.org> <chenhc@lemote.com> Huacai Chen <chenhuacai@kernel.org> <chenhuacai@loongson.cn> +Ignat Korchagin <ignat@linux.win> <ignat@cloudflare.com> Ike Panhc <ikepanhc@gmail.com> <ike.pan@canonical.com> J. Bruce Fields <bfields@fieldses.org> <bfields@redhat.com> J. Bruce Fields <bfields@fieldses.org> <bfields@citi.umich.edu> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 55ffc0f8858a..03a550630644 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -8196,6 +8196,9 @@ Kernel parameters p = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT (Reduce timeout of the SET_ADDRESS request from 5000 ms to 500 ms); + q = USB_QUIRK_FORCE_ONE_CONFIG (Device + claims zero configurations, + forcing to 1); Example: quirks=0781:5580:bk,0a5c:5834:gij usbhid.mousepoll= diff --git a/Documentation/dev-tools/kunit/run_wrapper.rst b/Documentation/dev-tools/kunit/run_wrapper.rst index 3c0b585dcfff..770bb09a475a 100644 --- a/Documentation/dev-tools/kunit/run_wrapper.rst +++ b/Documentation/dev-tools/kunit/run_wrapper.rst @@ -336,6 +336,8 @@ command line arguments: - ``--list_tests_attr``: If set, lists all tests that will be run and all of their attributes. +- ``--list_suites``: If set, lists all suites that will be run. + Command-line completion ============================== diff --git a/Documentation/devicetree/bindings/display/msm/dp-controller.yaml b/Documentation/devicetree/bindings/display/msm/dp-controller.yaml index ebda78db87a6..02ddfaab5f56 100644 --- a/Documentation/devicetree/bindings/display/msm/dp-controller.yaml +++ b/Documentation/devicetree/bindings/display/msm/dp-controller.yaml @@ -253,7 +253,6 @@ allOf: enum: # these platforms support 2 streams MST on some interfaces, # others are SST only - - qcom,glymur-dp - qcom,sc8280xp-dp - qcom,x1e80100-dp then: @@ -310,6 +309,26 @@ allOf: minItems: 6 maxItems: 8 + - if: + properties: + compatible: + contains: + enum: + # these platforms support 2 streams MST on some interfaces, + # others are SST only, but all controllers have 4 ports + - qcom,glymur-dp + then: + properties: + reg: + minItems: 9 + maxItems: 9 + clocks: + minItems: 5 + maxItems: 6 + clocks-names: + minItems: 5 + maxItems: 6 + unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml index 2329ed96e6cb..64dde43373ac 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml @@ -176,13 +176,17 @@ examples: }; }; - displayport-controller@ae90000 { + displayport-controller@af54000 { compatible = "qcom,glymur-dp"; - reg = <0xae90000 0x200>, - <0xae90200 0x200>, - <0xae90400 0x600>, - <0xae91000 0x400>, - <0xae91400 0x400>; + reg = <0xaf54000 0x200>, + <0xaf54200 0x200>, + <0xaf55000 0xc00>, + <0xaf56000 0x400>, + <0xaf57000 0x400>, + <0xaf58000 0x400>, + <0xaf59000 0x400>, + <0xaf5a000 0x600>, + <0xaf5b000 0x600>; interrupt-parent = <&mdss>; interrupts = <12>; diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml index d55fda9a523e..a38c2261ef1a 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml @@ -10,7 +10,7 @@ maintainers: - Krzysztof Kozlowski <krzk@kernel.org> description: - SM8650 MSM Mobile Display Subsystem(MDSS), which encapsulates sub-blocks like + SM8750 MSM Mobile Display Subsystem(MDSS), which encapsulates sub-blocks like DPU display controller, DSI and DP interfaces etc. $ref: /schemas/display/msm/mdss-common.yaml# diff --git a/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml b/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml index 914200188809..082fdc2e69ea 100644 --- a/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Synopsys DesignWare APB I2C Controller maintainers: - - Jarkko Nikula <jarkko.nikula@linux.intel.com> + - Mika Westerberg <mika.westerberg@linux.intel.com> allOf: - $ref: /schemas/i2c/i2c-controller.yaml# diff --git a/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml b/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml index a6067030c5ed..6af4ff233158 100644 --- a/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml +++ b/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml @@ -6,9 +6,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Allwinner A31 SPI Controller -allOf: - - $ref: spi-controller.yaml - maintainers: - Chen-Yu Tsai <wens@csie.org> - Maxime Ripard <mripard@kernel.org> @@ -82,11 +79,11 @@ patternProperties: spi-rx-bus-width: items: - - const: 1 + enum: [0, 1, 2, 4] spi-tx-bus-width: items: - - const: 1 + enum: [0, 1, 2, 4] required: - compatible @@ -95,6 +92,28 @@ required: - clocks - clock-names +allOf: + - $ref: spi-controller.yaml + - if: + not: + properties: + compatible: + contains: + enum: + - allwinner,sun50i-r329-spi + - allwinner,sun55i-a523-spi + then: + patternProperties: + "^.*@[0-9a-f]+": + properties: + spi-rx-bus-width: + items: + enum: [0, 1] + + spi-tx-bus-width: + items: + enum: [0, 1] + unevaluatedProperties: false examples: diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst index 9e2882d937b4..d74c2c2b9ef3 100644 --- a/Documentation/scheduler/sched-ext.rst +++ b/Documentation/scheduler/sched-ext.rst @@ -43,7 +43,6 @@ options should be enabled to use sched_ext: CONFIG_DEBUG_INFO_BTF=y CONFIG_BPF_JIT_ALWAYS_ON=y CONFIG_BPF_JIT_DEFAULT_ON=y - CONFIG_PAHOLE_HAS_BTF_TAG=y sched_ext is used only when the BPF scheduler is loaded and running. @@ -58,7 +57,8 @@ in ``ops->flags``, all ``SCHED_NORMAL``, ``SCHED_BATCH``, ``SCHED_IDLE``, and However, when the BPF scheduler is loaded and ``SCX_OPS_SWITCH_PARTIAL`` is set in ``ops->flags``, only tasks with the ``SCHED_EXT`` policy are scheduled by sched_ext, while tasks with ``SCHED_NORMAL``, ``SCHED_BATCH`` and -``SCHED_IDLE`` policies are scheduled by the fair-class scheduler. +``SCHED_IDLE`` policies are scheduled by the fair-class scheduler which has +higher sched_class precedence than ``SCHED_EXT``. Terminating the sched_ext scheduler program, triggering `SysRq-S`, or detection of any internal error including stalled runnable tasks aborts the @@ -345,6 +345,8 @@ Where to Look The functions prefixed with ``scx_bpf_`` can be called from the BPF scheduler. +* ``kernel/sched/ext_idle.c`` contains the built-in idle CPU selection policy. + * ``tools/sched_ext/`` hosts example BPF scheduler implementations. * ``scx_simple[.bpf].c``: Minimal global FIFO scheduler example using a @@ -353,13 +355,35 @@ Where to Look * ``scx_qmap[.bpf].c``: A multi-level FIFO scheduler supporting five levels of priority implemented with ``BPF_MAP_TYPE_QUEUE``. + * ``scx_central[.bpf].c``: A central FIFO scheduler where all scheduling + decisions are made on one CPU, demonstrating ``LOCAL_ON`` dispatching, + tickless operation, and kthread preemption. + + * ``scx_cpu0[.bpf].c``: A scheduler that queues all tasks to a shared DSQ + and only dispatches them on CPU0 in FIFO order. Useful for testing bypass + behavior. + + * ``scx_flatcg[.bpf].c``: A flattened cgroup hierarchy scheduler + implementing hierarchical weight-based cgroup CPU control by compounding + each cgroup's share at every level into a single flat scheduling layer. + + * ``scx_pair[.bpf].c``: A core-scheduling example that always makes + sibling CPU pairs execute tasks from the same CPU cgroup. + + * ``scx_sdt[.bpf].c``: A variation of ``scx_simple`` demonstrating BPF + arena memory management for per-task data. + + * ``scx_userland[.bpf].c``: A minimal scheduler demonstrating user space + scheduling. Tasks with CPU affinity are direct-dispatched in FIFO order; + all others are scheduled in user space by a simple vruntime scheduler. + ABI Instability =============== The APIs provided by sched_ext to BPF schedulers programs have no stability guarantees. This includes the ops table callbacks and constants defined in ``include/linux/sched/ext.h``, as well as the ``scx_bpf_`` kfuncs defined in -``kernel/sched/ext.c``. +``kernel/sched/ext.c`` and ``kernel/sched/ext_idle.c``. While we will attempt to provide a relatively stable API surface when possible, they are subject to change without warning between kernel diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 6f85e1b321dd..032516783e96 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -8435,115 +8435,123 @@ KVM_CHECK_EXTENSION. The valid bits in cap.args[0] are: -=================================== ============================================ - KVM_X86_QUIRK_LINT0_REENABLED By default, the reset value for the LVT - LINT0 register is 0x700 (APIC_MODE_EXTINT). - When this quirk is disabled, the reset value - is 0x10000 (APIC_LVT_MASKED). - - KVM_X86_QUIRK_CD_NW_CLEARED By default, KVM clears CR0.CD and CR0.NW on - AMD CPUs to workaround buggy guest firmware - that runs in perpetuity with CR0.CD, i.e. - with caches in "no fill" mode. - - When this quirk is disabled, KVM does not - change the value of CR0.CD and CR0.NW. - - KVM_X86_QUIRK_LAPIC_MMIO_HOLE By default, the MMIO LAPIC interface is - available even when configured for x2APIC - mode. When this quirk is disabled, KVM - disables the MMIO LAPIC interface if the - LAPIC is in x2APIC mode. - - KVM_X86_QUIRK_OUT_7E_INC_RIP By default, KVM pre-increments %rip before - exiting to userspace for an OUT instruction - to port 0x7e. When this quirk is disabled, - KVM does not pre-increment %rip before - exiting to userspace. - - KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT When this quirk is disabled, KVM sets - CPUID.01H:ECX[bit 3] (MONITOR/MWAIT) if - IA32_MISC_ENABLE[bit 18] (MWAIT) is set. - Additionally, when this quirk is disabled, - KVM clears CPUID.01H:ECX[bit 3] if - IA32_MISC_ENABLE[bit 18] is cleared. - - KVM_X86_QUIRK_FIX_HYPERCALL_INSN By default, KVM rewrites guest - VMMCALL/VMCALL instructions to match the - vendor's hypercall instruction for the - system. When this quirk is disabled, KVM - will no longer rewrite invalid guest - hypercall instructions. Executing the - incorrect hypercall instruction will - generate a #UD within the guest. - -KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By default, KVM emulates MONITOR/MWAIT (if - they are intercepted) as NOPs regardless of - whether or not MONITOR/MWAIT are supported - according to guest CPUID. When this quirk - is disabled and KVM_X86_DISABLE_EXITS_MWAIT - is not set (MONITOR/MWAIT are intercepted), - KVM will inject a #UD on MONITOR/MWAIT if - they're unsupported per guest CPUID. Note, - KVM will modify MONITOR/MWAIT support in - guest CPUID on writes to MISC_ENABLE if - KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is - disabled. - -KVM_X86_QUIRK_SLOT_ZAP_ALL By default, for KVM_X86_DEFAULT_VM VMs, KVM - invalidates all SPTEs in all memslots and - address spaces when a memslot is deleted or - moved. When this quirk is disabled (or the - VM type isn't KVM_X86_DEFAULT_VM), KVM only - ensures the backing memory of the deleted - or moved memslot isn't reachable, i.e KVM - _may_ invalidate only SPTEs related to the - memslot. - -KVM_X86_QUIRK_STUFF_FEATURE_MSRS By default, at vCPU creation, KVM sets the - vCPU's MSR_IA32_PERF_CAPABILITIES (0x345), - MSR_IA32_ARCH_CAPABILITIES (0x10a), - MSR_PLATFORM_INFO (0xce), and all VMX MSRs - (0x480..0x492) to the maximal capabilities - supported by KVM. KVM also sets - MSR_IA32_UCODE_REV (0x8b) to an arbitrary - value (which is different for Intel vs. - AMD). Lastly, when guest CPUID is set (by - userspace), KVM modifies select VMX MSR - fields to force consistency between guest - CPUID and L2's effective ISA. When this - quirk is disabled, KVM zeroes the vCPU's MSR - values (with two exceptions, see below), - i.e. treats the feature MSRs like CPUID - leaves and gives userspace full control of - the vCPU model definition. This quirk does - not affect VMX MSRs CR0/CR4_FIXED1 (0x487 - and 0x489), as KVM does now allow them to - be set by userspace (KVM sets them based on - guest CPUID, for safety purposes). - -KVM_X86_QUIRK_IGNORE_GUEST_PAT By default, on Intel platforms, KVM ignores - guest PAT and forces the effective memory - type to WB in EPT. The quirk is not available - on Intel platforms which are incapable of - safely honoring guest PAT (i.e., without CPU - self-snoop, KVM always ignores guest PAT and - forces effective memory type to WB). It is - also ignored on AMD platforms or, on Intel, - when a VM has non-coherent DMA devices - assigned; KVM always honors guest PAT in - such case. The quirk is needed to avoid - slowdowns on certain Intel Xeon platforms - (e.g. ICX, SPR) where self-snoop feature is - supported but UC is slow enough to cause - issues with some older guests that use - UC instead of WC to map the video RAM. - Userspace can disable the quirk to honor - guest PAT if it knows that there is no such - guest software, for example if it does not - expose a bochs graphics device (which is - known to have had a buggy driver). -=================================== ============================================ +======================================== ================================================ +KVM_X86_QUIRK_LINT0_REENABLED By default, the reset value for the LVT + LINT0 register is 0x700 (APIC_MODE_EXTINT). + When this quirk is disabled, the reset value + is 0x10000 (APIC_LVT_MASKED). + +KVM_X86_QUIRK_CD_NW_CLEARED By default, KVM clears CR0.CD and CR0.NW on + AMD CPUs to workaround buggy guest firmware + that runs in perpetuity with CR0.CD, i.e. + with caches in "no fill" mode. + + When this quirk is disabled, KVM does not + change the value of CR0.CD and CR0.NW. + +KVM_X86_QUIRK_LAPIC_MMIO_HOLE By default, the MMIO LAPIC interface is + available even when configured for x2APIC + mode. When this quirk is disabled, KVM + disables the MMIO LAPIC interface if the + LAPIC is in x2APIC mode. + +KVM_X86_QUIRK_OUT_7E_INC_RIP By default, KVM pre-increments %rip before + exiting to userspace for an OUT instruction + to port 0x7e. When this quirk is disabled, + KVM does not pre-increment %rip before + exiting to userspace. + +KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT When this quirk is disabled, KVM sets + CPUID.01H:ECX[bit 3] (MONITOR/MWAIT) if + IA32_MISC_ENABLE[bit 18] (MWAIT) is set. + Additionally, when this quirk is disabled, + KVM clears CPUID.01H:ECX[bit 3] if + IA32_MISC_ENABLE[bit 18] is cleared. + +KVM_X86_QUIRK_FIX_HYPERCALL_INSN By default, KVM rewrites guest + VMMCALL/VMCALL instructions to match the + vendor's hypercall instruction for the + system. When this quirk is disabled, KVM + will no longer rewrite invalid guest + hypercall instructions. Executing the + incorrect hypercall instruction will + generate a #UD within the guest. + +KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By default, KVM emulates MONITOR/MWAIT (if + they are intercepted) as NOPs regardless of + whether or not MONITOR/MWAIT are supported + according to guest CPUID. When this quirk + is disabled and KVM_X86_DISABLE_EXITS_MWAIT + is not set (MONITOR/MWAIT are intercepted), + KVM will inject a #UD on MONITOR/MWAIT if + they're unsupported per guest CPUID. Note, + KVM will modify MONITOR/MWAIT support in + guest CPUID on writes to MISC_ENABLE if + KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is + disabled. + +KVM_X86_QUIRK_SLOT_ZAP_ALL By default, for KVM_X86_DEFAULT_VM VMs, KVM + invalidates all SPTEs in all memslots and + address spaces when a memslot is deleted or + moved. When this quirk is disabled (or the + VM type isn't KVM_X86_DEFAULT_VM), KVM only + ensures the backing memory of the deleted + or moved memslot isn't reachable, i.e KVM + _may_ invalidate only SPTEs related to the + memslot. + +KVM_X86_QUIRK_STUFF_FEATURE_MSRS By default, at vCPU creation, KVM sets the + vCPU's MSR_IA32_PERF_CAPABILITIES (0x345), + MSR_IA32_ARCH_CAPABILITIES (0x10a), + MSR_PLATFORM_INFO (0xce), and all VMX MSRs + (0x480..0x492) to the maximal capabilities + supported by KVM. KVM also sets + MSR_IA32_UCODE_REV (0x8b) to an arbitrary + value (which is different for Intel vs. + AMD). Lastly, when guest CPUID is set (by + userspace), KVM modifies select VMX MSR + fields to force consistency between guest + CPUID and L2's effective ISA. When this + quirk is disabled, KVM zeroes the vCPU's MSR + values (with two exceptions, see below), + i.e. treats the feature MSRs like CPUID + leaves and gives userspace full control of + the vCPU model definition. This quirk does + not affect VMX MSRs CR0/CR4_FIXED1 (0x487 + and 0x489), as KVM does now allow them to + be set by userspace (KVM sets them based on + guest CPUID, for safety purposes). + +KVM_X86_QUIRK_IGNORE_GUEST_PAT By default, on Intel platforms, KVM ignores + guest PAT and forces the effective memory + type to WB in EPT. The quirk is not available + on Intel platforms which are incapable of + safely honoring guest PAT (i.e., without CPU + self-snoop, KVM always ignores guest PAT and + forces effective memory type to WB). It is + also ignored on AMD platforms or, on Intel, + when a VM has non-coherent DMA devices + assigned; KVM always honors guest PAT in + such case. The quirk is needed to avoid + slowdowns on certain Intel Xeon platforms + (e.g. ICX, SPR) where self-snoop feature is + supported but UC is slow enough to cause + issues with some older guests that use + UC instead of WC to map the video RAM. + Userspace can disable the quirk to honor + guest PAT if it knows that there is no such + guest software, for example if it does not + expose a bochs graphics device (which is + known to have had a buggy driver). + +KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM By default, KVM relaxes the consistency + check for GUEST_IA32_DEBUGCTL in vmcs12 + to allow FREEZE_IN_SMM to be set. When + this quirk is disabled, KVM requires this + bit to be cleared. Note that the vmcs02 + bit is still completely controlled by the + host, regardless of the quirk setting. +======================================== ================================================ 7.32 KVM_CAP_MAX_VCPU_ID ------------------------ diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index ae8bce7fecbe..662231e958a0 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -17,6 +17,8 @@ The acquisition orders for mutexes are as follows: - kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock +- vcpu->mutex is taken outside kvm->slots_lock and kvm->slots_arch_lock + - kvm->slots_lock is taken outside kvm->irq_lock, though acquiring them together is quite rare. diff --git a/MAINTAINERS b/MAINTAINERS index bc3bcc641663..d7241695df96 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4022,7 +4022,7 @@ F: drivers/hwmon/asus_wmi_sensors.c ASYMMETRIC KEYS M: David Howells <dhowells@redhat.com> M: Lukas Wunner <lukas@wunner.de> -M: Ignat Korchagin <ignat@cloudflare.com> +M: Ignat Korchagin <ignat@linux.win> L: keyrings@vger.kernel.org L: linux-crypto@vger.kernel.org S: Maintained @@ -4035,7 +4035,7 @@ F: include/linux/verification.h ASYMMETRIC KEYS - ECDSA M: Lukas Wunner <lukas@wunner.de> -M: Ignat Korchagin <ignat@cloudflare.com> +M: Ignat Korchagin <ignat@linux.win> R: Stefan Berger <stefanb@linux.ibm.com> L: linux-crypto@vger.kernel.org S: Maintained @@ -4045,14 +4045,14 @@ F: include/crypto/ecc* ASYMMETRIC KEYS - GOST M: Lukas Wunner <lukas@wunner.de> -M: Ignat Korchagin <ignat@cloudflare.com> +M: Ignat Korchagin <ignat@linux.win> L: linux-crypto@vger.kernel.org S: Odd fixes F: crypto/ecrdsa* ASYMMETRIC KEYS - RSA M: Lukas Wunner <lukas@wunner.de> -M: Ignat Korchagin <ignat@cloudflare.com> +M: Ignat Korchagin <ignat@linux.win> L: linux-crypto@vger.kernel.org S: Maintained F: crypto/rsa* @@ -8626,9 +8626,8 @@ F: drivers/gpu/drm/lima/ F: include/uapi/drm/lima_drm.h DRM DRIVERS FOR LOONGSON -M: Sui Jingfeng <suijingfeng@loongson.cn> L: dri-devel@lists.freedesktop.org -S: Supported +S: Orphan T: git https://gitlab.freedesktop.org/drm/misc/kernel.git F: drivers/gpu/drm/loongson/ @@ -21937,7 +21936,7 @@ F: drivers/media/radio/radio-tea5777.c RADOS BLOCK DEVICE (RBD) M: Ilya Dryomov <idryomov@gmail.com> -R: Dongsheng Yang <dongsheng.yang@easystack.cn> +R: Dongsheng Yang <dongsheng.yang@linux.dev> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ @@ -2,7 +2,7 @@ VERSION = 7 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Baby Opossum Posse # *DOCUMENTATION* @@ -476,6 +476,7 @@ KBUILD_USERLDFLAGS := $(USERLDFLAGS) export rust_common_flags := --edition=2021 \ -Zbinary_dep_depinfo=y \ -Astable_features \ + -Aunused_features \ -Dnon_ascii_idents \ -Dunsafe_op_in_unsafe_fn \ -Wmissing_docs \ @@ -1113,6 +1114,9 @@ KBUILD_CFLAGS += -fno-builtin-wcslen # change __FILE__ to the relative path to the source directory ifdef building_out_of_srctree KBUILD_CPPFLAGS += -fmacro-prefix-map=$(srcroot)/= +ifeq ($(call rustc-option-yn, --remap-path-scope=macro),y) +KBUILD_RUSTFLAGS += --remap-path-prefix=$(srcroot)/= --remap-path-scope=macro +endif endif # include additional Makefiles when needed diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index f75d75cf91c8..70d05f74049e 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -279,7 +279,6 @@ CONFIG_TI_CPSW_SWITCHDEV=y CONFIG_TI_CPTS=y CONFIG_TI_KEYSTONE_NETCP=y CONFIG_TI_KEYSTONE_NETCP_ETHSS=y -CONFIG_TI_PRUSS=m CONFIG_TI_PRUETH=m CONFIG_XILINX_EMACLITE=y CONFIG_SFP=m diff --git a/arch/arm64/boot/dts/renesas/r8a78000.dtsi b/arch/arm64/boot/dts/renesas/r8a78000.dtsi index 4c97298fa763..3e1c98903cea 100644 --- a/arch/arm64/boot/dts/renesas/r8a78000.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a78000.dtsi @@ -698,7 +698,7 @@ compatible = "renesas,scif-r8a78000", "renesas,rcar-gen5-scif", "renesas,scif"; reg = <0 0xc0700000 0 0x40>; - interrupts = <GIC_SPI 4074 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 10 IRQ_TYPE_LEVEL_HIGH>; clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd16>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; @@ -708,7 +708,7 @@ compatible = "renesas,scif-r8a78000", "renesas,rcar-gen5-scif", "renesas,scif"; reg = <0 0xc0704000 0 0x40>; - interrupts = <GIC_SPI 4075 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 11 IRQ_TYPE_LEVEL_HIGH>; clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd16>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; @@ -718,7 +718,7 @@ compatible = "renesas,scif-r8a78000", "renesas,rcar-gen5-scif", "renesas,scif"; reg = <0 0xc0708000 0 0x40>; - interrupts = <GIC_SPI 4076 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 12 IRQ_TYPE_LEVEL_HIGH>; clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd16>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; @@ -728,7 +728,7 @@ compatible = "renesas,scif-r8a78000", "renesas,rcar-gen5-scif", "renesas,scif"; reg = <0 0xc070c000 0 0x40>; - interrupts = <GIC_SPI 4077 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 13 IRQ_TYPE_LEVEL_HIGH>; clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd16>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; @@ -738,7 +738,7 @@ compatible = "renesas,hscif-r8a78000", "renesas,rcar-gen5-hscif", "renesas,hscif"; reg = <0 0xc0710000 0 0x60>; - interrupts = <GIC_SPI 4078 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 14 IRQ_TYPE_LEVEL_HIGH>; clocks = <&dummy_clk_sgasyncd4>, <&dummy_clk_sgasyncd4>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; @@ -748,7 +748,7 @@ compatible = "renesas,hscif-r8a78000", "renesas,rcar-gen5-hscif", "renesas,hscif"; reg = <0 0xc0714000 0 0x60>; - interrupts = <GIC_SPI 4079 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 15 IRQ_TYPE_LEVEL_HIGH>; clocks = <&dummy_clk_sgasyncd4>, <&dummy_clk_sgasyncd4>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; @@ -758,7 +758,7 @@ compatible = "renesas,hscif-r8a78000", "renesas,rcar-gen5-hscif", "renesas,hscif"; reg = <0 0xc0718000 0 0x60>; - interrupts = <GIC_SPI 4080 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 16 IRQ_TYPE_LEVEL_HIGH>; clocks = <&dummy_clk_sgasyncd4>, <&dummy_clk_sgasyncd4>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; @@ -768,7 +768,7 @@ compatible = "renesas,hscif-r8a78000", "renesas,rcar-gen5-hscif", "renesas,hscif"; reg = <0 0xc071c000 0 0x60>; - interrupts = <GIC_SPI 4081 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 17 IRQ_TYPE_LEVEL_HIGH>; clocks = <&dummy_clk_sgasyncd4>, <&dummy_clk_sgasyncd4>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; diff --git a/arch/arm64/boot/dts/renesas/r9a09g057.dtsi b/arch/arm64/boot/dts/renesas/r9a09g057.dtsi index 80cba9fcfe7b..504c28386622 100644 --- a/arch/arm64/boot/dts/renesas/r9a09g057.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a09g057.dtsi @@ -581,16 +581,6 @@ status = "disabled"; }; - wdt0: watchdog@11c00400 { - compatible = "renesas,r9a09g057-wdt"; - reg = <0 0x11c00400 0 0x400>; - clocks = <&cpg CPG_MOD 0x4b>, <&cpg CPG_MOD 0x4c>; - clock-names = "pclk", "oscclk"; - resets = <&cpg 0x75>; - power-domains = <&cpg>; - status = "disabled"; - }; - wdt1: watchdog@14400000 { compatible = "renesas,r9a09g057-wdt"; reg = <0 0x14400000 0 0x400>; @@ -601,26 +591,6 @@ status = "disabled"; }; - wdt2: watchdog@13000000 { - compatible = "renesas,r9a09g057-wdt"; - reg = <0 0x13000000 0 0x400>; - clocks = <&cpg CPG_MOD 0x4f>, <&cpg CPG_MOD 0x50>; - clock-names = "pclk", "oscclk"; - resets = <&cpg 0x77>; - power-domains = <&cpg>; - status = "disabled"; - }; - - wdt3: watchdog@13000400 { - compatible = "renesas,r9a09g057-wdt"; - reg = <0 0x13000400 0 0x400>; - clocks = <&cpg CPG_MOD 0x51>, <&cpg CPG_MOD 0x52>; - clock-names = "pclk", "oscclk"; - resets = <&cpg 0x78>; - power-domains = <&cpg>; - status = "disabled"; - }; - rtc: rtc@11c00800 { compatible = "renesas,r9a09g057-rtca3", "renesas,rz-rtca3"; reg = <0 0x11c00800 0 0x400>; diff --git a/arch/arm64/boot/dts/renesas/r9a09g077.dtsi b/arch/arm64/boot/dts/renesas/r9a09g077.dtsi index 14d7fb6f8952..9d0b4d8d3d5b 100644 --- a/arch/arm64/boot/dts/renesas/r9a09g077.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a09g077.dtsi @@ -974,8 +974,8 @@ cpg: clock-controller@80280000 { compatible = "renesas,r9a09g077-cpg-mssr"; - reg = <0 0x80280000 0 0x1000>, - <0 0x81280000 0 0x9000>; + reg = <0 0x80280000 0 0x10000>, + <0 0x81280000 0 0x10000>; clocks = <&extal_clk>; clock-names = "extal"; #clock-cells = <2>; diff --git a/arch/arm64/boot/dts/renesas/r9a09g087.dtsi b/arch/arm64/boot/dts/renesas/r9a09g087.dtsi index 4a1339561332..d407c48f9966 100644 --- a/arch/arm64/boot/dts/renesas/r9a09g087.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a09g087.dtsi @@ -977,8 +977,8 @@ cpg: clock-controller@80280000 { compatible = "renesas,r9a09g087-cpg-mssr"; - reg = <0 0x80280000 0 0x1000>, - <0 0x81280000 0 0x9000>; + reg = <0 0x80280000 0 0x10000>, + <0 0x81280000 0 0x10000>; clocks = <&extal_clk>; clock-names = "extal"; #clock-cells = <2>; diff --git a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi index 982f17aafbc5..b45acfe6288a 100644 --- a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi +++ b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi @@ -162,7 +162,7 @@ <100000000>; renesas,settings = [ 80 00 11 19 4c 42 dc 2f 06 7d 20 1a 5f 1e f2 27 - 00 40 00 00 00 00 00 00 06 0c 19 02 3f f0 90 86 + 00 40 00 00 00 00 00 00 06 0c 19 02 3b f0 90 86 a0 80 30 30 9c ]; }; diff --git a/arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi b/arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi index 510399febf29..f87c2492f414 100644 --- a/arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi +++ b/arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi @@ -53,6 +53,7 @@ regulator-max-microvolt = <3300000>; gpios-states = <0>; states = <3300000 0>, <1800000 1>; + regulator-ramp-delay = <60>; }; #endif diff --git a/arch/arm64/boot/dts/renesas/rzv2-evk-cn15-sd.dtso b/arch/arm64/boot/dts/renesas/rzv2-evk-cn15-sd.dtso index 0af1e0a6c7f4..fc53c1aae3b5 100644 --- a/arch/arm64/boot/dts/renesas/rzv2-evk-cn15-sd.dtso +++ b/arch/arm64/boot/dts/renesas/rzv2-evk-cn15-sd.dtso @@ -25,6 +25,7 @@ regulator-max-microvolt = <3300000>; gpios-states = <0>; states = <3300000 0>, <1800000 1>; + regulator-ramp-delay = <60>; }; }; diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c index cb87c8fc66b3..00530b291010 100644 --- a/arch/arm64/crypto/aes-neonbs-glue.c +++ b/arch/arm64/crypto/aes-neonbs-glue.c @@ -76,19 +76,24 @@ static int aesbs_setkey(struct crypto_skcipher *tfm, const u8 *in_key, unsigned int key_len) { struct aesbs_ctx *ctx = crypto_skcipher_ctx(tfm); - struct crypto_aes_ctx rk; + struct crypto_aes_ctx *rk; int err; - err = aes_expandkey(&rk, in_key, key_len); + rk = kmalloc(sizeof(*rk), GFP_KERNEL); + if (!rk) + return -ENOMEM; + + err = aes_expandkey(rk, in_key, key_len); if (err) - return err; + goto out; ctx->rounds = 6 + key_len / 4; scoped_ksimd() - aesbs_convert_key(ctx->rk, rk.key_enc, ctx->rounds); - - return 0; + aesbs_convert_key(ctx->rk, rk->key_enc, ctx->rounds); +out: + kfree_sensitive(rk); + return err; } static int __ecb_crypt(struct skcipher_request *req, @@ -133,22 +138,26 @@ static int aesbs_cbc_ctr_setkey(struct crypto_skcipher *tfm, const u8 *in_key, unsigned int key_len) { struct aesbs_cbc_ctr_ctx *ctx = crypto_skcipher_ctx(tfm); - struct crypto_aes_ctx rk; + struct crypto_aes_ctx *rk; int err; - err = aes_expandkey(&rk, in_key, key_len); + rk = kmalloc(sizeof(*rk), GFP_KERNEL); + if (!rk) + return -ENOMEM; + + err = aes_expandkey(rk, in_key, key_len); if (err) - return err; + goto out; ctx->key.rounds = 6 + key_len / 4; - memcpy(ctx->enc, rk.key_enc, sizeof(ctx->enc)); + memcpy(ctx->enc, rk->key_enc, sizeof(ctx->enc)); scoped_ksimd() - aesbs_convert_key(ctx->key.rk, rk.key_enc, ctx->key.rounds); - memzero_explicit(&rk, sizeof(rk)); - - return 0; + aesbs_convert_key(ctx->key.rk, rk->key_enc, ctx->key.rounds); +out: + kfree_sensitive(rk); + return err; } static int cbc_encrypt(struct skcipher_request *req) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 2ca264b3db5f..70cb9cfd760a 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -784,6 +784,9 @@ struct kvm_host_data { /* Number of debug breakpoints/watchpoints for this CPU (minus 1) */ unsigned int debug_brps; unsigned int debug_wrps; + + /* Last vgic_irq part of the AP list recorded in an LR */ + struct vgic_irq *last_lr_irq; }; struct kvm_host_psci_config { diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index c31f8e17732a..32c2dbcc0c64 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2345,6 +2345,15 @@ static bool can_trap_icv_dir_el1(const struct arm64_cpu_capabilities *entry, !is_midr_in_range_list(has_vgic_v3)) return false; + /* + * pKVM prevents late onlining of CPUs. This means that whatever + * state the capability is in after deprivilege cannot be affected + * by a new CPU booting -- this is garanteed to be a CPU we have + * already seen, and the cap is therefore unchanged. + */ + if (system_capabilities_finalized() && is_protected_kvm_enabled()) + return cpus_have_final_cap(ARM64_HAS_ICH_HCR_EL2_TDIR); + if (is_kernel_in_hyp_mode()) res.a1 = read_sysreg_s(SYS_ICH_VTR_EL2); else diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c index 6588ea251ed7..c5c5644b1878 100644 --- a/arch/arm64/kvm/at.c +++ b/arch/arm64/kvm/at.c @@ -1504,8 +1504,6 @@ int __kvm_at_s1e2(struct kvm_vcpu *vcpu, u32 op, u64 vaddr) fail = true; } - isb(); - if (!fail) par = read_sysreg_par(); diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 1c87699fd886..332c453b87cf 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -29,7 +29,7 @@ #include "trace.h" -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS() }; @@ -42,7 +42,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, hvc_exit_stat), STATS_DESC_COUNTER(VCPU, wfe_exit_stat), diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 38f66a56a766..d815265bd374 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -518,7 +518,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range) granule = kvm_granule_size(level); cur.start = ALIGN_DOWN(addr, granule); cur.end = cur.start + granule; - if (!range_included(&cur, range)) + if (!range_included(&cur, range) && level < KVM_PGTABLE_LAST_LEVEL) continue; *range = cur; return 0; diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index ec2eee857208..17d64a1e11e5 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1751,6 +1751,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, force_pte = (max_map_size == PAGE_SIZE); vma_pagesize = min_t(long, vma_pagesize, max_map_size); + vma_shift = __ffs(vma_pagesize); } /* @@ -1837,10 +1838,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (exec_fault && s2_force_noncacheable) ret = -ENOEXEC; - if (ret) { - kvm_release_page_unused(page); - return ret; - } + if (ret) + goto out_put_page; /* * Guest performs atomic/exclusive operations on memory with unsupported @@ -1850,7 +1849,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, */ if (esr_fsc_is_excl_atomic_fault(kvm_vcpu_get_esr(vcpu))) { kvm_inject_dabt_excl_atomic(vcpu, kvm_vcpu_get_hfar(vcpu)); - return 1; + ret = 1; + goto out_put_page; } if (nested) @@ -1936,6 +1936,10 @@ out_unlock: mark_page_dirty_in_slot(kvm, memslot, gfn); return ret != -EAGAIN ? ret : 0; + +out_put_page: + kvm_release_page_unused(page); + return ret; } /* Resolve the access fault by making the page young again. */ diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 12c9f6e8dfda..2c43097248b2 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -152,31 +152,31 @@ static int get_ia_size(struct s2_walk_info *wi) return 64 - wi->t0sz; } -static int check_base_s2_limits(struct s2_walk_info *wi, +static int check_base_s2_limits(struct kvm_vcpu *vcpu, struct s2_walk_info *wi, int level, int input_size, int stride) { - int start_size, ia_size; + int start_size, pa_max; - ia_size = get_ia_size(wi); + pa_max = kvm_get_pa_bits(vcpu->kvm); /* Check translation limits */ switch (BIT(wi->pgshift)) { case SZ_64K: - if (level == 0 || (level == 1 && ia_size <= 42)) + if (level == 0 || (level == 1 && pa_max <= 42)) return -EFAULT; break; case SZ_16K: - if (level == 0 || (level == 1 && ia_size <= 40)) + if (level == 0 || (level == 1 && pa_max <= 40)) return -EFAULT; break; case SZ_4K: - if (level < 0 || (level == 0 && ia_size <= 42)) + if (level < 0 || (level == 0 && pa_max <= 42)) return -EFAULT; break; } /* Check input size limits */ - if (input_size > ia_size) + if (input_size > pa_max) return -EFAULT; /* Check number of entries in starting level table */ @@ -269,16 +269,19 @@ static int walk_nested_s2_pgd(struct kvm_vcpu *vcpu, phys_addr_t ipa, if (input_size > 48 || input_size < 25) return -EFAULT; - ret = check_base_s2_limits(wi, level, input_size, stride); - if (WARN_ON(ret)) + ret = check_base_s2_limits(vcpu, wi, level, input_size, stride); + if (WARN_ON(ret)) { + out->esr = compute_fsc(0, ESR_ELx_FSC_FAULT); return ret; + } base_lower_bound = 3 + input_size - ((3 - level) * stride + wi->pgshift); base_addr = wi->baddr & GENMASK_ULL(47, base_lower_bound); if (check_output_size(wi, base_addr)) { - out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ); + /* R_BFHQH */ + out->esr = compute_fsc(0, ESR_ELx_FSC_ADDRSZ); return 1; } @@ -293,8 +296,10 @@ static int walk_nested_s2_pgd(struct kvm_vcpu *vcpu, phys_addr_t ipa, paddr = base_addr | index; ret = read_guest_s2_desc(vcpu, paddr, &desc, wi); - if (ret < 0) + if (ret < 0) { + out->esr = ESR_ELx_FSC_SEA_TTW(level); return ret; + } new_desc = desc; diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 9b3091ad868c..e9b8b5fc480c 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -143,6 +143,21 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) kvm->arch.vgic.in_kernel = true; kvm->arch.vgic.vgic_model = type; kvm->arch.vgic.implementation_rev = KVM_VGIC_IMP_REV_LATEST; + kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; + + aa64pfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC; + pfr1 = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC; + + if (type == KVM_DEV_TYPE_ARM_VGIC_V2) { + kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; + } else { + INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); + aa64pfr0 |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP); + pfr1 |= SYS_FIELD_PREP_ENUM(ID_PFR1_EL1, GIC, GICv3); + } + + kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, aa64pfr0); + kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, pfr1); kvm_for_each_vcpu(i, vcpu, kvm) { ret = vgic_allocate_private_irqs_locked(vcpu, type); @@ -157,25 +172,10 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) vgic_cpu->private_irqs = NULL; } + kvm->arch.vgic.vgic_model = 0; goto out_unlock; } - kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; - - aa64pfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC; - pfr1 = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC; - - if (type == KVM_DEV_TYPE_ARM_VGIC_V2) { - kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; - } else { - INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); - aa64pfr0 |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP); - pfr1 |= SYS_FIELD_PREP_ENUM(ID_PFR1_EL1, GIC, GICv3); - } - - kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, aa64pfr0); - kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, pfr1); - if (type == KVM_DEV_TYPE_ARM_VGIC_V3) kvm->arch.vgic.nassgicap = system_supports_direct_sgis(); diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c index 585491fbda80..cafa3cb32bda 100644 --- a/arch/arm64/kvm/vgic/vgic-v2.c +++ b/arch/arm64/kvm/vgic/vgic-v2.c @@ -115,7 +115,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_v2_cpu_if *cpuif = &vgic_cpu->vgic_v2; u32 eoicount = FIELD_GET(GICH_HCR_EOICOUNT, cpuif->vgic_hcr); - struct vgic_irq *irq; + struct vgic_irq *irq = *host_data_ptr(last_lr_irq); DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); @@ -123,7 +123,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) vgic_v2_fold_lr(vcpu, cpuif->vgic_lr[lr]); /* See the GICv3 equivalent for the EOIcount handling rationale */ - list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { + list_for_each_entry_continue(irq, &vgic_cpu->ap_list_head, ap_list) { u32 lr; if (!eoicount) { diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 386ddf69a9c5..6a355eca1934 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -148,7 +148,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3; u32 eoicount = FIELD_GET(ICH_HCR_EL2_EOIcount, cpuif->vgic_hcr); - struct vgic_irq *irq; + struct vgic_irq *irq = *host_data_ptr(last_lr_irq); DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); @@ -158,12 +158,12 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) /* * EOIMode=0: use EOIcount to emulate deactivation. We are * guaranteed to deactivate in reverse order of the activation, so - * just pick one active interrupt after the other in the ap_list, - * and replay the deactivation as if the CPU was doing it. We also - * rely on priority drop to have taken place, and the list to be - * sorted by priority. + * just pick one active interrupt after the other in the tail part + * of the ap_list, past the LRs, and replay the deactivation as if + * the CPU was doing it. We also rely on priority drop to have taken + * place, and the list to be sorted by priority. */ - list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { + list_for_each_entry_continue(irq, &vgic_cpu->ap_list_head, ap_list) { u64 lr; /* diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index 430aa98888fd..e22b79cfff96 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -814,6 +814,9 @@ retry: static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu) { + if (!*host_data_ptr(last_lr_irq)) + return; + if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_fold_lr_state(vcpu); else @@ -960,10 +963,13 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu) if (irqs_outside_lrs(&als)) vgic_sort_ap_list(vcpu); + *host_data_ptr(last_lr_irq) = NULL; + list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { scoped_guard(raw_spinlock, &irq->irq_lock) { if (likely(vgic_target_oracle(irq) == vcpu)) { vgic_populate_lr(vcpu, irq, count++); + *host_data_ptr(last_lr_irq) = irq; } } diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index d211c6572b0a..92068ff38685 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -304,6 +304,9 @@ config AS_HAS_LBT_EXTENSION config AS_HAS_LVZ_EXTENSION def_bool $(as-instr,hvcl 0) +config AS_HAS_SCQ_EXTENSION + def_bool $(as-instr,sc.q \$t0$(comma)\$t1$(comma)\$t2) + config CC_HAS_ANNOTATE_TABLEJUMP def_bool $(cc-option,-mannotate-tablejump) diff --git a/arch/loongarch/include/asm/cmpxchg.h b/arch/loongarch/include/asm/cmpxchg.h index 58cabab6d90d..909f9274fe71 100644 --- a/arch/loongarch/include/asm/cmpxchg.h +++ b/arch/loongarch/include/asm/cmpxchg.h @@ -238,6 +238,8 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, unsigned int arch_cmpxchg((ptr), (o), (n)); \ }) +#ifdef CONFIG_AS_HAS_SCQ_EXTENSION + union __u128_halves { u128 full; struct { @@ -290,6 +292,9 @@ union __u128_halves { BUILD_BUG_ON(sizeof(*(ptr)) != 16); \ __arch_cmpxchg128(ptr, o, n, ""); \ }) + +#endif /* CONFIG_AS_HAS_SCQ_EXTENSION */ + #else #include <asm-generic/cmpxchg-local.h> #define arch_cmpxchg64_local(ptr, o, n) __generic_cmpxchg64_local((ptr), (o), (n)) diff --git a/arch/loongarch/include/asm/uaccess.h b/arch/loongarch/include/asm/uaccess.h index 4e259d490e45..438269313e78 100644 --- a/arch/loongarch/include/asm/uaccess.h +++ b/arch/loongarch/include/asm/uaccess.h @@ -253,8 +253,13 @@ do { \ \ __get_kernel_common(*((type *)(dst)), sizeof(type), \ (__force type *)(src)); \ - if (unlikely(__gu_err)) \ + if (unlikely(__gu_err)) { \ + pr_info("%s: memory access failed, ecode 0x%x\n", \ + __func__, read_csr_excode()); \ + pr_info("%s: the caller is %pS\n", \ + __func__, __builtin_return_address(0)); \ goto err_label; \ + } \ } while (0) #define __put_kernel_nofault(dst, src, type, err_label) \ @@ -264,8 +269,13 @@ do { \ \ __pu_val = *(__force type *)(src); \ __put_kernel_common(((type *)(dst)), sizeof(type)); \ - if (unlikely(__pu_err)) \ + if (unlikely(__pu_err)) { \ + pr_info("%s: memory access failed, ecode 0x%x\n", \ + __func__, read_csr_excode()); \ + pr_info("%s: the caller is %pS\n", \ + __func__, __builtin_return_address(0)); \ goto err_label; \ + } \ } while (0) extern unsigned long __copy_user(void *to, const void *from, __kernel_size_t n); diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c index bf037f0c6b26..1a728082944c 100644 --- a/arch/loongarch/kernel/inst.c +++ b/arch/loongarch/kernel/inst.c @@ -246,32 +246,51 @@ static int text_copy_cb(void *data) if (smp_processor_id() == copy->cpu) { ret = copy_to_kernel_nofault(copy->dst, copy->src, copy->len); - if (ret) + if (ret) { pr_err("%s: operation failed\n", __func__); + return ret; + } } flush_icache_range((unsigned long)copy->dst, (unsigned long)copy->dst + copy->len); - return ret; + return 0; } int larch_insn_text_copy(void *dst, void *src, size_t len) { int ret = 0; + int err = 0; size_t start, end; struct insn_copy copy = { .dst = dst, .src = src, .len = len, - .cpu = smp_processor_id(), + .cpu = raw_smp_processor_id(), }; + /* + * Ensure copy.cpu won't be hot removed before stop_machine. + * If it is removed nobody will really update the text. + */ + lockdep_assert_cpus_held(); + start = round_down((size_t)dst, PAGE_SIZE); end = round_up((size_t)dst + len, PAGE_SIZE); - set_memory_rw(start, (end - start) / PAGE_SIZE); - ret = stop_machine(text_copy_cb, ©, cpu_online_mask); - set_memory_rox(start, (end - start) / PAGE_SIZE); + err = set_memory_rw(start, (end - start) / PAGE_SIZE); + if (err) { + pr_info("%s: set_memory_rw() failed\n", __func__); + return err; + } + + ret = stop_machine_cpuslocked(text_copy_cb, ©, cpu_online_mask); + + err = set_memory_rox(start, (end - start) / PAGE_SIZE); + if (err) { + pr_info("%s: set_memory_rox() failed\n", __func__); + return err; + } return ret; } diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c index 09e137f2f841..8ffd50a470e6 100644 --- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -14,7 +14,7 @@ #define CREATE_TRACE_POINTS #include "trace.h" -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, int_exits), STATS_DESC_COUNTER(VCPU, idle_exits), diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c index 5282158b8122..8cc5ee1c53ef 100644 --- a/arch/loongarch/kvm/vm.c +++ b/arch/loongarch/kvm/vm.c @@ -10,7 +10,7 @@ #include <asm/kvm_eiointc.h> #include <asm/kvm_pch_pic.h> -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_ICOUNTER(VM, pages), STATS_DESC_ICOUNTER(VM, hugepages), @@ -49,8 +49,8 @@ static void kvm_vm_init_features(struct kvm *kvm) kvm->arch.kvm_features |= BIT(KVM_LOONGARCH_VM_FEAT_PMU); /* Enable all PV features by default */ - kvm->arch.pv_features = BIT(KVM_FEATURE_IPI); - kvm->arch.kvm_features = BIT(KVM_LOONGARCH_VM_FEAT_PV_IPI); + kvm->arch.pv_features |= BIT(KVM_FEATURE_IPI); + kvm->arch.kvm_features |= BIT(KVM_LOONGARCH_VM_FEAT_PV_IPI); if (kvm_pvtime_supported()) { kvm->arch.pv_features |= BIT(KVM_FEATURE_PREEMPT); kvm->arch.pv_features |= BIT(KVM_FEATURE_STEAL_TIME); diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index 3bd89f55960d..9cb796e16379 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -1379,9 +1379,11 @@ void *bpf_arch_text_copy(void *dst, void *src, size_t len) { int ret; + cpus_read_lock(); mutex_lock(&text_mutex); ret = larch_insn_text_copy(dst, src, len); mutex_unlock(&text_mutex); + cpus_read_unlock(); return ret ? ERR_PTR(-EINVAL) : dst; } @@ -1429,10 +1431,12 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t, if (ret) return ret; + cpus_read_lock(); mutex_lock(&text_mutex); if (memcmp(ip, new_insns, LOONGARCH_LONG_JUMP_NBYTES)) ret = larch_insn_text_copy(ip, new_insns, LOONGARCH_LONG_JUMP_NBYTES); mutex_unlock(&text_mutex); + cpus_read_unlock(); return ret; } @@ -1450,10 +1454,12 @@ int bpf_arch_text_invalidate(void *dst, size_t len) for (i = 0; i < (len / sizeof(u32)); i++) inst[i] = INSN_BREAK; + cpus_read_lock(); mutex_lock(&text_mutex); if (larch_insn_text_copy(dst, inst, len)) ret = -EINVAL; mutex_unlock(&text_mutex); + cpus_read_unlock(); kvfree(inst); @@ -1568,6 +1574,11 @@ void arch_free_bpf_trampoline(void *image, unsigned int size) bpf_prog_pack_free(image, size); } +int arch_protect_bpf_trampoline(void *image, unsigned int size) +{ + return 0; +} + /* * Sign-extend the register if necessary */ diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 29d9f630edfb..a53abbba43ea 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -38,7 +38,7 @@ #define VECTORSPACING 0x100 /* for EI/VI mode */ #endif -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS() }; @@ -51,7 +51,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, wait_exits), STATS_DESC_COUNTER(VCPU, cache_exits), diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 570b3d91e2e4..17e63244e885 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -15,6 +15,9 @@ #define TASK_SIZE_MAX TASK_SIZE_USER64 #endif +/* Threshold above which VMX copy path is used */ +#define VMX_COPY_THRESHOLD 3328 + #include <asm-generic/access_ok.h> /* @@ -326,40 +329,62 @@ do { \ extern unsigned long __copy_tofrom_user(void __user *to, const void __user *from, unsigned long size); -#ifdef __powerpc64__ -static inline unsigned long -raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) +unsigned long __copy_tofrom_user_base(void __user *to, + const void __user *from, unsigned long size); + +unsigned long __copy_tofrom_user_power7_vmx(void __user *to, + const void __user *from, unsigned long size); + +static __always_inline bool will_use_vmx(unsigned long n) +{ + return IS_ENABLED(CONFIG_ALTIVEC) && cpu_has_feature(CPU_FTR_VMX_COPY) && + n > VMX_COPY_THRESHOLD; +} + +static __always_inline unsigned long +raw_copy_tofrom_user(void __user *to, const void __user *from, + unsigned long n, unsigned long dir) { unsigned long ret; - barrier_nospec(); - allow_user_access(to, KUAP_READ_WRITE); + if (will_use_vmx(n) && enter_vmx_usercopy()) { + allow_user_access(to, dir); + ret = __copy_tofrom_user_power7_vmx(to, from, n); + prevent_user_access(dir); + exit_vmx_usercopy(); + + if (unlikely(ret)) { + allow_user_access(to, dir); + ret = __copy_tofrom_user_base(to, from, n); + prevent_user_access(dir); + } + return ret; + } + + allow_user_access(to, dir); ret = __copy_tofrom_user(to, from, n); - prevent_user_access(KUAP_READ_WRITE); + prevent_user_access(dir); return ret; } -#endif /* __powerpc64__ */ -static inline unsigned long raw_copy_from_user(void *to, - const void __user *from, unsigned long n) +#ifdef CONFIG_PPC64 +static inline unsigned long +raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) { - unsigned long ret; + barrier_nospec(); + return raw_copy_tofrom_user(to, from, n, KUAP_READ_WRITE); +} +#endif /* CONFIG_PPC64 */ - allow_user_access(NULL, KUAP_READ); - ret = __copy_tofrom_user((__force void __user *)to, from, n); - prevent_user_access(KUAP_READ); - return ret; +static inline unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n) +{ + return raw_copy_tofrom_user((__force void __user *)to, from, n, KUAP_READ); } static inline unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n) { - unsigned long ret; - - allow_user_access(to, KUAP_WRITE); - ret = __copy_tofrom_user(to, (__force const void __user *)from, n); - prevent_user_access(KUAP_WRITE); - return ret; + return raw_copy_tofrom_user(to, (__force const void __user *)from, n, KUAP_WRITE); } unsigned long __arch_clear_user(void __user *addr, unsigned long size); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 0ce71310b7d9..d122e8447831 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1159,7 +1159,7 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain, struct device *dev, struct iommu_domain *old) { - struct iommu_domain *domain = iommu_get_domain_for_dev(dev); + struct iommu_domain *domain = iommu_driver_get_domain_for_dev(dev); struct iommu_table_group *table_group; struct iommu_group *grp; diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index cb5b73adc250..b1761909c23f 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -35,7 +35,6 @@ #include <linux/of_irq.h> #include <linux/hugetlb.h> #include <linux/pgtable.h> -#include <asm/kexec.h> #include <asm/io.h> #include <asm/paca.h> #include <asm/processor.h> @@ -995,15 +994,6 @@ void __init setup_arch(char **cmdline_p) initmem_init(); - /* - * Reserve large chunks of memory for use by CMA for kdump, fadump, KVM and - * hugetlb. These must be called after initmem_init(), so that - * pageblock_order is initialised. - */ - fadump_cma_init(); - kdump_cma_reserve(); - kvm_cma_reserve(); - early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT); if (ppc_md.setup_arch) diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index d79c5d1098c0..2efbe05caed7 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -38,7 +38,7 @@ /* #define EXIT_DEBUG */ -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_ICOUNTER(VM, num_2M_pages), STATS_DESC_ICOUNTER(VM, num_1G_pages) @@ -53,7 +53,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, sum_exits), STATS_DESC_COUNTER(VCPU, mmio_exits), diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 3401b96be475..f3ddb24ece74 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -36,7 +36,7 @@ unsigned long kvmppc_booke_handlers; -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_ICOUNTER(VM, num_2M_pages), STATS_DESC_ICOUNTER(VM, num_1G_pages) @@ -51,7 +51,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, sum_exits), STATS_DESC_COUNTER(VCPU, mmio_exits), diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index f9acf866c709..e4469ad73a2e 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -39,15 +39,11 @@ enum vcpu_ftr { /* bits [6-5] MAS2_X1 and MAS2_X0 and [4-0] bits for WIMGE */ #define E500_TLB_MAS2_ATTR (0x7f) -struct tlbe_ref { +struct tlbe_priv { kvm_pfn_t pfn; /* valid only for TLB0, except briefly */ unsigned int flags; /* E500_TLB_* */ }; -struct tlbe_priv { - struct tlbe_ref ref; -}; - #ifdef CONFIG_KVM_E500V2 struct vcpu_id_table; #endif diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c index 48580c85f23b..75ed1496ead5 100644 --- a/arch/powerpc/kvm/e500_mmu.c +++ b/arch/powerpc/kvm/e500_mmu.c @@ -920,12 +920,12 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500) vcpu_e500->gtlb_offset[0] = 0; vcpu_e500->gtlb_offset[1] = KVM_E500_TLB0_SIZE; - vcpu_e500->gtlb_priv[0] = kzalloc_objs(struct tlbe_ref, + vcpu_e500->gtlb_priv[0] = kzalloc_objs(struct tlbe_priv, vcpu_e500->gtlb_params[0].entries); if (!vcpu_e500->gtlb_priv[0]) goto free_vcpu; - vcpu_e500->gtlb_priv[1] = kzalloc_objs(struct tlbe_ref, + vcpu_e500->gtlb_priv[1] = kzalloc_objs(struct tlbe_priv, vcpu_e500->gtlb_params[1].entries); if (!vcpu_e500->gtlb_priv[1]) goto free_vcpu; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 06caf8bbbe2b..37e0d3d9e244 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -189,16 +189,16 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, { struct kvm_book3e_206_tlb_entry *gtlbe = get_entry(vcpu_e500, tlbsel, esel); - struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref; + struct tlbe_priv *tlbe = &vcpu_e500->gtlb_priv[tlbsel][esel]; /* Don't bother with unmapped entries */ - if (!(ref->flags & E500_TLB_VALID)) { - WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0), - "%s: flags %x\n", __func__, ref->flags); + if (!(tlbe->flags & E500_TLB_VALID)) { + WARN(tlbe->flags & (E500_TLB_BITMAP | E500_TLB_TLB0), + "%s: flags %x\n", __func__, tlbe->flags); WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]); } - if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) { + if (tlbsel == 1 && tlbe->flags & E500_TLB_BITMAP) { u64 tmp = vcpu_e500->g2h_tlb1_map[esel]; int hw_tlb_indx; unsigned long flags; @@ -216,28 +216,28 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, } mb(); vcpu_e500->g2h_tlb1_map[esel] = 0; - ref->flags &= ~(E500_TLB_BITMAP | E500_TLB_VALID); + tlbe->flags &= ~(E500_TLB_BITMAP | E500_TLB_VALID); local_irq_restore(flags); } - if (tlbsel == 1 && ref->flags & E500_TLB_TLB0) { + if (tlbsel == 1 && tlbe->flags & E500_TLB_TLB0) { /* * TLB1 entry is backed by 4k pages. This should happen * rarely and is not worth optimizing. Invalidate everything. */ kvmppc_e500_tlbil_all(vcpu_e500); - ref->flags &= ~(E500_TLB_TLB0 | E500_TLB_VALID); + tlbe->flags &= ~(E500_TLB_TLB0 | E500_TLB_VALID); } /* * If TLB entry is still valid then it's a TLB0 entry, and thus * backed by at most one host tlbe per shadow pid */ - if (ref->flags & E500_TLB_VALID) + if (tlbe->flags & E500_TLB_VALID) kvmppc_e500_tlbil_one(vcpu_e500, gtlbe); /* Mark the TLB as not backed by the host anymore */ - ref->flags = 0; + tlbe->flags = 0; } static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) @@ -245,26 +245,26 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) return tlbe->mas7_3 & (MAS3_SW|MAS3_UW); } -static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, - struct kvm_book3e_206_tlb_entry *gtlbe, - kvm_pfn_t pfn, unsigned int wimg, - bool writable) +static inline void kvmppc_e500_tlbe_setup(struct tlbe_priv *tlbe, + struct kvm_book3e_206_tlb_entry *gtlbe, + kvm_pfn_t pfn, unsigned int wimg, + bool writable) { - ref->pfn = pfn; - ref->flags = E500_TLB_VALID; + tlbe->pfn = pfn; + tlbe->flags = E500_TLB_VALID; if (writable) - ref->flags |= E500_TLB_WRITABLE; + tlbe->flags |= E500_TLB_WRITABLE; /* Use guest supplied MAS2_G and MAS2_E */ - ref->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg; + tlbe->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg; } -static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref) +static inline void kvmppc_e500_tlbe_release(struct tlbe_priv *tlbe) { - if (ref->flags & E500_TLB_VALID) { + if (tlbe->flags & E500_TLB_VALID) { /* FIXME: don't log bogus pfn for TLB1 */ - trace_kvm_booke206_ref_release(ref->pfn, ref->flags); - ref->flags = 0; + trace_kvm_booke206_ref_release(tlbe->pfn, tlbe->flags); + tlbe->flags = 0; } } @@ -284,11 +284,8 @@ static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500) int i; for (tlbsel = 0; tlbsel <= 1; tlbsel++) { - for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) { - struct tlbe_ref *ref = - &vcpu_e500->gtlb_priv[tlbsel][i].ref; - kvmppc_e500_ref_release(ref); - } + for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) + kvmppc_e500_tlbe_release(&vcpu_e500->gtlb_priv[tlbsel][i]); } } @@ -304,18 +301,18 @@ void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu) static void kvmppc_e500_setup_stlbe( struct kvm_vcpu *vcpu, struct kvm_book3e_206_tlb_entry *gtlbe, - int tsize, struct tlbe_ref *ref, u64 gvaddr, + int tsize, struct tlbe_priv *tlbe, u64 gvaddr, struct kvm_book3e_206_tlb_entry *stlbe) { - kvm_pfn_t pfn = ref->pfn; + kvm_pfn_t pfn = tlbe->pfn; u32 pr = vcpu->arch.shared->msr & MSR_PR; - bool writable = !!(ref->flags & E500_TLB_WRITABLE); + bool writable = !!(tlbe->flags & E500_TLB_WRITABLE); - BUG_ON(!(ref->flags & E500_TLB_VALID)); + BUG_ON(!(tlbe->flags & E500_TLB_VALID)); /* Force IPROT=0 for all guest mappings. */ stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID; - stlbe->mas2 = (gvaddr & MAS2_EPN) | (ref->flags & E500_TLB_MAS2_ATTR); + stlbe->mas2 = (gvaddr & MAS2_EPN) | (tlbe->flags & E500_TLB_MAS2_ATTR); stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) | e500_shadow_mas3_attrib(gtlbe->mas7_3, writable, pr); } @@ -323,7 +320,7 @@ static void kvmppc_e500_setup_stlbe( static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe, int tlbsel, struct kvm_book3e_206_tlb_entry *stlbe, - struct tlbe_ref *ref) + struct tlbe_priv *tlbe) { struct kvm_memory_slot *slot; unsigned int psize; @@ -455,9 +452,9 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, } } - kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg, writable); + kvmppc_e500_tlbe_setup(tlbe, gtlbe, pfn, wimg, writable); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, - ref, gvaddr, stlbe); + tlbe, gvaddr, stlbe); writable = tlbe_is_writable(stlbe); /* Clear i-cache for new pages */ @@ -474,17 +471,17 @@ static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, int esel, struct kvm_book3e_206_tlb_entry *stlbe) { struct kvm_book3e_206_tlb_entry *gtlbe; - struct tlbe_ref *ref; + struct tlbe_priv *tlbe; int stlbsel = 0; int sesel = 0; int r; gtlbe = get_entry(vcpu_e500, 0, esel); - ref = &vcpu_e500->gtlb_priv[0][esel].ref; + tlbe = &vcpu_e500->gtlb_priv[0][esel]; r = kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe), get_tlb_raddr(gtlbe) >> PAGE_SHIFT, - gtlbe, 0, stlbe, ref); + gtlbe, 0, stlbe, tlbe); if (r) return r; @@ -494,7 +491,7 @@ static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, int esel, } static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500, - struct tlbe_ref *ref, + struct tlbe_priv *tlbe, int esel) { unsigned int sesel = vcpu_e500->host_tlb1_nv++; @@ -507,10 +504,10 @@ static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500, vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel); } - vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP; + vcpu_e500->gtlb_priv[1][esel].flags |= E500_TLB_BITMAP; vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel; vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1; - WARN_ON(!(ref->flags & E500_TLB_VALID)); + WARN_ON(!(tlbe->flags & E500_TLB_VALID)); return sesel; } @@ -522,24 +519,24 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe, struct kvm_book3e_206_tlb_entry *stlbe, int esel) { - struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref; + struct tlbe_priv *tlbe = &vcpu_e500->gtlb_priv[1][esel]; int sesel; int r; r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe, - ref); + tlbe); if (r) return r; /* Use TLB0 when we can only map a page with 4k */ if (get_tlb_tsize(stlbe) == BOOK3E_PAGESZ_4K) { - vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_TLB0; + vcpu_e500->gtlb_priv[1][esel].flags |= E500_TLB_TLB0; write_stlbe(vcpu_e500, gtlbe, stlbe, 0, 0); return 0; } /* Otherwise map into TLB1 */ - sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel); + sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, tlbe, esel); write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel); return 0; @@ -561,11 +558,11 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr, priv = &vcpu_e500->gtlb_priv[tlbsel][esel]; /* Triggers after clear_tlb_privs or on initial mapping */ - if (!(priv->ref.flags & E500_TLB_VALID)) { + if (!(priv->flags & E500_TLB_VALID)) { kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe); } else { kvmppc_e500_setup_stlbe(vcpu, gtlbe, BOOK3E_PAGESZ_4K, - &priv->ref, eaddr, &stlbe); + priv, eaddr, &stlbe); write_stlbe(vcpu_e500, gtlbe, &stlbe, 0, 0); } break; diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S index 9af969d2cc0c..25a99108caff 100644 --- a/arch/powerpc/lib/copyuser_64.S +++ b/arch/powerpc/lib/copyuser_64.S @@ -562,3 +562,4 @@ exc; std r10,32(3) li r5,4096 b .Ldst_aligned EXPORT_SYMBOL(__copy_tofrom_user) +EXPORT_SYMBOL(__copy_tofrom_user_base) diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index 8474c682a178..17dbcfbae25f 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -5,13 +5,9 @@ * * Author: Anton Blanchard <anton@au.ibm.com> */ +#include <linux/export.h> #include <asm/ppc_asm.h> -#ifndef SELFTEST_CASE -/* 0 == don't use VMX, 1 == use VMX */ -#define SELFTEST_CASE 0 -#endif - #ifdef __BIG_ENDIAN__ #define LVS(VRT,RA,RB) lvsl VRT,RA,RB #define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRA,VRB,VRC @@ -47,10 +43,14 @@ ld r15,STK_REG(R15)(r1) ld r14,STK_REG(R14)(r1) .Ldo_err3: - bl CFUNC(exit_vmx_usercopy) + ld r6,STK_REG(R31)(r1) /* original destination pointer */ + ld r5,STK_REG(R29)(r1) /* original number of bytes */ + subf r7,r6,r3 /* #bytes copied */ + subf r3,r7,r5 /* #bytes not copied in r3 */ ld r0,STACKFRAMESIZE+16(r1) mtlr r0 - b .Lexit + addi r1,r1,STACKFRAMESIZE + blr #endif /* CONFIG_ALTIVEC */ .Ldo_err2: @@ -74,7 +74,6 @@ _GLOBAL(__copy_tofrom_user_power7) cmpldi r5,16 - cmpldi cr1,r5,3328 std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) @@ -82,12 +81,6 @@ _GLOBAL(__copy_tofrom_user_power7) blt .Lshort_copy -#ifdef CONFIG_ALTIVEC -test_feature = SELFTEST_CASE -BEGIN_FTR_SECTION - bgt cr1,.Lvmx_copy -END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) -#endif .Lnonvmx_copy: /* Get the source 8B aligned */ @@ -263,23 +256,14 @@ err1; stb r0,0(r3) 15: li r3,0 blr -.Lunwind_stack_nonvmx_copy: - addi r1,r1,STACKFRAMESIZE - b .Lnonvmx_copy - -.Lvmx_copy: #ifdef CONFIG_ALTIVEC +_GLOBAL(__copy_tofrom_user_power7_vmx) mflr r0 std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) - bl CFUNC(enter_vmx_usercopy) - cmpwi cr1,r3,0 - ld r0,STACKFRAMESIZE+16(r1) - ld r3,STK_REG(R31)(r1) - ld r4,STK_REG(R30)(r1) - ld r5,STK_REG(R29)(r1) - mtlr r0 + std r3,STK_REG(R31)(r1) + std r5,STK_REG(R29)(r1) /* * We prefetch both the source and destination using enhanced touch * instructions. We use a stream ID of 0 for the load side and @@ -300,8 +284,6 @@ err1; stb r0,0(r3) DCBT_SETUP_STREAMS(r6, r7, r9, r10, r8) - beq cr1,.Lunwind_stack_nonvmx_copy - /* * If source and destination are not relatively aligned we use a * slower permute loop. @@ -478,7 +460,8 @@ err3; lbz r0,0(r4) err3; stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - b CFUNC(exit_vmx_usercopy) /* tail call optimise */ + li r3,0 + blr .Lvmx_unaligned_copy: /* Get the destination 16B aligned */ @@ -681,5 +664,7 @@ err3; lbz r0,0(r4) err3; stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - b CFUNC(exit_vmx_usercopy) /* tail call optimise */ + li r3,0 + blr +EXPORT_SYMBOL(__copy_tofrom_user_power7_vmx) #endif /* CONFIG_ALTIVEC */ diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c index 54340912398f..554b248002b4 100644 --- a/arch/powerpc/lib/vmx-helper.c +++ b/arch/powerpc/lib/vmx-helper.c @@ -27,6 +27,7 @@ int enter_vmx_usercopy(void) return 1; } +EXPORT_SYMBOL(enter_vmx_usercopy); /* * This function must return 0 because we tail call optimise when calling @@ -49,6 +50,7 @@ int exit_vmx_usercopy(void) set_dec(1); return 0; } +EXPORT_SYMBOL(exit_vmx_usercopy); int enter_vmx_ops(void) { diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index a985fc96b953..b7982d0243d4 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -30,6 +30,10 @@ #include <asm/setup.h> #include <asm/fixmap.h> +#include <asm/fadump.h> +#include <asm/kexec.h> +#include <asm/kvm_ppc.h> + #include <mm/mmu_decl.h> unsigned long long memory_limit __initdata; @@ -268,6 +272,16 @@ void __init paging_init(void) void __init arch_mm_preinit(void) { + + /* + * Reserve large chunks of memory for use by CMA for kdump, fadump, KVM + * and hugetlb. These must be called after pageblock_order is + * initialised. + */ + fadump_cma_init(); + kdump_cma_reserve(); + kvm_cma_reserve(); + /* * book3s is limited to 16 page sizes due to encoding this in * a 4-bit field for slices. diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c index 26aa26482c9a..992cc5c98214 100644 --- a/arch/powerpc/perf/callchain.c +++ b/arch/powerpc/perf/callchain.c @@ -103,6 +103,11 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + perf_callchain_store(entry, perf_arch_instruction_pointer(regs)); + + if (!current->mm) + return; + if (!is_32bit_task()) perf_callchain_user_64(entry, regs); else diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c index ddcc2d8aa64a..0de21c5d272c 100644 --- a/arch/powerpc/perf/callchain_32.c +++ b/arch/powerpc/perf/callchain_32.c @@ -142,7 +142,6 @@ void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry, next_ip = perf_arch_instruction_pointer(regs); lr = regs->link; sp = regs->gpr[1]; - perf_callchain_store(entry, next_ip); while (entry->nr < entry->max_stack) { fp = (unsigned int __user *) (unsigned long) sp; diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c index 115d1c105e8a..30fb61c5f0cb 100644 --- a/arch/powerpc/perf/callchain_64.c +++ b/arch/powerpc/perf/callchain_64.c @@ -77,7 +77,6 @@ void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry, next_ip = perf_arch_instruction_pointer(regs); lr = regs->link; sp = regs->gpr[1]; - perf_callchain_store(entry, next_ip); while (entry->nr < entry->max_stack) { fp = (unsigned long __user *) sp; diff --git a/arch/riscv/boot/dts/microchip/mpfs.dtsi b/arch/riscv/boot/dts/microchip/mpfs.dtsi index 5c2963e269b8..a0ffedc2d344 100644 --- a/arch/riscv/boot/dts/microchip/mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs.dtsi @@ -428,6 +428,7 @@ clocks = <&clkcfg CLK_CAN0>, <&clkcfg CLK_MSSPLL3>; interrupt-parent = <&plic>; interrupts = <56>; + resets = <&mss_top_sysreg CLK_CAN0>; status = "disabled"; }; @@ -437,6 +438,7 @@ clocks = <&clkcfg CLK_CAN1>, <&clkcfg CLK_MSSPLL3>; interrupt-parent = <&plic>; interrupts = <57>; + resets = <&mss_top_sysreg CLK_CAN1>; status = "disabled"; }; diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c index cac3c2b51d72..5ec503288555 100644 --- a/arch/riscv/kvm/aia.c +++ b/arch/riscv/kvm/aia.c @@ -13,6 +13,7 @@ #include <linux/irqchip/riscv-imsic.h> #include <linux/irqdomain.h> #include <linux/kvm_host.h> +#include <linux/nospec.h> #include <linux/percpu.h> #include <linux/spinlock.h> #include <asm/cpufeature.h> @@ -182,9 +183,14 @@ int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu, unsigned long *out_val) { struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long)) + if (!riscv_isa_extension_available(vcpu->arch.isa, SSAIA)) return -ENOENT; + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); *out_val = 0; if (kvm_riscv_aia_available()) @@ -198,9 +204,14 @@ int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu, unsigned long val) { struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long)) + if (!riscv_isa_extension_available(vcpu->arch.isa, SSAIA)) return -ENOENT; + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); if (kvm_riscv_aia_available()) { ((unsigned long *)csr)[reg_num] = val; diff --git a/arch/riscv/kvm/aia_aplic.c b/arch/riscv/kvm/aia_aplic.c index d1e50bf5c351..3464f3351df7 100644 --- a/arch/riscv/kvm/aia_aplic.c +++ b/arch/riscv/kvm/aia_aplic.c @@ -10,6 +10,7 @@ #include <linux/irqchip/riscv-aplic.h> #include <linux/kvm_host.h> #include <linux/math.h> +#include <linux/nospec.h> #include <linux/spinlock.h> #include <linux/swab.h> #include <kvm/iodev.h> @@ -45,7 +46,7 @@ static u32 aplic_read_sourcecfg(struct aplic *aplic, u32 irq) if (!irq || aplic->nr_irqs <= irq) return 0; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); ret = irqd->sourcecfg; @@ -61,7 +62,7 @@ static void aplic_write_sourcecfg(struct aplic *aplic, u32 irq, u32 val) if (!irq || aplic->nr_irqs <= irq) return; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; if (val & APLIC_SOURCECFG_D) val = 0; @@ -81,7 +82,7 @@ static u32 aplic_read_target(struct aplic *aplic, u32 irq) if (!irq || aplic->nr_irqs <= irq) return 0; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); ret = irqd->target; @@ -97,7 +98,7 @@ static void aplic_write_target(struct aplic *aplic, u32 irq, u32 val) if (!irq || aplic->nr_irqs <= irq) return; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; val &= APLIC_TARGET_EIID_MASK | (APLIC_TARGET_HART_IDX_MASK << APLIC_TARGET_HART_IDX_SHIFT) | @@ -116,7 +117,7 @@ static bool aplic_read_pending(struct aplic *aplic, u32 irq) if (!irq || aplic->nr_irqs <= irq) return false; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); ret = (irqd->state & APLIC_IRQ_STATE_PENDING) ? true : false; @@ -132,7 +133,7 @@ static void aplic_write_pending(struct aplic *aplic, u32 irq, bool pending) if (!irq || aplic->nr_irqs <= irq) return; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); @@ -170,7 +171,7 @@ static bool aplic_read_enabled(struct aplic *aplic, u32 irq) if (!irq || aplic->nr_irqs <= irq) return false; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); ret = (irqd->state & APLIC_IRQ_STATE_ENABLED) ? true : false; @@ -186,7 +187,7 @@ static void aplic_write_enabled(struct aplic *aplic, u32 irq, bool enabled) if (!irq || aplic->nr_irqs <= irq) return; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); if (enabled) @@ -205,7 +206,7 @@ static bool aplic_read_input(struct aplic *aplic, u32 irq) if (!irq || aplic->nr_irqs <= irq) return false; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); @@ -254,7 +255,7 @@ static void aplic_update_irq_range(struct kvm *kvm, u32 first, u32 last) for (irq = first; irq <= last; irq++) { if (!irq || aplic->nr_irqs <= irq) continue; - irqd = &aplic->irqs[irq]; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; raw_spin_lock_irqsave(&irqd->lock, flags); @@ -283,7 +284,7 @@ int kvm_riscv_aia_aplic_inject(struct kvm *kvm, u32 source, bool level) if (!aplic || !source || (aplic->nr_irqs <= source)) return -ENODEV; - irqd = &aplic->irqs[source]; + irqd = &aplic->irqs[array_index_nospec(source, aplic->nr_irqs)]; ie = (aplic->domaincfg & APLIC_DOMAINCFG_IE) ? true : false; raw_spin_lock_irqsave(&irqd->lock, flags); diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c index b195a93add1c..49c71d3cdb00 100644 --- a/arch/riscv/kvm/aia_device.c +++ b/arch/riscv/kvm/aia_device.c @@ -11,6 +11,7 @@ #include <linux/irqchip/riscv-imsic.h> #include <linux/kvm_host.h> #include <linux/uaccess.h> +#include <linux/cpufeature.h> static int aia_create(struct kvm_device *dev, u32 type) { @@ -22,6 +23,9 @@ static int aia_create(struct kvm_device *dev, u32 type) if (irqchip_in_kernel(kvm)) return -EEXIST; + if (!riscv_isa_extension_available(NULL, SSAIA)) + return -ENODEV; + ret = -EBUSY; if (kvm_trylock_all_vcpus(kvm)) return ret; @@ -437,7 +441,7 @@ static int aia_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) static int aia_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { - int nr_vcpus; + int nr_vcpus, r = -ENXIO; switch (attr->group) { case KVM_DEV_RISCV_AIA_GRP_CONFIG: @@ -466,12 +470,18 @@ static int aia_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) } break; case KVM_DEV_RISCV_AIA_GRP_APLIC: - return kvm_riscv_aia_aplic_has_attr(dev->kvm, attr->attr); + mutex_lock(&dev->kvm->lock); + r = kvm_riscv_aia_aplic_has_attr(dev->kvm, attr->attr); + mutex_unlock(&dev->kvm->lock); + break; case KVM_DEV_RISCV_AIA_GRP_IMSIC: - return kvm_riscv_aia_imsic_has_attr(dev->kvm, attr->attr); + mutex_lock(&dev->kvm->lock); + r = kvm_riscv_aia_imsic_has_attr(dev->kvm, attr->attr); + mutex_unlock(&dev->kvm->lock); + break; } - return -ENXIO; + return r; } struct kvm_device_ops kvm_riscv_aia_device_ops = { diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c index 06752fa24798..8786f52cf65a 100644 --- a/arch/riscv/kvm/aia_imsic.c +++ b/arch/riscv/kvm/aia_imsic.c @@ -908,6 +908,10 @@ int kvm_riscv_vcpu_aia_imsic_rmw(struct kvm_vcpu *vcpu, unsigned long isel, int r, rc = KVM_INSN_CONTINUE_NEXT_SEPC; struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + /* If IMSIC vCPU state not initialized then forward to user space */ + if (!imsic) + return KVM_INSN_EXIT_TO_USER_SPACE; + if (isel == KVM_RISCV_AIA_IMSIC_TOPEI) { /* Read pending and enabled interrupt with highest priority */ topei = imsic_mrif_topei(imsic->swfile, imsic->nr_eix, diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 0b75eb2a1820..088d33ba90ed 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -245,6 +245,7 @@ out: bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { struct kvm_gstage gstage; + bool mmu_locked; if (!kvm->arch.pgd) return false; @@ -253,9 +254,12 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) gstage.flags = 0; gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid); gstage.pgd = kvm->arch.pgd; + mmu_locked = spin_trylock(&kvm->mmu_lock); kvm_riscv_gstage_unmap_range(&gstage, range->start << PAGE_SHIFT, (range->end - range->start) << PAGE_SHIFT, range->may_block); + if (mmu_locked) + spin_unlock(&kvm->mmu_lock); return false; } @@ -535,7 +539,7 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, goto out_unlock; /* Check if we are backed by a THP and thus use block mapping if possible */ - if (vma_pagesize == PAGE_SIZE) + if (!logging && (vma_pagesize == PAGE_SIZE)) vma_pagesize = transparent_hugepage_adjust(kvm, memslot, hva, &hfn, &gpa); if (writable) { diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index a55a95da54d0..fdd99ac1e714 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -24,7 +24,7 @@ #define CREATE_TRACE_POINTS #include "trace.h" -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, ecall_exit_stat), STATS_DESC_COUNTER(VCPU, wfi_exit_stat), diff --git a/arch/riscv/kvm/vcpu_fp.c b/arch/riscv/kvm/vcpu_fp.c index 030904d82b58..bd5a9e7e7165 100644 --- a/arch/riscv/kvm/vcpu_fp.c +++ b/arch/riscv/kvm/vcpu_fp.c @@ -10,6 +10,7 @@ #include <linux/errno.h> #include <linux/err.h> #include <linux/kvm_host.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <asm/cpufeature.h> @@ -93,9 +94,11 @@ int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu, if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr)) reg_val = &cntx->fp.f.fcsr; else if ((KVM_REG_RISCV_FP_F_REG(f[0]) <= reg_num) && - reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) + reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) { + reg_num = array_index_nospec(reg_num, + ARRAY_SIZE(cntx->fp.f.f)); reg_val = &cntx->fp.f.f[reg_num]; - else + } else return -ENOENT; } else if ((rtype == KVM_REG_RISCV_FP_D) && riscv_isa_extension_available(vcpu->arch.isa, d)) { @@ -107,6 +110,8 @@ int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu, reg_num <= KVM_REG_RISCV_FP_D_REG(f[31])) { if (KVM_REG_SIZE(reg->id) != sizeof(u64)) return -EINVAL; + reg_num = array_index_nospec(reg_num, + ARRAY_SIZE(cntx->fp.d.f)); reg_val = &cntx->fp.d.f[reg_num]; } else return -ENOENT; @@ -138,9 +143,11 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu, if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr)) reg_val = &cntx->fp.f.fcsr; else if ((KVM_REG_RISCV_FP_F_REG(f[0]) <= reg_num) && - reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) + reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) { + reg_num = array_index_nospec(reg_num, + ARRAY_SIZE(cntx->fp.f.f)); reg_val = &cntx->fp.f.f[reg_num]; - else + } else return -ENOENT; } else if ((rtype == KVM_REG_RISCV_FP_D) && riscv_isa_extension_available(vcpu->arch.isa, d)) { @@ -152,6 +159,8 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu, reg_num <= KVM_REG_RISCV_FP_D_REG(f[31])) { if (KVM_REG_SIZE(reg->id) != sizeof(u64)) return -EINVAL; + reg_num = array_index_nospec(reg_num, + ARRAY_SIZE(cntx->fp.d.f)); reg_val = &cntx->fp.d.f[reg_num]; } else return -ENOENT; diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c index e7ab6cb00646..45ecc0082e90 100644 --- a/arch/riscv/kvm/vcpu_onereg.c +++ b/arch/riscv/kvm/vcpu_onereg.c @@ -10,6 +10,7 @@ #include <linux/bitops.h> #include <linux/errno.h> #include <linux/err.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <linux/kvm_host.h> #include <asm/cacheflush.h> @@ -127,6 +128,7 @@ static int kvm_riscv_vcpu_isa_check_host(unsigned long kvm_ext, unsigned long *g kvm_ext >= ARRAY_SIZE(kvm_isa_ext_arr)) return -ENOENT; + kvm_ext = array_index_nospec(kvm_ext, ARRAY_SIZE(kvm_isa_ext_arr)); *guest_ext = kvm_isa_ext_arr[kvm_ext]; switch (*guest_ext) { case RISCV_ISA_EXT_SMNPM: @@ -443,13 +445,16 @@ static int kvm_riscv_vcpu_get_reg_core(struct kvm_vcpu *vcpu, unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_RISCV_CORE); + unsigned long regs_max = sizeof(struct kvm_riscv_core) / sizeof(unsigned long); unsigned long reg_val; if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) return -EINVAL; - if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long)) + if (reg_num >= regs_max) return -ENOENT; + reg_num = array_index_nospec(reg_num, regs_max); + if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc)) reg_val = cntx->sepc; else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num && @@ -476,13 +481,16 @@ static int kvm_riscv_vcpu_set_reg_core(struct kvm_vcpu *vcpu, unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_RISCV_CORE); + unsigned long regs_max = sizeof(struct kvm_riscv_core) / sizeof(unsigned long); unsigned long reg_val; if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) return -EINVAL; - if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long)) + if (reg_num >= regs_max) return -ENOENT; + reg_num = array_index_nospec(reg_num, regs_max); + if (copy_from_user(®_val, uaddr, KVM_REG_SIZE(reg->id))) return -EFAULT; @@ -507,10 +515,13 @@ static int kvm_riscv_vcpu_general_get_csr(struct kvm_vcpu *vcpu, unsigned long *out_val) { struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long)) + if (reg_num >= regs_max) return -ENOENT; + reg_num = array_index_nospec(reg_num, regs_max); + if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) { kvm_riscv_vcpu_flush_interrupts(vcpu); *out_val = (csr->hvip >> VSIP_TO_HVIP_SHIFT) & VSIP_VALID_MASK; @@ -526,10 +537,13 @@ static int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu, unsigned long reg_val) { struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long)) + if (reg_num >= regs_max) return -ENOENT; + reg_num = array_index_nospec(reg_num, regs_max); + if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) { reg_val &= VSIP_VALID_MASK; reg_val <<= VSIP_TO_HVIP_SHIFT; @@ -548,10 +562,15 @@ static inline int kvm_riscv_vcpu_smstateen_set_csr(struct kvm_vcpu *vcpu, unsigned long reg_val) { struct kvm_vcpu_smstateen_csr *csr = &vcpu->arch.smstateen_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) / + sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_smstateen_csr) / - sizeof(unsigned long)) - return -EINVAL; + if (!riscv_isa_extension_available(vcpu->arch.isa, SMSTATEEN)) + return -ENOENT; + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); ((unsigned long *)csr)[reg_num] = reg_val; return 0; @@ -562,10 +581,15 @@ static int kvm_riscv_vcpu_smstateen_get_csr(struct kvm_vcpu *vcpu, unsigned long *out_val) { struct kvm_vcpu_smstateen_csr *csr = &vcpu->arch.smstateen_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) / + sizeof(unsigned long); - if (reg_num >= sizeof(struct kvm_riscv_smstateen_csr) / - sizeof(unsigned long)) - return -EINVAL; + if (!riscv_isa_extension_available(vcpu->arch.isa, SMSTATEEN)) + return -ENOENT; + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); *out_val = ((unsigned long *)csr)[reg_num]; return 0; @@ -595,10 +619,7 @@ static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu, rc = kvm_riscv_vcpu_aia_get_csr(vcpu, reg_num, ®_val); break; case KVM_REG_RISCV_CSR_SMSTATEEN: - rc = -EINVAL; - if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) - rc = kvm_riscv_vcpu_smstateen_get_csr(vcpu, reg_num, - ®_val); + rc = kvm_riscv_vcpu_smstateen_get_csr(vcpu, reg_num, ®_val); break; default: rc = -ENOENT; @@ -640,10 +661,7 @@ static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu, rc = kvm_riscv_vcpu_aia_set_csr(vcpu, reg_num, reg_val); break; case KVM_REG_RISCV_CSR_SMSTATEEN: - rc = -EINVAL; - if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) - rc = kvm_riscv_vcpu_smstateen_set_csr(vcpu, reg_num, - reg_val); + rc = kvm_riscv_vcpu_smstateen_set_csr(vcpu, reg_num, reg_val); break; default: rc = -ENOENT; diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c index 4d8d5e9aa53d..e873430e596b 100644 --- a/arch/riscv/kvm/vcpu_pmu.c +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -10,6 +10,7 @@ #include <linux/errno.h> #include <linux/err.h> #include <linux/kvm_host.h> +#include <linux/nospec.h> #include <linux/perf/riscv_pmu.h> #include <asm/csr.h> #include <asm/kvm_vcpu_sbi.h> @@ -87,7 +88,8 @@ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc) static u64 kvm_pmu_get_perf_event_hw_config(u32 sbi_event_code) { - return hw_event_perf_map[sbi_event_code]; + return hw_event_perf_map[array_index_nospec(sbi_event_code, + SBI_PMU_HW_GENERAL_MAX)]; } static u64 kvm_pmu_get_perf_event_cache_config(u32 sbi_event_code) @@ -218,6 +220,7 @@ static int pmu_fw_ctr_read_hi(struct kvm_vcpu *vcpu, unsigned long cidx, return -EINVAL; } + cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS); pmc = &kvpmu->pmc[cidx]; if (pmc->cinfo.type != SBI_PMU_CTR_TYPE_FW) @@ -244,6 +247,7 @@ static int pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, return -EINVAL; } + cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS); pmc = &kvpmu->pmc[cidx]; if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { @@ -520,11 +524,12 @@ int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx, { struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); - if (cidx > RISCV_KVM_MAX_COUNTERS || cidx == 1) { + if (cidx >= RISCV_KVM_MAX_COUNTERS || cidx == 1) { retdata->err_val = SBI_ERR_INVALID_PARAM; return 0; } + cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS); retdata->out_val = kvpmu->pmc[cidx].cinfo.value; return 0; @@ -559,7 +564,8 @@ int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base, } /* Start the counters that have been configured and requested by the guest */ for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) { - pmc_index = i + ctr_base; + pmc_index = array_index_nospec(i + ctr_base, + RISCV_KVM_MAX_COUNTERS); if (!test_bit(pmc_index, kvpmu->pmc_in_use)) continue; /* The guest started the counter again. Reset the overflow status */ @@ -630,7 +636,8 @@ int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base, /* Stop the counters that have been configured and requested by the guest */ for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) { - pmc_index = i + ctr_base; + pmc_index = array_index_nospec(i + ctr_base, + RISCV_KVM_MAX_COUNTERS); if (!test_bit(pmc_index, kvpmu->pmc_in_use)) continue; pmc = &kvpmu->pmc[pmc_index]; @@ -761,6 +768,7 @@ int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_ba } } + ctr_idx = array_index_nospec(ctr_idx, RISCV_KVM_MAX_COUNTERS); pmc = &kvpmu->pmc[ctr_idx]; pmc->idx = ctr_idx; diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index 58bce57dc55b..13c63ae1a78b 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -13,7 +13,7 @@ #include <linux/kvm_host.h> #include <asm/kvm_mmu.h> -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS() }; static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 7fdf960191d3..d10a17e6531d 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -147,10 +147,8 @@ void noinstr do_io_irq(struct pt_regs *regs) bool from_idle; from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT); - if (from_idle) { + if (from_idle) update_timer_idle(); - regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT); - } irq_enter_rcu(); @@ -176,6 +174,9 @@ void noinstr do_io_irq(struct pt_regs *regs) set_irq_regs(old_regs); irqentry_exit(regs, state); + + if (from_idle) + regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT); } void noinstr do_ext_irq(struct pt_regs *regs) @@ -185,10 +186,8 @@ void noinstr do_ext_irq(struct pt_regs *regs) bool from_idle; from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT); - if (from_idle) { + if (from_idle) update_timer_idle(); - regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT); - } irq_enter_rcu(); @@ -210,6 +209,9 @@ void noinstr do_ext_irq(struct pt_regs *regs) irq_exit_rcu(); set_irq_regs(old_regs); irqentry_exit(regs, state); + + if (from_idle) + regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT); } static void show_msi_interrupt(struct seq_file *p, int irq) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index bc7d6fa66eaf..3eb60aa932ec 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -65,7 +65,7 @@ #define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \ (KVM_MAX_VCPUS + LOCAL_IRQS)) -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_COUNTER(VM, inject_io), STATS_DESC_COUNTER(VM, inject_float_mchk), @@ -91,7 +91,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, exit_userspace), STATS_DESC_COUNTER(VCPU, exit_null), diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index ff07c45e3c73..6e4e3ef9b8c7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -2485,7 +2485,8 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS | \ KVM_X86_QUIRK_SLOT_ZAP_ALL | \ KVM_X86_QUIRK_STUFF_FEATURE_MSRS | \ - KVM_X86_QUIRK_IGNORE_GUEST_PAT) + KVM_X86_QUIRK_IGNORE_GUEST_PAT | \ + KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM) #define KVM_X86_CONDITIONAL_QUIRKS \ (KVM_X86_QUIRK_CD_NW_CLEARED | \ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 846a63215ce1..0d4538fa6c31 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -476,6 +476,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_SLOT_ZAP_ALL (1 << 7) #define KVM_X86_QUIRK_STUFF_FEATURE_MSRS (1 << 8) #define KVM_X86_QUIRK_IGNORE_GUEST_PAT (1 << 9) +#define KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM (1 << 10) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index d93f87f29d03..961714e6adae 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1894,6 +1894,7 @@ void __init check_x2apic(void) static inline void try_to_enable_x2apic(int remap_mode) { } static inline void __x2apic_enable(void) { } +static inline void __x2apic_disable(void) { } #endif /* !CONFIG_X86_X2APIC */ void __init enable_IR_x2apic(void) @@ -2456,6 +2457,11 @@ static void lapic_resume(void *data) if (x2apic_mode) { __x2apic_enable(); } else { + if (x2apic_enabled()) { + pr_warn_once("x2apic: re-enabled by firmware during resume. Disabling\n"); + __x2apic_disable(); + } + /* * Make sure the APICBASE points to the right address * diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index d2486506a808..8137927e7387 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -776,7 +776,10 @@ do { \ #define SYNTHESIZED_F(name) \ ({ \ kvm_cpu_cap_synthesized |= feature_bit(name); \ - F(name); \ + \ + BUILD_BUG_ON(X86_FEATURE_##name >= MAX_CPU_FEATURES); \ + if (boot_cpu_has(X86_FEATURE_##name)) \ + F(name); \ }) /* diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 30202942289a..9b140bbdc1d8 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1981,16 +1981,17 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu) if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY) goto out_flush_all; - if (is_noncanonical_invlpg_address(entries[i], vcpu)) - continue; - /* * Lower 12 bits of 'address' encode the number of additional * pages to flush. */ gva = entries[i] & PAGE_MASK; - for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++) + for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++) { + if (is_noncanonical_invlpg_address(gva + j * PAGE_SIZE, vcpu)) + continue; + kvm_x86_call(flush_tlb_gva)(vcpu, gva + j * PAGE_SIZE); + } ++vcpu->stat.tlb_flush; } diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index bb257793b6cb..eed96ff6e722 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -321,7 +321,8 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, idx = srcu_read_lock(&kvm->irq_srcu); gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin); if (gsi != -1) - hlist_for_each_entry_rcu(kimn, &ioapic->mask_notifier_list, link) + hlist_for_each_entry_srcu(kimn, &ioapic->mask_notifier_list, link, + srcu_read_lock_held(&kvm->irq_srcu)) if (kimn->irq == gsi) kimn->func(kimn, mask); srcu_read_unlock(&kvm->irq_srcu, idx); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index f92214b1a938..f7ec7914e3c4 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -189,12 +189,12 @@ static void avic_activate_vmcb(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu; vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK); - vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK; vmcb->control.avic_physical_id |= avic_get_max_physical_id(vcpu); - vmcb->control.int_ctl |= AVIC_ENABLE_MASK; + svm_clr_intercept(svm, INTERCEPT_CR8_WRITE); + /* * Note: KVM supports hybrid-AVIC mode, where KVM emulates x2APIC MSR * accesses, while interrupt injection to a running vCPU can be @@ -226,6 +226,9 @@ static void avic_deactivate_vmcb(struct vcpu_svm *svm) vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK); vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK; + if (!sev_es_guest(svm->vcpu.kvm)) + svm_set_intercept(svm, INTERCEPT_CR8_WRITE); + /* * If running nested and the guest uses its own MSR bitmap, there * is no need to update L0's msr bitmap @@ -368,7 +371,7 @@ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb) vmcb->control.avic_physical_id = __sme_set(__pa(kvm_svm->avic_physical_id_table)); vmcb->control.avic_vapic_bar = APIC_DEFAULT_PHYS_BASE; - if (kvm_apicv_activated(svm->vcpu.kvm)) + if (kvm_vcpu_apicv_active(&svm->vcpu)) avic_activate_vmcb(svm); else avic_deactivate_vmcb(svm); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 53ab6ce3cc26..b36c33255bed 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -418,6 +418,15 @@ static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu) return __nested_vmcb_check_controls(vcpu, ctl); } +int nested_svm_check_cached_vmcb12(struct kvm_vcpu *vcpu) +{ + if (!nested_vmcb_check_save(vcpu) || + !nested_vmcb_check_controls(vcpu)) + return -EINVAL; + + return 0; +} + /* * If a feature is not advertised to L1, clear the corresponding vmcb12 * intercept. @@ -1028,8 +1037,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); - if (!nested_vmcb_check_save(vcpu) || - !nested_vmcb_check_controls(vcpu)) { + if (nested_svm_check_cached_vmcb12(vcpu) < 0) { vmcb12->control.exit_code = SVM_EXIT_ERR; vmcb12->control.exit_info_1 = 0; vmcb12->control.exit_info_2 = 0; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 8f8bc863e214..e6477affac9a 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1077,8 +1077,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu, bool init_event) svm_set_intercept(svm, INTERCEPT_CR0_WRITE); svm_set_intercept(svm, INTERCEPT_CR3_WRITE); svm_set_intercept(svm, INTERCEPT_CR4_WRITE); - if (!kvm_vcpu_apicv_active(vcpu)) - svm_set_intercept(svm, INTERCEPT_CR8_WRITE); + svm_set_intercept(svm, INTERCEPT_CR8_WRITE); set_dr_intercepts(svm); @@ -1189,7 +1188,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu, bool init_event) if (guest_cpu_cap_has(vcpu, X86_FEATURE_ERAPS)) svm->vmcb->control.erap_ctl |= ERAP_CONTROL_ALLOW_LARGER_RAP; - if (kvm_vcpu_apicv_active(vcpu)) + if (enable_apicv && irqchip_in_kernel(vcpu->kvm)) avic_init_vmcb(svm, vmcb); if (vnmi) @@ -2674,9 +2673,11 @@ static int dr_interception(struct kvm_vcpu *vcpu) static int cr8_write_interception(struct kvm_vcpu *vcpu) { + u8 cr8_prev = kvm_get_cr8(vcpu); int r; - u8 cr8_prev = kvm_get_cr8(vcpu); + WARN_ON_ONCE(kvm_vcpu_apicv_active(vcpu)); + /* instruction emulation calls kvm_set_cr8() */ r = cr_interception(vcpu); if (lapic_in_kernel(vcpu)) @@ -4879,11 +4880,15 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) vmcb12 = map.hva; nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); - ret = enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa, vmcb12, false); - if (ret) + if (nested_svm_check_cached_vmcb12(vcpu) < 0) + goto unmap_save; + + if (enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa, + vmcb12, false) != 0) goto unmap_save; + ret = 0; svm->nested.nested_run_pending = 1; unmap_save: diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index ebd7b36b1ceb..6942e6b0eda6 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -797,6 +797,7 @@ static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code) int nested_svm_exit_handled(struct vcpu_svm *svm); int nested_svm_check_permissions(struct kvm_vcpu *vcpu); +int nested_svm_check_cached_vmcb12(struct kvm_vcpu *vcpu); int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); int nested_svm_exit_special(struct vcpu_svm *svm); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 248635da6766..937aeb474af7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3300,10 +3300,24 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, if (CC(vmcs12->guest_cr4 & X86_CR4_CET && !(vmcs12->guest_cr0 & X86_CR0_WP))) return -EINVAL; - if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) && - (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) || - CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false)))) - return -EINVAL; + if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) { + u64 debugctl = vmcs12->guest_ia32_debugctl; + + /* + * FREEZE_IN_SMM is not virtualized, but allow L1 to set it in + * vmcs12's DEBUGCTL under a quirk for backwards compatibility. + * Note that the quirk only relaxes the consistency check. The + * vmcc02 bit is still under the control of the host. In + * particular, if a host administrator decides to clear the bit, + * then L1 has no say in the matter. + */ + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM)) + debugctl &= ~DEBUGCTLMSR_FREEZE_IN_SMM; + + if (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) || + CC(!vmx_is_valid_debugctl(vcpu, debugctl, false))) + return -EINVAL; + } if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) && CC(!kvm_pat_valid(vmcs12->guest_ia32_pat))) @@ -6842,13 +6856,34 @@ void vmx_leave_nested(struct kvm_vcpu *vcpu) free_nested(vcpu); } +int nested_vmx_check_restored_vmcs12(struct kvm_vcpu *vcpu) +{ + enum vm_entry_failure_code ignored; + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + + if (nested_cpu_has_shadow_vmcs(vmcs12) && + vmcs12->vmcs_link_pointer != INVALID_GPA) { + struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu); + + if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION || + !shadow_vmcs12->hdr.shadow_vmcs) + return -EINVAL; + } + + if (nested_vmx_check_controls(vcpu, vmcs12) || + nested_vmx_check_host_state(vcpu, vmcs12) || + nested_vmx_check_guest_state(vcpu, vmcs12, &ignored)) + return -EINVAL; + + return 0; +} + static int vmx_set_nested_state(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, struct kvm_nested_state *kvm_state) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12; - enum vm_entry_failure_code ignored; struct kvm_vmx_nested_state_data __user *user_vmx_nested_state = &user_kvm_nested_state->data.vmx[0]; int ret; @@ -6979,25 +7014,20 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, vmx->nested.mtf_pending = !!(kvm_state->flags & KVM_STATE_NESTED_MTF_PENDING); - ret = -EINVAL; if (nested_cpu_has_shadow_vmcs(vmcs12) && vmcs12->vmcs_link_pointer != INVALID_GPA) { struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu); + ret = -EINVAL; if (kvm_state->size < sizeof(*kvm_state) + sizeof(user_vmx_nested_state->vmcs12) + sizeof(*shadow_vmcs12)) goto error_guest_mode; + ret = -EFAULT; if (copy_from_user(shadow_vmcs12, user_vmx_nested_state->shadow_vmcs12, - sizeof(*shadow_vmcs12))) { - ret = -EFAULT; - goto error_guest_mode; - } - - if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION || - !shadow_vmcs12->hdr.shadow_vmcs) + sizeof(*shadow_vmcs12))) goto error_guest_mode; } @@ -7008,9 +7038,8 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, kvm_state->hdr.vmx.preemption_timer_deadline; } - if (nested_vmx_check_controls(vcpu, vmcs12) || - nested_vmx_check_host_state(vcpu, vmcs12) || - nested_vmx_check_guest_state(vcpu, vmcs12, &ignored)) + ret = nested_vmx_check_restored_vmcs12(vcpu); + if (ret < 0) goto error_guest_mode; vmx->nested.dirty_vmcs12 = true; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index b844c5d59025..213a448104af 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -22,6 +22,7 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps); void nested_vmx_hardware_unsetup(void); __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); void nested_vmx_set_vmcs_shadowing_bitmap(void); +int nested_vmx_check_restored_vmcs12(struct kvm_vcpu *vcpu); void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu); enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 967b58a8ab9d..8b24e682535b 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1149,7 +1149,7 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, } vmx_add_auto_msr(&m->guest, msr, guest_val, VM_ENTRY_MSR_LOAD_COUNT, kvm); - vmx_add_auto_msr(&m->guest, msr, host_val, VM_EXIT_MSR_LOAD_COUNT, kvm); + vmx_add_auto_msr(&m->host, msr, host_val, VM_EXIT_MSR_LOAD_COUNT, kvm); } static bool update_transition_efer(struct vcpu_vmx *vmx) @@ -8528,9 +8528,13 @@ int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) } if (vmx->nested.smm.guest_mode) { + /* Triple fault if the state is invalid. */ + if (nested_vmx_check_restored_vmcs12(vcpu) < 0) + return 1; + ret = nested_vmx_enter_non_root_mode(vcpu, false); - if (ret) - return ret; + if (ret != NVMX_VMENTRY_SUCCESS) + return 1; vmx->nested.nested_run_pending = 1; vmx->nested.smm.guest_mode = false; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a03530795707..fd1c4a36b593 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -243,7 +243,7 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_ipiv); bool __read_mostly enable_device_posted_irqs = true; EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_device_posted_irqs); -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_COUNTER(VM, mmu_shadow_zapped), STATS_DESC_COUNTER(VM, mmu_pte_write), @@ -269,7 +269,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, pf_taken), STATS_DESC_COUNTER(VCPU, pf_fixed), diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c index afee5e667f77..c0d348884f74 100644 --- a/drivers/accel/amdxdna/aie2_ctx.c +++ b/drivers/accel/amdxdna/aie2_ctx.c @@ -165,7 +165,6 @@ aie2_sched_notify(struct amdxdna_sched_job *job) trace_xdna_job(&job->base, job->hwctx->name, "signaled fence", job->seq); - amdxdna_pm_suspend_put(job->hwctx->client->xdna); job->hwctx->priv->completed++; dma_fence_signal(fence); @@ -290,19 +289,11 @@ aie2_sched_job_run(struct drm_sched_job *sched_job) struct dma_fence *fence; int ret; - ret = amdxdna_pm_resume_get(hwctx->client->xdna); - if (ret) + if (!hwctx->priv->mbox_chann) return NULL; - if (!hwctx->priv->mbox_chann) { - amdxdna_pm_suspend_put(hwctx->client->xdna); - return NULL; - } - - if (!mmget_not_zero(job->mm)) { - amdxdna_pm_suspend_put(hwctx->client->xdna); + if (!mmget_not_zero(job->mm)) return ERR_PTR(-ESRCH); - } kref_get(&job->refcnt); fence = dma_fence_get(job->fence); @@ -333,7 +324,6 @@ aie2_sched_job_run(struct drm_sched_job *sched_job) out: if (ret) { - amdxdna_pm_suspend_put(hwctx->client->xdna); dma_fence_put(job->fence); aie2_job_put(job); mmput(job->mm); diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c index 666dfd7b2a80..838430903a3e 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.c +++ b/drivers/accel/amdxdna/amdxdna_ctx.c @@ -17,6 +17,7 @@ #include "amdxdna_ctx.h" #include "amdxdna_gem.h" #include "amdxdna_pci_drv.h" +#include "amdxdna_pm.h" #define MAX_HWCTX_ID 255 #define MAX_ARG_COUNT 4095 @@ -445,6 +446,7 @@ put_shmem_bo: void amdxdna_sched_job_cleanup(struct amdxdna_sched_job *job) { trace_amdxdna_debug_point(job->hwctx->name, job->seq, "job release"); + amdxdna_pm_suspend_put(job->hwctx->client->xdna); amdxdna_arg_bos_put(job); amdxdna_gem_put_obj(job->cmd_bo); dma_fence_put(job->fence); @@ -482,6 +484,12 @@ int amdxdna_cmd_submit(struct amdxdna_client *client, goto cmd_put; } + ret = amdxdna_pm_resume_get(xdna); + if (ret) { + XDNA_ERR(xdna, "Resume failed, ret %d", ret); + goto put_bos; + } + idx = srcu_read_lock(&client->hwctx_srcu); hwctx = xa_load(&client->hwctx_xa, hwctx_hdl); if (!hwctx) { @@ -522,6 +530,8 @@ put_fence: dma_fence_put(job->fence); unlock_srcu: srcu_read_unlock(&client->hwctx_srcu, idx); + amdxdna_pm_suspend_put(xdna); +put_bos: amdxdna_arg_bos_put(job); cmd_put: amdxdna_gem_put_obj(job->cmd_bo); diff --git a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h index 421242acb184..fc0ee8d637f9 100644 --- a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h +++ b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h @@ -121,12 +121,6 @@ #define VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY 0x0003006cu #define VPU_50XX_HOST_SS_AON_PWR_ISLAND_STATUS_DLY_STATUS_DLY_MASK GENMASK(7, 0) -#define VPU_40XX_HOST_SS_AON_RETENTION0 0x0003000cu -#define VPU_40XX_HOST_SS_AON_RETENTION1 0x00030010u -#define VPU_40XX_HOST_SS_AON_RETENTION2 0x00030014u -#define VPU_40XX_HOST_SS_AON_RETENTION3 0x00030018u -#define VPU_40XX_HOST_SS_AON_RETENTION4 0x0003001cu - #define VPU_40XX_HOST_SS_AON_IDLE_GEN 0x00030200u #define VPU_40XX_HOST_SS_AON_IDLE_GEN_EN_MASK BIT_MASK(0) #define VPU_40XX_HOST_SS_AON_IDLE_GEN_HW_PG_EN_MASK BIT_MASK(1) diff --git a/drivers/accel/ivpu/ivpu_hw_ip.c b/drivers/accel/ivpu/ivpu_hw_ip.c index 959984c54341..37f95a0551ed 100644 --- a/drivers/accel/ivpu/ivpu_hw_ip.c +++ b/drivers/accel/ivpu/ivpu_hw_ip.c @@ -931,7 +931,6 @@ static int soc_cpu_boot_40xx(struct ivpu_device *vdev) static int soc_cpu_boot_60xx(struct ivpu_device *vdev) { - REGV_WR64(VPU_40XX_HOST_SS_AON_RETENTION1, vdev->fw->mem_bp->vpu_addr); soc_cpu_set_entry_point_40xx(vdev, vdev->fw->cold_boot_entry_point); return 0; diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index df0ff0764d0d..6f4b545f7377 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -9,6 +9,7 @@ config ARCH_SUPPORTS_ACPI menuconfig ACPI bool "ACPI (Advanced Configuration and Power Interface) Support" depends on ARCH_SUPPORTS_ACPI + select AUXILIARY_BUS select PNP select NLS select CRC32 diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c index 64199b19ceff..a09636a4168e 100644 --- a/drivers/acpi/acpi_platform.c +++ b/drivers/acpi/acpi_platform.c @@ -135,7 +135,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev, } } - if (adev->device_type == ACPI_BUS_TYPE_DEVICE && !adev->pnp.type.backlight) { + if (adev->device_type == ACPI_BUS_TYPE_DEVICE) { LIST_HEAD(resource_list); count = acpi_dev_get_resources(adev, &resource_list, NULL, NULL); diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c index b34a48068a8d..b1652cab631a 100644 --- a/drivers/acpi/acpi_processor.c +++ b/drivers/acpi/acpi_processor.c @@ -113,6 +113,10 @@ static int acpi_processor_errata_piix4(struct pci_dev *dev) PCI_ANY_ID, PCI_ANY_ID, NULL); if (ide_dev) { errata.piix4.bmisx = pci_resource_start(ide_dev, 4); + if (errata.piix4.bmisx) + dev_dbg(&ide_dev->dev, + "Bus master activity detection (BM-IDE) erratum enabled\n"); + pci_dev_put(ide_dev); } @@ -131,20 +135,17 @@ static int acpi_processor_errata_piix4(struct pci_dev *dev) if (isa_dev) { pci_read_config_byte(isa_dev, 0x76, &value1); pci_read_config_byte(isa_dev, 0x77, &value2); - if ((value1 & 0x80) || (value2 & 0x80)) + if ((value1 & 0x80) || (value2 & 0x80)) { errata.piix4.fdma = 1; + dev_dbg(&isa_dev->dev, + "Type-F DMA livelock erratum (C3 disabled)\n"); + } pci_dev_put(isa_dev); } break; } - if (ide_dev) - dev_dbg(&ide_dev->dev, "Bus master activity detection (BM-IDE) erratum enabled\n"); - - if (isa_dev) - dev_dbg(&isa_dev->dev, "Type-F DMA livelock erratum (C3 disabled)\n"); - return 0; } diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index 3fa28f1abca3..adbaf0226c90 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -9,6 +9,7 @@ #define pr_fmt(fmt) "ACPI: video: " fmt +#include <linux/auxiliary_bus.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> @@ -21,7 +22,6 @@ #include <linux/sort.h> #include <linux/pci.h> #include <linux/pci_ids.h> -#include <linux/platform_device.h> #include <linux/slab.h> #include <linux/dmi.h> #include <linux/suspend.h> @@ -77,8 +77,9 @@ static int register_count; static DEFINE_MUTEX(register_count_mutex); static DEFINE_MUTEX(video_list_lock); static LIST_HEAD(video_bus_head); -static int acpi_video_bus_probe(struct platform_device *pdev); -static void acpi_video_bus_remove(struct platform_device *pdev); +static int acpi_video_bus_probe(struct auxiliary_device *aux_dev, + const struct auxiliary_device_id *id); +static void acpi_video_bus_remove(struct auxiliary_device *aux); static void acpi_video_bus_notify(acpi_handle handle, u32 event, void *data); /* @@ -93,19 +94,16 @@ enum acpi_video_level_idx { ACPI_VIDEO_FIRST_LEVEL, /* actual supported levels begin here */ }; -static const struct acpi_device_id video_device_ids[] = { - {ACPI_VIDEO_HID, 0}, - {"", 0}, +static const struct auxiliary_device_id video_bus_auxiliary_id_table[] = { + { .name = "acpi.video_bus" }, + {}, }; -MODULE_DEVICE_TABLE(acpi, video_device_ids); +MODULE_DEVICE_TABLE(auxiliary, video_bus_auxiliary_id_table); -static struct platform_driver acpi_video_bus = { +static struct auxiliary_driver acpi_video_bus = { .probe = acpi_video_bus_probe, .remove = acpi_video_bus_remove, - .driver = { - .name = "acpi-video", - .acpi_match_table = video_device_ids, - }, + .id_table = video_bus_auxiliary_id_table, }; struct acpi_video_bus_flags { @@ -1885,7 +1883,7 @@ static void acpi_video_dev_add_notify_handler(struct acpi_video_device *device) } static int acpi_video_bus_add_notify_handler(struct acpi_video_bus *video, - struct platform_device *pdev) + struct device *parent) { struct input_dev *input; struct acpi_video_device *dev; @@ -1908,7 +1906,7 @@ static int acpi_video_bus_add_notify_handler(struct acpi_video_bus *video, input->phys = video->phys; input->id.bustype = BUS_HOST; input->id.product = 0x06; - input->dev.parent = &pdev->dev; + input->dev.parent = parent; input->evbit[0] = BIT(EV_KEY); set_bit(KEY_SWITCHVIDEOMODE, input->keybit); set_bit(KEY_VIDEO_NEXT, input->keybit); @@ -1980,9 +1978,10 @@ static int acpi_video_bus_put_devices(struct acpi_video_bus *video) static int instance; -static int acpi_video_bus_probe(struct platform_device *pdev) +static int acpi_video_bus_probe(struct auxiliary_device *aux_dev, + const struct auxiliary_device_id *id_unused) { - struct acpi_device *device = ACPI_COMPANION(&pdev->dev); + struct acpi_device *device = ACPI_COMPANION(&aux_dev->dev); struct acpi_video_bus *video; bool auto_detect; int error; @@ -2019,7 +2018,7 @@ static int acpi_video_bus_probe(struct platform_device *pdev) instance++; } - platform_set_drvdata(pdev, video); + auxiliary_set_drvdata(aux_dev, video); video->device = device; strscpy(acpi_device_name(device), ACPI_VIDEO_BUS_NAME); @@ -2068,7 +2067,7 @@ static int acpi_video_bus_probe(struct platform_device *pdev) !auto_detect) acpi_video_bus_register_backlight(video); - error = acpi_video_bus_add_notify_handler(video, pdev); + error = acpi_video_bus_add_notify_handler(video, &aux_dev->dev); if (error) goto err_del; @@ -2096,10 +2095,10 @@ err_free_video: return error; } -static void acpi_video_bus_remove(struct platform_device *pdev) +static void acpi_video_bus_remove(struct auxiliary_device *aux_dev) { - struct acpi_video_bus *video = platform_get_drvdata(pdev); - struct acpi_device *device = ACPI_COMPANION(&pdev->dev); + struct acpi_video_bus *video = auxiliary_get_drvdata(aux_dev); + struct acpi_device *device = ACPI_COMPANION(&aux_dev->dev); acpi_dev_remove_notify_handler(device, ACPI_DEVICE_NOTIFY, acpi_video_bus_notify); @@ -2163,7 +2162,7 @@ int acpi_video_register(void) dmi_check_system(video_dmi_table); - ret = platform_driver_register(&acpi_video_bus); + ret = auxiliary_driver_register(&acpi_video_bus); if (ret) goto leave; @@ -2183,7 +2182,7 @@ void acpi_video_unregister(void) { mutex_lock(®ister_count_mutex); if (register_count) { - platform_driver_unregister(&acpi_video_bus); + auxiliary_driver_unregister(&acpi_video_bus); register_count = 0; may_report_brightness_keys = false; } diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h index 6c9b5bf7d392..07d5790d09f8 100644 --- a/drivers/acpi/acpica/acpredef.h +++ b/drivers/acpi/acpica/acpredef.h @@ -451,7 +451,7 @@ const union acpi_predefined_info acpi_gbl_predefined_methods[] = { {{"_DSM", METHOD_4ARGS(ACPI_TYPE_BUFFER, ACPI_TYPE_INTEGER, ACPI_TYPE_INTEGER, - ACPI_TYPE_ANY | ACPI_TYPE_PACKAGE) | + ACPI_TYPE_PACKAGE | ACPI_TYPE_ANY) | ARG_COUNT_IS_MINIMUM, METHOD_RETURNS(ACPI_RTYPE_ALL)}}, /* Must return a value, but it can be of any type */ diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index f6707325f582..2ec095e2009e 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -818,9 +818,6 @@ const struct acpi_device *acpi_companion_match(const struct device *dev) if (list_empty(&adev->pnp.ids)) return NULL; - if (adev->pnp.type.backlight) - return adev; - return acpi_primary_dev_companion(adev, dev); } diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 5b777316b9ac..62b9c83d4f20 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -1681,7 +1681,7 @@ acpi_status __init acpi_os_initialize(void) * Use acpi_os_map_generic_address to pre-map the reset * register if it's in system memory. */ - void *rv; + void __iomem *rv; rv = acpi_os_map_generic_address(&acpi_gbl_FADT.reset_register); pr_debug("%s: Reset register mapping %s\n", __func__, diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index dfdd004fb1a9..e8cdbdb46fdb 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -6,6 +6,7 @@ #define pr_fmt(fmt) "ACPI: " fmt #include <linux/async.h> +#include <linux/auxiliary_bus.h> #include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> @@ -2192,6 +2193,44 @@ static acpi_status acpi_bus_check_add_2(acpi_handle handle, u32 lvl_not_used, return acpi_bus_check_add(handle, false, (struct acpi_device **)ret_p); } +static void acpi_video_bus_device_release(struct device *dev) +{ + struct auxiliary_device *aux_dev = to_auxiliary_dev(dev); + + kfree(aux_dev); +} + +static void acpi_create_video_bus_device(struct acpi_device *adev, + struct acpi_device *parent) +{ + struct auxiliary_device *aux_dev; + static unsigned int aux_dev_id; + + aux_dev = kzalloc_obj(*aux_dev); + if (!aux_dev) + return; + + aux_dev->id = aux_dev_id++; + aux_dev->name = "video_bus"; + aux_dev->dev.parent = acpi_get_first_physical_node(parent); + if (!aux_dev->dev.parent) + goto err; + + aux_dev->dev.release = acpi_video_bus_device_release; + + if (auxiliary_device_init(aux_dev)) + goto err; + + ACPI_COMPANION_SET(&aux_dev->dev, adev); + if (__auxiliary_device_add(aux_dev, "acpi")) + auxiliary_device_uninit(aux_dev); + + return; + +err: + kfree(aux_dev); +} + struct acpi_scan_system_dev { struct list_head node; struct acpi_device *adev; @@ -2229,6 +2268,12 @@ static void acpi_default_enumeration(struct acpi_device *device) sd->adev = device; list_add_tail(&sd->node, &acpi_scan_system_dev_list); } + } else if (device->pnp.type.backlight) { + struct acpi_device *parent; + + parent = acpi_dev_parent(device); + if (parent) + acpi_create_video_bus_device(device, parent); } else { /* For a regular device object, create a platform device. */ acpi_create_platform_device(device, NULL); diff --git a/drivers/android/binder/page_range.rs b/drivers/android/binder/page_range.rs index fdd97112ef5c..9dfc154e5dd4 100644 --- a/drivers/android/binder/page_range.rs +++ b/drivers/android/binder/page_range.rs @@ -142,6 +142,30 @@ pub(crate) struct ShrinkablePageRange { _pin: PhantomPinned, } +// We do not define any ops. For now, used only to check identity of vmas. +static BINDER_VM_OPS: bindings::vm_operations_struct = pin_init::zeroed(); + +// To ensure that we do not accidentally install pages into or zap pages from the wrong vma, we +// check its vm_ops and private data before using it. +fn check_vma(vma: &virt::VmaRef, owner: *const ShrinkablePageRange) -> Option<&virt::VmaMixedMap> { + // SAFETY: Just reading the vm_ops pointer of any active vma is safe. + let vm_ops = unsafe { (*vma.as_ptr()).vm_ops }; + if !ptr::eq(vm_ops, &BINDER_VM_OPS) { + return None; + } + + // SAFETY: Reading the vm_private_data pointer of a binder-owned vma is safe. + let vm_private_data = unsafe { (*vma.as_ptr()).vm_private_data }; + // The ShrinkablePageRange is only dropped when the Process is dropped, which only happens once + // the file's ->release handler is invoked, which means the ShrinkablePageRange outlives any + // VMA associated with it, so there can't be any false positives due to pointer reuse here. + if !ptr::eq(vm_private_data, owner.cast()) { + return None; + } + + vma.as_mixedmap_vma() +} + struct Inner { /// Array of pages. /// @@ -308,6 +332,18 @@ impl ShrinkablePageRange { inner.size = num_pages; inner.vma_addr = vma.start(); + // This pointer is only used for comparison - it's not dereferenced. + // + // SAFETY: We own the vma, and we don't use any methods on VmaNew that rely on + // `vm_private_data`. + unsafe { + (*vma.as_ptr()).vm_private_data = ptr::from_ref(self).cast_mut().cast::<c_void>() + }; + + // SAFETY: We own the vma, and we don't use any methods on VmaNew that rely on + // `vm_ops`. + unsafe { (*vma.as_ptr()).vm_ops = &BINDER_VM_OPS }; + Ok(num_pages) } @@ -399,22 +435,25 @@ impl ShrinkablePageRange { // // Using `mmput_async` avoids this, because then the `mm` cleanup is instead queued to a // workqueue. - MmWithUser::into_mmput_async(self.mm.mmget_not_zero().ok_or(ESRCH)?) - .mmap_read_lock() - .vma_lookup(vma_addr) - .ok_or(ESRCH)? - .as_mixedmap_vma() - .ok_or(ESRCH)? - .vm_insert_page(user_page_addr, &new_page) - .inspect_err(|err| { - pr_warn!( - "Failed to vm_insert_page({}): vma_addr:{} i:{} err:{:?}", - user_page_addr, - vma_addr, - i, - err - ) - })?; + let mm = MmWithUser::into_mmput_async(self.mm.mmget_not_zero().ok_or(ESRCH)?); + { + let vma_read; + let mmap_read; + let vma = if let Some(ret) = mm.lock_vma_under_rcu(vma_addr) { + vma_read = ret; + check_vma(&vma_read, self) + } else { + mmap_read = mm.mmap_read_lock(); + mmap_read + .vma_lookup(vma_addr) + .and_then(|vma| check_vma(vma, self)) + }; + + match vma { + Some(vma) => vma.vm_insert_page(user_page_addr, &new_page)?, + None => return Err(ESRCH), + } + } let inner = self.lock.lock(); @@ -667,12 +706,15 @@ unsafe extern "C" fn rust_shrink_free_page( let mmap_read; let mm_mutex; let vma_addr; + let range_ptr; { // CAST: The `list_head` field is first in `PageInfo`. let info = item as *mut PageInfo; // SAFETY: The `range` field of `PageInfo` is immutable. - let range = unsafe { &*((*info).range) }; + range_ptr = unsafe { (*info).range }; + // SAFETY: The `range` outlives its `PageInfo` values. + let range = unsafe { &*range_ptr }; mm = match range.mm.mmget_not_zero() { Some(mm) => MmWithUser::into_mmput_async(mm), @@ -717,9 +759,11 @@ unsafe extern "C" fn rust_shrink_free_page( // SAFETY: The lru lock is locked when this method is called. unsafe { bindings::spin_unlock(&raw mut (*lru).lock) }; - if let Some(vma) = mmap_read.vma_lookup(vma_addr) { - let user_page_addr = vma_addr + (page_index << PAGE_SHIFT); - vma.zap_page_range_single(user_page_addr, PAGE_SIZE); + if let Some(unchecked_vma) = mmap_read.vma_lookup(vma_addr) { + if let Some(vma) = check_vma(unchecked_vma, range_ptr) { + let user_page_addr = vma_addr + (page_index << PAGE_SHIFT); + vma.zap_page_range_single(user_page_addr, PAGE_SIZE); + } } drop(mmap_read); diff --git a/drivers/android/binder/process.rs b/drivers/android/binder/process.rs index 41de5593197c..f06498129aa9 100644 --- a/drivers/android/binder/process.rs +++ b/drivers/android/binder/process.rs @@ -1295,7 +1295,8 @@ impl Process { } pub(crate) fn dead_binder_done(&self, cookie: u64, thread: &Thread) { - if let Some(death) = self.inner.lock().pull_delivered_death(cookie) { + let death = self.inner.lock().pull_delivered_death(cookie); + if let Some(death) = death { death.set_notification_done(thread); } } diff --git a/drivers/android/binder/range_alloc/array.rs b/drivers/android/binder/range_alloc/array.rs index 07e1dec2ce63..ada1d1b4302e 100644 --- a/drivers/android/binder/range_alloc/array.rs +++ b/drivers/android/binder/range_alloc/array.rs @@ -118,7 +118,7 @@ impl<T> ArrayRangeAllocator<T> { size: usize, is_oneway: bool, pid: Pid, - ) -> Result<usize> { + ) -> Result<(usize, bool)> { // Compute new value of free_oneway_space, which is set only on success. let new_oneway_space = if is_oneway { match self.free_oneway_space.checked_sub(size) { @@ -146,7 +146,38 @@ impl<T> ArrayRangeAllocator<T> { .ok() .unwrap(); - Ok(insert_at_offset) + // Start detecting spammers once we have less than 20% + // of async space left (which is less than 10% of total + // buffer size). + // + // (This will short-circuit, so `low_oneway_space` is + // only called when necessary.) + let oneway_spam_detected = + is_oneway && new_oneway_space < self.size / 10 && self.low_oneway_space(pid); + + Ok((insert_at_offset, oneway_spam_detected)) + } + + /// Find the amount and size of buffers allocated by the current caller. + /// + /// The idea is that once we cross the threshold, whoever is responsible + /// for the low async space is likely to try to send another async transaction, + /// and at some point we'll catch them in the act. This is more efficient + /// than keeping a map per pid. + fn low_oneway_space(&self, calling_pid: Pid) -> bool { + let mut total_alloc_size = 0; + let mut num_buffers = 0; + + // Warn if this pid has more than 50 transactions, or more than 50% of + // async space (which is 25% of total buffer size). Oneway spam is only + // detected when the threshold is exceeded. + for range in &self.ranges { + if range.state.is_oneway() && range.state.pid() == calling_pid { + total_alloc_size += range.size; + num_buffers += 1; + } + } + num_buffers > 50 || total_alloc_size > self.size / 4 } pub(crate) fn reservation_abort(&mut self, offset: usize) -> Result<FreedRange> { diff --git a/drivers/android/binder/range_alloc/mod.rs b/drivers/android/binder/range_alloc/mod.rs index 2301e2bc1a1f..1f4734468ff1 100644 --- a/drivers/android/binder/range_alloc/mod.rs +++ b/drivers/android/binder/range_alloc/mod.rs @@ -188,11 +188,11 @@ impl<T> RangeAllocator<T> { self.reserve_new(args) } Impl::Array(array) => { - let offset = + let (offset, oneway_spam_detected) = array.reserve_new(args.debug_id, args.size, args.is_oneway, args.pid)?; Ok(ReserveNew::Success(ReserveNewSuccess { offset, - oneway_spam_detected: false, + oneway_spam_detected, _empty_array_alloc: args.empty_array_alloc, _new_tree_alloc: args.new_tree_alloc, _tree_alloc: args.tree_alloc, diff --git a/drivers/android/binder/range_alloc/tree.rs b/drivers/android/binder/range_alloc/tree.rs index 838fdd2b47ea..48796fcdb362 100644 --- a/drivers/android/binder/range_alloc/tree.rs +++ b/drivers/android/binder/range_alloc/tree.rs @@ -164,15 +164,6 @@ impl<T> TreeRangeAllocator<T> { self.free_oneway_space }; - // Start detecting spammers once we have less than 20% - // of async space left (which is less than 10% of total - // buffer size). - // - // (This will short-circut, so `low_oneway_space` is - // only called when necessary.) - let oneway_spam_detected = - is_oneway && new_oneway_space < self.size / 10 && self.low_oneway_space(pid); - let (found_size, found_off, tree_node, free_tree_node) = match self.find_best_match(size) { None => { pr_warn!("ENOSPC from range_alloc.reserve_new - size: {}", size); @@ -203,6 +194,15 @@ impl<T> TreeRangeAllocator<T> { self.free_tree.insert(free_tree_node); } + // Start detecting spammers once we have less than 20% + // of async space left (which is less than 10% of total + // buffer size). + // + // (This will short-circuit, so `low_oneway_space` is + // only called when necessary.) + let oneway_spam_detected = + is_oneway && new_oneway_space < self.size / 10 && self.low_oneway_space(pid); + Ok((found_off, oneway_spam_detected)) } diff --git a/drivers/android/binder/thread.rs b/drivers/android/binder/thread.rs index 0b62d24b2118..c004214b1662 100644 --- a/drivers/android/binder/thread.rs +++ b/drivers/android/binder/thread.rs @@ -1015,12 +1015,9 @@ impl Thread { // Copy offsets if there are any. if offsets_size > 0 { - { - let mut reader = - UserSlice::new(UserPtr::from_addr(trd_data_ptr.offsets as _), offsets_size) - .reader(); - alloc.copy_into(&mut reader, aligned_data_size, offsets_size)?; - } + let mut offsets_reader = + UserSlice::new(UserPtr::from_addr(trd_data_ptr.offsets as _), offsets_size) + .reader(); let offsets_start = aligned_data_size; let offsets_end = aligned_data_size + offsets_size; @@ -1041,11 +1038,9 @@ impl Thread { .step_by(size_of::<u64>()) .enumerate() { - let offset: usize = view - .alloc - .read::<u64>(index_offset)? - .try_into() - .map_err(|_| EINVAL)?; + let offset = offsets_reader.read::<u64>()?; + view.alloc.write(index_offset, &offset)?; + let offset: usize = offset.try_into().map_err(|_| EINVAL)?; if offset < end_of_previous_object || !is_aligned(offset, size_of::<u32>()) { pr_warn!("Got transaction with invalid offset."); diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 0ee8ea971aa4..335288e8b5b3 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -1895,6 +1895,7 @@ void pm_runtime_reinit(struct device *dev) void pm_runtime_remove(struct device *dev) { __pm_runtime_disable(dev, false); + flush_work(&dev->power.work); pm_runtime_reinit(dev); } diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 004f367243b6..63aeb7a76a8c 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -4443,7 +4443,9 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, /* Skip partition scan if disabled by user */ if (ub->dev_info.flags & UBLK_F_NO_AUTO_PART_SCAN) { - clear_bit(GD_SUPPRESS_PART_SCAN, &disk->state); + /* Not clear for unprivileged daemons, see comment above */ + if (!ub->unprivileged_daemons) + clear_bit(GD_SUPPRESS_PART_SCAN, &disk->state); } else { /* Schedule async partition scan for trusted daemons */ if (!ub->unprivileged_daemons) @@ -5006,15 +5008,22 @@ static int ublk_ctrl_get_features(const struct ublksrv_ctrl_cmd *header) return 0; } -static void ublk_ctrl_set_size(struct ublk_device *ub, const struct ublksrv_ctrl_cmd *header) +static int ublk_ctrl_set_size(struct ublk_device *ub, const struct ublksrv_ctrl_cmd *header) { struct ublk_param_basic *p = &ub->params.basic; u64 new_size = header->data[0]; + int ret = 0; mutex_lock(&ub->mutex); + if (!ub->ub_disk) { + ret = -ENODEV; + goto out; + } p->dev_sectors = new_size; set_capacity_and_notify(ub->ub_disk, p->dev_sectors); +out: mutex_unlock(&ub->mutex); + return ret; } struct count_busy { @@ -5335,8 +5344,7 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, ret = ublk_ctrl_end_recovery(ub, &header); break; case UBLK_CMD_UPDATE_SIZE: - ublk_ctrl_set_size(ub, &header); - ret = 0; + ret = ublk_ctrl_set_size(ub, &header); break; case UBLK_CMD_QUIESCE_DEV: ret = ublk_ctrl_quiesce_dev(ub, &header); diff --git a/drivers/cache/ax45mp_cache.c b/drivers/cache/ax45mp_cache.c index 1d7dd3d2c101..934c5087ec2b 100644 --- a/drivers/cache/ax45mp_cache.c +++ b/drivers/cache/ax45mp_cache.c @@ -178,11 +178,11 @@ static const struct of_device_id ax45mp_cache_ids[] = { static int __init ax45mp_cache_init(void) { - struct device_node *np; struct resource res; int ret; - np = of_find_matching_node(NULL, ax45mp_cache_ids); + struct device_node *np __free(device_node) = + of_find_matching_node(NULL, ax45mp_cache_ids); if (!of_device_is_available(np)) return -ENODEV; diff --git a/drivers/cache/starfive_starlink_cache.c b/drivers/cache/starfive_starlink_cache.c index 24c7d078ca22..3a25d2d7c70c 100644 --- a/drivers/cache/starfive_starlink_cache.c +++ b/drivers/cache/starfive_starlink_cache.c @@ -102,11 +102,11 @@ static const struct of_device_id starlink_cache_ids[] = { static int __init starlink_cache_init(void) { - struct device_node *np; u32 block_size; int ret; - np = of_find_matching_node(NULL, starlink_cache_ids); + struct device_node *np __free(device_node) = + of_find_matching_node(NULL, starlink_cache_ids); if (!of_device_is_available(np)) return -ENODEV; diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 65fbb8e807b9..c7876e9e024f 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -359,16 +359,6 @@ noinstr int cpuidle_enter_state(struct cpuidle_device *dev, int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, bool *stop_tick) { - /* - * If there is only a single idle state (or none), there is nothing - * meaningful for the governor to choose. Skip the governor and - * always use state 0 with the tick running. - */ - if (drv->state_count <= 1) { - *stop_tick = false; - return 0; - } - return cpuidle_curr_governor->select(drv, dev, stop_tick); } diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 8b2dfc11289b..aebf4dad545e 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -2408,10 +2408,8 @@ static int sev_ioctl_do_snp_platform_status(struct sev_issue_cmd *argp) * in Firmware state on failure. Use snp_reclaim_pages() to * transition either case back to Hypervisor-owned state. */ - if (snp_reclaim_pages(__pa(data), 1, true)) { - snp_leak_pages(__page_to_pfn(status_page), 1); + if (snp_reclaim_pages(__pa(data), 1, true)) return -EFAULT; - } } if (ret) diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c index 329f60ad422e..9214bbfc868f 100644 --- a/drivers/crypto/padlock-sha.c +++ b/drivers/crypto/padlock-sha.c @@ -332,6 +332,13 @@ static int __init padlock_init(void) if (!x86_match_cpu(padlock_sha_ids) || !boot_cpu_has(X86_FEATURE_PHE_EN)) return -ENODEV; + /* + * Skip family 0x07 and newer used by Zhaoxin processors, + * as the driver's self-tests fail on these CPUs. + */ + if (c->x86 >= 0x07) + return -ENODEV; + /* Register the newly added algorithm module if on * * VIA Nano processor, or else just do as before */ if (c->x86_model < 0x0f) { diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index 12a625387d6e..f2f94d4d533e 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -205,12 +205,12 @@ static int ffa_rxtx_map(phys_addr_t tx_buf, phys_addr_t rx_buf, u32 pg_cnt) return 0; } -static int ffa_rxtx_unmap(u16 vm_id) +static int ffa_rxtx_unmap(void) { ffa_value_t ret; invoke_ffa_fn((ffa_value_t){ - .a0 = FFA_RXTX_UNMAP, .a1 = PACK_TARGET_INFO(vm_id, 0), + .a0 = FFA_RXTX_UNMAP, }, &ret); if (ret.a0 == FFA_ERROR) @@ -2097,7 +2097,7 @@ static int __init ffa_init(void) pr_err("failed to setup partitions\n"); ffa_notifications_cleanup(); - ffa_rxtx_unmap(drv_info->vm_id); + ffa_rxtx_unmap(); free_pages: if (drv_info->tx_buffer) free_pages_exact(drv_info->tx_buffer, rxtx_bufsz); @@ -2112,7 +2112,7 @@ static void __exit ffa_exit(void) { ffa_notifications_cleanup(); ffa_partitions_cleanup(); - ffa_rxtx_unmap(drv_info->vm_id); + ffa_rxtx_unmap(); free_pages_exact(drv_info->tx_buffer, drv_info->rxtx_bufsz); free_pages_exact(drv_info->rx_buffer, drv_info->rxtx_bufsz); kfree(drv_info); diff --git a/drivers/firmware/arm_scmi/notify.c b/drivers/firmware/arm_scmi/notify.c index 9168794adae4..40ec184eedae 100644 --- a/drivers/firmware/arm_scmi/notify.c +++ b/drivers/firmware/arm_scmi/notify.c @@ -1066,7 +1066,7 @@ static int scmi_register_event_handler(struct scmi_notify_instance *ni, * since at creation time we usually want to have all setup and ready before * events really start flowing. * - * Return: A properly refcounted handler on Success, NULL on Failure + * Return: A properly refcounted handler on Success, ERR_PTR on Failure */ static inline struct scmi_event_handler * __scmi_event_handler_get_ops(struct scmi_notify_instance *ni, @@ -1113,7 +1113,7 @@ __scmi_event_handler_get_ops(struct scmi_notify_instance *ni, } mutex_unlock(&ni->pending_mtx); - return hndl; + return hndl ?: ERR_PTR(-ENODEV); } static struct scmi_event_handler * diff --git a/drivers/firmware/arm_scmi/protocols.h b/drivers/firmware/arm_scmi/protocols.h index 4c75970326e6..f51245aca259 100644 --- a/drivers/firmware/arm_scmi/protocols.h +++ b/drivers/firmware/arm_scmi/protocols.h @@ -189,13 +189,13 @@ struct scmi_protocol_handle { /** * struct scmi_iterator_state - Iterator current state descriptor - * @desc_index: Starting index for the current mulit-part request. + * @desc_index: Starting index for the current multi-part request. * @num_returned: Number of returned items in the last multi-part reply. * @num_remaining: Number of remaining items in the multi-part message. * @max_resources: Maximum acceptable number of items, configured by the caller * depending on the underlying resources that it is querying. * @loop_idx: The iterator loop index in the current multi-part reply. - * @rx_len: Size in bytes of the currenly processed message; it can be used by + * @rx_len: Size in bytes of the currently processed message; it can be used by * the user of the iterator to verify a reply size. * @priv: Optional pointer to some additional state-related private data setup * by the caller during the iterations. diff --git a/drivers/firmware/arm_scpi.c b/drivers/firmware/arm_scpi.c index 00e74449ce09..2acad5fa5a28 100644 --- a/drivers/firmware/arm_scpi.c +++ b/drivers/firmware/arm_scpi.c @@ -18,6 +18,7 @@ #include <linux/bitmap.h> #include <linux/bitfield.h> +#include <linux/cleanup.h> #include <linux/device.h> #include <linux/err.h> #include <linux/export.h> @@ -940,13 +941,13 @@ static int scpi_probe(struct platform_device *pdev) int idx = scpi_drvinfo->num_chans; struct scpi_chan *pchan = scpi_drvinfo->channels + idx; struct mbox_client *cl = &pchan->cl; - struct device_node *shmem = of_parse_phandle(np, "shmem", idx); + struct device_node *shmem __free(device_node) = + of_parse_phandle(np, "shmem", idx); if (!of_match_node(shmem_of_match, shmem)) return -ENXIO; ret = of_address_to_resource(shmem, 0, &res); - of_node_put(shmem); if (ret) { dev_err(dev, "failed to get SCPI payload mem resource\n"); return ret; diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index b4f1c01e3b5b..5d8be0ac7c5e 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -1610,11 +1610,17 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware, region_name); if (reg) { + /* + * Although we expect the underlying bus does not require + * physically-contiguous buffers, we pessimistically use + * a temporary buffer instead of trusting that the + * alignment of region->data is ok. + */ region_len = le32_to_cpu(region->len); if (region_len > buf_len) { buf_len = round_up(region_len, PAGE_SIZE); - kfree(buf); - buf = kmalloc(buf_len, GFP_KERNEL | GFP_DMA); + vfree(buf); + buf = vmalloc(buf_len); if (!buf) { ret = -ENOMEM; goto out_fw; @@ -1643,7 +1649,7 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware, ret = 0; out_fw: - kfree(buf); + vfree(buf); if (ret == -EOVERFLOW) cs_dsp_err(dsp, "%s: file content overflows file data\n", file); @@ -2331,11 +2337,17 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware } if (reg) { + /* + * Although we expect the underlying bus does not require + * physically-contiguous buffers, we pessimistically use + * a temporary buffer instead of trusting that the + * alignment of blk->data is ok. + */ region_len = le32_to_cpu(blk->len); if (region_len > buf_len) { buf_len = round_up(region_len, PAGE_SIZE); - kfree(buf); - buf = kmalloc(buf_len, GFP_KERNEL | GFP_DMA); + vfree(buf); + buf = vmalloc(buf_len); if (!buf) { ret = -ENOMEM; goto out_fw; @@ -2366,7 +2378,7 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware ret = 0; out_fw: - kfree(buf); + vfree(buf); if (ret == -EOVERFLOW) cs_dsp_err(dsp, "%s: file content overflows file data\n", file); diff --git a/drivers/firmware/stratix10-rsu.c b/drivers/firmware/stratix10-rsu.c index 41da07c445a6..e1912108a0fe 100644 --- a/drivers/firmware/stratix10-rsu.c +++ b/drivers/firmware/stratix10-rsu.c @@ -768,7 +768,9 @@ static int stratix10_rsu_probe(struct platform_device *pdev) rsu_async_status_callback); if (ret) { dev_err(dev, "Error, getting RSU status %i\n", ret); + stratix10_svc_remove_async_client(priv->chan); stratix10_svc_free_channel(priv->chan); + return ret; } /* get DCMF version from firmware */ diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c index 6f5c298582ab..e9e35d67ef96 100644 --- a/drivers/firmware/stratix10-svc.c +++ b/drivers/firmware/stratix10-svc.c @@ -37,15 +37,14 @@ * service layer will return error to FPGA manager when timeout occurs, * timeout is set to 30 seconds (30 * 1000) at Intel Stratix10 SoC. */ -#define SVC_NUM_DATA_IN_FIFO 32 +#define SVC_NUM_DATA_IN_FIFO 8 #define SVC_NUM_CHANNEL 4 -#define FPGA_CONFIG_DATA_CLAIM_TIMEOUT_MS 200 +#define FPGA_CONFIG_DATA_CLAIM_TIMEOUT_MS 2000 #define FPGA_CONFIG_STATUS_TIMEOUT_SEC 30 #define BYTE_TO_WORD_SIZE 4 /* stratix10 service layer clients */ #define STRATIX10_RSU "stratix10-rsu" -#define INTEL_FCS "intel-fcs" /* Maximum number of SDM client IDs. */ #define MAX_SDM_CLIENT_IDS 16 @@ -105,11 +104,9 @@ struct stratix10_svc_chan; /** * struct stratix10_svc - svc private data * @stratix10_svc_rsu: pointer to stratix10 RSU device - * @intel_svc_fcs: pointer to the FCS device */ struct stratix10_svc { struct platform_device *stratix10_svc_rsu; - struct platform_device *intel_svc_fcs; }; /** @@ -251,12 +248,10 @@ struct stratix10_async_ctrl { * @num_active_client: number of active service client * @node: list management * @genpool: memory pool pointing to the memory region - * @task: pointer to the thread task which handles SMC or HVC call - * @svc_fifo: a queue for storing service message data * @complete_status: state for completion - * @svc_fifo_lock: protect access to service message data queue * @invoke_fn: function to issue secure monitor call or hypervisor call * @svc: manages the list of client svc drivers + * @sdm_lock: only allows a single command single response to SDM * @actrl: async control structure * * This struct is used to create communication channels for service clients, to @@ -269,12 +264,10 @@ struct stratix10_svc_controller { int num_active_client; struct list_head node; struct gen_pool *genpool; - struct task_struct *task; - struct kfifo svc_fifo; struct completion complete_status; - spinlock_t svc_fifo_lock; svc_invoke_fn *invoke_fn; struct stratix10_svc *svc; + struct mutex sdm_lock; struct stratix10_async_ctrl actrl; }; @@ -283,6 +276,9 @@ struct stratix10_svc_controller { * @ctrl: pointer to service controller which is the provider of this channel * @scl: pointer to service client which owns the channel * @name: service client name associated with the channel + * @task: pointer to the thread task which handles SMC or HVC call + * @svc_fifo: a queue for storing service message data (separate fifo for every channel) + * @svc_fifo_lock: protect access to service message data queue (locking pending fifo) * @lock: protect access to the channel * @async_chan: reference to asynchronous channel object for this channel * @@ -293,6 +289,9 @@ struct stratix10_svc_chan { struct stratix10_svc_controller *ctrl; struct stratix10_svc_client *scl; char *name; + struct task_struct *task; + struct kfifo svc_fifo; + spinlock_t svc_fifo_lock; spinlock_t lock; struct stratix10_async_chan *async_chan; }; @@ -527,10 +526,10 @@ static void svc_thread_recv_status_ok(struct stratix10_svc_data *p_data, */ static int svc_normal_to_secure_thread(void *data) { - struct stratix10_svc_controller - *ctrl = (struct stratix10_svc_controller *)data; - struct stratix10_svc_data *pdata; - struct stratix10_svc_cb_data *cbdata; + struct stratix10_svc_chan *chan = (struct stratix10_svc_chan *)data; + struct stratix10_svc_controller *ctrl = chan->ctrl; + struct stratix10_svc_data *pdata = NULL; + struct stratix10_svc_cb_data *cbdata = NULL; struct arm_smccc_res res; unsigned long a0, a1, a2, a3, a4, a5, a6, a7; int ret_fifo = 0; @@ -555,12 +554,12 @@ static int svc_normal_to_secure_thread(void *data) a6 = 0; a7 = 0; - pr_debug("smc_hvc_shm_thread is running\n"); + pr_debug("%s: %s: Thread is running!\n", __func__, chan->name); while (!kthread_should_stop()) { - ret_fifo = kfifo_out_spinlocked(&ctrl->svc_fifo, + ret_fifo = kfifo_out_spinlocked(&chan->svc_fifo, pdata, sizeof(*pdata), - &ctrl->svc_fifo_lock); + &chan->svc_fifo_lock); if (!ret_fifo) continue; @@ -569,9 +568,25 @@ static int svc_normal_to_secure_thread(void *data) (unsigned int)pdata->paddr, pdata->command, (unsigned int)pdata->size); + /* SDM can only process one command at a time */ + pr_debug("%s: %s: Thread is waiting for mutex!\n", + __func__, chan->name); + if (mutex_lock_interruptible(&ctrl->sdm_lock)) { + /* item already dequeued; notify client to unblock it */ + cbdata->status = BIT(SVC_STATUS_ERROR); + cbdata->kaddr1 = NULL; + cbdata->kaddr2 = NULL; + cbdata->kaddr3 = NULL; + if (pdata->chan->scl) + pdata->chan->scl->receive_cb(pdata->chan->scl, + cbdata); + break; + } + switch (pdata->command) { case COMMAND_RECONFIG_DATA_CLAIM: svc_thread_cmd_data_claim(ctrl, pdata, cbdata); + mutex_unlock(&ctrl->sdm_lock); continue; case COMMAND_RECONFIG: a0 = INTEL_SIP_SMC_FPGA_CONFIG_START; @@ -700,10 +715,11 @@ static int svc_normal_to_secure_thread(void *data) break; default: pr_warn("it shouldn't happen\n"); - break; + mutex_unlock(&ctrl->sdm_lock); + continue; } - pr_debug("%s: before SMC call -- a0=0x%016x a1=0x%016x", - __func__, + pr_debug("%s: %s: before SMC call -- a0=0x%016x a1=0x%016x", + __func__, chan->name, (unsigned int)a0, (unsigned int)a1); pr_debug(" a2=0x%016x\n", (unsigned int)a2); @@ -712,8 +728,8 @@ static int svc_normal_to_secure_thread(void *data) pr_debug(" a5=0x%016x\n", (unsigned int)a5); ctrl->invoke_fn(a0, a1, a2, a3, a4, a5, a6, a7, &res); - pr_debug("%s: after SMC call -- res.a0=0x%016x", - __func__, (unsigned int)res.a0); + pr_debug("%s: %s: after SMC call -- res.a0=0x%016x", + __func__, chan->name, (unsigned int)res.a0); pr_debug(" res.a1=0x%016x, res.a2=0x%016x", (unsigned int)res.a1, (unsigned int)res.a2); pr_debug(" res.a3=0x%016x\n", (unsigned int)res.a3); @@ -728,6 +744,7 @@ static int svc_normal_to_secure_thread(void *data) cbdata->kaddr2 = NULL; cbdata->kaddr3 = NULL; pdata->chan->scl->receive_cb(pdata->chan->scl, cbdata); + mutex_unlock(&ctrl->sdm_lock); continue; } @@ -801,6 +818,8 @@ static int svc_normal_to_secure_thread(void *data) break; } + + mutex_unlock(&ctrl->sdm_lock); } kfree(cbdata); @@ -1696,22 +1715,33 @@ int stratix10_svc_send(struct stratix10_svc_chan *chan, void *msg) if (!p_data) return -ENOMEM; - /* first client will create kernel thread */ - if (!chan->ctrl->task) { - chan->ctrl->task = - kthread_run_on_cpu(svc_normal_to_secure_thread, - (void *)chan->ctrl, - cpu, "svc_smc_hvc_thread"); - if (IS_ERR(chan->ctrl->task)) { + /* first caller creates the per-channel kthread */ + if (!chan->task) { + struct task_struct *task; + + task = kthread_run_on_cpu(svc_normal_to_secure_thread, + (void *)chan, + cpu, "svc_smc_hvc_thread"); + if (IS_ERR(task)) { dev_err(chan->ctrl->dev, "failed to create svc_smc_hvc_thread\n"); kfree(p_data); return -EINVAL; } + + spin_lock(&chan->lock); + if (chan->task) { + /* another caller won the race; discard our thread */ + spin_unlock(&chan->lock); + kthread_stop(task); + } else { + chan->task = task; + spin_unlock(&chan->lock); + } } - pr_debug("%s: sent P-va=%p, P-com=%x, P-size=%u\n", __func__, - p_msg->payload, p_msg->command, + pr_debug("%s: %s: sent P-va=%p, P-com=%x, P-size=%u\n", __func__, + chan->name, p_msg->payload, p_msg->command, (unsigned int)p_msg->payload_length); if (list_empty(&svc_data_mem)) { @@ -1747,12 +1777,16 @@ int stratix10_svc_send(struct stratix10_svc_chan *chan, void *msg) p_data->arg[2] = p_msg->arg[2]; p_data->size = p_msg->payload_length; p_data->chan = chan; - pr_debug("%s: put to FIFO pa=0x%016x, cmd=%x, size=%u\n", __func__, - (unsigned int)p_data->paddr, p_data->command, - (unsigned int)p_data->size); - ret = kfifo_in_spinlocked(&chan->ctrl->svc_fifo, p_data, + pr_debug("%s: %s: put to FIFO pa=0x%016x, cmd=%x, size=%u\n", + __func__, + chan->name, + (unsigned int)p_data->paddr, + p_data->command, + (unsigned int)p_data->size); + + ret = kfifo_in_spinlocked(&chan->svc_fifo, p_data, sizeof(*p_data), - &chan->ctrl->svc_fifo_lock); + &chan->svc_fifo_lock); kfree(p_data); @@ -1773,11 +1807,12 @@ EXPORT_SYMBOL_GPL(stratix10_svc_send); */ void stratix10_svc_done(struct stratix10_svc_chan *chan) { - /* stop thread when thread is running AND only one active client */ - if (chan->ctrl->task && chan->ctrl->num_active_client <= 1) { - pr_debug("svc_smc_hvc_shm_thread is stopped\n"); - kthread_stop(chan->ctrl->task); - chan->ctrl->task = NULL; + /* stop thread when thread is running */ + if (chan->task) { + pr_debug("%s: %s: svc_smc_hvc_shm_thread is stopping\n", + __func__, chan->name); + kthread_stop(chan->task); + chan->task = NULL; } } EXPORT_SYMBOL_GPL(stratix10_svc_done); @@ -1817,8 +1852,8 @@ void *stratix10_svc_allocate_memory(struct stratix10_svc_chan *chan, pmem->paddr = pa; pmem->size = s; list_add_tail(&pmem->node, &svc_data_mem); - pr_debug("%s: va=%p, pa=0x%016x\n", __func__, - pmem->vaddr, (unsigned int)pmem->paddr); + pr_debug("%s: %s: va=%p, pa=0x%016x\n", __func__, + chan->name, pmem->vaddr, (unsigned int)pmem->paddr); return (void *)va; } @@ -1855,6 +1890,13 @@ static const struct of_device_id stratix10_svc_drv_match[] = { {}, }; +static const char * const chan_names[SVC_NUM_CHANNEL] = { + SVC_CLIENT_FPGA, + SVC_CLIENT_RSU, + SVC_CLIENT_FCS, + SVC_CLIENT_HWMON +}; + static int stratix10_svc_drv_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1862,11 +1904,11 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev) struct stratix10_svc_chan *chans; struct gen_pool *genpool; struct stratix10_svc_sh_memory *sh_memory; - struct stratix10_svc *svc; + struct stratix10_svc *svc = NULL; svc_invoke_fn *invoke_fn; size_t fifo_size; - int ret; + int ret, i = 0; /* get SMC or HVC function */ invoke_fn = get_invoke_func(dev); @@ -1905,8 +1947,8 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev) controller->num_active_client = 0; controller->chans = chans; controller->genpool = genpool; - controller->task = NULL; controller->invoke_fn = invoke_fn; + INIT_LIST_HEAD(&controller->node); init_completion(&controller->complete_status); ret = stratix10_svc_async_init(controller); @@ -1917,32 +1959,20 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev) } fifo_size = sizeof(struct stratix10_svc_data) * SVC_NUM_DATA_IN_FIFO; - ret = kfifo_alloc(&controller->svc_fifo, fifo_size, GFP_KERNEL); - if (ret) { - dev_err(dev, "failed to allocate FIFO\n"); - goto err_async_exit; - } - spin_lock_init(&controller->svc_fifo_lock); - - chans[0].scl = NULL; - chans[0].ctrl = controller; - chans[0].name = SVC_CLIENT_FPGA; - spin_lock_init(&chans[0].lock); + mutex_init(&controller->sdm_lock); - chans[1].scl = NULL; - chans[1].ctrl = controller; - chans[1].name = SVC_CLIENT_RSU; - spin_lock_init(&chans[1].lock); - - chans[2].scl = NULL; - chans[2].ctrl = controller; - chans[2].name = SVC_CLIENT_FCS; - spin_lock_init(&chans[2].lock); - - chans[3].scl = NULL; - chans[3].ctrl = controller; - chans[3].name = SVC_CLIENT_HWMON; - spin_lock_init(&chans[3].lock); + for (i = 0; i < SVC_NUM_CHANNEL; i++) { + chans[i].scl = NULL; + chans[i].ctrl = controller; + chans[i].name = (char *)chan_names[i]; + spin_lock_init(&chans[i].lock); + ret = kfifo_alloc(&chans[i].svc_fifo, fifo_size, GFP_KERNEL); + if (ret) { + dev_err(dev, "failed to allocate FIFO %d\n", i); + goto err_free_fifos; + } + spin_lock_init(&chans[i].svc_fifo_lock); + } list_add_tail(&controller->node, &svc_ctrl); platform_set_drvdata(pdev, controller); @@ -1951,7 +1981,7 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev) svc = devm_kzalloc(dev, sizeof(*svc), GFP_KERNEL); if (!svc) { ret = -ENOMEM; - goto err_free_kfifo; + goto err_free_fifos; } controller->svc = svc; @@ -1959,51 +1989,43 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev) if (!svc->stratix10_svc_rsu) { dev_err(dev, "failed to allocate %s device\n", STRATIX10_RSU); ret = -ENOMEM; - goto err_free_kfifo; + goto err_free_fifos; } ret = platform_device_add(svc->stratix10_svc_rsu); - if (ret) { - platform_device_put(svc->stratix10_svc_rsu); - goto err_free_kfifo; - } - - svc->intel_svc_fcs = platform_device_alloc(INTEL_FCS, 1); - if (!svc->intel_svc_fcs) { - dev_err(dev, "failed to allocate %s device\n", INTEL_FCS); - ret = -ENOMEM; - goto err_unregister_rsu_dev; - } - - ret = platform_device_add(svc->intel_svc_fcs); - if (ret) { - platform_device_put(svc->intel_svc_fcs); - goto err_unregister_rsu_dev; - } + if (ret) + goto err_put_device; ret = of_platform_default_populate(dev_of_node(dev), NULL, dev); if (ret) - goto err_unregister_fcs_dev; + goto err_unregister_rsu_dev; pr_info("Intel Service Layer Driver Initialized\n"); return 0; -err_unregister_fcs_dev: - platform_device_unregister(svc->intel_svc_fcs); err_unregister_rsu_dev: platform_device_unregister(svc->stratix10_svc_rsu); -err_free_kfifo: - kfifo_free(&controller->svc_fifo); -err_async_exit: + goto err_free_fifos; +err_put_device: + platform_device_put(svc->stratix10_svc_rsu); +err_free_fifos: + /* only remove from list if list_add_tail() was reached */ + if (!list_empty(&controller->node)) + list_del(&controller->node); + /* free only the FIFOs that were successfully allocated */ + while (i--) + kfifo_free(&chans[i].svc_fifo); stratix10_svc_async_exit(controller); err_destroy_pool: gen_pool_destroy(genpool); + return ret; } static void stratix10_svc_drv_remove(struct platform_device *pdev) { + int i; struct stratix10_svc_controller *ctrl = platform_get_drvdata(pdev); struct stratix10_svc *svc = ctrl->svc; @@ -2011,14 +2033,16 @@ static void stratix10_svc_drv_remove(struct platform_device *pdev) of_platform_depopulate(ctrl->dev); - platform_device_unregister(svc->intel_svc_fcs); platform_device_unregister(svc->stratix10_svc_rsu); - kfifo_free(&ctrl->svc_fifo); - if (ctrl->task) { - kthread_stop(ctrl->task); - ctrl->task = NULL; + for (i = 0; i < SVC_NUM_CHANNEL; i++) { + if (ctrl->chans[i].task) { + kthread_stop(ctrl->chans[i].task); + ctrl->chans[i].task = NULL; + } + kfifo_free(&ctrl->chans[i].svc_fifo); } + if (ctrl->genpool) gen_pool_destroy(ctrl->genpool); list_del(&ctrl->node); diff --git a/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c b/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c index 6fc4e3452b88..ee781d2f0b8e 100644 --- a/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c +++ b/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c @@ -38,8 +38,10 @@ MODULE_DESCRIPTION("GPIB driver for LPVO usb devices"); /* * Table of devices that work with this driver. * - * Currently, only one device is known to be used in the - * lpvo_usb_gpib adapter (FTDI 0403:6001). + * Currently, only one device is known to be used in the lpvo_usb_gpib + * adapter (FTDI 0403:6001) but as this device id is already handled by the + * ftdi_sio USB serial driver the LPVO driver must not bind to it by default. + * * If your adapter uses a different chip, insert a line * in the following table with proper <Vendor-id>, <Product-id>. * @@ -50,7 +52,6 @@ MODULE_DESCRIPTION("GPIB driver for LPVO usb devices"); */ static const struct usb_device_id skel_table[] = { - { USB_DEVICE(0x0403, 0x6001) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, skel_table); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 3e19b51a2763..d8296dfc5e8a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2690,8 +2690,10 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) break; default: r = amdgpu_discovery_set_ip_blocks(adev); - if (r) + if (r) { + adev->num_ip_blocks = 0; return r; + } break; } @@ -3247,6 +3249,8 @@ int amdgpu_device_set_cg_state(struct amdgpu_device *adev, i = state == AMD_CG_STATE_GATE ? j : adev->num_ip_blocks - j - 1; if (!adev->ip_blocks[i].status.late_initialized) continue; + if (!adev->ip_blocks[i].version) + continue; /* skip CG for GFX, SDMA on S0ix */ if (adev->in_s0ix && (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX || @@ -3286,6 +3290,8 @@ int amdgpu_device_set_pg_state(struct amdgpu_device *adev, i = state == AMD_PG_STATE_GATE ? j : adev->num_ip_blocks - j - 1; if (!adev->ip_blocks[i].status.late_initialized) continue; + if (!adev->ip_blocks[i].version) + continue; /* skip PG for GFX, SDMA on S0ix */ if (adev->in_s0ix && (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX || @@ -3493,6 +3499,8 @@ static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev) int i, r; for (i = 0; i < adev->num_ip_blocks; i++) { + if (!adev->ip_blocks[i].version) + continue; if (!adev->ip_blocks[i].version->funcs->early_fini) continue; @@ -3570,6 +3578,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev) if (!adev->ip_blocks[i].status.sw) continue; + if (!adev->ip_blocks[i].version) + continue; if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) { amdgpu_ucode_free_bo(adev); amdgpu_free_static_csa(&adev->virt.csa_obj); @@ -3596,6 +3606,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev) for (i = adev->num_ip_blocks - 1; i >= 0; i--) { if (!adev->ip_blocks[i].status.late_initialized) continue; + if (!adev->ip_blocks[i].version) + continue; if (adev->ip_blocks[i].version->funcs->late_fini) adev->ip_blocks[i].version->funcs->late_fini(&adev->ip_blocks[i]); adev->ip_blocks[i].status.late_initialized = false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 77e2133de5cf..7f19554b9ad1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -83,7 +83,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev) { struct amdgpu_device *adev = drm_to_adev(dev); - if (adev == NULL) + if (adev == NULL || !adev->num_ip_blocks) return; amdgpu_unregister_gpu_instance(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h index dc8d2f52c7d6..e244c12ceb23 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h @@ -368,15 +368,15 @@ struct amdgpu_mode_info { struct drm_property *plane_ctm_property; /** - * @shaper_lut_property: Plane property to set pre-blending shaper LUT - * that converts color content before 3D LUT. If - * plane_shaper_tf_property != Identity TF, AMD color module will + * @plane_shaper_lut_property: Plane property to set pre-blending + * shaper LUT that converts color content before 3D LUT. + * If plane_shaper_tf_property != Identity TF, AMD color module will * combine the user LUT values with pre-defined TF into the LUT * parameters to be programmed. */ struct drm_property *plane_shaper_lut_property; /** - * @shaper_lut_size_property: Plane property for the size of + * @plane_shaper_lut_size_property: Plane property for the size of * pre-blending shaper LUT as supported by the driver (read-only). */ struct drm_property *plane_shaper_lut_size_property; @@ -400,10 +400,10 @@ struct amdgpu_mode_info { */ struct drm_property *plane_lut3d_property; /** - * @plane_degamma_lut_size_property: Plane property to define the max - * size of 3D LUT as supported by the driver (read-only). The max size - * is the max size of one dimension and, therefore, the max number of - * entries for 3D LUT array is the 3D LUT size cubed; + * @plane_lut3d_size_property: Plane property to define the max size + * of 3D LUT as supported by the driver (read-only). The max size is + * the max size of one dimension and, therefore, the max number of + * entries for 3D LUT array is the 3D LUT size cubed. */ struct drm_property *plane_lut3d_size_property; /** diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index 5bfa5d1d0b36..023c7345ea54 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -731,6 +731,9 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe) int i; struct amdgpu_device *adev = mes->adev; union MESAPI_SET_HW_RESOURCES mes_set_hw_res_pkt; + uint32_t mes_rev = (pipe == AMDGPU_MES_SCHED_PIPE) ? + (mes->sched_version & AMDGPU_MES_VERSION_MASK) : + (mes->kiq_version & AMDGPU_MES_VERSION_MASK); memset(&mes_set_hw_res_pkt, 0, sizeof(mes_set_hw_res_pkt)); @@ -785,7 +788,7 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe) * handling support, other queue will not use the oversubscribe timer. * handling mode - 0: disabled; 1: basic version; 2: basic+ version */ - mes_set_hw_res_pkt.oversubscription_timer = 50; + mes_set_hw_res_pkt.oversubscription_timer = mes_rev < 0x8b ? 0 : 50; mes_set_hw_res_pkt.unmapped_doorbell_handling = 1; if (amdgpu_mes_log_enable) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 8ea31699d38b..f5d2847e1cbb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -593,6 +593,7 @@ int pqm_update_queue_properties(struct process_queue_manager *pqm, p->queue_size)) { pr_debug("ring buf 0x%llx size 0x%llx not mapped on GPU\n", p->queue_address, p->queue_size); + amdgpu_bo_unreserve(vm->root.bo); return -EFAULT; } diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h index 3711d400773a..4c4e61bc91b5 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h @@ -38,7 +38,11 @@ DCCG_SRII(PIXEL_RATE_CNTL, OTG, 0),\ DCCG_SRII(PIXEL_RATE_CNTL, OTG, 1),\ SR(DISPCLK_FREQ_CHANGE_CNTL),\ - SR(DC_MEM_GLOBAL_PWR_REQ_CNTL) + SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\ + SR(MICROSECOND_TIME_BASE_DIV),\ + SR(MILLISECOND_TIME_BASE_DIV),\ + SR(DCCG_GATE_DISABLE_CNTL),\ + SR(DCCG_GATE_DISABLE_CNTL2) #define DCCG_REG_LIST_DCN2() \ DCCG_COMMON_REG_LIST_DCN_BASE(),\ diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c index 75c69348027e..c4d4eea140f3 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c @@ -96,6 +96,25 @@ static void dccg21_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppcl dccg->pipe_dppclk_khz[dpp_inst] = req_dppclk; } +/* + * On DCN21 S0i3 resume, BIOS programs MICROSECOND_TIME_BASE_DIV to + * 0x00120464 as a marker that golden init has already been done. + * dcn21_s0i3_golden_init_wa() reads this marker later in bios_golden_init() + * to decide whether to skip golden init. + * + * dccg2_init() unconditionally overwrites MICROSECOND_TIME_BASE_DIV to + * 0x00120264, destroying the marker before it can be read. + * + * Guard the call: if the S0i3 marker is present, skip dccg2_init() so the + * WA can function correctly. bios_golden_init() will handle init in that case. + */ +static void dccg21_init(struct dccg *dccg) +{ + if (dccg2_is_s0i3_golden_init_wa_done(dccg)) + return; + + dccg2_init(dccg); +} static const struct dccg_funcs dccg21_funcs = { .update_dpp_dto = dccg21_update_dpp_dto, @@ -103,7 +122,7 @@ static const struct dccg_funcs dccg21_funcs = { .set_fifo_errdet_ovr_en = dccg2_set_fifo_errdet_ovr_en, .otg_add_pixel = dccg2_otg_add_pixel, .otg_drop_pixel = dccg2_otg_drop_pixel, - .dccg_init = dccg2_init, + .dccg_init = dccg21_init, .refclk_setup = dccg2_refclk_setup, /* Deprecated - for backward compatibility only */ .allow_clock_gating = dccg2_allow_clock_gating, .enable_memory_low_power = dccg2_enable_memory_low_power, diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h index 067e49cb238e..e2381ca0be0b 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h @@ -34,7 +34,13 @@ DCCG_SRII(DTO_PARAM, DPPCLK, 1),\ DCCG_SRII(DTO_PARAM, DPPCLK, 2),\ DCCG_SRII(DTO_PARAM, DPPCLK, 3),\ - SR(REFCLK_CNTL) + SR(REFCLK_CNTL),\ + SR(DISPCLK_FREQ_CHANGE_CNTL),\ + SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\ + SR(MICROSECOND_TIME_BASE_DIV),\ + SR(MILLISECOND_TIME_BASE_DIV),\ + SR(DCCG_GATE_DISABLE_CNTL),\ + SR(DCCG_GATE_DISABLE_CNTL2) #define DCCG_MASK_SH_LIST_DCN301(mask_sh) \ DCCG_SFI(DPPCLK_DTO_CTRL, DTO_ENABLE, DPPCLK, 0, mask_sh),\ diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h index bf659920d4cc..b5e3849ef12a 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h @@ -64,9 +64,12 @@ SR(DSCCLK1_DTO_PARAM),\ SR(DSCCLK2_DTO_PARAM),\ SR(DSCCLK_DTO_CTRL),\ + SR(DCCG_GATE_DISABLE_CNTL),\ SR(DCCG_GATE_DISABLE_CNTL2),\ SR(DCCG_GATE_DISABLE_CNTL3),\ - SR(HDMISTREAMCLK0_DTO_PARAM) + SR(HDMISTREAMCLK0_DTO_PARAM),\ + SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\ + SR(MICROSECOND_TIME_BASE_DIV) #define DCCG_MASK_SH_LIST_DCN31(mask_sh) \ diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h index a609635f35db..ecbdc05f7c45 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h @@ -70,11 +70,14 @@ SR(DSCCLK2_DTO_PARAM),\ SR(DSCCLK3_DTO_PARAM),\ SR(DSCCLK_DTO_CTRL),\ + SR(DCCG_GATE_DISABLE_CNTL),\ SR(DCCG_GATE_DISABLE_CNTL2),\ SR(DCCG_GATE_DISABLE_CNTL3),\ SR(HDMISTREAMCLK0_DTO_PARAM),\ SR(OTG_PIXEL_RATE_DIV),\ - SR(DTBCLK_P_CNTL) + SR(DTBCLK_P_CNTL),\ + SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\ + SR(MICROSECOND_TIME_BASE_DIV) #define DCCG_MASK_SH_LIST_DCN314_COMMON(mask_sh) \ DCCG_SFI(DPPCLK_DTO_CTRL, DTO_DB_EN, DPPCLK, 0, mask_sh),\ diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index b32c053950c9..a8d63d4d1f6e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2222,7 +2222,8 @@ static int smu_v13_0_0_restore_user_od_settings(struct smu_context *smu) user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) | BIT(PP_OD_FEATURE_UCLK_BIT) | BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) | - BIT(PP_OD_FEATURE_FAN_CURVE_BIT); + BIT(PP_OD_FEATURE_FAN_CURVE_BIT) | + BIT(PP_OD_FEATURE_ZERO_FAN_BIT); res = smu_v13_0_0_upload_overdrive_table(smu, user_od_table); user_od_table->OverDriveTable.FeatureCtrlMask = 0; if (res == 0) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index f08cfa510a8a..5500a0f12f0e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -2224,7 +2224,8 @@ static int smu_v13_0_7_restore_user_od_settings(struct smu_context *smu) user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) | BIT(PP_OD_FEATURE_UCLK_BIT) | BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) | - BIT(PP_OD_FEATURE_FAN_CURVE_BIT); + BIT(PP_OD_FEATURE_FAN_CURVE_BIT) | + BIT(PP_OD_FEATURE_ZERO_FAN_BIT); res = smu_v13_0_7_upload_overdrive_table(smu, user_od_table); user_od_table->OverDriveTable.FeatureCtrlMask = 0; if (res == 0) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index 9994d4369da8..73762d9b5969 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -2311,7 +2311,8 @@ static int smu_v14_0_2_restore_user_od_settings(struct smu_context *smu) user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) | BIT(PP_OD_FEATURE_UCLK_BIT) | BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) | - BIT(PP_OD_FEATURE_FAN_CURVE_BIT); + BIT(PP_OD_FEATURE_FAN_CURVE_BIT) | + BIT(PP_OD_FEATURE_ZERO_FAN_BIT); res = smu_v14_0_2_upload_overdrive_table(smu, user_od_table); user_od_table->OverDriveTable.FeatureCtrlMask = 0; if (res == 0) diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c index f6736b4457bb..17a885244e1e 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -351,9 +351,9 @@ static u8 sn65dsi83_get_dsi_range(struct sn65dsi83 *ctx, * DSI_CLK = mode clock * bpp / dsi_data_lanes / 2 * the 2 is there because the bus is DDR. */ - return DIV_ROUND_UP(clamp((unsigned int)mode->clock * - mipi_dsi_pixel_format_to_bpp(ctx->dsi->format) / - ctx->dsi->lanes / 2, 40000U, 500000U), 5000U); + return clamp((unsigned int)mode->clock * + mipi_dsi_pixel_format_to_bpp(ctx->dsi->format) / + ctx->dsi->lanes / 2, 40000U, 500000U) / 5000U; } static u8 sn65dsi83_get_dsi_div(struct sn65dsi83 *ctx) @@ -517,6 +517,7 @@ static void sn65dsi83_atomic_pre_enable(struct drm_bridge *bridge, struct drm_atomic_state *state) { struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + const unsigned int dual_factor = ctx->lvds_dual_link ? 2 : 1; const struct drm_bridge_state *bridge_state; const struct drm_crtc_state *crtc_state; const struct drm_display_mode *mode; @@ -653,18 +654,18 @@ static void sn65dsi83_atomic_pre_enable(struct drm_bridge *bridge, /* 32 + 1 pixel clock to ensure proper operation */ le16val = cpu_to_le16(32 + 1); regmap_bulk_write(ctx->regmap, REG_VID_CHA_SYNC_DELAY_LOW, &le16val, 2); - le16val = cpu_to_le16(mode->hsync_end - mode->hsync_start); + le16val = cpu_to_le16((mode->hsync_end - mode->hsync_start) / dual_factor); regmap_bulk_write(ctx->regmap, REG_VID_CHA_HSYNC_PULSE_WIDTH_LOW, &le16val, 2); le16val = cpu_to_le16(mode->vsync_end - mode->vsync_start); regmap_bulk_write(ctx->regmap, REG_VID_CHA_VSYNC_PULSE_WIDTH_LOW, &le16val, 2); regmap_write(ctx->regmap, REG_VID_CHA_HORIZONTAL_BACK_PORCH, - mode->htotal - mode->hsync_end); + (mode->htotal - mode->hsync_end) / dual_factor); regmap_write(ctx->regmap, REG_VID_CHA_VERTICAL_BACK_PORCH, mode->vtotal - mode->vsync_end); regmap_write(ctx->regmap, REG_VID_CHA_HORIZONTAL_FRONT_PORCH, - mode->hsync_start - mode->hdisplay); + (mode->hsync_start - mode->hdisplay) / dual_factor); regmap_write(ctx->regmap, REG_VID_CHA_VERTICAL_FRONT_PORCH, mode->vsync_start - mode->vdisplay); regmap_write(ctx->regmap, REG_VID_CHA_TEST_PATTERN, 0x00); diff --git a/drivers/gpu/drm/gud/gud_drv.c b/drivers/gpu/drm/gud/gud_drv.c index d0122d477610..17c2dead2c13 100644 --- a/drivers/gpu/drm/gud/gud_drv.c +++ b/drivers/gpu/drm/gud/gud_drv.c @@ -339,7 +339,9 @@ static int gud_stats_debugfs(struct seq_file *m, void *data) } static const struct drm_crtc_helper_funcs gud_crtc_helper_funcs = { - .atomic_check = drm_crtc_helper_atomic_check + .atomic_check = drm_crtc_helper_atomic_check, + .atomic_enable = gud_crtc_atomic_enable, + .atomic_disable = gud_crtc_atomic_disable, }; static const struct drm_crtc_funcs gud_crtc_funcs = { @@ -364,6 +366,10 @@ static const struct drm_plane_funcs gud_plane_funcs = { DRM_GEM_SHADOW_PLANE_FUNCS, }; +static const struct drm_mode_config_helper_funcs gud_mode_config_helpers = { + .atomic_commit_tail = drm_atomic_helper_commit_tail_rpm, +}; + static const struct drm_mode_config_funcs gud_mode_config_funcs = { .fb_create = drm_gem_fb_create_with_dirty, .atomic_check = drm_atomic_helper_check, @@ -499,6 +505,7 @@ static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id) drm->mode_config.min_height = le32_to_cpu(desc.min_height); drm->mode_config.max_height = le32_to_cpu(desc.max_height); drm->mode_config.funcs = &gud_mode_config_funcs; + drm->mode_config.helper_private = &gud_mode_config_helpers; /* Format init */ formats_dev = devm_kmalloc(dev, GUD_FORMATS_MAX_NUM, GFP_KERNEL); diff --git a/drivers/gpu/drm/gud/gud_internal.h b/drivers/gpu/drm/gud/gud_internal.h index d27c31648341..8eec8335f5f9 100644 --- a/drivers/gpu/drm/gud/gud_internal.h +++ b/drivers/gpu/drm/gud/gud_internal.h @@ -62,6 +62,10 @@ int gud_usb_set_u8(struct gud_device *gdrm, u8 request, u8 val); void gud_clear_damage(struct gud_device *gdrm); void gud_flush_work(struct work_struct *work); +void gud_crtc_atomic_enable(struct drm_crtc *crtc, + struct drm_atomic_state *state); +void gud_crtc_atomic_disable(struct drm_crtc *crtc, + struct drm_atomic_state *state); int gud_plane_atomic_check(struct drm_plane *plane, struct drm_atomic_state *state); void gud_plane_atomic_update(struct drm_plane *plane, diff --git a/drivers/gpu/drm/gud/gud_pipe.c b/drivers/gpu/drm/gud/gud_pipe.c index 4b77be94348d..b355bf4d3389 100644 --- a/drivers/gpu/drm/gud/gud_pipe.c +++ b/drivers/gpu/drm/gud/gud_pipe.c @@ -580,6 +580,39 @@ out: return ret; } +void gud_crtc_atomic_enable(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + struct drm_device *drm = crtc->dev; + struct gud_device *gdrm = to_gud_device(drm); + int idx; + + if (!drm_dev_enter(drm, &idx)) + return; + + gud_usb_set_u8(gdrm, GUD_REQ_SET_CONTROLLER_ENABLE, 1); + gud_usb_set(gdrm, GUD_REQ_SET_STATE_COMMIT, 0, NULL, 0); + gud_usb_set_u8(gdrm, GUD_REQ_SET_DISPLAY_ENABLE, 1); + + drm_dev_exit(idx); +} + +void gud_crtc_atomic_disable(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + struct drm_device *drm = crtc->dev; + struct gud_device *gdrm = to_gud_device(drm); + int idx; + + if (!drm_dev_enter(drm, &idx)) + return; + + gud_usb_set_u8(gdrm, GUD_REQ_SET_DISPLAY_ENABLE, 0); + gud_usb_set_u8(gdrm, GUD_REQ_SET_CONTROLLER_ENABLE, 0); + + drm_dev_exit(idx); +} + void gud_plane_atomic_update(struct drm_plane *plane, struct drm_atomic_state *atomic_state) { @@ -607,24 +640,12 @@ void gud_plane_atomic_update(struct drm_plane *plane, mutex_unlock(&gdrm->damage_lock); } - if (!drm_dev_enter(drm, &idx)) + if (!crtc || !drm_dev_enter(drm, &idx)) return; - if (!old_state->fb) - gud_usb_set_u8(gdrm, GUD_REQ_SET_CONTROLLER_ENABLE, 1); - - if (fb && (crtc->state->mode_changed || crtc->state->connectors_changed)) - gud_usb_set(gdrm, GUD_REQ_SET_STATE_COMMIT, 0, NULL, 0); - - if (crtc->state->active_changed) - gud_usb_set_u8(gdrm, GUD_REQ_SET_DISPLAY_ENABLE, crtc->state->active); - - if (!fb) - goto ctrl_disable; - ret = drm_gem_fb_begin_cpu_access(fb, DMA_FROM_DEVICE); if (ret) - goto ctrl_disable; + goto out; drm_atomic_helper_damage_iter_init(&iter, old_state, new_state); drm_atomic_for_each_plane_damage(&iter, &damage) @@ -632,9 +653,6 @@ void gud_plane_atomic_update(struct drm_plane *plane, drm_gem_fb_end_cpu_access(fb, DMA_FROM_DEVICE); -ctrl_disable: - if (!crtc->state->enable) - gud_usb_set_u8(gdrm, GUD_REQ_SET_CONTROLLER_ENABLE, 0); - +out: drm_dev_exit(idx); } diff --git a/drivers/gpu/drm/i915/display/intel_alpm.c b/drivers/gpu/drm/i915/display/intel_alpm.c index 07ffee38974b..f4f1b68f7543 100644 --- a/drivers/gpu/drm/i915/display/intel_alpm.c +++ b/drivers/gpu/drm/i915/display/intel_alpm.c @@ -43,12 +43,6 @@ bool intel_alpm_is_alpm_aux_less(struct intel_dp *intel_dp, void intel_alpm_init(struct intel_dp *intel_dp) { - u8 dpcd; - - if (drm_dp_dpcd_readb(&intel_dp->aux, DP_RECEIVER_ALPM_CAP, &dpcd) < 0) - return; - - intel_dp->alpm_dpcd = dpcd; mutex_init(&intel_dp->alpm.lock); } diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 3b8ba8ab76a1..c4246481fc2f 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -1614,7 +1614,6 @@ static void hsw_configure_cpu_transcoder(const struct intel_crtc_state *crtc_sta } intel_set_transcoder_timings(crtc_state); - intel_vrr_set_transcoder_timings(crtc_state); if (cpu_transcoder != TRANSCODER_EDP) intel_de_write(display, TRANS_MULT(display, cpu_transcoder), diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 559cf3bb23fd..696edf40b243 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -4577,6 +4577,7 @@ static bool intel_edp_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *connector) { struct intel_display *display = to_intel_display(intel_dp); + int ret; /* this function is meant to be called only once */ drm_WARN_ON(display->drm, intel_dp->dpcd[DP_DPCD_REV] != 0); @@ -4616,6 +4617,12 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *connector */ intel_dp_init_source_oui(intel_dp); + /* Read the ALPM DPCD caps */ + ret = drm_dp_dpcd_read_byte(&intel_dp->aux, DP_RECEIVER_ALPM_CAP, + &intel_dp->alpm_dpcd); + if (ret < 0) + return false; + /* * This has to be called after intel_dp->edp_dpcd is filled, PSR checks * for SET_POWER_CAPABLE bit in intel_dp->edp_dpcd[1] diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 4ce1173a2e91..b7302a32ded4 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -2619,6 +2619,12 @@ void intel_psr2_program_trans_man_trk_ctl(struct intel_dsb *dsb, intel_de_write_dsb(display, dsb, PIPE_SRCSZ_ERLY_TPT(crtc->pipe), crtc_state->pipe_srcsz_early_tpt); + + if (!crtc_state->dsc.compression_enable) + return; + + intel_dsc_su_et_parameters_configure(dsb, encoder, crtc_state, + drm_rect_height(&crtc_state->psr2_su_area)); } static void psr2_man_trk_ctl_calc(struct intel_crtc_state *crtc_state, @@ -2689,11 +2695,12 @@ static void clip_area_update(struct drm_rect *overlap_damage_area, overlap_damage_area->y2 = damage_area->y2; } -static void intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_state) +static bool intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_state) { struct intel_display *display = to_intel_display(crtc_state); const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config; u16 y_alignment; + bool su_area_changed = false; /* ADLP aligns the SU region to vdsc slice height in case dsc is enabled */ if (crtc_state->dsc.compression_enable && @@ -2702,10 +2709,18 @@ static void intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_st else y_alignment = crtc_state->su_y_granularity; - crtc_state->psr2_su_area.y1 -= crtc_state->psr2_su_area.y1 % y_alignment; - if (crtc_state->psr2_su_area.y2 % y_alignment) + if (crtc_state->psr2_su_area.y1 % y_alignment) { + crtc_state->psr2_su_area.y1 -= crtc_state->psr2_su_area.y1 % y_alignment; + su_area_changed = true; + } + + if (crtc_state->psr2_su_area.y2 % y_alignment) { crtc_state->psr2_su_area.y2 = ((crtc_state->psr2_su_area.y2 / y_alignment) + 1) * y_alignment; + su_area_changed = true; + } + + return su_area_changed; } /* @@ -2839,7 +2854,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); struct intel_plane_state *new_plane_state, *old_plane_state; struct intel_plane *plane; - bool full_update = false, cursor_in_su_area = false; + bool full_update = false, su_area_changed; int i, ret; if (!crtc_state->enable_psr2_sel_fetch) @@ -2946,15 +2961,32 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, if (ret) return ret; - /* - * Adjust su area to cover cursor fully as necessary (early - * transport). This needs to be done after - * drm_atomic_add_affected_planes to ensure visible cursor is added into - * affected planes even when cursor is not updated by itself. - */ - intel_psr2_sel_fetch_et_alignment(state, crtc, &cursor_in_su_area); + do { + bool cursor_in_su_area; - intel_psr2_sel_fetch_pipe_alignment(crtc_state); + /* + * Adjust su area to cover cursor fully as necessary + * (early transport). This needs to be done after + * drm_atomic_add_affected_planes to ensure visible + * cursor is added into affected planes even when + * cursor is not updated by itself. + */ + intel_psr2_sel_fetch_et_alignment(state, crtc, &cursor_in_su_area); + + su_area_changed = intel_psr2_sel_fetch_pipe_alignment(crtc_state); + + /* + * If the cursor was outside the SU area before + * alignment, the alignment step (which only expands + * SU) may pull the cursor partially inside, so we + * must run ET alignment again to fully cover it. But + * if the cursor was already fully inside before + * alignment, expanding the SU area won't change that, + * so no further work is needed. + */ + if (cursor_in_su_area) + break; + } while (su_area_changed); /* * Now that we have the pipe damaged area check if it intersect with @@ -3014,6 +3046,10 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, } skip_sel_fetch_set_loop: + if (full_update) + clip_area_update(&crtc_state->psr2_su_area, &crtc_state->pipe_src, + &crtc_state->pipe_src); + psr2_man_trk_ctl_calc(crtc_state, full_update); crtc_state->pipe_srcsz_early_tpt = psr2_pipe_srcsz_early_tpt_calc(crtc_state, full_update); diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c index 5493082f30a7..2065dac1e3fd 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.c +++ b/drivers/gpu/drm/i915/display/intel_vdsc.c @@ -767,6 +767,29 @@ void intel_dsc_dp_pps_write(struct intel_encoder *encoder, sizeof(dp_dsc_pps_sdp)); } +void intel_dsc_su_et_parameters_configure(struct intel_dsb *dsb, struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, int su_lines) +{ + struct intel_display *display = to_intel_display(crtc_state); + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config; + enum pipe pipe = crtc->pipe; + int vdsc_instances_per_pipe = intel_dsc_get_vdsc_per_pipe(crtc_state); + int slice_row_per_frame = su_lines / vdsc_cfg->slice_height; + u32 val; + + drm_WARN_ON_ONCE(display->drm, su_lines % vdsc_cfg->slice_height); + drm_WARN_ON_ONCE(display->drm, vdsc_instances_per_pipe > 2); + + val = DSC_SUPS0_SU_SLICE_ROW_PER_FRAME(slice_row_per_frame); + val |= DSC_SUPS0_SU_PIC_HEIGHT(su_lines); + + intel_de_write_dsb(display, dsb, LNL_DSC0_SU_PARAMETER_SET_0(pipe), val); + + if (vdsc_instances_per_pipe == 2) + intel_de_write_dsb(display, dsb, LNL_DSC1_SU_PARAMETER_SET_0(pipe), val); +} + static i915_reg_t dss_ctl1_reg(struct intel_crtc *crtc, enum transcoder cpu_transcoder) { return is_pipe_dsc(crtc, cpu_transcoder) ? diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.h b/drivers/gpu/drm/i915/display/intel_vdsc.h index 99f64ac54b27..99bb9042592a 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.h +++ b/drivers/gpu/drm/i915/display/intel_vdsc.h @@ -13,6 +13,7 @@ struct drm_printer; enum transcoder; struct intel_crtc; struct intel_crtc_state; +struct intel_dsb; struct intel_encoder; bool intel_dsc_source_support(const struct intel_crtc_state *crtc_state); @@ -31,6 +32,8 @@ void intel_dsc_dsi_pps_write(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state); void intel_dsc_dp_pps_write(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state); +void intel_dsc_su_et_parameters_configure(struct intel_dsb *dsb, struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, int su_lines); void intel_vdsc_state_dump(struct drm_printer *p, int indent, const struct intel_crtc_state *crtc_state); int intel_vdsc_min_cdclk(const struct intel_crtc_state *crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h index 2d478a84b07c..2b2e3c1b8138 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h +++ b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h @@ -196,6 +196,18 @@ #define DSC_PPS18_NSL_BPG_OFFSET(offset) REG_FIELD_PREP(DSC_PPS18_NSL_BPG_OFFSET_MASK, offset) #define DSC_PPS18_SL_OFFSET_ADJ(offset) REG_FIELD_PREP(DSC_PPS18_SL_OFFSET_ADJ_MASK, offset) +#define _LNL_DSC0_SU_PARAMETER_SET_0_PA 0x78064 +#define _LNL_DSC1_SU_PARAMETER_SET_0_PA 0x78164 +#define _LNL_DSC0_SU_PARAMETER_SET_0_PB 0x78264 +#define _LNL_DSC1_SU_PARAMETER_SET_0_PB 0x78364 +#define LNL_DSC0_SU_PARAMETER_SET_0(pipe) _MMIO_PIPE((pipe), _LNL_DSC0_SU_PARAMETER_SET_0_PA, _LNL_DSC0_SU_PARAMETER_SET_0_PB) +#define LNL_DSC1_SU_PARAMETER_SET_0(pipe) _MMIO_PIPE((pipe), _LNL_DSC1_SU_PARAMETER_SET_0_PA, _LNL_DSC1_SU_PARAMETER_SET_0_PB) + +#define DSC_SUPS0_SU_SLICE_ROW_PER_FRAME_MASK REG_GENMASK(31, 20) +#define DSC_SUPS0_SU_SLICE_ROW_PER_FRAME(rows) REG_FIELD_PREP(DSC_SUPS0_SU_SLICE_ROW_PER_FRAME_MASK, (rows)) +#define DSC_SUPS0_SU_PIC_HEIGHT_MASK REG_GENMASK(15, 0) +#define DSC_SUPS0_SU_PIC_HEIGHT(h) REG_FIELD_PREP(DSC_SUPS0_SU_PIC_HEIGHT_MASK, (h)) + /* Icelake Rate Control Buffer Threshold Registers */ #define DSCA_RC_BUF_THRESH_0 _MMIO(0x6B230) #define DSCA_RC_BUF_THRESH_0_UDW _MMIO(0x6B230 + 4) diff --git a/drivers/gpu/drm/i915/display/intel_vrr.c b/drivers/gpu/drm/i915/display/intel_vrr.c index db74744ddb31..bea005752327 100644 --- a/drivers/gpu/drm/i915/display/intel_vrr.c +++ b/drivers/gpu/drm/i915/display/intel_vrr.c @@ -598,6 +598,18 @@ void intel_vrr_set_transcoder_timings(const struct intel_crtc_state *crtc_state) return; /* + * Bspec says: + * "(note: VRR needs to be programmed after + * TRANS_DDI_FUNC_CTL and before TRANS_CONF)." + * + * In practice it turns out that ICL can hang if + * TRANS_VRR_VMAX/FLIPLINE are written before + * enabling TRANS_DDI_FUNC_CTL. + */ + drm_WARN_ON(display->drm, + !(intel_de_read(display, TRANS_DDI_FUNC_CTL(display, cpu_transcoder)) & TRANS_DDI_FUNC_ENABLE)); + + /* * This bit seems to have two meanings depending on the platform: * TGL: generate VRR "safe window" for DSB vblank waits * ADL/DG2: make TRANS_SET_CONTEXT_LATENCY effective with VRR @@ -939,6 +951,8 @@ void intel_vrr_transcoder_enable(const struct intel_crtc_state *crtc_state) { struct intel_display *display = to_intel_display(crtc_state); + intel_vrr_set_transcoder_timings(crtc_state); + if (!intel_vrr_possible(crtc_state)) return; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index c6c64ba29bc4..720a9ad39aa2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -153,8 +153,12 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, } } while (1); - nr_pages = min_t(unsigned long, - folio_nr_pages(folio), page_count - i); + nr_pages = min_array(((unsigned long[]) { + folio_nr_pages(folio), + page_count - i, + max_segment / PAGE_SIZE, + }), 3); + if (!i || sg->length >= max_segment || folio_pfn(folio) != next_pfn) { @@ -164,7 +168,9 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, st->nents++; sg_set_folio(sg, folio, nr_pages * PAGE_SIZE, 0); } else { - /* XXX: could overflow? */ + nr_pages = min_t(unsigned long, nr_pages, + (max_segment - sg->length) / PAGE_SIZE); + sg->length += nr_pages * PAGE_SIZE; } next_pfn = folio_pfn(folio) + nr_pages; diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c index d77b4774d414..e2225c5ba647 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c @@ -78,7 +78,7 @@ static void a2xx_gpummu_destroy(struct msm_mmu *mmu) { struct a2xx_gpummu *gpummu = to_a2xx_gpummu(mmu); - dma_free_attrs(mmu->dev, TABLE_SIZE, gpummu->table, gpummu->pt_base, + dma_free_attrs(mmu->dev, TABLE_SIZE + 32, gpummu->table, gpummu->pt_base, DMA_ATTR_FORCE_CONTIGUOUS); kfree(gpummu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c index 550a53a7865e..38561f26837e 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c @@ -1759,7 +1759,7 @@ static const u32 x285_protect_regs[] = { A6XX_PROTECT_NORDWR(0x27c06, 0x0000), }; -DECLARE_ADRENO_PROTECT(x285_protect, 64); +DECLARE_ADRENO_PROTECT(x285_protect, 15); static const struct adreno_reglist_pipe a840_nonctxt_regs[] = { { REG_A8XX_CP_SMMU_STREAM_ID_LPAC, 0x00000101, BIT(PIPE_NONE) }, @@ -1966,5 +1966,4 @@ static inline __always_unused void __build_asserts(void) BUILD_BUG_ON(a660_protect.count > a660_protect.count_max); BUILD_BUG_ON(a690_protect.count > a690_protect.count_max); BUILD_BUG_ON(a730_protect.count > a730_protect.count_max); - BUILD_BUG_ON(a840_protect.count > a840_protect.count_max); } diff --git a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c index 5a320f5bde41..b1887e0cf698 100644 --- a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c @@ -310,11 +310,21 @@ static void a8xx_set_ubwc_config(struct msm_gpu *gpu) hbb = cfg->highest_bank_bit - 13; hbb_hi = hbb >> 2; hbb_lo = hbb & 3; - a8xx_write_pipe(gpu, PIPE_BV, REG_A8XX_GRAS_NC_MODE_CNTL, hbb << 5); - a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_GRAS_NC_MODE_CNTL, hbb << 5); + + a8xx_write_pipe(gpu, PIPE_BV, REG_A8XX_GRAS_NC_MODE_CNTL, + hbb << 5 | + level3_swizzling_dis << 4 | + level2_swizzling_dis << 3); + + a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_GRAS_NC_MODE_CNTL, + hbb << 5 | + level3_swizzling_dis << 4 | + level2_swizzling_dis << 3); a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_RB_CCU_NC_MODE_CNTL, yuvnotcomptofc << 6 | + level3_swizzling_dis << 5 | + level2_swizzling_dis << 4 | hbb_hi << 3 | hbb_lo << 1); diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 554d746f115b..4edfe80c5be7 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -302,6 +302,7 @@ static const struct of_device_id dt_match[] = { { .compatible = "qcom,kgsl-3d0" }, {} }; +MODULE_DEVICE_TABLE(of, dt_match); static int adreno_runtime_resume(struct device *dev) { diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h index 303d33dc7783..9f2bceca1789 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h @@ -133,7 +133,7 @@ static const struct dpu_sspp_cfg sc8280xp_sspp[] = { static const struct dpu_lm_cfg sc8280xp_lm[] = { { .name = "lm_0", .id = LM_0, - .base = 0x44000, .len = 0x320, + .base = 0x44000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_1, @@ -141,7 +141,7 @@ static const struct dpu_lm_cfg sc8280xp_lm[] = { .dspp = DSPP_0, }, { .name = "lm_1", .id = LM_1, - .base = 0x45000, .len = 0x320, + .base = 0x45000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_0, @@ -149,7 +149,7 @@ static const struct dpu_lm_cfg sc8280xp_lm[] = { .dspp = DSPP_1, }, { .name = "lm_2", .id = LM_2, - .base = 0x46000, .len = 0x320, + .base = 0x46000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, @@ -157,7 +157,7 @@ static const struct dpu_lm_cfg sc8280xp_lm[] = { .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, - .base = 0x47000, .len = 0x320, + .base = 0x47000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, @@ -165,14 +165,14 @@ static const struct dpu_lm_cfg sc8280xp_lm[] = { .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, - .base = 0x48000, .len = 0x320, + .base = 0x48000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_5, .pingpong = PINGPONG_4, }, { .name = "lm_5", .id = LM_5, - .base = 0x49000, .len = 0x320, + .base = 0x49000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_4, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h index b09a6af4c474..04b22167f93d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h @@ -134,7 +134,7 @@ static const struct dpu_sspp_cfg sm8450_sspp[] = { static const struct dpu_lm_cfg sm8450_lm[] = { { .name = "lm_0", .id = LM_0, - .base = 0x44000, .len = 0x320, + .base = 0x44000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_1, @@ -142,7 +142,7 @@ static const struct dpu_lm_cfg sm8450_lm[] = { .dspp = DSPP_0, }, { .name = "lm_1", .id = LM_1, - .base = 0x45000, .len = 0x320, + .base = 0x45000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_0, @@ -150,7 +150,7 @@ static const struct dpu_lm_cfg sm8450_lm[] = { .dspp = DSPP_1, }, { .name = "lm_2", .id = LM_2, - .base = 0x46000, .len = 0x320, + .base = 0x46000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, @@ -158,7 +158,7 @@ static const struct dpu_lm_cfg sm8450_lm[] = { .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, - .base = 0x47000, .len = 0x320, + .base = 0x47000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, @@ -166,14 +166,14 @@ static const struct dpu_lm_cfg sm8450_lm[] = { .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, - .base = 0x48000, .len = 0x320, + .base = 0x48000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_5, .pingpong = PINGPONG_4, }, { .name = "lm_5", .id = LM_5, - .base = 0x49000, .len = 0x320, + .base = 0x49000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_4, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h index 0f7b4a224e4c..42cf3bd5a12a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h @@ -366,8 +366,8 @@ static const struct dpu_intf_cfg sa8775p_intf[] = { .type = INTF_NONE, .controller_id = MSM_DP_CONTROLLER_0, /* pair with intf_0 for DP MST */ .prog_fetch_lines_worst_case = 24, - .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17), - .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16), + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17), }, { .name = "intf_7", .id = INTF_7, .base = 0x3b000, .len = 0x280, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h index 465b6460f875..4c7eb55d474c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h @@ -131,7 +131,7 @@ static const struct dpu_sspp_cfg sm8550_sspp[] = { static const struct dpu_lm_cfg sm8550_lm[] = { { .name = "lm_0", .id = LM_0, - .base = 0x44000, .len = 0x320, + .base = 0x44000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_1, @@ -139,7 +139,7 @@ static const struct dpu_lm_cfg sm8550_lm[] = { .dspp = DSPP_0, }, { .name = "lm_1", .id = LM_1, - .base = 0x45000, .len = 0x320, + .base = 0x45000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_0, @@ -147,7 +147,7 @@ static const struct dpu_lm_cfg sm8550_lm[] = { .dspp = DSPP_1, }, { .name = "lm_2", .id = LM_2, - .base = 0x46000, .len = 0x320, + .base = 0x46000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, @@ -155,7 +155,7 @@ static const struct dpu_lm_cfg sm8550_lm[] = { .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, - .base = 0x47000, .len = 0x320, + .base = 0x47000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, @@ -163,14 +163,14 @@ static const struct dpu_lm_cfg sm8550_lm[] = { .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, - .base = 0x48000, .len = 0x320, + .base = 0x48000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_5, .pingpong = PINGPONG_4, }, { .name = "lm_5", .id = LM_5, - .base = 0x49000, .len = 0x320, + .base = 0x49000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_4, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h index 6caa7d40f368..dec83ea8167d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h @@ -131,7 +131,7 @@ static const struct dpu_sspp_cfg sar2130p_sspp[] = { static const struct dpu_lm_cfg sar2130p_lm[] = { { .name = "lm_0", .id = LM_0, - .base = 0x44000, .len = 0x320, + .base = 0x44000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_1, @@ -139,7 +139,7 @@ static const struct dpu_lm_cfg sar2130p_lm[] = { .dspp = DSPP_0, }, { .name = "lm_1", .id = LM_1, - .base = 0x45000, .len = 0x320, + .base = 0x45000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_0, @@ -147,7 +147,7 @@ static const struct dpu_lm_cfg sar2130p_lm[] = { .dspp = DSPP_1, }, { .name = "lm_2", .id = LM_2, - .base = 0x46000, .len = 0x320, + .base = 0x46000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, @@ -155,7 +155,7 @@ static const struct dpu_lm_cfg sar2130p_lm[] = { .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, - .base = 0x47000, .len = 0x320, + .base = 0x47000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, @@ -163,14 +163,14 @@ static const struct dpu_lm_cfg sar2130p_lm[] = { .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, - .base = 0x48000, .len = 0x320, + .base = 0x48000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_5, .pingpong = PINGPONG_4, }, { .name = "lm_5", .id = LM_5, - .base = 0x49000, .len = 0x320, + .base = 0x49000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_4, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h index 7243eebb85f3..52ff4baa668a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h @@ -130,7 +130,7 @@ static const struct dpu_sspp_cfg x1e80100_sspp[] = { static const struct dpu_lm_cfg x1e80100_lm[] = { { .name = "lm_0", .id = LM_0, - .base = 0x44000, .len = 0x320, + .base = 0x44000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_1, @@ -138,7 +138,7 @@ static const struct dpu_lm_cfg x1e80100_lm[] = { .dspp = DSPP_0, }, { .name = "lm_1", .id = LM_1, - .base = 0x45000, .len = 0x320, + .base = 0x45000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_0, @@ -146,7 +146,7 @@ static const struct dpu_lm_cfg x1e80100_lm[] = { .dspp = DSPP_1, }, { .name = "lm_2", .id = LM_2, - .base = 0x46000, .len = 0x320, + .base = 0x46000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_3, @@ -154,7 +154,7 @@ static const struct dpu_lm_cfg x1e80100_lm[] = { .dspp = DSPP_2, }, { .name = "lm_3", .id = LM_3, - .base = 0x47000, .len = 0x320, + .base = 0x47000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_2, @@ -162,14 +162,14 @@ static const struct dpu_lm_cfg x1e80100_lm[] = { .dspp = DSPP_3, }, { .name = "lm_4", .id = LM_4, - .base = 0x48000, .len = 0x320, + .base = 0x48000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_5, .pingpong = PINGPONG_4, }, { .name = "lm_5", .id = LM_5, - .base = 0x49000, .len = 0x320, + .base = 0x49000, .len = 0x400, .features = MIXER_MSM8998_MASK, .sblk = &sdm845_lm_sblk, .lm_pair = LM_4, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c index 188ee0af2c90..23dcbe1ce1b8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c @@ -89,7 +89,7 @@ static void dpu_setup_dspp_gc(struct dpu_hw_dspp *ctx, base = ctx->cap->sblk->gc.base; if (!base) { - DRM_ERROR("invalid ctx %pK gc base\n", ctx); + DRM_ERROR("invalid ctx %p gc base\n", ctx); return; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c index e65f1fc026fd..f8f96ad971d7 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c @@ -156,11 +156,13 @@ static void dpu_hw_sspp_setup_pe_config_v13(struct dpu_hw_sspp *ctx, u8 color; u32 lr_pe[4], tb_pe[4]; const u32 bytemask = 0xff; - u32 offset = ctx->cap->sblk->sspp_rec0_blk.base; + u32 offset; if (!ctx || !pe_ext) return; + offset = ctx->cap->sblk->sspp_rec0_blk.base; + c = &ctx->hw; /* program SW pixel extension override for all pipes*/ for (color = 0; color < DPU_MAX_PLANES; color++) { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c index 451a4fcf3e65..7e77d88f8959 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c @@ -350,26 +350,28 @@ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, return true; } -static bool dpu_rm_find_lms(struct dpu_rm *rm, - struct dpu_global_state *global_state, - uint32_t crtc_id, bool skip_dspp, - struct msm_display_topology *topology, - int *lm_idx, int *pp_idx, int *dspp_idx) +static int _dpu_rm_reserve_lms(struct dpu_rm *rm, + struct dpu_global_state *global_state, + uint32_t crtc_id, + struct msm_display_topology *topology) { + int lm_idx[MAX_BLOCKS]; + int pp_idx[MAX_BLOCKS]; + int dspp_idx[MAX_BLOCKS] = {0}; int i, lm_count = 0; + if (!topology->num_lm) { + DPU_ERROR("zero LMs in topology\n"); + return -EINVAL; + } + /* Find a primary mixer */ for (i = 0; i < ARRAY_SIZE(rm->mixer_blks) && lm_count < topology->num_lm; i++) { if (!rm->mixer_blks[i]) continue; - if (skip_dspp && to_dpu_hw_mixer(rm->mixer_blks[i])->cap->dspp) { - DPU_DEBUG("Skipping LM_%d, skipping LMs with DSPPs\n", i); - continue; - } - /* * Reset lm_count to an even index. This will drop the previous * primary mixer if failed to find its peer. @@ -408,38 +410,12 @@ static bool dpu_rm_find_lms(struct dpu_rm *rm, } } - return lm_count == topology->num_lm; -} - -static int _dpu_rm_reserve_lms(struct dpu_rm *rm, - struct dpu_global_state *global_state, - uint32_t crtc_id, - struct msm_display_topology *topology) - -{ - int lm_idx[MAX_BLOCKS]; - int pp_idx[MAX_BLOCKS]; - int dspp_idx[MAX_BLOCKS] = {0}; - int i; - bool found; - - if (!topology->num_lm) { - DPU_ERROR("zero LMs in topology\n"); - return -EINVAL; - } - - /* Try using non-DSPP LM blocks first */ - found = dpu_rm_find_lms(rm, global_state, crtc_id, !topology->num_dspp, - topology, lm_idx, pp_idx, dspp_idx); - if (!found && !topology->num_dspp) - found = dpu_rm_find_lms(rm, global_state, crtc_id, false, - topology, lm_idx, pp_idx, dspp_idx); - if (!found) { + if (lm_count != topology->num_lm) { DPU_DEBUG("unable to find appropriate mixers\n"); return -ENAVAIL; } - for (i = 0; i < topology->num_lm; i++) { + for (i = 0; i < lm_count; i++) { global_state->mixer_to_crtc_id[lm_idx[i]] = crtc_id; global_state->pingpong_to_crtc_id[pp_idx[i]] = crtc_id; global_state->dspp_to_crtc_id[dspp_idx[i]] = diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index e0de545d4077..db6da99375a1 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -584,13 +584,30 @@ void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host) * FIXME: Reconsider this if/when CMD mode handling is rewritten to use * transfer time and data overhead as a starting point of the calculations. */ -static unsigned long dsi_adjust_pclk_for_compression(const struct drm_display_mode *mode, - const struct drm_dsc_config *dsc) +static unsigned long +dsi_adjust_pclk_for_compression(const struct drm_display_mode *mode, + const struct drm_dsc_config *dsc, + bool is_bonded_dsi) { - int new_hdisplay = DIV_ROUND_UP(mode->hdisplay * drm_dsc_get_bpp_int(dsc), - dsc->bits_per_component * 3); + int hdisplay, new_hdisplay, new_htotal; - int new_htotal = mode->htotal - mode->hdisplay + new_hdisplay; + /* + * For bonded DSI, split hdisplay across two links and round up each + * half separately, passing the full hdisplay would only round up once. + * This also aligns with the hdisplay we program later in + * dsi_timing_setup() + */ + hdisplay = mode->hdisplay; + if (is_bonded_dsi) + hdisplay /= 2; + + new_hdisplay = DIV_ROUND_UP(hdisplay * drm_dsc_get_bpp_int(dsc), + dsc->bits_per_component * 3); + + if (is_bonded_dsi) + new_hdisplay *= 2; + + new_htotal = mode->htotal - mode->hdisplay + new_hdisplay; return mult_frac(mode->clock * 1000u, new_htotal, mode->htotal); } @@ -603,7 +620,7 @@ static unsigned long dsi_get_pclk_rate(const struct drm_display_mode *mode, pclk_rate = mode->clock * 1000u; if (dsc) - pclk_rate = dsi_adjust_pclk_for_compression(mode, dsc); + pclk_rate = dsi_adjust_pclk_for_compression(mode, dsc, is_bonded_dsi); /* * For bonded DSI mode, the current DRM mode has the complete width of the @@ -993,7 +1010,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) if (msm_host->dsc) { struct drm_dsc_config *dsc = msm_host->dsc; - u32 bytes_per_pclk; + u32 bits_per_pclk; /* update dsc params with timing params */ if (!dsc || !mode->hdisplay || !mode->vdisplay) { @@ -1015,7 +1032,9 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) /* * DPU sends 3 bytes per pclk cycle to DSI. If widebus is - * enabled, bus width is extended to 6 bytes. + * enabled, MDP always sends out 48-bit compressed data per + * pclk and on average, DSI consumes an amount of compressed + * data equivalent to the uncompressed pixel depth per pclk. * * Calculate the number of pclks needed to transmit one line of * the compressed data. @@ -1027,12 +1046,12 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) * unused anyway. */ h_total -= hdisplay; - if (wide_bus_enabled && !(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO)) - bytes_per_pclk = 6; + if (wide_bus_enabled) + bits_per_pclk = mipi_dsi_pixel_format_to_bpp(msm_host->format); else - bytes_per_pclk = 3; + bits_per_pclk = 24; - hdisplay = DIV_ROUND_UP(msm_dsc_get_bytes_per_line(msm_host->dsc), bytes_per_pclk); + hdisplay = DIV_ROUND_UP(msm_dsc_get_bytes_per_line(msm_host->dsc) * 8, bits_per_pclk); h_total += hdisplay; ha_end = ha_start + hdisplay; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c index 8cb0db3a9880..01182442dfd6 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -51,8 +51,8 @@ #define DSI_PHY_7NM_QUIRK_V4_3 BIT(3) /* Hardware is V5.2 */ #define DSI_PHY_7NM_QUIRK_V5_2 BIT(4) -/* Hardware is V7.0 */ -#define DSI_PHY_7NM_QUIRK_V7_0 BIT(5) +/* Hardware is V7.2 */ +#define DSI_PHY_7NM_QUIRK_V7_2 BIT(5) struct dsi_pll_config { bool enable_ssc; @@ -143,7 +143,7 @@ static void dsi_pll_calc_dec_frac(struct dsi_pll_7nm *pll, struct dsi_pll_config if (pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_PRE_V4_1) { config->pll_clock_inverters = 0x28; - } else if ((pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) { + } else if ((pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) { if (pll_freq < 163000000ULL) config->pll_clock_inverters = 0xa0; else if (pll_freq < 175000000ULL) @@ -284,7 +284,7 @@ static void dsi_pll_config_hzindep_reg(struct dsi_pll_7nm *pll) } if ((pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2) || - (pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) { + (pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) { if (pll->vco_current_rate < 1557000000ULL) vco_config_1 = 0x08; else @@ -699,7 +699,7 @@ static int dsi_7nm_set_usecase(struct msm_dsi_phy *phy) case MSM_DSI_PHY_MASTER: pll_7nm->slave = pll_7nm_list[(pll_7nm->phy->id + 1) % DSI_MAX]; /* v7.0: Enable ATB_EN0 and alternate clock output to external phy */ - if (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0) + if (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2) writel(0x07, base + REG_DSI_7nm_PHY_CMN_CTRL_5); break; case MSM_DSI_PHY_SLAVE: @@ -987,7 +987,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, /* Request for REFGEN READY */ if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_3) || (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2) || - (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) { + (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) { writel(0x1, phy->base + REG_DSI_7nm_PHY_CMN_GLBL_DIGTOP_SPARE10); udelay(500); } @@ -1021,7 +1021,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, lane_ctrl0 = 0x1f; } - if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) { + if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) { if (phy->cphy_mode) { /* TODO: different for second phy */ vreg_ctrl_0 = 0x57; @@ -1097,7 +1097,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, /* program CMN_CTRL_4 for minor_ver 2 chipsets*/ if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2) || - (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0) || + (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2) || (readl(base + REG_DSI_7nm_PHY_CMN_REVISION_ID0) & (0xf0)) == 0x20) writel(0x04, base + REG_DSI_7nm_PHY_CMN_CTRL_4); @@ -1213,7 +1213,7 @@ static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy) /* Turn off REFGEN Vote */ if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_3) || (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2) || - (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) { + (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) { writel(0x0, base + REG_DSI_7nm_PHY_CMN_GLBL_DIGTOP_SPARE10); wmb(); /* Delay to ensure HW removes vote before PHY shut down */ @@ -1502,7 +1502,7 @@ const struct msm_dsi_phy_cfg dsi_phy_3nm_8750_cfgs = { #endif .io_start = { 0xae95000, 0xae97000 }, .num_dsi_phy = 2, - .quirks = DSI_PHY_7NM_QUIRK_V7_0, + .quirks = DSI_PHY_7NM_QUIRK_V7_2, }; const struct msm_dsi_phy_cfg dsi_phy_3nm_kaanapali_cfgs = { @@ -1525,5 +1525,5 @@ const struct msm_dsi_phy_cfg dsi_phy_3nm_kaanapali_cfgs = { #endif .io_start = { 0x9ac1000, 0x9ac4000 }, .num_dsi_phy = 2, - .quirks = DSI_PHY_7NM_QUIRK_V7_0, + .quirks = DSI_PHY_7NM_QUIRK_V7_2, }; diff --git a/drivers/gpu/drm/sitronix/st7586.c b/drivers/gpu/drm/sitronix/st7586.c index b57ebf37a664..16b6b4e368af 100644 --- a/drivers/gpu/drm/sitronix/st7586.c +++ b/drivers/gpu/drm/sitronix/st7586.c @@ -347,6 +347,12 @@ static int st7586_probe(struct spi_device *spi) if (ret) return ret; + /* + * Override value set by mipi_dbi_spi_init(). This driver is a bit + * non-standard, so best to set it explicitly here. + */ + dbi->write_memory_bpw = 8; + /* Cannot read from this controller via SPI */ dbi->read_commands = NULL; @@ -356,15 +362,6 @@ static int st7586_probe(struct spi_device *spi) if (ret) return ret; - /* - * we are using 8-bit data, so we are not actually swapping anything, - * but setting mipi->swap_bytes makes mipi_dbi_typec3_command() do the - * right thing and not use 16-bit transfers (which results in swapped - * bytes on little-endian systems and causes out of order data to be - * sent to the display). - */ - dbi->swap_bytes = true; - drm_mode_config_reset(drm); ret = drm_dev_register(drm, 0); diff --git a/drivers/gpu/nova-core/gsp.rs b/drivers/gpu/nova-core/gsp.rs index 174feaca0a6b..c69adaa92bbe 100644 --- a/drivers/gpu/nova-core/gsp.rs +++ b/drivers/gpu/nova-core/gsp.rs @@ -47,16 +47,12 @@ struct PteArray<const NUM_ENTRIES: usize>([u64; NUM_ENTRIES]); unsafe impl<const NUM_ENTRIES: usize> AsBytes for PteArray<NUM_ENTRIES> {} impl<const NUM_PAGES: usize> PteArray<NUM_PAGES> { - /// Creates a new page table array mapping `NUM_PAGES` GSP pages starting at address `start`. - fn new(start: DmaAddress) -> Result<Self> { - let mut ptes = [0u64; NUM_PAGES]; - for (i, pte) in ptes.iter_mut().enumerate() { - *pte = start - .checked_add(num::usize_as_u64(i) << GSP_PAGE_SHIFT) - .ok_or(EOVERFLOW)?; - } - - Ok(Self(ptes)) + /// Returns the page table entry for `index`, for a mapping starting at `start`. + // TODO: Replace with `IoView` projection once available. + fn entry(start: DmaAddress, index: usize) -> Result<u64> { + start + .checked_add(num::usize_as_u64(index) << GSP_PAGE_SHIFT) + .ok_or(EOVERFLOW) } } @@ -86,16 +82,22 @@ impl LogBuffer { NUM_PAGES * GSP_PAGE_SIZE, GFP_KERNEL | __GFP_ZERO, )?); - let ptes = PteArray::<NUM_PAGES>::new(obj.0.dma_handle())?; + + let start_addr = obj.0.dma_handle(); // SAFETY: `obj` has just been created and we are its sole user. - unsafe { - // Copy the self-mapping PTE at the expected location. + let pte_region = unsafe { obj.0 - .as_slice_mut(size_of::<u64>(), size_of_val(&ptes))? - .copy_from_slice(ptes.as_bytes()) + .as_slice_mut(size_of::<u64>(), NUM_PAGES * size_of::<u64>())? }; + // Write values one by one to avoid an on-stack instance of `PteArray`. + for (i, chunk) in pte_region.chunks_exact_mut(size_of::<u64>()).enumerate() { + let pte_value = PteArray::<0>::entry(start_addr, i)?; + + chunk.copy_from_slice(&pte_value.to_ne_bytes()); + } + Ok(obj) } } @@ -143,14 +145,14 @@ impl Gsp { // _kgspInitLibosLoggingStructures (allocates memory for buffers) // kgspSetupLibosInitArgs_IMPL (creates pLibosInitArgs[] array) dma_write!( - libos[0] = LibosMemoryRegionInitArgument::new("LOGINIT", &loginit.0) - )?; + libos, [0]?, LibosMemoryRegionInitArgument::new("LOGINIT", &loginit.0) + ); dma_write!( - libos[1] = LibosMemoryRegionInitArgument::new("LOGINTR", &logintr.0) - )?; - dma_write!(libos[2] = LibosMemoryRegionInitArgument::new("LOGRM", &logrm.0))?; - dma_write!(rmargs[0].inner = fw::GspArgumentsCached::new(cmdq))?; - dma_write!(libos[3] = LibosMemoryRegionInitArgument::new("RMARGS", rmargs))?; + libos, [1]?, LibosMemoryRegionInitArgument::new("LOGINTR", &logintr.0) + ); + dma_write!(libos, [2]?, LibosMemoryRegionInitArgument::new("LOGRM", &logrm.0)); + dma_write!(rmargs, [0]?.inner, fw::GspArgumentsCached::new(cmdq)); + dma_write!(libos, [3]?, LibosMemoryRegionInitArgument::new("RMARGS", rmargs)); }, })) }) diff --git a/drivers/gpu/nova-core/gsp/boot.rs b/drivers/gpu/nova-core/gsp/boot.rs index be427fe26a58..94833f7996e8 100644 --- a/drivers/gpu/nova-core/gsp/boot.rs +++ b/drivers/gpu/nova-core/gsp/boot.rs @@ -157,7 +157,7 @@ impl super::Gsp { let wpr_meta = CoherentAllocation::<GspFwWprMeta>::alloc_coherent(dev, 1, GFP_KERNEL | __GFP_ZERO)?; - dma_write!(wpr_meta[0] = GspFwWprMeta::new(&gsp_fw, &fb_layout))?; + dma_write!(wpr_meta, [0]?, GspFwWprMeta::new(&gsp_fw, &fb_layout)); self.cmdq .send_command(bar, commands::SetSystemInfo::new(pdev))?; diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs index 46819a82a51a..03a4f3599849 100644 --- a/drivers/gpu/nova-core/gsp/cmdq.rs +++ b/drivers/gpu/nova-core/gsp/cmdq.rs @@ -2,11 +2,7 @@ use core::{ cmp, - mem, - sync::atomic::{ - fence, - Ordering, // - }, // + mem, // }; use kernel::{ @@ -146,30 +142,36 @@ static_assert!(align_of::<MsgqData>() == GSP_PAGE_SIZE); #[repr(C)] // There is no struct defined for this in the open-gpu-kernel-source headers. // Instead it is defined by code in `GspMsgQueuesInit()`. -struct Msgq { +// TODO: Revert to private once `IoView` projections replace the `gsp_mem` module. +pub(super) struct Msgq { /// Header for sending messages, including the write pointer. - tx: MsgqTxHeader, + pub(super) tx: MsgqTxHeader, /// Header for receiving messages, including the read pointer. - rx: MsgqRxHeader, + pub(super) rx: MsgqRxHeader, /// The message queue proper. msgq: MsgqData, } /// Structure shared between the driver and the GSP and containing the command and message queues. #[repr(C)] -struct GspMem { +// TODO: Revert to private once `IoView` projections replace the `gsp_mem` module. +pub(super) struct GspMem { /// Self-mapping page table entries. - ptes: PteArray<{ GSP_PAGE_SIZE / size_of::<u64>() }>, + ptes: PteArray<{ Self::PTE_ARRAY_SIZE }>, /// CPU queue: the driver writes commands here, and the GSP reads them. It also contains the /// write and read pointers that the CPU updates. /// /// This member is read-only for the GSP. - cpuq: Msgq, + pub(super) cpuq: Msgq, /// GSP queue: the GSP writes messages here, and the driver reads them. It also contains the /// write and read pointers that the GSP updates. /// /// This member is read-only for the driver. - gspq: Msgq, + pub(super) gspq: Msgq, +} + +impl GspMem { + const PTE_ARRAY_SIZE: usize = GSP_PAGE_SIZE / size_of::<u64>(); } // SAFETY: These structs don't meet the no-padding requirements of AsBytes but @@ -201,9 +203,19 @@ impl DmaGspMem { let gsp_mem = CoherentAllocation::<GspMem>::alloc_coherent(dev, 1, GFP_KERNEL | __GFP_ZERO)?; - dma_write!(gsp_mem[0].ptes = PteArray::new(gsp_mem.dma_handle())?)?; - dma_write!(gsp_mem[0].cpuq.tx = MsgqTxHeader::new(MSGQ_SIZE, RX_HDR_OFF, MSGQ_NUM_PAGES))?; - dma_write!(gsp_mem[0].cpuq.rx = MsgqRxHeader::new())?; + + let start = gsp_mem.dma_handle(); + // Write values one by one to avoid an on-stack instance of `PteArray`. + for i in 0..GspMem::PTE_ARRAY_SIZE { + dma_write!(gsp_mem, [0]?.ptes.0[i], PteArray::<0>::entry(start, i)?); + } + + dma_write!( + gsp_mem, + [0]?.cpuq.tx, + MsgqTxHeader::new(MSGQ_SIZE, RX_HDR_OFF, MSGQ_NUM_PAGES) + ); + dma_write!(gsp_mem, [0]?.cpuq.rx, MsgqRxHeader::new()); Ok(Self(gsp_mem)) } @@ -317,12 +329,7 @@ impl DmaGspMem { // // - The returned value is between `0` and `MSGQ_NUM_PAGES`. fn gsp_write_ptr(&self) -> u32 { - let gsp_mem = self.0.start_ptr(); - - // SAFETY: - // - The 'CoherentAllocation' contains at least one object. - // - By the invariants of `CoherentAllocation` the pointer is valid. - (unsafe { (*gsp_mem).gspq.tx.write_ptr() } % MSGQ_NUM_PAGES) + super::fw::gsp_mem::gsp_write_ptr(&self.0) } // Returns the index of the memory page the GSP will read the next command from. @@ -331,12 +338,7 @@ impl DmaGspMem { // // - The returned value is between `0` and `MSGQ_NUM_PAGES`. fn gsp_read_ptr(&self) -> u32 { - let gsp_mem = self.0.start_ptr(); - - // SAFETY: - // - The 'CoherentAllocation' contains at least one object. - // - By the invariants of `CoherentAllocation` the pointer is valid. - (unsafe { (*gsp_mem).gspq.rx.read_ptr() } % MSGQ_NUM_PAGES) + super::fw::gsp_mem::gsp_read_ptr(&self.0) } // Returns the index of the memory page the CPU can read the next message from. @@ -345,27 +347,12 @@ impl DmaGspMem { // // - The returned value is between `0` and `MSGQ_NUM_PAGES`. fn cpu_read_ptr(&self) -> u32 { - let gsp_mem = self.0.start_ptr(); - - // SAFETY: - // - The ['CoherentAllocation'] contains at least one object. - // - By the invariants of CoherentAllocation the pointer is valid. - (unsafe { (*gsp_mem).cpuq.rx.read_ptr() } % MSGQ_NUM_PAGES) + super::fw::gsp_mem::cpu_read_ptr(&self.0) } // Informs the GSP that it can send `elem_count` new pages into the message queue. fn advance_cpu_read_ptr(&mut self, elem_count: u32) { - let rptr = self.cpu_read_ptr().wrapping_add(elem_count) % MSGQ_NUM_PAGES; - - // Ensure read pointer is properly ordered. - fence(Ordering::SeqCst); - - let gsp_mem = self.0.start_ptr_mut(); - - // SAFETY: - // - The 'CoherentAllocation' contains at least one object. - // - By the invariants of `CoherentAllocation` the pointer is valid. - unsafe { (*gsp_mem).cpuq.rx.set_read_ptr(rptr) }; + super::fw::gsp_mem::advance_cpu_read_ptr(&self.0, elem_count) } // Returns the index of the memory page the CPU can write the next command to. @@ -374,26 +361,12 @@ impl DmaGspMem { // // - The returned value is between `0` and `MSGQ_NUM_PAGES`. fn cpu_write_ptr(&self) -> u32 { - let gsp_mem = self.0.start_ptr(); - - // SAFETY: - // - The 'CoherentAllocation' contains at least one object. - // - By the invariants of `CoherentAllocation` the pointer is valid. - (unsafe { (*gsp_mem).cpuq.tx.write_ptr() } % MSGQ_NUM_PAGES) + super::fw::gsp_mem::cpu_write_ptr(&self.0) } // Informs the GSP that it can process `elem_count` new pages from the command queue. fn advance_cpu_write_ptr(&mut self, elem_count: u32) { - let wptr = self.cpu_write_ptr().wrapping_add(elem_count) & MSGQ_NUM_PAGES; - let gsp_mem = self.0.start_ptr_mut(); - - // SAFETY: - // - The 'CoherentAllocation' contains at least one object. - // - By the invariants of `CoherentAllocation` the pointer is valid. - unsafe { (*gsp_mem).cpuq.tx.set_write_ptr(wptr) }; - - // Ensure all command data is visible before triggering the GSP read. - fence(Ordering::SeqCst); + super::fw::gsp_mem::advance_cpu_write_ptr(&self.0, elem_count) } } diff --git a/drivers/gpu/nova-core/gsp/fw.rs b/drivers/gpu/nova-core/gsp/fw.rs index 83ff91614e36..040b30ec3089 100644 --- a/drivers/gpu/nova-core/gsp/fw.rs +++ b/drivers/gpu/nova-core/gsp/fw.rs @@ -40,6 +40,75 @@ use crate::{ }, }; +// TODO: Replace with `IoView` projections once available; the `unwrap()` calls go away once we +// switch to the new `dma::Coherent` API. +pub(super) mod gsp_mem { + use core::sync::atomic::{ + fence, + Ordering, // + }; + + use kernel::{ + dma::CoherentAllocation, + dma_read, + dma_write, + prelude::*, // + }; + + use crate::gsp::cmdq::{ + GspMem, + MSGQ_NUM_PAGES, // + }; + + pub(in crate::gsp) fn gsp_write_ptr(qs: &CoherentAllocation<GspMem>) -> u32 { + // PANIC: A `dma::CoherentAllocation` always contains at least one element. + || -> Result<u32> { Ok(dma_read!(qs, [0]?.gspq.tx.0.writePtr) % MSGQ_NUM_PAGES) }().unwrap() + } + + pub(in crate::gsp) fn gsp_read_ptr(qs: &CoherentAllocation<GspMem>) -> u32 { + // PANIC: A `dma::CoherentAllocation` always contains at least one element. + || -> Result<u32> { Ok(dma_read!(qs, [0]?.gspq.rx.0.readPtr) % MSGQ_NUM_PAGES) }().unwrap() + } + + pub(in crate::gsp) fn cpu_read_ptr(qs: &CoherentAllocation<GspMem>) -> u32 { + // PANIC: A `dma::CoherentAllocation` always contains at least one element. + || -> Result<u32> { Ok(dma_read!(qs, [0]?.cpuq.rx.0.readPtr) % MSGQ_NUM_PAGES) }().unwrap() + } + + pub(in crate::gsp) fn advance_cpu_read_ptr(qs: &CoherentAllocation<GspMem>, count: u32) { + let rptr = cpu_read_ptr(qs).wrapping_add(count) % MSGQ_NUM_PAGES; + + // Ensure read pointer is properly ordered. + fence(Ordering::SeqCst); + + // PANIC: A `dma::CoherentAllocation` always contains at least one element. + || -> Result { + dma_write!(qs, [0]?.cpuq.rx.0.readPtr, rptr); + Ok(()) + }() + .unwrap() + } + + pub(in crate::gsp) fn cpu_write_ptr(qs: &CoherentAllocation<GspMem>) -> u32 { + // PANIC: A `dma::CoherentAllocation` always contains at least one element. + || -> Result<u32> { Ok(dma_read!(qs, [0]?.cpuq.tx.0.writePtr) % MSGQ_NUM_PAGES) }().unwrap() + } + + pub(in crate::gsp) fn advance_cpu_write_ptr(qs: &CoherentAllocation<GspMem>, count: u32) { + let wptr = cpu_write_ptr(qs).wrapping_add(count) % MSGQ_NUM_PAGES; + + // PANIC: A `dma::CoherentAllocation` always contains at least one element. + || -> Result { + dma_write!(qs, [0]?.cpuq.tx.0.writePtr, wptr); + Ok(()) + }() + .unwrap(); + + // Ensure all command data is visible before triggering the GSP read. + fence(Ordering::SeqCst); + } +} + /// Empty type to group methods related to heap parameters for running the GSP firmware. enum GspFwHeapParams {} @@ -708,22 +777,6 @@ impl MsgqTxHeader { entryOff: num::usize_into_u32::<GSP_PAGE_SIZE>(), }) } - - /// Returns the value of the write pointer for this queue. - pub(crate) fn write_ptr(&self) -> u32 { - let ptr = core::ptr::from_ref(&self.0.writePtr); - - // SAFETY: `ptr` is a valid pointer to a `u32`. - unsafe { ptr.read_volatile() } - } - - /// Sets the value of the write pointer for this queue. - pub(crate) fn set_write_ptr(&mut self, val: u32) { - let ptr = core::ptr::from_mut(&mut self.0.writePtr); - - // SAFETY: `ptr` is a valid pointer to a `u32`. - unsafe { ptr.write_volatile(val) } - } } // SAFETY: Padding is explicit and does not contain uninitialized data. @@ -739,22 +792,6 @@ impl MsgqRxHeader { pub(crate) fn new() -> Self { Self(Default::default()) } - - /// Returns the value of the read pointer for this queue. - pub(crate) fn read_ptr(&self) -> u32 { - let ptr = core::ptr::from_ref(&self.0.readPtr); - - // SAFETY: `ptr` is a valid pointer to a `u32`. - unsafe { ptr.read_volatile() } - } - - /// Sets the value of the read pointer for this queue. - pub(crate) fn set_read_ptr(&mut self, val: u32) { - let ptr = core::ptr::from_mut(&mut self.0.readPtr); - - // SAFETY: `ptr` is a valid pointer to a `u32`. - unsafe { ptr.write_volatile(val) } - } } // SAFETY: Padding is explicit and does not contain uninitialized data. diff --git a/drivers/hid/bpf/hid_bpf_dispatch.c b/drivers/hid/bpf/hid_bpf_dispatch.c index f3d15994ca1e..50c7b45c59e3 100644 --- a/drivers/hid/bpf/hid_bpf_dispatch.c +++ b/drivers/hid/bpf/hid_bpf_dispatch.c @@ -444,6 +444,8 @@ hid_bpf_hw_request(struct hid_bpf_ctx *ctx, __u8 *buf, size_t buf__sz, (u64)(long)ctx, true); /* prevent infinite recursions */ + if (ret > size) + ret = size; if (ret > 0) memcpy(buf, dma_data, ret); diff --git a/drivers/hid/hid-appletb-kbd.c b/drivers/hid/hid-appletb-kbd.c index a1db3b3d0667..0fdc0968b9ef 100644 --- a/drivers/hid/hid-appletb-kbd.c +++ b/drivers/hid/hid-appletb-kbd.c @@ -476,7 +476,7 @@ static int appletb_kbd_suspend(struct hid_device *hdev, pm_message_t msg) return 0; } -static int appletb_kbd_reset_resume(struct hid_device *hdev) +static int appletb_kbd_resume(struct hid_device *hdev) { struct appletb_kbd *kbd = hid_get_drvdata(hdev); @@ -500,7 +500,8 @@ static struct hid_driver appletb_kbd_hid_driver = { .event = appletb_kbd_hid_event, .input_configured = appletb_kbd_input_configured, .suspend = pm_ptr(appletb_kbd_suspend), - .reset_resume = pm_ptr(appletb_kbd_reset_resume), + .resume = pm_ptr(appletb_kbd_resume), + .reset_resume = pm_ptr(appletb_kbd_resume), .driver.dev_groups = appletb_kbd_groups, }; module_hid_driver(appletb_kbd_hid_driver); diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 687b785e2d0c..bc93b27f9b13 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -1498,6 +1498,9 @@ static const struct hid_device_id asus_devices[] = { USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X), QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD | QUIRK_ROG_ALLY_XPAD }, { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, + USB_DEVICE_ID_ASUSTEK_XGM_2022), + }, + { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_XGM_2023), }, { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 840a60113868..833df14ef68f 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2057,9 +2057,10 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 * rsize = max_buffer_size; if (csize < rsize) { - dbg_hid("report %d is too short, (%d < %d)\n", report->id, - csize, rsize); - memset(cdata + csize, 0, rsize - csize); + hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %d)\n", + report->id, rsize, csize); + ret = -EINVAL; + goto out; } if ((hid->claimed & HID_CLAIMED_HIDDEV) && hid->hiddev_report_event) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 4ab7640b119a..afcee13bad61 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -229,6 +229,7 @@ #define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X 0x1b4c #define USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD 0x196b #define USB_DEVICE_ID_ASUSTEK_FX503VD_KEYBOARD 0x1869 +#define USB_DEVICE_ID_ASUSTEK_XGM_2022 0x1970 #define USB_DEVICE_ID_ASUSTEK_XGM_2023 0x1a9a #define USB_VENDOR_ID_ATEN 0x0557 @@ -454,8 +455,6 @@ #define USB_DEVICE_ID_TOSHIBA_CLICK_L9W 0x0401 #define USB_DEVICE_ID_HP_X2 0x074d #define USB_DEVICE_ID_HP_X2_10_COVER 0x0755 -#define USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN 0x2544 -#define USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN 0x2706 #define I2C_DEVICE_ID_CHROMEBOOK_TROGDOR_POMPOM 0x2F81 #define USB_VENDOR_ID_ELECOM 0x056e diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index d5308adb2894..9475b7e9da43 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -354,6 +354,7 @@ static enum power_supply_property hidinput_battery_props[] = { #define HID_BATTERY_QUIRK_FEATURE (1 << 1) /* ask for feature report */ #define HID_BATTERY_QUIRK_IGNORE (1 << 2) /* completely ignore the battery */ #define HID_BATTERY_QUIRK_AVOID_QUERY (1 << 3) /* do not query the battery */ +#define HID_BATTERY_QUIRK_DYNAMIC (1 << 4) /* report present only after life signs */ static const struct hid_device_id hid_battery_quirks[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, @@ -386,10 +387,6 @@ static const struct hid_device_id hid_battery_quirks[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD), HID_BATTERY_QUIRK_IGNORE }, - { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN), - HID_BATTERY_QUIRK_IGNORE }, - { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN), - HID_BATTERY_QUIRK_IGNORE }, { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_L), HID_BATTERY_QUIRK_AVOID_QUERY }, { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_PRO_MW), @@ -402,8 +399,8 @@ static const struct hid_device_id hid_battery_quirks[] = { * Elan HID touchscreens seem to all report a non present battery, * set HID_BATTERY_QUIRK_IGNORE for all Elan I2C and USB HID devices. */ - { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, HID_ANY_ID), HID_BATTERY_QUIRK_IGNORE }, - { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, HID_ANY_ID), HID_BATTERY_QUIRK_IGNORE }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, HID_ANY_ID), HID_BATTERY_QUIRK_DYNAMIC }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, HID_ANY_ID), HID_BATTERY_QUIRK_DYNAMIC }, {} }; @@ -460,11 +457,14 @@ static int hidinput_get_battery_property(struct power_supply *psy, int ret = 0; switch (prop) { - case POWER_SUPPLY_PROP_PRESENT: case POWER_SUPPLY_PROP_ONLINE: val->intval = 1; break; + case POWER_SUPPLY_PROP_PRESENT: + val->intval = dev->battery_present; + break; + case POWER_SUPPLY_PROP_CAPACITY: if (dev->battery_status != HID_BATTERY_REPORTED && !dev->battery_avoid_query) { @@ -577,6 +577,8 @@ static int hidinput_setup_battery(struct hid_device *dev, unsigned report_type, if (quirks & HID_BATTERY_QUIRK_AVOID_QUERY) dev->battery_avoid_query = true; + dev->battery_present = (quirks & HID_BATTERY_QUIRK_DYNAMIC) ? false : true; + dev->battery = power_supply_register(&dev->dev, psy_desc, &psy_cfg); if (IS_ERR(dev->battery)) { error = PTR_ERR(dev->battery); @@ -632,6 +634,7 @@ static void hidinput_update_battery(struct hid_device *dev, unsigned int usage, return; if (hidinput_update_battery_charge_status(dev, usage, value)) { + dev->battery_present = true; power_supply_changed(dev->battery); return; } @@ -647,6 +650,7 @@ static void hidinput_update_battery(struct hid_device *dev, unsigned int usage, if (dev->battery_status != HID_BATTERY_REPORTED || capacity != dev->battery_capacity || ktime_after(ktime_get_coarse(), dev->battery_ratelimit_time)) { + dev->battery_present = true; dev->battery_capacity = capacity; dev->battery_status = HID_BATTERY_REPORTED; dev->battery_ratelimit_time = diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index d40932809ce1..d1dea7297712 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -4487,10 +4487,12 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) if (!ret) ret = hidpp_ff_init(hidpp, &data); - if (ret) + if (ret) { hid_warn(hidpp->hid_dev, "Unable to initialize force feedback support, errno %d\n", ret); + ret = 0; + } } /* @@ -4668,6 +4670,8 @@ static const struct hid_device_id hidpp_devices[] = { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb038) }, { /* Slim Solar+ K980 Keyboard over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb391) }, + { /* MX Master 4 mouse over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb042) }, {} }; diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index b8a748bbf0fd..e82a3c4e5b44 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -526,12 +526,19 @@ static void mt_get_feature(struct hid_device *hdev, struct hid_report *report) dev_warn(&hdev->dev, "failed to fetch feature %d\n", report->id); } else { + /* The report ID in the request and the response should match */ + if (report->id != buf[0]) { + hid_err(hdev, "Returned feature report did not match the request\n"); + goto free; + } + ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, buf, size, 0); if (ret) dev_warn(&hdev->dev, "failed to report feature\n"); } +free: kfree(buf); } diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-hid.c b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-hid.c index f9fcb398673b..8075992e8732 100644 --- a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-hid.c +++ b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-hid.c @@ -127,6 +127,7 @@ int quicki2c_hid_probe(struct quicki2c_device *qcdev) hid->product = le16_to_cpu(qcdev->dev_desc.product_id); snprintf(hid->name, sizeof(hid->name), "%s %04X:%04X", "quicki2c-hid", hid->vendor, hid->product); + strscpy(hid->phys, dev_name(qcdev->dev), sizeof(hid->phys)); ret = hid_add_device(hid); if (ret) { diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.c b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.c index 82c72bfa2795..91d5807b4a83 100644 --- a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.c +++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.c @@ -118,6 +118,7 @@ int quickspi_hid_probe(struct quickspi_device *qsdev) hid->product = le16_to_cpu(qsdev->dev_desc.product_id); snprintf(hid->name, sizeof(hid->name), "%s %04X:%04X", "quickspi-hid", hid->vendor, hid->product); + strscpy(hid->phys, dev_name(qsdev->dev), sizeof(hid->phys)); ret = hid_add_device(hid); if (ret) { diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 9b2c710f8da1..da1f0ea85625 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1208,10 +1208,20 @@ static int wacom_intuos_bt_irq(struct wacom_wac *wacom, size_t len) switch (data[0]) { case 0x04: + if (len < 32) { + dev_warn(wacom->pen_input->dev.parent, + "Report 0x04 too short: %zu bytes\n", len); + break; + } wacom_intuos_bt_process_data(wacom, data + i); i += 10; fallthrough; case 0x03: + if (i == 1 && len < 22) { + dev_warn(wacom->pen_input->dev.parent, + "Report 0x03 too short: %zu bytes\n", len); + break; + } wacom_intuos_bt_process_data(wacom, data + i); i += 10; wacom_intuos_bt_process_data(wacom, data + i); diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 486152a8ea77..328867242cb3 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -1493,8 +1493,7 @@ config SENSORS_LM73 config SENSORS_LM75 tristate "National Semiconductor LM75 and compatibles" - depends on I2C - depends on I3C || !I3C + depends on I3C_OR_I2C select REGMAP_I2C select REGMAP_I3C if I3C help @@ -2382,8 +2381,7 @@ config SENSORS_TMP103 config SENSORS_TMP108 tristate "Texas Instruments TMP108" - depends on I2C - depends on I3C || !I3C + depends on I3C_OR_I2C select REGMAP_I2C select REGMAP_I3C if I3C help diff --git a/drivers/i3c/Kconfig b/drivers/i3c/Kconfig index 30a441506f61..626c54b386d5 100644 --- a/drivers/i3c/Kconfig +++ b/drivers/i3c/Kconfig @@ -22,3 +22,15 @@ menuconfig I3C if I3C source "drivers/i3c/master/Kconfig" endif # I3C + +config I3C_OR_I2C + tristate + default m if I3C=m + default I2C + help + Device drivers using module_i3c_i2c_driver() can use either + i2c or i3c hosts, but cannot be built-in for the kernel when + CONFIG_I3C=m. + + Add 'depends on I2C_OR_I3C' in Kconfig for those drivers to + get the correct dependencies. diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index d87bde3f7700..d6bdb32397fb 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -1024,7 +1024,7 @@ static int dw_i3c_master_reattach_i3c_dev(struct i3c_dev_desc *dev, master->free_pos &= ~BIT(pos); } - writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(dev->info.dyn_addr), + writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(dev->info.dyn_addr) | DEV_ADDR_TABLE_SIR_REJECT, master->regs + DEV_ADDR_TABLE_LOC(master->datstartaddr, data->index)); @@ -1053,7 +1053,7 @@ static int dw_i3c_master_attach_i3c_dev(struct i3c_dev_desc *dev) master->free_pos &= ~BIT(pos); i3c_dev_set_master_data(dev, data); - writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(master->devs[pos].addr), + writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(master->devs[pos].addr) | DEV_ADDR_TABLE_SIR_REJECT, master->regs + DEV_ADDR_TABLE_LOC(master->datstartaddr, data->index)); @@ -1659,6 +1659,8 @@ int dw_i3c_common_probe(struct dw_i3c_master *master, pm_runtime_get_noresume(&pdev->dev); INIT_WORK(&master->hj_work, dw_i3c_hj_work); + + device_set_of_node_from_dev(&master->base.i2c.dev, &pdev->dev); ret = i3c_master_register(&master->base, &pdev->dev, &dw_mipi_i3c_ops, false); if (ret) diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd.h b/drivers/i3c/master/mipi-i3c-hci/cmd.h index 1d6dd2c5d01a..b1bf87daa651 100644 --- a/drivers/i3c/master/mipi-i3c-hci/cmd.h +++ b/drivers/i3c/master/mipi-i3c-hci/cmd.h @@ -17,6 +17,7 @@ #define CMD_0_TOC W0_BIT_(31) #define CMD_0_ROC W0_BIT_(30) #define CMD_0_ATTR W0_MASK(2, 0) +#define CMD_0_TID W0_MASK(6, 3) /* * Response Descriptor Structure diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c index fe260461e7e6..75d452d7f6af 100644 --- a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c +++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c @@ -331,12 +331,10 @@ static int hci_cmd_v1_daa(struct i3c_hci *hci) CMD_A0_ROC | CMD_A0_TOC; xfer->cmd_desc[1] = 0; xfer->completion = &done; - hci->io->queue_xfer(hci, xfer, 1); - if (!wait_for_completion_timeout(&done, HZ) && - hci->io->dequeue_xfer(hci, xfer, 1)) { - ret = -ETIME; + xfer->timeout = HZ; + ret = i3c_hci_process_xfer(hci, xfer, 1); + if (ret) break; - } if ((RESP_STATUS(xfer->response) == RESP_ERR_ADDR_HEADER || RESP_STATUS(xfer->response) == RESP_ERR_NACK) && RESP_DATA_LENGTH(xfer->response) == 1) { diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c index 3729e6419581..39eec26a363c 100644 --- a/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c +++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c @@ -253,6 +253,7 @@ static int hci_cmd_v2_daa(struct i3c_hci *hci) xfer[0].rnw = true; xfer[0].cmd_desc[1] = CMD_A1_DATA_LENGTH(8); xfer[1].completion = &done; + xfer[1].timeout = HZ; for (;;) { ret = i3c_master_get_free_addr(&hci->master, next_addr); @@ -272,12 +273,9 @@ static int hci_cmd_v2_daa(struct i3c_hci *hci) CMD_A0_ASSIGN_ADDRESS(next_addr) | CMD_A0_ROC | CMD_A0_TOC; - hci->io->queue_xfer(hci, xfer, 2); - if (!wait_for_completion_timeout(&done, HZ) && - hci->io->dequeue_xfer(hci, xfer, 2)) { - ret = -ETIME; + ret = i3c_hci_process_xfer(hci, xfer, 2); + if (ret) break; - } if (RESP_STATUS(xfer[0].response) != RESP_SUCCESS) { ret = 0; /* no more devices to be assigned */ break; diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c index 5879bba78164..284f3ed7af8c 100644 --- a/drivers/i3c/master/mipi-i3c-hci/core.c +++ b/drivers/i3c/master/mipi-i3c-hci/core.c @@ -152,7 +152,11 @@ static int i3c_hci_bus_init(struct i3c_master_controller *m) if (hci->quirks & HCI_QUIRK_RESP_BUF_THLD) amd_set_resp_buf_thld(hci); - reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE); + scoped_guard(spinlock_irqsave, &hci->lock) + hci->irq_inactive = false; + + /* Enable bus with Hot-Join disabled */ + reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE | HC_CONTROL_HOT_JOIN_CTRL); dev_dbg(&hci->master.dev, "HC_CONTROL = %#x", reg_read(HC_CONTROL)); return 0; @@ -177,21 +181,51 @@ static int i3c_hci_bus_disable(struct i3c_hci *hci) return ret; } +static int i3c_hci_software_reset(struct i3c_hci *hci) +{ + u32 regval; + int ret; + + /* + * SOFT_RST must be clear before we write to it. + * Then we must wait until it clears again. + */ + ret = readx_poll_timeout(reg_read, RESET_CONTROL, regval, + !(regval & SOFT_RST), 0, 10 * USEC_PER_MSEC); + if (ret) { + dev_err(&hci->master.dev, "%s: Software reset stuck\n", __func__); + return ret; + } + + reg_write(RESET_CONTROL, SOFT_RST); + + ret = readx_poll_timeout(reg_read, RESET_CONTROL, regval, + !(regval & SOFT_RST), 0, 10 * USEC_PER_MSEC); + if (ret) { + dev_err(&hci->master.dev, "%s: Software reset failed\n", __func__); + return ret; + } + + return 0; +} + void i3c_hci_sync_irq_inactive(struct i3c_hci *hci) { struct platform_device *pdev = to_platform_device(hci->master.dev.parent); int irq = platform_get_irq(pdev, 0); reg_write(INTR_SIGNAL_ENABLE, 0x0); - hci->irq_inactive = true; synchronize_irq(irq); + scoped_guard(spinlock_irqsave, &hci->lock) + hci->irq_inactive = true; } static void i3c_hci_bus_cleanup(struct i3c_master_controller *m) { struct i3c_hci *hci = to_i3c_hci(m); - i3c_hci_bus_disable(hci); + if (i3c_hci_bus_disable(hci)) + i3c_hci_software_reset(hci); hci->io->cleanup(hci); } @@ -212,6 +246,36 @@ void mipi_i3c_hci_dct_index_reset(struct i3c_hci *hci) reg_write(DCT_SECTION, FIELD_PREP(DCT_TABLE_INDEX, 0)); } +int i3c_hci_process_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n) +{ + struct completion *done = xfer[n - 1].completion; + unsigned long timeout = xfer[n - 1].timeout; + int ret; + + ret = hci->io->queue_xfer(hci, xfer, n); + if (ret) + return ret; + + if (!wait_for_completion_timeout(done, timeout)) { + if (hci->io->dequeue_xfer(hci, xfer, n)) { + dev_err(&hci->master.dev, "%s: timeout error\n", __func__); + return -ETIMEDOUT; + } + return 0; + } + + if (hci->io->handle_error) { + bool error = false; + + for (int i = 0; i < n && !error; i++) + error = RESP_STATUS(xfer[i].response); + if (error) + return hci->io->handle_error(hci, xfer, n); + } + + return 0; +} + static int i3c_hci_send_ccc_cmd(struct i3c_master_controller *m, struct i3c_ccc_cmd *ccc) { @@ -252,18 +316,14 @@ static int i3c_hci_send_ccc_cmd(struct i3c_master_controller *m, last = i - 1; xfer[last].cmd_desc[0] |= CMD_0_TOC; xfer[last].completion = &done; + xfer[last].timeout = HZ; if (prefixed) xfer--; - ret = hci->io->queue_xfer(hci, xfer, nxfers); + ret = i3c_hci_process_xfer(hci, xfer, nxfers); if (ret) goto out; - if (!wait_for_completion_timeout(&done, HZ) && - hci->io->dequeue_xfer(hci, xfer, nxfers)) { - ret = -ETIME; - goto out; - } for (i = prefixed; i < nxfers; i++) { if (ccc->rnw) ccc->dests[i - prefixed].payload.len = @@ -334,15 +394,11 @@ static int i3c_hci_i3c_xfers(struct i3c_dev_desc *dev, last = i - 1; xfer[last].cmd_desc[0] |= CMD_0_TOC; xfer[last].completion = &done; + xfer[last].timeout = HZ; - ret = hci->io->queue_xfer(hci, xfer, nxfers); + ret = i3c_hci_process_xfer(hci, xfer, nxfers); if (ret) goto out; - if (!wait_for_completion_timeout(&done, HZ) && - hci->io->dequeue_xfer(hci, xfer, nxfers)) { - ret = -ETIME; - goto out; - } for (i = 0; i < nxfers; i++) { if (i3c_xfers[i].rnw) i3c_xfers[i].len = RESP_DATA_LENGTH(xfer[i].response); @@ -382,15 +438,11 @@ static int i3c_hci_i2c_xfers(struct i2c_dev_desc *dev, last = i - 1; xfer[last].cmd_desc[0] |= CMD_0_TOC; xfer[last].completion = &done; + xfer[last].timeout = m->i2c.timeout; - ret = hci->io->queue_xfer(hci, xfer, nxfers); + ret = i3c_hci_process_xfer(hci, xfer, nxfers); if (ret) goto out; - if (!wait_for_completion_timeout(&done, m->i2c.timeout) && - hci->io->dequeue_xfer(hci, xfer, nxfers)) { - ret = -ETIME; - goto out; - } for (i = 0; i < nxfers; i++) { if (RESP_STATUS(xfer[i].response) != RESP_SUCCESS) { ret = -EIO; @@ -566,6 +618,8 @@ static irqreturn_t i3c_hci_irq_handler(int irq, void *dev_id) irqreturn_t result = IRQ_NONE; u32 val; + guard(spinlock)(&hci->lock); + /* * The IRQ can be shared, so the handler may be called when the IRQ is * due to a different device. That could happen when runtime suspended, @@ -601,34 +655,6 @@ static irqreturn_t i3c_hci_irq_handler(int irq, void *dev_id) return result; } -static int i3c_hci_software_reset(struct i3c_hci *hci) -{ - u32 regval; - int ret; - - /* - * SOFT_RST must be clear before we write to it. - * Then we must wait until it clears again. - */ - ret = readx_poll_timeout(reg_read, RESET_CONTROL, regval, - !(regval & SOFT_RST), 0, 10 * USEC_PER_MSEC); - if (ret) { - dev_err(&hci->master.dev, "%s: Software reset stuck\n", __func__); - return ret; - } - - reg_write(RESET_CONTROL, SOFT_RST); - - ret = readx_poll_timeout(reg_read, RESET_CONTROL, regval, - !(regval & SOFT_RST), 0, 10 * USEC_PER_MSEC); - if (ret) { - dev_err(&hci->master.dev, "%s: Software reset failed\n", __func__); - return ret; - } - - return 0; -} - static inline bool is_version_1_1_or_newer(struct i3c_hci *hci) { return hci->version_major > 1 || (hci->version_major == 1 && hci->version_minor > 0); @@ -739,8 +765,12 @@ static int i3c_hci_runtime_suspend(struct device *dev) int ret; ret = i3c_hci_bus_disable(hci); - if (ret) + if (ret) { + /* Fall back to software reset to disable the bus */ + ret = i3c_hci_software_reset(hci); + i3c_hci_sync_irq_inactive(hci); return ret; + } hci->io->suspend(hci); @@ -760,11 +790,13 @@ static int i3c_hci_runtime_resume(struct device *dev) mipi_i3c_hci_dat_v1.restore(hci); - hci->irq_inactive = false; - hci->io->resume(hci); - reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE); + scoped_guard(spinlock_irqsave, &hci->lock) + hci->irq_inactive = false; + + /* Enable bus with Hot-Join disabled */ + reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE | HC_CONTROL_HOT_JOIN_CTRL); return 0; } @@ -924,6 +956,9 @@ static int i3c_hci_probe(struct platform_device *pdev) if (!hci) return -ENOMEM; + spin_lock_init(&hci->lock); + mutex_init(&hci->control_mutex); + /* * Multi-bus instances share the same MMIO address range, but not * necessarily in separate contiguous sub-ranges. To avoid overlapping @@ -950,6 +985,8 @@ static int i3c_hci_probe(struct platform_device *pdev) if (ret) return ret; + hci->irq_inactive = true; + irq = platform_get_irq(pdev, 0); ret = devm_request_irq(&pdev->dev, irq, i3c_hci_irq_handler, IRQF_SHARED, NULL, hci); diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c index b903a2da1fd1..e487ef52f6b4 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dma.c +++ b/drivers/i3c/master/mipi-i3c-hci/dma.c @@ -129,9 +129,8 @@ struct hci_rh_data { dma_addr_t xfer_dma, resp_dma, ibi_status_dma, ibi_data_dma; unsigned int xfer_entries, ibi_status_entries, ibi_chunks_total; unsigned int xfer_struct_sz, resp_struct_sz, ibi_status_sz, ibi_chunk_sz; - unsigned int done_ptr, ibi_chunk_ptr; + unsigned int done_ptr, ibi_chunk_ptr, xfer_space; struct hci_xfer **src_xfers; - spinlock_t lock; struct completion op_done; }; @@ -261,6 +260,7 @@ ring_ready: rh->done_ptr = 0; rh->ibi_chunk_ptr = 0; + rh->xfer_space = rh->xfer_entries; } static void hci_dma_init_rings(struct i3c_hci *hci) @@ -344,7 +344,6 @@ static int hci_dma_init(struct i3c_hci *hci) goto err_out; rh = &rings->headers[i]; rh->regs = hci->base_regs + offset; - spin_lock_init(&rh->lock); init_completion(&rh->op_done); rh->xfer_entries = XFER_RING_ENTRIES; @@ -439,26 +438,63 @@ static void hci_dma_unmap_xfer(struct i3c_hci *hci, } } +static struct i3c_dma *hci_dma_map_xfer(struct device *dev, struct hci_xfer *xfer) +{ + enum dma_data_direction dir = xfer->rnw ? DMA_FROM_DEVICE : DMA_TO_DEVICE; + bool need_bounce = device_iommu_mapped(dev) && xfer->rnw && (xfer->data_len & 3); + + return i3c_master_dma_map_single(dev, xfer->data, xfer->data_len, need_bounce, dir); +} + +static int hci_dma_map_xfer_list(struct i3c_hci *hci, struct device *dev, + struct hci_xfer *xfer_list, int n) +{ + for (int i = 0; i < n; i++) { + struct hci_xfer *xfer = xfer_list + i; + + if (!xfer->data) + continue; + + xfer->dma = hci_dma_map_xfer(dev, xfer); + if (!xfer->dma) { + hci_dma_unmap_xfer(hci, xfer_list, i); + return -ENOMEM; + } + } + + return 0; +} + static int hci_dma_queue_xfer(struct i3c_hci *hci, struct hci_xfer *xfer_list, int n) { struct hci_rings_data *rings = hci->io_data; struct hci_rh_data *rh; unsigned int i, ring, enqueue_ptr; - u32 op1_val, op2_val; + u32 op1_val; + int ret; + + ret = hci_dma_map_xfer_list(hci, rings->sysdev, xfer_list, n); + if (ret) + return ret; /* For now we only use ring 0 */ ring = 0; rh = &rings->headers[ring]; + spin_lock_irq(&hci->lock); + + if (n > rh->xfer_space) { + spin_unlock_irq(&hci->lock); + hci_dma_unmap_xfer(hci, xfer_list, n); + return -EBUSY; + } + op1_val = rh_reg_read(RING_OPERATION1); enqueue_ptr = FIELD_GET(RING_OP1_CR_ENQ_PTR, op1_val); for (i = 0; i < n; i++) { struct hci_xfer *xfer = xfer_list + i; u32 *ring_data = rh->xfer + rh->xfer_struct_sz * enqueue_ptr; - enum dma_data_direction dir = xfer->rnw ? DMA_FROM_DEVICE : - DMA_TO_DEVICE; - bool need_bounce; /* store cmd descriptor */ *ring_data++ = xfer->cmd_desc[0]; @@ -477,18 +513,6 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci, /* 2nd and 3rd words of Data Buffer Descriptor Structure */ if (xfer->data) { - need_bounce = device_iommu_mapped(rings->sysdev) && - xfer->rnw && - xfer->data_len != ALIGN(xfer->data_len, 4); - xfer->dma = i3c_master_dma_map_single(rings->sysdev, - xfer->data, - xfer->data_len, - need_bounce, - dir); - if (!xfer->dma) { - hci_dma_unmap_xfer(hci, xfer_list, i); - return -ENOMEM; - } *ring_data++ = lower_32_bits(xfer->dma->addr); *ring_data++ = upper_32_bits(xfer->dma->addr); } else { @@ -503,26 +527,14 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci, xfer->ring_entry = enqueue_ptr; enqueue_ptr = (enqueue_ptr + 1) % rh->xfer_entries; - - /* - * We may update the hardware view of the enqueue pointer - * only if we didn't reach its dequeue pointer. - */ - op2_val = rh_reg_read(RING_OPERATION2); - if (enqueue_ptr == FIELD_GET(RING_OP2_CR_DEQ_PTR, op2_val)) { - /* the ring is full */ - hci_dma_unmap_xfer(hci, xfer_list, i + 1); - return -EBUSY; - } } - /* take care to update the hardware enqueue pointer atomically */ - spin_lock_irq(&rh->lock); - op1_val = rh_reg_read(RING_OPERATION1); + rh->xfer_space -= n; + op1_val &= ~RING_OP1_CR_ENQ_PTR; op1_val |= FIELD_PREP(RING_OP1_CR_ENQ_PTR, enqueue_ptr); rh_reg_write(RING_OPERATION1, op1_val); - spin_unlock_irq(&rh->lock); + spin_unlock_irq(&hci->lock); return 0; } @@ -534,18 +546,29 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci, struct hci_rh_data *rh = &rings->headers[xfer_list[0].ring_number]; unsigned int i; bool did_unqueue = false; - - /* stop the ring */ - rh_reg_write(RING_CONTROL, RING_CTRL_ABORT); - if (wait_for_completion_timeout(&rh->op_done, HZ) == 0) { - /* - * We're deep in it if ever this condition is ever met. - * Hardware might still be writing to memory, etc. - */ - dev_crit(&hci->master.dev, "unable to abort the ring\n"); - WARN_ON(1); + u32 ring_status; + + guard(mutex)(&hci->control_mutex); + + ring_status = rh_reg_read(RING_STATUS); + if (ring_status & RING_STATUS_RUNNING) { + /* stop the ring */ + reinit_completion(&rh->op_done); + rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE | RING_CTRL_ABORT); + wait_for_completion_timeout(&rh->op_done, HZ); + ring_status = rh_reg_read(RING_STATUS); + if (ring_status & RING_STATUS_RUNNING) { + /* + * We're deep in it if ever this condition is ever met. + * Hardware might still be writing to memory, etc. + */ + dev_crit(&hci->master.dev, "unable to abort the ring\n"); + WARN_ON(1); + } } + spin_lock_irq(&hci->lock); + for (i = 0; i < n; i++) { struct hci_xfer *xfer = xfer_list + i; int idx = xfer->ring_entry; @@ -559,7 +582,7 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci, u32 *ring_data = rh->xfer + rh->xfer_struct_sz * idx; /* store no-op cmd descriptor */ - *ring_data++ = FIELD_PREP(CMD_0_ATTR, 0x7); + *ring_data++ = FIELD_PREP(CMD_0_ATTR, 0x7) | FIELD_PREP(CMD_0_TID, xfer->cmd_tid); *ring_data++ = 0; if (hci->cmd == &mipi_i3c_hci_cmd_v2) { *ring_data++ = 0; @@ -577,15 +600,25 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci, } /* restart the ring */ + mipi_i3c_hci_resume(hci); rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE); + rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE | RING_CTRL_RUN_STOP); + + spin_unlock_irq(&hci->lock); return did_unqueue; } +static int hci_dma_handle_error(struct i3c_hci *hci, struct hci_xfer *xfer_list, int n) +{ + return hci_dma_dequeue_xfer(hci, xfer_list, n) ? -EIO : 0; +} + static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh) { u32 op1_val, op2_val, resp, *ring_resp; unsigned int tid, done_ptr = rh->done_ptr; + unsigned int done_cnt = 0; struct hci_xfer *xfer; for (;;) { @@ -603,6 +636,7 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh) dev_dbg(&hci->master.dev, "orphaned ring entry"); } else { hci_dma_unmap_xfer(hci, xfer, 1); + rh->src_xfers[done_ptr] = NULL; xfer->ring_entry = -1; xfer->response = resp; if (tid != xfer->cmd_tid) { @@ -617,15 +651,14 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh) done_ptr = (done_ptr + 1) % rh->xfer_entries; rh->done_ptr = done_ptr; + done_cnt += 1; } - /* take care to update the software dequeue pointer atomically */ - spin_lock(&rh->lock); + rh->xfer_space += done_cnt; op1_val = rh_reg_read(RING_OPERATION1); op1_val &= ~RING_OP1_CR_SW_DEQ_PTR; op1_val |= FIELD_PREP(RING_OP1_CR_SW_DEQ_PTR, done_ptr); rh_reg_write(RING_OPERATION1, op1_val); - spin_unlock(&rh->lock); } static int hci_dma_request_ibi(struct i3c_hci *hci, struct i3c_dev_desc *dev, @@ -805,13 +838,10 @@ static void hci_dma_process_ibi(struct i3c_hci *hci, struct hci_rh_data *rh) i3c_master_queue_ibi(dev, slot); done: - /* take care to update the ibi dequeue pointer atomically */ - spin_lock(&rh->lock); op1_val = rh_reg_read(RING_OPERATION1); op1_val &= ~RING_OP1_IBI_DEQ_PTR; op1_val |= FIELD_PREP(RING_OP1_IBI_DEQ_PTR, deq_ptr); rh_reg_write(RING_OPERATION1, op1_val); - spin_unlock(&rh->lock); /* update the chunk pointer */ rh->ibi_chunk_ptr += ibi_chunks; @@ -845,29 +875,8 @@ static bool hci_dma_irq_handler(struct i3c_hci *hci) hci_dma_xfer_done(hci, rh); if (status & INTR_RING_OP) complete(&rh->op_done); - - if (status & INTR_TRANSFER_ABORT) { - u32 ring_status; - - dev_notice_ratelimited(&hci->master.dev, - "Ring %d: Transfer Aborted\n", i); - mipi_i3c_hci_resume(hci); - ring_status = rh_reg_read(RING_STATUS); - if (!(ring_status & RING_STATUS_RUNNING) && - status & INTR_TRANSFER_COMPLETION && - status & INTR_TRANSFER_ERR) { - /* - * Ring stop followed by run is an Intel - * specific required quirk after resuming the - * halted controller. Do it only when the ring - * is not in running state after a transfer - * error. - */ - rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE); - rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE | - RING_CTRL_RUN_STOP); - } - } + if (status & INTR_TRANSFER_ABORT) + dev_dbg(&hci->master.dev, "Ring %d: Transfer Aborted\n", i); if (status & INTR_IBI_RING_FULL) dev_err_ratelimited(&hci->master.dev, "Ring %d: IBI Ring Full Condition\n", i); @@ -883,6 +892,7 @@ const struct hci_io_ops mipi_i3c_hci_dma = { .cleanup = hci_dma_cleanup, .queue_xfer = hci_dma_queue_xfer, .dequeue_xfer = hci_dma_dequeue_xfer, + .handle_error = hci_dma_handle_error, .irq_handler = hci_dma_irq_handler, .request_ibi = hci_dma_request_ibi, .free_ibi = hci_dma_free_ibi, diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h index 337b7ab1cb06..9ac9d0e342f4 100644 --- a/drivers/i3c/master/mipi-i3c-hci/hci.h +++ b/drivers/i3c/master/mipi-i3c-hci/hci.h @@ -50,6 +50,8 @@ struct i3c_hci { const struct hci_io_ops *io; void *io_data; const struct hci_cmd_ops *cmd; + spinlock_t lock; + struct mutex control_mutex; atomic_t next_cmd_tid; bool irq_inactive; u32 caps; @@ -87,6 +89,7 @@ struct hci_xfer { unsigned int data_len; unsigned int cmd_tid; struct completion *completion; + unsigned long timeout; union { struct { /* PIO specific */ @@ -120,6 +123,7 @@ struct hci_io_ops { bool (*irq_handler)(struct i3c_hci *hci); int (*queue_xfer)(struct i3c_hci *hci, struct hci_xfer *xfer, int n); bool (*dequeue_xfer)(struct i3c_hci *hci, struct hci_xfer *xfer, int n); + int (*handle_error)(struct i3c_hci *hci, struct hci_xfer *xfer, int n); int (*request_ibi)(struct i3c_hci *hci, struct i3c_dev_desc *dev, const struct i3c_ibi_setup *req); void (*free_ibi)(struct i3c_hci *hci, struct i3c_dev_desc *dev); @@ -154,5 +158,6 @@ void mipi_i3c_hci_dct_index_reset(struct i3c_hci *hci); void amd_set_od_pp_timing(struct i3c_hci *hci); void amd_set_resp_buf_thld(struct i3c_hci *hci); void i3c_hci_sync_irq_inactive(struct i3c_hci *hci); +int i3c_hci_process_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n); #endif diff --git a/drivers/i3c/master/mipi-i3c-hci/pio.c b/drivers/i3c/master/mipi-i3c-hci/pio.c index f8825ac81408..8f48a81e65ab 100644 --- a/drivers/i3c/master/mipi-i3c-hci/pio.c +++ b/drivers/i3c/master/mipi-i3c-hci/pio.c @@ -123,7 +123,6 @@ struct hci_pio_ibi_data { }; struct hci_pio_data { - spinlock_t lock; struct hci_xfer *curr_xfer, *xfer_queue; struct hci_xfer *curr_rx, *rx_queue; struct hci_xfer *curr_tx, *tx_queue; @@ -212,7 +211,6 @@ static int hci_pio_init(struct i3c_hci *hci) return -ENOMEM; hci->io_data = pio; - spin_lock_init(&pio->lock); __hci_pio_init(hci, &size_val); @@ -631,7 +629,7 @@ static int hci_pio_queue_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n) xfer[i].data_left = xfer[i].data_len; } - spin_lock_irq(&pio->lock); + spin_lock_irq(&hci->lock); prev_queue_tail = pio->xfer_queue; pio->xfer_queue = &xfer[n - 1]; if (pio->curr_xfer) { @@ -645,7 +643,7 @@ static int hci_pio_queue_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n) pio_reg_read(INTR_STATUS), pio_reg_read(INTR_SIGNAL_ENABLE)); } - spin_unlock_irq(&pio->lock); + spin_unlock_irq(&hci->lock); return 0; } @@ -716,14 +714,14 @@ static bool hci_pio_dequeue_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int struct hci_pio_data *pio = hci->io_data; int ret; - spin_lock_irq(&pio->lock); + spin_lock_irq(&hci->lock); dev_dbg(&hci->master.dev, "n=%d status=%#x/%#x", n, pio_reg_read(INTR_STATUS), pio_reg_read(INTR_SIGNAL_ENABLE)); dev_dbg(&hci->master.dev, "main_status = %#x/%#x", readl(hci->base_regs + 0x20), readl(hci->base_regs + 0x28)); ret = hci_pio_dequeue_xfer_common(hci, pio, xfer, n); - spin_unlock_irq(&pio->lock); + spin_unlock_irq(&hci->lock); return ret; } @@ -1016,15 +1014,12 @@ static bool hci_pio_irq_handler(struct i3c_hci *hci) struct hci_pio_data *pio = hci->io_data; u32 status; - spin_lock(&pio->lock); status = pio_reg_read(INTR_STATUS); dev_dbg(&hci->master.dev, "PIO_INTR_STATUS %#x/%#x", status, pio->enabled_irqs); status &= pio->enabled_irqs | STAT_LATENCY_WARNINGS; - if (!status) { - spin_unlock(&pio->lock); + if (!status) return false; - } if (status & STAT_IBI_STATUS_THLD) hci_pio_process_ibi(hci, pio); @@ -1058,7 +1053,6 @@ static bool hci_pio_irq_handler(struct i3c_hci *hci) pio_reg_write(INTR_SIGNAL_ENABLE, pio->enabled_irqs); dev_dbg(&hci->master.dev, "PIO_INTR_STATUS %#x/%#x", pio_reg_read(INTR_STATUS), pio_reg_read(INTR_SIGNAL_ENABLE)); - spin_unlock(&pio->lock); return true; } diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c index fcd8aea7152e..e16dede687d3 100644 --- a/drivers/iio/adc/ad7768-1.c +++ b/drivers/iio/adc/ad7768-1.c @@ -531,7 +531,7 @@ static int ad7768_reg_access(struct iio_dev *indio_dev, return ret; } -static void ad7768_fill_scale_tbl(struct iio_dev *dev) +static int ad7768_fill_scale_tbl(struct iio_dev *dev) { struct ad7768_state *st = iio_priv(dev); const struct iio_scan_type *scan_type; @@ -541,6 +541,11 @@ static void ad7768_fill_scale_tbl(struct iio_dev *dev) u64 tmp2; scan_type = iio_get_current_scan_type(dev, &dev->channels[0]); + if (IS_ERR(scan_type)) { + dev_err(&st->spi->dev, "Failed to get scan type.\n"); + return PTR_ERR(scan_type); + } + if (scan_type->sign == 's') val2 = scan_type->realbits - 1; else @@ -565,6 +570,8 @@ static void ad7768_fill_scale_tbl(struct iio_dev *dev) st->scale_tbl[i][0] = tmp0; /* Integer part */ st->scale_tbl[i][1] = abs(tmp1); /* Fractional part */ } + + return 0; } static int ad7768_set_sinc3_dec_rate(struct ad7768_state *st, @@ -669,7 +676,9 @@ static int ad7768_configure_dig_fil(struct iio_dev *dev, } /* Update scale table: scale values vary according to the precision */ - ad7768_fill_scale_tbl(dev); + ret = ad7768_fill_scale_tbl(dev); + if (ret) + return ret; ad7768_fill_samp_freq_tbl(st); diff --git a/drivers/iio/chemical/bme680_core.c b/drivers/iio/chemical/bme680_core.c index 70f81c4a96ba..24e0b59e2fdf 100644 --- a/drivers/iio/chemical/bme680_core.c +++ b/drivers/iio/chemical/bme680_core.c @@ -613,7 +613,7 @@ static int bme680_wait_for_eoc(struct bme680_data *data) * + heater duration */ int wait_eoc_us = ((data->oversampling_temp + data->oversampling_press + - data->oversampling_humid) * 1936) + (477 * 4) + + data->oversampling_humid) * 1963) + (477 * 4) + (477 * 5) + 1000 + (data->heater_dur * 1000); fsleep(wait_eoc_us); diff --git a/drivers/iio/chemical/sps30_i2c.c b/drivers/iio/chemical/sps30_i2c.c index f692c089d17b..c92f04990c34 100644 --- a/drivers/iio/chemical/sps30_i2c.c +++ b/drivers/iio/chemical/sps30_i2c.c @@ -171,7 +171,7 @@ static int sps30_i2c_read_meas(struct sps30_state *state, __be32 *meas, size_t n if (!sps30_i2c_meas_ready(state)) return -ETIMEDOUT; - return sps30_i2c_command(state, SPS30_I2C_READ_MEAS, NULL, 0, meas, sizeof(num) * num); + return sps30_i2c_command(state, SPS30_I2C_READ_MEAS, NULL, 0, meas, sizeof(*meas) * num); } static int sps30_i2c_clean_fan(struct sps30_state *state) diff --git a/drivers/iio/chemical/sps30_serial.c b/drivers/iio/chemical/sps30_serial.c index 008bc88590f3..a5e6bc08d5fd 100644 --- a/drivers/iio/chemical/sps30_serial.c +++ b/drivers/iio/chemical/sps30_serial.c @@ -303,7 +303,7 @@ static int sps30_serial_read_meas(struct sps30_state *state, __be32 *meas, size_ if (msleep_interruptible(1000)) return -EINTR; - ret = sps30_serial_command(state, SPS30_SERIAL_READ_MEAS, NULL, 0, meas, num * sizeof(num)); + ret = sps30_serial_command(state, SPS30_SERIAL_READ_MEAS, NULL, 0, meas, num * sizeof(*meas)); if (ret < 0) return ret; /* if measurements aren't ready sensor returns empty frame */ diff --git a/drivers/iio/dac/ds4424.c b/drivers/iio/dac/ds4424.c index 6dda8918975a..c61868f2de31 100644 --- a/drivers/iio/dac/ds4424.c +++ b/drivers/iio/dac/ds4424.c @@ -140,7 +140,7 @@ static int ds4424_write_raw(struct iio_dev *indio_dev, switch (mask) { case IIO_CHAN_INFO_RAW: - if (val < S8_MIN || val > S8_MAX) + if (val <= S8_MIN || val > S8_MAX) return -EINVAL; if (val > 0) { diff --git a/drivers/iio/frequency/adf4377.c b/drivers/iio/frequency/adf4377.c index fa686f785fa4..8e2da218d48a 100644 --- a/drivers/iio/frequency/adf4377.c +++ b/drivers/iio/frequency/adf4377.c @@ -508,7 +508,7 @@ static int adf4377_soft_reset(struct adf4377_state *st) return ret; return regmap_read_poll_timeout(st->regmap, 0x0, read_val, - !(read_val & (ADF4377_0000_SOFT_RESET_R_MSK | + !(read_val & (ADF4377_0000_SOFT_RESET_MSK | ADF4377_0000_SOFT_RESET_R_MSK)), 200, 200 * 100); } diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c index ee2fcd20545d..317e7b217ec6 100644 --- a/drivers/iio/gyro/mpu3050-core.c +++ b/drivers/iio/gyro/mpu3050-core.c @@ -322,7 +322,9 @@ static int mpu3050_read_raw(struct iio_dev *indio_dev, } case IIO_CHAN_INFO_RAW: /* Resume device */ - pm_runtime_get_sync(mpu3050->dev); + ret = pm_runtime_resume_and_get(mpu3050->dev); + if (ret) + return ret; mutex_lock(&mpu3050->lock); ret = mpu3050_set_8khz_samplerate(mpu3050); @@ -647,14 +649,20 @@ out_trigger_unlock: static int mpu3050_buffer_preenable(struct iio_dev *indio_dev) { struct mpu3050 *mpu3050 = iio_priv(indio_dev); + int ret; - pm_runtime_get_sync(mpu3050->dev); + ret = pm_runtime_resume_and_get(mpu3050->dev); + if (ret) + return ret; /* Unless we have OUR trigger active, run at full speed */ - if (!mpu3050->hw_irq_trigger) - return mpu3050_set_8khz_samplerate(mpu3050); + if (!mpu3050->hw_irq_trigger) { + ret = mpu3050_set_8khz_samplerate(mpu3050); + if (ret) + pm_runtime_put_autosuspend(mpu3050->dev); + } - return 0; + return ret; } static int mpu3050_buffer_postdisable(struct iio_dev *indio_dev) diff --git a/drivers/iio/gyro/mpu3050-i2c.c b/drivers/iio/gyro/mpu3050-i2c.c index 092878f2c886..6549b22e643d 100644 --- a/drivers/iio/gyro/mpu3050-i2c.c +++ b/drivers/iio/gyro/mpu3050-i2c.c @@ -19,8 +19,7 @@ static int mpu3050_i2c_bypass_select(struct i2c_mux_core *mux, u32 chan_id) struct mpu3050 *mpu3050 = i2c_mux_priv(mux); /* Just power up the device, that is all that is needed */ - pm_runtime_get_sync(mpu3050->dev); - return 0; + return pm_runtime_resume_and_get(mpu3050->dev); } static int mpu3050_i2c_bypass_deselect(struct i2c_mux_core *mux, u32 chan_id) diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c index d160147cce0b..a2bc1d14ed91 100644 --- a/drivers/iio/imu/adis.c +++ b/drivers/iio/imu/adis.c @@ -526,7 +526,7 @@ int adis_init(struct adis *adis, struct iio_dev *indio_dev, adis->spi = spi; adis->data = data; - if (!adis->ops->write && !adis->ops->read && !adis->ops->reset) + if (!adis->ops) adis->ops = &adis_default_ops; else if (!adis->ops->write || !adis->ops->read || !adis->ops->reset) return -EINVAL; diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c index 54760d8f92a2..0ab6eddf0543 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c @@ -651,6 +651,8 @@ static int inv_icm42600_accel_write_odr(struct iio_dev *indio_dev, return -EINVAL; conf.odr = inv_icm42600_accel_odr_conv[idx / 2]; + if (conf.odr == st->conf.accel.odr) + return 0; pm_runtime_get_sync(dev); mutex_lock(&st->lock); diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c index ada968be954d..68a395758031 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c @@ -371,6 +371,8 @@ static int inv_icm42600_buffer_predisable(struct iio_dev *indio_dev) static int inv_icm42600_buffer_postdisable(struct iio_dev *indio_dev) { struct inv_icm42600_state *st = iio_device_get_drvdata(indio_dev); + struct inv_icm42600_sensor_state *sensor_st = iio_priv(indio_dev); + struct inv_sensors_timestamp *ts = &sensor_st->ts; struct device *dev = regmap_get_device(st->map); unsigned int sensor; unsigned int *watermark; @@ -392,6 +394,8 @@ static int inv_icm42600_buffer_postdisable(struct iio_dev *indio_dev) mutex_lock(&st->lock); + inv_sensors_timestamp_apply_odr(ts, 0, 0, 0); + ret = inv_icm42600_buffer_set_fifo_en(st, st->fifo.en & ~sensor); if (ret) goto out_unlock; diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c index 7ef0a25ec74f..11339ddf1da3 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c @@ -358,6 +358,8 @@ static int inv_icm42600_gyro_write_odr(struct iio_dev *indio_dev, return -EINVAL; conf.odr = inv_icm42600_gyro_odr_conv[idx / 2]; + if (conf.odr == st->conf.gyro.odr) + return 0; pm_runtime_get_sync(dev); mutex_lock(&st->lock); diff --git a/drivers/iio/imu/inv_icm45600/inv_icm45600.h b/drivers/iio/imu/inv_icm45600/inv_icm45600.h index c5b5446f6c3b..1c796d4b2a40 100644 --- a/drivers/iio/imu/inv_icm45600/inv_icm45600.h +++ b/drivers/iio/imu/inv_icm45600/inv_icm45600.h @@ -205,7 +205,7 @@ struct inv_icm45600_sensor_state { #define INV_ICM45600_SPI_SLEW_RATE_38NS 0 #define INV_ICM45600_REG_INT1_CONFIG2 0x0018 -#define INV_ICM45600_INT1_CONFIG2_PUSH_PULL BIT(2) +#define INV_ICM45600_INT1_CONFIG2_OPEN_DRAIN BIT(2) #define INV_ICM45600_INT1_CONFIG2_LATCHED BIT(1) #define INV_ICM45600_INT1_CONFIG2_ACTIVE_HIGH BIT(0) #define INV_ICM45600_INT1_CONFIG2_ACTIVE_LOW 0x00 diff --git a/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c b/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c index 25bd9757a594..d49053161a65 100644 --- a/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c +++ b/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c @@ -637,8 +637,8 @@ static int inv_icm45600_irq_init(struct inv_icm45600_state *st, int irq, break; } - if (!open_drain) - val |= INV_ICM45600_INT1_CONFIG2_PUSH_PULL; + if (open_drain) + val |= INV_ICM45600_INT1_CONFIG2_OPEN_DRAIN; ret = regmap_write(st->map, INV_ICM45600_REG_INT1_CONFIG2, val); if (ret) @@ -744,6 +744,11 @@ int inv_icm45600_core_probe(struct regmap *regmap, const struct inv_icm45600_chi */ fsleep(5 * USEC_PER_MSEC); + /* set pm_runtime active early for disable vddio resource cleanup */ + ret = pm_runtime_set_active(dev); + if (ret) + return ret; + ret = inv_icm45600_enable_regulator_vddio(st); if (ret) return ret; @@ -776,7 +781,7 @@ int inv_icm45600_core_probe(struct regmap *regmap, const struct inv_icm45600_chi if (ret) return ret; - ret = devm_pm_runtime_set_active_enabled(dev); + ret = devm_pm_runtime_enable(dev); if (ret) return ret; diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c index b2fa1f4957a5..5796896d54cd 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c @@ -1943,6 +1943,14 @@ int inv_mpu_core_probe(struct regmap *regmap, int irq, const char *name, irq_type); return -EINVAL; } + + /* + * Acking interrupts by status register does not work reliably + * but seem to work when this bit is set. + */ + if (st->chip_type == INV_MPU9150) + st->irq_mask |= INV_MPU6050_INT_RD_CLEAR; + device_set_wakeup_capable(dev, true); st->vdd_supply = devm_regulator_get(dev, "vdd"); diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h index 211901f8b8eb..6239b1a803f7 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h @@ -390,6 +390,8 @@ struct inv_mpu6050_state { /* enable level triggering */ #define INV_MPU6050_LATCH_INT_EN 0x20 #define INV_MPU6050_BIT_BYPASS_EN 0x2 +/* allow acking interrupts by any register read */ +#define INV_MPU6050_INT_RD_CLEAR 0x10 /* Allowed timestamp period jitter in percent */ #define INV_MPU6050_TS_PERIOD_JITTER 4 diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c index 10a473342075..22c1ce66f99e 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c @@ -248,7 +248,6 @@ static irqreturn_t inv_mpu6050_interrupt_handle(int irq, void *p) switch (st->chip_type) { case INV_MPU6000: case INV_MPU6050: - case INV_MPU9150: /* * WoM is not supported and interrupt status read seems to be broken for * some chips. Since data ready is the only interrupt, bypass interrupt @@ -257,6 +256,10 @@ static irqreturn_t inv_mpu6050_interrupt_handle(int irq, void *p) wom_bits = 0; int_status = INV_MPU6050_BIT_RAW_DATA_RDY_INT; goto data_ready_interrupt; + case INV_MPU9150: + /* IRQ needs to be acked */ + wom_bits = 0; + break; case INV_MPU6500: case INV_MPU6515: case INV_MPU6880: diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index f15a180dc49e..46f36a6ed271 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -228,8 +228,10 @@ static ssize_t iio_buffer_write(struct file *filp, const char __user *buf, written = 0; add_wait_queue(&rb->pollq, &wait); do { - if (!indio_dev->info) - return -ENODEV; + if (!indio_dev->info) { + ret = -ENODEV; + break; + } if (!iio_buffer_space_available(rb)) { if (signal_pending(current)) { diff --git a/drivers/iio/light/bh1780.c b/drivers/iio/light/bh1780.c index 5d3c6d5276ba..a740d1f992a8 100644 --- a/drivers/iio/light/bh1780.c +++ b/drivers/iio/light/bh1780.c @@ -109,9 +109,9 @@ static int bh1780_read_raw(struct iio_dev *indio_dev, case IIO_LIGHT: pm_runtime_get_sync(&bh1780->client->dev); value = bh1780_read_word(bh1780, BH1780_REG_DLOW); + pm_runtime_put_autosuspend(&bh1780->client->dev); if (value < 0) return value; - pm_runtime_put_autosuspend(&bh1780->client->dev); *val = value; return IIO_VAL_INT; diff --git a/drivers/iio/magnetometer/Kconfig b/drivers/iio/magnetometer/Kconfig index 9345fb6d5317..fb313e591e85 100644 --- a/drivers/iio/magnetometer/Kconfig +++ b/drivers/iio/magnetometer/Kconfig @@ -143,8 +143,7 @@ config MMC5633 tristate "MEMSIC MMC5633 3-axis magnetic sensor" select REGMAP_I2C select REGMAP_I3C if I3C - depends on I2C - depends on I3C || !I3C + depends on I3C_OR_I2C help Say yes here to build support for the MEMSIC MMC5633 3-axis magnetic sensor. diff --git a/drivers/iio/magnetometer/tlv493d.c b/drivers/iio/magnetometer/tlv493d.c index ec53fd40277b..e5e050af2b74 100644 --- a/drivers/iio/magnetometer/tlv493d.c +++ b/drivers/iio/magnetometer/tlv493d.c @@ -171,7 +171,7 @@ static s16 tlv493d_get_channel_data(u8 *b, enum tlv493d_channels ch) switch (ch) { case TLV493D_AXIS_X: val = FIELD_GET(TLV493D_BX_MAG_X_AXIS_MSB, b[TLV493D_RD_REG_BX]) << 4 | - FIELD_GET(TLV493D_BX2_MAG_X_AXIS_LSB, b[TLV493D_RD_REG_BX2]) >> 4; + FIELD_GET(TLV493D_BX2_MAG_X_AXIS_LSB, b[TLV493D_RD_REG_BX2]); break; case TLV493D_AXIS_Y: val = FIELD_GET(TLV493D_BY_MAG_Y_AXIS_MSB, b[TLV493D_RD_REG_BY]) << 4 | diff --git a/drivers/iio/potentiometer/mcp4131.c b/drivers/iio/potentiometer/mcp4131.c index ad082827aad5..56c9111ef5e8 100644 --- a/drivers/iio/potentiometer/mcp4131.c +++ b/drivers/iio/potentiometer/mcp4131.c @@ -221,7 +221,7 @@ static int mcp4131_write_raw(struct iio_dev *indio_dev, mutex_lock(&data->lock); - data->buf[0] = address << MCP4131_WIPER_SHIFT; + data->buf[0] = address; data->buf[0] |= MCP4131_WRITE | (val >> 8); data->buf[1] = val & 0xFF; /* 8 bits here */ diff --git a/drivers/iio/proximity/hx9023s.c b/drivers/iio/proximity/hx9023s.c index 2918dfc0df54..17e00ee2b6f8 100644 --- a/drivers/iio/proximity/hx9023s.c +++ b/drivers/iio/proximity/hx9023s.c @@ -719,6 +719,9 @@ static int hx9023s_set_samp_freq(struct hx9023s_data *data, int val, int val2) struct device *dev = regmap_get_device(data->regmap); unsigned int i, period_ms; + if (!val && !val2) + return -EINVAL; + period_ms = div_u64(NANO, (val * MEGA + val2)); for (i = 0; i < ARRAY_SIZE(hx9023s_samp_freq_table); i++) { @@ -1034,9 +1037,8 @@ static int hx9023s_send_cfg(const struct firmware *fw, struct hx9023s_data *data if (!bin) return -ENOMEM; - memcpy(bin->data, fw->data, fw->size); - bin->fw_size = fw->size; + memcpy(bin->data, fw->data, bin->fw_size); bin->fw_ver = bin->data[FW_VER_OFFSET]; bin->reg_count = get_unaligned_le16(bin->data + FW_REG_CNT_OFFSET); diff --git a/drivers/irqchip/irq-riscv-aplic-main.c b/drivers/irqchip/irq-riscv-aplic-main.c index 4495ca26abf5..9f53979b6962 100644 --- a/drivers/irqchip/irq-riscv-aplic-main.c +++ b/drivers/irqchip/irq-riscv-aplic-main.c @@ -116,6 +116,16 @@ static struct syscore aplic_syscore = { .ops = &aplic_syscore_ops, }; +static bool aplic_syscore_registered __ro_after_init; + +static void aplic_syscore_init(void) +{ + if (!aplic_syscore_registered) { + register_syscore(&aplic_syscore); + aplic_syscore_registered = true; + } +} + static int aplic_pm_notifier(struct notifier_block *nb, unsigned long action, void *data) { struct aplic_priv *priv = container_of(nb, struct aplic_priv, genpd_nb); @@ -372,18 +382,21 @@ static int aplic_probe(struct platform_device *pdev) rc = aplic_msi_setup(dev, regs); else rc = aplic_direct_setup(dev, regs); - if (rc) + + if (rc) { dev_err_probe(dev, rc, "failed to setup APLIC in %s mode\n", msi_mode ? "MSI" : "direct"); - else - register_syscore(&aplic_syscore); + return rc; + } + + aplic_syscore_init(); #ifdef CONFIG_ACPI if (!acpi_disabled) acpi_dev_clear_dependencies(ACPI_COMPANION(dev)); #endif - return rc; + return 0; } static const struct of_device_id aplic_match[] = { diff --git a/drivers/misc/amd-sbi/Kconfig b/drivers/misc/amd-sbi/Kconfig index be022c71a90c..30e7fad7356c 100644 --- a/drivers/misc/amd-sbi/Kconfig +++ b/drivers/misc/amd-sbi/Kconfig @@ -1,10 +1,9 @@ # SPDX-License-Identifier: GPL-2.0-only config AMD_SBRMI_I2C tristate "AMD side band RMI support" - depends on I2C + depends on I3C_OR_I2C depends on ARM || ARM64 || COMPILE_TEST select REGMAP_I2C - depends on I3C || !I3C select REGMAP_I3C if I3C help Side band RMI over I2C/I3C support for AMD out of band management. diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index bd9621d3f73c..45b7d756e39a 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -486,14 +486,15 @@ EXPORT_SYMBOL_GPL(nd_synchronize); static void nd_async_device_register(void *d, async_cookie_t cookie) { struct device *dev = d; + struct device *parent = dev->parent; if (device_add(dev) != 0) { dev_err(dev, "%s: failed\n", __func__); put_device(dev); } put_device(dev); - if (dev->parent) - put_device(dev->parent); + if (parent) + put_device(parent); } static void nd_async_device_unregister(void *d, async_cookie_t cookie) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 58bf432ec5e6..766e9cc4ffca 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4834,7 +4834,6 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event); int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, const struct blk_mq_ops *ops, unsigned int cmd_size) { - struct queue_limits lim = {}; int ret; memset(set, 0, sizeof(*set)); @@ -4861,7 +4860,7 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, if (ctrl->admin_q) blk_put_queue(ctrl->admin_q); - ctrl->admin_q = blk_mq_alloc_queue(set, &lim, NULL); + ctrl->admin_q = blk_mq_alloc_queue(set, NULL, NULL); if (IS_ERR(ctrl->admin_q)) { ret = PTR_ERR(ctrl->admin_q); goto out_free_tagset; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 8d09fa7d7ff9..b78ba239c8ea 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -544,7 +544,7 @@ static void nvme_dbbuf_set(struct nvme_dev *dev) /* Free memory and continue on */ nvme_dbbuf_dma_free(dev); - for (i = 1; i <= dev->online_queues; i++) + for (i = 1; i < dev->online_queues; i++) nvme_dbbuf_free(&dev->queues[i]); } } @@ -1625,14 +1625,16 @@ static irqreturn_t nvme_irq_check(int irq, void *data) static void nvme_poll_irqdisable(struct nvme_queue *nvmeq) { struct pci_dev *pdev = to_pci_dev(nvmeq->dev->dev); + int irq; WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags)); - disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)); + irq = pci_irq_vector(pdev, nvmeq->cq_vector); + disable_irq(irq); spin_lock(&nvmeq->cq_poll_lock); nvme_poll_cq(nvmeq, NULL); spin_unlock(&nvmeq->cq_poll_lock); - enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)); + enable_irq(irq); } static int nvme_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 9de93f65d7d7..ca5b08ce1211 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -1585,7 +1585,7 @@ void nvmet_execute_async_event(struct nvmet_req *req) ctrl->async_event_cmds[ctrl->nr_async_event_cmds++] = req; mutex_unlock(&ctrl->lock); - queue_work(nvmet_wq, &ctrl->async_event_work); + queue_work(nvmet_aen_wq, &ctrl->async_event_work); } void nvmet_execute_keep_alive(struct nvmet_req *req) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 5e43d0acc86e..9238e13bd480 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -27,6 +27,8 @@ static DEFINE_IDA(cntlid_ida); struct workqueue_struct *nvmet_wq; EXPORT_SYMBOL_GPL(nvmet_wq); +struct workqueue_struct *nvmet_aen_wq; +EXPORT_SYMBOL_GPL(nvmet_aen_wq); /* * This read/write semaphore is used to synchronize access to configuration @@ -206,7 +208,7 @@ void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type, list_add_tail(&aen->entry, &ctrl->async_events); mutex_unlock(&ctrl->lock); - queue_work(nvmet_wq, &ctrl->async_event_work); + queue_work(nvmet_aen_wq, &ctrl->async_event_work); } static void nvmet_add_to_changed_ns_log(struct nvmet_ctrl *ctrl, __le32 nsid) @@ -1956,9 +1958,14 @@ static int __init nvmet_init(void) if (!nvmet_wq) goto out_free_buffered_work_queue; + nvmet_aen_wq = alloc_workqueue("nvmet-aen-wq", + WQ_MEM_RECLAIM | WQ_UNBOUND, 0); + if (!nvmet_aen_wq) + goto out_free_nvmet_work_queue; + error = nvmet_init_debugfs(); if (error) - goto out_free_nvmet_work_queue; + goto out_free_nvmet_aen_work_queue; error = nvmet_init_discovery(); if (error) @@ -1974,6 +1981,8 @@ out_exit_discovery: nvmet_exit_discovery(); out_exit_debugfs: nvmet_exit_debugfs(); +out_free_nvmet_aen_work_queue: + destroy_workqueue(nvmet_aen_wq); out_free_nvmet_work_queue: destroy_workqueue(nvmet_wq); out_free_buffered_work_queue: @@ -1991,6 +2000,7 @@ static void __exit nvmet_exit(void) nvmet_exit_discovery(); nvmet_exit_debugfs(); ida_destroy(&cntlid_ida); + destroy_workqueue(nvmet_aen_wq); destroy_workqueue(nvmet_wq); destroy_workqueue(buffered_io_wq); destroy_workqueue(zbd_wq); diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index b664b584fdc8..319d6a5e9cf0 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -501,6 +501,7 @@ extern struct kmem_cache *nvmet_bvec_cache; extern struct workqueue_struct *buffered_io_wq; extern struct workqueue_struct *zbd_wq; extern struct workqueue_struct *nvmet_wq; +extern struct workqueue_struct *nvmet_aen_wq; static inline void nvmet_set_result(struct nvmet_req *req, u32 result) { diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 2d6eb89f98af..e6e2c3f9afdf 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -2087,6 +2087,7 @@ static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data mutex_unlock(&nvmet_rdma_queue_mutex); flush_workqueue(nvmet_wq); + flush_workqueue(nvmet_aen_wq); } static struct ib_client nvmet_rdma_ib_client = { diff --git a/drivers/power/sequencing/pwrseq-pcie-m2.c b/drivers/power/sequencing/pwrseq-pcie-m2.c index d31a7dd8b35c..dadb4aad9d5d 100644 --- a/drivers/power/sequencing/pwrseq-pcie-m2.c +++ b/drivers/power/sequencing/pwrseq-pcie-m2.c @@ -109,7 +109,7 @@ static int pwrseq_pcie_m2_probe(struct platform_device *pdev) if (!ctx) return -ENOMEM; - ctx->of_node = of_node_get(dev->of_node); + ctx->of_node = dev_of_node(dev); ctx->pdata = device_get_match_data(dev); if (!ctx->pdata) return dev_err_probe(dev, -ENODEV, diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index 5fa868264250..45d7dc44c2cd 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -1293,6 +1293,7 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) struct regulator_dev *ldo5; struct pca9450 *pca9450; unsigned int device_id, i; + const char *type_name; int ret; pca9450 = devm_kzalloc(&i2c->dev, sizeof(struct pca9450), GFP_KERNEL); @@ -1303,15 +1304,22 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) case PCA9450_TYPE_PCA9450A: regulator_desc = pca9450a_regulators; pca9450->rcnt = ARRAY_SIZE(pca9450a_regulators); + type_name = "pca9450a"; break; case PCA9450_TYPE_PCA9450BC: regulator_desc = pca9450bc_regulators; pca9450->rcnt = ARRAY_SIZE(pca9450bc_regulators); + type_name = "pca9450bc"; break; case PCA9450_TYPE_PCA9451A: + regulator_desc = pca9451a_regulators; + pca9450->rcnt = ARRAY_SIZE(pca9451a_regulators); + type_name = "pca9451a"; + break; case PCA9450_TYPE_PCA9452: regulator_desc = pca9451a_regulators; pca9450->rcnt = ARRAY_SIZE(pca9451a_regulators); + type_name = "pca9452"; break; default: dev_err(&i2c->dev, "Unknown device type"); @@ -1369,7 +1377,7 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) if (pca9450->irq) { ret = devm_request_threaded_irq(pca9450->dev, pca9450->irq, NULL, pca9450_irq_handler, - (IRQF_TRIGGER_FALLING | IRQF_ONESHOT), + (IRQF_TRIGGER_LOW | IRQF_ONESHOT), "pca9450-irq", pca9450); if (ret != 0) return dev_err_probe(pca9450->dev, ret, "Failed to request IRQ: %d\n", @@ -1413,9 +1421,7 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) pca9450_i2c_restart_handler, pca9450)) dev_warn(&i2c->dev, "Failed to register restart handler\n"); - dev_info(&i2c->dev, "%s probed.\n", - type == PCA9450_TYPE_PCA9450A ? "pca9450a" : - (type == PCA9450_TYPE_PCA9451A ? "pca9451a" : "pca9450bc")); + dev_info(&i2c->dev, "%s probed.\n", type_name); return 0; } diff --git a/drivers/reset/reset-rzg2l-usbphy-ctrl.c b/drivers/reset/reset-rzg2l-usbphy-ctrl.c index 32bc268c9149..05dd9b4a02df 100644 --- a/drivers/reset/reset-rzg2l-usbphy-ctrl.c +++ b/drivers/reset/reset-rzg2l-usbphy-ctrl.c @@ -136,6 +136,9 @@ static int rzg2l_usbphy_ctrl_set_pwrrdy(struct regmap_field *pwrrdy, { u32 val = power_on ? 0 : 1; + if (!pwrrdy) + return 0; + /* The initialization path guarantees that the mask is 1 bit long. */ return regmap_field_update_bits(pwrrdy, 1, val); } diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index cb068d5e2145..14e58c336baa 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -6135,6 +6135,7 @@ static void copy_pair_set_active(struct dasd_copy_relation *copy, char *new_busi static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid, char *sec_busid) { + struct dasd_eckd_private *prim_priv, *sec_priv; struct dasd_device *primary, *secondary; struct dasd_copy_relation *copy; struct dasd_block *block; @@ -6155,6 +6156,9 @@ static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid if (!secondary) return DASD_COPYPAIRSWAP_SECONDARY; + prim_priv = primary->private; + sec_priv = secondary->private; + /* * usually the device should be quiesced for swap * for paranoia stop device and requeue requests again @@ -6182,6 +6186,18 @@ static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid dev_name(&secondary->cdev->dev), rc); } + if (primary->stopped & DASD_STOPPED_QUIESCE) { + dasd_device_set_stop_bits(secondary, DASD_STOPPED_QUIESCE); + dasd_device_remove_stop_bits(primary, DASD_STOPPED_QUIESCE); + } + + /* + * The secondary device never got through format detection, but since it + * is a copy of the primary device, the format is exactly the same; + * therefore, the detected layout can simply be copied. + */ + sec_priv->uses_cdl = prim_priv->uses_cdl; + /* re-enable device */ dasd_device_remove_stop_bits(primary, DASD_STOPPED_PPRC); dasd_device_remove_stop_bits(secondary, DASD_STOPPED_PPRC); diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index 573bad1d6d86..37a157a1d969 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -1639,11 +1639,13 @@ int cca_get_info(u16 cardnr, u16 domain, struct cca_info *ci, u32 xflags) memset(ci, 0, sizeof(*ci)); - /* get first info from zcrypt device driver about this apqn */ - rc = zcrypt_device_status_ext(cardnr, domain, &devstat); - if (rc) - return rc; - ci->hwtype = devstat.hwtype; + /* if specific domain given, fetch status and hw info for this apqn */ + if (domain != AUTOSEL_DOM) { + rc = zcrypt_device_status_ext(cardnr, domain, &devstat); + if (rc) + return rc; + ci->hwtype = devstat.hwtype; + } /* * Prep memory for rule array and var array use. diff --git a/drivers/s390/crypto/zcrypt_cex4.c b/drivers/s390/crypto/zcrypt_cex4.c index e9a984903bff..e7b0ed26a9ec 100644 --- a/drivers/s390/crypto/zcrypt_cex4.c +++ b/drivers/s390/crypto/zcrypt_cex4.c @@ -85,8 +85,7 @@ static ssize_t cca_serialnr_show(struct device *dev, memset(&ci, 0, sizeof(ci)); - if (ap_domain_index >= 0) - cca_get_info(ac->id, ap_domain_index, &ci, 0); + cca_get_info(ac->id, AUTOSEL_DOM, &ci, 0); return sysfs_emit(buf, "%s\n", ci.serial); } diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 30a9c6612651..c2b082f1252c 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -2578,7 +2578,7 @@ int hisi_sas_probe(struct platform_device *pdev, shost->transportt = hisi_sas_stt; shost->max_id = HISI_SAS_MAX_DEVICES; shost->max_lun = ~0; - shost->max_channel = 1; + shost->max_channel = 0; shost->max_cmd_len = HISI_SAS_MAX_CDB_LEN; if (hisi_hba->hw->slot_index_alloc) { shost->can_queue = HISI_SAS_MAX_COMMANDS; diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 2f9e01717ef3..f69efc6494b8 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -4993,7 +4993,7 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id) shost->transportt = hisi_sas_stt; shost->max_id = HISI_SAS_MAX_DEVICES; shost->max_lun = ~0; - shost->max_channel = 1; + shost->max_channel = 0; shost->max_cmd_len = HISI_SAS_MAX_CDB_LEN; shost->can_queue = HISI_SAS_UNRESERVED_IPTT; shost->cmd_per_lun = HISI_SAS_UNRESERVED_IPTT; diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index 9038f6723444..dbe3cd4e274c 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -2751,7 +2751,6 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, if (!elsio->u.els_logo.els_logo_pyld) { /* ref: INIT */ kref_put(&sp->cmd_kref, qla2x00_sp_release); - qla2x00_free_fcport(fcport); return QLA_FUNCTION_FAILED; } @@ -2776,7 +2775,6 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, if (rval != QLA_SUCCESS) { /* ref: INIT */ kref_put(&sp->cmd_kref, qla2x00_sp_release); - qla2x00_free_fcport(fcport); return QLA_FUNCTION_FAILED; } diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 2cfcf1f5d6a4..7b11bc7de0e3 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -360,12 +360,8 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget, * default device queue depth to figure out sbitmap shift * since we use this queue depth most of times. */ - if (scsi_realloc_sdev_budget_map(sdev, depth)) { - kref_put(&sdev->host->tagset_refcnt, scsi_mq_free_tags); - put_device(&starget->dev); - kfree(sdev); - goto out; - } + if (scsi_realloc_sdev_budget_map(sdev, depth)) + goto out_device_destroy; scsi_change_queue_depth(sdev, depth); diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index 411381f1a1c4..9ddafcb18f1c 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -1827,6 +1827,8 @@ EXPORT_SYMBOL(qman_create_fq); void qman_destroy_fq(struct qman_fq *fq) { + int leaked; + /* * We don't need to lock the FQ as it is a pre-condition that the FQ be * quiesced. Instead, run some checks. @@ -1834,11 +1836,29 @@ void qman_destroy_fq(struct qman_fq *fq) switch (fq->state) { case qman_fq_state_parked: case qman_fq_state_oos: - if (fq_isset(fq, QMAN_FQ_FLAG_DYNAMIC_FQID)) - qman_release_fqid(fq->fqid); + /* + * There's a race condition here on releasing the fqid, + * setting the fq_table to NULL, and freeing the fqid. + * To prevent it, this order should be respected: + */ + if (fq_isset(fq, QMAN_FQ_FLAG_DYNAMIC_FQID)) { + leaked = qman_shutdown_fq(fq->fqid); + if (leaked) + pr_debug("FQID %d leaked\n", fq->fqid); + } DPAA_ASSERT(fq_table[fq->idx]); fq_table[fq->idx] = NULL; + + if (fq_isset(fq, QMAN_FQ_FLAG_DYNAMIC_FQID) && !leaked) { + /* + * fq_table[fq->idx] should be set to null before + * freeing fq->fqid otherwise it could by allocated by + * qman_alloc_fqid() while still being !NULL + */ + smp_wmb(); + gen_pool_free(qm_fqalloc, fq->fqid | DPAA_GENALLOC_OFF, 1); + } return; default: break; diff --git a/drivers/soc/fsl/qe/qmc.c b/drivers/soc/fsl/qe/qmc.c index c4587b32a59b..672adff8e35f 100644 --- a/drivers/soc/fsl/qe/qmc.c +++ b/drivers/soc/fsl/qe/qmc.c @@ -1790,8 +1790,8 @@ static int qmc_qe_init_resources(struct qmc *qmc, struct platform_device *pdev) return -EINVAL; qmc->dpram_offset = res->start - qe_muram_dma(qe_muram_addr(0)); qmc->dpram = devm_ioremap_resource(qmc->dev, res); - if (IS_ERR(qmc->scc_pram)) - return PTR_ERR(qmc->scc_pram); + if (IS_ERR(qmc->dpram)) + return PTR_ERR(qmc->dpram); return 0; } diff --git a/drivers/soc/microchip/mpfs-sys-controller.c b/drivers/soc/microchip/mpfs-sys-controller.c index 8e7ae3cb92ff..10b2fc39da66 100644 --- a/drivers/soc/microchip/mpfs-sys-controller.c +++ b/drivers/soc/microchip/mpfs-sys-controller.c @@ -142,8 +142,10 @@ static int mpfs_sys_controller_probe(struct platform_device *pdev) sys_controller->flash = of_get_mtd_device_by_node(np); of_node_put(np); - if (IS_ERR(sys_controller->flash)) - return dev_err_probe(dev, PTR_ERR(sys_controller->flash), "Failed to get flash\n"); + if (IS_ERR(sys_controller->flash)) { + ret = dev_err_probe(dev, PTR_ERR(sys_controller->flash), "Failed to get flash\n"); + goto out_free; + } no_flash: sys_controller->client.dev = dev; @@ -155,8 +157,7 @@ no_flash: if (IS_ERR(sys_controller->chan)) { ret = dev_err_probe(dev, PTR_ERR(sys_controller->chan), "Failed to get mbox channel\n"); - kfree(sys_controller); - return ret; + goto out_free; } init_completion(&sys_controller->c); @@ -174,6 +175,10 @@ no_flash: dev_info(&pdev->dev, "Registered MPFS system controller\n"); return 0; + +out_free: + kfree(sys_controller); + return ret; } static void mpfs_sys_controller_remove(struct platform_device *pdev) diff --git a/drivers/soc/rockchip/grf.c b/drivers/soc/rockchip/grf.c index 04937c40da47..b459607c118a 100644 --- a/drivers/soc/rockchip/grf.c +++ b/drivers/soc/rockchip/grf.c @@ -231,6 +231,7 @@ static int __init rockchip_grf_init(void) grf = syscon_node_to_regmap(np); if (IS_ERR(grf)) { pr_err("%s: could not get grf syscon\n", __func__); + of_node_put(np); return PTR_ERR(grf); } diff --git a/drivers/spi/spi-amlogic-spifc-a4.c b/drivers/spi/spi-amlogic-spifc-a4.c index 2aef528cfc1b..3956869cfec1 100644 --- a/drivers/spi/spi-amlogic-spifc-a4.c +++ b/drivers/spi/spi-amlogic-spifc-a4.c @@ -411,7 +411,7 @@ static int aml_sfc_dma_buffer_setup(struct aml_sfc *sfc, void *databuf, ret = dma_mapping_error(sfc->dev, sfc->daddr); if (ret) { dev_err(sfc->dev, "DMA mapping error\n"); - goto out_map_data; + return ret; } cmd = CMD_DATA_ADDRL(sfc->daddr); @@ -429,7 +429,6 @@ static int aml_sfc_dma_buffer_setup(struct aml_sfc *sfc, void *databuf, ret = dma_mapping_error(sfc->dev, sfc->iaddr); if (ret) { dev_err(sfc->dev, "DMA mapping error\n"); - dma_unmap_single(sfc->dev, sfc->daddr, datalen, dir); goto out_map_data; } @@ -448,7 +447,7 @@ static int aml_sfc_dma_buffer_setup(struct aml_sfc *sfc, void *databuf, return 0; out_map_info: - dma_unmap_single(sfc->dev, sfc->iaddr, datalen, dir); + dma_unmap_single(sfc->dev, sfc->iaddr, infolen, dir); out_map_data: dma_unmap_single(sfc->dev, sfc->daddr, datalen, dir); diff --git a/drivers/spi/spi-atcspi200.c b/drivers/spi/spi-atcspi200.c index 60a37ff5c6f5..2665f31a49ce 100644 --- a/drivers/spi/spi-atcspi200.c +++ b/drivers/spi/spi-atcspi200.c @@ -195,7 +195,15 @@ static void atcspi_set_trans_ctl(struct atcspi_dev *spi, if (op->addr.buswidth > 1) tc |= TRANS_ADDR_FMT; if (op->data.nbytes) { - tc |= TRANS_DUAL_QUAD(ffs(op->data.buswidth) - 1); + unsigned int width_code; + + width_code = ffs(op->data.buswidth) - 1; + if (unlikely(width_code > 3)) { + WARN_ON_ONCE(1); + width_code = 0; + } + tc |= TRANS_DUAL_QUAD(width_code); + if (op->data.dir == SPI_MEM_DATA_IN) { if (op->dummy.nbytes) tc |= TRANS_MODE_DMY_READ | @@ -497,31 +505,17 @@ static int atcspi_init_resources(struct platform_device *pdev, static int atcspi_configure_dma(struct atcspi_dev *spi) { - struct dma_chan *dma_chan; - int ret = 0; + spi->host->dma_rx = devm_dma_request_chan(spi->dev, "rx"); + if (IS_ERR(spi->host->dma_rx)) + return PTR_ERR(spi->host->dma_rx); - dma_chan = devm_dma_request_chan(spi->dev, "rx"); - if (IS_ERR(dma_chan)) { - ret = PTR_ERR(dma_chan); - goto err_exit; - } - spi->host->dma_rx = dma_chan; + spi->host->dma_tx = devm_dma_request_chan(spi->dev, "tx"); + if (IS_ERR(spi->host->dma_tx)) + return PTR_ERR(spi->host->dma_tx); - dma_chan = devm_dma_request_chan(spi->dev, "tx"); - if (IS_ERR(dma_chan)) { - ret = PTR_ERR(dma_chan); - goto free_rx; - } - spi->host->dma_tx = dma_chan; init_completion(&spi->dma_completion); - return ret; - -free_rx: - dma_release_channel(spi->host->dma_rx); - spi->host->dma_rx = NULL; -err_exit: - return ret; + return 0; } static int atcspi_enable_clk(struct atcspi_dev *spi) diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 649ff55333f0..5fb0cb07c110 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -76,6 +76,11 @@ struct cqspi_flash_pdata { u8 cs; }; +static const struct clk_bulk_data cqspi_clks[CLK_QSPI_NUM] = { + [CLK_QSPI_APB] = { .id = "apb" }, + [CLK_QSPI_AHB] = { .id = "ahb" }, +}; + struct cqspi_st { struct platform_device *pdev; struct spi_controller *host; @@ -1823,6 +1828,7 @@ static int cqspi_probe(struct platform_device *pdev) } /* Obtain QSPI clocks. */ + memcpy(&cqspi->clks, &cqspi_clks, sizeof(cqspi->clks)); ret = devm_clk_bulk_get_optional(dev, CLK_QSPI_NUM, cqspi->clks); if (ret) return dev_err_probe(dev, ret, "Failed to get clocks\n"); diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c index bce3d149bea1..d8ef8f89330a 100644 --- a/drivers/spi/spi-intel-pci.c +++ b/drivers/spi/spi-intel-pci.c @@ -96,6 +96,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = { { PCI_VDEVICE(INTEL, 0xa324), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0xa3a4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0xa823), (unsigned long)&cnl_info }, + { PCI_VDEVICE(INTEL, 0xd323), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0xe323), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0xe423), (unsigned long)&cnl_info }, { }, diff --git a/drivers/spi/spi-rockchip-sfc.c b/drivers/spi/spi-rockchip-sfc.c index 2990bf85ee47..174995042f53 100644 --- a/drivers/spi/spi-rockchip-sfc.c +++ b/drivers/spi/spi-rockchip-sfc.c @@ -711,7 +711,7 @@ static int rockchip_sfc_probe(struct platform_device *pdev) } } - ret = devm_spi_register_controller(dev, host); + ret = spi_register_controller(host); if (ret) goto err_register; diff --git a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c index 6cf217e21593..3e2b5e6b07f9 100644 --- a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c +++ b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c @@ -186,20 +186,25 @@ u8 *rtw_get_ie_ex(u8 *in_ie, uint in_len, u8 eid, u8 *oui, u8 oui_len, u8 *ie, u cnt = 0; - while (cnt < in_len) { + while (cnt + 2 <= in_len) { + u8 ie_len = in_ie[cnt + 1]; + + if (cnt + 2 + ie_len > in_len) + break; + if (eid == in_ie[cnt] - && (!oui || !memcmp(&in_ie[cnt+2], oui, oui_len))) { + && (!oui || (ie_len >= oui_len && !memcmp(&in_ie[cnt + 2], oui, oui_len)))) { target_ie = &in_ie[cnt]; if (ie) - memcpy(ie, &in_ie[cnt], in_ie[cnt+1]+2); + memcpy(ie, &in_ie[cnt], ie_len + 2); if (ielen) - *ielen = in_ie[cnt+1]+2; + *ielen = ie_len + 2; break; } - cnt += in_ie[cnt+1]+2; /* goto next */ + cnt += ie_len + 2; /* goto next */ } return target_ie; diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme.c b/drivers/staging/rtl8723bs/core/rtw_mlme.c index 7df651708381..1ef48bf6581c 100644 --- a/drivers/staging/rtl8723bs/core/rtw_mlme.c +++ b/drivers/staging/rtl8723bs/core/rtw_mlme.c @@ -1988,7 +1988,10 @@ int rtw_restruct_wmm_ie(struct adapter *adapter, u8 *in_ie, u8 *out_ie, uint in_ while (i < in_len) { ielength = initial_out_len; - if (in_ie[i] == 0xDD && in_ie[i + 2] == 0x00 && in_ie[i + 3] == 0x50 && in_ie[i + 4] == 0xF2 && in_ie[i + 5] == 0x02 && i + 5 < in_len) { /* WMM element ID and OUI */ + if (i + 5 < in_len && + in_ie[i] == 0xDD && in_ie[i + 2] == 0x00 && + in_ie[i + 3] == 0x50 && in_ie[i + 4] == 0xF2 && + in_ie[i + 5] == 0x02) { for (j = i; j < i + 9; j++) { out_ie[ielength] = in_ie[j]; ielength++; diff --git a/drivers/staging/sm750fb/sm750.c b/drivers/staging/sm750fb/sm750.c index dec1f6b88a7d..62f6e0cdff4d 100644 --- a/drivers/staging/sm750fb/sm750.c +++ b/drivers/staging/sm750fb/sm750.c @@ -1123,6 +1123,7 @@ static void lynxfb_pci_remove(struct pci_dev *pdev) iounmap(sm750_dev->pvReg); iounmap(sm750_dev->pvMem); + pci_release_region(pdev, 1); kfree(g_settings); } diff --git a/drivers/staging/sm750fb/sm750_hw.c b/drivers/staging/sm750fb/sm750_hw.c index a29faee91c78..f60b152a647d 100644 --- a/drivers/staging/sm750fb/sm750_hw.c +++ b/drivers/staging/sm750fb/sm750_hw.c @@ -36,16 +36,11 @@ int hw_sm750_map(struct sm750_dev *sm750_dev, struct pci_dev *pdev) pr_info("mmio phyAddr = %lx\n", sm750_dev->vidreg_start); - /* - * reserve the vidreg space of smi adaptor - * if you do this, you need to add release region code - * in lynxfb_remove, or memory will not be mapped again - * successfully - */ + /* reserve the vidreg space of smi adaptor */ ret = pci_request_region(pdev, 1, "sm750fb"); if (ret) { pr_err("Can not request PCI regions.\n"); - goto exit; + return ret; } /* now map mmio and vidmem */ @@ -54,7 +49,7 @@ int hw_sm750_map(struct sm750_dev *sm750_dev, struct pci_dev *pdev) if (!sm750_dev->pvReg) { pr_err("mmio failed\n"); ret = -EFAULT; - goto exit; + goto err_release_region; } pr_info("mmio virtual addr = %p\n", sm750_dev->pvReg); @@ -79,13 +74,18 @@ int hw_sm750_map(struct sm750_dev *sm750_dev, struct pci_dev *pdev) sm750_dev->pvMem = ioremap_wc(sm750_dev->vidmem_start, sm750_dev->vidmem_size); if (!sm750_dev->pvMem) { - iounmap(sm750_dev->pvReg); pr_err("Map video memory failed\n"); ret = -EFAULT; - goto exit; + goto err_unmap_reg; } pr_info("video memory vaddr = %p\n", sm750_dev->pvMem); -exit: + + return 0; + +err_unmap_reg: + iounmap(sm750_dev->pvReg); +err_release_region: + pci_release_region(pdev, 1); return ret; } diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index 6c5b9e352e5e..e9ea9f80cfd9 100644 --- a/drivers/tee/tee_shm.c +++ b/drivers/tee/tee_shm.c @@ -23,29 +23,11 @@ struct tee_shm_dma_mem { struct page *page; }; -static void shm_put_kernel_pages(struct page **pages, size_t page_count) -{ - size_t n; - - for (n = 0; n < page_count; n++) - put_page(pages[n]); -} - -static void shm_get_kernel_pages(struct page **pages, size_t page_count) -{ - size_t n; - - for (n = 0; n < page_count; n++) - get_page(pages[n]); -} - static void release_registered_pages(struct tee_shm *shm) { if (shm->pages) { if (shm->flags & TEE_SHM_USER_MAPPED) unpin_user_pages(shm->pages, shm->num_pages); - else - shm_put_kernel_pages(shm->pages, shm->num_pages); kfree(shm->pages); } @@ -477,13 +459,6 @@ register_shm_helper(struct tee_context *ctx, struct iov_iter *iter, u32 flags, goto err_put_shm_pages; } - /* - * iov_iter_extract_kvec_pages does not get reference on the pages, - * get a reference on them. - */ - if (iov_iter_is_kvec(iter)) - shm_get_kernel_pages(shm->pages, num_pages); - shm->offset = off; shm->size = len; shm->num_pages = num_pages; @@ -499,8 +474,6 @@ register_shm_helper(struct tee_context *ctx, struct iov_iter *iter, u32 flags, err_put_shm_pages: if (!iov_iter_is_kvec(iter)) unpin_user_pages(shm->pages, shm->num_pages); - else - shm_put_kernel_pages(shm->pages, shm->num_pages); err_free_shm_pages: kfree(shm->pages); err_free_shm: diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 899e663fea6e..9ceb6d6d479d 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -10066,6 +10066,7 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) } flush_work(&hba->eeh_work); + cancel_delayed_work_sync(&hba->ufs_rtc_update_work); ret = ufshcd_vops_suspend(hba, pm_op, PRE_CHANGE); if (ret) @@ -10120,7 +10121,6 @@ vops_suspend: if (ret) goto set_link_active; - cancel_delayed_work_sync(&hba->ufs_rtc_update_work); goto out; set_link_active: diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index ad38c746270a..7ede29d4c7c1 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1379,6 +1379,8 @@ made_compressed_probe: acm->ctrl_caps = h.usb_cdc_acm_descriptor->bmCapabilities; if (quirks & NO_CAP_LINE) acm->ctrl_caps &= ~USB_CDC_CAP_LINE; + if (quirks & MISSING_CAP_BRK) + acm->ctrl_caps |= USB_CDC_CAP_BRK; acm->ctrlsize = ctrlsize; acm->readsize = readsize; acm->rx_buflimit = num_rx_buf; @@ -2002,6 +2004,9 @@ static const struct usb_device_id acm_ids[] = { .driver_info = IGNORE_DEVICE, }, + /* CH343 supports CAP_BRK, but doesn't advertise it */ + { USB_DEVICE(0x1a86, 0x55d3), .driver_info = MISSING_CAP_BRK, }, + /* control interfaces without any protocol set */ { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM, USB_CDC_PROTO_NONE) }, diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h index 759ac15631d3..76f73853a60b 100644 --- a/drivers/usb/class/cdc-acm.h +++ b/drivers/usb/class/cdc-acm.h @@ -113,3 +113,4 @@ struct acm { #define CLEAR_HALT_CONDITIONS BIT(5) #define SEND_ZERO_PACKET BIT(6) #define DISABLE_ECHO BIT(7) +#define MISSING_CAP_BRK BIT(8) diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index f2d94cfc70af..7556c0dac908 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -225,7 +225,8 @@ static void wdm_in_callback(struct urb *urb) /* we may already be in overflow */ if (!test_bit(WDM_OVERFLOW, &desc->flags)) { memmove(desc->ubuf + desc->length, desc->inbuf, length); - desc->length += length; + smp_wmb(); /* against wdm_read() */ + WRITE_ONCE(desc->length, desc->length + length); } } skip_error: @@ -533,6 +534,7 @@ static ssize_t wdm_read return -ERESTARTSYS; cntr = READ_ONCE(desc->length); + smp_rmb(); /* against wdm_in_callback() */ if (cntr == 0) { desc->read = 0; retry: diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 2526a0e03cde..d39bbfd7fd18 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -727,7 +727,7 @@ static int usbtmc488_ioctl_trigger(struct usbtmc_file_data *file_data) buffer[1] = data->bTag; buffer[2] = ~data->bTag; - retval = usb_bulk_msg(data->usb_dev, + retval = usb_bulk_msg_killable(data->usb_dev, usb_sndbulkpipe(data->usb_dev, data->bulk_out), buffer, USBTMC_HEADER_SIZE, @@ -1347,7 +1347,7 @@ static int send_request_dev_dep_msg_in(struct usbtmc_file_data *file_data, buffer[11] = 0; /* Reserved */ /* Send bulk URB */ - retval = usb_bulk_msg(data->usb_dev, + retval = usb_bulk_msg_killable(data->usb_dev, usb_sndbulkpipe(data->usb_dev, data->bulk_out), buffer, USBTMC_HEADER_SIZE, @@ -1419,7 +1419,7 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf, actual = 0; /* Send bulk URB */ - retval = usb_bulk_msg(data->usb_dev, + retval = usb_bulk_msg_killable(data->usb_dev, usb_rcvbulkpipe(data->usb_dev, data->bulk_in), buffer, bufsize, &actual, diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 1cd5fa61dc76..6a1fd967e0a6 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -927,7 +927,11 @@ int usb_get_configuration(struct usb_device *dev) dev->descriptor.bNumConfigurations = ncfg = USB_MAXCONFIG; } - if (ncfg < 1) { + if (ncfg < 1 && dev->quirks & USB_QUIRK_FORCE_ONE_CONFIG) { + dev_info(ddev, "Device claims zero configurations, forcing to 1\n"); + dev->descriptor.bNumConfigurations = 1; + ncfg = 1; + } else if (ncfg < 1) { dev_err(ddev, "no configurations\n"); return -EINVAL; } diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index ea970ddf8879..2ab120ce2fa8 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -42,16 +42,19 @@ static void usb_api_blocking_completion(struct urb *urb) /* - * Starts urb and waits for completion or timeout. Note that this call - * is NOT interruptible. Many device driver i/o requests should be - * interruptible and therefore these drivers should implement their - * own interruptible routines. + * Starts urb and waits for completion or timeout. + * Whether or not the wait is killable depends on the flag passed in. + * For example, compare usb_bulk_msg() and usb_bulk_msg_killable(). + * + * For non-killable waits, we enforce a maximum limit on the timeout value. */ -static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length) +static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length, + bool killable) { struct api_context ctx; unsigned long expire; int retval; + long rc; init_completion(&ctx.done); urb->context = &ctx; @@ -60,13 +63,24 @@ static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length) if (unlikely(retval)) goto out; - expire = timeout ? msecs_to_jiffies(timeout) : MAX_SCHEDULE_TIMEOUT; - if (!wait_for_completion_timeout(&ctx.done, expire)) { + if (!killable && (timeout <= 0 || timeout > USB_MAX_SYNCHRONOUS_TIMEOUT)) + timeout = USB_MAX_SYNCHRONOUS_TIMEOUT; + expire = (timeout > 0) ? msecs_to_jiffies(timeout) : MAX_SCHEDULE_TIMEOUT; + if (killable) + rc = wait_for_completion_killable_timeout(&ctx.done, expire); + else + rc = wait_for_completion_timeout(&ctx.done, expire); + if (rc <= 0) { usb_kill_urb(urb); - retval = (ctx.status == -ENOENT ? -ETIMEDOUT : ctx.status); + if (ctx.status != -ENOENT) + retval = ctx.status; + else if (rc == 0) + retval = -ETIMEDOUT; + else + retval = rc; dev_dbg(&urb->dev->dev, - "%s timed out on ep%d%s len=%u/%u\n", + "%s timed out or killed on ep%d%s len=%u/%u\n", current->comm, usb_endpoint_num(&urb->ep->desc), usb_urb_dir_in(urb) ? "in" : "out", @@ -100,7 +114,7 @@ static int usb_internal_control_msg(struct usb_device *usb_dev, usb_fill_control_urb(urb, usb_dev, pipe, (unsigned char *)cmd, data, len, usb_api_blocking_completion, NULL); - retv = usb_start_wait_urb(urb, timeout, &length); + retv = usb_start_wait_urb(urb, timeout, &length, false); if (retv < 0) return retv; else @@ -117,8 +131,7 @@ static int usb_internal_control_msg(struct usb_device *usb_dev, * @index: USB message index value * @data: pointer to the data to send * @size: length in bytes of the data to send - * @timeout: time in msecs to wait for the message to complete before timing - * out (if 0 the wait is forever) + * @timeout: time in msecs to wait for the message to complete before timing out * * Context: task context, might sleep. * @@ -173,8 +186,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg); * @index: USB message index value * @driver_data: pointer to the data to send * @size: length in bytes of the data to send - * @timeout: time in msecs to wait for the message to complete before timing - * out (if 0 the wait is forever) + * @timeout: time in msecs to wait for the message to complete before timing out * @memflags: the flags for memory allocation for buffers * * Context: !in_interrupt () @@ -232,8 +244,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg_send); * @index: USB message index value * @driver_data: pointer to the data to be filled in by the message * @size: length in bytes of the data to be received - * @timeout: time in msecs to wait for the message to complete before timing - * out (if 0 the wait is forever) + * @timeout: time in msecs to wait for the message to complete before timing out * @memflags: the flags for memory allocation for buffers * * Context: !in_interrupt () @@ -304,8 +315,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg_recv); * @len: length in bytes of the data to send * @actual_length: pointer to a location to put the actual length transferred * in bytes - * @timeout: time in msecs to wait for the message to complete before - * timing out (if 0 the wait is forever) + * @timeout: time in msecs to wait for the message to complete before timing out * * Context: task context, might sleep. * @@ -337,8 +347,7 @@ EXPORT_SYMBOL_GPL(usb_interrupt_msg); * @len: length in bytes of the data to send * @actual_length: pointer to a location to put the actual length transferred * in bytes - * @timeout: time in msecs to wait for the message to complete before - * timing out (if 0 the wait is forever) + * @timeout: time in msecs to wait for the message to complete before timing out * * Context: task context, might sleep. * @@ -385,10 +394,59 @@ int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe, usb_fill_bulk_urb(urb, usb_dev, pipe, data, len, usb_api_blocking_completion, NULL); - return usb_start_wait_urb(urb, timeout, actual_length); + return usb_start_wait_urb(urb, timeout, actual_length, false); } EXPORT_SYMBOL_GPL(usb_bulk_msg); +/** + * usb_bulk_msg_killable - Builds a bulk urb, sends it off and waits for completion in a killable state + * @usb_dev: pointer to the usb device to send the message to + * @pipe: endpoint "pipe" to send the message to + * @data: pointer to the data to send + * @len: length in bytes of the data to send + * @actual_length: pointer to a location to put the actual length transferred + * in bytes + * @timeout: time in msecs to wait for the message to complete before + * timing out (if <= 0, the wait is as long as possible) + * + * Context: task context, might sleep. + * + * This function is just like usb_blk_msg(), except that it waits in a + * killable state and there is no limit on the timeout length. + * + * Return: + * If successful, 0. Otherwise a negative error number. The number of actual + * bytes transferred will be stored in the @actual_length parameter. + * + */ +int usb_bulk_msg_killable(struct usb_device *usb_dev, unsigned int pipe, + void *data, int len, int *actual_length, int timeout) +{ + struct urb *urb; + struct usb_host_endpoint *ep; + + ep = usb_pipe_endpoint(usb_dev, pipe); + if (!ep || len < 0) + return -EINVAL; + + urb = usb_alloc_urb(0, GFP_KERNEL); + if (!urb) + return -ENOMEM; + + if ((ep->desc.bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == + USB_ENDPOINT_XFER_INT) { + pipe = (pipe & ~(3 << 30)) | (PIPE_INTERRUPT << 30); + usb_fill_int_urb(urb, usb_dev, pipe, data, len, + usb_api_blocking_completion, NULL, + ep->desc.bInterval); + } else + usb_fill_bulk_urb(urb, usb_dev, pipe, data, len, + usb_api_blocking_completion, NULL); + + return usb_start_wait_urb(urb, timeout, actual_length, true); +} +EXPORT_SYMBOL_GPL(usb_bulk_msg_killable); + /*-------------------------------------------------------------------*/ static void sg_clean(struct usb_sg_request *io) diff --git a/drivers/usb/core/phy.c b/drivers/usb/core/phy.c index faa20054ad5a..4bba1c275740 100644 --- a/drivers/usb/core/phy.c +++ b/drivers/usb/core/phy.c @@ -200,16 +200,10 @@ int usb_phy_roothub_set_mode(struct usb_phy_roothub *phy_roothub, list_for_each_entry(roothub_entry, head, list) { err = phy_set_mode(roothub_entry->phy, mode); if (err) - goto err_out; + return err; } return 0; - -err_out: - list_for_each_entry_continue_reverse(roothub_entry, head, list) - phy_power_off(roothub_entry->phy); - - return err; } EXPORT_SYMBOL_GPL(usb_phy_roothub_set_mode); diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 9e7e49712739..5523a8e29021 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -140,6 +140,8 @@ static int quirks_param_set(const char *value, const struct kernel_param *kp) case 'p': flags |= USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT; break; + case 'q': + flags |= USB_QUIRK_FORCE_ONE_CONFIG; /* Ignore unrecognized flag characters */ } } @@ -207,6 +209,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* HP v222w 16GB Mini USB Drive */ { USB_DEVICE(0x03f0, 0x3f40), .driver_info = USB_QUIRK_DELAY_INIT }, + /* Huawei 4G LTE module ME906S */ + { USB_DEVICE(0x03f0, 0xa31d), .driver_info = + USB_QUIRK_DISCONNECT_SUSPEND }, + /* Creative SB Audigy 2 NX */ { USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -376,6 +382,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* SanDisk Extreme 55AE */ { USB_DEVICE(0x0781, 0x55ae), .driver_info = USB_QUIRK_NO_LPM }, + /* Avermedia Live Gamer Ultra 2.1 (GC553G2) - BOS descriptor fetch hangs at SuperSpeed Plus */ + { USB_DEVICE(0x07ca, 0x2553), .driver_info = USB_QUIRK_NO_BOS }, + /* Realforce 87U Keyboard */ { USB_DEVICE(0x0853, 0x011b), .driver_info = USB_QUIRK_NO_LPM }, @@ -436,6 +445,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0b05, 0x17e0), .driver_info = USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* ASUS TUF 4K PRO - BOS descriptor fetch hangs at SuperSpeed Plus */ + { USB_DEVICE(0x0b05, 0x1ab9), .driver_info = USB_QUIRK_NO_BOS }, + /* Realtek Semiconductor Corp. Mass Storage Device (Multicard Reader)*/ { USB_DEVICE(0x0bda, 0x0151), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, @@ -564,6 +576,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x2386, 0x350e), .driver_info = USB_QUIRK_NO_LPM }, + /* UGREEN 35871 - BOS descriptor fetch hangs at SuperSpeed Plus */ + { USB_DEVICE(0x2b89, 0x5871), .driver_info = USB_QUIRK_NO_BOS }, + /* APTIV AUTOMOTIVE HUB */ { USB_DEVICE(0x2c48, 0x0132), .driver_info = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT }, @@ -574,12 +589,18 @@ static const struct usb_device_id usb_quirk_list[] = { /* Alcor Link AK9563 SC Reader used in 2022 Lenovo ThinkPads */ { USB_DEVICE(0x2ce3, 0x9563), .driver_info = USB_QUIRK_NO_LPM }, + /* ezcap401 - BOS descriptor fetch hangs at SuperSpeed Plus */ + { USB_DEVICE(0x32ed, 0x0401), .driver_info = USB_QUIRK_NO_BOS }, + /* DELL USB GEN2 */ { USB_DEVICE(0x413c, 0xb062), .driver_info = USB_QUIRK_NO_LPM | USB_QUIRK_RESET_RESUME }, /* VCOM device */ { USB_DEVICE(0x4296, 0x7570), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* Noji-MCS SmartCard Reader */ + { USB_DEVICE(0x5131, 0x2007), .driver_info = USB_QUIRK_FORCE_ONE_CONFIG }, + /* INTEL VALUE SSD */ { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 6ecadc81bd6b..6c1cbb722ca8 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -56,6 +56,7 @@ #define PCI_DEVICE_ID_INTEL_CNPH 0xa36e #define PCI_DEVICE_ID_INTEL_CNPV 0xa3b0 #define PCI_DEVICE_ID_INTEL_RPL 0xa70e +#define PCI_DEVICE_ID_INTEL_NVLH 0xd37f #define PCI_DEVICE_ID_INTEL_PTLH 0xe332 #define PCI_DEVICE_ID_INTEL_PTLH_PCH 0xe37e #define PCI_DEVICE_ID_INTEL_PTLU 0xe432 @@ -447,6 +448,7 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_DEVICE_DATA(INTEL, CNPH, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, CNPV, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, RPL, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, NVLH, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, PTLH, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, PTLH_PCH, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, PTLU, &dwc3_pci_intel_swnode) }, diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index 8c855c00b887..8812ebf33d14 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -1207,9 +1207,11 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f) if (!hidg->interval_user_set) { hidg_fs_in_ep_desc.bInterval = 10; hidg_hs_in_ep_desc.bInterval = 4; + hidg_ss_in_ep_desc.bInterval = 4; } else { hidg_fs_in_ep_desc.bInterval = hidg->interval; hidg_hs_in_ep_desc.bInterval = hidg->interval; + hidg_ss_in_ep_desc.bInterval = hidg->interval; } hidg_ss_out_comp_desc.wBytesPerInterval = @@ -1239,9 +1241,11 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f) if (!hidg->interval_user_set) { hidg_fs_out_ep_desc.bInterval = 10; hidg_hs_out_ep_desc.bInterval = 4; + hidg_ss_out_ep_desc.bInterval = 4; } else { hidg_fs_out_ep_desc.bInterval = hidg->interval; hidg_hs_out_ep_desc.bInterval = hidg->interval; + hidg_ss_out_ep_desc.bInterval = hidg->interval; } status = usb_assign_descriptors(f, hidg_fs_descriptors_intout, diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index 6af96e2b44eb..b7b06cb79ff5 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -180,6 +180,7 @@ #include <linux/kthread.h> #include <linux/sched/signal.h> #include <linux/limits.h> +#include <linux/overflow.h> #include <linux/pagemap.h> #include <linux/rwsem.h> #include <linux/slab.h> @@ -1853,8 +1854,15 @@ static int check_command_size_in_blocks(struct fsg_common *common, int cmnd_size, enum data_direction data_dir, unsigned int mask, int needs_medium, const char *name) { - if (common->curlun) - common->data_size_from_cmnd <<= common->curlun->blkbits; + if (common->curlun) { + if (check_shl_overflow(common->data_size_from_cmnd, + common->curlun->blkbits, + &common->data_size_from_cmnd)) { + common->phase_error = 1; + return -EINVAL; + } + } + return check_command(common, cmnd_size, data_dir, mask, needs_medium, name); } diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index 14fc7dce6f39..a6fa5ed3d6cb 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -83,11 +83,6 @@ static inline struct f_ncm *func_to_ncm(struct usb_function *f) return container_of(f, struct f_ncm, port.func); } -static inline struct f_ncm_opts *func_to_ncm_opts(struct usb_function *f) -{ - return container_of(f->fi, struct f_ncm_opts, func_inst); -} - /*-------------------------------------------------------------------------*/ /* @@ -864,7 +859,6 @@ invalid: static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) { struct f_ncm *ncm = func_to_ncm(f); - struct f_ncm_opts *opts = func_to_ncm_opts(f); struct usb_composite_dev *cdev = f->config->cdev; /* Control interface has only altsetting 0 */ @@ -887,13 +881,12 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) if (alt > 1) goto fail; - scoped_guard(mutex, &opts->lock) - if (opts->net) { - DBG(cdev, "reset ncm\n"); - opts->net = NULL; - gether_disconnect(&ncm->port); - ncm_reset_values(ncm); - } + if (ncm->netdev) { + DBG(cdev, "reset ncm\n"); + ncm->netdev = NULL; + gether_disconnect(&ncm->port); + ncm_reset_values(ncm); + } /* * CDC Network only sends data in non-default altsettings. @@ -926,8 +919,7 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) net = gether_connect(&ncm->port); if (IS_ERR(net)) return PTR_ERR(net); - scoped_guard(mutex, &opts->lock) - opts->net = net; + ncm->netdev = net; } spin_lock(&ncm->lock); @@ -1374,16 +1366,14 @@ err: static void ncm_disable(struct usb_function *f) { struct f_ncm *ncm = func_to_ncm(f); - struct f_ncm_opts *opts = func_to_ncm_opts(f); struct usb_composite_dev *cdev = f->config->cdev; DBG(cdev, "ncm deactivated\n"); - scoped_guard(mutex, &opts->lock) - if (opts->net) { - opts->net = NULL; - gether_disconnect(&ncm->port); - } + if (ncm->netdev) { + ncm->netdev = NULL; + gether_disconnect(&ncm->port); + } if (ncm->notify->enabled) { usb_ep_disable(ncm->notify); @@ -1443,44 +1433,41 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f) { struct usb_composite_dev *cdev = c->cdev; struct f_ncm *ncm = func_to_ncm(f); - struct f_ncm_opts *ncm_opts = func_to_ncm_opts(f); struct usb_string *us; int status = 0; struct usb_ep *ep; + struct f_ncm_opts *ncm_opts; struct usb_os_desc_table *os_desc_table __free(kfree) = NULL; - struct net_device *netdev __free(free_gether_netdev) = NULL; + struct net_device *net __free(detach_gadget) = NULL; struct usb_request *request __free(free_usb_request) = NULL; if (!can_support_ecm(cdev->gadget)) return -EINVAL; + ncm_opts = container_of(f->fi, struct f_ncm_opts, func_inst); + if (cdev->use_os_string) { os_desc_table = kzalloc(sizeof(*os_desc_table), GFP_KERNEL); if (!os_desc_table) return -ENOMEM; } - netdev = gether_setup_default(); - if (IS_ERR(netdev)) - return -ENOMEM; - - scoped_guard(mutex, &ncm_opts->lock) { - gether_apply_opts(netdev, &ncm_opts->net_opts); - netdev->mtu = ncm_opts->max_segment_size - ETH_HLEN; - } - - gether_set_gadget(netdev, cdev->gadget); - status = gether_register_netdev(netdev); - if (status) - return status; + scoped_guard(mutex, &ncm_opts->lock) + if (ncm_opts->bind_count == 0) { + if (!device_is_registered(&ncm_opts->net->dev)) { + ncm_opts->net->mtu = (ncm_opts->max_segment_size - ETH_HLEN); + gether_set_gadget(ncm_opts->net, cdev->gadget); + status = gether_register_netdev(ncm_opts->net); + } else + status = gether_attach_gadget(ncm_opts->net, cdev->gadget); + + if (status) + return status; + net = ncm_opts->net; + } - /* export host's Ethernet address in CDC format */ - status = gether_get_host_addr_cdc(netdev, ncm->ethaddr, - sizeof(ncm->ethaddr)); - if (status < 12) - return -EINVAL; - ncm_string_defs[STRING_MAC_IDX].s = ncm->ethaddr; + ncm_string_defs[1].s = ncm->ethaddr; us = usb_gstrings_attach(cdev, ncm_strings, ARRAY_SIZE(ncm_string_defs)); @@ -1578,8 +1565,9 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f) f->os_desc_n = 1; } ncm->notify_req = no_free_ptr(request); - ncm->netdev = no_free_ptr(netdev); - ncm->port.ioport = netdev_priv(ncm->netdev); + + ncm_opts->bind_count++; + retain_and_null_ptr(net); DBG(cdev, "CDC Network: IN/%s OUT/%s NOTIFY/%s\n", ncm->port.in_ep->name, ncm->port.out_ep->name, @@ -1594,19 +1582,19 @@ static inline struct f_ncm_opts *to_f_ncm_opts(struct config_item *item) } /* f_ncm_item_ops */ -USB_ETHER_OPTS_ITEM(ncm); +USB_ETHERNET_CONFIGFS_ITEM(ncm); /* f_ncm_opts_dev_addr */ -USB_ETHER_OPTS_ATTR_DEV_ADDR(ncm); +USB_ETHERNET_CONFIGFS_ITEM_ATTR_DEV_ADDR(ncm); /* f_ncm_opts_host_addr */ -USB_ETHER_OPTS_ATTR_HOST_ADDR(ncm); +USB_ETHERNET_CONFIGFS_ITEM_ATTR_HOST_ADDR(ncm); /* f_ncm_opts_qmult */ -USB_ETHER_OPTS_ATTR_QMULT(ncm); +USB_ETHERNET_CONFIGFS_ITEM_ATTR_QMULT(ncm); /* f_ncm_opts_ifname */ -USB_ETHER_OPTS_ATTR_IFNAME(ncm); +USB_ETHERNET_CONFIGFS_ITEM_ATTR_IFNAME(ncm); static ssize_t ncm_opts_max_segment_size_show(struct config_item *item, char *page) @@ -1672,27 +1660,34 @@ static void ncm_free_inst(struct usb_function_instance *f) struct f_ncm_opts *opts; opts = container_of(f, struct f_ncm_opts, func_inst); + if (device_is_registered(&opts->net->dev)) + gether_cleanup(netdev_priv(opts->net)); + else + free_netdev(opts->net); kfree(opts->ncm_interf_group); kfree(opts); } static struct usb_function_instance *ncm_alloc_inst(void) { - struct usb_function_instance *ret; + struct f_ncm_opts *opts; struct usb_os_desc *descs[1]; char *names[1]; struct config_group *ncm_interf_group; - struct f_ncm_opts *opts __free(kfree) = kzalloc_obj(*opts); + opts = kzalloc_obj(*opts); if (!opts) return ERR_PTR(-ENOMEM); - - opts->net = NULL; opts->ncm_os_desc.ext_compat_id = opts->ncm_ext_compat_id; - gether_setup_opts_default(&opts->net_opts, "usb"); mutex_init(&opts->lock); opts->func_inst.free_func_inst = ncm_free_inst; + opts->net = gether_setup_default(); + if (IS_ERR(opts->net)) { + struct net_device *net = opts->net; + kfree(opts); + return ERR_CAST(net); + } opts->max_segment_size = ETH_FRAME_LEN; INIT_LIST_HEAD(&opts->ncm_os_desc.ext_prop); @@ -1703,30 +1698,37 @@ static struct usb_function_instance *ncm_alloc_inst(void) ncm_interf_group = usb_os_desc_prepare_interf_dir(&opts->func_inst.group, 1, descs, names, THIS_MODULE); - if (IS_ERR(ncm_interf_group)) + if (IS_ERR(ncm_interf_group)) { + ncm_free_inst(&opts->func_inst); return ERR_CAST(ncm_interf_group); + } opts->ncm_interf_group = ncm_interf_group; - ret = &opts->func_inst; - retain_and_null_ptr(opts); - return ret; + return &opts->func_inst; } static void ncm_free(struct usb_function *f) { - struct f_ncm_opts *opts = func_to_ncm_opts(f); + struct f_ncm *ncm; + struct f_ncm_opts *opts; - scoped_guard(mutex, &opts->lock) - opts->refcnt--; - kfree(func_to_ncm(f)); + ncm = func_to_ncm(f); + opts = container_of(f->fi, struct f_ncm_opts, func_inst); + kfree(ncm); + mutex_lock(&opts->lock); + opts->refcnt--; + mutex_unlock(&opts->lock); } static void ncm_unbind(struct usb_configuration *c, struct usb_function *f) { struct f_ncm *ncm = func_to_ncm(f); + struct f_ncm_opts *ncm_opts; DBG(c->cdev, "ncm unbind\n"); + ncm_opts = container_of(f->fi, struct f_ncm_opts, func_inst); + hrtimer_cancel(&ncm->task_timer); kfree(f->os_desc_table); @@ -1743,14 +1745,16 @@ static void ncm_unbind(struct usb_configuration *c, struct usb_function *f) kfree(ncm->notify_req->buf); usb_ep_free_request(ncm->notify, ncm->notify_req); - ncm->port.ioport = NULL; - gether_cleanup(netdev_priv(ncm->netdev)); + ncm_opts->bind_count--; + if (ncm_opts->bind_count == 0) + gether_detach_gadget(ncm_opts->net); } static struct usb_function *ncm_alloc(struct usb_function_instance *fi) { struct f_ncm *ncm; struct f_ncm_opts *opts; + int status; /* allocate and initialize one new instance */ ncm = kzalloc(sizeof(*ncm), GFP_KERNEL); @@ -1758,12 +1762,22 @@ static struct usb_function *ncm_alloc(struct usb_function_instance *fi) return ERR_PTR(-ENOMEM); opts = container_of(fi, struct f_ncm_opts, func_inst); + mutex_lock(&opts->lock); + opts->refcnt++; - scoped_guard(mutex, &opts->lock) - opts->refcnt++; + /* export host's Ethernet address in CDC format */ + status = gether_get_host_addr_cdc(opts->net, ncm->ethaddr, + sizeof(ncm->ethaddr)); + if (status < 12) { /* strlen("01234567890a") */ + kfree(ncm); + mutex_unlock(&opts->lock); + return ERR_PTR(-EINVAL); + } spin_lock_init(&ncm->lock); ncm_reset_values(ncm); + ncm->port.ioport = netdev_priv(opts->net); + mutex_unlock(&opts->lock); ncm->port.is_fixed = true; ncm->port.supports_multi_frame = true; diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c index ec050d8f99f1..a7853dcbb14c 100644 --- a/drivers/usb/gadget/function/f_tcm.c +++ b/drivers/usb/gadget/function/f_tcm.c @@ -1222,6 +1222,13 @@ static void usbg_submit_cmd(struct usbg_cmd *cmd) se_cmd = &cmd->se_cmd; tpg = cmd->fu->tpg; tv_nexus = tpg->tpg_nexus; + if (!tv_nexus) { + struct usb_gadget *gadget = fuas_to_gadget(cmd->fu); + + dev_err(&gadget->dev, "Missing nexus, ignoring command\n"); + return; + } + dir = get_cmd_dir(cmd->cmd_buf); if (dir < 0) goto out; @@ -1483,6 +1490,13 @@ static void bot_cmd_work(struct work_struct *work) se_cmd = &cmd->se_cmd; tpg = cmd->fu->tpg; tv_nexus = tpg->tpg_nexus; + if (!tv_nexus) { + struct usb_gadget *gadget = fuas_to_gadget(cmd->fu); + + dev_err(&gadget->dev, "Missing nexus, ignoring command\n"); + return; + } + dir = get_cmd_dir(cmd->cmd_buf); if (dir < 0) goto out; diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index 338f6e2a85a9..1a9e7c495e2e 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -897,6 +897,28 @@ void gether_set_gadget(struct net_device *net, struct usb_gadget *g) } EXPORT_SYMBOL_GPL(gether_set_gadget); +int gether_attach_gadget(struct net_device *net, struct usb_gadget *g) +{ + int ret; + + ret = device_move(&net->dev, &g->dev, DPM_ORDER_DEV_AFTER_PARENT); + if (ret) + return ret; + + gether_set_gadget(net, g); + return 0; +} +EXPORT_SYMBOL_GPL(gether_attach_gadget); + +void gether_detach_gadget(struct net_device *net) +{ + struct eth_dev *dev = netdev_priv(net); + + device_move(&net->dev, NULL, DPM_ORDER_NONE); + dev->gadget = NULL; +} +EXPORT_SYMBOL_GPL(gether_detach_gadget); + int gether_set_dev_addr(struct net_device *net, const char *dev_addr) { struct eth_dev *dev; @@ -1040,36 +1062,6 @@ int gether_set_ifname(struct net_device *net, const char *name, int len) } EXPORT_SYMBOL_GPL(gether_set_ifname); -void gether_setup_opts_default(struct gether_opts *opts, const char *name) -{ - opts->qmult = QMULT_DEFAULT; - snprintf(opts->name, sizeof(opts->name), "%s%%d", name); - eth_random_addr(opts->dev_mac); - opts->addr_assign_type = NET_ADDR_RANDOM; - eth_random_addr(opts->host_mac); -} -EXPORT_SYMBOL_GPL(gether_setup_opts_default); - -void gether_apply_opts(struct net_device *net, struct gether_opts *opts) -{ - struct eth_dev *dev = netdev_priv(net); - - dev->qmult = opts->qmult; - - if (opts->ifname_set) { - strscpy(net->name, opts->name, sizeof(net->name)); - dev->ifname_set = true; - } - - memcpy(dev->host_mac, opts->host_mac, sizeof(dev->host_mac)); - - if (opts->addr_assign_type == NET_ADDR_SET) { - memcpy(dev->dev_mac, opts->dev_mac, sizeof(dev->dev_mac)); - net->addr_assign_type = opts->addr_assign_type; - } -} -EXPORT_SYMBOL_GPL(gether_apply_opts); - void gether_suspend(struct gether *link) { struct eth_dev *dev = link->ioport; @@ -1126,21 +1118,6 @@ void gether_cleanup(struct eth_dev *dev) } EXPORT_SYMBOL_GPL(gether_cleanup); -void gether_unregister_free_netdev(struct net_device *net) -{ - if (!net) - return; - - struct eth_dev *dev = netdev_priv(net); - - if (net->reg_state == NETREG_REGISTERED) { - unregister_netdev(net); - flush_work(&dev->work); - } - free_netdev(net); -} -EXPORT_SYMBOL_GPL(gether_unregister_free_netdev); - /** * gether_connect - notify network layer that USB link is active * @link: the USB link, set up with endpoints, descriptors matching diff --git a/drivers/usb/gadget/function/u_ether.h b/drivers/usb/gadget/function/u_ether.h index a212a8ec5eb1..c85a1cf3c115 100644 --- a/drivers/usb/gadget/function/u_ether.h +++ b/drivers/usb/gadget/function/u_ether.h @@ -38,31 +38,6 @@ struct eth_dev; -/** - * struct gether_opts - Options for Ethernet gadget function instances - * @name: Pattern for the network interface name (e.g., "usb%d"). - * Used to generate the net device name. - * @qmult: Queue length multiplier for high/super speed. - * @host_mac: The MAC address to be used by the host side. - * @dev_mac: The MAC address to be used by the device side. - * @ifname_set: True if the interface name pattern has been set by userspace. - * @addr_assign_type: The method used for assigning the device MAC address - * (e.g., NET_ADDR_RANDOM, NET_ADDR_SET). - * - * This structure caches network-related settings provided through configfs - * before the net_device is fully instantiated. This allows for early - * configuration while deferring net_device allocation until the function - * is bound. - */ -struct gether_opts { - char name[IFNAMSIZ]; - unsigned int qmult; - u8 host_mac[ETH_ALEN]; - u8 dev_mac[ETH_ALEN]; - bool ifname_set; - unsigned char addr_assign_type; -}; - /* * This represents the USB side of an "ethernet" link, managed by a USB * function which provides control and (maybe) framing. Two functions @@ -176,6 +151,32 @@ static inline struct net_device *gether_setup_default(void) void gether_set_gadget(struct net_device *net, struct usb_gadget *g); /** + * gether_attach_gadget - Reparent net_device to the gadget device. + * @net: The network device to reparent. + * @g: The target USB gadget device to parent to. + * + * This function moves the network device to be a child of the USB gadget + * device in the device hierarchy. This is typically done when the function + * is bound to a configuration. + * + * Returns 0 on success, or a negative error code on failure. + */ +int gether_attach_gadget(struct net_device *net, struct usb_gadget *g); + +/** + * gether_detach_gadget - Detach net_device from its gadget parent. + * @net: The network device to detach. + * + * This function moves the network device to be a child of the virtual + * devices parent, effectively detaching it from the USB gadget device + * hierarchy. This is typically done when the function is unbound + * from a configuration but the instance is not yet freed. + */ +void gether_detach_gadget(struct net_device *net); + +DEFINE_FREE(detach_gadget, struct net_device *, if (_T) gether_detach_gadget(_T)) + +/** * gether_set_dev_addr - initialize an ethernet-over-usb link with eth address * @net: device representing this link * @dev_addr: eth address of this device @@ -283,11 +284,6 @@ int gether_get_ifname(struct net_device *net, char *name, int len); int gether_set_ifname(struct net_device *net, const char *name, int len); void gether_cleanup(struct eth_dev *dev); -void gether_unregister_free_netdev(struct net_device *net); -DEFINE_FREE(free_gether_netdev, struct net_device *, gether_unregister_free_netdev(_T)); - -void gether_setup_opts_default(struct gether_opts *opts, const char *name); -void gether_apply_opts(struct net_device *net, struct gether_opts *opts); void gether_suspend(struct gether *link); void gether_resume(struct gether *link); diff --git a/drivers/usb/gadget/function/u_ether_configfs.h b/drivers/usb/gadget/function/u_ether_configfs.h index 217990a266b2..51f0d79e5eca 100644 --- a/drivers/usb/gadget/function/u_ether_configfs.h +++ b/drivers/usb/gadget/function/u_ether_configfs.h @@ -13,13 +13,6 @@ #ifndef __U_ETHER_CONFIGFS_H #define __U_ETHER_CONFIGFS_H -#include <linux/cleanup.h> -#include <linux/hex.h> -#include <linux/if_ether.h> -#include <linux/mutex.h> -#include <linux/netdevice.h> -#include <linux/rtnetlink.h> - #define USB_ETHERNET_CONFIGFS_ITEM(_f_) \ static void _f_##_attr_release(struct config_item *item) \ { \ @@ -204,174 +197,4 @@ out: \ \ CONFIGFS_ATTR(_f_##_opts_, _n_) -#define USB_ETHER_OPTS_ITEM(_f_) \ - static void _f_##_attr_release(struct config_item *item) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - \ - usb_put_function_instance(&opts->func_inst); \ - } \ - \ - static struct configfs_item_operations _f_##_item_ops = { \ - .release = _f_##_attr_release, \ - } - -#define USB_ETHER_OPTS_ATTR_DEV_ADDR(_f_) \ - static ssize_t _f_##_opts_dev_addr_show(struct config_item *item, \ - char *page) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - \ - guard(mutex)(&opts->lock); \ - return sysfs_emit(page, "%pM\n", opts->net_opts.dev_mac); \ - } \ - \ - static ssize_t _f_##_opts_dev_addr_store(struct config_item *item, \ - const char *page, size_t len) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - u8 new_addr[ETH_ALEN]; \ - const char *p = page; \ - \ - guard(mutex)(&opts->lock); \ - if (opts->refcnt) \ - return -EBUSY; \ - \ - for (int i = 0; i < ETH_ALEN; i++) { \ - unsigned char num; \ - if ((*p == '.') || (*p == ':')) \ - p++; \ - num = hex_to_bin(*p++) << 4; \ - num |= hex_to_bin(*p++); \ - new_addr[i] = num; \ - } \ - if (!is_valid_ether_addr(new_addr)) \ - return -EINVAL; \ - memcpy(opts->net_opts.dev_mac, new_addr, ETH_ALEN); \ - opts->net_opts.addr_assign_type = NET_ADDR_SET; \ - return len; \ - } \ - \ - CONFIGFS_ATTR(_f_##_opts_, dev_addr) - -#define USB_ETHER_OPTS_ATTR_HOST_ADDR(_f_) \ - static ssize_t _f_##_opts_host_addr_show(struct config_item *item, \ - char *page) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - \ - guard(mutex)(&opts->lock); \ - return sysfs_emit(page, "%pM\n", opts->net_opts.host_mac); \ - } \ - \ - static ssize_t _f_##_opts_host_addr_store(struct config_item *item, \ - const char *page, size_t len) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - u8 new_addr[ETH_ALEN]; \ - const char *p = page; \ - \ - guard(mutex)(&opts->lock); \ - if (opts->refcnt) \ - return -EBUSY; \ - \ - for (int i = 0; i < ETH_ALEN; i++) { \ - unsigned char num; \ - if ((*p == '.') || (*p == ':')) \ - p++; \ - num = hex_to_bin(*p++) << 4; \ - num |= hex_to_bin(*p++); \ - new_addr[i] = num; \ - } \ - if (!is_valid_ether_addr(new_addr)) \ - return -EINVAL; \ - memcpy(opts->net_opts.host_mac, new_addr, ETH_ALEN); \ - return len; \ - } \ - \ - CONFIGFS_ATTR(_f_##_opts_, host_addr) - -#define USB_ETHER_OPTS_ATTR_QMULT(_f_) \ - static ssize_t _f_##_opts_qmult_show(struct config_item *item, \ - char *page) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - \ - guard(mutex)(&opts->lock); \ - return sysfs_emit(page, "%u\n", opts->net_opts.qmult); \ - } \ - \ - static ssize_t _f_##_opts_qmult_store(struct config_item *item, \ - const char *page, size_t len) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - u32 val; \ - int ret; \ - \ - guard(mutex)(&opts->lock); \ - if (opts->refcnt) \ - return -EBUSY; \ - \ - ret = kstrtou32(page, 0, &val); \ - if (ret) \ - return ret; \ - \ - opts->net_opts.qmult = val; \ - return len; \ - } \ - \ - CONFIGFS_ATTR(_f_##_opts_, qmult) - -#define USB_ETHER_OPTS_ATTR_IFNAME(_f_) \ - static ssize_t _f_##_opts_ifname_show(struct config_item *item, \ - char *page) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - const char *name; \ - \ - guard(mutex)(&opts->lock); \ - rtnl_lock(); \ - if (opts->net_opts.ifname_set) \ - name = opts->net_opts.name; \ - else if (opts->net) \ - name = netdev_name(opts->net); \ - else \ - name = "(inactive net_device)"; \ - rtnl_unlock(); \ - return sysfs_emit(page, "%s\n", name); \ - } \ - \ - static ssize_t _f_##_opts_ifname_store(struct config_item *item, \ - const char *page, size_t len) \ - { \ - struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \ - char tmp[IFNAMSIZ]; \ - const char *p; \ - size_t c_len = len; \ - \ - if (c_len > 0 && page[c_len - 1] == '\n') \ - c_len--; \ - \ - if (c_len >= sizeof(tmp)) \ - return -E2BIG; \ - \ - strscpy(tmp, page, c_len + 1); \ - if (!dev_valid_name(tmp)) \ - return -EINVAL; \ - \ - /* Require exactly one %d */ \ - p = strchr(tmp, '%'); \ - if (!p || p[1] != 'd' || strchr(p + 2, '%')) \ - return -EINVAL; \ - \ - guard(mutex)(&opts->lock); \ - if (opts->refcnt) \ - return -EBUSY; \ - strscpy(opts->net_opts.name, tmp, sizeof(opts->net_opts.name)); \ - opts->net_opts.ifname_set = true; \ - return len; \ - } \ - \ - CONFIGFS_ATTR(_f_##_opts_, ifname) - #endif /* __U_ETHER_CONFIGFS_H */ diff --git a/drivers/usb/gadget/function/u_ncm.h b/drivers/usb/gadget/function/u_ncm.h index d99330fe31e8..b1f3db8b68c1 100644 --- a/drivers/usb/gadget/function/u_ncm.h +++ b/drivers/usb/gadget/function/u_ncm.h @@ -15,13 +15,11 @@ #include <linux/usb/composite.h> -#include "u_ether.h" - struct f_ncm_opts { struct usb_function_instance func_inst; struct net_device *net; + int bind_count; - struct gether_opts net_opts; struct config_group *ncm_interf_group; struct usb_os_desc ncm_os_desc; char ncm_ext_compat_id[16]; diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c index 7cea641b06b4..2f9700b3f1b6 100644 --- a/drivers/usb/gadget/function/uvc_video.c +++ b/drivers/usb/gadget/function/uvc_video.c @@ -513,7 +513,7 @@ uvc_video_prep_requests(struct uvc_video *video) return; } - interval_duration = 2 << (video->ep->desc->bInterval - 1); + interval_duration = 1 << (video->ep->desc->bInterval - 1); if (cdev->gadget->speed < USB_SPEED_HIGH) interval_duration *= 10000; else diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c index 890fc5e892f1..ade178ab34a7 100644 --- a/drivers/usb/host/xhci-debugfs.c +++ b/drivers/usb/host/xhci-debugfs.c @@ -386,11 +386,19 @@ static const struct file_operations port_fops = { static int xhci_portli_show(struct seq_file *s, void *unused) { struct xhci_port *port = s->private; - struct xhci_hcd *xhci = hcd_to_xhci(port->rhub->hcd); + struct xhci_hcd *xhci; u32 portli; portli = readl(&port->port_reg->portli); + /* port without protocol capability isn't added to a roothub */ + if (!port->rhub) { + seq_printf(s, "0x%08x\n", portli); + return 0; + } + + xhci = hcd_to_xhci(port->rhub->hcd); + /* PORTLI fields are valid if port is a USB3 or eUSB2V2 port */ if (port->rhub == &xhci->usb3_rhub) seq_printf(s, "0x%08x LEC=%u RLC=%u TLC=%u\n", portli, diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 9315ba18310d..1cbefee3c4ca 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -3195,6 +3195,7 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) if (status & STS_HCE) { xhci_warn(xhci, "WARNING: Host Controller Error\n"); + xhci_halt(xhci); goto out; } diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index c36ab323d68e..ef6d8662adec 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -4146,7 +4146,7 @@ int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id) if (state == 0xffffffff || (xhci->xhc_state & XHCI_STATE_DYING) || (xhci->xhc_state & XHCI_STATE_HALTED)) { spin_unlock_irqrestore(&xhci->lock, flags); - kfree(command); + xhci_free_command(xhci, command); return -ENODEV; } @@ -4154,7 +4154,7 @@ int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id) slot_id); if (ret) { spin_unlock_irqrestore(&xhci->lock, flags); - kfree(command); + xhci_free_command(xhci, command); return ret; } xhci_ring_cmd_db(xhci); diff --git a/drivers/usb/image/mdc800.c b/drivers/usb/image/mdc800.c index 8d8e79afa600..ca287b770e8c 100644 --- a/drivers/usb/image/mdc800.c +++ b/drivers/usb/image/mdc800.c @@ -707,7 +707,7 @@ static ssize_t mdc800_device_read (struct file *file, char __user *buf, size_t l if (signal_pending (current)) { mutex_unlock(&mdc800->io_lock); - return -EINTR; + return len == left ? -EINTR : len-left; } sts=left > (mdc800->out_count-mdc800->out_ptr)?mdc800->out_count-mdc800->out_ptr:left; @@ -730,9 +730,11 @@ static ssize_t mdc800_device_read (struct file *file, char __user *buf, size_t l mutex_unlock(&mdc800->io_lock); return len-left; } - wait_event_timeout(mdc800->download_wait, + retval = wait_event_timeout(mdc800->download_wait, mdc800->downloaded, msecs_to_jiffies(TO_DOWNLOAD_GET_READY)); + if (!retval) + usb_kill_urb(mdc800->download_urb); mdc800->downloaded = 0; if (mdc800->download_urb->status != 0) { diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c index ec8bd968c4de..a8af7615b1bf 100644 --- a/drivers/usb/misc/uss720.c +++ b/drivers/usb/misc/uss720.c @@ -736,7 +736,7 @@ static int uss720_probe(struct usb_interface *intf, ret = get_1284_register(pp, 0, ®, GFP_KERNEL); dev_dbg(&intf->dev, "reg: %7ph\n", priv->reg); if (ret < 0) - return ret; + goto probe_abort; ret = usb_find_last_int_in_endpoint(interface, &epd); if (!ret) { diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c index 9189e4bb213a..7a482cdee1e9 100644 --- a/drivers/usb/misc/yurex.c +++ b/drivers/usb/misc/yurex.c @@ -272,6 +272,7 @@ static int yurex_probe(struct usb_interface *interface, const struct usb_device_ dev->int_buffer, YUREX_BUF_SIZE, yurex_interrupt, dev, 1); dev->urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; + dev->bbu = -1; if (usb_submit_urb(dev->urb, GFP_KERNEL)) { retval = -EIO; dev_err(&interface->dev, "Could not submitting URB\n"); @@ -280,7 +281,6 @@ static int yurex_probe(struct usb_interface *interface, const struct usb_device_ /* save our data pointer in this interface device */ usb_set_intfdata(interface, dev); - dev->bbu = -1; /* we can register the device now, as it is ready */ retval = usb_register_dev(interface, &yurex_class); diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c index cf4a0367d6d6..8c93bde4b816 100644 --- a/drivers/usb/renesas_usbhs/common.c +++ b/drivers/usb/renesas_usbhs/common.c @@ -815,6 +815,15 @@ static void usbhs_remove(struct platform_device *pdev) usbhs_platform_call(priv, hardware_exit, pdev); reset_control_assert(priv->rsts); + + /* + * Explicitly free the IRQ to ensure the interrupt handler is + * disabled and synchronized before freeing resources. + * devm_free_irq() calls free_irq() which waits for any running + * ISR to complete, preventing UAF. + */ + devm_free_irq(&pdev->dev, priv->irq, priv); + usbhs_mod_remove(priv); usbhs_fifo_remove(priv); usbhs_pipe_remove(priv); diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c index b8e28ceca51e..edec139b68b5 100644 --- a/drivers/usb/roles/class.c +++ b/drivers/usb/roles/class.c @@ -139,9 +139,14 @@ static void *usb_role_switch_match(const struct fwnode_handle *fwnode, const cha static struct usb_role_switch * usb_role_switch_is_parent(struct fwnode_handle *fwnode) { - struct fwnode_handle *parent = fwnode_get_parent(fwnode); + struct fwnode_handle *parent; struct device *dev; + if (!fwnode_device_is_compatible(fwnode, "usb-b-connector")) + return NULL; + + parent = fwnode_get_parent(fwnode); + if (!fwnode_property_present(parent, "usb-role-switch")) { fwnode_handle_put(parent); return NULL; diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index d185688a16b1..35d9c3086990 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -100,9 +100,14 @@ static int dp_altmode_configure(struct dp_altmode *dp, u8 con) { u8 pin_assign = 0; u32 conf; + u32 signal; /* DP Signalling */ - conf = (dp->data.conf & DP_CONF_SIGNALLING_MASK) >> DP_CONF_SIGNALLING_SHIFT; + signal = DP_CAP_DP_SIGNALLING(dp->port->vdo) & DP_CAP_DP_SIGNALLING(dp->alt->vdo); + if (dp->plug_prime) + signal &= DP_CAP_DP_SIGNALLING(dp->plug_prime->vdo); + + conf = signal << DP_CONF_SIGNALLING_SHIFT; switch (con) { case DP_STATUS_CON_DISABLED: diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 1d2f3af034c5..8e0e14a2704e 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -7890,7 +7890,7 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) port->partner_desc.identity = &port->partner_ident; port->role_sw = fwnode_usb_role_switch_get(tcpc->fwnode); - if (IS_ERR_OR_NULL(port->role_sw)) + if (!port->role_sw) port->role_sw = usb_role_switch_get(port->dev); if (IS_ERR(port->role_sw)) { err = PTR_ERR(port->role_sw); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index e4fad777b034..407830d86d0d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3594,7 +3594,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device } } - btrfs_zoned_reserve_data_reloc_bg(fs_info); btrfs_free_zone_cache(fs_info); btrfs_check_active_zone_reservation(fs_info); @@ -3622,6 +3621,12 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_cleaner; } + /* + * Starts a transaction, must be called after the transaction kthread + * is initialized. + */ + btrfs_zoned_reserve_data_reloc_bg(fs_info); + ret = btrfs_read_qgroup_config(fs_info); if (ret) goto fail_trans_kthread; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 744a1fff6eef..5f97a3d2a8d7 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4507,6 +4507,7 @@ static int try_release_subpage_extent_buffer(struct folio *folio) */ if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) { spin_unlock(&eb->refs_lock); + rcu_read_lock(); break; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a11fcc9e9f50..a6da98435ef7 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6612,6 +6612,25 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans, int ret; bool xa_reserved = false; + if (!args->orphan && !args->subvol) { + /* + * Before anything else, check if we can add the name to the + * parent directory. We want to avoid a dir item overflow in + * case we have an existing dir item due to existing name + * hash collisions. We do this check here before we call + * btrfs_add_link() down below so that we can avoid a + * transaction abort (which could be exploited by malicious + * users). + * + * For subvolumes we already do this in btrfs_mksubvol(). + */ + ret = btrfs_check_dir_item_collision(BTRFS_I(dir)->root, + btrfs_ino(BTRFS_I(dir)), + name); + if (ret < 0) + return ret; + } + path = btrfs_alloc_path(); if (!path) return -ENOMEM; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a1fd44c44ecf..b805dd9227ef 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -672,6 +672,13 @@ static noinline int create_subvol(struct mnt_idmap *idmap, goto out; } + /* + * Subvolumes have orphans cleaned on first dentry lookup. A new + * subvolume cannot have any orphans, so we should set the bit before we + * add the subvolume dentry to the dentry cache, so that it is in the + * same state as a subvolume after first lookup. + */ + set_bit(BTRFS_ROOT_ORPHAN_CLEANUP, &new_root->state); d_instantiate_new(dentry, new_inode_args.inode); new_inode_args.inode = NULL; @@ -3852,6 +3859,25 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, goto out; } + received_uuid_changed = memcmp(root_item->received_uuid, sa->uuid, + BTRFS_UUID_SIZE); + + /* + * Before we attempt to add the new received uuid, check if we have room + * for it in case there's already an item. If the size of the existing + * item plus this root's ID (u64) exceeds the maximum item size, we can + * return here without the need to abort a transaction. If we don't do + * this check, the btrfs_uuid_tree_add() call below would fail with + * -EOVERFLOW and result in a transaction abort. Malicious users could + * exploit this to turn the fs into RO mode. + */ + if (received_uuid_changed && !btrfs_is_empty_uuid(sa->uuid)) { + ret = btrfs_uuid_tree_check_overflow(fs_info, sa->uuid, + BTRFS_UUID_KEY_RECEIVED_SUBVOL); + if (ret < 0) + goto out; + } + /* * 1 - root item * 2 - uuid items (received uuid + subvol uuid) @@ -3867,15 +3893,12 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, sa->rtime.sec = ct.tv_sec; sa->rtime.nsec = ct.tv_nsec; - received_uuid_changed = memcmp(root_item->received_uuid, sa->uuid, - BTRFS_UUID_SIZE); if (received_uuid_changed && !btrfs_is_empty_uuid(root_item->received_uuid)) { ret = btrfs_uuid_tree_remove(trans, root_item->received_uuid, BTRFS_UUID_KEY_RECEIVED_SUBVOL, btrfs_root_id(root)); if (unlikely(ret && ret != -ENOENT)) { - btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); goto out; } @@ -3890,7 +3913,8 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, ret = btrfs_update_root(trans, fs_info->tree_root, &root->root_key, &root->root_item); - if (ret < 0) { + if (unlikely(ret < 0)) { + btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); goto out; } diff --git a/fs/btrfs/messages.h b/fs/btrfs/messages.h index 943e53980945..c8e92efce405 100644 --- a/fs/btrfs/messages.h +++ b/fs/btrfs/messages.h @@ -31,9 +31,6 @@ void _btrfs_printk(const struct btrfs_fs_info *fs_info, unsigned int level, cons #define btrfs_printk_in_rcu(fs_info, level, fmt, args...) \ btrfs_no_printk(fs_info, fmt, ##args) -#define btrfs_printk_in_rcu(fs_info, level, fmt, args...) \ - btrfs_no_printk(fs_info, fmt, ##args) - #define btrfs_printk_rl_in_rcu(fs_info, level, fmt, args...) \ btrfs_no_printk(fs_info, fmt, ##args) diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index f189bf09ce6a..b7dfe877cf8d 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -38,6 +38,7 @@ static const struct root_name_map root_map[] = { { BTRFS_BLOCK_GROUP_TREE_OBJECTID, "BLOCK_GROUP_TREE" }, { BTRFS_DATA_RELOC_TREE_OBJECTID, "DATA_RELOC_TREE" }, { BTRFS_RAID_STRIPE_TREE_OBJECTID, "RAID_STRIPE_TREE" }, + { BTRFS_REMAP_TREE_OBJECTID, "REMAP_TREE" }, }; const char *btrfs_root_name(const struct btrfs_key *key, char *buf) @@ -415,6 +416,9 @@ static void key_type_string(const struct btrfs_key *key, char *buf, int buf_size [BTRFS_UUID_KEY_SUBVOL] = "UUID_KEY_SUBVOL", [BTRFS_UUID_KEY_RECEIVED_SUBVOL] = "UUID_KEY_RECEIVED_SUBVOL", [BTRFS_RAID_STRIPE_KEY] = "RAID_STRIPE", + [BTRFS_IDENTITY_REMAP_KEY] = "IDENTITY_REMAP", + [BTRFS_REMAP_KEY] = "REMAP", + [BTRFS_REMAP_BACKREF_KEY] = "REMAP_BACKREF", }; if (key->type == 0 && key->objectid == BTRFS_FREE_SPACE_OBJECTID) @@ -435,6 +439,7 @@ void btrfs_print_leaf(const struct extent_buffer *l) struct btrfs_extent_data_ref *dref; struct btrfs_shared_data_ref *sref; struct btrfs_dev_extent *dev_extent; + struct btrfs_remap_item *remap; struct btrfs_key key; if (!l) @@ -569,6 +574,11 @@ void btrfs_print_leaf(const struct extent_buffer *l) print_raid_stripe_key(l, btrfs_item_size(l, i), btrfs_item_ptr(l, i, struct btrfs_stripe_extent)); break; + case BTRFS_REMAP_KEY: + case BTRFS_REMAP_BACKREF_KEY: + remap = btrfs_item_ptr(l, i, struct btrfs_remap_item); + pr_info("\t\taddress %llu\n", btrfs_remap_address(l, remap)); + break; } } } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index a330d8624b83..b2343aed7a5d 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4399,6 +4399,8 @@ static int move_existing_remaps(struct btrfs_fs_info *fs_info, leaf = path->nodes[0]; } + + btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); } remap = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_remap_item); diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 52a267a5dd80..87cbc051cb12 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -2194,8 +2194,11 @@ void btrfs_reclaim_sweep(const struct btrfs_fs_info *fs_info) if (!btrfs_should_periodic_reclaim(space_info)) continue; for (raid = 0; raid < BTRFS_NR_RAID_TYPES; raid++) { - if (do_reclaim_sweep(space_info, raid)) + if (do_reclaim_sweep(space_info, raid)) { + spin_lock(&space_info->lock); btrfs_set_periodic_reclaim_ready(space_info, false); + spin_unlock(&space_info->lock); + } } } } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 7ef8c9b7dfc1..8dd77c431974 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1905,6 +1905,22 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, ret = btrfs_uuid_tree_add(trans, new_root_item->received_uuid, BTRFS_UUID_KEY_RECEIVED_SUBVOL, objectid); + /* + * We are creating of lot of snapshots of the same root that was + * received (has a received UUID) and reached a leaf's limit for + * an item. We can safely ignore this and avoid a transaction + * abort. A deletion of this snapshot will still work since we + * ignore if an item with a BTRFS_UUID_KEY_RECEIVED_SUBVOL key + * is missing (see btrfs_delete_subvolume()). Send/receive will + * work too since it peeks the first root id from the existing + * item (it could peek any), and in case it's missing it + * falls back to search by BTRFS_UUID_KEY_SUBVOL keys. + * Creation of a snapshot does not require CAP_SYS_ADMIN, so + * we don't want users triggering transaction aborts, either + * intentionally or not. + */ + if (ret == -EOVERFLOW) + ret = 0; if (unlikely(ret && ret != -EEXIST)) { btrfs_abort_transaction(trans, ret); goto fail; diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index ac4c4573ee39..516ef62c8f43 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1284,7 +1284,7 @@ static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key, } if (unlikely(btrfs_root_drop_level(&ri) >= BTRFS_MAX_LEVEL)) { generic_err(leaf, slot, - "invalid root level, have %u expect [0, %u]", + "invalid root drop_level, have %u expect [0, %u]", btrfs_root_drop_level(&ri), BTRFS_MAX_LEVEL - 1); return -EUCLEAN; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 780a06d59240..552fef3c385a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -6195,6 +6195,7 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_log_ctx *ctx) { + const bool orig_log_new_dentries = ctx->log_new_dentries; int ret = 0; /* @@ -6256,7 +6257,11 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans, * dir index key range logged for the directory. So we * must make sure the deletion is recorded. */ + ctx->log_new_dentries = false; ret = btrfs_log_inode(trans, inode, LOG_INODE_ALL, ctx); + if (!ret && ctx->log_new_dentries) + ret = log_new_dir_dentries(trans, inode, ctx); + btrfs_add_delayed_iput(inode); if (ret) break; @@ -6291,6 +6296,7 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans, break; } + ctx->log_new_dentries = orig_log_new_dentries; ctx->logging_conflict_inodes = false; if (ret) free_conflicting_inodes(ctx); diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c index f24c14b9bb2f..43c17a1d3451 100644 --- a/fs/btrfs/uuid-tree.c +++ b/fs/btrfs/uuid-tree.c @@ -199,6 +199,44 @@ int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, const u8 *uuid, u8 return 0; } +/* + * Check if we can add one root ID to a UUID key. + * If the key does not yet exists, we can, otherwise only if extended item does + * not exceeds the maximum item size permitted by the leaf size. + * + * Returns 0 on success, negative value on error. + */ +int btrfs_uuid_tree_check_overflow(struct btrfs_fs_info *fs_info, + const u8 *uuid, u8 type) +{ + BTRFS_PATH_AUTO_FREE(path); + int ret; + u32 item_size; + struct btrfs_key key; + + if (WARN_ON_ONCE(!fs_info->uuid_root)) + return -EINVAL; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + btrfs_uuid_to_key(uuid, type, &key); + ret = btrfs_search_slot(NULL, fs_info->uuid_root, &key, path, 0, 0); + if (ret < 0) + return ret; + if (ret > 0) + return 0; + + item_size = btrfs_item_size(path->nodes[0], path->slots[0]); + + if (sizeof(struct btrfs_item) + item_size + sizeof(u64) > + BTRFS_LEAF_DATA_SIZE(fs_info)) + return -EOVERFLOW; + + return 0; +} + static int btrfs_uuid_iter_rem(struct btrfs_root *uuid_root, u8 *uuid, u8 type, u64 subid) { diff --git a/fs/btrfs/uuid-tree.h b/fs/btrfs/uuid-tree.h index c60ad20325cc..02b235a3653f 100644 --- a/fs/btrfs/uuid-tree.h +++ b/fs/btrfs/uuid-tree.h @@ -12,6 +12,8 @@ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, const u8 *uuid, u8 typ u64 subid); int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, const u8 *uuid, u8 type, u64 subid); +int btrfs_uuid_tree_check_overflow(struct btrfs_fs_info *fs_info, + const u8 *uuid, u8 type); int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info); int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info); int btrfs_uuid_scan_kthread(void *data); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 648bb09fc416..be8975ef8b24 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3587,7 +3587,7 @@ int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset, bool v /* step one, relocate all the extents inside this chunk */ btrfs_scrub_pause(fs_info); - ret = btrfs_relocate_block_group(fs_info, chunk_offset, true); + ret = btrfs_relocate_block_group(fs_info, chunk_offset, verbose); btrfs_scrub_continue(fs_info); if (ret) { /* diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 39930d99943c..817ca4fb9efa 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -337,7 +337,10 @@ int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info) if (!btrfs_fs_incompat(fs_info, ZONED)) return 0; - mutex_lock(&fs_devices->device_list_mutex); + /* + * No need to take the device_list mutex here, we're still in the mount + * path and devices cannot be added to or removed from the list yet. + */ list_for_each_entry(device, &fs_devices->devices, dev_list) { /* We can skip reading of zone info for missing devices */ if (!device->bdev) @@ -347,7 +350,6 @@ int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info) if (ret) break; } - mutex_unlock(&fs_devices->device_list_mutex); return ret; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index e87b3bb94ee8..2090fc78529c 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1326,7 +1326,6 @@ void ceph_process_folio_batch(struct address_space *mapping, continue; } else if (rc == -E2BIG) { folio_unlock(folio); - ceph_wbc->fbatch.folios[i] = NULL; break; } diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index f3fe786b4143..7dc307790240 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -79,7 +79,7 @@ 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) { - struct ceph_path_info path_info; + struct ceph_path_info path_info = {0}; path = ceph_mdsc_build_path(mdsc, req->r_dentry, &path_info, 0); if (IS_ERR(path)) path = NULL; @@ -98,7 +98,7 @@ static int mdsc_show(struct seq_file *s, void *p) } if (req->r_old_dentry) { - struct ceph_path_info path_info; + struct ceph_path_info path_info = {0}; path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &path_info, 0); if (IS_ERR(path)) path = NULL; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 86d7aa594ea9..bac9cfb6b982 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1339,6 +1339,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) struct ceph_client *cl = fsc->client; struct ceph_mds_client *mdsc = fsc->mdsc; struct inode *inode = d_inode(dentry); + struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_request *req; bool try_async = ceph_test_mount_opt(fsc, ASYNC_DIROPS); struct dentry *dn; @@ -1363,7 +1364,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) if (!dn) { try_async = false; } else { - struct ceph_path_info path_info; + struct ceph_path_info path_info = {0}; path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0); if (IS_ERR(path)) { try_async = false; @@ -1424,7 +1425,19 @@ retry: * We have enough caps, so we assume that the unlink * will succeed. Fix up the target inode and dcache. */ - drop_nlink(inode); + + /* + * Protect the i_nlink update with i_ceph_lock + * to precent racing against ceph_fill_inode() + * handling our completion on a worker thread + * and don't decrement if i_nlink has already + * been updated to zero by this completion. + */ + spin_lock(&ci->i_ceph_lock); + if (inode->i_nlink > 0) + drop_nlink(inode); + spin_unlock(&ci->i_ceph_lock); + d_delete(dentry); } else { spin_lock(&fsc->async_unlink_conflict_lock); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 66bbf6d517a9..5e7c73a29aa3 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -397,7 +397,7 @@ int ceph_open(struct inode *inode, struct file *file) if (!dentry) { do_sync = true; } else { - struct ceph_path_info path_info; + struct ceph_path_info path_info = {0}; path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0); if (IS_ERR(path)) { do_sync = true; @@ -807,7 +807,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, if (!dn) { try_async = false; } else { - struct ceph_path_info path_info; + struct ceph_path_info path_info = {0}; path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0); if (IS_ERR(path)) { try_async = false; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index d76f9a79dc0c..d99e12d1100b 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -2551,7 +2551,7 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode, if (!dentry) { do_sync = true; } else { - struct ceph_path_info path_info; + struct ceph_path_info path_info = {0}; path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0); if (IS_ERR(path)) { do_sync = true; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 23b6d00643c9..b1746273f186 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2768,6 +2768,7 @@ retry: if (ret < 0) { dput(parent); dput(cur); + __putname(path); return ERR_PTR(ret); } @@ -2777,6 +2778,7 @@ retry: if (len < 0) { dput(parent); dput(cur); + __putname(path); return ERR_PTR(len); } } @@ -2813,6 +2815,7 @@ retry: * cannot ever succeed. Creating paths that long is * possible with Ceph, but Linux cannot use them. */ + __putname(path); return ERR_PTR(-ENAMETOOLONG); } diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 12cb0ca738af..6bb30543eff0 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -87,7 +87,7 @@ config NFS_V4 space programs which can be found in the Linux nfs-utils package, available from http://linux-nfs.org/. - If unsure, say Y. + If unsure, say N. config NFS_SWAP bool "Provide swap over NFS support" @@ -100,6 +100,7 @@ config NFS_SWAP config NFS_V4_0 bool "NFS client support for NFSv4.0" depends on NFS_V4 + default y help This option enables support for minor version 0 of the NFSv4 protocol (RFC 3530) in the kernel's NFS client. diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 3e2de45c95fe..be2aebf62056 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -392,8 +392,13 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, if (status != 0) goto out_release_acls; - if (d_alias) + if (d_alias) { + if (d_is_dir(d_alias)) { + status = -EISDIR; + goto out_dput; + } dentry = d_alias; + } /* When we created the file with exclusive semantics, make * sure we set the attributes afterwards. */ diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 8fdbba7cad96..8e8a76a44ff0 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -36,19 +36,30 @@ * second map contains a reference to the entry in the first map. */ +static struct workqueue_struct *nfsd_export_wq; + #define EXPKEY_HASHBITS 8 #define EXPKEY_HASHMAX (1 << EXPKEY_HASHBITS) #define EXPKEY_HASHMASK (EXPKEY_HASHMAX -1) -static void expkey_put(struct kref *ref) +static void expkey_release(struct work_struct *work) { - struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); + struct svc_expkey *key = container_of(to_rcu_work(work), + struct svc_expkey, ek_rwork); if (test_bit(CACHE_VALID, &key->h.flags) && !test_bit(CACHE_NEGATIVE, &key->h.flags)) path_put(&key->ek_path); auth_domain_put(key->ek_client); - kfree_rcu(key, ek_rcu); + kfree(key); +} + +static void expkey_put(struct kref *ref) +{ + struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); + + INIT_RCU_WORK(&key->ek_rwork, expkey_release); + queue_rcu_work(nfsd_export_wq, &key->ek_rwork); } static int expkey_upcall(struct cache_detail *cd, struct cache_head *h) @@ -353,11 +364,13 @@ static void export_stats_destroy(struct export_stats *stats) EXP_STATS_COUNTERS_NUM); } -static void svc_export_release(struct rcu_head *rcu_head) +static void svc_export_release(struct work_struct *work) { - struct svc_export *exp = container_of(rcu_head, struct svc_export, - ex_rcu); + struct svc_export *exp = container_of(to_rcu_work(work), + struct svc_export, ex_rwork); + path_put(&exp->ex_path); + auth_domain_put(exp->ex_client); nfsd4_fslocs_free(&exp->ex_fslocs); export_stats_destroy(exp->ex_stats); kfree(exp->ex_stats); @@ -369,9 +382,8 @@ static void svc_export_put(struct kref *ref) { struct svc_export *exp = container_of(ref, struct svc_export, h.ref); - path_put(&exp->ex_path); - auth_domain_put(exp->ex_client); - call_rcu(&exp->ex_rcu, svc_export_release); + INIT_RCU_WORK(&exp->ex_rwork, svc_export_release); + queue_rcu_work(nfsd_export_wq, &exp->ex_rwork); } static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h) @@ -1479,6 +1491,36 @@ const struct seq_operations nfs_exports_op = { .show = e_show, }; +/** + * nfsd_export_wq_init - allocate the export release workqueue + * + * Called once at module load. The workqueue runs deferred svc_export and + * svc_expkey release work scheduled by queue_rcu_work() in the cache put + * callbacks. + * + * Return values: + * %0: workqueue allocated + * %-ENOMEM: allocation failed + */ +int nfsd_export_wq_init(void) +{ + nfsd_export_wq = alloc_workqueue("nfsd_export", WQ_UNBOUND, 0); + if (!nfsd_export_wq) + return -ENOMEM; + return 0; +} + +/** + * nfsd_export_wq_shutdown - drain and free the export release workqueue + * + * Called once at module unload. Per-namespace teardown in + * nfsd_export_shutdown() has already drained all deferred work. + */ +void nfsd_export_wq_shutdown(void) +{ + destroy_workqueue(nfsd_export_wq); +} + /* * Initialize the exports module. */ @@ -1540,6 +1582,9 @@ nfsd_export_shutdown(struct net *net) cache_unregister_net(nn->svc_expkey_cache, net); cache_unregister_net(nn->svc_export_cache, net); + /* Drain deferred export and expkey release work. */ + rcu_barrier(); + flush_workqueue(nfsd_export_wq); cache_destroy_net(nn->svc_expkey_cache, net); cache_destroy_net(nn->svc_export_cache, net); svcauth_unix_purge(net); diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index d2b09cd76145..b05399374574 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -7,6 +7,7 @@ #include <linux/sunrpc/cache.h> #include <linux/percpu_counter.h> +#include <linux/workqueue.h> #include <uapi/linux/nfsd/export.h> #include <linux/nfs4.h> @@ -75,7 +76,7 @@ struct svc_export { u32 ex_layout_types; struct nfsd4_deviceid_map *ex_devid_map; struct cache_detail *cd; - struct rcu_head ex_rcu; + struct rcu_work ex_rwork; unsigned long ex_xprtsec_modes; struct export_stats *ex_stats; }; @@ -92,7 +93,7 @@ struct svc_expkey { u32 ek_fsid[6]; struct path ek_path; - struct rcu_head ek_rcu; + struct rcu_work ek_rwork; }; #define EX_ISSYNC(exp) (!((exp)->ex_flags & NFSEXP_ASYNC)) @@ -110,6 +111,8 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp, /* * Function declarations */ +int nfsd_export_wq_init(void); +void nfsd_export_wq_shutdown(void); int nfsd_export_init(struct net *); void nfsd_export_shutdown(struct net *); void nfsd_export_flush(struct net *); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 41dfba5ab8b8..9d234913100b 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -6281,9 +6281,14 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) int len = xdr->buf->len - (op_status_offset + XDR_UNIT); so->so_replay.rp_status = op->status; - so->so_replay.rp_buflen = len; - read_bytes_from_xdr_buf(xdr->buf, op_status_offset + XDR_UNIT, + if (len <= NFSD4_REPLAY_ISIZE) { + so->so_replay.rp_buflen = len; + read_bytes_from_xdr_buf(xdr->buf, + op_status_offset + XDR_UNIT, so->so_replay.rp_buf, len); + } else { + so->so_replay.rp_buflen = 0; + } } status: op->status = nfsd4_map_status(op->status, diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 4cc8a58fa56a..71aabdaa1d15 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -149,9 +149,19 @@ static int exports_net_open(struct net *net, struct file *file) seq = file->private_data; seq->private = nn->svc_export_cache; + get_net(net); return 0; } +static int exports_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct cache_detail *cd = seq->private; + + put_net(cd->net); + return seq_release(inode, file); +} + static int exports_nfsd_open(struct inode *inode, struct file *file) { return exports_net_open(inode->i_sb->s_fs_info, file); @@ -161,7 +171,7 @@ static const struct file_operations exports_nfsd_operations = { .open = exports_nfsd_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = exports_release, }; static int export_features_show(struct seq_file *m, void *v) @@ -1376,7 +1386,7 @@ static const struct proc_ops exports_proc_ops = { .proc_open = exports_proc_open, .proc_read = seq_read, .proc_lseek = seq_lseek, - .proc_release = seq_release, + .proc_release = exports_release, }; static int create_proc_exports_entry(void) @@ -2259,9 +2269,12 @@ static int __init init_nfsd(void) if (retval) goto out_free_pnfs; nfsd_lockd_init(); /* lockd->nfsd callbacks */ + retval = nfsd_export_wq_init(); + if (retval) + goto out_free_lockd; retval = register_pernet_subsys(&nfsd_net_ops); if (retval < 0) - goto out_free_lockd; + goto out_free_export_wq; retval = register_cld_notifier(); if (retval) goto out_free_subsys; @@ -2290,6 +2303,8 @@ out_free_cld: unregister_cld_notifier(); out_free_subsys: unregister_pernet_subsys(&nfsd_net_ops); +out_free_export_wq: + nfsd_export_wq_shutdown(); out_free_lockd: nfsd_lockd_shutdown(); nfsd_drc_slab_free(); @@ -2310,6 +2325,7 @@ static void __exit exit_nfsd(void) nfsd4_destroy_laundry_wq(); unregister_cld_notifier(); unregister_pernet_subsys(&nfsd_net_ops); + nfsd_export_wq_shutdown(); nfsd_drc_slab_free(); nfsd_lockd_shutdown(); nfsd4_free_slabs(); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 6fcbf1e427d4..c0ca115c3b74 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -541,11 +541,18 @@ struct nfs4_client_reclaim { struct xdr_netobj cr_princhash; }; -/* A reasonable value for REPLAY_ISIZE was estimated as follows: - * The OPEN response, typically the largest, requires - * 4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) + 8(verifier) + - * 4(deleg. type) + 8(deleg. stateid) + 4(deleg. recall flag) + - * 20(deleg. space limit) + ~32(deleg. ace) = 112 bytes +/* + * REPLAY_ISIZE is sized for an OPEN response with delegation: + * 4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) + + * 8(verifier) + 4(deleg. type) + 8(deleg. stateid) + + * 4(deleg. recall flag) + 20(deleg. space limit) + + * ~32(deleg. ace) = 112 bytes + * + * Some responses can exceed this. A LOCK denial includes the conflicting + * lock owner, which can be up to 1024 bytes (NFS4_OPAQUE_LIMIT). Responses + * larger than REPLAY_ISIZE are not cached in rp_ibuf; only rp_status is + * saved. Enlarging this constant increases the size of every + * nfs4_stateowner. */ #define NFSD4_REPLAY_ISIZE 112 diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index f4cb3018a358..c920039d733c 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -1489,7 +1489,7 @@ struct smb_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb, struct cifsFileInfo *open_file = NULL; if (inode) - open_file = find_readable_file(CIFS_I(inode), true); + open_file = find_readable_file(CIFS_I(inode), FIND_FSUID_ONLY); if (!open_file) return get_cifs_acl_by_path(cifs_sb, path, pacllen, info); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index b6e3db993cc6..32d0305a1239 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -1269,7 +1269,7 @@ static int cifs_precopy_set_eof(struct inode *src_inode, struct cifsInodeInfo *s struct cifsFileInfo *writeable_srcfile; int rc = -EINVAL; - writeable_srcfile = find_writable_file(src_cifsi, FIND_WR_FSUID_ONLY); + writeable_srcfile = find_writable_file(src_cifsi, FIND_FSUID_ONLY); if (writeable_srcfile) { if (src_tcon->ses->server->ops->set_file_size) rc = src_tcon->ses->server->ops->set_file_size( diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 6f9b6c72962b..7877d327dbb0 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -20,6 +20,7 @@ #include <linux/utsname.h> #include <linux/sched/mm.h> #include <linux/netfs.h> +#include <linux/fcntl.h> #include "cifs_fs_sb.h" #include "cifsacl.h" #include <crypto/internal/hash.h> @@ -1884,12 +1885,12 @@ static inline bool is_replayable_error(int error) } -/* cifs_get_writable_file() flags */ -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), +enum cifs_find_flags { + FIND_ANY = 0U, + FIND_FSUID_ONLY = (1U << 0), + FIND_WITH_DELETE = (1U << 1), + FIND_NO_PENDING_DELETE = (1U << 2), + FIND_OPEN_FLAGS = (1U << 3), }; #define MID_FREE 0 @@ -2375,4 +2376,14 @@ static inline bool cifs_forced_shutdown(const struct cifs_sb_info *sbi) return cifs_sb_flags(sbi) & CIFS_MOUNT_SHUTDOWN; } +static inline int cifs_open_create_options(unsigned int oflags, int opts) +{ + /* O_SYNC also has bit for O_DSYNC so following check picks up either */ + if (oflags & O_SYNC) + opts |= CREATE_WRITE_THROUGH; + if (oflags & O_DIRECT) + opts |= CREATE_NO_BUFFER; + return opts; +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 800a7e418c32..884bfa1cf0b4 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -138,12 +138,14 @@ void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t result); struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode, int flags); -int cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags, - struct cifsFileInfo **ret_file); +int __cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, + unsigned int find_flags, unsigned int open_flags, + struct cifsFileInfo **ret_file); int cifs_get_writable_path(struct cifs_tcon *tcon, const char *name, int flags, struct cifsFileInfo **ret_file); -struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, - bool fsuid_only); +struct cifsFileInfo *__find_readable_file(struct cifsInodeInfo *cifs_inode, + unsigned int find_flags, + unsigned int open_flags); int cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, struct cifsFileInfo **ret_file); int cifs_get_hardlink_path(struct cifs_tcon *tcon, struct inode *inode, @@ -596,4 +598,20 @@ static inline void cifs_sg_set_buf(struct sg_table *sgtable, } } +static inline int cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, + unsigned int find_flags, + struct cifsFileInfo **ret_file) +{ + find_flags &= ~FIND_OPEN_FLAGS; + return __cifs_get_writable_file(cifs_inode, find_flags, 0, ret_file); +} + +static inline struct cifsFileInfo * +find_readable_file(struct cifsInodeInfo *cinode, unsigned int find_flags) +{ + find_flags &= ~FIND_OPEN_FLAGS; + find_flags |= FIND_NO_PENDING_DELETE; + return __find_readable_file(cinode, find_flags, 0); +} + #endif /* _CIFSPROTO_H */ diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index 953f1fee8cb8..6d2378eeb7f6 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -187,7 +187,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned const char *full_path; void *page = alloc_dentry_path(); struct inode *newinode = NULL; - unsigned int sbflags; + unsigned int sbflags = cifs_sb_flags(cifs_sb); int disposition; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; @@ -308,6 +308,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned goto out; } + create_options |= cifs_open_create_options(oflags, create_options); /* * if we're not using unix extensions, see if we need to set * ATTR_READONLY on the create call @@ -367,7 +368,6 @@ retry_open: * If Open reported that we actually created a file then we now have to * set the mode if possible. */ - sbflags = cifs_sb_flags(cifs_sb); if ((tcon->unix_ext) && (*oplock & CIFS_CREATE_ACTION)) { struct cifs_unix_set_info_args args = { .mode = mode, diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index cffcf82c1b69..27f61fe7e4e2 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -255,7 +255,7 @@ static void cifs_begin_writeback(struct netfs_io_request *wreq) struct cifs_io_request *req = container_of(wreq, struct cifs_io_request, rreq); int ret; - ret = cifs_get_writable_file(CIFS_I(wreq->inode), FIND_WR_ANY, &req->cfile); + ret = cifs_get_writable_file(CIFS_I(wreq->inode), FIND_ANY, &req->cfile); if (ret) { cifs_dbg(VFS, "No writable handle in writepages ret=%d\n", ret); return; @@ -584,15 +584,8 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ *********************************************************************/ disposition = cifs_get_disposition(f_flags); - /* BB pass O_SYNC flag through on file attributes .. BB */ - - /* O_SYNC also has bit for O_DSYNC so following check picks up either */ - if (f_flags & O_SYNC) - create_options |= CREATE_WRITE_THROUGH; - - if (f_flags & O_DIRECT) - create_options |= CREATE_NO_BUFFER; + create_options |= cifs_open_create_options(f_flags, create_options); retry_open: oparms = (struct cifs_open_parms) { @@ -963,7 +956,7 @@ int cifs_file_flush(const unsigned int xid, struct inode *inode, return tcon->ses->server->ops->flush(xid, tcon, &cfile->fid); } - rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, &cfile); + rc = cifs_get_writable_file(CIFS_I(inode), FIND_ANY, &cfile); if (!rc) { tcon = tlink_tcon(cfile->tlink); rc = tcon->ses->server->ops->flush(xid, tcon, &cfile->fid); @@ -988,7 +981,7 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry) return -ERESTARTSYS; mapping_set_error(inode->i_mapping, rc); - cfile = find_writable_file(cinode, FIND_WR_FSUID_ONLY); + cfile = find_writable_file(cinode, FIND_FSUID_ONLY); rc = cifs_file_flush(xid, inode, cfile); if (!rc) { if (cfile) { @@ -1068,32 +1061,29 @@ 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 | - FIND_WR_NO_PENDING_DELETE, - &cfile); + rc = __cifs_get_writable_file(CIFS_I(inode), + FIND_FSUID_ONLY | + FIND_NO_PENDING_DELETE | + FIND_OPEN_FLAGS, + file->f_flags, &cfile); } else { - rc = cifs_get_readable_path(tcon, full_path, &cfile); + cfile = __find_readable_file(CIFS_I(inode), + FIND_NO_PENDING_DELETE | + FIND_OPEN_FLAGS, + file->f_flags); + rc = cfile ? 0 : -ENOENT; } if (rc == 0) { - unsigned int oflags = file->f_flags & ~(O_CREAT|O_EXCL|O_TRUNC); - unsigned int cflags = cfile->f_flags & ~(O_CREAT|O_EXCL|O_TRUNC); - - if (cifs_convert_flags(oflags, 0) == cifs_convert_flags(cflags, 0) && - (oflags & (O_SYNC|O_DIRECT)) == (cflags & (O_SYNC|O_DIRECT))) { - file->private_data = cfile; - spin_lock(&CIFS_I(inode)->deferred_lock); - cifs_del_deferred_close(cfile); - spin_unlock(&CIFS_I(inode)->deferred_lock); - goto use_cache; - } - _cifsFileInfo_put(cfile, true, false); - } else { - /* hard link on the defeered close file */ - rc = cifs_get_hardlink_path(tcon, inode, file); - if (rc) - cifs_close_deferred_file(CIFS_I(inode)); - } + file->private_data = cfile; + spin_lock(&CIFS_I(inode)->deferred_lock); + cifs_del_deferred_close(cfile); + spin_unlock(&CIFS_I(inode)->deferred_lock); + goto use_cache; + } + /* hard link on the deferred close file */ + rc = cifs_get_hardlink_path(tcon, inode, file); + if (rc) + cifs_close_deferred_file(CIFS_I(inode)); if (server->oplocks) oplock = REQ_OPLOCK; @@ -1314,13 +1304,8 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) rdwr_for_fscache = 1; desired_access = cifs_convert_flags(cfile->f_flags, rdwr_for_fscache); - - /* O_SYNC also has bit for O_DSYNC so following check picks up either */ - if (cfile->f_flags & O_SYNC) - create_options |= CREATE_WRITE_THROUGH; - - if (cfile->f_flags & O_DIRECT) - create_options |= CREATE_NO_BUFFER; + create_options |= cifs_open_create_options(cfile->f_flags, + create_options); if (server->ops->get_lease_key) server->ops->get_lease_key(inode, &cfile->fid); @@ -2524,10 +2509,33 @@ void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t netfs_write_subrequest_terminated(&wdata->subreq, result); } -struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, - bool fsuid_only) +static bool open_flags_match(struct cifsInodeInfo *cinode, + unsigned int oflags, unsigned int cflags) +{ + struct inode *inode = &cinode->netfs.inode; + int crw = 0, orw = 0; + + oflags &= ~(O_CREAT | O_EXCL | O_TRUNC); + cflags &= ~(O_CREAT | O_EXCL | O_TRUNC); + + if (cifs_fscache_enabled(inode)) { + if (OPEN_FMODE(cflags) & FMODE_WRITE) + crw = 1; + if (OPEN_FMODE(oflags) & FMODE_WRITE) + orw = 1; + } + if (cifs_convert_flags(oflags, orw) != cifs_convert_flags(cflags, crw)) + return false; + + return (oflags & (O_SYNC | O_DIRECT)) == (cflags & (O_SYNC | O_DIRECT)); +} + +struct cifsFileInfo *__find_readable_file(struct cifsInodeInfo *cifs_inode, + unsigned int find_flags, + unsigned int open_flags) { struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode); + bool fsuid_only = find_flags & FIND_FSUID_ONLY; struct cifsFileInfo *open_file = NULL; /* only filter by fsuid on multiuser mounts */ @@ -2541,6 +2549,13 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, list_for_each_entry(open_file, &cifs_inode->openFileList, flist) { if (fsuid_only && !uid_eq(open_file->uid, current_fsuid())) continue; + if ((find_flags & FIND_NO_PENDING_DELETE) && + open_file->status_file_deleted) + continue; + if ((find_flags & FIND_OPEN_FLAGS) && + !open_flags_match(cifs_inode, open_flags, + open_file->f_flags)) + continue; if (OPEN_FMODE(open_file->f_flags) & FMODE_READ) { if ((!open_file->invalidHandle)) { /* found a good file */ @@ -2559,17 +2574,17 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, } /* Return -EBADF if no handle is found and general rc otherwise */ -int -cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags, - struct cifsFileInfo **ret_file) +int __cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, + unsigned int find_flags, unsigned int open_flags, + struct cifsFileInfo **ret_file) { struct cifsFileInfo *open_file, *inv_file = NULL; struct cifs_sb_info *cifs_sb; bool any_available = false; int rc = -EBADF; unsigned int refind = 0; - bool fsuid_only = flags & FIND_WR_FSUID_ONLY; - bool with_delete = flags & FIND_WR_WITH_DELETE; + bool fsuid_only = find_flags & FIND_FSUID_ONLY; + bool with_delete = find_flags & FIND_WITH_DELETE; *ret_file = NULL; /* @@ -2603,9 +2618,13 @@ refind_writable: continue; if (with_delete && !(open_file->fid.access & DELETE)) continue; - if ((flags & FIND_WR_NO_PENDING_DELETE) && + if ((find_flags & FIND_NO_PENDING_DELETE) && open_file->status_file_deleted) continue; + if ((find_flags & FIND_OPEN_FLAGS) && + !open_flags_match(cifs_inode, open_flags, + open_file->f_flags)) + continue; if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) { if (!open_file->invalidHandle) { /* found a good writable file */ @@ -2722,17 +2741,7 @@ cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, cinode = CIFS_I(d_inode(cfile->dentry)); 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); - } - } + *ret_file = find_readable_file(cinode, FIND_ANY); return *ret_file ? 0 : -ENOENT; } @@ -2804,7 +2813,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) } if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) { - smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY); + smbfile = find_writable_file(CIFS_I(inode), FIND_ANY); if (smbfile) { rc = server->ops->flush(xid, tcon, &smbfile->fid); cifsFileInfo_put(smbfile); diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index 54090739535f..a4a7c7eee038 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -1997,7 +1997,7 @@ int smb3_init_fs_context(struct fs_context *fc) ctx->backupuid_specified = false; /* no backup intent for a user */ ctx->backupgid_specified = false; /* no backup intent for a group */ - ctx->retrans = 1; + ctx->retrans = 0; ctx->reparse_type = CIFS_REPARSE_TYPE_DEFAULT; ctx->symlink_type = CIFS_SYMLINK_TYPE_DEFAULT; ctx->nonativesocket = 0; diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 3e844c55ab8a..143fa2e665ed 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -2997,7 +2997,7 @@ int cifs_fiemap(struct inode *inode, struct fiemap_extent_info *fei, u64 start, } } - cfile = find_readable_file(cifs_i, false); + cfile = find_readable_file(cifs_i, FIND_ANY); if (cfile == NULL) return -EINVAL; @@ -3050,7 +3050,7 @@ int cifs_file_set_size(const unsigned int xid, struct dentry *dentry, size, false); cifs_dbg(FYI, "%s: set_file_size: rc = %d\n", __func__, rc); } else { - open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY); + open_file = find_writable_file(cifsInode, FIND_FSUID_ONLY); if (open_file) { tcon = tlink_tcon(open_file->tlink); server = tcon->ses->server; @@ -3219,7 +3219,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) open_file->fid.netfid, open_file->pid); } else { - open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY); + open_file = find_writable_file(cifsInode, FIND_FSUID_ONLY); if (open_file) { pTcon = tlink_tcon(open_file->tlink); rc = CIFSSMBUnixSetFileInfo(xid, pTcon, args, diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index 9643eca0cb70..9694117050a6 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -960,7 +960,7 @@ smb_set_file_info(struct inode *inode, const char *full_path, struct cifs_tcon *tcon; /* if the file is already open for write, just use that fileid */ - open_file = find_writable_file(cinode, FIND_WR_FSUID_ONLY); + open_file = find_writable_file(cinode, FIND_FSUID_ONLY); if (open_file) { fid.netfid = open_file->fid.netfid; diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 5280c5c869ad..364bdcff9c9d 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -1156,7 +1156,7 @@ smb2_mkdir_setinfo(struct inode *inode, const char *name, cifs_i = CIFS_I(inode); dosattrs = cifs_i->cifsAttrs | ATTR_READONLY; data.Attributes = cpu_to_le32(dosattrs); - cifs_get_writable_path(tcon, name, FIND_WR_ANY, &cfile); + cifs_get_writable_path(tcon, name, FIND_ANY, &cfile); oparms = CIFS_OPARMS(cifs_sb, tcon, name, FILE_WRITE_ATTRIBUTES, FILE_CREATE, CREATE_NOT_FILE, ACL_NO_MODE); tmprc = smb2_compound_op(xid, tcon, cifs_sb, name, @@ -1336,14 +1336,13 @@ int smb2_rename_path(const unsigned int xid, __u32 co = file_create_options(source_dentry); drop_cached_dir_by_name(xid, tcon, from_name, cifs_sb); - cifs_get_writable_path(tcon, from_name, FIND_WR_WITH_DELETE, &cfile); + cifs_get_writable_path(tcon, from_name, FIND_WITH_DELETE, &cfile); int rc = smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb, co, DELETE, SMB2_OP_RENAME, cfile, source_dentry); if (rc == -EINVAL) { cifs_dbg(FYI, "invalid lease key, resending request without lease"); - cifs_get_writable_path(tcon, from_name, - FIND_WR_WITH_DELETE, &cfile); + cifs_get_writable_path(tcon, from_name, FIND_WITH_DELETE, &cfile); rc = smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb, co, DELETE, SMB2_OP_RENAME, cfile, NULL); } @@ -1377,7 +1376,7 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon, in_iov.iov_base = &eof; in_iov.iov_len = sizeof(eof); - cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); + cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile); oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_WRITE_DATA, FILE_OPEN, 0, ACL_NO_MODE); @@ -1387,7 +1386,7 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon, cfile, NULL, NULL, dentry); if (rc == -EINVAL) { cifs_dbg(FYI, "invalid lease key, resending request without lease"); - cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); + cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, &in_iov, &(int){SMB2_OP_SET_EOF}, 1, @@ -1417,7 +1416,7 @@ smb2_set_file_info(struct inode *inode, const char *full_path, (buf->LastWriteTime == 0) && (buf->ChangeTime == 0)) { if (buf->Attributes == 0) goto out; /* would be a no op, no sense sending this */ - cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); + cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile); } oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_WRITE_ATTRIBUTES, @@ -1476,7 +1475,7 @@ struct inode *smb2_create_reparse_inode(struct cifs_open_info_data *data, if (tcon->posix_extensions) { cmds[1] = SMB2_OP_POSIX_QUERY_INFO; - cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); + cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, in_iov, cmds, 2, cfile, out_iov, out_buftype, NULL); if (!rc) { @@ -1485,7 +1484,7 @@ struct inode *smb2_create_reparse_inode(struct cifs_open_info_data *data, } } else { cmds[1] = SMB2_OP_QUERY_INFO; - cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); + cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, in_iov, cmds, 2, cfile, out_iov, out_buftype, NULL); if (!rc) { @@ -1636,13 +1635,12 @@ int smb2_rename_pending_delete(const char *full_path, 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); + cifs_get_writable_path(tcon, full_path, FIND_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); + cifs_get_writable_path(tcon, full_path, FIND_WITH_DELETE, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov, cmds, num_cmds, cfile, NULL, NULL, NULL); } diff --git a/fs/smb/client/smb2maperror.c b/fs/smb/client/smb2maperror.c index f4cff44e2796..2b8782c4f684 100644 --- a/fs/smb/client/smb2maperror.c +++ b/fs/smb/client/smb2maperror.c @@ -109,6 +109,9 @@ int __init smb2_init_maperror(void) } #if IS_ENABLED(CONFIG_SMB_KUNIT_TESTS) +#define EXPORT_SYMBOL_FOR_SMB_TEST(sym) \ + EXPORT_SYMBOL_FOR_MODULES(sym, "smb2maperror_test") + /* Previous prototype for eliminating the build warning. */ const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status); @@ -116,11 +119,11 @@ const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status) { return smb2_get_err_map(smb2_status); } -EXPORT_SYMBOL_GPL(smb2_get_err_map_test); +EXPORT_SYMBOL_FOR_SMB_TEST(smb2_get_err_map_test); const struct status_to_posix_error *smb2_error_map_table_test = smb2_error_map_table; -EXPORT_SYMBOL_GPL(smb2_error_map_table_test); +EXPORT_SYMBOL_FOR_SMB_TEST(smb2_error_map_table_test); unsigned int smb2_error_map_num = ARRAY_SIZE(smb2_error_map_table); -EXPORT_SYMBOL_GPL(smb2_error_map_num); +EXPORT_SYMBOL_FOR_SMB_TEST(smb2_error_map_num); #endif diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 7f2d3459cbf9..98ac4e86bf99 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -628,6 +628,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, struct smb_sockaddr_in6 *p6; struct cifs_server_iface *info = NULL, *iface = NULL, *niface = NULL; struct cifs_server_iface tmp_iface; + __be16 port; ssize_t bytes_left; size_t next = 0; int nb_iface = 0; @@ -662,6 +663,15 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, goto out; } + spin_lock(&ses->server->srv_lock); + if (ses->server->dstaddr.ss_family == AF_INET) + port = ((struct sockaddr_in *)&ses->server->dstaddr)->sin_port; + else if (ses->server->dstaddr.ss_family == AF_INET6) + port = ((struct sockaddr_in6 *)&ses->server->dstaddr)->sin6_port; + else + port = cpu_to_be16(CIFS_PORT); + spin_unlock(&ses->server->srv_lock); + while (bytes_left >= (ssize_t)sizeof(*p)) { memset(&tmp_iface, 0, sizeof(tmp_iface)); /* default to 1Gbps when link speed is unset */ @@ -682,7 +692,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, memcpy(&addr4->sin_addr, &p4->IPv4Address, 4); /* [MS-SMB2] 2.2.32.5.1.1 Clients MUST ignore these */ - addr4->sin_port = cpu_to_be16(CIFS_PORT); + addr4->sin_port = port; cifs_dbg(FYI, "%s: ipv4 %pI4\n", __func__, &addr4->sin_addr); @@ -696,7 +706,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, /* [MS-SMB2] 2.2.32.5.1.2 Clients MUST ignore these */ addr6->sin6_flowinfo = 0; addr6->sin6_scope_id = 0; - addr6->sin6_port = cpu_to_be16(CIFS_PORT); + addr6->sin6_port = port; cifs_dbg(FYI, "%s: ipv6 %pI6\n", __func__, &addr6->sin6_addr); @@ -3352,7 +3362,7 @@ get_smb2_acl(struct cifs_sb_info *cifs_sb, struct cifsFileInfo *open_file = NULL; if (inode && !(info & SACL_SECINFO)) - open_file = find_readable_file(CIFS_I(inode), true); + open_file = find_readable_file(CIFS_I(inode), FIND_FSUID_ONLY); if (!open_file || (info & SACL_SECINFO)) return get_smb2_acl_by_path(cifs_sb, path, pacllen, info); @@ -3898,7 +3908,7 @@ static loff_t smb3_llseek(struct file *file, struct cifs_tcon *tcon, loff_t offs * some servers (Windows2016) will not reflect recent writes in * QUERY_ALLOCATED_RANGES until SMB2_flush is called. */ - wrcfile = find_writable_file(cifsi, FIND_WR_ANY); + wrcfile = find_writable_file(cifsi, FIND_ANY); if (wrcfile) { filemap_write_and_wait(inode->i_mapping); smb2_flush_file(xid, tcon, &wrcfile->fid); diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index c43ca74e8704..5188218c25be 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -5307,7 +5307,10 @@ replay_again: memset(&rqst, 0, sizeof(struct smb_rqst)); rqst.rq_iov = iov; - rqst.rq_nvec = n_vec + 1; + /* iov[0] is the SMB header; move payload to rq_iter for encryption safety */ + rqst.rq_nvec = 1; + iov_iter_kvec(&rqst.rq_iter, ITER_SOURCE, &iov[1], n_vec, + io_parms->length); if (retries) { /* Back-off before retry */ diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index 766631f0562e..09d4c17b3e7b 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -2716,12 +2716,8 @@ xfs_dabuf_map( * larger one that needs to be free by the caller. */ if (nirecs > 1) { - map = kzalloc(nirecs * sizeof(struct xfs_buf_map), - GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); - if (!map) { - error = -ENOMEM; - goto out_free_irecs; - } + map = kcalloc(nirecs, sizeof(struct xfs_buf_map), + GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); *mapp = map; } diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 472c261163ed..c6909716b041 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -809,7 +809,7 @@ xfs_defer_can_append( /* Paused items cannot absorb more work */ if (dfp->dfp_flags & XFS_DEFER_PAUSED) - return NULL; + return false; /* Already full? */ if (ops->max_items && dfp->dfp_count >= ops->max_items) diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index e8775f254c89..b237a25d6045 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -245,7 +245,7 @@ xfs_bmap_update_diff_items( struct xfs_bmap_intent *ba = bi_entry(a); struct xfs_bmap_intent *bb = bi_entry(b); - return ba->bi_owner->i_ino - bb->bi_owner->i_ino; + return cmp_int(ba->bi_owner->i_ino, bb->bi_owner->i_ino); } /* Log bmap updates in the intent item. */ diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 2b208e2c5264..69e9bc588c8b 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -1439,9 +1439,15 @@ xfs_qm_dqflush( return 0; out_abort: + /* + * Shut down the log before removing the dquot item from the AIL. + * Otherwise, the log tail may advance past this item's LSN while + * log writes are still in progress, making these unflushed changes + * unrecoverable on the next mount. + */ + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); dqp->q_flags &= ~XFS_DQFLAG_DIRTY; xfs_trans_ail_delete(lip, 0); - xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); xfs_dqfunlock(dqp); return error; } diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c index 4a06d6632f65..26c325d34bd1 100644 --- a/fs/xfs/xfs_healthmon.c +++ b/fs/xfs/xfs_healthmon.c @@ -141,6 +141,16 @@ xfs_healthmon_detach( hm->mount_cookie = DETACHED_MOUNT_COOKIE; spin_unlock(&xfs_healthmon_lock); + /* + * Wake up any readers that might remain. This can happen if unmount + * races with the healthmon fd owner entering ->read_iter, having + * already emptied the event queue. + * + * In the ->release case there shouldn't be any readers because the + * only users of the waiter are read and poll. + */ + wake_up_all(&hm->wait); + trace_xfs_healthmon_detach(hm); xfs_healthmon_put(hm); } @@ -1027,13 +1037,6 @@ xfs_healthmon_release( * process can create another health monitor file. */ xfs_healthmon_detach(hm); - - /* - * Wake up any readers that might be left. There shouldn't be any - * because the only users of the waiter are read and poll. - */ - wake_up_all(&hm->wait); - xfs_healthmon_put(hm); return 0; } diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index a7a09e7eec81..2040a9292ee6 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -159,7 +159,6 @@ xfs_inode_free_callback( ASSERT(!test_bit(XFS_LI_IN_AIL, &ip->i_itemp->ili_item.li_flags)); xfs_inode_item_destroy(ip); - ip->i_itemp = NULL; } kmem_cache_free(xfs_inode_cache, ip); diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index b96f262ba139..f807f8f4f705 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1357,6 +1357,8 @@ xlog_alloc_log( if (xfs_has_logv2(mp) && mp->m_sb.sb_logsunit > 1) log->l_iclog_roundoff = mp->m_sb.sb_logsunit; + else if (mp->m_sb.sb_logsectsize > 0) + log->l_iclog_roundoff = mp->m_sb.sb_logsectsize; else log->l_iclog_roundoff = BBSIZE; diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c index 7efeecd2d85f..309f70098524 100644 --- a/fs/xfs/xfs_zone_gc.c +++ b/fs/xfs/xfs_zone_gc.c @@ -96,7 +96,6 @@ struct xfs_gc_bio { */ xfs_fsblock_t old_startblock; xfs_daddr_t new_daddr; - struct xfs_zone_scratch *scratch; /* Are we writing to a sequential write required zone? */ bool is_seq; @@ -779,7 +778,6 @@ xfs_zone_gc_split_write( ihold(VFS_I(chunk->ip)); split_chunk->ip = chunk->ip; split_chunk->is_seq = chunk->is_seq; - split_chunk->scratch = chunk->scratch; split_chunk->offset = chunk->offset; split_chunk->len = split_len; split_chunk->old_startblock = chunk->old_startblock; diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h index 2cfbb4c65c78..d3dc5dc5f916 100644 --- a/include/linux/build_bug.h +++ b/include/linux/build_bug.h @@ -32,7 +32,8 @@ /** * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied * error message. - * @condition: the condition which the compiler should know is false. + * @cond: the condition which the compiler should know is false. + * @msg: build-time error message * * See BUILD_BUG_ON for description. */ @@ -60,6 +61,7 @@ /** * static_assert - check integer constant expression at build time + * @expr: expression to be checked * * static_assert() is a wrapper for the C11 _Static_assert, with a * little macro magic to make the message optional (defaulting to the diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index d290060f4c73..91013161e9db 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -68,12 +68,12 @@ * timeout value used in Stratix10 FPGA manager driver. * timeout value used in RSU driver */ -#define SVC_RECONFIG_REQUEST_TIMEOUT_MS 300 -#define SVC_RECONFIG_BUFFER_TIMEOUT_MS 720 -#define SVC_RSU_REQUEST_TIMEOUT_MS 300 +#define SVC_RECONFIG_REQUEST_TIMEOUT_MS 5000 +#define SVC_RECONFIG_BUFFER_TIMEOUT_MS 5000 +#define SVC_RSU_REQUEST_TIMEOUT_MS 2000 #define SVC_FCS_REQUEST_TIMEOUT_MS 2000 #define SVC_COMPLETED_TIMEOUT_MS 30000 -#define SVC_HWMON_REQUEST_TIMEOUT_MS 300 +#define SVC_HWMON_REQUEST_TIMEOUT_MS 2000 struct stratix10_svc_chan; diff --git a/include/linux/hid.h b/include/linux/hid.h index 2990b9f94cb5..31324609af4d 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -682,6 +682,7 @@ struct hid_device { __s32 battery_charge_status; enum hid_battery_status battery_status; bool battery_avoid_query; + bool battery_present; ktime_t battery_ratelimit_time; #endif diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 3e4a82a6f817..dd1420bfcb73 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -388,6 +388,7 @@ struct io_ring_ctx { * regularly bounce b/w CPUs. */ struct { + struct io_rings __rcu *rings_rcu; struct llist_head work_llist; struct llist_head retry_llist; unsigned long check_cq; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 34759a262b28..6b76e7a6f4c2 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1940,56 +1940,43 @@ enum kvm_stat_kind { struct kvm_stat_data { struct kvm *kvm; - const struct _kvm_stats_desc *desc; + const struct kvm_stats_desc *desc; enum kvm_stat_kind kind; }; -struct _kvm_stats_desc { - struct kvm_stats_desc desc; - char name[KVM_STATS_NAME_SIZE]; -}; - -#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \ - .flags = type | unit | base | \ - BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ - BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ - BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ - .exponent = exp, \ - .size = sz, \ +#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \ + .flags = type | unit | base | \ + BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ + BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ + BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ + .exponent = exp, \ + .size = sz, \ .bucket_size = bsz -#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vm_stat, generic.stat) \ - }, \ - .name = #stat, \ - } -#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vcpu_stat, generic.stat) \ - }, \ - .name = #stat, \ - } -#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vm_stat, stat) \ - }, \ - .name = #stat, \ - } -#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vcpu_stat, stat) \ - }, \ - .name = #stat, \ - } +#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vm_stat, generic.stat), \ + .name = #stat, \ +} +#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vcpu_stat, generic.stat), \ + .name = #stat, \ +} +#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vm_stat, stat), \ + .name = #stat, \ +} +#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vcpu_stat, stat), \ + .name = #stat, \ +} /* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */ #define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz) \ SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz) @@ -2066,7 +2053,7 @@ struct _kvm_stats_desc { STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, - const struct _kvm_stats_desc *desc, + const struct kvm_stats_desc *desc, void *stats, size_t size_stats, char __user *user_buffer, size_t size, loff_t *offset); @@ -2111,9 +2098,9 @@ static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value) extern const struct kvm_stats_header kvm_vm_stats_header; -extern const struct _kvm_stats_desc kvm_vm_stats_desc[]; +extern const struct kvm_stats_desc kvm_vm_stats_desc[]; extern const struct kvm_stats_header kvm_vcpu_stats_header; -extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[]; +extern const struct kvm_stats_desc kvm_vcpu_stats_desc[]; static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq) { diff --git a/include/linux/nvme-auth.h b/include/linux/nvme-auth.h index 60e069a6757f..e75c29c51464 100644 --- a/include/linux/nvme-auth.h +++ b/include/linux/nvme-auth.h @@ -11,7 +11,7 @@ struct nvme_dhchap_key { size_t len; u8 hash; - u8 key[]; + u8 key[] __counted_by(len); }; u32 nvme_auth_get_seqnum(void); diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h index da5fa6f40294..0b42045988db 100644 --- a/include/linux/rseq_types.h +++ b/include/linux/rseq_types.h @@ -133,10 +133,12 @@ struct rseq_data { }; * @active: MM CID is active for the task * @cid: The CID associated to the task either permanently or * borrowed from the CPU + * @node: Queued in the per MM MMCID list */ struct sched_mm_cid { unsigned int active; unsigned int cid; + struct hlist_node node; }; /** @@ -157,6 +159,7 @@ struct mm_cid_pcpu { * @work: Regular work to handle the affinity mode change case * @lock: Spinlock to protect against affinity setting which can't take @mutex * @mutex: Mutex to serialize forks and exits related to this mm + * @user_list: List of the MM CID users of a MM * @nr_cpus_allowed: The number of CPUs in the per MM allowed CPUs map. The map * is growth only. * @users: The number of tasks sharing this MM. Separate from mm::mm_users @@ -177,13 +180,14 @@ struct mm_mm_cid { raw_spinlock_t lock; struct mutex mutex; + struct hlist_head user_list; /* Low frequency modified */ unsigned int nr_cpus_allowed; unsigned int users; unsigned int pcpu_thrs; unsigned int update_deferred; -}____cacheline_aligned_in_smp; +} ____cacheline_aligned; #else /* CONFIG_SCHED_MM_CID */ struct mm_mm_cid { }; struct sched_mm_cid { }; diff --git a/include/linux/sched.h b/include/linux/sched.h index a7b4a980eb2f..5a5d3dbc9cdf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2354,7 +2354,6 @@ static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct allo #ifdef CONFIG_SCHED_MM_CID void sched_mm_cid_before_execve(struct task_struct *t); void sched_mm_cid_after_execve(struct task_struct *t); -void sched_mm_cid_fork(struct task_struct *t); void sched_mm_cid_exit(struct task_struct *t); static __always_inline int task_mm_cid(struct task_struct *t) { @@ -2363,7 +2362,6 @@ static __always_inline int task_mm_cid(struct task_struct *t) #else static inline void sched_mm_cid_before_execve(struct task_struct *t) { } static inline void sched_mm_cid_after_execve(struct task_struct *t) { } -static inline void sched_mm_cid_fork(struct task_struct *t) { } static inline void sched_mm_cid_exit(struct task_struct *t) { } static __always_inline int task_mm_cid(struct task_struct *t) { diff --git a/include/linux/usb.h b/include/linux/usb.h index fbfcc70b07fb..04277af4bb9d 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1862,14 +1862,18 @@ void usb_free_noncoherent(struct usb_device *dev, size_t size, * SYNCHRONOUS CALL SUPPORT * *-------------------------------------------------------------------*/ +/* Maximum value allowed for timeout in synchronous routines below */ +#define USB_MAX_SYNCHRONOUS_TIMEOUT 60000 /* ms */ + extern int usb_control_msg(struct usb_device *dev, unsigned int pipe, __u8 request, __u8 requesttype, __u16 value, __u16 index, void *data, __u16 size, int timeout); extern int usb_interrupt_msg(struct usb_device *usb_dev, unsigned int pipe, void *data, int len, int *actual_length, int timeout); extern int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe, - void *data, int len, int *actual_length, - int timeout); + void *data, int len, int *actual_length, int timeout); +extern int usb_bulk_msg_killable(struct usb_device *usb_dev, unsigned int pipe, + void *data, int len, int *actual_length, int timeout); /* wrappers around usb_control_msg() for the most common standard requests */ int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request, diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 2f7bd2fdc616..b3cc7beab4a3 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -78,4 +78,7 @@ /* skip BOS descriptor request */ #define USB_QUIRK_NO_BOS BIT(17) +/* Device claims zero configurations, forcing to 1 */ +#define USB_QUIRK_FORCE_ONE_CONFIG BIT(18) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 65500f5db379..80364d4dbebb 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -14,6 +14,10 @@ #include <linux/ioctl.h> #include <asm/kvm.h> +#ifdef __KERNEL__ +#include <linux/kvm_types.h> +#endif + #define KVM_API_VERSION 12 /* @@ -1601,7 +1605,11 @@ struct kvm_stats_desc { __u16 size; __u32 offset; __u32 bucket_size; +#ifdef __KERNEL__ + char name[KVM_STATS_NAME_SIZE]; +#else char name[]; +#endif }; #define KVM_GET_STATS_FD _IO(KVMIO, 0xce) diff --git a/io_uring/bpf_filter.c b/io_uring/bpf_filter.c index 6a98750e38b0..c0037632b7af 100644 --- a/io_uring/bpf_filter.c +++ b/io_uring/bpf_filter.c @@ -85,7 +85,7 @@ int __io_uring_run_bpf_filters(struct io_bpf_filter __rcu **filters, do { if (filter == &dummy_filter) return -EACCES; - ret = bpf_prog_run(filter->prog, &bpf_ctx); + ret = bpf_prog_run_pin_on_cpu(filter->prog, &bpf_ctx); if (!ret) return -EACCES; filter = filter->next; diff --git a/io_uring/eventfd.c b/io_uring/eventfd.c index cbea1c289485..7482a7dc6b38 100644 --- a/io_uring/eventfd.c +++ b/io_uring/eventfd.c @@ -76,11 +76,15 @@ void io_eventfd_signal(struct io_ring_ctx *ctx, bool cqe_event) { bool skip = false; struct io_ev_fd *ev_fd; - - if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED) - return; + struct io_rings *rings; guard(rcu)(); + + rings = rcu_dereference(ctx->rings_rcu); + if (!rings) + return; + if (READ_ONCE(rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED) + return; ev_fd = rcu_dereference(ctx->io_ev_fd); /* * Check again if ev_fd exists in case an io_eventfd_unregister call diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index aa95703165f1..9a37035e76c0 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1745,7 +1745,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, * well as 2 contiguous entries. */ if (!(ctx->flags & IORING_SETUP_SQE_MIXED) || *left < 2 || - !(ctx->cached_sq_head & (ctx->sq_entries - 1))) + (unsigned)(sqe - ctx->sq_sqes) >= ctx->sq_entries - 1) return io_init_fail_req(req, -EINVAL); /* * A 128b operation on a mixed SQ uses two entries, so we have @@ -2066,6 +2066,7 @@ static void io_rings_free(struct io_ring_ctx *ctx) io_free_region(ctx->user, &ctx->sq_region); io_free_region(ctx->user, &ctx->ring_region); ctx->rings = NULL; + RCU_INIT_POINTER(ctx->rings_rcu, NULL); ctx->sq_sqes = NULL; } @@ -2703,6 +2704,7 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, if (ret) return ret; ctx->rings = rings = io_region_get_ptr(&ctx->ring_region); + rcu_assign_pointer(ctx->rings_rcu, rings); if (!(ctx->flags & IORING_SETUP_NO_SQARRAY)) ctx->sq_array = (u32 *)((char *)rings + rl->sq_array_offset); diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index 2ffa95b1c601..26813b0f1dfd 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -111,9 +111,18 @@ bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags) buf = req->kbuf; bl = io_buffer_get_list(ctx, buf->bgid); - list_add(&buf->list, &bl->buf_list); - bl->nbufs++; + /* + * If the buffer list was upgraded to a ring-based one, or removed, + * while the request was in-flight in io-wq, drop it. + */ + if (bl && !(bl->flags & IOBL_BUF_RING)) { + list_add(&buf->list, &bl->buf_list); + bl->nbufs++; + } else { + kfree(buf); + } req->flags &= ~REQ_F_BUFFER_SELECTED; + req->kbuf = NULL; io_ring_submit_unlock(ctx, issue_flags); return true; diff --git a/io_uring/register.c b/io_uring/register.c index 6015a3e9ce69..0148735f7711 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -202,7 +202,7 @@ static int io_register_restrictions_task(void __user *arg, unsigned int nr_args) return -EPERM; /* * Similar to seccomp, disallow setting a filter if task_no_new_privs - * is true and we're not CAP_SYS_ADMIN. + * is false and we're not CAP_SYS_ADMIN. */ if (!task_no_new_privs(current) && !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)) @@ -238,7 +238,7 @@ static int io_register_bpf_filter_task(void __user *arg, unsigned int nr_args) /* * Similar to seccomp, disallow setting a filter if task_no_new_privs - * is true and we're not CAP_SYS_ADMIN. + * is false and we're not CAP_SYS_ADMIN. */ if (!task_no_new_privs(current) && !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)) @@ -633,7 +633,15 @@ overflow: ctx->sq_entries = p->sq_entries; ctx->cq_entries = p->cq_entries; + /* + * Just mark any flag we may have missed and that the application + * should act on unconditionally. Worst case it'll be an extra + * syscall. + */ + atomic_or(IORING_SQ_TASKRUN | IORING_SQ_NEED_WAKEUP, &n.rings->sq_flags); ctx->rings = n.rings; + rcu_assign_pointer(ctx->rings_rcu, n.rings); + ctx->sq_sqes = n.sq_sqes; swap_old(ctx, o, n, ring_region); swap_old(ctx, o, n, sq_region); @@ -642,6 +650,9 @@ overflow: out: spin_unlock(&ctx->completion_lock); mutex_unlock(&ctx->mmap_lock); + /* Wait for concurrent io_ctx_mark_taskrun() */ + if (to_free == &o) + synchronize_rcu_expedited(); io_register_free_rings(ctx, to_free); if (ctx->sq_data) diff --git a/io_uring/tw.c b/io_uring/tw.c index 1ee2b8ab07c8..2f2b4ac4b126 100644 --- a/io_uring/tw.c +++ b/io_uring/tw.c @@ -152,6 +152,21 @@ void tctx_task_work(struct callback_head *cb) WARN_ON_ONCE(ret); } +/* + * Sets IORING_SQ_TASKRUN in the sq_flags shared with userspace, using the + * RCU protected rings pointer to be safe against concurrent ring resizing. + */ +static void io_ctx_mark_taskrun(struct io_ring_ctx *ctx) +{ + lockdep_assert_in_rcu_read_lock(); + + if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) { + struct io_rings *rings = rcu_dereference(ctx->rings_rcu); + + atomic_or(IORING_SQ_TASKRUN, &rings->sq_flags); + } +} + void io_req_local_work_add(struct io_kiocb *req, unsigned flags) { struct io_ring_ctx *ctx = req->ctx; @@ -206,8 +221,7 @@ void io_req_local_work_add(struct io_kiocb *req, unsigned flags) */ if (!head) { - if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) - atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); + io_ctx_mark_taskrun(ctx); if (ctx->has_evfd) io_eventfd_signal(ctx, false); } @@ -231,6 +245,10 @@ void io_req_normal_work_add(struct io_kiocb *req) if (!llist_add(&req->io_task_work.node, &tctx->task_list)) return; + /* + * Doesn't need to use ->rings_rcu, as resizing isn't supported for + * !DEFER_TASKRUN. + */ if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index be1d71dda317..01fc2a93f3ef 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5109,6 +5109,12 @@ repeat: return; task = list_entry(it->task_pos, struct task_struct, cg_list); + /* + * Hide tasks that are exiting but not yet removed. Keep zombie + * leaders with live threads visible. + */ + if ((task->flags & PF_EXITING) && !atomic_read(&task->signal->live)) + goto repeat; if (it->flags & CSS_TASK_ITER_PROCS) { /* if PROCS, skip over tasks which aren't group leaders */ diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index e200de7c60b6..d21868455341 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -879,7 +879,7 @@ generate_doms: /* * Cgroup v2 doesn't support domain attributes, just set all of them * to SD_ATTR_INIT. Also non-isolating partition root CPUs are a - * subset of HK_TYPE_DOMAIN housekeeping CPUs. + * subset of HK_TYPE_DOMAIN_BOOT housekeeping CPUs. */ for (i = 0; i < ndoms; i++) { /* @@ -888,7 +888,7 @@ generate_doms: */ if (!csa || csa[i] == &top_cpuset) cpumask_and(doms[i], top_cpuset.effective_cpus, - housekeeping_cpumask(HK_TYPE_DOMAIN)); + housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT)); else cpumask_copy(doms[i], csa[i]->effective_cpus); if (dattr) @@ -1329,17 +1329,22 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus) } /* - * update_hk_sched_domains - Update HK cpumasks & rebuild sched domains + * cpuset_update_sd_hk_unlock - Rebuild sched domains, update HK & unlock * - * Update housekeeping cpumasks and rebuild sched domains if necessary. - * This should be called at the end of cpuset or hotplug actions. + * Update housekeeping cpumasks and rebuild sched domains if necessary and + * then do a cpuset_full_unlock(). + * This should be called at the end of cpuset operation. */ -static void update_hk_sched_domains(void) +static void cpuset_update_sd_hk_unlock(void) + __releases(&cpuset_mutex) + __releases(&cpuset_top_mutex) { + /* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */ + if (force_sd_rebuild) + rebuild_sched_domains_locked(); + if (update_housekeeping) { - /* Updating HK cpumasks implies rebuild sched domains */ update_housekeeping = false; - force_sd_rebuild = true; cpumask_copy(isolated_hk_cpus, isolated_cpus); /* @@ -1350,22 +1355,19 @@ static void update_hk_sched_domains(void) mutex_unlock(&cpuset_mutex); cpus_read_unlock(); WARN_ON_ONCE(housekeeping_update(isolated_hk_cpus)); - cpus_read_lock(); - mutex_lock(&cpuset_mutex); + mutex_unlock(&cpuset_top_mutex); + } else { + cpuset_full_unlock(); } - /* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */ - if (force_sd_rebuild) - rebuild_sched_domains_locked(); } /* - * Work function to invoke update_hk_sched_domains() + * Work function to invoke cpuset_update_sd_hk_unlock() */ static void hk_sd_workfn(struct work_struct *work) { cpuset_full_lock(); - update_hk_sched_domains(); - cpuset_full_unlock(); + cpuset_update_sd_hk_unlock(); } /** @@ -3230,8 +3232,7 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of, free_cpuset(trialcs); out_unlock: - update_hk_sched_domains(); - cpuset_full_unlock(); + cpuset_update_sd_hk_unlock(); if (of_cft(of)->private == FILE_MEMLIST) schedule_flush_migrate_mm(); return retval ?: nbytes; @@ -3338,8 +3339,7 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf, cpuset_full_lock(); if (is_cpuset_online(cs)) retval = update_prstate(cs, val); - update_hk_sched_domains(); - cpuset_full_unlock(); + cpuset_update_sd_hk_unlock(); return retval ?: nbytes; } @@ -3513,8 +3513,7 @@ static void cpuset_css_killed(struct cgroup_subsys_state *css) /* Reset valid partition back to member */ if (is_partition_valid(cs)) update_prstate(cs, PRS_MEMBER); - update_hk_sched_domains(); - cpuset_full_unlock(); + cpuset_update_sd_hk_unlock(); } static void cpuset_css_free(struct cgroup_subsys_state *css) @@ -3923,11 +3922,13 @@ static void cpuset_handle_hotplug(void) rcu_read_unlock(); } - /* - * Queue a work to call housekeeping_update() & rebuild_sched_domains() - * There will be a slight delay before the HK_TYPE_DOMAIN housekeeping - * cpumask can correctly reflect what is in isolated_cpus. + * rebuild_sched_domains() will always be called directly if needed + * to make sure that newly added or removed CPU will be reflected in + * the sched domains. However, if isolated partition invalidation + * or recreation is being done (update_housekeeping set), a work item + * will be queued to call housekeeping_update() to update the + * corresponding housekeeping cpumasks after some slight delay. * * We rely on WORK_STRUCT_PENDING_BIT to not requeue a work item that * is still pending. Before the pending bit is cleared, the work data @@ -3936,8 +3937,10 @@ static void cpuset_handle_hotplug(void) * previously queued work. Since hk_sd_workfn() doesn't use the work * item at all, this is not a problem. */ - if (update_housekeeping || force_sd_rebuild) - queue_work(system_unbound_wq, &hk_sd_work); + if (force_sd_rebuild) + rebuild_sched_domains_cpuslocked(); + if (update_housekeeping) + queue_work(system_dfl_wq, &hk_sd_work); free_tmpmasks(ptmp); } diff --git a/kernel/crash_dump_dm_crypt.c b/kernel/crash_dump_dm_crypt.c index 1f4067fbdb94..a20d4097744a 100644 --- a/kernel/crash_dump_dm_crypt.c +++ b/kernel/crash_dump_dm_crypt.c @@ -168,8 +168,8 @@ static int read_key_from_user_keying(struct dm_crypt_key *dm_key) memcpy(dm_key->data, ukp->data, ukp->datalen); dm_key->key_size = ukp->datalen; - kexec_dprintk("Get dm crypt key (size=%u) %s: %8ph\n", dm_key->key_size, - dm_key->key_desc, dm_key->data); + kexec_dprintk("Get dm crypt key (size=%u) %s\n", dm_key->key_size, + dm_key->key_desc); out: up_read(&key->sem); diff --git a/kernel/fork.c b/kernel/fork.c index 65113a304518..bc2bf58b93b6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1000,6 +1000,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) #ifdef CONFIG_SCHED_MM_CID tsk->mm_cid.cid = MM_CID_UNSET; tsk->mm_cid.active = 0; + INIT_HLIST_NODE(&tsk->mm_cid.node); #endif return tsk; @@ -1586,7 +1587,6 @@ static int copy_mm(u64 clone_flags, struct task_struct *tsk) tsk->mm = mm; tsk->active_mm = mm; - sched_mm_cid_fork(tsk); return 0; } @@ -2498,7 +2498,6 @@ bad_fork_cleanup_namespaces: exit_nsproxy_namespaces(p); bad_fork_cleanup_mm: if (p->mm) { - sched_mm_cid_exit(p); mm_clear_owner(p->mm, p); mmput(p->mm); } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ab25b4aa9095..bfc89083daa9 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1144,12 +1144,12 @@ static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, lockdep_assert_held(&kprobe_mutex); ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 0, 0); - if (WARN_ONCE(ret < 0, "Failed to arm kprobe-ftrace at %pS (error %d)\n", p->addr, ret)) + if (ret < 0) return ret; if (*cnt == 0) { ret = register_ftrace_function(ops); - if (WARN(ret < 0, "Failed to register kprobe-ftrace (error %d)\n", ret)) { + if (ret < 0) { /* * At this point, sinec ops is not registered, we should be sefe from * registering empty filter. @@ -1178,6 +1178,10 @@ static int __disarm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int ret; lockdep_assert_held(&kprobe_mutex); + if (unlikely(kprobe_ftrace_disabled)) { + /* Now ftrace is disabled forever, disarm is already done. */ + return 0; + } if (*cnt == 1) { ret = unregister_ftrace_function(ops); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b7f77c165a6e..496dff740dca 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4729,8 +4729,11 @@ void sched_cancel_fork(struct task_struct *p) scx_cancel_fork(p); } +static void sched_mm_cid_fork(struct task_struct *t); + void sched_post_fork(struct task_struct *p) { + sched_mm_cid_fork(p); uclamp_post_fork(p); scx_post_fork(p); } @@ -10617,13 +10620,10 @@ static inline void mm_cid_transit_to_cpu(struct task_struct *t, struct mm_cid_pc } } -static bool mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm) +static void mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm) { /* Remote access to mm::mm_cid::pcpu requires rq_lock */ guard(task_rq_lock)(t); - /* If the task is not active it is not in the users count */ - if (!t->mm_cid.active) - return false; if (cid_on_task(t->mm_cid.cid)) { /* If running on the CPU, put the CID in transit mode, otherwise drop it */ if (task_rq(t)->curr == t) @@ -10631,69 +10631,43 @@ static bool mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm else mm_unset_cid_on_task(t); } - return true; } -static void mm_cid_do_fixup_tasks_to_cpus(struct mm_struct *mm) +static void mm_cid_fixup_tasks_to_cpus(void) { - struct task_struct *p, *t; - unsigned int users; + struct mm_struct *mm = current->mm; + struct task_struct *t; - /* - * This can obviously race with a concurrent affinity change, which - * increases the number of allowed CPUs for this mm, but that does - * not affect the mode and only changes the CID constraints. A - * possible switch back to per task mode happens either in the - * deferred handler function or in the next fork()/exit(). - * - * The caller has already transferred. The newly incoming task is - * already accounted for, but not yet visible. - */ - users = mm->mm_cid.users - 2; - if (!users) - return; + lockdep_assert_held(&mm->mm_cid.mutex); - guard(rcu)(); - for_other_threads(current, t) { - if (mm_cid_fixup_task_to_cpu(t, mm)) - users--; + hlist_for_each_entry(t, &mm->mm_cid.user_list, mm_cid.node) { + /* Current has already transferred before invoking the fixup. */ + if (t != current) + mm_cid_fixup_task_to_cpu(t, mm); } - if (!users) - return; - - /* Happens only for VM_CLONE processes. */ - for_each_process_thread(p, t) { - if (t == current || t->mm != mm) - continue; - if (mm_cid_fixup_task_to_cpu(t, mm)) { - if (--users == 0) - return; - } - } -} - -static void mm_cid_fixup_tasks_to_cpus(void) -{ - struct mm_struct *mm = current->mm; - - mm_cid_do_fixup_tasks_to_cpus(mm); mm_cid_complete_transit(mm, MM_CID_ONCPU); } static bool sched_mm_cid_add_user(struct task_struct *t, struct mm_struct *mm) { + lockdep_assert_held(&mm->mm_cid.lock); + t->mm_cid.active = 1; + hlist_add_head(&t->mm_cid.node, &mm->mm_cid.user_list); mm->mm_cid.users++; return mm_update_max_cids(mm); } -void sched_mm_cid_fork(struct task_struct *t) +static void sched_mm_cid_fork(struct task_struct *t) { struct mm_struct *mm = t->mm; bool percpu; - WARN_ON_ONCE(!mm || t->mm_cid.cid != MM_CID_UNSET); + if (!mm) + return; + + WARN_ON_ONCE(t->mm_cid.cid != MM_CID_UNSET); guard(mutex)(&mm->mm_cid.mutex); scoped_guard(raw_spinlock_irq, &mm->mm_cid.lock) { @@ -10732,12 +10706,13 @@ void sched_mm_cid_fork(struct task_struct *t) static bool sched_mm_cid_remove_user(struct task_struct *t) { + lockdep_assert_held(&t->mm->mm_cid.lock); + t->mm_cid.active = 0; - scoped_guard(preempt) { - /* Clear the transition bit */ - t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid); - mm_unset_cid_on_task(t); - } + /* Clear the transition bit */ + t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid); + mm_unset_cid_on_task(t); + hlist_del_init(&t->mm_cid.node); t->mm->mm_cid.users--; return mm_update_max_cids(t->mm); } @@ -10880,11 +10855,13 @@ void mm_init_cid(struct mm_struct *mm, struct task_struct *p) mutex_init(&mm->mm_cid.mutex); mm->mm_cid.irq_work = IRQ_WORK_INIT_HARD(mm_cid_irq_work); INIT_WORK(&mm->mm_cid.work, mm_cid_work_fn); + INIT_HLIST_HEAD(&mm->mm_cid.user_list); cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask); bitmap_zero(mm_cidmask(mm), num_possible_cpus()); } #else /* CONFIG_SCHED_MM_CID */ static inline void mm_update_cpus_allowed(struct mm_struct *mm, const struct cpumask *affmsk) { } +static inline void sched_mm_cid_fork(struct task_struct *t) { } #endif /* !CONFIG_SCHED_MM_CID */ static DEFINE_PER_CPU(struct sched_change_ctx, sched_change_ctx); diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 1594987d637b..26a6ac2f8826 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1103,7 +1103,7 @@ static void dispatch_enqueue(struct scx_sched *sch, struct scx_dispatch_q *dsq, } /* seq records the order tasks are queued, used by BPF DSQ iterator */ - dsq->seq++; + WRITE_ONCE(dsq->seq, dsq->seq + 1); p->scx.dsq_seq = dsq->seq; dsq_mod_nr(dsq, 1); @@ -1470,16 +1470,15 @@ static void clr_task_runnable(struct task_struct *p, bool reset_runnable_at) p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT; } -static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags) +static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int core_enq_flags) { struct scx_sched *sch = scx_root; int sticky_cpu = p->scx.sticky_cpu; + u64 enq_flags = core_enq_flags | rq->scx.extra_enq_flags; if (enq_flags & ENQUEUE_WAKEUP) rq->scx.flags |= SCX_RQ_IN_WAKEUP; - enq_flags |= rq->scx.extra_enq_flags; - if (sticky_cpu >= 0) p->scx.sticky_cpu = -1; @@ -3908,8 +3907,8 @@ static u32 bypass_lb_cpu(struct scx_sched *sch, struct rq *rq, * consider offloading iff the total queued duration is over the * threshold. */ - min_delta_us = scx_bypass_lb_intv_us / SCX_BYPASS_LB_MIN_DELTA_DIV; - if (delta < DIV_ROUND_UP(min_delta_us, scx_slice_bypass_us)) + min_delta_us = READ_ONCE(scx_bypass_lb_intv_us) / SCX_BYPASS_LB_MIN_DELTA_DIV; + if (delta < DIV_ROUND_UP(min_delta_us, READ_ONCE(scx_slice_bypass_us))) return 0; raw_spin_rq_lock_irq(rq); @@ -4137,7 +4136,7 @@ static void scx_bypass(bool bypass) WARN_ON_ONCE(scx_bypass_depth <= 0); if (scx_bypass_depth != 1) goto unlock; - WRITE_ONCE(scx_slice_dfl, scx_slice_bypass_us * NSEC_PER_USEC); + WRITE_ONCE(scx_slice_dfl, READ_ONCE(scx_slice_bypass_us) * NSEC_PER_USEC); bypass_timestamp = ktime_get_ns(); if (sch) scx_add_event(sch, SCX_EV_BYPASS_ACTIVATE, 1); @@ -5259,13 +5258,14 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) if (!READ_ONCE(helper)) { mutex_lock(&helper_mutex); if (!helper) { - helper = kthread_run_worker(0, "scx_enable_helper"); - if (IS_ERR_OR_NULL(helper)) { - helper = NULL; + struct kthread_worker *w = + kthread_run_worker(0, "scx_enable_helper"); + if (IS_ERR_OR_NULL(w)) { mutex_unlock(&helper_mutex); return -ENOMEM; } - sched_set_fifo(helper->task); + sched_set_fifo(w->task); + WRITE_ONCE(helper, w); } mutex_unlock(&helper_mutex); } diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h index 11ebb744d893..00b450597f3e 100644 --- a/kernel/sched/ext_internal.h +++ b/kernel/sched/ext_internal.h @@ -1035,26 +1035,108 @@ static const char *scx_enable_state_str[] = { }; /* - * sched_ext_entity->ops_state + * Task Ownership State Machine (sched_ext_entity->ops_state) * - * Used to track the task ownership between the SCX core and the BPF scheduler. - * State transitions look as follows: + * The sched_ext core uses this state machine to track task ownership + * between the SCX core and the BPF scheduler. This allows the BPF + * scheduler to dispatch tasks without strict ordering requirements, while + * the SCX core safely rejects invalid dispatches. * - * NONE -> QUEUEING -> QUEUED -> DISPATCHING - * ^ | | - * | v v - * \-------------------------------/ + * State Transitions * - * QUEUEING and DISPATCHING states can be waited upon. See wait_ops_state() call - * sites for explanations on the conditions being waited upon and why they are - * safe. Transitions out of them into NONE or QUEUED must store_release and the - * waiters should load_acquire. + * .------------> NONE (owned by SCX core) + * | | ^ + * | enqueue | | direct dispatch + * | v | + * | QUEUEING -------' + * | | + * | enqueue | + * | completes | + * | v + * | QUEUED (owned by BPF scheduler) + * | | + * | dispatch | + * | | + * | v + * | DISPATCHING + * | | + * | dispatch | + * | completes | + * `---------------' * - * Tracking scx_ops_state enables sched_ext core to reliably determine whether - * any given task can be dispatched by the BPF scheduler at all times and thus - * relaxes the requirements on the BPF scheduler. This allows the BPF scheduler - * to try to dispatch any task anytime regardless of its state as the SCX core - * can safely reject invalid dispatches. + * State Descriptions + * + * - %SCX_OPSS_NONE: + * Task is owned by the SCX core. It's either on a run queue, running, + * or being manipulated by the core scheduler. The BPF scheduler has no + * claim on this task. + * + * - %SCX_OPSS_QUEUEING: + * Transitional state while transferring a task from the SCX core to + * the BPF scheduler. The task's rq lock is held during this state. + * Since QUEUEING is both entered and exited under the rq lock, dequeue + * can never observe this state (it would be a BUG). When finishing a + * dispatch, if the task is still in %SCX_OPSS_QUEUEING the completion + * path busy-waits for it to leave this state (via wait_ops_state()) + * before retrying. + * + * - %SCX_OPSS_QUEUED: + * Task is owned by the BPF scheduler. It's on a DSQ (dispatch queue) + * and the BPF scheduler is responsible for dispatching it. A QSEQ + * (queue sequence number) is embedded in this state to detect + * dispatch/dequeue races: if a task is dequeued and re-enqueued, the + * QSEQ changes and any in-flight dispatch operations targeting the old + * QSEQ are safely ignored. + * + * - %SCX_OPSS_DISPATCHING: + * Transitional state while transferring a task from the BPF scheduler + * back to the SCX core. This state indicates the BPF scheduler has + * selected the task for execution. When dequeue needs to take the task + * off a DSQ and it is still in %SCX_OPSS_DISPATCHING, the dequeue path + * busy-waits for it to leave this state (via wait_ops_state()) before + * proceeding. Exits to %SCX_OPSS_NONE when dispatch completes. + * + * Memory Ordering + * + * Transitions out of %SCX_OPSS_QUEUEING and %SCX_OPSS_DISPATCHING into + * %SCX_OPSS_NONE or %SCX_OPSS_QUEUED must use atomic_long_set_release() + * and waiters must use atomic_long_read_acquire(). This ensures proper + * synchronization between concurrent operations. + * + * Cross-CPU Task Migration + * + * When moving a task in the %SCX_OPSS_DISPATCHING state, we can't simply + * grab the target CPU's rq lock because a concurrent dequeue might be + * waiting on %SCX_OPSS_DISPATCHING while holding the source rq lock + * (deadlock). + * + * The sched_ext core uses a "lock dancing" protocol coordinated by + * p->scx.holding_cpu. When moving a task to a different rq: + * + * 1. Verify task can be moved (CPU affinity, migration_disabled, etc.) + * 2. Set p->scx.holding_cpu to the current CPU + * 3. Set task state to %SCX_OPSS_NONE; dequeue waits while DISPATCHING + * is set, so clearing DISPATCHING first prevents the circular wait + * (safe to lock the rq we need) + * 4. Unlock the current CPU's rq + * 5. Lock src_rq (where the task currently lives) + * 6. Verify p->scx.holding_cpu == current CPU, if not, dequeue won the + * race (dequeue clears holding_cpu to -1 when it takes the task), in + * this case migration is aborted + * 7. If src_rq == dst_rq: clear holding_cpu and enqueue directly + * into dst_rq's local DSQ (no lock swap needed) + * 8. Otherwise: call move_remote_task_to_local_dsq(), which releases + * src_rq, locks dst_rq, and performs the deactivate/activate + * migration cycle (dst_rq is held on return) + * 9. Unlock dst_rq and re-lock the current CPU's rq to restore + * the lock state expected by the caller + * + * If any verification fails, abort the migration. + * + * This state tracking allows the BPF scheduler to try to dispatch any task + * at any time regardless of its state. The SCX core can safely + * reject/ignore invalid dispatches, simplifying the BPF scheduler + * implementation. */ enum scx_ops_state { SCX_OPSS_NONE, /* owned by the SCX core */ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 3681b6ad9276..a83be0c834dd 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -161,6 +161,14 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev, return cpuidle_enter(drv, dev, next_state); } +static void idle_call_stop_or_retain_tick(bool stop_tick) +{ + if (stop_tick || tick_nohz_tick_stopped()) + tick_nohz_idle_stop_tick(); + else + tick_nohz_idle_retain_tick(); +} + /** * cpuidle_idle_call - the main idle function * @@ -170,7 +178,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev, * set, and it returns with polling set. If it ever stops polling, it * must clear the polling bit. */ -static void cpuidle_idle_call(void) +static void cpuidle_idle_call(bool stop_tick) { struct cpuidle_device *dev = cpuidle_get_device(); struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); @@ -186,7 +194,7 @@ static void cpuidle_idle_call(void) } if (cpuidle_not_available(drv, dev)) { - tick_nohz_idle_stop_tick(); + idle_call_stop_or_retain_tick(stop_tick); default_idle_call(); goto exit_idle; @@ -221,24 +229,35 @@ static void cpuidle_idle_call(void) next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns); call_cpuidle(drv, dev, next_state); - } else { - bool stop_tick = true; + } else if (drv->state_count > 1) { + /* + * stop_tick is expected to be true by default by cpuidle + * governors, which allows them to select idle states with + * target residency above the tick period length. + */ + stop_tick = true; /* * Ask the cpuidle framework to choose a convenient idle state. */ next_state = cpuidle_select(drv, dev, &stop_tick); - if (stop_tick || tick_nohz_tick_stopped()) - tick_nohz_idle_stop_tick(); - else - tick_nohz_idle_retain_tick(); + idle_call_stop_or_retain_tick(stop_tick); entered_state = call_cpuidle(drv, dev, next_state); /* * Give the governor an opportunity to reflect on the outcome */ cpuidle_reflect(dev, entered_state); + } else { + idle_call_stop_or_retain_tick(stop_tick); + + /* + * If there is only a single idle state (or none), there is + * nothing meaningful for the governor to choose. Skip the + * governor and always use state 0. + */ + call_cpuidle(drv, dev, 0); } exit_idle: @@ -259,6 +278,7 @@ exit_idle: static void do_idle(void) { int cpu = smp_processor_id(); + bool got_tick = false; /* * Check if we need to update blocked load @@ -329,8 +349,9 @@ static void do_idle(void) tick_nohz_idle_restart_tick(); cpu_idle_poll(); } else { - cpuidle_idle_call(); + cpuidle_idle_call(got_tick); } + got_tick = tick_nohz_idle_got_tick(); arch_cpu_idle_exit(); } diff --git a/kernel/time/time.c b/kernel/time/time.c index 36fd2313ae7e..0d832317d576 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -697,7 +697,7 @@ EXPORT_SYMBOL(clock_t_to_jiffies); * * Return: jiffies_64 value converted to 64-bit "clock_t" (CLOCKS_PER_SEC) */ -u64 jiffies_64_to_clock_t(u64 x) +notrace u64 jiffies_64_to_clock_t(u64 x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index aeaec79bc09c..b77119d71641 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -190,7 +190,7 @@ struct worker_pool { int id; /* I: pool ID */ unsigned int flags; /* L: flags */ - unsigned long watchdog_ts; /* L: watchdog timestamp */ + unsigned long last_progress_ts; /* L: last forward progress timestamp */ bool cpu_stall; /* WD: stalled cpu bound pool */ /* @@ -1697,7 +1697,7 @@ static void __pwq_activate_work(struct pool_workqueue *pwq, WARN_ON_ONCE(!(*wdb & WORK_STRUCT_INACTIVE)); trace_workqueue_activate_work(work); if (list_empty(&pwq->pool->worklist)) - pwq->pool->watchdog_ts = jiffies; + pwq->pool->last_progress_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); __clear_bit(WORK_STRUCT_INACTIVE_BIT, wdb); } @@ -2348,7 +2348,7 @@ retry: */ if (list_empty(&pwq->inactive_works) && pwq_tryinc_nr_active(pwq, false)) { if (list_empty(&pool->worklist)) - pool->watchdog_ts = jiffies; + pool->last_progress_ts = jiffies; trace_workqueue_activate_work(work); insert_work(pwq, work, &pool->worklist, work_flags); @@ -3204,6 +3204,7 @@ __acquires(&pool->lock) worker->current_pwq = pwq; if (worker->task) worker->current_at = worker->task->se.sum_exec_runtime; + worker->current_start = jiffies; work_data = *work_data_bits(work); worker->current_color = get_work_color(work_data); @@ -3352,7 +3353,7 @@ static void process_scheduled_works(struct worker *worker) while ((work = list_first_entry_or_null(&worker->scheduled, struct work_struct, entry))) { if (first) { - worker->pool->watchdog_ts = jiffies; + worker->pool->last_progress_ts = jiffies; first = false; } process_one_work(worker, work); @@ -4850,7 +4851,7 @@ static int init_worker_pool(struct worker_pool *pool) pool->cpu = -1; pool->node = NUMA_NO_NODE; pool->flags |= POOL_DISASSOCIATED; - pool->watchdog_ts = jiffies; + pool->last_progress_ts = jiffies; INIT_LIST_HEAD(&pool->worklist); INIT_LIST_HEAD(&pool->idle_list); hash_init(pool->busy_hash); @@ -6274,7 +6275,7 @@ static void pr_cont_worker_id(struct worker *worker) { struct worker_pool *pool = worker->pool; - if (pool->flags & WQ_BH) + if (pool->flags & POOL_BH) pr_cont("bh%s", pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); else @@ -6359,6 +6360,8 @@ static void show_pwq(struct pool_workqueue *pwq) pr_cont(" %s", comma ? "," : ""); pr_cont_worker_id(worker); pr_cont(":%ps", worker->current_func); + pr_cont(" for %us", + jiffies_to_msecs(jiffies - worker->current_start) / 1000); list_for_each_entry(work, &worker->scheduled, entry) pr_cont_work(false, work, &pcws); pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); @@ -6462,7 +6465,7 @@ static void show_one_worker_pool(struct worker_pool *pool) /* How long the first pending work is waiting for a worker. */ if (!list_empty(&pool->worklist)) - hung = jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000; + hung = jiffies_to_msecs(jiffies - pool->last_progress_ts) / 1000; /* * Defer printing to avoid deadlocks in console drivers that @@ -7580,11 +7583,11 @@ MODULE_PARM_DESC(panic_on_stall_time, "Panic if stall exceeds this many seconds /* * Show workers that might prevent the processing of pending work items. - * The only candidates are CPU-bound workers in the running state. - * Pending work items should be handled by another idle worker - * in all other situations. + * A busy worker that is not running on the CPU (e.g. sleeping in + * wait_event_idle() with PF_WQ_WORKER cleared) can stall the pool just as + * effectively as a CPU-bound one, so dump every in-flight worker. */ -static void show_cpu_pool_hog(struct worker_pool *pool) +static void show_cpu_pool_busy_workers(struct worker_pool *pool) { struct worker *worker; unsigned long irq_flags; @@ -7593,36 +7596,34 @@ static void show_cpu_pool_hog(struct worker_pool *pool) raw_spin_lock_irqsave(&pool->lock, irq_flags); hash_for_each(pool->busy_hash, bkt, worker, hentry) { - if (task_is_running(worker->task)) { - /* - * Defer printing to avoid deadlocks in console - * drivers that queue work while holding locks - * also taken in their write paths. - */ - printk_deferred_enter(); + /* + * Defer printing to avoid deadlocks in console + * drivers that queue work while holding locks + * also taken in their write paths. + */ + printk_deferred_enter(); - pr_info("pool %d:\n", pool->id); - sched_show_task(worker->task); + pr_info("pool %d:\n", pool->id); + sched_show_task(worker->task); - printk_deferred_exit(); - } + printk_deferred_exit(); } raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } -static void show_cpu_pools_hogs(void) +static void show_cpu_pools_busy_workers(void) { struct worker_pool *pool; int pi; - pr_info("Showing backtraces of running workers in stalled CPU-bound worker pools:\n"); + pr_info("Showing backtraces of busy workers in stalled worker pools:\n"); rcu_read_lock(); for_each_pool(pool, pi) { if (pool->cpu_stall) - show_cpu_pool_hog(pool); + show_cpu_pool_busy_workers(pool); } @@ -7691,7 +7692,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); else touched = READ_ONCE(wq_watchdog_touched); - pool_ts = READ_ONCE(pool->watchdog_ts); + pool_ts = READ_ONCE(pool->last_progress_ts); if (time_after(pool_ts, touched)) ts = pool_ts; @@ -7719,7 +7720,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) show_all_workqueues(); if (cpu_pool_stall) - show_cpu_pools_hogs(); + show_cpu_pools_busy_workers(); if (lockup_detected) panic_on_wq_watchdog(max_stall_time); diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index f6275944ada7..8def1ddc5a1b 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -32,6 +32,7 @@ struct worker { work_func_t current_func; /* K: function */ struct pool_workqueue *current_pwq; /* K: pwq */ u64 current_at; /* K: runtime at start or last wakeup */ + unsigned long current_start; /* K: start time of current work item */ unsigned int current_color; /* K: color */ int sleeping; /* S: is worker sleeping? */ diff --git a/lib/bootconfig.c b/lib/bootconfig.c index 449369a60846..2da049216fe0 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -316,7 +316,7 @@ int __init xbc_node_compose_key_after(struct xbc_node *root, depth ? "." : ""); if (ret < 0) return ret; - if (ret > size) { + if (ret >= size) { size = 0; } else { size -= ret; @@ -532,9 +532,9 @@ static char *skip_spaces_until_newline(char *p) static int __init __xbc_open_brace(char *p) { /* Push the last key as open brace */ - open_brace[brace_index++] = xbc_node_index(last_parent); if (brace_index >= XBC_DEPTH_MAX) return xbc_parse_error("Exceed max depth of braces", p); + open_brace[brace_index++] = xbc_node_index(last_parent); return 0; } @@ -802,7 +802,7 @@ static int __init xbc_verify_tree(void) /* Brace closing */ if (brace_index) { - n = &xbc_nodes[open_brace[brace_index]]; + n = &xbc_nodes[open_brace[brace_index - 1]]; return xbc_parse_error("Brace is not closed", xbc_node_get_data(n)); } diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile index 725eef05b758..dc7a56f7287d 100644 --- a/lib/crypto/Makefile +++ b/lib/crypto/Makefile @@ -55,6 +55,9 @@ libaes-$(CONFIG_SPARC) += sparc/aes_asm.o libaes-$(CONFIG_X86) += x86/aes-aesni.o endif # CONFIG_CRYPTO_LIB_AES_ARCH +# clean-files must be defined unconditionally +clean-files += powerpc/aesp8-ppc.S + ################################################################################ obj-$(CONFIG_CRYPTO_LIB_AESCFB) += libaescfb.o diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 912c248a3f7e..b298cba853ab 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2797,7 +2797,8 @@ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pm _dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd), dst_vma); } else { src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd); - _dst_pmd = folio_mk_pmd(src_folio, dst_vma->vm_page_prot); + _dst_pmd = move_soft_dirty_pmd(src_pmdval); + _dst_pmd = clear_uffd_wp_pmd(_dst_pmd); } set_pmd_at(mm, dst_addr, dst_pmd, _dst_pmd); diff --git a/mm/rmap.c b/mm/rmap.c index 0f00570d1b9e..391337282e3f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1955,7 +1955,14 @@ static inline unsigned int folio_unmap_pte_batch(struct folio *folio, if (userfaultfd_wp(vma)) return 1; - return folio_pte_batch(folio, pvmw->pte, pte, max_nr); + /* + * If unmap fails, we need to restore the ptes. To avoid accidentally + * upgrading write permissions for ptes that were not originally + * writable, and to avoid losing the soft-dirty bit, use the + * appropriate FPB flags. + */ + return folio_pte_batch_flags(folio, vma, pvmw->pte, &pte, max_nr, + FPB_RESPECT_WRITE | FPB_RESPECT_SOFT_DIRTY); } /* @@ -2443,11 +2450,17 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, __maybe_unused pmd_t pmdval; if (flags & TTU_SPLIT_HUGE_PMD) { + /* + * split_huge_pmd_locked() might leave the + * folio mapped through PTEs. Retry the walk + * so we can detect this scenario and properly + * abort the walk. + */ split_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, true); - ret = false; - page_vma_mapped_walk_done(&pvmw); - break; + flags &= ~TTU_SPLIT_HUGE_PMD; + page_vma_mapped_walk_restart(&pvmw); + continue; } #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION pmdval = pmdp_get(pvmw.pmd); diff --git a/mm/slub.c b/mm/slub.c index 20cb4f3b636d..2b2d33cc735c 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2119,13 +2119,6 @@ static inline size_t obj_exts_alloc_size(struct kmem_cache *s, size_t sz = sizeof(struct slabobj_ext) * slab->objects; struct kmem_cache *obj_exts_cache; - /* - * slabobj_ext array for KMALLOC_CGROUP allocations - * are served from KMALLOC_NORMAL caches. - */ - if (!mem_alloc_profiling_enabled()) - return sz; - if (sz > KMALLOC_MAX_CACHE_SIZE) return sz; @@ -2797,6 +2790,7 @@ static void free_empty_sheaf(struct kmem_cache *s, struct slab_sheaf *sheaf) if (s->flags & SLAB_KMALLOC) mark_obj_codetag_empty(sheaf); + VM_WARN_ON_ONCE(sheaf->size > 0); kfree(sheaf); stat(s, SHEAF_FREE); @@ -2828,6 +2822,7 @@ static int refill_sheaf(struct kmem_cache *s, struct slab_sheaf *sheaf, return 0; } +static void sheaf_flush_unused(struct kmem_cache *s, struct slab_sheaf *sheaf); static struct slab_sheaf *alloc_full_sheaf(struct kmem_cache *s, gfp_t gfp) { @@ -2837,6 +2832,7 @@ static struct slab_sheaf *alloc_full_sheaf(struct kmem_cache *s, gfp_t gfp) return NULL; if (refill_sheaf(s, sheaf, gfp | __GFP_NOMEMALLOC | __GFP_NOWARN)) { + sheaf_flush_unused(s, sheaf); free_empty_sheaf(s, sheaf); return NULL; } @@ -4623,6 +4619,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs, * we must be very low on memory so don't bother * with the barn */ + sheaf_flush_unused(s, empty); free_empty_sheaf(s, empty); } } else { diff --git a/net/ceph/auth.c b/net/ceph/auth.c index 343c841784ce..901b93530b21 100644 --- a/net/ceph/auth.c +++ b/net/ceph/auth.c @@ -205,9 +205,9 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac, s32 result; u64 global_id; void *payload, *payload_end; - int payload_len; + u32 payload_len; char *result_msg; - int result_msg_len; + u32 result_msg_len; int ret = -EINVAL; mutex_lock(&ac->mutex); @@ -217,10 +217,12 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac, result = ceph_decode_32(&p); global_id = ceph_decode_64(&p); payload_len = ceph_decode_32(&p); + ceph_decode_need(&p, end, payload_len, bad); payload = p; p += payload_len; ceph_decode_need(&p, end, sizeof(u32), bad); result_msg_len = ceph_decode_32(&p); + ceph_decode_need(&p, end, result_msg_len, bad); result_msg = p; p += result_msg_len; if (p != end) diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index 5ec3272cd2dd..50f65820f623 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -392,7 +392,7 @@ static int head_onwire_len(int ctrl_len, bool secure) int head_len; int rem_len; - BUG_ON(ctrl_len < 0 || ctrl_len > CEPH_MSG_MAX_CONTROL_LEN); + BUG_ON(ctrl_len < 1 || ctrl_len > CEPH_MSG_MAX_CONTROL_LEN); if (secure) { head_len = CEPH_PREAMBLE_SECURE_LEN; @@ -401,9 +401,7 @@ static int head_onwire_len(int ctrl_len, bool secure) head_len += padded_len(rem_len) + CEPH_GCM_TAG_LEN; } } else { - head_len = CEPH_PREAMBLE_PLAIN_LEN; - if (ctrl_len) - head_len += ctrl_len + CEPH_CRC_LEN; + head_len = CEPH_PREAMBLE_PLAIN_LEN + ctrl_len + CEPH_CRC_LEN; } return head_len; } @@ -528,11 +526,16 @@ static int decode_preamble(void *p, struct ceph_frame_desc *desc) desc->fd_aligns[i] = ceph_decode_16(&p); } - if (desc->fd_lens[0] < 0 || + /* + * This would fire for FRAME_TAG_WAIT (it has one empty + * segment), but we should never get it as client. + */ + if (desc->fd_lens[0] < 1 || desc->fd_lens[0] > CEPH_MSG_MAX_CONTROL_LEN) { pr_err("bad control segment length %d\n", desc->fd_lens[0]); return -EINVAL; } + if (desc->fd_lens[1] < 0 || desc->fd_lens[1] > CEPH_MSG_MAX_FRONT_LEN) { pr_err("bad front segment length %d\n", desc->fd_lens[1]); @@ -549,10 +552,6 @@ static int decode_preamble(void *p, struct ceph_frame_desc *desc) return -EINVAL; } - /* - * This would fire for FRAME_TAG_WAIT (it has one empty - * segment), but we should never get it as client. - */ if (!desc->fd_lens[desc->fd_seg_cnt - 1]) { pr_err("last segment empty, segment count %d\n", desc->fd_seg_cnt); @@ -2833,12 +2832,15 @@ static int process_message_header(struct ceph_connection *con, void *p, void *end) { struct ceph_frame_desc *desc = &con->v2.in_desc; - struct ceph_msg_header2 *hdr2 = p; + struct ceph_msg_header2 *hdr2; struct ceph_msg_header hdr; int skip; int ret; u64 seq; + ceph_decode_need(&p, end, sizeof(*hdr2), bad); + hdr2 = p; + /* verify seq# */ seq = le64_to_cpu(hdr2->seq); if ((s64)seq - (s64)con->in_seq < 1) { @@ -2869,6 +2871,10 @@ static int process_message_header(struct ceph_connection *con, WARN_ON(!con->in_msg); WARN_ON(con->in_msg->con != con); return 1; + +bad: + pr_err("failed to decode message header\n"); + return -EINVAL; } static int process_message(struct ceph_connection *con) @@ -2898,6 +2904,11 @@ static int __handle_control(struct ceph_connection *con, void *p) if (con->v2.in_desc.fd_tag != FRAME_TAG_MESSAGE) return process_control(con, p, end); + if (con->state != CEPH_CON_S_OPEN) { + con->error_msg = "protocol error, unexpected message"; + return -EINVAL; + } + ret = process_message_header(con, p, end); if (ret < 0) return ret; diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 5136b3766c44..d5080530ce0c 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -72,8 +72,8 @@ static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2) struct ceph_monmap *monmap = NULL; struct ceph_fsid fsid; u32 struct_len; - int blob_len; - int num_mon; + u32 blob_len; + u32 num_mon; u8 struct_v; u32 epoch; int ret; @@ -112,7 +112,7 @@ static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2) } ceph_decode_32_safe(p, end, num_mon, e_inval); - dout("%s fsid %pU epoch %u num_mon %d\n", __func__, &fsid, epoch, + dout("%s fsid %pU epoch %u num_mon %u\n", __func__, &fsid, epoch, num_mon); if (num_mon > CEPH_MAX_MON) goto e_inval; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 237f67a5d004..ef8b7e8b1e9c 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1062,14 +1062,25 @@ static int cache_release(struct inode *inode, struct file *filp, struct cache_reader *rp = filp->private_data; if (rp) { + struct cache_request *rq = NULL; + spin_lock(&queue_lock); if (rp->offset) { struct cache_queue *cq; - for (cq= &rp->q; &cq->list != &cd->queue; - cq = list_entry(cq->list.next, struct cache_queue, list)) + for (cq = &rp->q; &cq->list != &cd->queue; + cq = list_entry(cq->list.next, + struct cache_queue, list)) if (!cq->reader) { - container_of(cq, struct cache_request, q) - ->readers--; + struct cache_request *cr = + container_of(cq, + struct cache_request, q); + cr->readers--; + if (cr->readers == 0 && + !test_bit(CACHE_PENDING, + &cr->item->flags)) { + list_del(&cr->q.list); + rq = cr; + } break; } rp->offset = 0; @@ -1077,9 +1088,14 @@ static int cache_release(struct inode *inode, struct file *filp, list_del(&rp->q.list); spin_unlock(&queue_lock); + if (rq) { + cache_put(rq->item, cd); + kfree(rq->buf); + kfree(rq); + } + filp->private_data = NULL; kfree(rp); - } if (filp->f_mode & FMODE_WRITE) { atomic_dec(&cd->writers); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 15bbf953dfad..b51a162885bb 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1362,7 +1362,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed) needed += RPCRDMA_MAX_RECV_BATCH; if (atomic_inc_return(&ep->re_receiving) > 1) - goto out; + goto out_dec; /* fast path: all needed reps can be found on the free list */ wr = NULL; @@ -1385,7 +1385,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed) ++count; } if (!wr) - goto out; + goto out_dec; rc = ib_post_recv(ep->re_id->qp, wr, (const struct ib_recv_wr **)&bad_wr); @@ -1400,9 +1400,10 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed) --count; } } + +out_dec: if (atomic_dec_return(&ep->re_receiving) > 0) complete(&ep->re_done); - out: trace_xprtrdma_post_recvs(r_xprt, count); ep->re_receive_count += count; diff --git a/rust/Makefile b/rust/Makefile index 629b3bdd2b20..9801af2e1e02 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -148,7 +148,8 @@ doctests_modifiers_workaround := $(rustdoc_modifiers_workaround)$(if $(call rust quiet_cmd_rustdoc = RUSTDOC $(if $(rustdoc_host),H, ) $< cmd_rustdoc = \ OBJTREE=$(abspath $(objtree)) \ - $(RUSTDOC) $(filter-out $(skip_flags) --remap-path-prefix=%,$(if $(rustdoc_host),$(rust_common_flags),$(rust_flags))) \ + $(RUSTDOC) $(filter-out $(skip_flags) --remap-path-prefix=% --remap-path-scope=%, \ + $(if $(rustdoc_host),$(rust_common_flags),$(rust_flags))) \ $(rustc_target_flags) -L$(objtree)/$(obj) \ -Zunstable-options --generate-link-to-definition \ --output $(rustdoc_output) \ @@ -334,7 +335,7 @@ quiet_cmd_rustdoc_test_kernel = RUSTDOC TK $< rm -rf $(objtree)/$(obj)/test/doctests/kernel; \ mkdir -p $(objtree)/$(obj)/test/doctests/kernel; \ OBJTREE=$(abspath $(objtree)) \ - $(RUSTDOC) --test $(filter-out --remap-path-prefix=%,$(rust_flags)) \ + $(RUSTDOC) --test $(filter-out --remap-path-prefix=% --remap-path-scope=%,$(rust_flags)) \ -L$(objtree)/$(obj) --extern ffi --extern pin_init \ --extern kernel --extern build_error --extern macros \ --extern bindings --extern uapi \ @@ -526,11 +527,9 @@ quiet_cmd_rustc_procmacrolibrary = $(RUSTC_OR_CLIPPY_QUIET) PL $@ cmd_rustc_procmacrolibrary = \ $(if $(skip_clippy),$(RUSTC),$(RUSTC_OR_CLIPPY)) \ $(filter-out $(skip_flags),$(rust_common_flags) $(rustc_target_flags)) \ - --emit=dep-info,link --crate-type rlib -O \ + --emit=dep-info=$(depfile) --emit=link=$@ --crate-type rlib -O \ --out-dir $(objtree)/$(obj) -L$(objtree)/$(obj) \ - --crate-name $(patsubst lib%.rlib,%,$(notdir $@)) $<; \ - mv $(objtree)/$(obj)/$(patsubst lib%.rlib,%,$(notdir $@)).d $(depfile); \ - sed -i '/^\#/d' $(depfile) + --crate-name $(patsubst lib%.rlib,%,$(notdir $@)) $< $(obj)/libproc_macro2.rlib: private skip_clippy = 1 $(obj)/libproc_macro2.rlib: private rustc_target_flags = $(proc_macro2-flags) diff --git a/rust/kernel/cpufreq.rs b/rust/kernel/cpufreq.rs index 76faa1ac8501..f5adee48d40c 100644 --- a/rust/kernel/cpufreq.rs +++ b/rust/kernel/cpufreq.rs @@ -401,6 +401,7 @@ impl TableBuilder { /// ``` /// use kernel::cpufreq::{DEFAULT_TRANSITION_LATENCY_NS, Policy}; /// +/// #[allow(clippy::double_parens, reason = "False positive before 1.92.0")] /// fn update_policy(policy: &mut Policy) { /// policy /// .set_dvfs_possible_from_any_cpu(true) diff --git a/rust/kernel/dma.rs b/rust/kernel/dma.rs index 909d56fd5118..a396f8435739 100644 --- a/rust/kernel/dma.rs +++ b/rust/kernel/dma.rs @@ -461,6 +461,19 @@ impl<T: AsBytes + FromBytes> CoherentAllocation<T> { self.count * core::mem::size_of::<T>() } + /// Returns the raw pointer to the allocated region in the CPU's virtual address space. + #[inline] + pub fn as_ptr(&self) -> *const [T] { + core::ptr::slice_from_raw_parts(self.cpu_addr.as_ptr(), self.count) + } + + /// Returns the raw pointer to the allocated region in the CPU's virtual address space as + /// a mutable pointer. + #[inline] + pub fn as_mut_ptr(&self) -> *mut [T] { + core::ptr::slice_from_raw_parts_mut(self.cpu_addr.as_ptr(), self.count) + } + /// Returns the base address to the allocated region in the CPU's virtual address space. pub fn start_ptr(&self) -> *const T { self.cpu_addr.as_ptr() @@ -581,23 +594,6 @@ impl<T: AsBytes + FromBytes> CoherentAllocation<T> { Ok(()) } - /// Returns a pointer to an element from the region with bounds checking. `offset` is in - /// units of `T`, not the number of bytes. - /// - /// Public but hidden since it should only be used from [`dma_read`] and [`dma_write`] macros. - #[doc(hidden)] - pub fn item_from_index(&self, offset: usize) -> Result<*mut T> { - if offset >= self.count { - return Err(EINVAL); - } - // SAFETY: - // - The pointer is valid due to type invariant on `CoherentAllocation` - // and we've just checked that the range and index is within bounds. - // - `offset` can't overflow since it is smaller than `self.count` and we've checked - // that `self.count` won't overflow early in the constructor. - Ok(unsafe { self.cpu_addr.as_ptr().add(offset) }) - } - /// Reads the value of `field` and ensures that its type is [`FromBytes`]. /// /// # Safety @@ -670,6 +666,9 @@ unsafe impl<T: AsBytes + FromBytes + Send> Send for CoherentAllocation<T> {} /// Reads a field of an item from an allocated region of structs. /// +/// The syntax is of the form `kernel::dma_read!(dma, proj)` where `dma` is an expression evaluating +/// to a [`CoherentAllocation`] and `proj` is a [projection specification](kernel::ptr::project!). +/// /// # Examples /// /// ``` @@ -684,36 +683,29 @@ unsafe impl<T: AsBytes + FromBytes + Send> Send for CoherentAllocation<T> {} /// unsafe impl kernel::transmute::AsBytes for MyStruct{}; /// /// # fn test(alloc: &kernel::dma::CoherentAllocation<MyStruct>) -> Result { -/// let whole = kernel::dma_read!(alloc[2]); -/// let field = kernel::dma_read!(alloc[1].field); +/// let whole = kernel::dma_read!(alloc, [2]?); +/// let field = kernel::dma_read!(alloc, [1]?.field); /// # Ok::<(), Error>(()) } /// ``` #[macro_export] macro_rules! dma_read { - ($dma:expr, $idx: expr, $($field:tt)*) => {{ - (|| -> ::core::result::Result<_, $crate::error::Error> { - let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?; - // SAFETY: `item_from_index` ensures that `item` is always a valid pointer and can be - // dereferenced. The compiler also further validates the expression on whether `field` - // is a member of `item` when expanded by the macro. - unsafe { - let ptr_field = ::core::ptr::addr_of!((*item) $($field)*); - ::core::result::Result::Ok( - $crate::dma::CoherentAllocation::field_read(&$dma, ptr_field) - ) - } - })() + ($dma:expr, $($proj:tt)*) => {{ + let dma = &$dma; + let ptr = $crate::ptr::project!( + $crate::dma::CoherentAllocation::as_ptr(dma), $($proj)* + ); + // SAFETY: The pointer created by the projection is within the DMA region. + unsafe { $crate::dma::CoherentAllocation::field_read(dma, ptr) } }}; - ($dma:ident [ $idx:expr ] $($field:tt)* ) => { - $crate::dma_read!($dma, $idx, $($field)*) - }; - ($($dma:ident).* [ $idx:expr ] $($field:tt)* ) => { - $crate::dma_read!($($dma).*, $idx, $($field)*) - }; } /// Writes to a field of an item from an allocated region of structs. /// +/// The syntax is of the form `kernel::dma_write!(dma, proj, val)` where `dma` is an expression +/// evaluating to a [`CoherentAllocation`], `proj` is a +/// [projection specification](kernel::ptr::project!), and `val` is the value to be written to the +/// projected location. +/// /// # Examples /// /// ``` @@ -728,37 +720,31 @@ macro_rules! dma_read { /// unsafe impl kernel::transmute::AsBytes for MyStruct{}; /// /// # fn test(alloc: &kernel::dma::CoherentAllocation<MyStruct>) -> Result { -/// kernel::dma_write!(alloc[2].member = 0xf); -/// kernel::dma_write!(alloc[1] = MyStruct { member: 0xf }); +/// kernel::dma_write!(alloc, [2]?.member, 0xf); +/// kernel::dma_write!(alloc, [1]?, MyStruct { member: 0xf }); /// # Ok::<(), Error>(()) } /// ``` #[macro_export] macro_rules! dma_write { - ($dma:ident [ $idx:expr ] $($field:tt)*) => {{ - $crate::dma_write!($dma, $idx, $($field)*) - }}; - ($($dma:ident).* [ $idx:expr ] $($field:tt)* ) => {{ - $crate::dma_write!($($dma).*, $idx, $($field)*) + (@parse [$dma:expr] [$($proj:tt)*] [, $val:expr]) => {{ + let dma = &$dma; + let ptr = $crate::ptr::project!( + mut $crate::dma::CoherentAllocation::as_mut_ptr(dma), $($proj)* + ); + let val = $val; + // SAFETY: The pointer created by the projection is within the DMA region. + unsafe { $crate::dma::CoherentAllocation::field_write(dma, ptr, val) } }}; - ($dma:expr, $idx: expr, = $val:expr) => { - (|| -> ::core::result::Result<_, $crate::error::Error> { - let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?; - // SAFETY: `item_from_index` ensures that `item` is always a valid item. - unsafe { $crate::dma::CoherentAllocation::field_write(&$dma, item, $val) } - ::core::result::Result::Ok(()) - })() + (@parse [$dma:expr] [$($proj:tt)*] [.$field:tt $($rest:tt)*]) => { + $crate::dma_write!(@parse [$dma] [$($proj)* .$field] [$($rest)*]) + }; + (@parse [$dma:expr] [$($proj:tt)*] [[$index:expr]? $($rest:tt)*]) => { + $crate::dma_write!(@parse [$dma] [$($proj)* [$index]?] [$($rest)*]) + }; + (@parse [$dma:expr] [$($proj:tt)*] [[$index:expr] $($rest:tt)*]) => { + $crate::dma_write!(@parse [$dma] [$($proj)* [$index]] [$($rest)*]) }; - ($dma:expr, $idx: expr, $(.$field:ident)* = $val:expr) => { - (|| -> ::core::result::Result<_, $crate::error::Error> { - let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?; - // SAFETY: `item_from_index` ensures that `item` is always a valid pointer and can be - // dereferenced. The compiler also further validates the expression on whether `field` - // is a member of `item` when expanded by the macro. - unsafe { - let ptr_field = ::core::ptr::addr_of_mut!((*item) $(.$field)*); - $crate::dma::CoherentAllocation::field_write(&$dma, ptr_field, $val) - } - ::core::result::Result::Ok(()) - })() + ($dma:expr, $($rest:tt)*) => { + $crate::dma_write!(@parse [$dma] [] [$($rest)*]) }; } diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 3da92f18f4ee..d93292d47420 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -20,6 +20,7 @@ #![feature(generic_nonzero)] #![feature(inline_const)] #![feature(pointer_is_aligned)] +#![feature(slice_ptr_len)] // // Stable since Rust 1.80.0. #![feature(slice_flatten)] @@ -37,6 +38,9 @@ #![feature(const_ptr_write)] #![feature(const_refs_to_cell)] // +// Stable since Rust 1.84.0. +#![feature(strict_provenance)] +// // Expected to become stable. #![feature(arbitrary_self_types)] // diff --git a/rust/kernel/ptr.rs b/rust/kernel/ptr.rs index 5b6a382637fe..bdc2d79ff669 100644 --- a/rust/kernel/ptr.rs +++ b/rust/kernel/ptr.rs @@ -2,7 +2,13 @@ //! Types and functions to work with pointers and addresses. -use core::mem::align_of; +pub mod projection; +pub use crate::project_pointer as project; + +use core::mem::{ + align_of, + size_of, // +}; use core::num::NonZero; /// Type representing an alignment, which is always a power of two. @@ -225,3 +231,25 @@ macro_rules! impl_alignable_uint { } impl_alignable_uint!(u8, u16, u32, u64, usize); + +/// Trait to represent compile-time known size information. +/// +/// This is a generalization of [`size_of`] that works for dynamically sized types. +pub trait KnownSize { + /// Get the size of an object of this type in bytes, with the metadata of the given pointer. + fn size(p: *const Self) -> usize; +} + +impl<T> KnownSize for T { + #[inline(always)] + fn size(_: *const Self) -> usize { + size_of::<T>() + } +} + +impl<T> KnownSize for [T] { + #[inline(always)] + fn size(p: *const Self) -> usize { + p.len() * size_of::<T>() + } +} diff --git a/rust/kernel/ptr/projection.rs b/rust/kernel/ptr/projection.rs new file mode 100644 index 000000000000..140ea8e21617 --- /dev/null +++ b/rust/kernel/ptr/projection.rs @@ -0,0 +1,305 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Infrastructure for handling projections. + +use core::{ + mem::MaybeUninit, + ops::Deref, // +}; + +use crate::prelude::*; + +/// Error raised when a projection is attempted on an array or slice out of bounds. +pub struct OutOfBound; + +impl From<OutOfBound> for Error { + #[inline(always)] + fn from(_: OutOfBound) -> Self { + ERANGE + } +} + +/// A helper trait to perform index projection. +/// +/// This is similar to [`core::slice::SliceIndex`], but operates on raw pointers safely and +/// fallibly. +/// +/// # Safety +/// +/// The implementation of `index` and `get` (if [`Some`] is returned) must ensure that, if provided +/// input pointer `slice` and returned pointer `output`, then: +/// - `output` has the same provenance as `slice`; +/// - `output.byte_offset_from(slice)` is between 0 to +/// `KnownSize::size(slice) - KnownSize::size(output)`. +/// +/// This means that if the input pointer is valid, then pointer returned by `get` or `index` is +/// also valid. +#[diagnostic::on_unimplemented(message = "`{Self}` cannot be used to index `{T}`")] +#[doc(hidden)] +pub unsafe trait ProjectIndex<T: ?Sized>: Sized { + type Output: ?Sized; + + /// Returns an index-projected pointer, if in bounds. + fn get(self, slice: *mut T) -> Option<*mut Self::Output>; + + /// Returns an index-projected pointer; fail the build if it cannot be proved to be in bounds. + #[inline(always)] + fn index(self, slice: *mut T) -> *mut Self::Output { + Self::get(self, slice).unwrap_or_else(|| build_error!()) + } +} + +// Forward array impl to slice impl. +// +// SAFETY: Safety requirement guaranteed by the forwarded impl. +unsafe impl<T, I, const N: usize> ProjectIndex<[T; N]> for I +where + I: ProjectIndex<[T]>, +{ + type Output = <I as ProjectIndex<[T]>>::Output; + + #[inline(always)] + fn get(self, slice: *mut [T; N]) -> Option<*mut Self::Output> { + <I as ProjectIndex<[T]>>::get(self, slice) + } + + #[inline(always)] + fn index(self, slice: *mut [T; N]) -> *mut Self::Output { + <I as ProjectIndex<[T]>>::index(self, slice) + } +} + +// SAFETY: `get`-returned pointer has the same provenance as `slice` and the offset is checked to +// not exceed the required bound. +unsafe impl<T> ProjectIndex<[T]> for usize { + type Output = T; + + #[inline(always)] + fn get(self, slice: *mut [T]) -> Option<*mut T> { + if self >= slice.len() { + None + } else { + Some(slice.cast::<T>().wrapping_add(self)) + } + } +} + +// SAFETY: `get`-returned pointer has the same provenance as `slice` and the offset is checked to +// not exceed the required bound. +unsafe impl<T> ProjectIndex<[T]> for core::ops::Range<usize> { + type Output = [T]; + + #[inline(always)] + fn get(self, slice: *mut [T]) -> Option<*mut [T]> { + let new_len = self.end.checked_sub(self.start)?; + if self.end > slice.len() { + return None; + } + Some(core::ptr::slice_from_raw_parts_mut( + slice.cast::<T>().wrapping_add(self.start), + new_len, + )) + } +} + +// SAFETY: Safety requirement guaranteed by the forwarded impl. +unsafe impl<T> ProjectIndex<[T]> for core::ops::RangeTo<usize> { + type Output = [T]; + + #[inline(always)] + fn get(self, slice: *mut [T]) -> Option<*mut [T]> { + (0..self.end).get(slice) + } +} + +// SAFETY: Safety requirement guaranteed by the forwarded impl. +unsafe impl<T> ProjectIndex<[T]> for core::ops::RangeFrom<usize> { + type Output = [T]; + + #[inline(always)] + fn get(self, slice: *mut [T]) -> Option<*mut [T]> { + (self.start..slice.len()).get(slice) + } +} + +// SAFETY: `get` returned the pointer as is, so it always has the same provenance and offset of 0. +unsafe impl<T> ProjectIndex<[T]> for core::ops::RangeFull { + type Output = [T]; + + #[inline(always)] + fn get(self, slice: *mut [T]) -> Option<*mut [T]> { + Some(slice) + } +} + +/// A helper trait to perform field projection. +/// +/// This trait has a `DEREF` generic parameter so it can be implemented twice for types that +/// implement [`Deref`]. This will cause an ambiguity error and thus block [`Deref`] types being +/// used as base of projection, as they can inject unsoundness. Users therefore must not specify +/// `DEREF` and should always leave it to be inferred. +/// +/// # Safety +/// +/// `proj` may only invoke `f` with a valid allocation, as the documentation of [`Self::proj`] +/// describes. +#[doc(hidden)] +pub unsafe trait ProjectField<const DEREF: bool> { + /// Project a pointer to a type to a pointer of a field. + /// + /// `f` may only be invoked with a valid allocation so it can safely obtain raw pointers to + /// fields using `&raw mut`. + /// + /// This is needed because `base` might not point to a valid allocation, while `&raw mut` + /// requires pointers to be in bounds of a valid allocation. + /// + /// # Safety + /// + /// `f` must return a pointer in bounds of the provided pointer. + unsafe fn proj<F>(base: *mut Self, f: impl FnOnce(*mut Self) -> *mut F) -> *mut F; +} + +// NOTE: in theory, this API should work for `T: ?Sized` and `F: ?Sized`, too. However, we cannot +// currently support that as we need to obtain a valid allocation that `&raw const` can operate on. +// +// SAFETY: `proj` invokes `f` with valid allocation. +unsafe impl<T> ProjectField<false> for T { + #[inline(always)] + unsafe fn proj<F>(base: *mut Self, f: impl FnOnce(*mut Self) -> *mut F) -> *mut F { + // Create a valid allocation to start projection, as `base` is not necessarily so. The + // memory is never actually used so it will be optimized out, so it should work even for + // very large `T` (`memoffset` crate also relies on this). To be extra certain, we also + // annotate `f` closure with `#[inline(always)]` in the macro. + let mut place = MaybeUninit::uninit(); + let place_base = place.as_mut_ptr(); + let field = f(place_base); + // SAFETY: `field` is in bounds from `base` per safety requirement. + let offset = unsafe { field.byte_offset_from(place_base) }; + // Use `wrapping_byte_offset` as `base` does not need to be of valid allocation. + base.wrapping_byte_offset(offset).cast() + } +} + +// SAFETY: Vacuously satisfied. +unsafe impl<T: Deref> ProjectField<true> for T { + #[inline(always)] + unsafe fn proj<F>(_: *mut Self, _: impl FnOnce(*mut Self) -> *mut F) -> *mut F { + build_error!("this function is a guard against `Deref` impl and is never invoked"); + } +} + +/// Create a projection from a raw pointer. +/// +/// The projected pointer is within the memory region marked by the input pointer. There is no +/// requirement that the input raw pointer needs to be valid, so this macro may be used for +/// projecting pointers outside normal address space, e.g. I/O pointers. However, if the input +/// pointer is valid, the projected pointer is also valid. +/// +/// Supported projections include field projections and index projections. +/// It is not allowed to project into types that implement custom [`Deref`] or +/// [`Index`](core::ops::Index). +/// +/// The macro has basic syntax of `kernel::ptr::project!(ptr, projection)`, where `ptr` is an +/// expression that evaluates to a raw pointer which serves as the base of projection. `projection` +/// can be a projection expression of form `.field` (normally identifier, or numeral in case of +/// tuple structs) or of form `[index]`. +/// +/// If a mutable pointer is needed, the macro input can be prefixed with the `mut` keyword, i.e. +/// `kernel::ptr::project!(mut ptr, projection)`. By default, a const pointer is created. +/// +/// `ptr::project!` macro can perform both fallible indexing and build-time checked indexing. +/// `[index]` form performs build-time bounds checking; if compiler fails to prove `[index]` is in +/// bounds, compilation will fail. `[index]?` can be used to perform runtime bounds checking; +/// `OutOfBound` error is raised via `?` if the index is out of bounds. +/// +/// # Examples +/// +/// Field projections are performed with `.field_name`: +/// +/// ``` +/// struct MyStruct { field: u32, } +/// let ptr: *const MyStruct = core::ptr::dangling(); +/// let field_ptr: *const u32 = kernel::ptr::project!(ptr, .field); +/// +/// struct MyTupleStruct(u32, u32); +/// +/// fn proj(ptr: *const MyTupleStruct) { +/// let field_ptr: *const u32 = kernel::ptr::project!(ptr, .1); +/// } +/// ``` +/// +/// Index projections are performed with `[index]`: +/// +/// ``` +/// fn proj(ptr: *const [u8; 32]) -> Result { +/// let field_ptr: *const u8 = kernel::ptr::project!(ptr, [1]); +/// // The following invocation, if uncommented, would fail the build. +/// // +/// // kernel::ptr::project!(ptr, [128]); +/// +/// // This will raise an `OutOfBound` error (which is convertible to `ERANGE`). +/// kernel::ptr::project!(ptr, [128]?); +/// Ok(()) +/// } +/// ``` +/// +/// If you need to match on the error instead of propagate, put the invocation inside a closure: +/// +/// ``` +/// let ptr: *const [u8; 32] = core::ptr::dangling(); +/// let field_ptr: Result<*const u8> = (|| -> Result<_> { +/// Ok(kernel::ptr::project!(ptr, [128]?)) +/// })(); +/// assert!(field_ptr.is_err()); +/// ``` +/// +/// For mutable pointers, put `mut` as the first token in macro invocation. +/// +/// ``` +/// let ptr: *mut [(u8, u16); 32] = core::ptr::dangling_mut(); +/// let field_ptr: *mut u16 = kernel::ptr::project!(mut ptr, [1].1); +/// ``` +#[macro_export] +macro_rules! project_pointer { + (@gen $ptr:ident, ) => {}; + // Field projection. `$field` needs to be `tt` to support tuple index like `.0`. + (@gen $ptr:ident, .$field:tt $($rest:tt)*) => { + // SAFETY: The provided closure always returns an in-bounds pointer. + let $ptr = unsafe { + $crate::ptr::projection::ProjectField::proj($ptr, #[inline(always)] |ptr| { + // Check unaligned field. Not all users (e.g. DMA) can handle unaligned + // projections. + if false { + let _ = &(*ptr).$field; + } + // SAFETY: `$field` is in bounds, and no implicit `Deref` is possible (if the + // type implements `Deref`, Rust cannot infer the generic parameter `DEREF`). + &raw mut (*ptr).$field + }) + }; + $crate::ptr::project!(@gen $ptr, $($rest)*) + }; + // Fallible index projection. + (@gen $ptr:ident, [$index:expr]? $($rest:tt)*) => { + let $ptr = $crate::ptr::projection::ProjectIndex::get($index, $ptr) + .ok_or($crate::ptr::projection::OutOfBound)?; + $crate::ptr::project!(@gen $ptr, $($rest)*) + }; + // Build-time checked index projection. + (@gen $ptr:ident, [$index:expr] $($rest:tt)*) => { + let $ptr = $crate::ptr::projection::ProjectIndex::index($index, $ptr); + $crate::ptr::project!(@gen $ptr, $($rest)*) + }; + (mut $ptr:expr, $($proj:tt)*) => {{ + let ptr: *mut _ = $ptr; + $crate::ptr::project!(@gen ptr, $($proj)*); + ptr + }}; + ($ptr:expr, $($proj:tt)*) => {{ + let ptr = <*const _>::cast_mut($ptr); + // We currently always project using mutable pointer, as it is not decided whether `&raw + // const` allows the resulting pointer to be mutated (see documentation of `addr_of!`). + $crate::ptr::project!(@gen ptr, $($proj)*); + ptr.cast_const() + }}; +} diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs index fa87779d2253..3f8918764640 100644 --- a/rust/kernel/str.rs +++ b/rust/kernel/str.rs @@ -664,13 +664,13 @@ impl fmt::Write for Formatter<'_> { /// /// * The first byte of `buffer` is always zero. /// * The length of `buffer` is at least 1. -pub(crate) struct NullTerminatedFormatter<'a> { +pub struct NullTerminatedFormatter<'a> { buffer: &'a mut [u8], } impl<'a> NullTerminatedFormatter<'a> { /// Create a new [`Self`] instance. - pub(crate) fn new(buffer: &'a mut [u8]) -> Option<NullTerminatedFormatter<'a>> { + pub fn new(buffer: &'a mut [u8]) -> Option<NullTerminatedFormatter<'a>> { *(buffer.first_mut()?) = 0; // INVARIANT: diff --git a/rust/pin-init/internal/src/init.rs b/rust/pin-init/internal/src/init.rs index 42936f915a07..2fe918f4d82a 100644 --- a/rust/pin-init/internal/src/init.rs +++ b/rust/pin-init/internal/src/init.rs @@ -62,7 +62,6 @@ impl InitializerKind { enum InitializerAttribute { DefaultError(DefaultErrorAttribute), - DisableInitializedFieldAccess, } struct DefaultErrorAttribute { @@ -86,6 +85,7 @@ pub(crate) fn expand( let error = error.map_or_else( || { if let Some(default_error) = attrs.iter().fold(None, |acc, attr| { + #[expect(irrefutable_let_patterns)] if let InitializerAttribute::DefaultError(DefaultErrorAttribute { ty }) = attr { Some(ty.clone()) } else { @@ -145,22 +145,9 @@ pub(crate) fn expand( }; // `mixed_site` ensures that the data is not accessible to the user-controlled code. let data = Ident::new("__data", Span::mixed_site()); - let init_fields = init_fields( - &fields, - pinned, - !attrs - .iter() - .any(|attr| matches!(attr, InitializerAttribute::DisableInitializedFieldAccess)), - &data, - &slot, - ); + let init_fields = init_fields(&fields, pinned, &data, &slot); let field_check = make_field_check(&fields, init_kind, &path); Ok(quote! {{ - // We do not want to allow arbitrary returns, so we declare this type as the `Ok` return - // type and shadow it later when we insert the arbitrary user code. That way there will be - // no possibility of returning without `unsafe`. - struct __InitOk; - // Get the data about fields from the supplied type. // SAFETY: TODO let #data = unsafe { @@ -170,18 +157,15 @@ pub(crate) fn expand( #path::#get_data() }; // Ensure that `#data` really is of type `#data` and help with type inference: - let init = ::pin_init::__internal::#data_trait::make_closure::<_, __InitOk, #error>( + let init = ::pin_init::__internal::#data_trait::make_closure::<_, #error>( #data, move |slot| { - { - // Shadow the structure so it cannot be used to return early. - struct __InitOk; - #zeroable_check - #this - #init_fields - #field_check - } - Ok(__InitOk) + #zeroable_check + #this + #init_fields + #field_check + // SAFETY: we are the `init!` macro that is allowed to call this. + Ok(unsafe { ::pin_init::__internal::InitOk::new() }) } ); let init = move |slot| -> ::core::result::Result<(), #error> { @@ -236,7 +220,6 @@ fn get_init_kind(rest: Option<(Token![..], Expr)>, dcx: &mut DiagCtxt) -> InitKi fn init_fields( fields: &Punctuated<InitializerField, Token![,]>, pinned: bool, - generate_initialized_accessors: bool, data: &Ident, slot: &Ident, ) -> TokenStream { @@ -260,6 +243,10 @@ fn init_fields( }); // Again span for better diagnostics let write = quote_spanned!(ident.span()=> ::core::ptr::write); + // NOTE: the field accessor ensures that the initialized field is properly aligned. + // Unaligned fields will cause the compiler to emit E0793. We do not support + // unaligned fields since `Init::__init` requires an aligned pointer; the call to + // `ptr::write` below has the same requirement. let accessor = if pinned { let project_ident = format_ident!("__project_{ident}"); quote! { @@ -272,13 +259,6 @@ fn init_fields( unsafe { &mut (*#slot).#ident } } }; - let accessor = generate_initialized_accessors.then(|| { - quote! { - #(#cfgs)* - #[allow(unused_variables)] - let #ident = #accessor; - } - }); quote! { #(#attrs)* { @@ -286,12 +266,18 @@ fn init_fields( // SAFETY: TODO unsafe { #write(::core::ptr::addr_of_mut!((*#slot).#ident), #value_ident) }; } - #accessor + #(#cfgs)* + #[allow(unused_variables)] + let #ident = #accessor; } } InitializerKind::Init { ident, value, .. } => { // Again span for better diagnostics let init = format_ident!("init", span = value.span()); + // NOTE: the field accessor ensures that the initialized field is properly aligned. + // Unaligned fields will cause the compiler to emit E0793. We do not support + // unaligned fields since `Init::__init` requires an aligned pointer; the call to + // `ptr::write` below has the same requirement. let (value_init, accessor) = if pinned { let project_ident = format_ident!("__project_{ident}"); ( @@ -326,20 +312,15 @@ fn init_fields( }, ) }; - let accessor = generate_initialized_accessors.then(|| { - quote! { - #(#cfgs)* - #[allow(unused_variables)] - let #ident = #accessor; - } - }); quote! { #(#attrs)* { let #init = #value; #value_init } - #accessor + #(#cfgs)* + #[allow(unused_variables)] + let #ident = #accessor; } } InitializerKind::Code { block: value, .. } => quote! { @@ -466,10 +447,6 @@ impl Parse for Initializer { if a.path().is_ident("default_error") { a.parse_args::<DefaultErrorAttribute>() .map(InitializerAttribute::DefaultError) - } else if a.path().is_ident("disable_initialized_field_access") { - a.meta - .require_path_only() - .map(|_| InitializerAttribute::DisableInitializedFieldAccess) } else { Err(syn::Error::new_spanned(a, "unknown initializer attribute")) } diff --git a/rust/pin-init/src/__internal.rs b/rust/pin-init/src/__internal.rs index 90f18e9a2912..90adbdc1893b 100644 --- a/rust/pin-init/src/__internal.rs +++ b/rust/pin-init/src/__internal.rs @@ -46,6 +46,24 @@ where } } +/// Token type to signify successful initialization. +/// +/// Can only be constructed via the unsafe [`Self::new`] function. The initializer macros use this +/// token type to prevent returning `Ok` from an initializer without initializing all fields. +pub struct InitOk(()); + +impl InitOk { + /// Creates a new token. + /// + /// # Safety + /// + /// This function may only be called from the `init!` macro in `../internal/src/init.rs`. + #[inline(always)] + pub unsafe fn new() -> Self { + Self(()) + } +} + /// This trait is only implemented via the `#[pin_data]` proc-macro. It is used to facilitate /// the pin projections within the initializers. /// @@ -68,9 +86,10 @@ pub unsafe trait PinData: Copy { type Datee: ?Sized + HasPinData; /// Type inference helper function. - fn make_closure<F, O, E>(self, f: F) -> F + #[inline(always)] + fn make_closure<F, E>(self, f: F) -> F where - F: FnOnce(*mut Self::Datee) -> Result<O, E>, + F: FnOnce(*mut Self::Datee) -> Result<InitOk, E>, { f } @@ -98,9 +117,10 @@ pub unsafe trait InitData: Copy { type Datee: ?Sized + HasInitData; /// Type inference helper function. - fn make_closure<F, O, E>(self, f: F) -> F + #[inline(always)] + fn make_closure<F, E>(self, f: F) -> F where - F: FnOnce(*mut Self::Datee) -> Result<O, E>, + F: FnOnce(*mut Self::Datee) -> Result<InitOk, E>, { f } diff --git a/samples/rust/rust_dma.rs b/samples/rust/rust_dma.rs index 9c45851c876e..ce39b5545097 100644 --- a/samples/rust/rust_dma.rs +++ b/samples/rust/rust_dma.rs @@ -68,7 +68,7 @@ impl pci::Driver for DmaSampleDriver { CoherentAllocation::alloc_coherent(pdev.as_ref(), TEST_VALUES.len(), GFP_KERNEL)?; for (i, value) in TEST_VALUES.into_iter().enumerate() { - kernel::dma_write!(ca[i] = MyStruct::new(value.0, value.1))?; + kernel::dma_write!(ca, [i]?, MyStruct::new(value.0, value.1)); } let size = 4 * page::PAGE_SIZE; @@ -85,24 +85,26 @@ impl pci::Driver for DmaSampleDriver { } } +impl DmaSampleDriver { + fn check_dma(&self) -> Result { + for (i, value) in TEST_VALUES.into_iter().enumerate() { + let val0 = kernel::dma_read!(self.ca, [i]?.h); + let val1 = kernel::dma_read!(self.ca, [i]?.b); + + assert_eq!(val0, value.0); + assert_eq!(val1, value.1); + } + + Ok(()) + } +} + #[pinned_drop] impl PinnedDrop for DmaSampleDriver { fn drop(self: Pin<&mut Self>) { dev_info!(self.pdev, "Unload DMA test driver.\n"); - for (i, value) in TEST_VALUES.into_iter().enumerate() { - let val0 = kernel::dma_read!(self.ca[i].h); - let val1 = kernel::dma_read!(self.ca[i].b); - assert!(val0.is_ok()); - assert!(val1.is_ok()); - - if let Ok(val0) = val0 { - assert_eq!(val0, value.0); - } - if let Ok(val1) = val1 { - assert_eq!(val1, value.1); - } - } + assert!(self.check_dma().is_ok()); for (i, entry) in self.sgt.iter().enumerate() { dev_info!( diff --git a/samples/workqueue/stall_detector/Makefile b/samples/workqueue/stall_detector/Makefile new file mode 100644 index 000000000000..8849e85e95bb --- /dev/null +++ b/samples/workqueue/stall_detector/Makefile @@ -0,0 +1 @@ +obj-m += wq_stall.o diff --git a/samples/workqueue/stall_detector/wq_stall.c b/samples/workqueue/stall_detector/wq_stall.c new file mode 100644 index 000000000000..6f4a497b1881 --- /dev/null +++ b/samples/workqueue/stall_detector/wq_stall.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * wq_stall - Test module for the workqueue stall detector. + * + * Deliberately creates a workqueue stall so the watchdog fires and + * prints diagnostic output. Useful for verifying that the stall + * detector correctly identifies stuck workers and produces useful + * backtraces. + * + * The stall is triggered by clearing PF_WQ_WORKER before sleeping, + * which hides the worker from the concurrency manager. A second + * work item queued on the same pool then sits in the worklist with + * no worker available to process it. + * + * After ~30s the workqueue watchdog fires: + * BUG: workqueue lockup - pool cpus=N ... + * + * Build: + * make -C <kernel tree> M=samples/workqueue/stall_detector modules + * + * Copyright (c) 2026 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2026 Breno Leitao <leitao@debian.org> + */ + +#include <linux/module.h> +#include <linux/workqueue.h> +#include <linux/wait.h> +#include <linux/atomic.h> +#include <linux/sched.h> + +static DECLARE_WAIT_QUEUE_HEAD(stall_wq_head); +static atomic_t wake_condition = ATOMIC_INIT(0); +static struct work_struct stall_work1; +static struct work_struct stall_work2; + +static void stall_work2_fn(struct work_struct *work) +{ + pr_info("wq_stall: second work item finally ran\n"); +} + +static void stall_work1_fn(struct work_struct *work) +{ + pr_info("wq_stall: first work item running on cpu %d\n", + raw_smp_processor_id()); + + /* + * Queue second item while we're still counted as running + * (pool->nr_running > 0). Since schedule_work() on a per-CPU + * workqueue targets raw_smp_processor_id(), item 2 lands on the + * same pool. __queue_work -> kick_pool -> need_more_worker() + * sees nr_running > 0 and does NOT wake a new worker. + */ + schedule_work(&stall_work2); + + /* + * Hide from the workqueue concurrency manager. Without + * PF_WQ_WORKER, schedule() won't call wq_worker_sleeping(), + * so nr_running is never decremented and no replacement + * worker is created. Item 2 stays stuck in pool->worklist. + */ + current->flags &= ~PF_WQ_WORKER; + + pr_info("wq_stall: entering wait_event_idle (PF_WQ_WORKER cleared)\n"); + pr_info("wq_stall: expect 'BUG: workqueue lockup' in ~30-60s\n"); + wait_event_idle(stall_wq_head, atomic_read(&wake_condition) != 0); + + /* Restore so process_one_work() cleanup works correctly */ + current->flags |= PF_WQ_WORKER; + pr_info("wq_stall: woke up, PF_WQ_WORKER restored\n"); +} + +static int __init wq_stall_init(void) +{ + pr_info("wq_stall: loading\n"); + + INIT_WORK(&stall_work1, stall_work1_fn); + INIT_WORK(&stall_work2, stall_work2_fn); + schedule_work(&stall_work1); + + return 0; +} + +static void __exit wq_stall_exit(void) +{ + pr_info("wq_stall: unloading\n"); + atomic_set(&wake_condition, 1); + wake_up(&stall_wq_head); + flush_work(&stall_work1); + flush_work(&stall_work2); + pr_info("wq_stall: all work flushed, module unloaded\n"); +} + +module_init(wq_stall_init); +module_exit(wq_stall_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Reproduce workqueue stall caused by PF_WQ_WORKER misuse"); +MODULE_AUTHOR("Breno Leitao <leitao@debian.org>"); diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 32e209bc7985..3652b85be545 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -310,16 +310,18 @@ $(obj)/%.lst: $(obj)/%.c FORCE # The features in this list are the ones allowed for non-`rust/` code. # +# - Stable since Rust 1.79.0: `feature(slice_ptr_len)`. # - Stable since Rust 1.81.0: `feature(lint_reasons)`. # - Stable since Rust 1.82.0: `feature(asm_const)`, # `feature(offset_of_nested)`, `feature(raw_ref_op)`. +# - Stable since Rust 1.84.0: `feature(strict_provenance)`. # - Stable since Rust 1.87.0: `feature(asm_goto)`. # - Expected to become stable: `feature(arbitrary_self_types)`. # - To be determined: `feature(used_with_arg)`. # # Please see https://github.com/Rust-for-Linux/linux/issues/2 for details on # the unstable features in use. -rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,lint_reasons,offset_of_nested,raw_ref_op,used_with_arg +rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,lint_reasons,offset_of_nested,raw_ref_op,slice_ptr_len,strict_provenance,used_with_arg # `--out-dir` is required to avoid temporaries being created by `rustc` in the # current working directory, which may be not accessible in the out-of-tree diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 67cf6a0e17ba..5a64453da728 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -2144,6 +2144,10 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream, for (;;) { long tout; struct snd_pcm_runtime *to_check; + unsigned int drain_rate; + snd_pcm_uframes_t drain_bufsz; + bool drain_no_period_wakeup; + if (signal_pending(current)) { result = -ERESTARTSYS; break; @@ -2163,16 +2167,25 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream, snd_pcm_group_unref(group, substream); if (!to_check) break; /* all drained */ + /* + * Cache the runtime fields needed after unlock. + * A concurrent close() on the linked stream may free + * its runtime via snd_pcm_detach_substream() once we + * release the stream lock below. + */ + drain_no_period_wakeup = to_check->no_period_wakeup; + drain_rate = to_check->rate; + drain_bufsz = to_check->buffer_size; init_waitqueue_entry(&wait, current); set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&to_check->sleep, &wait); snd_pcm_stream_unlock_irq(substream); - if (runtime->no_period_wakeup) + if (drain_no_period_wakeup) tout = MAX_SCHEDULE_TIMEOUT; else { tout = 100; - if (runtime->rate) { - long t = runtime->buffer_size * 1100 / runtime->rate; + if (drain_rate) { + long t = drain_bufsz * 1100 / drain_rate; tout = max(t, tout); } tout = msecs_to_jiffies(tout); diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 4c49f1195e1b..ab4b22fcb72e 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -6940,6 +6940,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x89da, "HP Spectre x360 14t-ea100", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX), SND_PCI_QUIRK(0x103c, 0x89e7, "HP Elite x2 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8a0f, "HP Pavilion 14-ec1xxx", ALC287_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8a1f, "HP Laptop 14s-dr5xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8a20, "HP Laptop 15s-fq5xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8a25, "HP Victus 16-d1xxx (MB 8A25)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a26, "HP Victus 16-d1xxx (MB 8A26)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), @@ -7273,6 +7274,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1e93, "ASUS ExpertBook B9403CVAR", ALC294_FIXUP_ASUS_HPE), SND_PCI_QUIRK(0x1043, 0x1eb3, "ASUS Ally RCLA72", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x1043, 0x1ed3, "ASUS HN7306W", ALC287_FIXUP_CS35L41_I2C_2), + HDA_CODEC_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC285_FIXUP_ASUS_I2C_SPEAKER2_TO_DAC1), SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), @@ -7493,6 +7495,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x224c, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x224d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x17aa, 0x2288, "Thinkpad X390", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x22be, "Thinkpad X1 Carbon 8th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x22c1, "Thinkpad P1 Gen 3", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK), diff --git a/sound/hda/codecs/realtek/alc662.c b/sound/hda/codecs/realtek/alc662.c index 5073165d1f3c..3a943adf9087 100644 --- a/sound/hda/codecs/realtek/alc662.c +++ b/sound/hda/codecs/realtek/alc662.c @@ -313,6 +313,7 @@ enum { ALC897_FIXUP_HEADSET_MIC_PIN2, ALC897_FIXUP_UNIS_H3C_X500S, ALC897_FIXUP_HEADSET_MIC_PIN3, + ALC897_FIXUP_H610M_HP_PIN, }; static const struct hda_fixup alc662_fixups[] = { @@ -766,6 +767,13 @@ static const struct hda_fixup alc662_fixups[] = { { } }, }, + [ALC897_FIXUP_H610M_HP_PIN] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x0321403f }, /* HP out */ + { } + }, + }, }; static const struct hda_quirk alc662_fixup_tbl[] = { @@ -815,6 +823,7 @@ static const struct hda_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x8469, "ASUS mobo", ALC662_FIXUP_NO_JACK_DETECT), SND_PCI_QUIRK(0x105b, 0x0cd6, "Foxconn", ALC662_FIXUP_ASUS_MODE2), SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD), + SND_PCI_QUIRK(0x1458, 0xa194, "H610M H V2 DDR4", ALC897_FIXUP_H610M_HP_PIN), SND_PCI_QUIRK(0x14cd, 0x5003, "USI", ALC662_FIXUP_USI_HEADSET_MODE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC662_FIXUP_LENOVO_MULTI_CODECS), SND_PCI_QUIRK(0x17aa, 0x1057, "Lenovo P360", ALC897_FIXUP_HEADSET_MIC_PIN), diff --git a/sound/soc/amd/acp/acp-mach-common.c b/sound/soc/amd/acp/acp-mach-common.c index 4d99472c75ba..09f6c9a2c041 100644 --- a/sound/soc/amd/acp/acp-mach-common.c +++ b/sound/soc/amd/acp/acp-mach-common.c @@ -127,8 +127,13 @@ static int acp_card_rt5682_init(struct snd_soc_pcm_runtime *rtd) if (drvdata->hs_codec_id != RT5682) return -EINVAL; - drvdata->wclk = clk_get(component->dev, "rt5682-dai-wclk"); - drvdata->bclk = clk_get(component->dev, "rt5682-dai-bclk"); + drvdata->wclk = devm_clk_get(component->dev, "rt5682-dai-wclk"); + if (IS_ERR(drvdata->wclk)) + return PTR_ERR(drvdata->wclk); + + drvdata->bclk = devm_clk_get(component->dev, "rt5682-dai-bclk"); + if (IS_ERR(drvdata->bclk)) + return PTR_ERR(drvdata->bclk); ret = snd_soc_dapm_new_controls(dapm, rt5682_widgets, ARRAY_SIZE(rt5682_widgets)); @@ -370,8 +375,13 @@ static int acp_card_rt5682s_init(struct snd_soc_pcm_runtime *rtd) return -EINVAL; if (!drvdata->soc_mclk) { - drvdata->wclk = clk_get(component->dev, "rt5682-dai-wclk"); - drvdata->bclk = clk_get(component->dev, "rt5682-dai-bclk"); + drvdata->wclk = devm_clk_get(component->dev, "rt5682-dai-wclk"); + if (IS_ERR(drvdata->wclk)) + return PTR_ERR(drvdata->wclk); + + drvdata->bclk = devm_clk_get(component->dev, "rt5682-dai-bclk"); + if (IS_ERR(drvdata->bclk)) + return PTR_ERR(drvdata->bclk); } ret = snd_soc_dapm_new_controls(dapm, rt5682s_widgets, diff --git a/sound/soc/amd/acp3x-rt5682-max9836.c b/sound/soc/amd/acp3x-rt5682-max9836.c index 4ca1978020a9..d1eb6f12a183 100644 --- a/sound/soc/amd/acp3x-rt5682-max9836.c +++ b/sound/soc/amd/acp3x-rt5682-max9836.c @@ -94,8 +94,13 @@ static int acp3x_5682_init(struct snd_soc_pcm_runtime *rtd) return ret; } - rt5682_dai_wclk = clk_get(component->dev, "rt5682-dai-wclk"); - rt5682_dai_bclk = clk_get(component->dev, "rt5682-dai-bclk"); + rt5682_dai_wclk = devm_clk_get(component->dev, "rt5682-dai-wclk"); + if (IS_ERR(rt5682_dai_wclk)) + return PTR_ERR(rt5682_dai_wclk); + + rt5682_dai_bclk = devm_clk_get(component->dev, "rt5682-dai-bclk"); + if (IS_ERR(rt5682_dai_bclk)) + return PTR_ERR(rt5682_dai_bclk); ret = snd_soc_card_jack_new_pins(card, "Headset Jack", SND_JACK_HEADSET | diff --git a/sound/soc/codecs/rt1011.c b/sound/soc/codecs/rt1011.c index 9f34a6a35487..03f31d9d916e 100644 --- a/sound/soc/codecs/rt1011.c +++ b/sound/soc/codecs/rt1011.c @@ -1047,7 +1047,7 @@ static int rt1011_recv_spk_mode_put(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); - struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_to_dapm(kcontrol); + struct snd_soc_dapm_context *dapm = snd_soc_component_to_dapm(component); struct rt1011_priv *rt1011 = snd_soc_component_get_drvdata(component); diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index bdc02e85b089..9e5be0eaa77f 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -1038,11 +1038,15 @@ int graph_util_is_ports0(struct device_node *np) else port = np; - struct device_node *ports __free(device_node) = of_get_parent(port); - struct device_node *top __free(device_node) = of_get_parent(ports); - struct device_node *ports0 __free(device_node) = of_get_child_by_name(top, "ports"); + struct device_node *ports __free(device_node) = of_get_parent(port); + const char *at = strchr(kbasename(ports->full_name), '@'); - return ports0 == ports; + /* + * Since child iteration order may differ + * between a base DT and DT overlays, + * string match "ports" or "ports@0" in the node name instead. + */ + return !at || !strcmp(at, "@0"); } EXPORT_SYMBOL_GPL(graph_util_is_ports0); diff --git a/sound/soc/qcom/qdsp6/q6apm-dai.c b/sound/soc/qcom/qdsp6/q6apm-dai.c index de3bdac3e791..168c166c960d 100644 --- a/sound/soc/qcom/qdsp6/q6apm-dai.c +++ b/sound/soc/qcom/qdsp6/q6apm-dai.c @@ -838,6 +838,7 @@ static const struct snd_soc_component_driver q6apm_fe_dai_component = { .ack = q6apm_dai_ack, .compress_ops = &q6apm_dai_compress_ops, .use_dai_pcm_id = true, + .remove_order = SND_SOC_COMP_ORDER_EARLY, }; static int q6apm_dai_probe(struct platform_device *pdev) diff --git a/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c b/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c index 528756f1332b..5be37eeea329 100644 --- a/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c +++ b/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c @@ -278,6 +278,7 @@ static const struct snd_soc_component_driver q6apm_lpass_dai_component = { .of_xlate_dai_name = q6dsp_audio_ports_of_xlate_dai_name, .be_pcm_base = AUDIOREACH_BE_PCM_BASE, .use_dai_pcm_id = true, + .remove_order = SND_SOC_COMP_ORDER_FIRST, }; static int q6apm_lpass_dai_dev_probe(struct platform_device *pdev) diff --git a/sound/soc/qcom/qdsp6/q6apm.c b/sound/soc/qcom/qdsp6/q6apm.c index 44841fde3856..970b08c89bb3 100644 --- a/sound/soc/qcom/qdsp6/q6apm.c +++ b/sound/soc/qcom/qdsp6/q6apm.c @@ -715,6 +715,7 @@ static const struct snd_soc_component_driver q6apm_audio_component = { .name = APM_AUDIO_DRV_NAME, .probe = q6apm_audio_probe, .remove = q6apm_audio_remove, + .remove_order = SND_SOC_COMP_ORDER_LAST, }; static int apm_probe(gpr_device_t *gdev) diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index d0fffef65daf..573693e21780 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -462,8 +462,7 @@ static void soc_free_pcm_runtime(struct snd_soc_pcm_runtime *rtd) list_del(&rtd->list); - if (delayed_work_pending(&rtd->delayed_work)) - flush_delayed_work(&rtd->delayed_work); + flush_delayed_work(&rtd->delayed_work); snd_soc_pcm_component_free(rtd); /* @@ -1864,12 +1863,15 @@ static void cleanup_dmi_name(char *name) /* * Check if a DMI field is valid, i.e. not containing any string - * in the black list. + * in the black list and not the empty string. */ static int is_dmi_valid(const char *field) { int i = 0; + if (!field[0]) + return 0; + while (dmi_blacklist[i]) { if (strstr(field, dmi_blacklist[i])) return 0; @@ -2122,6 +2124,9 @@ static void soc_cleanup_card_resources(struct snd_soc_card *card) for_each_card_rtds(card, rtd) if (rtd->initialized) snd_soc_link_exit(rtd); + /* flush delayed work before removing DAIs and DAPM widgets */ + snd_soc_flush_all_delayed_work(card); + /* remove and free each DAI */ soc_remove_link_dais(card); soc_remove_link_components(card); diff --git a/sound/soc/tegra/tegra_audio_graph_card.c b/sound/soc/tegra/tegra_audio_graph_card.c index 94b5ab77649b..ea10e6e8a9fe 100644 --- a/sound/soc/tegra/tegra_audio_graph_card.c +++ b/sound/soc/tegra/tegra_audio_graph_card.c @@ -231,6 +231,15 @@ static const struct tegra_audio_cdata tegra186_data = { .plla_out0_rates[x11_RATE] = 45158400, }; +static const struct tegra_audio_cdata tegra238_data = { + /* PLLA */ + .plla_rates[x8_RATE] = 1277952000, + .plla_rates[x11_RATE] = 1264435200, + /* PLLA_OUT0 */ + .plla_out0_rates[x8_RATE] = 49152000, + .plla_out0_rates[x11_RATE] = 45158400, +}; + static const struct tegra_audio_cdata tegra264_data = { /* PLLA1 */ .plla_rates[x8_RATE] = 983040000, @@ -245,6 +254,8 @@ static const struct of_device_id graph_of_tegra_match[] = { .data = &tegra210_data }, { .compatible = "nvidia,tegra186-audio-graph-card", .data = &tegra186_data }, + { .compatible = "nvidia,tegra238-audio-graph-card", + .data = &tegra238_data }, { .compatible = "nvidia,tegra264-audio-graph-card", .data = &tegra264_data }, {}, diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c index ef3150581eab..fd1fb668929a 100644 --- a/sound/usb/mixer_scarlett2.c +++ b/sound/usb/mixer_scarlett2.c @@ -8251,6 +8251,8 @@ static int scarlett2_find_fc_interface(struct usb_device *dev, if (desc->bInterfaceClass != 255) continue; + if (desc->bNumEndpoints < 1) + continue; epd = get_endpoint(intf->altsetting, 0); private->bInterfaceNumber = desc->bInterfaceNumber; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index d54a1a44a69b..049a94079f9e 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2243,6 +2243,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_IFACE_DELAY | QUIRK_FLAG_FORCE_IFACE_RESET), DEVICE_FLG(0x0661, 0x0883, /* iBasso DC04 Ultra */ QUIRK_FLAG_DSD_RAW), + DEVICE_FLG(0x0666, 0x0880, /* SPACETOUCH USB Audio */ + QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY), DEVICE_FLG(0x06f8, 0xb000, /* Hercules DJ Console (Windows Edition) */ QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x06f8, 0xd002, /* Hercules DJ Console (Macintosh Edition) */ diff --git a/tools/arch/x86/include/asm/amd/ibs.h b/tools/arch/x86/include/asm/amd/ibs.h index cbce54fec7b9..41e8abd72c8b 100644 --- a/tools/arch/x86/include/asm/amd/ibs.h +++ b/tools/arch/x86/include/asm/amd/ibs.h @@ -110,7 +110,7 @@ union ibs_op_data3 { __u64 ld_op:1, /* 0: load op */ st_op:1, /* 1: store op */ dc_l1tlb_miss:1, /* 2: data cache L1TLB miss */ - dc_l2tlb_miss:1, /* 3: data cache L2TLB hit in 2M page */ + dc_l2tlb_miss:1, /* 3: data cache L2TLB miss in 2M page */ dc_l1tlb_hit_2m:1, /* 4: data cache L1TLB hit in 2M page */ dc_l1tlb_hit_1g:1, /* 5: data cache L1TLB hit in 1G page */ dc_l2tlb_hit_2m:1, /* 6: data cache L2TLB hit in 2M page */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index c3b53beb1300..dbe104df339b 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -84,7 +84,7 @@ #define X86_FEATURE_PEBS ( 3*32+12) /* "pebs" Precise-Event Based Sampling */ #define X86_FEATURE_BTS ( 3*32+13) /* "bts" Branch Trace Store */ #define X86_FEATURE_SYSCALL32 ( 3*32+14) /* syscall in IA32 userspace */ -#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* sysenter in IA32 userspace */ +#define X86_FEATURE_SYSFAST32 ( 3*32+15) /* sysenter/syscall in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* "rep_good" REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* "amd_lbr_v2" AMD Last Branch Record Extension Version 2 */ #define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* Clear CPU buffers using VERW */ @@ -326,6 +326,7 @@ #define X86_FEATURE_AMX_FP16 (12*32+21) /* AMX fp16 Support */ #define X86_FEATURE_AVX_IFMA (12*32+23) /* Support for VPMADD52[H,L]UQ */ #define X86_FEATURE_LAM (12*32+26) /* "lam" Linear Address Masking */ +#define X86_FEATURE_MOVRS (12*32+31) /* MOVRS instructions */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* "clzero" CLZERO instruction */ @@ -472,6 +473,7 @@ #define X86_FEATURE_GP_ON_USER_CPUID (20*32+17) /* User CPUID faulting */ #define X86_FEATURE_PREFETCHI (20*32+20) /* Prefetch Data/Instruction to Cache Level */ +#define X86_FEATURE_ERAPS (20*32+24) /* Enhanced Return Address Predictor Security */ #define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */ #define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */ #define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 43adc38d31d5..da5275d8eda6 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -263,6 +263,11 @@ #define MSR_SNOOP_RSP_0 0x00001328 #define MSR_SNOOP_RSP_1 0x00001329 +#define MSR_OMR_0 0x000003e0 +#define MSR_OMR_1 0x000003e1 +#define MSR_OMR_2 0x000003e2 +#define MSR_OMR_3 0x000003e3 + #define MSR_LBR_SELECT 0x000001c8 #define MSR_LBR_TOS 0x000001c9 @@ -1219,6 +1224,7 @@ #define MSR_CORE_PERF_GLOBAL_STATUS 0x0000038e #define MSR_CORE_PERF_GLOBAL_CTRL 0x0000038f #define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x00000390 +#define MSR_CORE_PERF_GLOBAL_STATUS_SET 0x00000391 #define MSR_PERF_METRICS 0x00000329 diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 7ceff6583652..846a63215ce1 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -503,6 +503,7 @@ struct kvm_sync_regs { #define KVM_X86_GRP_SEV 1 # define KVM_X86_SEV_VMSA_FEATURES 0 # define KVM_X86_SNP_POLICY_BITS 1 +# define KVM_X86_SEV_SNP_REQ_CERTS 2 struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; @@ -743,6 +744,7 @@ enum sev_cmd_id { KVM_SEV_SNP_LAUNCH_START = 100, KVM_SEV_SNP_LAUNCH_UPDATE, KVM_SEV_SNP_LAUNCH_FINISH, + KVM_SEV_SNP_ENABLE_REQ_CERTS, KVM_SEV_NR_MAX, }; @@ -914,8 +916,10 @@ struct kvm_sev_snp_launch_finish { __u64 pad1[4]; }; -#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) -#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) +#define KVM_X2APIC_API_USE_32BIT_IDS _BITULL(0) +#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK _BITULL(1) +#define KVM_X2APIC_ENABLE_SUPPRESS_EOI_BROADCAST _BITULL(2) +#define KVM_X2APIC_DISABLE_SUPPRESS_EOI_BROADCAST _BITULL(3) struct kvm_hyperv_eventfd { __u32 conn_id; diff --git a/tools/bootconfig/samples/bad-non-closed-brace.bconf b/tools/bootconfig/samples/bad-non-closed-brace.bconf new file mode 100644 index 000000000000..6ed9f3363dde --- /dev/null +++ b/tools/bootconfig/samples/bad-non-closed-brace.bconf @@ -0,0 +1,4 @@ +foo { + bar { + buz + } diff --git a/tools/bootconfig/samples/bad-over-max-brace.bconf b/tools/bootconfig/samples/bad-over-max-brace.bconf new file mode 100644 index 000000000000..74b5dc9e21dc --- /dev/null +++ b/tools/bootconfig/samples/bad-over-max-brace.bconf @@ -0,0 +1,19 @@ +key1 { +key2 { +key3 { +key4 { +key5 { +key6 { +key7 { +key8 { +key9 { +key10 { +key11 { +key12 { +key13 { +key14 { +key15 { +key16 { +key17 { +}}}}}}}}}}}}}}}}} + diff --git a/tools/bootconfig/samples/exp-good-nested-brace.bconf b/tools/bootconfig/samples/exp-good-nested-brace.bconf new file mode 100644 index 000000000000..19e0f51b4553 --- /dev/null +++ b/tools/bootconfig/samples/exp-good-nested-brace.bconf @@ -0,0 +1 @@ +key1.key2.key3.key4.key5.key6.key7.key8.key9.key10.key11.key12.key13.key14.key15.key16; diff --git a/tools/bootconfig/samples/good-nested-brace.bconf b/tools/bootconfig/samples/good-nested-brace.bconf new file mode 100644 index 000000000000..980d094f296e --- /dev/null +++ b/tools/bootconfig/samples/good-nested-brace.bconf @@ -0,0 +1,18 @@ +key1 { +key2 { +key3 { +key4 { +key5 { +key6 { +key7 { +key8 { +key9 { +key10 { +key11 { +key12 { +key13 { +key14 { +key15 { +key16 { +}}}}}}}}}}}}}}}} + diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh index be9bd18b1d56..fc69f815ce4a 100755 --- a/tools/bootconfig/test-bootconfig.sh +++ b/tools/bootconfig/test-bootconfig.sh @@ -171,6 +171,15 @@ $BOOTCONF $INITRD > $OUTFILE xfail grep -q 'val[[:space:]]' $OUTFILE xpass grep -q 'val2[[:space:]]' $OUTFILE +echo "Showing correct line:column of no closing brace" +cat > $TEMPCONF << EOF +foo { +bar { +} +EOF +$BOOTCONF -a $TEMPCONF $INITRD 2> $OUTFILE +xpass grep -q "1:1" $OUTFILE + echo "=== expected failure cases ===" for i in samples/bad-* ; do xfail $BOOTCONF -a $i $INITRD diff --git a/tools/build/Build.include b/tools/build/Build.include index e45b2eb0d24a..cd0baa7a168d 100644 --- a/tools/build/Build.include +++ b/tools/build/Build.include @@ -99,6 +99,15 @@ c_flags = $(filter-out $(CFLAGS_REMOVE_$(obj)), $(c_flags_2)) cxx_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXXFLAGS_$(basetarget).o) $(CXXFLAGS_$(obj)) ### +# Rust flags to be used on rule definition, includes: +# - global $(RUST_FLAGS) +# - per target Rust flags +# - per object Rust flags +rust_flags_1 = $(RUST_FLAGS) $(RUST_FLAGS_$(basetarget).o) $(RUST_FLAGS_$(obj)) +rust_flags_2 = $(filter-out $(RUST_FLAGS_REMOVE_$(basetarget).o), $(rust_flags_1)) +rust_flags = $(filter-out $(RUST_FLAGS_REMOVE_$(obj)), $(rust_flags_2)) + +### ## HOSTCC C flags host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj)) diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build index 60e65870eae1..ad69efdd4e85 100644 --- a/tools/build/Makefile.build +++ b/tools/build/Makefile.build @@ -70,11 +70,13 @@ quiet_cmd_gen = GEN $@ # If there's nothing to link, create empty $@ object. quiet_cmd_ld_multi = LD $@ cmd_ld_multi = $(if $(strip $(obj-y)),\ - $(LD) -r -o $@ $(filter $(obj-y),$^),rm -f $@; $(AR) rcs $@) + printf "$(objprefix)%s " $(patsubst $(objprefix)%,%,$(filter $(obj-y),$^)) | \ + xargs $(LD) -r -o $@,rm -f $@; $(AR) rcs $@) quiet_cmd_host_ld_multi = HOSTLD $@ cmd_host_ld_multi = $(if $(strip $(obj-y)),\ - $(HOSTLD) -r -o $@ $(filter $(obj-y),$^),rm -f $@; $(HOSTAR) rcs $@) + printf "$(objprefix)%s " $(patsubst $(objprefix)%,%,$(filter $(obj-y),$^)) | \ + xargs $(HOSTLD) -r -o $@,rm -f $@; $(HOSTAR) rcs $@) rust_common_cmd = \ $(RUSTC) $(rust_flags) \ diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index 89b0ac0014b0..2e179abe472a 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -22,30 +22,6 @@ #define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) (0x10 + (cpu * 2)) /* - * Below are the definition of bit offsets for perf option, and works as - * arbitrary values for all ETM versions. - * - * Most of them are orignally from ETMv3.5/PTM's ETMCR config, therefore, - * ETMv3.5/PTM doesn't define ETMCR config bits with prefix "ETM3_" and - * directly use below macros as config bits. - */ -#define ETM_OPT_BRANCH_BROADCAST 8 -#define ETM_OPT_CYCACC 12 -#define ETM_OPT_CTXTID 14 -#define ETM_OPT_CTXTID2 15 -#define ETM_OPT_TS 28 -#define ETM_OPT_RETSTK 29 - -/* ETMv4 CONFIGR programming bits for the ETM OPTs */ -#define ETM4_CFG_BIT_BB 3 -#define ETM4_CFG_BIT_CYCACC 4 -#define ETM4_CFG_BIT_CTXTID 6 -#define ETM4_CFG_BIT_VMID 7 -#define ETM4_CFG_BIT_TS 11 -#define ETM4_CFG_BIT_RETSTK 12 -#define ETM4_CFG_BIT_VMID_OPT 15 - -/* * Interpretation of the PERF_RECORD_AUX_OUTPUT_HW_ID payload. * Used to associate a CPU with the CoreSight Trace ID. * [07:00] - Trace ID - uses 8 bits to make value easy to read in file. diff --git a/tools/include/linux/gfp_types.h b/tools/include/linux/gfp_types.h index 3de43b12209e..6c75df30a281 100644 --- a/tools/include/linux/gfp_types.h +++ b/tools/include/linux/gfp_types.h @@ -139,6 +139,8 @@ enum { * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. * * %__GFP_NO_OBJ_EXT causes slab allocation to have no object extension. + * mark_obj_codetag_empty() should be called upon freeing for objects allocated + * with this flag to indicate that their NULL tags are expected and normal. */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) @@ -309,8 +311,10 @@ enum { * * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower * watermark is applied to allow access to "atomic reserves". - * The current implementation doesn't support NMI and few other strict - * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT. + * The current implementation doesn't support NMI, nor contexts that disable + * preemption under PREEMPT_RT. This includes raw_spin_lock() and plain + * preempt_disable() - see "Memory allocation" in + * Documentation/core-api/real-time/differences.rst for more info. * * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim. @@ -321,6 +325,7 @@ enum { * %GFP_NOWAIT is for kernel allocations that should not stall for direct * reclaim, start physical IO or use any filesystem callback. It is very * likely to fail to allocate memory, even for very small allocations. + * The same restrictions on calling contexts apply as for %GFP_ATOMIC. * * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages * that do not require the starting of any physical IO. diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 942370b3f5d2..a627acc8fb5f 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -860,8 +860,11 @@ __SYSCALL(__NR_file_setattr, sys_file_setattr) #define __NR_listns 470 __SYSCALL(__NR_listns, sys_listns) +#define __NR_rseq_slice_yield 471 +__SYSCALL(__NR_rseq_slice_yield, sys_rseq_slice_yield) + #undef __NR_syscalls -#define __NR_syscalls 471 +#define __NR_syscalls 472 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index dddb781b0507..65500f5db379 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -135,6 +135,12 @@ struct kvm_xen_exit { } u; }; +struct kvm_exit_snp_req_certs { + __u64 gpa; + __u64 npages; + __u64 ret; +}; + #define KVM_S390_GET_SKEYS_NONE 1 #define KVM_S390_SKEYS_MAX 1048576 @@ -180,6 +186,8 @@ struct kvm_xen_exit { #define KVM_EXIT_MEMORY_FAULT 39 #define KVM_EXIT_TDX 40 #define KVM_EXIT_ARM_SEA 41 +#define KVM_EXIT_ARM_LDST64B 42 +#define KVM_EXIT_SNP_REQ_CERTS 43 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -402,7 +410,7 @@ struct kvm_run { } eoi; /* KVM_EXIT_HYPERV */ struct kvm_hyperv_exit hyperv; - /* KVM_EXIT_ARM_NISV */ + /* KVM_EXIT_ARM_NISV / KVM_EXIT_ARM_LDST64B */ struct { __u64 esr_iss; __u64 fault_ipa; @@ -482,6 +490,8 @@ struct kvm_run { __u64 gva; __u64 gpa; } arm_sea; + /* KVM_EXIT_SNP_REQ_CERTS */ + struct kvm_exit_snp_req_certs snp_req_certs; /* Fix the size of the union. */ char padding[256]; }; @@ -974,6 +984,7 @@ struct kvm_enable_cap { #define KVM_CAP_GUEST_MEMFD_FLAGS 244 #define KVM_CAP_ARM_SEA_TO_USER 245 #define KVM_CAP_S390_USER_OPEREXEC 246 +#define KVM_CAP_S390_KEYOP 247 struct kvm_irq_routing_irqchip { __u32 irqchip; @@ -1219,6 +1230,16 @@ struct kvm_vfio_spapr_tce { __s32 tablefd; }; +#define KVM_S390_KEYOP_ISKE 0x01 +#define KVM_S390_KEYOP_RRBE 0x02 +#define KVM_S390_KEYOP_SSKE 0x03 +struct kvm_s390_keyop { + __u64 guest_addr; + __u8 key; + __u8 operation; + __u8 pad[6]; +}; + /* * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns * a vcpu fd. @@ -1238,6 +1259,7 @@ struct kvm_vfio_spapr_tce { #define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping) #define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping) #define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long) +#define KVM_S390_KEYOP _IOWR(KVMIO, 0x53, struct kvm_s390_keyop) /* Device model IOC */ #define KVM_CREATE_IRQCHIP _IO(KVMIO, 0x60) diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 76e9d0664d0c..fd10aa8d697f 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1396,7 +1396,7 @@ union perf_mem_data_src { #define PERF_MEM_LVLNUM_L4 0x0004 /* L4 */ #define PERF_MEM_LVLNUM_L2_MHB 0x0005 /* L2 Miss Handling Buffer */ #define PERF_MEM_LVLNUM_MSC 0x0006 /* Memory-side Cache */ -#define PERF_MEM_LVLNUM_L0 0x0007 /* L0 */ +#define PERF_MEM_LVLNUM_L0 0x0007 /* L0 */ #define PERF_MEM_LVLNUM_UNC 0x0008 /* Uncached */ #define PERF_MEM_LVLNUM_CXL 0x0009 /* CXL */ #define PERF_MEM_LVLNUM_IO 0x000a /* I/O */ diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index 76bcd4e85de3..b71d1886022e 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -13,7 +13,7 @@ endif ifeq ($(ARCH_HAS_KLP),y) HAVE_XXHASH = $(shell printf "$(pound)include <xxhash.h>\nXXH3_state_t *state;int main() {}" | \ - $(HOSTCC) -xc - -o /dev/null -lxxhash 2> /dev/null && echo y || echo n) + $(HOSTCC) $(HOSTCFLAGS) -xc - -o /dev/null -lxxhash 2> /dev/null && echo y || echo n) ifeq ($(HAVE_XXHASH),y) BUILD_KLP := y LIBXXHASH_CFLAGS := $(shell $(HOSTPKG_CONFIG) libxxhash --cflags 2>/dev/null) \ diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 73bfea220d1b..c5817829cdfa 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -395,52 +395,36 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec if (!rex_w) break; - if (modrm_reg == CFI_SP) { - - if (mod_is_reg()) { - /* mov %rsp, reg */ - ADD_OP(op) { - op->src.type = OP_SRC_REG; - op->src.reg = CFI_SP; - op->dest.type = OP_DEST_REG; - op->dest.reg = modrm_rm; - } - break; - - } else { - /* skip RIP relative displacement */ - if (is_RIP()) - break; - - /* skip nontrivial SIB */ - if (have_SIB()) { - modrm_rm = sib_base; - if (sib_index != CFI_SP) - break; - } - - /* mov %rsp, disp(%reg) */ - ADD_OP(op) { - op->src.type = OP_SRC_REG; - op->src.reg = CFI_SP; - op->dest.type = OP_DEST_REG_INDIRECT; - op->dest.reg = modrm_rm; - op->dest.offset = ins.displacement.value; - } - break; + if (mod_is_reg()) { + /* mov reg, reg */ + ADD_OP(op) { + op->src.type = OP_SRC_REG; + op->src.reg = modrm_reg; + op->dest.type = OP_DEST_REG; + op->dest.reg = modrm_rm; } - break; } - if (rm_is_reg(CFI_SP)) { + /* skip RIP relative displacement */ + if (is_RIP()) + break; - /* mov reg, %rsp */ + /* skip nontrivial SIB */ + if (have_SIB()) { + modrm_rm = sib_base; + if (sib_index != CFI_SP) + break; + } + + /* mov %rsp, disp(%reg) */ + if (modrm_reg == CFI_SP) { ADD_OP(op) { op->src.type = OP_SRC_REG; - op->src.reg = modrm_reg; - op->dest.type = OP_DEST_REG; - op->dest.reg = CFI_SP; + op->src.reg = CFI_SP; + op->dest.type = OP_DEST_REG_INDIRECT; + op->dest.reg = modrm_rm; + op->dest.offset = ins.displacement.value; } break; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index a30379e4ff97..91b3ff4803cf 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3000,6 +3000,20 @@ static int update_cfi_state(struct instruction *insn, cfi->stack_size += 8; } + else if (cfi->vals[op->src.reg].base == CFI_CFA) { + /* + * Clang RSP musical chairs: + * + * mov %rsp, %rdx [handled above] + * ... + * mov %rdx, %rbx [handled here] + * ... + * mov %rbx, %rsp [handled above] + */ + cfi->vals[op->dest.reg].base = CFI_CFA; + cfi->vals[op->dest.reg].offset = cfi->vals[op->src.reg].offset; + } + break; @@ -3734,7 +3748,7 @@ static void checksum_update_insn(struct objtool_file *file, struct symbol *func, static int validate_branch(struct objtool_file *file, struct symbol *func, struct instruction *insn, struct insn_state state); static int do_validate_branch(struct objtool_file *file, struct symbol *func, - struct instruction *insn, struct insn_state state); + struct instruction *insn, struct insn_state *state); static int validate_insn(struct objtool_file *file, struct symbol *func, struct instruction *insn, struct insn_state *statep, @@ -3999,7 +4013,7 @@ static int validate_insn(struct objtool_file *file, struct symbol *func, * tools/objtool/Documentation/objtool.txt. */ static int do_validate_branch(struct objtool_file *file, struct symbol *func, - struct instruction *insn, struct insn_state state) + struct instruction *insn, struct insn_state *state) { struct instruction *next_insn, *prev_insn = NULL; bool dead_end; @@ -4030,7 +4044,7 @@ static int do_validate_branch(struct objtool_file *file, struct symbol *func, return 1; } - ret = validate_insn(file, func, insn, &state, prev_insn, next_insn, + ret = validate_insn(file, func, insn, state, prev_insn, next_insn, &dead_end); if (!insn->trace) { @@ -4041,7 +4055,7 @@ static int do_validate_branch(struct objtool_file *file, struct symbol *func, } if (!dead_end && !next_insn) { - if (state.cfi.cfa.base == CFI_UNDEFINED) + if (state->cfi.cfa.base == CFI_UNDEFINED) return 0; if (file->ignore_unreachables) return 0; @@ -4066,7 +4080,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, int ret; trace_depth_inc(); - ret = do_validate_branch(file, func, insn, state); + ret = do_validate_branch(file, func, insn, &state); trace_depth_dec(); return ret; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 2c02c7b49265..3da90686350d 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -1375,7 +1375,7 @@ void *elf_add_data(struct elf *elf, struct section *sec, const void *data, size_ memcpy(sec->data->d_buf, data, size); sec->data->d_size = size; - sec->data->d_align = 1; + sec->data->d_align = sec->sh.sh_addralign; offset = ALIGN(sec->sh.sh_size, sec->sh.sh_addralign); sec->sh.sh_size = offset + size; diff --git a/tools/objtool/include/objtool/warn.h b/tools/objtool/include/objtool/warn.h index 2b27b54096b8..fa8b7d292e83 100644 --- a/tools/objtool/include/objtool/warn.h +++ b/tools/objtool/include/objtool/warn.h @@ -107,7 +107,7 @@ static inline char *offstr(struct section *sec, unsigned long offset) #define ERROR_ELF(format, ...) __WARN_ELF(ERROR_STR, format, ##__VA_ARGS__) #define ERROR_GLIBC(format, ...) __WARN_GLIBC(ERROR_STR, format, ##__VA_ARGS__) #define ERROR_FUNC(sec, offset, format, ...) __WARN_FUNC(ERROR_STR, sec, offset, format, ##__VA_ARGS__) -#define ERROR_INSN(insn, format, ...) WARN_FUNC(insn->sec, insn->offset, format, ##__VA_ARGS__) +#define ERROR_INSN(insn, format, ...) ERROR_FUNC(insn->sec, insn->offset, format, ##__VA_ARGS__) extern bool debug; extern int indent; diff --git a/tools/objtool/klp-diff.c b/tools/objtool/klp-diff.c index 9f1f4011eb9c..a3198a63c2f0 100644 --- a/tools/objtool/klp-diff.c +++ b/tools/objtool/klp-diff.c @@ -1334,25 +1334,25 @@ static bool should_keep_special_sym(struct elf *elf, struct symbol *sym) * be applied after static branch/call init, resulting in code corruption. * * Validate a special section entry to avoid that. Note that an inert - * tracepoint is harmless enough, in that case just skip the entry and print a - * warning. Otherwise, return an error. + * tracepoint or pr_debug() is harmless enough, in that case just skip the + * entry and print a warning. Otherwise, return an error. * - * This is only a temporary limitation which will be fixed when livepatch adds - * support for submodules: fully self-contained modules which are embedded in - * the top-level livepatch module's data and which can be loaded on demand when - * their corresponding to-be-patched module gets loaded. Then klp relocs can - * be retired. + * TODO: This is only a temporary limitation which will be fixed when livepatch + * adds support for submodules: fully self-contained modules which are embedded + * in the top-level livepatch module's data and which can be loaded on demand + * when their corresponding to-be-patched module gets loaded. Then klp relocs + * can be retired. * * Return: * -1: error: validation failed - * 1: warning: tracepoint skipped + * 1: warning: disabled tracepoint or pr_debug() * 0: success */ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym) { bool static_branch = !strcmp(sym->sec->name, "__jump_table"); bool static_call = !strcmp(sym->sec->name, ".static_call_sites"); - struct symbol *code_sym = NULL; + const char *code_sym = NULL; unsigned long code_offset = 0; struct reloc *reloc; int ret = 0; @@ -1364,12 +1364,15 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym const char *sym_modname; struct export *export; + if (convert_reloc_sym(e->patched, reloc)) + continue; + /* Static branch/call keys are always STT_OBJECT */ if (reloc->sym->type != STT_OBJECT) { /* Save code location which can be printed below */ if (reloc->sym->type == STT_FUNC && !code_sym) { - code_sym = reloc->sym; + code_sym = reloc->sym->name; code_offset = reloc_addend(reloc); } @@ -1392,16 +1395,26 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym if (!strcmp(sym_modname, "vmlinux")) continue; + if (!code_sym) + code_sym = "<unknown>"; + if (static_branch) { if (strstarts(reloc->sym->name, "__tracepoint_")) { WARN("%s: disabling unsupported tracepoint %s", - code_sym->name, reloc->sym->name + 13); + code_sym, reloc->sym->name + 13); + ret = 1; + continue; + } + + if (strstr(reloc->sym->name, "__UNIQUE_ID_ddebug_")) { + WARN("%s: disabling unsupported pr_debug()", + code_sym); ret = 1; continue; } ERROR("%s+0x%lx: unsupported static branch key %s. Use static_key_enabled() instead", - code_sym->name, code_offset, reloc->sym->name); + code_sym, code_offset, reloc->sym->name); return -1; } @@ -1412,7 +1425,7 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym } ERROR("%s()+0x%lx: unsupported static call key %s. Use KLP_STATIC_CALL() instead", - code_sym->name, code_offset, reloc->sym->name); + code_sym, code_offset, reloc->sym->name); return -1; } diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index a8dc72cfe48e..15fbba9f4ca8 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -1163,6 +1163,24 @@ ifndef NO_RUST CFLAGS += -DHAVE_RUST_SUPPORT $(call detected,CONFIG_RUST_SUPPORT) endif + + ifneq ($(CROSS_COMPILE),) + RUST_TARGET_FLAGS_arm := arm-unknown-linux-gnueabi + RUST_TARGET_FLAGS_arm64 := aarch64-unknown-linux-gnu + RUST_TARGET_FLAGS_m68k := m68k-unknown-linux-gnu + RUST_TARGET_FLAGS_mips := mipsel-unknown-linux-gnu + RUST_TARGET_FLAGS_powerpc := powerpc64le-unknown-linux-gnu + RUST_TARGET_FLAGS_riscv := riscv64gc-unknown-linux-gnu + RUST_TARGET_FLAGS_s390 := s390x-unknown-linux-gnu + RUST_TARGET_FLAGS_x86 := x86_64-unknown-linux-gnu + RUST_TARGET_FLAGS_x86_64 := x86_64-unknown-linux-gnu + + ifeq ($(RUST_TARGET_FLAGS_$(ARCH)),) + $(error Unknown rust cross compilation architecture $(ARCH)) + endif + + RUST_FLAGS += --target=$(RUST_TARGET_FLAGS_$(ARCH)) + endif endif # Among the variables below, these: diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 11b63bafdb23..f7b936deeaa2 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -274,7 +274,7 @@ ifeq ($(PYLINT),1) PYLINT := $(shell which pylint 2> /dev/null) endif -export srctree OUTPUT RM CC CXX RUSTC LD AR CFLAGS CXXFLAGS V BISON FLEX AWK +export srctree OUTPUT RM CC CXX RUSTC LD AR CFLAGS CXXFLAGS RUST_FLAGS V BISON FLEX AWK export HOSTCC HOSTLD HOSTAR HOSTCFLAGS SHELLCHECK MYPY PYLINT include $(srctree)/tools/build/Makefile.include diff --git a/tools/perf/arch/arm/entry/syscalls/syscall.tbl b/tools/perf/arch/arm/entry/syscalls/syscall.tbl index fd09afae72a2..94351e22bfcf 100644 --- a/tools/perf/arch/arm/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/arm/entry/syscalls/syscall.tbl @@ -485,3 +485,4 @@ 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr 470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index dc3f4e86b075..4418d21708d6 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -68,20 +68,6 @@ static const char * const metadata_ete_ro[] = { enum cs_etm_version { CS_NOT_PRESENT, CS_ETMV3, CS_ETMV4, CS_ETE }; -/* ETMv4 CONFIGR register bits */ -#define TRCCONFIGR_BB BIT(3) -#define TRCCONFIGR_CCI BIT(4) -#define TRCCONFIGR_CID BIT(6) -#define TRCCONFIGR_VMID BIT(7) -#define TRCCONFIGR_TS BIT(11) -#define TRCCONFIGR_RS BIT(12) -#define TRCCONFIGR_VMIDOPT BIT(15) - -/* ETMv3 ETMCR register bits */ -#define ETMCR_CYC_ACC BIT(12) -#define ETMCR_TIMESTAMP_EN BIT(28) -#define ETMCR_RETURN_STACK BIT(29) - static bool cs_etm_is_ete(struct perf_pmu *cs_etm_pmu, struct perf_cpu cpu); static int cs_etm_get_ro(struct perf_pmu *pmu, struct perf_cpu cpu, const char *path, __u64 *val); static bool cs_etm_pmu_path_exists(struct perf_pmu *pmu, struct perf_cpu cpu, const char *path); diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index 9b92bddf06b5..630aab9e5425 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -385,3 +385,4 @@ 468 n64 file_getattr sys_file_getattr 469 n64 file_setattr sys_file_setattr 470 n64 listns sys_listns +471 n64 rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index ec4458cdb97b..4fcc7c58a105 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -561,3 +561,4 @@ 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr 470 common listns sys_listns +471 nospu rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 5863787ab036..09a7ef04d979 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -3,473 +3,398 @@ # System call table for s390 # # Format: +# <nr> <abi> <syscall> <entry> # -# <nr> <abi> <syscall> <entry-64bit> <compat-entry> -# -# where <abi> can be common, 64, or 32 +# <abi> is always common. -1 common exit sys_exit sys_exit -2 common fork sys_fork sys_fork -3 common read sys_read compat_sys_s390_read -4 common write sys_write compat_sys_s390_write -5 common open sys_open compat_sys_open -6 common close sys_close sys_close -7 common restart_syscall sys_restart_syscall sys_restart_syscall -8 common creat sys_creat sys_creat -9 common link sys_link sys_link -10 common unlink sys_unlink sys_unlink -11 common execve sys_execve compat_sys_execve -12 common chdir sys_chdir sys_chdir -13 32 time - sys_time32 -14 common mknod sys_mknod sys_mknod -15 common chmod sys_chmod sys_chmod -16 32 lchown - sys_lchown16 -19 common lseek sys_lseek compat_sys_lseek -20 common getpid sys_getpid sys_getpid -21 common mount sys_mount sys_mount -22 common umount sys_oldumount sys_oldumount -23 32 setuid - sys_setuid16 -24 32 getuid - sys_getuid16 -25 32 stime - sys_stime32 -26 common ptrace sys_ptrace compat_sys_ptrace -27 common alarm sys_alarm sys_alarm -29 common pause sys_pause sys_pause -30 common utime sys_utime sys_utime32 -33 common access sys_access sys_access -34 common nice sys_nice sys_nice -36 common sync sys_sync sys_sync -37 common kill sys_kill sys_kill -38 common rename sys_rename sys_rename -39 common mkdir sys_mkdir sys_mkdir -40 common rmdir sys_rmdir sys_rmdir -41 common dup sys_dup sys_dup -42 common pipe sys_pipe sys_pipe -43 common times sys_times compat_sys_times -45 common brk sys_brk sys_brk -46 32 setgid - sys_setgid16 -47 32 getgid - sys_getgid16 -48 common signal sys_signal sys_signal -49 32 geteuid - sys_geteuid16 -50 32 getegid - sys_getegid16 -51 common acct sys_acct sys_acct -52 common umount2 sys_umount sys_umount -54 common ioctl sys_ioctl compat_sys_ioctl -55 common fcntl sys_fcntl compat_sys_fcntl -57 common setpgid sys_setpgid sys_setpgid -60 common umask sys_umask sys_umask -61 common chroot sys_chroot sys_chroot -62 common ustat sys_ustat compat_sys_ustat -63 common dup2 sys_dup2 sys_dup2 -64 common getppid sys_getppid sys_getppid -65 common getpgrp sys_getpgrp sys_getpgrp -66 common setsid sys_setsid sys_setsid -67 common sigaction sys_sigaction compat_sys_sigaction -70 32 setreuid - sys_setreuid16 -71 32 setregid - sys_setregid16 -72 common sigsuspend sys_sigsuspend sys_sigsuspend -73 common sigpending sys_sigpending compat_sys_sigpending -74 common sethostname sys_sethostname sys_sethostname -75 common setrlimit sys_setrlimit compat_sys_setrlimit -76 32 getrlimit - compat_sys_old_getrlimit -77 common getrusage sys_getrusage compat_sys_getrusage -78 common gettimeofday sys_gettimeofday compat_sys_gettimeofday -79 common settimeofday sys_settimeofday compat_sys_settimeofday -80 32 getgroups - sys_getgroups16 -81 32 setgroups - sys_setgroups16 -83 common symlink sys_symlink sys_symlink -85 common readlink sys_readlink sys_readlink -86 common uselib sys_uselib sys_uselib -87 common swapon sys_swapon sys_swapon -88 common reboot sys_reboot sys_reboot -89 common readdir - compat_sys_old_readdir -90 common mmap sys_old_mmap compat_sys_s390_old_mmap -91 common munmap sys_munmap sys_munmap -92 common truncate sys_truncate compat_sys_truncate -93 common ftruncate sys_ftruncate compat_sys_ftruncate -94 common fchmod sys_fchmod sys_fchmod -95 32 fchown - sys_fchown16 -96 common getpriority sys_getpriority sys_getpriority -97 common setpriority sys_setpriority sys_setpriority -99 common statfs sys_statfs compat_sys_statfs -100 common fstatfs sys_fstatfs compat_sys_fstatfs -101 32 ioperm - - -102 common socketcall sys_socketcall compat_sys_socketcall -103 common syslog sys_syslog sys_syslog -104 common setitimer sys_setitimer compat_sys_setitimer -105 common getitimer sys_getitimer compat_sys_getitimer -106 common stat sys_newstat compat_sys_newstat -107 common lstat sys_newlstat compat_sys_newlstat -108 common fstat sys_newfstat compat_sys_newfstat -110 common lookup_dcookie - - -111 common vhangup sys_vhangup sys_vhangup -112 common idle - - -114 common wait4 sys_wait4 compat_sys_wait4 -115 common swapoff sys_swapoff sys_swapoff -116 common sysinfo sys_sysinfo compat_sys_sysinfo -117 common ipc sys_s390_ipc compat_sys_s390_ipc -118 common fsync sys_fsync sys_fsync -119 common sigreturn sys_sigreturn compat_sys_sigreturn -120 common clone sys_clone sys_clone -121 common setdomainname sys_setdomainname sys_setdomainname -122 common uname sys_newuname sys_newuname -124 common adjtimex sys_adjtimex sys_adjtimex_time32 -125 common mprotect sys_mprotect sys_mprotect -126 common sigprocmask sys_sigprocmask compat_sys_sigprocmask -127 common create_module - - -128 common init_module sys_init_module sys_init_module -129 common delete_module sys_delete_module sys_delete_module -130 common get_kernel_syms - - -131 common quotactl sys_quotactl sys_quotactl -132 common getpgid sys_getpgid sys_getpgid -133 common fchdir sys_fchdir sys_fchdir -134 common bdflush sys_ni_syscall sys_ni_syscall -135 common sysfs sys_sysfs sys_sysfs -136 common personality sys_s390_personality sys_s390_personality -137 common afs_syscall - - -138 32 setfsuid - sys_setfsuid16 -139 32 setfsgid - sys_setfsgid16 -140 32 _llseek - sys_llseek -141 common getdents sys_getdents compat_sys_getdents -142 32 _newselect - compat_sys_select -142 64 select sys_select - -143 common flock sys_flock sys_flock -144 common msync sys_msync sys_msync -145 common readv sys_readv sys_readv -146 common writev sys_writev sys_writev -147 common getsid sys_getsid sys_getsid -148 common fdatasync sys_fdatasync sys_fdatasync -149 common _sysctl - - -150 common mlock sys_mlock sys_mlock -151 common munlock sys_munlock sys_munlock -152 common mlockall sys_mlockall sys_mlockall -153 common munlockall sys_munlockall sys_munlockall -154 common sched_setparam sys_sched_setparam sys_sched_setparam -155 common sched_getparam sys_sched_getparam sys_sched_getparam -156 common sched_setscheduler sys_sched_setscheduler sys_sched_setscheduler -157 common sched_getscheduler sys_sched_getscheduler sys_sched_getscheduler -158 common sched_yield sys_sched_yield sys_sched_yield -159 common sched_get_priority_max sys_sched_get_priority_max sys_sched_get_priority_max -160 common sched_get_priority_min sys_sched_get_priority_min sys_sched_get_priority_min -161 common sched_rr_get_interval sys_sched_rr_get_interval sys_sched_rr_get_interval_time32 -162 common nanosleep sys_nanosleep sys_nanosleep_time32 -163 common mremap sys_mremap sys_mremap -164 32 setresuid - sys_setresuid16 -165 32 getresuid - sys_getresuid16 -167 common query_module - - -168 common poll sys_poll sys_poll -169 common nfsservctl - - -170 32 setresgid - sys_setresgid16 -171 32 getresgid - sys_getresgid16 -172 common prctl sys_prctl sys_prctl -173 common rt_sigreturn sys_rt_sigreturn compat_sys_rt_sigreturn -174 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction -175 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask -176 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending -177 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time32 -178 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo -179 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend -180 common pread64 sys_pread64 compat_sys_s390_pread64 -181 common pwrite64 sys_pwrite64 compat_sys_s390_pwrite64 -182 32 chown - sys_chown16 -183 common getcwd sys_getcwd sys_getcwd -184 common capget sys_capget sys_capget -185 common capset sys_capset sys_capset -186 common sigaltstack sys_sigaltstack compat_sys_sigaltstack -187 common sendfile sys_sendfile64 compat_sys_sendfile -188 common getpmsg - - -189 common putpmsg - - -190 common vfork sys_vfork sys_vfork -191 32 ugetrlimit - compat_sys_getrlimit -191 64 getrlimit sys_getrlimit - -192 32 mmap2 - compat_sys_s390_mmap2 -193 32 truncate64 - compat_sys_s390_truncate64 -194 32 ftruncate64 - compat_sys_s390_ftruncate64 -195 32 stat64 - compat_sys_s390_stat64 -196 32 lstat64 - compat_sys_s390_lstat64 -197 32 fstat64 - compat_sys_s390_fstat64 -198 32 lchown32 - sys_lchown -198 64 lchown sys_lchown - -199 32 getuid32 - sys_getuid -199 64 getuid sys_getuid - -200 32 getgid32 - sys_getgid -200 64 getgid sys_getgid - -201 32 geteuid32 - sys_geteuid -201 64 geteuid sys_geteuid - -202 32 getegid32 - sys_getegid -202 64 getegid sys_getegid - -203 32 setreuid32 - sys_setreuid -203 64 setreuid sys_setreuid - -204 32 setregid32 - sys_setregid -204 64 setregid sys_setregid - -205 32 getgroups32 - sys_getgroups -205 64 getgroups sys_getgroups - -206 32 setgroups32 - sys_setgroups -206 64 setgroups sys_setgroups - -207 32 fchown32 - sys_fchown -207 64 fchown sys_fchown - -208 32 setresuid32 - sys_setresuid -208 64 setresuid sys_setresuid - -209 32 getresuid32 - sys_getresuid -209 64 getresuid sys_getresuid - -210 32 setresgid32 - sys_setresgid -210 64 setresgid sys_setresgid - -211 32 getresgid32 - sys_getresgid -211 64 getresgid sys_getresgid - -212 32 chown32 - sys_chown -212 64 chown sys_chown - -213 32 setuid32 - sys_setuid -213 64 setuid sys_setuid - -214 32 setgid32 - sys_setgid -214 64 setgid sys_setgid - -215 32 setfsuid32 - sys_setfsuid -215 64 setfsuid sys_setfsuid - -216 32 setfsgid32 - sys_setfsgid -216 64 setfsgid sys_setfsgid - -217 common pivot_root sys_pivot_root sys_pivot_root -218 common mincore sys_mincore sys_mincore -219 common madvise sys_madvise sys_madvise -220 common getdents64 sys_getdents64 sys_getdents64 -221 32 fcntl64 - compat_sys_fcntl64 -222 common readahead sys_readahead compat_sys_s390_readahead -223 32 sendfile64 - compat_sys_sendfile64 -224 common setxattr sys_setxattr sys_setxattr -225 common lsetxattr sys_lsetxattr sys_lsetxattr -226 common fsetxattr sys_fsetxattr sys_fsetxattr -227 common getxattr sys_getxattr sys_getxattr -228 common lgetxattr sys_lgetxattr sys_lgetxattr -229 common fgetxattr sys_fgetxattr sys_fgetxattr -230 common listxattr sys_listxattr sys_listxattr -231 common llistxattr sys_llistxattr sys_llistxattr -232 common flistxattr sys_flistxattr sys_flistxattr -233 common removexattr sys_removexattr sys_removexattr -234 common lremovexattr sys_lremovexattr sys_lremovexattr -235 common fremovexattr sys_fremovexattr sys_fremovexattr -236 common gettid sys_gettid sys_gettid -237 common tkill sys_tkill sys_tkill -238 common futex sys_futex sys_futex_time32 -239 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity -240 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity -241 common tgkill sys_tgkill sys_tgkill -243 common io_setup sys_io_setup compat_sys_io_setup -244 common io_destroy sys_io_destroy sys_io_destroy -245 common io_getevents sys_io_getevents sys_io_getevents_time32 -246 common io_submit sys_io_submit compat_sys_io_submit -247 common io_cancel sys_io_cancel sys_io_cancel -248 common exit_group sys_exit_group sys_exit_group -249 common epoll_create sys_epoll_create sys_epoll_create -250 common epoll_ctl sys_epoll_ctl sys_epoll_ctl -251 common epoll_wait sys_epoll_wait sys_epoll_wait -252 common set_tid_address sys_set_tid_address sys_set_tid_address -253 common fadvise64 sys_fadvise64_64 compat_sys_s390_fadvise64 -254 common timer_create sys_timer_create compat_sys_timer_create -255 common timer_settime sys_timer_settime sys_timer_settime32 -256 common timer_gettime sys_timer_gettime sys_timer_gettime32 -257 common timer_getoverrun sys_timer_getoverrun sys_timer_getoverrun -258 common timer_delete sys_timer_delete sys_timer_delete -259 common clock_settime sys_clock_settime sys_clock_settime32 -260 common clock_gettime sys_clock_gettime sys_clock_gettime32 -261 common clock_getres sys_clock_getres sys_clock_getres_time32 -262 common clock_nanosleep sys_clock_nanosleep sys_clock_nanosleep_time32 -264 32 fadvise64_64 - compat_sys_s390_fadvise64_64 -265 common statfs64 sys_statfs64 compat_sys_statfs64 -266 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 -267 common remap_file_pages sys_remap_file_pages sys_remap_file_pages -268 common mbind sys_mbind sys_mbind -269 common get_mempolicy sys_get_mempolicy sys_get_mempolicy -270 common set_mempolicy sys_set_mempolicy sys_set_mempolicy -271 common mq_open sys_mq_open compat_sys_mq_open -272 common mq_unlink sys_mq_unlink sys_mq_unlink -273 common mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32 -274 common mq_timedreceive sys_mq_timedreceive sys_mq_timedreceive_time32 -275 common mq_notify sys_mq_notify compat_sys_mq_notify -276 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr -277 common kexec_load sys_kexec_load compat_sys_kexec_load -278 common add_key sys_add_key sys_add_key -279 common request_key sys_request_key sys_request_key -280 common keyctl sys_keyctl compat_sys_keyctl -281 common waitid sys_waitid compat_sys_waitid -282 common ioprio_set sys_ioprio_set sys_ioprio_set -283 common ioprio_get sys_ioprio_get sys_ioprio_get -284 common inotify_init sys_inotify_init sys_inotify_init -285 common inotify_add_watch sys_inotify_add_watch sys_inotify_add_watch -286 common inotify_rm_watch sys_inotify_rm_watch sys_inotify_rm_watch -287 common migrate_pages sys_migrate_pages sys_migrate_pages -288 common openat sys_openat compat_sys_openat -289 common mkdirat sys_mkdirat sys_mkdirat -290 common mknodat sys_mknodat sys_mknodat -291 common fchownat sys_fchownat sys_fchownat -292 common futimesat sys_futimesat sys_futimesat_time32 -293 32 fstatat64 - compat_sys_s390_fstatat64 -293 64 newfstatat sys_newfstatat - -294 common unlinkat sys_unlinkat sys_unlinkat -295 common renameat sys_renameat sys_renameat -296 common linkat sys_linkat sys_linkat -297 common symlinkat sys_symlinkat sys_symlinkat -298 common readlinkat sys_readlinkat sys_readlinkat -299 common fchmodat sys_fchmodat sys_fchmodat -300 common faccessat sys_faccessat sys_faccessat -301 common pselect6 sys_pselect6 compat_sys_pselect6_time32 -302 common ppoll sys_ppoll compat_sys_ppoll_time32 -303 common unshare sys_unshare sys_unshare -304 common set_robust_list sys_set_robust_list compat_sys_set_robust_list -305 common get_robust_list sys_get_robust_list compat_sys_get_robust_list -306 common splice sys_splice sys_splice -307 common sync_file_range sys_sync_file_range compat_sys_s390_sync_file_range -308 common tee sys_tee sys_tee -309 common vmsplice sys_vmsplice sys_vmsplice -310 common move_pages sys_move_pages sys_move_pages -311 common getcpu sys_getcpu sys_getcpu -312 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait -313 common utimes sys_utimes sys_utimes_time32 -314 common fallocate sys_fallocate compat_sys_s390_fallocate -315 common utimensat sys_utimensat sys_utimensat_time32 -316 common signalfd sys_signalfd compat_sys_signalfd -317 common timerfd - - -318 common eventfd sys_eventfd sys_eventfd -319 common timerfd_create sys_timerfd_create sys_timerfd_create -320 common timerfd_settime sys_timerfd_settime sys_timerfd_settime32 -321 common timerfd_gettime sys_timerfd_gettime sys_timerfd_gettime32 -322 common signalfd4 sys_signalfd4 compat_sys_signalfd4 -323 common eventfd2 sys_eventfd2 sys_eventfd2 -324 common inotify_init1 sys_inotify_init1 sys_inotify_init1 -325 common pipe2 sys_pipe2 sys_pipe2 -326 common dup3 sys_dup3 sys_dup3 -327 common epoll_create1 sys_epoll_create1 sys_epoll_create1 -328 common preadv sys_preadv compat_sys_preadv -329 common pwritev sys_pwritev compat_sys_pwritev -330 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo -331 common perf_event_open sys_perf_event_open sys_perf_event_open -332 common fanotify_init sys_fanotify_init sys_fanotify_init -333 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark -334 common prlimit64 sys_prlimit64 sys_prlimit64 -335 common name_to_handle_at sys_name_to_handle_at sys_name_to_handle_at -336 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at -337 common clock_adjtime sys_clock_adjtime sys_clock_adjtime32 -338 common syncfs sys_syncfs sys_syncfs -339 common setns sys_setns sys_setns -340 common process_vm_readv sys_process_vm_readv sys_process_vm_readv -341 common process_vm_writev sys_process_vm_writev sys_process_vm_writev -342 common s390_runtime_instr sys_s390_runtime_instr sys_s390_runtime_instr -343 common kcmp sys_kcmp sys_kcmp -344 common finit_module sys_finit_module sys_finit_module -345 common sched_setattr sys_sched_setattr sys_sched_setattr -346 common sched_getattr sys_sched_getattr sys_sched_getattr -347 common renameat2 sys_renameat2 sys_renameat2 -348 common seccomp sys_seccomp sys_seccomp -349 common getrandom sys_getrandom sys_getrandom -350 common memfd_create sys_memfd_create sys_memfd_create -351 common bpf sys_bpf sys_bpf -352 common s390_pci_mmio_write sys_s390_pci_mmio_write sys_s390_pci_mmio_write -353 common s390_pci_mmio_read sys_s390_pci_mmio_read sys_s390_pci_mmio_read -354 common execveat sys_execveat compat_sys_execveat -355 common userfaultfd sys_userfaultfd sys_userfaultfd -356 common membarrier sys_membarrier sys_membarrier -357 common recvmmsg sys_recvmmsg compat_sys_recvmmsg_time32 -358 common sendmmsg sys_sendmmsg compat_sys_sendmmsg -359 common socket sys_socket sys_socket -360 common socketpair sys_socketpair sys_socketpair -361 common bind sys_bind sys_bind -362 common connect sys_connect sys_connect -363 common listen sys_listen sys_listen -364 common accept4 sys_accept4 sys_accept4 -365 common getsockopt sys_getsockopt sys_getsockopt -366 common setsockopt sys_setsockopt sys_setsockopt -367 common getsockname sys_getsockname sys_getsockname -368 common getpeername sys_getpeername sys_getpeername -369 common sendto sys_sendto sys_sendto -370 common sendmsg sys_sendmsg compat_sys_sendmsg -371 common recvfrom sys_recvfrom compat_sys_recvfrom -372 common recvmsg sys_recvmsg compat_sys_recvmsg -373 common shutdown sys_shutdown sys_shutdown -374 common mlock2 sys_mlock2 sys_mlock2 -375 common copy_file_range sys_copy_file_range sys_copy_file_range -376 common preadv2 sys_preadv2 compat_sys_preadv2 -377 common pwritev2 sys_pwritev2 compat_sys_pwritev2 -378 common s390_guarded_storage sys_s390_guarded_storage sys_s390_guarded_storage -379 common statx sys_statx sys_statx -380 common s390_sthyi sys_s390_sthyi sys_s390_sthyi -381 common kexec_file_load sys_kexec_file_load sys_kexec_file_load -382 common io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents -383 common rseq sys_rseq sys_rseq -384 common pkey_mprotect sys_pkey_mprotect sys_pkey_mprotect -385 common pkey_alloc sys_pkey_alloc sys_pkey_alloc -386 common pkey_free sys_pkey_free sys_pkey_free +1 common exit sys_exit +2 common fork sys_fork +3 common read sys_read +4 common write sys_write +5 common open sys_open +6 common close sys_close +7 common restart_syscall sys_restart_syscall +8 common creat sys_creat +9 common link sys_link +10 common unlink sys_unlink +11 common execve sys_execve +12 common chdir sys_chdir +14 common mknod sys_mknod +15 common chmod sys_chmod +19 common lseek sys_lseek +20 common getpid sys_getpid +21 common mount sys_mount +22 common umount sys_oldumount +26 common ptrace sys_ptrace +27 common alarm sys_alarm +29 common pause sys_pause +30 common utime sys_utime +33 common access sys_access +34 common nice sys_nice +36 common sync sys_sync +37 common kill sys_kill +38 common rename sys_rename +39 common mkdir sys_mkdir +40 common rmdir sys_rmdir +41 common dup sys_dup +42 common pipe sys_pipe +43 common times sys_times +45 common brk sys_brk +48 common signal sys_signal +51 common acct sys_acct +52 common umount2 sys_umount +54 common ioctl sys_ioctl +55 common fcntl sys_fcntl +57 common setpgid sys_setpgid +60 common umask sys_umask +61 common chroot sys_chroot +62 common ustat sys_ustat +63 common dup2 sys_dup2 +64 common getppid sys_getppid +65 common getpgrp sys_getpgrp +66 common setsid sys_setsid +67 common sigaction sys_sigaction +72 common sigsuspend sys_sigsuspend +73 common sigpending sys_sigpending +74 common sethostname sys_sethostname +75 common setrlimit sys_setrlimit +77 common getrusage sys_getrusage +78 common gettimeofday sys_gettimeofday +79 common settimeofday sys_settimeofday +83 common symlink sys_symlink +85 common readlink sys_readlink +86 common uselib sys_uselib +87 common swapon sys_swapon +88 common reboot sys_reboot +89 common readdir sys_ni_syscall +90 common mmap sys_old_mmap +91 common munmap sys_munmap +92 common truncate sys_truncate +93 common ftruncate sys_ftruncate +94 common fchmod sys_fchmod +96 common getpriority sys_getpriority +97 common setpriority sys_setpriority +99 common statfs sys_statfs +100 common fstatfs sys_fstatfs +102 common socketcall sys_socketcall +103 common syslog sys_syslog +104 common setitimer sys_setitimer +105 common getitimer sys_getitimer +106 common stat sys_newstat +107 common lstat sys_newlstat +108 common fstat sys_newfstat +110 common lookup_dcookie sys_ni_syscall +111 common vhangup sys_vhangup +112 common idle sys_ni_syscall +114 common wait4 sys_wait4 +115 common swapoff sys_swapoff +116 common sysinfo sys_sysinfo +117 common ipc sys_s390_ipc +118 common fsync sys_fsync +119 common sigreturn sys_sigreturn +120 common clone sys_clone +121 common setdomainname sys_setdomainname +122 common uname sys_newuname +124 common adjtimex sys_adjtimex +125 common mprotect sys_mprotect +126 common sigprocmask sys_sigprocmask +127 common create_module sys_ni_syscall +128 common init_module sys_init_module +129 common delete_module sys_delete_module +130 common get_kernel_syms sys_ni_syscall +131 common quotactl sys_quotactl +132 common getpgid sys_getpgid +133 common fchdir sys_fchdir +134 common bdflush sys_ni_syscall +135 common sysfs sys_sysfs +136 common personality sys_s390_personality +137 common afs_syscall sys_ni_syscall +141 common getdents sys_getdents +142 common select sys_select +143 common flock sys_flock +144 common msync sys_msync +145 common readv sys_readv +146 common writev sys_writev +147 common getsid sys_getsid +148 common fdatasync sys_fdatasync +149 common _sysctl sys_ni_syscall +150 common mlock sys_mlock +151 common munlock sys_munlock +152 common mlockall sys_mlockall +153 common munlockall sys_munlockall +154 common sched_setparam sys_sched_setparam +155 common sched_getparam sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler +157 common sched_getscheduler sys_sched_getscheduler +158 common sched_yield sys_sched_yield +159 common sched_get_priority_max sys_sched_get_priority_max +160 common sched_get_priority_min sys_sched_get_priority_min +161 common sched_rr_get_interval sys_sched_rr_get_interval +162 common nanosleep sys_nanosleep +163 common mremap sys_mremap +167 common query_module sys_ni_syscall +168 common poll sys_poll +169 common nfsservctl sys_ni_syscall +172 common prctl sys_prctl +173 common rt_sigreturn sys_rt_sigreturn +174 common rt_sigaction sys_rt_sigaction +175 common rt_sigprocmask sys_rt_sigprocmask +176 common rt_sigpending sys_rt_sigpending +177 common rt_sigtimedwait sys_rt_sigtimedwait +178 common rt_sigqueueinfo sys_rt_sigqueueinfo +179 common rt_sigsuspend sys_rt_sigsuspend +180 common pread64 sys_pread64 +181 common pwrite64 sys_pwrite64 +183 common getcwd sys_getcwd +184 common capget sys_capget +185 common capset sys_capset +186 common sigaltstack sys_sigaltstack +187 common sendfile sys_sendfile64 +188 common getpmsg sys_ni_syscall +189 common putpmsg sys_ni_syscall +190 common vfork sys_vfork +191 common getrlimit sys_getrlimit +198 common lchown sys_lchown +199 common getuid sys_getuid +200 common getgid sys_getgid +201 common geteuid sys_geteuid +202 common getegid sys_getegid +203 common setreuid sys_setreuid +204 common setregid sys_setregid +205 common getgroups sys_getgroups +206 common setgroups sys_setgroups +207 common fchown sys_fchown +208 common setresuid sys_setresuid +209 common getresuid sys_getresuid +210 common setresgid sys_setresgid +211 common getresgid sys_getresgid +212 common chown sys_chown +213 common setuid sys_setuid +214 common setgid sys_setgid +215 common setfsuid sys_setfsuid +216 common setfsgid sys_setfsgid +217 common pivot_root sys_pivot_root +218 common mincore sys_mincore +219 common madvise sys_madvise +220 common getdents64 sys_getdents64 +222 common readahead sys_readahead +224 common setxattr sys_setxattr +225 common lsetxattr sys_lsetxattr +226 common fsetxattr sys_fsetxattr +227 common getxattr sys_getxattr +228 common lgetxattr sys_lgetxattr +229 common fgetxattr sys_fgetxattr +230 common listxattr sys_listxattr +231 common llistxattr sys_llistxattr +232 common flistxattr sys_flistxattr +233 common removexattr sys_removexattr +234 common lremovexattr sys_lremovexattr +235 common fremovexattr sys_fremovexattr +236 common gettid sys_gettid +237 common tkill sys_tkill +238 common futex sys_futex +239 common sched_setaffinity sys_sched_setaffinity +240 common sched_getaffinity sys_sched_getaffinity +241 common tgkill sys_tgkill +243 common io_setup sys_io_setup +244 common io_destroy sys_io_destroy +245 common io_getevents sys_io_getevents +246 common io_submit sys_io_submit +247 common io_cancel sys_io_cancel +248 common exit_group sys_exit_group +249 common epoll_create sys_epoll_create +250 common epoll_ctl sys_epoll_ctl +251 common epoll_wait sys_epoll_wait +252 common set_tid_address sys_set_tid_address +253 common fadvise64 sys_fadvise64_64 +254 common timer_create sys_timer_create +255 common timer_settime sys_timer_settime +256 common timer_gettime sys_timer_gettime +257 common timer_getoverrun sys_timer_getoverrun +258 common timer_delete sys_timer_delete +259 common clock_settime sys_clock_settime +260 common clock_gettime sys_clock_gettime +261 common clock_getres sys_clock_getres +262 common clock_nanosleep sys_clock_nanosleep +265 common statfs64 sys_statfs64 +266 common fstatfs64 sys_fstatfs64 +267 common remap_file_pages sys_remap_file_pages +268 common mbind sys_mbind +269 common get_mempolicy sys_get_mempolicy +270 common set_mempolicy sys_set_mempolicy +271 common mq_open sys_mq_open +272 common mq_unlink sys_mq_unlink +273 common mq_timedsend sys_mq_timedsend +274 common mq_timedreceive sys_mq_timedreceive +275 common mq_notify sys_mq_notify +276 common mq_getsetattr sys_mq_getsetattr +277 common kexec_load sys_kexec_load +278 common add_key sys_add_key +279 common request_key sys_request_key +280 common keyctl sys_keyctl +281 common waitid sys_waitid +282 common ioprio_set sys_ioprio_set +283 common ioprio_get sys_ioprio_get +284 common inotify_init sys_inotify_init +285 common inotify_add_watch sys_inotify_add_watch +286 common inotify_rm_watch sys_inotify_rm_watch +287 common migrate_pages sys_migrate_pages +288 common openat sys_openat +289 common mkdirat sys_mkdirat +290 common mknodat sys_mknodat +291 common fchownat sys_fchownat +292 common futimesat sys_futimesat +293 common newfstatat sys_newfstatat +294 common unlinkat sys_unlinkat +295 common renameat sys_renameat +296 common linkat sys_linkat +297 common symlinkat sys_symlinkat +298 common readlinkat sys_readlinkat +299 common fchmodat sys_fchmodat +300 common faccessat sys_faccessat +301 common pselect6 sys_pselect6 +302 common ppoll sys_ppoll +303 common unshare sys_unshare +304 common set_robust_list sys_set_robust_list +305 common get_robust_list sys_get_robust_list +306 common splice sys_splice +307 common sync_file_range sys_sync_file_range +308 common tee sys_tee +309 common vmsplice sys_vmsplice +310 common move_pages sys_move_pages +311 common getcpu sys_getcpu +312 common epoll_pwait sys_epoll_pwait +313 common utimes sys_utimes +314 common fallocate sys_fallocate +315 common utimensat sys_utimensat +316 common signalfd sys_signalfd +317 common timerfd sys_ni_syscall +318 common eventfd sys_eventfd +319 common timerfd_create sys_timerfd_create +320 common timerfd_settime sys_timerfd_settime +321 common timerfd_gettime sys_timerfd_gettime +322 common signalfd4 sys_signalfd4 +323 common eventfd2 sys_eventfd2 +324 common inotify_init1 sys_inotify_init1 +325 common pipe2 sys_pipe2 +326 common dup3 sys_dup3 +327 common epoll_create1 sys_epoll_create1 +328 common preadv sys_preadv +329 common pwritev sys_pwritev +330 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +331 common perf_event_open sys_perf_event_open +332 common fanotify_init sys_fanotify_init +333 common fanotify_mark sys_fanotify_mark +334 common prlimit64 sys_prlimit64 +335 common name_to_handle_at sys_name_to_handle_at +336 common open_by_handle_at sys_open_by_handle_at +337 common clock_adjtime sys_clock_adjtime +338 common syncfs sys_syncfs +339 common setns sys_setns +340 common process_vm_readv sys_process_vm_readv +341 common process_vm_writev sys_process_vm_writev +342 common s390_runtime_instr sys_s390_runtime_instr +343 common kcmp sys_kcmp +344 common finit_module sys_finit_module +345 common sched_setattr sys_sched_setattr +346 common sched_getattr sys_sched_getattr +347 common renameat2 sys_renameat2 +348 common seccomp sys_seccomp +349 common getrandom sys_getrandom +350 common memfd_create sys_memfd_create +351 common bpf sys_bpf +352 common s390_pci_mmio_write sys_s390_pci_mmio_write +353 common s390_pci_mmio_read sys_s390_pci_mmio_read +354 common execveat sys_execveat +355 common userfaultfd sys_userfaultfd +356 common membarrier sys_membarrier +357 common recvmmsg sys_recvmmsg +358 common sendmmsg sys_sendmmsg +359 common socket sys_socket +360 common socketpair sys_socketpair +361 common bind sys_bind +362 common connect sys_connect +363 common listen sys_listen +364 common accept4 sys_accept4 +365 common getsockopt sys_getsockopt +366 common setsockopt sys_setsockopt +367 common getsockname sys_getsockname +368 common getpeername sys_getpeername +369 common sendto sys_sendto +370 common sendmsg sys_sendmsg +371 common recvfrom sys_recvfrom +372 common recvmsg sys_recvmsg +373 common shutdown sys_shutdown +374 common mlock2 sys_mlock2 +375 common copy_file_range sys_copy_file_range +376 common preadv2 sys_preadv2 +377 common pwritev2 sys_pwritev2 +378 common s390_guarded_storage sys_s390_guarded_storage +379 common statx sys_statx +380 common s390_sthyi sys_s390_sthyi +381 common kexec_file_load sys_kexec_file_load +382 common io_pgetevents sys_io_pgetevents +383 common rseq sys_rseq +384 common pkey_mprotect sys_pkey_mprotect +385 common pkey_alloc sys_pkey_alloc +386 common pkey_free sys_pkey_free # room for arch specific syscalls -392 64 semtimedop sys_semtimedop - -393 common semget sys_semget sys_semget -394 common semctl sys_semctl compat_sys_semctl -395 common shmget sys_shmget sys_shmget -396 common shmctl sys_shmctl compat_sys_shmctl -397 common shmat sys_shmat compat_sys_shmat -398 common shmdt sys_shmdt sys_shmdt -399 common msgget sys_msgget sys_msgget -400 common msgsnd sys_msgsnd compat_sys_msgsnd -401 common msgrcv sys_msgrcv compat_sys_msgrcv -402 common msgctl sys_msgctl compat_sys_msgctl -403 32 clock_gettime64 - sys_clock_gettime -404 32 clock_settime64 - sys_clock_settime -405 32 clock_adjtime64 - sys_clock_adjtime -406 32 clock_getres_time64 - sys_clock_getres -407 32 clock_nanosleep_time64 - sys_clock_nanosleep -408 32 timer_gettime64 - sys_timer_gettime -409 32 timer_settime64 - sys_timer_settime -410 32 timerfd_gettime64 - sys_timerfd_gettime -411 32 timerfd_settime64 - sys_timerfd_settime -412 32 utimensat_time64 - sys_utimensat -413 32 pselect6_time64 - compat_sys_pselect6_time64 -414 32 ppoll_time64 - compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 - compat_sys_io_pgetevents_time64 -417 32 recvmmsg_time64 - compat_sys_recvmmsg_time64 -418 32 mq_timedsend_time64 - sys_mq_timedsend -419 32 mq_timedreceive_time64 - sys_mq_timedreceive -420 32 semtimedop_time64 - sys_semtimedop -421 32 rt_sigtimedwait_time64 - compat_sys_rt_sigtimedwait_time64 -422 32 futex_time64 - sys_futex -423 32 sched_rr_get_interval_time64 - sys_sched_rr_get_interval -424 common pidfd_send_signal sys_pidfd_send_signal sys_pidfd_send_signal -425 common io_uring_setup sys_io_uring_setup sys_io_uring_setup -426 common io_uring_enter sys_io_uring_enter sys_io_uring_enter -427 common io_uring_register sys_io_uring_register sys_io_uring_register -428 common open_tree sys_open_tree sys_open_tree -429 common move_mount sys_move_mount sys_move_mount -430 common fsopen sys_fsopen sys_fsopen -431 common fsconfig sys_fsconfig sys_fsconfig -432 common fsmount sys_fsmount sys_fsmount -433 common fspick sys_fspick sys_fspick -434 common pidfd_open sys_pidfd_open sys_pidfd_open -435 common clone3 sys_clone3 sys_clone3 -436 common close_range sys_close_range sys_close_range -437 common openat2 sys_openat2 sys_openat2 -438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd -439 common faccessat2 sys_faccessat2 sys_faccessat2 -440 common process_madvise sys_process_madvise sys_process_madvise -441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 -442 common mount_setattr sys_mount_setattr sys_mount_setattr -443 common quotactl_fd sys_quotactl_fd sys_quotactl_fd -444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset -445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule -446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self -447 common memfd_secret sys_memfd_secret sys_memfd_secret -448 common process_mrelease sys_process_mrelease sys_process_mrelease -449 common futex_waitv sys_futex_waitv sys_futex_waitv -450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node -451 common cachestat sys_cachestat sys_cachestat -452 common fchmodat2 sys_fchmodat2 sys_fchmodat2 -453 common map_shadow_stack sys_map_shadow_stack sys_map_shadow_stack -454 common futex_wake sys_futex_wake sys_futex_wake -455 common futex_wait sys_futex_wait sys_futex_wait -456 common futex_requeue sys_futex_requeue sys_futex_requeue -457 common statmount sys_statmount sys_statmount -458 common listmount sys_listmount sys_listmount -459 common lsm_get_self_attr sys_lsm_get_self_attr sys_lsm_get_self_attr -460 common lsm_set_self_attr sys_lsm_set_self_attr sys_lsm_set_self_attr -461 common lsm_list_modules sys_lsm_list_modules sys_lsm_list_modules -462 common mseal sys_mseal sys_mseal -463 common setxattrat sys_setxattrat sys_setxattrat -464 common getxattrat sys_getxattrat sys_getxattrat -465 common listxattrat sys_listxattrat sys_listxattrat -466 common removexattrat sys_removexattrat sys_removexattrat -467 common open_tree_attr sys_open_tree_attr sys_open_tree_attr -468 common file_getattr sys_file_getattr sys_file_getattr -469 common file_setattr sys_file_setattr sys_file_setattr -470 common listns sys_listns sys_listns +392 common semtimedop sys_semtimedop +393 common semget sys_semget +394 common semctl sys_semctl +395 common shmget sys_shmget +396 common shmctl sys_shmctl +397 common shmat sys_shmat +398 common shmdt sys_shmdt +399 common msgget sys_msgget +400 common msgsnd sys_msgsnd +401 common msgrcv sys_msgrcv +402 common msgctl sys_msgctl +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +435 common clone3 sys_clone3 +436 common close_range sys_close_range +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +443 common quotactl_fd sys_quotactl_fd +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self +447 common memfd_secret sys_memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal +463 common setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat +467 common open_tree_attr sys_open_tree_attr +468 common file_getattr sys_file_getattr +469 common file_setattr sys_file_setattr +470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/sh/entry/syscalls/syscall.tbl b/tools/perf/arch/sh/entry/syscalls/syscall.tbl index 969c11325ade..70b315cbe710 100644 --- a/tools/perf/arch/sh/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/sh/entry/syscalls/syscall.tbl @@ -474,3 +474,4 @@ 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr 470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl index 39aa26b6a50b..7e71bf7fcd14 100644 --- a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl @@ -480,7 +480,7 @@ 432 common fsmount sys_fsmount 433 common fspick sys_fspick 434 common pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 common clone3 __sys_clone3 436 common close_range sys_close_range 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd @@ -516,3 +516,4 @@ 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr 470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl index e979a3eac7a3..f832ebd2d79b 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl @@ -476,3 +476,4 @@ 468 i386 file_getattr sys_file_getattr 469 i386 file_setattr sys_file_setattr 470 i386 listns sys_listns +471 i386 rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 8a4ac4841be6..524155d655da 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -395,6 +395,7 @@ 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr 470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl index 438a3b170402..a9bca4e484de 100644 --- a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl @@ -441,3 +441,4 @@ 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr 470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 6b6eec65f93f..4cc33452d79b 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -18,6 +18,7 @@ #include <poll.h> #include <ctype.h> #include <linux/capability.h> +#include <linux/err.h> #include <linux/string.h> #include <sys/stat.h> @@ -1209,8 +1210,12 @@ static int prepare_func_profile(struct perf_ftrace *ftrace) ftrace->graph_verbose = 0; ftrace->profile_hash = hashmap__new(profile_hash, profile_equal, NULL); - if (ftrace->profile_hash == NULL) - return -ENOMEM; + if (IS_ERR(ftrace->profile_hash)) { + int err = PTR_ERR(ftrace->profile_hash); + + ftrace->profile_hash = NULL; + return err; + } return 0; } diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build index 63c65788d442..dc5f94862a3b 100644 --- a/tools/perf/pmu-events/Build +++ b/tools/perf/pmu-events/Build @@ -214,7 +214,8 @@ ifneq ($(strip $(ORPHAN_FILES)),) quiet_cmd_rm = RM $^ prune_orphans: $(ORPHAN_FILES) - $(Q)$(call echo-cmd,rm)rm -f $^ + # The list of files can be long. Use xargs to prevent issues. + $(Q)$(call echo-cmd,rm)echo "$^" | xargs rm -f JEVENTS_DEPS += prune_orphans endif diff --git a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h index 6e1d5b955aae..85253fc8e384 100644 --- a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h +++ b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h @@ -77,6 +77,7 @@ */ #define IRQ_WORK_VECTOR 0xf6 +/* IRQ vector for PMIs when running a guest with a mediated PMU. */ #define PERF_GUEST_MEDIATED_PMI_VECTOR 0xf5 #define DEFERRED_ERROR_VECTOR 0xf4 diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h index 66ca526cf786..70b2b661f42c 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fs.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h @@ -253,6 +253,7 @@ struct file_attr { #define FS_XFLAG_FILESTREAM 0x00004000 /* use filestream allocator */ #define FS_XFLAG_DAX 0x00008000 /* use DAX for IO */ #define FS_XFLAG_COWEXTSIZE 0x00010000 /* CoW extent size allocator hint */ +#define FS_XFLAG_VERITY 0x00020000 /* fs-verity enabled */ #define FS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */ /* the read-only stuff doesn't really belong here, but any other place is diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h index 5d3f8c9e3a62..d9d86598d100 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/mount.h +++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h @@ -61,7 +61,8 @@ /* * open_tree() flags. */ -#define OPEN_TREE_CLONE 1 /* Clone the target tree and attach the clone */ +#define OPEN_TREE_CLONE (1 << 0) /* Clone the target tree and attach the clone */ +#define OPEN_TREE_NAMESPACE (1 << 1) /* Clone the target tree into a new mount namespace */ #define OPEN_TREE_CLOEXEC O_CLOEXEC /* Close the file on execve() */ /* @@ -197,7 +198,10 @@ struct statmount { */ struct mnt_id_req { __u32 size; - __u32 mnt_ns_fd; + union { + __u32 mnt_ns_fd; + __u32 mnt_fd; + }; __u64 mnt_id; __u64 param; __u64 mnt_ns_id; @@ -232,4 +236,9 @@ struct mnt_id_req { #define LSMT_ROOT 0xffffffffffffffff /* root mount */ #define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */ +/* + * @flag bits for statmount(2) + */ +#define STATMOUNT_BY_FD 0x00000001U /* want mountinfo for given fd */ + #endif /* _UAPI_LINUX_MOUNT_H */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h index 51c4e8c82b1e..55b0446fff9d 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h +++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h @@ -386,4 +386,41 @@ struct prctl_mm_map { # define PR_FUTEX_HASH_SET_SLOTS 1 # define PR_FUTEX_HASH_GET_SLOTS 2 +/* RSEQ time slice extensions */ +#define PR_RSEQ_SLICE_EXTENSION 79 +# define PR_RSEQ_SLICE_EXTENSION_GET 1 +# define PR_RSEQ_SLICE_EXTENSION_SET 2 +/* + * Bits for RSEQ_SLICE_EXTENSION_GET/SET + * PR_RSEQ_SLICE_EXT_ENABLE: Enable + */ +# define PR_RSEQ_SLICE_EXT_ENABLE 0x01 + +/* + * Get the current indirect branch tracking configuration for the current + * thread, this will be the value configured via PR_SET_INDIR_BR_LP_STATUS. + */ +#define PR_GET_INDIR_BR_LP_STATUS 80 + +/* + * Set the indirect branch tracking configuration. PR_INDIR_BR_LP_ENABLE will + * enable cpu feature for user thread, to track all indirect branches and ensure + * they land on arch defined landing pad instruction. + * x86 - If enabled, an indirect branch must land on an ENDBRANCH instruction. + * arch64 - If enabled, an indirect branch must land on a BTI instruction. + * riscv - If enabled, an indirect branch must land on an lpad instruction. + * PR_INDIR_BR_LP_DISABLE will disable feature for user thread and indirect + * branches will no more be tracked by cpu to land on arch defined landing pad + * instruction. + */ +#define PR_SET_INDIR_BR_LP_STATUS 81 +# define PR_INDIR_BR_LP_ENABLE (1UL << 0) + +/* + * Prevent further changes to the specified indirect branch tracking + * configuration. All bits may be locked via this call, including + * undefined bits. + */ +#define PR_LOCK_INDIR_BR_LP_STATUS 82 + #endif /* _LINUX_PRCTL_H */ diff --git a/tools/perf/util/annotate-arch/annotate-loongarch.c b/tools/perf/util/annotate-arch/annotate-loongarch.c index 3aeab453a059..950f34e59e5c 100644 --- a/tools/perf/util/annotate-arch/annotate-loongarch.c +++ b/tools/perf/util/annotate-arch/annotate-loongarch.c @@ -93,7 +93,7 @@ static int loongarch_jump__parse(const struct arch *arch, struct ins_operands *o start = map__unmap_ip(map, sym->start); end = map__unmap_ip(map, sym->end); - ops->target.outside = target.addr < start || target.addr > end; + ops->target.outside = target.addr < start || target.addr >= end; if (maps__find_ams(thread__maps(ms->thread), &target) == 0 && map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr) diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 2e3522905046..63f0ee9d4c03 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -44,6 +44,7 @@ #include "strbuf.h" #include <regex.h> #include <linux/bitops.h> +#include <linux/err.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/zalloc.h> @@ -137,8 +138,10 @@ static int annotated_source__alloc_histograms(struct annotated_source *src, return -1; src->samples = hashmap__new(sym_hist_hash, sym_hist_equal, NULL); - if (src->samples == NULL) + if (IS_ERR(src->samples)) { zfree(&src->histograms); + src->samples = NULL; + } return src->histograms ? 0 : -1; } diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index 3050fe212666..212f17a3dc72 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -549,7 +549,7 @@ cs_etm_decoder__set_tid(struct cs_etm_queue *etmq, /* * Process the PE_CONTEXT packets if we have a valid contextID or VMID. * If the kernel is running at EL2, the PID is traced in CONTEXTIDR_EL2 - * as VMID, Bit ETM_OPT_CTXTID2 is set in this case. + * as VMID, Format attribute 'contextid2' is set in this case. */ switch (cs_etm__get_pid_fmt(etmq)) { case CS_ETM_PIDFMT_CTXTID: diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 95f439c96180..8a639d2e51a4 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -194,7 +194,7 @@ int cs_etm__get_cpu(struct cs_etm_queue *etmq, u8 trace_chan_id, int *cpu) * CS_ETM_PIDFMT_CTXTID2: CONTEXTIDR_EL2 is traced. * CS_ETM_PIDFMT_NONE: No context IDs * - * It's possible that the two bits ETM_OPT_CTXTID and ETM_OPT_CTXTID2 + * It's possible that the two format attributes 'contextid1' and 'contextid2' * are enabled at the same time when the session runs on an EL2 kernel. * This means the CONTEXTIDR_EL1 and CONTEXTIDR_EL2 both will be * recorded in the trace data, the tool will selectively use @@ -210,15 +210,15 @@ static enum cs_etm_pid_fmt cs_etm__init_pid_fmt(u64 *metadata) if (metadata[CS_ETM_MAGIC] == __perf_cs_etmv3_magic) { val = metadata[CS_ETM_ETMCR]; /* CONTEXTIDR is traced */ - if (val & BIT(ETM_OPT_CTXTID)) + if (val & ETMCR_CTXTID) return CS_ETM_PIDFMT_CTXTID; } else { val = metadata[CS_ETMV4_TRCCONFIGR]; /* CONTEXTIDR_EL2 is traced */ - if (val & (BIT(ETM4_CFG_BIT_VMID) | BIT(ETM4_CFG_BIT_VMID_OPT))) + if (val & (TRCCONFIGR_VMID | TRCCONFIGR_VMIDOPT)) return CS_ETM_PIDFMT_CTXTID2; /* CONTEXTIDR_EL1 is traced */ - else if (val & BIT(ETM4_CFG_BIT_CTXTID)) + else if (val & TRCCONFIGR_CID) return CS_ETM_PIDFMT_CTXTID; } @@ -2914,29 +2914,21 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session, return 0; } -static int cs_etm__setup_timeless_decoding(struct cs_etm_auxtrace *etm) +static void cs_etm__setup_timeless_decoding(struct cs_etm_auxtrace *etm) { - struct evsel *evsel; - struct evlist *evlist = etm->session->evlist; + /* Take first ETM as all options will be the same for all ETMs */ + u64 *metadata = etm->metadata[0]; /* Override timeless mode with user input from --itrace=Z */ if (etm->synth_opts.timeless_decoding) { etm->timeless_decoding = true; - return 0; + return; } - /* - * Find the cs_etm evsel and look at what its timestamp setting was - */ - evlist__for_each_entry(evlist, evsel) - if (cs_etm__evsel_is_auxtrace(etm->session, evsel)) { - etm->timeless_decoding = - !(evsel->core.attr.config & BIT(ETM_OPT_TS)); - return 0; - } - - pr_err("CS ETM: Couldn't find ETM evsel\n"); - return -EINVAL; + if (metadata[CS_ETM_MAGIC] == __perf_cs_etmv3_magic) + etm->timeless_decoding = !(metadata[CS_ETM_ETMCR] & ETMCR_TIMESTAMP_EN); + else + etm->timeless_decoding = !(metadata[CS_ETMV4_TRCCONFIGR] & TRCCONFIGR_TS); } /* @@ -3499,9 +3491,7 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, etm->auxtrace.evsel_is_auxtrace = cs_etm__evsel_is_auxtrace; session->auxtrace = &etm->auxtrace; - err = cs_etm__setup_timeless_decoding(etm); - if (err) - return err; + cs_etm__setup_timeless_decoding(etm); etm->tc.time_shift = tc->time_shift; etm->tc.time_mult = tc->time_mult; diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index a8caeea720aa..aa9bb4a32eca 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -230,6 +230,21 @@ struct cs_etm_packet_queue { /* CoreSight trace ID is currently the bottom 7 bits of the value */ #define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) +/* ETMv4 CONFIGR register bits */ +#define TRCCONFIGR_BB BIT(3) +#define TRCCONFIGR_CCI BIT(4) +#define TRCCONFIGR_CID BIT(6) +#define TRCCONFIGR_VMID BIT(7) +#define TRCCONFIGR_TS BIT(11) +#define TRCCONFIGR_RS BIT(12) +#define TRCCONFIGR_VMIDOPT BIT(15) + +/* ETMv3 ETMCR register bits */ +#define ETMCR_CYC_ACC BIT(12) +#define ETMCR_CTXTID BIT(14) +#define ETMCR_TIMESTAMP_EN BIT(28) +#define ETMCR_RETURN_STACK BIT(29) + int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session); void cs_etm_get_default_config(const struct perf_pmu *pmu, struct perf_event_attr *attr); diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c index ddcc488f2e5f..9e0420e14be1 100644 --- a/tools/perf/util/disasm.c +++ b/tools/perf/util/disasm.c @@ -384,7 +384,7 @@ static int jump__parse(const struct arch *arch, struct ins_operands *ops, struct start = map__unmap_ip(map, sym->start); end = map__unmap_ip(map, sym->end); - ops->target.outside = target.addr < start || target.addr > end; + ops->target.outside = target.addr < start || target.addr >= end; /* * FIXME: things like this in _cpp_lex_token (gcc's cc1 program): diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index ef79433ebc3a..ddf1cbda1902 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -703,6 +703,11 @@ static int perf_event__synthesize_modules_maps_cb(struct map *map, void *data) memcpy(event->mmap2.filename, dso__long_name(dso), dso__long_name_len(dso) + 1); + /* Clear stale build ID from previous module iteration */ + event->mmap2.header.misc &= ~PERF_RECORD_MISC_MMAP_BUILD_ID; + memset(event->mmap2.build_id, 0, sizeof(event->mmap2.build_id)); + event->mmap2.build_id_size = 0; + perf_record_mmap2__read_build_id(&event->mmap2, args->machine, false); } else { size = PERF_ALIGN(dso__long_name_len(dso) + 1, sizeof(u64)); diff --git a/tools/power/cpupower/cpupower-service.conf b/tools/power/cpupower/cpupower-service.conf index 02eabe8e3614..abbb46967565 100644 --- a/tools/power/cpupower/cpupower-service.conf +++ b/tools/power/cpupower/cpupower-service.conf @@ -30,3 +30,8 @@ # its policy for the relative importance of performance versus energy savings to # the processor. See man CPUPOWER-SET(1) for additional details #PERF_BIAS= + +# Set the Energy Performance Preference +# Available options can be read from +# /sys/devices/system/cpu/cpufreq/policy0/energy_performance_available_preferences +#EPP= diff --git a/tools/power/cpupower/cpupower.sh b/tools/power/cpupower/cpupower.sh index a37dd4cfdb2b..6283e8bf275d 100644 --- a/tools/power/cpupower/cpupower.sh +++ b/tools/power/cpupower/cpupower.sh @@ -23,4 +23,10 @@ then cpupower set -b "$PERF_BIAS" > /dev/null || ESTATUS=1 fi +# apply Energy Performance Preference +if test -n "$EPP" +then + cpupower set -e "$EPP" > /dev/null || ESTATUS=1 +fi + exit $ESTATUS diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c index c2117e5650dd..550a942e72ce 100644 --- a/tools/power/cpupower/utils/cpupower-set.c +++ b/tools/power/cpupower/utils/cpupower-set.c @@ -124,7 +124,11 @@ int cmd_set(int argc, char **argv) } if (params.turbo_boost) { - ret = cpupower_set_turbo_boost(turbo_boost); + if (cpupower_cpu_info.vendor == X86_VENDOR_INTEL) + ret = cpupower_set_intel_turbo_boost(turbo_boost); + else + ret = cpupower_set_generic_turbo_boost(turbo_boost); + if (ret) fprintf(stderr, "Error setting turbo-boost\n"); } diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h index 82ea62bdf5a2..a3ad80b9c2c2 100644 --- a/tools/power/cpupower/utils/helpers/helpers.h +++ b/tools/power/cpupower/utils/helpers/helpers.h @@ -104,7 +104,7 @@ extern struct cpupower_cpu_info cpupower_cpu_info; /* cpuid and cpuinfo helpers **************************/ int cpufreq_has_generic_boost_support(bool *active); -int cpupower_set_turbo_boost(int turbo_boost); +int cpupower_set_generic_turbo_boost(int turbo_boost); /* X86 ONLY ****************************************/ #if defined(__i386__) || defined(__x86_64__) @@ -143,6 +143,7 @@ extern int decode_pstates(unsigned int cpu, int boost_states, int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, int *active, int *states); +int cpupower_set_intel_turbo_boost(int turbo_boost); /* AMD P-State stuff **************************/ bool cpupower_amd_pstate_enabled(void); @@ -189,6 +190,8 @@ static inline int cpupower_set_amd_pstate_mode(char *mode) static inline int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, int *active, int *states) { return -1; } +static inline int cpupower_set_intel_turbo_boost(int turbo_boost) +{ return -1; } static inline bool cpupower_amd_pstate_enabled(void) { return false; } diff --git a/tools/power/cpupower/utils/helpers/misc.c b/tools/power/cpupower/utils/helpers/misc.c index 166dc1e470ea..eebfc79a4889 100644 --- a/tools/power/cpupower/utils/helpers/misc.c +++ b/tools/power/cpupower/utils/helpers/misc.c @@ -19,6 +19,9 @@ int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, int *active, { int ret; unsigned long long val; + char linebuf[MAX_LINE_LEN]; + char path[SYSFS_PATH_MAX]; + char *endp; *support = *active = *states = 0; @@ -42,8 +45,42 @@ int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, int *active, } } else if (cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATE) { amd_pstate_boost_init(cpu, support, active); - } else if (cpupower_cpu_info.caps & CPUPOWER_CAP_INTEL_IDA) + } else if (cpupower_cpu_info.caps & CPUPOWER_CAP_INTEL_IDA) { *support = *active = 1; + + snprintf(path, sizeof(path), PATH_TO_CPU "intel_pstate/no_turbo"); + + if (!is_valid_path(path)) + return 0; + + if (cpupower_read_sysfs(path, linebuf, MAX_LINE_LEN) == 0) + return -1; + + val = strtol(linebuf, &endp, 0); + if (endp == linebuf || errno == ERANGE) + return -1; + + *active = !val; + } + return 0; +} + +int cpupower_set_intel_turbo_boost(int turbo_boost) +{ + char path[SYSFS_PATH_MAX]; + char linebuf[2] = {}; + + snprintf(path, sizeof(path), PATH_TO_CPU "intel_pstate/no_turbo"); + + /* Fallback to generic solution when intel_pstate driver not running */ + if (!is_valid_path(path)) + return cpupower_set_generic_turbo_boost(turbo_boost); + + snprintf(linebuf, sizeof(linebuf), "%d", !turbo_boost); + + if (cpupower_write_sysfs(path, linebuf, 2) <= 0) + return -1; + return 0; } @@ -274,7 +311,7 @@ void print_speed(unsigned long speed, int no_rounding) } } -int cpupower_set_turbo_boost(int turbo_boost) +int cpupower_set_generic_turbo_boost(int turbo_boost) { char path[SYSFS_PATH_MAX]; char linebuf[2] = {}; diff --git a/tools/power/cpupower/utils/powercap-info.c b/tools/power/cpupower/utils/powercap-info.c index 3ea4486f1a0e..e53033488218 100644 --- a/tools/power/cpupower/utils/powercap-info.c +++ b/tools/power/cpupower/utils/powercap-info.c @@ -38,11 +38,11 @@ static int powercap_print_one_zone(struct powercap_zone *zone) printf(" (%s)\n", mode ? "enabled" : "disabled"); if (zone->has_power_uw) - printf(_("%sPower can be monitored in micro Jules\n"), + printf(_("%sPower can be monitored in micro Watts\n"), pr_prefix); if (zone->has_energy_uj) - printf(_("%sPower can be monitored in micro Watts\n"), + printf(_("%sPower can be monitored in micro Jules\n"), pr_prefix); printf("\n"); diff --git a/tools/scripts/syscall.tbl b/tools/scripts/syscall.tbl index e74868be513c..7a42b32b6577 100644 --- a/tools/scripts/syscall.tbl +++ b/tools/scripts/syscall.tbl @@ -411,3 +411,4 @@ 468 common file_getattr sys_file_getattr 469 common file_setattr sys_file_setattr 470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h index 80ab60905865..cdca912f3afd 100644 --- a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h +++ b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h @@ -6,8 +6,10 @@ #define __HID_BPF_HELPERS_H /* "undefine" structs and enums in vmlinux.h, because we "override" them below */ +#define bpf_wq bpf_wq___not_used #define hid_bpf_ctx hid_bpf_ctx___not_used #define hid_bpf_ops hid_bpf_ops___not_used +#define hid_device hid_device___not_used #define hid_report_type hid_report_type___not_used #define hid_class_request hid_class_request___not_used #define hid_bpf_attach_flags hid_bpf_attach_flags___not_used @@ -27,8 +29,10 @@ #include "vmlinux.h" +#undef bpf_wq #undef hid_bpf_ctx #undef hid_bpf_ops +#undef hid_device #undef hid_report_type #undef hid_class_request #undef hid_bpf_attach_flags @@ -55,6 +59,14 @@ enum hid_report_type { HID_REPORT_TYPES, }; +struct hid_device { + unsigned int id; +} __attribute__((preserve_access_index)); + +struct bpf_wq { + __u64 __opaque[2]; +}; + struct hid_bpf_ctx { struct hid_device *hid; __u32 allocated_size; diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index fdec90e85467..dc68371f76a3 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -71,6 +71,7 @@ TEST_GEN_PROGS_x86 += x86/cpuid_test TEST_GEN_PROGS_x86 += x86/cr4_cpuid_sync_test TEST_GEN_PROGS_x86 += x86/dirty_log_page_splitting_test TEST_GEN_PROGS_x86 += x86/feature_msrs_test +TEST_GEN_PROGS_x86 += x86/evmcs_smm_controls_test TEST_GEN_PROGS_x86 += x86/exit_on_emulation_failure_test TEST_GEN_PROGS_x86 += x86/fastops_test TEST_GEN_PROGS_x86 += x86/fix_hypercall_test diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index 618c937f3c90..cc329b57ce2e 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -80,7 +80,7 @@ static void test_mbind(int fd, size_t total_size) { const unsigned long nodemask_0 = 1; /* nid: 0 */ unsigned long nodemask = 0; - unsigned long maxnode = 8; + unsigned long maxnode = BITS_PER_TYPE(nodemask); int policy; char *mem; int ret; diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h index 4ebae4269e68..469a22122157 100644 --- a/tools/testing/selftests/kvm/include/x86/processor.h +++ b/tools/testing/selftests/kvm/include/x86/processor.h @@ -557,6 +557,11 @@ static inline uint64_t get_cr0(void) return cr0; } +static inline void set_cr0(uint64_t val) +{ + __asm__ __volatile__("mov %0, %%cr0" : : "r" (val) : "memory"); +} + static inline uint64_t get_cr3(void) { uint64_t cr3; @@ -566,6 +571,11 @@ static inline uint64_t get_cr3(void) return cr3; } +static inline void set_cr3(uint64_t val) +{ + __asm__ __volatile__("mov %0, %%cr3" : : "r" (val) : "memory"); +} + static inline uint64_t get_cr4(void) { uint64_t cr4; @@ -580,6 +590,19 @@ static inline void set_cr4(uint64_t val) __asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory"); } +static inline uint64_t get_cr8(void) +{ + uint64_t cr8; + + __asm__ __volatile__("mov %%cr8, %[cr8]" : [cr8]"=r"(cr8)); + return cr8; +} + +static inline void set_cr8(uint64_t val) +{ + __asm__ __volatile__("mov %0, %%cr8" : : "r" (val) : "memory"); +} + static inline void set_idt(const struct desc_ptr *idt_desc) { __asm__ __volatile__("lidt %0"::"m"(*idt_desc)); diff --git a/tools/testing/selftests/kvm/include/x86/smm.h b/tools/testing/selftests/kvm/include/x86/smm.h new file mode 100644 index 000000000000..19337c34f13e --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86/smm.h @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef SELFTEST_KVM_SMM_H +#define SELFTEST_KVM_SMM_H + +#include "kvm_util.h" + +#define SMRAM_SIZE 65536 +#define SMRAM_MEMSLOT ((1 << 16) | 1) +#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) + +void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu, + uint64_t smram_gpa, + const void *smi_handler, size_t handler_size); + +void inject_smi(struct kvm_vcpu *vcpu); + +#endif /* SELFTEST_KVM_SMM_H */ diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c index fab18e9be66c..23a44941e283 100644 --- a/tools/testing/selftests/kvm/lib/x86/processor.c +++ b/tools/testing/selftests/kvm/lib/x86/processor.c @@ -8,6 +8,7 @@ #include "kvm_util.h" #include "pmu.h" #include "processor.h" +#include "smm.h" #include "svm_util.h" #include "sev.h" #include "vmx.h" @@ -1444,3 +1445,28 @@ bool kvm_arch_has_default_irqchip(void) { return true; } + +void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu, + uint64_t smram_gpa, + const void *smi_handler, size_t handler_size) +{ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, smram_gpa, + SMRAM_MEMSLOT, SMRAM_PAGES, 0); + TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, smram_gpa, + SMRAM_MEMSLOT) == smram_gpa, + "Could not allocate guest physical addresses for SMRAM"); + + memset(addr_gpa2hva(vm, smram_gpa), 0x0, SMRAM_SIZE); + memcpy(addr_gpa2hva(vm, smram_gpa) + 0x8000, smi_handler, handler_size); + vcpu_set_msr(vcpu, MSR_IA32_SMBASE, smram_gpa); +} + +void inject_smi(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_events events; + + vcpu_events_get(vcpu, &events); + events.smi.pending = 1; + events.flags |= KVM_VCPUEVENT_VALID_SMM; + vcpu_events_set(vcpu, &events); +} diff --git a/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c b/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c new file mode 100644 index 000000000000..af7c90103396 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2026, Red Hat, Inc. + * + * Test that vmx_leave_smm() validates vmcs12 controls before re-entering + * nested guest mode on RSM. + */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "smm.h" +#include "hyperv.h" +#include "vmx.h" + +#define SMRAM_GPA 0x1000000 +#define SMRAM_STAGE 0xfe + +#define SYNC_PORT 0xe + +#define STR(x) #x +#define XSTR(s) STR(s) + +/* + * SMI handler: runs in real-address mode. + * Reports SMRAM_STAGE via port IO, then does RSM. + */ +static uint8_t smi_handler[] = { + 0xb0, SMRAM_STAGE, /* mov $SMRAM_STAGE, %al */ + 0xe4, SYNC_PORT, /* in $SYNC_PORT, %al */ + 0x0f, 0xaa, /* rsm */ +}; + +static inline void sync_with_host(uint64_t phase) +{ + asm volatile("in $" XSTR(SYNC_PORT) ", %%al \n" + : "+a" (phase)); +} + +static void l2_guest_code(void) +{ + sync_with_host(1); + + /* After SMI+RSM with invalid controls, we should not reach here. */ + vmcall(); +} + +static void guest_code(struct vmx_pages *vmx_pages, + struct hyperv_test_pages *hv_pages) +{ +#define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + /* Set up Hyper-V enlightenments and eVMCS */ + wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); + enable_vp_assist(hv_pages->vp_assist_gpa, hv_pages->vp_assist); + evmcs_enable(); + + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_ASSERT(load_evmcs(hv_pages)); + prepare_vmcs(vmx_pages, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + GUEST_ASSERT(!vmlaunch()); + + /* L2 exits via vmcall if test fails */ + sync_with_host(2); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t vmx_pages_gva = 0, hv_pages_gva = 0; + struct hyperv_test_pages *hv; + struct hv_enlightened_vmcs *evmcs; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct kvm_regs regs; + int stage_reported; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_SMM)); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + setup_smram(vm, vcpu, SMRAM_GPA, smi_handler, sizeof(smi_handler)); + + vcpu_set_hv_cpuid(vcpu); + vcpu_enable_evmcs(vcpu); + vcpu_alloc_vmx(vm, &vmx_pages_gva); + hv = vcpu_alloc_hyperv_test_pages(vm, &hv_pages_gva); + vcpu_args_set(vcpu, 2, vmx_pages_gva, hv_pages_gva); + + vcpu_run(vcpu); + + /* L2 is running and syncs with host. */ + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + vcpu_regs_get(vcpu, ®s); + stage_reported = regs.rax & 0xff; + TEST_ASSERT(stage_reported == 1, + "Expected stage 1, got %d", stage_reported); + + /* Inject SMI while L2 is running. */ + inject_smi(vcpu); + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + vcpu_regs_get(vcpu, ®s); + stage_reported = regs.rax & 0xff; + TEST_ASSERT(stage_reported == SMRAM_STAGE, + "Expected SMM handler stage %#x, got %#x", + SMRAM_STAGE, stage_reported); + + /* + * Guest is now paused in the SMI handler, about to execute RSM. + * Hack the eVMCS page to set-up invalid pin-based execution + * control (PIN_BASED_VIRTUAL_NMIS without PIN_BASED_NMI_EXITING). + */ + evmcs = hv->enlightened_vmcs_hva; + evmcs->pin_based_vm_exec_control |= PIN_BASED_VIRTUAL_NMIS; + evmcs->hv_clean_fields = 0; + + /* + * Trigger copy_enlightened_to_vmcs12() via KVM_GET_NESTED_STATE, + * copying the invalid pin_based_vm_exec_control into cached_vmcs12. + */ + union { + struct kvm_nested_state state; + char state_[16384]; + } nested_state_buf; + + memset(&nested_state_buf, 0, sizeof(nested_state_buf)); + nested_state_buf.state.size = sizeof(nested_state_buf); + vcpu_nested_state_get(vcpu, &nested_state_buf.state); + + /* + * Resume the guest. The SMI handler executes RSM, which calls + * vmx_leave_smm(). nested_vmx_check_controls() should detect + * VIRTUAL_NMIS without NMI_EXITING and cause a triple fault. + */ + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_SHUTDOWN); + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86/sev_smoke_test.c b/tools/testing/selftests/kvm/x86/sev_smoke_test.c index 86ad1c7d068f..8bd37a476f15 100644 --- a/tools/testing/selftests/kvm/x86/sev_smoke_test.c +++ b/tools/testing/selftests/kvm/x86/sev_smoke_test.c @@ -13,6 +13,30 @@ #include "linux/psp-sev.h" #include "sev.h" +static void guest_sev_test_msr(uint32_t msr) +{ + uint64_t val = rdmsr(msr); + + wrmsr(msr, val); + GUEST_ASSERT(val == rdmsr(msr)); +} + +#define guest_sev_test_reg(reg) \ +do { \ + uint64_t val = get_##reg(); \ + \ + set_##reg(val); \ + GUEST_ASSERT(val == get_##reg()); \ +} while (0) + +static void guest_sev_test_regs(void) +{ + guest_sev_test_msr(MSR_EFER); + guest_sev_test_reg(cr0); + guest_sev_test_reg(cr3); + guest_sev_test_reg(cr4); + guest_sev_test_reg(cr8); +} #define XFEATURE_MASK_X87_AVX (XFEATURE_MASK_FP | XFEATURE_MASK_SSE | XFEATURE_MASK_YMM) @@ -24,6 +48,8 @@ static void guest_snp_code(void) GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_ES_ENABLED); GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_SNP_ENABLED); + guest_sev_test_regs(); + wrmsr(MSR_AMD64_SEV_ES_GHCB, GHCB_MSR_TERM_REQ); vmgexit(); } @@ -34,6 +60,8 @@ static void guest_sev_es_code(void) GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED); GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ES_ENABLED); + guest_sev_test_regs(); + /* * TODO: Add GHCB and ucall support for SEV-ES guests. For now, simply * force "termination" to signal "done" via the GHCB MSR protocol. @@ -47,6 +75,8 @@ static void guest_sev_code(void) GUEST_ASSERT(this_cpu_has(X86_FEATURE_SEV)); GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED); + guest_sev_test_regs(); + GUEST_DONE(); } diff --git a/tools/testing/selftests/kvm/x86/smm_test.c b/tools/testing/selftests/kvm/x86/smm_test.c index 55c88d664a94..ade8412bf94a 100644 --- a/tools/testing/selftests/kvm/x86/smm_test.c +++ b/tools/testing/selftests/kvm/x86/smm_test.c @@ -14,13 +14,11 @@ #include "test_util.h" #include "kvm_util.h" +#include "smm.h" #include "vmx.h" #include "svm_util.h" -#define SMRAM_SIZE 65536 -#define SMRAM_MEMSLOT ((1 << 16) | 1) -#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) #define SMRAM_GPA 0x1000000 #define SMRAM_STAGE 0xfe @@ -113,18 +111,6 @@ static void guest_code(void *arg) sync_with_host(DONE); } -void inject_smi(struct kvm_vcpu *vcpu) -{ - struct kvm_vcpu_events events; - - vcpu_events_get(vcpu, &events); - - events.smi.pending = 1; - events.flags |= KVM_VCPUEVENT_VALID_SMM; - - vcpu_events_set(vcpu, &events); -} - int main(int argc, char *argv[]) { vm_vaddr_t nested_gva = 0; @@ -140,16 +126,7 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA, - SMRAM_MEMSLOT, SMRAM_PAGES, 0); - TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, SMRAM_GPA, SMRAM_MEMSLOT) - == SMRAM_GPA, "could not allocate guest physical addresses?"); - - memset(addr_gpa2hva(vm, SMRAM_GPA), 0x0, SMRAM_SIZE); - memcpy(addr_gpa2hva(vm, SMRAM_GPA) + 0x8000, smi_handler, - sizeof(smi_handler)); - - vcpu_set_msr(vcpu, MSR_IA32_SMBASE, SMRAM_GPA); + setup_smram(vm, vcpu, SMRAM_GPA, smi_handler, sizeof(smi_handler)); if (kvm_has_cap(KVM_CAP_NESTED_STATE)) { if (kvm_cpu_has(X86_FEATURE_SVM)) diff --git a/tools/testing/selftests/powerpc/copyloops/.gitignore b/tools/testing/selftests/powerpc/copyloops/.gitignore index 7283e8b07b75..80d4270a71ac 100644 --- a/tools/testing/selftests/powerpc/copyloops/.gitignore +++ b/tools/testing/selftests/powerpc/copyloops/.gitignore @@ -2,8 +2,8 @@ copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 -copyuser_p7_t0 -copyuser_p7_t1 +copyuser_p7 +copyuser_p7_vmx memcpy_64_t0 memcpy_64_t1 memcpy_64_t2 diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile index 42940f92d832..0c8efb0bddeb 100644 --- a/tools/testing/selftests/powerpc/copyloops/Makefile +++ b/tools/testing/selftests/powerpc/copyloops/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 TEST_GEN_PROGS := copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 \ - copyuser_p7_t0 copyuser_p7_t1 \ + copyuser_p7 copyuser_p7_vmx \ memcpy_64_t0 memcpy_64_t1 memcpy_64_t2 \ memcpy_p7_t0 memcpy_p7_t1 copy_mc_64 \ copyuser_64_exc_t0 copyuser_64_exc_t1 copyuser_64_exc_t2 \ @@ -28,10 +28,15 @@ $(OUTPUT)/copyuser_64_t%: copyuser_64.S $(EXTRA_SOURCES) -D SELFTEST_CASE=$(subst copyuser_64_t,,$(notdir $@)) \ -o $@ $^ -$(OUTPUT)/copyuser_p7_t%: copyuser_power7.S $(EXTRA_SOURCES) +$(OUTPUT)/copyuser_p7: copyuser_power7.S $(EXTRA_SOURCES) $(CC) $(CPPFLAGS) $(CFLAGS) \ -D COPY_LOOP=test___copy_tofrom_user_power7 \ - -D SELFTEST_CASE=$(subst copyuser_p7_t,,$(notdir $@)) \ + -o $@ $^ + +$(OUTPUT)/copyuser_p7_vmx: copyuser_power7.S $(EXTRA_SOURCES) ../utils.c + $(CC) $(CPPFLAGS) $(CFLAGS) \ + -D COPY_LOOP=test___copy_tofrom_user_power7_vmx \ + -D VMX_TEST \ -o $@ $^ # Strictly speaking, we only need the memcpy_64 test cases for big-endian diff --git a/tools/testing/selftests/powerpc/copyloops/stubs.S b/tools/testing/selftests/powerpc/copyloops/stubs.S index ec8bcf2bf1c2..3a9cb8c9a3ee 100644 --- a/tools/testing/selftests/powerpc/copyloops/stubs.S +++ b/tools/testing/selftests/powerpc/copyloops/stubs.S @@ -1,13 +1,5 @@ #include <asm/ppc_asm.h> -FUNC_START(enter_vmx_usercopy) - li r3,1 - blr - -FUNC_START(exit_vmx_usercopy) - li r3,0 - blr - FUNC_START(enter_vmx_ops) li r3,1 blr diff --git a/tools/testing/selftests/powerpc/copyloops/validate.c b/tools/testing/selftests/powerpc/copyloops/validate.c index 0f6873618552..fb822534fbe9 100644 --- a/tools/testing/selftests/powerpc/copyloops/validate.c +++ b/tools/testing/selftests/powerpc/copyloops/validate.c @@ -12,6 +12,10 @@ #define BUFLEN (MAX_LEN+MAX_OFFSET+2*MIN_REDZONE) #define POISON 0xa5 +#ifdef VMX_TEST +#define VMX_COPY_THRESHOLD 3328 +#endif + unsigned long COPY_LOOP(void *to, const void *from, unsigned long size); static void do_one(char *src, char *dst, unsigned long src_off, @@ -81,8 +85,12 @@ int test_copy_loop(void) /* Fill with sequential bytes */ for (i = 0; i < BUFLEN; i++) fill[i] = i & 0xff; - +#ifdef VMX_TEST + /* Force sizes above kernel VMX threshold (3328) */ + for (len = VMX_COPY_THRESHOLD + 1; len < MAX_LEN; len++) { +#else for (len = 1; len < MAX_LEN; len++) { +#endif for (src_off = 0; src_off < MAX_OFFSET; src_off++) { for (dst_off = 0; dst_off < MAX_OFFSET; dst_off++) { do_one(src, dst, src_off, dst_off, len, @@ -96,5 +104,10 @@ int test_copy_loop(void) int main(void) { +#ifdef VMX_TEST + /* Skip if Altivec not present */ + SKIP_IF_MSG(!have_hwcap(PPC_FEATURE_HAS_ALTIVEC), "ALTIVEC not supported"); +#endif + return test_harness(test_copy_loop, str(COPY_LOOP)); } diff --git a/tools/testing/selftests/sched_ext/util.c b/tools/testing/selftests/sched_ext/util.c index e47769c91918..2111329ed289 100644 --- a/tools/testing/selftests/sched_ext/util.c +++ b/tools/testing/selftests/sched_ext/util.c @@ -60,11 +60,11 @@ int file_write_long(const char *path, long val) char buf[64]; int ret; - ret = sprintf(buf, "%lu", val); + ret = sprintf(buf, "%ld", val); if (ret < 0) return ret; - if (write_text(path, buf, sizeof(buf)) <= 0) + if (write_text(path, buf, ret) <= 0) return -1; return 0; diff --git a/virt/kvm/binary_stats.c b/virt/kvm/binary_stats.c index eefca6c69f51..76ce697c773b 100644 --- a/virt/kvm/binary_stats.c +++ b/virt/kvm/binary_stats.c @@ -50,7 +50,7 @@ * Return: the number of bytes that has been successfully read */ ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, - const struct _kvm_stats_desc *desc, + const struct kvm_stats_desc *desc, void *stats, size_t size_stats, char __user *user_buffer, size_t size, loff_t *offset) { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 1bc1da66b4b0..9093251beb39 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -973,9 +973,9 @@ static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots) kvm_free_memslot(kvm, memslot); } -static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc) +static umode_t kvm_stats_debugfs_mode(const struct kvm_stats_desc *desc) { - switch (pdesc->desc.flags & KVM_STATS_TYPE_MASK) { + switch (desc->flags & KVM_STATS_TYPE_MASK) { case KVM_STATS_TYPE_INSTANT: return 0444; case KVM_STATS_TYPE_CUMULATIVE: @@ -1010,7 +1010,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname) struct dentry *dent; char dir_name[ITOA_MAX_LEN * 2]; struct kvm_stat_data *stat_data; - const struct _kvm_stats_desc *pdesc; + const struct kvm_stats_desc *pdesc; int i, ret = -ENOMEM; int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + kvm_vcpu_stats_header.num_desc; @@ -6171,11 +6171,11 @@ static int kvm_stat_data_get(void *data, u64 *val) switch (stat_data->kind) { case KVM_STAT_VM: r = kvm_get_stat_per_vm(stat_data->kvm, - stat_data->desc->desc.offset, val); + stat_data->desc->offset, val); break; case KVM_STAT_VCPU: r = kvm_get_stat_per_vcpu(stat_data->kvm, - stat_data->desc->desc.offset, val); + stat_data->desc->offset, val); break; } @@ -6193,11 +6193,11 @@ static int kvm_stat_data_clear(void *data, u64 val) switch (stat_data->kind) { case KVM_STAT_VM: r = kvm_clear_stat_per_vm(stat_data->kvm, - stat_data->desc->desc.offset); + stat_data->desc->offset); break; case KVM_STAT_VCPU: r = kvm_clear_stat_per_vcpu(stat_data->kvm, - stat_data->desc->desc.offset); + stat_data->desc->offset); break; } @@ -6345,7 +6345,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) static void kvm_init_debug(void) { const struct file_operations *fops; - const struct _kvm_stats_desc *pdesc; + const struct kvm_stats_desc *pdesc; int i; kvm_debugfs_dir = debugfs_create_dir("kvm", NULL); @@ -6358,7 +6358,7 @@ static void kvm_init_debug(void) fops = &vm_stat_readonly_fops; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm_debugfs_dir, - (void *)(long)pdesc->desc.offset, fops); + (void *)(long)pdesc->offset, fops); } for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) { @@ -6369,7 +6369,7 @@ static void kvm_init_debug(void) fops = &vcpu_stat_readonly_fops; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm_debugfs_dir, - (void *)(long)pdesc->desc.offset, fops); + (void *)(long)pdesc->offset, fops); } } |