diff options
821 files changed, 11508 insertions, 6555 deletions
@@ -416,6 +416,7 @@ Kenneth W Chen <kenneth.w.chen@intel.com> Kenneth Westfield <quic_kwestfie@quicinc.com> <kwestfie@codeaurora.org> Kiran Gunda <quic_kgunda@quicinc.com> <kgunda@codeaurora.org> Kirill Tkhai <tkhai@ya.ru> <ktkhai@virtuozzo.com> +Kirill A. Shutemov <kas@kernel.org> <kirill.shutemov@linux.intel.com> Kishon Vijay Abraham I <kishon@kernel.org> <kishon@ti.com> Konrad Dybcio <konradybcio@kernel.org> <konrad.dybcio@linaro.org> Konrad Dybcio <konradybcio@kernel.org> <konrad.dybcio@somainline.org> @@ -693,6 +694,10 @@ Sedat Dilek <sedat.dilek@gmail.com> <sedat.dilek@credativ.de> Senthilkumar N L <quic_snlakshm@quicinc.com> <snlakshm@codeaurora.org> Serge Hallyn <sergeh@kernel.org> <serge.hallyn@canonical.com> Serge Hallyn <sergeh@kernel.org> <serue@us.ibm.com> +Sergey Senozhatsky <senozhatsky@chromium.org> <sergey.senozhatsky.work@gmail.com> +Sergey Senozhatsky <senozhatsky@chromium.org> <sergey.senozhatsky@gmail.com> +Sergey Senozhatsky <senozhatsky@chromium.org> <sergey.senozhatsky@mail.by> +Sergey Senozhatsky <senozhatsky@chromium.org> <senozhatsky@google.com> Seth Forshee <sforshee@kernel.org> <seth.forshee@canonical.com> Shakeel Butt <shakeel.butt@linux.dev> <shakeelb@google.com> Shannon Nelson <sln@onemain.com> <shannon.nelson@amd.com> @@ -1397,6 +1397,10 @@ N: Thomas Gleixner E: tglx@linutronix.de D: NAND flash hardware support, JFFS2 on NAND flash +N: Jérôme Glisse +E: jglisse@redhat.com +D: HMM - Heterogeneous Memory Management + N: Richard E. Gooch E: rgooch@atnf.csiro.au D: parent process death signal to children diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index bf85f4de6862..ab8cd337f43a 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -584,6 +584,7 @@ What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/spectre_v1 /sys/devices/system/cpu/vulnerabilities/spectre_v2 /sys/devices/system/cpu/vulnerabilities/srbds + /sys/devices/system/cpu/vulnerabilities/tsa /sys/devices/system/cpu/vulnerabilities/tsx_async_abort Date: January 2018 Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 0cc35a14afbe..bd98ea3175ec 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1732,12 +1732,6 @@ The following nested keys are defined. numa_hint_faults (npn) Number of NUMA hinting faults. - numa_task_migrated (npn) - Number of task migration by NUMA balancing. - - numa_task_swapped (npn) - Number of task swap by NUMA balancing. - pgdemote_kswapd Number of pages demoted by kswapd. diff --git a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst index 1302fd1b55e8..6dba18dbb9ab 100644 --- a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst +++ b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst @@ -157,9 +157,7 @@ This is achieved by using the otherwise unused and obsolete VERW instruction in combination with a microcode update. The microcode clears the affected CPU buffers when the VERW instruction is executed. -Kernel reuses the MDS function to invoke the buffer clearing: - - mds_clear_cpu_buffers() +Kernel does the buffer clearing with x86_clear_cpu_buffers(). On MDS affected CPUs, the kernel already invokes CPU buffer clear on kernel/userspace, hypervisor/guest and C-state (idle) transitions. No diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index f1f2c0874da9..07e22ba5bfe3 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -7488,6 +7488,19 @@ having this key zero'ed is acceptable. E.g. in testing scenarios. + tsa= [X86] Control mitigation for Transient Scheduler + Attacks on AMD CPUs. Search the following in your + favourite search engine for more details: + + "Technical guidance for mitigating transient scheduler + attacks". + + off - disable the mitigation + on - enable the mitigation (default) + user - mitigate only user/kernel transitions + vm - mitigate only guest/host transitions + + tsc= Disable clocksource stability checks for TSC. Format: <string> [x86] reliable: mark tsc clocksource as reliable, this diff --git a/Documentation/arch/x86/mds.rst b/Documentation/arch/x86/mds.rst index 5a2e6c0ef04a..3518671e1a85 100644 --- a/Documentation/arch/x86/mds.rst +++ b/Documentation/arch/x86/mds.rst @@ -93,7 +93,7 @@ enters a C-state. The kernel provides a function to invoke the buffer clearing: - mds_clear_cpu_buffers() + x86_clear_cpu_buffers() Also macro CLEAR_CPU_BUFFERS can be used in ASM late in exit-to-user path. Other than CFLAGS.ZF, this macro doesn't clobber any registers. @@ -185,9 +185,9 @@ Mitigation points idle clearing would be a window dressing exercise and is therefore not activated. - The invocation is controlled by the static key mds_idle_clear which is - switched depending on the chosen mitigation mode and the SMT state of - the system. + The invocation is controlled by the static key cpu_buf_idle_clear which is + switched depending on the chosen mitigation mode and the SMT state of the + system. The buffer clear is only invoked before entering the C-State to prevent that stale data from the idling CPU from spilling to the Hyper-Thread diff --git a/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml b/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml index 2985c8c717d7..5403242545ab 100644 --- a/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml +++ b/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml @@ -52,6 +52,9 @@ properties: '#clock-cells': const: 1 + '#reset-cells': + const: 1 + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml index 29f12d650442..1a5209139e13 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml @@ -223,12 +223,6 @@ allOf: - required: - pwms - - oneOf: - - required: - - interrupts - - required: - - io-backends - - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.yaml b/Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.yaml index d1a6103fc37a..f3242dc0e7e6 100644 --- a/Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.yaml +++ b/Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.yaml @@ -21,7 +21,7 @@ properties: vlogic-supply: true interrupts: - minItems: 1 + maxItems: 1 description: Interrupt mapping for the trigger interrupt from the internal oscillator. diff --git a/Documentation/devicetree/bindings/media/allwinner,sun6i-a31-csi.yaml b/Documentation/devicetree/bindings/media/allwinner,sun6i-a31-csi.yaml index b3d6db922693..1aa5775ba2bc 100644 --- a/Documentation/devicetree/bindings/media/allwinner,sun6i-a31-csi.yaml +++ b/Documentation/devicetree/bindings/media/allwinner,sun6i-a31-csi.yaml @@ -110,7 +110,7 @@ examples: reg = <0x01cb4000 0x1000>; interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>; clocks = <&ccu CLK_BUS_CSI>, - <&ccu CLK_CSI1_SCLK>, + <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI>; clock-names = "bus", "mod", diff --git a/Documentation/devicetree/bindings/media/allwinner,sun6i-a31-isp.yaml b/Documentation/devicetree/bindings/media/allwinner,sun6i-a31-isp.yaml index a61a76bb611c..3ea4a4290f23 100644 --- a/Documentation/devicetree/bindings/media/allwinner,sun6i-a31-isp.yaml +++ b/Documentation/devicetree/bindings/media/allwinner,sun6i-a31-isp.yaml @@ -79,7 +79,7 @@ examples: reg = <0x01cb8000 0x1000>; interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>; clocks = <&ccu CLK_BUS_CSI>, - <&ccu CLK_CSI1_SCLK>, + <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI>; clock-names = "bus", "mod", "ram"; resets = <&ccu RST_BUS_CSI>; diff --git a/Documentation/devicetree/bindings/media/allwinner,sun6i-a31-mipi-csi2.yaml b/Documentation/devicetree/bindings/media/allwinner,sun6i-a31-mipi-csi2.yaml index 54e15ab8a7f5..627b28e94354 100644 --- a/Documentation/devicetree/bindings/media/allwinner,sun6i-a31-mipi-csi2.yaml +++ b/Documentation/devicetree/bindings/media/allwinner,sun6i-a31-mipi-csi2.yaml @@ -103,7 +103,7 @@ examples: reg = <0x01cb1000 0x1000>; interrupts = <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>; clocks = <&ccu CLK_BUS_CSI>, - <&ccu CLK_CSI1_SCLK>; + <&ccu CLK_CSI_SCLK>; clock-names = "bus", "mod"; resets = <&ccu RST_BUS_CSI>; diff --git a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml index 7b6a2fde8175..19934d5c24e5 100644 --- a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml +++ b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml @@ -23,7 +23,7 @@ properties: - allwinner,sun20i-d1-emac - allwinner,sun50i-h6-emac - allwinner,sun50i-h616-emac0 - - allwinner,sun55i-a523-emac0 + - allwinner,sun55i-a523-gmac0 - const: allwinner,sun50i-a64-emac reg: diff --git a/Documentation/hwmon/ina238.rst b/Documentation/hwmon/ina238.rst index d1b93cf8627f..9a24da4786a4 100644 --- a/Documentation/hwmon/ina238.rst +++ b/Documentation/hwmon/ina238.rst @@ -65,7 +65,7 @@ Additional sysfs entries for sq52206 ------------------------------------ ======================= ======================================================= -energy1_input Energy measurement (mJ) +energy1_input Energy measurement (uJ) power1_input_highest Peak Power (uW) ======================= ======================================================= diff --git a/Documentation/netlink/specs/ovpn.yaml b/Documentation/netlink/specs/ovpn.yaml index 096c51f0c69a..ba76426a542d 100644 --- a/Documentation/netlink/specs/ovpn.yaml +++ b/Documentation/netlink/specs/ovpn.yaml @@ -161,6 +161,66 @@ attribute-sets: type: uint doc: Number of packets transmitted at the transport level - + name: peer-new-input + subset-of: peer + attributes: + - + name: id + - + name: remote-ipv4 + - + name: remote-ipv6 + - + name: remote-ipv6-scope-id + - + name: remote-port + - + name: socket + - + name: vpn-ipv4 + - + name: vpn-ipv6 + - + name: local-ipv4 + - + name: local-ipv6 + - + name: keepalive-interval + - + name: keepalive-timeout + - + name: peer-set-input + subset-of: peer + attributes: + - + name: id + - + name: remote-ipv4 + - + name: remote-ipv6 + - + name: remote-ipv6-scope-id + - + name: remote-port + - + name: vpn-ipv4 + - + name: vpn-ipv6 + - + name: local-ipv4 + - + name: local-ipv6 + - + name: keepalive-interval + - + name: keepalive-timeout + - + name: peer-del-input + subset-of: peer + attributes: + - + name: id + - name: keyconf attributes: - @@ -216,6 +276,33 @@ attribute-sets: obtain the actual cipher IV checks: exact-len: nonce-tail-size + + - + name: keyconf-get + subset-of: keyconf + attributes: + - + name: peer-id + - + name: slot + - + name: key-id + - + name: cipher-alg + - + name: keyconf-swap-input + subset-of: keyconf + attributes: + - + name: peer-id + - + name: keyconf-del-input + subset-of: keyconf + attributes: + - + name: peer-id + - + name: slot - name: ovpn attributes: @@ -235,12 +322,66 @@ attribute-sets: type: nest doc: Peer specific cipher configuration nested-attributes: keyconf + - + name: ovpn-peer-new-input + subset-of: ovpn + attributes: + - + name: ifindex + - + name: peer + nested-attributes: peer-new-input + - + name: ovpn-peer-set-input + subset-of: ovpn + attributes: + - + name: ifindex + - + name: peer + nested-attributes: peer-set-input + - + name: ovpn-peer-del-input + subset-of: ovpn + attributes: + - + name: ifindex + - + name: peer + nested-attributes: peer-del-input + - + name: ovpn-keyconf-get + subset-of: ovpn + attributes: + - + name: ifindex + - + name: keyconf + nested-attributes: keyconf-get + - + name: ovpn-keyconf-swap-input + subset-of: ovpn + attributes: + - + name: ifindex + - + name: keyconf + nested-attributes: keyconf-swap-input + - + name: ovpn-keyconf-del-input + subset-of: ovpn + attributes: + - + name: ifindex + - + name: keyconf + nested-attributes: keyconf-del-input operations: list: - name: peer-new - attribute-set: ovpn + attribute-set: ovpn-peer-new-input flags: [ admin-perm ] doc: Add a remote peer do: @@ -252,7 +393,7 @@ operations: - peer - name: peer-set - attribute-set: ovpn + attribute-set: ovpn-peer-set-input flags: [ admin-perm ] doc: modify a remote peer do: @@ -286,7 +427,7 @@ operations: - peer - name: peer-del - attribute-set: ovpn + attribute-set: ovpn-peer-del-input flags: [ admin-perm ] doc: Delete existing remote peer do: @@ -316,7 +457,7 @@ operations: - keyconf - name: key-get - attribute-set: ovpn + attribute-set: ovpn-keyconf-get flags: [ admin-perm ] doc: Retrieve non-sensitive data about peer key and cipher do: @@ -331,7 +472,7 @@ operations: - keyconf - name: key-swap - attribute-set: ovpn + attribute-set: ovpn-keyconf-swap-input flags: [ admin-perm ] doc: Swap primary and secondary session keys for a specific peer do: @@ -350,7 +491,7 @@ operations: mcgrp: peers - name: key-del - attribute-set: ovpn + attribute-set: ovpn-keyconf-del-input flags: [ admin-perm ] doc: Delete cipher key for a specific peer do: diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 9abf93ee5f65..fcb783735dd1 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -2006,7 +2006,14 @@ frequency is KHz. If the KVM_CAP_VM_TSC_CONTROL capability is advertised, this can also be used as a vm ioctl to set the initial tsc frequency of subsequently -created vCPUs. +created vCPUs. Note, the vm ioctl is only allowed prior to creating vCPUs. + +For TSC protected Confidential Computing (CoCo) VMs where TSC frequency +is configured once at VM scope and remains unchanged during VM's +lifetime, the vm ioctl should be used to configure the TSC frequency +and the vcpu ioctl is not supported. + +Example of such CoCo VMs: TDX guests. 4.56 KVM_GET_TSC_KHZ -------------------- @@ -7196,6 +7203,10 @@ The valid value for 'flags' is: u64 leaf; u64 r11, r12, r13, r14; } get_tdvmcall_info; + struct { + u64 ret; + u64 vector; + } setup_event_notify; }; } tdx; @@ -7210,21 +7221,24 @@ number from register R11. The remaining field of the union provide the inputs and outputs of the TDVMCALL. Currently the following values of ``nr`` are defined: -* ``TDVMCALL_GET_QUOTE``: the guest has requested to generate a TD-Quote -signed by a service hosting TD-Quoting Enclave operating on the host. -Parameters and return value are in the ``get_quote`` field of the union. -The ``gpa`` field and ``size`` specify the guest physical address -(without the shared bit set) and the size of a shared-memory buffer, in -which the TDX guest passes a TD Report. The ``ret`` field represents -the return value of the GetQuote request. When the request has been -queued successfully, the TDX guest can poll the status field in the -shared-memory area to check whether the Quote generation is completed or -not. When completed, the generated Quote is returned via the same buffer. - -* ``TDVMCALL_GET_TD_VM_CALL_INFO``: the guest has requested the support -status of TDVMCALLs. The output values for the given leaf should be -placed in fields from ``r11`` to ``r14`` of the ``get_tdvmcall_info`` -field of the union. + * ``TDVMCALL_GET_QUOTE``: the guest has requested to generate a TD-Quote + signed by a service hosting TD-Quoting Enclave operating on the host. + Parameters and return value are in the ``get_quote`` field of the union. + The ``gpa`` field and ``size`` specify the guest physical address + (without the shared bit set) and the size of a shared-memory buffer, in + which the TDX guest passes a TD Report. The ``ret`` field represents + the return value of the GetQuote request. When the request has been + queued successfully, the TDX guest can poll the status field in the + shared-memory area to check whether the Quote generation is completed or + not. When completed, the generated Quote is returned via the same buffer. + + * ``TDVMCALL_GET_TD_VM_CALL_INFO``: the guest has requested the support + status of TDVMCALLs. The output values for the given leaf should be + placed in fields from ``r11`` to ``r14`` of the ``get_tdvmcall_info`` + field of the union. + + * ``TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT``: the guest has requested to + set up a notification interrupt for vector ``vector``. KVM may add support for more values in the future that may cause a userspace exit, even without calls to ``KVM_ENABLE_CAP`` or similar. In this case, @@ -7837,6 +7851,7 @@ Valid bits in args[0] are:: #define KVM_X86_DISABLE_EXITS_HLT (1 << 1) #define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) #define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3) + #define KVM_X86_DISABLE_EXITS_APERFMPERF (1 << 4) Enabling this capability on a VM provides userspace with a way to no longer intercept some instructions for improved latency in some @@ -7847,6 +7862,28 @@ all such vmexits. Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits. +Virtualizing the ``IA32_APERF`` and ``IA32_MPERF`` MSRs requires more +than just disabling APERF/MPERF exits. While both Intel and AMD +document strict usage conditions for these MSRs--emphasizing that only +the ratio of their deltas over a time interval (T0 to T1) is +architecturally defined--simply passing through the MSRs can still +produce an incorrect ratio. + +This erroneous ratio can occur if, between T0 and T1: + +1. The vCPU thread migrates between logical processors. +2. Live migration or suspend/resume operations take place. +3. Another task shares the vCPU's logical processor. +4. C-states lower than C0 are emulated (e.g., via HLT interception). +5. The guest TSC frequency doesn't match the host TSC frequency. + +Due to these complexities, KVM does not automatically associate this +passthrough capability with the guest CPUID bit, +``CPUID.6:ECX.APERFMPERF[bit 0]``. Userspace VMMs that deem this +mechanism adequate for virtualizing the ``IA32_APERF`` and +``IA32_MPERF`` MSRs must set the guest CPUID bit explicitly. + + 7.14 KVM_CAP_S390_HPAGE_1M -------------------------- @@ -8373,7 +8410,7 @@ core crystal clock frequency, if a non-zero CPUID 0x15 is exposed to the guest. 7.36 KVM_CAP_DIRTY_LOG_RING/KVM_CAP_DIRTY_LOG_RING_ACQ_REL ---------------------------------------------------------- -:Architectures: x86, arm64 +:Architectures: x86, arm64, riscv :Type: vm :Parameters: args[0] - size of the dirty log ring diff --git a/Documentation/virt/kvm/review-checklist.rst b/Documentation/virt/kvm/review-checklist.rst index dc01aea4057b..debac54e14e7 100644 --- a/Documentation/virt/kvm/review-checklist.rst +++ b/Documentation/virt/kvm/review-checklist.rst @@ -7,7 +7,7 @@ Review checklist for kvm patches 1. The patch must follow Documentation/process/coding-style.rst and Documentation/process/submitting-patches.rst. -2. Patches should be against kvm.git master branch. +2. Patches should be against kvm.git master or next branches. 3. If the patch introduces or modifies a new userspace API: - the API must be documented in Documentation/virt/kvm/api.rst @@ -18,10 +18,10 @@ Review checklist for kvm patches 5. New features must default to off (userspace should explicitly request them). Performance improvements can and should default to on. -6. New cpu features should be exposed via KVM_GET_SUPPORTED_CPUID2 +6. New cpu features should be exposed via KVM_GET_SUPPORTED_CPUID2, + or its equivalent for non-x86 architectures -7. Emulator changes should be accompanied by unit tests for qemu-kvm.git - kvm/test directory. +7. The feature should be testable (see below). 8. Changes should be vendor neutral when possible. Changes to common code are better than duplicating changes to vendor code. @@ -36,6 +36,87 @@ Review checklist for kvm patches 11. New guest visible features must either be documented in a hardware manual or be accompanied by documentation. -12. Features must be robust against reset and kexec - for example, shared - host/guest memory must be unshared to prevent the host from writing to - guest memory that the guest has not reserved for this purpose. +Testing of KVM code +------------------- + +All features contributed to KVM, and in many cases bugfixes too, should be +accompanied by some kind of tests and/or enablement in open source guests +and VMMs. KVM is covered by multiple test suites: + +*Selftests* + These are low level tests that allow granular testing of kernel APIs. + This includes API failure scenarios, invoking APIs after specific + guest instructions, and testing multiple calls to ``KVM_CREATE_VM`` + within a single test. They are included in the kernel tree at + ``tools/testing/selftests/kvm``. + +``kvm-unit-tests`` + A collection of small guests that test CPU and emulated device features + from a guest's perspective. They run under QEMU or ``kvmtool``, and + are generally not KVM-specific: they can be run with any accelerator + that QEMU support or even on bare metal, making it possible to compare + behavior across hypervisors and processor families. + +Functional test suites + Various sets of functional tests exist, such as QEMU's ``tests/functional`` + suite and `avocado-vt <https://avocado-vt.readthedocs.io/en/latest/>`__. + These typically involve running a full operating system in a virtual + machine. + +The best testing approach depends on the feature's complexity and +operation. Here are some examples and guidelines: + +New instructions (no new registers or APIs) + The corresponding CPU features (if applicable) should be made available + in QEMU. If the instructions require emulation support or other code in + KVM, it is worth adding coverage to ``kvm-unit-tests`` or selftests; + the latter can be a better choice if the instructions relate to an API + that already has good selftest coverage. + +New hardware features (new registers, no new APIs) + These should be tested via ``kvm-unit-tests``; this more or less implies + supporting them in QEMU and/or ``kvmtool``. In some cases selftests + can be used instead, similar to the previous case, or specifically to + test corner cases in guest state save/restore. + +Bug fixes and performance improvements + These usually do not introduce new APIs, but it's worth sharing + any benchmarks and tests that will validate your contribution, + ideally in the form of regression tests. Tests and benchmarks + can be included in either ``kvm-unit-tests`` or selftests, depending + on the specifics of your change. Selftests are especially useful for + regression tests because they are included directly in Linux's tree. + +Large scale internal changes + While it's difficult to provide a single policy, you should ensure that + the changed code is covered by either ``kvm-unit-tests`` or selftests. + In some cases the affected code is run for any guests and functional + tests suffice. Explain your testing process in the cover letter, + as that can help identify gaps in existing test suites. + +New APIs + It is important to demonstrate your use case. This can be as simple as + explaining that the feature is already in use on bare metal, or it can be + a proof-of-concept implementation in userspace. The latter need not be + open source, though that is of course preferrable for easier testing. + Selftests should test corner cases of the APIs, and should also cover + basic host and guest operation if no open source VMM uses the feature. + +Bigger features, usually spanning host and guest + These should be supported by Linux guests, with limited exceptions for + Hyper-V features that are testable on Windows guests. It is strongly + suggested that the feature be usable with an open source host VMM, such + as at least one of QEMU or crosvm, and guest firmware. Selftests should + test at least API error cases. Guest operation can be covered by + either selftests of ``kvm-unit-tests`` (this is especially important for + paravirtualized and Windows-only features). Strong selftest coverage + can also be a replacement for implementation in an open source VMM, + but this is generally not recommended. + +Following the above suggestions for testing in selftests and +``kvm-unit-tests`` will make it easier for the maintainers to review +and accept your code. In fact, even before you contribute your changes +upstream it will make it easier for you to develop for KVM. + +Of course, the KVM maintainers reserve the right to require more tests, +though they may also waive the requirement from time to time. diff --git a/Documentation/virt/kvm/x86/intel-tdx.rst b/Documentation/virt/kvm/x86/intel-tdx.rst index 76bdd95334d6..5efac62c92c7 100644 --- a/Documentation/virt/kvm/x86/intel-tdx.rst +++ b/Documentation/virt/kvm/x86/intel-tdx.rst @@ -79,7 +79,20 @@ to be configured to the TDX guest. struct kvm_tdx_capabilities { __u64 supported_attrs; __u64 supported_xfam; - __u64 reserved[254]; + + /* TDG.VP.VMCALL hypercalls executed in kernel and forwarded to + * userspace, respectively + */ + __u64 kernel_tdvmcallinfo_1_r11; + __u64 user_tdvmcallinfo_1_r11; + + /* TDG.VP.VMCALL instruction executions subfunctions executed in kernel + * and forwarded to userspace, respectively + */ + __u64 kernel_tdvmcallinfo_1_r12; + __u64 user_tdvmcallinfo_1_r12; + + __u64 reserved[250]; /* Configurable CPUID bits for userspace */ struct kvm_cpuid2 cpuid; diff --git a/MAINTAINERS b/MAINTAINERS index fad6cb025a19..c0b444e5fd5a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4181,6 +4181,7 @@ F: include/linux/cpumask_types.h F: include/linux/find.h F: include/linux/nodemask.h F: include/linux/nodemask_types.h +F: include/uapi/linux/bits.h F: include/vdso/bits.h F: lib/bitmap-str.c F: lib/bitmap.c @@ -4193,6 +4194,7 @@ F: tools/include/linux/bitfield.h F: tools/include/linux/bitmap.h F: tools/include/linux/bits.h F: tools/include/linux/find.h +F: tools/include/uapi/linux/bits.h F: tools/include/vdso/bits.h F: tools/lib/bitmap.c F: tools/lib/find_bit.c @@ -5568,6 +5570,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git F: drivers/char/ F: drivers/misc/ F: include/linux/miscdevice.h +F: rust/kernel/miscdevice.rs F: samples/rust/rust_misc_device.rs X: drivers/char/agp/ X: drivers/char/hw_random/ @@ -10504,7 +10507,7 @@ S: Maintained F: block/partitions/efi.* HABANALABS PCI DRIVER -M: Ofir Bitton <obitton@habana.ai> +M: Yaron Avizrat <yaron.avizrat@intel.com> L: dri-devel@lists.freedesktop.org S: Supported C: irc://irc.oftc.net/dri-devel @@ -11006,7 +11009,8 @@ F: Documentation/ABI/testing/debugfs-hisi-zip F: drivers/crypto/hisilicon/zip/ HMM - Heterogeneous Memory Management -M: Jérôme Glisse <jglisse@redhat.com> +M: Jason Gunthorpe <jgg@nvidia.com> +M: Leon Romanovsky <leonro@nvidia.com> L: linux-mm@kvack.org S: Maintained F: Documentation/mm/hmm.rst @@ -12185,9 +12189,8 @@ F: drivers/dma/idxd/* F: include/uapi/linux/idxd.h INTEL IN FIELD SCAN (IFS) DEVICE -M: Jithu Joseph <jithu.joseph@intel.com> +M: Tony Luck <tony.luck@intel.com> R: Ashok Raj <ashok.raj.linux@gmail.com> -R: Tony Luck <tony.luck@intel.com> S: Maintained F: drivers/platform/x86/intel/ifs F: include/trace/events/intel_ifs.h @@ -12527,8 +12530,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/iwlwifi/iwlwifi.git F: drivers/net/wireless/intel/iwlwifi/ INTEL WMI SLIM BOOTLOADER (SBL) FIRMWARE UPDATE DRIVER -M: Jithu Joseph <jithu.joseph@intel.com> -S: Maintained +S: Orphan W: https://slimbootloader.github.io/security/firmware-update.html F: drivers/platform/x86/intel/wmi/sbl-fw-update.c @@ -16822,8 +16824,8 @@ F: include/dt-bindings/clock/mobileye,eyeq5-clk.h MODULE SUPPORT M: Luis Chamberlain <mcgrof@kernel.org> M: Petr Pavlu <petr.pavlu@suse.com> +M: Daniel Gomez <da.gomez@kernel.org> R: Sami Tolvanen <samitolvanen@google.com> -R: Daniel Gomez <da.gomez@samsung.com> L: linux-modules@vger.kernel.org L: linux-kernel@vger.kernel.org S: Maintained @@ -17222,10 +17224,10 @@ F: drivers/rtc/rtc-ntxec.c F: include/linux/mfd/ntxec.h NETRONOME ETHERNET DRIVERS -M: Louis Peens <louis.peens@corigine.com> R: Jakub Kicinski <kuba@kernel.org> +R: Simon Horman <horms@kernel.org> L: oss-drivers@corigine.com -S: Maintained +S: Odd Fixes F: drivers/net/ethernet/netronome/ NETWORK BLOCK DEVICE (NBD) @@ -17382,6 +17384,7 @@ F: include/linux/ethtool.h F: include/linux/framer/framer-provider.h F: include/linux/framer/framer.h F: include/linux/in.h +F: include/linux/in6.h F: include/linux/indirect_call_wrapper.h F: include/linux/inet.h F: include/linux/inet_diag.h @@ -19601,8 +19604,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/pinctrl/intel.git F: drivers/pinctrl/intel/ PIN CONTROLLER - KEEMBAY -M: Lakshmi Sowjanya D <lakshmi.sowjanya.d@intel.com> -S: Supported +S: Orphan F: drivers/pinctrl/pinctrl-keembay* PIN CONTROLLER - MEDIATEK @@ -20155,21 +20157,15 @@ S: Supported F: Documentation/devicetree/bindings/soc/qcom/qcom,apr* F: Documentation/devicetree/bindings/sound/qcom,* F: drivers/soc/qcom/apr.c -F: include/dt-bindings/sound/qcom,wcd9335.h -F: include/dt-bindings/sound/qcom,wcd934x.h -F: sound/soc/codecs/lpass-rx-macro.* -F: sound/soc/codecs/lpass-tx-macro.* -F: sound/soc/codecs/lpass-va-macro.c -F: sound/soc/codecs/lpass-wsa-macro.* +F: drivers/soundwire/qcom.c +F: include/dt-bindings/sound/qcom,wcd93* +F: sound/soc/codecs/lpass-*.* F: sound/soc/codecs/msm8916-wcd-analog.c F: sound/soc/codecs/msm8916-wcd-digital.c F: sound/soc/codecs/wcd-clsh-v2.* F: sound/soc/codecs/wcd-mbhc-v2.* -F: sound/soc/codecs/wcd9335.* -F: sound/soc/codecs/wcd934x.c -F: sound/soc/codecs/wsa881x.c -F: sound/soc/codecs/wsa883x.c -F: sound/soc/codecs/wsa884x.c +F: sound/soc/codecs/wcd93*.* +F: sound/soc/codecs/wsa88*.* F: sound/soc/qcom/ QCOM EMBEDDED USB DEBUGGER (EUD) @@ -25907,6 +25903,8 @@ F: fs/hostfs/ USERSPACE COPYIN/COPYOUT (UIOVEC) M: Alexander Viro <viro@zeniv.linux.org.uk> +L: linux-block@vger.kernel.org +L: linux-fsdevel@vger.kernel.org S: Maintained F: include/linux/uio.h F: lib/iov_iter.c @@ -26944,7 +26942,7 @@ F: arch/x86/kernel/stacktrace.c F: arch/x86/kernel/unwind_*.c X86 TRUST DOMAIN EXTENSIONS (TDX) -M: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> +M: Kirill A. Shutemov <kas@kernel.org> R: Dave Hansen <dave.hansen@linux.intel.com> L: x86@kernel.org L: linux-coco@lists.linux.dev @@ -27313,13 +27311,6 @@ S: Supported W: http://www.marvell.com F: drivers/i2c/busses/i2c-xlp9xx.c -XRA1403 GPIO EXPANDER -M: Nandor Han <nandor.han@ge.com> -L: linux-gpio@vger.kernel.org -S: Maintained -F: Documentation/devicetree/bindings/gpio/gpio-xra1403.txt -F: drivers/gpio/gpio-xra1403.c - XTENSA XTFPGA PLATFORM SUPPORT M: Max Filippov <jcmvbkbc@gmail.com> S: Maintained @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 3072731fe09c..962451e54fdd 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -121,7 +121,7 @@ config ARM select HAVE_KERNEL_XZ select HAVE_KPROBES if !XIP_KERNEL && !CPU_ENDIAN_BE32 && !CPU_V7M select HAVE_KRETPROBES if HAVE_KPROBES - select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if (LD_VERSION >= 23600 || LD_CAN_USE_KEEP_IN_OVERLAY) + select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if (LD_VERSION >= 23600 || LD_IS_LLD) && LD_CAN_USE_KEEP_IN_OVERLAY select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI select HAVE_OPTPROBES if !THUMB2_KERNEL diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 4808d3ed98e4..e31e95ffd33f 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -149,7 +149,7 @@ endif # Need -Uarm for gcc < 3.x KBUILD_CPPFLAGS +=$(cpp-y) KBUILD_CFLAGS +=$(CFLAGS_ABI) $(CFLAGS_ISA) $(arch-y) $(tune-y) $(call cc-option,-mshort-load-bytes,$(call cc-option,-malignment-traps,)) -msoft-float -Uarm -KBUILD_AFLAGS +=$(CFLAGS_ABI) $(AFLAGS_ISA) -Wa,$(arch-y) $(tune-y) -include asm/unified.h -msoft-float +KBUILD_AFLAGS +=$(CFLAGS_ABI) $(AFLAGS_ISA) -Wa,$(arch-y) $(tune-y) -include $(srctree)/arch/arm/include/asm/unified.h -msoft-float KBUILD_RUSTFLAGS += --target=arm-unknown-linux-gnueabi CHECKFLAGS += -D__arm__ diff --git a/arch/arm/boot/dts/allwinner/sun8i-v3s.dtsi b/arch/arm/boot/dts/allwinner/sun8i-v3s.dtsi index f909b1d4dbca..e82cf312da25 100644 --- a/arch/arm/boot/dts/allwinner/sun8i-v3s.dtsi +++ b/arch/arm/boot/dts/allwinner/sun8i-v3s.dtsi @@ -652,7 +652,7 @@ reg = <0x01cb4000 0x3000>; interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>; clocks = <&ccu CLK_BUS_CSI>, - <&ccu CLK_CSI1_SCLK>, + <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI>; clock-names = "bus", "mod", "ram"; resets = <&ccu RST_BUS_CSI>; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 55fc331af337..393d71124f5d 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -256,6 +256,7 @@ config ARM64 select HOTPLUG_SMT if HOTPLUG_CPU select IRQ_DOMAIN select IRQ_FORCED_THREADING + select JUMP_LABEL select KASAN_VMALLOC if KASAN select LOCK_MM_AND_FIND_VMA select MODULES_USE_ELF_RELA diff --git a/arch/arm64/boot/dts/allwinner/sun55i-a523.dtsi b/arch/arm64/boot/dts/allwinner/sun55i-a523.dtsi index 8b7cbc2e78f5..51cd148f4227 100644 --- a/arch/arm64/boot/dts/allwinner/sun55i-a523.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun55i-a523.dtsi @@ -131,7 +131,7 @@ "PH5", "PH6", "PH7", "PH9", "PH10", "PH14", "PH15", "PH16", "PH17", "PH18"; allwinner,pinmux = <5>; - function = "emac0"; + function = "gmac0"; drive-strength = <40>; bias-disable; }; @@ -540,8 +540,8 @@ status = "disabled"; }; - emac0: ethernet@4500000 { - compatible = "allwinner,sun55i-a523-emac0", + gmac0: ethernet@4500000 { + compatible = "allwinner,sun55i-a523-gmac0", "allwinner,sun50i-a64-emac"; reg = <0x04500000 0x10000>; clocks = <&ccu CLK_BUS_EMAC0>; diff --git a/arch/arm64/boot/dts/allwinner/sun55i-a527-cubie-a5e.dts b/arch/arm64/boot/dts/allwinner/sun55i-a527-cubie-a5e.dts index 0f58d92a6adc..8bc0f2c72a24 100644 --- a/arch/arm64/boot/dts/allwinner/sun55i-a527-cubie-a5e.dts +++ b/arch/arm64/boot/dts/allwinner/sun55i-a527-cubie-a5e.dts @@ -12,7 +12,7 @@ compatible = "radxa,cubie-a5e", "allwinner,sun55i-a527"; aliases { - ethernet0 = &emac0; + ethernet0 = &gmac0; serial0 = &uart0; }; @@ -55,7 +55,7 @@ status = "okay"; }; -&emac0 { +&gmac0 { phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_cldo3>; diff --git a/arch/arm64/boot/dts/allwinner/sun55i-t527-avaota-a1.dts b/arch/arm64/boot/dts/allwinner/sun55i-t527-avaota-a1.dts index 08127f0cdd35..142177c1f737 100644 --- a/arch/arm64/boot/dts/allwinner/sun55i-t527-avaota-a1.dts +++ b/arch/arm64/boot/dts/allwinner/sun55i-t527-avaota-a1.dts @@ -12,7 +12,7 @@ compatible = "yuzukihd,avaota-a1", "allwinner,sun55i-t527"; aliases { - ethernet0 = &emac0; + ethernet0 = &gmac0; serial0 = &uart0; }; @@ -65,7 +65,7 @@ status = "okay"; }; -&emac0 { +&gmac0 { phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_dcdc4>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi index 0baf256b4400..983b2f0e8797 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi @@ -687,11 +687,12 @@ }; wdog0: watchdog@2ad0000 { - compatible = "fsl,imx21-wdt"; + compatible = "fsl,ls1046a-wdt", "fsl,imx21-wdt"; reg = <0x0 0x2ad0000 0x0 0x10000>; interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL QORIQ_CLK_PLL_DIV(2)>; + big-endian; }; edma0: dma-controller@2c00000 { diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index d29710772569..1594ce9182a5 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -464,6 +464,7 @@ }; reg_nvcc_sd: LDO5 { + regulator-always-on; regulator-max-microvolt = <3300000>; regulator-min-microvolt = <1800000>; regulator-name = "On-module +V3.3_1.8_SD (LDO5)"; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi index 2f740d74707b..4bf818873fe3 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi @@ -70,7 +70,7 @@ tpm@1 { compatible = "atmel,attpm20p", "tcg,tpm_tis-spi"; reg = <0x1>; - spi-max-frequency = <36000000>; + spi-max-frequency = <25000000>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi index 5ab3ffe9931d..cf747ec6fa16 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi @@ -110,7 +110,7 @@ tpm@1 { compatible = "atmel,attpm20p", "tcg,tpm_tis-spi"; reg = <0x1>; - spi-max-frequency = <36000000>; + spi-max-frequency = <25000000>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi index e2b5e7ac3e46..5eb114d2360a 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi @@ -122,7 +122,7 @@ tpm@1 { compatible = "atmel,attpm20p", "tcg,tpm_tis-spi"; reg = <0x1>; - spi-max-frequency = <36000000>; + spi-max-frequency = <25000000>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts index 6daa2313f879..568d24265ddf 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts @@ -201,7 +201,7 @@ tpm@0 { compatible = "atmel,attpm20p", "tcg,tpm_tis-spi"; reg = <0x0>; - spi-max-frequency = <36000000>; + spi-max-frequency = <25000000>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx95-15x15-evk.dts b/arch/arm64/boot/dts/freescale/imx95-15x15-evk.dts index 6c47f4b47356..9f4d0899a94d 100644 --- a/arch/arm64/boot/dts/freescale/imx95-15x15-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx95-15x15-evk.dts @@ -574,17 +574,17 @@ &scmi_iomuxc { pinctrl_emdio: emdiogrp { fsl,pins = < - IMX95_PAD_ENET2_MDC__NETCMIX_TOP_NETC_MDC 0x57e - IMX95_PAD_ENET2_MDIO__NETCMIX_TOP_NETC_MDIO 0x97e + IMX95_PAD_ENET2_MDC__NETCMIX_TOP_NETC_MDC 0x50e + IMX95_PAD_ENET2_MDIO__NETCMIX_TOP_NETC_MDIO 0x90e >; }; pinctrl_enetc0: enetc0grp { fsl,pins = < - IMX95_PAD_ENET1_TD3__NETCMIX_TOP_ETH0_RGMII_TD3 0x57e - IMX95_PAD_ENET1_TD2__NETCMIX_TOP_ETH0_RGMII_TD2 0x57e - IMX95_PAD_ENET1_TD1__NETCMIX_TOP_ETH0_RGMII_TD1 0x57e - IMX95_PAD_ENET1_TD0__NETCMIX_TOP_ETH0_RGMII_TD0 0x57e + IMX95_PAD_ENET1_TD3__NETCMIX_TOP_ETH0_RGMII_TD3 0x50e + IMX95_PAD_ENET1_TD2__NETCMIX_TOP_ETH0_RGMII_TD2 0x50e + IMX95_PAD_ENET1_TD1__NETCMIX_TOP_ETH0_RGMII_TD1 0x50e + IMX95_PAD_ENET1_TD0__NETCMIX_TOP_ETH0_RGMII_TD0 0x50e IMX95_PAD_ENET1_TX_CTL__NETCMIX_TOP_ETH0_RGMII_TX_CTL 0x57e IMX95_PAD_ENET1_TXC__NETCMIX_TOP_ETH0_RGMII_TX_CLK 0x58e IMX95_PAD_ENET1_RX_CTL__NETCMIX_TOP_ETH0_RGMII_RX_CTL 0x57e @@ -598,10 +598,10 @@ pinctrl_enetc1: enetc1grp { fsl,pins = < - IMX95_PAD_ENET2_TD3__NETCMIX_TOP_ETH1_RGMII_TD3 0x57e - IMX95_PAD_ENET2_TD2__NETCMIX_TOP_ETH1_RGMII_TD2 0x57e - IMX95_PAD_ENET2_TD1__NETCMIX_TOP_ETH1_RGMII_TD1 0x57e - IMX95_PAD_ENET2_TD0__NETCMIX_TOP_ETH1_RGMII_TD0 0x57e + IMX95_PAD_ENET2_TD3__NETCMIX_TOP_ETH1_RGMII_TD3 0x50e + IMX95_PAD_ENET2_TD2__NETCMIX_TOP_ETH1_RGMII_TD2 0x50e + IMX95_PAD_ENET2_TD1__NETCMIX_TOP_ETH1_RGMII_TD1 0x50e + IMX95_PAD_ENET2_TD0__NETCMIX_TOP_ETH1_RGMII_TD0 0x50e IMX95_PAD_ENET2_TX_CTL__NETCMIX_TOP_ETH1_RGMII_TX_CTL 0x57e IMX95_PAD_ENET2_TXC__NETCMIX_TOP_ETH1_RGMII_TX_CLK 0x58e IMX95_PAD_ENET2_RX_CTL__NETCMIX_TOP_ETH1_RGMII_RX_CTL 0x57e diff --git a/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts b/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts index 6886ea766655..d7d845231312 100644 --- a/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts @@ -566,17 +566,17 @@ &scmi_iomuxc { pinctrl_emdio: emdiogrp{ fsl,pins = < - IMX95_PAD_ENET1_MDC__NETCMIX_TOP_NETC_MDC 0x57e - IMX95_PAD_ENET1_MDIO__NETCMIX_TOP_NETC_MDIO 0x97e + IMX95_PAD_ENET1_MDC__NETCMIX_TOP_NETC_MDC 0x50e + IMX95_PAD_ENET1_MDIO__NETCMIX_TOP_NETC_MDIO 0x90e >; }; pinctrl_enetc0: enetc0grp { fsl,pins = < - IMX95_PAD_ENET1_TD3__NETCMIX_TOP_ETH0_RGMII_TD3 0x57e - IMX95_PAD_ENET1_TD2__NETCMIX_TOP_ETH0_RGMII_TD2 0x57e - IMX95_PAD_ENET1_TD1__NETCMIX_TOP_ETH0_RGMII_TD1 0x57e - IMX95_PAD_ENET1_TD0__NETCMIX_TOP_ETH0_RGMII_TD0 0x57e + IMX95_PAD_ENET1_TD3__NETCMIX_TOP_ETH0_RGMII_TD3 0x50e + IMX95_PAD_ENET1_TD2__NETCMIX_TOP_ETH0_RGMII_TD2 0x50e + IMX95_PAD_ENET1_TD1__NETCMIX_TOP_ETH0_RGMII_TD1 0x50e + IMX95_PAD_ENET1_TD0__NETCMIX_TOP_ETH0_RGMII_TD0 0x50e IMX95_PAD_ENET1_TX_CTL__NETCMIX_TOP_ETH0_RGMII_TX_CTL 0x57e IMX95_PAD_ENET1_TXC__NETCMIX_TOP_ETH0_RGMII_TX_CLK 0x58e IMX95_PAD_ENET1_RX_CTL__NETCMIX_TOP_ETH0_RGMII_RX_CTL 0x57e diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi index 632631a29112..5aecdd9b62ff 100644 --- a/arch/arm64/boot/dts/freescale/imx95.dtsi +++ b/arch/arm64/boot/dts/freescale/imx95.dtsi @@ -1708,7 +1708,7 @@ <0x9 0 1 0>; reg-names = "dbi","atu", "dbi2", "app", "dma", "addr_space"; num-lanes = <1>; - interrupts = <GIC_SPI 317 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 311 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "dma"; clocks = <&scmi_clk IMX95_CLK_HSIO>, <&scmi_clk IMX95_CLK_HSIOPLL>, diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts index ae7a275fd223..cefecb7a23cf 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts +++ b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts @@ -1090,6 +1090,8 @@ }; &pmk8280_rtc { + qcom,uefi-rtc-info; + status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-pmics.dtsi b/arch/arm64/boot/dts/qcom/x1e80100-pmics.dtsi index c02fd4d15c96..e3888bc143a0 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-pmics.dtsi +++ b/arch/arm64/boot/dts/qcom/x1e80100-pmics.dtsi @@ -224,6 +224,7 @@ reg-names = "rtc", "alarm"; interrupts = <0x0 0x62 0x1 IRQ_TYPE_EDGE_RISING>; qcom,no-alarm; /* alarm owned by ADSP */ + qcom,uefi-rtc-info; }; pmk8550_sdam_2: nvram@7100 { diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi index ab232e5c7ad6..4203b335a263 100644 --- a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi @@ -379,6 +379,18 @@ <0 RK_PA7 RK_FUNC_GPIO &pcfg_pull_up>; }; }; + + spi1 { + spi1_csn0_gpio_pin: spi1-csn0-gpio-pin { + rockchip,pins = + <3 RK_PB1 RK_FUNC_GPIO &pcfg_pull_up_4ma>; + }; + + spi1_csn1_gpio_pin: spi1-csn1-gpio-pin { + rockchip,pins = + <3 RK_PB2 RK_FUNC_GPIO &pcfg_pull_up_4ma>; + }; + }; }; &pmu_io_domains { @@ -396,6 +408,17 @@ vqmmc-supply = <&vccio_sd>; }; +&spi1 { + /* + * Hardware CS has a very slow rise time of about 6us, + * causing transmission errors. + * With cs-gpios we have a rise time of about 20ns. + */ + cs-gpios = <&gpio3 RK_PB1 GPIO_ACTIVE_LOW>, <&gpio3 RK_PB2 GPIO_ACTIVE_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&spi1_clk &spi1_csn0_gpio_pin &spi1_csn1_gpio_pin &spi1_miso &spi1_mosi>; +}; + &tsadc { status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts index 3c127c5c2607..a9021c524afb 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts @@ -30,6 +30,7 @@ fan: gpio_fan { compatible = "gpio-fan"; + fan-supply = <&vcc12v_dcin>; gpios = <&gpio0 RK_PD5 GPIO_ACTIVE_HIGH>; gpio-fan,speed-map = < 0 0>, diff --git a/arch/arm64/boot/dts/rockchip/rk3568-nanopi-r5s.dts b/arch/arm64/boot/dts/rockchip/rk3568-nanopi-r5s.dts index 3b31f0dd8f3b..539edc3c535f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-nanopi-r5s.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-nanopi-r5s.dts @@ -29,7 +29,6 @@ function-enumerator = <1>; gpios = <&gpio3 RK_PD6 GPIO_ACTIVE_HIGH>; label = "LAN-1"; - linux,default-trigger = "netdev"; }; led-lan2 { @@ -39,7 +38,6 @@ function-enumerator = <2>; gpios = <&gpio3 RK_PD7 GPIO_ACTIVE_HIGH>; label = "LAN-2"; - linux,default-trigger = "netdev"; }; power_led: led-sys { @@ -56,7 +54,6 @@ function = LED_FUNCTION_WAN; gpios = <&gpio2 RK_PC1 GPIO_ACTIVE_HIGH>; label = "WAN"; - linux,default-trigger = "netdev"; }; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts b/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts index b09e789c75c4..801b40fea4e8 100644 --- a/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts +++ b/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts @@ -211,10 +211,38 @@ status = "okay"; }; +&cpu_b0 { + cpu-supply = <&vdd_cpu_big_s0>; +}; + +&cpu_b1 { + cpu-supply = <&vdd_cpu_big_s0>; +}; + +&cpu_b2 { + cpu-supply = <&vdd_cpu_big_s0>; +}; + +&cpu_b3 { + cpu-supply = <&vdd_cpu_big_s0>; +}; + &cpu_l0 { cpu-supply = <&vdd_cpu_lit_s0>; }; +&cpu_l1 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_l2 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_l3 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + &gmac0 { phy-mode = "rgmii-id"; clock_in_out = "output"; diff --git a/arch/arm64/boot/dts/rockchip/rk3576.dtsi b/arch/arm64/boot/dts/rockchip/rk3576.dtsi index 1086482f0479..64812e3bcb61 100644 --- a/arch/arm64/boot/dts/rockchip/rk3576.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3576.dtsi @@ -615,7 +615,7 @@ <0 0 0 2 &pcie1_intc 1>, <0 0 0 3 &pcie1_intc 2>, <0 0 0 4 &pcie1_intc 3>; - linux,pci-domain = <0>; + linux,pci-domain = <1>; max-link-speed = <2>; num-ib-windows = <8>; num-viewport = <8>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-base-pinctrl.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-base-pinctrl.dtsi index 7f874c77410c..6584d73660f6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-base-pinctrl.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-base-pinctrl.dtsi @@ -578,14 +578,14 @@ hdmim0_tx0_scl: hdmim0-tx0-scl { rockchip,pins = /* hdmim0_tx0_scl */ - <4 RK_PB7 5 &pcfg_pull_none>; + <4 RK_PB7 5 &pcfg_pull_none_drv_level_5_smt>; }; /omit-if-no-ref/ hdmim0_tx0_sda: hdmim0-tx0-sda { rockchip,pins = /* hdmim0_tx0_sda */ - <4 RK_PC0 5 &pcfg_pull_none>; + <4 RK_PC0 5 &pcfg_pull_none_drv_level_1_smt>; }; /omit-if-no-ref/ @@ -640,14 +640,14 @@ hdmim1_tx0_scl: hdmim1-tx0-scl { rockchip,pins = /* hdmim1_tx0_scl */ - <0 RK_PD5 11 &pcfg_pull_none>; + <0 RK_PD5 11 &pcfg_pull_none_drv_level_5_smt>; }; /omit-if-no-ref/ hdmim1_tx0_sda: hdmim1-tx0-sda { rockchip,pins = /* hdmim1_tx0_sda */ - <0 RK_PD4 11 &pcfg_pull_none>; + <0 RK_PD4 11 &pcfg_pull_none_drv_level_1_smt>; }; /omit-if-no-ref/ @@ -668,14 +668,14 @@ hdmim1_tx1_scl: hdmim1-tx1-scl { rockchip,pins = /* hdmim1_tx1_scl */ - <3 RK_PC6 5 &pcfg_pull_none>; + <3 RK_PC6 5 &pcfg_pull_none_drv_level_5_smt>; }; /omit-if-no-ref/ hdmim1_tx1_sda: hdmim1-tx1-sda { rockchip,pins = /* hdmim1_tx1_sda */ - <3 RK_PC5 5 &pcfg_pull_none>; + <3 RK_PC5 5 &pcfg_pull_none_drv_level_1_smt>; }; /omit-if-no-ref/ hdmim2_rx_cec: hdmim2-rx-cec { @@ -709,14 +709,14 @@ hdmim2_tx0_scl: hdmim2-tx0-scl { rockchip,pins = /* hdmim2_tx0_scl */ - <3 RK_PC7 5 &pcfg_pull_none>; + <3 RK_PC7 5 &pcfg_pull_none_drv_level_5_smt>; }; /omit-if-no-ref/ hdmim2_tx0_sda: hdmim2-tx0-sda { rockchip,pins = /* hdmim2_tx0_sda */ - <3 RK_PD0 5 &pcfg_pull_none>; + <3 RK_PD0 5 &pcfg_pull_none_drv_level_1_smt>; }; /omit-if-no-ref/ @@ -730,14 +730,14 @@ hdmim2_tx1_scl: hdmim2-tx1-scl { rockchip,pins = /* hdmim2_tx1_scl */ - <1 RK_PA4 5 &pcfg_pull_none>; + <1 RK_PA4 5 &pcfg_pull_none_drv_level_5_smt>; }; /omit-if-no-ref/ hdmim2_tx1_sda: hdmim2-tx1-sda { rockchip,pins = /* hdmim2_tx1_sda */ - <1 RK_PA3 5 &pcfg_pull_none>; + <1 RK_PA3 5 &pcfg_pull_none_drv_level_1_smt>; }; /omit-if-no-ref/ diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi index cc37f082adea..b07543315f87 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi @@ -321,6 +321,7 @@ bus-width = <4>; cap-mmc-highspeed; cap-sd-highspeed; + cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; disable-wp; max-frequency = <150000000>; no-sdio; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-extra-pinctrl.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-extra-pinctrl.dtsi index 244c66faa161..fb48ddc04bcb 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-extra-pinctrl.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-extra-pinctrl.dtsi @@ -160,14 +160,15 @@ hdmim0_tx1_scl: hdmim0-tx1-scl { rockchip,pins = /* hdmim0_tx1_scl */ - <2 RK_PB5 4 &pcfg_pull_none>; + <2 RK_PB5 4 &pcfg_pull_none_drv_level_3_smt>; }; /omit-if-no-ref/ hdmim0_tx1_sda: hdmim0-tx1-sda { rockchip,pins = /* hdmim0_tx1_sda */ - <2 RK_PB4 4 &pcfg_pull_none>; + <2 RK_PB4 4 &pcfg_pull_none_drv_level_1_smt>; + }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts index 8b717c4017a4..b2947b36fada 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts @@ -474,6 +474,7 @@ bus-width = <4>; cap-mmc-highspeed; cap-sd-highspeed; + cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; disable-wp; max-frequency = <150000000>; no-sdio; diff --git a/arch/arm64/boot/dts/rockchip/rockchip-pinconf.dtsi b/arch/arm64/boot/dts/rockchip/rockchip-pinconf.dtsi index 5c645437b507..b0475b7c655a 100644 --- a/arch/arm64/boot/dts/rockchip/rockchip-pinconf.dtsi +++ b/arch/arm64/boot/dts/rockchip/rockchip-pinconf.dtsi @@ -333,6 +333,41 @@ }; /omit-if-no-ref/ + pcfg_pull_none_drv_level_1_smt: pcfg-pull-none-drv-level-1-smt { + bias-disable; + drive-strength = <1>; + input-schmitt-enable; + }; + + /omit-if-no-ref/ + pcfg_pull_none_drv_level_2_smt: pcfg-pull-none-drv-level-2-smt { + bias-disable; + drive-strength = <2>; + input-schmitt-enable; + }; + + /omit-if-no-ref/ + pcfg_pull_none_drv_level_3_smt: pcfg-pull-none-drv-level-3-smt { + bias-disable; + drive-strength = <3>; + input-schmitt-enable; + }; + + /omit-if-no-ref/ + pcfg_pull_none_drv_level_4_smt: pcfg-pull-none-drv-level-4-smt { + bias-disable; + drive-strength = <4>; + input-schmitt-enable; + }; + + /omit-if-no-ref/ + pcfg_pull_none_drv_level_5_smt: pcfg-pull-none-drv-level-5-smt { + bias-disable; + drive-strength = <5>; + input-schmitt-enable; + }; + + /omit-if-no-ref/ pcfg_output_high: pcfg-output-high { output-high; }; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 7e04a2905ce4..eb5c17d4c7ec 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -1444,6 +1444,7 @@ CONFIG_PLATFORM_MHU=y CONFIG_BCM2835_MBOX=y CONFIG_QCOM_APCS_IPC=y CONFIG_MTK_ADSP_MBOX=m +CONFIG_QCOM_CPUCP_MBOX=m CONFIG_QCOM_IPCC=y CONFIG_ROCKCHIP_IOMMU=y CONFIG_TEGRA_IOMMU_SMMU=y diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index ad63457a05c5..c56c21bb1eec 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -41,6 +41,11 @@ /* * Save/restore interrupts. */ + .macro save_and_disable_daif, flags + mrs \flags, daif + msr daifset, #0xf + .endm + .macro save_and_disable_irq, flags mrs \flags, daif msr daifset, #3 diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index ba5df0df02a4..9f38340d24c2 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -287,17 +287,6 @@ .Lskip_fgt2_\@: .endm -.macro __init_el2_gcs - mrs_s x1, SYS_ID_AA64PFR1_EL1 - ubfx x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4 - cbz x1, .Lskip_gcs_\@ - - /* Ensure GCS is not enabled when we start trying to do BLs */ - msr_s SYS_GCSCR_EL1, xzr - msr_s SYS_GCSCRE0_EL1, xzr -.Lskip_gcs_\@: -.endm - /** * Initialize EL2 registers to sane values. This should be called early on all * cores that were booted in EL2. Note that everything gets initialised as @@ -319,7 +308,6 @@ __init_el2_cptr __init_el2_fgt __init_el2_fgt2 - __init_el2_gcs .endm #ifndef __KVM_NVHE_HYPERVISOR__ @@ -371,6 +359,13 @@ msr_s SYS_MPAMHCR_EL2, xzr // clear TRAP_MPAMIDR_EL1 -> EL2 .Lskip_mpam_\@: + check_override id_aa64pfr1, ID_AA64PFR1_EL1_GCS_SHIFT, .Linit_gcs_\@, .Lskip_gcs_\@, x1, x2 + +.Linit_gcs_\@: + msr_s SYS_GCSCR_EL1, xzr + msr_s SYS_GCSCRE0_EL1, xzr + +.Lskip_gcs_\@: check_override id_aa64pfr0, ID_AA64PFR0_EL1_SVE_SHIFT, .Linit_sve_\@, .Lskip_sve_\@, x1, x2 .Linit_sve_\@: /* SVE register access */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index d27079968341..3e41a880b062 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -1480,7 +1480,6 @@ int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm, struct reg_mask_range *range); /* Guest/host FPSIMD coordination helpers */ -int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 2920b0a51403..a2faf0049dab 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -34,7 +34,7 @@ obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ cpufeature.o alternative.o cacheinfo.o \ smp.o smp_spin_table.o topology.o smccc-call.o \ syscall.o proton-pack.o idle.o patching.o pi/ \ - rsi.o + rsi.o jump_label.o obj-$(CONFIG_COMPAT) += sys32.o signal32.o \ sys_compat.o @@ -47,7 +47,6 @@ obj-$(CONFIG_PERF_EVENTS) += perf_regs.o perf_callchain.o obj-$(CONFIG_HARDLOCKUP_DETECTOR_PERF) += watchdog_hld.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_CPU_PM) += sleep.o suspend.o -obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_EFI) += efi.o efi-rt-wrapper.o obj-$(CONFIG_PCI) += pci.o diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index b34044e20128..e151585c6cca 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -3135,6 +3135,13 @@ static bool has_sve_feature(const struct arm64_cpu_capabilities *cap, int scope) } #endif +#ifdef CONFIG_ARM64_SME +static bool has_sme_feature(const struct arm64_cpu_capabilities *cap, int scope) +{ + return system_supports_sme() && has_user_cpuid_feature(cap, scope); +} +#endif + static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL), HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES), @@ -3223,31 +3230,31 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR2_EL1, BC, IMP, CAP_HWCAP, KERNEL_HWCAP_HBC), #ifdef CONFIG_ARM64_SME HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME), - HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), - HWCAP_CAP(ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2), - HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p2, CAP_HWCAP, KERNEL_HWCAP_SME2P2), - HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1), - HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2), - HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), - HWCAP_CAP(ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64), - HWCAP_CAP(ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32), - HWCAP_CAP(ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16), - HWCAP_CAP(ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16), - HWCAP_CAP(ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16), - HWCAP_CAP(ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32), - HWCAP_CAP(ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32), - HWCAP_CAP(ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32), - HWCAP_CAP(ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32), - HWCAP_CAP(ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32), - HWCAP_CAP(ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32), - HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA), - HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4), - HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2), - HWCAP_CAP(ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM), - HWCAP_CAP(ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES), - HWCAP_CAP(ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA), - HWCAP_CAP(ID_AA64SMFR0_EL1, STMOP, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_STMOP), - HWCAP_CAP(ID_AA64SMFR0_EL1, SMOP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SMOP4), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2p2, CAP_HWCAP, KERNEL_HWCAP_SME2P2), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, STMOP, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_STMOP), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMOP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SMOP4), #endif /* CONFIG_ARM64_SME */ HWCAP_CAP(ID_AA64FPFR0_EL1, F8CVT, IMP, CAP_HWCAP, KERNEL_HWCAP_F8CVT), HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA), diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 3857fd7ee8d4..62230d6dd919 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -15,6 +15,7 @@ #include <asm/efi.h> #include <asm/stacktrace.h> +#include <asm/vmap_stack.h> static bool region_is_misaligned(const efi_memory_desc_t *md) { @@ -214,9 +215,13 @@ static int __init arm64_efi_rt_init(void) if (!efi_enabled(EFI_RUNTIME_SERVICES)) return 0; - p = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, GFP_KERNEL, - NUMA_NO_NODE, &&l); -l: if (!p) { + if (!IS_ENABLED(CONFIG_VMAP_STACK)) { + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + return -ENOMEM; + } + + p = arch_alloc_vmap_stack(THREAD_SIZE, NUMA_NO_NODE); + if (!p) { pr_warn("Failed to allocate EFI runtime stack\n"); clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); return -ENOMEM; diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 5ae2a34b50bd..30dcb719685b 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -825,6 +825,7 @@ SYM_CODE_END(__bp_harden_el1_vectors) * */ SYM_FUNC_START(cpu_switch_to) + save_and_disable_daif x11 mov x10, #THREAD_CPU_CONTEXT add x8, x0, x10 mov x9, sp @@ -848,6 +849,7 @@ SYM_FUNC_START(cpu_switch_to) ptrauth_keys_install_kernel x1, x8, x9, x10 scs_save x0 scs_load_current + restore_irq x11 ret SYM_FUNC_END(cpu_switch_to) NOKPROBE(cpu_switch_to) @@ -874,6 +876,7 @@ NOKPROBE(ret_from_fork) * Calls func(regs) using this CPU's irq stack and shadow irq stack. */ SYM_FUNC_START(call_on_irq_stack) + save_and_disable_daif x9 #ifdef CONFIG_SHADOW_CALL_STACK get_current_task x16 scs_save x16 @@ -888,8 +891,10 @@ SYM_FUNC_START(call_on_irq_stack) /* Move to the new stack and call the function there */ add sp, x16, #IRQ_STACK_SIZE + restore_irq x9 blr x1 + save_and_disable_daif x9 /* * Restore the SP from the FP, and restore the FP and LR from the frame * record. @@ -897,6 +902,7 @@ SYM_FUNC_START(call_on_irq_stack) mov sp, x29 ldp x29, x30, [sp], #16 scs_load_current + restore_irq x9 ret SYM_FUNC_END(call_on_irq_stack) NOKPROBE(call_on_irq_stack) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 5954cec19660..08b7042a2e2d 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -673,6 +673,11 @@ static void permission_overlay_switch(struct task_struct *next) current->thread.por_el0 = read_sysreg_s(SYS_POR_EL0); if (current->thread.por_el0 != next->thread.por_el0) { write_sysreg_s(next->thread.por_el0, SYS_POR_EL0); + /* + * No ISB required as we can tolerate spurious Overlay faults - + * the fault handler will check again based on the new value + * of POR_EL0. + */ } } diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 3b3f6b56e733..21a795303568 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -1143,7 +1143,7 @@ static inline unsigned int num_other_online_cpus(void) void smp_send_stop(void) { static unsigned long stop_in_progress; - cpumask_t mask; + static cpumask_t mask; unsigned long timeout; /* diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 38a91bb5d4c7..f946926716b0 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -825,10 +825,6 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) if (!kvm_arm_vcpu_is_finalized(vcpu)) return -EPERM; - ret = kvm_arch_vcpu_run_map_fp(vcpu); - if (ret) - return ret; - if (likely(vcpu_has_run_once(vcpu))) return 0; @@ -2129,7 +2125,7 @@ static void cpu_hyp_init(void *discard) static void cpu_hyp_uninit(void *discard) { - if (__this_cpu_read(kvm_hyp_initialized)) { + if (!is_protected_kvm_enabled() && __this_cpu_read(kvm_hyp_initialized)) { cpu_hyp_reset(); __this_cpu_write(kvm_hyp_initialized, 0); } @@ -2345,8 +2341,13 @@ static void __init teardown_hyp_mode(void) free_hyp_pgds(); for_each_possible_cpu(cpu) { + if (per_cpu(kvm_hyp_initialized, cpu)) + continue; + free_pages(per_cpu(kvm_arm_hyp_stack_base, cpu), NVHE_STACK_SHIFT - PAGE_SHIFT); - free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order()); + + if (!kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu]) + continue; if (free_sve) { struct cpu_sve_state *sve_state; @@ -2354,6 +2355,9 @@ static void __init teardown_hyp_mode(void) sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state; free_pages((unsigned long) sve_state, pkvm_host_sve_state_order()); } + + free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order()); + } } @@ -2761,19 +2765,15 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, kvm_vgic_v4_unset_forwarding(irqfd->kvm, prod->irq); } -bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old, - struct kvm_kernel_irq_routing_entry *new) +void kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd, + struct kvm_kernel_irq_routing_entry *old, + struct kvm_kernel_irq_routing_entry *new) { - if (old->type != KVM_IRQ_ROUTING_MSI || - new->type != KVM_IRQ_ROUTING_MSI) - return true; - - return memcmp(&old->msi, &new->msi, sizeof(new->msi)); -} + if (old->type == KVM_IRQ_ROUTING_MSI && + new->type == KVM_IRQ_ROUTING_MSI && + !memcmp(&old->msi, &new->msi, sizeof(new->msi))) + return; -int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set) -{ /* * Remapping the vLPI requires taking the its_lock mutex to resolve * the new translation. We're in spinlock land at this point, so no @@ -2781,7 +2781,7 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, * * Unmap the vLPI and fall back to software LPI injection. */ - return kvm_vgic_v4_unset_forwarding(kvm, host_irq); + return kvm_vgic_v4_unset_forwarding(irqfd->kvm, irqfd->producer->irq); } void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *cons) diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 8f6c8f57c6b9..15e17aca1dec 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -15,32 +15,6 @@ #include <asm/sysreg.h> /* - * Called on entry to KVM_RUN unless this vcpu previously ran at least - * once and the most recent prior KVM_RUN for this vcpu was called from - * the same task as current (highly likely). - * - * This is guaranteed to execute before kvm_arch_vcpu_load_fp(vcpu), - * such that on entering hyp the relevant parts of current are already - * mapped. - */ -int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu) -{ - struct user_fpsimd_state *fpsimd = ¤t->thread.uw.fpsimd_state; - int ret; - - /* pKVM has its own tracking of the host fpsimd state. */ - if (is_protected_kvm_enabled()) - return 0; - - /* Make sure the host task fpsimd state is visible to hyp: */ - ret = kvm_share_hyp(fpsimd, fpsimd + 1); - if (ret) - return ret; - - return 0; -} - -/* * Prepare vcpu for saving the host's FPSIMD state and loading the guest's. * The actual loading is done by the FPSIMD access trap taken to hyp. * diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 95d7534c9679..8957734d6183 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -479,6 +479,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range) { struct kvm_mem_range cur; kvm_pte_t pte; + u64 granule; s8 level; int ret; @@ -496,18 +497,21 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range) return -EPERM; } - do { - u64 granule = kvm_granule_size(level); + for (; level <= KVM_PGTABLE_LAST_LEVEL; level++) { + if (!kvm_level_supports_block_mapping(level)) + continue; + granule = kvm_granule_size(level); cur.start = ALIGN_DOWN(addr, granule); cur.end = cur.start + granule; - level++; - } while ((level <= KVM_PGTABLE_LAST_LEVEL) && - !(kvm_level_supports_block_mapping(level) && - range_included(&cur, range))); + if (!range_included(&cur, range)) + continue; + *range = cur; + return 0; + } - *range = cur; + WARN_ON(1); - return 0; + return -EINVAL; } int host_stage2_idmap_locked(phys_addr_t addr, u64 size, diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 5b191f4dc566..dc1d26559bfa 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -1402,6 +1402,21 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu) } } +#define has_tgran_2(__r, __sz) \ + ({ \ + u64 _s1, _s2, _mmfr0 = __r; \ + \ + _s2 = SYS_FIELD_GET(ID_AA64MMFR0_EL1, \ + TGRAN##__sz##_2, _mmfr0); \ + \ + _s1 = SYS_FIELD_GET(ID_AA64MMFR0_EL1, \ + TGRAN##__sz, _mmfr0); \ + \ + ((_s2 != ID_AA64MMFR0_EL1_TGRAN##__sz##_2_NI && \ + _s2 != ID_AA64MMFR0_EL1_TGRAN##__sz##_2_TGRAN##__sz) || \ + (_s2 == ID_AA64MMFR0_EL1_TGRAN##__sz##_2_TGRAN##__sz && \ + _s1 != ID_AA64MMFR0_EL1_TGRAN##__sz##_NI)); \ + }) /* * Our emulated CPU doesn't support all the possible features. For the * sake of simplicity (and probably mental sanity), wipe out a number @@ -1411,6 +1426,8 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu) */ u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val) { + u64 orig_val = val; + switch (reg) { case SYS_ID_AA64ISAR0_EL1: /* Support everything but TME */ @@ -1480,13 +1497,16 @@ u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val) */ switch (PAGE_SIZE) { case SZ_4K: - val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, IMP); + if (has_tgran_2(orig_val, 4)) + val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, IMP); fallthrough; case SZ_16K: - val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, IMP); + if (has_tgran_2(orig_val, 16)) + val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, IMP); fallthrough; case SZ_64K: - val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN64_2, IMP); + if (has_tgran_2(orig_val, 64)) + val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN64_2, IMP); break; } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 76c2f0da821f..c20bd6f21e60 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -2624,7 +2624,7 @@ static bool access_mdcr(struct kvm_vcpu *vcpu, */ if (hpmn > vcpu->kvm->arch.nr_pmu_counters) { hpmn = vcpu->kvm->arch.nr_pmu_counters; - u64_replace_bits(val, hpmn, MDCR_EL2_HPMN); + u64p_replace_bits(&val, hpmn, MDCR_EL2_HPMN); } __vcpu_assign_sys_reg(vcpu, MDCR_EL2, val); diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 534049c7c94b..98630dae910d 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -758,7 +758,7 @@ static void its_free_ite(struct kvm *kvm, struct its_ite *ite) if (irq) { scoped_guard(raw_spinlock_irqsave, &irq->irq_lock) { if (irq->hw) - WARN_ON(its_unmap_vlpi(ite->irq->host_irq)); + its_unmap_vlpi(ite->irq->host_irq); irq->hw = false; } diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c index a50fb7e6841f..679aafe77de2 100644 --- a/arch/arm64/kvm/vgic/vgic-v3-nested.c +++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c @@ -401,9 +401,7 @@ void vgic_v3_nested_update_mi(struct kvm_vcpu *vcpu) { bool level; - level = __vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_En; - if (level) - level &= vgic_v3_get_misr(vcpu); + level = (__vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_En) && vgic_v3_get_misr(vcpu); kvm_vgic_inject_irq(vcpu->kvm, vcpu, vcpu->kvm->arch.vgic.mi_intid, level, vcpu); } diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index 193946108192..ef3481963122 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -527,28 +527,26 @@ static struct vgic_irq *__vgic_host_irq_get_vlpi(struct kvm *kvm, int host_irq) return NULL; } -int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int host_irq) +void kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int host_irq) { struct vgic_irq *irq; unsigned long flags; - int ret = 0; if (!vgic_supports_direct_msis(kvm)) - return 0; + return; irq = __vgic_host_irq_get_vlpi(kvm, host_irq); if (!irq) - return 0; + return; raw_spin_lock_irqsave(&irq->irq_lock, flags); WARN_ON(irq->hw && irq->host_irq != host_irq); if (irq->hw) { atomic_dec(&irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count); irq->hw = false; - ret = its_unmap_vlpi(host_irq); + its_unmap_vlpi(host_irq); } raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(kvm, irq); - return ret; } diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index ec0a337891dd..11eb8d1adc84 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -487,17 +487,29 @@ static void do_bad_area(unsigned long far, unsigned long esr, } } -static bool fault_from_pkey(unsigned long esr, struct vm_area_struct *vma, - unsigned int mm_flags) +static bool fault_from_pkey(struct vm_area_struct *vma, unsigned int mm_flags) { - unsigned long iss2 = ESR_ELx_ISS2(esr); - if (!system_supports_poe()) return false; - if (esr_fsc_is_permission_fault(esr) && (iss2 & ESR_ELx_Overlay)) - return true; - + /* + * We do not check whether an Overlay fault has occurred because we + * cannot make a decision based solely on its value: + * + * - If Overlay is set, a fault did occur due to POE, but it may be + * spurious in those cases where we update POR_EL0 without ISB (e.g. + * on context-switch). We would then need to manually check POR_EL0 + * against vma_pkey(vma), which is exactly what + * arch_vma_access_permitted() does. + * + * - If Overlay is not set, we may still need to report a pkey fault. + * This is the case if an access was made within a mapping but with no + * page mapped, and POR_EL0 forbids the access (according to + * vma_pkey()). Such access will result in a SIGSEGV regardless + * because core code checks arch_vma_access_permitted(), but in order + * to report the correct error code - SEGV_PKUERR - we must handle + * that case here. + */ return !arch_vma_access_permitted(vma, mm_flags & FAULT_FLAG_WRITE, mm_flags & FAULT_FLAG_INSTRUCTION, @@ -635,7 +647,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, goto bad_area; } - if (fault_from_pkey(esr, vma, mm_flags)) { + if (fault_from_pkey(vma, mm_flags)) { pkey = vma_pkey(vma); vma_end_read(vma); fault = 0; @@ -679,7 +691,7 @@ retry: goto bad_area; } - if (fault_from_pkey(esr, vma, mm_flags)) { + if (fault_from_pkey(vma, mm_flags)) { pkey = vma_pkey(vma); mmap_read_unlock(mm); fault = 0; diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 80d470aa469d..54dccfd6aa11 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -518,7 +518,6 @@ alternative_else_nop_endif msr REG_PIR_EL1, x0 orr tcr2, tcr2, TCR2_EL1_PIE - msr REG_TCR2_EL1, x0 .Lskip_indirection: diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index d71ea0f4466f..1c5544401530 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -98,6 +98,7 @@ config RISCV select CLONE_BACKWARDS select COMMON_CLK select CPU_PM if CPU_IDLE || HIBERNATION || SUSPEND + select DYNAMIC_FTRACE if FUNCTION_TRACER select EDAC_SUPPORT select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if DYNAMIC_FTRACE @@ -162,7 +163,7 @@ config RISCV select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_GRAPH_TRACER if HAVE_DYNAMIC_FTRACE_WITH_ARGS select HAVE_FUNCTION_GRAPH_FREGS - select HAVE_FUNCTION_TRACER if !XIP_KERNEL + select HAVE_FUNCTION_TRACER if !XIP_KERNEL && HAVE_DYNAMIC_FTRACE select HAVE_EBPF_JIT if MMU select HAVE_GUP_FAST if MMU select HAVE_FUNCTION_ARG_ACCESS_API diff --git a/arch/riscv/include/asm/kvm_aia.h b/arch/riscv/include/asm/kvm_aia.h index 3b643b9efc07..b04ecdd1a860 100644 --- a/arch/riscv/include/asm/kvm_aia.h +++ b/arch/riscv/include/asm/kvm_aia.h @@ -87,6 +87,9 @@ DECLARE_STATIC_KEY_FALSE(kvm_riscv_aia_available); extern struct kvm_device_ops kvm_riscv_aia_device_ops; +bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_aia_imsic_load(struct kvm_vcpu *vcpu, int cpu); +void kvm_riscv_vcpu_aia_imsic_put(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu); int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu); @@ -147,7 +150,7 @@ int kvm_riscv_vcpu_aia_rmw_ireg(struct kvm_vcpu *vcpu, unsigned int csr_num, int kvm_riscv_vcpu_aia_update(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_aia_reset(struct kvm_vcpu *vcpu); -int kvm_riscv_vcpu_aia_init(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_aia_init(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_aia_deinit(struct kvm_vcpu *vcpu); int kvm_riscv_aia_inject_msi_by_id(struct kvm *kvm, u32 hart_index, @@ -161,7 +164,6 @@ void kvm_riscv_aia_destroy_vm(struct kvm *kvm); int kvm_riscv_aia_alloc_hgei(int cpu, struct kvm_vcpu *owner, void __iomem **hgei_va, phys_addr_t *hgei_pa); void kvm_riscv_aia_free_hgei(int cpu, int hgei); -void kvm_riscv_aia_wakeon_hgei(struct kvm_vcpu *owner, bool enable); void kvm_riscv_aia_enable(void); void kvm_riscv_aia_disable(void); diff --git a/arch/riscv/include/asm/kvm_gstage.h b/arch/riscv/include/asm/kvm_gstage.h new file mode 100644 index 000000000000..595e2183173e --- /dev/null +++ b/arch/riscv/include/asm/kvm_gstage.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * Copyright (c) 2025 Ventana Micro Systems Inc. + */ + +#ifndef __RISCV_KVM_GSTAGE_H_ +#define __RISCV_KVM_GSTAGE_H_ + +#include <linux/kvm_types.h> + +struct kvm_gstage { + struct kvm *kvm; + unsigned long flags; +#define KVM_GSTAGE_FLAGS_LOCAL BIT(0) + unsigned long vmid; + pgd_t *pgd; +}; + +struct kvm_gstage_mapping { + gpa_t addr; + pte_t pte; + u32 level; +}; + +#ifdef CONFIG_64BIT +#define kvm_riscv_gstage_index_bits 9 +#else +#define kvm_riscv_gstage_index_bits 10 +#endif + +extern unsigned long kvm_riscv_gstage_mode; +extern unsigned long kvm_riscv_gstage_pgd_levels; + +#define kvm_riscv_gstage_pgd_xbits 2 +#define kvm_riscv_gstage_pgd_size (1UL << (HGATP_PAGE_SHIFT + kvm_riscv_gstage_pgd_xbits)) +#define kvm_riscv_gstage_gpa_bits (HGATP_PAGE_SHIFT + \ + (kvm_riscv_gstage_pgd_levels * \ + kvm_riscv_gstage_index_bits) + \ + kvm_riscv_gstage_pgd_xbits) +#define kvm_riscv_gstage_gpa_size ((gpa_t)(1ULL << kvm_riscv_gstage_gpa_bits)) + +bool kvm_riscv_gstage_get_leaf(struct kvm_gstage *gstage, gpa_t addr, + pte_t **ptepp, u32 *ptep_level); + +int kvm_riscv_gstage_set_pte(struct kvm_gstage *gstage, + struct kvm_mmu_memory_cache *pcache, + const struct kvm_gstage_mapping *map); + +int kvm_riscv_gstage_map_page(struct kvm_gstage *gstage, + struct kvm_mmu_memory_cache *pcache, + gpa_t gpa, phys_addr_t hpa, unsigned long page_size, + bool page_rdonly, bool page_exec, + struct kvm_gstage_mapping *out_map); + +enum kvm_riscv_gstage_op { + GSTAGE_OP_NOP = 0, /* Nothing */ + GSTAGE_OP_CLEAR, /* Clear/Unmap */ + GSTAGE_OP_WP, /* Write-protect */ +}; + +void kvm_riscv_gstage_op_pte(struct kvm_gstage *gstage, gpa_t addr, + pte_t *ptep, u32 ptep_level, enum kvm_riscv_gstage_op op); + +void kvm_riscv_gstage_unmap_range(struct kvm_gstage *gstage, + gpa_t start, gpa_t size, bool may_block); + +void kvm_riscv_gstage_wp_range(struct kvm_gstage *gstage, gpa_t start, gpa_t end); + +void kvm_riscv_gstage_mode_detect(void); + +#endif diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 85cfebc32e4c..d71d3299a335 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -16,6 +16,8 @@ #include <asm/hwcap.h> #include <asm/kvm_aia.h> #include <asm/ptrace.h> +#include <asm/kvm_tlb.h> +#include <asm/kvm_vmid.h> #include <asm/kvm_vcpu_fp.h> #include <asm/kvm_vcpu_insn.h> #include <asm/kvm_vcpu_sbi.h> @@ -36,14 +38,16 @@ #define KVM_REQ_UPDATE_HGATP KVM_ARCH_REQ(2) #define KVM_REQ_FENCE_I \ KVM_ARCH_REQ_FLAGS(3, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_HFENCE_GVMA_VMID_ALL KVM_REQ_TLB_FLUSH #define KVM_REQ_HFENCE_VVMA_ALL \ KVM_ARCH_REQ_FLAGS(4, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_HFENCE \ KVM_ARCH_REQ_FLAGS(5, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_STEAL_UPDATE KVM_ARCH_REQ(6) +#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE + #define KVM_HEDELEG_DEFAULT (BIT(EXC_INST_MISALIGNED) | \ + BIT(EXC_INST_ILLEGAL) | \ BIT(EXC_BREAKPOINT) | \ BIT(EXC_SYSCALL) | \ BIT(EXC_INST_PAGE_FAULT) | \ @@ -54,24 +58,6 @@ BIT(IRQ_VS_TIMER) | \ BIT(IRQ_VS_EXT)) -enum kvm_riscv_hfence_type { - KVM_RISCV_HFENCE_UNKNOWN = 0, - KVM_RISCV_HFENCE_GVMA_VMID_GPA, - KVM_RISCV_HFENCE_VVMA_ASID_GVA, - KVM_RISCV_HFENCE_VVMA_ASID_ALL, - KVM_RISCV_HFENCE_VVMA_GVA, -}; - -struct kvm_riscv_hfence { - enum kvm_riscv_hfence_type type; - unsigned long asid; - unsigned long order; - gpa_t addr; - gpa_t size; -}; - -#define KVM_RISCV_VCPU_MAX_HFENCE 64 - struct kvm_vm_stat { struct kvm_vm_stat_generic generic; }; @@ -97,15 +83,6 @@ struct kvm_vcpu_stat { struct kvm_arch_memory_slot { }; -struct kvm_vmid { - /* - * Writes to vmid_version and vmid happen with vmid_lock held - * whereas reads happen without any lock held. - */ - unsigned long vmid_version; - unsigned long vmid; -}; - struct kvm_arch { /* G-stage vmid */ struct kvm_vmid vmid; @@ -306,76 +283,8 @@ static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu) return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu; } -#define KVM_RISCV_GSTAGE_TLB_MIN_ORDER 12 - -void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid, - gpa_t gpa, gpa_t gpsz, - unsigned long order); -void kvm_riscv_local_hfence_gvma_vmid_all(unsigned long vmid); -void kvm_riscv_local_hfence_gvma_gpa(gpa_t gpa, gpa_t gpsz, - unsigned long order); -void kvm_riscv_local_hfence_gvma_all(void); -void kvm_riscv_local_hfence_vvma_asid_gva(unsigned long vmid, - unsigned long asid, - unsigned long gva, - unsigned long gvsz, - unsigned long order); -void kvm_riscv_local_hfence_vvma_asid_all(unsigned long vmid, - unsigned long asid); -void kvm_riscv_local_hfence_vvma_gva(unsigned long vmid, - unsigned long gva, unsigned long gvsz, - unsigned long order); -void kvm_riscv_local_hfence_vvma_all(unsigned long vmid); - -void kvm_riscv_local_tlb_sanitize(struct kvm_vcpu *vcpu); - -void kvm_riscv_fence_i_process(struct kvm_vcpu *vcpu); -void kvm_riscv_hfence_gvma_vmid_all_process(struct kvm_vcpu *vcpu); -void kvm_riscv_hfence_vvma_all_process(struct kvm_vcpu *vcpu); -void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu); - -void kvm_riscv_fence_i(struct kvm *kvm, - unsigned long hbase, unsigned long hmask); -void kvm_riscv_hfence_gvma_vmid_gpa(struct kvm *kvm, - unsigned long hbase, unsigned long hmask, - gpa_t gpa, gpa_t gpsz, - unsigned long order); -void kvm_riscv_hfence_gvma_vmid_all(struct kvm *kvm, - unsigned long hbase, unsigned long hmask); -void kvm_riscv_hfence_vvma_asid_gva(struct kvm *kvm, - unsigned long hbase, unsigned long hmask, - unsigned long gva, unsigned long gvsz, - unsigned long order, unsigned long asid); -void kvm_riscv_hfence_vvma_asid_all(struct kvm *kvm, - unsigned long hbase, unsigned long hmask, - unsigned long asid); -void kvm_riscv_hfence_vvma_gva(struct kvm *kvm, - unsigned long hbase, unsigned long hmask, - unsigned long gva, unsigned long gvsz, - unsigned long order); -void kvm_riscv_hfence_vvma_all(struct kvm *kvm, - unsigned long hbase, unsigned long hmask); - -int kvm_riscv_gstage_ioremap(struct kvm *kvm, gpa_t gpa, - phys_addr_t hpa, unsigned long size, - bool writable, bool in_atomic); -void kvm_riscv_gstage_iounmap(struct kvm *kvm, gpa_t gpa, - unsigned long size); -int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, - struct kvm_memory_slot *memslot, - gpa_t gpa, unsigned long hva, bool is_write); -int kvm_riscv_gstage_alloc_pgd(struct kvm *kvm); -void kvm_riscv_gstage_free_pgd(struct kvm *kvm); -void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu); -void __init kvm_riscv_gstage_mode_detect(void); -unsigned long __init kvm_riscv_gstage_mode(void); -int kvm_riscv_gstage_gpa_bits(void); - -void __init kvm_riscv_gstage_vmid_detect(void); -unsigned long kvm_riscv_gstage_vmid_bits(void); -int kvm_riscv_gstage_vmid_init(struct kvm *kvm); -bool kvm_riscv_gstage_vmid_ver_changed(struct kvm_vmid *vmid); -void kvm_riscv_gstage_vmid_update(struct kvm_vcpu *vcpu); +static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} +static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} int kvm_riscv_setup_default_irq_routing(struct kvm *kvm, u32 lines); @@ -412,7 +321,6 @@ void __kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu); bool kvm_riscv_vcpu_stopped(struct kvm_vcpu *vcpu); -void kvm_riscv_vcpu_sbi_sta_reset(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu); #endif /* __RISCV_KVM_HOST_H__ */ diff --git a/arch/riscv/include/asm/kvm_mmu.h b/arch/riscv/include/asm/kvm_mmu.h new file mode 100644 index 000000000000..5439e76f0a96 --- /dev/null +++ b/arch/riscv/include/asm/kvm_mmu.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 Ventana Micro Systems Inc. + */ + +#ifndef __RISCV_KVM_MMU_H_ +#define __RISCV_KVM_MMU_H_ + +#include <asm/kvm_gstage.h> + +int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa, + unsigned long size, bool writable, bool in_atomic); +void kvm_riscv_mmu_iounmap(struct kvm *kvm, gpa_t gpa, unsigned long size); +int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, + gpa_t gpa, unsigned long hva, bool is_write, + struct kvm_gstage_mapping *out_map); +int kvm_riscv_mmu_alloc_pgd(struct kvm *kvm); +void kvm_riscv_mmu_free_pgd(struct kvm *kvm); +void kvm_riscv_mmu_update_hgatp(struct kvm_vcpu *vcpu); + +#endif diff --git a/arch/riscv/include/asm/kvm_tlb.h b/arch/riscv/include/asm/kvm_tlb.h new file mode 100644 index 000000000000..38a2f933ad3a --- /dev/null +++ b/arch/riscv/include/asm/kvm_tlb.h @@ -0,0 +1,84 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 Ventana Micro Systems Inc. + */ + +#ifndef __RISCV_KVM_TLB_H_ +#define __RISCV_KVM_TLB_H_ + +#include <linux/kvm_types.h> + +enum kvm_riscv_hfence_type { + KVM_RISCV_HFENCE_UNKNOWN = 0, + KVM_RISCV_HFENCE_GVMA_VMID_GPA, + KVM_RISCV_HFENCE_GVMA_VMID_ALL, + KVM_RISCV_HFENCE_VVMA_ASID_GVA, + KVM_RISCV_HFENCE_VVMA_ASID_ALL, + KVM_RISCV_HFENCE_VVMA_GVA, + KVM_RISCV_HFENCE_VVMA_ALL +}; + +struct kvm_riscv_hfence { + enum kvm_riscv_hfence_type type; + unsigned long asid; + unsigned long vmid; + unsigned long order; + gpa_t addr; + gpa_t size; +}; + +#define KVM_RISCV_VCPU_MAX_HFENCE 64 + +#define KVM_RISCV_GSTAGE_TLB_MIN_ORDER 12 + +void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid, + gpa_t gpa, gpa_t gpsz, + unsigned long order); +void kvm_riscv_local_hfence_gvma_vmid_all(unsigned long vmid); +void kvm_riscv_local_hfence_gvma_gpa(gpa_t gpa, gpa_t gpsz, + unsigned long order); +void kvm_riscv_local_hfence_gvma_all(void); +void kvm_riscv_local_hfence_vvma_asid_gva(unsigned long vmid, + unsigned long asid, + unsigned long gva, + unsigned long gvsz, + unsigned long order); +void kvm_riscv_local_hfence_vvma_asid_all(unsigned long vmid, + unsigned long asid); +void kvm_riscv_local_hfence_vvma_gva(unsigned long vmid, + unsigned long gva, unsigned long gvsz, + unsigned long order); +void kvm_riscv_local_hfence_vvma_all(unsigned long vmid); + +void kvm_riscv_tlb_flush_process(struct kvm_vcpu *vcpu); + +void kvm_riscv_fence_i_process(struct kvm_vcpu *vcpu); +void kvm_riscv_hfence_vvma_all_process(struct kvm_vcpu *vcpu); +void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu); + +void kvm_riscv_fence_i(struct kvm *kvm, + unsigned long hbase, unsigned long hmask); +void kvm_riscv_hfence_gvma_vmid_gpa(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + gpa_t gpa, gpa_t gpsz, + unsigned long order, unsigned long vmid); +void kvm_riscv_hfence_gvma_vmid_all(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long vmid); +void kvm_riscv_hfence_vvma_asid_gva(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long gva, unsigned long gvsz, + unsigned long order, unsigned long asid, + unsigned long vmid); +void kvm_riscv_hfence_vvma_asid_all(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long asid, unsigned long vmid); +void kvm_riscv_hfence_vvma_gva(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long gva, unsigned long gvsz, + unsigned long order, unsigned long vmid); +void kvm_riscv_hfence_vvma_all(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long vmid); + +#endif diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h index 439ab2b3534f..d678fd7e5973 100644 --- a/arch/riscv/include/asm/kvm_vcpu_sbi.h +++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h @@ -49,6 +49,16 @@ struct kvm_vcpu_sbi_extension { /* Extension specific probe function */ unsigned long (*probe)(struct kvm_vcpu *vcpu); + + /* + * Init/deinit function called once during VCPU init/destroy. These + * might be use if the SBI extensions need to allocate or do specific + * init time only configuration. + */ + int (*init)(struct kvm_vcpu *vcpu); + void (*deinit)(struct kvm_vcpu *vcpu); + + void (*reset)(struct kvm_vcpu *vcpu); }; void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run); @@ -72,6 +82,8 @@ const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext( bool riscv_vcpu_supports_sbi_ext(struct kvm_vcpu *vcpu, int idx); int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run); void kvm_riscv_vcpu_sbi_init(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_sbi_deinit(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_sbi_reset(struct kvm_vcpu *vcpu); int kvm_riscv_vcpu_get_reg_sbi_sta(struct kvm_vcpu *vcpu, unsigned long reg_num, unsigned long *reg_val); diff --git a/arch/riscv/include/asm/kvm_vmid.h b/arch/riscv/include/asm/kvm_vmid.h new file mode 100644 index 000000000000..ab98e1434fb7 --- /dev/null +++ b/arch/riscv/include/asm/kvm_vmid.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 Ventana Micro Systems Inc. + */ + +#ifndef __RISCV_KVM_VMID_H_ +#define __RISCV_KVM_VMID_H_ + +#include <linux/kvm_types.h> + +struct kvm_vmid { + /* + * Writes to vmid_version and vmid happen with vmid_lock held + * whereas reads happen without any lock held. + */ + unsigned long vmid_version; + unsigned long vmid; +}; + +void __init kvm_riscv_gstage_vmid_detect(void); +unsigned long kvm_riscv_gstage_vmid_bits(void); +int kvm_riscv_gstage_vmid_init(struct kvm *kvm); +bool kvm_riscv_gstage_vmid_ver_changed(struct kvm_vmid *vmid); +void kvm_riscv_gstage_vmid_update(struct kvm_vcpu *vcpu); +void kvm_riscv_gstage_vmid_sanitize(struct kvm_vcpu *vcpu); + +#endif diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index 525e50db24f7..b88a6218b7f2 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -311,8 +311,8 @@ do { \ do { \ if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && \ !IS_ALIGNED((uintptr_t)__gu_ptr, sizeof(*__gu_ptr))) { \ - __inttype(x) val = (__inttype(x))x; \ - if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(val), sizeof(*__gu_ptr))) \ + __inttype(x) ___val = (__inttype(x))x; \ + if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(___val), sizeof(*__gu_ptr))) \ goto label; \ break; \ } \ diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h index 5f59fd226cc5..ef27d4289da1 100644 --- a/arch/riscv/include/uapi/asm/kvm.h +++ b/arch/riscv/include/uapi/asm/kvm.h @@ -18,6 +18,7 @@ #define __KVM_HAVE_IRQ_LINE #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 +#define KVM_DIRTY_LOG_PAGE_OFFSET 64 #define KVM_INTERRUPT_SET -1U #define KVM_INTERRUPT_UNSET -2U diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 4c6c24380cfd..8d18d6727f0f 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -14,6 +14,18 @@ #include <asm/text-patching.h> #ifdef CONFIG_DYNAMIC_FTRACE +void ftrace_arch_code_modify_prepare(void) + __acquires(&text_mutex) +{ + mutex_lock(&text_mutex); +} + +void ftrace_arch_code_modify_post_process(void) + __releases(&text_mutex) +{ + mutex_unlock(&text_mutex); +} + unsigned long ftrace_call_adjust(unsigned long addr) { if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) @@ -29,10 +41,8 @@ unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip) void arch_ftrace_update_code(int command) { - mutex_lock(&text_mutex); command |= FTRACE_MAY_SLEEP; ftrace_modify_all_code(command); - mutex_unlock(&text_mutex); flush_icache_all(); } @@ -149,6 +159,8 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) unsigned int nops[2], offset; int ret; + guard(mutex)(&text_mutex); + ret = ftrace_rec_set_nop_ops(rec); if (ret) return ret; @@ -157,9 +169,7 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) nops[0] = to_auipc_t0(offset); nops[1] = RISCV_INSN_NOP4; - mutex_lock(&text_mutex); ret = patch_insn_write((void *)pc, nops, 2 * MCOUNT_INSN_SIZE); - mutex_unlock(&text_mutex); return ret; } diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 9c83848797a7..80230de167de 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -6,6 +6,7 @@ #include <linux/cpu.h> #include <linux/kernel.h> #include <linux/init.h> +#include <linux/irqflags.h> #include <linux/randomize_kstack.h> #include <linux/sched.h> #include <linux/sched/debug.h> @@ -151,7 +152,9 @@ asmlinkage __visible __trap_section void name(struct pt_regs *regs) \ { \ if (user_mode(regs)) { \ irqentry_enter_from_user_mode(regs); \ + local_irq_enable(); \ do_trap_error(regs, signo, code, regs->epc, "Oops - " str); \ + local_irq_disable(); \ irqentry_exit_to_user_mode(regs); \ } else { \ irqentry_state_t state = irqentry_nmi_enter(regs); \ @@ -173,17 +176,14 @@ asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *re if (user_mode(regs)) { irqentry_enter_from_user_mode(regs); - local_irq_enable(); handled = riscv_v_first_use_handler(regs); - - local_irq_disable(); - if (!handled) do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc, "Oops - illegal instruction"); + local_irq_disable(); irqentry_exit_to_user_mode(regs); } else { irqentry_state_t state = irqentry_nmi_enter(regs); @@ -308,9 +308,11 @@ asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs) { if (user_mode(regs)) { irqentry_enter_from_user_mode(regs); + local_irq_enable(); handle_break(regs); + local_irq_disable(); irqentry_exit_to_user_mode(regs); } else { irqentry_state_t state = irqentry_nmi_enter(regs); diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index 93043924fe6c..f760e4fcc052 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -461,7 +461,7 @@ static int handle_scalar_misaligned_load(struct pt_regs *regs) } if (!fp) - SET_RD(insn, regs, val.data_ulong << shift >> shift); + SET_RD(insn, regs, (long)(val.data_ulong << shift) >> shift); else if (len == 8) set_f64_rd(insn, regs, val.data_u64); else diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig index 704c2899197e..5a62091b0809 100644 --- a/arch/riscv/kvm/Kconfig +++ b/arch/riscv/kvm/Kconfig @@ -25,6 +25,7 @@ config KVM select HAVE_KVM_MSI select HAVE_KVM_VCPU_ASYNC_IOCTL select HAVE_KVM_READONLY_MEM + select HAVE_KVM_DIRTY_RING_ACQ_REL select KVM_COMMON select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_GENERIC_HARDWARE_ENABLING diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index 4e0bba91d284..4b199dc3e58b 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -14,6 +14,7 @@ kvm-y += aia.o kvm-y += aia_aplic.o kvm-y += aia_device.o kvm-y += aia_imsic.o +kvm-y += gstage.o kvm-y += main.o kvm-y += mmu.o kvm-y += nacl.o diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c index 19afd1f23537..dad318185660 100644 --- a/arch/riscv/kvm/aia.c +++ b/arch/riscv/kvm/aia.c @@ -30,28 +30,6 @@ unsigned int kvm_riscv_aia_nr_hgei; unsigned int kvm_riscv_aia_max_ids; DEFINE_STATIC_KEY_FALSE(kvm_riscv_aia_available); -static int aia_find_hgei(struct kvm_vcpu *owner) -{ - int i, hgei; - unsigned long flags; - struct aia_hgei_control *hgctrl = get_cpu_ptr(&aia_hgei); - - raw_spin_lock_irqsave(&hgctrl->lock, flags); - - hgei = -1; - for (i = 1; i <= kvm_riscv_aia_nr_hgei; i++) { - if (hgctrl->owners[i] == owner) { - hgei = i; - break; - } - } - - raw_spin_unlock_irqrestore(&hgctrl->lock, flags); - - put_cpu_ptr(&aia_hgei); - return hgei; -} - static inline unsigned long aia_hvictl_value(bool ext_irq_pending) { unsigned long hvictl; @@ -95,7 +73,6 @@ void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu) bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask) { - int hgei; unsigned long seip; if (!kvm_riscv_aia_available()) @@ -114,11 +91,7 @@ bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask) if (!kvm_riscv_aia_initialized(vcpu->kvm) || !seip) return false; - hgei = aia_find_hgei(vcpu); - if (hgei > 0) - return !!(ncsr_read(CSR_HGEIP) & BIT(hgei)); - - return false; + return kvm_riscv_vcpu_aia_imsic_has_interrupt(vcpu); } void kvm_riscv_vcpu_aia_update_hvip(struct kvm_vcpu *vcpu) @@ -164,6 +137,9 @@ void kvm_riscv_vcpu_aia_load(struct kvm_vcpu *vcpu, int cpu) csr_write(CSR_HVIPRIO2H, csr->hviprio2h); #endif } + + if (kvm_riscv_aia_initialized(vcpu->kvm)) + kvm_riscv_vcpu_aia_imsic_load(vcpu, cpu); } void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu) @@ -174,6 +150,9 @@ void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu) if (!kvm_riscv_aia_available()) return; + if (kvm_riscv_aia_initialized(vcpu->kvm)) + kvm_riscv_vcpu_aia_imsic_put(vcpu); + if (kvm_riscv_nacl_available()) { nsh = nacl_shmem(); csr->vsiselect = nacl_csr_read(nsh, CSR_VSISELECT); @@ -472,22 +451,6 @@ void kvm_riscv_aia_free_hgei(int cpu, int hgei) raw_spin_unlock_irqrestore(&hgctrl->lock, flags); } -void kvm_riscv_aia_wakeon_hgei(struct kvm_vcpu *owner, bool enable) -{ - int hgei; - - if (!kvm_riscv_aia_available()) - return; - - hgei = aia_find_hgei(owner); - if (hgei > 0) { - if (enable) - csr_set(CSR_HGEIE, BIT(hgei)); - else - csr_clear(CSR_HGEIE, BIT(hgei)); - } -} - static irqreturn_t hgei_interrupt(int irq, void *dev_id) { int i; diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c index 806c41931cde..b195a93add1c 100644 --- a/arch/riscv/kvm/aia_device.c +++ b/arch/riscv/kvm/aia_device.c @@ -509,12 +509,12 @@ void kvm_riscv_vcpu_aia_reset(struct kvm_vcpu *vcpu) kvm_riscv_vcpu_aia_imsic_reset(vcpu); } -int kvm_riscv_vcpu_aia_init(struct kvm_vcpu *vcpu) +void kvm_riscv_vcpu_aia_init(struct kvm_vcpu *vcpu) { struct kvm_vcpu_aia *vaia = &vcpu->arch.aia_context; if (!kvm_riscv_aia_available()) - return 0; + return; /* * We don't do any memory allocations over here because these @@ -526,8 +526,6 @@ int kvm_riscv_vcpu_aia_init(struct kvm_vcpu *vcpu) /* Initialize default values in AIA vcpu context */ vaia->imsic_addr = KVM_RISCV_AIA_UNDEF_ADDR; vaia->hart_index = vcpu->vcpu_idx; - - return 0; } void kvm_riscv_vcpu_aia_deinit(struct kvm_vcpu *vcpu) diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c index 29ef9c2133a9..fda0346f0ea1 100644 --- a/arch/riscv/kvm/aia_imsic.c +++ b/arch/riscv/kvm/aia_imsic.c @@ -16,6 +16,7 @@ #include <linux/swab.h> #include <kvm/iodev.h> #include <asm/csr.h> +#include <asm/kvm_mmu.h> #define IMSIC_MAX_EIX (IMSIC_MAX_ID / BITS_PER_TYPE(u64)) @@ -676,6 +677,48 @@ static void imsic_swfile_update(struct kvm_vcpu *vcpu, imsic_swfile_extirq_update(vcpu); } +bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu) +{ + struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + unsigned long flags; + bool ret = false; + + /* + * The IMSIC SW-file directly injects interrupt via hvip so + * only check for interrupt when IMSIC VS-file is being used. + */ + + read_lock_irqsave(&imsic->vsfile_lock, flags); + if (imsic->vsfile_cpu > -1) + ret = !!(csr_read(CSR_HGEIP) & BIT(imsic->vsfile_hgei)); + read_unlock_irqrestore(&imsic->vsfile_lock, flags); + + return ret; +} + +void kvm_riscv_vcpu_aia_imsic_load(struct kvm_vcpu *vcpu, int cpu) +{ + /* + * No need to explicitly clear HGEIE CSR bits because the + * hgei interrupt handler (aka hgei_interrupt()) will always + * clear it for us. + */ +} + +void kvm_riscv_vcpu_aia_imsic_put(struct kvm_vcpu *vcpu) +{ + struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + unsigned long flags; + + if (!kvm_vcpu_is_blocking(vcpu)) + return; + + read_lock_irqsave(&imsic->vsfile_lock, flags); + if (imsic->vsfile_cpu > -1) + csr_set(CSR_HGEIE, BIT(imsic->vsfile_hgei)); + read_unlock_irqrestore(&imsic->vsfile_lock, flags); +} + void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu) { unsigned long flags; @@ -703,9 +746,8 @@ void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu) */ /* Purge the G-stage mapping */ - kvm_riscv_gstage_iounmap(vcpu->kvm, - vcpu->arch.aia_context.imsic_addr, - IMSIC_MMIO_PAGE_SZ); + kvm_riscv_mmu_iounmap(vcpu->kvm, vcpu->arch.aia_context.imsic_addr, + IMSIC_MMIO_PAGE_SZ); /* TODO: Purge the IOMMU mapping ??? */ @@ -781,13 +823,16 @@ int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu) * producers to the new IMSIC VS-file. */ + /* Ensure HGEIE CSR bit is zero before using the new IMSIC VS-file */ + csr_clear(CSR_HGEIE, BIT(new_vsfile_hgei)); + /* Zero-out new IMSIC VS-file */ imsic_vsfile_local_clear(new_vsfile_hgei, imsic->nr_hw_eix); /* Update G-stage mapping for the new IMSIC VS-file */ - ret = kvm_riscv_gstage_ioremap(kvm, vcpu->arch.aia_context.imsic_addr, - new_vsfile_pa, IMSIC_MMIO_PAGE_SZ, - true, true); + ret = kvm_riscv_mmu_ioremap(kvm, vcpu->arch.aia_context.imsic_addr, + new_vsfile_pa, IMSIC_MMIO_PAGE_SZ, + true, true); if (ret) goto fail_free_vsfile_hgei; diff --git a/arch/riscv/kvm/gstage.c b/arch/riscv/kvm/gstage.c new file mode 100644 index 000000000000..24c270d6d0e2 --- /dev/null +++ b/arch/riscv/kvm/gstage.c @@ -0,0 +1,338 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * Copyright (c) 2025 Ventana Micro Systems Inc. + */ + +#include <linux/bitops.h> +#include <linux/errno.h> +#include <linux/kvm_host.h> +#include <linux/module.h> +#include <linux/pgtable.h> +#include <asm/kvm_gstage.h> + +#ifdef CONFIG_64BIT +unsigned long kvm_riscv_gstage_mode __ro_after_init = HGATP_MODE_SV39X4; +unsigned long kvm_riscv_gstage_pgd_levels __ro_after_init = 3; +#else +unsigned long kvm_riscv_gstage_mode __ro_after_init = HGATP_MODE_SV32X4; +unsigned long kvm_riscv_gstage_pgd_levels __ro_after_init = 2; +#endif + +#define gstage_pte_leaf(__ptep) \ + (pte_val(*(__ptep)) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)) + +static inline unsigned long gstage_pte_index(gpa_t addr, u32 level) +{ + unsigned long mask; + unsigned long shift = HGATP_PAGE_SHIFT + (kvm_riscv_gstage_index_bits * level); + + if (level == (kvm_riscv_gstage_pgd_levels - 1)) + mask = (PTRS_PER_PTE * (1UL << kvm_riscv_gstage_pgd_xbits)) - 1; + else + mask = PTRS_PER_PTE - 1; + + return (addr >> shift) & mask; +} + +static inline unsigned long gstage_pte_page_vaddr(pte_t pte) +{ + return (unsigned long)pfn_to_virt(__page_val_to_pfn(pte_val(pte))); +} + +static int gstage_page_size_to_level(unsigned long page_size, u32 *out_level) +{ + u32 i; + unsigned long psz = 1UL << 12; + + for (i = 0; i < kvm_riscv_gstage_pgd_levels; i++) { + if (page_size == (psz << (i * kvm_riscv_gstage_index_bits))) { + *out_level = i; + return 0; + } + } + + return -EINVAL; +} + +static int gstage_level_to_page_order(u32 level, unsigned long *out_pgorder) +{ + if (kvm_riscv_gstage_pgd_levels < level) + return -EINVAL; + + *out_pgorder = 12 + (level * kvm_riscv_gstage_index_bits); + return 0; +} + +static int gstage_level_to_page_size(u32 level, unsigned long *out_pgsize) +{ + int rc; + unsigned long page_order = PAGE_SHIFT; + + rc = gstage_level_to_page_order(level, &page_order); + if (rc) + return rc; + + *out_pgsize = BIT(page_order); + return 0; +} + +bool kvm_riscv_gstage_get_leaf(struct kvm_gstage *gstage, gpa_t addr, + pte_t **ptepp, u32 *ptep_level) +{ + pte_t *ptep; + u32 current_level = kvm_riscv_gstage_pgd_levels - 1; + + *ptep_level = current_level; + ptep = (pte_t *)gstage->pgd; + ptep = &ptep[gstage_pte_index(addr, current_level)]; + while (ptep && pte_val(ptep_get(ptep))) { + if (gstage_pte_leaf(ptep)) { + *ptep_level = current_level; + *ptepp = ptep; + return true; + } + + if (current_level) { + current_level--; + *ptep_level = current_level; + ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep)); + ptep = &ptep[gstage_pte_index(addr, current_level)]; + } else { + ptep = NULL; + } + } + + return false; +} + +static void gstage_tlb_flush(struct kvm_gstage *gstage, u32 level, gpa_t addr) +{ + unsigned long order = PAGE_SHIFT; + + if (gstage_level_to_page_order(level, &order)) + return; + addr &= ~(BIT(order) - 1); + + if (gstage->flags & KVM_GSTAGE_FLAGS_LOCAL) + kvm_riscv_local_hfence_gvma_vmid_gpa(gstage->vmid, addr, BIT(order), order); + else + kvm_riscv_hfence_gvma_vmid_gpa(gstage->kvm, -1UL, 0, addr, BIT(order), order, + gstage->vmid); +} + +int kvm_riscv_gstage_set_pte(struct kvm_gstage *gstage, + struct kvm_mmu_memory_cache *pcache, + const struct kvm_gstage_mapping *map) +{ + u32 current_level = kvm_riscv_gstage_pgd_levels - 1; + pte_t *next_ptep = (pte_t *)gstage->pgd; + pte_t *ptep = &next_ptep[gstage_pte_index(map->addr, current_level)]; + + if (current_level < map->level) + return -EINVAL; + + while (current_level != map->level) { + if (gstage_pte_leaf(ptep)) + return -EEXIST; + + if (!pte_val(ptep_get(ptep))) { + if (!pcache) + return -ENOMEM; + next_ptep = kvm_mmu_memory_cache_alloc(pcache); + if (!next_ptep) + return -ENOMEM; + set_pte(ptep, pfn_pte(PFN_DOWN(__pa(next_ptep)), + __pgprot(_PAGE_TABLE))); + } else { + if (gstage_pte_leaf(ptep)) + return -EEXIST; + next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep)); + } + + current_level--; + ptep = &next_ptep[gstage_pte_index(map->addr, current_level)]; + } + + if (pte_val(*ptep) != pte_val(map->pte)) { + set_pte(ptep, map->pte); + if (gstage_pte_leaf(ptep)) + gstage_tlb_flush(gstage, current_level, map->addr); + } + + return 0; +} + +int kvm_riscv_gstage_map_page(struct kvm_gstage *gstage, + struct kvm_mmu_memory_cache *pcache, + gpa_t gpa, phys_addr_t hpa, unsigned long page_size, + bool page_rdonly, bool page_exec, + struct kvm_gstage_mapping *out_map) +{ + pgprot_t prot; + int ret; + + out_map->addr = gpa; + out_map->level = 0; + + ret = gstage_page_size_to_level(page_size, &out_map->level); + if (ret) + return ret; + + /* + * A RISC-V implementation can choose to either: + * 1) Update 'A' and 'D' PTE bits in hardware + * 2) Generate page fault when 'A' and/or 'D' bits are not set + * PTE so that software can update these bits. + * + * We support both options mentioned above. To achieve this, we + * always set 'A' and 'D' PTE bits at time of creating G-stage + * mapping. To support KVM dirty page logging with both options + * mentioned above, we will write-protect G-stage PTEs to track + * dirty pages. + */ + + if (page_exec) { + if (page_rdonly) + prot = PAGE_READ_EXEC; + else + prot = PAGE_WRITE_EXEC; + } else { + if (page_rdonly) + prot = PAGE_READ; + else + prot = PAGE_WRITE; + } + out_map->pte = pfn_pte(PFN_DOWN(hpa), prot); + out_map->pte = pte_mkdirty(out_map->pte); + + return kvm_riscv_gstage_set_pte(gstage, pcache, out_map); +} + +void kvm_riscv_gstage_op_pte(struct kvm_gstage *gstage, gpa_t addr, + pte_t *ptep, u32 ptep_level, enum kvm_riscv_gstage_op op) +{ + int i, ret; + pte_t old_pte, *next_ptep; + u32 next_ptep_level; + unsigned long next_page_size, page_size; + + ret = gstage_level_to_page_size(ptep_level, &page_size); + if (ret) + return; + + WARN_ON(addr & (page_size - 1)); + + if (!pte_val(ptep_get(ptep))) + return; + + if (ptep_level && !gstage_pte_leaf(ptep)) { + next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep)); + next_ptep_level = ptep_level - 1; + ret = gstage_level_to_page_size(next_ptep_level, &next_page_size); + if (ret) + return; + + if (op == GSTAGE_OP_CLEAR) + set_pte(ptep, __pte(0)); + for (i = 0; i < PTRS_PER_PTE; i++) + kvm_riscv_gstage_op_pte(gstage, addr + i * next_page_size, + &next_ptep[i], next_ptep_level, op); + if (op == GSTAGE_OP_CLEAR) + put_page(virt_to_page(next_ptep)); + } else { + old_pte = *ptep; + if (op == GSTAGE_OP_CLEAR) + set_pte(ptep, __pte(0)); + else if (op == GSTAGE_OP_WP) + set_pte(ptep, __pte(pte_val(ptep_get(ptep)) & ~_PAGE_WRITE)); + if (pte_val(*ptep) != pte_val(old_pte)) + gstage_tlb_flush(gstage, ptep_level, addr); + } +} + +void kvm_riscv_gstage_unmap_range(struct kvm_gstage *gstage, + gpa_t start, gpa_t size, bool may_block) +{ + int ret; + pte_t *ptep; + u32 ptep_level; + bool found_leaf; + unsigned long page_size; + gpa_t addr = start, end = start + size; + + while (addr < end) { + found_leaf = kvm_riscv_gstage_get_leaf(gstage, addr, &ptep, &ptep_level); + ret = gstage_level_to_page_size(ptep_level, &page_size); + if (ret) + break; + + if (!found_leaf) + goto next; + + if (!(addr & (page_size - 1)) && ((end - addr) >= page_size)) + kvm_riscv_gstage_op_pte(gstage, addr, ptep, + ptep_level, GSTAGE_OP_CLEAR); + +next: + addr += page_size; + + /* + * If the range is too large, release the kvm->mmu_lock + * to prevent starvation and lockup detector warnings. + */ + if (!(gstage->flags & KVM_GSTAGE_FLAGS_LOCAL) && may_block && addr < end) + cond_resched_lock(&gstage->kvm->mmu_lock); + } +} + +void kvm_riscv_gstage_wp_range(struct kvm_gstage *gstage, gpa_t start, gpa_t end) +{ + int ret; + pte_t *ptep; + u32 ptep_level; + bool found_leaf; + gpa_t addr = start; + unsigned long page_size; + + while (addr < end) { + found_leaf = kvm_riscv_gstage_get_leaf(gstage, addr, &ptep, &ptep_level); + ret = gstage_level_to_page_size(ptep_level, &page_size); + if (ret) + break; + + if (!found_leaf) + goto next; + + if (!(addr & (page_size - 1)) && ((end - addr) >= page_size)) + kvm_riscv_gstage_op_pte(gstage, addr, ptep, + ptep_level, GSTAGE_OP_WP); + +next: + addr += page_size; + } +} + +void __init kvm_riscv_gstage_mode_detect(void) +{ +#ifdef CONFIG_64BIT + /* Try Sv57x4 G-stage mode */ + csr_write(CSR_HGATP, HGATP_MODE_SV57X4 << HGATP_MODE_SHIFT); + if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV57X4) { + kvm_riscv_gstage_mode = HGATP_MODE_SV57X4; + kvm_riscv_gstage_pgd_levels = 5; + goto skip_sv48x4_test; + } + + /* Try Sv48x4 G-stage mode */ + csr_write(CSR_HGATP, HGATP_MODE_SV48X4 << HGATP_MODE_SHIFT); + if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV48X4) { + kvm_riscv_gstage_mode = HGATP_MODE_SV48X4; + kvm_riscv_gstage_pgd_levels = 4; + } +skip_sv48x4_test: + + csr_write(CSR_HGATP, 0); + kvm_riscv_local_hfence_gvma_all(); +#endif +} diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c index 4b24705dc63a..67c876de74ef 100644 --- a/arch/riscv/kvm/main.c +++ b/arch/riscv/kvm/main.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/kvm_host.h> #include <asm/cpufeature.h> +#include <asm/kvm_mmu.h> #include <asm/kvm_nacl.h> #include <asm/sbi.h> @@ -134,7 +135,7 @@ static int __init riscv_kvm_init(void) (rc) ? slist : "no features"); } - switch (kvm_riscv_gstage_mode()) { + switch (kvm_riscv_gstage_mode) { case HGATP_MODE_SV32X4: str = "Sv32x4"; break; diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 1087ea74567b..a1c3b2ec1dde 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -6,348 +6,38 @@ * Anup Patel <anup.patel@wdc.com> */ -#include <linux/bitops.h> #include <linux/errno.h> -#include <linux/err.h> #include <linux/hugetlb.h> #include <linux/module.h> #include <linux/uaccess.h> #include <linux/vmalloc.h> #include <linux/kvm_host.h> #include <linux/sched/signal.h> +#include <asm/kvm_mmu.h> #include <asm/kvm_nacl.h> -#include <asm/page.h> -#include <asm/pgtable.h> - -#ifdef CONFIG_64BIT -static unsigned long gstage_mode __ro_after_init = (HGATP_MODE_SV39X4 << HGATP_MODE_SHIFT); -static unsigned long gstage_pgd_levels __ro_after_init = 3; -#define gstage_index_bits 9 -#else -static unsigned long gstage_mode __ro_after_init = (HGATP_MODE_SV32X4 << HGATP_MODE_SHIFT); -static unsigned long gstage_pgd_levels __ro_after_init = 2; -#define gstage_index_bits 10 -#endif - -#define gstage_pgd_xbits 2 -#define gstage_pgd_size (1UL << (HGATP_PAGE_SHIFT + gstage_pgd_xbits)) -#define gstage_gpa_bits (HGATP_PAGE_SHIFT + \ - (gstage_pgd_levels * gstage_index_bits) + \ - gstage_pgd_xbits) -#define gstage_gpa_size ((gpa_t)(1ULL << gstage_gpa_bits)) - -#define gstage_pte_leaf(__ptep) \ - (pte_val(*(__ptep)) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)) - -static inline unsigned long gstage_pte_index(gpa_t addr, u32 level) -{ - unsigned long mask; - unsigned long shift = HGATP_PAGE_SHIFT + (gstage_index_bits * level); - - if (level == (gstage_pgd_levels - 1)) - mask = (PTRS_PER_PTE * (1UL << gstage_pgd_xbits)) - 1; - else - mask = PTRS_PER_PTE - 1; - - return (addr >> shift) & mask; -} - -static inline unsigned long gstage_pte_page_vaddr(pte_t pte) -{ - return (unsigned long)pfn_to_virt(__page_val_to_pfn(pte_val(pte))); -} - -static int gstage_page_size_to_level(unsigned long page_size, u32 *out_level) -{ - u32 i; - unsigned long psz = 1UL << 12; - - for (i = 0; i < gstage_pgd_levels; i++) { - if (page_size == (psz << (i * gstage_index_bits))) { - *out_level = i; - return 0; - } - } - - return -EINVAL; -} - -static int gstage_level_to_page_order(u32 level, unsigned long *out_pgorder) -{ - if (gstage_pgd_levels < level) - return -EINVAL; - - *out_pgorder = 12 + (level * gstage_index_bits); - return 0; -} - -static int gstage_level_to_page_size(u32 level, unsigned long *out_pgsize) -{ - int rc; - unsigned long page_order = PAGE_SHIFT; - - rc = gstage_level_to_page_order(level, &page_order); - if (rc) - return rc; - - *out_pgsize = BIT(page_order); - return 0; -} - -static bool gstage_get_leaf_entry(struct kvm *kvm, gpa_t addr, - pte_t **ptepp, u32 *ptep_level) -{ - pte_t *ptep; - u32 current_level = gstage_pgd_levels - 1; - - *ptep_level = current_level; - ptep = (pte_t *)kvm->arch.pgd; - ptep = &ptep[gstage_pte_index(addr, current_level)]; - while (ptep && pte_val(ptep_get(ptep))) { - if (gstage_pte_leaf(ptep)) { - *ptep_level = current_level; - *ptepp = ptep; - return true; - } - - if (current_level) { - current_level--; - *ptep_level = current_level; - ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep)); - ptep = &ptep[gstage_pte_index(addr, current_level)]; - } else { - ptep = NULL; - } - } - - return false; -} - -static void gstage_remote_tlb_flush(struct kvm *kvm, u32 level, gpa_t addr) -{ - unsigned long order = PAGE_SHIFT; - - if (gstage_level_to_page_order(level, &order)) - return; - addr &= ~(BIT(order) - 1); - - kvm_riscv_hfence_gvma_vmid_gpa(kvm, -1UL, 0, addr, BIT(order), order); -} - -static int gstage_set_pte(struct kvm *kvm, u32 level, - struct kvm_mmu_memory_cache *pcache, - gpa_t addr, const pte_t *new_pte) -{ - u32 current_level = gstage_pgd_levels - 1; - pte_t *next_ptep = (pte_t *)kvm->arch.pgd; - pte_t *ptep = &next_ptep[gstage_pte_index(addr, current_level)]; - - if (current_level < level) - return -EINVAL; - - while (current_level != level) { - if (gstage_pte_leaf(ptep)) - return -EEXIST; - - if (!pte_val(ptep_get(ptep))) { - if (!pcache) - return -ENOMEM; - next_ptep = kvm_mmu_memory_cache_alloc(pcache); - if (!next_ptep) - return -ENOMEM; - set_pte(ptep, pfn_pte(PFN_DOWN(__pa(next_ptep)), - __pgprot(_PAGE_TABLE))); - } else { - if (gstage_pte_leaf(ptep)) - return -EEXIST; - next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep)); - } - - current_level--; - ptep = &next_ptep[gstage_pte_index(addr, current_level)]; - } - - set_pte(ptep, *new_pte); - if (gstage_pte_leaf(ptep)) - gstage_remote_tlb_flush(kvm, current_level, addr); - - return 0; -} - -static int gstage_map_page(struct kvm *kvm, - struct kvm_mmu_memory_cache *pcache, - gpa_t gpa, phys_addr_t hpa, - unsigned long page_size, - bool page_rdonly, bool page_exec) -{ - int ret; - u32 level = 0; - pte_t new_pte; - pgprot_t prot; - - ret = gstage_page_size_to_level(page_size, &level); - if (ret) - return ret; - - /* - * A RISC-V implementation can choose to either: - * 1) Update 'A' and 'D' PTE bits in hardware - * 2) Generate page fault when 'A' and/or 'D' bits are not set - * PTE so that software can update these bits. - * - * We support both options mentioned above. To achieve this, we - * always set 'A' and 'D' PTE bits at time of creating G-stage - * mapping. To support KVM dirty page logging with both options - * mentioned above, we will write-protect G-stage PTEs to track - * dirty pages. - */ - if (page_exec) { - if (page_rdonly) - prot = PAGE_READ_EXEC; - else - prot = PAGE_WRITE_EXEC; - } else { - if (page_rdonly) - prot = PAGE_READ; - else - prot = PAGE_WRITE; - } - new_pte = pfn_pte(PFN_DOWN(hpa), prot); - new_pte = pte_mkdirty(new_pte); - - return gstage_set_pte(kvm, level, pcache, gpa, &new_pte); -} - -enum gstage_op { - GSTAGE_OP_NOP = 0, /* Nothing */ - GSTAGE_OP_CLEAR, /* Clear/Unmap */ - GSTAGE_OP_WP, /* Write-protect */ -}; - -static void gstage_op_pte(struct kvm *kvm, gpa_t addr, - pte_t *ptep, u32 ptep_level, enum gstage_op op) -{ - int i, ret; - pte_t *next_ptep; - u32 next_ptep_level; - unsigned long next_page_size, page_size; - - ret = gstage_level_to_page_size(ptep_level, &page_size); - if (ret) - return; - - BUG_ON(addr & (page_size - 1)); - - if (!pte_val(ptep_get(ptep))) - return; - - if (ptep_level && !gstage_pte_leaf(ptep)) { - next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep)); - next_ptep_level = ptep_level - 1; - ret = gstage_level_to_page_size(next_ptep_level, - &next_page_size); - if (ret) - return; - - if (op == GSTAGE_OP_CLEAR) - set_pte(ptep, __pte(0)); - for (i = 0; i < PTRS_PER_PTE; i++) - gstage_op_pte(kvm, addr + i * next_page_size, - &next_ptep[i], next_ptep_level, op); - if (op == GSTAGE_OP_CLEAR) - put_page(virt_to_page(next_ptep)); - } else { - if (op == GSTAGE_OP_CLEAR) - set_pte(ptep, __pte(0)); - else if (op == GSTAGE_OP_WP) - set_pte(ptep, __pte(pte_val(ptep_get(ptep)) & ~_PAGE_WRITE)); - gstage_remote_tlb_flush(kvm, ptep_level, addr); - } -} - -static void gstage_unmap_range(struct kvm *kvm, gpa_t start, - gpa_t size, bool may_block) -{ - int ret; - pte_t *ptep; - u32 ptep_level; - bool found_leaf; - unsigned long page_size; - gpa_t addr = start, end = start + size; - - while (addr < end) { - found_leaf = gstage_get_leaf_entry(kvm, addr, - &ptep, &ptep_level); - ret = gstage_level_to_page_size(ptep_level, &page_size); - if (ret) - break; - - if (!found_leaf) - goto next; - - if (!(addr & (page_size - 1)) && ((end - addr) >= page_size)) - gstage_op_pte(kvm, addr, ptep, - ptep_level, GSTAGE_OP_CLEAR); - -next: - addr += page_size; - - /* - * If the range is too large, release the kvm->mmu_lock - * to prevent starvation and lockup detector warnings. - */ - if (may_block && addr < end) - cond_resched_lock(&kvm->mmu_lock); - } -} - -static void gstage_wp_range(struct kvm *kvm, gpa_t start, gpa_t end) -{ - int ret; - pte_t *ptep; - u32 ptep_level; - bool found_leaf; - gpa_t addr = start; - unsigned long page_size; - - while (addr < end) { - found_leaf = gstage_get_leaf_entry(kvm, addr, - &ptep, &ptep_level); - ret = gstage_level_to_page_size(ptep_level, &page_size); - if (ret) - break; - - if (!found_leaf) - goto next; - - if (!(addr & (page_size - 1)) && ((end - addr) >= page_size)) - gstage_op_pte(kvm, addr, ptep, - ptep_level, GSTAGE_OP_WP); - -next: - addr += page_size; - } -} - -static void gstage_wp_memory_region(struct kvm *kvm, int slot) +static void mmu_wp_memory_region(struct kvm *kvm, int slot) { struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *memslot = id_to_memslot(slots, slot); phys_addr_t start = memslot->base_gfn << PAGE_SHIFT; phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; + struct kvm_gstage gstage; + + gstage.kvm = kvm; + gstage.flags = 0; + gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid); + gstage.pgd = kvm->arch.pgd; spin_lock(&kvm->mmu_lock); - gstage_wp_range(kvm, start, end); + kvm_riscv_gstage_wp_range(&gstage, start, end); spin_unlock(&kvm->mmu_lock); - kvm_flush_remote_tlbs(kvm); + kvm_flush_remote_tlbs_memslot(kvm, memslot); } -int kvm_riscv_gstage_ioremap(struct kvm *kvm, gpa_t gpa, - phys_addr_t hpa, unsigned long size, - bool writable, bool in_atomic) +int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa, + unsigned long size, bool writable, bool in_atomic) { - pte_t pte; int ret = 0; unsigned long pfn; phys_addr_t addr, end; @@ -355,22 +45,31 @@ int kvm_riscv_gstage_ioremap(struct kvm *kvm, gpa_t gpa, .gfp_custom = (in_atomic) ? GFP_ATOMIC | __GFP_ACCOUNT : 0, .gfp_zero = __GFP_ZERO, }; + struct kvm_gstage_mapping map; + struct kvm_gstage gstage; + + gstage.kvm = kvm; + gstage.flags = 0; + gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid); + gstage.pgd = kvm->arch.pgd; end = (gpa + size + PAGE_SIZE - 1) & PAGE_MASK; pfn = __phys_to_pfn(hpa); for (addr = gpa; addr < end; addr += PAGE_SIZE) { - pte = pfn_pte(pfn, PAGE_KERNEL_IO); + map.addr = addr; + map.pte = pfn_pte(pfn, PAGE_KERNEL_IO); + map.level = 0; if (!writable) - pte = pte_wrprotect(pte); + map.pte = pte_wrprotect(map.pte); - ret = kvm_mmu_topup_memory_cache(&pcache, gstage_pgd_levels); + ret = kvm_mmu_topup_memory_cache(&pcache, kvm_riscv_gstage_pgd_levels); if (ret) goto out; spin_lock(&kvm->mmu_lock); - ret = gstage_set_pte(kvm, 0, &pcache, addr, &pte); + ret = kvm_riscv_gstage_set_pte(&gstage, &pcache, &map); spin_unlock(&kvm->mmu_lock); if (ret) goto out; @@ -383,10 +82,17 @@ out: return ret; } -void kvm_riscv_gstage_iounmap(struct kvm *kvm, gpa_t gpa, unsigned long size) +void kvm_riscv_mmu_iounmap(struct kvm *kvm, gpa_t gpa, unsigned long size) { + struct kvm_gstage gstage; + + gstage.kvm = kvm; + gstage.flags = 0; + gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid); + gstage.pgd = kvm->arch.pgd; + spin_lock(&kvm->mmu_lock); - gstage_unmap_range(kvm, gpa, size, false); + kvm_riscv_gstage_unmap_range(&gstage, gpa, size, false); spin_unlock(&kvm->mmu_lock); } @@ -398,8 +104,14 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, phys_addr_t base_gfn = slot->base_gfn + gfn_offset; phys_addr_t start = (base_gfn + __ffs(mask)) << PAGE_SHIFT; phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT; + struct kvm_gstage gstage; - gstage_wp_range(kvm, start, end); + gstage.kvm = kvm; + gstage.flags = 0; + gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid); + gstage.pgd = kvm->arch.pgd; + + kvm_riscv_gstage_wp_range(&gstage, start, end); } void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) @@ -416,7 +128,7 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) void kvm_arch_flush_shadow_all(struct kvm *kvm) { - kvm_riscv_gstage_free_pgd(kvm); + kvm_riscv_mmu_free_pgd(kvm); } void kvm_arch_flush_shadow_memslot(struct kvm *kvm, @@ -424,9 +136,15 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, { gpa_t gpa = slot->base_gfn << PAGE_SHIFT; phys_addr_t size = slot->npages << PAGE_SHIFT; + struct kvm_gstage gstage; + + gstage.kvm = kvm; + gstage.flags = 0; + gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid); + gstage.pgd = kvm->arch.pgd; spin_lock(&kvm->mmu_lock); - gstage_unmap_range(kvm, gpa, size, false); + kvm_riscv_gstage_unmap_range(&gstage, gpa, size, false); spin_unlock(&kvm->mmu_lock); } @@ -441,7 +159,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * the memory slot is write protected. */ if (change != KVM_MR_DELETE && new->flags & KVM_MEM_LOG_DIRTY_PAGES) - gstage_wp_memory_region(kvm, new->id); + mmu_wp_memory_region(kvm, new->id); } int kvm_arch_prepare_memory_region(struct kvm *kvm, @@ -463,7 +181,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, * space addressable by the KVM guest GPA space. */ if ((new->base_gfn + new->npages) >= - (gstage_gpa_size >> PAGE_SHIFT)) + (kvm_riscv_gstage_gpa_size >> PAGE_SHIFT)) return -EFAULT; hva = new->userspace_addr; @@ -487,10 +205,11 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, * +--------------------------------------------+ */ do { - struct vm_area_struct *vma = find_vma(current->mm, hva); + struct vm_area_struct *vma; hva_t vm_start, vm_end; - if (!vma || vma->vm_start >= reg_end) + vma = find_vma_intersection(current->mm, hva, reg_end); + if (!vma) break; /* @@ -519,9 +238,8 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, goto out; } - ret = kvm_riscv_gstage_ioremap(kvm, gpa, pa, - vm_end - vm_start, - writable, false); + ret = kvm_riscv_mmu_ioremap(kvm, gpa, pa, vm_end - vm_start, + writable, false); if (ret) break; } @@ -532,7 +250,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, goto out; if (ret) - kvm_riscv_gstage_iounmap(kvm, base_gpa, size); + kvm_riscv_mmu_iounmap(kvm, base_gpa, size); out: mmap_read_unlock(current->mm); @@ -541,12 +259,18 @@ out: bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { + struct kvm_gstage gstage; + if (!kvm->arch.pgd) return false; - gstage_unmap_range(kvm, range->start << PAGE_SHIFT, - (range->end - range->start) << PAGE_SHIFT, - range->may_block); + gstage.kvm = kvm; + gstage.flags = 0; + gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid); + gstage.pgd = kvm->arch.pgd; + kvm_riscv_gstage_unmap_range(&gstage, range->start << PAGE_SHIFT, + (range->end - range->start) << PAGE_SHIFT, + range->may_block); return false; } @@ -555,14 +279,19 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) pte_t *ptep; u32 ptep_level = 0; u64 size = (range->end - range->start) << PAGE_SHIFT; + struct kvm_gstage gstage; if (!kvm->arch.pgd) return false; WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); - if (!gstage_get_leaf_entry(kvm, range->start << PAGE_SHIFT, - &ptep, &ptep_level)) + gstage.kvm = kvm; + gstage.flags = 0; + gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid); + gstage.pgd = kvm->arch.pgd; + if (!kvm_riscv_gstage_get_leaf(&gstage, range->start << PAGE_SHIFT, + &ptep, &ptep_level)) return false; return ptep_test_and_clear_young(NULL, 0, ptep); @@ -573,22 +302,27 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) pte_t *ptep; u32 ptep_level = 0; u64 size = (range->end - range->start) << PAGE_SHIFT; + struct kvm_gstage gstage; if (!kvm->arch.pgd) return false; WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); - if (!gstage_get_leaf_entry(kvm, range->start << PAGE_SHIFT, - &ptep, &ptep_level)) + gstage.kvm = kvm; + gstage.flags = 0; + gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid); + gstage.pgd = kvm->arch.pgd; + if (!kvm_riscv_gstage_get_leaf(&gstage, range->start << PAGE_SHIFT, + &ptep, &ptep_level)) return false; return pte_young(ptep_get(ptep)); } -int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, - struct kvm_memory_slot *memslot, - gpa_t gpa, unsigned long hva, bool is_write) +int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, + gpa_t gpa, unsigned long hva, bool is_write, + struct kvm_gstage_mapping *out_map) { int ret; kvm_pfn_t hfn; @@ -601,10 +335,19 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, bool logging = (memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY)) ? true : false; unsigned long vma_pagesize, mmu_seq; + struct kvm_gstage gstage; struct page *page; + gstage.kvm = kvm; + gstage.flags = 0; + gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid); + gstage.pgd = kvm->arch.pgd; + + /* Setup initial state of output mapping */ + memset(out_map, 0, sizeof(*out_map)); + /* We need minimum second+third level pages */ - ret = kvm_mmu_topup_memory_cache(pcache, gstage_pgd_levels); + ret = kvm_mmu_topup_memory_cache(pcache, kvm_riscv_gstage_pgd_levels); if (ret) { kvm_err("Failed to topup G-stage cache\n"); return ret; @@ -648,7 +391,8 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, return -EFAULT; } - hfn = kvm_faultin_pfn(vcpu, gfn, is_write, &writable, &page); + hfn = __kvm_faultin_pfn(memslot, gfn, is_write ? FOLL_WRITE : 0, + &writable, &page); if (hfn == KVM_PFN_ERR_HWPOISON) { send_sig_mceerr(BUS_MCEERR_AR, (void __user *)hva, vma_pageshift, current); @@ -670,12 +414,12 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, goto out_unlock; if (writable) { - mark_page_dirty(kvm, gfn); - ret = gstage_map_page(kvm, pcache, gpa, hfn << PAGE_SHIFT, - vma_pagesize, false, true); + mark_page_dirty_in_slot(kvm, memslot, gfn); + ret = kvm_riscv_gstage_map_page(&gstage, pcache, gpa, hfn << PAGE_SHIFT, + vma_pagesize, false, true, out_map); } else { - ret = gstage_map_page(kvm, pcache, gpa, hfn << PAGE_SHIFT, - vma_pagesize, true, true); + ret = kvm_riscv_gstage_map_page(&gstage, pcache, gpa, hfn << PAGE_SHIFT, + vma_pagesize, true, true, out_map); } if (ret) @@ -687,7 +431,7 @@ out_unlock: return ret; } -int kvm_riscv_gstage_alloc_pgd(struct kvm *kvm) +int kvm_riscv_mmu_alloc_pgd(struct kvm *kvm) { struct page *pgd_page; @@ -697,7 +441,7 @@ int kvm_riscv_gstage_alloc_pgd(struct kvm *kvm) } pgd_page = alloc_pages(GFP_KERNEL | __GFP_ZERO, - get_order(gstage_pgd_size)); + get_order(kvm_riscv_gstage_pgd_size)); if (!pgd_page) return -ENOMEM; kvm->arch.pgd = page_to_virt(pgd_page); @@ -706,13 +450,18 @@ int kvm_riscv_gstage_alloc_pgd(struct kvm *kvm) return 0; } -void kvm_riscv_gstage_free_pgd(struct kvm *kvm) +void kvm_riscv_mmu_free_pgd(struct kvm *kvm) { + struct kvm_gstage gstage; void *pgd = NULL; spin_lock(&kvm->mmu_lock); if (kvm->arch.pgd) { - gstage_unmap_range(kvm, 0UL, gstage_gpa_size, false); + gstage.kvm = kvm; + gstage.flags = 0; + gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid); + gstage.pgd = kvm->arch.pgd; + kvm_riscv_gstage_unmap_range(&gstage, 0UL, kvm_riscv_gstage_gpa_size, false); pgd = READ_ONCE(kvm->arch.pgd); kvm->arch.pgd = NULL; kvm->arch.pgd_phys = 0; @@ -720,12 +469,12 @@ void kvm_riscv_gstage_free_pgd(struct kvm *kvm) spin_unlock(&kvm->mmu_lock); if (pgd) - free_pages((unsigned long)pgd, get_order(gstage_pgd_size)); + free_pages((unsigned long)pgd, get_order(kvm_riscv_gstage_pgd_size)); } -void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu) +void kvm_riscv_mmu_update_hgatp(struct kvm_vcpu *vcpu) { - unsigned long hgatp = gstage_mode; + unsigned long hgatp = kvm_riscv_gstage_mode << HGATP_MODE_SHIFT; struct kvm_arch *k = &vcpu->kvm->arch; hgatp |= (READ_ONCE(k->vmid.vmid) << HGATP_VMID_SHIFT) & HGATP_VMID; @@ -736,37 +485,3 @@ void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu) if (!kvm_riscv_gstage_vmid_bits()) kvm_riscv_local_hfence_gvma_all(); } - -void __init kvm_riscv_gstage_mode_detect(void) -{ -#ifdef CONFIG_64BIT - /* Try Sv57x4 G-stage mode */ - csr_write(CSR_HGATP, HGATP_MODE_SV57X4 << HGATP_MODE_SHIFT); - if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV57X4) { - gstage_mode = (HGATP_MODE_SV57X4 << HGATP_MODE_SHIFT); - gstage_pgd_levels = 5; - goto skip_sv48x4_test; - } - - /* Try Sv48x4 G-stage mode */ - csr_write(CSR_HGATP, HGATP_MODE_SV48X4 << HGATP_MODE_SHIFT); - if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV48X4) { - gstage_mode = (HGATP_MODE_SV48X4 << HGATP_MODE_SHIFT); - gstage_pgd_levels = 4; - } -skip_sv48x4_test: - - csr_write(CSR_HGATP, 0); - kvm_riscv_local_hfence_gvma_all(); -#endif -} - -unsigned long __init kvm_riscv_gstage_mode(void) -{ - return gstage_mode >> HGATP_MODE_SHIFT; -} - -int kvm_riscv_gstage_gpa_bits(void) -{ - return gstage_gpa_bits; -} diff --git a/arch/riscv/kvm/tlb.c b/arch/riscv/kvm/tlb.c index 2f91ea5f8493..3c5a70a2b927 100644 --- a/arch/riscv/kvm/tlb.c +++ b/arch/riscv/kvm/tlb.c @@ -15,6 +15,8 @@ #include <asm/cpufeature.h> #include <asm/insn-def.h> #include <asm/kvm_nacl.h> +#include <asm/kvm_tlb.h> +#include <asm/kvm_vmid.h> #define has_svinval() riscv_has_extension_unlikely(RISCV_ISA_EXT_SVINVAL) @@ -156,36 +158,13 @@ void kvm_riscv_local_hfence_vvma_all(unsigned long vmid) csr_write(CSR_HGATP, hgatp); } -void kvm_riscv_local_tlb_sanitize(struct kvm_vcpu *vcpu) -{ - unsigned long vmid; - - if (!kvm_riscv_gstage_vmid_bits() || - vcpu->arch.last_exit_cpu == vcpu->cpu) - return; - - /* - * On RISC-V platforms with hardware VMID support, we share same - * VMID for all VCPUs of a particular Guest/VM. This means we might - * have stale G-stage TLB entries on the current Host CPU due to - * some other VCPU of the same Guest which ran previously on the - * current Host CPU. - * - * To cleanup stale TLB entries, we simply flush all G-stage TLB - * entries by VMID whenever underlying Host CPU changes for a VCPU. - */ - - vmid = READ_ONCE(vcpu->kvm->arch.vmid.vmid); - kvm_riscv_local_hfence_gvma_vmid_all(vmid); -} - void kvm_riscv_fence_i_process(struct kvm_vcpu *vcpu) { kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_FENCE_I_RCVD); local_flush_icache_all(); } -void kvm_riscv_hfence_gvma_vmid_all_process(struct kvm_vcpu *vcpu) +void kvm_riscv_tlb_flush_process(struct kvm_vcpu *vcpu) { struct kvm_vmid *v = &vcpu->kvm->arch.vmid; unsigned long vmid = READ_ONCE(v->vmid); @@ -258,51 +237,58 @@ static bool vcpu_hfence_enqueue(struct kvm_vcpu *vcpu, void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu) { - unsigned long vmid; struct kvm_riscv_hfence d = { 0 }; - struct kvm_vmid *v = &vcpu->kvm->arch.vmid; while (vcpu_hfence_dequeue(vcpu, &d)) { switch (d.type) { case KVM_RISCV_HFENCE_UNKNOWN: break; case KVM_RISCV_HFENCE_GVMA_VMID_GPA: - vmid = READ_ONCE(v->vmid); if (kvm_riscv_nacl_available()) - nacl_hfence_gvma_vmid(nacl_shmem(), vmid, + nacl_hfence_gvma_vmid(nacl_shmem(), d.vmid, d.addr, d.size, d.order); else - kvm_riscv_local_hfence_gvma_vmid_gpa(vmid, d.addr, + kvm_riscv_local_hfence_gvma_vmid_gpa(d.vmid, d.addr, d.size, d.order); break; + case KVM_RISCV_HFENCE_GVMA_VMID_ALL: + if (kvm_riscv_nacl_available()) + nacl_hfence_gvma_vmid_all(nacl_shmem(), d.vmid); + else + kvm_riscv_local_hfence_gvma_vmid_all(d.vmid); + break; case KVM_RISCV_HFENCE_VVMA_ASID_GVA: kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD); - vmid = READ_ONCE(v->vmid); if (kvm_riscv_nacl_available()) - nacl_hfence_vvma_asid(nacl_shmem(), vmid, d.asid, + nacl_hfence_vvma_asid(nacl_shmem(), d.vmid, d.asid, d.addr, d.size, d.order); else - kvm_riscv_local_hfence_vvma_asid_gva(vmid, d.asid, d.addr, + kvm_riscv_local_hfence_vvma_asid_gva(d.vmid, d.asid, d.addr, d.size, d.order); break; case KVM_RISCV_HFENCE_VVMA_ASID_ALL: kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD); - vmid = READ_ONCE(v->vmid); if (kvm_riscv_nacl_available()) - nacl_hfence_vvma_asid_all(nacl_shmem(), vmid, d.asid); + nacl_hfence_vvma_asid_all(nacl_shmem(), d.vmid, d.asid); else - kvm_riscv_local_hfence_vvma_asid_all(vmid, d.asid); + kvm_riscv_local_hfence_vvma_asid_all(d.vmid, d.asid); break; case KVM_RISCV_HFENCE_VVMA_GVA: kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_RCVD); - vmid = READ_ONCE(v->vmid); if (kvm_riscv_nacl_available()) - nacl_hfence_vvma(nacl_shmem(), vmid, + nacl_hfence_vvma(nacl_shmem(), d.vmid, d.addr, d.size, d.order); else - kvm_riscv_local_hfence_vvma_gva(vmid, d.addr, + kvm_riscv_local_hfence_vvma_gva(d.vmid, d.addr, d.size, d.order); break; + case KVM_RISCV_HFENCE_VVMA_ALL: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_RCVD); + if (kvm_riscv_nacl_available()) + nacl_hfence_vvma_all(nacl_shmem(), d.vmid); + else + kvm_riscv_local_hfence_vvma_all(d.vmid); + break; default: break; } @@ -355,35 +341,43 @@ void kvm_riscv_fence_i(struct kvm *kvm, void kvm_riscv_hfence_gvma_vmid_gpa(struct kvm *kvm, unsigned long hbase, unsigned long hmask, gpa_t gpa, gpa_t gpsz, - unsigned long order) + unsigned long order, unsigned long vmid) { struct kvm_riscv_hfence data; data.type = KVM_RISCV_HFENCE_GVMA_VMID_GPA; data.asid = 0; + data.vmid = vmid; data.addr = gpa; data.size = gpsz; data.order = order; make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE, - KVM_REQ_HFENCE_GVMA_VMID_ALL, &data); + KVM_REQ_TLB_FLUSH, &data); } void kvm_riscv_hfence_gvma_vmid_all(struct kvm *kvm, - unsigned long hbase, unsigned long hmask) + unsigned long hbase, unsigned long hmask, + unsigned long vmid) { - make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE_GVMA_VMID_ALL, - KVM_REQ_HFENCE_GVMA_VMID_ALL, NULL); + struct kvm_riscv_hfence data = {0}; + + data.type = KVM_RISCV_HFENCE_GVMA_VMID_ALL; + data.vmid = vmid; + make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE, + KVM_REQ_TLB_FLUSH, &data); } void kvm_riscv_hfence_vvma_asid_gva(struct kvm *kvm, unsigned long hbase, unsigned long hmask, unsigned long gva, unsigned long gvsz, - unsigned long order, unsigned long asid) + unsigned long order, unsigned long asid, + unsigned long vmid) { struct kvm_riscv_hfence data; data.type = KVM_RISCV_HFENCE_VVMA_ASID_GVA; data.asid = asid; + data.vmid = vmid; data.addr = gva; data.size = gvsz; data.order = order; @@ -393,13 +387,13 @@ void kvm_riscv_hfence_vvma_asid_gva(struct kvm *kvm, void kvm_riscv_hfence_vvma_asid_all(struct kvm *kvm, unsigned long hbase, unsigned long hmask, - unsigned long asid) + unsigned long asid, unsigned long vmid) { - struct kvm_riscv_hfence data; + struct kvm_riscv_hfence data = {0}; data.type = KVM_RISCV_HFENCE_VVMA_ASID_ALL; data.asid = asid; - data.addr = data.size = data.order = 0; + data.vmid = vmid; make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE, KVM_REQ_HFENCE_VVMA_ALL, &data); } @@ -407,12 +401,13 @@ void kvm_riscv_hfence_vvma_asid_all(struct kvm *kvm, void kvm_riscv_hfence_vvma_gva(struct kvm *kvm, unsigned long hbase, unsigned long hmask, unsigned long gva, unsigned long gvsz, - unsigned long order) + unsigned long order, unsigned long vmid) { struct kvm_riscv_hfence data; data.type = KVM_RISCV_HFENCE_VVMA_GVA; data.asid = 0; + data.vmid = vmid; data.addr = gva; data.size = gvsz; data.order = order; @@ -421,8 +416,21 @@ void kvm_riscv_hfence_vvma_gva(struct kvm *kvm, } void kvm_riscv_hfence_vvma_all(struct kvm *kvm, - unsigned long hbase, unsigned long hmask) + unsigned long hbase, unsigned long hmask, + unsigned long vmid) +{ + struct kvm_riscv_hfence data = {0}; + + data.type = KVM_RISCV_HFENCE_VVMA_ALL; + data.vmid = vmid; + make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE, + KVM_REQ_HFENCE_VVMA_ALL, &data); +} + +int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) { - make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE_VVMA_ALL, - KVM_REQ_HFENCE_VVMA_ALL, NULL); + kvm_riscv_hfence_gvma_vmid_gpa(kvm, -1UL, 0, + gfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT, + PAGE_SHIFT, READ_ONCE(kvm->arch.vmid.vmid)); + return 0; } diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index e0a01af426ff..f001e56403f9 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -18,6 +18,7 @@ #include <linux/fs.h> #include <linux/kvm_host.h> #include <asm/cacheflush.h> +#include <asm/kvm_mmu.h> #include <asm/kvm_nacl.h> #include <asm/kvm_vcpu_vector.h> @@ -111,7 +112,7 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu, bool kvm_sbi_reset) vcpu->arch.hfence_tail = 0; memset(vcpu->arch.hfence_queue, 0, sizeof(vcpu->arch.hfence_queue)); - kvm_riscv_vcpu_sbi_sta_reset(vcpu); + kvm_riscv_vcpu_sbi_reset(vcpu); /* Reset the guest CSRs for hotplug usecase */ if (loaded) @@ -148,8 +149,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) spin_lock_init(&vcpu->arch.reset_state.lock); - if (kvm_riscv_vcpu_alloc_vector_context(vcpu)) - return -ENOMEM; + rc = kvm_riscv_vcpu_alloc_vector_context(vcpu); + if (rc) + return rc; /* Setup VCPU timer */ kvm_riscv_vcpu_timer_init(vcpu); @@ -158,9 +160,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) kvm_riscv_vcpu_pmu_init(vcpu); /* Setup VCPU AIA */ - rc = kvm_riscv_vcpu_aia_init(vcpu); - if (rc) - return rc; + kvm_riscv_vcpu_aia_init(vcpu); /* * Setup SBI extensions @@ -187,6 +187,8 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { + kvm_riscv_vcpu_sbi_deinit(vcpu); + /* Cleanup VCPU AIA context */ kvm_riscv_vcpu_aia_deinit(vcpu); @@ -207,16 +209,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) return kvm_riscv_vcpu_timer_pending(vcpu); } -void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) -{ - kvm_riscv_aia_wakeon_hgei(vcpu, true); -} - -void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) -{ - kvm_riscv_aia_wakeon_hgei(vcpu, false); -} - int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { return (kvm_riscv_vcpu_has_interrupts(vcpu, -1UL) && @@ -630,7 +622,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } } - kvm_riscv_gstage_update_hgatp(vcpu); + kvm_riscv_mmu_update_hgatp(vcpu); kvm_riscv_vcpu_timer_restore(vcpu); @@ -690,7 +682,14 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) } } -static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu) +/** + * check_vcpu_requests - check and handle pending vCPU requests + * @vcpu: the VCPU pointer + * + * Return: 1 if we should enter the guest + * 0 if we should exit to userspace + */ +static int kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu) { struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); @@ -715,17 +714,13 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu) kvm_riscv_reset_vcpu(vcpu, true); if (kvm_check_request(KVM_REQ_UPDATE_HGATP, vcpu)) - kvm_riscv_gstage_update_hgatp(vcpu); + kvm_riscv_mmu_update_hgatp(vcpu); if (kvm_check_request(KVM_REQ_FENCE_I, vcpu)) kvm_riscv_fence_i_process(vcpu); - /* - * The generic KVM_REQ_TLB_FLUSH is same as - * KVM_REQ_HFENCE_GVMA_VMID_ALL - */ - if (kvm_check_request(KVM_REQ_HFENCE_GVMA_VMID_ALL, vcpu)) - kvm_riscv_hfence_gvma_vmid_all_process(vcpu); + if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) + kvm_riscv_tlb_flush_process(vcpu); if (kvm_check_request(KVM_REQ_HFENCE_VVMA_ALL, vcpu)) kvm_riscv_hfence_vvma_all_process(vcpu); @@ -735,7 +730,12 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) kvm_riscv_vcpu_record_steal_time(vcpu); + + if (kvm_dirty_ring_check_request(vcpu)) + return 0; } + + return 1; } static void kvm_riscv_update_hvip(struct kvm_vcpu *vcpu) @@ -917,7 +917,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_riscv_gstage_vmid_update(vcpu); - kvm_riscv_check_vcpu_requests(vcpu); + ret = kvm_riscv_check_vcpu_requests(vcpu); + if (ret <= 0) + continue; preempt_disable(); @@ -961,12 +963,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) } /* - * Cleanup stale TLB enteries + * Sanitize VMID mappings cached (TLB) on current CPU * * Note: This should be done after G-stage VMID has been * updated using kvm_riscv_gstage_vmid_ver_changed() */ - kvm_riscv_local_tlb_sanitize(vcpu); + kvm_riscv_gstage_vmid_sanitize(vcpu); trace_kvm_entry(vcpu); diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index 6e0c18412795..0bb0c51e3c89 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -9,10 +9,13 @@ #include <linux/kvm_host.h> #include <asm/csr.h> #include <asm/insn-def.h> +#include <asm/kvm_mmu.h> +#include <asm/kvm_nacl.h> static int gstage_page_fault(struct kvm_vcpu *vcpu, struct kvm_run *run, struct kvm_cpu_trap *trap) { + struct kvm_gstage_mapping host_map; struct kvm_memory_slot *memslot; unsigned long hva, fault_addr; bool writable; @@ -40,8 +43,9 @@ static int gstage_page_fault(struct kvm_vcpu *vcpu, struct kvm_run *run, }; } - ret = kvm_riscv_gstage_map(vcpu, memslot, fault_addr, hva, - (trap->scause == EXC_STORE_GUEST_PAGE_FAULT) ? true : false); + ret = kvm_riscv_mmu_map(vcpu, memslot, fault_addr, hva, + (trap->scause == EXC_STORE_GUEST_PAGE_FAULT) ? true : false, + &host_map); if (ret < 0) return ret; @@ -135,7 +139,7 @@ unsigned long kvm_riscv_vcpu_unpriv_read(struct kvm_vcpu *vcpu, void kvm_riscv_vcpu_trap_redirect(struct kvm_vcpu *vcpu, struct kvm_cpu_trap *trap) { - unsigned long vsstatus = csr_read(CSR_VSSTATUS); + unsigned long vsstatus = ncsr_read(CSR_VSSTATUS); /* Change Guest SSTATUS.SPP bit */ vsstatus &= ~SR_SPP; @@ -151,15 +155,15 @@ void kvm_riscv_vcpu_trap_redirect(struct kvm_vcpu *vcpu, vsstatus &= ~SR_SIE; /* Update Guest SSTATUS */ - csr_write(CSR_VSSTATUS, vsstatus); + ncsr_write(CSR_VSSTATUS, vsstatus); /* Update Guest SCAUSE, STVAL, and SEPC */ - csr_write(CSR_VSCAUSE, trap->scause); - csr_write(CSR_VSTVAL, trap->stval); - csr_write(CSR_VSEPC, trap->sepc); + ncsr_write(CSR_VSCAUSE, trap->scause); + ncsr_write(CSR_VSTVAL, trap->stval); + ncsr_write(CSR_VSEPC, trap->sepc); /* Set Guest PC to Guest exception vector */ - vcpu->arch.guest_context.sepc = csr_read(CSR_VSTVEC); + vcpu->arch.guest_context.sepc = ncsr_read(CSR_VSTVEC); /* Set Guest privilege mode to supervisor */ vcpu->arch.guest_context.sstatus |= SR_SPP; diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c index 2e1b646f0d61..cce6a38ea54f 100644 --- a/arch/riscv/kvm/vcpu_onereg.c +++ b/arch/riscv/kvm/vcpu_onereg.c @@ -23,7 +23,7 @@ #define KVM_ISA_EXT_ARR(ext) \ [KVM_RISCV_ISA_EXT_##ext] = RISCV_ISA_EXT_##ext -/* Mapping between KVM ISA Extension ID & Host ISA extension ID */ +/* Mapping between KVM ISA Extension ID & guest ISA extension ID */ static const unsigned long kvm_isa_ext_arr[] = { /* Single letter extensions (alphabetically sorted) */ [KVM_RISCV_ISA_EXT_A] = RISCV_ISA_EXT_a, @@ -35,7 +35,7 @@ static const unsigned long kvm_isa_ext_arr[] = { [KVM_RISCV_ISA_EXT_M] = RISCV_ISA_EXT_m, [KVM_RISCV_ISA_EXT_V] = RISCV_ISA_EXT_v, /* Multi letter extensions (alphabetically sorted) */ - [KVM_RISCV_ISA_EXT_SMNPM] = RISCV_ISA_EXT_SSNPM, + KVM_ISA_EXT_ARR(SMNPM), KVM_ISA_EXT_ARR(SMSTATEEN), KVM_ISA_EXT_ARR(SSAIA), KVM_ISA_EXT_ARR(SSCOFPMF), @@ -112,6 +112,36 @@ static unsigned long kvm_riscv_vcpu_base2isa_ext(unsigned long base_ext) return KVM_RISCV_ISA_EXT_MAX; } +static int kvm_riscv_vcpu_isa_check_host(unsigned long kvm_ext, unsigned long *guest_ext) +{ + unsigned long host_ext; + + if (kvm_ext >= KVM_RISCV_ISA_EXT_MAX || + kvm_ext >= ARRAY_SIZE(kvm_isa_ext_arr)) + return -ENOENT; + + *guest_ext = kvm_isa_ext_arr[kvm_ext]; + switch (*guest_ext) { + case RISCV_ISA_EXT_SMNPM: + /* + * Pointer masking effective in (H)S-mode is provided by the + * Smnpm extension, so that extension is reported to the guest, + * even though the CSR bits for configuring VS-mode pointer + * masking on the host side are part of the Ssnpm extension. + */ + host_ext = RISCV_ISA_EXT_SSNPM; + break; + default: + host_ext = *guest_ext; + break; + } + + if (!__riscv_isa_extension_available(NULL, host_ext)) + return -ENOENT; + + return 0; +} + static bool kvm_riscv_vcpu_isa_enable_allowed(unsigned long ext) { switch (ext) { @@ -219,13 +249,13 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext) void kvm_riscv_vcpu_setup_isa(struct kvm_vcpu *vcpu) { - unsigned long host_isa, i; + unsigned long guest_ext, i; for (i = 0; i < ARRAY_SIZE(kvm_isa_ext_arr); i++) { - host_isa = kvm_isa_ext_arr[i]; - if (__riscv_isa_extension_available(NULL, host_isa) && - kvm_riscv_vcpu_isa_enable_allowed(i)) - set_bit(host_isa, vcpu->arch.isa); + if (kvm_riscv_vcpu_isa_check_host(i, &guest_ext)) + continue; + if (kvm_riscv_vcpu_isa_enable_allowed(i)) + set_bit(guest_ext, vcpu->arch.isa); } } @@ -607,18 +637,15 @@ static int riscv_vcpu_get_isa_ext_single(struct kvm_vcpu *vcpu, unsigned long reg_num, unsigned long *reg_val) { - unsigned long host_isa_ext; - - if (reg_num >= KVM_RISCV_ISA_EXT_MAX || - reg_num >= ARRAY_SIZE(kvm_isa_ext_arr)) - return -ENOENT; + unsigned long guest_ext; + int ret; - host_isa_ext = kvm_isa_ext_arr[reg_num]; - if (!__riscv_isa_extension_available(NULL, host_isa_ext)) - return -ENOENT; + ret = kvm_riscv_vcpu_isa_check_host(reg_num, &guest_ext); + if (ret) + return ret; *reg_val = 0; - if (__riscv_isa_extension_available(vcpu->arch.isa, host_isa_ext)) + if (__riscv_isa_extension_available(vcpu->arch.isa, guest_ext)) *reg_val = 1; /* Mark the given extension as available */ return 0; @@ -628,17 +655,14 @@ static int riscv_vcpu_set_isa_ext_single(struct kvm_vcpu *vcpu, unsigned long reg_num, unsigned long reg_val) { - unsigned long host_isa_ext; - - if (reg_num >= KVM_RISCV_ISA_EXT_MAX || - reg_num >= ARRAY_SIZE(kvm_isa_ext_arr)) - return -ENOENT; + unsigned long guest_ext; + int ret; - host_isa_ext = kvm_isa_ext_arr[reg_num]; - if (!__riscv_isa_extension_available(NULL, host_isa_ext)) - return -ENOENT; + ret = kvm_riscv_vcpu_isa_check_host(reg_num, &guest_ext); + if (ret) + return ret; - if (reg_val == test_bit(host_isa_ext, vcpu->arch.isa)) + if (reg_val == test_bit(guest_ext, vcpu->arch.isa)) return 0; if (!vcpu->arch.ran_atleast_once) { @@ -648,10 +672,10 @@ static int riscv_vcpu_set_isa_ext_single(struct kvm_vcpu *vcpu, */ if (reg_val == 1 && kvm_riscv_vcpu_isa_enable_allowed(reg_num)) - set_bit(host_isa_ext, vcpu->arch.isa); + set_bit(guest_ext, vcpu->arch.isa); else if (!reg_val && kvm_riscv_vcpu_isa_disable_allowed(reg_num)) - clear_bit(host_isa_ext, vcpu->arch.isa); + clear_bit(guest_ext, vcpu->arch.isa); else return -EINVAL; kvm_riscv_vcpu_fp_reset(vcpu); @@ -1009,16 +1033,15 @@ static int copy_fp_d_reg_indices(const struct kvm_vcpu *vcpu, static int copy_isa_ext_reg_indices(const struct kvm_vcpu *vcpu, u64 __user *uindices) { + unsigned long guest_ext; unsigned int n = 0; - unsigned long isa_ext; for (int i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) { u64 size = IS_ENABLED(CONFIG_32BIT) ? KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64; u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_ISA_EXT | i; - isa_ext = kvm_isa_ext_arr[i]; - if (!__riscv_isa_extension_available(NULL, isa_ext)) + if (kvm_riscv_vcpu_isa_check_host(i, &guest_ext)) continue; if (uindices) { diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index 6e09b518a5d1..a56c4959f9ad 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -536,5 +536,54 @@ void kvm_riscv_vcpu_sbi_init(struct kvm_vcpu *vcpu) scontext->ext_status[idx] = ext->default_disabled ? KVM_RISCV_SBI_EXT_STATUS_DISABLED : KVM_RISCV_SBI_EXT_STATUS_ENABLED; + + if (ext->init && ext->init(vcpu) != 0) + scontext->ext_status[idx] = KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE; + } +} + +void kvm_riscv_vcpu_sbi_deinit(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context; + const struct kvm_riscv_sbi_extension_entry *entry; + const struct kvm_vcpu_sbi_extension *ext; + int idx, i; + + for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) { + entry = &sbi_ext[i]; + ext = entry->ext_ptr; + idx = entry->ext_idx; + + if (idx < 0 || idx >= ARRAY_SIZE(scontext->ext_status)) + continue; + + if (scontext->ext_status[idx] == KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE || + !ext->deinit) + continue; + + ext->deinit(vcpu); + } +} + +void kvm_riscv_vcpu_sbi_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context; + const struct kvm_riscv_sbi_extension_entry *entry; + const struct kvm_vcpu_sbi_extension *ext; + int idx, i; + + for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) { + entry = &sbi_ext[i]; + ext = entry->ext_ptr; + idx = entry->ext_idx; + + if (idx < 0 || idx >= ARRAY_SIZE(scontext->ext_status)) + continue; + + if (scontext->ext_status[idx] != KVM_RISCV_SBI_EXT_STATUS_ENABLED || + !ext->reset) + continue; + + ext->reset(vcpu); } } diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c index b17fad091bab..b490ed1428a6 100644 --- a/arch/riscv/kvm/vcpu_sbi_replace.c +++ b/arch/riscv/kvm/vcpu_sbi_replace.c @@ -96,6 +96,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run unsigned long hmask = cp->a0; unsigned long hbase = cp->a1; unsigned long funcid = cp->a6; + unsigned long vmid; switch (funcid) { case SBI_EXT_RFENCE_REMOTE_FENCE_I: @@ -103,22 +104,22 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_FENCE_I_SENT); break; case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA: + vmid = READ_ONCE(vcpu->kvm->arch.vmid.vmid); if ((cp->a2 == 0 && cp->a3 == 0) || cp->a3 == -1UL) - kvm_riscv_hfence_vvma_all(vcpu->kvm, hbase, hmask); + kvm_riscv_hfence_vvma_all(vcpu->kvm, hbase, hmask, vmid); else kvm_riscv_hfence_vvma_gva(vcpu->kvm, hbase, hmask, - cp->a2, cp->a3, PAGE_SHIFT); + cp->a2, cp->a3, PAGE_SHIFT, vmid); kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_SENT); break; case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID: + vmid = READ_ONCE(vcpu->kvm->arch.vmid.vmid); if ((cp->a2 == 0 && cp->a3 == 0) || cp->a3 == -1UL) - kvm_riscv_hfence_vvma_asid_all(vcpu->kvm, - hbase, hmask, cp->a4); + kvm_riscv_hfence_vvma_asid_all(vcpu->kvm, hbase, hmask, + cp->a4, vmid); else - kvm_riscv_hfence_vvma_asid_gva(vcpu->kvm, - hbase, hmask, - cp->a2, cp->a3, - PAGE_SHIFT, cp->a4); + kvm_riscv_hfence_vvma_asid_gva(vcpu->kvm, hbase, hmask, cp->a2, + cp->a3, PAGE_SHIFT, cp->a4, vmid); kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_SENT); break; case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA: diff --git a/arch/riscv/kvm/vcpu_sbi_sta.c b/arch/riscv/kvm/vcpu_sbi_sta.c index 5f35427114c1..cc6cb7c8f0e4 100644 --- a/arch/riscv/kvm/vcpu_sbi_sta.c +++ b/arch/riscv/kvm/vcpu_sbi_sta.c @@ -16,7 +16,7 @@ #include <asm/sbi.h> #include <asm/uaccess.h> -void kvm_riscv_vcpu_sbi_sta_reset(struct kvm_vcpu *vcpu) +static void kvm_riscv_vcpu_sbi_sta_reset(struct kvm_vcpu *vcpu) { vcpu->arch.sta.shmem = INVALID_GPA; vcpu->arch.sta.last_steal = 0; @@ -156,6 +156,7 @@ const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_sta = { .extid_end = SBI_EXT_STA, .handler = kvm_sbi_ext_sta_handler, .probe = kvm_sbi_ext_sta_probe, + .reset = kvm_riscv_vcpu_sbi_sta_reset, }; int kvm_riscv_vcpu_get_reg_sbi_sta(struct kvm_vcpu *vcpu, diff --git a/arch/riscv/kvm/vcpu_sbi_v01.c b/arch/riscv/kvm/vcpu_sbi_v01.c index 8f4c4fa16227..368dfddd23d9 100644 --- a/arch/riscv/kvm/vcpu_sbi_v01.c +++ b/arch/riscv/kvm/vcpu_sbi_v01.c @@ -23,6 +23,7 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, struct kvm *kvm = vcpu->kvm; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; struct kvm_cpu_trap *utrap = retdata->utrap; + unsigned long vmid; switch (cp->a7) { case SBI_EXT_0_1_CONSOLE_GETCHAR: @@ -78,25 +79,21 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, if (cp->a7 == SBI_EXT_0_1_REMOTE_FENCE_I) kvm_riscv_fence_i(vcpu->kvm, 0, hmask); else if (cp->a7 == SBI_EXT_0_1_REMOTE_SFENCE_VMA) { + vmid = READ_ONCE(vcpu->kvm->arch.vmid.vmid); if (cp->a1 == 0 && cp->a2 == 0) - kvm_riscv_hfence_vvma_all(vcpu->kvm, - 0, hmask); + kvm_riscv_hfence_vvma_all(vcpu->kvm, 0, hmask, vmid); else - kvm_riscv_hfence_vvma_gva(vcpu->kvm, - 0, hmask, - cp->a1, cp->a2, - PAGE_SHIFT); + kvm_riscv_hfence_vvma_gva(vcpu->kvm, 0, hmask, cp->a1, + cp->a2, PAGE_SHIFT, vmid); } else { + vmid = READ_ONCE(vcpu->kvm->arch.vmid.vmid); if (cp->a1 == 0 && cp->a2 == 0) - kvm_riscv_hfence_vvma_asid_all(vcpu->kvm, - 0, hmask, - cp->a3); + kvm_riscv_hfence_vvma_asid_all(vcpu->kvm, 0, hmask, + cp->a3, vmid); else - kvm_riscv_hfence_vvma_asid_gva(vcpu->kvm, - 0, hmask, - cp->a1, cp->a2, - PAGE_SHIFT, - cp->a3); + kvm_riscv_hfence_vvma_asid_gva(vcpu->kvm, 0, hmask, + cp->a1, cp->a2, PAGE_SHIFT, + cp->a3, vmid); } break; default: diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c index ff672fa71fcc..85a7262115e1 100644 --- a/arch/riscv/kvm/vcpu_timer.c +++ b/arch/riscv/kvm/vcpu_timer.c @@ -345,8 +345,24 @@ void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu) /* * The vstimecmp CSRs are saved by kvm_riscv_vcpu_timer_sync() * upon every VM exit so no need to save here. + * + * If VS-timer expires when no VCPU running on a host CPU then + * WFI executed by such host CPU will be effective NOP resulting + * in no power savings. This is because as-per RISC-V Privileged + * specificaiton: "WFI is also required to resume execution for + * locally enabled interrupts pending at any privilege level, + * regardless of the global interrupt enable at each privilege + * level." + * + * To address the above issue, vstimecmp CSR must be set to -1UL + * over here when VCPU is scheduled-out or exits to user space. */ + csr_write(CSR_VSTIMECMP, -1UL); +#if defined(CONFIG_32BIT) + csr_write(CSR_VSTIMECMPH, -1UL); +#endif + /* timer should be enabled for the remaining operations */ if (unlikely(!t->init_done)) return; diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index b27ec8f96697..66d91ae6e9b2 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/uaccess.h> #include <linux/kvm_host.h> +#include <asm/kvm_mmu.h> const struct _kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS() @@ -31,13 +32,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { int r; - r = kvm_riscv_gstage_alloc_pgd(kvm); + r = kvm_riscv_mmu_alloc_pgd(kvm); if (r) return r; r = kvm_riscv_gstage_vmid_init(kvm); if (r) { - kvm_riscv_gstage_free_pgd(kvm); + kvm_riscv_mmu_free_pgd(kvm); return r; } @@ -199,7 +200,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_USER_MEM_SLOTS; break; case KVM_CAP_VM_GPA_BITS: - r = kvm_riscv_gstage_gpa_bits(); + r = kvm_riscv_gstage_gpa_bits; break; default: r = 0; diff --git a/arch/riscv/kvm/vmid.c b/arch/riscv/kvm/vmid.c index ddc98714ce8e..3b426c800480 100644 --- a/arch/riscv/kvm/vmid.c +++ b/arch/riscv/kvm/vmid.c @@ -14,6 +14,8 @@ #include <linux/smp.h> #include <linux/kvm_host.h> #include <asm/csr.h> +#include <asm/kvm_tlb.h> +#include <asm/kvm_vmid.h> static unsigned long vmid_version = 1; static unsigned long vmid_next; @@ -122,3 +124,26 @@ void kvm_riscv_gstage_vmid_update(struct kvm_vcpu *vcpu) kvm_for_each_vcpu(i, v, vcpu->kvm) kvm_make_request(KVM_REQ_UPDATE_HGATP, v); } + +void kvm_riscv_gstage_vmid_sanitize(struct kvm_vcpu *vcpu) +{ + unsigned long vmid; + + if (!kvm_riscv_gstage_vmid_bits() || + vcpu->arch.last_exit_cpu == vcpu->cpu) + return; + + /* + * On RISC-V platforms with hardware VMID support, we share same + * VMID for all VCPUs of a particular Guest/VM. This means we might + * have stale G-stage TLB entries on the current Host CPU due to + * some other VCPU of the same Guest which ran previously on the + * current Host CPU. + * + * To cleanup stale TLB entries, we simply flush all G-stage TLB + * entries by VMID whenever underlying Host CPU changes for a VCPU. + */ + + vmid = READ_ONCE(vcpu->kvm->arch.vmid.vmid); + kvm_riscv_local_hfence_gvma_vmid_all(vmid); +} diff --git a/arch/riscv/tools/relocs_check.sh b/arch/riscv/tools/relocs_check.sh index baeb2e7b2290..742993e6a8cb 100755 --- a/arch/riscv/tools/relocs_check.sh +++ b/arch/riscv/tools/relocs_check.sh @@ -14,7 +14,9 @@ bad_relocs=$( ${srctree}/scripts/relocs_check.sh "$@" | # These relocations are okay # R_RISCV_RELATIVE - grep -F -w -v 'R_RISCV_RELATIVE' + # R_RISCV_NONE + grep -F -w -v 'R_RISCV_RELATIVE +R_RISCV_NONE' ) if [ -z "$bad_relocs" ]; then diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c index d229cbd2ba22..9b0d55be1239 100644 --- a/arch/s390/crypto/sha1_s390.c +++ b/arch/s390/crypto/sha1_s390.c @@ -38,6 +38,7 @@ static int s390_sha1_init(struct shash_desc *desc) sctx->state[4] = SHA1_H4; sctx->count = 0; sctx->func = CPACF_KIMD_SHA_1; + sctx->first_message_part = 0; return 0; } @@ -60,6 +61,7 @@ static int s390_sha1_import(struct shash_desc *desc, const void *in) sctx->count = ictx->count; memcpy(sctx->state, ictx->state, sizeof(ictx->state)); sctx->func = CPACF_KIMD_SHA_1; + sctx->first_message_part = 0; return 0; } diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c index 33711a29618c..6cbbf5e8555f 100644 --- a/arch/s390/crypto/sha512_s390.c +++ b/arch/s390/crypto/sha512_s390.c @@ -32,6 +32,7 @@ static int sha512_init(struct shash_desc *desc) ctx->count = 0; ctx->sha512.count_hi = 0; ctx->func = CPACF_KIMD_SHA_512; + ctx->first_message_part = 0; return 0; } @@ -57,6 +58,7 @@ static int sha512_import(struct shash_desc *desc, const void *in) memcpy(sctx->state, ictx->state, sizeof(ictx->state)); sctx->func = CPACF_KIMD_SHA_512; + sctx->first_message_part = 0; return 0; } @@ -97,6 +99,7 @@ static int sha384_init(struct shash_desc *desc) ctx->count = 0; ctx->sha512.count_hi = 0; ctx->func = CPACF_KIMD_SHA_512; + ctx->first_message_part = 0; return 0; } diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index c7f8313ba449..0c9a35782c83 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -566,7 +566,15 @@ static void bpf_jit_plt(struct bpf_plt *plt, void *ret, void *target) { memcpy(plt, &bpf_plt, sizeof(*plt)); plt->ret = ret; - plt->target = target; + /* + * (target == NULL) implies that the branch to this PLT entry was + * patched and became a no-op. However, some CPU could have jumped + * to this PLT entry before patching and may be still executing it. + * + * Since the intention in this case is to make the PLT entry a no-op, + * make the target point to the return label instead of NULL. + */ + plt->target = target ?: ret; } /* diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 71019b3b54ea..8bed9030ad47 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -147,7 +147,7 @@ config X86 select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANTS_NO_INSTR select ARCH_WANT_GENERAL_HUGETLB - select ARCH_WANT_HUGE_PMD_SHARE + select ARCH_WANT_HUGE_PMD_SHARE if X86_64 select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP if X86_64 select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP if X86_64 @@ -2695,6 +2695,15 @@ config MITIGATION_ITS disabled, mitigation cannot be enabled via cmdline. See <file:Documentation/admin-guide/hw-vuln/indirect-target-selection.rst> +config MITIGATION_TSA + bool "Mitigate Transient Scheduler Attacks" + depends on CPU_SUP_AMD + default y + help + Enable mitigation for Transient Scheduler Attacks. TSA is a hardware + security vulnerability on AMD CPUs which can lead to forwarding of + invalid info to subsequent instructions and thus can affect their + timing and thereby cause a leakage. endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/coco/sev/Makefile b/arch/x86/coco/sev/Makefile index db3255b979bd..342d79f0ab6a 100644 --- a/arch/x86/coco/sev/Makefile +++ b/arch/x86/coco/sev/Makefile @@ -5,5 +5,6 @@ obj-y += core.o sev-nmi.o vc-handle.o # Clang 14 and older may fail to respect __no_sanitize_undefined when inlining UBSAN_SANITIZE_sev-nmi.o := n -# GCC may fail to respect __no_sanitize_address when inlining +# GCC may fail to respect __no_sanitize_address or __no_kcsan when inlining KASAN_SANITIZE_sev-nmi.o := n +KCSAN_SANITIZE_sev-nmi.o := n diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index 175958b02f2b..8e9a0cc20a4a 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -36,20 +36,20 @@ EXPORT_SYMBOL_GPL(write_ibpb); /* * Define the VERW operand that is disguised as entry code so that - * it can be referenced with KPTI enabled. This ensure VERW can be + * it can be referenced with KPTI enabled. This ensures VERW can be * used late in exit-to-user path after page tables are switched. */ .pushsection .entry.text, "ax" .align L1_CACHE_BYTES, 0xcc -SYM_CODE_START_NOALIGN(mds_verw_sel) +SYM_CODE_START_NOALIGN(x86_verw_sel) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR .word __KERNEL_DS .align L1_CACHE_BYTES, 0xcc -SYM_CODE_END(mds_verw_sel); +SYM_CODE_END(x86_verw_sel); /* For KVM */ -EXPORT_SYMBOL_GPL(mds_verw_sel); +EXPORT_SYMBOL_GPL(x86_verw_sel); .popsection diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 3d1d3547095a..afdbda2dd7b7 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -34,6 +34,7 @@ #include <linux/syscore_ops.h> #include <clocksource/hyperv_timer.h> #include <linux/highmem.h> +#include <linux/export.h> void *hv_hypercall_pg; EXPORT_SYMBOL_GPL(hv_hypercall_pg); diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c index 31f0d29cbc5e..090f5ac9f492 100644 --- a/arch/x86/hyperv/irqdomain.c +++ b/arch/x86/hyperv/irqdomain.c @@ -10,6 +10,7 @@ #include <linux/pci.h> #include <linux/irq.h> +#include <linux/export.h> #include <asm/mshyperv.h> static int hv_map_interrupt(union hv_device_id device_id, bool level, @@ -46,7 +47,7 @@ static int hv_map_interrupt(union hv_device_id device_id, bool level, if (nr_bank < 0) { local_irq_restore(flags); pr_err("%s: unable to generate VP set\n", __func__); - return EINVAL; + return -EINVAL; } intr_desc->target.flags = HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET; @@ -66,7 +67,7 @@ static int hv_map_interrupt(union hv_device_id device_id, bool level, if (!hv_result_success(status)) hv_status_err(status, "\n"); - return hv_result(status); + return hv_result_to_errno(status); } static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry) @@ -88,7 +89,10 @@ static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry) status = hv_do_hypercall(HVCALL_UNMAP_DEVICE_INTERRUPT, input, NULL); local_irq_restore(flags); - return hv_result(status); + if (!hv_result_success(status)) + hv_status_err(status, "\n"); + + return hv_result_to_errno(status); } #ifdef CONFIG_PCI_MSI @@ -169,13 +173,34 @@ static union hv_device_id hv_build_pci_dev_id(struct pci_dev *dev) return dev_id; } -static int hv_map_msi_interrupt(struct pci_dev *dev, int cpu, int vector, - struct hv_interrupt_entry *entry) +/** + * hv_map_msi_interrupt() - "Map" the MSI IRQ in the hypervisor. + * @data: Describes the IRQ + * @out_entry: Hypervisor (MSI) interrupt entry (can be NULL) + * + * Map the IRQ in the hypervisor by issuing a MAP_DEVICE_INTERRUPT hypercall. + * + * Return: 0 on success, -errno on failure + */ +int hv_map_msi_interrupt(struct irq_data *data, + struct hv_interrupt_entry *out_entry) { - union hv_device_id device_id = hv_build_pci_dev_id(dev); + struct irq_cfg *cfg = irqd_cfg(data); + struct hv_interrupt_entry dummy; + union hv_device_id device_id; + struct msi_desc *msidesc; + struct pci_dev *dev; + int cpu; - return hv_map_interrupt(device_id, false, cpu, vector, entry); + msidesc = irq_data_get_msi_desc(data); + dev = msi_desc_to_pci_dev(msidesc); + device_id = hv_build_pci_dev_id(dev); + cpu = cpumask_first(irq_data_get_effective_affinity_mask(data)); + + return hv_map_interrupt(device_id, false, cpu, cfg->vector, + out_entry ? out_entry : &dummy); } +EXPORT_SYMBOL_GPL(hv_map_msi_interrupt); static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi_msg *msg) { @@ -188,13 +213,11 @@ static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi static int hv_unmap_msi_interrupt(struct pci_dev *dev, struct hv_interrupt_entry *old_entry); static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { + struct hv_interrupt_entry *stored_entry; + struct irq_cfg *cfg = irqd_cfg(data); struct msi_desc *msidesc; struct pci_dev *dev; - struct hv_interrupt_entry out_entry, *stored_entry; - struct irq_cfg *cfg = irqd_cfg(data); - const cpumask_t *affinity; - int cpu; - u64 status; + int ret; msidesc = irq_data_get_msi_desc(data); dev = msi_desc_to_pci_dev(msidesc); @@ -204,9 +227,6 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) return; } - affinity = irq_data_get_effective_affinity_mask(data); - cpu = cpumask_first_and(affinity, cpu_online_mask); - if (data->chip_data) { /* * This interrupt is already mapped. Let's unmap first. @@ -219,14 +239,12 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) stored_entry = data->chip_data; data->chip_data = NULL; - status = hv_unmap_msi_interrupt(dev, stored_entry); + ret = hv_unmap_msi_interrupt(dev, stored_entry); kfree(stored_entry); - if (status != HV_STATUS_SUCCESS) { - hv_status_debug(status, "failed to unmap\n"); + if (ret) return; - } } stored_entry = kzalloc(sizeof(*stored_entry), GFP_ATOMIC); @@ -235,15 +253,14 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) return; } - status = hv_map_msi_interrupt(dev, cpu, cfg->vector, &out_entry); - if (status != HV_STATUS_SUCCESS) { + ret = hv_map_msi_interrupt(data, stored_entry); + if (ret) { kfree(stored_entry); return; } - *stored_entry = out_entry; data->chip_data = stored_entry; - entry_to_msi_msg(&out_entry, msg); + entry_to_msi_msg(data->chip_data, msg); return; } @@ -257,7 +274,6 @@ static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd) { struct hv_interrupt_entry old_entry; struct msi_msg msg; - u64 status; if (!irqd->chip_data) { pr_debug("%s: no chip data\n!", __func__); @@ -270,10 +286,7 @@ static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd) kfree(irqd->chip_data); irqd->chip_data = NULL; - status = hv_unmap_msi_interrupt(dev, &old_entry); - - if (status != HV_STATUS_SUCCESS) - hv_status_err(status, "\n"); + (void)hv_unmap_msi_interrupt(dev, &old_entry); } static void hv_msi_free_irq(struct irq_domain *domain, diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index e93a2f488ff7..ade6c665c97e 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -10,6 +10,7 @@ #include <linux/types.h> #include <linux/slab.h> #include <linux/cpu.h> +#include <linux/export.h> #include <asm/svm.h> #include <asm/sev.h> #include <asm/io.h> diff --git a/arch/x86/hyperv/nested.c b/arch/x86/hyperv/nested.c index 1083dc8646f9..8ccbb7c4fc27 100644 --- a/arch/x86/hyperv/nested.c +++ b/arch/x86/hyperv/nested.c @@ -11,6 +11,7 @@ #include <linux/types.h> +#include <linux/export.h> #include <hyperv/hvhdk.h> #include <asm/mshyperv.h> #include <asm/tlbflush.h> diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index ee176236c2be..286d509f9363 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -456,6 +456,7 @@ #define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */ #define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */ #define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */ +#define X86_FEATURE_VERW_CLEAR (20*32+ 5) /* The memory form of VERW mitigates TSA */ #define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* Null Selector Clears Base */ #define X86_FEATURE_AUTOIBRS (20*32+ 8) /* Automatic IBRS */ #define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* SMM_CTL MSR is not present */ @@ -487,6 +488,9 @@ #define X86_FEATURE_PREFER_YMM (21*32+ 8) /* Avoid ZMM registers due to downclocking */ #define X86_FEATURE_APX (21*32+ 9) /* Advanced Performance Extensions */ #define X86_FEATURE_INDIRECT_THUNK_ITS (21*32+10) /* Use thunk for indirect branches in lower half of cacheline */ +#define X86_FEATURE_TSA_SQ_NO (21*32+11) /* AMD CPU not vulnerable to TSA-SQ */ +#define X86_FEATURE_TSA_L1_NO (21*32+12) /* AMD CPU not vulnerable to TSA-L1 */ +#define X86_FEATURE_CLEAR_CPU_BUF_VM (21*32+13) /* Clear CPU buffers using VERW before VMRUN */ /* * BUG word(s) @@ -542,5 +546,5 @@ #define X86_BUG_OLD_MICROCODE X86_BUG( 1*32+ 6) /* "old_microcode" CPU has old microcode, it is surely vulnerable to something */ #define X86_BUG_ITS X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */ #define X86_BUG_ITS_NATIVE_ONLY X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */ - +#define X86_BUG_TSA X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index 5036f13ab69f..5a0d42464d44 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -26,7 +26,22 @@ enum { IRQ_REMAP_X2APIC_MODE, }; -struct vcpu_data { +/* + * This is mainly used to communicate information back-and-forth + * between SVM and IOMMU for setting up and tearing down posted + * interrupt + */ +struct amd_iommu_pi_data { + u64 vapic_addr; /* Physical address of the vCPU's vAPIC. */ + u32 ga_tag; + u32 vector; /* Guest vector of the interrupt */ + int cpu; + bool ga_log_intr; + bool is_guest_mode; + void *ir_data; +}; + +struct intel_iommu_pi_data { u64 pi_desc_addr; /* Physical address of PI Descriptor */ u32 vector; /* Guest vector of the interrupt */ }; diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 9a9b21b78905..b30e5474c18e 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -44,13 +44,13 @@ static __always_inline void native_irq_enable(void) static __always_inline void native_safe_halt(void) { - mds_idle_clear_cpu_buffers(); + x86_idle_clear_cpu_buffers(); asm volatile("sti; hlt": : :"memory"); } static __always_inline void native_halt(void) { - mds_idle_clear_cpu_buffers(); + x86_idle_clear_cpu_buffers(); asm volatile("hlt": : :"memory"); } diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 8d50e3e0a19b..18a5c3119e1a 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -49,7 +49,6 @@ KVM_X86_OP(set_idt) KVM_X86_OP(get_gdt) KVM_X86_OP(set_gdt) KVM_X86_OP(sync_dirty_debug_regs) -KVM_X86_OP(set_dr6) KVM_X86_OP(set_dr7) KVM_X86_OP(cache_reg) KVM_X86_OP(get_rflags) @@ -112,7 +111,7 @@ KVM_X86_OP_OPTIONAL(update_cpu_dirty_logging) KVM_X86_OP_OPTIONAL(vcpu_blocking) KVM_X86_OP_OPTIONAL(vcpu_unblocking) KVM_X86_OP_OPTIONAL(pi_update_irte) -KVM_X86_OP_OPTIONAL(pi_start_assignment) +KVM_X86_OP_OPTIONAL(pi_start_bypass) KVM_X86_OP_OPTIONAL(apicv_pre_state_restore) KVM_X86_OP_OPTIONAL(apicv_post_state_restore) KVM_X86_OP_OPTIONAL_RET0(dy_apicv_has_pending_interrupt) @@ -139,7 +138,7 @@ KVM_X86_OP(check_emulate_instruction) KVM_X86_OP(apic_init_signal_blocked) KVM_X86_OP_OPTIONAL(enable_l2_tlb_flush) KVM_X86_OP_OPTIONAL(migrate_timers) -KVM_X86_OP(msr_filter_changed) +KVM_X86_OP(recalc_msr_intercepts) KVM_X86_OP(complete_emulated_msr) KVM_X86_OP(vcpu_deliver_sipi_vector) KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 639d9bcee842..f19a76d3ca0e 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -297,6 +297,7 @@ enum x86_intercept_stage; */ #define KVM_APIC_PV_EOI_PENDING 1 +struct kvm_kernel_irqfd; struct kvm_kernel_irq_routing_entry; /* @@ -700,8 +701,13 @@ struct kvm_vcpu_hv { struct kvm_vcpu_hv_tlb_flush_fifo tlb_flush_fifo[HV_NR_TLB_FLUSH_FIFOS]; - /* Preallocated buffer for handling hypercalls passing sparse vCPU set */ + /* + * Preallocated buffers for handling hypercalls that pass sparse vCPU + * sets (for high vCPU counts, they're too large to comfortably fit on + * the stack). + */ u64 sparse_banks[HV_MAX_SPARSE_VCPU_BANKS]; + DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS); struct hv_vp_assist_page vp_assist_page; @@ -764,6 +770,7 @@ enum kvm_only_cpuid_leafs { CPUID_8000_0022_EAX, CPUID_7_2_EDX, CPUID_24_0_EBX, + CPUID_8000_0021_ECX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, @@ -1314,6 +1321,12 @@ enum kvm_apicv_inhibit { */ APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED, + /* + * AVIC is disabled because the vCPU's APIC ID is beyond the max + * supported by AVIC/x2AVIC, i.e. the vCPU is unaddressable. + */ + APICV_INHIBIT_REASON_PHYSICAL_ID_TOO_BIG, + NR_APICV_INHIBIT_REASONS, }; @@ -1332,7 +1345,8 @@ enum kvm_apicv_inhibit { __APICV_INHIBIT_REASON(IRQWIN), \ __APICV_INHIBIT_REASON(PIT_REINJ), \ __APICV_INHIBIT_REASON(SEV), \ - __APICV_INHIBIT_REASON(LOGICAL_ID_ALIASED) + __APICV_INHIBIT_REASON(LOGICAL_ID_ALIASED), \ + __APICV_INHIBIT_REASON(PHYSICAL_ID_TOO_BIG) struct kvm_arch { unsigned long n_used_mmu_pages; @@ -1344,7 +1358,7 @@ struct kvm_arch { bool has_private_mem; bool has_protected_state; bool pre_fault_allowed; - struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; + struct hlist_head *mmu_page_hash; struct list_head active_mmu_pages; /* * A list of kvm_mmu_page structs that, if zapped, could possibly be @@ -1373,11 +1387,13 @@ struct kvm_arch { #define __KVM_HAVE_ARCH_NONCOHERENT_DMA atomic_t noncoherent_dma_count; -#define __KVM_HAVE_ARCH_ASSIGNED_DEVICE - atomic_t assigned_device_count; + unsigned long nr_possible_bypass_irqs; + +#ifdef CONFIG_KVM_IOAPIC struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; +#endif atomic_t vapics_in_nmi_mode; struct mutex apic_map_lock; struct kvm_apic_map __rcu *apic_map; @@ -1392,12 +1408,8 @@ struct kvm_arch { gpa_t wall_clock; - bool mwait_in_guest; - bool hlt_in_guest; - bool pause_in_guest; - bool cstate_in_guest; + u64 disabled_exits; - unsigned long irq_sources_bitmap; s64 kvmclock_offset; /* @@ -1426,9 +1438,6 @@ struct kvm_arch { struct delayed_work kvmclock_update_work; struct delayed_work kvmclock_sync_work; - /* reads protected by irq_srcu, writes by irq_lock */ - struct hlist_head mask_notifier_list; - #ifdef CONFIG_KVM_HYPERV struct kvm_hv hyperv; #endif @@ -1451,6 +1460,7 @@ struct kvm_arch { bool x2apic_format; bool x2apic_broadcast_quirk_disabled; + bool has_mapped_host_mmio; bool guest_can_read_msr_platform_info; bool exception_payload_enabled; @@ -1674,6 +1684,12 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical) return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL; } +enum kvm_x86_run_flags { + KVM_RUN_FORCE_IMMEDIATE_EXIT = BIT(0), + KVM_RUN_LOAD_GUEST_DR6 = BIT(1), + KVM_RUN_LOAD_DEBUGCTL = BIT(2), +}; + struct kvm_x86_ops { const char *name; @@ -1702,6 +1718,12 @@ struct kvm_x86_ops { void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); void (*vcpu_put)(struct kvm_vcpu *vcpu); + /* + * Mask of DEBUGCTL bits that are owned by the host, i.e. that need to + * match the host's value even while the guest is active. + */ + const u64 HOST_OWNED_DEBUGCTL; + void (*update_exception_bitmap)(struct kvm_vcpu *vcpu); int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); @@ -1724,7 +1746,6 @@ struct kvm_x86_ops { void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu); - void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value); void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value); void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); @@ -1755,7 +1776,7 @@ struct kvm_x86_ops { int (*vcpu_pre_run)(struct kvm_vcpu *vcpu); enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu, - bool force_immediate_exit); + u64 run_flags); int (*handle_exit)(struct kvm_vcpu *vcpu, enum exit_fastpath_completion exit_fastpath); int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); @@ -1847,9 +1868,10 @@ struct kvm_x86_ops { void (*vcpu_blocking)(struct kvm_vcpu *vcpu); void (*vcpu_unblocking)(struct kvm_vcpu *vcpu); - int (*pi_update_irte)(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set); - void (*pi_start_assignment)(struct kvm *kvm); + int (*pi_update_irte)(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, + unsigned int host_irq, uint32_t guest_irq, + struct kvm_vcpu *vcpu, u32 vector); + void (*pi_start_bypass)(struct kvm *kvm); void (*apicv_pre_state_restore)(struct kvm_vcpu *vcpu); void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu); bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu); @@ -1886,7 +1908,7 @@ struct kvm_x86_ops { int (*enable_l2_tlb_flush)(struct kvm_vcpu *vcpu); void (*migrate_timers)(struct kvm_vcpu *vcpu); - void (*msr_filter_changed)(struct kvm_vcpu *vcpu); + void (*recalc_msr_intercepts)(struct kvm_vcpu *vcpu); int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err); void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector); @@ -1944,6 +1966,7 @@ struct kvm_arch_async_pf { extern u32 __read_mostly kvm_nr_uret_msrs; extern bool __read_mostly allow_smaller_maxphyaddr; extern bool __read_mostly enable_apicv; +extern bool __read_mostly enable_ipiv; extern bool __read_mostly enable_device_posted_irqs; extern struct kvm_x86_ops kvm_x86_ops; @@ -1962,7 +1985,7 @@ void kvm_x86_vendor_exit(void); #define __KVM_HAVE_ARCH_VM_ALLOC static inline struct kvm *kvm_arch_alloc_vm(void) { - return __vmalloc(kvm_x86_ops.vm_size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); + return kvzalloc(kvm_x86_ops.vm_size, GFP_KERNEL_ACCOUNT); } #define __KVM_HAVE_ARCH_VM_FREE @@ -2007,7 +2030,7 @@ void kvm_mmu_vendor_module_exit(void); void kvm_mmu_destroy(struct kvm_vcpu *vcpu); int kvm_mmu_create(struct kvm_vcpu *vcpu); -void kvm_mmu_init_vm(struct kvm *kvm); +int kvm_mmu_init_vm(struct kvm *kvm); void kvm_mmu_uninit_vm(struct kvm *kvm); void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm, @@ -2038,19 +2061,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3); int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, const void *val, int bytes); -struct kvm_irq_mask_notifier { - void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked); - int irq; - struct hlist_node link; -}; - -void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq, - struct kvm_irq_mask_notifier *kimn); -void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, - struct kvm_irq_mask_notifier *kimn); -void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, - bool mask); - extern bool tdp_enabled; u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); @@ -2209,9 +2219,6 @@ static inline int __kvm_irq_line_state(unsigned long *irq_state, return !!(*irq_state); } -int kvm_pic_set_irq(struct kvm_pic *pic, int irq, int irq_source_id, int level); -void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id); - void kvm_inject_nmi(struct kvm_vcpu *vcpu); int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu); @@ -2388,9 +2395,6 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu); bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu); -void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, - struct kvm_lapic_irq *irq); - static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq) { /* We can only post Fixed and LowPrio IRQs */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index e1752ba47e67..abc4659f5809 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -112,12 +112,6 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) return hv_status; } -/* Hypercall to the L0 hypervisor */ -static inline u64 hv_do_nested_hypercall(u64 control, void *input, void *output) -{ - return hv_do_hypercall(control | HV_HYPERCALL_NESTED, input, output); -} - /* Fast hypercall with 8 bytes of input and no output */ static inline u64 _hv_do_fast_hypercall8(u64 control, u64 input1) { @@ -165,13 +159,6 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) return _hv_do_fast_hypercall8(control, input1); } -static inline u64 hv_do_fast_nested_hypercall8(u16 code, u64 input1) -{ - u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED; - - return _hv_do_fast_hypercall8(control, input1); -} - /* Fast hypercall with 16 bytes of input */ static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2) { @@ -223,13 +210,6 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2) return _hv_do_fast_hypercall16(control, input1, input2); } -static inline u64 hv_do_fast_nested_hypercall16(u16 code, u64 input1, u64 input2) -{ - u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED; - - return _hv_do_fast_hypercall16(control, input1, input2); -} - extern struct hv_vp_assist_page **hv_vp_assist_page; static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu) @@ -262,6 +242,8 @@ static inline void hv_apic_init(void) {} struct irq_domain *hv_create_pci_msi_domain(void); +int hv_map_msi_interrupt(struct irq_data *data, + struct hv_interrupt_entry *out_entry); int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector, struct hv_interrupt_entry *entry); int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index b7dded3c8113..c29127ac626a 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -419,6 +419,7 @@ #define DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI (1UL << 12) #define DEBUGCTLMSR_FREEZE_IN_SMM_BIT 14 #define DEBUGCTLMSR_FREEZE_IN_SMM (1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT) +#define DEBUGCTLMSR_RTM_DEBUG BIT(15) #define MSR_PEBS_FRONTEND 0x000003f7 @@ -628,6 +629,7 @@ #define MSR_AMD64_OSVW_STATUS 0xc0010141 #define MSR_AMD_PPIN_CTL 0xc00102f0 #define MSR_AMD_PPIN 0xc00102f1 +#define MSR_AMD64_CPUID_FN_7 0xc0011002 #define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index dd2b129b0418..6ca6516c7492 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -43,8 +43,6 @@ static __always_inline void __monitorx(const void *eax, u32 ecx, u32 edx) static __always_inline void __mwait(u32 eax, u32 ecx) { - mds_idle_clear_cpu_buffers(); - /* * Use the instruction mnemonic with implicit operands, as the LLVM * assembler fails to assemble the mnemonic with explicit operands: @@ -80,7 +78,7 @@ static __always_inline void __mwait(u32 eax, u32 ecx) */ static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx) { - /* No MDS buffer clear as this is AMD/HYGON only */ + /* No need for TSA buffer clearing on AMD */ /* "mwaitx %eax, %ebx, %ecx" */ asm volatile(".byte 0x0f, 0x01, 0xfb" @@ -98,7 +96,6 @@ static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx) */ static __always_inline void __sti_mwait(u32 eax, u32 ecx) { - mds_idle_clear_cpu_buffers(); asm volatile("sti; mwait" :: "a" (eax), "c" (ecx)); } @@ -115,21 +112,29 @@ static __always_inline void __sti_mwait(u32 eax, u32 ecx) */ static __always_inline void mwait_idle_with_hints(u32 eax, u32 ecx) { + if (need_resched()) + return; + + x86_idle_clear_cpu_buffers(); + if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) { const void *addr = ¤t_thread_info()->flags; alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr)); __monitor(addr, 0, 0); - if (!need_resched()) { - if (ecx & 1) { - __mwait(eax, ecx); - } else { - __sti_mwait(eax, ecx); - raw_local_irq_disable(); - } + if (need_resched()) + goto out; + + if (ecx & 1) { + __mwait(eax, ecx); + } else { + __sti_mwait(eax, ecx); + raw_local_irq_disable(); } } + +out: current_clr_polling(); } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 20d754b98f3f..10f261678749 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -302,25 +302,31 @@ .endm /* - * Macro to execute VERW instruction that mitigate transient data sampling - * attacks such as MDS. On affected systems a microcode update overloaded VERW - * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF. - * + * Macro to execute VERW insns that mitigate transient data sampling + * attacks such as MDS or TSA. On affected systems a microcode update + * overloaded VERW insns to also clear the CPU buffers. VERW clobbers + * CFLAGS.ZF. * Note: Only the memory operand variant of VERW clears the CPU buffers. */ -.macro CLEAR_CPU_BUFFERS +.macro __CLEAR_CPU_BUFFERS feature #ifdef CONFIG_X86_64 - ALTERNATIVE "", "verw mds_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF + ALTERNATIVE "", "verw x86_verw_sel(%rip)", \feature #else /* * In 32bit mode, the memory operand must be a %cs reference. The data * segments may not be usable (vm86 mode), and the stack segment may not * be flat (ESPFIX32). */ - ALTERNATIVE "", "verw %cs:mds_verw_sel", X86_FEATURE_CLEAR_CPU_BUF + ALTERNATIVE "", "verw %cs:x86_verw_sel", \feature #endif .endm +#define CLEAR_CPU_BUFFERS \ + __CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF + +#define VM_CLEAR_CPU_BUFFERS \ + __CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF_VM + #ifdef CONFIG_X86_64 .macro CLEAR_BRANCH_HISTORY ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP @@ -567,24 +573,24 @@ DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); DECLARE_STATIC_KEY_FALSE(switch_vcpu_ibpb); -DECLARE_STATIC_KEY_FALSE(mds_idle_clear); +DECLARE_STATIC_KEY_FALSE(cpu_buf_idle_clear); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DECLARE_STATIC_KEY_FALSE(cpu_buf_vm_clear); -extern u16 mds_verw_sel; +extern u16 x86_verw_sel; #include <asm/segment.h> /** - * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability + * x86_clear_cpu_buffers - Buffer clearing support for different x86 CPU vulns * * This uses the otherwise unused and obsolete VERW instruction in * combination with microcode which triggers a CPU buffer flush when the * instruction is executed. */ -static __always_inline void mds_clear_cpu_buffers(void) +static __always_inline void x86_clear_cpu_buffers(void) { static const u16 ds = __KERNEL_DS; @@ -601,14 +607,15 @@ static __always_inline void mds_clear_cpu_buffers(void) } /** - * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability + * x86_idle_clear_cpu_buffers - Buffer clearing support in idle for the MDS + * and TSA vulnerabilities. * * Clear CPU buffers if the corresponding static key is enabled */ -static __always_inline void mds_idle_clear_cpu_buffers(void) +static __always_inline void x86_idle_clear_cpu_buffers(void) { - if (static_branch_likely(&mds_idle_clear)) - mds_clear_cpu_buffers(); + if (static_branch_likely(&cpu_buf_idle_clear)) + x86_clear_cpu_buffers(); } #endif /* __ASSEMBLER__ */ diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h index d8525e6ef50a..8bc074c8d7c6 100644 --- a/arch/x86/include/asm/shared/tdx.h +++ b/arch/x86/include/asm/shared/tdx.h @@ -72,6 +72,7 @@ #define TDVMCALL_MAP_GPA 0x10001 #define TDVMCALL_GET_QUOTE 0x10002 #define TDVMCALL_REPORT_FATAL_ERROR 0x10003 +#define TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT 0x10004ULL /* * TDG.VP.VMCALL Status Codes (returned in R10) diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index ad954a1a6656..ffc27f676243 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -252,16 +252,21 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 #define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) +/* + * GA_LOG_INTR is a synthetic flag that's never propagated to hardware-visible + * tables. GA_LOG_INTR is set if the vCPU needs device posted IRQs to generate + * GA log interrupts to wake the vCPU (because it's blocking or about to block). + */ +#define AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR BIT_ULL(61) + #define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK GENMASK_ULL(11, 0) -#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) +#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK GENMASK_ULL(51, 12) #define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) #define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) #define AVIC_PHYSICAL_ID_TABLE_SIZE_MASK (0xFFULL) #define AVIC_DOORBELL_PHYSICAL_ID_MASK GENMASK_ULL(11, 0) -#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL - #define AVIC_UNACCEL_ACCESS_WRITE_MASK 1 #define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 #define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF @@ -290,8 +295,6 @@ enum avic_ipi_failure_cause { static_assert((AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == AVIC_MAX_PHYSICAL_ID); static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_MAX_PHYSICAL_ID); -#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) - #define SVM_SEV_FEAT_SNP_ACTIVE BIT(0) #define SVM_SEV_FEAT_RESTRICTED_INJECTION BIT(3) #define SVM_SEV_FEAT_ALTERNATE_INJECTION BIT(4) diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 6f3499507c5e..0f15d683817d 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -965,7 +965,13 @@ struct kvm_tdx_cmd { struct kvm_tdx_capabilities { __u64 supported_attrs; __u64 supported_xfam; - __u64 reserved[254]; + + __u64 kernel_tdvmcallinfo_1_r11; + __u64 user_tdvmcallinfo_1_r11; + __u64 kernel_tdvmcallinfo_1_r12; + __u64 user_tdvmcallinfo_1_r12; + + __u64 reserved[250]; /* Configurable CPUID bits for userspace */ struct kvm_cpuid2 cpuid; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 655f44f89ded..329ee185d8cc 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -377,6 +377,47 @@ static void bsp_determine_snp(struct cpuinfo_x86 *c) #endif } +#define ZEN_MODEL_STEP_UCODE(fam, model, step, ucode) \ + X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, fam, model), \ + step, step, ucode) + +static const struct x86_cpu_id amd_tsa_microcode[] = { + ZEN_MODEL_STEP_UCODE(0x19, 0x01, 0x1, 0x0a0011d7), + ZEN_MODEL_STEP_UCODE(0x19, 0x01, 0x2, 0x0a00123b), + ZEN_MODEL_STEP_UCODE(0x19, 0x08, 0x2, 0x0a00820d), + ZEN_MODEL_STEP_UCODE(0x19, 0x11, 0x1, 0x0a10114c), + ZEN_MODEL_STEP_UCODE(0x19, 0x11, 0x2, 0x0a10124c), + ZEN_MODEL_STEP_UCODE(0x19, 0x18, 0x1, 0x0a108109), + ZEN_MODEL_STEP_UCODE(0x19, 0x21, 0x0, 0x0a20102e), + ZEN_MODEL_STEP_UCODE(0x19, 0x21, 0x2, 0x0a201211), + ZEN_MODEL_STEP_UCODE(0x19, 0x44, 0x1, 0x0a404108), + ZEN_MODEL_STEP_UCODE(0x19, 0x50, 0x0, 0x0a500012), + ZEN_MODEL_STEP_UCODE(0x19, 0x61, 0x2, 0x0a60120a), + ZEN_MODEL_STEP_UCODE(0x19, 0x74, 0x1, 0x0a704108), + ZEN_MODEL_STEP_UCODE(0x19, 0x75, 0x2, 0x0a705208), + ZEN_MODEL_STEP_UCODE(0x19, 0x78, 0x0, 0x0a708008), + ZEN_MODEL_STEP_UCODE(0x19, 0x7c, 0x0, 0x0a70c008), + ZEN_MODEL_STEP_UCODE(0x19, 0xa0, 0x2, 0x0aa00216), + {}, +}; + +static void tsa_init(struct cpuinfo_x86 *c) +{ + if (cpu_has(c, X86_FEATURE_HYPERVISOR)) + return; + + if (cpu_has(c, X86_FEATURE_ZEN3) || + cpu_has(c, X86_FEATURE_ZEN4)) { + if (x86_match_min_microcode_rev(amd_tsa_microcode)) + setup_force_cpu_cap(X86_FEATURE_VERW_CLEAR); + else + pr_debug("%s: current revision: 0x%x\n", __func__, c->microcode); + } else { + setup_force_cpu_cap(X86_FEATURE_TSA_SQ_NO); + setup_force_cpu_cap(X86_FEATURE_TSA_L1_NO); + } +} + static void bsp_init_amd(struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { @@ -489,6 +530,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) } bsp_determine_snp(c); + + tsa_init(c); + return; warn: @@ -930,6 +974,16 @@ static void init_amd_zen2(struct cpuinfo_x86 *c) init_spectral_chicken(c); fix_erratum_1386(c); zen2_zenbleed_check(c); + + /* Disable RDSEED on AMD Cyan Skillfish because of an error. */ + if (c->x86_model == 0x47 && c->x86_stepping == 0x0) { + clear_cpu_cap(c, X86_FEATURE_RDSEED); + msr_clear_bit(MSR_AMD64_CPUID_FN_7, 18); + pr_emerg("RDSEED is not reliable on this platform; disabling.\n"); + } + + /* Correct misconfigured CPUID on some clients. */ + clear_cpu_cap(c, X86_FEATURE_INVLPGB); } static void init_amd_zen3(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 7f94e6a5497d..f4d3abb12317 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -94,6 +94,8 @@ static void __init bhi_apply_mitigation(void); static void __init its_select_mitigation(void); static void __init its_update_mitigation(void); static void __init its_apply_mitigation(void); +static void __init tsa_select_mitigation(void); +static void __init tsa_apply_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -169,9 +171,9 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb); DEFINE_STATIC_KEY_FALSE(switch_vcpu_ibpb); EXPORT_SYMBOL_GPL(switch_vcpu_ibpb); -/* Control MDS CPU buffer clear before idling (halt, mwait) */ -DEFINE_STATIC_KEY_FALSE(mds_idle_clear); -EXPORT_SYMBOL_GPL(mds_idle_clear); +/* Control CPU buffer clear before idling (halt, mwait) */ +DEFINE_STATIC_KEY_FALSE(cpu_buf_idle_clear); +EXPORT_SYMBOL_GPL(cpu_buf_idle_clear); /* * Controls whether l1d flush based mitigations are enabled, @@ -225,6 +227,7 @@ void __init cpu_select_mitigations(void) gds_select_mitigation(); its_select_mitigation(); bhi_select_mitigation(); + tsa_select_mitigation(); /* * After mitigations are selected, some may need to update their @@ -272,6 +275,7 @@ void __init cpu_select_mitigations(void) gds_apply_mitigation(); its_apply_mitigation(); bhi_apply_mitigation(); + tsa_apply_mitigation(); } /* @@ -637,7 +641,7 @@ static void __init mmio_apply_mitigation(void) * is required irrespective of SMT state. */ if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) - static_branch_enable(&mds_idle_clear); + static_branch_enable(&cpu_buf_idle_clear); if (mmio_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); @@ -1488,6 +1492,94 @@ static void __init its_apply_mitigation(void) } #undef pr_fmt +#define pr_fmt(fmt) "Transient Scheduler Attacks: " fmt + +enum tsa_mitigations { + TSA_MITIGATION_NONE, + TSA_MITIGATION_AUTO, + TSA_MITIGATION_UCODE_NEEDED, + TSA_MITIGATION_USER_KERNEL, + TSA_MITIGATION_VM, + TSA_MITIGATION_FULL, +}; + +static const char * const tsa_strings[] = { + [TSA_MITIGATION_NONE] = "Vulnerable", + [TSA_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", + [TSA_MITIGATION_USER_KERNEL] = "Mitigation: Clear CPU buffers: user/kernel boundary", + [TSA_MITIGATION_VM] = "Mitigation: Clear CPU buffers: VM", + [TSA_MITIGATION_FULL] = "Mitigation: Clear CPU buffers", +}; + +static enum tsa_mitigations tsa_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_TSA) ? TSA_MITIGATION_AUTO : TSA_MITIGATION_NONE; + +static int __init tsa_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + tsa_mitigation = TSA_MITIGATION_NONE; + else if (!strcmp(str, "on")) + tsa_mitigation = TSA_MITIGATION_FULL; + else if (!strcmp(str, "user")) + tsa_mitigation = TSA_MITIGATION_USER_KERNEL; + else if (!strcmp(str, "vm")) + tsa_mitigation = TSA_MITIGATION_VM; + else + pr_err("Ignoring unknown tsa=%s option.\n", str); + + return 0; +} +early_param("tsa", tsa_parse_cmdline); + +static void __init tsa_select_mitigation(void) +{ + if (cpu_mitigations_off() || !boot_cpu_has_bug(X86_BUG_TSA)) { + tsa_mitigation = TSA_MITIGATION_NONE; + return; + } + + if (tsa_mitigation == TSA_MITIGATION_NONE) + return; + + if (!boot_cpu_has(X86_FEATURE_VERW_CLEAR)) { + tsa_mitigation = TSA_MITIGATION_UCODE_NEEDED; + goto out; + } + + if (tsa_mitigation == TSA_MITIGATION_AUTO) + tsa_mitigation = TSA_MITIGATION_FULL; + + /* + * No need to set verw_clear_cpu_buf_mitigation_selected - it + * doesn't fit all cases here and it is not needed because this + * is the only VERW-based mitigation on AMD. + */ +out: + pr_info("%s\n", tsa_strings[tsa_mitigation]); +} + +static void __init tsa_apply_mitigation(void) +{ + switch (tsa_mitigation) { + case TSA_MITIGATION_USER_KERNEL: + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + break; + case TSA_MITIGATION_VM: + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM); + break; + case TSA_MITIGATION_FULL: + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM); + break; + default: + break; + } +} + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init = @@ -2249,10 +2341,10 @@ static void update_mds_branch_idle(void) return; if (sched_smt_active()) { - static_branch_enable(&mds_idle_clear); + static_branch_enable(&cpu_buf_idle_clear); } else if (mmio_mitigation == MMIO_MITIGATION_OFF || (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) { - static_branch_disable(&mds_idle_clear); + static_branch_disable(&cpu_buf_idle_clear); } } @@ -2316,6 +2408,25 @@ void cpu_bugs_smt_update(void) break; } + switch (tsa_mitigation) { + case TSA_MITIGATION_USER_KERNEL: + case TSA_MITIGATION_VM: + case TSA_MITIGATION_AUTO: + case TSA_MITIGATION_FULL: + /* + * TSA-SQ can potentially lead to info leakage between + * SMT threads. + */ + if (sched_smt_active()) + static_branch_enable(&cpu_buf_idle_clear); + else + static_branch_disable(&cpu_buf_idle_clear); + break; + case TSA_MITIGATION_NONE: + case TSA_MITIGATION_UCODE_NEEDED: + break; + } + mutex_unlock(&spec_ctrl_mutex); } @@ -3265,6 +3376,11 @@ static ssize_t gds_show_state(char *buf) return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]); } +static ssize_t tsa_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", tsa_strings[tsa_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -3328,6 +3444,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_ITS: return its_show_state(buf); + case X86_BUG_TSA: + return tsa_show_state(buf); + default: break; } @@ -3414,6 +3533,11 @@ ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_att { return cpu_show_common(dev, attr, buf, X86_BUG_ITS); } + +ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_TSA); +} #endif void __warn_thunk(void) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 27125e009847..fb50c1dd53ef 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1233,6 +1233,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define ITS BIT(8) /* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */ #define ITS_NATIVE_ONLY BIT(9) +/* CPU is affected by Transient Scheduler Attacks */ +#define TSA BIT(10) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS), @@ -1280,7 +1282,7 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_AMD(0x16, RETBLEED), VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO), VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO), - VULNBL_AMD(0x19, SRSO), + VULNBL_AMD(0x19, SRSO | TSA), VULNBL_AMD(0x1a, SRSO), {} }; @@ -1530,6 +1532,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY); } + if (c->x86_vendor == X86_VENDOR_AMD) { + if (!cpu_has(c, X86_FEATURE_TSA_SQ_NO) || + !cpu_has(c, X86_FEATURE_TSA_L1_NO)) { + if (cpu_matches(cpu_vuln_blacklist, TSA) || + /* Enable bug on Zen guests to allow for live migration. */ + (cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_ZEN))) + setup_force_cpu_bug(X86_BUG_TSA); + } + } + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/cpu/microcode/amd_shas.c b/arch/x86/kernel/cpu/microcode/amd_shas.c index 2a1655b1fdd8..1fd349cfc802 100644 --- a/arch/x86/kernel/cpu/microcode/amd_shas.c +++ b/arch/x86/kernel/cpu/microcode/amd_shas.c @@ -231,6 +231,13 @@ static const struct patch_digest phashes[] = { 0x0d,0x5b,0x65,0x34,0x69,0xb2,0x62,0x21, } }, + { 0xa0011d7, { + 0x35,0x07,0xcd,0x40,0x94,0xbc,0x81,0x6b, + 0xfc,0x61,0x56,0x1a,0xe2,0xdb,0x96,0x12, + 0x1c,0x1c,0x31,0xb1,0x02,0x6f,0xe5,0xd2, + 0xfe,0x1b,0x04,0x03,0x2c,0x8f,0x4c,0x36, + } + }, { 0xa001223, { 0xfb,0x32,0x5f,0xc6,0x83,0x4f,0x8c,0xb8, 0xa4,0x05,0xf9,0x71,0x53,0x01,0x16,0xc4, @@ -294,6 +301,13 @@ static const struct patch_digest phashes[] = { 0xc0,0xcd,0x33,0xf2,0x8d,0xf9,0xef,0x59, } }, + { 0xa00123b, { + 0xef,0xa1,0x1e,0x71,0xf1,0xc3,0x2c,0xe2, + 0xc3,0xef,0x69,0x41,0x7a,0x54,0xca,0xc3, + 0x8f,0x62,0x84,0xee,0xc2,0x39,0xd9,0x28, + 0x95,0xa7,0x12,0x49,0x1e,0x30,0x71,0x72, + } + }, { 0xa00820c, { 0xa8,0x0c,0x81,0xc0,0xa6,0x00,0xe7,0xf3, 0x5f,0x65,0xd3,0xb9,0x6f,0xea,0x93,0x63, @@ -301,6 +315,13 @@ static const struct patch_digest phashes[] = { 0xe1,0x3b,0x8d,0xb2,0xf8,0x22,0x03,0xe2, } }, + { 0xa00820d, { + 0xf9,0x2a,0xc0,0xf4,0x9e,0xa4,0x87,0xa4, + 0x7d,0x87,0x00,0xfd,0xab,0xda,0x19,0xca, + 0x26,0x51,0x32,0xc1,0x57,0x91,0xdf,0xc1, + 0x05,0xeb,0x01,0x7c,0x5a,0x95,0x21,0xb7, + } + }, { 0xa10113e, { 0x05,0x3c,0x66,0xd7,0xa9,0x5a,0x33,0x10, 0x1b,0xf8,0x9c,0x8f,0xed,0xfc,0xa7,0xa0, @@ -322,6 +343,13 @@ static const struct patch_digest phashes[] = { 0xf1,0x5e,0xb0,0xde,0xb4,0x98,0xae,0xc4, } }, + { 0xa10114c, { + 0x9e,0xb6,0xa2,0xd9,0x87,0x38,0xc5,0x64, + 0xd8,0x88,0xfa,0x78,0x98,0xf9,0x6f,0x74, + 0x39,0x90,0x1b,0xa5,0xcf,0x5e,0xb4,0x2a, + 0x02,0xff,0xd4,0x8c,0x71,0x8b,0xe2,0xc0, + } + }, { 0xa10123e, { 0x03,0xb9,0x2c,0x76,0x48,0x93,0xc9,0x18, 0xfb,0x56,0xfd,0xf7,0xe2,0x1d,0xca,0x4d, @@ -343,6 +371,13 @@ static const struct patch_digest phashes[] = { 0x1b,0x7d,0x64,0x9d,0x4b,0x53,0x13,0x75, } }, + { 0xa10124c, { + 0x29,0xea,0xf1,0x2c,0xb2,0xe4,0xef,0x90, + 0xa4,0xcd,0x1d,0x86,0x97,0x17,0x61,0x46, + 0xfc,0x22,0xcb,0x57,0x75,0x19,0xc8,0xcc, + 0x0c,0xf5,0xbc,0xac,0x81,0x9d,0x9a,0xd2, + } + }, { 0xa108108, { 0xed,0xc2,0xec,0xa1,0x15,0xc6,0x65,0xe9, 0xd0,0xef,0x39,0xaa,0x7f,0x55,0x06,0xc6, @@ -350,6 +385,13 @@ static const struct patch_digest phashes[] = { 0x28,0x1e,0x9c,0x59,0x69,0x99,0x4d,0x16, } }, + { 0xa108109, { + 0x85,0xb4,0xbd,0x7c,0x49,0xa7,0xbd,0xfa, + 0x49,0x36,0x80,0x81,0xc5,0xb7,0x39,0x1b, + 0x9a,0xaa,0x50,0xde,0x9b,0xe9,0x32,0x35, + 0x42,0x7e,0x51,0x4f,0x52,0x2c,0x28,0x59, + } + }, { 0xa20102d, { 0xf9,0x6e,0xf2,0x32,0xd3,0x0f,0x5f,0x11, 0x59,0xa1,0xfe,0xcc,0xcd,0x9b,0x42,0x89, @@ -357,6 +399,13 @@ static const struct patch_digest phashes[] = { 0x8c,0xe9,0x19,0x3e,0xcc,0x3f,0x7b,0xb4, } }, + { 0xa20102e, { + 0xbe,0x1f,0x32,0x04,0x0d,0x3c,0x9c,0xdd, + 0xe1,0xa4,0xbf,0x76,0x3a,0xec,0xc2,0xf6, + 0x11,0x00,0xa7,0xaf,0x0f,0xe5,0x02,0xc5, + 0x54,0x3a,0x1f,0x8c,0x16,0xb5,0xff,0xbe, + } + }, { 0xa201210, { 0xe8,0x6d,0x51,0x6a,0x8e,0x72,0xf3,0xfe, 0x6e,0x16,0xbc,0x62,0x59,0x40,0x17,0xe9, @@ -364,6 +413,13 @@ static const struct patch_digest phashes[] = { 0xf7,0x55,0xf0,0x13,0xbb,0x22,0xf6,0x41, } }, + { 0xa201211, { + 0x69,0xa1,0x17,0xec,0xd0,0xf6,0x6c,0x95, + 0xe2,0x1e,0xc5,0x59,0x1a,0x52,0x0a,0x27, + 0xc4,0xed,0xd5,0x59,0x1f,0xbf,0x00,0xff, + 0x08,0x88,0xb5,0xe1,0x12,0xb6,0xcc,0x27, + } + }, { 0xa404107, { 0xbb,0x04,0x4e,0x47,0xdd,0x5e,0x26,0x45, 0x1a,0xc9,0x56,0x24,0xa4,0x4c,0x82,0xb0, @@ -371,6 +427,13 @@ static const struct patch_digest phashes[] = { 0x13,0xbc,0xc5,0x25,0xe4,0xc5,0xc3,0x99, } }, + { 0xa404108, { + 0x69,0x67,0x43,0x06,0xf8,0x0c,0x62,0xdc, + 0xa4,0x21,0x30,0x4f,0x0f,0x21,0x2c,0xcb, + 0xcc,0x37,0xf1,0x1c,0xc3,0xf8,0x2f,0x19, + 0xdf,0x53,0x53,0x46,0xb1,0x15,0xea,0x00, + } + }, { 0xa500011, { 0x23,0x3d,0x70,0x7d,0x03,0xc3,0xc4,0xf4, 0x2b,0x82,0xc6,0x05,0xda,0x80,0x0a,0xf1, @@ -378,6 +441,13 @@ static const struct patch_digest phashes[] = { 0x11,0x5e,0x96,0x7e,0x71,0xe9,0xfc,0x74, } }, + { 0xa500012, { + 0xeb,0x74,0x0d,0x47,0xa1,0x8e,0x09,0xe4, + 0x93,0x4c,0xad,0x03,0x32,0x4c,0x38,0x16, + 0x10,0x39,0xdd,0x06,0xaa,0xce,0xd6,0x0f, + 0x62,0x83,0x9d,0x8e,0x64,0x55,0xbe,0x63, + } + }, { 0xa601209, { 0x66,0x48,0xd4,0x09,0x05,0xcb,0x29,0x32, 0x66,0xb7,0x9a,0x76,0xcd,0x11,0xf3,0x30, @@ -385,6 +455,13 @@ static const struct patch_digest phashes[] = { 0xe8,0x73,0xe2,0xd6,0xdb,0xd2,0x77,0x1d, } }, + { 0xa60120a, { + 0x0c,0x8b,0x3d,0xfd,0x52,0x52,0x85,0x7d, + 0x20,0x3a,0xe1,0x7e,0xa4,0x21,0x3b,0x7b, + 0x17,0x86,0xae,0xac,0x13,0xb8,0x63,0x9d, + 0x06,0x01,0xd0,0xa0,0x51,0x9a,0x91,0x2c, + } + }, { 0xa704107, { 0xf3,0xc6,0x58,0x26,0xee,0xac,0x3f,0xd6, 0xce,0xa1,0x72,0x47,0x3b,0xba,0x2b,0x93, @@ -392,6 +469,13 @@ static const struct patch_digest phashes[] = { 0x64,0x39,0x71,0x8c,0xce,0xe7,0x41,0x39, } }, + { 0xa704108, { + 0xd7,0x55,0x15,0x2b,0xfe,0xc4,0xbc,0x93, + 0xec,0x91,0xa0,0xae,0x45,0xb7,0xc3,0x98, + 0x4e,0xff,0x61,0x77,0x88,0xc2,0x70,0x49, + 0xe0,0x3a,0x1d,0x84,0x38,0x52,0xbf,0x5a, + } + }, { 0xa705206, { 0x8d,0xc0,0x76,0xbd,0x58,0x9f,0x8f,0xa4, 0x12,0x9d,0x21,0xfb,0x48,0x21,0xbc,0xe7, @@ -399,6 +483,13 @@ static const struct patch_digest phashes[] = { 0x03,0x35,0xe9,0xbe,0xfb,0x06,0xdf,0xfc, } }, + { 0xa705208, { + 0x30,0x1d,0x55,0x24,0xbc,0x6b,0x5a,0x19, + 0x0c,0x7d,0x1d,0x74,0xaa,0xd1,0xeb,0xd2, + 0x16,0x62,0xf7,0x5b,0xe1,0x1f,0x18,0x11, + 0x5c,0xf0,0x94,0x90,0x26,0xec,0x69,0xff, + } + }, { 0xa708007, { 0x6b,0x76,0xcc,0x78,0xc5,0x8a,0xa3,0xe3, 0x32,0x2d,0x79,0xe4,0xc3,0x80,0xdb,0xb2, @@ -406,6 +497,13 @@ static const struct patch_digest phashes[] = { 0xdf,0x92,0x73,0x84,0x87,0x3c,0x73,0x93, } }, + { 0xa708008, { + 0x08,0x6e,0xf0,0x22,0x4b,0x8e,0xc4,0x46, + 0x58,0x34,0xe6,0x47,0xa2,0x28,0xfd,0xab, + 0x22,0x3d,0xdd,0xd8,0x52,0x9e,0x1d,0x16, + 0xfa,0x01,0x68,0x14,0x79,0x3e,0xe8,0x6b, + } + }, { 0xa70c005, { 0x88,0x5d,0xfb,0x79,0x64,0xd8,0x46,0x3b, 0x4a,0x83,0x8e,0x77,0x7e,0xcf,0xb3,0x0f, @@ -413,6 +511,13 @@ static const struct patch_digest phashes[] = { 0xee,0x49,0xac,0xe1,0x8b,0x13,0xc5,0x13, } }, + { 0xa70c008, { + 0x0f,0xdb,0x37,0xa1,0x10,0xaf,0xd4,0x21, + 0x94,0x0d,0xa4,0xa2,0xe9,0x86,0x6c,0x0e, + 0x85,0x7c,0x36,0x30,0xa3,0x3a,0x78,0x66, + 0x18,0x10,0x60,0x0d,0x78,0x3d,0x44,0xd0, + } + }, { 0xaa00116, { 0xe8,0x4c,0x2c,0x88,0xa1,0xac,0x24,0x63, 0x65,0xe5,0xaa,0x2d,0x16,0xa9,0xc3,0xf5, @@ -441,4 +546,11 @@ static const struct patch_digest phashes[] = { 0x68,0x2f,0x46,0xee,0xfe,0xc6,0x6d,0xef, } }, + { 0xaa00216, { + 0x79,0xfb,0x5b,0x9f,0xb6,0xe6,0xa8,0xf5, + 0x4e,0x7c,0x4f,0x8e,0x1d,0xad,0xd0,0x08, + 0xc2,0x43,0x7c,0x8b,0xe6,0xdb,0xd0,0xd2, + 0xe8,0x39,0x26,0xc1,0xe5,0x5a,0x48,0xf1, + } + }, }; diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index dbf6d71bdf18..b4a1f6732a3a 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -50,6 +50,8 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, { X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 }, { X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 }, + { X86_FEATURE_TSA_SQ_NO, CPUID_ECX, 1, 0x80000021, 0 }, + { X86_FEATURE_TSA_L1_NO, CPUID_ECX, 2, 0x80000021, 0 }, { X86_FEATURE_AMD_WORKLOAD_CLASS, CPUID_EAX, 22, 0x80000021, 0 }, { X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 }, { X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 }, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 704883c21f3a..a838be04f874 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -907,16 +907,24 @@ static __init bool prefer_mwait_c1_over_halt(void) */ static __cpuidle void mwait_idle(void) { + if (need_resched()) + return; + + x86_idle_clear_cpu_buffers(); + if (!current_set_polling_and_test()) { const void *addr = ¤t_thread_info()->flags; alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr)); __monitor(addr, 0, 0); - if (!need_resched()) { - __sti_mwait(0, 0); - raw_local_irq_disable(); - } + if (need_resched()) + goto out; + + __sti_mwait(0, 0); + raw_local_irq_disable(); } + +out: __current_clr_polling(); } diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 2eeffcec5382..2c86673155c9 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -166,6 +166,16 @@ config KVM_AMD_SEV Encrypted State (SEV-ES), and Secure Encrypted Virtualization with Secure Nested Paging (SEV-SNP) technologies on AMD processors. +config KVM_IOAPIC + bool "I/O APIC, PIC, and PIT emulation" + default y + depends on KVM + help + Provides support for KVM to emulate an I/O APIC, PIC, and PIT, i.e. + for full in-kernel APIC emulation. + + If unsure, say Y. + config KVM_SMM bool "System Management Mode emulation" default y diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index a5d362c7b504..c4b8950c7abe 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -5,12 +5,11 @@ ccflags-$(CONFIG_KVM_WERROR) += -Werror include $(srctree)/virt/kvm/Makefile.kvm -kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ - i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ - debugfs.o mmu/mmu.o mmu/page_track.o \ - mmu/spte.o +kvm-y += x86.o emulate.o irq.o lapic.o cpuid.o pmu.o mtrr.o \ + debugfs.o mmu/mmu.o mmu/page_track.o mmu/spte.o kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o +kvm-$(CONFIG_KVM_IOAPIC) += i8259.o i8254.o ioapic.o kvm-$(CONFIG_KVM_HYPERV) += hyperv.o kvm-$(CONFIG_KVM_XEN) += xen.o kvm-$(CONFIG_KVM_SMM) += smm.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index b2d006756e02..e2836a255b16 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -979,6 +979,7 @@ void kvm_set_cpu_caps(void) F(FSRS), F(FSRC), F(WRMSRNS), + X86_64_F(LKGS), F(AMX_FP16), F(AVX_IFMA), F(LAM), @@ -1165,6 +1166,8 @@ void kvm_set_cpu_caps(void) */ SYNTHESIZED_F(LFENCE_RDTSC), /* SmmPgCfgLock */ + /* 4: Resv */ + SYNTHESIZED_F(VERW_CLEAR), F(NULL_SEL_CLR_BASE), /* UpperAddressIgnore */ F(AUTOIBRS), @@ -1179,6 +1182,11 @@ void kvm_set_cpu_caps(void) F(SRSO_USER_KERNEL_NO), ); + kvm_cpu_cap_init(CPUID_8000_0021_ECX, + SYNTHESIZED_F(TSA_SQ_NO), + SYNTHESIZED_F(TSA_L1_NO), + ); + kvm_cpu_cap_init(CPUID_8000_0022_EAX, F(PERFMON_V2), ); @@ -1748,8 +1756,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; case 0x80000021: - entry->ebx = entry->ecx = entry->edx = 0; + entry->ebx = entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0021_EAX); + cpuid_entry_override(entry, CPUID_8000_0021_ECX); break; /* AMD Extended Performance Monitoring and Debug */ case 0x80000022: { diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 24f0318c50d7..72b19a88a776 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -497,15 +497,19 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint) return ret; } -int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vpidx, u32 sint) +int kvm_hv_synic_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, + int irq_source_id, int level, bool line_status) { struct kvm_vcpu_hv_synic *synic; - synic = synic_get(kvm, vpidx); + if (!level) + return -1; + + synic = synic_get(kvm, e->hv_sint.vcpu); if (!synic) return -EINVAL; - return synic_set_irq(synic, sint); + return synic_set_irq(synic, e->hv_sint.sint); } void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector) @@ -1979,6 +1983,9 @@ 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. @@ -2001,11 +2008,11 @@ out_flush_all: static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + unsigned long *vcpu_mask = hv_vcpu->vcpu_mask; u64 *sparse_banks = hv_vcpu->sparse_banks; struct kvm *kvm = vcpu->kvm; struct hv_tlb_flush_ex flush_ex; struct hv_tlb_flush flush; - DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS); struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo; /* * Normally, there can be no more than 'KVM_HV_TLB_FLUSH_FIFO_SIZE' diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 913bfc96959c..6ce160ffa678 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -103,7 +103,8 @@ static inline bool kvm_hv_hypercall_enabled(struct kvm_vcpu *vcpu) int kvm_hv_hypercall(struct kvm_vcpu *vcpu); void kvm_hv_irq_routing_update(struct kvm *kvm); -int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint); +int kvm_hv_synic_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, + int irq_source_id, int level, bool line_status); void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector); int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages); diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 739aa6c0d0c3..d1b79b418c05 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -248,8 +248,8 @@ static void pit_do_work(struct kthread_work *work) if (atomic_read(&ps->reinject) && !atomic_xchg(&ps->irq_ack, 0)) return; - kvm_set_irq(kvm, pit->irq_source_id, 0, 1, false); - kvm_set_irq(kvm, pit->irq_source_id, 0, 0, false); + kvm_set_irq(kvm, KVM_PIT_IRQ_SOURCE_ID, 0, 1, false); + kvm_set_irq(kvm, KVM_PIT_IRQ_SOURCE_ID, 0, 0, false); /* * Provides NMI watchdog support via Virtual Wire mode. @@ -288,7 +288,7 @@ static inline void kvm_pit_reset_reinject(struct kvm_pit *pit) atomic_set(&pit->pit_state.irq_ack, 1); } -void kvm_pit_set_reinject(struct kvm_pit *pit, bool reinject) +static void kvm_pit_set_reinject(struct kvm_pit *pit, bool reinject) { struct kvm_kpit_state *ps = &pit->pit_state; struct kvm *kvm = pit->kvm; @@ -400,8 +400,8 @@ static void pit_load_count(struct kvm_pit *pit, int channel, u32 val) } } -void kvm_pit_load_count(struct kvm_pit *pit, int channel, u32 val, - int hpet_legacy_start) +static void kvm_pit_load_count(struct kvm_pit *pit, int channel, u32 val, + int hpet_legacy_start) { u8 saved_mode; @@ -649,6 +649,79 @@ static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask) kvm_pit_reset_reinject(pit); } +int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) +{ + struct kvm_kpit_state *kps = &kvm->arch.vpit->pit_state; + + BUILD_BUG_ON(sizeof(*ps) != sizeof(kps->channels)); + + mutex_lock(&kps->lock); + memcpy(ps, &kps->channels, sizeof(*ps)); + mutex_unlock(&kps->lock); + return 0; +} + +int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) +{ + int i; + struct kvm_pit *pit = kvm->arch.vpit; + + mutex_lock(&pit->pit_state.lock); + memcpy(&pit->pit_state.channels, ps, sizeof(*ps)); + for (i = 0; i < 3; i++) + kvm_pit_load_count(pit, i, ps->channels[i].count, 0); + mutex_unlock(&pit->pit_state.lock); + return 0; +} + +int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) +{ + mutex_lock(&kvm->arch.vpit->pit_state.lock); + memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels, + sizeof(ps->channels)); + ps->flags = kvm->arch.vpit->pit_state.flags; + mutex_unlock(&kvm->arch.vpit->pit_state.lock); + memset(&ps->reserved, 0, sizeof(ps->reserved)); + return 0; +} + +int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) +{ + int start = 0; + int i; + u32 prev_legacy, cur_legacy; + struct kvm_pit *pit = kvm->arch.vpit; + + mutex_lock(&pit->pit_state.lock); + prev_legacy = pit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY; + cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY; + if (!prev_legacy && cur_legacy) + start = 1; + memcpy(&pit->pit_state.channels, &ps->channels, + sizeof(pit->pit_state.channels)); + pit->pit_state.flags = ps->flags; + for (i = 0; i < 3; i++) + kvm_pit_load_count(pit, i, pit->pit_state.channels[i].count, + start && i == 0); + mutex_unlock(&pit->pit_state.lock); + return 0; +} + +int kvm_vm_ioctl_reinject(struct kvm *kvm, struct kvm_reinject_control *control) +{ + struct kvm_pit *pit = kvm->arch.vpit; + + /* pit->pit_state.lock was overloaded to prevent userspace from getting + * an inconsistent state after running multiple KVM_REINJECT_CONTROL + * ioctls in parallel. Use a separate lock if that ioctl isn't rare. + */ + mutex_lock(&pit->pit_state.lock); + kvm_pit_set_reinject(pit, control->pit_reinject); + mutex_unlock(&pit->pit_state.lock); + + return 0; +} + static const struct kvm_io_device_ops pit_dev_ops = { .read = pit_ioport_read, .write = pit_ioport_write, @@ -671,10 +744,6 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) if (!pit) return NULL; - pit->irq_source_id = kvm_request_irq_source_id(kvm); - if (pit->irq_source_id < 0) - goto fail_request; - mutex_init(&pit->pit_state.lock); pid = get_pid(task_tgid(current)); @@ -726,8 +795,6 @@ fail_register_pit: kvm_pit_set_reinject(pit, false); kthread_destroy_worker(pit->worker); fail_kthread: - kvm_free_irq_source_id(kvm, pit->irq_source_id); -fail_request: kfree(pit); return NULL; } @@ -744,7 +811,6 @@ void kvm_free_pit(struct kvm *kvm) kvm_pit_set_reinject(pit, false); hrtimer_cancel(&pit->pit_state.timer); kthread_destroy_worker(pit->worker); - kvm_free_irq_source_id(kvm, pit->irq_source_id); kfree(pit); } } diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index a768212ba821..60fa499d2f8a 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -6,6 +6,11 @@ #include <kvm/iodev.h> +#include <uapi/asm/kvm.h> + +#include "ioapic.h" + +#ifdef CONFIG_KVM_IOAPIC struct kvm_kpit_channel_state { u32 count; /* can be 65536 */ u16 latched_count; @@ -42,7 +47,6 @@ struct kvm_pit { struct kvm_io_device speaker_dev; struct kvm *kvm; struct kvm_kpit_state pit_state; - int irq_source_id; struct kvm_irq_mask_notifier mask_notifier; struct kthread_worker *worker; struct kthread_work expired; @@ -55,11 +59,14 @@ struct kvm_pit { #define KVM_MAX_PIT_INTR_INTERVAL HZ / 100 #define KVM_PIT_CHANNEL_MASK 0x3 +int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps); +int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps); +int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps); +int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps); +int kvm_vm_ioctl_reinject(struct kvm *kvm, struct kvm_reinject_control *control); + struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags); void kvm_free_pit(struct kvm *kvm); - -void kvm_pit_load_count(struct kvm_pit *pit, int channel, u32 val, - int hpet_legacy_start); -void kvm_pit_set_reinject(struct kvm_pit *pit, bool reinject); +#endif /* CONFIG_KVM_IOAPIC */ #endif diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index a8fb19940975..2ac7f1678c46 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -31,6 +31,8 @@ #include <linux/mm.h> #include <linux/slab.h> #include <linux/bitops.h> + +#include "ioapic.h" #include "irq.h" #include <linux/kvm_host.h> @@ -185,8 +187,11 @@ void kvm_pic_update_irq(struct kvm_pic *s) pic_unlock(s); } -int kvm_pic_set_irq(struct kvm_pic *s, int irq, int irq_source_id, int level) +int kvm_pic_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, + int irq_source_id, int level, bool line_status) { + struct kvm_pic *s = kvm->arch.vpic; + int irq = e->irqchip.pin; int ret, irq_level; BUG_ON(irq < 0 || irq >= PIC_NUM_PINS); @@ -203,16 +208,6 @@ int kvm_pic_set_irq(struct kvm_pic *s, int irq, int irq_source_id, int level) return ret; } -void kvm_pic_clear_all(struct kvm_pic *s, int irq_source_id) -{ - int i; - - pic_lock(s); - for (i = 0; i < PIC_NUM_PINS; i++) - __clear_bit(irq_source_id, &s->irq_states[i]); - pic_unlock(s); -} - /* * acknowledge interrupt 'irq' */ diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 45dae2d5d2f1..2b5d389bca5f 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -41,11 +41,11 @@ #include <asm/processor.h> #include <asm/page.h> #include <asm/current.h> -#include <trace/events/kvm.h> #include "ioapic.h" #include "lapic.h" #include "irq.h" +#include "trace.h" static int ioapic_service(struct kvm_ioapic *vioapic, int irq, bool line_status); @@ -310,6 +310,42 @@ void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm) kvm_make_scan_ioapic_request(kvm); } +void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq, + struct kvm_irq_mask_notifier *kimn) +{ + struct kvm_ioapic *ioapic = kvm->arch.vioapic; + + mutex_lock(&kvm->irq_lock); + kimn->irq = irq; + hlist_add_head_rcu(&kimn->link, &ioapic->mask_notifier_list); + mutex_unlock(&kvm->irq_lock); +} + +void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, + struct kvm_irq_mask_notifier *kimn) +{ + mutex_lock(&kvm->irq_lock); + hlist_del_rcu(&kimn->link); + mutex_unlock(&kvm->irq_lock); + synchronize_srcu(&kvm->irq_srcu); +} + +void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, + bool mask) +{ + struct kvm_ioapic *ioapic = kvm->arch.vioapic; + struct kvm_irq_mask_notifier *kimn; + int idx, gsi; + + 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) + if (kimn->irq == gsi) + kimn->func(kimn, mask); + srcu_read_unlock(&kvm->irq_srcu, idx); +} + static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) { unsigned index; @@ -479,9 +515,11 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status) return ret; } -int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id, - int level, bool line_status) +int kvm_ioapic_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, + int irq_source_id, int level, bool line_status) { + struct kvm_ioapic *ioapic = kvm->arch.vioapic; + int irq = e->irqchip.pin; int ret, irq_level; BUG_ON(irq < 0 || irq >= IOAPIC_NUM_PINS); @@ -496,16 +534,6 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id, return ret; } -void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id) -{ - int i; - - spin_lock(&ioapic->lock); - for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) - __clear_bit(irq_source_id, &ioapic->irq_states[i]); - spin_unlock(&ioapic->lock); -} - static void kvm_ioapic_eoi_inject_work(struct work_struct *work) { int i; @@ -718,6 +746,7 @@ int kvm_ioapic_init(struct kvm *kvm) return -ENOMEM; spin_lock_init(&ioapic->lock); INIT_DELAYED_WORK(&ioapic->eoi_inject, kvm_ioapic_eoi_inject_work); + INIT_HLIST_HEAD(&ioapic->mask_notifier_list); kvm->arch.vioapic = ioapic; kvm_ioapic_reset(ioapic); kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index aa8cb4ac0479..bf28dbc11ff6 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -86,8 +86,24 @@ struct kvm_ioapic { struct delayed_work eoi_inject; u32 irq_eoi[IOAPIC_NUM_PINS]; u32 irr_delivered; + + /* reads protected by irq_srcu, writes by irq_lock */ + struct hlist_head mask_notifier_list; +}; + +struct kvm_irq_mask_notifier { + void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked); + int irq; + struct hlist_node link; }; +void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq, + struct kvm_irq_mask_notifier *kimn); +void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, + struct kvm_irq_mask_notifier *kimn); +void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, + bool mask); + #ifdef DEBUG #define ASSERT(x) \ do { \ @@ -103,7 +119,7 @@ do { \ static inline int ioapic_in_kernel(struct kvm *kvm) { - return irqchip_kernel(kvm); + return irqchip_full(kvm); } void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu); @@ -111,9 +127,9 @@ void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode); int kvm_ioapic_init(struct kvm *kvm); void kvm_ioapic_destroy(struct kvm *kvm); -int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id, - int level, bool line_status); -void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id); +int kvm_ioapic_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, + int irq_source_id, int level, bool line_status); + void kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); void kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 97d68d837929..16da89259011 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -11,9 +11,12 @@ #include <linux/export.h> #include <linux/kvm_host.h> +#include <linux/kvm_irqfd.h> +#include "hyperv.h" +#include "ioapic.h" #include "irq.h" -#include "i8254.h" +#include "trace.h" #include "x86.h" #include "xen.h" @@ -41,6 +44,14 @@ static int pending_userspace_extint(struct kvm_vcpu *v) return v->arch.pending_external_vector != -1; } +static int get_userspace_extint(struct kvm_vcpu *vcpu) +{ + int vector = vcpu->arch.pending_external_vector; + + vcpu->arch.pending_external_vector = -1; + return vector; +} + /* * check if there is pending interrupt from * non-APIC source without intack. @@ -67,10 +78,13 @@ int kvm_cpu_has_extint(struct kvm_vcpu *v) if (!kvm_apic_accept_pic_intr(v)) return 0; - if (irqchip_split(v->kvm)) - return pending_userspace_extint(v); - else +#ifdef CONFIG_KVM_IOAPIC + if (pic_in_kernel(v->kvm)) return v->kvm->arch.vpic->output; +#endif + + WARN_ON_ONCE(!irqchip_split(v->kvm)); + return pending_userspace_extint(v); } /* @@ -126,13 +140,13 @@ int kvm_cpu_get_extint(struct kvm_vcpu *v) return v->kvm->arch.xen.upcall_vector; #endif - if (irqchip_split(v->kvm)) { - int vector = v->arch.pending_external_vector; - - v->arch.pending_external_vector = -1; - return vector; - } else +#ifdef CONFIG_KVM_IOAPIC + if (pic_in_kernel(v->kvm)) return kvm_pic_read_irq(v->kvm); /* PIC */ +#endif + + WARN_ON_ONCE(!irqchip_split(v->kvm)); + return get_userspace_extint(v); } EXPORT_SYMBOL_GPL(kvm_cpu_get_extint); @@ -163,7 +177,9 @@ void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu) void __kvm_migrate_timers(struct kvm_vcpu *vcpu) { __kvm_migrate_apic_timer(vcpu); +#ifdef CONFIG_KVM_IOAPIC __kvm_migrate_pit_timer(vcpu); +#endif kvm_x86_call(migrate_timers)(vcpu); } @@ -171,10 +187,532 @@ bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args) { bool resample = args->flags & KVM_IRQFD_FLAG_RESAMPLE; - return resample ? irqchip_kernel(kvm) : irqchip_in_kernel(kvm); + return resample ? irqchip_full(kvm) : irqchip_in_kernel(kvm); } bool kvm_arch_irqchip_in_kernel(struct kvm *kvm) { return irqchip_in_kernel(kvm); } + +int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, + struct kvm_lapic_irq *irq, struct dest_map *dest_map) +{ + int r = -1; + struct kvm_vcpu *vcpu, *lowest = NULL; + unsigned long i, dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]; + unsigned int dest_vcpus = 0; + + if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map)) + return r; + + if (irq->dest_mode == APIC_DEST_PHYSICAL && + irq->dest_id == 0xff && kvm_lowest_prio_delivery(irq)) { + pr_info("apic: phys broadcast and lowest prio\n"); + irq->delivery_mode = APIC_DM_FIXED; + } + + memset(dest_vcpu_bitmap, 0, sizeof(dest_vcpu_bitmap)); + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!kvm_apic_present(vcpu)) + continue; + + if (!kvm_apic_match_dest(vcpu, src, irq->shorthand, + irq->dest_id, irq->dest_mode)) + continue; + + if (!kvm_lowest_prio_delivery(irq)) { + if (r < 0) + r = 0; + r += kvm_apic_set_irq(vcpu, irq, dest_map); + } else if (kvm_apic_sw_enabled(vcpu->arch.apic)) { + if (!kvm_vector_hashing_enabled()) { + if (!lowest) + lowest = vcpu; + else if (kvm_apic_compare_prio(vcpu, lowest) < 0) + lowest = vcpu; + } else { + __set_bit(i, dest_vcpu_bitmap); + dest_vcpus++; + } + } + } + + if (dest_vcpus != 0) { + int idx = kvm_vector_to_index(irq->vector, dest_vcpus, + dest_vcpu_bitmap, KVM_MAX_VCPUS); + + lowest = kvm_get_vcpu(kvm, idx); + } + + if (lowest) + r = kvm_apic_set_irq(lowest, irq, dest_map); + + return r; +} + +static void kvm_msi_to_lapic_irq(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *e, + struct kvm_lapic_irq *irq) +{ + struct msi_msg msg = { .address_lo = e->msi.address_lo, + .address_hi = e->msi.address_hi, + .data = e->msi.data }; + + trace_kvm_msi_set_irq(msg.address_lo | (kvm->arch.x2apic_format ? + (u64)msg.address_hi << 32 : 0), msg.data); + + irq->dest_id = x86_msi_msg_get_destid(&msg, kvm->arch.x2apic_format); + irq->vector = msg.arch_data.vector; + irq->dest_mode = kvm_lapic_irq_dest_mode(msg.arch_addr_lo.dest_mode_logical); + irq->trig_mode = msg.arch_data.is_level; + irq->delivery_mode = msg.arch_data.delivery_mode << 8; + irq->msi_redir_hint = msg.arch_addr_lo.redirect_hint; + irq->level = 1; + irq->shorthand = APIC_DEST_NOSHORT; +} + +static inline bool kvm_msi_route_invalid(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *e) +{ + return kvm->arch.x2apic_format && (e->msi.address_hi & 0xff); +} + +int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, int level, bool line_status) +{ + struct kvm_lapic_irq irq; + + if (kvm_msi_route_invalid(kvm, e)) + return -EINVAL; + + if (!level) + return -1; + + kvm_msi_to_lapic_irq(kvm, e, &irq); + + return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL); +} + +int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, int level, + bool line_status) +{ + struct kvm_lapic_irq irq; + int r; + + switch (e->type) { +#ifdef CONFIG_KVM_HYPERV + case KVM_IRQ_ROUTING_HV_SINT: + return kvm_hv_synic_set_irq(e, kvm, irq_source_id, level, + line_status); +#endif + + case KVM_IRQ_ROUTING_MSI: + if (kvm_msi_route_invalid(kvm, e)) + return -EINVAL; + + kvm_msi_to_lapic_irq(kvm, e, &irq); + + if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL)) + return r; + break; + +#ifdef CONFIG_KVM_XEN + case KVM_IRQ_ROUTING_XEN_EVTCHN: + if (!level) + return -1; + + return kvm_xen_set_evtchn_fast(&e->xen_evtchn, kvm); +#endif + default: + break; + } + + return -EWOULDBLOCK; +} + +int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, + bool line_status) +{ + if (!irqchip_in_kernel(kvm)) + return -ENXIO; + + irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, + irq_event->irq, irq_event->level, + line_status); + return 0; +} + +bool kvm_arch_can_set_irq_routing(struct kvm *kvm) +{ + return irqchip_in_kernel(kvm); +} + +int kvm_set_routing_entry(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue) +{ + /* We can't check irqchip_in_kernel() here as some callers are + * currently initializing the irqchip. Other callers should therefore + * check kvm_arch_can_set_irq_routing() before calling this function. + */ + switch (ue->type) { +#ifdef CONFIG_KVM_IOAPIC + case KVM_IRQ_ROUTING_IRQCHIP: + if (irqchip_split(kvm)) + return -EINVAL; + e->irqchip.pin = ue->u.irqchip.pin; + switch (ue->u.irqchip.irqchip) { + case KVM_IRQCHIP_PIC_SLAVE: + e->irqchip.pin += PIC_NUM_PINS / 2; + fallthrough; + case KVM_IRQCHIP_PIC_MASTER: + if (ue->u.irqchip.pin >= PIC_NUM_PINS / 2) + return -EINVAL; + e->set = kvm_pic_set_irq; + break; + case KVM_IRQCHIP_IOAPIC: + if (ue->u.irqchip.pin >= KVM_IOAPIC_NUM_PINS) + return -EINVAL; + e->set = kvm_ioapic_set_irq; + break; + default: + return -EINVAL; + } + e->irqchip.irqchip = ue->u.irqchip.irqchip; + break; +#endif + case KVM_IRQ_ROUTING_MSI: + e->set = kvm_set_msi; + e->msi.address_lo = ue->u.msi.address_lo; + e->msi.address_hi = ue->u.msi.address_hi; + e->msi.data = ue->u.msi.data; + + if (kvm_msi_route_invalid(kvm, e)) + return -EINVAL; + break; +#ifdef CONFIG_KVM_HYPERV + case KVM_IRQ_ROUTING_HV_SINT: + e->set = kvm_hv_synic_set_irq; + e->hv_sint.vcpu = ue->u.hv_sint.vcpu; + e->hv_sint.sint = ue->u.hv_sint.sint; + break; +#endif +#ifdef CONFIG_KVM_XEN + case KVM_IRQ_ROUTING_XEN_EVTCHN: + return kvm_xen_setup_evtchn(kvm, e, ue); +#endif + default: + return -EINVAL; + } + + return 0; +} + +bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, + struct kvm_vcpu **dest_vcpu) +{ + int r = 0; + unsigned long i; + struct kvm_vcpu *vcpu; + + if (kvm_intr_is_single_vcpu_fast(kvm, irq, dest_vcpu)) + return true; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!kvm_apic_present(vcpu)) + continue; + + if (!kvm_apic_match_dest(vcpu, NULL, irq->shorthand, + irq->dest_id, irq->dest_mode)) + continue; + + if (++r == 2) + return false; + + *dest_vcpu = vcpu; + } + + return r == 1; +} +EXPORT_SYMBOL_GPL(kvm_intr_is_single_vcpu); + +void kvm_scan_ioapic_irq(struct kvm_vcpu *vcpu, u32 dest_id, u16 dest_mode, + u8 vector, unsigned long *ioapic_handled_vectors) +{ + /* + * Intercept EOI if the vCPU is the target of the new IRQ routing, or + * the vCPU has a pending IRQ from the old routing, i.e. if the vCPU + * may receive a level-triggered IRQ in the future, or already received + * level-triggered IRQ. The EOI needs to be intercepted and forwarded + * to I/O APIC emulation so that the IRQ can be de-asserted. + */ + if (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, dest_id, dest_mode)) { + __set_bit(vector, ioapic_handled_vectors); + } else if (kvm_apic_pending_eoi(vcpu, vector)) { + __set_bit(vector, ioapic_handled_vectors); + + /* + * Track the highest pending EOI for which the vCPU is NOT the + * target in the new routing. Only the EOI for the IRQ that is + * in-flight (for the old routing) needs to be intercepted, any + * future IRQs that arrive on this vCPU will be coincidental to + * the level-triggered routing and don't need to be intercepted. + */ + if ((int)vector > vcpu->arch.highest_stale_pending_ioapic_eoi) + vcpu->arch.highest_stale_pending_ioapic_eoi = vector; + } +} + +void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, + ulong *ioapic_handled_vectors) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_kernel_irq_routing_entry *entry; + struct kvm_irq_routing_table *table; + u32 i, nr_ioapic_pins; + int idx; + + idx = srcu_read_lock(&kvm->irq_srcu); + table = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); + nr_ioapic_pins = min_t(u32, table->nr_rt_entries, + kvm->arch.nr_reserved_ioapic_pins); + for (i = 0; i < nr_ioapic_pins; ++i) { + hlist_for_each_entry(entry, &table->map[i], link) { + struct kvm_lapic_irq irq; + + if (entry->type != KVM_IRQ_ROUTING_MSI) + continue; + + kvm_msi_to_lapic_irq(vcpu->kvm, entry, &irq); + + if (!irq.trig_mode) + continue; + + kvm_scan_ioapic_irq(vcpu, irq.dest_id, irq.dest_mode, + irq.vector, ioapic_handled_vectors); + } + } + srcu_read_unlock(&kvm->irq_srcu, idx); +} + +void kvm_arch_irq_routing_update(struct kvm *kvm) +{ +#ifdef CONFIG_KVM_HYPERV + kvm_hv_irq_routing_update(kvm); +#endif + + if (irqchip_split(kvm)) + kvm_make_scan_ioapic_request(kvm); +} + +static int kvm_pi_update_irte(struct kvm_kernel_irqfd *irqfd, + struct kvm_kernel_irq_routing_entry *entry) +{ + unsigned int host_irq = irqfd->producer->irq; + struct kvm *kvm = irqfd->kvm; + struct kvm_vcpu *vcpu = NULL; + struct kvm_lapic_irq irq; + int r; + + if (WARN_ON_ONCE(!irqchip_in_kernel(kvm) || !kvm_arch_has_irq_bypass())) + return -EINVAL; + + if (entry && entry->type == KVM_IRQ_ROUTING_MSI) { + kvm_msi_to_lapic_irq(kvm, entry, &irq); + + /* + * Force remapped mode if hardware doesn't support posting the + * virtual interrupt to a vCPU. Only IRQs are postable (NMIs, + * SMIs, etc. are not), and neither AMD nor Intel IOMMUs support + * posting multicast/broadcast IRQs. If the interrupt can't be + * posted, the device MSI needs to be routed to the host so that + * the guest's desired interrupt can be synthesized by KVM. + * + * This means that KVM can only post lowest-priority interrupts + * if they have a single CPU as the destination, e.g. only if + * the guest has affined the interrupt to a single vCPU. + */ + if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) || + !kvm_irq_is_postable(&irq)) + vcpu = NULL; + } + + if (!irqfd->irq_bypass_vcpu && !vcpu) + return 0; + + r = kvm_x86_call(pi_update_irte)(irqfd, irqfd->kvm, host_irq, irqfd->gsi, + vcpu, irq.vector); + if (r) { + WARN_ON_ONCE(irqfd->irq_bypass_vcpu && !vcpu); + irqfd->irq_bypass_vcpu = NULL; + return r; + } + + irqfd->irq_bypass_vcpu = vcpu; + + trace_kvm_pi_irte_update(host_irq, vcpu, irqfd->gsi, irq.vector, !!vcpu); + return 0; +} + +int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, + struct irq_bypass_producer *prod) +{ + struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + struct kvm *kvm = irqfd->kvm; + int ret = 0; + + spin_lock_irq(&kvm->irqfds.lock); + irqfd->producer = prod; + + if (!kvm->arch.nr_possible_bypass_irqs++) + kvm_x86_call(pi_start_bypass)(kvm); + + if (irqfd->irq_entry.type == KVM_IRQ_ROUTING_MSI) { + ret = kvm_pi_update_irte(irqfd, &irqfd->irq_entry); + if (ret) + kvm->arch.nr_possible_bypass_irqs--; + } + spin_unlock_irq(&kvm->irqfds.lock); + + return ret; +} + +void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, + struct irq_bypass_producer *prod) +{ + struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + struct kvm *kvm = irqfd->kvm; + int ret; + + WARN_ON(irqfd->producer != prod); + + /* + * If the producer of an IRQ that is currently being posted to a vCPU + * is unregistered, change the associated IRTE back to remapped mode as + * the IRQ has been released (or repurposed) by the device driver, i.e. + * KVM must relinquish control of the IRTE. + */ + spin_lock_irq(&kvm->irqfds.lock); + + if (irqfd->irq_entry.type == KVM_IRQ_ROUTING_MSI) { + ret = kvm_pi_update_irte(irqfd, NULL); + if (ret) + pr_info("irq bypass consumer (eventfd %p) unregistration fails: %d\n", + irqfd->consumer.eventfd, ret); + } + irqfd->producer = NULL; + + kvm->arch.nr_possible_bypass_irqs--; + + spin_unlock_irq(&kvm->irqfds.lock); +} + +void kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd, + struct kvm_kernel_irq_routing_entry *old, + struct kvm_kernel_irq_routing_entry *new) +{ + if (new->type != KVM_IRQ_ROUTING_MSI && + old->type != KVM_IRQ_ROUTING_MSI) + return; + + if (old->type == KVM_IRQ_ROUTING_MSI && + new->type == KVM_IRQ_ROUTING_MSI && + !memcmp(&old->msi, &new->msi, sizeof(new->msi))) + return; + + kvm_pi_update_irte(irqfd, new); +} + +#ifdef CONFIG_KVM_IOAPIC +#define IOAPIC_ROUTING_ENTRY(irq) \ + { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \ + .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } } +#define ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq) + +#define PIC_ROUTING_ENTRY(irq) \ + { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \ + .u.irqchip = { .irqchip = SELECT_PIC(irq), .pin = (irq) % 8 } } +#define ROUTING_ENTRY2(irq) \ + IOAPIC_ROUTING_ENTRY(irq), PIC_ROUTING_ENTRY(irq) + +static const struct kvm_irq_routing_entry default_routing[] = { + ROUTING_ENTRY2(0), ROUTING_ENTRY2(1), + ROUTING_ENTRY2(2), ROUTING_ENTRY2(3), + ROUTING_ENTRY2(4), ROUTING_ENTRY2(5), + ROUTING_ENTRY2(6), ROUTING_ENTRY2(7), + ROUTING_ENTRY2(8), ROUTING_ENTRY2(9), + ROUTING_ENTRY2(10), ROUTING_ENTRY2(11), + ROUTING_ENTRY2(12), ROUTING_ENTRY2(13), + ROUTING_ENTRY2(14), ROUTING_ENTRY2(15), + ROUTING_ENTRY1(16), ROUTING_ENTRY1(17), + ROUTING_ENTRY1(18), ROUTING_ENTRY1(19), + ROUTING_ENTRY1(20), ROUTING_ENTRY1(21), + ROUTING_ENTRY1(22), ROUTING_ENTRY1(23), +}; + +int kvm_setup_default_ioapic_and_pic_routing(struct kvm *kvm) +{ + return kvm_set_irq_routing(kvm, default_routing, + ARRAY_SIZE(default_routing), 0); +} + +int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) +{ + struct kvm_pic *pic = kvm->arch.vpic; + int r; + + r = 0; + switch (chip->chip_id) { + case KVM_IRQCHIP_PIC_MASTER: + memcpy(&chip->chip.pic, &pic->pics[0], + sizeof(struct kvm_pic_state)); + break; + case KVM_IRQCHIP_PIC_SLAVE: + memcpy(&chip->chip.pic, &pic->pics[1], + sizeof(struct kvm_pic_state)); + break; + case KVM_IRQCHIP_IOAPIC: + kvm_get_ioapic(kvm, &chip->chip.ioapic); + break; + default: + r = -EINVAL; + break; + } + return r; +} + +int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) +{ + struct kvm_pic *pic = kvm->arch.vpic; + int r; + + r = 0; + switch (chip->chip_id) { + case KVM_IRQCHIP_PIC_MASTER: + spin_lock(&pic->lock); + memcpy(&pic->pics[0], &chip->chip.pic, + sizeof(struct kvm_pic_state)); + spin_unlock(&pic->lock); + break; + case KVM_IRQCHIP_PIC_SLAVE: + spin_lock(&pic->lock); + memcpy(&pic->pics[1], &chip->chip.pic, + sizeof(struct kvm_pic_state)); + spin_unlock(&pic->lock); + break; + case KVM_IRQCHIP_IOAPIC: + kvm_set_ioapic(kvm, &chip->chip.ioapic); + break; + default: + r = -EINVAL; + break; + } + kvm_pic_update_irq(pic); + return r; +} +#endif diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 76d46b2f41dd..5e62c1f79ce6 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -18,6 +18,8 @@ #include <kvm/iodev.h> #include "lapic.h" +#ifdef CONFIG_KVM_IOAPIC + #define PIC_NUM_PINS 16 #define SELECT_PIC(irq) \ ((irq) < 8 ? KVM_IRQCHIP_PIC_MASTER : KVM_IRQCHIP_PIC_SLAVE) @@ -63,17 +65,15 @@ int kvm_pic_init(struct kvm *kvm); void kvm_pic_destroy(struct kvm *kvm); int kvm_pic_read_irq(struct kvm *kvm); void kvm_pic_update_irq(struct kvm_pic *s); +int kvm_pic_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, + int irq_source_id, int level, bool line_status); -static inline int irqchip_split(struct kvm *kvm) -{ - int mode = kvm->arch.irqchip_mode; +int kvm_setup_default_ioapic_and_pic_routing(struct kvm *kvm); - /* Matches smp_wmb() when setting irqchip_mode */ - smp_rmb(); - return mode == KVM_IRQCHIP_SPLIT; -} +int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip); +int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip); -static inline int irqchip_kernel(struct kvm *kvm) +static inline int irqchip_full(struct kvm *kvm) { int mode = kvm->arch.irqchip_mode; @@ -81,10 +81,26 @@ static inline int irqchip_kernel(struct kvm *kvm) smp_rmb(); return mode == KVM_IRQCHIP_KERNEL; } +#else /* CONFIG_KVM_IOAPIC */ +static __always_inline int irqchip_full(struct kvm *kvm) +{ + return false; +} +#endif static inline int pic_in_kernel(struct kvm *kvm) { - return irqchip_kernel(kvm); + return irqchip_full(kvm); +} + + +static inline int irqchip_split(struct kvm *kvm) +{ + int mode = kvm->arch.irqchip_mode; + + /* Matches smp_wmb() when setting irqchip_mode */ + smp_rmb(); + return mode == KVM_IRQCHIP_SPLIT; } static inline int irqchip_in_kernel(struct kvm *kvm) @@ -105,7 +121,6 @@ void __kvm_migrate_timers(struct kvm_vcpu *vcpu); int apic_has_pending_timer(struct kvm_vcpu *vcpu); -int kvm_setup_default_irq_routing(struct kvm *kvm); int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, struct dest_map *dest_map); diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c deleted file mode 100644 index d6d792b5d1bd..000000000000 --- a/arch/x86/kvm/irq_comm.c +++ /dev/null @@ -1,469 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * irq_comm.c: Common API for in kernel interrupt controller - * Copyright (c) 2007, Intel Corporation. - * - * Authors: - * Yaozu (Eddie) Dong <Eddie.dong@intel.com> - * - * Copyright 2010 Red Hat, Inc. and/or its affiliates. - */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/kvm_host.h> -#include <linux/slab.h> -#include <linux/export.h> -#include <linux/rculist.h> - -#include <trace/events/kvm.h> - -#include "irq.h" - -#include "ioapic.h" - -#include "lapic.h" - -#include "hyperv.h" -#include "x86.h" -#include "xen.h" - -static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, int level, - bool line_status) -{ - struct kvm_pic *pic = kvm->arch.vpic; - return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level); -} - -static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, int level, - bool line_status) -{ - struct kvm_ioapic *ioapic = kvm->arch.vioapic; - return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level, - line_status); -} - -int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, - struct kvm_lapic_irq *irq, struct dest_map *dest_map) -{ - int r = -1; - struct kvm_vcpu *vcpu, *lowest = NULL; - unsigned long i, dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]; - unsigned int dest_vcpus = 0; - - if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map)) - return r; - - if (irq->dest_mode == APIC_DEST_PHYSICAL && - irq->dest_id == 0xff && kvm_lowest_prio_delivery(irq)) { - pr_info("apic: phys broadcast and lowest prio\n"); - irq->delivery_mode = APIC_DM_FIXED; - } - - memset(dest_vcpu_bitmap, 0, sizeof(dest_vcpu_bitmap)); - - kvm_for_each_vcpu(i, vcpu, kvm) { - if (!kvm_apic_present(vcpu)) - continue; - - if (!kvm_apic_match_dest(vcpu, src, irq->shorthand, - irq->dest_id, irq->dest_mode)) - continue; - - if (!kvm_lowest_prio_delivery(irq)) { - if (r < 0) - r = 0; - r += kvm_apic_set_irq(vcpu, irq, dest_map); - } else if (kvm_apic_sw_enabled(vcpu->arch.apic)) { - if (!kvm_vector_hashing_enabled()) { - if (!lowest) - lowest = vcpu; - else if (kvm_apic_compare_prio(vcpu, lowest) < 0) - lowest = vcpu; - } else { - __set_bit(i, dest_vcpu_bitmap); - dest_vcpus++; - } - } - } - - if (dest_vcpus != 0) { - int idx = kvm_vector_to_index(irq->vector, dest_vcpus, - dest_vcpu_bitmap, KVM_MAX_VCPUS); - - lowest = kvm_get_vcpu(kvm, idx); - } - - if (lowest) - r = kvm_apic_set_irq(lowest, irq, dest_map); - - return r; -} - -void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, - struct kvm_lapic_irq *irq) -{ - struct msi_msg msg = { .address_lo = e->msi.address_lo, - .address_hi = e->msi.address_hi, - .data = e->msi.data }; - - trace_kvm_msi_set_irq(msg.address_lo | (kvm->arch.x2apic_format ? - (u64)msg.address_hi << 32 : 0), msg.data); - - irq->dest_id = x86_msi_msg_get_destid(&msg, kvm->arch.x2apic_format); - irq->vector = msg.arch_data.vector; - irq->dest_mode = kvm_lapic_irq_dest_mode(msg.arch_addr_lo.dest_mode_logical); - irq->trig_mode = msg.arch_data.is_level; - irq->delivery_mode = msg.arch_data.delivery_mode << 8; - irq->msi_redir_hint = msg.arch_addr_lo.redirect_hint; - irq->level = 1; - irq->shorthand = APIC_DEST_NOSHORT; -} -EXPORT_SYMBOL_GPL(kvm_set_msi_irq); - -static inline bool kvm_msi_route_invalid(struct kvm *kvm, - struct kvm_kernel_irq_routing_entry *e) -{ - return kvm->arch.x2apic_format && (e->msi.address_hi & 0xff); -} - -int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, int level, bool line_status) -{ - struct kvm_lapic_irq irq; - - if (kvm_msi_route_invalid(kvm, e)) - return -EINVAL; - - if (!level) - return -1; - - kvm_set_msi_irq(kvm, e, &irq); - - return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL); -} - -#ifdef CONFIG_KVM_HYPERV -static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, int level, - bool line_status) -{ - if (!level) - return -1; - - return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint); -} -#endif - -int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, int level, - bool line_status) -{ - struct kvm_lapic_irq irq; - int r; - - switch (e->type) { -#ifdef CONFIG_KVM_HYPERV - case KVM_IRQ_ROUTING_HV_SINT: - return kvm_hv_set_sint(e, kvm, irq_source_id, level, - line_status); -#endif - - case KVM_IRQ_ROUTING_MSI: - if (kvm_msi_route_invalid(kvm, e)) - return -EINVAL; - - kvm_set_msi_irq(kvm, e, &irq); - - if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL)) - return r; - break; - -#ifdef CONFIG_KVM_XEN - case KVM_IRQ_ROUTING_XEN_EVTCHN: - if (!level) - return -1; - - return kvm_xen_set_evtchn_fast(&e->xen_evtchn, kvm); -#endif - default: - break; - } - - return -EWOULDBLOCK; -} - -int kvm_request_irq_source_id(struct kvm *kvm) -{ - unsigned long *bitmap = &kvm->arch.irq_sources_bitmap; - int irq_source_id; - - mutex_lock(&kvm->irq_lock); - irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG); - - if (irq_source_id >= BITS_PER_LONG) { - pr_warn("exhausted allocatable IRQ sources!\n"); - irq_source_id = -EFAULT; - goto unlock; - } - - ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID); - ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID); - set_bit(irq_source_id, bitmap); -unlock: - mutex_unlock(&kvm->irq_lock); - - return irq_source_id; -} - -void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) -{ - ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID); - ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID); - - mutex_lock(&kvm->irq_lock); - if (irq_source_id < 0 || - irq_source_id >= BITS_PER_LONG) { - pr_err("IRQ source ID out of range!\n"); - goto unlock; - } - clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); - if (!irqchip_kernel(kvm)) - goto unlock; - - kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id); - kvm_pic_clear_all(kvm->arch.vpic, irq_source_id); -unlock: - mutex_unlock(&kvm->irq_lock); -} - -void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq, - struct kvm_irq_mask_notifier *kimn) -{ - mutex_lock(&kvm->irq_lock); - kimn->irq = irq; - hlist_add_head_rcu(&kimn->link, &kvm->arch.mask_notifier_list); - mutex_unlock(&kvm->irq_lock); -} - -void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, - struct kvm_irq_mask_notifier *kimn) -{ - mutex_lock(&kvm->irq_lock); - hlist_del_rcu(&kimn->link); - mutex_unlock(&kvm->irq_lock); - synchronize_srcu(&kvm->irq_srcu); -} - -void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, - bool mask) -{ - struct kvm_irq_mask_notifier *kimn; - int idx, gsi; - - 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, &kvm->arch.mask_notifier_list, link) - if (kimn->irq == gsi) - kimn->func(kimn, mask); - srcu_read_unlock(&kvm->irq_srcu, idx); -} - -bool kvm_arch_can_set_irq_routing(struct kvm *kvm) -{ - return irqchip_in_kernel(kvm); -} - -int kvm_set_routing_entry(struct kvm *kvm, - struct kvm_kernel_irq_routing_entry *e, - const struct kvm_irq_routing_entry *ue) -{ - /* We can't check irqchip_in_kernel() here as some callers are - * currently initializing the irqchip. Other callers should therefore - * check kvm_arch_can_set_irq_routing() before calling this function. - */ - switch (ue->type) { - case KVM_IRQ_ROUTING_IRQCHIP: - if (irqchip_split(kvm)) - return -EINVAL; - e->irqchip.pin = ue->u.irqchip.pin; - switch (ue->u.irqchip.irqchip) { - case KVM_IRQCHIP_PIC_SLAVE: - e->irqchip.pin += PIC_NUM_PINS / 2; - fallthrough; - case KVM_IRQCHIP_PIC_MASTER: - if (ue->u.irqchip.pin >= PIC_NUM_PINS / 2) - return -EINVAL; - e->set = kvm_set_pic_irq; - break; - case KVM_IRQCHIP_IOAPIC: - if (ue->u.irqchip.pin >= KVM_IOAPIC_NUM_PINS) - return -EINVAL; - e->set = kvm_set_ioapic_irq; - break; - default: - return -EINVAL; - } - e->irqchip.irqchip = ue->u.irqchip.irqchip; - break; - case KVM_IRQ_ROUTING_MSI: - e->set = kvm_set_msi; - e->msi.address_lo = ue->u.msi.address_lo; - e->msi.address_hi = ue->u.msi.address_hi; - e->msi.data = ue->u.msi.data; - - if (kvm_msi_route_invalid(kvm, e)) - return -EINVAL; - break; -#ifdef CONFIG_KVM_HYPERV - case KVM_IRQ_ROUTING_HV_SINT: - e->set = kvm_hv_set_sint; - e->hv_sint.vcpu = ue->u.hv_sint.vcpu; - e->hv_sint.sint = ue->u.hv_sint.sint; - break; -#endif -#ifdef CONFIG_KVM_XEN - case KVM_IRQ_ROUTING_XEN_EVTCHN: - return kvm_xen_setup_evtchn(kvm, e, ue); -#endif - default: - return -EINVAL; - } - - return 0; -} - -bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, - struct kvm_vcpu **dest_vcpu) -{ - int r = 0; - unsigned long i; - struct kvm_vcpu *vcpu; - - if (kvm_intr_is_single_vcpu_fast(kvm, irq, dest_vcpu)) - return true; - - kvm_for_each_vcpu(i, vcpu, kvm) { - if (!kvm_apic_present(vcpu)) - continue; - - if (!kvm_apic_match_dest(vcpu, NULL, irq->shorthand, - irq->dest_id, irq->dest_mode)) - continue; - - if (++r == 2) - return false; - - *dest_vcpu = vcpu; - } - - return r == 1; -} -EXPORT_SYMBOL_GPL(kvm_intr_is_single_vcpu); - -#define IOAPIC_ROUTING_ENTRY(irq) \ - { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \ - .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } } -#define ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq) - -#define PIC_ROUTING_ENTRY(irq) \ - { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \ - .u.irqchip = { .irqchip = SELECT_PIC(irq), .pin = (irq) % 8 } } -#define ROUTING_ENTRY2(irq) \ - IOAPIC_ROUTING_ENTRY(irq), PIC_ROUTING_ENTRY(irq) - -static const struct kvm_irq_routing_entry default_routing[] = { - ROUTING_ENTRY2(0), ROUTING_ENTRY2(1), - ROUTING_ENTRY2(2), ROUTING_ENTRY2(3), - ROUTING_ENTRY2(4), ROUTING_ENTRY2(5), - ROUTING_ENTRY2(6), ROUTING_ENTRY2(7), - ROUTING_ENTRY2(8), ROUTING_ENTRY2(9), - ROUTING_ENTRY2(10), ROUTING_ENTRY2(11), - ROUTING_ENTRY2(12), ROUTING_ENTRY2(13), - ROUTING_ENTRY2(14), ROUTING_ENTRY2(15), - ROUTING_ENTRY1(16), ROUTING_ENTRY1(17), - ROUTING_ENTRY1(18), ROUTING_ENTRY1(19), - ROUTING_ENTRY1(20), ROUTING_ENTRY1(21), - ROUTING_ENTRY1(22), ROUTING_ENTRY1(23), -}; - -int kvm_setup_default_irq_routing(struct kvm *kvm) -{ - return kvm_set_irq_routing(kvm, default_routing, - ARRAY_SIZE(default_routing), 0); -} - -void kvm_arch_post_irq_routing_update(struct kvm *kvm) -{ - if (!irqchip_split(kvm)) - return; - kvm_make_scan_ioapic_request(kvm); -} - -void kvm_scan_ioapic_irq(struct kvm_vcpu *vcpu, u32 dest_id, u16 dest_mode, - u8 vector, unsigned long *ioapic_handled_vectors) -{ - /* - * Intercept EOI if the vCPU is the target of the new IRQ routing, or - * the vCPU has a pending IRQ from the old routing, i.e. if the vCPU - * may receive a level-triggered IRQ in the future, or already received - * level-triggered IRQ. The EOI needs to be intercepted and forwarded - * to I/O APIC emulation so that the IRQ can be de-asserted. - */ - if (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, dest_id, dest_mode)) { - __set_bit(vector, ioapic_handled_vectors); - } else if (kvm_apic_pending_eoi(vcpu, vector)) { - __set_bit(vector, ioapic_handled_vectors); - - /* - * Track the highest pending EOI for which the vCPU is NOT the - * target in the new routing. Only the EOI for the IRQ that is - * in-flight (for the old routing) needs to be intercepted, any - * future IRQs that arrive on this vCPU will be coincidental to - * the level-triggered routing and don't need to be intercepted. - */ - if ((int)vector > vcpu->arch.highest_stale_pending_ioapic_eoi) - vcpu->arch.highest_stale_pending_ioapic_eoi = vector; - } -} - -void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, - ulong *ioapic_handled_vectors) -{ - struct kvm *kvm = vcpu->kvm; - struct kvm_kernel_irq_routing_entry *entry; - struct kvm_irq_routing_table *table; - u32 i, nr_ioapic_pins; - int idx; - - idx = srcu_read_lock(&kvm->irq_srcu); - table = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); - nr_ioapic_pins = min_t(u32, table->nr_rt_entries, - kvm->arch.nr_reserved_ioapic_pins); - for (i = 0; i < nr_ioapic_pins; ++i) { - hlist_for_each_entry(entry, &table->map[i], link) { - struct kvm_lapic_irq irq; - - if (entry->type != KVM_IRQ_ROUTING_MSI) - continue; - - kvm_set_msi_irq(vcpu->kvm, entry, &irq); - - if (!irq.trig_mode) - continue; - - kvm_scan_ioapic_irq(vcpu, irq.dest_id, irq.dest_mode, - irq.vector, ioapic_handled_vectors); - } - } - srcu_read_unlock(&kvm->irq_srcu, idx); -} - -void kvm_arch_irq_routing_update(struct kvm *kvm) -{ -#ifdef CONFIG_KVM_HYPERV - kvm_hv_irq_routing_update(kvm); -#endif -} diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 241b3535cb4f..8172c2042dd6 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1411,7 +1411,7 @@ static bool kvm_ioapic_handles_vector(struct kvm_lapic *apic, int vector) static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector) { - int trigger_mode; + int __maybe_unused trigger_mode; /* Eoi the ioapic only if the ioapic doesn't own the vector. */ if (!kvm_ioapic_handles_vector(apic, vector)) @@ -1432,12 +1432,14 @@ static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector) return; } +#ifdef CONFIG_KVM_IOAPIC if (apic_test_vector(vector, apic->regs + APIC_TMR)) trigger_mode = IOAPIC_LEVEL_TRIG; else trigger_mode = IOAPIC_EDGE_TRIG; kvm_ioapic_update_eoi(apic->vcpu, vector, trigger_mode); +#endif } static int apic_set_eoi(struct kvm_lapic *apic) @@ -3101,8 +3103,11 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) kvm_x86_call(hwapic_isr_update)(vcpu, apic_find_highest_isr(apic)); } kvm_make_request(KVM_REQ_EVENT, vcpu); + +#ifdef CONFIG_KVM_IOAPIC if (ioapic_in_kernel(vcpu->kvm)) kvm_rtc_eoi_tracking_restore_one(vcpu); +#endif vcpu->arch.apic_arb_prio = 0; diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 31284ec61a6a..72de14527698 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -23,6 +23,8 @@ #define APIC_BROADCAST 0xFF #define X2APIC_BROADCAST 0xFFFFFFFFul +#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) + enum lapic_mode { LAPIC_MODE_DISABLED = 0, LAPIC_MODE_INVALID = X2APIC_ENABLE, diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 4e06e2e89a8f..6e838cb6c9e1 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1983,14 +1983,35 @@ static bool sp_has_gptes(struct kvm_mmu_page *sp) return true; } +static __ro_after_init HLIST_HEAD(empty_page_hash); + +static struct hlist_head *kvm_get_mmu_page_hash(struct kvm *kvm, gfn_t gfn) +{ + /* + * Ensure the load of the hash table pointer itself is ordered before + * loads to walk the table. The pointer is set at runtime outside of + * mmu_lock when the TDP MMU is enabled, i.e. when the hash table of + * shadow pages becomes necessary only when KVM needs to shadow L1's + * TDP for an L2 guest. Pairs with the smp_store_release() in + * kvm_mmu_alloc_page_hash(). + */ + struct hlist_head *page_hash = smp_load_acquire(&kvm->arch.mmu_page_hash); + + lockdep_assert_held(&kvm->mmu_lock); + + if (!page_hash) + return &empty_page_hash; + + return &page_hash[kvm_page_table_hashfn(gfn)]; +} + #define for_each_valid_sp(_kvm, _sp, _list) \ hlist_for_each_entry(_sp, _list, hash_link) \ if (is_obsolete_sp((_kvm), (_sp))) { \ } else #define for_each_gfn_valid_sp_with_gptes(_kvm, _sp, _gfn) \ - for_each_valid_sp(_kvm, _sp, \ - &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)]) \ + for_each_valid_sp(_kvm, _sp, kvm_get_mmu_page_hash(_kvm, _gfn)) \ if ((_sp)->gfn != (_gfn) || !sp_has_gptes(_sp)) {} else static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) @@ -2358,6 +2379,12 @@ static struct kvm_mmu_page *__kvm_mmu_get_shadow_page(struct kvm *kvm, struct kvm_mmu_page *sp; bool created = false; + /* + * No need for memory barriers, unlike in kvm_get_mmu_page_hash(), as + * mmu_page_hash must be set prior to creating the first shadow root, + * i.e. reaching this point is fully serialized by slots_arch_lock. + */ + BUG_ON(!kvm->arch.mmu_page_hash); sp_list = &kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]; sp = kvm_mmu_find_shadow_page(kvm, vcpu, gfn, sp_list, role); @@ -3882,6 +3909,28 @@ out_unlock: return r; } +static int kvm_mmu_alloc_page_hash(struct kvm *kvm) +{ + struct hlist_head *h; + + if (kvm->arch.mmu_page_hash) + return 0; + + h = kvcalloc(KVM_NUM_MMU_PAGES, sizeof(*h), GFP_KERNEL_ACCOUNT); + if (!h) + return -ENOMEM; + + /* + * Ensure the hash table pointer is set only after all stores to zero + * the memory are retired. Pairs with the smp_load_acquire() in + * kvm_get_mmu_page_hash(). Note, mmu_lock must be held for write to + * add (or remove) shadow pages, and so readers are guaranteed to see + * an empty list for their current mmu_lock critical section. + */ + smp_store_release(&kvm->arch.mmu_page_hash, h); + return 0; +} + static int mmu_first_shadow_root_alloc(struct kvm *kvm) { struct kvm_memslots *slots; @@ -3901,9 +3950,13 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm) if (kvm_shadow_root_allocated(kvm)) goto out_unlock; + r = kvm_mmu_alloc_page_hash(kvm); + if (r) + goto out_unlock; + /* - * Check if anything actually needs to be allocated, e.g. all metadata - * will be allocated upfront if TDP is disabled. + * Check if memslot metadata actually needs to be allocated, e.g. all + * metadata will be allocated upfront if TDP is disabled. */ if (kvm_memslots_have_rmaps(kvm) && kvm_page_track_write_tracking_enabled(kvm)) @@ -6682,15 +6735,22 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) kvm_tdp_mmu_zap_invalidated_roots(kvm, true); } -void kvm_mmu_init_vm(struct kvm *kvm) +int kvm_mmu_init_vm(struct kvm *kvm) { + int r; + kvm->arch.shadow_mmio_value = shadow_mmio_value; INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages); spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); - if (tdp_mmu_enabled) + if (tdp_mmu_enabled) { kvm_mmu_init_tdp_mmu(kvm); + } else { + r = kvm_mmu_alloc_page_hash(kvm); + if (r) + return r; + } kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache; kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO; @@ -6699,6 +6759,7 @@ void kvm_mmu_init_vm(struct kvm *kvm) kvm->arch.split_desc_cache.kmem_cache = pte_list_desc_cache; kvm->arch.split_desc_cache.gfp_zero = __GFP_ZERO; + return 0; } static void mmu_free_vm_memory_caches(struct kvm *kvm) @@ -6710,6 +6771,8 @@ static void mmu_free_vm_memory_caches(struct kvm *kvm) void kvm_mmu_uninit_vm(struct kvm *kvm) { + kvfree(kvm->arch.mmu_page_hash); + if (tdp_mmu_enabled) kvm_mmu_uninit_tdp_mmu(kvm); diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index db8f33e4de62..65f3c89d7c5d 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -103,6 +103,9 @@ struct kvm_mmu_page { int root_count; refcount_t tdp_mmu_root_count; }; + + bool has_mapped_host_mmio; + union { /* These two members aren't used for TDP MMU */ struct { diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 68e323568e95..ed762bb4b007 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -804,9 +804,12 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (r != RET_PF_CONTINUE) return r; +#if PTTYPE != PTTYPE_EPT /* - * Do not change pte_access if the pfn is a mmio page, otherwise - * we will cache the incorrect access into mmio spte. + * Treat the guest PTE protections as writable, supervisor-only if this + * is a supervisor write fault and CR0.WP=0 (supervisor accesses ignore + * PTE.W if CR0.WP=0). Don't change the access type for emulated MMIO, + * otherwise KVM will cache incorrect access information in the SPTE. */ if (fault->write && !(walker.pte_access & ACC_WRITE_MASK) && !is_cr0_wp(vcpu->arch.mmu) && !fault->user && fault->slot) { @@ -822,6 +825,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (is_cr4_smep(vcpu->arch.mmu)) walker.pte_access &= ~ACC_EXEC_MASK; } +#endif r = RET_PF_RETRY; write_lock(&vcpu->kvm->mmu_lock); diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index cfce03d8f123..df31039b5d63 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -104,7 +104,7 @@ u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access) return spte; } -static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) +static bool __kvm_is_mmio_pfn(kvm_pfn_t pfn) { if (pfn_valid(pfn)) return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)) && @@ -125,6 +125,35 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) E820_TYPE_RAM); } +static bool kvm_is_mmio_pfn(kvm_pfn_t pfn, int *is_host_mmio) +{ + /* + * Determining if a PFN is host MMIO is relative expensive. Cache the + * result locally (in the sole caller) to avoid doing the full query + * multiple times when creating a single SPTE. + */ + if (*is_host_mmio < 0) + *is_host_mmio = __kvm_is_mmio_pfn(pfn); + + return *is_host_mmio; +} + +static void kvm_track_host_mmio_mapping(struct kvm_vcpu *vcpu) +{ + struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa); + + if (root) + WRITE_ONCE(root->has_mapped_host_mmio, true); + else + WRITE_ONCE(vcpu->kvm->arch.has_mapped_host_mmio, true); + + /* + * Force vCPUs to exit and flush CPU buffers if the vCPU is using the + * affected root(s). + */ + kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_OUTSIDE_GUEST_MODE); +} + /* * Returns true if the SPTE needs to be updated atomically due to having bits * that may be changed without holding mmu_lock, and for which KVM must not @@ -162,6 +191,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, { int level = sp->role.level; u64 spte = SPTE_MMU_PRESENT_MASK; + int is_host_mmio = -1; bool wrprot = false; /* @@ -209,13 +239,15 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, if (level > PG_LEVEL_4K) spte |= PT_PAGE_SIZE_MASK; - spte |= kvm_x86_call(get_mt_mask)(vcpu, gfn, kvm_is_mmio_pfn(pfn)); + if (kvm_x86_ops.get_mt_mask) + spte |= kvm_x86_call(get_mt_mask)(vcpu, gfn, + kvm_is_mmio_pfn(pfn, &is_host_mmio)); if (host_writable) spte |= shadow_host_writable_mask; else pte_access &= ~ACC_WRITE_MASK; - if (shadow_me_value && !kvm_is_mmio_pfn(pfn)) + if (shadow_me_value && !kvm_is_mmio_pfn(pfn, &is_host_mmio)) spte |= shadow_me_value; spte |= (u64)pfn << PAGE_SHIFT; @@ -260,6 +292,11 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, mark_page_dirty_in_slot(vcpu->kvm, slot, gfn); } + if (static_branch_unlikely(&cpu_buf_vm_clear) && + !kvm_vcpu_can_access_host_mmio(vcpu) && + kvm_is_mmio_pfn(pfn, &is_host_mmio)) + kvm_track_host_mmio_mapping(vcpu); + *new_spte = spte; return wrprot; } diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 1e94f081bdaf..3133f066927e 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -280,6 +280,16 @@ static inline bool is_mirror_sptep(tdp_ptep_t sptep) return is_mirror_sp(sptep_to_sp(rcu_dereference(sptep))); } +static inline bool kvm_vcpu_can_access_host_mmio(struct kvm_vcpu *vcpu) +{ + struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa); + + if (root) + return READ_ONCE(root->has_mapped_host_mmio); + + return READ_ONCE(vcpu->kvm->arch.has_mapped_host_mmio); +} + static inline bool is_mmio_spte(struct kvm *kvm, u64 spte) { return (spte & shadow_mmio_mask) == kvm->arch.shadow_mmio_value && diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index fde0ae986003..c53b92379e6e 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -52,6 +52,10 @@ /* CPUID level 0x80000022 (EAX) */ #define KVM_X86_FEATURE_PERFMON_V2 KVM_X86_FEATURE(CPUID_8000_0022_EAX, 0) +/* CPUID level 0x80000021 (ECX) */ +#define KVM_X86_FEATURE_TSA_SQ_NO KVM_X86_FEATURE(CPUID_8000_0021_ECX, 1) +#define KVM_X86_FEATURE_TSA_L1_NO KVM_X86_FEATURE(CPUID_8000_0021_ECX, 2) + struct cpuid_reg { u32 function; u32 index; @@ -82,6 +86,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX}, [CPUID_7_2_EDX] = { 7, 2, CPUID_EDX}, [CPUID_24_0_EBX] = { 0x24, 0, CPUID_EBX}, + [CPUID_8000_0021_ECX] = {0x80000021, 0, CPUID_ECX}, }; /* @@ -121,6 +126,8 @@ static __always_inline u32 __feature_translate(int x86_feature) KVM_X86_TRANSLATE_FEATURE(PERFMON_V2); KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL); KVM_X86_TRANSLATE_FEATURE(BHI_CTRL); + KVM_X86_TRANSLATE_FEATURE(TSA_SQ_NO); + KVM_X86_TRANSLATE_FEATURE(TSA_L1_NO); default: return x86_feature; } diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 067f8e3f5a0d..a34c5c3b164e 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -18,6 +18,7 @@ #include <linux/hashtable.h> #include <linux/amd-iommu.h> #include <linux/kvm_host.h> +#include <linux/kvm_irqfd.h> #include <asm/irq_remapping.h> #include <asm/msr.h> @@ -29,36 +30,39 @@ #include "svm.h" /* - * Encode the arbitrary VM ID and the vCPU's default APIC ID, i.e the vCPU ID, - * into the GATag so that KVM can retrieve the correct vCPU from a GALog entry - * if an interrupt can't be delivered, e.g. because the vCPU isn't running. + * Encode the arbitrary VM ID and the vCPU's _index_ into the GATag so that + * KVM can retrieve the correct vCPU from a GALog entry if an interrupt can't + * be delivered, e.g. because the vCPU isn't running. Use the vCPU's index + * instead of its ID (a.k.a. its default APIC ID), as KVM is guaranteed a fast + * lookup on the index, where as vCPUs whose index doesn't match their ID need + * to walk the entire xarray of vCPUs in the worst case scenario. * - * For the vCPU ID, use however many bits are currently allowed for the max + * For the vCPU index, use however many bits are currently allowed for the max * guest physical APIC ID (limited by the size of the physical ID table), and * use whatever bits remain to assign arbitrary AVIC IDs to VMs. Note, the * size of the GATag is defined by hardware (32 bits), but is an opaque value * as far as hardware is concerned. */ -#define AVIC_VCPU_ID_MASK AVIC_PHYSICAL_MAX_INDEX_MASK +#define AVIC_VCPU_IDX_MASK AVIC_PHYSICAL_MAX_INDEX_MASK #define AVIC_VM_ID_SHIFT HWEIGHT32(AVIC_PHYSICAL_MAX_INDEX_MASK) #define AVIC_VM_ID_MASK (GENMASK(31, AVIC_VM_ID_SHIFT) >> AVIC_VM_ID_SHIFT) #define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VM_ID_SHIFT) & AVIC_VM_ID_MASK) -#define AVIC_GATAG_TO_VCPUID(x) (x & AVIC_VCPU_ID_MASK) +#define AVIC_GATAG_TO_VCPUIDX(x) (x & AVIC_VCPU_IDX_MASK) -#define __AVIC_GATAG(vm_id, vcpu_id) ((((vm_id) & AVIC_VM_ID_MASK) << AVIC_VM_ID_SHIFT) | \ - ((vcpu_id) & AVIC_VCPU_ID_MASK)) -#define AVIC_GATAG(vm_id, vcpu_id) \ +#define __AVIC_GATAG(vm_id, vcpu_idx) ((((vm_id) & AVIC_VM_ID_MASK) << AVIC_VM_ID_SHIFT) | \ + ((vcpu_idx) & AVIC_VCPU_IDX_MASK)) +#define AVIC_GATAG(vm_id, vcpu_idx) \ ({ \ - u32 ga_tag = __AVIC_GATAG(vm_id, vcpu_id); \ + u32 ga_tag = __AVIC_GATAG(vm_id, vcpu_idx); \ \ - WARN_ON_ONCE(AVIC_GATAG_TO_VCPUID(ga_tag) != (vcpu_id)); \ + WARN_ON_ONCE(AVIC_GATAG_TO_VCPUIDX(ga_tag) != (vcpu_idx)); \ WARN_ON_ONCE(AVIC_GATAG_TO_VMID(ga_tag) != (vm_id)); \ ga_tag; \ }) -static_assert(__AVIC_GATAG(AVIC_VM_ID_MASK, AVIC_VCPU_ID_MASK) == -1u); +static_assert(__AVIC_GATAG(AVIC_VM_ID_MASK, AVIC_VCPU_IDX_MASK) == -1u); static bool force_avic; module_param_unsafe(force_avic, bool, 0444); @@ -75,14 +79,6 @@ static bool next_vm_id_wrapped = 0; static DEFINE_SPINLOCK(svm_vm_data_hash_lock); bool x2avic_enabled; -/* - * This is a wrapper of struct amd_iommu_ir_data. - */ -struct amd_svm_iommu_ir { - struct list_head node; /* Used by SVM for per-vcpu ir_list */ - void *data; /* Storing pointer to struct amd_ir_data */ -}; - static void avic_activate_vmcb(struct vcpu_svm *svm) { struct vmcb *vmcb = svm->vmcb01.ptr; @@ -147,16 +143,16 @@ int avic_ga_log_notifier(u32 ga_tag) struct kvm_svm *kvm_svm; struct kvm_vcpu *vcpu = NULL; u32 vm_id = AVIC_GATAG_TO_VMID(ga_tag); - u32 vcpu_id = AVIC_GATAG_TO_VCPUID(ga_tag); + u32 vcpu_idx = AVIC_GATAG_TO_VCPUIDX(ga_tag); - pr_debug("SVM: %s: vm_id=%#x, vcpu_id=%#x\n", __func__, vm_id, vcpu_id); - trace_kvm_avic_ga_log(vm_id, vcpu_id); + pr_debug("SVM: %s: vm_id=%#x, vcpu_idx=%#x\n", __func__, vm_id, vcpu_idx); + trace_kvm_avic_ga_log(vm_id, vcpu_idx); spin_lock_irqsave(&svm_vm_data_hash_lock, flags); hash_for_each_possible(svm_vm_data_hash, kvm_svm, hnode, vm_id) { if (kvm_svm->avic_vm_id != vm_id) continue; - vcpu = kvm_get_vcpu_by_id(&kvm_svm->kvm, vcpu_id); + vcpu = kvm_get_vcpu(&kvm_svm->kvm, vcpu_idx); break; } spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); @@ -180,10 +176,8 @@ void avic_vm_destroy(struct kvm *kvm) if (!enable_apicv) return; - if (kvm_svm->avic_logical_id_table_page) - __free_page(kvm_svm->avic_logical_id_table_page); - if (kvm_svm->avic_physical_id_table_page) - __free_page(kvm_svm->avic_physical_id_table_page); + free_page((unsigned long)kvm_svm->avic_logical_id_table); + free_page((unsigned long)kvm_svm->avic_physical_id_table); spin_lock_irqsave(&svm_vm_data_hash_lock, flags); hash_del(&kvm_svm->hnode); @@ -196,27 +190,19 @@ int avic_vm_init(struct kvm *kvm) int err = -ENOMEM; struct kvm_svm *kvm_svm = to_kvm_svm(kvm); struct kvm_svm *k2; - struct page *p_page; - struct page *l_page; u32 vm_id; if (!enable_apicv) return 0; - /* Allocating physical APIC ID table (4KB) */ - p_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); - if (!p_page) + kvm_svm->avic_physical_id_table = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); + if (!kvm_svm->avic_physical_id_table) goto free_avic; - kvm_svm->avic_physical_id_table_page = p_page; - - /* Allocating logical APIC ID table (4KB) */ - l_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); - if (!l_page) + kvm_svm->avic_logical_id_table = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); + if (!kvm_svm->avic_logical_id_table) goto free_avic; - kvm_svm->avic_logical_id_table_page = l_page; - spin_lock_irqsave(&svm_vm_data_hash_lock, flags); again: vm_id = next_vm_id = (next_vm_id + 1) & AVIC_VM_ID_MASK; @@ -242,17 +228,19 @@ free_avic: return err; } +static phys_addr_t avic_get_backing_page_address(struct vcpu_svm *svm) +{ + return __sme_set(__pa(svm->vcpu.arch.apic->regs)); +} + void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb) { struct kvm_svm *kvm_svm = to_kvm_svm(svm->vcpu.kvm); - phys_addr_t bpa = __sme_set(page_to_phys(svm->avic_backing_page)); - phys_addr_t lpa = __sme_set(page_to_phys(kvm_svm->avic_logical_id_table_page)); - phys_addr_t ppa = __sme_set(page_to_phys(kvm_svm->avic_physical_id_table_page)); - vmcb->control.avic_backing_page = bpa & AVIC_HPA_MASK; - vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK; - vmcb->control.avic_physical_id = ppa & AVIC_HPA_MASK; - vmcb->control.avic_vapic_bar = APIC_DEFAULT_PHYS_BASE & VMCB_AVIC_APIC_BAR_MASK; + vmcb->control.avic_backing_page = avic_get_backing_page_address(svm); + vmcb->control.avic_logical_id = __sme_set(__pa(kvm_svm->avic_logical_id_table)); + 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)) avic_activate_vmcb(svm); @@ -260,32 +248,31 @@ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb) avic_deactivate_vmcb(svm); } -static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, - unsigned int index) -{ - u64 *avic_physical_id_table; - struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); - - if ((!x2avic_enabled && index > AVIC_MAX_PHYSICAL_ID) || - (index > X2AVIC_MAX_PHYSICAL_ID)) - return NULL; - - avic_physical_id_table = page_address(kvm_svm->avic_physical_id_table_page); - - return &avic_physical_id_table[index]; -} - static int avic_init_backing_page(struct kvm_vcpu *vcpu) { - u64 *entry, new_entry; - int id = vcpu->vcpu_id; + struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); struct vcpu_svm *svm = to_svm(vcpu); + u32 id = vcpu->vcpu_id; + u64 new_entry; + /* + * Inhibit AVIC if the vCPU ID is bigger than what is supported by AVIC + * hardware. Immediately clear apicv_active, i.e. don't wait until the + * KVM_REQ_APICV_UPDATE request is processed on the first KVM_RUN, as + * avic_vcpu_load() expects to be called if and only if the vCPU has + * fully initialized AVIC. + */ if ((!x2avic_enabled && id > AVIC_MAX_PHYSICAL_ID) || - (id > X2AVIC_MAX_PHYSICAL_ID)) - return -EINVAL; + (id > X2AVIC_MAX_PHYSICAL_ID)) { + kvm_set_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_PHYSICAL_ID_TOO_BIG); + vcpu->arch.apic->apicv_active = false; + return 0; + } + + BUILD_BUG_ON((AVIC_MAX_PHYSICAL_ID + 1) * sizeof(new_entry) > PAGE_SIZE || + (X2AVIC_MAX_PHYSICAL_ID + 1) * sizeof(new_entry) > PAGE_SIZE); - if (!vcpu->arch.apic->regs) + if (WARN_ON_ONCE(!vcpu->arch.apic->regs)) return -EINVAL; if (kvm_apicv_activated(vcpu->kvm)) { @@ -302,19 +289,21 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) return ret; } - svm->avic_backing_page = virt_to_page(vcpu->arch.apic->regs); + /* Note, fls64() returns the bit position, +1. */ + BUILD_BUG_ON(__PHYSICAL_MASK_SHIFT > + fls64(AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK)); /* Setting AVIC backing page address in the phy APIC ID table */ - entry = avic_get_physical_id_entry(vcpu, id); - if (!entry) - return -EINVAL; + new_entry = avic_get_backing_page_address(svm) | + AVIC_PHYSICAL_ID_ENTRY_VALID_MASK; + svm->avic_physical_id_entry = new_entry; - new_entry = __sme_set((page_to_phys(svm->avic_backing_page) & - AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) | - AVIC_PHYSICAL_ID_ENTRY_VALID_MASK); - WRITE_ONCE(*entry, new_entry); - - svm->avic_physical_id_cache = entry; + /* + * Initialize the real table, as vCPUs must have a valid entry in order + * for broadcast IPIs to function correctly (broadcast IPIs ignore + * invalid entries, i.e. aren't guaranteed to generate a VM-Exit). + */ + WRITE_ONCE(kvm_svm->avic_physical_id_table[id], new_entry); return 0; } @@ -448,7 +437,7 @@ static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source if (apic_x2apic_mode(source)) avic_logical_id_table = NULL; else - avic_logical_id_table = page_address(kvm_svm->avic_logical_id_table_page); + avic_logical_id_table = kvm_svm->avic_logical_id_table; /* * AVIC is inhibited if vCPUs aren't mapped 1:1 with logical @@ -550,7 +539,6 @@ unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu) static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat) { struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); - u32 *logical_apic_id_table; u32 cluster, index; ldr = GET_APIC_LOGICAL_ID(ldr); @@ -571,9 +559,7 @@ static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat) return NULL; index += (cluster << 2); - logical_apic_id_table = (u32 *) page_address(kvm_svm->avic_logical_id_table_page); - - return &logical_apic_id_table[index]; + return &kvm_svm->avic_logical_id_table[index]; } static void avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr) @@ -722,6 +708,9 @@ int avic_init_vcpu(struct vcpu_svm *svm) int ret; struct kvm_vcpu *vcpu = &svm->vcpu; + INIT_LIST_HEAD(&svm->ir_list); + spin_lock_init(&svm->ir_list_lock); + if (!enable_apicv || !irqchip_in_kernel(vcpu->kvm)) return 0; @@ -729,8 +718,6 @@ int avic_init_vcpu(struct vcpu_svm *svm) if (ret) return ret; - INIT_LIST_HEAD(&svm->ir_list); - spin_lock_init(&svm->ir_list_lock); svm->dfr_reg = APIC_DFR_FLAT; return ret; @@ -742,316 +729,161 @@ void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu) avic_handle_ldr_update(vcpu); } -static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate) +static void svm_ir_list_del(struct kvm_kernel_irqfd *irqfd) { - int ret = 0; + struct kvm_vcpu *vcpu = irqfd->irq_bypass_vcpu; unsigned long flags; - struct amd_svm_iommu_ir *ir; - struct vcpu_svm *svm = to_svm(vcpu); - - if (!kvm_arch_has_assigned_device(vcpu->kvm)) - return 0; - /* - * Here, we go through the per-vcpu ir_list to update all existing - * interrupt remapping table entry targeting this vcpu. - */ - spin_lock_irqsave(&svm->ir_list_lock, flags); - - if (list_empty(&svm->ir_list)) - goto out; + if (!vcpu) + return; - list_for_each_entry(ir, &svm->ir_list, node) { - if (activate) - ret = amd_iommu_activate_guest_mode(ir->data); - else - ret = amd_iommu_deactivate_guest_mode(ir->data); - if (ret) - break; - } -out: - spin_unlock_irqrestore(&svm->ir_list_lock, flags); - return ret; + spin_lock_irqsave(&to_svm(vcpu)->ir_list_lock, flags); + list_del(&irqfd->vcpu_list); + spin_unlock_irqrestore(&to_svm(vcpu)->ir_list_lock, flags); } -static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) +int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, + unsigned int host_irq, uint32_t guest_irq, + struct kvm_vcpu *vcpu, u32 vector) { - unsigned long flags; - struct amd_svm_iommu_ir *cur; - - spin_lock_irqsave(&svm->ir_list_lock, flags); - list_for_each_entry(cur, &svm->ir_list, node) { - if (cur->data != pi->ir_data) - continue; - list_del(&cur->node); - kfree(cur); - break; - } - spin_unlock_irqrestore(&svm->ir_list_lock, flags); -} - -static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) -{ - int ret = 0; - unsigned long flags; - struct amd_svm_iommu_ir *ir; - u64 entry; - - if (WARN_ON_ONCE(!pi->ir_data)) - return -EINVAL; - - /** - * In some cases, the existing irte is updated and re-set, - * so we need to check here if it's already been * added - * to the ir_list. - */ - if (pi->prev_ga_tag) { - struct kvm *kvm = svm->vcpu.kvm; - u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag); - struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id); - struct vcpu_svm *prev_svm; - - if (!prev_vcpu) { - ret = -EINVAL; - goto out; - } - - prev_svm = to_svm(prev_vcpu); - svm_ir_list_del(prev_svm, pi); - } - - /** - * Allocating new amd_iommu_pi_data, which will get - * add to the per-vcpu ir_list. - */ - ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_ATOMIC | __GFP_ACCOUNT); - if (!ir) { - ret = -ENOMEM; - goto out; - } - ir->data = pi->ir_data; - - spin_lock_irqsave(&svm->ir_list_lock, flags); - /* - * Update the target pCPU for IOMMU doorbells if the vCPU is running. - * If the vCPU is NOT running, i.e. is blocking or scheduled out, KVM - * will update the pCPU info when the vCPU awkened and/or scheduled in. - * See also avic_vcpu_load(). + * If the IRQ was affined to a different vCPU, remove the IRTE metadata + * from the *previous* vCPU's list. */ - entry = READ_ONCE(*(svm->avic_physical_id_cache)); - if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK) - amd_iommu_update_ga(entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK, - true, pi->ir_data); - - list_add(&ir->node, &svm->ir_list); - spin_unlock_irqrestore(&svm->ir_list_lock, flags); -out: - return ret; -} + svm_ir_list_del(irqfd); -/* - * Note: - * The HW cannot support posting multicast/broadcast - * interrupts to a vCPU. So, we still use legacy interrupt - * remapping for these kind of interrupts. - * - * For lowest-priority interrupts, we only support - * those with single CPU as the destination, e.g. user - * configures the interrupts via /proc/irq or uses - * irqbalance to make the interrupts single-CPU. - */ -static int -get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, - struct vcpu_data *vcpu_info, struct vcpu_svm **svm) -{ - struct kvm_lapic_irq irq; - struct kvm_vcpu *vcpu = NULL; - - kvm_set_msi_irq(kvm, e, &irq); - - if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) || - !kvm_irq_is_postable(&irq)) { - pr_debug("SVM: %s: use legacy intr remap mode for irq %u\n", - __func__, irq.vector); - return -1; - } - - pr_debug("SVM: %s: use GA mode for irq %u\n", __func__, - irq.vector); - *svm = to_svm(vcpu); - vcpu_info->pi_desc_addr = __sme_set(page_to_phys((*svm)->avic_backing_page)); - vcpu_info->vector = irq.vector; - - return 0; -} - -/* - * avic_pi_update_irte - set IRTE for Posted-Interrupts - * - * @kvm: kvm - * @host_irq: host irq of the interrupt - * @guest_irq: gsi of the interrupt - * @set: set or unset PI - * returns 0 on success, < 0 on failure - */ -int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set) -{ - struct kvm_kernel_irq_routing_entry *e; - struct kvm_irq_routing_table *irq_rt; - bool enable_remapped_mode = true; - int idx, ret = 0; - - if (!kvm_arch_has_assigned_device(kvm) || !kvm_arch_has_irq_bypass()) - return 0; - - pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n", - __func__, host_irq, guest_irq, set); - - idx = srcu_read_lock(&kvm->irq_srcu); - irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); - - if (guest_irq >= irq_rt->nr_rt_entries || - hlist_empty(&irq_rt->map[guest_irq])) { - pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n", - guest_irq, irq_rt->nr_rt_entries); - goto out; - } - - hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) { - struct vcpu_data vcpu_info; - struct vcpu_svm *svm = NULL; + if (vcpu) { + /* + * Try to enable guest_mode in IRTE, unless AVIC is inhibited, + * in which case configure the IRTE for legacy mode, but track + * the IRTE metadata so that it can be converted to guest mode + * if AVIC is enabled/uninhibited in the future. + */ + struct amd_iommu_pi_data pi_data = { + .ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->avic_vm_id, + vcpu->vcpu_idx), + .is_guest_mode = kvm_vcpu_apicv_active(vcpu), + .vapic_addr = avic_get_backing_page_address(to_svm(vcpu)), + .vector = vector, + }; + struct vcpu_svm *svm = to_svm(vcpu); + u64 entry; + int ret; - if (e->type != KVM_IRQ_ROUTING_MSI) - continue; + /* + * Prevent the vCPU from being scheduled out or migrated until + * the IRTE is updated and its metadata has been added to the + * list of IRQs being posted to the vCPU, to ensure the IRTE + * isn't programmed with stale pCPU/IsRunning information. + */ + guard(spinlock_irqsave)(&svm->ir_list_lock); - /** - * Here, we setup with legacy mode in the following cases: - * 1. When cannot target interrupt to a specific vcpu. - * 2. Unsetting posted interrupt. - * 3. APIC virtualization is disabled for the vcpu. - * 4. IRQ has incompatible delivery mode (SMI, INIT, etc) + /* + * Update the target pCPU for IOMMU doorbells if the vCPU is + * running. If the vCPU is NOT running, i.e. is blocking or + * scheduled out, KVM will update the pCPU info when the vCPU + * is awakened and/or scheduled in. See also avic_vcpu_load(). */ - if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set && - kvm_vcpu_apicv_active(&svm->vcpu)) { - struct amd_iommu_pi_data pi; - - enable_remapped_mode = false; - - /* Try to enable guest_mode in IRTE */ - pi.base = __sme_set(page_to_phys(svm->avic_backing_page) & - AVIC_HPA_MASK); - pi.ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->avic_vm_id, - svm->vcpu.vcpu_id); - pi.is_guest_mode = true; - pi.vcpu_data = &vcpu_info; - ret = irq_set_vcpu_affinity(host_irq, &pi); - - /** - * Here, we successfully setting up vcpu affinity in - * IOMMU guest mode. Now, we need to store the posted - * interrupt information in a per-vcpu ir_list so that - * we can reference to them directly when we update vcpu - * scheduling information in IOMMU irte. - */ - if (!ret && pi.is_guest_mode) - svm_ir_list_add(svm, &pi); + entry = svm->avic_physical_id_entry; + if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK) { + pi_data.cpu = entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK; + } else { + pi_data.cpu = -1; + pi_data.ga_log_intr = entry & AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR; } - if (!ret && svm) { - trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id, - e->gsi, vcpu_info.vector, - vcpu_info.pi_desc_addr, set); - } + ret = irq_set_vcpu_affinity(host_irq, &pi_data); + if (ret) + return ret; - if (ret < 0) { - pr_err("%s: failed to update PI IRTE\n", __func__); - goto out; + /* + * Revert to legacy mode if the IOMMU didn't provide metadata + * for the IRTE, which KVM needs to keep the IRTE up-to-date, + * e.g. if the vCPU is migrated or AVIC is disabled. + */ + if (WARN_ON_ONCE(!pi_data.ir_data)) { + irq_set_vcpu_affinity(host_irq, NULL); + return -EIO; } - } - ret = 0; - if (enable_remapped_mode) { - /* Use legacy mode in IRTE */ - struct amd_iommu_pi_data pi; + irqfd->irq_bypass_data = pi_data.ir_data; + list_add(&irqfd->vcpu_list, &svm->ir_list); + return 0; + } + return irq_set_vcpu_affinity(host_irq, NULL); +} - /** - * Here, pi is used to: - * - Tell IOMMU to use legacy mode for this interrupt. - * - Retrieve ga_tag of prior interrupt remapping data. - */ - pi.prev_ga_tag = 0; - pi.is_guest_mode = false; - ret = irq_set_vcpu_affinity(host_irq, &pi); +enum avic_vcpu_action { + /* + * There is no need to differentiate between activate and deactivate, + * as KVM only refreshes AVIC state when the vCPU is scheduled in and + * isn't blocking, i.e. the pCPU must always be (in)valid when AVIC is + * being (de)activated. + */ + AVIC_TOGGLE_ON_OFF = BIT(0), + AVIC_ACTIVATE = AVIC_TOGGLE_ON_OFF, + AVIC_DEACTIVATE = AVIC_TOGGLE_ON_OFF, - /** - * Check if the posted interrupt was previously - * setup with the guest_mode by checking if the ga_tag - * was cached. If so, we need to clean up the per-vcpu - * ir_list. - */ - if (!ret && pi.prev_ga_tag) { - int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag); - struct kvm_vcpu *vcpu; + /* + * No unique action is required to deal with a vCPU that stops/starts + * running. A vCPU that starts running by definition stops blocking as + * well, and a vCPU that stops running can't have been blocking, i.e. + * doesn't need to toggle GALogIntr. + */ + AVIC_START_RUNNING = 0, + AVIC_STOP_RUNNING = 0, - vcpu = kvm_get_vcpu_by_id(kvm, id); - if (vcpu) - svm_ir_list_del(to_svm(vcpu), &pi); - } - } -out: - srcu_read_unlock(&kvm->irq_srcu, idx); - return ret; -} + /* + * When a vCPU starts blocking, KVM needs to set the GALogIntr flag + * int all associated IRTEs so that KVM can wake the vCPU if an IRQ is + * sent to the vCPU. + */ + AVIC_START_BLOCKING = BIT(1), +}; -static inline int -avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) +static void avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, + enum avic_vcpu_action action) { - int ret = 0; - struct amd_svm_iommu_ir *ir; + bool ga_log_intr = (action & AVIC_START_BLOCKING); struct vcpu_svm *svm = to_svm(vcpu); + struct kvm_kernel_irqfd *irqfd; lockdep_assert_held(&svm->ir_list_lock); - if (!kvm_arch_has_assigned_device(vcpu->kvm)) - return 0; - /* * Here, we go through the per-vcpu ir_list to update all existing * interrupt remapping table entry targeting this vcpu. */ if (list_empty(&svm->ir_list)) - return 0; + return; - list_for_each_entry(ir, &svm->ir_list, node) { - ret = amd_iommu_update_ga(cpu, r, ir->data); - if (ret) - return ret; + list_for_each_entry(irqfd, &svm->ir_list, vcpu_list) { + void *data = irqfd->irq_bypass_data; + + if (!(action & AVIC_TOGGLE_ON_OFF)) + WARN_ON_ONCE(amd_iommu_update_ga(data, cpu, ga_log_intr)); + else if (cpu >= 0) + WARN_ON_ONCE(amd_iommu_activate_guest_mode(data, cpu, ga_log_intr)); + else + WARN_ON_ONCE(amd_iommu_deactivate_guest_mode(data)); } - return 0; } -void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +static void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu, + enum avic_vcpu_action action) { - u64 entry; + struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); int h_physical_id = kvm_cpu_get_apicid(cpu); struct vcpu_svm *svm = to_svm(vcpu); unsigned long flags; + u64 entry; lockdep_assert_preemption_disabled(); if (WARN_ON(h_physical_id & ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK)) return; - /* - * No need to update anything if the vCPU is blocking, i.e. if the vCPU - * is being scheduled in after being preempted. The CPU entries in the - * Physical APIC table and IRTE are consumed iff IsRun{ning} is '1'. - * If the vCPU was migrated, its new CPU value will be stuffed when the - * vCPU unblocks. - */ - if (kvm_vcpu_is_blocking(vcpu)) + if (WARN_ON_ONCE(vcpu->vcpu_id * sizeof(entry) >= PAGE_SIZE)) return; /* @@ -1063,38 +895,57 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) */ spin_lock_irqsave(&svm->ir_list_lock, flags); - entry = READ_ONCE(*(svm->avic_physical_id_cache)); + entry = svm->avic_physical_id_entry; WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK); - entry &= ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK; + entry &= ~(AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK | + AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR); entry |= (h_physical_id & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK); entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; - WRITE_ONCE(*(svm->avic_physical_id_cache), entry); - avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true); + svm->avic_physical_id_entry = entry; + + /* + * If IPI virtualization is disabled, clear IsRunning when updating the + * actual Physical ID table, so that the CPU never sees IsRunning=1. + * Keep the APIC ID up-to-date in the entry to minimize the chances of + * things going sideways if hardware peeks at the ID. + */ + if (!enable_ipiv) + entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; + + WRITE_ONCE(kvm_svm->avic_physical_id_table[vcpu->vcpu_id], entry); + + avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, action); spin_unlock_irqrestore(&svm->ir_list_lock, flags); } -void avic_vcpu_put(struct kvm_vcpu *vcpu) +void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { - u64 entry; + /* + * No need to update anything if the vCPU is blocking, i.e. if the vCPU + * is being scheduled in after being preempted. The CPU entries in the + * Physical APIC table and IRTE are consumed iff IsRun{ning} is '1'. + * If the vCPU was migrated, its new CPU value will be stuffed when the + * vCPU unblocks. + */ + if (kvm_vcpu_is_blocking(vcpu)) + return; + + __avic_vcpu_load(vcpu, cpu, AVIC_START_RUNNING); +} + +static void __avic_vcpu_put(struct kvm_vcpu *vcpu, enum avic_vcpu_action action) +{ + struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); struct vcpu_svm *svm = to_svm(vcpu); unsigned long flags; + u64 entry = svm->avic_physical_id_entry; lockdep_assert_preemption_disabled(); - /* - * Note, reading the Physical ID entry outside of ir_list_lock is safe - * as only the pCPU that has loaded (or is loading) the vCPU is allowed - * to modify the entry, and preemption is disabled. I.e. the vCPU - * can't be scheduled out and thus avic_vcpu_{put,load}() can't run - * recursively. - */ - entry = READ_ONCE(*(svm->avic_physical_id_cache)); - - /* Nothing to do if IsRunning == '0' due to vCPU blocking. */ - if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)) + if (WARN_ON_ONCE(vcpu->vcpu_id * sizeof(entry) >= PAGE_SIZE)) return; /* @@ -1107,13 +958,62 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu) */ spin_lock_irqsave(&svm->ir_list_lock, flags); - avic_update_iommu_vcpu_affinity(vcpu, -1, 0); + avic_update_iommu_vcpu_affinity(vcpu, -1, action); + + WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR); + /* + * Keep the previous APIC ID in the entry so that a rogue doorbell from + * hardware is at least restricted to a CPU associated with the vCPU. + */ entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; - WRITE_ONCE(*(svm->avic_physical_id_cache), entry); + + if (enable_ipiv) + WRITE_ONCE(kvm_svm->avic_physical_id_table[vcpu->vcpu_id], entry); + + /* + * Note! Don't set AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR in the table as + * it's a synthetic flag that usurps an unused should-be-zero bit. + */ + if (action & AVIC_START_BLOCKING) + entry |= AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR; + + svm->avic_physical_id_entry = entry; spin_unlock_irqrestore(&svm->ir_list_lock, flags); +} + +void avic_vcpu_put(struct kvm_vcpu *vcpu) +{ + /* + * Note, reading the Physical ID entry outside of ir_list_lock is safe + * as only the pCPU that has loaded (or is loading) the vCPU is allowed + * to modify the entry, and preemption is disabled. I.e. the vCPU + * can't be scheduled out and thus avic_vcpu_{put,load}() can't run + * recursively. + */ + u64 entry = to_svm(vcpu)->avic_physical_id_entry; + + /* + * Nothing to do if IsRunning == '0' due to vCPU blocking, i.e. if the + * vCPU is preempted while its in the process of blocking. WARN if the + * vCPU wasn't running and isn't blocking, KVM shouldn't attempt to put + * the AVIC if it wasn't previously loaded. + */ + if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)) { + if (WARN_ON_ONCE(!kvm_vcpu_is_blocking(vcpu))) + return; + /* + * The vCPU was preempted while blocking, ensure its IRTEs are + * configured to generate GA Log Interrupts. + */ + if (!(WARN_ON_ONCE(!(entry & AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR)))) + return; + } + + __avic_vcpu_put(vcpu, kvm_vcpu_is_blocking(vcpu) ? AVIC_START_BLOCKING : + AVIC_STOP_RUNNING); } void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu) @@ -1142,19 +1042,18 @@ void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu) void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { - bool activated = kvm_vcpu_apicv_active(vcpu); - if (!enable_apicv) return; + /* APICv should only be toggled on/off while the vCPU is running. */ + WARN_ON_ONCE(kvm_vcpu_is_blocking(vcpu)); + avic_refresh_virtual_apic_mode(vcpu); - if (activated) - avic_vcpu_load(vcpu, vcpu->cpu); + if (kvm_vcpu_apicv_active(vcpu)) + __avic_vcpu_load(vcpu, vcpu->cpu, AVIC_ACTIVATE); else - avic_vcpu_put(vcpu); - - avic_set_pi_irte_mode(vcpu, activated); + __avic_vcpu_put(vcpu, AVIC_DEACTIVATE); } void avic_vcpu_blocking(struct kvm_vcpu *vcpu) @@ -1162,20 +1061,25 @@ void avic_vcpu_blocking(struct kvm_vcpu *vcpu) if (!kvm_vcpu_apicv_active(vcpu)) return; - /* - * Unload the AVIC when the vCPU is about to block, _before_ - * the vCPU actually blocks. - * - * Any IRQs that arrive before IsRunning=0 will not cause an - * incomplete IPI vmexit on the source, therefore vIRR will also - * be checked by kvm_vcpu_check_block() before blocking. The - * memory barrier implicit in set_current_state orders writing - * IsRunning=0 before reading the vIRR. The processor needs a - * matching memory barrier on interrupt delivery between writing - * IRR and reading IsRunning; the lack of this barrier might be - * the cause of errata #1235). - */ - avic_vcpu_put(vcpu); + /* + * Unload the AVIC when the vCPU is about to block, _before_ the vCPU + * actually blocks. + * + * Note, any IRQs that arrive before IsRunning=0 will not cause an + * incomplete IPI vmexit on the source; kvm_vcpu_check_block() handles + * this by checking vIRR one last time before blocking. The memory + * barrier implicit in set_current_state orders writing IsRunning=0 + * before reading the vIRR. The processor needs a matching memory + * barrier on interrupt delivery between writing IRR and reading + * IsRunning; the lack of this barrier might be the cause of errata #1235). + * + * Clear IsRunning=0 even if guest IRQs are disabled, i.e. even if KVM + * doesn't need to detect events for scheduling purposes. The doorbell + * used to signal running vCPUs cannot be blocked, i.e. will perturb the + * CPU and cause noisy neighbor problems if the VM is sending interrupts + * to the vCPU while it's scheduled out. + */ + __avic_vcpu_put(vcpu, AVIC_START_BLOCKING); } void avic_vcpu_unblocking(struct kvm_vcpu *vcpu) @@ -1228,6 +1132,14 @@ bool avic_hardware_setup(void) if (x2avic_enabled) pr_info("x2AVIC enabled\n"); + /* + * Disable IPI virtualization for AMD Family 17h CPUs (Zen1 and Zen2) + * due to erratum 1235, which results in missed VM-Exits on the sender + * and thus missed wake events for blocking vCPUs due to the CPU + * failing to see a software update to clear IsRunning. + */ + enable_ipiv = enable_ipiv && boot_cpu_data.x86 != 0x17; + amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); return true; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 8427a48b8b7a..b7fd2e869998 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -185,12 +185,87 @@ void recalc_intercepts(struct vcpu_svm *svm) } /* + * This array (and its actual size) holds the set of offsets (indexing by chunk + * size) to process when merging vmcb12's MSRPM with vmcb01's MSRPM. Note, the + * set of MSRs for which interception is disabled in vmcb01 is per-vCPU, e.g. + * based on CPUID features. This array only tracks MSRs that *might* be passed + * through to the guest. + * + * Hardcode the capacity of the array based on the maximum number of _offsets_. + * MSRs are batched together, so there are fewer offsets than MSRs. + */ +static int nested_svm_msrpm_merge_offsets[7] __ro_after_init; +static int nested_svm_nr_msrpm_merge_offsets __ro_after_init; +typedef unsigned long nsvm_msrpm_merge_t; + +int __init nested_svm_init_msrpm_merge_offsets(void) +{ + static const u32 merge_msrs[] __initconst = { + MSR_STAR, + MSR_IA32_SYSENTER_CS, + MSR_IA32_SYSENTER_EIP, + MSR_IA32_SYSENTER_ESP, + #ifdef CONFIG_X86_64 + MSR_GS_BASE, + MSR_FS_BASE, + MSR_KERNEL_GS_BASE, + MSR_LSTAR, + MSR_CSTAR, + MSR_SYSCALL_MASK, + #endif + MSR_IA32_SPEC_CTRL, + MSR_IA32_PRED_CMD, + MSR_IA32_FLUSH_CMD, + MSR_IA32_APERF, + MSR_IA32_MPERF, + MSR_IA32_LASTBRANCHFROMIP, + MSR_IA32_LASTBRANCHTOIP, + MSR_IA32_LASTINTFROMIP, + MSR_IA32_LASTINTTOIP, + }; + int i, j; + + for (i = 0; i < ARRAY_SIZE(merge_msrs); i++) { + int bit_nr = svm_msrpm_bit_nr(merge_msrs[i]); + u32 offset; + + if (WARN_ON(bit_nr < 0)) + return -EIO; + + /* + * Merging is done in chunks to reduce the number of accesses + * to L1's bitmap. + */ + offset = bit_nr / BITS_PER_BYTE / sizeof(nsvm_msrpm_merge_t); + + for (j = 0; j < nested_svm_nr_msrpm_merge_offsets; j++) { + if (nested_svm_msrpm_merge_offsets[j] == offset) + break; + } + + if (j < nested_svm_nr_msrpm_merge_offsets) + continue; + + if (WARN_ON(j >= ARRAY_SIZE(nested_svm_msrpm_merge_offsets))) + return -EIO; + + nested_svm_msrpm_merge_offsets[j] = offset; + nested_svm_nr_msrpm_merge_offsets++; + } + + return 0; +} + +/* * Merge L0's (KVM) and L1's (Nested VMCB) MSR permission bitmaps. The function * is optimized in that it only merges the parts where KVM MSR permission bitmap * may contain zero bits. */ -static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) +static bool nested_svm_merge_msrpm(struct kvm_vcpu *vcpu) { + struct vcpu_svm *svm = to_svm(vcpu); + nsvm_msrpm_merge_t *msrpm02 = svm->nested.msrpm; + nsvm_msrpm_merge_t *msrpm01 = svm->msrpm; int i; /* @@ -205,7 +280,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) if (!svm->nested.force_msr_bitmap_recalc) { struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments; - if (kvm_hv_hypercall_enabled(&svm->vcpu) && + if (kvm_hv_hypercall_enabled(vcpu) && hve->hv_enlightenments_control.msr_bitmap && (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS))) goto set_msrpm_base_pa; @@ -215,25 +290,17 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) return true; - for (i = 0; i < MSRPM_OFFSETS; i++) { - u32 value, p; - u64 offset; + for (i = 0; i < nested_svm_nr_msrpm_merge_offsets; i++) { + const int p = nested_svm_msrpm_merge_offsets[i]; + nsvm_msrpm_merge_t l1_val; + gpa_t gpa; - if (msrpm_offsets[i] == 0xffffffff) - break; + gpa = svm->nested.ctl.msrpm_base_pa + (p * sizeof(l1_val)); - p = msrpm_offsets[i]; - - /* x2apic msrs are intercepted always for the nested guest */ - if (is_x2apic_msrpm_offset(p)) - continue; - - offset = svm->nested.ctl.msrpm_base_pa + (p * 4); - - if (kvm_vcpu_read_guest(&svm->vcpu, offset, &value, 4)) + if (kvm_vcpu_read_guest(vcpu, gpa, &l1_val, sizeof(l1_val))) return false; - svm->nested.msrpm[p] = svm->msrpm[p] | value; + msrpm02[p] = msrpm01[p] | l1_val; } svm->nested.force_msr_bitmap_recalc = false; @@ -937,7 +1004,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, true)) goto out_exit_err; - if (nested_svm_vmrun_msrpm(svm)) + if (nested_svm_merge_msrpm(vcpu)) goto out; out_exit_err: @@ -1230,7 +1297,6 @@ int svm_allocate_nested(struct vcpu_svm *svm) svm->nested.msrpm = svm_vcpu_alloc_msrpm(); if (!svm->nested.msrpm) goto err_free_vmcb02; - svm_vcpu_init_msrpm(&svm->vcpu, svm->nested.msrpm); svm->nested.initialized = true; return 0; @@ -1290,26 +1356,26 @@ void svm_leave_nested(struct kvm_vcpu *vcpu) static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) { - u32 offset, msr, value; - int write, mask; + gpa_t base = svm->nested.ctl.msrpm_base_pa; + int write, bit_nr; + u8 value, mask; + u32 msr; if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) return NESTED_EXIT_HOST; msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; - offset = svm_msrpm_offset(msr); + bit_nr = svm_msrpm_bit_nr(msr); write = svm->vmcb->control.exit_info_1 & 1; - mask = 1 << ((2 * (msr & 0xf)) + write); - if (offset == MSR_INVALID) + if (bit_nr < 0) return NESTED_EXIT_DONE; - /* Offset is in 32 bit units but need in 8 bit units */ - offset *= 4; - - if (kvm_vcpu_read_guest(&svm->vcpu, svm->nested.ctl.msrpm_base_pa + offset, &value, 4)) + if (kvm_vcpu_read_guest(&svm->vcpu, base + bit_nr / BITS_PER_BYTE, + &value, sizeof(value))) return NESTED_EXIT_DONE; + mask = BIT(write) << (bit_nr & (BITS_PER_BYTE - 1)); return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; } @@ -1819,13 +1885,11 @@ out_free: static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) { - struct vcpu_svm *svm = to_svm(vcpu); - if (WARN_ON(!is_guest_mode(vcpu))) return true; if (!vcpu->arch.pdptrs_from_userspace && - !nested_npt_enabled(svm) && is_pae_paging(vcpu)) + !nested_npt_enabled(to_svm(vcpu)) && is_pae_paging(vcpu)) /* * Reload the guest's PDPTRs since after a migration * the guest CR3 might be restored prior to setting the nested @@ -1834,7 +1898,7 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3))) return false; - if (!nested_svm_vmrun_msrpm(svm)) { + if (!nested_svm_merge_msrpm(vcpu)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 459c3b791fd4..d061ebb430ce 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1971,6 +1971,10 @@ static int sev_check_source_vcpus(struct kvm *dst, struct kvm *src) struct kvm_vcpu *src_vcpu; unsigned long i; + if (src->created_vcpus != atomic_read(&src->online_vcpus) || + dst->created_vcpus != atomic_read(&dst->online_vcpus)) + return -EBUSY; + if (!sev_es_guest(src)) return 0; @@ -4386,16 +4390,17 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) count, in); } -static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm) +void sev_es_recalc_msr_intercepts(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *vcpu = &svm->vcpu; + /* Clear intercepts on MSRs that are context switched by hardware. */ + svm_disable_intercept_for_msr(vcpu, MSR_AMD64_SEV_ES_GHCB, MSR_TYPE_RW); + svm_disable_intercept_for_msr(vcpu, MSR_EFER, MSR_TYPE_RW); + svm_disable_intercept_for_msr(vcpu, MSR_IA32_CR_PAT, MSR_TYPE_RW); - if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { - bool v_tsc_aux = guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) || - guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID); - - set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux); - } + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) + svm_set_intercept_for_msr(vcpu, MSR_TSC_AUX, MSR_TYPE_RW, + !guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID)); /* * For SEV-ES, accesses to MSR_IA32_XSS should not be intercepted if @@ -4409,11 +4414,9 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm) * XSAVES being exposed to the guest so that KVM can at least honor * guest CPUID for RDMSR and WRMSR. */ - if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 1, 1); - else - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 0, 0); + svm_set_intercept_for_msr(vcpu, MSR_IA32_XSS, MSR_TYPE_RW, + !guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) || + !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)); } void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm) @@ -4425,16 +4428,12 @@ void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm) best = kvm_find_cpuid_entry(vcpu, 0x8000001F); if (best) vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); - - if (sev_es_guest(svm->vcpu.kvm)) - sev_es_vcpu_after_set_cpuid(svm); } static void sev_es_init_vmcb(struct vcpu_svm *svm) { struct kvm_sev_info *sev = to_kvm_sev_info(svm->vcpu.kvm); struct vmcb *vmcb = svm->vmcb01.ptr; - struct kvm_vcpu *vcpu = &svm->vcpu; svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE; @@ -4445,8 +4444,12 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) * the VMSA will be NULL if this vCPU is the destination for intrahost * migration, and will be copied later. */ - if (svm->sev_es.vmsa && !svm->sev_es.snp_has_guest_vmsa) - svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa); + if (!svm->sev_es.snp_has_guest_vmsa) { + if (svm->sev_es.vmsa) + svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa); + else + svm->vmcb->control.vmsa_pa = INVALID_PAGE; + } if (cpu_feature_enabled(X86_FEATURE_ALLOWED_SEV_FEATURES)) svm->vmcb->control.allowed_sev_features = sev->vmsa_features | @@ -4488,10 +4491,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) /* Can't intercept XSETBV, HV can't modify XCR0 directly */ svm_clr_intercept(svm, INTERCEPT_XSETBV); - - /* Clear intercepts on selected MSRs */ - set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1); } void sev_init_vmcb(struct vcpu_svm *svm) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index ab9b947dbf4f..d9931c6c4bc6 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -72,8 +72,6 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id); static bool erratum_383_found __read_mostly; -u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; - /* * Set osvw_len to higher value when updated Revision Guides * are published and we know what the new status bits are @@ -82,72 +80,6 @@ static uint64_t osvw_len = 4, osvw_status; static DEFINE_PER_CPU(u64, current_tsc_ratio); -#define X2APIC_MSR(x) (APIC_BASE_MSR + (x >> 4)) - -static const struct svm_direct_access_msrs { - u32 index; /* Index of the MSR */ - bool always; /* True if intercept is initially cleared */ -} direct_access_msrs[MAX_DIRECT_ACCESS_MSRS] = { - { .index = MSR_STAR, .always = true }, - { .index = MSR_IA32_SYSENTER_CS, .always = true }, - { .index = MSR_IA32_SYSENTER_EIP, .always = false }, - { .index = MSR_IA32_SYSENTER_ESP, .always = false }, -#ifdef CONFIG_X86_64 - { .index = MSR_GS_BASE, .always = true }, - { .index = MSR_FS_BASE, .always = true }, - { .index = MSR_KERNEL_GS_BASE, .always = true }, - { .index = MSR_LSTAR, .always = true }, - { .index = MSR_CSTAR, .always = true }, - { .index = MSR_SYSCALL_MASK, .always = true }, -#endif - { .index = MSR_IA32_SPEC_CTRL, .always = false }, - { .index = MSR_IA32_PRED_CMD, .always = false }, - { .index = MSR_IA32_FLUSH_CMD, .always = false }, - { .index = MSR_IA32_DEBUGCTLMSR, .always = false }, - { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, - { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, - { .index = MSR_IA32_LASTINTFROMIP, .always = false }, - { .index = MSR_IA32_LASTINTTOIP, .always = false }, - { .index = MSR_IA32_XSS, .always = false }, - { .index = MSR_EFER, .always = false }, - { .index = MSR_IA32_CR_PAT, .always = false }, - { .index = MSR_AMD64_SEV_ES_GHCB, .always = true }, - { .index = MSR_TSC_AUX, .always = false }, - { .index = X2APIC_MSR(APIC_ID), .always = false }, - { .index = X2APIC_MSR(APIC_LVR), .always = false }, - { .index = X2APIC_MSR(APIC_TASKPRI), .always = false }, - { .index = X2APIC_MSR(APIC_ARBPRI), .always = false }, - { .index = X2APIC_MSR(APIC_PROCPRI), .always = false }, - { .index = X2APIC_MSR(APIC_EOI), .always = false }, - { .index = X2APIC_MSR(APIC_RRR), .always = false }, - { .index = X2APIC_MSR(APIC_LDR), .always = false }, - { .index = X2APIC_MSR(APIC_DFR), .always = false }, - { .index = X2APIC_MSR(APIC_SPIV), .always = false }, - { .index = X2APIC_MSR(APIC_ISR), .always = false }, - { .index = X2APIC_MSR(APIC_TMR), .always = false }, - { .index = X2APIC_MSR(APIC_IRR), .always = false }, - { .index = X2APIC_MSR(APIC_ESR), .always = false }, - { .index = X2APIC_MSR(APIC_ICR), .always = false }, - { .index = X2APIC_MSR(APIC_ICR2), .always = false }, - - /* - * Note: - * AMD does not virtualize APIC TSC-deadline timer mode, but it is - * emulated by KVM. When setting APIC LVTT (0x832) register bit 18, - * the AVIC hardware would generate GP fault. Therefore, always - * intercept the MSR 0x832, and do not setup direct_access_msr. - */ - { .index = X2APIC_MSR(APIC_LVTTHMR), .always = false }, - { .index = X2APIC_MSR(APIC_LVTPC), .always = false }, - { .index = X2APIC_MSR(APIC_LVT0), .always = false }, - { .index = X2APIC_MSR(APIC_LVT1), .always = false }, - { .index = X2APIC_MSR(APIC_LVTERR), .always = false }, - { .index = X2APIC_MSR(APIC_TMICT), .always = false }, - { .index = X2APIC_MSR(APIC_TMCCT), .always = false }, - { .index = X2APIC_MSR(APIC_TDCR), .always = false }, - { .index = MSR_INVALID, .always = false }, -}; - /* * These 2 parameters are used to config the controls for Pause-Loop Exiting: * pause_filter_count: On processors that support Pause filtering(indicated @@ -232,6 +164,7 @@ module_param(tsc_scaling, int, 0444); */ static bool avic; module_param(avic, bool, 0444); +module_param(enable_ipiv, bool, 0444); module_param(enable_device_posted_irqs, bool, 0444); @@ -264,33 +197,6 @@ static DEFINE_MUTEX(vmcb_dump_mutex); */ static int tsc_aux_uret_slot __read_mostly = -1; -static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000}; - -#define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges) -#define MSRS_RANGE_SIZE 2048 -#define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2) - -u32 svm_msrpm_offset(u32 msr) -{ - u32 offset; - int i; - - for (i = 0; i < NUM_MSR_MAPS; i++) { - if (msr < msrpm_ranges[i] || - msr >= msrpm_ranges[i] + MSRS_IN_RANGE) - continue; - - offset = (msr - msrpm_ranges[i]) / 4; /* 4 msrs per u8 */ - offset += (i * MSRS_RANGE_SIZE); /* add range offset */ - - /* Now we have the u8 offset - but need the u32 offset */ - return offset / 4; - } - - /* MSR not in any range */ - return MSR_INVALID; -} - static int get_npt_level(void) { #ifdef CONFIG_X86_64 @@ -757,50 +663,8 @@ static void clr_dr_intercepts(struct vcpu_svm *svm) recalc_intercepts(svm); } -static int direct_access_msr_slot(u32 msr) -{ - u32 i; - - for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) - if (direct_access_msrs[i].index == msr) - return i; - - return -ENOENT; -} - -static void set_shadow_msr_intercept(struct kvm_vcpu *vcpu, u32 msr, int read, - int write) -{ - struct vcpu_svm *svm = to_svm(vcpu); - int slot = direct_access_msr_slot(msr); - - if (slot == -ENOENT) - return; - - /* Set the shadow bitmaps to the desired intercept states */ - if (read) - set_bit(slot, svm->shadow_msr_intercept.read); - else - clear_bit(slot, svm->shadow_msr_intercept.read); - - if (write) - set_bit(slot, svm->shadow_msr_intercept.write); - else - clear_bit(slot, svm->shadow_msr_intercept.write); -} - -static bool valid_msr_intercept(u32 index) -{ - return direct_access_msr_slot(index) != -ENOENT; -} - static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) { - u8 bit_write; - unsigned long tmp; - u32 offset; - u32 *msrpm; - /* * For non-nested case: * If the L01 MSR bitmap does not intercept the MSR, then we need to @@ -810,90 +674,102 @@ static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) * If the L02 MSR bitmap does not intercept the MSR, then we need to * save it. */ - msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm: - to_svm(vcpu)->msrpm; + void *msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm : + to_svm(vcpu)->msrpm; - offset = svm_msrpm_offset(msr); - bit_write = 2 * (msr & 0x0f) + 1; - tmp = msrpm[offset]; - - BUG_ON(offset == MSR_INVALID); - - return test_bit(bit_write, &tmp); + return svm_test_msr_bitmap_write(msrpm, msr); } -static void set_msr_interception_bitmap(struct kvm_vcpu *vcpu, u32 *msrpm, - u32 msr, int read, int write) +void svm_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool set) { struct vcpu_svm *svm = to_svm(vcpu); - u8 bit_read, bit_write; - unsigned long tmp; - u32 offset; + void *msrpm = svm->msrpm; - /* - * If this warning triggers extend the direct_access_msrs list at the - * beginning of the file - */ - WARN_ON(!valid_msr_intercept(msr)); - - /* Enforce non allowed MSRs to trap */ - if (read && !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ)) - read = 0; - - if (write && !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE)) - write = 0; - - offset = svm_msrpm_offset(msr); - bit_read = 2 * (msr & 0x0f); - bit_write = 2 * (msr & 0x0f) + 1; - tmp = msrpm[offset]; - - BUG_ON(offset == MSR_INVALID); - - read ? clear_bit(bit_read, &tmp) : set_bit(bit_read, &tmp); - write ? clear_bit(bit_write, &tmp) : set_bit(bit_write, &tmp); + /* Don't disable interception for MSRs userspace wants to handle. */ + if (type & MSR_TYPE_R) { + if (!set && kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ)) + svm_clear_msr_bitmap_read(msrpm, msr); + else + svm_set_msr_bitmap_read(msrpm, msr); + } - msrpm[offset] = tmp; + if (type & MSR_TYPE_W) { + if (!set && kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE)) + svm_clear_msr_bitmap_write(msrpm, msr); + else + svm_set_msr_bitmap_write(msrpm, msr); + } svm_hv_vmcb_dirty_nested_enlightenments(vcpu); svm->nested.force_msr_bitmap_recalc = true; } -void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr, - int read, int write) -{ - set_shadow_msr_intercept(vcpu, msr, read, write); - set_msr_interception_bitmap(vcpu, msrpm, msr, read, write); -} - -u32 *svm_vcpu_alloc_msrpm(void) +void *svm_alloc_permissions_map(unsigned long size, gfp_t gfp_mask) { - unsigned int order = get_order(MSRPM_SIZE); - struct page *pages = alloc_pages(GFP_KERNEL_ACCOUNT, order); - u32 *msrpm; + unsigned int order = get_order(size); + struct page *pages = alloc_pages(gfp_mask, order); + void *pm; if (!pages) return NULL; - msrpm = page_address(pages); - memset(msrpm, 0xff, PAGE_SIZE * (1 << order)); + /* + * Set all bits in the permissions map so that all MSR and I/O accesses + * are intercepted by default. + */ + pm = page_address(pages); + memset(pm, 0xff, PAGE_SIZE * (1 << order)); - return msrpm; + return pm; } -void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm) +static void svm_recalc_lbr_msr_intercepts(struct kvm_vcpu *vcpu) { - int i; + bool intercept = !(to_svm(vcpu)->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK); - for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) { - if (!direct_access_msrs[i].always) - continue; - set_msr_interception(vcpu, msrpm, direct_access_msrs[i].index, 1, 1); - } + svm_set_intercept_for_msr(vcpu, MSR_IA32_LASTBRANCHFROMIP, MSR_TYPE_RW, intercept); + svm_set_intercept_for_msr(vcpu, MSR_IA32_LASTBRANCHTOIP, MSR_TYPE_RW, intercept); + svm_set_intercept_for_msr(vcpu, MSR_IA32_LASTINTFROMIP, MSR_TYPE_RW, intercept); + svm_set_intercept_for_msr(vcpu, MSR_IA32_LASTINTTOIP, MSR_TYPE_RW, intercept); + + if (sev_es_guest(vcpu->kvm)) + svm_set_intercept_for_msr(vcpu, MSR_IA32_DEBUGCTLMSR, MSR_TYPE_RW, intercept); } void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept) { + static const u32 x2avic_passthrough_msrs[] = { + X2APIC_MSR(APIC_ID), + X2APIC_MSR(APIC_LVR), + X2APIC_MSR(APIC_TASKPRI), + X2APIC_MSR(APIC_ARBPRI), + X2APIC_MSR(APIC_PROCPRI), + X2APIC_MSR(APIC_EOI), + X2APIC_MSR(APIC_RRR), + X2APIC_MSR(APIC_LDR), + X2APIC_MSR(APIC_DFR), + X2APIC_MSR(APIC_SPIV), + X2APIC_MSR(APIC_ISR), + X2APIC_MSR(APIC_TMR), + X2APIC_MSR(APIC_IRR), + X2APIC_MSR(APIC_ESR), + X2APIC_MSR(APIC_ICR), + X2APIC_MSR(APIC_ICR2), + + /* + * Note! Always intercept LVTT, as TSC-deadline timer mode + * isn't virtualized by hardware, and the CPU will generate a + * #GP instead of a #VMEXIT. + */ + X2APIC_MSR(APIC_LVTTHMR), + X2APIC_MSR(APIC_LVTPC), + X2APIC_MSR(APIC_LVT0), + X2APIC_MSR(APIC_LVT1), + X2APIC_MSR(APIC_LVTERR), + X2APIC_MSR(APIC_TMICT), + X2APIC_MSR(APIC_TMCCT), + X2APIC_MSR(APIC_TDCR), + }; int i; if (intercept == svm->x2avic_msrs_intercepted) @@ -902,84 +778,79 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept) if (!x2avic_enabled) return; - for (i = 0; i < MAX_DIRECT_ACCESS_MSRS; i++) { - int index = direct_access_msrs[i].index; - - if ((index < APIC_BASE_MSR) || - (index > APIC_BASE_MSR + 0xff)) - continue; - set_msr_interception(&svm->vcpu, svm->msrpm, index, - !intercept, !intercept); - } + for (i = 0; i < ARRAY_SIZE(x2avic_passthrough_msrs); i++) + svm_set_intercept_for_msr(&svm->vcpu, x2avic_passthrough_msrs[i], + MSR_TYPE_RW, intercept); svm->x2avic_msrs_intercepted = intercept; } -void svm_vcpu_free_msrpm(u32 *msrpm) +void svm_vcpu_free_msrpm(void *msrpm) { __free_pages(virt_to_page(msrpm), get_order(MSRPM_SIZE)); } -static void svm_msr_filter_changed(struct kvm_vcpu *vcpu) +static void svm_recalc_msr_intercepts(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - u32 i; - /* - * Set intercept permissions for all direct access MSRs again. They - * will automatically get filtered through the MSR filter, so we are - * back in sync after this. - */ - for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) { - u32 msr = direct_access_msrs[i].index; - u32 read = test_bit(i, svm->shadow_msr_intercept.read); - u32 write = test_bit(i, svm->shadow_msr_intercept.write); - - set_msr_interception_bitmap(vcpu, svm->msrpm, msr, read, write); - } -} - -static void add_msr_offset(u32 offset) -{ - int i; - - for (i = 0; i < MSRPM_OFFSETS; ++i) { + svm_disable_intercept_for_msr(vcpu, MSR_STAR, MSR_TYPE_RW); + svm_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); - /* Offset already in list? */ - if (msrpm_offsets[i] == offset) - return; +#ifdef CONFIG_X86_64 + svm_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW); + svm_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW); + svm_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); + svm_disable_intercept_for_msr(vcpu, MSR_LSTAR, MSR_TYPE_RW); + svm_disable_intercept_for_msr(vcpu, MSR_CSTAR, MSR_TYPE_RW); + svm_disable_intercept_for_msr(vcpu, MSR_SYSCALL_MASK, MSR_TYPE_RW); +#endif - /* Slot used by another offset? */ - if (msrpm_offsets[i] != MSR_INVALID) - continue; + if (lbrv) + svm_recalc_lbr_msr_intercepts(vcpu); - /* Add offset to list */ - msrpm_offsets[i] = offset; + if (cpu_feature_enabled(X86_FEATURE_IBPB)) + svm_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W, + !guest_has_pred_cmd_msr(vcpu)); - return; - } + if (cpu_feature_enabled(X86_FEATURE_FLUSH_L1D)) + svm_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W, + !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)); /* - * If this BUG triggers the msrpm_offsets table has an overflow. Just - * increase MSRPM_OFFSETS in this case. + * Disable interception of SPEC_CTRL if KVM doesn't need to manually + * context switch the MSR (SPEC_CTRL is virtualized by the CPU), or if + * the guest has a non-zero SPEC_CTRL value, i.e. is likely actively + * using SPEC_CTRL. */ - BUG(); -} - -static void init_msrpm_offsets(void) -{ - int i; - - memset(msrpm_offsets, 0xff, sizeof(msrpm_offsets)); + if (cpu_feature_enabled(X86_FEATURE_V_SPEC_CTRL)) + svm_set_intercept_for_msr(vcpu, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW, + !guest_has_spec_ctrl_msr(vcpu)); + else + svm_set_intercept_for_msr(vcpu, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW, + !svm->spec_ctrl); - for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) { - u32 offset; + /* + * Intercept SYSENTER_EIP and SYSENTER_ESP when emulating an Intel CPU, + * as AMD hardware only store 32 bits, whereas Intel CPUs track 64 bits. + */ + svm_set_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW, + guest_cpuid_is_intel_compatible(vcpu)); + svm_set_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW, + guest_cpuid_is_intel_compatible(vcpu)); + + if (kvm_aperfmperf_in_guest(vcpu->kvm)) { + svm_disable_intercept_for_msr(vcpu, MSR_IA32_APERF, MSR_TYPE_R); + svm_disable_intercept_for_msr(vcpu, MSR_IA32_MPERF, MSR_TYPE_R); + } - offset = svm_msrpm_offset(direct_access_msrs[i].index); - BUG_ON(offset == MSR_INVALID); + if (sev_es_guest(vcpu->kvm)) + sev_es_recalc_msr_intercepts(vcpu); - add_msr_offset(offset); - } + /* + * x2APIC intercepts are modified on-demand and cannot be filtered by + * userspace. + */ } void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb) @@ -998,13 +869,7 @@ void svm_enable_lbrv(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); - - if (sev_es_guest(vcpu->kvm)) - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_DEBUGCTLMSR, 1, 1); + svm_recalc_lbr_msr_intercepts(vcpu); /* Move the LBR msrs to the vmcb02 so that the guest can see them. */ if (is_guest_mode(vcpu)) @@ -1016,12 +881,8 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm); - svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK; - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 0, 0); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 0, 0); + svm_recalc_lbr_msr_intercepts(vcpu); /* * Move the LBR msrs back to the vmcb01 to avoid copying them @@ -1176,9 +1037,10 @@ void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu) } /* Evaluate instruction intercepts that depend on guest CPUID features. */ -static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu, - struct vcpu_svm *svm) +static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu) { + struct vcpu_svm *svm = to_svm(vcpu); + /* * Intercept INVPCID if shadow paging is enabled to sync/free shadow * roots, or if INVPCID is disabled in the guest to inject #UD. @@ -1197,24 +1059,11 @@ static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu, else svm_set_intercept(svm, INTERCEPT_RDTSCP); } -} - -static inline void init_vmcb_after_set_cpuid(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); if (guest_cpuid_is_intel_compatible(vcpu)) { - /* - * We must intercept SYSENTER_EIP and SYSENTER_ESP - * accesses because the processor only stores 32 bits. - * For the same reason we cannot use virtual VMLOAD/VMSAVE. - */ svm_set_intercept(svm, INTERCEPT_VMLOAD); svm_set_intercept(svm, INTERCEPT_VMSAVE); svm->vmcb->control.virt_ext &= ~VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; - - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 0, 0); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 0, 0); } else { /* * If hardware supports Virtual VMLOAD VMSAVE then enable it @@ -1225,12 +1074,15 @@ static inline void init_vmcb_after_set_cpuid(struct kvm_vcpu *vcpu) svm_clr_intercept(svm, INTERCEPT_VMSAVE); svm->vmcb->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; } - /* No need to intercept these MSRs */ - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 1, 1); } } +static void svm_recalc_intercepts_after_set_cpuid(struct kvm_vcpu *vcpu) +{ + svm_recalc_instruction_intercepts(vcpu); + svm_recalc_msr_intercepts(vcpu); +} + static void init_vmcb(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1353,15 +1205,6 @@ static void init_vmcb(struct kvm_vcpu *vcpu) svm_clr_intercept(svm, INTERCEPT_PAUSE); } - svm_recalc_instruction_intercepts(vcpu, svm); - - /* - * If the host supports V_SPEC_CTRL then disable the interception - * of MSR_IA32_SPEC_CTRL. - */ - if (boot_cpu_has(X86_FEATURE_V_SPEC_CTRL)) - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1); - if (kvm_vcpu_apicv_active(vcpu)) avic_init_vmcb(svm, vmcb); @@ -1381,7 +1224,8 @@ static void init_vmcb(struct kvm_vcpu *vcpu) sev_init_vmcb(svm); svm_hv_init_vmcb(vmcb); - init_vmcb_after_set_cpuid(vcpu); + + svm_recalc_intercepts_after_set_cpuid(vcpu); vmcb_mark_all_dirty(vmcb); @@ -1392,8 +1236,6 @@ static void __svm_vcpu_reset(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - svm_vcpu_init_msrpm(vcpu, svm->msrpm); - svm_init_osvw(vcpu); if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) @@ -1490,13 +1332,15 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + WARN_ON_ONCE(!list_empty(&svm->ir_list)); + svm_leave_nested(vcpu); svm_free_nested(svm); sev_free_vcpu(vcpu); __free_page(__sme_pa_to_page(svm->vmcb01.pa)); - __free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE)); + svm_vcpu_free_msrpm(svm->msrpm); } #ifdef CONFIG_CPU_MITIGATIONS @@ -2880,12 +2724,11 @@ static int svm_get_feature_msr(u32 msr, u64 *data) return 0; } -static bool -sev_es_prevent_msr_access(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +static bool sev_es_prevent_msr_access(struct kvm_vcpu *vcpu, + struct msr_data *msr_info) { return sev_es_guest(vcpu->kvm) && vcpu->arch.guest_state_protected && - svm_msrpm_offset(msr_info->index) != MSR_INVALID && !msr_write_intercepted(vcpu, msr_info->index); } @@ -3116,11 +2959,11 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) * * For nested: * The handling of the MSR bitmap for L2 guests is done in - * nested_svm_vmrun_msrpm. + * nested_svm_merge_msrpm(). * We update the L1 MSR bit as well since it will end up * touching the MSR anyway now. */ - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1); + svm_disable_intercept_for_msr(vcpu, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW); break; case MSR_AMD64_VIRT_SPEC_CTRL: if (!msr->host_initiated && @@ -3186,8 +3029,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) /* * TSC_AUX is usually changed only during boot and never read - * directly. Intercept TSC_AUX instead of exposing it to the - * guest via direct_access_msrs, and switch it via user return. + * directly. Intercept TSC_AUX and switch it via user return. */ preempt_disable(); ret = kvm_set_user_return_msr(tsc_aux_uret_slot, data, -1ull); @@ -4389,9 +4231,9 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in guest_state_exit_irqoff(); } -static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, - bool force_immediate_exit) +static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) { + bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT; struct vcpu_svm *svm = to_svm(vcpu); bool spec_ctrl_intercepted = msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL); @@ -4438,10 +4280,13 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, svm_hv_update_vp_id(svm->vmcb, vcpu); /* - * Run with all-zero DR6 unless needed, so that we can get the exact cause - * of a #DB. + * Run with all-zero DR6 unless the guest can write DR6 freely, so that + * KVM can get the exact cause of a #DB. Note, loading guest DR6 from + * KVM's snapshot is only necessary when DR accesses won't exit. */ - if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))) + if (unlikely(run_flags & KVM_RUN_LOAD_GUEST_DR6)) + svm_set_dr6(vcpu, vcpu->arch.dr6); + else if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))) svm_set_dr6(vcpu, DR6_ACTIVE_LOW); clgi(); @@ -4621,20 +4466,10 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) if (guest_cpuid_is_intel_compatible(vcpu)) guest_cpu_cap_clear(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD); - svm_recalc_instruction_intercepts(vcpu, svm); - - if (boot_cpu_has(X86_FEATURE_IBPB)) - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0, - !!guest_has_pred_cmd_msr(vcpu)); - - if (boot_cpu_has(X86_FEATURE_FLUSH_L1D)) - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0, - !!guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)); - if (sev_guest(vcpu->kvm)) sev_vcpu_after_set_cpuid(svm); - init_vmcb_after_set_cpuid(vcpu); + svm_recalc_intercepts_after_set_cpuid(vcpu); } static bool svm_has_wbinvd_exit(void) @@ -5185,7 +5020,7 @@ static int svm_vm_init(struct kvm *kvm) } if (!pause_filter_count || !pause_filter_thresh) - kvm->arch.pause_in_guest = true; + kvm_disable_exits(kvm, KVM_X86_DISABLE_EXITS_PAUSE); if (enable_apicv) { int ret = avic_vm_init(kvm); @@ -5252,7 +5087,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .set_idt = svm_set_idt, .get_gdt = svm_get_gdt, .set_gdt = svm_set_gdt, - .set_dr6 = svm_set_dr6, .set_dr7 = svm_set_dr7, .sync_dirty_debug_regs = svm_sync_dirty_debug_regs, .cache_reg = svm_cache_reg, @@ -5337,7 +5171,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .apic_init_signal_blocked = svm_apic_init_signal_blocked, - .msr_filter_changed = svm_msr_filter_changed, + .recalc_msr_intercepts = svm_recalc_msr_intercepts, .complete_emulated_msr = svm_complete_emulated_msr, .vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector, @@ -5473,11 +5307,8 @@ static __init void svm_set_cpu_caps(void) static __init int svm_hardware_setup(void) { - int cpu; - struct page *iopm_pages; void *iopm_va; - int r; - unsigned int order = get_order(IOPM_SIZE); + int cpu, r; /* * NX is required for shadow paging and for NPT if the NX huge pages @@ -5489,17 +5320,6 @@ static __init int svm_hardware_setup(void) } kvm_enable_efer_bits(EFER_NX); - iopm_pages = alloc_pages(GFP_KERNEL, order); - - if (!iopm_pages) - return -ENOMEM; - - iopm_va = page_address(iopm_pages); - memset(iopm_va, 0xff, PAGE_SIZE * (1 << order)); - iopm_base = __sme_page_pa(iopm_pages); - - init_msrpm_offsets(); - kvm_caps.supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); @@ -5533,6 +5353,10 @@ static __init int svm_hardware_setup(void) if (nested) { pr_info("Nested Virtualization enabled\n"); kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE); + + r = nested_svm_init_msrpm_merge_offsets(); + if (r) + return r; } /* @@ -5564,6 +5388,13 @@ static __init int svm_hardware_setup(void) else pr_info("LBR virtualization supported\n"); } + + iopm_va = svm_alloc_permissions_map(IOPM_SIZE, GFP_KERNEL); + if (!iopm_va) + return -ENOMEM; + + iopm_base = __sme_set(__pa(iopm_va)); + /* * Note, SEV setup consumes npt_enabled and enable_mmio_caching (which * may be modified by svm_adjust_mmio_mask()), as well as nrips. @@ -5581,6 +5412,7 @@ static __init int svm_hardware_setup(void) enable_apicv = avic = avic && avic_hardware_setup(); if (!enable_apicv) { + enable_ipiv = false; svm_x86_ops.vcpu_blocking = NULL; svm_x86_ops.vcpu_unblocking = NULL; svm_x86_ops.vcpu_get_apicv_inhibit_reasons = NULL; @@ -5662,6 +5494,8 @@ static int __init svm_init(void) { int r; + KVM_SANITY_CHECK_VM_STRUCT_SIZE(kvm_svm); + __unused_size_checks(); if (!kvm_is_svm_supported()) diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index e6f3c6a153a0..81c7b147b731 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -44,9 +44,6 @@ static inline struct page *__sme_pa_to_page(unsigned long pa) #define IOPM_SIZE PAGE_SIZE * 3 #define MSRPM_SIZE PAGE_SIZE * 2 -#define MAX_DIRECT_ACCESS_MSRS 48 -#define MSRPM_OFFSETS 32 -extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; extern int nrips; extern int vgif; @@ -123,8 +120,8 @@ struct kvm_svm { /* Struct members for AVIC */ u32 avic_vm_id; - struct page *avic_logical_id_table_page; - struct page *avic_physical_id_table_page; + u32 *avic_logical_id_table; + u64 *avic_physical_id_table; struct hlist_node hnode; struct kvm_sev_info sev_info; @@ -189,8 +186,11 @@ struct svm_nested_state { u64 vmcb12_gpa; u64 last_vmcb12_gpa; - /* These are the merged vectors */ - u32 *msrpm; + /* + * The MSR permissions map used for vmcb02, which is the merge result + * of vmcb01 and vmcb12 + */ + void *msrpm; /* A VMRUN has started but has not yet been performed, so * we cannot inject a nested vmexit yet. */ @@ -271,7 +271,7 @@ struct vcpu_svm { */ u64 virt_spec_ctrl; - u32 *msrpm; + void *msrpm; ulong nmi_iret_rip; @@ -306,24 +306,26 @@ struct vcpu_svm { u32 ldr_reg; u32 dfr_reg; - struct page *avic_backing_page; - u64 *avic_physical_id_cache; + + /* This is essentially a shadow of the vCPU's actual entry in the + * Physical ID table that is programmed into the VMCB, i.e. that is + * seen by the CPU. If IPI virtualization is disabled, IsRunning is + * only ever set in the shadow, i.e. is never propagated to the "real" + * table, so that hardware never sees IsRunning=1. + */ + u64 avic_physical_id_entry; /* - * Per-vcpu list of struct amd_svm_iommu_ir: - * This is used mainly to store interrupt remapping information used - * when update the vcpu affinity. This avoids the need to scan for - * IRTE and try to match ga_tag in the IOMMU driver. + * Per-vCPU list of irqfds that are eligible to post IRQs directly to + * the vCPU (a.k.a. device posted IRQs, a.k.a. IRQ bypass). The list + * is used to reconfigure IRTEs when the vCPU is loaded/put (to set the + * target pCPU), when AVIC is toggled on/off (to (de)activate bypass), + * and if the irqfd becomes ineligible for posting (to put the IRTE + * back into remapped mode). */ struct list_head ir_list; spinlock_t ir_list_lock; - /* Save desired MSR intercept (read: pass-through) state */ - struct { - DECLARE_BITMAP(read, MAX_DIRECT_ACCESS_MSRS); - DECLARE_BITMAP(write, MAX_DIRECT_ACCESS_MSRS); - } shadow_msr_intercept; - struct vcpu_sev_es_state sev_es; bool guest_state_loaded; @@ -613,17 +615,74 @@ static inline void svm_vmgexit_no_action(struct vcpu_svm *svm, u64 data) svm_vmgexit_set_return_code(svm, GHCB_HV_RESP_NO_ACTION, data); } -/* svm.c */ -#define MSR_INVALID 0xffffffffU +/* + * The MSRPM is 8KiB in size, divided into four 2KiB ranges (the fourth range + * is reserved). Each MSR within a range is covered by two bits, one each for + * read (bit 0) and write (bit 1), where a bit value of '1' means intercepted. + */ +#define SVM_MSRPM_BYTES_PER_RANGE 2048 +#define SVM_BITS_PER_MSR 2 +#define SVM_MSRS_PER_BYTE (BITS_PER_BYTE / SVM_BITS_PER_MSR) +#define SVM_MSRS_PER_RANGE (SVM_MSRPM_BYTES_PER_RANGE * SVM_MSRS_PER_BYTE) +static_assert(SVM_MSRS_PER_RANGE == 8192); +#define SVM_MSRPM_OFFSET_MASK (SVM_MSRS_PER_RANGE - 1) + +static __always_inline int svm_msrpm_bit_nr(u32 msr) +{ + int range_nr; + + switch (msr & ~SVM_MSRPM_OFFSET_MASK) { + case 0: + range_nr = 0; + break; + case 0xc0000000: + range_nr = 1; + break; + case 0xc0010000: + range_nr = 2; + break; + default: + return -EINVAL; + } + + return range_nr * SVM_MSRPM_BYTES_PER_RANGE * BITS_PER_BYTE + + (msr & SVM_MSRPM_OFFSET_MASK) * SVM_BITS_PER_MSR; +} + +#define __BUILD_SVM_MSR_BITMAP_HELPER(rtype, action, bitop, access, bit_rw) \ +static inline rtype svm_##action##_msr_bitmap_##access(unsigned long *bitmap, \ + u32 msr) \ +{ \ + int bit_nr; \ + \ + bit_nr = svm_msrpm_bit_nr(msr); \ + if (bit_nr < 0) \ + return (rtype)true; \ + \ + return bitop##_bit(bit_nr + bit_rw, bitmap); \ +} + +#define BUILD_SVM_MSR_BITMAP_HELPERS(ret_type, action, bitop) \ + __BUILD_SVM_MSR_BITMAP_HELPER(ret_type, action, bitop, read, 0) \ + __BUILD_SVM_MSR_BITMAP_HELPER(ret_type, action, bitop, write, 1) + +BUILD_SVM_MSR_BITMAP_HELPERS(bool, test, test) +BUILD_SVM_MSR_BITMAP_HELPERS(void, clear, __clear) +BUILD_SVM_MSR_BITMAP_HELPERS(void, set, __set) #define DEBUGCTL_RESERVED_BITS (~DEBUGCTLMSR_LBR) +/* svm.c */ extern bool dump_invalid_vmcb; -u32 svm_msrpm_offset(u32 msr); -u32 *svm_vcpu_alloc_msrpm(void); -void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm); -void svm_vcpu_free_msrpm(u32 *msrpm); +void *svm_alloc_permissions_map(unsigned long size, gfp_t gfp_mask); + +static inline void *svm_vcpu_alloc_msrpm(void) +{ + return svm_alloc_permissions_map(MSRPM_SIZE, GFP_KERNEL_ACCOUNT); +} + +void svm_vcpu_free_msrpm(void *msrpm); void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb); void svm_enable_lbrv(struct kvm_vcpu *vcpu); void svm_update_lbrv(struct kvm_vcpu *vcpu); @@ -643,6 +702,20 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool disable); void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, int trig_mode, int vec); +void svm_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool set); + +static inline void svm_disable_intercept_for_msr(struct kvm_vcpu *vcpu, + u32 msr, int type) +{ + svm_set_intercept_for_msr(vcpu, msr, type, false); +} + +static inline void svm_enable_intercept_for_msr(struct kvm_vcpu *vcpu, + u32 msr, int type) +{ + svm_set_intercept_for_msr(vcpu, msr, type, true); +} + /* nested.c */ #define NESTED_EXIT_HOST 0 /* Exit handled on host level */ @@ -671,6 +744,8 @@ static inline bool nested_exit_on_nmi(struct vcpu_svm *svm) return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_NMI); } +int __init nested_svm_init_msrpm_merge_offsets(void); + int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun); void svm_leave_nested(struct kvm_vcpu *vcpu); @@ -721,7 +796,8 @@ extern struct kvm_x86_nested_ops svm_nested_ops; BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \ BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \ BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED) | \ - BIT(APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED) \ + BIT(APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED) | \ + BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_TOO_BIG) \ ) bool avic_hardware_setup(void); @@ -736,8 +812,9 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void avic_vcpu_put(struct kvm_vcpu *vcpu); void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu); void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu); -int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set); +int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, + unsigned int host_irq, uint32_t guest_irq, + struct kvm_vcpu *vcpu, u32 vector); void avic_vcpu_blocking(struct kvm_vcpu *vcpu); void avic_vcpu_unblocking(struct kvm_vcpu *vcpu); void avic_ring_doorbell(struct kvm_vcpu *vcpu); @@ -752,6 +829,7 @@ void sev_init_vmcb(struct vcpu_svm *svm); void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm); int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); void sev_es_vcpu_reset(struct vcpu_svm *svm); +void sev_es_recalc_msr_intercepts(struct kvm_vcpu *vcpu); void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa); void sev_es_unmap_ghcb(struct vcpu_svm *svm); diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 0c61153b275f..235c4af6b692 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -169,6 +169,9 @@ SYM_FUNC_START(__svm_vcpu_run) #endif mov VCPU_RDI(%_ASM_DI), %_ASM_DI + /* Clobbers EFLAGS.ZF */ + VM_CLEAR_CPU_BUFFERS + /* Enter guest mode */ 3: vmrun %_ASM_AX 4: @@ -335,6 +338,9 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) mov SVM_current_vmcb(%rdi), %rax mov KVM_VMCB_pa(%rax), %rax + /* Clobbers EFLAGS.ZF */ + VM_CLEAR_CPU_BUFFERS + /* Enter guest mode */ 1: vmrun %rax 2: diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index ba736cbb0587..57d79fd31df0 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -260,6 +260,86 @@ TRACE_EVENT(kvm_cpuid, __entry->used_max_basic ? ", used max basic" : "") ); +#define kvm_deliver_mode \ + {0x0, "Fixed"}, \ + {0x1, "LowPrio"}, \ + {0x2, "SMI"}, \ + {0x3, "Res3"}, \ + {0x4, "NMI"}, \ + {0x5, "INIT"}, \ + {0x6, "SIPI"}, \ + {0x7, "ExtINT"} + +#ifdef CONFIG_KVM_IOAPIC +TRACE_EVENT(kvm_ioapic_set_irq, + TP_PROTO(__u64 e, int pin, bool coalesced), + TP_ARGS(e, pin, coalesced), + + TP_STRUCT__entry( + __field( __u64, e ) + __field( int, pin ) + __field( bool, coalesced ) + ), + + TP_fast_assign( + __entry->e = e; + __entry->pin = pin; + __entry->coalesced = coalesced; + ), + + TP_printk("pin %u dst %x vec %u (%s|%s|%s%s)%s", + __entry->pin, (u8)(__entry->e >> 56), (u8)__entry->e, + __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode), + (__entry->e & (1<<11)) ? "logical" : "physical", + (__entry->e & (1<<15)) ? "level" : "edge", + (__entry->e & (1<<16)) ? "|masked" : "", + __entry->coalesced ? " (coalesced)" : "") +); + +TRACE_EVENT(kvm_ioapic_delayed_eoi_inj, + TP_PROTO(__u64 e), + TP_ARGS(e), + + TP_STRUCT__entry( + __field( __u64, e ) + ), + + TP_fast_assign( + __entry->e = e; + ), + + TP_printk("dst %x vec %u (%s|%s|%s%s)", + (u8)(__entry->e >> 56), (u8)__entry->e, + __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode), + (__entry->e & (1<<11)) ? "logical" : "physical", + (__entry->e & (1<<15)) ? "level" : "edge", + (__entry->e & (1<<16)) ? "|masked" : "") +); +#endif + +TRACE_EVENT(kvm_msi_set_irq, + TP_PROTO(__u64 address, __u64 data), + TP_ARGS(address, data), + + TP_STRUCT__entry( + __field( __u64, address ) + __field( __u64, data ) + ), + + TP_fast_assign( + __entry->address = address; + __entry->data = data; + ), + + TP_printk("dst %llx vec %u (%s|%s|%s%s)", + (u8)(__entry->address >> 12) | ((__entry->address >> 32) & 0xffffff00), + (u8)__entry->data, + __print_symbolic((__entry->data >> 8 & 0x7), kvm_deliver_mode), + (__entry->address & (1<<2)) ? "logical" : "physical", + (__entry->data & (1<<15)) ? "level" : "edge", + (__entry->address & (1<<3)) ? "|rh" : "") +); + #define AREG(x) { APIC_##x, "APIC_" #x } #define kvm_trace_symbol_apic \ @@ -1096,37 +1176,32 @@ TRACE_EVENT(kvm_smm_transition, * Tracepoint for VT-d posted-interrupts and AMD-Vi Guest Virtual APIC. */ TRACE_EVENT(kvm_pi_irte_update, - TP_PROTO(unsigned int host_irq, unsigned int vcpu_id, - unsigned int gsi, unsigned int gvec, - u64 pi_desc_addr, bool set), - TP_ARGS(host_irq, vcpu_id, gsi, gvec, pi_desc_addr, set), + TP_PROTO(unsigned int host_irq, struct kvm_vcpu *vcpu, + unsigned int gsi, unsigned int gvec, bool set), + TP_ARGS(host_irq, vcpu, gsi, gvec, set), TP_STRUCT__entry( __field( unsigned int, host_irq ) - __field( unsigned int, vcpu_id ) + __field( int, vcpu_id ) __field( unsigned int, gsi ) __field( unsigned int, gvec ) - __field( u64, pi_desc_addr ) __field( bool, set ) ), TP_fast_assign( __entry->host_irq = host_irq; - __entry->vcpu_id = vcpu_id; + __entry->vcpu_id = vcpu ? vcpu->vcpu_id : -1; __entry->gsi = gsi; __entry->gvec = gvec; - __entry->pi_desc_addr = pi_desc_addr; __entry->set = set; ), - TP_printk("PI is %s for irq %u, vcpu %u, gsi: 0x%x, " - "gvec: 0x%x, pi_desc_addr: 0x%llx", + TP_printk("PI is %s for irq %u, vcpu %d, gsi: 0x%x, gvec: 0x%x", __entry->set ? "enabled and being updated" : "disabled", __entry->host_irq, __entry->vcpu_id, __entry->gsi, - __entry->gvec, - __entry->pi_desc_addr) + __entry->gvec) ); /* diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index cb6588238f46..5316c27f6099 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -15,7 +15,6 @@ extern bool __read_mostly enable_ept; extern bool __read_mostly enable_unrestricted_guest; extern bool __read_mostly enable_ept_ad_bits; extern bool __read_mostly enable_pml; -extern bool __read_mostly enable_ipiv; extern int __read_mostly pt_mode; #define PT_MODE_SYSTEM 0 diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h index a0c5e8781c33..bc5ece76533a 100644 --- a/arch/x86/kvm/vmx/common.h +++ b/arch/x86/kvm/vmx/common.h @@ -53,8 +53,6 @@ struct vcpu_vt { #ifdef CONFIG_X86_64 u64 msr_host_kernel_gs_base; #endif - - unsigned long host_debugctlmsr; }; #ifdef CONFIG_KVM_INTEL_TDX diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index d1e02e567b57..dbab1c15b0cd 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -29,40 +29,8 @@ static __init int vt_hardware_setup(void) if (ret) return ret; - /* - * Update vt_x86_ops::vm_size here so it is ready before - * kvm_ops_update() is called in kvm_x86_vendor_init(). - * - * Note, the actual bringing up of TDX must be done after - * kvm_ops_update() because enabling TDX requires enabling - * hardware virtualization first, i.e., all online CPUs must - * be in post-VMXON state. This means the @vm_size here - * may be updated to TDX's size but TDX may fail to enable - * at later time. - * - * The VMX/VT code could update kvm_x86_ops::vm_size again - * after bringing up TDX, but this would require exporting - * either kvm_x86_ops or kvm_ops_update() from the base KVM - * module, which looks overkill. Anyway, the worst case here - * is KVM may allocate couple of more bytes than needed for - * each VM. - */ - if (enable_tdx) { - vt_x86_ops.vm_size = max_t(unsigned int, vt_x86_ops.vm_size, - sizeof(struct kvm_tdx)); - /* - * Note, TDX may fail to initialize in a later time in - * vt_init(), in which case it is not necessary to setup - * those callbacks. But making them valid here even - * when TDX fails to init later is fine because those - * callbacks won't be called if the VM isn't TDX guest. - */ - vt_x86_ops.link_external_spt = tdx_sept_link_private_spt; - vt_x86_ops.set_external_spte = tdx_sept_set_private_spte; - vt_x86_ops.free_external_spt = tdx_sept_free_private_spt; - vt_x86_ops.remove_external_spte = tdx_sept_remove_private_spte; - vt_x86_ops.protected_apic_has_interrupt = tdx_protected_apic_has_interrupt; - } + if (enable_tdx) + tdx_hardware_setup(); return 0; } @@ -175,12 +143,12 @@ static int vt_vcpu_pre_run(struct kvm_vcpu *vcpu) return vmx_vcpu_pre_run(vcpu); } -static fastpath_t vt_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) +static fastpath_t vt_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) { if (is_td_vcpu(vcpu)) - return tdx_vcpu_run(vcpu, force_immediate_exit); + return tdx_vcpu_run(vcpu, run_flags); - return vmx_vcpu_run(vcpu, force_immediate_exit); + return vmx_vcpu_run(vcpu, run_flags); } static int vt_handle_exit(struct kvm_vcpu *vcpu, @@ -220,7 +188,7 @@ static int vt_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return vmx_get_msr(vcpu, msr_info); } -static void vt_msr_filter_changed(struct kvm_vcpu *vcpu) +static void vt_recalc_msr_intercepts(struct kvm_vcpu *vcpu) { /* * TDX doesn't allow VMM to configure interception of MSR accesses. @@ -231,7 +199,7 @@ static void vt_msr_filter_changed(struct kvm_vcpu *vcpu) if (is_td_vcpu(vcpu)) return; - vmx_msr_filter_changed(vcpu); + vmx_recalc_msr_intercepts(vcpu); } static int vt_complete_emulated_msr(struct kvm_vcpu *vcpu, int err) @@ -489,14 +457,6 @@ static void vt_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) vmx_set_gdt(vcpu, dt); } -static void vt_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) -{ - if (is_td_vcpu(vcpu)) - return; - - vmx_set_dr6(vcpu, val); -} - static void vt_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { if (is_td_vcpu(vcpu)) @@ -923,6 +883,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .vcpu_load = vt_op(vcpu_load), .vcpu_put = vt_op(vcpu_put), + .HOST_OWNED_DEBUGCTL = VMX_HOST_OWNED_DEBUGCTL_BITS, + .update_exception_bitmap = vt_op(update_exception_bitmap), .get_feature_msr = vmx_get_feature_msr, .get_msr = vt_op(get_msr), @@ -943,7 +905,6 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .set_idt = vt_op(set_idt), .get_gdt = vt_op(get_gdt), .set_gdt = vt_op(set_gdt), - .set_dr6 = vt_op(set_dr6), .set_dr7 = vt_op(set_dr7), .sync_dirty_debug_regs = vt_op(sync_dirty_debug_regs), .cache_reg = vt_op(cache_reg), @@ -1014,7 +975,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .nested_ops = &vmx_nested_ops, .pi_update_irte = vmx_pi_update_irte, - .pi_start_assignment = vmx_pi_start_assignment, + .pi_start_bypass = vmx_pi_start_bypass, #ifdef CONFIG_X86_64 .set_hv_timer = vt_op(set_hv_timer), @@ -1034,7 +995,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .apic_init_signal_blocked = vt_op(apic_init_signal_blocked), .migrate_timers = vmx_migrate_timers, - .msr_filter_changed = vt_op(msr_filter_changed), + .recalc_msr_intercepts = vt_op(recalc_msr_intercepts), .complete_emulated_msr = vt_op(complete_emulated_msr), .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 7211c71d4241..b8ea1969113d 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -715,6 +715,12 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_FLUSH_CMD, MSR_TYPE_W); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_APERF, MSR_TYPE_R); + + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_MPERF, MSR_TYPE_R); + kvm_vcpu_unmap(vcpu, &map); vmx->nested.force_msr_bitmap_recalc = false; @@ -2663,10 +2669,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (vmx->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) { kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); - vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl); + vmx_guest_debugctl_write(vcpu, vmcs12->guest_ia32_debugctl & + vmx_get_supported_debugctl(vcpu, false)); } else { kvm_set_dr(vcpu, 7, vcpu->arch.dr7); - vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl); + vmx_guest_debugctl_write(vcpu, vmx->nested.pre_vmenter_debugctl); } if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) @@ -3156,7 +3163,8 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, return -EINVAL; if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) && - CC(!kvm_dr7_valid(vmcs12->guest_dr7))) + (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_IA32_PAT) && @@ -3530,7 +3538,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, if (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) - vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); + vmx->nested.pre_vmenter_debugctl = vmx_guest_debugctl_read(); if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) @@ -4608,6 +4616,12 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) (vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) | (vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE); + /* + * Note! Save DR7, but intentionally don't grab DEBUGCTL from vmcs02. + * Writes to DEBUGCTL that aren't intercepted by L1 are immediately + * propagated to vmcs12 (see vmx_set_msr()), as the value loaded into + * vmcs02 doesn't strictly track vmcs12. + */ if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) vmcs12->guest_dr7 = vcpu->arch.dr7; @@ -4798,7 +4812,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, __vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR); kvm_set_dr(vcpu, 7, 0x400); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + vmx_guest_debugctl_write(vcpu, 0); if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) @@ -4853,6 +4867,9 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7))); } + /* Reload DEBUGCTL to ensure vmcs01 has a fresh FREEZE_IN_SMM value. */ + vmx_reload_guest_debugctl(vcpu); + /* * Note that calling vmx_set_{efer,cr0,cr4} is important as they * handle a variety of side effects to KVM's software model. diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index bbf4509f32d0..0b173602821b 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -653,11 +653,11 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu) */ static void intel_pmu_legacy_freezing_lbrs_on_pmi(struct kvm_vcpu *vcpu) { - u64 data = vmcs_read64(GUEST_IA32_DEBUGCTL); + u64 data = vmx_guest_debugctl_read(); if (data & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) { data &= ~DEBUGCTLMSR_LBR; - vmcs_write64(GUEST_IA32_DEBUGCTL, data); + vmx_guest_debugctl_write(vcpu, data); } } @@ -730,7 +730,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu) if (!lbr_desc->event) { vmx_disable_lbr_msrs_passthrough(vcpu); - if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR) + if (vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR) goto warn; if (test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use)) goto warn; @@ -752,7 +752,7 @@ warn: static void intel_pmu_cleanup(struct kvm_vcpu *vcpu) { - if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR)) + if (!(vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR)) intel_pmu_release_guest_lbr_event(vcpu); } diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 5c615e5845bf..4a6d9a17da23 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -2,6 +2,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> +#include <linux/kvm_irqfd.h> #include <asm/irq_remapping.h> #include <asm/cpu.h> @@ -72,13 +73,10 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) /* * If the vCPU wasn't on the wakeup list and wasn't migrated, then the * full update can be skipped as neither the vector nor the destination - * needs to be changed. + * needs to be changed. Clear SN even if there is no assigned device, + * again for simplicity. */ if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR && vcpu->cpu == cpu) { - /* - * Clear SN if it was set due to being preempted. Again, do - * this even if there is no assigned device for simplicity. - */ if (pi_test_and_clear_sn(pi_desc)) goto after_clear_sn; return; @@ -148,8 +146,13 @@ after_clear_sn: static bool vmx_can_use_vtd_pi(struct kvm *kvm) { + /* + * Note, reading the number of possible bypass IRQs can race with a + * bypass IRQ being attached to the VM. vmx_pi_start_bypass() ensures + * blockng vCPUs will see an elevated count or get KVM_REQ_UNBLOCK. + */ return irqchip_in_kernel(kvm) && kvm_arch_has_irq_bypass() && - kvm_arch_has_assigned_device(kvm); + READ_ONCE(kvm->arch.nr_possible_bypass_irqs); } /* @@ -224,17 +227,23 @@ void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) if (!vmx_needs_pi_wakeup(vcpu)) return; - if (kvm_vcpu_is_blocking(vcpu) && + /* + * If the vCPU is blocking with IRQs enabled and ISN'T being preempted, + * enable the wakeup handler so that notification IRQ wakes the vCPU as + * expected. There is no need to enable the wakeup handler if the vCPU + * is preempted between setting its wait state and manually scheduling + * out, as the task is still runnable, i.e. doesn't need a wake event + * from KVM to be scheduled in. + * + * If the wakeup handler isn't being enabled, Suppress Notifications as + * the cost of propagating PIR.IRR to PID.ON is negligible compared to + * the cost of a spurious IRQ, and vCPU put/load is a slow path. + */ + if (!vcpu->preempted && kvm_vcpu_is_blocking(vcpu) && ((is_td_vcpu(vcpu) && tdx_interrupt_allowed(vcpu)) || (!is_td_vcpu(vcpu) && !vmx_interrupt_blocked(vcpu)))) pi_enable_wakeup_handler(vcpu); - - /* - * Set SN when the vCPU is preempted. Note, the vCPU can both be seen - * as blocking and preempted, e.g. if it's preempted between setting - * its wait state and manually scheduling out. - */ - if (vcpu->preempted) + else pi_set_sn(pi_desc); } @@ -281,99 +290,30 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu) /* - * Bail out of the block loop if the VM has an assigned - * device, but the blocking vCPU didn't reconfigure the - * PI.NV to the wakeup vector, i.e. the assigned device - * came along after the initial check in vmx_vcpu_pi_put(). + * Kick all vCPUs when the first possible bypass IRQ is attached to a VM, as + * blocking vCPUs may scheduled out without reconfiguring PID.NV to the wakeup + * vector, i.e. if the bypass IRQ came along after vmx_vcpu_pi_put(). */ -void vmx_pi_start_assignment(struct kvm *kvm) +void vmx_pi_start_bypass(struct kvm *kvm) { - if (!kvm_arch_has_irq_bypass()) + if (WARN_ON_ONCE(!vmx_can_use_vtd_pi(kvm))) return; kvm_make_all_cpus_request(kvm, KVM_REQ_UNBLOCK); } -/* - * vmx_pi_update_irte - set IRTE for Posted-Interrupts - * - * @kvm: kvm - * @host_irq: host irq of the interrupt - * @guest_irq: gsi of the interrupt - * @set: set or unset PI - * returns 0 on success, < 0 on failure - */ -int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set) +int vmx_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, + unsigned int host_irq, uint32_t guest_irq, + struct kvm_vcpu *vcpu, u32 vector) { - struct kvm_kernel_irq_routing_entry *e; - struct kvm_irq_routing_table *irq_rt; - bool enable_remapped_mode = true; - struct kvm_lapic_irq irq; - struct kvm_vcpu *vcpu; - struct vcpu_data vcpu_info; - int idx, ret = 0; - - if (!vmx_can_use_vtd_pi(kvm)) - return 0; - - idx = srcu_read_lock(&kvm->irq_srcu); - irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); - if (guest_irq >= irq_rt->nr_rt_entries || - hlist_empty(&irq_rt->map[guest_irq])) { - pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n", - guest_irq, irq_rt->nr_rt_entries); - goto out; + if (vcpu) { + struct intel_iommu_pi_data pi_data = { + .pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu)), + .vector = vector, + }; + + return irq_set_vcpu_affinity(host_irq, &pi_data); + } else { + return irq_set_vcpu_affinity(host_irq, NULL); } - - hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) { - if (e->type != KVM_IRQ_ROUTING_MSI) - continue; - /* - * VT-d PI cannot support posting multicast/broadcast - * interrupts to a vCPU, we still use interrupt remapping - * for these kind of interrupts. - * - * For lowest-priority interrupts, we only support - * those with single CPU as the destination, e.g. user - * configures the interrupts via /proc/irq or uses - * irqbalance to make the interrupts single-CPU. - * - * We will support full lowest-priority interrupt later. - * - * In addition, we can only inject generic interrupts using - * the PI mechanism, refuse to route others through it. - */ - - kvm_set_msi_irq(kvm, e, &irq); - if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) || - !kvm_irq_is_postable(&irq)) - continue; - - vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu)); - vcpu_info.vector = irq.vector; - - trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi, - vcpu_info.vector, vcpu_info.pi_desc_addr, set); - - if (!set) - continue; - - enable_remapped_mode = false; - - ret = irq_set_vcpu_affinity(host_irq, &vcpu_info); - if (ret < 0) { - printk(KERN_INFO "%s: failed to update PI IRTE\n", - __func__); - goto out; - } - } - - if (enable_remapped_mode) - ret = irq_set_vcpu_affinity(host_irq, NULL); - - ret = 0; -out: - srcu_read_unlock(&kvm->irq_srcu, idx); - return ret; } diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 80499ea0e674..a4af39948cf0 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -3,6 +3,9 @@ #define __KVM_X86_VMX_POSTED_INTR_H #include <linux/bitmap.h> +#include <linux/find.h> +#include <linux/kvm_host.h> + #include <asm/posted_intr.h> void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu); @@ -11,9 +14,10 @@ void pi_wakeup_handler(void); void __init pi_init_cpu(int cpu); void pi_apicv_pre_state_restore(struct kvm_vcpu *vcpu); bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu); -int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set); -void vmx_pi_start_assignment(struct kvm *kvm); +int vmx_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, + unsigned int host_irq, uint32_t guest_irq, + struct kvm_vcpu *vcpu, u32 vector); +void vmx_pi_start_bypass(struct kvm *kvm); static inline int pi_find_highest_vector(struct pi_desc *pi_desc) { diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h index 6a9bfdfbb6e5..2f20fb170def 100644 --- a/arch/x86/kvm/vmx/run_flags.h +++ b/arch/x86/kvm/vmx/run_flags.h @@ -2,10 +2,12 @@ #ifndef __KVM_X86_VMX_RUN_FLAGS_H #define __KVM_X86_VMX_RUN_FLAGS_H -#define VMX_RUN_VMRESUME_SHIFT 0 -#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT 1 +#define VMX_RUN_VMRESUME_SHIFT 0 +#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT 1 +#define VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO_SHIFT 2 -#define VMX_RUN_VMRESUME BIT(VMX_RUN_VMRESUME_SHIFT) -#define VMX_RUN_SAVE_SPEC_CTRL BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT) +#define VMX_RUN_VMRESUME BIT(VMX_RUN_VMRESUME_SHIFT) +#define VMX_RUN_SAVE_SPEC_CTRL BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT) +#define VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO BIT(VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO_SHIFT) #endif /* __KVM_X86_VMX_RUN_FLAGS_H */ diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index 1ad20c273f3b..66744f5768c8 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -173,6 +173,8 @@ static void td_init_cpuid_entry2(struct kvm_cpuid_entry2 *entry, unsigned char i tdx_clear_unsupported_cpuid(entry); } +#define TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT BIT(1) + static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf, struct kvm_tdx_capabilities *caps) { @@ -188,6 +190,9 @@ static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf, caps->cpuid.nent = td_conf->num_cpuid_config; + caps->user_tdvmcallinfo_1_r11 = + TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT; + for (i = 0; i < td_conf->num_cpuid_config; i++) td_init_cpuid_entry2(&caps->cpuid.entries[i], i); @@ -738,7 +743,7 @@ bool tdx_interrupt_allowed(struct kvm_vcpu *vcpu) !to_tdx(vcpu)->vp_enter_args.r12; } -bool tdx_protected_apic_has_interrupt(struct kvm_vcpu *vcpu) +static bool tdx_protected_apic_has_interrupt(struct kvm_vcpu *vcpu) { u64 vcpu_state_details; @@ -778,8 +783,6 @@ void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) else vt->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); - vt->host_debugctlmsr = get_debugctlmsr(); - vt->guest_state_loaded = true; } @@ -1020,20 +1023,20 @@ static void tdx_load_host_xsave_state(struct kvm_vcpu *vcpu) DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI | \ DEBUGCTLMSR_FREEZE_IN_SMM) -fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) +fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) { struct vcpu_tdx *tdx = to_tdx(vcpu); struct vcpu_vt *vt = to_vt(vcpu); /* - * force_immediate_exit requires vCPU entering for events injection with - * an immediately exit followed. But The TDX module doesn't guarantee - * entry, it's already possible for KVM to _think_ it completely entry - * to the guest without actually having done so. - * Since KVM never needs to force an immediate exit for TDX, and can't - * do direct injection, just warn on force_immediate_exit. + * WARN if KVM wants to force an immediate exit, as the TDX module does + * not guarantee entry into the guest, i.e. it's possible for KVM to + * _think_ it completed entry to the guest and forced an immediate exit + * without actually having done so. Luckily, KVM never needs to force + * an immediate exit for TDX (KVM can't do direct event injection, so + * just WARN and continue on. */ - WARN_ON_ONCE(force_immediate_exit); + WARN_ON_ONCE(run_flags); /* * Wait until retry of SEPT-zap-related SEAMCALL completes before @@ -1043,7 +1046,7 @@ fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) if (unlikely(READ_ONCE(to_kvm_tdx(vcpu->kvm)->wait_for_sept_zap))) return EXIT_FASTPATH_EXIT_HANDLED; - trace_kvm_entry(vcpu, force_immediate_exit); + trace_kvm_entry(vcpu, run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT); if (pi_test_on(&vt->pi_desc)) { apic->send_IPI_self(POSTED_INTR_VECTOR); @@ -1055,8 +1058,8 @@ fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) tdx_vcpu_enter_exit(vcpu); - if (vt->host_debugctlmsr & ~TDX_DEBUGCTL_PRESERVED) - update_debugctlmsr(vt->host_debugctlmsr); + if (vcpu->arch.host_debugctl & ~TDX_DEBUGCTL_PRESERVED) + update_debugctlmsr(vcpu->arch.host_debugctl); tdx_load_host_xsave_state(vcpu); tdx->guest_entered = true; @@ -1530,6 +1533,27 @@ static int tdx_get_quote(struct kvm_vcpu *vcpu) return 0; } +static int tdx_setup_event_notify_interrupt(struct kvm_vcpu *vcpu) +{ + struct vcpu_tdx *tdx = to_tdx(vcpu); + u64 vector = tdx->vp_enter_args.r12; + + if (vector < 32 || vector > 255) { + tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND); + return 1; + } + + vcpu->run->exit_reason = KVM_EXIT_TDX; + vcpu->run->tdx.flags = 0; + vcpu->run->tdx.nr = TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT; + vcpu->run->tdx.setup_event_notify.ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED; + vcpu->run->tdx.setup_event_notify.vector = vector; + + vcpu->arch.complete_userspace_io = tdx_complete_simple; + + return 0; +} + static int handle_tdvmcall(struct kvm_vcpu *vcpu) { switch (tdvmcall_leaf(vcpu)) { @@ -1541,6 +1565,8 @@ static int handle_tdvmcall(struct kvm_vcpu *vcpu) return tdx_get_td_vm_call_info(vcpu); case TDVMCALL_GET_QUOTE: return tdx_get_quote(vcpu); + case TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT: + return tdx_setup_event_notify_interrupt(vcpu); default: break; } @@ -1612,8 +1638,8 @@ static int tdx_mem_page_record_premap_cnt(struct kvm *kvm, gfn_t gfn, return 0; } -int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn, - enum pg_level level, kvm_pfn_t pfn) +static int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn, + enum pg_level level, kvm_pfn_t pfn) { struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); struct page *page = pfn_to_page(pfn); @@ -1693,8 +1719,8 @@ static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn, return 0; } -int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn, - enum pg_level level, void *private_spt) +static int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn, + enum pg_level level, void *private_spt) { int tdx_level = pg_level_to_tdx_sept_level(level); gpa_t gpa = gfn_to_gpa(gfn); @@ -1829,8 +1855,8 @@ static void tdx_track(struct kvm *kvm) kvm_make_all_cpus_request(kvm, KVM_REQ_OUTSIDE_GUEST_MODE); } -int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn, - enum pg_level level, void *private_spt) +static int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn, + enum pg_level level, void *private_spt) { struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); @@ -1852,8 +1878,8 @@ int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn, return tdx_reclaim_page(virt_to_page(private_spt)); } -int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn, - enum pg_level level, kvm_pfn_t pfn) +static int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn, + enum pg_level level, kvm_pfn_t pfn) { struct page *page = pfn_to_page(pfn); int ret; @@ -2241,25 +2267,26 @@ static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd) const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf; struct kvm_tdx_capabilities __user *user_caps; struct kvm_tdx_capabilities *caps = NULL; + u32 nr_user_entries; int ret = 0; /* flags is reserved for future use */ if (cmd->flags) return -EINVAL; - caps = kmalloc(sizeof(*caps) + + caps = kzalloc(sizeof(*caps) + sizeof(struct kvm_cpuid_entry2) * td_conf->num_cpuid_config, GFP_KERNEL); if (!caps) return -ENOMEM; user_caps = u64_to_user_ptr(cmd->data); - if (copy_from_user(caps, user_caps, sizeof(*caps))) { + if (get_user(nr_user_entries, &user_caps->cpuid.nent)) { ret = -EFAULT; goto out; } - if (caps->cpuid.nent < td_conf->num_cpuid_config) { + if (nr_user_entries < td_conf->num_cpuid_config) { ret = -E2BIG; goto out; } @@ -3576,10 +3603,14 @@ int __init tdx_bringup(void) r = __tdx_bringup(); if (r) { /* - * Disable TDX only but don't fail to load module if - * the TDX module could not be loaded. No need to print - * message saying "module is not loaded" because it was - * printed when the first SEAMCALL failed. + * Disable TDX only but don't fail to load module if the TDX + * module could not be loaded. No need to print message saying + * "module is not loaded" because it was printed when the first + * SEAMCALL failed. Don't bother unwinding the S-EPT hooks or + * vm_size, as kvm_x86_ops have already been finalized (and are + * intentionally not exported). The S-EPT code is unreachable, + * and allocating a few more bytes per VM in a should-be-rare + * failure scenario is a non-issue. */ if (r == -ENODEV) goto success_disable_tdx; @@ -3593,3 +3624,20 @@ success_disable_tdx: enable_tdx = 0; return 0; } + +void __init tdx_hardware_setup(void) +{ + KVM_SANITY_CHECK_VM_STRUCT_SIZE(kvm_tdx); + + /* + * Note, if the TDX module can't be loaded, KVM TDX support will be + * disabled but KVM will continue loading (see tdx_bringup()). + */ + vt_x86_ops.vm_size = max_t(unsigned int, vt_x86_ops.vm_size, sizeof(struct kvm_tdx)); + + vt_x86_ops.link_external_spt = tdx_sept_link_private_spt; + vt_x86_ops.set_external_spte = tdx_sept_set_private_spte; + vt_x86_ops.free_external_spt = tdx_sept_free_private_spt; + vt_x86_ops.remove_external_spte = tdx_sept_remove_private_spte; + vt_x86_ops.protected_apic_has_interrupt = tdx_protected_apic_has_interrupt; +} diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h index 51f98443e8a2..ca39a9391db1 100644 --- a/arch/x86/kvm/vmx/tdx.h +++ b/arch/x86/kvm/vmx/tdx.h @@ -8,6 +8,7 @@ #ifdef CONFIG_KVM_INTEL_TDX #include "common.h" +void tdx_hardware_setup(void); int tdx_bringup(void); void tdx_cleanup(void); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 4953846cb30d..aa157fe5b7b3 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -75,6 +75,8 @@ #include "vmx_onhyperv.h" #include "posted_intr.h" +#include "mmu/spte.h" + MODULE_AUTHOR("Qumranet"); MODULE_DESCRIPTION("KVM support for VMX (Intel VT-x) extensions"); MODULE_LICENSE("GPL"); @@ -113,8 +115,6 @@ static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, 0444); module_param(enable_apicv, bool, 0444); - -bool __read_mostly enable_ipiv = true; module_param(enable_ipiv, bool, 0444); module_param(enable_device_posted_irqs, bool, 0444); @@ -168,31 +168,6 @@ module_param(allow_smaller_maxphyaddr, bool, S_IRUGO); RTIT_STATUS_BYTECNT)) /* - * List of MSRs that can be directly passed to the guest. - * In addition to these x2apic, PT and LBR MSRs are handled specially. - */ -static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = { - MSR_IA32_SPEC_CTRL, - MSR_IA32_PRED_CMD, - MSR_IA32_FLUSH_CMD, - MSR_IA32_TSC, -#ifdef CONFIG_X86_64 - MSR_FS_BASE, - MSR_GS_BASE, - MSR_KERNEL_GS_BASE, - MSR_IA32_XFD, - MSR_IA32_XFD_ERR, -#endif - MSR_IA32_SYSENTER_CS, - MSR_IA32_SYSENTER_ESP, - MSR_IA32_SYSENTER_EIP, - MSR_CORE_C1_RES, - MSR_CORE_C3_RESIDENCY, - MSR_CORE_C6_RESIDENCY, - MSR_CORE_C7_RESIDENCY, -}; - -/* * These 2 parameters are used to config the controls for Pause-Loop Exiting: * ple_gap: upper bound on the amount of time between two successive * executions of PAUSE in a loop. Also indicate if ple enabled. @@ -674,40 +649,6 @@ static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu) return flexpriority_enabled && lapic_in_kernel(vcpu); } -static int vmx_get_passthrough_msr_slot(u32 msr) -{ - int i; - - switch (msr) { - case 0x800 ... 0x8ff: - /* x2APIC MSRs. These are handled in vmx_update_msr_bitmap_x2apic() */ - return -ENOENT; - case MSR_IA32_RTIT_STATUS: - case MSR_IA32_RTIT_OUTPUT_BASE: - case MSR_IA32_RTIT_OUTPUT_MASK: - case MSR_IA32_RTIT_CR3_MATCH: - case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: - /* PT MSRs. These are handled in pt_update_intercept_for_msr() */ - case MSR_LBR_SELECT: - case MSR_LBR_TOS: - case MSR_LBR_INFO_0 ... MSR_LBR_INFO_0 + 31: - case MSR_LBR_NHM_FROM ... MSR_LBR_NHM_FROM + 31: - case MSR_LBR_NHM_TO ... MSR_LBR_NHM_TO + 31: - case MSR_LBR_CORE_FROM ... MSR_LBR_CORE_FROM + 8: - case MSR_LBR_CORE_TO ... MSR_LBR_CORE_TO + 8: - /* LBR MSRs. These are handled in vmx_update_intercept_for_lbr_msrs() */ - return -ENOENT; - } - - for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) { - if (vmx_possible_passthrough_msrs[i] == msr) - return i; - } - - WARN(1, "Invalid MSR %x, please adapt vmx_possible_passthrough_msrs[]", msr); - return -ENOENT; -} - struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) { int i; @@ -963,6 +904,10 @@ unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx) if (!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL)) flags |= VMX_RUN_SAVE_SPEC_CTRL; + if (static_branch_unlikely(&cpu_buf_vm_clear) && + kvm_vcpu_can_access_host_mmio(&vmx->vcpu)) + flags |= VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO; + return flags; } @@ -2149,7 +2094,7 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vmx->pt_desc.guest.addr_a[index / 2]; break; case MSR_IA32_DEBUGCTLMSR: - msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL); + msr_info->data = vmx_guest_debugctl_read(); break; default: find_uret_msr: @@ -2174,7 +2119,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, return (unsigned long)data; } -static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) +u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) { u64 debugctl = 0; @@ -2186,9 +2131,25 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated (host_initiated || intel_pmu_lbr_is_enabled(vcpu))) debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI; + if (boot_cpu_has(X86_FEATURE_RTM) && + (host_initiated || guest_cpu_cap_has(vcpu, X86_FEATURE_RTM))) + debugctl |= DEBUGCTLMSR_RTM_DEBUG; + return debugctl; } +bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated) +{ + u64 invalid; + + invalid = data & ~vmx_get_supported_debugctl(vcpu, host_initiated); + if (invalid & (DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR)) { + kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data); + invalid &= ~(DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR); + } + return !invalid; +} + /* * Writes msr value into the appropriate "register". * Returns 0 on success, non-0 otherwise. @@ -2257,29 +2218,22 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } vmcs_writel(GUEST_SYSENTER_ESP, data); break; - case MSR_IA32_DEBUGCTLMSR: { - u64 invalid; - - invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); - if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) { - kvm_pr_unimpl_wrmsr(vcpu, msr_index, data); - data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); - invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); - } - - if (invalid) + case MSR_IA32_DEBUGCTLMSR: + if (!vmx_is_valid_debugctl(vcpu, data, msr_info->host_initiated)) return 1; + data &= vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); + if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) get_vmcs12(vcpu)->guest_ia32_debugctl = data; - vmcs_write64(GUEST_IA32_DEBUGCTL, data); + vmx_guest_debugctl_write(vcpu, data); + if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event && (data & DEBUGCTLMSR_LBR)) intel_pmu_create_guest_lbr_event(vcpu); return 0; - } case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && @@ -4013,76 +3967,29 @@ static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx) vmx->nested.force_msr_bitmap_recalc = true; } -void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) +void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool set) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; - int idx; if (!cpu_has_vmx_msr_bitmap()) return; vmx_msr_bitmap_l01_changed(vmx); - /* - * Mark the desired intercept state in shadow bitmap, this is needed - * for resync when the MSR filters change. - */ - idx = vmx_get_passthrough_msr_slot(msr); - if (idx >= 0) { - if (type & MSR_TYPE_R) - clear_bit(idx, vmx->shadow_msr_intercept.read); - if (type & MSR_TYPE_W) - clear_bit(idx, vmx->shadow_msr_intercept.write); - } - - if ((type & MSR_TYPE_R) && - !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ)) { - vmx_set_msr_bitmap_read(msr_bitmap, msr); - type &= ~MSR_TYPE_R; - } - - if ((type & MSR_TYPE_W) && - !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE)) { - vmx_set_msr_bitmap_write(msr_bitmap, msr); - type &= ~MSR_TYPE_W; + if (type & MSR_TYPE_R) { + if (!set && kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ)) + vmx_clear_msr_bitmap_read(msr_bitmap, msr); + else + vmx_set_msr_bitmap_read(msr_bitmap, msr); } - if (type & MSR_TYPE_R) - vmx_clear_msr_bitmap_read(msr_bitmap, msr); - - if (type & MSR_TYPE_W) - vmx_clear_msr_bitmap_write(msr_bitmap, msr); -} - -void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; - int idx; - - if (!cpu_has_vmx_msr_bitmap()) - return; - - vmx_msr_bitmap_l01_changed(vmx); - - /* - * Mark the desired intercept state in shadow bitmap, this is needed - * for resync when the MSR filter changes. - */ - idx = vmx_get_passthrough_msr_slot(msr); - if (idx >= 0) { - if (type & MSR_TYPE_R) - set_bit(idx, vmx->shadow_msr_intercept.read); - if (type & MSR_TYPE_W) - set_bit(idx, vmx->shadow_msr_intercept.write); + if (type & MSR_TYPE_W) { + if (!set && kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE)) + vmx_clear_msr_bitmap_write(msr_bitmap, msr); + else + vmx_set_msr_bitmap_write(msr_bitmap, msr); } - - if (type & MSR_TYPE_R) - vmx_set_msr_bitmap_read(msr_bitmap, msr); - - if (type & MSR_TYPE_W) - vmx_set_msr_bitmap_write(msr_bitmap, msr); } static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu) @@ -4161,35 +4068,57 @@ void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu) } } -void vmx_msr_filter_changed(struct kvm_vcpu *vcpu) +void vmx_recalc_msr_intercepts(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 i; - if (!cpu_has_vmx_msr_bitmap()) return; - /* - * Redo intercept permissions for MSRs that KVM is passing through to - * the guest. Disabling interception will check the new MSR filter and - * ensure that KVM enables interception if usersepace wants to filter - * the MSR. MSRs that KVM is already intercepting don't need to be - * refreshed since KVM is going to intercept them regardless of what - * userspace wants. - */ - for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) { - u32 msr = vmx_possible_passthrough_msrs[i]; - - if (!test_bit(i, vmx->shadow_msr_intercept.read)) - vmx_disable_intercept_for_msr(vcpu, msr, MSR_TYPE_R); - - if (!test_bit(i, vmx->shadow_msr_intercept.write)) - vmx_disable_intercept_for_msr(vcpu, msr, MSR_TYPE_W); + vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R); +#ifdef CONFIG_X86_64 + vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); +#endif + vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); + if (kvm_cstate_in_guest(vcpu->kvm)) { + vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C1_RES, MSR_TYPE_R); + vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R); + vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R); + vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R); + } + if (kvm_aperfmperf_in_guest(vcpu->kvm)) { + vmx_disable_intercept_for_msr(vcpu, MSR_IA32_APERF, MSR_TYPE_R); + vmx_disable_intercept_for_msr(vcpu, MSR_IA32_MPERF, MSR_TYPE_R); } /* PT MSRs can be passed through iff PT is exposed to the guest. */ if (vmx_pt_mode_is_host_guest()) pt_update_intercept_for_msr(vcpu); + + if (vcpu->arch.xfd_no_write_intercept) + vmx_disable_intercept_for_msr(vcpu, MSR_IA32_XFD, MSR_TYPE_RW); + + vmx_set_intercept_for_msr(vcpu, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW, + !to_vmx(vcpu)->spec_ctrl); + + if (kvm_cpu_cap_has(X86_FEATURE_XFD)) + vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R, + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)); + + if (cpu_feature_enabled(X86_FEATURE_IBPB)) + vmx_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W, + !guest_has_pred_cmd_msr(vcpu)); + + if (cpu_feature_enabled(X86_FEATURE_FLUSH_L1D)) + vmx_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W, + !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)); + + /* + * x2APIC and LBR MSR intercepts are modified on-demand and cannot be + * filtered by userspace. + */ } static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, @@ -4790,7 +4719,8 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmcs_write32(GUEST_SYSENTER_CS, 0); vmcs_writel(GUEST_SYSENTER_ESP, 0); vmcs_writel(GUEST_SYSENTER_EIP, 0); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + + vmx_guest_debugctl_write(&vmx->vcpu, 0); if (cpu_has_vmx_tpr_shadow()) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); @@ -5606,12 +5536,6 @@ void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) set_debugreg(DR6_RESERVED, 6); } -void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) -{ - lockdep_assert_irqs_disabled(); - set_debugreg(vcpu->arch.dr6, 6); -} - void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { vmcs_writel(GUEST_DR7, val); @@ -7290,8 +7214,8 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); else if (static_branch_unlikely(&cpu_buf_vm_clear) && - kvm_arch_has_assigned_device(vcpu->kvm)) - mds_clear_cpu_buffers(); + (flags & VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO)) + x86_clear_cpu_buffers(); vmx_disable_fb_clear(vmx); @@ -7323,8 +7247,9 @@ out: guest_state_exit_irqoff(); } -fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) +fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) { + bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT; struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; @@ -7369,6 +7294,12 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); vcpu->arch.regs_dirty = 0; + if (run_flags & KVM_RUN_LOAD_GUEST_DR6) + set_debugreg(vcpu->arch.dr6, 6); + + if (run_flags & KVM_RUN_LOAD_DEBUGCTL) + vmx_reload_guest_debugctl(vcpu); + /* * Refresh vmcs.HOST_CR3 if necessary. This must be done immediately * prior to VM-Enter, as the kernel may load a new ASID (PCID) any time @@ -7543,26 +7474,6 @@ int vmx_vcpu_create(struct kvm_vcpu *vcpu) evmcs->hv_enlightenments_control.msr_bitmap = 1; } - /* The MSR bitmap starts with all ones */ - bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS); - bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS); - - vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R); -#ifdef CONFIG_X86_64 - vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); -#endif - vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); - if (kvm_cstate_in_guest(vcpu->kvm)) { - vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C1_RES, MSR_TYPE_R); - vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R); - vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R); - vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R); - } - vmx->loaded_vmcs = &vmx->vmcs01; if (cpu_need_virtualize_apic_accesses(vcpu)) { @@ -7612,7 +7523,7 @@ free_vpid: int vmx_vm_init(struct kvm *kvm) { if (!ple_gap) - kvm->arch.pause_in_guest = true; + kvm_disable_exits(kvm, KVM_X86_DISABLE_EXITS_PAUSE); if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) { switch (l1tf_mitigation) { @@ -7849,18 +7760,6 @@ void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) } } - if (kvm_cpu_cap_has(X86_FEATURE_XFD)) - vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R, - !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)); - - if (boot_cpu_has(X86_FEATURE_IBPB)) - vmx_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W, - !guest_has_pred_cmd_msr(vcpu)); - - if (boot_cpu_has(X86_FEATURE_FLUSH_L1D)) - vmx_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W, - !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)); - set_cr4_guest_host_mask(vmx); vmx_write_encls_bitmap(vcpu, NULL); @@ -7876,6 +7775,9 @@ void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmx->msr_ia32_feature_control_valid_bits &= ~FEAT_CTL_SGX_LC_ENABLED; + /* Recalc MSR interception to account for feature changes. */ + vmx_recalc_msr_intercepts(vcpu); + /* Refresh #PF interception to account for MAXPHYADDR changes. */ vmx_update_exception_bitmap(vcpu); } @@ -8650,6 +8552,8 @@ int __init vmx_init(void) { int r, cpu; + KVM_SANITY_CHECK_VM_STRUCT_SIZE(kvm_vmx); + if (!kvm_is_vmx_supported()) return -EOPNOTSUPP; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index b5758c33c60f..d3389baf3ab3 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -19,8 +19,6 @@ #include "../mmu.h" #include "common.h" -#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) - #ifdef CONFIG_X86_64 #define MAX_NR_USER_RETURN_MSRS 7 #else @@ -296,13 +294,6 @@ struct vcpu_vmx { struct pt_desc pt_desc; struct lbr_desc lbr_desc; - /* Save desired MSR intercept (read: pass-through) state */ -#define MAX_POSSIBLE_PASSTHROUGH_MSRS 16 - struct { - DECLARE_BITMAP(read, MAX_POSSIBLE_PASSTHROUGH_MSRS); - DECLARE_BITMAP(write, MAX_POSSIBLE_PASSTHROUGH_MSRS); - } shadow_msr_intercept; - /* ve_info must be page aligned. */ struct vmx_ve_information *ve_info; }; @@ -395,24 +386,54 @@ bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr); void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu); -void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type); -void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type); +void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool set); + +static inline void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, + u32 msr, int type) +{ + vmx_set_intercept_for_msr(vcpu, msr, type, false); +} + +static inline void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, + u32 msr, int type) +{ + vmx_set_intercept_for_msr(vcpu, msr, type, true); +} u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu); u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu); gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags); -static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, - int type, bool value) +void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); + +u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated); +bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated); + +#define VMX_HOST_OWNED_DEBUGCTL_BITS (DEBUGCTLMSR_FREEZE_IN_SMM) + +static inline void vmx_guest_debugctl_write(struct kvm_vcpu *vcpu, u64 val) { - if (value) - vmx_enable_intercept_for_msr(vcpu, msr, type); - else - vmx_disable_intercept_for_msr(vcpu, msr, type); + WARN_ON_ONCE(val & VMX_HOST_OWNED_DEBUGCTL_BITS); + + val |= vcpu->arch.host_debugctl & VMX_HOST_OWNED_DEBUGCTL_BITS; + vmcs_write64(GUEST_IA32_DEBUGCTL, val); } -void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); +static inline u64 vmx_guest_debugctl_read(void) +{ + return vmcs_read64(GUEST_IA32_DEBUGCTL) & ~VMX_HOST_OWNED_DEBUGCTL_BITS; +} + +static inline void vmx_reload_guest_debugctl(struct kvm_vcpu *vcpu) +{ + u64 val = vmcs_read64(GUEST_IA32_DEBUGCTL); + + if (!((val ^ vcpu->arch.host_debugctl) & VMX_HOST_OWNED_DEBUGCTL_BITS)) + return; + + vmx_guest_debugctl_write(vcpu, val & ~VMX_HOST_OWNED_DEBUGCTL_BITS); +} /* * Note, early Intel manuals have the write-low and read-high bitmap offsets diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index b4596f651232..2b3424f638db 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -21,7 +21,7 @@ void vmx_vm_destroy(struct kvm *kvm); int vmx_vcpu_precreate(struct kvm *kvm); int vmx_vcpu_create(struct kvm_vcpu *vcpu); int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu); -fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit); +fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags); void vmx_vcpu_free(struct kvm_vcpu *vcpu); void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu); @@ -52,7 +52,7 @@ void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, int trig_mode, int vector); void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu); bool vmx_has_emulated_msr(struct kvm *kvm, u32 index); -void vmx_msr_filter_changed(struct kvm_vcpu *vcpu); +void vmx_recalc_msr_intercepts(struct kvm_vcpu *vcpu); void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu); int vmx_get_feature_msr(u32 msr, u64 *data); @@ -133,10 +133,9 @@ void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void tdx_vcpu_free(struct kvm_vcpu *vcpu); void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu); int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu); -fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit); +fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags); void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); void tdx_vcpu_put(struct kvm_vcpu *vcpu); -bool tdx_protected_apic_has_interrupt(struct kvm_vcpu *vcpu); int tdx_handle_exit(struct kvm_vcpu *vcpu, enum exit_fastpath_completion fastpath); @@ -151,15 +150,6 @@ int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr); int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp); -int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn, - enum pg_level level, void *private_spt); -int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn, - enum pg_level level, void *private_spt); -int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn, - enum pg_level level, kvm_pfn_t pfn); -int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn, - enum pg_level level, kvm_pfn_t pfn); - void tdx_flush_tlb_current(struct kvm_vcpu *vcpu); void tdx_flush_tlb_all(struct kvm_vcpu *vcpu); void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a9d992d5652f..ba269385a9fa 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -226,6 +226,9 @@ EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr); bool __read_mostly enable_apicv = true; EXPORT_SYMBOL_GPL(enable_apicv); +bool __read_mostly enable_ipiv = true; +EXPORT_SYMBOL_GPL(enable_ipiv); + bool __read_mostly enable_device_posted_irqs = true; EXPORT_SYMBOL_GPL(enable_device_posted_irqs); @@ -3258,9 +3261,11 @@ int kvm_guest_time_update(struct kvm_vcpu *v) /* With all the info we got, fill in the values */ - if (kvm_caps.has_tsc_control) + if (kvm_caps.has_tsc_control) { tgt_tsc_khz = kvm_scale_tsc(tgt_tsc_khz, v->arch.l1_tsc_scaling_ratio); + tgt_tsc_khz = tgt_tsc_khz ? : 1; + } if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) { kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL, @@ -4577,6 +4582,9 @@ static u64 kvm_get_allowed_disable_exits(void) { u64 r = KVM_X86_DISABLE_EXITS_PAUSE; + if (boot_cpu_has(X86_FEATURE_APERFMPERF)) + r |= KVM_X86_DISABLE_EXITS_APERFMPERF; + if (!mitigate_smt_rsb) { r |= KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_CSTATE; @@ -4632,17 +4640,20 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_EXT_CPUID: case KVM_CAP_EXT_EMUL_CPUID: case KVM_CAP_CLOCKSOURCE: +#ifdef CONFIG_KVM_IOAPIC case KVM_CAP_PIT: + case KVM_CAP_PIT2: + case KVM_CAP_PIT_STATE2: + case KVM_CAP_REINJECT_CONTROL: +#endif case KVM_CAP_NOP_IO_DELAY: case KVM_CAP_MP_STATE: case KVM_CAP_SYNC_MMU: case KVM_CAP_USER_NMI: - case KVM_CAP_REINJECT_CONTROL: case KVM_CAP_IRQ_INJECT_STATUS: case KVM_CAP_IOEVENTFD: case KVM_CAP_IOEVENTFD_NO_LENGTH: - case KVM_CAP_PIT2: - case KVM_CAP_PIT_STATE2: + case KVM_CAP_SET_IDENTITY_MAP_ADDR: case KVM_CAP_VCPU_EVENTS: #ifdef CONFIG_KVM_HYPERV @@ -5487,12 +5498,6 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR)) return -EINVAL; - /* INITs are latched while in SMM */ - if (events->flags & KVM_VCPUEVENT_VALID_SMM && - (events->smi.smm || events->smi.pending) && - vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) - return -EINVAL; - process_nmi(vcpu); /* @@ -6186,6 +6191,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, u32 user_tsc_khz; r = -EINVAL; + + if (vcpu->arch.guest_tsc_protected) + goto out; + user_tsc_khz = (u32)arg; if (kvm_caps.has_tsc_control && @@ -6395,135 +6404,6 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, return 0; } -static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) -{ - struct kvm_pic *pic = kvm->arch.vpic; - int r; - - r = 0; - switch (chip->chip_id) { - case KVM_IRQCHIP_PIC_MASTER: - memcpy(&chip->chip.pic, &pic->pics[0], - sizeof(struct kvm_pic_state)); - break; - case KVM_IRQCHIP_PIC_SLAVE: - memcpy(&chip->chip.pic, &pic->pics[1], - sizeof(struct kvm_pic_state)); - break; - case KVM_IRQCHIP_IOAPIC: - kvm_get_ioapic(kvm, &chip->chip.ioapic); - break; - default: - r = -EINVAL; - break; - } - return r; -} - -static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) -{ - struct kvm_pic *pic = kvm->arch.vpic; - int r; - - r = 0; - switch (chip->chip_id) { - case KVM_IRQCHIP_PIC_MASTER: - spin_lock(&pic->lock); - memcpy(&pic->pics[0], &chip->chip.pic, - sizeof(struct kvm_pic_state)); - spin_unlock(&pic->lock); - break; - case KVM_IRQCHIP_PIC_SLAVE: - spin_lock(&pic->lock); - memcpy(&pic->pics[1], &chip->chip.pic, - sizeof(struct kvm_pic_state)); - spin_unlock(&pic->lock); - break; - case KVM_IRQCHIP_IOAPIC: - kvm_set_ioapic(kvm, &chip->chip.ioapic); - break; - default: - r = -EINVAL; - break; - } - kvm_pic_update_irq(pic); - return r; -} - -static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) -{ - struct kvm_kpit_state *kps = &kvm->arch.vpit->pit_state; - - BUILD_BUG_ON(sizeof(*ps) != sizeof(kps->channels)); - - mutex_lock(&kps->lock); - memcpy(ps, &kps->channels, sizeof(*ps)); - mutex_unlock(&kps->lock); - return 0; -} - -static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) -{ - int i; - struct kvm_pit *pit = kvm->arch.vpit; - - mutex_lock(&pit->pit_state.lock); - memcpy(&pit->pit_state.channels, ps, sizeof(*ps)); - for (i = 0; i < 3; i++) - kvm_pit_load_count(pit, i, ps->channels[i].count, 0); - mutex_unlock(&pit->pit_state.lock); - return 0; -} - -static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) -{ - mutex_lock(&kvm->arch.vpit->pit_state.lock); - memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels, - sizeof(ps->channels)); - ps->flags = kvm->arch.vpit->pit_state.flags; - mutex_unlock(&kvm->arch.vpit->pit_state.lock); - memset(&ps->reserved, 0, sizeof(ps->reserved)); - return 0; -} - -static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) -{ - int start = 0; - int i; - u32 prev_legacy, cur_legacy; - struct kvm_pit *pit = kvm->arch.vpit; - - mutex_lock(&pit->pit_state.lock); - prev_legacy = pit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY; - cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY; - if (!prev_legacy && cur_legacy) - start = 1; - memcpy(&pit->pit_state.channels, &ps->channels, - sizeof(pit->pit_state.channels)); - pit->pit_state.flags = ps->flags; - for (i = 0; i < 3; i++) - kvm_pit_load_count(pit, i, pit->pit_state.channels[i].count, - start && i == 0); - mutex_unlock(&pit->pit_state.lock); - return 0; -} - -static int kvm_vm_ioctl_reinject(struct kvm *kvm, - struct kvm_reinject_control *control) -{ - struct kvm_pit *pit = kvm->arch.vpit; - - /* pit->pit_state.lock was overloaded to prevent userspace from getting - * an inconsistent state after running multiple KVM_REINJECT_CONTROL - * ioctls in parallel. Use a separate lock if that ioctl isn't rare. - */ - mutex_lock(&pit->pit_state.lock); - kvm_pit_set_reinject(pit, control->pit_reinject); - mutex_unlock(&pit->pit_state.lock); - - return 0; -} - void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { @@ -6543,18 +6423,6 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) kvm_vcpu_kick(vcpu); } -int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, - bool line_status) -{ - if (!irqchip_in_kernel(kvm)) - return -ENXIO; - - irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, - irq_event->irq, irq_event->level, - line_status); - return 0; -} - int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { @@ -6619,17 +6487,11 @@ split_irqchip_unlock: if (!mitigate_smt_rsb && boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible() && - (cap->args[0] & ~KVM_X86_DISABLE_EXITS_PAUSE)) + (cap->args[0] & ~(KVM_X86_DISABLE_EXITS_PAUSE | + KVM_X86_DISABLE_EXITS_APERFMPERF))) pr_warn_once(SMT_RSB_MSG); - if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE) - kvm->arch.pause_in_guest = true; - if (cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) - kvm->arch.mwait_in_guest = true; - if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT) - kvm->arch.hlt_in_guest = true; - if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE) - kvm->arch.cstate_in_guest = true; + kvm_disable_exits(kvm, cap->args[0]); r = 0; disable_exits_unlock: mutex_unlock(&kvm->lock); @@ -7066,9 +6928,11 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; int r = -ENOTTY; + +#ifdef CONFIG_KVM_IOAPIC /* * This union makes it completely explicit to gcc-3.x - * that these two variables' stack usage should be + * that these three variables' stack usage should be * combined, not added together. */ union { @@ -7076,6 +6940,7 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) struct kvm_pit_state2 ps2; struct kvm_pit_config pit_config; } u; +#endif switch (ioctl) { case KVM_SET_TSS_ADDR: @@ -7099,6 +6964,7 @@ set_identity_unlock: case KVM_SET_NR_MMU_PAGES: r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg); break; +#ifdef CONFIG_KVM_IOAPIC case KVM_CREATE_IRQCHIP: { mutex_lock(&kvm->lock); @@ -7120,7 +6986,7 @@ set_identity_unlock: goto create_irqchip_unlock; } - r = kvm_setup_default_irq_routing(kvm); + r = kvm_setup_default_ioapic_and_pic_routing(kvm); if (r) { kvm_ioapic_destroy(kvm); kvm_pic_destroy(kvm); @@ -7168,7 +7034,7 @@ set_identity_unlock: } r = -ENXIO; - if (!irqchip_kernel(kvm)) + if (!irqchip_full(kvm)) goto get_irqchip_out; r = kvm_vm_ioctl_get_irqchip(kvm, chip); if (r) @@ -7192,7 +7058,7 @@ set_identity_unlock: } r = -ENXIO; - if (!irqchip_kernel(kvm)) + if (!irqchip_full(kvm)) goto set_irqchip_out; r = kvm_vm_ioctl_set_irqchip(kvm, chip); set_irqchip_out: @@ -7265,6 +7131,7 @@ set_pit2_out: r = kvm_vm_ioctl_reinject(kvm, &control); break; } +#endif case KVM_SET_BOOT_CPU_ID: r = 0; mutex_lock(&kvm->lock); @@ -7335,9 +7202,12 @@ set_pit2_out: if (user_tsc_khz == 0) user_tsc_khz = tsc_khz; - WRITE_ONCE(kvm->arch.default_tsc_khz, user_tsc_khz); - r = 0; - + mutex_lock(&kvm->lock); + if (!kvm->created_vcpus) { + WRITE_ONCE(kvm->arch.default_tsc_khz, user_tsc_khz); + r = 0; + } + mutex_unlock(&kvm->lock); goto out; } case KVM_GET_TSC_KHZ: { @@ -10724,8 +10594,10 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); +#ifdef CONFIG_KVM_IOAPIC else if (ioapic_in_kernel(vcpu->kvm)) kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); +#endif if (is_guest_mode(vcpu)) vcpu->arch.load_eoi_exitmap_pending = true; @@ -10779,6 +10651,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) dm_request_for_irq_injection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); fastpath_t exit_fastpath; + u64 run_flags, debug_ctl; bool req_immediate_exit = false; @@ -10926,8 +10799,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_vcpu_update_apicv(vcpu); if (kvm_check_request(KVM_REQ_APF_READY, vcpu)) kvm_check_async_pf_completion(vcpu); + + /* + * Recalc MSR intercepts as userspace may want to intercept + * accesses to MSRs that KVM would otherwise pass through to + * the guest. + */ if (kvm_check_request(KVM_REQ_MSR_FILTER_CHANGED, vcpu)) - kvm_x86_call(msr_filter_changed)(vcpu); + kvm_x86_call(recalc_msr_intercepts)(vcpu); if (kvm_check_request(KVM_REQ_UPDATE_CPU_DIRTY_LOGGING, vcpu)) kvm_x86_call(update_cpu_dirty_logging)(vcpu); @@ -11023,8 +10902,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } - if (req_immediate_exit) + run_flags = 0; + if (req_immediate_exit) { + run_flags |= KVM_RUN_FORCE_IMMEDIATE_EXIT; kvm_make_request(KVM_REQ_EVENT, vcpu); + } fpregs_assert_state_consistent(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) @@ -11042,12 +10924,22 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(vcpu->arch.eff_db[3], 3); /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) - kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6); + run_flags |= KVM_RUN_LOAD_GUEST_DR6; } else if (unlikely(hw_breakpoint_active())) { set_debugreg(DR7_FIXED_1, 7); } - vcpu->arch.host_debugctl = get_debugctlmsr(); + /* + * Refresh the host DEBUGCTL snapshot after disabling IRQs, as DEBUGCTL + * can be modified in IRQ context, e.g. via SMP function calls. Inform + * vendor code if any host-owned bits were changed, e.g. so that the + * value loaded into hardware while running the guest can be updated. + */ + debug_ctl = get_debugctlmsr(); + if ((debug_ctl ^ vcpu->arch.host_debugctl) & kvm_x86_ops.HOST_OWNED_DEBUGCTL && + !vcpu->arch.guest_state_protected) + run_flags |= KVM_RUN_LOAD_DEBUGCTL; + vcpu->arch.host_debugctl = debug_ctl; guest_timing_enter_irqoff(); @@ -11061,8 +10953,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) && (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED)); - exit_fastpath = kvm_x86_call(vcpu_run)(vcpu, - req_immediate_exit); + exit_fastpath = kvm_x86_call(vcpu_run)(vcpu, run_flags); if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) break; @@ -11074,6 +10965,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) break; } + run_flags = 0; + /* Note, VM-Exits that go down the "slow" path are accounted below. */ ++vcpu->stat.exits; } @@ -11547,6 +11440,28 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) trace_kvm_fpu(0); } +static int kvm_x86_vcpu_pre_run(struct kvm_vcpu *vcpu) +{ + /* + * SIPI_RECEIVED is obsolete; KVM leaves the vCPU in Wait-For-SIPI and + * tracks the pending SIPI separately. SIPI_RECEIVED is still accepted + * by KVM_SET_VCPU_EVENTS for backwards compatibility, but should be + * converted to INIT_RECEIVED. + */ + if (WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED)) + return -EINVAL; + + /* + * Disallow running the vCPU if userspace forced it into an impossible + * MP_STATE, e.g. if the vCPU is in WFS but SIPI is blocked. + */ + if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED && + !kvm_apic_init_sipi_allowed(vcpu)) + return -EINVAL; + + return kvm_x86_call(vcpu_pre_run)(vcpu); +} + int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_queued_exception *ex = &vcpu->arch.exception; @@ -11649,7 +11564,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) goto out; } - r = kvm_x86_call(vcpu_pre_run)(vcpu); + r = kvm_x86_vcpu_pre_run(vcpu); if (r <= 0) goto out; @@ -11893,21 +11808,16 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, } /* - * Pending INITs are reported using KVM_SET_VCPU_EVENTS, disallow - * forcing the guest into INIT/SIPI if those events are supposed to be - * blocked. KVM prioritizes SMI over INIT, so reject INIT/SIPI state - * if an SMI is pending as well. + * SIPI_RECEIVED is obsolete and no longer used internally; KVM instead + * leaves the vCPU in INIT_RECIEVED (Wait-For-SIPI) and pends the SIPI. + * Translate SIPI_RECEIVED as appropriate for backwards compatibility. */ - if ((!kvm_apic_init_sipi_allowed(vcpu) || vcpu->arch.smi_pending) && - (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED || - mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED)) - goto out; - if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) { - kvm_set_mp_state(vcpu, KVM_MP_STATE_INIT_RECEIVED); + mp_state->mp_state = KVM_MP_STATE_INIT_RECEIVED; set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events); - } else - kvm_set_mp_state(vcpu, mp_state->mp_state); + } + + kvm_set_mp_state(vcpu, mp_state->mp_state); kvm_make_request(KVM_REQ_EVENT, vcpu); ret = 0; @@ -12789,21 +12699,16 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) if (ret) goto out; - kvm_mmu_init_vm(kvm); + ret = kvm_mmu_init_vm(kvm); + if (ret) + goto out_cleanup_page_track; ret = kvm_x86_call(vm_init)(kvm); if (ret) goto out_uninit_mmu; - INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); atomic_set(&kvm->arch.noncoherent_dma_count, 0); - /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ - set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); - /* Reserve bit 1 of irq_sources_bitmap for irqfd-resampler */ - set_bit(KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, - &kvm->arch.irq_sources_bitmap); - raw_spin_lock_init(&kvm->arch.tsc_write_lock); mutex_init(&kvm->arch.apic_map_lock); seqcount_raw_spinlock_init(&kvm->arch.pvclock_sc, &kvm->arch.tsc_write_lock); @@ -12842,6 +12747,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) out_uninit_mmu: kvm_mmu_uninit_vm(kvm); +out_cleanup_page_track: kvm_page_track_cleanup(kvm); out: return ret; @@ -12934,7 +12840,9 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm) cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work); cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work); +#ifdef CONFIG_KVM_IOAPIC kvm_free_pit(kvm); +#endif kvm_mmu_pre_destroy_vm(kvm); static_call_cond(kvm_x86_vm_pre_destroy)(kvm); @@ -12958,8 +12866,10 @@ void kvm_arch_destroy_vm(struct kvm *kvm) } kvm_destroy_vcpus(kvm); kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1)); +#ifdef CONFIG_KVM_IOAPIC kvm_pic_destroy(kvm); kvm_ioapic_destroy(kvm); +#endif kvfree(rcu_dereference_check(kvm->arch.apic_map, 1)); kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1)); kvm_mmu_uninit_vm(kvm); @@ -13569,25 +13479,6 @@ bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu) return kvm_lapic_enabled(vcpu) && apf_pageready_slot_free(vcpu); } -void kvm_arch_start_assignment(struct kvm *kvm) -{ - if (atomic_inc_return(&kvm->arch.assigned_device_count) == 1) - kvm_x86_call(pi_start_assignment)(kvm); -} -EXPORT_SYMBOL_GPL(kvm_arch_start_assignment); - -void kvm_arch_end_assignment(struct kvm *kvm) -{ - atomic_dec(&kvm->arch.assigned_device_count); -} -EXPORT_SYMBOL_GPL(kvm_arch_end_assignment); - -bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm) -{ - return raw_atomic_read(&kvm->arch.assigned_device_count); -} -EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); - static void kvm_noncoherent_dma_assignment_start_or_stop(struct kvm *kvm) { /* @@ -13623,77 +13514,6 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma); -int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, - struct irq_bypass_producer *prod) -{ - struct kvm_kernel_irqfd *irqfd = - container_of(cons, struct kvm_kernel_irqfd, consumer); - struct kvm *kvm = irqfd->kvm; - int ret; - - kvm_arch_start_assignment(irqfd->kvm); - - spin_lock_irq(&kvm->irqfds.lock); - irqfd->producer = prod; - - ret = kvm_x86_call(pi_update_irte)(irqfd->kvm, - prod->irq, irqfd->gsi, 1); - if (ret) - kvm_arch_end_assignment(irqfd->kvm); - - spin_unlock_irq(&kvm->irqfds.lock); - - - return ret; -} - -void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, - struct irq_bypass_producer *prod) -{ - int ret; - struct kvm_kernel_irqfd *irqfd = - container_of(cons, struct kvm_kernel_irqfd, consumer); - struct kvm *kvm = irqfd->kvm; - - WARN_ON(irqfd->producer != prod); - - /* - * When producer of consumer is unregistered, we change back to - * remapped mode, so we can re-use the current implementation - * when the irq is masked/disabled or the consumer side (KVM - * int this case doesn't want to receive the interrupts. - */ - spin_lock_irq(&kvm->irqfds.lock); - irqfd->producer = NULL; - - ret = kvm_x86_call(pi_update_irte)(irqfd->kvm, - prod->irq, irqfd->gsi, 0); - if (ret) - printk(KERN_INFO "irq bypass consumer (token %p) unregistration" - " fails: %d\n", irqfd->consumer.token, ret); - - spin_unlock_irq(&kvm->irqfds.lock); - - - kvm_arch_end_assignment(irqfd->kvm); -} - -int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set) -{ - return kvm_x86_call(pi_update_irte)(kvm, host_irq, guest_irq, set); -} - -bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old, - struct kvm_kernel_irq_routing_entry *new) -{ - if (old->type != KVM_IRQ_ROUTING_MSI || - new->type != KVM_IRQ_ROUTING_MSI) - return true; - - return !!memcmp(&old->msi, &new->msi, sizeof(new->msi)); -} - bool kvm_vector_hashing_enabled(void) { return vector_hashing; @@ -14093,7 +13913,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window_update); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full); -EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 832f0faf4779..bcfd9b719ada 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -55,6 +55,28 @@ struct kvm_host_values { void kvm_spurious_fault(void); +#define SIZE_OF_MEMSLOTS_HASHTABLE \ + (sizeof(((struct kvm_memslots *)0)->id_hash) * 2 * KVM_MAX_NR_ADDRESS_SPACES) + +/* Sanity check the size of the memslot hash tables. */ +static_assert(SIZE_OF_MEMSLOTS_HASHTABLE == + (1024 * (1 + IS_ENABLED(CONFIG_X86_64)) * (1 + IS_ENABLED(CONFIG_KVM_SMM)))); + +/* + * Assert that "struct kvm_{svm,vmx,tdx}" is an order-0 or order-1 allocation. + * Spilling over to an order-2 allocation isn't fundamentally problematic, but + * isn't expected to happen in the foreseeable future (O(years)). Assert that + * the size is an order-0 allocation when ignoring the memslot hash tables, to + * help detect and debug unexpected size increases. + */ +#define KVM_SANITY_CHECK_VM_STRUCT_SIZE(x) \ +do { \ + BUILD_BUG_ON(get_order(sizeof(struct x) - SIZE_OF_MEMSLOTS_HASHTABLE) && \ + !IS_ENABLED(CONFIG_DEBUG_KERNEL) && !IS_ENABLED(CONFIG_KASAN)); \ + BUILD_BUG_ON(get_order(sizeof(struct x)) > 1 && \ + !IS_ENABLED(CONFIG_DEBUG_KERNEL) && !IS_ENABLED(CONFIG_KASAN)); \ +} while (0) + #define KVM_NESTED_VMENTER_CONSISTENCY_CHECK(consistency_check) \ ({ \ bool failed = (consistency_check); \ @@ -499,24 +521,34 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) __rem; \ }) +static inline void kvm_disable_exits(struct kvm *kvm, u64 mask) +{ + kvm->arch.disabled_exits |= mask; +} + static inline bool kvm_mwait_in_guest(struct kvm *kvm) { - return kvm->arch.mwait_in_guest; + return kvm->arch.disabled_exits & KVM_X86_DISABLE_EXITS_MWAIT; } static inline bool kvm_hlt_in_guest(struct kvm *kvm) { - return kvm->arch.hlt_in_guest; + return kvm->arch.disabled_exits & KVM_X86_DISABLE_EXITS_HLT; } static inline bool kvm_pause_in_guest(struct kvm *kvm) { - return kvm->arch.pause_in_guest; + return kvm->arch.disabled_exits & KVM_X86_DISABLE_EXITS_PAUSE; } static inline bool kvm_cstate_in_guest(struct kvm *kvm) { - return kvm->arch.cstate_in_guest; + return kvm->arch.disabled_exits & KVM_X86_DISABLE_EXITS_CSTATE; +} + +static inline bool kvm_aperfmperf_in_guest(struct kvm *kvm) +{ + return kvm->arch.disabled_exits & KVM_X86_DISABLE_EXITS_APERFMPERF; } static inline bool kvm_notify_vmexit_enabled(struct kvm *kvm) diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 9b029bb29a16..d6b2a665b499 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -1526,7 +1526,7 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, if (kvm_read_guest_virt(vcpu, (gva_t)sched_poll.ports, ports, sched_poll.nr_ports * sizeof(*ports), &e)) { *r = -EFAULT; - return true; + goto out; } for (i = 0; i < sched_poll.nr_ports; i++) { @@ -1971,8 +1971,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm, { struct kvm_vcpu *vcpu; - if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm)) - return -EINVAL; + /* + * Don't check for the port being within range of max_evtchn_port(). + * Userspace can configure what ever targets it likes; events just won't + * be delivered if/while the target is invalid, just like userspace can + * configure MSIs which target non-existent APICs. + * + * This allow on Live Migration and Live Update, the IRQ routing table + * can be restored *independently* of other things like creating vCPUs, + * without imposing an ordering dependency on userspace. In this + * particular case, the problematic ordering would be with setting the + * Xen 'long mode' flag, which changes max_evtchn_port() to allow 4096 + * instead of 1024 event channels. + */ /* We only support 2 level event channels for now */ if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL) diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index b2b9b89d6967..c611444480b3 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -960,4 +960,5 @@ void blk_unregister_queue(struct gendisk *disk) elevator_set_none(q); blk_debugfs_remove(disk); + kobject_put(&disk->queue_kobj); } diff --git a/block/elevator.c b/block/elevator.c index ab22542e6cf0..a960bdc869bc 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -719,7 +719,8 @@ void elevator_set_default(struct request_queue *q) .name = "mq-deadline", .no_uevent = true, }; - int err = 0; + int err; + struct elevator_type *e; /* now we allow to switch elevator */ blk_queue_flag_clear(QUEUE_FLAG_NO_ELV_SWITCH, q); @@ -732,12 +733,18 @@ void elevator_set_default(struct request_queue *q) * have multiple queues or mq-deadline is not available, default * to "none". */ - if (elevator_find_get(ctx.name) && (q->nr_hw_queues == 1 || - blk_mq_is_shared_tags(q->tag_set->flags))) + e = elevator_find_get(ctx.name); + if (!e) + return; + + if ((q->nr_hw_queues == 1 || + blk_mq_is_shared_tags(q->tag_set->flags))) { err = elevator_change(q, &ctx); - if (err < 0) - pr_warn("\"%s\" elevator initialization, failed %d, " - "falling back to \"none\"\n", ctx.name, err); + if (err < 0) + pr_warn("\"%s\" elevator initialization, failed %d, falling back to \"none\"\n", + ctx.name, err); + } + elevator_put(e); } void elevator_set_none(struct request_queue *q) diff --git a/drivers/acpi/riscv/cppc.c b/drivers/acpi/riscv/cppc.c index 4cdff387deff..440cf9fb91aa 100644 --- a/drivers/acpi/riscv/cppc.c +++ b/drivers/acpi/riscv/cppc.c @@ -37,10 +37,8 @@ static int __init sbi_cppc_init(void) { if (sbi_spec_version >= sbi_mk_version(2, 0) && sbi_probe_extension(SBI_EXT_CPPC) > 0) { - pr_info("SBI CPPC extension detected\n"); cppc_ext_present = true; } else { - pr_info("SBI CPPC extension NOT detected!!\n"); cppc_ext_present = false; } diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 7779ab0ca7ce..efc575a00edd 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -602,6 +602,7 @@ CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling); CPU_SHOW_VULN_FALLBACK(ghostwrite); CPU_SHOW_VULN_FALLBACK(old_microcode); CPU_SHOW_VULN_FALLBACK(indirect_target_selection); +CPU_SHOW_VULN_FALLBACK(tsa); static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); @@ -620,6 +621,7 @@ static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling static DEVICE_ATTR(ghostwrite, 0444, cpu_show_ghostwrite, NULL); static DEVICE_ATTR(old_microcode, 0444, cpu_show_old_microcode, NULL); static DEVICE_ATTR(indirect_target_selection, 0444, cpu_show_indirect_target_selection, NULL); +static DEVICE_ATTR(tsa, 0444, cpu_show_tsa, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -639,6 +641,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_ghostwrite.attr, &dev_attr_old_microcode.attr, &dev_attr_indirect_target_selection.attr, + &dev_attr_tsa.attr, NULL }; diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index bf77d28e959f..7a50af416cac 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1236,8 +1236,8 @@ void dpm_complete(pm_message_t state) */ void dpm_resume_end(pm_message_t state) { - pm_restore_gfp_mask(); dpm_resume(state); + pm_restore_gfp_mask(); dpm_complete(state); } EXPORT_SYMBOL_GPL(dpm_resume_end); @@ -1280,6 +1280,22 @@ static void dpm_async_suspend_parent(struct device *dev, async_func_t func) dpm_async_with_cleanup(dev->parent, func); } +static void dpm_async_suspend_complete_all(struct list_head *device_list) +{ + struct device *dev; + + guard(mutex)(&async_wip_mtx); + + list_for_each_entry_reverse(dev, device_list, power.entry) { + /* + * In case the device is being waited for and async processing + * has not started for it yet, let the waiters make progress. + */ + if (!dev->power.work_in_progress) + complete_all(&dev->power.completion); + } +} + /** * resume_event - Return a "resume" message for given "suspend" sleep state. * @sleep_state: PM message representing a sleep state. @@ -1456,6 +1472,7 @@ static int dpm_noirq_suspend_devices(pm_message_t state) mutex_lock(&dpm_list_mtx); if (error || async_error) { + dpm_async_suspend_complete_all(&dpm_late_early_list); /* * Move all devices to the target list to resume them * properly. @@ -1658,6 +1675,7 @@ int dpm_suspend_late(pm_message_t state) mutex_lock(&dpm_list_mtx); if (error || async_error) { + dpm_async_suspend_complete_all(&dpm_suspended_list); /* * Move all devices to the target list to resume them * properly. @@ -1951,6 +1969,7 @@ int dpm_suspend(pm_message_t state) mutex_lock(&dpm_list_mtx); if (error || async_error) { + dpm_async_suspend_complete_all(&dpm_prepared_list); /* * Move all devices to the target list to resume them * properly. diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index f2843f814675..1f3f782a04ba 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1173,6 +1173,8 @@ err_name: err_map: kfree(map); err: + if (bus && bus->free_on_exit) + kfree(bus); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(__regmap_init); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 500840e4a74e..8d994cae3b83 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -308,14 +308,13 @@ end_io: static void lo_rw_aio_do_completion(struct loop_cmd *cmd) { struct request *rq = blk_mq_rq_from_pdu(cmd); - struct loop_device *lo = rq->q->queuedata; if (!atomic_dec_and_test(&cmd->ref)) return; kfree(cmd->bvec); cmd->bvec = NULL; if (req_op(rq) == REQ_OP_WRITE) - file_end_write(lo->lo_backing_file); + kiocb_end_write(&cmd->iocb); if (likely(!blk_should_fake_timeout(rq->q))) blk_mq_complete_request(rq); } @@ -391,7 +390,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, } if (rw == ITER_SOURCE) { - file_start_write(lo->lo_backing_file); + kiocb_start_write(&cmd->iocb); ret = file->f_op->write_iter(&cmd->iocb, &iter); } else ret = file->f_op->read_iter(&cmd->iocb, &iter); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 7bdc7eb808ea..2592bd19ebc1 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -2198,9 +2198,7 @@ again: goto out; } } - ret = nbd_start_device(nbd); - if (ret) - goto out; + if (info->attrs[NBD_ATTR_BACKEND_IDENTIFIER]) { nbd->backend = nla_strdup(info->attrs[NBD_ATTR_BACKEND_IDENTIFIER], GFP_KERNEL); @@ -2216,6 +2214,8 @@ again: goto out; } set_bit(NBD_RT_HAS_BACKEND_FILE, &config->runtime_flags); + + ret = nbd_start_device(nbd); out: mutex_unlock(&nbd->config_lock); if (!ret) { diff --git a/drivers/bluetooth/bfusb.c b/drivers/bluetooth/bfusb.c index 0d6ad50da046..8df310983bf6 100644 --- a/drivers/bluetooth/bfusb.c +++ b/drivers/bluetooth/bfusb.c @@ -670,7 +670,7 @@ static int bfusb_probe(struct usb_interface *intf, const struct usb_device_id *i hdev->flush = bfusb_flush; hdev->send = bfusb_send_frame; - set_bit(HCI_QUIRK_BROKEN_LOCAL_COMMANDS, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_LOCAL_COMMANDS); if (hci_register_dev(hdev) < 0) { BT_ERR("Can't register HCI device"); diff --git a/drivers/bluetooth/bpa10x.c b/drivers/bluetooth/bpa10x.c index 1fa58c059cbf..8b43dfc755de 100644 --- a/drivers/bluetooth/bpa10x.c +++ b/drivers/bluetooth/bpa10x.c @@ -398,7 +398,7 @@ static int bpa10x_probe(struct usb_interface *intf, hdev->send = bpa10x_send_frame; hdev->set_diag = bpa10x_set_diag; - set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_RESET_ON_CLOSE); err = hci_register_dev(hdev); if (err < 0) { diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c index 0a60660fc8ce..3a3a56ddbb06 100644 --- a/drivers/bluetooth/btbcm.c +++ b/drivers/bluetooth/btbcm.c @@ -135,7 +135,7 @@ int btbcm_check_bdaddr(struct hci_dev *hdev) if (btbcm_set_bdaddr_from_efi(hdev) != 0) { bt_dev_info(hdev, "BCM: Using default device address (%pMR)", &bda->bdaddr); - set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_INVALID_BDADDR); } } @@ -467,7 +467,7 @@ static int btbcm_print_controller_features(struct hci_dev *hdev) /* Read DMI and disable broken Read LE Min/Max Tx Power */ if (dmi_first_match(disable_broken_read_transmit_power)) - set_bit(HCI_QUIRK_BROKEN_READ_TRANSMIT_POWER, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_READ_TRANSMIT_POWER); return 0; } @@ -706,7 +706,7 @@ int btbcm_finalize(struct hci_dev *hdev, bool *fw_load_done, bool use_autobaud_m btbcm_check_bdaddr(hdev); - set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_STRICT_DUPLICATE_FILTER); return 0; } @@ -769,7 +769,7 @@ int btbcm_setup_apple(struct hci_dev *hdev) kfree_skb(skb); } - set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_STRICT_DUPLICATE_FILTER); return 0; } diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 55cc1652bfe4..06016ac3965c 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -88,7 +88,7 @@ int btintel_check_bdaddr(struct hci_dev *hdev) if (!bacmp(&bda->bdaddr, BDADDR_INTEL)) { bt_dev_err(hdev, "Found Intel default device address (%pMR)", &bda->bdaddr); - set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_INVALID_BDADDR); } kfree_skb(skb); @@ -2027,7 +2027,7 @@ static int btintel_download_fw(struct hci_dev *hdev, */ if (!bacmp(¶ms->otp_bdaddr, BDADDR_ANY)) { bt_dev_info(hdev, "No device address configured"); - set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_INVALID_BDADDR); } download: @@ -2295,7 +2295,7 @@ static int btintel_prepare_fw_download_tlv(struct hci_dev *hdev, */ if (!bacmp(&ver->otp_bd_addr, BDADDR_ANY)) { bt_dev_info(hdev, "No device address configured"); - set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_INVALID_BDADDR); } } @@ -2670,7 +2670,7 @@ static u8 btintel_classify_pkt_type(struct hci_dev *hdev, struct sk_buff *skb) * Distinguish ISO data packets form ACL data packets * based on their connection handle value range. */ - if (hci_skb_pkt_type(skb) == HCI_ACLDATA_PKT) { + if (iso_capable(hdev) && hci_skb_pkt_type(skb) == HCI_ACLDATA_PKT) { __u16 handle = __le16_to_cpu(hci_acl_hdr(skb)->handle); if (hci_handle(handle) >= BTINTEL_ISODATA_HANDLE_BASE) @@ -3435,9 +3435,9 @@ static int btintel_setup_combined(struct hci_dev *hdev) } /* Apply the common HCI quirks for Intel device */ - set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks); - set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); - set_bit(HCI_QUIRK_NON_PERSISTENT_DIAG, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_STRICT_DUPLICATE_FILTER); + hci_set_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY); + hci_set_quirk(hdev, HCI_QUIRK_NON_PERSISTENT_DIAG); /* Set up the quality report callback for Intel devices */ hdev->set_quality_report = btintel_set_quality_report; @@ -3475,8 +3475,8 @@ static int btintel_setup_combined(struct hci_dev *hdev) */ if (!btintel_test_flag(hdev, INTEL_ROM_LEGACY_NO_WBS_SUPPORT)) - set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, - &hdev->quirks); + hci_set_quirk(hdev, + HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED); err = btintel_legacy_rom_setup(hdev, &ver); break; @@ -3491,11 +3491,11 @@ static int btintel_setup_combined(struct hci_dev *hdev) * * All Legacy bootloader devices support WBS */ - set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, - &hdev->quirks); + hci_set_quirk(hdev, + HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED); /* These variants don't seem to support LE Coded PHY */ - set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_LE_CODED); /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, ver.hw_variant); @@ -3571,10 +3571,10 @@ static int btintel_setup_combined(struct hci_dev *hdev) * * All Legacy bootloader devices support WBS */ - set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED); /* These variants don't seem to support LE Coded PHY */ - set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_LE_CODED); /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, ver.hw_variant); @@ -3600,7 +3600,7 @@ static int btintel_setup_combined(struct hci_dev *hdev) * * All TLV based devices support WBS */ - set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED); /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index e1c688dd2d45..f4e3fb54fe76 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -2081,9 +2081,9 @@ static int btintel_pcie_setup_internal(struct hci_dev *hdev) } /* Apply the common HCI quirks for Intel device */ - set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks); - set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); - set_bit(HCI_QUIRK_NON_PERSISTENT_DIAG, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_STRICT_DUPLICATE_FILTER); + hci_set_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY); + hci_set_quirk(hdev, HCI_QUIRK_NON_PERSISTENT_DIAG); /* Set up the quality report callback for Intel devices */ hdev->set_quality_report = btintel_set_quality_report; @@ -2123,7 +2123,7 @@ static int btintel_pcie_setup_internal(struct hci_dev *hdev) * * All TLV based devices support WBS */ - set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED); /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c index c16a3518b8ff..4fc673640bfc 100644 --- a/drivers/bluetooth/btmtksdio.c +++ b/drivers/bluetooth/btmtksdio.c @@ -1141,7 +1141,7 @@ static int btmtksdio_setup(struct hci_dev *hdev) } /* Enable WBS with mSBC codec */ - set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED); /* Enable GPIO reset mechanism */ if (bdev->reset) { @@ -1384,7 +1384,7 @@ static int btmtksdio_probe(struct sdio_func *func, SET_HCIDEV_DEV(hdev, &func->dev); hdev->manufacturer = 70; - set_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_NON_PERSISTENT_SETUP); sdio_set_drvdata(func, bdev); diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c index c97e260fcb0c..51400a891f6e 100644 --- a/drivers/bluetooth/btmtkuart.c +++ b/drivers/bluetooth/btmtkuart.c @@ -872,7 +872,7 @@ static int btmtkuart_probe(struct serdev_device *serdev) SET_HCIDEV_DEV(hdev, &serdev->dev); hdev->manufacturer = 70; - set_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_NON_PERSISTENT_SETUP); if (btmtkuart_is_standalone(bdev)) { err = clk_prepare_enable(bdev->osc); diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index 1088db6056a4..24f9b52605a1 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -1807,7 +1807,7 @@ static int nxp_serdev_probe(struct serdev_device *serdev) "local-bd-address", (u8 *)&ba, sizeof(ba)); if (bacmp(&ba, BDADDR_ANY)) - set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_USE_BDADDR_PROPERTY); if (hci_register_dev(hdev) < 0) { dev_err(&serdev->dev, "Can't register HCI device\n"); diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index edefb9dc76aa..7c958d6065be 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -739,7 +739,7 @@ static int qca_check_bdaddr(struct hci_dev *hdev, const struct qca_fw_config *co bda = (struct hci_rp_read_bd_addr *)skb->data; if (!bacmp(&bda->bdaddr, &config->bdaddr)) - set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_USE_BDADDR_PROPERTY); kfree_skb(skb); diff --git a/drivers/bluetooth/btqcomsmd.c b/drivers/bluetooth/btqcomsmd.c index c0eb71d6ffd3..d2e13fcb6bab 100644 --- a/drivers/bluetooth/btqcomsmd.c +++ b/drivers/bluetooth/btqcomsmd.c @@ -117,7 +117,7 @@ static int btqcomsmd_setup(struct hci_dev *hdev) /* Devices do not have persistent storage for BD address. Retrieve * it from the firmware node property. */ - set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_USE_BDADDR_PROPERTY); return 0; } diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 7838c89e529e..4d182cf6e037 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -1287,7 +1287,7 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev) /* Enable controller to do both LE scan and BR/EDR inquiry * simultaneously. */ - set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY); /* Enable central-peripheral role (able to create new connections with * an existing connection in slave role). @@ -1301,7 +1301,7 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev) case CHIP_ID_8851B: case CHIP_ID_8922A: case CHIP_ID_8852BT: - set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED); /* RTL8852C needs to transmit mSBC data continuously without * the zero length of USB packets for the ALT 6 supported chips @@ -1312,7 +1312,8 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev) if (btrtl_dev->project_id == CHIP_ID_8852A || btrtl_dev->project_id == CHIP_ID_8852B || btrtl_dev->project_id == CHIP_ID_8852C) - set_bit(HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER, &hdev->quirks); + hci_set_quirk(hdev, + HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER); hci_set_aosp_capable(hdev); break; @@ -1331,8 +1332,7 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev) * but it doesn't support any features from page 2 - * it either responds with garbage or with error status */ - set_bit(HCI_QUIRK_BROKEN_LOCAL_EXT_FEATURES_PAGE_2, - &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_LOCAL_EXT_FEATURES_PAGE_2); break; default: break; diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c index a69feb08486a..8325655ce6aa 100644 --- a/drivers/bluetooth/btsdio.c +++ b/drivers/bluetooth/btsdio.c @@ -327,7 +327,7 @@ static int btsdio_probe(struct sdio_func *func, hdev->send = btsdio_send_frame; if (func->vendor == 0x0104 && func->device == 0x00c5) - set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_RESET_ON_CLOSE); err = hci_register_dev(hdev); if (err < 0) { diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 9ab661d2d1e6..f9eeec0aed57 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -2472,18 +2472,18 @@ static int btusb_setup_csr(struct hci_dev *hdev) * Probably will need to be expanded in the future; * without these the controller will lock up. */ - set_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks); - set_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks); - set_bit(HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL, &hdev->quirks); - set_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks); - set_bit(HCI_QUIRK_BROKEN_READ_VOICE_SETTING, &hdev->quirks); - set_bit(HCI_QUIRK_BROKEN_READ_PAGE_SCAN_TYPE, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_STORED_LINK_KEY); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_ERR_DATA_REPORTING); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL); + hci_set_quirk(hdev, HCI_QUIRK_NO_SUSPEND_NOTIFIER); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_READ_VOICE_SETTING); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_READ_PAGE_SCAN_TYPE); /* Clear the reset quirk since this is not an actual * early Bluetooth 1.1 device from CSR. */ - clear_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); - clear_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); + hci_clear_quirk(hdev, HCI_QUIRK_RESET_ON_CLOSE); + hci_clear_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY); /* * Special workaround for these BT 4.0 chip clones, and potentially more: @@ -3192,6 +3192,32 @@ static const struct qca_device_info qca_devices_table[] = { { 0x00190200, 40, 4, 16 }, /* WCN785x 2.0 */ }; +static u16 qca_extract_board_id(const struct qca_version *ver) +{ + u16 flag = le16_to_cpu(ver->flag); + u16 board_id = 0; + + if (((flag >> 8) & 0xff) == QCA_FLAG_MULTI_NVM) { + /* The board_id should be split into two bytes + * The 1st byte is chip ID, and the 2nd byte is platform ID + * For example, board ID 0x010A, 0x01 is platform ID. 0x0A is chip ID + * we have several platforms, and platform IDs are continuously added + * Platform ID: + * 0x00 is for Mobile + * 0x01 is for X86 + * 0x02 is for Automotive + * 0x03 is for Consumer electronic + */ + board_id = (ver->chip_id << 8) + ver->platform_id; + } + + /* Take 0xffff as invalid board ID */ + if (board_id == 0xffff) + board_id = 0; + + return board_id; +} + static int btusb_qca_send_vendor_req(struct usb_device *udev, u8 request, void *data, u16 size) { @@ -3348,44 +3374,28 @@ static void btusb_generate_qca_nvm_name(char *fwname, size_t max_size, const struct qca_version *ver) { u32 rom_version = le32_to_cpu(ver->rom_version); - u16 flag = le16_to_cpu(ver->flag); + const char *variant; + int len; + u16 board_id; - if (((flag >> 8) & 0xff) == QCA_FLAG_MULTI_NVM) { - /* The board_id should be split into two bytes - * The 1st byte is chip ID, and the 2nd byte is platform ID - * For example, board ID 0x010A, 0x01 is platform ID. 0x0A is chip ID - * we have several platforms, and platform IDs are continuously added - * Platform ID: - * 0x00 is for Mobile - * 0x01 is for X86 - * 0x02 is for Automotive - * 0x03 is for Consumer electronic - */ - u16 board_id = (ver->chip_id << 8) + ver->platform_id; - const char *variant; + board_id = qca_extract_board_id(ver); - switch (le32_to_cpu(ver->ram_version)) { - case WCN6855_2_0_RAM_VERSION_GF: - case WCN6855_2_1_RAM_VERSION_GF: - variant = "_gf"; - break; - default: - variant = ""; - break; - } - - if (board_id == 0) { - snprintf(fwname, max_size, "qca/nvm_usb_%08x%s.bin", - rom_version, variant); - } else { - snprintf(fwname, max_size, "qca/nvm_usb_%08x%s_%04x.bin", - rom_version, variant, board_id); - } - } else { - snprintf(fwname, max_size, "qca/nvm_usb_%08x.bin", - rom_version); + switch (le32_to_cpu(ver->ram_version)) { + case WCN6855_2_0_RAM_VERSION_GF: + case WCN6855_2_1_RAM_VERSION_GF: + variant = "_gf"; + break; + default: + variant = NULL; + break; } + len = snprintf(fwname, max_size, "qca/nvm_usb_%08x", rom_version); + if (variant) + len += snprintf(fwname + len, max_size - len, "%s", variant); + if (board_id) + len += snprintf(fwname + len, max_size - len, "_%04x", board_id); + len += snprintf(fwname + len, max_size - len, ".bin"); } static int btusb_setup_qca_load_nvm(struct hci_dev *hdev, @@ -3494,7 +3504,7 @@ static int btusb_setup_qca(struct hci_dev *hdev) /* Mark HCI_OP_ENHANCED_SETUP_SYNC_CONN as broken as it doesn't seem to * work with the likes of HSP/HFP mSBC. */ - set_bit(HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN); return 0; } @@ -4008,10 +4018,10 @@ static int btusb_probe(struct usb_interface *intf, } #endif if (id->driver_info & BTUSB_CW6622) - set_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_STORED_LINK_KEY); if (id->driver_info & BTUSB_BCM2045) - set_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_STORED_LINK_KEY); if (id->driver_info & BTUSB_BCM92035) hdev->setup = btusb_setup_bcm92035; @@ -4068,8 +4078,8 @@ static int btusb_probe(struct usb_interface *intf, hdev->reset = btmtk_reset_sync; hdev->set_bdaddr = btmtk_set_bdaddr; hdev->send = btusb_send_frame_mtk; - set_bit(HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, &hdev->quirks); - set_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN); + hci_set_quirk(hdev, HCI_QUIRK_NON_PERSISTENT_SETUP); data->recv_acl = btmtk_usb_recv_acl; data->suspend = btmtk_usb_suspend; data->resume = btmtk_usb_resume; @@ -4077,20 +4087,20 @@ static int btusb_probe(struct usb_interface *intf, } if (id->driver_info & BTUSB_SWAVE) { - set_bit(HCI_QUIRK_FIXUP_INQUIRY_MODE, &hdev->quirks); - set_bit(HCI_QUIRK_BROKEN_LOCAL_COMMANDS, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_FIXUP_INQUIRY_MODE); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_LOCAL_COMMANDS); } if (id->driver_info & BTUSB_INTEL_BOOT) { hdev->manufacturer = 2; - set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_RAW_DEVICE); } if (id->driver_info & BTUSB_ATH3012) { data->setup_on_usb = btusb_setup_qca; hdev->set_bdaddr = btusb_set_bdaddr_ath3012; - set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); - set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY); + hci_set_quirk(hdev, HCI_QUIRK_STRICT_DUPLICATE_FILTER); } if (id->driver_info & BTUSB_QCA_ROME) { @@ -4098,7 +4108,7 @@ static int btusb_probe(struct usb_interface *intf, hdev->shutdown = btusb_shutdown_qca; hdev->set_bdaddr = btusb_set_bdaddr_ath3012; hdev->reset = btusb_qca_reset; - set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY); btusb_check_needs_reset_resume(intf); } @@ -4112,7 +4122,7 @@ static int btusb_probe(struct usb_interface *intf, hdev->shutdown = btusb_shutdown_qca; hdev->set_bdaddr = btusb_set_bdaddr_wcn6855; hdev->reset = btusb_qca_reset; - set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY); hci_set_msft_opcode(hdev, 0xFD70); } @@ -4140,35 +4150,35 @@ static int btusb_probe(struct usb_interface *intf, if (id->driver_info & BTUSB_ACTIONS_SEMI) { /* Support is advertised, but not implemented */ - set_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks); - set_bit(HCI_QUIRK_BROKEN_READ_TRANSMIT_POWER, &hdev->quirks); - set_bit(HCI_QUIRK_BROKEN_SET_RPA_TIMEOUT, &hdev->quirks); - set_bit(HCI_QUIRK_BROKEN_EXT_SCAN, &hdev->quirks); - set_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks); - set_bit(HCI_QUIRK_BROKEN_EXT_CREATE_CONN, &hdev->quirks); - set_bit(HCI_QUIRK_BROKEN_WRITE_AUTH_PAYLOAD_TIMEOUT, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_ERR_DATA_REPORTING); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_READ_TRANSMIT_POWER); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_SET_RPA_TIMEOUT); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_EXT_SCAN); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_EXT_CREATE_CONN); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_WRITE_AUTH_PAYLOAD_TIMEOUT); } if (!reset) - set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_RESET_ON_CLOSE); if (force_scofix || id->driver_info & BTUSB_WRONG_SCO_MTU) { if (!disable_scofix) - set_bit(HCI_QUIRK_FIXUP_BUFFER_SIZE, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_FIXUP_BUFFER_SIZE); } if (id->driver_info & BTUSB_BROKEN_ISOC) data->isoc = NULL; if (id->driver_info & BTUSB_WIDEBAND_SPEECH) - set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED); if (id->driver_info & BTUSB_INVALID_LE_STATES) - set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_LE_STATES); if (id->driver_info & BTUSB_DIGIANSWER) { data->cmdreq_type = USB_TYPE_VENDOR; - set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_RESET_ON_CLOSE); } if (id->driver_info & BTUSB_CSR) { @@ -4177,10 +4187,10 @@ static int btusb_probe(struct usb_interface *intf, /* Old firmware would otherwise execute USB reset */ if (bcdDevice < 0x117) - set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_RESET_ON_CLOSE); /* This must be set first in case we disable it for fakes */ - set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY); /* Fake CSR devices with broken commands */ if (le16_to_cpu(udev->descriptor.idVendor) == 0x0a12 && @@ -4193,7 +4203,7 @@ static int btusb_probe(struct usb_interface *intf, /* New sniffer firmware has crippled HCI interface */ if (le16_to_cpu(udev->descriptor.bcdDevice) > 0x997) - set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_RAW_DEVICE); } if (id->driver_info & BTUSB_INTEL_BOOT) { diff --git a/drivers/bluetooth/hci_aml.c b/drivers/bluetooth/hci_aml.c index 1394c575aa6d..707e90f80130 100644 --- a/drivers/bluetooth/hci_aml.c +++ b/drivers/bluetooth/hci_aml.c @@ -424,7 +424,7 @@ static int aml_check_bdaddr(struct hci_dev *hdev) if (!bacmp(&paddr->bdaddr, AML_BDADDR_DEFAULT)) { bt_dev_info(hdev, "amlbt using default bdaddr (%pM)", &paddr->bdaddr); - set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_INVALID_BDADDR); } exit: diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c index 9684eb16059b..f96617b85d87 100644 --- a/drivers/bluetooth/hci_bcm.c +++ b/drivers/bluetooth/hci_bcm.c @@ -643,8 +643,8 @@ static int bcm_setup(struct hci_uart *hu) * Allow the bootloader to set a valid address through the * device tree. */ - if (test_bit(HCI_QUIRK_INVALID_BDADDR, &hu->hdev->quirks)) - set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hu->hdev->quirks); + if (hci_test_quirk(hu->hdev, HCI_QUIRK_INVALID_BDADDR)) + hci_set_quirk(hu->hdev, HCI_QUIRK_USE_BDADDR_PROPERTY); if (!bcm_request_irq(bcm)) err = bcm_setup_sleep(hu); diff --git a/drivers/bluetooth/hci_bcm4377.c b/drivers/bluetooth/hci_bcm4377.c index 9bce53e49cfa..8a9aa33776b0 100644 --- a/drivers/bluetooth/hci_bcm4377.c +++ b/drivers/bluetooth/hci_bcm4377.c @@ -1435,7 +1435,7 @@ static int bcm4377_check_bdaddr(struct bcm4377_data *bcm4377) bda = (struct hci_rp_read_bd_addr *)skb->data; if (!bcm4377_is_valid_bdaddr(bcm4377, &bda->bdaddr)) - set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &bcm4377->hdev->quirks); + hci_set_quirk(bcm4377->hdev, HCI_QUIRK_USE_BDADDR_PROPERTY); kfree_skb(skb); return 0; @@ -2389,13 +2389,13 @@ static int bcm4377_probe(struct pci_dev *pdev, const struct pci_device_id *id) hdev->setup = bcm4377_hci_setup; if (bcm4377->hw->broken_mws_transport_config) - set_bit(HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG); if (bcm4377->hw->broken_ext_scan) - set_bit(HCI_QUIRK_BROKEN_EXT_SCAN, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_EXT_SCAN); if (bcm4377->hw->broken_le_coded) - set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_LE_CODED); if (bcm4377->hw->broken_le_ext_adv_report_phy) - set_bit(HCI_QUIRK_FIXUP_LE_EXT_ADV_REPORT_PHY, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_FIXUP_LE_EXT_ADV_REPORT_PHY); pci_set_drvdata(pdev, bcm4377); hci_set_drvdata(hdev, bcm4377); diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c index 811f33701f84..d22fbb7f9fc5 100644 --- a/drivers/bluetooth/hci_intel.c +++ b/drivers/bluetooth/hci_intel.c @@ -660,7 +660,7 @@ static int intel_setup(struct hci_uart *hu) */ if (!bacmp(¶ms.otp_bdaddr, BDADDR_ANY)) { bt_dev_info(hdev, "No device address configured"); - set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_INVALID_BDADDR); } /* With this Intel bootloader only the hardware variant and device diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index acba83156de9..d0adae3267b4 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -667,13 +667,13 @@ static int hci_uart_register_dev(struct hci_uart *hu) SET_HCIDEV_DEV(hdev, hu->tty->dev); if (test_bit(HCI_UART_RAW_DEVICE, &hu->hdev_flags)) - set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_RAW_DEVICE); if (test_bit(HCI_UART_EXT_CONFIG, &hu->hdev_flags)) - set_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_EXTERNAL_CONFIG); if (!test_bit(HCI_UART_RESET_ON_INIT, &hu->hdev_flags)) - set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_RESET_ON_CLOSE); /* Only call open() for the protocol after hdev is fully initialized as * open() (or a timer/workqueue it starts) may attempt to reference it. diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c index e19e9bd49555..7044c86325ce 100644 --- a/drivers/bluetooth/hci_ll.c +++ b/drivers/bluetooth/hci_ll.c @@ -649,11 +649,11 @@ static int ll_setup(struct hci_uart *hu) /* This means that there was an error getting the BD address * during probe, so mark the device as having a bad address. */ - set_bit(HCI_QUIRK_INVALID_BDADDR, &hu->hdev->quirks); + hci_set_quirk(hu->hdev, HCI_QUIRK_INVALID_BDADDR); } else if (bacmp(&lldev->bdaddr, BDADDR_ANY)) { err = ll_set_bdaddr(hu->hdev, &lldev->bdaddr); if (err) - set_bit(HCI_QUIRK_INVALID_BDADDR, &hu->hdev->quirks); + hci_set_quirk(hu->hdev, HCI_QUIRK_INVALID_BDADDR); } /* Operational speed if any */ diff --git a/drivers/bluetooth/hci_nokia.c b/drivers/bluetooth/hci_nokia.c index 9fc10a16fd96..cd7575c20f65 100644 --- a/drivers/bluetooth/hci_nokia.c +++ b/drivers/bluetooth/hci_nokia.c @@ -439,7 +439,7 @@ static int nokia_setup(struct hci_uart *hu) if (btdev->man_id == NOKIA_ID_BCM2048) { hu->hdev->set_bdaddr = btbcm_set_bdaddr; - set_bit(HCI_QUIRK_INVALID_BDADDR, &hu->hdev->quirks); + hci_set_quirk(hu->hdev, HCI_QUIRK_INVALID_BDADDR); dev_dbg(dev, "bcm2048 has invalid bluetooth address!"); } diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 3ec0be496820..33c43503714b 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -1892,7 +1892,7 @@ static int qca_setup(struct hci_uart *hu) /* Enable controller to do both LE scan and BR/EDR inquiry * simultaneously. */ - set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY); switch (soc_type) { case QCA_QCA2066: @@ -1944,7 +1944,7 @@ retry: case QCA_WCN7850: qcadev = serdev_device_get_drvdata(hu->serdev); if (qcadev->bdaddr_property_broken) - set_bit(HCI_QUIRK_BDADDR_PROPERTY_BROKEN, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BDADDR_PROPERTY_BROKEN); hci_set_aosp_capable(hdev); @@ -2487,7 +2487,7 @@ static int qca_serdev_probe(struct serdev_device *serdev) hdev = qcadev->serdev_hu.hdev; if (power_ctrl_enabled) { - set_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_NON_PERSISTENT_SETUP); hdev->shutdown = qca_power_off; } @@ -2496,11 +2496,11 @@ static int qca_serdev_probe(struct serdev_device *serdev) * be queried via hci. Same with the valid le states quirk. */ if (data->capabilities & QCA_CAP_WIDEBAND_SPEECH) - set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, - &hdev->quirks); + hci_set_quirk(hdev, + HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED); if (!(data->capabilities & QCA_CAP_VALID_LE_STATES)) - set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_LE_STATES); } return 0; @@ -2550,7 +2550,7 @@ static void qca_serdev_shutdown(struct device *dev) * invoked and the SOC is already in the initial state, so * don't also need to send the VSC. */ - if (test_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks) || + if (hci_test_quirk(hdev, HCI_QUIRK_NON_PERSISTENT_SETUP) || hci_dev_test_flag(hdev, HCI_SETUP)) return; diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c index 89a22e9b3253..593d9cefbbf9 100644 --- a/drivers/bluetooth/hci_serdev.c +++ b/drivers/bluetooth/hci_serdev.c @@ -152,7 +152,7 @@ static int hci_uart_close(struct hci_dev *hdev) * BT SOC is completely powered OFF during BT OFF, holding port * open may drain the battery. */ - if (test_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks)) { + if (hci_test_quirk(hdev, HCI_QUIRK_NON_PERSISTENT_SETUP)) { clear_bit(HCI_UART_PROTO_READY, &hu->flags); serdev_device_close(hu->serdev); } @@ -358,13 +358,13 @@ int hci_uart_register_device_priv(struct hci_uart *hu, SET_HCIDEV_DEV(hdev, &hu->serdev->dev); if (test_bit(HCI_UART_NO_SUSPEND_NOTIFIER, &hu->flags)) - set_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_NO_SUSPEND_NOTIFIER); if (test_bit(HCI_UART_RAW_DEVICE, &hu->hdev_flags)) - set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_RAW_DEVICE); if (test_bit(HCI_UART_EXT_CONFIG, &hu->hdev_flags)) - set_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_EXTERNAL_CONFIG); if (test_bit(HCI_UART_INIT_PENDING, &hu->hdev_flags)) return 0; diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index 59f4d7bdffdc..f7d8c3c00655 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -415,16 +415,16 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode) hdev->get_codec_config_data = vhci_get_codec_config_data; hdev->wakeup = vhci_wakeup; hdev->setup = vhci_setup; - set_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks); - set_bit(HCI_QUIRK_SYNC_FLOWCTL_SUPPORTED, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_NON_PERSISTENT_SETUP); + hci_set_quirk(hdev, HCI_QUIRK_SYNC_FLOWCTL_SUPPORTED); /* bit 6 is for external configuration */ if (opcode & 0x40) - set_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_EXTERNAL_CONFIG); /* bit 7 is for raw device */ if (opcode & 0x80) - set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_RAW_DEVICE); if (hci_register_dev(hdev) < 0) { BT_ERR("Can't register HCI device"); diff --git a/drivers/bluetooth/virtio_bt.c b/drivers/bluetooth/virtio_bt.c index 756f292df9e8..6f1a37e85c6a 100644 --- a/drivers/bluetooth/virtio_bt.c +++ b/drivers/bluetooth/virtio_bt.c @@ -327,17 +327,17 @@ static int virtbt_probe(struct virtio_device *vdev) hdev->setup = virtbt_setup_intel; hdev->shutdown = virtbt_shutdown_generic; hdev->set_bdaddr = virtbt_set_bdaddr_intel; - set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks); - set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); - set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_STRICT_DUPLICATE_FILTER); + hci_set_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY); + hci_set_quirk(hdev, HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED); break; case VIRTIO_BT_CONFIG_VENDOR_REALTEK: hdev->manufacturer = 93; hdev->setup = virtbt_setup_realtek; hdev->shutdown = virtbt_shutdown_generic; - set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); - set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); + hci_set_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY); + hci_set_quirk(hdev, HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED); break; } } diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index 7671bd158545..c1c0a4759c7e 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -943,6 +943,7 @@ struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev, struct fsl_mc_obj_desc endpoint_desc = {{ 0 }}; struct dprc_endpoint endpoint1 = {{ 0 }}; struct dprc_endpoint endpoint2 = {{ 0 }}; + struct fsl_mc_bus *mc_bus; int state, err; mc_bus_dev = to_fsl_mc_device(mc_dev->dev.parent); @@ -966,6 +967,8 @@ struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev, strcpy(endpoint_desc.type, endpoint2.type); endpoint_desc.id = endpoint2.id; endpoint = fsl_mc_device_lookup(&endpoint_desc, mc_bus_dev); + if (endpoint) + return endpoint; /* * We know that the device has an endpoint because we verified by @@ -973,17 +976,13 @@ struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev, * yet discovered by the fsl-mc bus, thus the lookup returned NULL. * Force a rescan of the devices in this container and retry the lookup. */ - if (!endpoint) { - struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_bus_dev); - - if (mutex_trylock(&mc_bus->scan_mutex)) { - err = dprc_scan_objects(mc_bus_dev, true); - mutex_unlock(&mc_bus->scan_mutex); - } - - if (err < 0) - return ERR_PTR(err); + mc_bus = to_fsl_mc_bus(mc_bus_dev); + if (mutex_trylock(&mc_bus->scan_mutex)) { + err = dprc_scan_objects(mc_bus_dev, true); + mutex_unlock(&mc_bus->scan_mutex); } + if (err < 0) + return ERR_PTR(err); endpoint = fsl_mc_device_lookup(&endpoint_desc, mc_bus_dev); /* diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c index bf490967241a..2505df1f4e69 100644 --- a/drivers/char/agp/amd64-agp.c +++ b/drivers/char/agp/amd64-agp.c @@ -720,11 +720,6 @@ static const struct pci_device_id agp_amd64_pci_table[] = { MODULE_DEVICE_TABLE(pci, agp_amd64_pci_table); -static const struct pci_device_id agp_amd64_pci_promisc_table[] = { - { PCI_DEVICE_CLASS(0, 0) }, - { } -}; - static DEFINE_SIMPLE_DEV_PM_OPS(agp_amd64_pm_ops, NULL, agp_amd64_resume); static struct pci_driver agp_amd64_pci_driver = { @@ -739,6 +734,7 @@ static struct pci_driver agp_amd64_pci_driver = { /* Not static due to IOMMU code calling it early. */ int __init agp_amd64_init(void) { + struct pci_dev *pdev = NULL; int err = 0; if (agp_off) @@ -767,9 +763,13 @@ int __init agp_amd64_init(void) } /* Look for any AGP bridge */ - agp_amd64_pci_driver.id_table = agp_amd64_pci_promisc_table; - err = driver_attach(&agp_amd64_pci_driver.driver); - if (err == 0 && agp_bridges_found == 0) { + for_each_pci_dev(pdev) + if (pci_find_capability(pdev, PCI_CAP_ID_AGP)) + pci_add_dynid(&agp_amd64_pci_driver, + pdev->vendor, pdev->device, + pdev->subsystem_vendor, + pdev->subsystem_device, 0, 0, 0); + if (agp_bridges_found == 0) { pci_unregister_driver(&agp_amd64_pci_driver); err = -ENODEV; } diff --git a/drivers/clk/clk-scmi.c b/drivers/clk/clk-scmi.c index 15510c2ff21c..1b1561c84127 100644 --- a/drivers/clk/clk-scmi.c +++ b/drivers/clk/clk-scmi.c @@ -404,6 +404,7 @@ static int scmi_clocks_probe(struct scmi_device *sdev) const struct scmi_handle *handle = sdev->handle; struct scmi_protocol_handle *ph; const struct clk_ops *scmi_clk_ops_db[SCMI_MAX_CLK_OPS] = {}; + struct scmi_clk *sclks; if (!handle) return -ENODEV; @@ -430,18 +431,21 @@ static int scmi_clocks_probe(struct scmi_device *sdev) transport_is_atomic = handle->is_transport_atomic(handle, &atomic_threshold_us); + sclks = devm_kcalloc(dev, count, sizeof(*sclks), GFP_KERNEL); + if (!sclks) + return -ENOMEM; + + for (idx = 0; idx < count; idx++) + hws[idx] = &sclks[idx].hw; + for (idx = 0; idx < count; idx++) { - struct scmi_clk *sclk; + struct scmi_clk *sclk = &sclks[idx]; const struct clk_ops *scmi_ops; - sclk = devm_kzalloc(dev, sizeof(*sclk), GFP_KERNEL); - if (!sclk) - return -ENOMEM; - sclk->info = scmi_proto_clk_ops->info_get(ph, idx); if (!sclk->info) { dev_dbg(dev, "invalid clock info for idx %d\n", idx); - devm_kfree(dev, sclk); + hws[idx] = NULL; continue; } @@ -479,13 +483,11 @@ static int scmi_clocks_probe(struct scmi_device *sdev) if (err) { dev_err(dev, "failed to register clock %d\n", idx); devm_kfree(dev, sclk->parent_data); - devm_kfree(dev, sclk); hws[idx] = NULL; } else { dev_dbg(dev, "Registered clock:%s%s\n", sclk->info->name, scmi_ops->enable ? " (atomic ops)" : ""); - hws[idx] = &sclk->hw; } } diff --git a/drivers/clk/imx/clk-imx95-blk-ctl.c b/drivers/clk/imx/clk-imx95-blk-ctl.c index 25974947ad0c..cc2ee2be1819 100644 --- a/drivers/clk/imx/clk-imx95-blk-ctl.c +++ b/drivers/clk/imx/clk-imx95-blk-ctl.c @@ -219,11 +219,15 @@ static const struct imx95_blk_ctl_dev_data lvds_csr_dev_data = { .clk_reg_offset = 0, }; +static const char * const disp_engine_parents[] = { + "videopll1", "dsi_pll", "ldb_pll_div7" +}; + static const struct imx95_blk_ctl_clk_dev_data dispmix_csr_clk_dev_data[] = { [IMX95_CLK_DISPMIX_ENG0_SEL] = { .name = "disp_engine0_sel", - .parent_names = (const char *[]){"videopll1", "dsi_pll", "ldb_pll_div7", }, - .num_parents = 4, + .parent_names = disp_engine_parents, + .num_parents = ARRAY_SIZE(disp_engine_parents), .reg = 0, .bit_idx = 0, .bit_width = 2, @@ -232,8 +236,8 @@ static const struct imx95_blk_ctl_clk_dev_data dispmix_csr_clk_dev_data[] = { }, [IMX95_CLK_DISPMIX_ENG1_SEL] = { .name = "disp_engine1_sel", - .parent_names = (const char *[]){"videopll1", "dsi_pll", "ldb_pll_div7", }, - .num_parents = 4, + .parent_names = disp_engine_parents, + .num_parents = ARRAY_SIZE(disp_engine_parents), .reg = 0, .bit_idx = 2, .bit_width = 2, diff --git a/drivers/clk/sunxi-ng/ccu-sun55i-a523.c b/drivers/clk/sunxi-ng/ccu-sun55i-a523.c index 9efb9fd24b42..1a9a1cb869e2 100644 --- a/drivers/clk/sunxi-ng/ccu-sun55i-a523.c +++ b/drivers/clk/sunxi-ng/ccu-sun55i-a523.c @@ -385,7 +385,8 @@ static SUNXI_CCU_MP_DATA_WITH_MUX_GATE_FEAT(mbus_clk, "mbus", mbus_parents, 0, 0, /* no P */ 24, 3, /* mux */ BIT(31), /* gate */ - 0, CCU_FEATURE_UPDATE_BIT); + CLK_IS_CRITICAL, + CCU_FEATURE_UPDATE_BIT); static const struct clk_hw *mbus_hws[] = { &mbus_clk.common.hw }; diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c b/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c index 579a81bb46df..52e4369664c5 100644 --- a/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c +++ b/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c @@ -350,7 +350,7 @@ static SUNXI_CCU_M_WITH_MUX_GATE(de_clk, "de", de_parents, 0x104, 0, 4, 24, 2, BIT(31), CLK_SET_RATE_PARENT); -static const char * const tcon_parents[] = { "pll-video" }; +static const char * const tcon_parents[] = { "pll-video", "pll-periph0" }; static SUNXI_CCU_M_WITH_MUX_GATE(tcon_clk, "tcon", tcon_parents, 0x118, 0, 4, 24, 3, BIT(31), 0); @@ -362,11 +362,11 @@ static const char * const csi_mclk_parents[] = { "osc24M", "pll-video", static SUNXI_CCU_M_WITH_MUX_GATE(csi0_mclk_clk, "csi0-mclk", csi_mclk_parents, 0x130, 0, 5, 8, 3, BIT(15), 0); -static const char * const csi1_sclk_parents[] = { "pll-video", "pll-isp" }; -static SUNXI_CCU_M_WITH_MUX_GATE(csi1_sclk_clk, "csi-sclk", csi1_sclk_parents, +static const char * const csi_sclk_parents[] = { "pll-video", "pll-isp" }; +static SUNXI_CCU_M_WITH_MUX_GATE(csi_sclk_clk, "csi-sclk", csi_sclk_parents, 0x134, 16, 4, 24, 3, BIT(31), 0); -static SUNXI_CCU_M_WITH_MUX_GATE(csi1_mclk_clk, "csi-mclk", csi_mclk_parents, +static SUNXI_CCU_M_WITH_MUX_GATE(csi1_mclk_clk, "csi1-mclk", csi_mclk_parents, 0x134, 0, 5, 8, 3, BIT(15), 0); static SUNXI_CCU_M_WITH_GATE(ve_clk, "ve", "pll-ve", @@ -452,7 +452,7 @@ static struct ccu_common *sun8i_v3s_ccu_clks[] = { &tcon_clk.common, &csi_misc_clk.common, &csi0_mclk_clk.common, - &csi1_sclk_clk.common, + &csi_sclk_clk.common, &csi1_mclk_clk.common, &ve_clk.common, &ac_dig_clk.common, @@ -551,7 +551,7 @@ static struct clk_hw_onecell_data sun8i_v3s_hw_clks = { [CLK_TCON0] = &tcon_clk.common.hw, [CLK_CSI_MISC] = &csi_misc_clk.common.hw, [CLK_CSI0_MCLK] = &csi0_mclk_clk.common.hw, - [CLK_CSI1_SCLK] = &csi1_sclk_clk.common.hw, + [CLK_CSI_SCLK] = &csi_sclk_clk.common.hw, [CLK_CSI1_MCLK] = &csi1_mclk_clk.common.hw, [CLK_VE] = &ve_clk.common.hw, [CLK_AC_DIG] = &ac_dig_clk.common.hw, @@ -633,7 +633,7 @@ static struct clk_hw_onecell_data sun8i_v3_hw_clks = { [CLK_TCON0] = &tcon_clk.common.hw, [CLK_CSI_MISC] = &csi_misc_clk.common.hw, [CLK_CSI0_MCLK] = &csi0_mclk_clk.common.hw, - [CLK_CSI1_SCLK] = &csi1_sclk_clk.common.hw, + [CLK_CSI_SCLK] = &csi_sclk_clk.common.hw, [CLK_CSI1_MCLK] = &csi1_mclk_clk.common.hw, [CLK_VE] = &ve_clk.common.hw, [CLK_AC_DIG] = &ac_dig_clk.common.hw, diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index 09549451dd51..2edc13ca184e 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -22,6 +22,7 @@ #include <linux/irq.h> #include <linux/acpi.h> #include <linux/hyperv.h> +#include <linux/export.h> #include <clocksource/hyperv_timer.h> #include <hyperv/hvhdk.h> #include <asm/mshyperv.h> diff --git a/drivers/comedi/comedi_fops.c b/drivers/comedi/comedi_fops.c index 3383a7ce27ff..c83fd14dd7ad 100644 --- a/drivers/comedi/comedi_fops.c +++ b/drivers/comedi/comedi_fops.c @@ -1556,21 +1556,27 @@ static int do_insnlist_ioctl(struct comedi_device *dev, } for (i = 0; i < n_insns; ++i) { + unsigned int n = insns[i].n; + if (insns[i].insn & INSN_MASK_WRITE) { if (copy_from_user(data, insns[i].data, - insns[i].n * sizeof(unsigned int))) { + n * sizeof(unsigned int))) { dev_dbg(dev->class_dev, "copy_from_user failed\n"); ret = -EFAULT; goto error; } + if (n < MIN_SAMPLES) { + memset(&data[n], 0, (MIN_SAMPLES - n) * + sizeof(unsigned int)); + } } ret = parse_insn(dev, insns + i, data, file); if (ret < 0) goto error; if (insns[i].insn & INSN_MASK_READ) { if (copy_to_user(insns[i].data, data, - insns[i].n * sizeof(unsigned int))) { + n * sizeof(unsigned int))) { dev_dbg(dev->class_dev, "copy_to_user failed\n"); ret = -EFAULT; @@ -1589,6 +1595,16 @@ error: return i; } +#define MAX_INSNS MAX_SAMPLES +static int check_insnlist_len(struct comedi_device *dev, unsigned int n_insns) +{ + if (n_insns > MAX_INSNS) { + dev_dbg(dev->class_dev, "insnlist length too large\n"); + return -EINVAL; + } + return 0; +} + /* * COMEDI_INSN ioctl * synchronous instruction @@ -1633,6 +1649,10 @@ static int do_insn_ioctl(struct comedi_device *dev, ret = -EFAULT; goto error; } + if (insn->n < MIN_SAMPLES) { + memset(&data[insn->n], 0, + (MIN_SAMPLES - insn->n) * sizeof(unsigned int)); + } } ret = parse_insn(dev, insn, data, file); if (ret < 0) @@ -2239,6 +2259,9 @@ static long comedi_unlocked_ioctl(struct file *file, unsigned int cmd, rc = -EFAULT; break; } + rc = check_insnlist_len(dev, insnlist.n_insns); + if (rc) + break; insns = kcalloc(insnlist.n_insns, sizeof(*insns), GFP_KERNEL); if (!insns) { rc = -ENOMEM; @@ -3142,6 +3165,9 @@ static int compat_insnlist(struct file *file, unsigned long arg) if (copy_from_user(&insnlist32, compat_ptr(arg), sizeof(insnlist32))) return -EFAULT; + rc = check_insnlist_len(dev, insnlist32.n_insns); + if (rc) + return rc; insns = kcalloc(insnlist32.n_insns, sizeof(*insns), GFP_KERNEL); if (!insns) return -ENOMEM; diff --git a/drivers/comedi/drivers.c b/drivers/comedi/drivers.c index 376130bfba8a..9e4b7c840a8f 100644 --- a/drivers/comedi/drivers.c +++ b/drivers/comedi/drivers.c @@ -339,10 +339,10 @@ int comedi_dio_insn_config(struct comedi_device *dev, unsigned int *data, unsigned int mask) { - unsigned int chan_mask = 1 << CR_CHAN(insn->chanspec); + unsigned int chan = CR_CHAN(insn->chanspec); - if (!mask) - mask = chan_mask; + if (!mask && chan < 32) + mask = 1U << chan; switch (data[0]) { case INSN_CONFIG_DIO_INPUT: @@ -382,7 +382,7 @@ EXPORT_SYMBOL_GPL(comedi_dio_insn_config); unsigned int comedi_dio_update_state(struct comedi_subdevice *s, unsigned int *data) { - unsigned int chanmask = (s->n_chan < 32) ? ((1 << s->n_chan) - 1) + unsigned int chanmask = (s->n_chan < 32) ? ((1U << s->n_chan) - 1) : 0xffffffff; unsigned int mask = data[0] & chanmask; unsigned int bits = data[1]; @@ -615,6 +615,9 @@ static int insn_rw_emulate_bits(struct comedi_device *dev, unsigned int _data[2]; int ret; + if (insn->n == 0) + return 0; + memset(_data, 0, sizeof(_data)); memset(&_insn, 0, sizeof(_insn)); _insn.insn = INSN_BITS; @@ -625,8 +628,8 @@ static int insn_rw_emulate_bits(struct comedi_device *dev, if (insn->insn == INSN_WRITE) { if (!(s->subdev_flags & SDF_WRITABLE)) return -EINVAL; - _data[0] = 1 << (chan - base_chan); /* mask */ - _data[1] = data[0] ? (1 << (chan - base_chan)) : 0; /* bits */ + _data[0] = 1U << (chan - base_chan); /* mask */ + _data[1] = data[0] ? (1U << (chan - base_chan)) : 0; /* bits */ } ret = s->insn_bits(dev, s, &_insn, _data); @@ -709,7 +712,7 @@ static int __comedi_device_postconfig(struct comedi_device *dev) if (s->type == COMEDI_SUBD_DO) { if (s->n_chan < 32) - s->io_bits = (1 << s->n_chan) - 1; + s->io_bits = (1U << s->n_chan) - 1; else s->io_bits = 0xffffffff; } diff --git a/drivers/comedi/drivers/aio_iiro_16.c b/drivers/comedi/drivers/aio_iiro_16.c index b00fab0b89d4..739cc4db52ac 100644 --- a/drivers/comedi/drivers/aio_iiro_16.c +++ b/drivers/comedi/drivers/aio_iiro_16.c @@ -177,7 +177,8 @@ static int aio_iiro_16_attach(struct comedi_device *dev, * Digital input change of state interrupts are optionally supported * using IRQ 2-7, 10-12, 14, or 15. */ - if ((1 << it->options[1]) & 0xdcfc) { + if (it->options[1] > 0 && it->options[1] < 16 && + (1 << it->options[1]) & 0xdcfc) { ret = request_irq(it->options[1], aio_iiro_16_cos, 0, dev->board_name, dev); if (ret == 0) diff --git a/drivers/comedi/drivers/comedi_test.c b/drivers/comedi/drivers/comedi_test.c index 9747e6d1f6eb..7984950f0f99 100644 --- a/drivers/comedi/drivers/comedi_test.c +++ b/drivers/comedi/drivers/comedi_test.c @@ -792,7 +792,7 @@ static void waveform_detach(struct comedi_device *dev) { struct waveform_private *devpriv = dev->private; - if (devpriv) { + if (devpriv && dev->n_subdevices) { timer_delete_sync(&devpriv->ai_timer); timer_delete_sync(&devpriv->ao_timer); } diff --git a/drivers/comedi/drivers/das16m1.c b/drivers/comedi/drivers/das16m1.c index b8ea737ad3d1..1b638f5b5a4f 100644 --- a/drivers/comedi/drivers/das16m1.c +++ b/drivers/comedi/drivers/das16m1.c @@ -522,7 +522,8 @@ static int das16m1_attach(struct comedi_device *dev, devpriv->extra_iobase = dev->iobase + DAS16M1_8255_IOBASE; /* only irqs 2, 3, 4, 5, 6, 7, 10, 11, 12, 14, and 15 are valid */ - if ((1 << it->options[1]) & 0xdcfc) { + if (it->options[1] >= 2 && it->options[1] <= 15 && + (1 << it->options[1]) & 0xdcfc) { ret = request_irq(it->options[1], das16m1_interrupt, 0, dev->board_name, dev); if (ret == 0) diff --git a/drivers/comedi/drivers/das6402.c b/drivers/comedi/drivers/das6402.c index 68f95330de45..7660487e563c 100644 --- a/drivers/comedi/drivers/das6402.c +++ b/drivers/comedi/drivers/das6402.c @@ -567,7 +567,8 @@ static int das6402_attach(struct comedi_device *dev, das6402_reset(dev); /* IRQs 2,3,5,6,7, 10,11,15 are valid for "enhanced" mode */ - if ((1 << it->options[1]) & 0x8cec) { + if (it->options[1] > 0 && it->options[1] < 16 && + (1 << it->options[1]) & 0x8cec) { ret = request_irq(it->options[1], das6402_interrupt, 0, dev->board_name, dev); if (ret == 0) { diff --git a/drivers/comedi/drivers/pcl812.c b/drivers/comedi/drivers/pcl812.c index 0df639c6a595..abca61a72cf7 100644 --- a/drivers/comedi/drivers/pcl812.c +++ b/drivers/comedi/drivers/pcl812.c @@ -1149,7 +1149,8 @@ static int pcl812_attach(struct comedi_device *dev, struct comedi_devconfig *it) if (IS_ERR(dev->pacer)) return PTR_ERR(dev->pacer); - if ((1 << it->options[1]) & board->irq_bits) { + if (it->options[1] > 0 && it->options[1] < 16 && + (1 << it->options[1]) & board->irq_bits) { ret = request_irq(it->options[1], pcl812_interrupt, 0, dev->board_name, dev); if (ret == 0) diff --git a/drivers/cpuidle/cpuidle-psci.c b/drivers/cpuidle/cpuidle-psci.c index 4e1ba35deda9..b19bc60cc627 100644 --- a/drivers/cpuidle/cpuidle-psci.c +++ b/drivers/cpuidle/cpuidle-psci.c @@ -45,7 +45,6 @@ struct psci_cpuidle_domain_state { static DEFINE_PER_CPU_READ_MOSTLY(struct psci_cpuidle_data, psci_cpuidle_data); static DEFINE_PER_CPU(struct psci_cpuidle_domain_state, psci_domain_state); static bool psci_cpuidle_use_syscore; -static bool psci_cpuidle_use_cpuhp; void psci_set_domain_state(struct generic_pm_domain *pd, unsigned int state_idx, u32 state) @@ -124,8 +123,12 @@ static int psci_idle_cpuhp_up(unsigned int cpu) { struct device *pd_dev = __this_cpu_read(psci_cpuidle_data.dev); - if (pd_dev) - pm_runtime_get_sync(pd_dev); + if (pd_dev) { + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + pm_runtime_get_sync(pd_dev); + else + dev_pm_genpd_resume(pd_dev); + } return 0; } @@ -135,7 +138,11 @@ static int psci_idle_cpuhp_down(unsigned int cpu) struct device *pd_dev = __this_cpu_read(psci_cpuidle_data.dev); if (pd_dev) { - pm_runtime_put_sync(pd_dev); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + pm_runtime_put_sync(pd_dev); + else + dev_pm_genpd_suspend(pd_dev); + /* Clear domain state to start fresh at next online. */ psci_clear_domain_state(); } @@ -196,9 +203,6 @@ static void psci_idle_init_cpuhp(void) { int err; - if (!psci_cpuidle_use_cpuhp) - return; - err = cpuhp_setup_state_nocalls(CPUHP_AP_CPU_PM_STARTING, "cpuidle/psci:online", psci_idle_cpuhp_up, @@ -259,10 +263,8 @@ static int psci_dt_cpu_init_topology(struct cpuidle_driver *drv, * s2ram and s2idle. */ drv->states[state_count - 1].enter_s2idle = psci_enter_s2idle_domain_idle_state; - if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) drv->states[state_count - 1].enter = psci_enter_domain_idle_state; - psci_cpuidle_use_cpuhp = true; - } return 0; } @@ -339,7 +341,6 @@ static void psci_cpu_deinit_idle(int cpu) dt_idle_detach_cpu(data->dev); psci_cpuidle_use_syscore = false; - psci_cpuidle_use_cpuhp = false; } static int psci_idle_init_cpu(struct device *dev, int cpu) diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c index af37477ffd8d..be21e4e2016c 100644 --- a/drivers/crypto/chelsio/chcr_algo.c +++ b/drivers/crypto/chelsio/chcr_algo.c @@ -314,30 +314,30 @@ static int chcr_compute_partial_hash(struct shash_desc *desc, if (digest_size == SHA1_DIGEST_SIZE) { error = crypto_shash_init(desc) ?: crypto_shash_update(desc, iopad, SHA1_BLOCK_SIZE) ?: - crypto_shash_export(desc, (void *)&sha1_st); + crypto_shash_export_core(desc, &sha1_st); memcpy(result_hash, sha1_st.state, SHA1_DIGEST_SIZE); } else if (digest_size == SHA224_DIGEST_SIZE) { error = crypto_shash_init(desc) ?: crypto_shash_update(desc, iopad, SHA256_BLOCK_SIZE) ?: - crypto_shash_export(desc, (void *)&sha256_st); + crypto_shash_export_core(desc, &sha256_st); memcpy(result_hash, sha256_st.state, SHA256_DIGEST_SIZE); } else if (digest_size == SHA256_DIGEST_SIZE) { error = crypto_shash_init(desc) ?: crypto_shash_update(desc, iopad, SHA256_BLOCK_SIZE) ?: - crypto_shash_export(desc, (void *)&sha256_st); + crypto_shash_export_core(desc, &sha256_st); memcpy(result_hash, sha256_st.state, SHA256_DIGEST_SIZE); } else if (digest_size == SHA384_DIGEST_SIZE) { error = crypto_shash_init(desc) ?: crypto_shash_update(desc, iopad, SHA512_BLOCK_SIZE) ?: - crypto_shash_export(desc, (void *)&sha512_st); + crypto_shash_export_core(desc, &sha512_st); memcpy(result_hash, sha512_st.state, SHA512_DIGEST_SIZE); } else if (digest_size == SHA512_DIGEST_SIZE) { error = crypto_shash_init(desc) ?: crypto_shash_update(desc, iopad, SHA512_BLOCK_SIZE) ?: - crypto_shash_export(desc, (void *)&sha512_st); + crypto_shash_export_core(desc, &sha512_st); memcpy(result_hash, sha512_st.state, SHA512_DIGEST_SIZE); } else { error = -EINVAL; diff --git a/drivers/crypto/intel/qat/qat_common/qat_algs.c b/drivers/crypto/intel/qat/qat_common/qat_algs.c index 3c4bba4a8779..c03a69851114 100644 --- a/drivers/crypto/intel/qat/qat_common/qat_algs.c +++ b/drivers/crypto/intel/qat/qat_common/qat_algs.c @@ -5,11 +5,11 @@ #include <linux/crypto.h> #include <crypto/internal/aead.h> #include <crypto/internal/cipher.h> +#include <crypto/internal/hash.h> #include <crypto/internal/skcipher.h> #include <crypto/aes.h> #include <crypto/sha1.h> #include <crypto/sha2.h> -#include <crypto/hash.h> #include <crypto/hmac.h> #include <crypto/algapi.h> #include <crypto/authenc.h> @@ -154,19 +154,19 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash, switch (ctx->qat_hash_alg) { case ICP_QAT_HW_AUTH_ALGO_SHA1: - if (crypto_shash_export(shash, &ctx->sha1)) + if (crypto_shash_export_core(shash, &ctx->sha1)) return -EFAULT; for (i = 0; i < digest_size >> 2; i++, hash_state_out++) *hash_state_out = cpu_to_be32(ctx->sha1.state[i]); break; case ICP_QAT_HW_AUTH_ALGO_SHA256: - if (crypto_shash_export(shash, &ctx->sha256)) + if (crypto_shash_export_core(shash, &ctx->sha256)) return -EFAULT; for (i = 0; i < digest_size >> 2; i++, hash_state_out++) *hash_state_out = cpu_to_be32(ctx->sha256.state[i]); break; case ICP_QAT_HW_AUTH_ALGO_SHA512: - if (crypto_shash_export(shash, &ctx->sha512)) + if (crypto_shash_export_core(shash, &ctx->sha512)) return -EFAULT; for (i = 0; i < digest_size >> 3; i++, hash512_state_out++) *hash512_state_out = cpu_to_be64(ctx->sha512.state[i]); @@ -190,19 +190,19 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash, switch (ctx->qat_hash_alg) { case ICP_QAT_HW_AUTH_ALGO_SHA1: - if (crypto_shash_export(shash, &ctx->sha1)) + if (crypto_shash_export_core(shash, &ctx->sha1)) return -EFAULT; for (i = 0; i < digest_size >> 2; i++, hash_state_out++) *hash_state_out = cpu_to_be32(ctx->sha1.state[i]); break; case ICP_QAT_HW_AUTH_ALGO_SHA256: - if (crypto_shash_export(shash, &ctx->sha256)) + if (crypto_shash_export_core(shash, &ctx->sha256)) return -EFAULT; for (i = 0; i < digest_size >> 2; i++, hash_state_out++) *hash_state_out = cpu_to_be32(ctx->sha256.state[i]); break; case ICP_QAT_HW_AUTH_ALGO_SHA512: - if (crypto_shash_export(shash, &ctx->sha512)) + if (crypto_shash_export_core(shash, &ctx->sha512)) return -EFAULT; for (i = 0; i < digest_size >> 3; i++, hash512_state_out++) *hash512_state_out = cpu_to_be64(ctx->sha512.state[i]); diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c index 49f09998e5c0..3371e0a76d3c 100644 --- a/drivers/dma/dw-edma/dw-edma-pcie.c +++ b/drivers/dma/dw-edma/dw-edma-pcie.c @@ -161,12 +161,16 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *pid) { struct dw_edma_pcie_data *pdata = (void *)pid->driver_data; - struct dw_edma_pcie_data vsec_data; + struct dw_edma_pcie_data *vsec_data __free(kfree) = NULL; struct device *dev = &pdev->dev; struct dw_edma_chip *chip; int err, nr_irqs; int i, mask; + vsec_data = kmalloc(sizeof(*vsec_data), GFP_KERNEL); + if (!vsec_data) + return -ENOMEM; + /* Enable PCI device */ err = pcim_enable_device(pdev); if (err) { @@ -174,23 +178,23 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, return err; } - memcpy(&vsec_data, pdata, sizeof(struct dw_edma_pcie_data)); + memcpy(vsec_data, pdata, sizeof(struct dw_edma_pcie_data)); /* * Tries to find if exists a PCIe Vendor-Specific Extended Capability * for the DMA, if one exists, then reconfigures it. */ - dw_edma_pcie_get_vsec_dma_data(pdev, &vsec_data); + dw_edma_pcie_get_vsec_dma_data(pdev, vsec_data); /* Mapping PCI BAR regions */ - mask = BIT(vsec_data.rg.bar); - for (i = 0; i < vsec_data.wr_ch_cnt; i++) { - mask |= BIT(vsec_data.ll_wr[i].bar); - mask |= BIT(vsec_data.dt_wr[i].bar); + mask = BIT(vsec_data->rg.bar); + for (i = 0; i < vsec_data->wr_ch_cnt; i++) { + mask |= BIT(vsec_data->ll_wr[i].bar); + mask |= BIT(vsec_data->dt_wr[i].bar); } - for (i = 0; i < vsec_data.rd_ch_cnt; i++) { - mask |= BIT(vsec_data.ll_rd[i].bar); - mask |= BIT(vsec_data.dt_rd[i].bar); + for (i = 0; i < vsec_data->rd_ch_cnt; i++) { + mask |= BIT(vsec_data->ll_rd[i].bar); + mask |= BIT(vsec_data->dt_rd[i].bar); } err = pcim_iomap_regions(pdev, mask, pci_name(pdev)); if (err) { @@ -213,7 +217,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, return -ENOMEM; /* IRQs allocation */ - nr_irqs = pci_alloc_irq_vectors(pdev, 1, vsec_data.irqs, + nr_irqs = pci_alloc_irq_vectors(pdev, 1, vsec_data->irqs, PCI_IRQ_MSI | PCI_IRQ_MSIX); if (nr_irqs < 1) { pci_err(pdev, "fail to alloc IRQ vector (number of IRQs=%u)\n", @@ -224,22 +228,22 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, /* Data structure initialization */ chip->dev = dev; - chip->mf = vsec_data.mf; + chip->mf = vsec_data->mf; chip->nr_irqs = nr_irqs; chip->ops = &dw_edma_pcie_plat_ops; - chip->ll_wr_cnt = vsec_data.wr_ch_cnt; - chip->ll_rd_cnt = vsec_data.rd_ch_cnt; + chip->ll_wr_cnt = vsec_data->wr_ch_cnt; + chip->ll_rd_cnt = vsec_data->rd_ch_cnt; - chip->reg_base = pcim_iomap_table(pdev)[vsec_data.rg.bar]; + chip->reg_base = pcim_iomap_table(pdev)[vsec_data->rg.bar]; if (!chip->reg_base) return -ENOMEM; for (i = 0; i < chip->ll_wr_cnt; i++) { struct dw_edma_region *ll_region = &chip->ll_region_wr[i]; struct dw_edma_region *dt_region = &chip->dt_region_wr[i]; - struct dw_edma_block *ll_block = &vsec_data.ll_wr[i]; - struct dw_edma_block *dt_block = &vsec_data.dt_wr[i]; + struct dw_edma_block *ll_block = &vsec_data->ll_wr[i]; + struct dw_edma_block *dt_block = &vsec_data->dt_wr[i]; ll_region->vaddr.io = pcim_iomap_table(pdev)[ll_block->bar]; if (!ll_region->vaddr.io) @@ -263,8 +267,8 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, for (i = 0; i < chip->ll_rd_cnt; i++) { struct dw_edma_region *ll_region = &chip->ll_region_rd[i]; struct dw_edma_region *dt_region = &chip->dt_region_rd[i]; - struct dw_edma_block *ll_block = &vsec_data.ll_rd[i]; - struct dw_edma_block *dt_block = &vsec_data.dt_rd[i]; + struct dw_edma_block *ll_block = &vsec_data->ll_rd[i]; + struct dw_edma_block *dt_block = &vsec_data->dt_rd[i]; ll_region->vaddr.io = pcim_iomap_table(pdev)[ll_block->bar]; if (!ll_region->vaddr.io) @@ -298,31 +302,31 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, pci_dbg(pdev, "Version:\tUnknown (0x%x)\n", chip->mf); pci_dbg(pdev, "Registers:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p)\n", - vsec_data.rg.bar, vsec_data.rg.off, vsec_data.rg.sz, + vsec_data->rg.bar, vsec_data->rg.off, vsec_data->rg.sz, chip->reg_base); for (i = 0; i < chip->ll_wr_cnt; i++) { pci_dbg(pdev, "L. List:\tWRITE CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n", - i, vsec_data.ll_wr[i].bar, - vsec_data.ll_wr[i].off, chip->ll_region_wr[i].sz, + i, vsec_data->ll_wr[i].bar, + vsec_data->ll_wr[i].off, chip->ll_region_wr[i].sz, chip->ll_region_wr[i].vaddr.io, &chip->ll_region_wr[i].paddr); pci_dbg(pdev, "Data:\tWRITE CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n", - i, vsec_data.dt_wr[i].bar, - vsec_data.dt_wr[i].off, chip->dt_region_wr[i].sz, + i, vsec_data->dt_wr[i].bar, + vsec_data->dt_wr[i].off, chip->dt_region_wr[i].sz, chip->dt_region_wr[i].vaddr.io, &chip->dt_region_wr[i].paddr); } for (i = 0; i < chip->ll_rd_cnt; i++) { pci_dbg(pdev, "L. List:\tREAD CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n", - i, vsec_data.ll_rd[i].bar, - vsec_data.ll_rd[i].off, chip->ll_region_rd[i].sz, + i, vsec_data->ll_rd[i].bar, + vsec_data->ll_rd[i].off, chip->ll_region_rd[i].sz, chip->ll_region_rd[i].vaddr.io, &chip->ll_region_rd[i].paddr); pci_dbg(pdev, "Data:\tREAD CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n", - i, vsec_data.dt_rd[i].bar, - vsec_data.dt_rd[i].off, chip->dt_region_rd[i].sz, + i, vsec_data->dt_rd[i].bar, + vsec_data->dt_rd[i].off, chip->dt_region_rd[i].sz, chip->dt_region_rd[i].vaddr.io, &chip->dt_region_rd[i].paddr); } diff --git a/drivers/dma/mediatek/mtk-cqdma.c b/drivers/dma/mediatek/mtk-cqdma.c index 47c8adfdc155..9f0c41ca7770 100644 --- a/drivers/dma/mediatek/mtk-cqdma.c +++ b/drivers/dma/mediatek/mtk-cqdma.c @@ -449,9 +449,9 @@ static enum dma_status mtk_cqdma_tx_status(struct dma_chan *c, return ret; spin_lock_irqsave(&cvc->pc->lock, flags); - spin_lock_irqsave(&cvc->vc.lock, flags); + spin_lock(&cvc->vc.lock); vd = mtk_cqdma_find_active_desc(c, cookie); - spin_unlock_irqrestore(&cvc->vc.lock, flags); + spin_unlock(&cvc->vc.lock); spin_unlock_irqrestore(&cvc->pc->lock, flags); if (vd) { diff --git a/drivers/dma/nbpfaxi.c b/drivers/dma/nbpfaxi.c index 0d6324c4e2be..7a2488a0d6a3 100644 --- a/drivers/dma/nbpfaxi.c +++ b/drivers/dma/nbpfaxi.c @@ -1351,7 +1351,7 @@ static int nbpf_probe(struct platform_device *pdev) if (irqs == 1) { eirq = irqbuf[0]; - for (i = 0; i <= num_channels; i++) + for (i = 0; i < num_channels; i++) nbpf->chan[i].irq = irqbuf[0]; } else { eirq = platform_get_irq_byname(pdev, "error"); @@ -1361,16 +1361,15 @@ static int nbpf_probe(struct platform_device *pdev) if (irqs == num_channels + 1) { struct nbpf_channel *chan; - for (i = 0, chan = nbpf->chan; i <= num_channels; + for (i = 0, chan = nbpf->chan; i < num_channels; i++, chan++) { /* Skip the error IRQ */ if (irqbuf[i] == eirq) i++; + if (i >= ARRAY_SIZE(irqbuf)) + return -EINVAL; chan->irq = irqbuf[i]; } - - if (chan != nbpf->chan + num_channels) - return -EINVAL; } else { /* 2 IRQs and more than one channel */ if (irqbuf[0] == eirq) @@ -1378,7 +1377,7 @@ static int nbpf_probe(struct platform_device *pdev) else irq = irqbuf[0]; - for (i = 0; i <= num_channels; i++) + for (i = 0; i < num_channels; i++) nbpf->chan[i].irq = irq; } } diff --git a/drivers/firmware/efi/libstub/zboot.lds b/drivers/firmware/efi/libstub/zboot.lds index c3a166675450..367907eb7d86 100644 --- a/drivers/firmware/efi/libstub/zboot.lds +++ b/drivers/firmware/efi/libstub/zboot.lds @@ -29,14 +29,12 @@ SECTIONS . = _etext; } -#ifdef CONFIG_EFI_SBAT .sbat : ALIGN(4096) { _sbat = .; *(.sbat) _esbat = ALIGN(4096); . = _esbat; } -#endif .data : ALIGN(4096) { _data = .; @@ -60,6 +58,6 @@ SECTIONS PROVIDE(__efistub__gzdata_size = ABSOLUTE(__efistub__gzdata_end - __efistub__gzdata_start)); -PROVIDE(__data_rawsize = ABSOLUTE(_edata - _etext)); -PROVIDE(__data_size = ABSOLUTE(_end - _etext)); +PROVIDE(__data_rawsize = ABSOLUTE(_edata - _data)); +PROVIDE(__data_size = ABSOLUTE(_end - _data)); PROVIDE(__sbat_size = ABSOLUTE(_esbat - _sbat)); diff --git a/drivers/gpio/gpiolib-acpi-quirks.c b/drivers/gpio/gpiolib-acpi-quirks.c index 219667315b2c..c13545dce349 100644 --- a/drivers/gpio/gpiolib-acpi-quirks.c +++ b/drivers/gpio/gpiolib-acpi-quirks.c @@ -331,6 +331,19 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = { .ignore_interrupt = "AMDI0030:00@11", }, }, + { + /* + * Wakeup only works when keyboard backlight is turned off + * https://gitlab.freedesktop.org/drm/amd/-/issues/4169 + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_FAMILY, "Acer Nitro V 15"), + }, + .driver_data = &(struct acpi_gpiolib_dmi_quirk) { + .ignore_interrupt = "AMDI0030:00@8", + }, + }, {} /* Terminating entry */ }; diff --git a/drivers/gpio/gpiolib-devres.c b/drivers/gpio/gpiolib-devres.c index 4d5f83b17624..72422c5db364 100644 --- a/drivers/gpio/gpiolib-devres.c +++ b/drivers/gpio/gpiolib-devres.c @@ -319,7 +319,7 @@ EXPORT_SYMBOL_GPL(devm_gpiod_unhinge); */ void devm_gpiod_put_array(struct device *dev, struct gpio_descs *descs) { - devm_remove_action(dev, devm_gpiod_release_array, descs); + devm_release_action(dev, devm_gpiod_release_array, descs); } EXPORT_SYMBOL_GPL(devm_gpiod_put_array); diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 73ba73b31cb1..37ab78243fab 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -708,7 +708,7 @@ struct gpio_desc *of_find_gpio(struct device_node *np, const char *con_id, unsigned int idx, unsigned long *flags) { char propname[32]; /* 32 is max size of property name */ - enum of_gpio_flags of_flags; + enum of_gpio_flags of_flags = 0; const of_find_gpio_quirk *q; struct gpio_desc *desc; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index fdafa0df1b43..3a3eca5b4c40 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -3297,14 +3297,15 @@ static int gpiod_get_raw_value_commit(const struct gpio_desc *desc) static int gpio_chip_get_multiple(struct gpio_chip *gc, unsigned long *mask, unsigned long *bits) { - int ret; - lockdep_assert_held(&gc->gpiodev->srcu); if (gc->get_multiple) { + int ret; + ret = gc->get_multiple(gc, mask, bits); if (ret > 0) return -EBADE; + return ret; } if (gc->get) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 78f8755996f0..aa32df7e2fb2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5193,6 +5193,8 @@ exit: dev->dev->power.disable_depth--; #endif } + + amdgpu_vram_mgr_clear_reset_blocks(adev); adev->in_suspend = false; if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D0)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 426834806fbf..6ac0ce361a2d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -427,6 +427,7 @@ bool amdgpu_ring_soft_recovery(struct amdgpu_ring *ring, unsigned int vmid, { unsigned long flags; ktime_t deadline; + bool ret; if (unlikely(ring->adev->debug_disable_soft_recovery)) return false; @@ -441,12 +442,16 @@ bool amdgpu_ring_soft_recovery(struct amdgpu_ring *ring, unsigned int vmid, dma_fence_set_error(fence, -ENODATA); spin_unlock_irqrestore(fence->lock, flags); - atomic_inc(&ring->adev->gpu_reset_counter); while (!dma_fence_is_signaled(fence) && ktime_to_ns(ktime_sub(deadline, ktime_get())) > 0) ring->funcs->soft_recovery(ring, vmid); - return dma_fence_is_signaled(fence); + ret = dma_fence_is_signaled(fence); + /* increment the counter only if soft reset worked */ + if (ret) + atomic_inc(&ring->adev->gpu_reset_counter); + + return ret; } /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 208b7d1d8a27..450e4bf093b7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -154,6 +154,7 @@ int amdgpu_vram_mgr_reserve_range(struct amdgpu_vram_mgr *mgr, uint64_t start, uint64_t size); int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr, uint64_t start); +void amdgpu_vram_mgr_clear_reset_blocks(struct amdgpu_device *adev); bool amdgpu_res_cpu_visible(struct amdgpu_device *adev, struct ttm_resource *res); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index abdc52b0895a..07c936e90d8e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -783,6 +783,23 @@ uint64_t amdgpu_vram_mgr_vis_usage(struct amdgpu_vram_mgr *mgr) } /** + * amdgpu_vram_mgr_clear_reset_blocks - reset clear blocks + * + * @adev: amdgpu device pointer + * + * Reset the cleared drm buddy blocks. + */ +void amdgpu_vram_mgr_clear_reset_blocks(struct amdgpu_device *adev) +{ + struct amdgpu_vram_mgr *mgr = &adev->mman.vram_mgr; + struct drm_buddy *mm = &mgr->mm; + + mutex_lock(&mgr->lock); + drm_buddy_reset_clear(mm, false); + mutex_unlock(&mgr->lock); +} + +/** * amdgpu_vram_mgr_intersects - test each drm buddy block for intersection * * @man: TTM memory type manager diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 5ee2237d8ee8..bc983ecf3d99 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4640,6 +4640,7 @@ static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring) memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(struct vi_mqd_allocation)); /* reset ring buffer */ ring->wptr = 0; + atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0); amdgpu_ring_clear_ring(ring); } return 0; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index 87058271b00c..2551823382f8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -728,7 +728,16 @@ int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm, * support programmable degamma anywhere. */ is_dcn = dm->adev->dm.dc->caps.color.dpp.dcn_arch; - drm_crtc_enable_color_mgmt(&acrtc->base, is_dcn ? MAX_COLOR_LUT_ENTRIES : 0, + /* Dont't enable DRM CRTC degamma property for DCN401 since the + * pre-blending degamma LUT doesn't apply to cursor, and therefore + * can't work similar to a post-blending degamma LUT as in other hw + * versions. + * TODO: revisit it once KMS plane color API is merged. + */ + drm_crtc_enable_color_mgmt(&acrtc->base, + (is_dcn && + dm->adev->dm.dc->ctx->dce_version != DCN_VERSION_4_01) ? + MAX_COLOR_LUT_ENTRIES : 0, true, MAX_COLOR_LUT_ENTRIES); drm_mode_crtc_set_gamma_size(&acrtc->base, MAX_COLOR_LEGACY_LUT_ENTRIES); diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c index a3b8e3d4a429..4b17d2fcd565 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c @@ -1565,7 +1565,7 @@ struct clk_mgr_internal *dcn401_clk_mgr_construct( clk_mgr->base.bw_params = kzalloc(sizeof(*clk_mgr->base.bw_params), GFP_KERNEL); if (!clk_mgr->base.bw_params) { BREAK_TO_DEBUGGER(); - kfree(clk_mgr); + kfree(clk_mgr401); return NULL; } @@ -1576,6 +1576,7 @@ struct clk_mgr_internal *dcn401_clk_mgr_construct( if (!clk_mgr->wm_range_table) { BREAK_TO_DEBUGGER(); kfree(clk_mgr->base.bw_params); + kfree(clk_mgr401); return NULL; } diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index de9c23537465..834b42a4d31f 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -1373,7 +1373,7 @@ static int ti_sn_bridge_probe(struct auxiliary_device *adev, regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, HPD_DISABLE, 0); mutex_unlock(&pdata->comms_mutex); - }; + } drm_bridge_add(&pdata->bridge); diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index dc622c78db9d..ea78c6c8ca7a 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -725,7 +725,7 @@ ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset, * monitor doesn't power down exactly after the throw away read. */ if (!aux->is_remote) { - ret = drm_dp_dpcd_probe(aux, DP_LANE0_1_STATUS); + ret = drm_dp_dpcd_probe(aux, DP_TRAINING_PATTERN_SET); if (ret < 0) return ret; } diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c index 241c855f891f..66aff35f8647 100644 --- a/drivers/gpu/drm/drm_buddy.c +++ b/drivers/gpu/drm/drm_buddy.c @@ -405,6 +405,49 @@ drm_get_buddy(struct drm_buddy_block *block) EXPORT_SYMBOL(drm_get_buddy); /** + * drm_buddy_reset_clear - reset blocks clear state + * + * @mm: DRM buddy manager + * @is_clear: blocks clear state + * + * Reset the clear state based on @is_clear value for each block + * in the freelist. + */ +void drm_buddy_reset_clear(struct drm_buddy *mm, bool is_clear) +{ + u64 root_size, size, start; + unsigned int order; + int i; + + size = mm->size; + for (i = 0; i < mm->n_roots; ++i) { + order = ilog2(size) - ilog2(mm->chunk_size); + start = drm_buddy_block_offset(mm->roots[i]); + __force_merge(mm, start, start + size, order); + + root_size = mm->chunk_size << order; + size -= root_size; + } + + for (i = 0; i <= mm->max_order; ++i) { + struct drm_buddy_block *block; + + list_for_each_entry_reverse(block, &mm->free_list[i], link) { + if (is_clear != drm_buddy_block_is_clear(block)) { + if (is_clear) { + mark_cleared(block); + mm->clear_avail += drm_buddy_block_size(mm, block); + } else { + clear_reset(block); + mm->clear_avail -= drm_buddy_block_size(mm, block); + } + } + } + } +} +EXPORT_SYMBOL(drm_buddy_reset_clear); + +/** * drm_buddy_free_block - free a block * * @mm: DRM buddy manager diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c index b781601946db..63a70f285cce 100644 --- a/drivers/gpu/drm/drm_framebuffer.c +++ b/drivers/gpu/drm/drm_framebuffer.c @@ -862,11 +862,23 @@ EXPORT_SYMBOL_FOR_TESTS_ONLY(drm_framebuffer_free); int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb, const struct drm_framebuffer_funcs *funcs) { + unsigned int i; int ret; + bool exists; if (WARN_ON_ONCE(fb->dev != dev || !fb->format)) return -EINVAL; + for (i = 0; i < fb->format->num_planes; i++) { + if (drm_WARN_ON_ONCE(dev, fb->internal_flags & DRM_FRAMEBUFFER_HAS_HANDLE_REF(i))) + fb->internal_flags &= ~DRM_FRAMEBUFFER_HAS_HANDLE_REF(i); + if (fb->obj[i]) { + exists = drm_gem_object_handle_get_if_exists_unlocked(fb->obj[i]); + if (exists) + fb->internal_flags |= DRM_FRAMEBUFFER_HAS_HANDLE_REF(i); + } + } + INIT_LIST_HEAD(&fb->filp_head); fb->funcs = funcs; @@ -875,7 +887,7 @@ int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb, ret = __drm_mode_object_add(dev, &fb->base, DRM_MODE_OBJECT_FB, false, drm_framebuffer_free); if (ret) - goto out; + goto err; mutex_lock(&dev->mode_config.fb_lock); dev->mode_config.num_fb++; @@ -883,7 +895,16 @@ int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb, mutex_unlock(&dev->mode_config.fb_lock); drm_mode_object_register(dev, &fb->base); -out: + + return 0; + +err: + for (i = 0; i < fb->format->num_planes; i++) { + if (fb->internal_flags & DRM_FRAMEBUFFER_HAS_HANDLE_REF(i)) { + drm_gem_object_handle_put_unlocked(fb->obj[i]); + fb->internal_flags &= ~DRM_FRAMEBUFFER_HAS_HANDLE_REF(i); + } + } return ret; } EXPORT_SYMBOL(drm_framebuffer_init); @@ -960,6 +981,12 @@ EXPORT_SYMBOL(drm_framebuffer_unregister_private); void drm_framebuffer_cleanup(struct drm_framebuffer *fb) { struct drm_device *dev = fb->dev; + unsigned int i; + + for (i = 0; i < fb->format->num_planes; i++) { + if (fb->internal_flags & DRM_FRAMEBUFFER_HAS_HANDLE_REF(i)) + drm_gem_object_handle_put_unlocked(fb->obj[i]); + } mutex_lock(&dev->mode_config.fb_lock); list_del(&fb->head); diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 4bf0a76bb35e..ac0524595bd6 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -223,23 +223,34 @@ static void drm_gem_object_handle_get(struct drm_gem_object *obj) } /** - * drm_gem_object_handle_get_unlocked - acquire reference on user-space handles + * drm_gem_object_handle_get_if_exists_unlocked - acquire reference on user-space handle, if any * @obj: GEM object * - * Acquires a reference on the GEM buffer object's handle. Required - * to keep the GEM object alive. Call drm_gem_object_handle_put_unlocked() - * to release the reference. + * Acquires a reference on the GEM buffer object's handle. Required to keep + * the GEM object alive. Call drm_gem_object_handle_put_if_exists_unlocked() + * to release the reference. Does nothing if the buffer object has no handle. + * + * Returns: + * True if a handle exists, or false otherwise */ -void drm_gem_object_handle_get_unlocked(struct drm_gem_object *obj) +bool drm_gem_object_handle_get_if_exists_unlocked(struct drm_gem_object *obj) { struct drm_device *dev = obj->dev; guard(mutex)(&dev->object_name_lock); - drm_WARN_ON(dev, !obj->handle_count); /* first ref taken in create-tail helper */ + /* + * First ref taken during GEM object creation, if any. Some + * drivers set up internal framebuffers with GEM objects that + * do not have a GEM handle. Hence, this counter can be zero. + */ + if (!obj->handle_count) + return false; + drm_gem_object_handle_get(obj); + + return true; } -EXPORT_SYMBOL(drm_gem_object_handle_get_unlocked); /** * drm_gem_object_handle_free - release resources bound to userspace handles @@ -272,7 +283,7 @@ static void drm_gem_object_exported_dma_buf_free(struct drm_gem_object *obj) } /** - * drm_gem_object_handle_put_unlocked - releases reference on user-space handles + * drm_gem_object_handle_put_unlocked - releases reference on user-space handle * @obj: GEM object * * Releases a reference on the GEM buffer object's handle. Possibly releases @@ -283,14 +294,14 @@ void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj) struct drm_device *dev = obj->dev; bool final = false; - if (WARN_ON(READ_ONCE(obj->handle_count) == 0)) + if (drm_WARN_ON(dev, READ_ONCE(obj->handle_count) == 0)) return; /* - * Must bump handle count first as this may be the last - * ref, in which case the object would disappear before we - * checked for a name - */ + * Must bump handle count first as this may be the last + * ref, in which case the object would disappear before + * we checked for a name. + */ mutex_lock(&dev->object_name_lock); if (--obj->handle_count == 0) { @@ -303,7 +314,6 @@ void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj) if (final) drm_gem_object_put(obj); } -EXPORT_SYMBOL(drm_gem_object_handle_put_unlocked); /* * Called at device or object close to release the file's @@ -315,6 +325,9 @@ drm_gem_object_release_handle(int id, void *ptr, void *data) struct drm_file *file_priv = data; struct drm_gem_object *obj = ptr; + if (drm_WARN_ON(obj->dev, !data)) + return 0; + if (obj->funcs->close) obj->funcs->close(obj, file_priv); @@ -435,7 +448,7 @@ drm_gem_handle_create_tail(struct drm_file *file_priv, idr_preload(GFP_KERNEL); spin_lock(&file_priv->table_lock); - ret = idr_alloc(&file_priv->object_idr, obj, 1, 0, GFP_NOWAIT); + ret = idr_alloc(&file_priv->object_idr, NULL, 1, 0, GFP_NOWAIT); spin_unlock(&file_priv->table_lock); idr_preload_end(); @@ -456,6 +469,11 @@ drm_gem_handle_create_tail(struct drm_file *file_priv, goto err_revoke; } + /* mirrors drm_gem_handle_delete to avoid races */ + spin_lock(&file_priv->table_lock); + obj = idr_replace(&file_priv->object_idr, obj, handle); + WARN_ON(obj != NULL); + spin_unlock(&file_priv->table_lock); *handlep = handle; return 0; diff --git a/drivers/gpu/drm/drm_gem_dma_helper.c b/drivers/gpu/drm/drm_gem_dma_helper.c index b7f033d4352a..4f0320df858f 100644 --- a/drivers/gpu/drm/drm_gem_dma_helper.c +++ b/drivers/gpu/drm/drm_gem_dma_helper.c @@ -230,7 +230,7 @@ void drm_gem_dma_free(struct drm_gem_dma_object *dma_obj) if (drm_gem_is_imported(gem_obj)) { if (dma_obj->vaddr) - dma_buf_vunmap_unlocked(gem_obj->dma_buf, &map); + dma_buf_vunmap_unlocked(gem_obj->import_attach->dmabuf, &map); drm_prime_gem_destroy(gem_obj, dma_obj->sgt); } else if (dma_obj->vaddr) { if (dma_obj->map_noncoherent) diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c index 14a87788695d..6ff22e04029e 100644 --- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c +++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c @@ -99,7 +99,7 @@ void drm_gem_fb_destroy(struct drm_framebuffer *fb) unsigned int i; for (i = 0; i < fb->format->num_planes; i++) - drm_gem_object_handle_put_unlocked(fb->obj[i]); + drm_gem_object_put(fb->obj[i]); drm_framebuffer_cleanup(fb); kfree(fb); @@ -182,10 +182,8 @@ int drm_gem_fb_init_with_funcs(struct drm_device *dev, if (!objs[i]) { drm_dbg_kms(dev, "Failed to lookup GEM object\n"); ret = -ENOENT; - goto err_gem_object_handle_put_unlocked; + goto err_gem_object_put; } - drm_gem_object_handle_get_unlocked(objs[i]); - drm_gem_object_put(objs[i]); min_size = (height - 1) * mode_cmd->pitches[i] + drm_format_info_min_pitch(info, i, width) @@ -195,22 +193,22 @@ int drm_gem_fb_init_with_funcs(struct drm_device *dev, drm_dbg_kms(dev, "GEM object size (%zu) smaller than minimum size (%u) for plane %d\n", objs[i]->size, min_size, i); - drm_gem_object_handle_put_unlocked(objs[i]); + drm_gem_object_put(objs[i]); ret = -EINVAL; - goto err_gem_object_handle_put_unlocked; + goto err_gem_object_put; } } ret = drm_gem_fb_init(dev, fb, mode_cmd, objs, i, funcs); if (ret) - goto err_gem_object_handle_put_unlocked; + goto err_gem_object_put; return 0; -err_gem_object_handle_put_unlocked: +err_gem_object_put: while (i > 0) { --i; - drm_gem_object_handle_put_unlocked(objs[i]); + drm_gem_object_put(objs[i]); } return ret; } @@ -421,6 +419,7 @@ EXPORT_SYMBOL(drm_gem_fb_vunmap); static void __drm_gem_fb_end_cpu_access(struct drm_framebuffer *fb, enum dma_data_direction dir, unsigned int num_planes) { + struct dma_buf_attachment *import_attach; struct drm_gem_object *obj; int ret; @@ -429,9 +428,10 @@ static void __drm_gem_fb_end_cpu_access(struct drm_framebuffer *fb, enum dma_dat obj = drm_gem_fb_get_obj(fb, num_planes); if (!obj) continue; + import_attach = obj->import_attach; if (!drm_gem_is_imported(obj)) continue; - ret = dma_buf_end_cpu_access(obj->dma_buf, dir); + ret = dma_buf_end_cpu_access(import_attach->dmabuf, dir); if (ret) drm_err(fb->dev, "dma_buf_end_cpu_access(%u, %d) failed: %d\n", ret, num_planes, dir); @@ -454,6 +454,7 @@ static void __drm_gem_fb_end_cpu_access(struct drm_framebuffer *fb, enum dma_dat */ int drm_gem_fb_begin_cpu_access(struct drm_framebuffer *fb, enum dma_data_direction dir) { + struct dma_buf_attachment *import_attach; struct drm_gem_object *obj; unsigned int i; int ret; @@ -464,9 +465,10 @@ int drm_gem_fb_begin_cpu_access(struct drm_framebuffer *fb, enum dma_data_direct ret = -EINVAL; goto err___drm_gem_fb_end_cpu_access; } + import_attach = obj->import_attach; if (!drm_gem_is_imported(obj)) continue; - ret = dma_buf_begin_cpu_access(obj->dma_buf, dir); + ret = dma_buf_begin_cpu_access(import_attach->dmabuf, dir); if (ret) goto err___drm_gem_fb_end_cpu_access; } diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index aa43265f4f4f..a5dbee6974ab 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -349,7 +349,7 @@ int drm_gem_shmem_vmap_locked(struct drm_gem_shmem_object *shmem, int ret = 0; if (drm_gem_is_imported(obj)) { - ret = dma_buf_vmap(obj->dma_buf, map); + ret = dma_buf_vmap(obj->import_attach->dmabuf, map); } else { pgprot_t prot = PAGE_KERNEL; @@ -409,7 +409,7 @@ void drm_gem_shmem_vunmap_locked(struct drm_gem_shmem_object *shmem, struct drm_gem_object *obj = &shmem->base; if (drm_gem_is_imported(obj)) { - dma_buf_vunmap(obj->dma_buf, map); + dma_buf_vunmap(obj->import_attach->dmabuf, map); } else { dma_resv_assert_held(shmem->base.resv); diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index be77d61a16ce..60c282881958 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -161,7 +161,7 @@ void drm_sysfs_lease_event(struct drm_device *dev); /* drm_gem.c */ int drm_gem_init(struct drm_device *dev); -void drm_gem_object_handle_get_unlocked(struct drm_gem_object *obj); +bool drm_gem_object_handle_get_if_exists_unlocked(struct drm_gem_object *obj); void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj); int drm_gem_handle_create_tail(struct drm_file *file_priv, struct drm_gem_object *obj, diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs index dd55b1cb764d..18492daae4b3 100644 --- a/drivers/gpu/drm/drm_panic_qr.rs +++ b/drivers/gpu/drm/drm_panic_qr.rs @@ -27,7 +27,7 @@ //! * <https://github.com/erwanvivien/fast_qr> //! * <https://github.com/bjguillot/qr> -use kernel::{prelude::*, str::CStr}; +use kernel::prelude::*; #[derive(Debug, Clone, Copy, PartialEq, Eq, Ord, PartialOrd)] struct Version(usize); diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index d828502268b8..a0a5d725eab0 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -453,7 +453,13 @@ struct dma_buf *drm_gem_prime_handle_to_dmabuf(struct drm_device *dev, } mutex_lock(&dev->object_name_lock); - /* re-export the original imported/exported object */ + /* re-export the original imported object */ + if (obj->import_attach) { + dmabuf = obj->import_attach->dmabuf; + get_dma_buf(dmabuf); + goto out_have_obj; + } + if (obj->dma_buf) { get_dma_buf(obj->dma_buf); dmabuf = obj->dma_buf; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c index 917ad527c961..40a50c60dfff 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c @@ -65,7 +65,7 @@ static void etnaviv_gem_prime_release(struct etnaviv_gem_object *etnaviv_obj) struct iosys_map map = IOSYS_MAP_INIT_VADDR(etnaviv_obj->vaddr); if (etnaviv_obj->vaddr) - dma_buf_vunmap_unlocked(etnaviv_obj->base.dma_buf, &map); + dma_buf_vunmap_unlocked(etnaviv_obj->base.import_attach->dmabuf, &map); /* Don't drop the pages for imported dmabuf, as they are not * ours, just free the array we allocated: @@ -82,7 +82,7 @@ static void *etnaviv_gem_prime_vmap_impl(struct etnaviv_gem_object *etnaviv_obj) lockdep_assert_held(&etnaviv_obj->lock); - ret = dma_buf_vmap(etnaviv_obj->base.dma_buf, &map); + ret = dma_buf_vmap(etnaviv_obj->base.import_attach->dmabuf, &map); if (ret) return NULL; return map.vaddr; diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index ba7b8938b17c..166ee11831ab 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -1938,7 +1938,7 @@ static int get_init_otp_deassert_fragment_len(struct intel_display *display, int index, len; if (drm_WARN_ON(display->drm, - !data || panel->vbt.dsi.seq_version != 1)) + !data || panel->vbt.dsi.seq_version >= 3)) return 0; /* index = 1 to skip sequence byte */ @@ -1961,7 +1961,7 @@ static int get_init_otp_deassert_fragment_len(struct intel_display *display, } /* - * Some v1 VBT MIPI sequences do the deassert in the init OTP sequence. + * Some v1/v2 VBT MIPI sequences do the deassert in the init OTP sequence. * The deassert must be done before calling intel_dsi_device_ready, so for * these devices we split the init OTP sequence into a deassert sequence and * the actual init OTP part. @@ -1972,9 +1972,9 @@ static void vlv_fixup_mipi_sequences(struct intel_display *display, u8 *init_otp; int len; - /* Limit this to v1 vid-mode sequences */ + /* Limit this to v1/v2 vid-mode sequences */ if (panel->vbt.dsi.config->is_cmd_mode || - panel->vbt.dsi.seq_version != 1) + panel->vbt.dsi.seq_version >= 3) return; /* Only do this if there are otp and assert seqs and no deassert seq */ diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 6f0a0bc71b06..43aa1f97378b 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -7061,7 +7061,8 @@ static void intel_atomic_commit_fence_wait(struct intel_atomic_state *intel_stat struct drm_i915_private *i915 = to_i915(intel_state->base.dev); struct drm_plane *plane; struct drm_plane_state *new_plane_state; - int ret, i; + long ret; + int i; for_each_new_plane_in_state(&intel_state->base, plane, new_plane_state, i) { if (new_plane_state->fence) { diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 640c43bf62d4..724de7ed3c04 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -1604,6 +1604,12 @@ int intel_dp_rate_select(struct intel_dp *intel_dp, int rate) void intel_dp_compute_rate(struct intel_dp *intel_dp, int port_clock, u8 *link_bw, u8 *rate_select) { + struct intel_display *display = to_intel_display(intel_dp); + + /* FIXME g4x can't generate an exact 2.7GHz with the 96MHz non-SSC refclk */ + if (display->platform.g4x && port_clock == 268800) + port_clock = 270000; + /* eDP 1.4 rate select method. */ if (intel_dp->use_rate_select) { *link_bw = 0; diff --git a/drivers/gpu/drm/imagination/pvr_power.c b/drivers/gpu/drm/imagination/pvr_power.c index 41f5d89e78b8..3e349d039fc0 100644 --- a/drivers/gpu/drm/imagination/pvr_power.c +++ b/drivers/gpu/drm/imagination/pvr_power.c @@ -386,13 +386,13 @@ pvr_power_reset(struct pvr_device *pvr_dev, bool hard_reset) if (!err) { if (hard_reset) { pvr_dev->fw_dev.booted = false; - WARN_ON(pm_runtime_force_suspend(from_pvr_device(pvr_dev)->dev)); + WARN_ON(pvr_power_device_suspend(from_pvr_device(pvr_dev)->dev)); err = pvr_fw_hard_reset(pvr_dev); if (err) goto err_device_lost; - err = pm_runtime_force_resume(from_pvr_device(pvr_dev)->dev); + err = pvr_power_device_resume(from_pvr_device(pvr_dev)->dev); pvr_dev->fw_dev.booted = true; if (err) goto err_device_lost; diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c index 8f6fba4217ec..bc7527542fdc 100644 --- a/drivers/gpu/drm/mediatek/mtk_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_crtc.c @@ -719,6 +719,39 @@ int mtk_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane, return 0; } +void mtk_crtc_plane_disable(struct drm_crtc *crtc, struct drm_plane *plane) +{ +#if IS_REACHABLE(CONFIG_MTK_CMDQ) + struct mtk_crtc *mtk_crtc = to_mtk_crtc(crtc); + struct mtk_plane_state *plane_state = to_mtk_plane_state(plane->state); + int i; + + /* no need to wait for disabling the plane by CPU */ + if (!mtk_crtc->cmdq_client.chan) + return; + + if (!mtk_crtc->enabled) + return; + + /* set pending plane state to disabled */ + for (i = 0; i < mtk_crtc->layer_nr; i++) { + struct drm_plane *mtk_plane = &mtk_crtc->planes[i]; + struct mtk_plane_state *mtk_plane_state = to_mtk_plane_state(mtk_plane->state); + + if (mtk_plane->index == plane->index) { + memcpy(mtk_plane_state, plane_state, sizeof(*plane_state)); + break; + } + } + mtk_crtc_update_config(mtk_crtc, false); + + /* wait for planes to be disabled by CMDQ */ + wait_event_timeout(mtk_crtc->cb_blocking_queue, + mtk_crtc->cmdq_vblank_cnt == 0, + msecs_to_jiffies(500)); +#endif +} + void mtk_crtc_async_update(struct drm_crtc *crtc, struct drm_plane *plane, struct drm_atomic_state *state) { @@ -930,7 +963,8 @@ static int mtk_crtc_init_comp_planes(struct drm_device *drm_dev, mtk_ddp_comp_supported_rotations(comp), mtk_ddp_comp_get_blend_modes(comp), mtk_ddp_comp_get_formats(comp), - mtk_ddp_comp_get_num_formats(comp), i); + mtk_ddp_comp_get_num_formats(comp), + mtk_ddp_comp_is_afbc_supported(comp), i); if (ret) return ret; diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.h b/drivers/gpu/drm/mediatek/mtk_crtc.h index 388e900b6f4d..828f109b83e7 100644 --- a/drivers/gpu/drm/mediatek/mtk_crtc.h +++ b/drivers/gpu/drm/mediatek/mtk_crtc.h @@ -21,6 +21,7 @@ int mtk_crtc_create(struct drm_device *drm_dev, const unsigned int *path, unsigned int num_conn_routes); int mtk_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane, struct mtk_plane_state *state); +void mtk_crtc_plane_disable(struct drm_crtc *crtc, struct drm_plane *plane); void mtk_crtc_async_update(struct drm_crtc *crtc, struct drm_plane *plane, struct drm_atomic_state *plane_state); struct device *mtk_crtc_dma_dev_get(struct drm_crtc *crtc); diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c index edc6417639e6..ac6620e10262 100644 --- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c +++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c @@ -366,6 +366,7 @@ static const struct mtk_ddp_comp_funcs ddp_ovl = { .get_blend_modes = mtk_ovl_get_blend_modes, .get_formats = mtk_ovl_get_formats, .get_num_formats = mtk_ovl_get_num_formats, + .is_afbc_supported = mtk_ovl_is_afbc_supported, }; static const struct mtk_ddp_comp_funcs ddp_postmask = { diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h index 39720b27f4e9..7289b3dcf22f 100644 --- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h +++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h @@ -83,6 +83,7 @@ struct mtk_ddp_comp_funcs { u32 (*get_blend_modes)(struct device *dev); const u32 *(*get_formats)(struct device *dev); size_t (*get_num_formats)(struct device *dev); + bool (*is_afbc_supported)(struct device *dev); void (*connect)(struct device *dev, struct device *mmsys_dev, unsigned int next); void (*disconnect)(struct device *dev, struct device *mmsys_dev, unsigned int next); void (*add)(struct device *dev, struct mtk_mutex *mutex); @@ -294,6 +295,14 @@ size_t mtk_ddp_comp_get_num_formats(struct mtk_ddp_comp *comp) return 0; } +static inline bool mtk_ddp_comp_is_afbc_supported(struct mtk_ddp_comp *comp) +{ + if (comp->funcs && comp->funcs->is_afbc_supported) + return comp->funcs->is_afbc_supported(comp->dev); + + return false; +} + static inline bool mtk_ddp_comp_add(struct mtk_ddp_comp *comp, struct mtk_mutex *mutex) { if (comp->funcs && comp->funcs->add) { diff --git a/drivers/gpu/drm/mediatek/mtk_disp_drv.h b/drivers/gpu/drm/mediatek/mtk_disp_drv.h index 04217a36939c..679d413bf10b 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_drv.h +++ b/drivers/gpu/drm/mediatek/mtk_disp_drv.h @@ -106,6 +106,7 @@ void mtk_ovl_disable_vblank(struct device *dev); u32 mtk_ovl_get_blend_modes(struct device *dev); const u32 *mtk_ovl_get_formats(struct device *dev); size_t mtk_ovl_get_num_formats(struct device *dev); +bool mtk_ovl_is_afbc_supported(struct device *dev); void mtk_ovl_adaptor_add_comp(struct device *dev, struct mtk_mutex *mutex); void mtk_ovl_adaptor_remove_comp(struct device *dev, struct mtk_mutex *mutex); diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index d0581c4e3c99..e0236353d499 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -236,6 +236,13 @@ size_t mtk_ovl_get_num_formats(struct device *dev) return ovl->data->num_formats; } +bool mtk_ovl_is_afbc_supported(struct device *dev) +{ + struct mtk_disp_ovl *ovl = dev_get_drvdata(dev); + + return ovl->data->supports_afbc; +} + int mtk_ovl_clk_enable(struct device *dev) { struct mtk_disp_ovl *ovl = dev_get_drvdata(dev); diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index 6fb85bc6487a..a2fdceadf209 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -1095,7 +1095,6 @@ static const u32 mt8183_output_fmts[] = { }; static const u32 mt8195_dpi_output_fmts[] = { - MEDIA_BUS_FMT_BGR888_1X24, MEDIA_BUS_FMT_RGB888_1X24, MEDIA_BUS_FMT_RGB888_2X12_LE, MEDIA_BUS_FMT_RGB888_2X12_BE, @@ -1103,18 +1102,19 @@ static const u32 mt8195_dpi_output_fmts[] = { MEDIA_BUS_FMT_YUYV8_1X16, MEDIA_BUS_FMT_YUYV10_1X20, MEDIA_BUS_FMT_YUYV12_1X24, + MEDIA_BUS_FMT_BGR888_1X24, MEDIA_BUS_FMT_YUV8_1X24, MEDIA_BUS_FMT_YUV10_1X30, }; static const u32 mt8195_dp_intf_output_fmts[] = { - MEDIA_BUS_FMT_BGR888_1X24, MEDIA_BUS_FMT_RGB888_1X24, MEDIA_BUS_FMT_RGB888_2X12_LE, MEDIA_BUS_FMT_RGB888_2X12_BE, MEDIA_BUS_FMT_RGB101010_1X30, MEDIA_BUS_FMT_YUYV8_1X16, MEDIA_BUS_FMT_YUYV10_1X20, + MEDIA_BUS_FMT_BGR888_1X24, MEDIA_BUS_FMT_YUV8_1X24, MEDIA_BUS_FMT_YUV10_1X30, }; diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c index 655106bbb76d..cbc4f37da8ba 100644 --- a/drivers/gpu/drm/mediatek/mtk_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_plane.c @@ -285,9 +285,14 @@ static void mtk_plane_atomic_disable(struct drm_plane *plane, struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane); struct mtk_plane_state *mtk_plane_state = to_mtk_plane_state(new_state); + struct drm_plane_state *old_state = drm_atomic_get_old_plane_state(state, + plane); + mtk_plane_state->pending.enable = false; wmb(); /* Make sure the above parameter is set before update */ mtk_plane_state->pending.dirty = true; + + mtk_crtc_plane_disable(old_state->crtc, plane); } static void mtk_plane_atomic_update(struct drm_plane *plane, @@ -321,7 +326,8 @@ static const struct drm_plane_helper_funcs mtk_plane_helper_funcs = { int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane, unsigned long possible_crtcs, enum drm_plane_type type, unsigned int supported_rotations, const u32 blend_modes, - const u32 *formats, size_t num_formats, unsigned int plane_idx) + const u32 *formats, size_t num_formats, + bool supports_afbc, unsigned int plane_idx) { int err; @@ -332,7 +338,9 @@ int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane, err = drm_universal_plane_init(dev, plane, possible_crtcs, &mtk_plane_funcs, formats, - num_formats, modifiers, type, NULL); + num_formats, + supports_afbc ? modifiers : NULL, + type, NULL); if (err) { DRM_ERROR("failed to initialize plane\n"); return err; diff --git a/drivers/gpu/drm/mediatek/mtk_plane.h b/drivers/gpu/drm/mediatek/mtk_plane.h index 3b13b89989c7..95c5fa5295d8 100644 --- a/drivers/gpu/drm/mediatek/mtk_plane.h +++ b/drivers/gpu/drm/mediatek/mtk_plane.h @@ -49,5 +49,6 @@ to_mtk_plane_state(struct drm_plane_state *state) int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane, unsigned long possible_crtcs, enum drm_plane_type type, unsigned int supported_rotations, const u32 blend_modes, - const u32 *formats, size_t num_formats, unsigned int plane_idx); + const u32 *formats, size_t num_formats, + bool supports_afbc, unsigned int plane_idx); #endif diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c index 200e65a7cefc..c7869a639bef 100644 --- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c +++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c @@ -314,14 +314,10 @@ nouveau_debugfs_fini(struct nouveau_drm *drm) drm->debugfs = NULL; } -int +void nouveau_module_debugfs_init(void) { nouveau_debugfs_root = debugfs_create_dir("nouveau", NULL); - if (IS_ERR(nouveau_debugfs_root)) - return PTR_ERR(nouveau_debugfs_root); - - return 0; } void diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.h b/drivers/gpu/drm/nouveau/nouveau_debugfs.h index b7617b344ee2..d05ed0e641c4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_debugfs.h +++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.h @@ -24,7 +24,7 @@ extern void nouveau_debugfs_fini(struct nouveau_drm *); extern struct dentry *nouveau_debugfs_root; -int nouveau_module_debugfs_init(void); +void nouveau_module_debugfs_init(void); void nouveau_module_debugfs_fini(void); #else static inline void @@ -42,10 +42,9 @@ nouveau_debugfs_fini(struct nouveau_drm *drm) { } -static inline int +static inline void nouveau_module_debugfs_init(void) { - return 0; } static inline void diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 0c82a63cd49d..1527b801f013 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -1461,9 +1461,7 @@ nouveau_drm_init(void) if (!nouveau_modeset) return 0; - ret = nouveau_module_debugfs_init(); - if (ret) - return ret; + nouveau_module_debugfs_init(); #ifdef CONFIG_NOUVEAU_PLATFORM_DRIVER platform_driver_register(&nouveau_platform_driver); diff --git a/drivers/gpu/drm/nouveau/nvif/chan.c b/drivers/gpu/drm/nouveau/nvif/chan.c index baa10227d51a..80c01017d642 100644 --- a/drivers/gpu/drm/nouveau/nvif/chan.c +++ b/drivers/gpu/drm/nouveau/nvif/chan.c @@ -39,6 +39,9 @@ nvif_chan_gpfifo_post(struct nvif_chan *chan) const u32 pbptr = (chan->push.cur - map) + chan->func->gpfifo.post_size; const u32 gpptr = (chan->gpfifo.cur + 1) & chan->gpfifo.max; + if (!chan->func->gpfifo.post) + return 0; + return chan->func->gpfifo.post(chan, gpptr, pbptr); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c index baf42339f93e..588cb4ab85cb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c @@ -719,7 +719,6 @@ r535_gsp_acpi_caps(acpi_handle handle, CAPS_METHOD_DATA *caps) union acpi_object argv4 = { .buffer.type = ACPI_TYPE_BUFFER, .buffer.length = 4, - .buffer.pointer = kmalloc(argv4.buffer.length, GFP_KERNEL), }, *obj; caps->status = 0xffff; @@ -727,17 +726,22 @@ r535_gsp_acpi_caps(acpi_handle handle, CAPS_METHOD_DATA *caps) if (!acpi_check_dsm(handle, &NVOP_DSM_GUID, NVOP_DSM_REV, BIT_ULL(0x1a))) return; + argv4.buffer.pointer = kmalloc(argv4.buffer.length, GFP_KERNEL); + if (!argv4.buffer.pointer) + return; + obj = acpi_evaluate_dsm(handle, &NVOP_DSM_GUID, NVOP_DSM_REV, 0x1a, &argv4); if (!obj) - return; + goto done; if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) || WARN_ON(obj->buffer.length != 4)) - return; + goto done; caps->status = 0; caps->optimusCaps = *(u32 *)obj->buffer.pointer; +done: ACPI_FREE(obj); kfree(argv4.buffer.pointer); @@ -754,24 +758,28 @@ r535_gsp_acpi_jt(acpi_handle handle, JT_METHOD_DATA *jt) union acpi_object argv4 = { .buffer.type = ACPI_TYPE_BUFFER, .buffer.length = sizeof(caps), - .buffer.pointer = kmalloc(argv4.buffer.length, GFP_KERNEL), }, *obj; jt->status = 0xffff; + argv4.buffer.pointer = kmalloc(argv4.buffer.length, GFP_KERNEL); + if (!argv4.buffer.pointer) + return; + obj = acpi_evaluate_dsm(handle, &JT_DSM_GUID, JT_DSM_REV, 0x1, &argv4); if (!obj) - return; + goto done; if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) || WARN_ON(obj->buffer.length != 4)) - return; + goto done; jt->status = 0; jt->jtCaps = *(u32 *)obj->buffer.pointer; jt->jtRevId = (jt->jtCaps & 0xfff00000) >> 20; jt->bSBIOSCaps = 0; +done: ACPI_FREE(obj); kfree(argv4.buffer.pointer); @@ -1744,6 +1752,13 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend) nvkm_gsp_sg_free(gsp->subdev.device, &gsp->sr.sgt); return ret; } + + /* + * TODO: Debug the GSP firmware / RPC handling to find out why + * without this Turing (but none of the other architectures) + * ends up resetting all channels after resume. + */ + msleep(50); } ret = r535_gsp_rpc_unloading_guest_driver(gsp, suspend); diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index 5657106c2f7d..15e2d505550f 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -841,7 +841,6 @@ int panfrost_job_init(struct panfrost_device *pfdev) .num_rqs = DRM_SCHED_PRIORITY_COUNT, .credit_limit = 2, .timeout = msecs_to_jiffies(JOB_TIMEOUT_MS), - .timeout_wq = pfdev->reset.wq, .name = "pan_js", .dev = pfdev->dev, }; @@ -879,6 +878,7 @@ int panfrost_job_init(struct panfrost_device *pfdev) pfdev->reset.wq = alloc_ordered_workqueue("panfrost-reset", 0); if (!pfdev->reset.wq) return -ENOMEM; + args.timeout_wq = pfdev->reset.wq; for (j = 0; j < NUM_JOB_SLOTS; j++) { js->queue[j].fence_context = dma_fence_context_alloc(1); diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index bbd39348a7ab..7a3e510327b7 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -26,7 +26,6 @@ * Jerome Glisse */ -#include <linux/console.h> #include <linux/efi.h> #include <linux/pci.h> #include <linux/pm_runtime.h> @@ -1635,11 +1634,9 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend, pci_set_power_state(pdev, PCI_D3hot); } - if (notify_clients) { - console_lock(); - drm_client_dev_suspend(dev, true); - console_unlock(); - } + if (notify_clients) + drm_client_dev_suspend(dev, false); + return 0; } @@ -1661,17 +1658,11 @@ int radeon_resume_kms(struct drm_device *dev, bool resume, bool notify_clients) if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) return 0; - if (notify_clients) { - console_lock(); - } if (resume) { pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); - if (pci_enable_device(pdev)) { - if (notify_clients) - console_unlock(); + if (pci_enable_device(pdev)) return -1; - } } /* resume AGP if in use */ radeon_agp_resume(rdev); @@ -1747,10 +1738,8 @@ int radeon_resume_kms(struct drm_device *dev, bool resume, bool notify_clients) if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) radeon_pm_compute_clocks(rdev); - if (notify_clients) { - drm_client_dev_resume(dev, true); - console_unlock(); - } + if (notify_clients) + drm_client_dev_resume(dev, false); return 0; } diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index e671aa241720..ac678de7fe5e 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -355,17 +355,6 @@ void drm_sched_entity_destroy(struct drm_sched_entity *entity) } EXPORT_SYMBOL(drm_sched_entity_destroy); -/* drm_sched_entity_clear_dep - callback to clear the entities dependency */ -static void drm_sched_entity_clear_dep(struct dma_fence *f, - struct dma_fence_cb *cb) -{ - struct drm_sched_entity *entity = - container_of(cb, struct drm_sched_entity, cb); - - entity->dependency = NULL; - dma_fence_put(f); -} - /* * drm_sched_entity_wakeup - callback to clear the entity's dependency and * wake up the scheduler @@ -376,7 +365,8 @@ static void drm_sched_entity_wakeup(struct dma_fence *f, struct drm_sched_entity *entity = container_of(cb, struct drm_sched_entity, cb); - drm_sched_entity_clear_dep(f, cb); + entity->dependency = NULL; + dma_fence_put(f); drm_sched_wakeup(entity->rq->sched); } @@ -429,13 +419,6 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity) fence = dma_fence_get(&s_fence->scheduled); dma_fence_put(entity->dependency); entity->dependency = fence; - if (!dma_fence_add_callback(fence, &entity->cb, - drm_sched_entity_clear_dep)) - return true; - - /* Ignore it when it is already scheduled */ - dma_fence_put(fence); - return false; } if (!dma_fence_add_callback(entity->dependency, &entity->cb, diff --git a/drivers/gpu/drm/tegra/nvdec.c b/drivers/gpu/drm/tegra/nvdec.c index 2d9a0a3f6c38..7a38664e890e 100644 --- a/drivers/gpu/drm/tegra/nvdec.c +++ b/drivers/gpu/drm/tegra/nvdec.c @@ -261,10 +261,8 @@ static int nvdec_load_falcon_firmware(struct nvdec *nvdec) if (!client->group) { virt = dma_alloc_coherent(nvdec->dev, size, &iova, GFP_KERNEL); - - err = dma_mapping_error(nvdec->dev, iova); - if (err < 0) - return err; + if (!virt) + return -ENOMEM; } else { virt = tegra_drm_alloc(tegra, size, &iova); if (IS_ERR(virt)) diff --git a/drivers/gpu/drm/virtio/virtgpu_prime.c b/drivers/gpu/drm/virtio/virtgpu_prime.c index 1118a0250279..ce49282198cb 100644 --- a/drivers/gpu/drm/virtio/virtgpu_prime.c +++ b/drivers/gpu/drm/virtio/virtgpu_prime.c @@ -204,15 +204,16 @@ static void virtgpu_dma_buf_free_obj(struct drm_gem_object *obj) { struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(obj); struct virtio_gpu_device *vgdev = obj->dev->dev_private; + struct dma_buf_attachment *attach = obj->import_attach; if (drm_gem_is_imported(obj)) { - struct dma_buf *dmabuf = obj->dma_buf; + struct dma_buf *dmabuf = attach->dmabuf; dma_resv_lock(dmabuf->resv, NULL); virtgpu_dma_buf_unmap(bo); dma_resv_unlock(dmabuf->resv); - dma_buf_detach(dmabuf, obj->import_attach); + dma_buf_detach(dmabuf, attach); dma_buf_put(dmabuf); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c index c55382167c1b..e417921af584 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c @@ -85,10 +85,10 @@ static int vmw_gem_vmap(struct drm_gem_object *obj, struct iosys_map *map) int ret; if (drm_gem_is_imported(obj)) { - ret = dma_buf_vmap(obj->dma_buf, map); + ret = dma_buf_vmap(obj->import_attach->dmabuf, map); if (!ret) { if (drm_WARN_ON(obj->dev, map->is_iomem)) { - dma_buf_vunmap(obj->dma_buf, map); + dma_buf_vunmap(obj->import_attach->dmabuf, map); return -EIO; } } @@ -102,7 +102,7 @@ static int vmw_gem_vmap(struct drm_gem_object *obj, struct iosys_map *map) static void vmw_gem_vunmap(struct drm_gem_object *obj, struct iosys_map *map) { if (drm_gem_is_imported(obj)) - dma_buf_vunmap(obj->dma_buf, map); + dma_buf_vunmap(obj->import_attach->dmabuf, map); else drm_gem_ttm_vunmap(obj, map); } diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c index 7a8af2311318..11e60d687572 100644 --- a/drivers/gpu/drm/xe/xe_devcoredump.c +++ b/drivers/gpu/drm/xe/xe_devcoredump.c @@ -171,14 +171,32 @@ static void xe_devcoredump_snapshot_free(struct xe_devcoredump_snapshot *ss) #define XE_DEVCOREDUMP_CHUNK_MAX (SZ_512M + SZ_1G) +/** + * xe_devcoredump_read() - Read data from the Xe device coredump snapshot + * @buffer: Destination buffer to copy the coredump data into + * @offset: Offset in the coredump data to start reading from + * @count: Number of bytes to read + * @data: Pointer to the xe_devcoredump structure + * @datalen: Length of the data (unused) + * + * Reads a chunk of the coredump snapshot data into the provided buffer. + * If the devcoredump is smaller than 1.5 GB (XE_DEVCOREDUMP_CHUNK_MAX), + * it is read directly from a pre-written buffer. For larger devcoredumps, + * the pre-written buffer must be periodically repopulated from the snapshot + * state due to kmalloc size limitations. + * + * Return: Number of bytes copied on success, or a negative error code on failure. + */ static ssize_t xe_devcoredump_read(char *buffer, loff_t offset, size_t count, void *data, size_t datalen) { struct xe_devcoredump *coredump = data; struct xe_devcoredump_snapshot *ss; - ssize_t byte_copied; + ssize_t byte_copied = 0; u32 chunk_offset; ssize_t new_chunk_position; + bool pm_needed = false; + int ret = 0; if (!coredump) return -ENODEV; @@ -188,20 +206,19 @@ static ssize_t xe_devcoredump_read(char *buffer, loff_t offset, /* Ensure delayed work is captured before continuing */ flush_work(&ss->work); - if (ss->read.size > XE_DEVCOREDUMP_CHUNK_MAX) + pm_needed = ss->read.size > XE_DEVCOREDUMP_CHUNK_MAX; + if (pm_needed) xe_pm_runtime_get(gt_to_xe(ss->gt)); mutex_lock(&coredump->lock); if (!ss->read.buffer) { - mutex_unlock(&coredump->lock); - return -ENODEV; + ret = -ENODEV; + goto unlock; } - if (offset >= ss->read.size) { - mutex_unlock(&coredump->lock); - return 0; - } + if (offset >= ss->read.size) + goto unlock; new_chunk_position = div_u64_rem(offset, XE_DEVCOREDUMP_CHUNK_MAX, @@ -221,12 +238,13 @@ static ssize_t xe_devcoredump_read(char *buffer, loff_t offset, ss->read.size - offset; memcpy(buffer, ss->read.buffer + chunk_offset, byte_copied); +unlock: mutex_unlock(&coredump->lock); - if (ss->read.size > XE_DEVCOREDUMP_CHUNK_MAX) + if (pm_needed) xe_pm_runtime_put(gt_to_xe(ss->gt)); - return byte_copied; + return byte_copied ? byte_copied : ret; } static void xe_devcoredump_free(void *data) diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index 6c4cb9576fb6..e3517ce2e18c 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -417,6 +417,8 @@ int xe_gt_init_early(struct xe_gt *gt) if (err) return err; + xe_mocs_init_early(gt); + return 0; } @@ -630,17 +632,15 @@ int xe_gt_init(struct xe_gt *gt) if (err) return err; - err = xe_gt_pagefault_init(gt); + err = xe_gt_sysfs_init(gt); if (err) return err; - xe_mocs_init_early(gt); - - err = xe_gt_sysfs_init(gt); + err = gt_fw_domain_init(gt); if (err) return err; - err = gt_fw_domain_init(gt); + err = xe_gt_pagefault_init(gt); if (err) return err; @@ -839,6 +839,9 @@ static int gt_reset(struct xe_gt *gt) goto err_out; } + if (IS_SRIOV_PF(gt_to_xe(gt))) + xe_gt_sriov_pf_stop_prepare(gt); + xe_uc_gucrc_disable(>->uc); xe_uc_stop_prepare(>->uc); xe_gt_pagefault_reset(gt); diff --git a/drivers/gpu/drm/xe/xe_gt.h b/drivers/gpu/drm/xe/xe_gt.h index 187fa6490eaf..6357325f3939 100644 --- a/drivers/gpu/drm/xe/xe_gt.h +++ b/drivers/gpu/drm/xe/xe_gt.h @@ -24,7 +24,7 @@ extern struct fault_attr gt_reset_failure; static inline bool xe_fault_inject_gt_reset(void) { - return should_fail(>_reset_failure, 1); + return IS_ENABLED(CONFIG_DEBUG_FS) && should_fail(>_reset_failure, 1); } struct xe_gt *xe_gt_alloc(struct xe_tile *tile); diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c index 10622ca471a2..6717a636b1d9 100644 --- a/drivers/gpu/drm/xe/xe_gt_pagefault.c +++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c @@ -444,6 +444,7 @@ static int xe_alloc_pf_queue(struct xe_gt *gt, struct pf_queue *pf_queue) #define PF_MULTIPLIER 8 pf_queue->num_dw = (num_eus + XE_NUM_HW_ENGINES) * PF_MSG_LEN_DW * PF_MULTIPLIER; + pf_queue->num_dw = roundup_pow_of_two(pf_queue->num_dw); #undef PF_MULTIPLIER pf_queue->gt = gt; diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c index c08efca6420e..35489fa81825 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c @@ -172,6 +172,25 @@ void xe_gt_sriov_pf_sanitize_hw(struct xe_gt *gt, unsigned int vfid) pf_clear_vf_scratch_regs(gt, vfid); } +static void pf_cancel_restart(struct xe_gt *gt) +{ + xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt))); + + if (cancel_work_sync(>->sriov.pf.workers.restart)) + xe_gt_sriov_dbg_verbose(gt, "pending restart canceled!\n"); +} + +/** + * xe_gt_sriov_pf_stop_prepare() - Prepare to stop SR-IOV support. + * @gt: the &xe_gt + * + * This function can only be called on the PF. + */ +void xe_gt_sriov_pf_stop_prepare(struct xe_gt *gt) +{ + pf_cancel_restart(gt); +} + static void pf_restart(struct xe_gt *gt) { struct xe_device *xe = gt_to_xe(gt); diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf.h index f474509411c0..e2b2ff8132dc 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.h +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.h @@ -13,6 +13,7 @@ int xe_gt_sriov_pf_init_early(struct xe_gt *gt); int xe_gt_sriov_pf_init(struct xe_gt *gt); void xe_gt_sriov_pf_init_hw(struct xe_gt *gt); void xe_gt_sriov_pf_sanitize_hw(struct xe_gt *gt, unsigned int vfid); +void xe_gt_sriov_pf_stop_prepare(struct xe_gt *gt); void xe_gt_sriov_pf_restart(struct xe_gt *gt); #else static inline int xe_gt_sriov_pf_init_early(struct xe_gt *gt) @@ -29,6 +30,10 @@ static inline void xe_gt_sriov_pf_init_hw(struct xe_gt *gt) { } +static inline void xe_gt_sriov_pf_stop_prepare(struct xe_gt *gt) +{ +} + static inline void xe_gt_sriov_pf_restart(struct xe_gt *gt) { } diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c index 2420a548cacc..53a44702c04a 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c @@ -2364,6 +2364,21 @@ int xe_gt_sriov_pf_config_restore(struct xe_gt *gt, unsigned int vfid, return err; } +static int pf_push_self_config(struct xe_gt *gt) +{ + int err; + + err = pf_push_full_vf_config(gt, PFID); + if (err) { + xe_gt_sriov_err(gt, "Failed to push self configuration (%pe)\n", + ERR_PTR(err)); + return err; + } + + xe_gt_sriov_dbg_verbose(gt, "self configuration completed\n"); + return 0; +} + static void fini_config(void *arg) { struct xe_gt *gt = arg; @@ -2387,9 +2402,17 @@ static void fini_config(void *arg) int xe_gt_sriov_pf_config_init(struct xe_gt *gt) { struct xe_device *xe = gt_to_xe(gt); + int err; xe_gt_assert(gt, IS_SRIOV_PF(xe)); + mutex_lock(xe_gt_sriov_pf_master_mutex(gt)); + err = pf_push_self_config(gt); + mutex_unlock(xe_gt_sriov_pf_master_mutex(gt)); + + if (err) + return err; + return devm_add_action_or_reset(xe->drm.dev, fini_config, gt); } @@ -2407,6 +2430,10 @@ void xe_gt_sriov_pf_config_restart(struct xe_gt *gt) unsigned int n, total_vfs = xe_sriov_pf_get_totalvfs(gt_to_xe(gt)); unsigned int fail = 0, skip = 0; + mutex_lock(xe_gt_sriov_pf_master_mutex(gt)); + pf_push_self_config(gt); + mutex_unlock(xe_gt_sriov_pf_master_mutex(gt)); + for (n = 1; n <= total_vfs; n++) { if (xe_gt_sriov_pf_config_is_empty(gt, n)) skip++; diff --git a/drivers/gpu/drm/xe/xe_lmtt.c b/drivers/gpu/drm/xe/xe_lmtt.c index 63db66df064b..023ed6a6b49d 100644 --- a/drivers/gpu/drm/xe/xe_lmtt.c +++ b/drivers/gpu/drm/xe/xe_lmtt.c @@ -78,6 +78,9 @@ static struct xe_lmtt_pt *lmtt_pt_alloc(struct xe_lmtt *lmtt, unsigned int level } lmtt_assert(lmtt, xe_bo_is_vram(bo)); + lmtt_debug(lmtt, "level=%u addr=%#llx\n", level, (u64)xe_bo_main_addr(bo, XE_PAGE_SIZE)); + + xe_map_memset(lmtt_to_xe(lmtt), &bo->vmap, 0, 0, bo->size); pt->level = level; pt->bo = bo; @@ -91,6 +94,9 @@ out: static void lmtt_pt_free(struct xe_lmtt_pt *pt) { + lmtt_debug(&pt->bo->tile->sriov.pf.lmtt, "level=%u addr=%llx\n", + pt->level, (u64)xe_bo_main_addr(pt->bo, XE_PAGE_SIZE)); + xe_bo_unpin_map_no_vm(pt->bo); kfree(pt); } @@ -226,9 +232,14 @@ static void lmtt_write_pte(struct xe_lmtt *lmtt, struct xe_lmtt_pt *pt, switch (lmtt->ops->lmtt_pte_size(level)) { case sizeof(u32): + lmtt_assert(lmtt, !overflows_type(pte, u32)); + lmtt_assert(lmtt, !pte || !iosys_map_rd(&pt->bo->vmap, idx * sizeof(u32), u32)); + xe_map_wr(lmtt_to_xe(lmtt), &pt->bo->vmap, idx * sizeof(u32), u32, pte); break; case sizeof(u64): + lmtt_assert(lmtt, !pte || !iosys_map_rd(&pt->bo->vmap, idx * sizeof(u64), u64)); + xe_map_wr(lmtt_to_xe(lmtt), &pt->bo->vmap, idx * sizeof(u64), u64, pte); break; default: diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index 7acdc4c78866..07a5161c7d5b 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -863,7 +863,7 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m, if (src_is_vram && xe_migrate_allow_identity(src_L0, &src_it)) xe_res_next(&src_it, src_L0); else - emit_pte(m, bb, src_L0_pt, src_is_vram, copy_system_ccs, + emit_pte(m, bb, src_L0_pt, src_is_vram, copy_system_ccs || use_comp_pat, &src_it, src_L0, src); if (dst_is_vram && xe_migrate_allow_identity(src_L0, &dst_it)) @@ -1817,8 +1817,8 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, xe_bo_assert_held(bo); /* Use bounce buffer for small access and unaligned access */ - if (len & XE_CACHELINE_MASK || - ((uintptr_t)buf | offset) & XE_CACHELINE_MASK) { + if (!IS_ALIGNED(len, XE_CACHELINE_BYTES) || + !IS_ALIGNED((unsigned long)buf + offset, XE_CACHELINE_BYTES)) { int buf_offset = 0; /* @@ -1848,7 +1848,7 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, err = xe_migrate_access_memory(m, bo, offset & ~XE_CACHELINE_MASK, (void *)ptr, - sizeof(bounce), 0); + sizeof(bounce), write); if (err) return err; } else { diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c index e4742e27e2cd..da6793c2f991 100644 --- a/drivers/gpu/drm/xe/xe_module.c +++ b/drivers/gpu/drm/xe/xe_module.c @@ -20,7 +20,7 @@ struct xe_modparam xe_modparam = { .probe_display = true, - .guc_log_level = 3, + .guc_log_level = IS_ENABLED(CONFIG_DRM_XE_DEBUG) ? 3 : 1, .force_probe = CONFIG_DRM_XE_FORCE_PROBE, .wedged_mode = 1, .svm_notifier_size = 512, diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c index ac4beaed58ff..278af53c74dc 100644 --- a/drivers/gpu/drm/xe/xe_pci.c +++ b/drivers/gpu/drm/xe/xe_pci.c @@ -140,7 +140,6 @@ static const struct xe_graphics_desc graphics_xelpg = { .has_asid = 1, \ .has_atomic_enable_pte_bit = 1, \ .has_flat_ccs = 1, \ - .has_indirect_ring_state = 1, \ .has_range_tlb_invalidation = 1, \ .has_usm = 1, \ .has_64bit_timestamp = 1, \ diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c index ff749edc005b..ad263de44111 100644 --- a/drivers/gpu/drm/xe/xe_pm.c +++ b/drivers/gpu/drm/xe/xe_pm.c @@ -134,7 +134,7 @@ int xe_pm_suspend(struct xe_device *xe) /* FIXME: Super racey... */ err = xe_bo_evict_all(xe); if (err) - goto err_pxp; + goto err_display; for_each_gt(gt, xe, id) { err = xe_gt_suspend(gt); @@ -151,7 +151,6 @@ int xe_pm_suspend(struct xe_device *xe) err_display: xe_display_pm_resume(xe); -err_pxp: xe_pxp_pm_resume(xe->pxp); err: drm_dbg(&xe->drm, "Device suspend failed %d\n", err); @@ -753,11 +752,13 @@ void xe_pm_assert_unbounded_bridge(struct xe_device *xe) } /** - * xe_pm_set_vram_threshold - Set a vram threshold for allowing/blocking D3Cold + * xe_pm_set_vram_threshold - Set a VRAM threshold for allowing/blocking D3Cold * @xe: xe device instance - * @threshold: VRAM size in bites for the D3cold threshold + * @threshold: VRAM size in MiB for the D3cold threshold * - * Returns 0 for success, negative error code otherwise. + * Return: + * * 0 - success + * * -EINVAL - invalid argument */ int xe_pm_set_vram_threshold(struct xe_device *xe, u32 threshold) { diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c index bc1689db4cd7..7b50c7c1ee21 100644 --- a/drivers/gpu/drm/xe/xe_ring_ops.c +++ b/drivers/gpu/drm/xe/xe_ring_ops.c @@ -110,13 +110,14 @@ static int emit_bb_start(u64 batch_addr, u32 ppgtt_flag, u32 *dw, int i) return i; } -static int emit_flush_invalidate(u32 *dw, int i) +static int emit_flush_invalidate(u32 addr, u32 val, u32 *dw, int i) { dw[i++] = MI_FLUSH_DW | MI_INVALIDATE_TLB | MI_FLUSH_DW_OP_STOREDW | - MI_FLUSH_IMM_DW | MI_FLUSH_DW_STORE_INDEX; - dw[i++] = LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR; - dw[i++] = 0; + MI_FLUSH_IMM_DW; + + dw[i++] = addr | MI_FLUSH_DW_USE_GTT; dw[i++] = 0; + dw[i++] = val; return i; } @@ -397,23 +398,20 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job, static void emit_migration_job_gen12(struct xe_sched_job *job, struct xe_lrc *lrc, u32 seqno) { + u32 saddr = xe_lrc_start_seqno_ggtt_addr(lrc); u32 dw[MAX_JOB_SIZE_DW], i = 0; i = emit_copy_timestamp(lrc, dw, i); - i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc), - seqno, dw, i); + i = emit_store_imm_ggtt(saddr, seqno, dw, i); dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE; /* Enabled again below */ i = emit_bb_start(job->ptrs[0].batch_addr, BIT(8), dw, i); - if (!IS_SRIOV_VF(gt_to_xe(job->q->gt))) { - /* XXX: Do we need this? Leaving for now. */ - dw[i++] = preparser_disable(true); - i = emit_flush_invalidate(dw, i); - dw[i++] = preparser_disable(false); - } + dw[i++] = preparser_disable(true); + i = emit_flush_invalidate(saddr, seqno, dw, i); + dw[i++] = preparser_disable(false); i = emit_bb_start(job->ptrs[1].batch_addr, BIT(8), dw, i); diff --git a/drivers/gpu/drm/xe/xe_uc_fw.c b/drivers/gpu/drm/xe/xe_uc_fw.c index 2741849bbf4d..a6612105201a 100644 --- a/drivers/gpu/drm/xe/xe_uc_fw.c +++ b/drivers/gpu/drm/xe/xe_uc_fw.c @@ -114,10 +114,10 @@ struct fw_blobs_by_type { #define XE_GT_TYPE_ANY XE_GT_TYPE_UNINITIALIZED #define XE_GUC_FIRMWARE_DEFS(fw_def, mmp_ver, major_ver) \ - fw_def(BATTLEMAGE, GT_TYPE_ANY, major_ver(xe, guc, bmg, 70, 44, 1)) \ - fw_def(LUNARLAKE, GT_TYPE_ANY, major_ver(xe, guc, lnl, 70, 44, 1)) \ + fw_def(BATTLEMAGE, GT_TYPE_ANY, major_ver(xe, guc, bmg, 70, 45, 2)) \ + fw_def(LUNARLAKE, GT_TYPE_ANY, major_ver(xe, guc, lnl, 70, 45, 2)) \ fw_def(METEORLAKE, GT_TYPE_ANY, major_ver(i915, guc, mtl, 70, 44, 1)) \ - fw_def(DG2, GT_TYPE_ANY, major_ver(i915, guc, dg2, 70, 44, 1)) \ + fw_def(DG2, GT_TYPE_ANY, major_ver(i915, guc, dg2, 70, 45, 2)) \ fw_def(DG1, GT_TYPE_ANY, major_ver(i915, guc, dg1, 70, 44, 1)) \ fw_def(ALDERLAKE_N, GT_TYPE_ANY, major_ver(i915, guc, tgl, 70, 44, 1)) \ fw_def(ALDERLAKE_P, GT_TYPE_ANY, major_ver(i915, guc, adlp, 70, 44, 1)) \ diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules index 69c1d7fc695e..6d70109fcc43 100644 --- a/drivers/gpu/drm/xe/xe_wa_oob.rules +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules @@ -38,10 +38,10 @@ GRAPHICS_VERSION(2004) GRAPHICS_VERSION_RANGE(3000, 3001) 22019338487 MEDIA_VERSION(2000) - GRAPHICS_VERSION(2001) + GRAPHICS_VERSION(2001), FUNC(xe_rtp_match_not_sriov_vf) MEDIA_VERSION(3000), MEDIA_STEP(A0, B0), FUNC(xe_rtp_match_not_sriov_vf) 22019338487_display PLATFORM(LUNARLAKE) -16023588340 GRAPHICS_VERSION(2001) +16023588340 GRAPHICS_VERSION(2001), FUNC(xe_rtp_match_not_sriov_vf) 14019789679 GRAPHICS_VERSION(1255) GRAPHICS_VERSION_RANGE(1270, 2004) no_media_l3 MEDIA_VERSION(3000) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index b348d0464314..b31b8a2fd540 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1883,9 +1883,12 @@ u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags) /* * 7 extra bytes are necessary to achieve proper functionality * of implement() working on 8 byte chunks + * 1 extra byte for the report ID if it is null (not used) so + * we can reserve that extra byte in the first position of the buffer + * when sending it to .raw_request() */ - u32 len = hid_report_len(report) + 7; + u32 len = hid_report_len(report) + 7 + (report->id == 0); return kzalloc(len, flags); } @@ -1973,7 +1976,7 @@ static struct hid_report *hid_get_report(struct hid_report_enum *report_enum, int __hid_request(struct hid_device *hid, struct hid_report *report, enum hid_class_request reqtype) { - char *buf; + char *buf, *data_buf; int ret; u32 len; @@ -1981,13 +1984,19 @@ int __hid_request(struct hid_device *hid, struct hid_report *report, if (!buf) return -ENOMEM; + data_buf = buf; len = hid_report_len(report); + if (report->id == 0) { + /* reserve the first byte for the report ID */ + data_buf++; + len++; + } + if (reqtype == HID_REQ_SET_REPORT) - hid_output_report(report, buf); + hid_output_report(report, data_buf); - ret = hid->ll_driver->raw_request(hid, report->id, buf, len, - report->type, reqtype); + ret = hid_hw_raw_request(hid, report->id, buf, len, report->type, reqtype); if (ret < 0) { dbg_hid("unable to complete request: %d\n", ret); goto out; diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index c6b6b1029540..4424c0512bae 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -3299,7 +3299,7 @@ static const char *keys[KEY_MAX + 1] = { [BTN_STYLUS2] = "Stylus2", [BTN_TOOL_DOUBLETAP] = "ToolDoubleTap", [BTN_TOOL_TRIPLETAP] = "ToolTripleTap", [BTN_TOOL_QUADTAP] = "ToolQuadrupleTap", [BTN_GEAR_DOWN] = "BtnGearDown", [BTN_GEAR_UP] = "BtnGearUp", - [BTN_WHEEL] = "BtnWheel", [KEY_OK] = "Ok", + [KEY_OK] = "Ok", [KEY_SELECT] = "Select", [KEY_GOTO] = "Goto", [KEY_CLEAR] = "Clear", [KEY_POWER2] = "Power2", [KEY_OPTION] = "Option", [KEY_INFO] = "Info", diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index 1cd188b73b74..57623ca7f350 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -9,7 +9,7 @@ config HYPERV select PARAVIRT select X86_HV_CALLBACK_VECTOR if X86 select OF_EARLY_FLATTREE if OF - select SYSFB if !HYPERV_VTL_MODE + select SYSFB if EFI && !HYPERV_VTL_MODE help Select this option to run Linux as a Hyper-V client operating system. diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 35f26fa1ffe7..7c7c66e0dc3f 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -18,6 +18,7 @@ #include <linux/uio.h> #include <linux/interrupt.h> #include <linux/set_memory.h> +#include <linux/export.h> #include <asm/page.h> #include <asm/mshyperv.h> diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 6e084c207414..65dd299e2944 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -20,6 +20,7 @@ #include <linux/delay.h> #include <linux/cpu.h> #include <linux/hyperv.h> +#include <linux/export.h> #include <asm/mshyperv.h> #include <linux/sched/isolation.h> diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index be490c598785..1fe3573ae52a 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -519,7 +519,10 @@ void vmbus_set_event(struct vmbus_channel *channel) else WARN_ON_ONCE(1); } else { - hv_do_fast_hypercall8(HVCALL_SIGNAL_EVENT, channel->sig_event); + u64 control = HVCALL_SIGNAL_EVENT; + + control |= hv_nested ? HV_HYPERCALL_NESTED : 0; + hv_do_fast_hypercall8(control, channel->sig_event); } } EXPORT_SYMBOL_GPL(vmbus_set_event); diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 308c8f279df8..b14c5f9e0ef2 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -85,8 +85,10 @@ int hv_post_message(union hv_connection_id connection_id, else status = HV_STATUS_INVALID_PARAMETER; } else { - status = hv_do_hypercall(HVCALL_POST_MESSAGE, - aligned_msg, NULL); + u64 control = HVCALL_POST_MESSAGE; + + control |= hv_nested ? HV_HYPERCALL_NESTED : 0; + status = hv_do_hypercall(control, aligned_msg, NULL); } local_irq_restore(flags); diff --git a/drivers/hv/hv_proc.c b/drivers/hv/hv_proc.c index 7d7ecb6f6137..fbb4eb3901bb 100644 --- a/drivers/hv/hv_proc.c +++ b/drivers/hv/hv_proc.c @@ -6,6 +6,7 @@ #include <linux/slab.h> #include <linux/cpuhotplug.h> #include <linux/minmax.h> +#include <linux/export.h> #include <asm/mshyperv.h> /* diff --git a/drivers/hv/mshv_common.c b/drivers/hv/mshv_common.c index 2575e6d7a71f..6f227a8a5af7 100644 --- a/drivers/hv/mshv_common.c +++ b/drivers/hv/mshv_common.c @@ -13,6 +13,7 @@ #include <linux/mm.h> #include <asm/mshyperv.h> #include <linux/resume_user_mode.h> +#include <linux/export.h> #include "mshv.h" diff --git a/drivers/hv/mshv_eventfd.c b/drivers/hv/mshv_eventfd.c index 8dd22be2ca0b..b348928871c2 100644 --- a/drivers/hv/mshv_eventfd.c +++ b/drivers/hv/mshv_eventfd.c @@ -368,6 +368,14 @@ static void mshv_irqfd_queue_proc(struct file *file, wait_queue_head_t *wqh, container_of(polltbl, struct mshv_irqfd, irqfd_polltbl); irqfd->irqfd_wqh = wqh; + + /* + * TODO: Ensure there isn't already an exclusive, priority waiter, e.g. + * that the irqfd isn't already bound to another partition. Only the + * first exclusive waiter encountered will be notified, and + * add_wait_queue_priority() doesn't enforce exclusivity. + */ + irqfd->irqfd_wait.flags |= WQ_FLAG_EXCLUSIVE; add_wait_queue_priority(wqh, &irqfd->irqfd_wait); } diff --git a/drivers/hv/mshv_root_hv_call.c b/drivers/hv/mshv_root_hv_call.c index a222a16107f6..c9c274f29c3c 100644 --- a/drivers/hv/mshv_root_hv_call.c +++ b/drivers/hv/mshv_root_hv_call.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/export.h> #include <asm/mshyperv.h> #include "mshv_root.h" diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 3c9b02471760..23ce1fb70de1 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -18,6 +18,7 @@ #include <linux/slab.h> #include <linux/prefetch.h> #include <linux/io.h> +#include <linux/export.h> #include <asm/mshyperv.h> #include "hyperv_vmbus.h" diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 33b524b4eb5e..2ed5a1e89d69 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -2509,7 +2509,7 @@ static int vmbus_acpi_add(struct platform_device *pdev) return 0; } #endif - +#ifndef HYPERVISOR_CALLBACK_VECTOR static int vmbus_set_irq(struct platform_device *pdev) { struct irq_data *data; @@ -2534,6 +2534,7 @@ static int vmbus_set_irq(struct platform_device *pdev) return 0; } +#endif static int vmbus_device_add(struct platform_device *pdev) { @@ -2549,11 +2550,11 @@ static int vmbus_device_add(struct platform_device *pdev) if (ret) return ret; - if (!__is_defined(HYPERVISOR_CALLBACK_VECTOR)) - ret = vmbus_set_irq(pdev); +#ifndef HYPERVISOR_CALLBACK_VECTOR + ret = vmbus_set_irq(pdev); if (ret) return ret; - +#endif for_each_of_range(&parser, &range) { struct resource *res; diff --git a/drivers/hwmon/corsair-cpro.c b/drivers/hwmon/corsair-cpro.c index e1a7f7aa7f80..b7b911f8359c 100644 --- a/drivers/hwmon/corsair-cpro.c +++ b/drivers/hwmon/corsair-cpro.c @@ -89,6 +89,7 @@ struct ccp_device { struct mutex mutex; /* whenever buffer is used, lock before send_usb_cmd */ u8 *cmd_buffer; u8 *buffer; + int buffer_recv_size; /* number of received bytes in buffer */ int target[6]; DECLARE_BITMAP(temp_cnct, NUM_TEMP_SENSORS); DECLARE_BITMAP(fan_cnct, NUM_FANS); @@ -146,6 +147,9 @@ static int send_usb_cmd(struct ccp_device *ccp, u8 command, u8 byte1, u8 byte2, if (!t) return -ETIMEDOUT; + if (ccp->buffer_recv_size != IN_BUFFER_SIZE) + return -EPROTO; + return ccp_get_errno(ccp); } @@ -157,6 +161,7 @@ static int ccp_raw_event(struct hid_device *hdev, struct hid_report *report, u8 spin_lock(&ccp->wait_input_report_lock); if (!completion_done(&ccp->wait_input_report)) { memcpy(ccp->buffer, data, min(IN_BUFFER_SIZE, size)); + ccp->buffer_recv_size = size; complete_all(&ccp->wait_input_report); } spin_unlock(&ccp->wait_input_report_lock); diff --git a/drivers/hwmon/ina238.c b/drivers/hwmon/ina238.c index a4a41742786b..9a5fd16a4ec2 100644 --- a/drivers/hwmon/ina238.c +++ b/drivers/hwmon/ina238.c @@ -97,7 +97,7 @@ * Power (mW) = 0.2 * register value * 20000 / rshunt / 4 * gain * (Specific for SQ52206) * Power (mW) = 0.24 * register value * 20000 / rshunt / 4 * gain - * Energy (mJ) = 16 * 0.24 * register value * 20000 / rshunt / 4 * gain + * Energy (uJ) = 16 * 0.24 * register value * 20000 / rshunt / 4 * gain * 1000 */ #define INA238_CALIBRATION_VALUE 16384 #define INA238_FIXED_SHUNT 20000 @@ -500,9 +500,9 @@ static ssize_t energy1_input_show(struct device *dev, if (ret) return ret; - /* result in mJ */ - energy = div_u64(regval * INA238_FIXED_SHUNT * data->gain * 16 * - data->config->power_calculate_factor, 4 * 100 * data->rshunt); + /* result in uJ */ + energy = div_u64(regval * INA238_FIXED_SHUNT * data->gain * 16 * 10 * + data->config->power_calculate_factor, 4 * data->rshunt); return sysfs_emit(buf, "%llu\n", energy); } diff --git a/drivers/hwmon/pmbus/ucd9000.c b/drivers/hwmon/pmbus/ucd9000.c index 2bc8cccb01fd..52d4000902d5 100644 --- a/drivers/hwmon/pmbus/ucd9000.c +++ b/drivers/hwmon/pmbus/ucd9000.c @@ -226,15 +226,15 @@ static int ucd9000_gpio_set(struct gpio_chip *gc, unsigned int offset, } if (value) { - if (ret & UCD9000_GPIO_CONFIG_STATUS) + if (ret & UCD9000_GPIO_CONFIG_OUT_VALUE) return 0; - ret |= UCD9000_GPIO_CONFIG_STATUS; + ret |= UCD9000_GPIO_CONFIG_OUT_VALUE; } else { - if (!(ret & UCD9000_GPIO_CONFIG_STATUS)) + if (!(ret & UCD9000_GPIO_CONFIG_OUT_VALUE)) return 0; - ret &= ~UCD9000_GPIO_CONFIG_STATUS; + ret &= ~UCD9000_GPIO_CONFIG_OUT_VALUE; } ret |= UCD9000_GPIO_CONFIG_ENABLE; diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index 8b01df3cc8e9..5fcc9f6c33e5 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -1472,7 +1472,9 @@ omap_i2c_probe(struct platform_device *pdev) } /* reset ASAP, clearing any IRQs */ - omap_i2c_init(omap); + r = omap_i2c_init(omap); + if (r) + goto err_mux_state_deselect; if (omap->rev < OMAP_I2C_OMAP1_REV_2) r = devm_request_irq(&pdev->dev, omap->irq, omap_i2c_omap1_isr, @@ -1515,12 +1517,13 @@ omap_i2c_probe(struct platform_device *pdev) err_unuse_clocks: omap_i2c_write_reg(omap, OMAP_I2C_CON_REG, 0); +err_mux_state_deselect: if (omap->mux_state) mux_state_deselect(omap->mux_state); err_put_pm: - pm_runtime_dont_use_autosuspend(omap->dev); pm_runtime_put_sync(omap->dev); err_disable_pm: + pm_runtime_dont_use_autosuspend(omap->dev); pm_runtime_disable(&pdev->dev); return r; diff --git a/drivers/i2c/busses/i2c-qup.c b/drivers/i2c/busses/i2c-qup.c index 6059f585843e..fc348924d522 100644 --- a/drivers/i2c/busses/i2c-qup.c +++ b/drivers/i2c/busses/i2c-qup.c @@ -452,8 +452,10 @@ static int qup_i2c_bus_active(struct qup_i2c_dev *qup, int len) if (!(status & I2C_STATUS_BUS_ACTIVE)) break; - if (time_after(jiffies, timeout)) + if (time_after(jiffies, timeout)) { ret = -ETIMEDOUT; + break; + } usleep_range(len, len * 2); } diff --git a/drivers/i2c/busses/i2c-stm32.c b/drivers/i2c/busses/i2c-stm32.c index 157c64e27d0b..f84ec056e36d 100644 --- a/drivers/i2c/busses/i2c-stm32.c +++ b/drivers/i2c/busses/i2c-stm32.c @@ -102,7 +102,6 @@ int stm32_i2c_prep_dma_xfer(struct device *dev, struct stm32_i2c_dma *dma, void *dma_async_param) { struct dma_async_tx_descriptor *txdesc; - struct device *chan_dev; int ret; if (rd_wr) { @@ -116,11 +115,10 @@ int stm32_i2c_prep_dma_xfer(struct device *dev, struct stm32_i2c_dma *dma, } dma->dma_len = len; - chan_dev = dma->chan_using->device->dev; - dma->dma_buf = dma_map_single(chan_dev, buf, dma->dma_len, + dma->dma_buf = dma_map_single(dev, buf, dma->dma_len, dma->dma_data_dir); - if (dma_mapping_error(chan_dev, dma->dma_buf)) { + if (dma_mapping_error(dev, dma->dma_buf)) { dev_err(dev, "DMA mapping failed\n"); return -EINVAL; } @@ -150,7 +148,7 @@ int stm32_i2c_prep_dma_xfer(struct device *dev, struct stm32_i2c_dma *dma, return 0; err: - dma_unmap_single(chan_dev, dma->dma_buf, dma->dma_len, + dma_unmap_single(dev, dma->dma_buf, dma->dma_len, dma->dma_data_dir); return ret; } diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c index e4aaeb2262d0..73a7b8894c0d 100644 --- a/drivers/i2c/busses/i2c-stm32f7.c +++ b/drivers/i2c/busses/i2c-stm32f7.c @@ -739,12 +739,13 @@ static void stm32f7_i2c_disable_dma_req(struct stm32f7_i2c_dev *i2c_dev) static void stm32f7_i2c_dma_callback(void *arg) { - struct stm32f7_i2c_dev *i2c_dev = (struct stm32f7_i2c_dev *)arg; + struct stm32f7_i2c_dev *i2c_dev = arg; struct stm32_i2c_dma *dma = i2c_dev->dma; - struct device *dev = dma->chan_using->device->dev; stm32f7_i2c_disable_dma_req(i2c_dev); - dma_unmap_single(dev, dma->dma_buf, dma->dma_len, dma->dma_data_dir); + dmaengine_terminate_async(dma->chan_using); + dma_unmap_single(i2c_dev->dev, dma->dma_buf, dma->dma_len, + dma->dma_data_dir); complete(&dma->dma_complete); } @@ -1510,7 +1511,6 @@ static irqreturn_t stm32f7_i2c_handle_isr_errs(struct stm32f7_i2c_dev *i2c_dev, u16 addr = f7_msg->addr; void __iomem *base = i2c_dev->base; struct device *dev = i2c_dev->dev; - struct stm32_i2c_dma *dma = i2c_dev->dma; /* Bus error */ if (status & STM32F7_I2C_ISR_BERR) { @@ -1551,10 +1551,8 @@ static irqreturn_t stm32f7_i2c_handle_isr_errs(struct stm32f7_i2c_dev *i2c_dev, } /* Disable dma */ - if (i2c_dev->use_dma) { - stm32f7_i2c_disable_dma_req(i2c_dev); - dmaengine_terminate_async(dma->chan_using); - } + if (i2c_dev->use_dma) + stm32f7_i2c_dma_callback(i2c_dev); i2c_dev->master_mode = false; complete(&i2c_dev->complete); @@ -1600,7 +1598,6 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data) { struct stm32f7_i2c_dev *i2c_dev = data; struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg; - struct stm32_i2c_dma *dma = i2c_dev->dma; void __iomem *base = i2c_dev->base; u32 status, mask; int ret; @@ -1619,10 +1616,8 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data) dev_dbg(i2c_dev->dev, "<%s>: Receive NACK (addr %x)\n", __func__, f7_msg->addr); writel_relaxed(STM32F7_I2C_ICR_NACKCF, base + STM32F7_I2C_ICR); - if (i2c_dev->use_dma) { - stm32f7_i2c_disable_dma_req(i2c_dev); - dmaengine_terminate_async(dma->chan_using); - } + if (i2c_dev->use_dma) + stm32f7_i2c_dma_callback(i2c_dev); f7_msg->result = -ENXIO; } @@ -1640,8 +1635,7 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data) ret = wait_for_completion_timeout(&i2c_dev->dma->dma_complete, HZ); if (!ret) { dev_dbg(i2c_dev->dev, "<%s>: Timed out\n", __func__); - stm32f7_i2c_disable_dma_req(i2c_dev); - dmaengine_terminate_async(dma->chan_using); + stm32f7_i2c_dma_callback(i2c_dev); f7_msg->result = -ETIMEDOUT; } } diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 0862b98007f5..6316360475e7 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -607,7 +607,6 @@ static int tegra_i2c_wait_for_config_load(struct tegra_i2c_dev *i2c_dev) static int tegra_i2c_init(struct tegra_i2c_dev *i2c_dev) { u32 val, clk_divisor, clk_multiplier, tsu_thd, tlow, thigh, non_hs_mode; - acpi_handle handle = ACPI_HANDLE(i2c_dev->dev); struct i2c_timings *t = &i2c_dev->timings; int err; @@ -619,11 +618,7 @@ static int tegra_i2c_init(struct tegra_i2c_dev *i2c_dev) * emit a noisy warning on error, which won't stay unnoticed and * won't hose machine entirely. */ - if (handle) - err = acpi_evaluate_object(handle, "_RST", NULL, NULL); - else - err = reset_control_reset(i2c_dev->rst); - + err = device_reset(i2c_dev->dev); WARN_ON_ONCE(err); if (IS_DVC(i2c_dev)) @@ -1666,19 +1661,6 @@ static void tegra_i2c_parse_dt(struct tegra_i2c_dev *i2c_dev) i2c_dev->is_vi = true; } -static int tegra_i2c_init_reset(struct tegra_i2c_dev *i2c_dev) -{ - if (ACPI_HANDLE(i2c_dev->dev)) - return 0; - - i2c_dev->rst = devm_reset_control_get_exclusive(i2c_dev->dev, "i2c"); - if (IS_ERR(i2c_dev->rst)) - return dev_err_probe(i2c_dev->dev, PTR_ERR(i2c_dev->rst), - "failed to get reset control\n"); - - return 0; -} - static int tegra_i2c_init_clocks(struct tegra_i2c_dev *i2c_dev) { int err; @@ -1788,10 +1770,6 @@ static int tegra_i2c_probe(struct platform_device *pdev) tegra_i2c_parse_dt(i2c_dev); - err = tegra_i2c_init_reset(i2c_dev); - if (err) - return err; - err = tegra_i2c_init_clocks(i2c_dev); if (err) return err; diff --git a/drivers/i2c/busses/i2c-virtio.c b/drivers/i2c/busses/i2c-virtio.c index 9b05ff53d3d7..af1381949f50 100644 --- a/drivers/i2c/busses/i2c-virtio.c +++ b/drivers/i2c/busses/i2c-virtio.c @@ -116,15 +116,16 @@ static int virtio_i2c_complete_reqs(struct virtqueue *vq, for (i = 0; i < num; i++) { struct virtio_i2c_req *req = &reqs[i]; - wait_for_completion(&req->completion); - - if (!failed && req->in_hdr.status != VIRTIO_I2C_MSG_OK) - failed = true; + if (!failed) { + if (wait_for_completion_interruptible(&req->completion)) + failed = true; + else if (req->in_hdr.status != VIRTIO_I2C_MSG_OK) + failed = true; + else + j++; + } i2c_put_dma_safe_msg_buf(reqs[i].buf, &msgs[i], !failed); - - if (!failed) - j++; } return j; diff --git a/drivers/iio/accel/fxls8962af-core.c b/drivers/iio/accel/fxls8962af-core.c index 12598feaa693..b10a30960e1e 100644 --- a/drivers/iio/accel/fxls8962af-core.c +++ b/drivers/iio/accel/fxls8962af-core.c @@ -877,6 +877,8 @@ static int fxls8962af_buffer_predisable(struct iio_dev *indio_dev) if (ret) return ret; + synchronize_irq(data->irq); + ret = __fxls8962af_fifo_set_mode(data, false); if (data->enable_event) diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index 99cb661fabb2..a7961c610ed2 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -1353,6 +1353,7 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev) union acpi_object *ont; union acpi_object *elements; acpi_status status; + struct device *parent = indio_dev->dev.parent; int ret = -EINVAL; unsigned int val; int i, j; @@ -1371,7 +1372,7 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev) }; - adev = ACPI_COMPANION(indio_dev->dev.parent); + adev = ACPI_COMPANION(parent); if (!adev) return -ENXIO; @@ -1380,8 +1381,7 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev) if (status == AE_NOT_FOUND) { return -ENXIO; } else if (ACPI_FAILURE(status)) { - dev_warn(&indio_dev->dev, "failed to execute _ONT: %d\n", - status); + dev_warn(parent, "failed to execute _ONT: %d\n", status); return status; } @@ -1457,12 +1457,12 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev) } ret = 0; - dev_info(&indio_dev->dev, "computed mount matrix from ACPI\n"); + dev_info(parent, "computed mount matrix from ACPI\n"); out: kfree(buffer.pointer); if (ret) - dev_dbg(&indio_dev->dev, + dev_dbg(parent, "failed to apply ACPI orientation data: %d\n", ret); return ret; diff --git a/drivers/iio/adc/ad7380.c b/drivers/iio/adc/ad7380.c index d96bd12dfea6..cabf5511d116 100644 --- a/drivers/iio/adc/ad7380.c +++ b/drivers/iio/adc/ad7380.c @@ -1953,8 +1953,9 @@ static int ad7380_probe(struct spi_device *spi) if (st->chip_info->has_hardware_gain) { device_for_each_child_node_scoped(dev, node) { - unsigned int channel, gain; + unsigned int channel; int gain_idx; + u16 gain; ret = fwnode_property_read_u32(node, "reg", &channel); if (ret) @@ -1966,7 +1967,7 @@ static int ad7380_probe(struct spi_device *spi) "Invalid channel number %i\n", channel); - ret = fwnode_property_read_u32(node, "adi,gain-milli", + ret = fwnode_property_read_u16(node, "adi,gain-milli", &gain); if (ret && ret != -EINVAL) return dev_err_probe(dev, ret, diff --git a/drivers/iio/adc/ad7949.c b/drivers/iio/adc/ad7949.c index edd0c3a35ab7..202561cad401 100644 --- a/drivers/iio/adc/ad7949.c +++ b/drivers/iio/adc/ad7949.c @@ -308,7 +308,6 @@ static void ad7949_disable_reg(void *reg) static int ad7949_spi_probe(struct spi_device *spi) { - u32 spi_ctrl_mask = spi->controller->bits_per_word_mask; struct device *dev = &spi->dev; const struct ad7949_adc_spec *spec; struct ad7949_adc_chip *ad7949_adc; @@ -337,11 +336,11 @@ static int ad7949_spi_probe(struct spi_device *spi) ad7949_adc->resolution = spec->resolution; /* Set SPI bits per word */ - if (spi_ctrl_mask & SPI_BPW_MASK(ad7949_adc->resolution)) { + if (spi_is_bpw_supported(spi, ad7949_adc->resolution)) { spi->bits_per_word = ad7949_adc->resolution; - } else if (spi_ctrl_mask == SPI_BPW_MASK(16)) { + } else if (spi_is_bpw_supported(spi, 16)) { spi->bits_per_word = 16; - } else if (spi_ctrl_mask == SPI_BPW_MASK(8)) { + } else if (spi_is_bpw_supported(spi, 8)) { spi->bits_per_word = 8; } else { dev_err(dev, "unable to find common BPW with spi controller\n"); diff --git a/drivers/iio/adc/adi-axi-adc.c b/drivers/iio/adc/adi-axi-adc.c index 4116c44197b8..2dbaa0b5b3d6 100644 --- a/drivers/iio/adc/adi-axi-adc.c +++ b/drivers/iio/adc/adi-axi-adc.c @@ -445,7 +445,7 @@ static int axi_adc_raw_read(struct iio_backend *back, u32 *val) static int ad7606_bus_reg_read(struct iio_backend *back, u32 reg, u32 *val) { struct adi_axi_adc_state *st = iio_backend_get_priv(back); - int addr; + u32 addr, reg_val; guard(mutex)(&st->lock); @@ -455,7 +455,9 @@ static int ad7606_bus_reg_read(struct iio_backend *back, u32 reg, u32 *val) */ addr = FIELD_PREP(ADI_AXI_REG_ADDRESS_MASK, reg) | ADI_AXI_REG_READ_BIT; axi_adc_raw_write(back, addr); - axi_adc_raw_read(back, val); + axi_adc_raw_read(back, ®_val); + + *val = FIELD_GET(ADI_AXI_REG_VALUE_MASK, reg_val); /* Write 0x0 on the bus to get back to ADC mode */ axi_adc_raw_write(back, 0); diff --git a/drivers/iio/adc/axp20x_adc.c b/drivers/iio/adc/axp20x_adc.c index 71584ffd3632..1b49325ec1ce 100644 --- a/drivers/iio/adc/axp20x_adc.c +++ b/drivers/iio/adc/axp20x_adc.c @@ -187,6 +187,7 @@ static struct iio_map axp717_maps[] = { .consumer_channel = "batt_chrg_i", .adc_channel_label = "batt_chrg_i", }, + { } }; /* diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c index a7e9912fb44a..9dd547e62b6c 100644 --- a/drivers/iio/adc/max1363.c +++ b/drivers/iio/adc/max1363.c @@ -511,10 +511,10 @@ static const struct iio_event_spec max1363_events[] = { MAX1363_CHAN_U(1, _s1, 1, bits, ev_spec, num_ev_spec), \ MAX1363_CHAN_U(2, _s2, 2, bits, ev_spec, num_ev_spec), \ MAX1363_CHAN_U(3, _s3, 3, bits, ev_spec, num_ev_spec), \ - MAX1363_CHAN_B(0, 1, d0m1, 4, bits, ev_spec, num_ev_spec), \ - MAX1363_CHAN_B(2, 3, d2m3, 5, bits, ev_spec, num_ev_spec), \ - MAX1363_CHAN_B(1, 0, d1m0, 6, bits, ev_spec, num_ev_spec), \ - MAX1363_CHAN_B(3, 2, d3m2, 7, bits, ev_spec, num_ev_spec), \ + MAX1363_CHAN_B(0, 1, d0m1, 12, bits, ev_spec, num_ev_spec), \ + MAX1363_CHAN_B(2, 3, d2m3, 13, bits, ev_spec, num_ev_spec), \ + MAX1363_CHAN_B(1, 0, d1m0, 18, bits, ev_spec, num_ev_spec), \ + MAX1363_CHAN_B(3, 2, d3m2, 19, bits, ev_spec, num_ev_spec), \ IIO_CHAN_SOFT_TIMESTAMP(8) \ } @@ -532,23 +532,23 @@ static const struct iio_chan_spec max1363_channels[] = /* Applies to max1236, max1237 */ static const enum max1363_modes max1236_mode_list[] = { _s0, _s1, _s2, _s3, - s0to1, s0to2, s0to3, + s0to1, s0to2, s2to3, s0to3, d0m1, d2m3, d1m0, d3m2, d0m1to2m3, d1m0to3m2, - s2to3, }; /* Applies to max1238, max1239 */ static const enum max1363_modes max1238_mode_list[] = { _s0, _s1, _s2, _s3, _s4, _s5, _s6, _s7, _s8, _s9, _s10, _s11, s0to1, s0to2, s0to3, s0to4, s0to5, s0to6, + s6to7, s6to8, s6to9, s6to10, s6to11, s0to7, s0to8, s0to9, s0to10, s0to11, d0m1, d2m3, d4m5, d6m7, d8m9, d10m11, d1m0, d3m2, d5m4, d7m6, d9m8, d11m10, - d0m1to2m3, d0m1to4m5, d0m1to6m7, d0m1to8m9, d0m1to10m11, - d1m0to3m2, d1m0to5m4, d1m0to7m6, d1m0to9m8, d1m0to11m10, - s6to7, s6to8, s6to9, s6to10, s6to11, - d6m7to8m9, d6m7to10m11, d7m6to9m8, d7m6to11m10, + d0m1to2m3, d0m1to4m5, d0m1to6m7, d6m7to8m9, + d0m1to8m9, d6m7to10m11, d0m1to10m11, d1m0to3m2, + d1m0to5m4, d1m0to7m6, d7m6to9m8, d1m0to9m8, + d7m6to11m10, d1m0to11m10, }; #define MAX1363_12X_CHANS(bits) { \ @@ -584,16 +584,15 @@ static const struct iio_chan_spec max1238_channels[] = MAX1363_12X_CHANS(12); static const enum max1363_modes max11607_mode_list[] = { _s0, _s1, _s2, _s3, - s0to1, s0to2, s0to3, - s2to3, + s0to1, s0to2, s2to3, + s0to3, d0m1, d2m3, d1m0, d3m2, d0m1to2m3, d1m0to3m2, }; static const enum max1363_modes max11608_mode_list[] = { _s0, _s1, _s2, _s3, _s4, _s5, _s6, _s7, - s0to1, s0to2, s0to3, s0to4, s0to5, s0to6, s0to7, - s6to7, + s0to1, s0to2, s0to3, s0to4, s0to5, s0to6, s6to7, s0to7, d0m1, d2m3, d4m5, d6m7, d1m0, d3m2, d5m4, d7m6, d0m1to2m3, d0m1to4m5, d0m1to6m7, @@ -609,14 +608,14 @@ static const enum max1363_modes max11608_mode_list[] = { MAX1363_CHAN_U(5, _s5, 5, bits, NULL, 0), \ MAX1363_CHAN_U(6, _s6, 6, bits, NULL, 0), \ MAX1363_CHAN_U(7, _s7, 7, bits, NULL, 0), \ - MAX1363_CHAN_B(0, 1, d0m1, 8, bits, NULL, 0), \ - MAX1363_CHAN_B(2, 3, d2m3, 9, bits, NULL, 0), \ - MAX1363_CHAN_B(4, 5, d4m5, 10, bits, NULL, 0), \ - MAX1363_CHAN_B(6, 7, d6m7, 11, bits, NULL, 0), \ - MAX1363_CHAN_B(1, 0, d1m0, 12, bits, NULL, 0), \ - MAX1363_CHAN_B(3, 2, d3m2, 13, bits, NULL, 0), \ - MAX1363_CHAN_B(5, 4, d5m4, 14, bits, NULL, 0), \ - MAX1363_CHAN_B(7, 6, d7m6, 15, bits, NULL, 0), \ + MAX1363_CHAN_B(0, 1, d0m1, 12, bits, NULL, 0), \ + MAX1363_CHAN_B(2, 3, d2m3, 13, bits, NULL, 0), \ + MAX1363_CHAN_B(4, 5, d4m5, 14, bits, NULL, 0), \ + MAX1363_CHAN_B(6, 7, d6m7, 15, bits, NULL, 0), \ + MAX1363_CHAN_B(1, 0, d1m0, 18, bits, NULL, 0), \ + MAX1363_CHAN_B(3, 2, d3m2, 19, bits, NULL, 0), \ + MAX1363_CHAN_B(5, 4, d5m4, 20, bits, NULL, 0), \ + MAX1363_CHAN_B(7, 6, d7m6, 21, bits, NULL, 0), \ IIO_CHAN_SOFT_TIMESTAMP(16) \ } static const struct iio_chan_spec max11602_channels[] = MAX1363_8X_CHANS(8); diff --git a/drivers/iio/adc/stm32-adc-core.c b/drivers/iio/adc/stm32-adc-core.c index bd3458965bff..21c04a98b3b6 100644 --- a/drivers/iio/adc/stm32-adc-core.c +++ b/drivers/iio/adc/stm32-adc-core.c @@ -430,10 +430,9 @@ static int stm32_adc_irq_probe(struct platform_device *pdev, return -ENOMEM; } - for (i = 0; i < priv->cfg->num_irqs; i++) { - irq_set_chained_handler(priv->irq[i], stm32_adc_irq_handler); - irq_set_handler_data(priv->irq[i], priv); - } + for (i = 0; i < priv->cfg->num_irqs; i++) + irq_set_chained_handler_and_data(priv->irq[i], + stm32_adc_irq_handler, priv); return 0; } diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index 8ce1dccfea4f..dac593be5695 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -154,7 +154,7 @@ static int st_sensors_set_fullscale(struct iio_dev *indio_dev, unsigned int fs) return err; st_accel_set_fullscale_error: - dev_err(&indio_dev->dev, "failed to set new fullscale.\n"); + dev_err(indio_dev->dev.parent, "failed to set new fullscale.\n"); return err; } @@ -231,8 +231,7 @@ int st_sensors_power_enable(struct iio_dev *indio_dev) ARRAY_SIZE(regulator_names), regulator_names); if (err) - return dev_err_probe(&indio_dev->dev, err, - "unable to enable supplies\n"); + return dev_err_probe(parent, err, "unable to enable supplies\n"); return 0; } @@ -241,13 +240,14 @@ EXPORT_SYMBOL_NS(st_sensors_power_enable, "IIO_ST_SENSORS"); static int st_sensors_set_drdy_int_pin(struct iio_dev *indio_dev, struct st_sensors_platform_data *pdata) { + struct device *parent = indio_dev->dev.parent; struct st_sensor_data *sdata = iio_priv(indio_dev); /* Sensor does not support interrupts */ if (!sdata->sensor_settings->drdy_irq.int1.addr && !sdata->sensor_settings->drdy_irq.int2.addr) { if (pdata->drdy_int_pin) - dev_info(&indio_dev->dev, + dev_info(parent, "DRDY on pin INT%d specified, but sensor does not support interrupts\n", pdata->drdy_int_pin); return 0; @@ -256,29 +256,27 @@ static int st_sensors_set_drdy_int_pin(struct iio_dev *indio_dev, switch (pdata->drdy_int_pin) { case 1: if (!sdata->sensor_settings->drdy_irq.int1.mask) { - dev_err(&indio_dev->dev, - "DRDY on INT1 not available.\n"); + dev_err(parent, "DRDY on INT1 not available.\n"); return -EINVAL; } sdata->drdy_int_pin = 1; break; case 2: if (!sdata->sensor_settings->drdy_irq.int2.mask) { - dev_err(&indio_dev->dev, - "DRDY on INT2 not available.\n"); + dev_err(parent, "DRDY on INT2 not available.\n"); return -EINVAL; } sdata->drdy_int_pin = 2; break; default: - dev_err(&indio_dev->dev, "DRDY on pdata not valid.\n"); + dev_err(parent, "DRDY on pdata not valid.\n"); return -EINVAL; } if (pdata->open_drain) { if (!sdata->sensor_settings->drdy_irq.int1.addr_od && !sdata->sensor_settings->drdy_irq.int2.addr_od) - dev_err(&indio_dev->dev, + dev_err(parent, "open drain requested but unsupported.\n"); else sdata->int_pin_open_drain = true; @@ -336,6 +334,7 @@ EXPORT_SYMBOL_NS(st_sensors_dev_name_probe, "IIO_ST_SENSORS"); int st_sensors_init_sensor(struct iio_dev *indio_dev, struct st_sensors_platform_data *pdata) { + struct device *parent = indio_dev->dev.parent; struct st_sensor_data *sdata = iio_priv(indio_dev); struct st_sensors_platform_data *of_pdata; int err = 0; @@ -343,7 +342,7 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev, mutex_init(&sdata->odr_lock); /* If OF/DT pdata exists, it will take precedence of anything else */ - of_pdata = st_sensors_dev_probe(indio_dev->dev.parent, pdata); + of_pdata = st_sensors_dev_probe(parent, pdata); if (IS_ERR(of_pdata)) return PTR_ERR(of_pdata); if (of_pdata) @@ -370,7 +369,7 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev, if (err < 0) return err; } else - dev_info(&indio_dev->dev, "Full-scale not possible\n"); + dev_info(parent, "Full-scale not possible\n"); err = st_sensors_set_odr(indio_dev, sdata->odr); if (err < 0) @@ -405,7 +404,7 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev, mask = sdata->sensor_settings->drdy_irq.int2.mask_od; } - dev_info(&indio_dev->dev, + dev_info(parent, "set interrupt line to open drain mode on pin %d\n", sdata->drdy_int_pin); err = st_sensors_write_data_with_mask(indio_dev, addr, @@ -593,21 +592,20 @@ EXPORT_SYMBOL_NS(st_sensors_get_settings_index, "IIO_ST_SENSORS"); int st_sensors_verify_id(struct iio_dev *indio_dev) { struct st_sensor_data *sdata = iio_priv(indio_dev); + struct device *parent = indio_dev->dev.parent; int wai, err; if (sdata->sensor_settings->wai_addr) { err = regmap_read(sdata->regmap, sdata->sensor_settings->wai_addr, &wai); if (err < 0) { - dev_err(&indio_dev->dev, - "failed to read Who-Am-I register.\n"); - return err; + return dev_err_probe(parent, err, + "failed to read Who-Am-I register.\n"); } if (sdata->sensor_settings->wai != wai) { - dev_warn(&indio_dev->dev, - "%s: WhoAmI mismatch (0x%x).\n", - indio_dev->name, wai); + dev_warn(parent, "%s: WhoAmI mismatch (0x%x).\n", + indio_dev->name, wai); } } diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c index 9d4bf822a15d..8a8ab688d798 100644 --- a/drivers/iio/common/st_sensors/st_sensors_trigger.c +++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c @@ -127,7 +127,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, sdata->trig = devm_iio_trigger_alloc(parent, "%s-trigger", indio_dev->name); if (sdata->trig == NULL) { - dev_err(&indio_dev->dev, "failed to allocate iio trigger.\n"); + dev_err(parent, "failed to allocate iio trigger.\n"); return -ENOMEM; } @@ -143,7 +143,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, case IRQF_TRIGGER_FALLING: case IRQF_TRIGGER_LOW: if (!sdata->sensor_settings->drdy_irq.addr_ihl) { - dev_err(&indio_dev->dev, + dev_err(parent, "falling/low specified for IRQ but hardware supports only rising/high: will request rising/high\n"); if (irq_trig == IRQF_TRIGGER_FALLING) irq_trig = IRQF_TRIGGER_RISING; @@ -156,21 +156,19 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, sdata->sensor_settings->drdy_irq.mask_ihl, 1); if (err < 0) return err; - dev_info(&indio_dev->dev, + dev_info(parent, "interrupts on the falling edge or active low level\n"); } break; case IRQF_TRIGGER_RISING: - dev_info(&indio_dev->dev, - "interrupts on the rising edge\n"); + dev_info(parent, "interrupts on the rising edge\n"); break; case IRQF_TRIGGER_HIGH: - dev_info(&indio_dev->dev, - "interrupts active high level\n"); + dev_info(parent, "interrupts active high level\n"); break; default: /* This is the most preferred mode, if possible */ - dev_err(&indio_dev->dev, + dev_err(parent, "unsupported IRQ trigger specified (%lx), enforce rising edge\n", irq_trig); irq_trig = IRQF_TRIGGER_RISING; } @@ -179,7 +177,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, if (irq_trig == IRQF_TRIGGER_FALLING || irq_trig == IRQF_TRIGGER_RISING) { if (!sdata->sensor_settings->drdy_irq.stat_drdy.addr) { - dev_err(&indio_dev->dev, + dev_err(parent, "edge IRQ not supported w/o stat register.\n"); return -EOPNOTSUPP; } @@ -214,13 +212,13 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, sdata->trig->name, sdata->trig); if (err) { - dev_err(&indio_dev->dev, "failed to request trigger IRQ.\n"); + dev_err(parent, "failed to request trigger IRQ.\n"); return err; } err = devm_iio_trigger_register(parent, sdata->trig); if (err < 0) { - dev_err(&indio_dev->dev, "failed to register iio trigger.\n"); + dev_err(parent, "failed to register iio trigger.\n"); return err; } indio_dev->trig = iio_trigger_get(sdata->trig); diff --git a/drivers/iio/dac/ad3530r.c b/drivers/iio/dac/ad3530r.c index f9752a571aa5..6134613777b8 100644 --- a/drivers/iio/dac/ad3530r.c +++ b/drivers/iio/dac/ad3530r.c @@ -166,7 +166,9 @@ static ssize_t ad3530r_set_dac_powerdown(struct iio_dev *indio_dev, AD3530R_OUTPUT_OPERATING_MODE_0 : AD3530R_OUTPUT_OPERATING_MODE_1; pdmode = powerdown ? st->chan[chan->channel].powerdown_mode : 0; - mask = AD3530R_OP_MODE_CHAN_MSK(chan->channel); + mask = chan->channel < AD3531R_MAX_CHANNELS ? + AD3530R_OP_MODE_CHAN_MSK(chan->channel) : + AD3530R_OP_MODE_CHAN_MSK(chan->channel - 4); val = field_prep(mask, pdmode); ret = regmap_update_bits(st->regmap, reg, mask, val); diff --git a/drivers/iio/industrialio-backend.c b/drivers/iio/industrialio-backend.c index c1eb9ef9db08..266e1b29bf91 100644 --- a/drivers/iio/industrialio-backend.c +++ b/drivers/iio/industrialio-backend.c @@ -155,11 +155,14 @@ static ssize_t iio_backend_debugfs_write_reg(struct file *file, ssize_t rc; int ret; + if (count >= sizeof(buf)) + return -ENOSPC; + rc = simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, userbuf, count); if (rc < 0) return rc; - buf[count] = '\0'; + buf[rc] = '\0'; ret = sscanf(buf, "%i %i", &back->cached_reg_addr, &val); diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 178e99b111de..5ffda104d4b2 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -411,12 +411,15 @@ static ssize_t iio_debugfs_write_reg(struct file *file, char buf[80]; int ret; + if (count >= sizeof(buf)) + return -EINVAL; + ret = simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, userbuf, count); if (ret < 0) return ret; - buf[count] = '\0'; + buf[ret] = '\0'; ret = sscanf(buf, "%i %i", ®, &val); diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 5d9b7007a730..1d8c579b5433 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -172,12 +172,12 @@ static const struct xpad_device { { 0x046d, 0xca88, "Logitech Compact Controller for Xbox", 0, XTYPE_XBOX }, { 0x046d, 0xca8a, "Logitech Precision Vibration Feedback Wheel", 0, XTYPE_XBOX }, { 0x046d, 0xcaa3, "Logitech DriveFx Racing Wheel", 0, XTYPE_XBOX360 }, + { 0x0502, 0x1305, "Acer NGR200", 0, XTYPE_XBOX360 }, { 0x056e, 0x2004, "Elecom JC-U3613M", 0, XTYPE_XBOX360 }, { 0x05fd, 0x1007, "Mad Catz Controller (unverified)", 0, XTYPE_XBOX }, { 0x05fd, 0x107a, "InterAct 'PowerPad Pro' X-Box pad (Germany)", 0, XTYPE_XBOX }, { 0x05fe, 0x3030, "Chic Controller", 0, XTYPE_XBOX }, { 0x05fe, 0x3031, "Chic Controller", 0, XTYPE_XBOX }, - { 0x0502, 0x1305, "Acer NGR200", 0, XTYPE_XBOX }, { 0x062a, 0x0020, "Logic3 Xbox GamePad", 0, XTYPE_XBOX }, { 0x062a, 0x0033, "Competition Pro Steering Wheel", 0, XTYPE_XBOX }, { 0x06a3, 0x0200, "Saitek Racing Wheel", 0, XTYPE_XBOX }, diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 1a41e59c77f8..3ebf37ddfc18 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -20,7 +20,7 @@ #include "internal.h" -#define ICC_DYN_ID_START 10000 +#define ICC_DYN_ID_START 100000 #define CREATE_TRACE_POINTS #include "trace.h" @@ -819,6 +819,9 @@ static struct icc_node *icc_node_create_nolock(int id) { struct icc_node *node; + if (id >= ICC_DYN_ID_START) + return ERR_PTR(-EINVAL); + /* check if node already exists */ node = node_find(id); if (node) @@ -906,11 +909,36 @@ void icc_node_destroy(int id) return; kfree(node->links); + if (node->id >= ICC_DYN_ID_START) + kfree(node->name); kfree(node); } EXPORT_SYMBOL_GPL(icc_node_destroy); /** + * icc_node_set_name() - set node name + * @node: node + * @provider: node provider + * @name: node name + * + * Return: 0 on success, or -ENOMEM on allocation failure + */ +int icc_node_set_name(struct icc_node *node, const struct icc_provider *provider, const char *name) +{ + if (node->id >= ICC_DYN_ID_START) { + node->name = kasprintf(GFP_KERNEL, "%s@%s", name, + dev_name(provider->dev)); + if (!node->name) + return -ENOMEM; + } else { + node->name = name; + } + + return 0; +} +EXPORT_SYMBOL_GPL(icc_node_set_name); + +/** * icc_link_nodes() - create link between two nodes * @src_node: source node * @dst_node: destination node @@ -1038,10 +1066,6 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider) node->avg_bw = node->init_avg; node->peak_bw = node->init_peak; - if (node->id >= ICC_DYN_ID_START) - node->name = devm_kasprintf(provider->dev, GFP_KERNEL, "%s@%s", - node->name, dev_name(provider->dev)); - if (node->avg_bw || node->peak_bw) { if (provider->pre_aggregate) provider->pre_aggregate(node); diff --git a/drivers/interconnect/icc-clk.c b/drivers/interconnect/icc-clk.c index 88f311c11020..93c030608d3e 100644 --- a/drivers/interconnect/icc-clk.c +++ b/drivers/interconnect/icc-clk.c @@ -117,6 +117,7 @@ struct icc_provider *icc_clk_register(struct device *dev, node->name = devm_kasprintf(dev, GFP_KERNEL, "%s_master", data[i].name); if (!node->name) { + icc_node_destroy(node->id); ret = -ENOMEM; goto err; } @@ -135,6 +136,7 @@ struct icc_provider *icc_clk_register(struct device *dev, node->name = devm_kasprintf(dev, GFP_KERNEL, "%s_slave", data[i].name); if (!node->name) { + icc_node_destroy(node->id); ret = -ENOMEM; goto err; } diff --git a/drivers/interconnect/qcom/icc-rpmh.c b/drivers/interconnect/qcom/icc-rpmh.c index 41bfc6e7ee1d..001404e91041 100644 --- a/drivers/interconnect/qcom/icc-rpmh.c +++ b/drivers/interconnect/qcom/icc-rpmh.c @@ -293,7 +293,12 @@ int qcom_icc_rpmh_probe(struct platform_device *pdev) goto err_remove_nodes; } - node->name = qn->name; + ret = icc_node_set_name(node, provider, qn->name); + if (ret) { + icc_node_destroy(node->id); + goto err_remove_nodes; + } + node->data = qn; icc_node_add(node, provider); diff --git a/drivers/interconnect/qcom/osm-l3.c b/drivers/interconnect/qcom/osm-l3.c index baecbf2533f7..b33f00da1880 100644 --- a/drivers/interconnect/qcom/osm-l3.c +++ b/drivers/interconnect/qcom/osm-l3.c @@ -236,7 +236,12 @@ static int qcom_osm_l3_probe(struct platform_device *pdev) goto err; } - node->name = qnodes[i]->name; + ret = icc_node_set_name(node, provider, qnodes[i]->name); + if (ret) { + icc_node_destroy(node->id); + goto err; + } + /* Cast away const and add it back in qcom_osm_l3_set() */ node->data = (void *)qnodes[i]; icc_node_add(node, provider); diff --git a/drivers/interconnect/qcom/sc7280.c b/drivers/interconnect/qcom/sc7280.c index 346f18d70e9e..905403a3a930 100644 --- a/drivers/interconnect/qcom/sc7280.c +++ b/drivers/interconnect/qcom/sc7280.c @@ -238,6 +238,7 @@ static struct qcom_icc_node xm_pcie3_1 = { .id = SC7280_MASTER_PCIE_1, .channels = 1, .buswidth = 8, + .num_links = 1, .links = { SC7280_SLAVE_ANOC_PCIE_GEM_NOC }, }; diff --git a/drivers/interconnect/samsung/exynos.c b/drivers/interconnect/samsung/exynos.c index 9e041365d909..8e8f56186a36 100644 --- a/drivers/interconnect/samsung/exynos.c +++ b/drivers/interconnect/samsung/exynos.c @@ -134,6 +134,11 @@ static int exynos_generic_icc_probe(struct platform_device *pdev) priv->node = icc_node; icc_node->name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%pOFn", bus_dev->of_node); + if (!icc_node->name) { + icc_node_destroy(pdev->id); + return -ENOMEM; + } + if (of_property_read_u32(bus_dev->of_node, "samsung,data-clock-ratio", &priv->bus_clk_ratio)) priv->bus_clk_ratio = EXYNOS_ICC_DEFAULT_BUS_CLK_RATIO; diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index ccbab3a4811a..053a0f05768c 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -1054,7 +1054,6 @@ struct irq_2_irte { }; struct amd_ir_data { - u32 cached_ga_tag; struct amd_iommu *iommu; struct irq_2_irte irq_2_irte; struct msi_msg msi_entry; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 3117d99cf83d..c50d4a8a51be 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -3804,13 +3804,70 @@ static const struct irq_domain_ops amd_ir_domain_ops = { .deactivate = irq_remapping_deactivate, }; -int amd_iommu_activate_guest_mode(void *data) +static void __amd_iommu_update_ga(struct irte_ga *entry, int cpu, + bool ga_log_intr) +{ + if (cpu >= 0) { + entry->lo.fields_vapic.destination = + APICID_TO_IRTE_DEST_LO(cpu); + entry->hi.fields.destination = + APICID_TO_IRTE_DEST_HI(cpu); + entry->lo.fields_vapic.is_run = true; + entry->lo.fields_vapic.ga_log_intr = false; + } else { + entry->lo.fields_vapic.is_run = false; + entry->lo.fields_vapic.ga_log_intr = ga_log_intr; + } +} + +/* + * Update the pCPU information for an IRTE that is configured to post IRQs to + * a vCPU, without issuing an IOMMU invalidation for the IRTE. + * + * If the vCPU is associated with a pCPU (@cpu >= 0), configure the Destination + * with the pCPU's APIC ID, set IsRun, and clear GALogIntr. If the vCPU isn't + * associated with a pCPU (@cpu < 0), clear IsRun and set/clear GALogIntr based + * on input from the caller (e.g. KVM only requests GALogIntr when the vCPU is + * blocking and requires a notification wake event). I.e. treat vCPUs that are + * associated with a pCPU as running. This API is intended to be used when a + * vCPU is scheduled in/out (or stops running for any reason), to do a fast + * update of IsRun, GALogIntr, and (conditionally) Destination. + * + * Per the IOMMU spec, the Destination, IsRun, and GATag fields are not cached + * and thus don't require an invalidation to ensure the IOMMU consumes fresh + * information. + */ +int amd_iommu_update_ga(void *data, int cpu, bool ga_log_intr) +{ + struct amd_ir_data *ir_data = (struct amd_ir_data *)data; + struct irte_ga *entry = (struct irte_ga *) ir_data->entry; + + if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))) + return -EINVAL; + + if (!entry || !entry->lo.fields_vapic.guest_mode) + return 0; + + if (!ir_data->iommu) + return -ENODEV; + + __amd_iommu_update_ga(entry, cpu, ga_log_intr); + + return __modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid, + ir_data->irq_2_irte.index, entry); +} +EXPORT_SYMBOL(amd_iommu_update_ga); + +int amd_iommu_activate_guest_mode(void *data, int cpu, bool ga_log_intr) { struct amd_ir_data *ir_data = (struct amd_ir_data *)data; struct irte_ga *entry = (struct irte_ga *) ir_data->entry; u64 valid; - if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || !entry) + if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))) + return -EINVAL; + + if (!entry) return 0; valid = entry->lo.fields_vapic.valid; @@ -3820,11 +3877,12 @@ int amd_iommu_activate_guest_mode(void *data) entry->lo.fields_vapic.valid = valid; entry->lo.fields_vapic.guest_mode = 1; - entry->lo.fields_vapic.ga_log_intr = 1; entry->hi.fields.ga_root_ptr = ir_data->ga_root_ptr; entry->hi.fields.vector = ir_data->ga_vector; entry->lo.fields_vapic.ga_tag = ir_data->ga_tag; + __amd_iommu_update_ga(entry, cpu, ga_log_intr); + return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid, ir_data->irq_2_irte.index, entry); } @@ -3837,8 +3895,10 @@ int amd_iommu_deactivate_guest_mode(void *data) struct irq_cfg *cfg = ir_data->cfg; u64 valid; - if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || - !entry || !entry->lo.fields_vapic.guest_mode) + if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))) + return -EINVAL; + + if (!entry || !entry->lo.fields_vapic.guest_mode) return 0; valid = entry->lo.fields_remap.valid; @@ -3860,11 +3920,10 @@ int amd_iommu_deactivate_guest_mode(void *data) } EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode); -static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info) +static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *info) { int ret; - struct amd_iommu_pi_data *pi_data = vcpu_info; - struct vcpu_data *vcpu_pi_info = pi_data->vcpu_data; + struct amd_iommu_pi_data *pi_data = info; struct amd_ir_data *ir_data = data->chip_data; struct irq_2_irte *irte_info = &ir_data->irq_2_irte; struct iommu_dev_data *dev_data; @@ -3885,25 +3944,20 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info) return -EINVAL; ir_data->cfg = irqd_cfg(data); - pi_data->ir_data = ir_data; - pi_data->prev_ga_tag = ir_data->cached_ga_tag; - if (pi_data->is_guest_mode) { - ir_data->ga_root_ptr = (pi_data->base >> 12); - ir_data->ga_vector = vcpu_pi_info->vector; + if (pi_data) { + pi_data->ir_data = ir_data; + + ir_data->ga_root_ptr = (pi_data->vapic_addr >> 12); + ir_data->ga_vector = pi_data->vector; ir_data->ga_tag = pi_data->ga_tag; - ret = amd_iommu_activate_guest_mode(ir_data); - if (!ret) - ir_data->cached_ga_tag = pi_data->ga_tag; + if (pi_data->is_guest_mode) + ret = amd_iommu_activate_guest_mode(ir_data, pi_data->cpu, + pi_data->ga_log_intr); + else + ret = amd_iommu_deactivate_guest_mode(ir_data); } else { ret = amd_iommu_deactivate_guest_mode(ir_data); - - /* - * This communicates the ga_tag back to the caller - * so that it can do all the necessary clean up. - */ - if (!ret) - ir_data->cached_ga_tag = 0; } return ret; @@ -3995,29 +4049,4 @@ int amd_iommu_create_irq_domain(struct amd_iommu *iommu) return 0; } - -int amd_iommu_update_ga(int cpu, bool is_run, void *data) -{ - struct amd_ir_data *ir_data = (struct amd_ir_data *)data; - struct irte_ga *entry = (struct irte_ga *) ir_data->entry; - - if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || - !entry || !entry->lo.fields_vapic.guest_mode) - return 0; - - if (!ir_data->iommu) - return -ENODEV; - - if (cpu >= 0) { - entry->lo.fields_vapic.destination = - APICID_TO_IRTE_DEST_LO(cpu); - entry->hi.fields.destination = - APICID_TO_IRTE_DEST_HI(cpu); - } - entry->lo.fields_vapic.is_run = is_run; - - return __modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid, - ir_data->irq_2_irte.index, entry); -} -EXPORT_SYMBOL(amd_iommu_update_ga); #endif diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c index 761ab647f372..0961ac805944 100644 --- a/drivers/iommu/hyperv-iommu.c +++ b/drivers/iommu/hyperv-iommu.c @@ -193,15 +193,13 @@ struct hyperv_root_ir_data { static void hyperv_root_ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg) { - u64 status; - u32 vector; - struct irq_cfg *cfg; - int ioapic_id; - const struct cpumask *affinity; - int cpu; - struct hv_interrupt_entry entry; struct hyperv_root_ir_data *data = irq_data->chip_data; + struct hv_interrupt_entry entry; + const struct cpumask *affinity; struct IO_APIC_route_entry e; + struct irq_cfg *cfg; + int cpu, ioapic_id; + u32 vector; cfg = irqd_cfg(irq_data); affinity = irq_data_get_effective_affinity_mask(irq_data); @@ -214,23 +212,16 @@ hyperv_root_ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg) && data->entry.ioapic_rte.as_uint64) { entry = data->entry; - status = hv_unmap_ioapic_interrupt(ioapic_id, &entry); - - if (status != HV_STATUS_SUCCESS) - hv_status_debug(status, "failed to unmap\n"); + (void)hv_unmap_ioapic_interrupt(ioapic_id, &entry); data->entry.ioapic_rte.as_uint64 = 0; data->entry.source = 0; /* Invalid source */ } - status = hv_map_ioapic_interrupt(ioapic_id, data->is_level, cpu, - vector, &entry); - - if (status != HV_STATUS_SUCCESS) { - hv_status_err(status, "map failed\n"); + if (hv_map_ioapic_interrupt(ioapic_id, data->is_level, cpu, + vector, &entry)) return; - } data->entry = entry; @@ -322,10 +313,10 @@ static void hyperv_root_irq_remapping_free(struct irq_domain *domain, data = irq_data->chip_data; e = &data->entry; - if (e->source == HV_DEVICE_TYPE_IOAPIC - && e->ioapic_rte.as_uint64) - hv_unmap_ioapic_interrupt(data->ioapic_id, - &data->entry); + if (e->source == HV_DEVICE_TYPE_IOAPIC && + e->ioapic_rte.as_uint64) + (void)hv_unmap_ioapic_interrupt(data->ioapic_id, + &data->entry); kfree(data); } diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index cf7b6882ec75..2fc451253dc3 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -1244,10 +1244,10 @@ static void intel_ir_compose_msi_msg(struct irq_data *irq_data, static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info) { struct intel_ir_data *ir_data = data->chip_data; - struct vcpu_data *vcpu_pi_info = info; + struct intel_iommu_pi_data *pi_data = info; /* stop posting interrupts, back to the default mode */ - if (!vcpu_pi_info) { + if (!pi_data) { __intel_ir_reconfigure_irte(data, true); } else { struct irte irte_pi; @@ -1265,10 +1265,10 @@ static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info) /* Update the posted mode fields */ irte_pi.p_pst = 1; irte_pi.p_urgent = 0; - irte_pi.p_vector = vcpu_pi_info->vector; - irte_pi.pda_l = (vcpu_pi_info->pi_desc_addr >> + irte_pi.p_vector = pi_data->vector; + irte_pi.pda_l = (pi_data->pi_desc_addr >> (32 - PDA_LOW_BIT)) & ~(-1UL << PDA_LOW_BIT); - irte_pi.pda_h = (vcpu_pi_info->pi_desc_addr >> 32) & + irte_pi.pda_h = (pi_data->pi_desc_addr >> 32) & ~(-1UL << PDA_HIGH_BIT); ir_data->irq_2_iommu.posted_vcpu = true; diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c index 58c28895f8c4..8455b4a5fbb0 100644 --- a/drivers/irqchip/irq-gic-v4.c +++ b/drivers/irqchip/irq-gic-v4.c @@ -342,10 +342,10 @@ int its_get_vlpi(int irq, struct its_vlpi_map *map) return irq_set_vcpu_affinity(irq, &info); } -int its_unmap_vlpi(int irq) +void its_unmap_vlpi(int irq) { irq_clear_status_flags(irq, IRQ_DISABLE_UNLAZY); - return irq_set_vcpu_affinity(irq, NULL); + WARN_ON_ONCE(irq_set_vcpu_affinity(irq, NULL)); } int its_prop_update_vlpi(int irq, u8 config, bool inv) diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index ec84ba5e93e5..ff7595caf440 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -2742,7 +2742,11 @@ static unsigned long __evict_a_few(unsigned long nr_buffers) __make_buffer_clean(b); __free_buffer_wake(b); - cond_resched(); + if (need_resched()) { + dm_bufio_unlock(c); + cond_resched(); + dm_bufio_lock(c); + } } dm_bufio_unlock(c); diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index bd694910b01b..7f524a26cebc 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2366,8 +2366,7 @@ static int bitmap_get_stats(void *data, struct md_bitmap_stats *stats) if (!bitmap) return -ENOENT; - if (!bitmap->mddev->bitmap_info.external && - !bitmap->storage.sb_page) + if (!bitmap->storage.sb_page) return -EINVAL; sb = kmap_local_page(bitmap->storage.sb_page); stats->sync_size = le64_to_cpu(sb->sync_size); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 19c5a0ce5a40..64b8176907a9 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1399,7 +1399,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, } read_bio = bio_alloc_clone(mirror->rdev->bdev, bio, gfp, &mddev->bio_set); - + read_bio->bi_opf &= ~REQ_NOWAIT; r1_bio->bios[rdisk] = read_bio; read_bio->bi_iter.bi_sector = r1_bio->sector + @@ -1649,6 +1649,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, wait_for_serialization(rdev, r1_bio); } + mbio->bi_opf &= ~REQ_NOWAIT; r1_bio->bios[i] = mbio; mbio->bi_iter.bi_sector = (r1_bio->sector + rdev->data_offset); @@ -3428,6 +3429,7 @@ static int raid1_reshape(struct mddev *mddev) /* ok, everything is stopped */ oldpool = conf->r1bio_pool; conf->r1bio_pool = newpool; + init_waitqueue_head(&conf->r1bio_pool.wait); for (d = d2 = 0; d < conf->raid_disks; d++) { struct md_rdev *rdev = conf->mirrors[d].rdev; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index b74780af4c22..c9bd2005bfd0 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1182,8 +1182,11 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, } } - if (!regular_request_wait(mddev, conf, bio, r10_bio->sectors)) + if (!regular_request_wait(mddev, conf, bio, r10_bio->sectors)) { + raid_end_bio_io(r10_bio); return; + } + rdev = read_balance(conf, r10_bio, &max_sectors); if (!rdev) { if (err_rdev) { @@ -1221,6 +1224,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, r10_bio->master_bio = bio; } read_bio = bio_alloc_clone(rdev->bdev, bio, gfp, &mddev->bio_set); + read_bio->bi_opf &= ~REQ_NOWAIT; r10_bio->devs[slot].bio = read_bio; r10_bio->devs[slot].rdev = rdev; @@ -1256,6 +1260,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, conf->mirrors[devnum].rdev; mbio = bio_alloc_clone(rdev->bdev, bio, GFP_NOIO, &mddev->bio_set); + mbio->bi_opf &= ~REQ_NOWAIT; if (replacement) r10_bio->devs[n_copy].repl_bio = mbio; else @@ -1370,8 +1375,11 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, } sectors = r10_bio->sectors; - if (!regular_request_wait(mddev, conf, bio, sectors)) + if (!regular_request_wait(mddev, conf, bio, sectors)) { + raid_end_bio_io(r10_bio); return; + } + if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && (mddev->reshape_backwards ? (bio->bi_iter.bi_sector < conf->reshape_safe && diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c index 043b9ec756ff..7f3f47db4c98 100644 --- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -324,7 +324,7 @@ EXPORT_SYMBOL(memstick_init_req); static int h_memstick_read_dev_id(struct memstick_dev *card, struct memstick_request **mrq) { - struct ms_id_register id_reg; + struct ms_id_register id_reg = {}; if (!(*mrq)) { memstick_init_req(&card->current_mrq, MS_TPC_READ_REG, &id_reg, diff --git a/drivers/misc/amd-sbi/rmi-core.c b/drivers/misc/amd-sbi/rmi-core.c index b653a21a909e..3dec2fc00124 100644 --- a/drivers/misc/amd-sbi/rmi-core.c +++ b/drivers/misc/amd-sbi/rmi-core.c @@ -42,7 +42,6 @@ #define RD_MCA_CMD 0x86 /* CPUID MCAMSR mask & index */ -#define CPUID_MCA_THRD_MASK GENMASK(15, 0) #define CPUID_MCA_THRD_INDEX 32 #define CPUID_MCA_FUNC_MASK GENMASK(31, 0) #define CPUID_EXT_FUNC_INDEX 56 @@ -129,7 +128,7 @@ static int rmi_cpuid_read(struct sbrmi_data *data, goto exit_unlock; } - thread = msg->cpu_in_out << CPUID_MCA_THRD_INDEX & CPUID_MCA_THRD_MASK; + thread = msg->cpu_in_out >> CPUID_MCA_THRD_INDEX; /* Thread > 127, Thread128 CS register, 1'b1 needs to be set to 1 */ if (thread > 127) { @@ -210,7 +209,7 @@ static int rmi_mca_msr_read(struct sbrmi_data *data, goto exit_unlock; } - thread = msg->mcamsr_in_out << CPUID_MCA_THRD_INDEX & CPUID_MCA_THRD_MASK; + thread = msg->mcamsr_in_out >> CPUID_MCA_THRD_INDEX; /* Thread > 127, Thread128 CS register, 1'b1 needs to be set to 1 */ if (thread > 127) { @@ -321,6 +320,10 @@ int rmi_mailbox_xfer(struct sbrmi_data *data, ret = regmap_read(data->regmap, SBRMI_OUTBNDMSG7, &ec); if (ret || ec) goto exit_clear_alert; + + /* Clear the input value before updating the output data */ + msg->mb_in_out = 0; + /* * For a read operation, the initiator (BMC) reads the firmware * response Command Data Out[31:0] from SBRMI::OutBndMsg_inst[4:1] @@ -373,7 +376,8 @@ static int apml_rmi_reg_xfer(struct sbrmi_data *data, mutex_unlock(&data->lock); if (msg.rflag && !ret) - return copy_to_user(arg, &msg, sizeof(struct apml_reg_xfer_msg)); + if (copy_to_user(arg, &msg, sizeof(struct apml_reg_xfer_msg))) + return -EFAULT; return ret; } @@ -391,7 +395,9 @@ static int apml_mailbox_xfer(struct sbrmi_data *data, struct apml_mbox_msg __use if (ret && ret != -EPROTOTYPE) return ret; - return copy_to_user(arg, &msg, sizeof(struct apml_mbox_msg)); + if (copy_to_user(arg, &msg, sizeof(struct apml_mbox_msg))) + return -EFAULT; + return ret; } static int apml_cpuid_xfer(struct sbrmi_data *data, struct apml_cpuid_msg __user *arg) @@ -408,7 +414,9 @@ static int apml_cpuid_xfer(struct sbrmi_data *data, struct apml_cpuid_msg __user if (ret && ret != -EPROTOTYPE) return ret; - return copy_to_user(arg, &msg, sizeof(struct apml_cpuid_msg)); + if (copy_to_user(arg, &msg, sizeof(struct apml_cpuid_msg))) + return -EFAULT; + return ret; } static int apml_mcamsr_xfer(struct sbrmi_data *data, struct apml_mcamsr_msg __user *arg) @@ -425,7 +433,9 @@ static int apml_mcamsr_xfer(struct sbrmi_data *data, struct apml_mcamsr_msg __us if (ret && ret != -EPROTOTYPE) return ret; - return copy_to_user(arg, &msg, sizeof(struct apml_mcamsr_msg)); + if (copy_to_user(arg, &msg, sizeof(struct apml_mcamsr_msg))) + return -EFAULT; + return ret; } static long sbrmi_ioctl(struct file *fp, unsigned int cmd, unsigned long arg) diff --git a/drivers/mmc/host/bcm2835.c b/drivers/mmc/host/bcm2835.c index def054ddd256..4fced9b36c80 100644 --- a/drivers/mmc/host/bcm2835.c +++ b/drivers/mmc/host/bcm2835.c @@ -503,7 +503,8 @@ void bcm2835_prepare_dma(struct bcm2835_host *host, struct mmc_data *data) DMA_PREP_INTERRUPT | DMA_CTRL_ACK); if (!desc) { - dma_unmap_sg(dma_chan->device->dev, data->sg, sg_len, dir_data); + dma_unmap_sg(dma_chan->device->dev, data->sg, data->sg_len, + dir_data); return; } diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index 13a84b9309e0..e3877a1c72a9 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -913,7 +913,8 @@ static bool glk_broken_cqhci(struct sdhci_pci_slot *slot) { return slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_GLK_EMMC && (dmi_match(DMI_BIOS_VENDOR, "LENOVO") || - dmi_match(DMI_SYS_VENDOR, "IRBIS")); + dmi_match(DMI_SYS_VENDOR, "IRBIS") || + dmi_match(DMI_SYS_VENDOR, "Positivo Tecnologia SA")); } static bool jsl_broken_hs400es(struct sdhci_pci_slot *slot) diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c index 73385ff4c0f3..9e94998e8df7 100644 --- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -613,7 +613,8 @@ static const struct sdhci_ops sdhci_am654_ops = { static const struct sdhci_pltfm_data sdhci_am654_pdata = { .ops = &sdhci_am654_ops, .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, - .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, + .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | + SDHCI_QUIRK2_DISABLE_HW_TIMEOUT, }; static const struct sdhci_am654_driver_data sdhci_am654_sr1_drvdata = { @@ -643,7 +644,8 @@ static const struct sdhci_ops sdhci_j721e_8bit_ops = { static const struct sdhci_pltfm_data sdhci_j721e_8bit_pdata = { .ops = &sdhci_j721e_8bit_ops, .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, - .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, + .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | + SDHCI_QUIRK2_DISABLE_HW_TIMEOUT, }; static const struct sdhci_am654_driver_data sdhci_j721e_8bit_drvdata = { @@ -667,7 +669,8 @@ static const struct sdhci_ops sdhci_j721e_4bit_ops = { static const struct sdhci_pltfm_data sdhci_j721e_4bit_pdata = { .ops = &sdhci_j721e_4bit_ops, .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, - .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, + .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | + SDHCI_QUIRK2_DISABLE_HW_TIMEOUT, }; static const struct sdhci_am654_driver_data sdhci_j721e_4bit_drvdata = { diff --git a/drivers/mux/Kconfig b/drivers/mux/Kconfig index 80f015cf6e54..c68132e38138 100644 --- a/drivers/mux/Kconfig +++ b/drivers/mux/Kconfig @@ -48,6 +48,7 @@ config MUX_GPIO config MUX_MMIO tristate "MMIO/Regmap register bitfield-controlled Multiplexer" depends on OF + select REGMAP_MMIO help MMIO/Regmap register bitfield-controlled Multiplexer controller. diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c index ea8c807af4d8..3913971125de 100644 --- a/drivers/net/can/dev/dev.c +++ b/drivers/net/can/dev/dev.c @@ -145,13 +145,16 @@ void can_change_state(struct net_device *dev, struct can_frame *cf, EXPORT_SYMBOL_GPL(can_change_state); /* CAN device restart for bus-off recovery */ -static void can_restart(struct net_device *dev) +static int can_restart(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); struct sk_buff *skb; struct can_frame *cf; int err; + if (!priv->do_set_mode) + return -EOPNOTSUPP; + if (netif_carrier_ok(dev)) netdev_err(dev, "Attempt to restart for bus-off recovery, but carrier is OK?\n"); @@ -173,10 +176,14 @@ static void can_restart(struct net_device *dev) if (err) { netdev_err(dev, "Restart failed, error %pe\n", ERR_PTR(err)); netif_carrier_off(dev); + + return err; } else { netdev_dbg(dev, "Restarted\n"); priv->can_stats.restarts++; } + + return 0; } static void can_restart_work(struct work_struct *work) @@ -201,9 +208,8 @@ int can_restart_now(struct net_device *dev) return -EBUSY; cancel_delayed_work_sync(&priv->restart_work); - can_restart(dev); - return 0; + return can_restart(dev); } /* CAN bus-off diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index a36842ace084..f0e3f0d538fb 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -285,6 +285,12 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], } if (data[IFLA_CAN_RESTART_MS]) { + if (!priv->do_set_mode) { + NL_SET_ERR_MSG(extack, + "Device doesn't support restart from Bus Off"); + return -EOPNOTSUPP; + } + /* Do not allow changing restart delay while running */ if (dev->flags & IFF_UP) return -EBUSY; @@ -292,6 +298,12 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], } if (data[IFLA_CAN_RESTART]) { + if (!priv->do_set_mode) { + NL_SET_ERR_MSG(extack, + "Device doesn't support restart from Bus Off"); + return -EOPNOTSUPP; + } + /* Do not allow a restart while not running */ if (!(dev->flags & IFF_UP)) return -EINVAL; diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 6c656bfdb323..fe74dbd2c966 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -665,7 +665,7 @@ static int m_can_handle_lost_msg(struct net_device *dev) struct can_frame *frame; u32 timestamp = 0; - netdev_err(dev, "msg lost in rxf0\n"); + netdev_dbg(dev, "msg lost in rxf0\n"); stats->rx_errors++; stats->rx_over_errors++; diff --git a/drivers/net/can/m_can/tcan4x5x-core.c b/drivers/net/can/m_can/tcan4x5x-core.c index 8edaa339d590..39b0b5277b11 100644 --- a/drivers/net/can/m_can/tcan4x5x-core.c +++ b/drivers/net/can/m_can/tcan4x5x-core.c @@ -343,21 +343,19 @@ static void tcan4x5x_get_dt_data(struct m_can_classdev *cdev) of_property_read_bool(cdev->dev->of_node, "ti,nwkrq-voltage-vio"); } -static int tcan4x5x_get_gpios(struct m_can_classdev *cdev, - const struct tcan4x5x_version_info *version_info) +static int tcan4x5x_get_gpios(struct m_can_classdev *cdev) { struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev); int ret; - if (version_info->has_wake_pin) { - tcan4x5x->device_wake_gpio = devm_gpiod_get(cdev->dev, "device-wake", - GPIOD_OUT_HIGH); - if (IS_ERR(tcan4x5x->device_wake_gpio)) { - if (PTR_ERR(tcan4x5x->device_wake_gpio) == -EPROBE_DEFER) - return -EPROBE_DEFER; + tcan4x5x->device_wake_gpio = devm_gpiod_get_optional(cdev->dev, + "device-wake", + GPIOD_OUT_HIGH); + if (IS_ERR(tcan4x5x->device_wake_gpio)) { + if (PTR_ERR(tcan4x5x->device_wake_gpio) == -EPROBE_DEFER) + return -EPROBE_DEFER; - tcan4x5x_disable_wake(cdev); - } + tcan4x5x->device_wake_gpio = NULL; } tcan4x5x->reset_gpio = devm_gpiod_get_optional(cdev->dev, "reset", @@ -369,14 +367,31 @@ static int tcan4x5x_get_gpios(struct m_can_classdev *cdev, if (ret) return ret; - if (version_info->has_state_pin) { - tcan4x5x->device_state_gpio = devm_gpiod_get_optional(cdev->dev, - "device-state", - GPIOD_IN); - if (IS_ERR(tcan4x5x->device_state_gpio)) { - tcan4x5x->device_state_gpio = NULL; - tcan4x5x_disable_state(cdev); - } + tcan4x5x->device_state_gpio = devm_gpiod_get_optional(cdev->dev, + "device-state", + GPIOD_IN); + if (IS_ERR(tcan4x5x->device_state_gpio)) + tcan4x5x->device_state_gpio = NULL; + + return 0; +} + +static int tcan4x5x_check_gpios(struct m_can_classdev *cdev, + const struct tcan4x5x_version_info *version_info) +{ + struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev); + int ret; + + if (version_info->has_wake_pin && !tcan4x5x->device_wake_gpio) { + ret = tcan4x5x_disable_wake(cdev); + if (ret) + return ret; + } + + if (version_info->has_state_pin && !tcan4x5x->device_state_gpio) { + ret = tcan4x5x_disable_state(cdev); + if (ret) + return ret; } return 0; @@ -468,15 +483,21 @@ static int tcan4x5x_can_probe(struct spi_device *spi) goto out_m_can_class_free_dev; } + ret = tcan4x5x_get_gpios(mcan_class); + if (ret) { + dev_err(&spi->dev, "Getting gpios failed %pe\n", ERR_PTR(ret)); + goto out_power; + } + version_info = tcan4x5x_find_version(priv); if (IS_ERR(version_info)) { ret = PTR_ERR(version_info); goto out_power; } - ret = tcan4x5x_get_gpios(mcan_class, version_info); + ret = tcan4x5x_check_gpios(mcan_class, version_info); if (ret) { - dev_err(&spi->dev, "Getting gpios failed %pe\n", ERR_PTR(ret)); + dev_err(&spi->dev, "Checking gpios failed %pe\n", ERR_PTR(ret)); goto out_power; } diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 06dea3a13e77..9057180051df 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -2984,6 +2984,7 @@ static int airoha_probe(struct platform_device *pdev) error_napi_stop: for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) airoha_qdma_stop_napi(ð->qdma[i]); + airoha_ppe_deinit(eth); error_hw_cleanup: for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) airoha_hw_cleanup(ð->qdma[i]); diff --git a/drivers/net/ethernet/airoha/airoha_npu.c b/drivers/net/ethernet/airoha/airoha_npu.c index 0e5b8c21b9aa..1e58a4aeb9a0 100644 --- a/drivers/net/ethernet/airoha/airoha_npu.c +++ b/drivers/net/ethernet/airoha/airoha_npu.c @@ -401,12 +401,13 @@ struct airoha_npu *airoha_npu_get(struct device *dev, dma_addr_t *stats_addr) return ERR_PTR(-ENODEV); pdev = of_find_device_by_node(np); - of_node_put(np); if (!pdev) { dev_err(dev, "cannot find device node %s\n", np->name); + of_node_put(np); return ERR_PTR(-ENODEV); } + of_node_put(np); if (!try_module_get(THIS_MODULE)) { dev_err(dev, "failed to get the device driver module\n"); diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index 0d61b8580d72..f832562bd7a3 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c @@ -818,6 +818,9 @@ static void bcmasp_init_tx(struct bcmasp_intf *intf) /* Tx SPB */ tx_spb_ctrl_wl(intf, ((intf->channel + 8) << TX_SPB_CTRL_XF_BID_SHIFT), TX_SPB_CTRL_XF_CTRL2); + + if (intf->parent->tx_chan_offset) + tx_pause_ctrl_wl(intf, (1 << (intf->channel + 8)), TX_PAUSE_MAP_VECTOR); tx_spb_top_wl(intf, 0x1e, TX_SPB_TOP_BLKOUT); tx_spb_dma_wq(intf, intf->tx_spb_dma_addr, TX_SPB_DMA_READ); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index ae89a981e052..243cb13cb01c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11607,11 +11607,9 @@ static void bnxt_free_irq(struct bnxt *bp) static int bnxt_request_irq(struct bnxt *bp) { + struct cpu_rmap *rmap = NULL; int i, j, rc = 0; unsigned long flags = 0; -#ifdef CONFIG_RFS_ACCEL - struct cpu_rmap *rmap; -#endif rc = bnxt_setup_int_mode(bp); if (rc) { @@ -11632,15 +11630,15 @@ static int bnxt_request_irq(struct bnxt *bp) int map_idx = bnxt_cp_num_to_irq_num(bp, i); struct bnxt_irq *irq = &bp->irq_tbl[map_idx]; -#ifdef CONFIG_RFS_ACCEL - if (rmap && bp->bnapi[i]->rx_ring) { + if (IS_ENABLED(CONFIG_RFS_ACCEL) && + rmap && bp->bnapi[i]->rx_ring) { rc = irq_cpu_rmap_add(rmap, irq->vector); if (rc) netdev_warn(bp->dev, "failed adding irq rmap for ring %d\n", j); j++; } -#endif + rc = request_irq(irq->vector, irq->handler, flags, irq->name, bp->bnapi[i]); if (rc) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c index ce97befd3cb3..67e70d3d0980 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c @@ -368,23 +368,27 @@ static u32 bnxt_get_ctx_coredump(struct bnxt *bp, void *buf, u32 offset, if (!ctxm->mem_valid || !seg_id) continue; - if (trace) + if (trace) { extra_hlen = BNXT_SEG_RCD_LEN; + if (buf) { + u16 trace_type = bnxt_bstore_to_trace[type]; + + bnxt_fill_drv_seg_record(bp, &record, ctxm, + trace_type); + } + } + if (buf) data = buf + BNXT_SEG_HDR_LEN + extra_hlen; + seg_len = bnxt_copy_ctx_mem(bp, ctxm, data, 0) + extra_hlen; if (buf) { bnxt_fill_coredump_seg_hdr(bp, &seg_hdr, NULL, seg_len, 0, 0, 0, comp_id, seg_id); memcpy(buf, &seg_hdr, BNXT_SEG_HDR_LEN); buf += BNXT_SEG_HDR_LEN; - if (trace) { - u16 trace_type = bnxt_bstore_to_trace[type]; - - bnxt_fill_drv_seg_record(bp, &record, ctxm, - trace_type); + if (trace) memcpy(buf, &record, BNXT_SEG_RCD_LEN); - } buf += seg_len; } len += BNXT_SEG_HDR_LEN + seg_len; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c index 0dbb880a7aa0..71e14be2507e 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c @@ -487,7 +487,9 @@ static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc) if ((ets->tc_tx_bw[i] || ets->tc_tsa[i]) && i > bp->max_tc) return -EINVAL; + } + for (i = 0; i < max_tc; i++) { switch (ets->tc_tsa[i]) { case IEEE_8021QAZ_TSA_STRICT: break; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 4a6d8cb9f970..09e7e8efa6fa 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -115,7 +115,7 @@ static void __bnxt_xmit_xdp_redirect(struct bnxt *bp, tx_buf->action = XDP_REDIRECT; tx_buf->xdpf = xdpf; dma_unmap_addr_set(tx_buf, mapping, mapping); - dma_unmap_len_set(tx_buf, len, 0); + dma_unmap_len_set(tx_buf, len, len); } void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int budget) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index fa0077bc67b7..97585c160de3 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -4092,6 +4092,12 @@ static int bcmgenet_probe(struct platform_device *pdev) for (i = 0; i <= priv->hw_params->rx_queues; i++) priv->rx_rings[i].rx_max_coalesced_frames = 1; + /* Initialize u64 stats seq counter for 32bit machines */ + for (i = 0; i <= priv->hw_params->rx_queues; i++) + u64_stats_init(&priv->rx_rings[i].stats64.syncp); + for (i = 0; i <= priv->hw_params->tx_queues; i++) + u64_stats_init(&priv->tx_rings[i].stats64.syncp); + /* libphy will determine the link state */ netif_carrier_off(dev); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index aebb9fef3f6e..1be2dc40a1a6 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1578,7 +1578,6 @@ napi_del: static int nicvf_change_mtu(struct net_device *netdev, int new_mtu) { struct nicvf *nic = netdev_priv(netdev); - int orig_mtu = netdev->mtu; /* For now just support only the usual MTU sized frames, * plus some headroom for VLAN, QinQ. @@ -1589,15 +1588,10 @@ static int nicvf_change_mtu(struct net_device *netdev, int new_mtu) return -EINVAL; } - WRITE_ONCE(netdev->mtu, new_mtu); - - if (!netif_running(netdev)) - return 0; - - if (nicvf_update_hw_max_frs(nic, new_mtu)) { - netdev->mtu = orig_mtu; + if (netif_running(netdev) && nicvf_update_hw_max_frs(nic, new_mtu)) return -EINVAL; - } + + WRITE_ONCE(netdev->mtu, new_mtu); return 0; } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index b82f121cadad..0f4efd505332 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -4666,12 +4666,19 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv) return PTR_ERR(dpmac_dev); } - if (IS_ERR(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) + if (IS_ERR(dpmac_dev)) return 0; + if (dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) { + err = 0; + goto out_put_device; + } + mac = kzalloc(sizeof(struct dpaa2_mac), GFP_KERNEL); - if (!mac) - return -ENOMEM; + if (!mac) { + err = -ENOMEM; + goto out_put_device; + } mac->mc_dev = dpmac_dev; mac->mc_io = priv->mc_io; @@ -4705,6 +4712,8 @@ err_close_mac: dpaa2_mac_close(mac); err_free_mac: kfree(mac); +out_put_device: + put_device(&dpmac_dev->dev); return err; } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index 147a93bf9fa9..4643a3380618 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1448,12 +1448,19 @@ static int dpaa2_switch_port_connect_mac(struct ethsw_port_priv *port_priv) if (PTR_ERR(dpmac_dev) == -EPROBE_DEFER) return PTR_ERR(dpmac_dev); - if (IS_ERR(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) + if (IS_ERR(dpmac_dev)) return 0; + if (dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) { + err = 0; + goto out_put_device; + } + mac = kzalloc(sizeof(*mac), GFP_KERNEL); - if (!mac) - return -ENOMEM; + if (!mac) { + err = -ENOMEM; + goto out_put_device; + } mac->mc_dev = dpmac_dev; mac->mc_io = port_priv->ethsw_data->mc_io; @@ -1483,6 +1490,8 @@ err_close_mac: dpaa2_mac_close(mac); err_free_mac: kfree(mac); +out_put_device: + put_device(&dpmac_dev->dev); return err; } diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index dc35a23ec47f..d1aeb722d48f 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1917,49 +1917,56 @@ static void gve_turnup_and_check_status(struct gve_priv *priv) gve_handle_link_status(priv, GVE_DEVICE_STATUS_LINK_STATUS_MASK & status); } -static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue) +static struct gve_notify_block *gve_get_tx_notify_block(struct gve_priv *priv, + unsigned int txqueue) { - struct gve_notify_block *block; - struct gve_tx_ring *tx = NULL; - struct gve_priv *priv; - u32 last_nic_done; - u32 current_time; u32 ntfy_idx; - netdev_info(dev, "Timeout on tx queue, %d", txqueue); - priv = netdev_priv(dev); if (txqueue > priv->tx_cfg.num_queues) - goto reset; + return NULL; ntfy_idx = gve_tx_idx_to_ntfy(priv, txqueue); if (ntfy_idx >= priv->num_ntfy_blks) - goto reset; + return NULL; + + return &priv->ntfy_blocks[ntfy_idx]; +} + +static bool gve_tx_timeout_try_q_kick(struct gve_priv *priv, + unsigned int txqueue) +{ + struct gve_notify_block *block; + u32 current_time; - block = &priv->ntfy_blocks[ntfy_idx]; - tx = block->tx; + block = gve_get_tx_notify_block(priv, txqueue); + + if (!block) + return false; current_time = jiffies_to_msecs(jiffies); - if (tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time) - goto reset; + if (block->tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time) + return false; - /* Check to see if there are missed completions, which will allow us to - * kick the queue. - */ - last_nic_done = gve_tx_load_event_counter(priv, tx); - if (last_nic_done - tx->done) { - netdev_info(dev, "Kicking queue %d", txqueue); - iowrite32be(GVE_IRQ_MASK, gve_irq_doorbell(priv, block)); - napi_schedule(&block->napi); - tx->last_kick_msec = current_time; - goto out; - } // Else reset. + netdev_info(priv->dev, "Kicking queue %d", txqueue); + napi_schedule(&block->napi); + block->tx->last_kick_msec = current_time; + return true; +} -reset: - gve_schedule_reset(priv); +static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue) +{ + struct gve_notify_block *block; + struct gve_priv *priv; -out: - if (tx) - tx->queue_timeout++; + netdev_info(dev, "Timeout on tx queue, %d", txqueue); + priv = netdev_priv(dev); + + if (!gve_tx_timeout_try_q_kick(priv, txqueue)) + gve_schedule_reset(priv); + + block = gve_get_tx_notify_block(priv, txqueue); + if (block) + block->tx->queue_timeout++; priv->tx_timeo_cnt++; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index b03b8758c777..aaa803563bd2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -11,6 +11,7 @@ #include <linux/irq.h> #include <linux/ip.h> #include <linux/ipv6.h> +#include <linux/iommu.h> #include <linux/module.h> #include <linux/pci.h> #include <linux/skbuff.h> @@ -1039,6 +1040,8 @@ static bool hns3_can_use_tx_sgl(struct hns3_enet_ring *ring, static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring) { u32 alloc_size = ring->tqp->handle->kinfo.tx_spare_buf_size; + struct net_device *netdev = ring_to_netdev(ring); + struct hns3_nic_priv *priv = netdev_priv(netdev); struct hns3_tx_spare *tx_spare; struct page *page; dma_addr_t dma; @@ -1080,6 +1083,7 @@ static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring) tx_spare->buf = page_address(page); tx_spare->len = PAGE_SIZE << order; ring->tx_spare = tx_spare; + ring->tx_copybreak = priv->tx_copybreak; return; dma_mapping_error: @@ -4874,6 +4878,30 @@ static void hns3_nic_dealloc_vector_data(struct hns3_nic_priv *priv) devm_kfree(&pdev->dev, priv->tqp_vector); } +static void hns3_update_tx_spare_buf_config(struct hns3_nic_priv *priv) +{ +#define HNS3_MIN_SPARE_BUF_SIZE (2 * 1024 * 1024) +#define HNS3_MAX_PACKET_SIZE (64 * 1024) + + struct iommu_domain *domain = iommu_get_domain_for_dev(priv->dev); + struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(priv->ae_handle); + struct hnae3_handle *handle = priv->ae_handle; + + if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3) + return; + + if (!(domain && iommu_is_dma_domain(domain))) + return; + + priv->min_tx_copybreak = HNS3_MAX_PACKET_SIZE; + priv->min_tx_spare_buf_size = HNS3_MIN_SPARE_BUF_SIZE; + + if (priv->tx_copybreak < priv->min_tx_copybreak) + priv->tx_copybreak = priv->min_tx_copybreak; + if (handle->kinfo.tx_spare_buf_size < priv->min_tx_spare_buf_size) + handle->kinfo.tx_spare_buf_size = priv->min_tx_spare_buf_size; +} + static void hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv, unsigned int ring_type) { @@ -5107,6 +5135,7 @@ int hns3_init_all_ring(struct hns3_nic_priv *priv) int i, j; int ret; + hns3_update_tx_spare_buf_config(priv); for (i = 0; i < ring_num; i++) { ret = hns3_alloc_ring_memory(&priv->ring[i]); if (ret) { @@ -5311,6 +5340,8 @@ static int hns3_client_init(struct hnae3_handle *handle) priv->ae_handle = handle; priv->tx_timeout_count = 0; priv->max_non_tso_bd_num = ae_dev->dev_specs.max_non_tso_bd_num; + priv->min_tx_copybreak = 0; + priv->min_tx_spare_buf_size = 0; set_bit(HNS3_NIC_STATE_DOWN, &priv->state); handle->msg_enable = netif_msg_init(debug, DEFAULT_MSG_LEVEL); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index d36c4ed16d8d..caf7a4df8585 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -596,6 +596,8 @@ struct hns3_nic_priv { struct hns3_enet_coalesce rx_coal; u32 tx_copybreak; u32 rx_copybreak; + u32 min_tx_copybreak; + u32 min_tx_spare_buf_size; }; union l3_hdr_info { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index a7de67699a01..30bdec1acb57 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -9576,33 +9576,36 @@ static bool hclge_need_enable_vport_vlan_filter(struct hclge_vport *vport) return false; } -int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en) +static int __hclge_enable_vport_vlan_filter(struct hclge_vport *vport, + bool request_en) { - struct hclge_dev *hdev = vport->back; bool need_en; int ret; - mutex_lock(&hdev->vport_lock); - - vport->req_vlan_fltr_en = request_en; - need_en = hclge_need_enable_vport_vlan_filter(vport); - if (need_en == vport->cur_vlan_fltr_en) { - mutex_unlock(&hdev->vport_lock); + if (need_en == vport->cur_vlan_fltr_en) return 0; - } ret = hclge_set_vport_vlan_filter(vport, need_en); - if (ret) { - mutex_unlock(&hdev->vport_lock); + if (ret) return ret; - } vport->cur_vlan_fltr_en = need_en; + return 0; +} + +int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en) +{ + struct hclge_dev *hdev = vport->back; + int ret; + + mutex_lock(&hdev->vport_lock); + vport->req_vlan_fltr_en = request_en; + ret = __hclge_enable_vport_vlan_filter(vport, request_en); mutex_unlock(&hdev->vport_lock); - return 0; + return ret; } static int hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable) @@ -10623,16 +10626,19 @@ static void hclge_sync_vlan_fltr_state(struct hclge_dev *hdev) &vport->state)) continue; - ret = hclge_enable_vport_vlan_filter(vport, - vport->req_vlan_fltr_en); + mutex_lock(&hdev->vport_lock); + ret = __hclge_enable_vport_vlan_filter(vport, + vport->req_vlan_fltr_en); if (ret) { dev_err(&hdev->pdev->dev, "failed to sync vlan filter state for vport%u, ret = %d\n", vport->vport_id, ret); set_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE, &vport->state); + mutex_unlock(&hdev->vport_lock); return; } + mutex_unlock(&hdev->vport_lock); } } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c index ec581d4b696f..4bd52eab3914 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c @@ -497,14 +497,14 @@ int hclge_ptp_init(struct hclge_dev *hdev) if (ret) { dev_err(&hdev->pdev->dev, "failed to init freq, ret = %d\n", ret); - goto out; + goto out_clear_int; } ret = hclge_ptp_set_ts_mode(hdev, &hdev->ptp->ts_cfg); if (ret) { dev_err(&hdev->pdev->dev, "failed to init ts mode, ret = %d\n", ret); - goto out; + goto out_clear_int; } ktime_get_real_ts64(&ts); @@ -512,7 +512,7 @@ int hclge_ptp_init(struct hclge_dev *hdev) if (ret) { dev_err(&hdev->pdev->dev, "failed to init ts time, ret = %d\n", ret); - goto out; + goto out_clear_int; } set_bit(HCLGE_STATE_PTP_EN, &hdev->state); @@ -520,6 +520,9 @@ int hclge_ptp_init(struct hclge_dev *hdev) return 0; +out_clear_int: + clear_bit(HCLGE_PTP_FLAG_EN, &hdev->ptp->flags); + hclge_ptp_int_en(hdev, false); out: hclge_ptp_destroy_clock(hdev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index c4f35e8e2177..4cf6ac04662a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -3094,11 +3094,7 @@ static void hclgevf_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) static u32 hclgevf_get_max_channels(struct hclgevf_dev *hdev) { - struct hnae3_handle *nic = &hdev->nic; - struct hnae3_knic_private_info *kinfo = &nic->kinfo; - - return min_t(u32, hdev->rss_size_max, - hdev->num_tqps / kinfo->tc_info.num_tc); + return min(hdev->rss_size_max, hdev->num_tqps); } /** diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index a189038d88df..246ddce753f9 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -211,7 +211,6 @@ struct ibmvnic_statistics { u8 reserved[72]; } __packed __aligned(8); -#define NUM_TX_STATS 3 struct ibmvnic_tx_queue_stats { u64 batched_packets; u64 direct_packets; @@ -219,13 +218,18 @@ struct ibmvnic_tx_queue_stats { u64 dropped_packets; }; -#define NUM_RX_STATS 3 +#define NUM_TX_STATS \ + (sizeof(struct ibmvnic_tx_queue_stats) / sizeof(u64)) + struct ibmvnic_rx_queue_stats { u64 packets; u64 bytes; u64 interrupts; }; +#define NUM_RX_STATS \ + (sizeof(struct ibmvnic_rx_queue_stats) / sizeof(u64)) + struct ibmvnic_acl_buffer { __be32 len; __be32 version; diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index 8294a7c4f122..ba331899d186 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -638,6 +638,9 @@ /* For checksumming, the sum of all words in the NVM should equal 0xBABA. */ #define NVM_SUM 0xBABA +/* Uninitialized ("empty") checksum word value */ +#define NVM_CHECKSUM_UNINITIALIZED 0xFFFF + /* PBA (printed board assembly) number words */ #define NVM_PBA_OFFSET_0 8 #define NVM_PBA_OFFSET_1 9 diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 364378133526..df4e7d781cb1 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -4274,6 +4274,8 @@ static s32 e1000_validate_nvm_checksum_ich8lan(struct e1000_hw *hw) ret_val = e1000e_update_nvm_checksum(hw); if (ret_val) return ret_val; + } else if (hw->mac.type == e1000_pch_tgp) { + return 0; } } diff --git a/drivers/net/ethernet/intel/e1000e/nvm.c b/drivers/net/ethernet/intel/e1000e/nvm.c index e609f4df86f4..16369e6d245a 100644 --- a/drivers/net/ethernet/intel/e1000e/nvm.c +++ b/drivers/net/ethernet/intel/e1000e/nvm.c @@ -558,6 +558,12 @@ s32 e1000e_validate_nvm_checksum_generic(struct e1000_hw *hw) checksum += nvm_data; } + if (hw->mac.type == e1000_pch_tgp && + nvm_data == NVM_CHECKSUM_UNINITIALIZED) { + e_dbg("Uninitialized NVM Checksum on TGP platform - ignoring\n"); + return 0; + } + if (checksum != (u16)NVM_SUM) { e_dbg("NVM Checksum Invalid\n"); return -E1000_ERR_NVM; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index 6119a4108838..65a2816142d9 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -189,13 +189,14 @@ struct fm10k_q_vector { struct fm10k_ring_container rx, tx; struct napi_struct napi; + struct rcu_head rcu; /* to avoid race with update stats on free */ + cpumask_t affinity_mask; char name[IFNAMSIZ + 9]; #ifdef CONFIG_DEBUG_FS struct dentry *dbg_q_vector; #endif /* CONFIG_DEBUG_FS */ - struct rcu_head rcu; /* to avoid race with update stats on free */ /* for dynamic allocation of rings associated with this q_vector */ struct fm10k_ring ring[] ____cacheline_internodealigned_in_smp; diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index c67963bfe14e..7c600d6e66ba 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -945,6 +945,7 @@ struct i40e_q_vector { u16 reg_idx; /* register index of the interrupt */ struct napi_struct napi; + struct rcu_head rcu; /* to avoid race with update stats on free */ struct i40e_ring_container rx; struct i40e_ring_container tx; @@ -955,7 +956,6 @@ struct i40e_q_vector { cpumask_t affinity_mask; struct irq_affinity_notify affinity_notify; - struct rcu_head rcu; /* to avoid race with update stats on free */ char name[I40E_INT_NAME_STR_LEN]; bool arm_wb_state; bool in_busy_poll; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 88e6bef69342..7ccfc1191ae5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -3137,10 +3137,10 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) const u8 *addr = al->list[i].addr; /* Allow to delete VF primary MAC only if it was not set - * administratively by PF or if VF is trusted. + * administratively by PF. */ if (ether_addr_equal(addr, vf->default_lan_addr.addr)) { - if (i40e_can_vf_change_mac(vf)) + if (!vf->pf_set_mac) was_unimac_deleted = true; else continue; @@ -5006,7 +5006,7 @@ int i40e_get_vf_stats(struct net_device *netdev, int vf_id, vf_stats->broadcast = stats->rx_broadcast; vf_stats->multicast = stats->rx_multicast; vf_stats->rx_dropped = stats->rx_discards + stats->rx_discards_other; - vf_stats->tx_dropped = stats->tx_discards; + vf_stats->tx_dropped = stats->tx_errors; return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index 59323c019544..351824dc3c62 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -2301,6 +2301,8 @@ enum ice_ddp_state ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, return ICE_DDP_PKG_ERR; buf_copy = devm_kmemdup(ice_hw_to_dev(hw), buf, len, GFP_KERNEL); + if (!buf_copy) + return ICE_DDP_PKG_ERR; state = ice_init_pkg(hw, buf_copy, len); if (!ice_is_init_pkg_successful(state)) { diff --git a/drivers/net/ethernet/intel/ice/ice_debugfs.c b/drivers/net/ethernet/intel/ice/ice_debugfs.c index 9fc0fd95a13d..cb71eca6a85b 100644 --- a/drivers/net/ethernet/intel/ice/ice_debugfs.c +++ b/drivers/net/ethernet/intel/ice/ice_debugfs.c @@ -606,7 +606,7 @@ void ice_debugfs_fwlog_init(struct ice_pf *pf) pf->ice_debugfs_pf_fwlog = debugfs_create_dir("fwlog", pf->ice_debugfs_pf); - if (IS_ERR(pf->ice_debugfs_pf)) + if (IS_ERR(pf->ice_debugfs_pf_fwlog)) goto err_create_module_files; fw_modules_dir = debugfs_create_dir("modules", diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index 2410aee59fb2..d132eb477551 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -2226,7 +2226,8 @@ bool ice_lag_is_switchdev_running(struct ice_pf *pf) struct ice_lag *lag = pf->lag; struct net_device *tmp_nd; - if (!ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) || !lag) + if (!ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) || + !lag || !lag->upper_netdev) return false; rcu_read_lock(); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 47311b134a7a..e6acd791bf64 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -507,9 +507,10 @@ struct ixgbe_q_vector { struct ixgbe_ring_container rx, tx; struct napi_struct napi; + struct rcu_head rcu; /* to avoid race with update stats on free */ + cpumask_t affinity_mask; int numa_node; - struct rcu_head rcu; /* to avoid race with update stats on free */ char name[IFNAMSIZ + 9]; /* for dynamic allocation of rings associated with this q_vector */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index b1aeea7c4a91..e395ef5f356e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1947,8 +1947,8 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, err = mlx5_cmd_invoke(dev, inb, outb, out, out_size, callback, context, pages_queue, token, force_polling); - if (callback) - return err; + if (callback && !err) + return 0; if (err > 0) /* Failed in FW, command didn't execute */ err = deliv_status_to_err(err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index b5c3a2a9d2a5..9560fcba643f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -18,7 +18,8 @@ enum { enum { MLX5E_TC_PRIO = 0, - MLX5E_NIC_PRIO + MLX5E_PROMISC_PRIO, + MLX5E_NIC_PRIO, }; struct mlx5e_flow_table { @@ -68,9 +69,13 @@ struct mlx5e_l2_table { MLX5_HASH_FIELD_SEL_DST_IP |\ MLX5_HASH_FIELD_SEL_IPSEC_SPI) -/* NIC prio FTS */ +/* NIC promisc FT level */ enum { MLX5E_PROMISC_FT_LEVEL, +}; + +/* NIC prio FTS */ +enum { MLX5E_VLAN_FT_LEVEL, MLX5E_L2_FT_LEVEL, MLX5E_TTC_FT_LEVEL, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c index 298bb74ec5e9..d1d629697e28 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c @@ -113,7 +113,7 @@ int mlx5e_dim_rx_change(struct mlx5e_rq *rq, bool enable) __set_bit(MLX5E_RQ_STATE_DIM, &rq->state); } else { __clear_bit(MLX5E_RQ_STATE_DIM, &rq->state); - + synchronize_net(); mlx5e_dim_disable(rq->dim); rq->dim = NULL; } @@ -140,7 +140,7 @@ int mlx5e_dim_tx_change(struct mlx5e_txqsq *sq, bool enable) __set_bit(MLX5E_SQ_STATE_DIM, &sq->state); } else { __clear_bit(MLX5E_SQ_STATE_DIM, &sq->state); - + synchronize_net(); mlx5e_dim_disable(sq->dim); sq->dim = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 04a969128161..265c4ca85f7d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -780,7 +780,7 @@ static int mlx5e_create_promisc_table(struct mlx5e_flow_steering *fs) ft_attr.max_fte = MLX5E_PROMISC_TABLE_SIZE; ft_attr.autogroup.max_num_groups = 1; ft_attr.level = MLX5E_PROMISC_FT_LEVEL; - ft_attr.prio = MLX5E_NIC_PRIO; + ft_attr.prio = MLX5E_PROMISC_PRIO; ft->t = mlx5_create_auto_grouped_flow_table(fs->ns, &ft_attr); if (IS_ERR(ft->t)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 84b1ab8233b8..7462514c7f3d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1154,8 +1154,9 @@ static void mlx5e_lro_update_tcp_hdr(struct mlx5_cqe64 *cqe, struct tcphdr *tcp) } } -static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe, - u32 cqe_bcnt) +static unsigned int mlx5e_lro_update_hdr(struct sk_buff *skb, + struct mlx5_cqe64 *cqe, + u32 cqe_bcnt) { struct ethhdr *eth = (struct ethhdr *)(skb->data); struct tcphdr *tcp; @@ -1205,6 +1206,8 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe, tcp->check = tcp_v6_check(payload_len, &ipv6->saddr, &ipv6->daddr, check); } + + return (unsigned int)((unsigned char *)tcp + tcp->doff * 4 - skb->data); } static void *mlx5e_shampo_get_packet_hd(struct mlx5e_rq *rq, u16 header_index) @@ -1561,8 +1564,9 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, mlx5e_macsec_offload_handle_rx_skb(netdev, skb, cqe); if (lro_num_seg > 1) { - mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt); - skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg); + unsigned int hdrlen = mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt); + + skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt - hdrlen, lro_num_seg); /* Subtract one since we already counted this as one * "regular" packet in mlx5e_complete_rx_cqe() */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index b6ae384396b3..ad9f6fca9b6a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -1076,6 +1076,7 @@ static int esw_qos_vports_node_update_parent(struct mlx5_esw_sched_node *node, return err; } esw_qos_node_set_parent(node, parent); + node->bw_share = 0; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 0e3a977d5332..bee906661282 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1182,19 +1182,19 @@ static void esw_set_peer_miss_rule_source_port(struct mlx5_eswitch *esw, static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, struct mlx5_core_dev *peer_dev) { + struct mlx5_eswitch *peer_esw = peer_dev->priv.eswitch; struct mlx5_flow_destination dest = {}; struct mlx5_flow_act flow_act = {0}; struct mlx5_flow_handle **flows; - /* total vports is the same for both e-switches */ - int nvports = esw->total_vports; struct mlx5_flow_handle *flow; + struct mlx5_vport *peer_vport; struct mlx5_flow_spec *spec; - struct mlx5_vport *vport; int err, pfindex; unsigned long i; void *misc; - if (!MLX5_VPORT_MANAGER(esw->dev) && !mlx5_core_is_ecpf_esw_manager(esw->dev)) + if (!MLX5_VPORT_MANAGER(peer_dev) && + !mlx5_core_is_ecpf_esw_manager(peer_dev)) return 0; spec = kvzalloc(sizeof(*spec), GFP_KERNEL); @@ -1203,7 +1203,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, peer_miss_rules_setup(esw, peer_dev, spec, &dest); - flows = kvcalloc(nvports, sizeof(*flows), GFP_KERNEL); + flows = kvcalloc(peer_esw->total_vports, sizeof(*flows), GFP_KERNEL); if (!flows) { err = -ENOMEM; goto alloc_flows_err; @@ -1213,10 +1213,10 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); - if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); - esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch, - spec, MLX5_VPORT_PF); + if (mlx5_core_is_ecpf_esw_manager(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF); + esw_set_peer_miss_rule_source_port(esw, peer_esw, spec, + MLX5_VPORT_PF); flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), spec, &flow_act, &dest, 1); @@ -1224,11 +1224,11 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, err = PTR_ERR(flow); goto add_pf_flow_err; } - flows[vport->index] = flow; + flows[peer_vport->index] = flow; } - if (mlx5_ecpf_vport_exists(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); + if (mlx5_ecpf_vport_exists(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_ECPF); MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_ECPF); flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), spec, &flow_act, &dest, 1); @@ -1236,13 +1236,14 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, err = PTR_ERR(flow); goto add_ecpf_flow_err; } - flows[vport->index] = flow; + flows[peer_vport->index] = flow; } - mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) { + mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_vfs(peer_dev)) { esw_set_peer_miss_rule_source_port(esw, - peer_dev->priv.eswitch, - spec, vport->vport); + peer_esw, + spec, peer_vport->vport); flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), spec, &flow_act, &dest, 1); @@ -1250,22 +1251,22 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, err = PTR_ERR(flow); goto add_vf_flow_err; } - flows[vport->index] = flow; + flows[peer_vport->index] = flow; } - if (mlx5_core_ec_sriov_enabled(esw->dev)) { - mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) { - if (i >= mlx5_core_max_ec_vfs(peer_dev)) - break; - esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch, - spec, vport->vport); + if (mlx5_core_ec_sriov_enabled(peer_dev)) { + mlx5_esw_for_each_ec_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_ec_vfs(peer_dev)) { + esw_set_peer_miss_rule_source_port(esw, peer_esw, + spec, + peer_vport->vport); flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec, &flow_act, &dest, 1); if (IS_ERR(flow)) { err = PTR_ERR(flow); goto add_ec_vf_flow_err; } - flows[vport->index] = flow; + flows[peer_vport->index] = flow; } } @@ -1282,25 +1283,27 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, return 0; add_ec_vf_flow_err: - mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) { - if (!flows[vport->index]) + mlx5_esw_for_each_ec_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_ec_vfs(peer_dev)) { + if (!flows[peer_vport->index]) continue; - mlx5_del_flow_rules(flows[vport->index]); + mlx5_del_flow_rules(flows[peer_vport->index]); } add_vf_flow_err: - mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) { - if (!flows[vport->index]) + mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_vfs(peer_dev)) { + if (!flows[peer_vport->index]) continue; - mlx5_del_flow_rules(flows[vport->index]); + mlx5_del_flow_rules(flows[peer_vport->index]); } - if (mlx5_ecpf_vport_exists(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); - mlx5_del_flow_rules(flows[vport->index]); + if (mlx5_ecpf_vport_exists(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_ECPF); + mlx5_del_flow_rules(flows[peer_vport->index]); } add_ecpf_flow_err: - if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); - mlx5_del_flow_rules(flows[vport->index]); + if (mlx5_core_is_ecpf_esw_manager(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF); + mlx5_del_flow_rules(flows[peer_vport->index]); } add_pf_flow_err: esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err); @@ -1313,37 +1316,34 @@ alloc_flows_err: static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw, struct mlx5_core_dev *peer_dev) { + struct mlx5_eswitch *peer_esw = peer_dev->priv.eswitch; u16 peer_index = mlx5_get_dev_index(peer_dev); struct mlx5_flow_handle **flows; - struct mlx5_vport *vport; + struct mlx5_vport *peer_vport; unsigned long i; flows = esw->fdb_table.offloads.peer_miss_rules[peer_index]; if (!flows) return; - if (mlx5_core_ec_sriov_enabled(esw->dev)) { - mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) { - /* The flow for a particular vport could be NULL if the other ECPF - * has fewer or no VFs enabled - */ - if (!flows[vport->index]) - continue; - mlx5_del_flow_rules(flows[vport->index]); - } + if (mlx5_core_ec_sriov_enabled(peer_dev)) { + mlx5_esw_for_each_ec_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_ec_vfs(peer_dev)) + mlx5_del_flow_rules(flows[peer_vport->index]); } - mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) - mlx5_del_flow_rules(flows[vport->index]); + mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_vfs(peer_dev)) + mlx5_del_flow_rules(flows[peer_vport->index]); - if (mlx5_ecpf_vport_exists(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); - mlx5_del_flow_rules(flows[vport->index]); + if (mlx5_ecpf_vport_exists(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_ECPF); + mlx5_del_flow_rules(flows[peer_vport->index]); } - if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); - mlx5_del_flow_rules(flows[vport->index]); + if (mlx5_core_is_ecpf_esw_manager(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF); + mlx5_del_flow_rules(flows[peer_vport->index]); } kvfree(flows); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index a8046200d376..3dd9a6f40709 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -113,13 +113,16 @@ #define ETHTOOL_PRIO_NUM_LEVELS 1 #define ETHTOOL_NUM_PRIOS 11 #define ETHTOOL_MIN_LEVEL (KERNEL_MIN_LEVEL + ETHTOOL_NUM_PRIOS) -/* Promiscuous, Vlan, mac, ttc, inner ttc, {UDP/ANY/aRFS/accel/{esp, esp_err}}, IPsec policy, +/* Vlan, mac, ttc, inner ttc, {UDP/ANY/aRFS/accel/{esp, esp_err}}, IPsec policy, * {IPsec RoCE MPV,Alias table},IPsec RoCE policy */ -#define KERNEL_NIC_PRIO_NUM_LEVELS 11 +#define KERNEL_NIC_PRIO_NUM_LEVELS 10 #define KERNEL_NIC_NUM_PRIOS 1 -/* One more level for tc */ -#define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 1) +/* One more level for tc, and one more for promisc */ +#define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 2) + +#define KERNEL_NIC_PROMISC_NUM_PRIOS 1 +#define KERNEL_NIC_PROMISC_NUM_LEVELS 1 #define KERNEL_NIC_TC_NUM_PRIOS 1 #define KERNEL_NIC_TC_NUM_LEVELS 3 @@ -187,6 +190,8 @@ static struct init_tree_node { ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, ADD_MULTIPLE_PRIO(KERNEL_NIC_TC_NUM_PRIOS, KERNEL_NIC_TC_NUM_LEVELS), + ADD_MULTIPLE_PRIO(KERNEL_NIC_PROMISC_NUM_PRIOS, + KERNEL_NIC_PROMISC_NUM_LEVELS), ADD_MULTIPLE_PRIO(KERNEL_NIC_NUM_PRIOS, KERNEL_NIC_PRIO_NUM_LEVELS))), ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0, FS_CHAINING_CAPS, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 41e8660c819c..9c1504d29d34 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -2257,6 +2257,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x1021) }, /* ConnectX-7 */ { PCI_VDEVICE(MELLANOX, 0x1023) }, /* ConnectX-8 */ { PCI_VDEVICE(MELLANOX, 0x1025) }, /* ConnectX-9 */ + { PCI_VDEVICE(MELLANOX, 0x1027) }, /* ConnectX-10 */ { PCI_VDEVICE(MELLANOX, 0xa2d2) }, /* BlueField integrated ConnectX-5 network controller */ { PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF}, /* BlueField integrated ConnectX-5 network controller VF */ { PCI_VDEVICE(MELLANOX, 0xa2d6) }, /* BlueField-2 integrated ConnectX-6 Dx network controller */ diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 52cf7112762c..58f8ee710912 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -6,6 +6,7 @@ #include <linux/pci.h> #include <linux/utsname.h> #include <linux/version.h> +#include <linux/export.h> #include <net/mana/mana.h> diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index ccd2885c939e..faad1cb880f8 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -10,6 +10,7 @@ #include <linux/filter.h> #include <linux/mm.h> #include <linux/pci.h> +#include <linux/export.h> #include <net/checksum.h> #include <net/ip6_checksum.h> diff --git a/drivers/net/ethernet/renesas/rtsn.c b/drivers/net/ethernet/renesas/rtsn.c index 6b3f7fca8d15..05c4b6c8c9c3 100644 --- a/drivers/net/ethernet/renesas/rtsn.c +++ b/drivers/net/ethernet/renesas/rtsn.c @@ -1259,7 +1259,12 @@ static int rtsn_probe(struct platform_device *pdev) priv = netdev_priv(ndev); priv->pdev = pdev; priv->ndev = ndev; + priv->ptp_priv = rcar_gen4_ptp_alloc(pdev); + if (!priv->ptp_priv) { + ret = -ENOMEM; + goto error_free; + } spin_lock_init(&priv->lock); platform_set_drvdata(pdev, priv); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 9a47015254bb..ea33ae39be6b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -433,6 +433,12 @@ static int intel_crosststamp(ktime_t *device, return -ETIMEDOUT; } + *system = (struct system_counterval_t) { + .cycles = 0, + .cs_id = CSID_X86_ART, + .use_nsecs = false, + }; + num_snapshot = (readl(ioaddr + GMAC_TIMESTAMP_STATUS) & GMAC_TIMESTAMP_ATSNS_MASK) >> GMAC_TIMESTAMP_ATSNS_SHIFT; @@ -448,7 +454,7 @@ static int intel_crosststamp(ktime_t *device, } system->cycles *= intel_priv->crossts_adj; - system->cs_id = CSID_X86_ART; + priv->plat->flags &= ~STMMAC_FLAG_INT_SNAPSHOT_EN; return 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index 7840bc403788..5dcc95bc0ad2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -364,19 +364,17 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv, } /* TX/RX NORMAL interrupts */ - if (likely(intr_status & XGMAC_NIS)) { - if (likely(intr_status & XGMAC_RI)) { - u64_stats_update_begin(&stats->syncp); - u64_stats_inc(&stats->rx_normal_irq_n[chan]); - u64_stats_update_end(&stats->syncp); - ret |= handle_rx; - } - if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) { - u64_stats_update_begin(&stats->syncp); - u64_stats_inc(&stats->tx_normal_irq_n[chan]); - u64_stats_update_end(&stats->syncp); - ret |= handle_tx; - } + if (likely(intr_status & XGMAC_RI)) { + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->rx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); + ret |= handle_rx; + } + if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) { + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->tx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); + ret |= handle_tx; } /* Clear interrupts */ diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index f20d1ff192ef..231ca141331f 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -856,8 +856,6 @@ static struct sk_buff *am65_cpsw_build_skb(void *page_addr, { struct sk_buff *skb; - len += AM65_CPSW_HEADROOM; - skb = build_skb(page_addr, len); if (unlikely(!skb)) return NULL; @@ -1344,7 +1342,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow, } skb = am65_cpsw_build_skb(page_addr, ndev, - AM65_CPSW_MAX_PACKET_SIZE, headroom); + PAGE_SIZE, headroom); if (unlikely(!skb)) { new_page = page; goto requeue; diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c index ddfd1c02a885..da53eb04b0a4 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.c +++ b/drivers/net/ethernet/ti/icssg/icssg_config.c @@ -288,8 +288,12 @@ static int prueth_fw_offload_buffer_setup(struct prueth_emac *emac) int i; addr = lower_32_bits(prueth->msmcram.pa); - if (slice) - addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE; + if (slice) { + if (prueth->pdata.banked_ms_ram) + addr += MSMC_RAM_BANK_SIZE; + else + addr += PRUETH_SW_TOTAL_BUF_SIZE_PER_SLICE; + } if (addr % SZ_64K) { dev_warn(prueth->dev, "buffer pool needs to be 64KB aligned\n"); @@ -297,43 +301,66 @@ static int prueth_fw_offload_buffer_setup(struct prueth_emac *emac) } bpool_cfg = emac->dram.va + BUFFER_POOL_0_ADDR_OFFSET; - /* workaround for f/w bug. bpool 0 needs to be initialized */ - for (i = 0; i < PRUETH_NUM_BUF_POOLS; i++) { + + /* Configure buffer pools for forwarding buffers + * - used by firmware to store packets to be forwarded to other port + * - 8 total pools per slice + */ + for (i = 0; i < PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE; i++) { writel(addr, &bpool_cfg[i].addr); - writel(PRUETH_EMAC_BUF_POOL_SIZE, &bpool_cfg[i].len); - addr += PRUETH_EMAC_BUF_POOL_SIZE; + writel(PRUETH_SW_FWD_BUF_POOL_SIZE, &bpool_cfg[i].len); + addr += PRUETH_SW_FWD_BUF_POOL_SIZE; } - if (!slice) - addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE; - else - addr += PRUETH_SW_NUM_BUF_POOLS_HOST * PRUETH_SW_BUF_POOL_SIZE_HOST; - - for (i = PRUETH_NUM_BUF_POOLS; - i < 2 * PRUETH_SW_NUM_BUF_POOLS_HOST + PRUETH_NUM_BUF_POOLS; - i++) { - /* The driver only uses first 4 queues per PRU so only initialize them */ - if (i % PRUETH_SW_NUM_BUF_POOLS_HOST < PRUETH_SW_NUM_BUF_POOLS_PER_PRU) { - writel(addr, &bpool_cfg[i].addr); - writel(PRUETH_SW_BUF_POOL_SIZE_HOST, &bpool_cfg[i].len); - addr += PRUETH_SW_BUF_POOL_SIZE_HOST; + /* Configure buffer pools for Local Injection buffers + * - used by firmware to store packets received from host core + * - 16 total pools per slice + */ + for (i = 0; i < PRUETH_NUM_LI_BUF_POOLS_PER_SLICE; i++) { + int cfg_idx = i + PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE; + + /* The driver only uses first 4 queues per PRU, + * so only initialize buffer for them + */ + if ((i % PRUETH_NUM_LI_BUF_POOLS_PER_PORT_PER_SLICE) + < PRUETH_SW_USED_LI_BUF_POOLS_PER_PORT_PER_SLICE) { + writel(addr, &bpool_cfg[cfg_idx].addr); + writel(PRUETH_SW_LI_BUF_POOL_SIZE, + &bpool_cfg[cfg_idx].len); + addr += PRUETH_SW_LI_BUF_POOL_SIZE; } else { - writel(0, &bpool_cfg[i].addr); - writel(0, &bpool_cfg[i].len); + writel(0, &bpool_cfg[cfg_idx].addr); + writel(0, &bpool_cfg[cfg_idx].len); } } - if (!slice) - addr += PRUETH_SW_NUM_BUF_POOLS_HOST * PRUETH_SW_BUF_POOL_SIZE_HOST; - else - addr += PRUETH_EMAC_RX_CTX_BUF_SIZE; + /* Express RX buffer queue + * - used by firmware to store express packets to be transmitted + * to the host core + */ + rxq_ctx = emac->dram.va + HOST_RX_Q_EXP_CONTEXT_OFFSET; + for (i = 0; i < 3; i++) + writel(addr, &rxq_ctx->start[i]); + + addr += PRUETH_SW_HOST_EXP_BUF_POOL_SIZE; + writel(addr, &rxq_ctx->end); + /* Pre-emptible RX buffer queue + * - used by firmware to store preemptible packets to be transmitted + * to the host core + */ rxq_ctx = emac->dram.va + HOST_RX_Q_PRE_CONTEXT_OFFSET; for (i = 0; i < 3; i++) writel(addr, &rxq_ctx->start[i]); - addr += PRUETH_EMAC_RX_CTX_BUF_SIZE; - writel(addr - SZ_2K, &rxq_ctx->end); + addr += PRUETH_SW_HOST_PRE_BUF_POOL_SIZE; + writel(addr, &rxq_ctx->end); + + /* Set pointer for default dropped packet write + * - used by firmware to temporarily store packet to be dropped + */ + rxq_ctx = emac->dram.va + DEFAULT_MSMC_Q_OFFSET; + writel(addr, &rxq_ctx->start[0]); return 0; } @@ -347,13 +374,13 @@ static int prueth_emac_buffer_setup(struct prueth_emac *emac) u32 addr; int i; - /* Layout to have 64KB aligned buffer pool - * |BPOOL0|BPOOL1|RX_CTX0|RX_CTX1| - */ - addr = lower_32_bits(prueth->msmcram.pa); - if (slice) - addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE; + if (slice) { + if (prueth->pdata.banked_ms_ram) + addr += MSMC_RAM_BANK_SIZE; + else + addr += PRUETH_EMAC_TOTAL_BUF_SIZE_PER_SLICE; + } if (addr % SZ_64K) { dev_warn(prueth->dev, "buffer pool needs to be 64KB aligned\n"); @@ -361,39 +388,66 @@ static int prueth_emac_buffer_setup(struct prueth_emac *emac) } bpool_cfg = emac->dram.va + BUFFER_POOL_0_ADDR_OFFSET; - /* workaround for f/w bug. bpool 0 needs to be initilalized */ - writel(addr, &bpool_cfg[0].addr); - writel(0, &bpool_cfg[0].len); - for (i = PRUETH_EMAC_BUF_POOL_START; - i < PRUETH_EMAC_BUF_POOL_START + PRUETH_NUM_BUF_POOLS; - i++) { - writel(addr, &bpool_cfg[i].addr); - writel(PRUETH_EMAC_BUF_POOL_SIZE, &bpool_cfg[i].len); - addr += PRUETH_EMAC_BUF_POOL_SIZE; + /* Configure buffer pools for forwarding buffers + * - in mac mode - no forwarding so initialize all pools to 0 + * - 8 total pools per slice + */ + for (i = 0; i < PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE; i++) { + writel(0, &bpool_cfg[i].addr); + writel(0, &bpool_cfg[i].len); } - if (!slice) - addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE; - else - addr += PRUETH_EMAC_RX_CTX_BUF_SIZE * 2; + /* Configure buffer pools for Local Injection buffers + * - used by firmware to store packets received from host core + * - 16 total pools per slice + */ + bpool_cfg = emac->dram.va + BUFFER_POOL_0_ADDR_OFFSET; + for (i = 0; i < PRUETH_NUM_LI_BUF_POOLS_PER_SLICE; i++) { + int cfg_idx = i + PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE; + + /* In EMAC mode, only first 4 buffers are used, + * as 1 slice needs to handle only 1 port + */ + if (i < PRUETH_EMAC_USED_LI_BUF_POOLS_PER_PORT_PER_SLICE) { + writel(addr, &bpool_cfg[cfg_idx].addr); + writel(PRUETH_EMAC_LI_BUF_POOL_SIZE, + &bpool_cfg[cfg_idx].len); + addr += PRUETH_EMAC_LI_BUF_POOL_SIZE; + } else { + writel(0, &bpool_cfg[cfg_idx].addr); + writel(0, &bpool_cfg[cfg_idx].len); + } + } - /* Pre-emptible RX buffer queue */ - rxq_ctx = emac->dram.va + HOST_RX_Q_PRE_CONTEXT_OFFSET; + /* Express RX buffer queue + * - used by firmware to store express packets to be transmitted + * to host core + */ + rxq_ctx = emac->dram.va + HOST_RX_Q_EXP_CONTEXT_OFFSET; for (i = 0; i < 3; i++) writel(addr, &rxq_ctx->start[i]); - addr += PRUETH_EMAC_RX_CTX_BUF_SIZE; + addr += PRUETH_EMAC_HOST_EXP_BUF_POOL_SIZE; writel(addr, &rxq_ctx->end); - /* Express RX buffer queue */ - rxq_ctx = emac->dram.va + HOST_RX_Q_EXP_CONTEXT_OFFSET; + /* Pre-emptible RX buffer queue + * - used by firmware to store preemptible packets to be transmitted + * to host core + */ + rxq_ctx = emac->dram.va + HOST_RX_Q_PRE_CONTEXT_OFFSET; for (i = 0; i < 3; i++) writel(addr, &rxq_ctx->start[i]); - addr += PRUETH_EMAC_RX_CTX_BUF_SIZE; + addr += PRUETH_EMAC_HOST_PRE_BUF_POOL_SIZE; writel(addr, &rxq_ctx->end); + /* Set pointer for default dropped packet write + * - used by firmware to temporarily store packet to be dropped + */ + rxq_ctx = emac->dram.va + DEFAULT_MSMC_Q_OFFSET; + writel(addr, &rxq_ctx->start[0]); + return 0; } diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h index c884e9fa099e..60d69744ffae 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.h +++ b/drivers/net/ethernet/ti/icssg/icssg_config.h @@ -26,21 +26,71 @@ struct icssg_flow_cfg { #define PRUETH_MAX_RX_FLOWS 1 /* excluding default flow */ #define PRUETH_RX_FLOW_DATA 0 -#define PRUETH_EMAC_BUF_POOL_SIZE SZ_8K -#define PRUETH_EMAC_POOLS_PER_SLICE 24 -#define PRUETH_EMAC_BUF_POOL_START 8 -#define PRUETH_NUM_BUF_POOLS 8 -#define PRUETH_EMAC_RX_CTX_BUF_SIZE SZ_16K /* per slice */ -#define MSMC_RAM_SIZE \ - (2 * (PRUETH_EMAC_BUF_POOL_SIZE * PRUETH_NUM_BUF_POOLS + \ - PRUETH_EMAC_RX_CTX_BUF_SIZE * 2)) - -#define PRUETH_SW_BUF_POOL_SIZE_HOST SZ_4K -#define PRUETH_SW_NUM_BUF_POOLS_HOST 8 -#define PRUETH_SW_NUM_BUF_POOLS_PER_PRU 4 -#define MSMC_RAM_SIZE_SWITCH_MODE \ - (MSMC_RAM_SIZE + \ - (2 * PRUETH_SW_BUF_POOL_SIZE_HOST * PRUETH_SW_NUM_BUF_POOLS_HOST)) +/* Defines for forwarding path buffer pools: + * - used by firmware to store packets to be forwarded to other port + * - 8 total pools per slice + * - only used in switch mode (as no forwarding in mac mode) + */ +#define PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE 8 +#define PRUETH_SW_FWD_BUF_POOL_SIZE (SZ_8K) + +/* Defines for local injection path buffer pools: + * - used by firmware to store packets received from host core + * - 16 total pools per slice + * - 8 pools per port per slice and each slice handles both ports + * - only 4 out of 8 pools used per port (as only 4 real QoS levels in ICSSG) + * - switch mode: 8 total pools used + * - mac mode: 4 total pools used + */ +#define PRUETH_NUM_LI_BUF_POOLS_PER_SLICE 16 +#define PRUETH_NUM_LI_BUF_POOLS_PER_PORT_PER_SLICE 8 +#define PRUETH_SW_LI_BUF_POOL_SIZE SZ_4K +#define PRUETH_SW_USED_LI_BUF_POOLS_PER_SLICE 8 +#define PRUETH_SW_USED_LI_BUF_POOLS_PER_PORT_PER_SLICE 4 +#define PRUETH_EMAC_LI_BUF_POOL_SIZE SZ_8K +#define PRUETH_EMAC_USED_LI_BUF_POOLS_PER_SLICE 4 +#define PRUETH_EMAC_USED_LI_BUF_POOLS_PER_PORT_PER_SLICE 4 + +/* Defines for host egress path - express and preemptible buffers + * - used by firmware to store express and preemptible packets + * to be transmitted to host core + * - used by both mac/switch modes + */ +#define PRUETH_SW_HOST_EXP_BUF_POOL_SIZE SZ_16K +#define PRUETH_SW_HOST_PRE_BUF_POOL_SIZE (SZ_16K - SZ_2K) +#define PRUETH_EMAC_HOST_EXP_BUF_POOL_SIZE PRUETH_SW_HOST_EXP_BUF_POOL_SIZE +#define PRUETH_EMAC_HOST_PRE_BUF_POOL_SIZE PRUETH_SW_HOST_PRE_BUF_POOL_SIZE + +/* Buffer used by firmware to temporarily store packet to be dropped */ +#define PRUETH_SW_DROP_PKT_BUF_SIZE SZ_2K +#define PRUETH_EMAC_DROP_PKT_BUF_SIZE PRUETH_SW_DROP_PKT_BUF_SIZE + +/* Total switch mode memory usage for buffers per slice */ +#define PRUETH_SW_TOTAL_BUF_SIZE_PER_SLICE \ + (PRUETH_SW_FWD_BUF_POOL_SIZE * PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE + \ + PRUETH_SW_LI_BUF_POOL_SIZE * PRUETH_SW_USED_LI_BUF_POOLS_PER_SLICE + \ + PRUETH_SW_HOST_EXP_BUF_POOL_SIZE + \ + PRUETH_SW_HOST_PRE_BUF_POOL_SIZE + \ + PRUETH_SW_DROP_PKT_BUF_SIZE) + +/* Total switch mode memory usage for all buffers */ +#define PRUETH_SW_TOTAL_BUF_SIZE \ + (2 * PRUETH_SW_TOTAL_BUF_SIZE_PER_SLICE) + +/* Total mac mode memory usage for buffers per slice */ +#define PRUETH_EMAC_TOTAL_BUF_SIZE_PER_SLICE \ + (PRUETH_EMAC_LI_BUF_POOL_SIZE * \ + PRUETH_EMAC_USED_LI_BUF_POOLS_PER_SLICE + \ + PRUETH_EMAC_HOST_EXP_BUF_POOL_SIZE + \ + PRUETH_EMAC_HOST_PRE_BUF_POOL_SIZE + \ + PRUETH_EMAC_DROP_PKT_BUF_SIZE) + +/* Total mac mode memory usage for all buffers */ +#define PRUETH_EMAC_TOTAL_BUF_SIZE \ + (2 * PRUETH_EMAC_TOTAL_BUF_SIZE_PER_SLICE) + +/* Size of 1 bank of MSMC/OC_SRAM memory */ +#define MSMC_RAM_BANK_SIZE SZ_256K #define PRUETH_SWITCH_FDB_MASK ((SIZE_OF_FDB / NUMBER_OF_FDB_BUCKET_ENTRIES) - 1) diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 86fc1278127c..2f5c4335dec3 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -1764,10 +1764,15 @@ static int prueth_probe(struct platform_device *pdev) goto put_mem; } - msmc_ram_size = MSMC_RAM_SIZE; prueth->is_switchmode_supported = prueth->pdata.switch_mode; - if (prueth->is_switchmode_supported) - msmc_ram_size = MSMC_RAM_SIZE_SWITCH_MODE; + if (prueth->pdata.banked_ms_ram) { + /* Reserve 2 MSMC RAM banks for buffers to avoid arbitration */ + msmc_ram_size = (2 * MSMC_RAM_BANK_SIZE); + } else { + msmc_ram_size = PRUETH_EMAC_TOTAL_BUF_SIZE; + if (prueth->is_switchmode_supported) + msmc_ram_size = PRUETH_SW_TOTAL_BUF_SIZE; + } /* NOTE: FW bug needs buffer base to be 64KB aligned */ prueth->msmcram.va = @@ -1924,7 +1929,8 @@ put_iep0: free_pool: gen_pool_free(prueth->sram_pool, - (unsigned long)prueth->msmcram.va, msmc_ram_size); + (unsigned long)prueth->msmcram.va, + prueth->msmcram.size); put_mem: pruss_release_mem_region(prueth->pruss, &prueth->shram); @@ -1976,8 +1982,8 @@ static void prueth_remove(struct platform_device *pdev) icss_iep_put(prueth->iep0); gen_pool_free(prueth->sram_pool, - (unsigned long)prueth->msmcram.va, - MSMC_RAM_SIZE); + (unsigned long)prueth->msmcram.va, + prueth->msmcram.size); pruss_release_mem_region(prueth->pruss, &prueth->shram); @@ -1994,12 +2000,14 @@ static const struct prueth_pdata am654_icssg_pdata = { .fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE, .quirk_10m_link_issue = 1, .switch_mode = 1, + .banked_ms_ram = 0, }; static const struct prueth_pdata am64x_icssg_pdata = { .fdqring_mode = K3_RINGACC_RING_MODE_RING, .quirk_10m_link_issue = 1, .switch_mode = 1, + .banked_ms_ram = 1, }; static const struct of_device_id prueth_dt_match[] = { diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index 23c465f1ce7f..3bb9fd8c3804 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -251,11 +251,13 @@ struct prueth_emac { * @fdqring_mode: Free desc queue mode * @quirk_10m_link_issue: 10M link detect errata * @switch_mode: switch firmware support + * @banked_ms_ram: banked memory support */ struct prueth_pdata { enum k3_ring_mode fdqring_mode; u32 quirk_10m_link_issue:1; u32 switch_mode:1; + u32 banked_ms_ram:1; }; struct icssg_firmwares { diff --git a/drivers/net/ethernet/ti/icssg/icssg_switch_map.h b/drivers/net/ethernet/ti/icssg/icssg_switch_map.h index 490a9cc06fb0..7e053b8af3ec 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_switch_map.h +++ b/drivers/net/ethernet/ti/icssg/icssg_switch_map.h @@ -180,6 +180,9 @@ /* Used to notify the FW of the current link speed */ #define PORT_LINK_SPEED_OFFSET 0x00A8 +/* 2k memory pointer reserved for default writes by PRU0*/ +#define DEFAULT_MSMC_Q_OFFSET 0x00AC + /* TAS gate mask for windows list0 */ #define TAS_GATE_MASK_LIST0 0x0100 diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index 0f4be72116b8..f0823aa1ede6 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -1912,7 +1912,6 @@ static void wx_configure_rx_ring(struct wx *wx, struct wx_ring *ring) { u16 reg_idx = ring->reg_idx; - union wx_rx_desc *rx_desc; u64 rdba = ring->dma; u32 rxdctl; @@ -1942,9 +1941,9 @@ static void wx_configure_rx_ring(struct wx *wx, memset(ring->rx_buffer_info, 0, sizeof(struct wx_rx_buffer) * ring->count); - /* initialize Rx descriptor 0 */ - rx_desc = WX_RX_DESC(ring, 0); - rx_desc->wb.upper.length = 0; + /* reset ntu and ntc to place SW in sync with hardware */ + ring->next_to_clean = 0; + ring->next_to_use = 0; /* enable receive descriptor ring */ wr32m(wx, WX_PX_RR_CFG(reg_idx), @@ -2778,6 +2777,8 @@ void wx_update_stats(struct wx *wx) hwstats->fdirmiss += rd32(wx, WX_RDB_FDIR_MISS); } + /* qmprc is not cleared on read, manual reset it */ + hwstats->qmprc = 0; for (i = wx->num_vfs * wx->num_rx_queues_per_pool; i < wx->mac.max_rx_queues; i++) hwstats->qmprc += rd32(wx, WX_PX_MPRC(i)); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index 55e252789db3..0213ad5a6ceb 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -174,10 +174,6 @@ static void wx_dma_sync_frag(struct wx_ring *rx_ring, skb_frag_off(frag), skb_frag_size(frag), DMA_FROM_DEVICE); - - /* If the page was released, just unmap it. */ - if (unlikely(WX_CB(skb)->page_released)) - page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false); } static struct wx_rx_buffer *wx_get_rx_buffer(struct wx_ring *rx_ring, @@ -227,10 +223,6 @@ static void wx_put_rx_buffer(struct wx_ring *rx_ring, struct sk_buff *skb, int rx_buffer_pgcnt) { - if (!IS_ERR(skb) && WX_CB(skb)->dma == rx_buffer->dma) - /* the page has been released from the ring */ - WX_CB(skb)->page_released = true; - /* clear contents of rx_buffer */ rx_buffer->page = NULL; rx_buffer->skb = NULL; @@ -315,7 +307,7 @@ static bool wx_alloc_mapped_page(struct wx_ring *rx_ring, return false; dma = page_pool_get_dma_addr(page); - bi->page_dma = dma; + bi->dma = dma; bi->page = page; bi->page_offset = 0; @@ -352,7 +344,7 @@ void wx_alloc_rx_buffers(struct wx_ring *rx_ring, u16 cleaned_count) DMA_FROM_DEVICE); rx_desc->read.pkt_addr = - cpu_to_le64(bi->page_dma + bi->page_offset); + cpu_to_le64(bi->dma + bi->page_offset); rx_desc++; bi++; @@ -365,6 +357,8 @@ void wx_alloc_rx_buffers(struct wx_ring *rx_ring, u16 cleaned_count) /* clear the status bits for the next_to_use descriptor */ rx_desc->wb.upper.status_error = 0; + /* clear the length for the next_to_use descriptor */ + rx_desc->wb.upper.length = 0; cleaned_count--; } while (cleaned_count); @@ -2423,9 +2417,6 @@ static void wx_clean_rx_ring(struct wx_ring *rx_ring) if (rx_buffer->skb) { struct sk_buff *skb = rx_buffer->skb; - if (WX_CB(skb)->page_released) - page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false); - dev_kfree_skb(skb); } @@ -2449,6 +2440,9 @@ static void wx_clean_rx_ring(struct wx_ring *rx_ring) } } + /* Zero out the descriptor ring */ + memset(rx_ring->desc, 0, rx_ring->size); + rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h index c363379126c0..1a90fcede86b 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_type.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h @@ -909,7 +909,6 @@ enum wx_reset_type { struct wx_cb { dma_addr_t dma; u16 append_cnt; /* number of skb's appended */ - bool page_released; bool dma_released; }; @@ -998,7 +997,6 @@ struct wx_tx_buffer { struct wx_rx_buffer { struct sk_buff *skb; dma_addr_t dma; - dma_addr_t page_dma; struct page *page; unsigned int page_offset; }; diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index edb36ff07a0c..6f82203a414c 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1309,7 +1309,7 @@ ll_temac_ethtools_set_ringparam(struct net_device *ndev, if (ering->rx_pending > RX_BD_NUM_MAX || ering->rx_mini_pending || ering->rx_jumbo_pending || - ering->rx_pending > TX_BD_NUM_MAX) + ering->tx_pending > TX_BD_NUM_MAX) return -EINVAL; if (netif_running(ndev)) diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index ecf47107146d..4719d40a63ba 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -286,7 +286,7 @@ static void xemaclite_aligned_read(u32 *src_ptr, u8 *dest_ptr, /* Read the remaining data */ for (; length > 0; length--) - *to_u8_ptr = *from_u8_ptr; + *to_u8_ptr++ = *from_u8_ptr++; } } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index c41a025c66f0..8be9bce66a4e 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2317,8 +2317,11 @@ static int netvsc_prepare_bonding(struct net_device *vf_netdev) if (!ndev) return NOTIFY_DONE; - /* set slave flag before open to prevent IPv6 addrconf */ + /* Set slave flag and no addrconf flag before open + * to prevent IPv6 addrconf. + */ vf_netdev->flags |= IFF_SLAVE; + vf_netdev->priv_flags |= IFF_NO_ADDRCONF; return NOTIFY_DONE; } diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c index ebf1e849506b..3e9e7f8444b3 100644 --- a/drivers/net/ovpn/io.c +++ b/drivers/net/ovpn/io.c @@ -62,6 +62,13 @@ static void ovpn_netdev_write(struct ovpn_peer *peer, struct sk_buff *skb) unsigned int pkt_len; int ret; + /* + * GSO state from the transport layer is not valid for the tunnel/data + * path. Reset all GSO fields to prevent any further GSO processing + * from entering an inconsistent state. + */ + skb_gso_reset(skb); + /* we can't guarantee the packet wasn't corrupted before entering the * VPN, therefore we give other layers a chance to check that */ diff --git a/drivers/net/ovpn/netlink-gen.c b/drivers/net/ovpn/netlink-gen.c index 58e1a4342378..14298188c5f1 100644 --- a/drivers/net/ovpn/netlink-gen.c +++ b/drivers/net/ovpn/netlink-gen.c @@ -29,6 +29,22 @@ const struct nla_policy ovpn_keyconf_nl_policy[OVPN_A_KEYCONF_DECRYPT_DIR + 1] = [OVPN_A_KEYCONF_DECRYPT_DIR] = NLA_POLICY_NESTED(ovpn_keydir_nl_policy), }; +const struct nla_policy ovpn_keyconf_del_input_nl_policy[OVPN_A_KEYCONF_SLOT + 1] = { + [OVPN_A_KEYCONF_PEER_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_keyconf_peer_id_range), + [OVPN_A_KEYCONF_SLOT] = NLA_POLICY_MAX(NLA_U32, 1), +}; + +const struct nla_policy ovpn_keyconf_get_nl_policy[OVPN_A_KEYCONF_CIPHER_ALG + 1] = { + [OVPN_A_KEYCONF_PEER_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_keyconf_peer_id_range), + [OVPN_A_KEYCONF_SLOT] = NLA_POLICY_MAX(NLA_U32, 1), + [OVPN_A_KEYCONF_KEY_ID] = NLA_POLICY_MAX(NLA_U32, 7), + [OVPN_A_KEYCONF_CIPHER_ALG] = NLA_POLICY_MAX(NLA_U32, 2), +}; + +const struct nla_policy ovpn_keyconf_swap_input_nl_policy[OVPN_A_KEYCONF_PEER_ID + 1] = { + [OVPN_A_KEYCONF_PEER_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_keyconf_peer_id_range), +}; + const struct nla_policy ovpn_keydir_nl_policy[OVPN_A_KEYDIR_NONCE_TAIL + 1] = { [OVPN_A_KEYDIR_CIPHER_KEY] = NLA_POLICY_MAX_LEN(256), [OVPN_A_KEYDIR_NONCE_TAIL] = NLA_POLICY_EXACT_LEN(OVPN_NONCE_TAIL_SIZE), @@ -60,16 +76,49 @@ const struct nla_policy ovpn_peer_nl_policy[OVPN_A_PEER_LINK_TX_PACKETS + 1] = { [OVPN_A_PEER_LINK_TX_PACKETS] = { .type = NLA_UINT, }, }; +const struct nla_policy ovpn_peer_del_input_nl_policy[OVPN_A_PEER_ID + 1] = { + [OVPN_A_PEER_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_peer_id_range), +}; + +const struct nla_policy ovpn_peer_new_input_nl_policy[OVPN_A_PEER_KEEPALIVE_TIMEOUT + 1] = { + [OVPN_A_PEER_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_peer_id_range), + [OVPN_A_PEER_REMOTE_IPV4] = { .type = NLA_BE32, }, + [OVPN_A_PEER_REMOTE_IPV6] = NLA_POLICY_EXACT_LEN(16), + [OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID] = { .type = NLA_U32, }, + [OVPN_A_PEER_REMOTE_PORT] = NLA_POLICY_MIN(NLA_BE16, 1), + [OVPN_A_PEER_SOCKET] = { .type = NLA_U32, }, + [OVPN_A_PEER_VPN_IPV4] = { .type = NLA_BE32, }, + [OVPN_A_PEER_VPN_IPV6] = NLA_POLICY_EXACT_LEN(16), + [OVPN_A_PEER_LOCAL_IPV4] = { .type = NLA_BE32, }, + [OVPN_A_PEER_LOCAL_IPV6] = NLA_POLICY_EXACT_LEN(16), + [OVPN_A_PEER_KEEPALIVE_INTERVAL] = { .type = NLA_U32, }, + [OVPN_A_PEER_KEEPALIVE_TIMEOUT] = { .type = NLA_U32, }, +}; + +const struct nla_policy ovpn_peer_set_input_nl_policy[OVPN_A_PEER_KEEPALIVE_TIMEOUT + 1] = { + [OVPN_A_PEER_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_peer_id_range), + [OVPN_A_PEER_REMOTE_IPV4] = { .type = NLA_BE32, }, + [OVPN_A_PEER_REMOTE_IPV6] = NLA_POLICY_EXACT_LEN(16), + [OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID] = { .type = NLA_U32, }, + [OVPN_A_PEER_REMOTE_PORT] = NLA_POLICY_MIN(NLA_BE16, 1), + [OVPN_A_PEER_VPN_IPV4] = { .type = NLA_BE32, }, + [OVPN_A_PEER_VPN_IPV6] = NLA_POLICY_EXACT_LEN(16), + [OVPN_A_PEER_LOCAL_IPV4] = { .type = NLA_BE32, }, + [OVPN_A_PEER_LOCAL_IPV6] = NLA_POLICY_EXACT_LEN(16), + [OVPN_A_PEER_KEEPALIVE_INTERVAL] = { .type = NLA_U32, }, + [OVPN_A_PEER_KEEPALIVE_TIMEOUT] = { .type = NLA_U32, }, +}; + /* OVPN_CMD_PEER_NEW - do */ static const struct nla_policy ovpn_peer_new_nl_policy[OVPN_A_PEER + 1] = { [OVPN_A_IFINDEX] = { .type = NLA_U32, }, - [OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy), + [OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_new_input_nl_policy), }; /* OVPN_CMD_PEER_SET - do */ static const struct nla_policy ovpn_peer_set_nl_policy[OVPN_A_PEER + 1] = { [OVPN_A_IFINDEX] = { .type = NLA_U32, }, - [OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy), + [OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_set_input_nl_policy), }; /* OVPN_CMD_PEER_GET - do */ @@ -86,7 +135,7 @@ static const struct nla_policy ovpn_peer_get_dump_nl_policy[OVPN_A_IFINDEX + 1] /* OVPN_CMD_PEER_DEL - do */ static const struct nla_policy ovpn_peer_del_nl_policy[OVPN_A_PEER + 1] = { [OVPN_A_IFINDEX] = { .type = NLA_U32, }, - [OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy), + [OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_del_input_nl_policy), }; /* OVPN_CMD_KEY_NEW - do */ @@ -98,19 +147,19 @@ static const struct nla_policy ovpn_key_new_nl_policy[OVPN_A_KEYCONF + 1] = { /* OVPN_CMD_KEY_GET - do */ static const struct nla_policy ovpn_key_get_nl_policy[OVPN_A_KEYCONF + 1] = { [OVPN_A_IFINDEX] = { .type = NLA_U32, }, - [OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy), + [OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_get_nl_policy), }; /* OVPN_CMD_KEY_SWAP - do */ static const struct nla_policy ovpn_key_swap_nl_policy[OVPN_A_KEYCONF + 1] = { [OVPN_A_IFINDEX] = { .type = NLA_U32, }, - [OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy), + [OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_swap_input_nl_policy), }; /* OVPN_CMD_KEY_DEL - do */ static const struct nla_policy ovpn_key_del_nl_policy[OVPN_A_KEYCONF + 1] = { [OVPN_A_IFINDEX] = { .type = NLA_U32, }, - [OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy), + [OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_del_input_nl_policy), }; /* Ops table for ovpn */ diff --git a/drivers/net/ovpn/netlink-gen.h b/drivers/net/ovpn/netlink-gen.h index 66a4e4a0a055..220b5b2fdd4f 100644 --- a/drivers/net/ovpn/netlink-gen.h +++ b/drivers/net/ovpn/netlink-gen.h @@ -13,8 +13,14 @@ /* Common nested types */ extern const struct nla_policy ovpn_keyconf_nl_policy[OVPN_A_KEYCONF_DECRYPT_DIR + 1]; +extern const struct nla_policy ovpn_keyconf_del_input_nl_policy[OVPN_A_KEYCONF_SLOT + 1]; +extern const struct nla_policy ovpn_keyconf_get_nl_policy[OVPN_A_KEYCONF_CIPHER_ALG + 1]; +extern const struct nla_policy ovpn_keyconf_swap_input_nl_policy[OVPN_A_KEYCONF_PEER_ID + 1]; extern const struct nla_policy ovpn_keydir_nl_policy[OVPN_A_KEYDIR_NONCE_TAIL + 1]; extern const struct nla_policy ovpn_peer_nl_policy[OVPN_A_PEER_LINK_TX_PACKETS + 1]; +extern const struct nla_policy ovpn_peer_del_input_nl_policy[OVPN_A_PEER_ID + 1]; +extern const struct nla_policy ovpn_peer_new_input_nl_policy[OVPN_A_PEER_KEEPALIVE_TIMEOUT + 1]; +extern const struct nla_policy ovpn_peer_set_input_nl_policy[OVPN_A_PEER_KEEPALIVE_TIMEOUT + 1]; int ovpn_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); diff --git a/drivers/net/ovpn/netlink.c b/drivers/net/ovpn/netlink.c index a4ec53def46e..c7f382437630 100644 --- a/drivers/net/ovpn/netlink.c +++ b/drivers/net/ovpn/netlink.c @@ -352,7 +352,7 @@ int ovpn_nl_peer_new_doit(struct sk_buff *skb, struct genl_info *info) return -EINVAL; ret = nla_parse_nested(attrs, OVPN_A_PEER_MAX, info->attrs[OVPN_A_PEER], - ovpn_peer_nl_policy, info->extack); + ovpn_peer_new_input_nl_policy, info->extack); if (ret) return ret; @@ -476,7 +476,7 @@ int ovpn_nl_peer_set_doit(struct sk_buff *skb, struct genl_info *info) return -EINVAL; ret = nla_parse_nested(attrs, OVPN_A_PEER_MAX, info->attrs[OVPN_A_PEER], - ovpn_peer_nl_policy, info->extack); + ovpn_peer_set_input_nl_policy, info->extack); if (ret) return ret; @@ -654,7 +654,7 @@ int ovpn_nl_peer_get_doit(struct sk_buff *skb, struct genl_info *info) struct ovpn_peer *peer; struct sk_buff *msg; u32 peer_id; - int ret; + int ret, i; if (GENL_REQ_ATTR_CHECK(info, OVPN_A_PEER)) return -EINVAL; @@ -668,6 +668,23 @@ int ovpn_nl_peer_get_doit(struct sk_buff *skb, struct genl_info *info) OVPN_A_PEER_ID)) return -EINVAL; + /* OVPN_CMD_PEER_GET expects only the PEER_ID, therefore + * ensure that the user hasn't specified any other attribute. + * + * Unfortunately this check cannot be performed via netlink + * spec/policy and must be open-coded. + */ + for (i = 0; i < OVPN_A_PEER_MAX + 1; i++) { + if (i == OVPN_A_PEER_ID) + continue; + + if (attrs[i]) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "unexpected attribute %u", i); + return -EINVAL; + } + } + peer_id = nla_get_u32(attrs[OVPN_A_PEER_ID]); peer = ovpn_peer_get_by_id(ovpn, peer_id); if (!peer) { @@ -768,7 +785,7 @@ int ovpn_nl_peer_del_doit(struct sk_buff *skb, struct genl_info *info) return -EINVAL; ret = nla_parse_nested(attrs, OVPN_A_PEER_MAX, info->attrs[OVPN_A_PEER], - ovpn_peer_nl_policy, info->extack); + ovpn_peer_del_input_nl_policy, info->extack); if (ret) return ret; @@ -969,14 +986,14 @@ int ovpn_nl_key_get_doit(struct sk_buff *skb, struct genl_info *info) struct ovpn_peer *peer; struct sk_buff *msg; u32 peer_id; - int ret; + int ret, i; if (GENL_REQ_ATTR_CHECK(info, OVPN_A_KEYCONF)) return -EINVAL; ret = nla_parse_nested(attrs, OVPN_A_KEYCONF_MAX, info->attrs[OVPN_A_KEYCONF], - ovpn_keyconf_nl_policy, info->extack); + ovpn_keyconf_get_nl_policy, info->extack); if (ret) return ret; @@ -988,6 +1005,24 @@ int ovpn_nl_key_get_doit(struct sk_buff *skb, struct genl_info *info) OVPN_A_KEYCONF_SLOT)) return -EINVAL; + /* OVPN_CMD_KEY_GET expects only the PEER_ID and the SLOT, therefore + * ensure that the user hasn't specified any other attribute. + * + * Unfortunately this check cannot be performed via netlink + * spec/policy and must be open-coded. + */ + for (i = 0; i < OVPN_A_KEYCONF_MAX + 1; i++) { + if (i == OVPN_A_KEYCONF_PEER_ID || + i == OVPN_A_KEYCONF_SLOT) + continue; + + if (attrs[i]) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "unexpected attribute %u", i); + return -EINVAL; + } + } + peer_id = nla_get_u32(attrs[OVPN_A_KEYCONF_PEER_ID]); peer = ovpn_peer_get_by_id(ovpn, peer_id); if (!peer) { @@ -1037,7 +1072,7 @@ int ovpn_nl_key_swap_doit(struct sk_buff *skb, struct genl_info *info) ret = nla_parse_nested(attrs, OVPN_A_KEYCONF_MAX, info->attrs[OVPN_A_KEYCONF], - ovpn_keyconf_nl_policy, info->extack); + ovpn_keyconf_swap_input_nl_policy, info->extack); if (ret) return ret; @@ -1074,7 +1109,7 @@ int ovpn_nl_key_del_doit(struct sk_buff *skb, struct genl_info *info) ret = nla_parse_nested(attrs, OVPN_A_KEYCONF_MAX, info->attrs[OVPN_A_KEYCONF], - ovpn_keyconf_nl_policy, info->extack); + ovpn_keyconf_del_input_nl_policy, info->extack); if (ret) return ret; diff --git a/drivers/net/ovpn/udp.c b/drivers/net/ovpn/udp.c index bff00946eae2..60435a21f29c 100644 --- a/drivers/net/ovpn/udp.c +++ b/drivers/net/ovpn/udp.c @@ -344,6 +344,7 @@ void ovpn_udp_send_skb(struct ovpn_peer *peer, struct sock *sk, int ret; skb->dev = peer->ovpn->dev; + skb->mark = READ_ONCE(sk->sk_mark); /* no checksum performed at this layer */ skb->ip_summed = CHECKSUM_NONE; diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c index 13570f628aa5..dc8634e7bcbe 100644 --- a/drivers/net/phy/microchip.c +++ b/drivers/net/phy/microchip.c @@ -332,7 +332,7 @@ static void lan88xx_link_change_notify(struct phy_device *phydev) * As workaround, set to 10 before setting to 100 * at forced 100 F/H mode. */ - if (!phydev->autoneg && phydev->speed == 100) { + if (phydev->state == PHY_NOLINK && !phydev->autoneg && phydev->speed == 100) { /* disable phy interrupt */ temp = phy_read(phydev, LAN88XX_INT_MASK); temp &= ~LAN88XX_INT_MASK_MDINTPIN_EN_; @@ -488,6 +488,7 @@ static struct phy_driver microchip_phy_driver[] = { .config_init = lan88xx_config_init, .config_aneg = lan88xx_config_aneg, .link_change_notify = lan88xx_link_change_notify, + .soft_reset = genphy_soft_reset, /* Interrupt handling is broken, do not define related * functions to force polling. diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 73f9cb2e2844..f76ee8489504 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3416,7 +3416,8 @@ static int phy_probe(struct device *dev) /* Get the LEDs from the device tree, and instantiate standard * LEDs for them. */ - if (IS_ENABLED(CONFIG_PHYLIB_LEDS)) + if (IS_ENABLED(CONFIG_PHYLIB_LEDS) && !phy_driver_is_genphy(phydev) && + !phy_driver_is_genphy_10g(phydev)) err = of_phy_leds(phydev); out: @@ -3433,7 +3434,8 @@ static int phy_remove(struct device *dev) cancel_delayed_work_sync(&phydev->state_queue); - if (IS_ENABLED(CONFIG_PHYLIB_LEDS)) + if (IS_ENABLED(CONFIG_PHYLIB_LEDS) && !phy_driver_is_genphy(phydev) && + !phy_driver_is_genphy_10g(phydev)) phy_leds_unregister(phydev); phydev->state = PHY_DOWN; diff --git a/drivers/net/phy/qcom/at803x.c b/drivers/net/phy/qcom/at803x.c index 26350b962890..8f26e395e39f 100644 --- a/drivers/net/phy/qcom/at803x.c +++ b/drivers/net/phy/qcom/at803x.c @@ -26,9 +26,6 @@ #define AT803X_LED_CONTROL 0x18 -#define AT803X_PHY_MMD3_WOL_CTRL 0x8012 -#define AT803X_WOL_EN BIT(5) - #define AT803X_REG_CHIP_CONFIG 0x1f #define AT803X_BT_BX_REG_SEL 0x8000 @@ -866,30 +863,6 @@ static int at8031_config_init(struct phy_device *phydev) return at803x_config_init(phydev); } -static int at8031_set_wol(struct phy_device *phydev, - struct ethtool_wolinfo *wol) -{ - int ret; - - /* First setup MAC address and enable WOL interrupt */ - ret = at803x_set_wol(phydev, wol); - if (ret) - return ret; - - if (wol->wolopts & WAKE_MAGIC) - /* Enable WOL function for 1588 */ - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, - AT803X_PHY_MMD3_WOL_CTRL, - 0, AT803X_WOL_EN); - else - /* Disable WoL function for 1588 */ - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, - AT803X_PHY_MMD3_WOL_CTRL, - AT803X_WOL_EN, 0); - - return ret; -} - static int at8031_config_intr(struct phy_device *phydev) { struct at803x_priv *priv = phydev->priv; diff --git a/drivers/net/phy/qcom/qca808x.c b/drivers/net/phy/qcom/qca808x.c index 71498c518f0f..6de16c0eaa08 100644 --- a/drivers/net/phy/qcom/qca808x.c +++ b/drivers/net/phy/qcom/qca808x.c @@ -633,7 +633,7 @@ static struct phy_driver qca808x_driver[] = { .handle_interrupt = at803x_handle_interrupt, .get_tunable = at803x_get_tunable, .set_tunable = at803x_set_tunable, - .set_wol = at803x_set_wol, + .set_wol = at8031_set_wol, .get_wol = at803x_get_wol, .get_features = qca808x_get_features, .config_aneg = qca808x_config_aneg, diff --git a/drivers/net/phy/qcom/qcom-phy-lib.c b/drivers/net/phy/qcom/qcom-phy-lib.c index d28815ef56bb..af7d0d8e81be 100644 --- a/drivers/net/phy/qcom/qcom-phy-lib.c +++ b/drivers/net/phy/qcom/qcom-phy-lib.c @@ -115,6 +115,31 @@ int at803x_set_wol(struct phy_device *phydev, } EXPORT_SYMBOL_GPL(at803x_set_wol); +int at8031_set_wol(struct phy_device *phydev, + struct ethtool_wolinfo *wol) +{ + int ret; + + /* First setup MAC address and enable WOL interrupt */ + ret = at803x_set_wol(phydev, wol); + if (ret) + return ret; + + if (wol->wolopts & WAKE_MAGIC) + /* Enable WOL function for 1588 */ + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + 0, AT803X_WOL_EN); + else + /* Disable WoL function for 1588 */ + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + AT803X_WOL_EN, 0); + + return ret; +} +EXPORT_SYMBOL_GPL(at8031_set_wol); + void at803x_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol) { diff --git a/drivers/net/phy/qcom/qcom.h b/drivers/net/phy/qcom/qcom.h index 4bb541728846..7f7151c8baca 100644 --- a/drivers/net/phy/qcom/qcom.h +++ b/drivers/net/phy/qcom/qcom.h @@ -172,6 +172,9 @@ #define AT803X_LOC_MAC_ADDR_16_31_OFFSET 0x804B #define AT803X_LOC_MAC_ADDR_32_47_OFFSET 0x804A +#define AT803X_PHY_MMD3_WOL_CTRL 0x8012 +#define AT803X_WOL_EN BIT(5) + #define AT803X_DEBUG_ADDR 0x1D #define AT803X_DEBUG_DATA 0x1E @@ -215,6 +218,8 @@ int at803x_debug_reg_mask(struct phy_device *phydev, u16 reg, int at803x_debug_reg_write(struct phy_device *phydev, u16 reg, u16 data); int at803x_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); +int at8031_set_wol(struct phy_device *phydev, + struct ethtool_wolinfo *wol); void at803x_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); int at803x_ack_interrupt(struct phy_device *phydev); diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index 31463b9e5697..b6489da5cfcd 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -155,10 +155,29 @@ static int smsc_phy_reset(struct phy_device *phydev) static int lan87xx_config_aneg(struct phy_device *phydev) { - int rc; + u8 mdix_ctrl; int val; + int rc; + + /* When auto-negotiation is disabled (forced mode), the PHY's + * Auto-MDIX will continue toggling the TX/RX pairs. + * + * To establish a stable link, we must select a fixed MDI mode. + * If the user has not specified a fixed MDI mode (i.e., mdix_ctrl is + * 'auto'), we default to ETH_TP_MDI. This choice of a ETH_TP_MDI mode + * mirrors the behavior the hardware would exhibit if the AUTOMDIX_EN + * strap were configured for a fixed MDI connection. + */ + if (phydev->autoneg == AUTONEG_DISABLE) { + if (phydev->mdix_ctrl == ETH_TP_MDI_AUTO) + mdix_ctrl = ETH_TP_MDI; + else + mdix_ctrl = phydev->mdix_ctrl; + } else { + mdix_ctrl = phydev->mdix_ctrl; + } - switch (phydev->mdix_ctrl) { + switch (mdix_ctrl) { case ETH_TP_MDI: val = SPECIAL_CTRL_STS_OVRRD_AMDIX_; break; @@ -167,7 +186,8 @@ static int lan87xx_config_aneg(struct phy_device *phydev) SPECIAL_CTRL_STS_AMDIX_STATE_; break; case ETH_TP_MDI_AUTO: - val = SPECIAL_CTRL_STS_AMDIX_ENABLE_; + val = SPECIAL_CTRL_STS_OVRRD_AMDIX_ | + SPECIAL_CTRL_STS_AMDIX_ENABLE_; break; default: return genphy_config_aneg(phydev); @@ -183,7 +203,7 @@ static int lan87xx_config_aneg(struct phy_device *phydev) rc |= val; phy_write(phydev, SPECIAL_CTRL_STS, rc); - phydev->mdix = phydev->mdix_ctrl; + phydev->mdix = mdix_ctrl; return genphy_config_aneg(phydev); } @@ -261,6 +281,33 @@ int lan87xx_read_status(struct phy_device *phydev) } EXPORT_SYMBOL_GPL(lan87xx_read_status); +static int lan87xx_phy_config_init(struct phy_device *phydev) +{ + int rc; + + /* The LAN87xx PHY's initial MDI-X mode is determined by the AUTOMDIX_EN + * hardware strap, but the driver cannot read the strap's status. This + * creates an unpredictable initial state. + * + * To ensure consistent and reliable behavior across all boards, + * override the strap configuration on initialization and force the PHY + * into a known state with Auto-MDIX enabled, which is the expected + * default for modern hardware. + */ + rc = phy_modify(phydev, SPECIAL_CTRL_STS, + SPECIAL_CTRL_STS_OVRRD_AMDIX_ | + SPECIAL_CTRL_STS_AMDIX_ENABLE_ | + SPECIAL_CTRL_STS_AMDIX_STATE_, + SPECIAL_CTRL_STS_OVRRD_AMDIX_ | + SPECIAL_CTRL_STS_AMDIX_ENABLE_); + if (rc < 0) + return rc; + + phydev->mdix_ctrl = ETH_TP_MDI_AUTO; + + return smsc_phy_config_init(phydev); +} + static int lan874x_phy_config_init(struct phy_device *phydev) { u16 val; @@ -695,7 +742,7 @@ static struct phy_driver smsc_phy_driver[] = { /* basic functions */ .read_status = lan87xx_read_status, - .config_init = smsc_phy_config_init, + .config_init = lan87xx_phy_config_init, .soft_reset = smsc_phy_reset, .config_aneg = lan87xx_config_aneg, diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c index c30ca415d1d3..36c73db44f77 100644 --- a/drivers/net/usb/sierra_net.c +++ b/drivers/net/usb/sierra_net.c @@ -689,6 +689,10 @@ static int sierra_net_bind(struct usbnet *dev, struct usb_interface *intf) status); return -ENODEV; } + if (!dev->status) { + dev_err(&dev->udev->dev, "No status endpoint found"); + return -ENODEV; + } /* Initialize sierra private data */ priv = kzalloc(sizeof *priv, GFP_KERNEL); if (!priv) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 5d674eb9a0f2..82b4a2a2b8c4 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -7059,7 +7059,7 @@ static int virtnet_probe(struct virtio_device *vdev) otherwise get link status from config. */ netif_carrier_off(dev); if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) { - virtnet_config_changed_work(&vi->config_work); + virtio_config_changed(vi->vdev); } else { vi->status = VIRTIO_NET_S_LINK_UP; virtnet_update_settings(vi); diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c index 57648febc4a4..bd95dc88f9b2 100644 --- a/drivers/net/wireless/ath/ath12k/dp_rx.c +++ b/drivers/net/wireless/ath/ath12k/dp_rx.c @@ -1060,7 +1060,6 @@ int ath12k_dp_rx_peer_tid_setup(struct ath12k *ar, const u8 *peer_mac, int vdev_ } rx_tid = &peer->rx_tid[tid]; - paddr_aligned = rx_tid->qbuf.paddr_aligned; /* Update the tid queue if it is already setup */ if (rx_tid->active) { ret = ath12k_peer_rx_tid_reo_update(ar, peer, rx_tid, @@ -1072,6 +1071,7 @@ int ath12k_dp_rx_peer_tid_setup(struct ath12k *ar, const u8 *peer_mac, int vdev_ } if (!ab->hw_params->reoq_lut_support) { + paddr_aligned = rx_tid->qbuf.paddr_aligned; ret = ath12k_wmi_peer_rx_reorder_queue_setup(ar, vdev_id, peer_mac, paddr_aligned, tid, @@ -1098,6 +1098,7 @@ int ath12k_dp_rx_peer_tid_setup(struct ath12k *ar, const u8 *peer_mac, int vdev_ return ret; } + paddr_aligned = rx_tid->qbuf.paddr_aligned; if (ab->hw_params->reoq_lut_support) { /* Update the REO queue LUT at the corresponding peer id * and tid with qaddr. diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h index 5cdc09d465d4..e90f3187e55c 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2012-2014, 2018-2024 Intel Corporation + * Copyright (C) 2012-2014, 2018-2025 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -754,7 +754,7 @@ struct iwl_lari_config_change_cmd_v10 { * according to the BIOS definitions. * For LARI cmd version 11 - bits 0:4 are supported. * For LARI cmd version 12 - bits 0:6 are supported and bits 7:31 are - * reserved. No need to mask out the reserved bits. + * reserved. * @force_disable_channels_bitmap: Bitmap of disabled bands/channels. * Each bit represents a set of channels in a specific band that should be * disabled @@ -787,6 +787,7 @@ struct iwl_lari_config_change_cmd { /* Activate UNII-1 (5.2GHz) for World Wide */ #define ACTIVATE_5G2_IN_WW_MASK BIT(4) #define CHAN_STATE_ACTIVE_BITMAP_CMD_V11 0x1F +#define CHAN_STATE_ACTIVE_BITMAP_CMD_V12 0x7F /** * struct iwl_pnvm_init_complete_ntfy - PNVM initialization complete diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c index 74b90bd92c48..ebfba981cf89 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c @@ -614,6 +614,7 @@ int iwl_fill_lari_config(struct iwl_fw_runtime *fwrt, ret = iwl_bios_get_dsm(fwrt, DSM_FUNC_ACTIVATE_CHANNEL, &value); if (!ret) { + value &= CHAN_STATE_ACTIVE_BITMAP_CMD_V12; if (cmd_ver < 8) value &= ~ACTIVATE_5G2_IN_WW_MASK; diff --git a/drivers/net/wireless/intel/iwlwifi/mld/regulatory.c b/drivers/net/wireless/intel/iwlwifi/mld/regulatory.c index 326c300470ea..436219d1ec5e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/regulatory.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/regulatory.c @@ -251,8 +251,10 @@ void iwl_mld_configure_lari(struct iwl_mld *mld) cpu_to_le32(value &= DSM_UNII4_ALLOW_BITMAP); ret = iwl_bios_get_dsm(fwrt, DSM_FUNC_ACTIVATE_CHANNEL, &value); - if (!ret) + if (!ret) { + value &= CHAN_STATE_ACTIVE_BITMAP_CMD_V12; cmd.chan_state_active_bitmap = cpu_to_le32(value); + } ret = iwl_bios_get_dsm(fwrt, DSM_FUNC_ENABLE_6E, &value); if (!ret) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c index c8f4f3a1d2eb..5a9c3b7976a1 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c @@ -546,8 +546,10 @@ again: } if (WARN_ON(trans->do_top_reset && - trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_SC)) - return -EINVAL; + trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_SC)) { + ret = -EINVAL; + goto out; + } /* we need to wait later - set state */ if (trans->do_top_reset) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index bb467e2b1779..eee55428749c 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -2101,10 +2101,10 @@ static void iwl_txq_gen1_update_byte_cnt_tbl(struct iwl_trans *trans, bc_ent = cpu_to_le16(len | (sta_id << 12)); - scd_bc_tbl[txq_id * BC_TABLE_SIZE + write_ptr].tfd_offset = bc_ent; + scd_bc_tbl[txq_id * TFD_QUEUE_BC_SIZE + write_ptr].tfd_offset = bc_ent; if (write_ptr < TFD_QUEUE_SIZE_BC_DUP) - scd_bc_tbl[txq_id * BC_TABLE_SIZE + TFD_QUEUE_SIZE_MAX + write_ptr].tfd_offset = + scd_bc_tbl[txq_id * TFD_QUEUE_BC_SIZE + TFD_QUEUE_SIZE_MAX + write_ptr].tfd_offset = bc_ent; } @@ -2328,10 +2328,10 @@ static void iwl_txq_gen1_inval_byte_cnt_tbl(struct iwl_trans *trans, bc_ent = cpu_to_le16(1 | (sta_id << 12)); - scd_bc_tbl[txq_id * BC_TABLE_SIZE + read_ptr].tfd_offset = bc_ent; + scd_bc_tbl[txq_id * TFD_QUEUE_BC_SIZE + read_ptr].tfd_offset = bc_ent; if (read_ptr < TFD_QUEUE_SIZE_BC_DUP) - scd_bc_tbl[txq_id * BC_TABLE_SIZE + TFD_QUEUE_SIZE_MAX + read_ptr].tfd_offset = + scd_bc_tbl[txq_id * TFD_QUEUE_BC_SIZE + TFD_QUEUE_SIZE_MAX + read_ptr].tfd_offset = bc_ent; } diff --git a/drivers/net/wireless/marvell/mwifiex/util.c b/drivers/net/wireless/marvell/mwifiex/util.c index 4c5b1de0e936..6882e90e90b2 100644 --- a/drivers/net/wireless/marvell/mwifiex/util.c +++ b/drivers/net/wireless/marvell/mwifiex/util.c @@ -459,7 +459,9 @@ mwifiex_process_mgmt_packet(struct mwifiex_private *priv, "auth: receive authentication from %pM\n", ieee_hdr->addr3); } else { - if (!priv->wdev.connected) + if (!priv->wdev.connected || + !ether_addr_equal(ieee_hdr->addr3, + priv->curr_bss_params.bss_descriptor.mac_address)) return 0; if (ieee80211_is_deauth(ieee_hdr->frame_control)) { diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 5f8d81cda6cd..74b75035d361 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -1224,6 +1224,16 @@ static inline int mt76_wed_dma_setup(struct mt76_dev *dev, struct mt76_queue *q, #define mt76_dereference(p, dev) \ rcu_dereference_protected(p, lockdep_is_held(&(dev)->mutex)) +static inline struct mt76_wcid * +__mt76_wcid_ptr(struct mt76_dev *dev, u16 idx) +{ + if (idx >= ARRAY_SIZE(dev->wcid)) + return NULL; + return rcu_dereference(dev->wcid[idx]); +} + +#define mt76_wcid_ptr(dev, idx) __mt76_wcid_ptr(&(dev)->mt76, idx) + struct mt76_dev *mt76_alloc_device(struct device *pdev, unsigned int size, const struct ieee80211_ops *ops, const struct mt76_driver_ops *drv_ops); diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c index 863e5770df51..e26cc78fff94 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c @@ -44,7 +44,7 @@ mt7603_rx_loopback_skb(struct mt7603_dev *dev, struct sk_buff *skb) if (idx >= MT7603_WTBL_STA - 1) goto free; - wcid = rcu_dereference(dev->mt76.wcid[idx]); + wcid = mt76_wcid_ptr(dev, idx); if (!wcid) goto free; diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c index 413973d05b43..6387f9e61060 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c @@ -487,10 +487,7 @@ mt7603_rx_get_wcid(struct mt7603_dev *dev, u8 idx, bool unicast) struct mt7603_sta *sta; struct mt76_wcid *wcid; - if (idx >= MT7603_WTBL_SIZE) - return NULL; - - wcid = rcu_dereference(dev->mt76.wcid[idx]); + wcid = mt76_wcid_ptr(dev, idx); if (unicast || !wcid) return wcid; @@ -1266,12 +1263,9 @@ void mt7603_mac_add_txs(struct mt7603_dev *dev, void *data) if (pid == MT_PACKET_ID_NO_ACK) return; - if (wcidx >= MT7603_WTBL_SIZE) - return; - rcu_read_lock(); - wcid = rcu_dereference(dev->mt76.wcid[wcidx]); + wcid = mt76_wcid_ptr(dev, wcidx); if (!wcid) goto out; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c index 3ca4fae7c4b0..f8d2cc94b742 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c @@ -90,10 +90,7 @@ static struct mt76_wcid *mt7615_rx_get_wcid(struct mt7615_dev *dev, struct mt7615_sta *sta; struct mt76_wcid *wcid; - if (idx >= MT7615_WTBL_SIZE) - return NULL; - - wcid = rcu_dereference(dev->mt76.wcid[idx]); + wcid = mt76_wcid_ptr(dev, idx); if (unicast || !wcid) return wcid; @@ -1504,7 +1501,7 @@ static void mt7615_mac_add_txs(struct mt7615_dev *dev, void *data) rcu_read_lock(); - wcid = rcu_dereference(dev->mt76.wcid[wcidx]); + wcid = mt76_wcid_ptr(dev, wcidx); if (!wcid) goto out; diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c index e9ac8a7317a1..0db00efe88b0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c @@ -1172,7 +1172,7 @@ void mt76_connac2_txwi_free(struct mt76_dev *dev, struct mt76_txwi_cache *t, wcid_idx = wcid->idx; } else { wcid_idx = le32_get_bits(txwi[1], MT_TXD1_WLAN_IDX); - wcid = rcu_dereference(dev->wcid[wcid_idx]); + wcid = __mt76_wcid_ptr(dev, wcid_idx); if (wcid && wcid->sta) { sta = container_of((void *)wcid, struct ieee80211_sta, diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c index cb13d0a76878..16db0f2082d1 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c @@ -287,7 +287,7 @@ __mt76_connac_mcu_alloc_sta_req(struct mt76_dev *dev, struct mt76_vif_link *mvif mt76_connac_mcu_get_wlan_idx(dev, wcid, &hdr.wlan_idx_lo, &hdr.wlan_idx_hi); - skb = mt76_mcu_msg_alloc(dev, NULL, len); + skb = __mt76_mcu_msg_alloc(dev, NULL, len, len, GFP_ATOMIC); if (!skb) return ERR_PTR(-ENOMEM); @@ -1740,8 +1740,8 @@ int mt76_connac_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif, if (!sreq->ssids[i].ssid_len) continue; - req->ssids[i].ssid_len = cpu_to_le32(sreq->ssids[i].ssid_len); - memcpy(req->ssids[i].ssid, sreq->ssids[i].ssid, + req->ssids[n_ssids].ssid_len = cpu_to_le32(sreq->ssids[i].ssid_len); + memcpy(req->ssids[n_ssids].ssid, sreq->ssids[i].ssid, sreq->ssids[i].ssid_len); n_ssids++; } diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h index 4cd63bacd742..9d7ee09b6cc9 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h @@ -262,10 +262,7 @@ mt76x02_rx_get_sta(struct mt76_dev *dev, u8 idx) { struct mt76_wcid *wcid; - if (idx >= MT76x02_N_WCIDS) - return NULL; - - wcid = rcu_dereference(dev->wcid[idx]); + wcid = __mt76_wcid_ptr(dev, idx); if (!wcid) return NULL; diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c index d5db6ffd6d36..83488b2d6efb 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c @@ -564,9 +564,7 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev, rcu_read_lock(); - if (stat->wcid < MT76x02_N_WCIDS) - wcid = rcu_dereference(dev->mt76.wcid[stat->wcid]); - + wcid = mt76_wcid_ptr(dev, stat->wcid); if (wcid && wcid->sta) { void *priv; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c index 9400e4af2a04..6639976afcee 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c @@ -56,10 +56,7 @@ static struct mt76_wcid *mt7915_rx_get_wcid(struct mt7915_dev *dev, struct mt7915_sta *sta; struct mt76_wcid *wcid; - if (idx >= ARRAY_SIZE(dev->mt76.wcid)) - return NULL; - - wcid = rcu_dereference(dev->mt76.wcid[idx]); + wcid = mt76_wcid_ptr(dev, idx); if (unicast || !wcid) return wcid; @@ -917,7 +914,7 @@ mt7915_mac_tx_free(struct mt7915_dev *dev, void *data, int len) u16 idx; idx = FIELD_GET(MT_TX_FREE_WLAN_ID, info); - wcid = rcu_dereference(dev->mt76.wcid[idx]); + wcid = mt76_wcid_ptr(dev, idx); sta = wcid_to_sta(wcid); if (!sta) continue; @@ -1013,12 +1010,9 @@ static void mt7915_mac_add_txs(struct mt7915_dev *dev, void *data) if (pid < MT_PACKET_ID_WED) return; - if (wcidx >= mt7915_wtbl_size(dev)) - return; - rcu_read_lock(); - wcid = rcu_dereference(dev->mt76.wcid[wcidx]); + wcid = mt76_wcid_ptr(dev, wcidx); if (!wcid) goto out; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c index 427542777abc..c6584d2b7509 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c @@ -3986,7 +3986,7 @@ int mt7915_mcu_wed_wa_tx_stats(struct mt7915_dev *dev, u16 wlan_idx) rcu_read_lock(); - wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]); + wcid = mt76_wcid_ptr(dev, wlan_idx); if (wcid) wcid->stats.tx_packets += le32_to_cpu(res->tx_packets); else diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c index 9c4d5cea0c42..4a82f8e4c118 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c @@ -587,12 +587,9 @@ static void mt7915_mmio_wed_update_rx_stats(struct mtk_wed_device *wed, dev = container_of(wed, struct mt7915_dev, mt76.mmio.wed); - if (idx >= mt7915_wtbl_size(dev)) - return; - rcu_read_lock(); - wcid = rcu_dereference(dev->mt76.wcid[idx]); + wcid = mt76_wcid_ptr(dev, idx); if (wcid) { wcid->stats.rx_bytes += le32_to_cpu(stats->rx_byte_cnt); wcid->stats.rx_packets += le32_to_cpu(stats->rx_pkt_cnt); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c index 5dd57de59f27..f1f76506b0a5 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c @@ -465,7 +465,7 @@ void mt7921_mac_add_txs(struct mt792x_dev *dev, void *data) rcu_read_lock(); - wcid = rcu_dereference(dev->mt76.wcid[wcidx]); + wcid = mt76_wcid_ptr(dev, wcidx); if (!wcid) goto out; @@ -516,7 +516,7 @@ static void mt7921_mac_tx_free(struct mt792x_dev *dev, void *data, int len) count++; idx = FIELD_GET(MT_TX_FREE_WLAN_ID, info); - wcid = rcu_dereference(dev->mt76.wcid[idx]); + wcid = mt76_wcid_ptr(dev, idx); sta = wcid_to_sta(wcid); if (!sta) continue; @@ -816,7 +816,7 @@ void mt7921_usb_sdio_tx_complete_skb(struct mt76_dev *mdev, u16 idx; idx = le32_get_bits(txwi[1], MT_TXD1_WLAN_IDX); - wcid = rcu_dereference(mdev->wcid[idx]); + wcid = __mt76_wcid_ptr(mdev, idx); sta = wcid_to_sta(wcid); if (sta && likely(e->skb->protocol != cpu_to_be16(ETH_P_PAE))) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 1fffa43379b2..77f73ae1d7ec 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -1180,6 +1180,9 @@ static void mt7921_sta_set_decap_offload(struct ieee80211_hw *hw, struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv; struct mt792x_dev *dev = mt792x_hw_dev(hw); + if (!msta->deflink.wcid.sta) + return; + mt792x_mutex_acquire(dev); if (enabled) diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/init.c b/drivers/net/wireless/mediatek/mt76/mt7925/init.c index 2a83ff59a968..4249bad83c93 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/init.c @@ -52,6 +52,8 @@ static int mt7925_thermal_init(struct mt792x_phy *phy) name = devm_kasprintf(&wiphy->dev, GFP_KERNEL, "mt7925_%s", wiphy_name(wiphy)); + if (!name) + return -ENOMEM; hwmon = devm_hwmon_device_register_with_groups(&wiphy->dev, name, phy, mt7925_hwmon_groups); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c index c871d2f9688b..75823c9fd3a1 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c @@ -1040,7 +1040,7 @@ void mt7925_mac_add_txs(struct mt792x_dev *dev, void *data) rcu_read_lock(); - wcid = rcu_dereference(dev->mt76.wcid[wcidx]); + wcid = mt76_wcid_ptr(dev, wcidx); if (!wcid) goto out; @@ -1122,7 +1122,7 @@ mt7925_mac_tx_free(struct mt792x_dev *dev, void *data, int len) u16 idx; idx = FIELD_GET(MT_TXFREE_INFO_WLAN_ID, info); - wcid = rcu_dereference(dev->mt76.wcid[idx]); + wcid = mt76_wcid_ptr(dev, idx); sta = wcid_to_sta(wcid); if (!sta) continue; @@ -1445,7 +1445,7 @@ void mt7925_usb_sdio_tx_complete_skb(struct mt76_dev *mdev, u16 idx; idx = le32_get_bits(txwi[1], MT_TXD1_WLAN_IDX); - wcid = rcu_dereference(mdev->wcid[idx]); + wcid = __mt76_wcid_ptr(mdev, idx); sta = wcid_to_sta(wcid); if (sta && likely(e->skb->protocol != cpu_to_be16(ETH_P_PAE))) diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c index 94b0099dcd41..5b001548dffc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c @@ -1481,7 +1481,7 @@ mt7925_start_sched_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif, mt792x_mutex_acquire(dev); - err = mt7925_mcu_sched_scan_req(mphy, vif, req); + err = mt7925_mcu_sched_scan_req(mphy, vif, req, ies); if (err < 0) goto out; @@ -1603,6 +1603,9 @@ static void mt7925_sta_set_decap_offload(struct ieee80211_hw *hw, unsigned long valid = mvif->valid_links; u8 i; + if (!msta->vif) + return; + mt792x_mutex_acquire(dev); valid = ieee80211_vif_is_mld(vif) ? mvif->valid_links : BIT(0); @@ -1617,6 +1620,9 @@ static void mt7925_sta_set_decap_offload(struct ieee80211_hw *hw, else clear_bit(MT_WCID_FLAG_HDR_TRANS, &mlink->wcid.flags); + if (!mlink->wcid.sta) + continue; + mt7925_mcu_wtbl_update_hdr_trans(dev, vif, sta, i); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c index b8542be0d945..8ac6fbb736ab 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c @@ -164,6 +164,7 @@ mt7925_connac_mcu_set_wow_ctrl(struct mt76_phy *phy, struct ieee80211_vif *vif, bool suspend, struct cfg80211_wowlan *wowlan) { struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; + struct ieee80211_scan_ies ies = {}; struct mt76_dev *dev = phy->dev; struct { struct { @@ -194,7 +195,7 @@ mt7925_connac_mcu_set_wow_ctrl(struct mt76_phy *phy, struct ieee80211_vif *vif, req.wow_ctrl_tlv.trigger |= (UNI_WOW_DETECT_TYPE_DISCONNECT | UNI_WOW_DETECT_TYPE_BCN_LOST); if (wowlan->nd_config) { - mt7925_mcu_sched_scan_req(phy, vif, wowlan->nd_config); + mt7925_mcu_sched_scan_req(phy, vif, wowlan->nd_config, &ies); req.wow_ctrl_tlv.trigger |= UNI_WOW_DETECT_TYPE_SCH_SCAN_HIT; mt7925_mcu_sched_scan_enable(phy, vif, suspend); } @@ -2818,6 +2819,54 @@ int mt7925_mcu_set_dbdc(struct mt76_phy *phy, bool enable) return err; } +static void +mt7925_mcu_build_scan_ie_tlv(struct mt76_dev *mdev, + struct sk_buff *skb, + struct ieee80211_scan_ies *scan_ies) +{ + u32 max_len = sizeof(struct scan_ie_tlv) + MT76_CONNAC_SCAN_IE_LEN; + struct scan_ie_tlv *ie; + enum nl80211_band i; + struct tlv *tlv; + const u8 *ies; + u16 ies_len; + + for (i = 0; i <= NL80211_BAND_6GHZ; i++) { + if (i == NL80211_BAND_60GHZ) + continue; + + ies = scan_ies->ies[i]; + ies_len = scan_ies->len[i]; + + if (!ies || !ies_len) + continue; + + if (ies_len > max_len) + return; + + tlv = mt76_connac_mcu_add_tlv(skb, UNI_SCAN_IE, + sizeof(*ie) + ies_len); + ie = (struct scan_ie_tlv *)tlv; + + memcpy(ie->ies, ies, ies_len); + ie->ies_len = cpu_to_le16(ies_len); + + switch (i) { + case NL80211_BAND_2GHZ: + ie->band = 1; + break; + case NL80211_BAND_6GHZ: + ie->band = 3; + break; + default: + ie->band = 2; + break; + } + + max_len -= (sizeof(*ie) + ies_len); + } +} + int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif, struct ieee80211_scan_request *scan_req) { @@ -2843,7 +2892,8 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif, max_len = sizeof(*hdr) + sizeof(*req) + sizeof(*ssid) + sizeof(*bssid) * MT7925_RNR_SCAN_MAX_BSSIDS + - sizeof(*chan_info) + sizeof(*misc) + sizeof(*ie); + sizeof(*chan_info) + sizeof(*misc) + sizeof(*ie) + + MT76_CONNAC_SCAN_IE_LEN; skb = mt76_mcu_msg_alloc(mdev, NULL, max_len); if (!skb) @@ -2869,8 +2919,8 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif, if (i > MT7925_RNR_SCAN_MAX_BSSIDS) break; - ssid->ssids[i].ssid_len = cpu_to_le32(sreq->ssids[i].ssid_len); - memcpy(ssid->ssids[i].ssid, sreq->ssids[i].ssid, + ssid->ssids[n_ssids].ssid_len = cpu_to_le32(sreq->ssids[i].ssid_len); + memcpy(ssid->ssids[n_ssids].ssid, sreq->ssids[i].ssid, sreq->ssids[i].ssid_len); n_ssids++; } @@ -2925,13 +2975,6 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif, } chan_info->channel_type = sreq->n_channels ? 4 : 0; - tlv = mt76_connac_mcu_add_tlv(skb, UNI_SCAN_IE, sizeof(*ie)); - ie = (struct scan_ie_tlv *)tlv; - if (sreq->ie_len > 0) { - memcpy(ie->ies, sreq->ie, sreq->ie_len); - ie->ies_len = cpu_to_le16(sreq->ie_len); - } - req->scan_func |= SCAN_FUNC_SPLIT_SCAN; tlv = mt76_connac_mcu_add_tlv(skb, UNI_SCAN_MISC, sizeof(*misc)); @@ -2942,6 +2985,9 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif, req->scan_func |= SCAN_FUNC_RANDOM_MAC; } + /* Append scan probe IEs as the last tlv */ + mt7925_mcu_build_scan_ie_tlv(mdev, skb, &scan_req->ies); + err = mt76_mcu_skb_send_msg(mdev, skb, MCU_UNI_CMD(SCAN_REQ), true); if (err < 0) @@ -2953,7 +2999,8 @@ EXPORT_SYMBOL_GPL(mt7925_mcu_hw_scan); int mt7925_mcu_sched_scan_req(struct mt76_phy *phy, struct ieee80211_vif *vif, - struct cfg80211_sched_scan_request *sreq) + struct cfg80211_sched_scan_request *sreq, + struct ieee80211_scan_ies *ies) { struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct ieee80211_channel **scan_list = sreq->channels; @@ -3041,12 +3088,8 @@ int mt7925_mcu_sched_scan_req(struct mt76_phy *phy, } chan_info->channel_type = sreq->n_channels ? 4 : 0; - tlv = mt76_connac_mcu_add_tlv(skb, UNI_SCAN_IE, sizeof(*ie)); - ie = (struct scan_ie_tlv *)tlv; - if (sreq->ie_len > 0) { - memcpy(ie->ies, sreq->ie, sreq->ie_len); - ie->ies_len = cpu_to_le16(sreq->ie_len); - } + /* Append scan probe IEs as the last tlv */ + mt7925_mcu_build_scan_ie_tlv(mdev, skb, ies); return mt76_mcu_skb_send_msg(mdev, skb, MCU_UNI_CMD(SCAN_REQ), true); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h index ee6fb16e83c5..a40764d89a1f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h @@ -269,7 +269,7 @@ struct scan_ie_tlv { __le16 ies_len; u8 band; u8 pad; - u8 ies[MT76_CONNAC_SCAN_IE_LEN]; + u8 ies[]; }; struct scan_misc_tlv { @@ -673,7 +673,8 @@ int mt7925_mcu_cancel_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif); int mt7925_mcu_sched_scan_req(struct mt76_phy *phy, struct ieee80211_vif *vif, - struct cfg80211_sched_scan_request *sreq); + struct cfg80211_sched_scan_request *sreq, + struct ieee80211_scan_ies *ies); int mt7925_mcu_sched_scan_enable(struct mt76_phy *phy, struct ieee80211_vif *vif, bool enable); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/regs.h b/drivers/net/wireless/mediatek/mt76/mt7925/regs.h index 547489092c29..341987e47f67 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/regs.h +++ b/drivers/net/wireless/mediatek/mt76/mt7925/regs.h @@ -58,7 +58,7 @@ #define MT_INT_TX_DONE_MCU (MT_INT_TX_DONE_MCU_WM | \ MT_INT_TX_DONE_FWDL) -#define MT_INT_TX_DONE_ALL (MT_INT_TX_DONE_MCU_WM | \ +#define MT_INT_TX_DONE_ALL (MT_INT_TX_DONE_MCU | \ MT_INT_TX_DONE_BAND0 | \ GENMASK(18, 4)) diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c index a50c1723ca29..05130ec1e5f7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c @@ -28,7 +28,7 @@ static const struct ieee80211_iface_combination if_comb[] = { }, }; -static const struct ieee80211_iface_limit if_limits_chanctx[] = { +static const struct ieee80211_iface_limit if_limits_chanctx_mcc[] = { { .max = 2, .types = BIT(NL80211_IFTYPE_STATION) | @@ -36,8 +36,23 @@ static const struct ieee80211_iface_limit if_limits_chanctx[] = { }, { .max = 1, - .types = BIT(NL80211_IFTYPE_AP) | - BIT(NL80211_IFTYPE_P2P_GO) + .types = BIT(NL80211_IFTYPE_P2P_GO) + }, + { + .max = 1, + .types = BIT(NL80211_IFTYPE_P2P_DEVICE) + } +}; + +static const struct ieee80211_iface_limit if_limits_chanctx_scc[] = { + { + .max = 2, + .types = BIT(NL80211_IFTYPE_STATION) | + BIT(NL80211_IFTYPE_P2P_CLIENT) + }, + { + .max = 1, + .types = BIT(NL80211_IFTYPE_AP) }, { .max = 1, @@ -47,11 +62,18 @@ static const struct ieee80211_iface_limit if_limits_chanctx[] = { static const struct ieee80211_iface_combination if_comb_chanctx[] = { { - .limits = if_limits_chanctx, - .n_limits = ARRAY_SIZE(if_limits_chanctx), + .limits = if_limits_chanctx_mcc, + .n_limits = ARRAY_SIZE(if_limits_chanctx_mcc), .max_interfaces = 3, .num_different_channels = 2, .beacon_int_infra_match = false, + }, + { + .limits = if_limits_chanctx_scc, + .n_limits = ARRAY_SIZE(if_limits_chanctx_scc), + .max_interfaces = 3, + .num_different_channels = 1, + .beacon_int_infra_match = false, } }; diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c index 05978d9c7b91..3f1d9ba49076 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c @@ -142,10 +142,7 @@ struct mt76_wcid *mt792x_rx_get_wcid(struct mt792x_dev *dev, u16 idx, struct mt792x_sta *sta; struct mt76_wcid *wcid; - if (idx >= ARRAY_SIZE(dev->mt76.wcid)) - return NULL; - - wcid = rcu_dereference(dev->mt76.wcid[idx]); + wcid = mt76_wcid_ptr(dev, idx); if (unicast || !wcid) return wcid; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 0dbd4662bc84..92148518f6a5 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -61,10 +61,7 @@ static struct mt76_wcid *mt7996_rx_get_wcid(struct mt7996_dev *dev, struct mt76_wcid *wcid; int i; - if (idx >= ARRAY_SIZE(dev->mt76.wcid)) - return NULL; - - wcid = rcu_dereference(dev->mt76.wcid[idx]); + wcid = mt76_wcid_ptr(dev, idx); if (!wcid) return NULL; @@ -1249,7 +1246,7 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len) u16 idx; idx = FIELD_GET(MT_TXFREE_INFO_WLAN_ID, info); - wcid = rcu_dereference(dev->mt76.wcid[idx]); + wcid = mt76_wcid_ptr(dev, idx); sta = wcid_to_sta(wcid); if (!sta) goto next; @@ -1471,12 +1468,9 @@ static void mt7996_mac_add_txs(struct mt7996_dev *dev, void *data) if (pid < MT_PACKET_ID_NO_SKB) return; - if (wcidx >= mt7996_wtbl_size(dev)) - return; - rcu_read_lock(); - wcid = rcu_dereference(dev->mt76.wcid[wcidx]); + wcid = mt76_wcid_ptr(dev, wcidx); if (!wcid) goto out; @@ -2353,20 +2347,12 @@ void mt7996_mac_update_stats(struct mt7996_phy *phy) void mt7996_mac_sta_rc_work(struct work_struct *work) { struct mt7996_dev *dev = container_of(work, struct mt7996_dev, rc_work); - struct ieee80211_bss_conf *link_conf; - struct ieee80211_link_sta *link_sta; struct mt7996_sta_link *msta_link; - struct mt7996_vif_link *link; - struct mt76_vif_link *mlink; - struct ieee80211_sta *sta; struct ieee80211_vif *vif; - struct mt7996_sta *msta; struct mt7996_vif *mvif; LIST_HEAD(list); u32 changed; - u8 link_id; - rcu_read_lock(); spin_lock_bh(&dev->mt76.sta_poll_lock); list_splice_init(&dev->sta_rc_list, &list); @@ -2377,46 +2363,28 @@ void mt7996_mac_sta_rc_work(struct work_struct *work) changed = msta_link->changed; msta_link->changed = 0; - - sta = wcid_to_sta(&msta_link->wcid); - link_id = msta_link->wcid.link_id; - msta = msta_link->sta; - mvif = msta->vif; - vif = container_of((void *)mvif, struct ieee80211_vif, drv_priv); - - mlink = rcu_dereference(mvif->mt76.link[link_id]); - if (!mlink) - continue; - - link_sta = rcu_dereference(sta->link[link_id]); - if (!link_sta) - continue; - - link_conf = rcu_dereference(vif->link_conf[link_id]); - if (!link_conf) - continue; + mvif = msta_link->sta->vif; + vif = container_of((void *)mvif, struct ieee80211_vif, + drv_priv); spin_unlock_bh(&dev->mt76.sta_poll_lock); - link = (struct mt7996_vif_link *)mlink; - if (changed & (IEEE80211_RC_SUPP_RATES_CHANGED | IEEE80211_RC_NSS_CHANGED | IEEE80211_RC_BW_CHANGED)) - mt7996_mcu_add_rate_ctrl(dev, vif, link_conf, - link_sta, link, msta_link, + mt7996_mcu_add_rate_ctrl(dev, msta_link->sta, vif, + msta_link->wcid.link_id, true); if (changed & IEEE80211_RC_SMPS_CHANGED) - mt7996_mcu_set_fixed_field(dev, link_sta, link, - msta_link, NULL, + mt7996_mcu_set_fixed_field(dev, msta_link->sta, NULL, + msta_link->wcid.link_id, RATE_PARAM_MMPS_UPDATE); spin_lock_bh(&dev->mt76.sta_poll_lock); } spin_unlock_bh(&dev->mt76.sta_poll_lock); - rcu_read_unlock(); } void mt7996_mac_work(struct work_struct *work) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c index 78ae9f5cb176..07dd75ce94a5 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c @@ -1112,9 +1112,8 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif, if (err) return err; - err = mt7996_mcu_add_rate_ctrl(dev, vif, link_conf, - link_sta, link, - msta_link, false); + err = mt7996_mcu_add_rate_ctrl(dev, msta_link->sta, vif, + link_id, false); if (err) return err; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c index f0adc0b4b8b6..994526c65bfc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c @@ -555,7 +555,7 @@ mt7996_mcu_rx_all_sta_info_event(struct mt7996_dev *dev, struct sk_buff *skb) switch (le16_to_cpu(res->tag)) { case UNI_ALL_STA_TXRX_RATE: wlan_idx = le16_to_cpu(res->rate[i].wlan_idx); - wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]); + wcid = mt76_wcid_ptr(dev, wlan_idx); if (!wcid) break; @@ -565,7 +565,7 @@ mt7996_mcu_rx_all_sta_info_event(struct mt7996_dev *dev, struct sk_buff *skb) break; case UNI_ALL_STA_TXRX_ADM_STAT: wlan_idx = le16_to_cpu(res->adm_stat[i].wlan_idx); - wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]); + wcid = mt76_wcid_ptr(dev, wlan_idx); if (!wcid) break; @@ -579,7 +579,7 @@ mt7996_mcu_rx_all_sta_info_event(struct mt7996_dev *dev, struct sk_buff *skb) break; case UNI_ALL_STA_TXRX_MSDU_COUNT: wlan_idx = le16_to_cpu(res->msdu_cnt[i].wlan_idx); - wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]); + wcid = mt76_wcid_ptr(dev, wlan_idx); if (!wcid) break; @@ -676,10 +676,7 @@ mt7996_mcu_wed_rro_event(struct mt7996_dev *dev, struct sk_buff *skb) e = (void *)skb->data; idx = le16_to_cpu(e->wlan_id); - if (idx >= ARRAY_SIZE(dev->mt76.wcid)) - break; - - wcid = rcu_dereference(dev->mt76.wcid[idx]); + wcid = mt76_wcid_ptr(dev, idx); if (!wcid || !wcid->sta) break; @@ -1905,22 +1902,35 @@ int mt7996_mcu_set_fixed_rate_ctrl(struct mt7996_dev *dev, MCU_WM_UNI_CMD(RA), true); } -int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, - struct ieee80211_link_sta *link_sta, - struct mt7996_vif_link *link, - struct mt7996_sta_link *msta_link, - void *data, u32 field) +int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, struct mt7996_sta *msta, + void *data, u8 link_id, u32 field) { - struct sta_phy_uni *phy = data; + struct mt7996_vif *mvif = msta->vif; + struct mt7996_sta_link *msta_link; struct sta_rec_ra_fixed_uni *ra; + struct sta_phy_uni *phy = data; + struct mt76_vif_link *mlink; struct sk_buff *skb; + int err = -ENODEV; struct tlv *tlv; - skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &link->mt76, + rcu_read_lock(); + + mlink = rcu_dereference(mvif->mt76.link[link_id]); + if (!mlink) + goto error_unlock; + + msta_link = rcu_dereference(msta->link[link_id]); + if (!msta_link) + goto error_unlock; + + skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, mlink, &msta_link->wcid, MT7996_STA_UPDATE_MAX_SIZE); - if (IS_ERR(skb)) - return PTR_ERR(skb); + if (IS_ERR(skb)) { + err = PTR_ERR(skb); + goto error_unlock; + } tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_RA_UPDATE, sizeof(*ra)); ra = (struct sta_rec_ra_fixed_uni *)tlv; @@ -1935,106 +1945,149 @@ int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, if (phy) ra->phy = *phy; break; - case RATE_PARAM_MMPS_UPDATE: + case RATE_PARAM_MMPS_UPDATE: { + struct ieee80211_sta *sta = wcid_to_sta(&msta_link->wcid); + struct ieee80211_link_sta *link_sta; + + link_sta = rcu_dereference(sta->link[link_id]); + if (!link_sta) { + dev_kfree_skb(skb); + goto error_unlock; + } + ra->mmps_mode = mt7996_mcu_get_mmps_mode(link_sta->smps_mode); break; + } default: break; } ra->field = cpu_to_le32(field); + rcu_read_unlock(); + return mt76_mcu_skb_send_msg(&dev->mt76, skb, MCU_WMWA_UNI_CMD(STA_REC_UPDATE), true); +error_unlock: + rcu_read_unlock(); + + return err; } static int -mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev, - struct ieee80211_link_sta *link_sta, - struct mt7996_vif_link *link, - struct mt7996_sta_link *msta_link) +mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev, struct mt7996_sta *msta, + struct ieee80211_vif *vif, u8 link_id) { - struct cfg80211_chan_def *chandef = &link->phy->mt76->chandef; - struct cfg80211_bitrate_mask *mask = &link->bitrate_mask; - enum nl80211_band band = chandef->chan->band; + struct ieee80211_link_sta *link_sta; + struct cfg80211_bitrate_mask mask; + struct mt7996_sta_link *msta_link; + struct mt7996_vif_link *link; struct sta_phy_uni phy = {}; - int ret, nrates = 0; + struct ieee80211_sta *sta; + int ret, nrates = 0, idx; + enum nl80211_band band; + bool has_he; #define __sta_phy_bitrate_mask_check(_mcs, _gi, _ht, _he) \ do { \ - u8 i, gi = mask->control[band]._gi; \ + u8 i, gi = mask.control[band]._gi; \ gi = (_he) ? gi : gi == NL80211_TXRATE_FORCE_SGI; \ phy.sgi = gi; \ - phy.he_ltf = mask->control[band].he_ltf; \ - for (i = 0; i < ARRAY_SIZE(mask->control[band]._mcs); i++) { \ - if (!mask->control[band]._mcs[i]) \ + phy.he_ltf = mask.control[band].he_ltf; \ + for (i = 0; i < ARRAY_SIZE(mask.control[band]._mcs); i++) { \ + if (!mask.control[band]._mcs[i]) \ continue; \ - nrates += hweight16(mask->control[band]._mcs[i]); \ - phy.mcs = ffs(mask->control[band]._mcs[i]) - 1; \ + nrates += hweight16(mask.control[band]._mcs[i]); \ + phy.mcs = ffs(mask.control[band]._mcs[i]) - 1; \ if (_ht) \ phy.mcs += 8 * i; \ } \ } while (0) - if (link_sta->he_cap.has_he) { + rcu_read_lock(); + + link = mt7996_vif_link(dev, vif, link_id); + if (!link) + goto error_unlock; + + msta_link = rcu_dereference(msta->link[link_id]); + if (!msta_link) + goto error_unlock; + + sta = wcid_to_sta(&msta_link->wcid); + link_sta = rcu_dereference(sta->link[link_id]); + if (!link_sta) + goto error_unlock; + + band = link->phy->mt76->chandef.chan->band; + has_he = link_sta->he_cap.has_he; + mask = link->bitrate_mask; + idx = msta_link->wcid.idx; + + if (has_he) { __sta_phy_bitrate_mask_check(he_mcs, he_gi, 0, 1); } else if (link_sta->vht_cap.vht_supported) { __sta_phy_bitrate_mask_check(vht_mcs, gi, 0, 0); } else if (link_sta->ht_cap.ht_supported) { __sta_phy_bitrate_mask_check(ht_mcs, gi, 1, 0); } else { - nrates = hweight32(mask->control[band].legacy); - phy.mcs = ffs(mask->control[band].legacy) - 1; + nrates = hweight32(mask.control[band].legacy); + phy.mcs = ffs(mask.control[band].legacy) - 1; } + + rcu_read_unlock(); + #undef __sta_phy_bitrate_mask_check /* fall back to auto rate control */ - if (mask->control[band].gi == NL80211_TXRATE_DEFAULT_GI && - mask->control[band].he_gi == GENMASK(7, 0) && - mask->control[band].he_ltf == GENMASK(7, 0) && + if (mask.control[band].gi == NL80211_TXRATE_DEFAULT_GI && + mask.control[band].he_gi == GENMASK(7, 0) && + mask.control[band].he_ltf == GENMASK(7, 0) && nrates != 1) return 0; /* fixed single rate */ if (nrates == 1) { - ret = mt7996_mcu_set_fixed_field(dev, link_sta, link, - msta_link, &phy, + ret = mt7996_mcu_set_fixed_field(dev, msta, &phy, link_id, RATE_PARAM_FIXED_MCS); if (ret) return ret; } /* fixed GI */ - if (mask->control[band].gi != NL80211_TXRATE_DEFAULT_GI || - mask->control[band].he_gi != GENMASK(7, 0)) { + if (mask.control[band].gi != NL80211_TXRATE_DEFAULT_GI || + mask.control[band].he_gi != GENMASK(7, 0)) { u32 addr; /* firmware updates only TXCMD but doesn't take WTBL into * account, so driver should update here to reflect the * actual txrate hardware sends out. */ - addr = mt7996_mac_wtbl_lmac_addr(dev, msta_link->wcid.idx, 7); - if (link_sta->he_cap.has_he) + addr = mt7996_mac_wtbl_lmac_addr(dev, idx, 7); + if (has_he) mt76_rmw_field(dev, addr, GENMASK(31, 24), phy.sgi); else mt76_rmw_field(dev, addr, GENMASK(15, 12), phy.sgi); - ret = mt7996_mcu_set_fixed_field(dev, link_sta, link, - msta_link, &phy, + ret = mt7996_mcu_set_fixed_field(dev, msta, &phy, link_id, RATE_PARAM_FIXED_GI); if (ret) return ret; } /* fixed HE_LTF */ - if (mask->control[band].he_ltf != GENMASK(7, 0)) { - ret = mt7996_mcu_set_fixed_field(dev, link_sta, link, - msta_link, &phy, + if (mask.control[band].he_ltf != GENMASK(7, 0)) { + ret = mt7996_mcu_set_fixed_field(dev, msta, &phy, link_id, RATE_PARAM_FIXED_HE_LTF); if (ret) return ret; } return 0; + +error_unlock: + rcu_read_unlock(); + + return -ENODEV; } static void @@ -2145,21 +2198,44 @@ mt7996_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7996_dev *dev, memset(ra->rx_rcpi, INIT_RCPI, sizeof(ra->rx_rcpi)); } -int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev, - struct ieee80211_vif *vif, - struct ieee80211_bss_conf *link_conf, - struct ieee80211_link_sta *link_sta, - struct mt7996_vif_link *link, - struct mt7996_sta_link *msta_link, bool changed) +int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev, struct mt7996_sta *msta, + struct ieee80211_vif *vif, u8 link_id, + bool changed) { + struct ieee80211_bss_conf *link_conf; + struct ieee80211_link_sta *link_sta; + struct mt7996_sta_link *msta_link; + struct mt7996_vif_link *link; + struct ieee80211_sta *sta; struct sk_buff *skb; - int ret; + int ret = -ENODEV; + + rcu_read_lock(); + + link = mt7996_vif_link(dev, vif, link_id); + if (!link) + goto error_unlock; + + msta_link = rcu_dereference(msta->link[link_id]); + if (!msta_link) + goto error_unlock; + + sta = wcid_to_sta(&msta_link->wcid); + link_sta = rcu_dereference(sta->link[link_id]); + if (!link_sta) + goto error_unlock; + + link_conf = rcu_dereference(vif->link_conf[link_id]); + if (!link_conf) + goto error_unlock; skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &link->mt76, &msta_link->wcid, MT7996_STA_UPDATE_MAX_SIZE); - if (IS_ERR(skb)) - return PTR_ERR(skb); + if (IS_ERR(skb)) { + ret = PTR_ERR(skb); + goto error_unlock; + } /* firmware rc algorithm refers to sta_rec_he for HE control. * once dev->rc_work changes the settings driver should also @@ -2173,12 +2249,19 @@ int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev, */ mt7996_mcu_sta_rate_ctrl_tlv(skb, dev, vif, link_conf, link_sta, link); + rcu_read_unlock(); + ret = mt76_mcu_skb_send_msg(&dev->mt76, skb, MCU_WMWA_UNI_CMD(STA_REC_UPDATE), true); if (ret) return ret; - return mt7996_mcu_add_rate_ctrl_fixed(dev, link_sta, link, msta_link); + return mt7996_mcu_add_rate_ctrl_fixed(dev, msta, vif, link_id); + +error_unlock: + rcu_read_unlock(); + + return ret; } static int diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h index 1ad6bc046f7c..33ac16b64ef1 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h @@ -620,23 +620,17 @@ int mt7996_mcu_beacon_inband_discov(struct mt7996_dev *dev, int mt7996_mcu_add_obss_spr(struct mt7996_phy *phy, struct mt7996_vif_link *link, struct ieee80211_he_obss_pd *he_obss_pd); -int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev, - struct ieee80211_vif *vif, - struct ieee80211_bss_conf *link_conf, - struct ieee80211_link_sta *link_sta, - struct mt7996_vif_link *link, - struct mt7996_sta_link *msta_link, bool changed); +int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev, struct mt7996_sta *msta, + struct ieee80211_vif *vif, u8 link_id, + bool changed); int mt7996_set_channel(struct mt76_phy *mphy); int mt7996_mcu_set_chan_info(struct mt7996_phy *phy, u16 tag); int mt7996_mcu_set_tx(struct mt7996_dev *dev, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf); int mt7996_mcu_set_fixed_rate_ctrl(struct mt7996_dev *dev, void *data, u16 version); -int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, - struct ieee80211_link_sta *link_sta, - struct mt7996_vif_link *link, - struct mt7996_sta_link *msta_link, - void *data, u32 field); +int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, struct mt7996_sta *msta, + void *data, u8 link_id, u32 field); int mt7996_mcu_set_eeprom(struct mt7996_dev *dev); int mt7996_mcu_get_eeprom(struct mt7996_dev *dev, u32 offset, u8 *buf, u32 buf_len); int mt7996_mcu_get_eeprom_free_block(struct mt7996_dev *dev, u8 *block_num); diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c index 513916469ca2..e6cf16706667 100644 --- a/drivers/net/wireless/mediatek/mt76/tx.c +++ b/drivers/net/wireless/mediatek/mt76/tx.c @@ -64,7 +64,7 @@ mt76_tx_status_unlock(struct mt76_dev *dev, struct sk_buff_head *list) struct mt76_tx_cb *cb = mt76_tx_skb_cb(skb); struct mt76_wcid *wcid; - wcid = rcu_dereference(dev->wcid[cb->wcid]); + wcid = __mt76_wcid_ptr(dev, cb->wcid); if (wcid) { status.sta = wcid_to_sta(wcid); if (status.sta && (wcid->rate.flags || wcid->rate.legacy)) { @@ -251,9 +251,7 @@ void __mt76_tx_complete_skb(struct mt76_dev *dev, u16 wcid_idx, struct sk_buff * rcu_read_lock(); - if (wcid_idx < ARRAY_SIZE(dev->wcid)) - wcid = rcu_dereference(dev->wcid[wcid_idx]); - + wcid = __mt76_wcid_ptr(dev, wcid_idx); mt76_tx_check_non_aql(dev, wcid, skb); #ifdef CONFIG_NL80211_TESTMODE @@ -538,7 +536,7 @@ mt76_txq_schedule_list(struct mt76_phy *phy, enum mt76_txq_id qid) break; mtxq = (struct mt76_txq *)txq->drv_priv; - wcid = rcu_dereference(dev->wcid[mtxq->wcid]); + wcid = __mt76_wcid_ptr(dev, mtxq->wcid); if (!wcid || test_bit(MT_WCID_FLAG_PS, &wcid->flags)) continue; @@ -617,7 +615,8 @@ mt76_txq_schedule_pending_wcid(struct mt76_phy *phy, struct mt76_wcid *wcid, if ((dev->drv->drv_flags & MT_DRV_HW_MGMT_TXQ) && !(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) && !ieee80211_is_data(hdr->frame_control) && - !ieee80211_is_bufferable_mmpdu(skb)) + (!ieee80211_is_bufferable_mmpdu(skb) || + ieee80211_is_deauth(hdr->frame_control))) qid = MT_TXQ_PSD; q = phy->q_tx[qid]; diff --git a/drivers/net/wireless/mediatek/mt76/util.c b/drivers/net/wireless/mediatek/mt76/util.c index 95b3dc96e4c4..97249ebb4bc8 100644 --- a/drivers/net/wireless/mediatek/mt76/util.c +++ b/drivers/net/wireless/mediatek/mt76/util.c @@ -83,7 +83,7 @@ int mt76_get_min_avg_rssi(struct mt76_dev *dev, u8 phy_idx) if (!(mask & 1)) continue; - wcid = rcu_dereference(dev->wcid[j]); + wcid = __mt76_wcid_ptr(dev, j); if (!wcid || wcid->phy_idx != phy_idx) continue; diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00soc.c b/drivers/net/wireless/ralink/rt2x00/rt2x00soc.c index eface610178d..f7f3a2340c39 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00soc.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00soc.c @@ -108,7 +108,7 @@ exit_free_device: } EXPORT_SYMBOL_GPL(rt2x00soc_probe); -int rt2x00soc_remove(struct platform_device *pdev) +void rt2x00soc_remove(struct platform_device *pdev) { struct ieee80211_hw *hw = platform_get_drvdata(pdev); struct rt2x00_dev *rt2x00dev = hw->priv; @@ -119,8 +119,6 @@ int rt2x00soc_remove(struct platform_device *pdev) rt2x00lib_remove_dev(rt2x00dev); rt2x00soc_free_reg(rt2x00dev); ieee80211_free_hw(hw); - - return 0; } EXPORT_SYMBOL_GPL(rt2x00soc_remove); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00soc.h b/drivers/net/wireless/ralink/rt2x00/rt2x00soc.h index 021fd06b3627..d6226b8a10e0 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00soc.h +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00soc.h @@ -17,7 +17,7 @@ * SoC driver handlers. */ int rt2x00soc_probe(struct platform_device *pdev, const struct rt2x00_ops *ops); -int rt2x00soc_remove(struct platform_device *pdev); +void rt2x00soc_remove(struct platform_device *pdev); #ifdef CONFIG_PM int rt2x00soc_suspend(struct platform_device *pdev, pm_message_t state); int rt2x00soc_resume(struct platform_device *pdev); diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_mac.c b/drivers/net/wireless/zydas/zd1211rw/zd_mac.c index 9653dbaac3c0..781510a3ec6d 100644 --- a/drivers/net/wireless/zydas/zd1211rw/zd_mac.c +++ b/drivers/net/wireless/zydas/zd1211rw/zd_mac.c @@ -583,7 +583,11 @@ void zd_mac_tx_to_dev(struct sk_buff *skb, int error) skb_queue_tail(q, skb); while (skb_queue_len(q) > ZD_MAC_MAX_ACK_WAITERS) { - zd_mac_tx_status(hw, skb_dequeue(q), + skb = skb_dequeue(q); + if (!skb) + break; + + zd_mac_tx_status(hw, skb, mac->ack_pending ? mac->ack_signal : 0, NULL); mac->ack_pending = 0; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 7493e5aa984c..895fb163d48e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -381,12 +381,12 @@ static void nvme_log_err_passthru(struct request *req) nr->status & NVME_SC_MASK, /* Status Code */ nr->status & NVME_STATUS_MORE ? "MORE " : "", nr->status & NVME_STATUS_DNR ? "DNR " : "", - nr->cmd->common.cdw10, - nr->cmd->common.cdw11, - nr->cmd->common.cdw12, - nr->cmd->common.cdw13, - nr->cmd->common.cdw14, - nr->cmd->common.cdw15); + le32_to_cpu(nr->cmd->common.cdw10), + le32_to_cpu(nr->cmd->common.cdw11), + le32_to_cpu(nr->cmd->common.cdw12), + le32_to_cpu(nr->cmd->common.cdw13), + le32_to_cpu(nr->cmd->common.cdw14), + le32_to_cpu(nr->cmd->common.cdw15)); } enum nvme_disposition { @@ -764,6 +764,10 @@ blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl, !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) && !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH)) return BLK_STS_RESOURCE; + + if (!(rq->rq_flags & RQF_DONTPREP)) + nvme_clear_nvme_request(rq); + return nvme_host_path_error(rq); } EXPORT_SYMBOL_GPL(nvme_fail_nonready_command); @@ -3537,15 +3541,6 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) if (ret) goto out_free; } - - if (le16_to_cpu(id->awupf) != ctrl->subsys->awupf) { - dev_err_ratelimited(ctrl->device, - "inconsistent AWUPF, controller not added (%u/%u).\n", - le16_to_cpu(id->awupf), ctrl->subsys->awupf); - ret = -EINVAL; - goto out_free; - } - memcpy(ctrl->subsys->firmware_rev, id->fr, sizeof(ctrl->subsys->firmware_rev)); @@ -4077,7 +4072,7 @@ static void nvme_ns_add_to_ctrl_list(struct nvme_ns *ns) return; } } - list_add(&ns->list, &ns->ctrl->namespaces); + list_add_rcu(&ns->list, &ns->ctrl->namespaces); } static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 688033b88d38..470bf37e5a63 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1928,10 +1928,10 @@ static void nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port, struct sock *sk = queue->sock->sk; /* Restore the default callbacks before starting upcall */ - read_lock_bh(&sk->sk_callback_lock); + write_lock_bh(&sk->sk_callback_lock); sk->sk_user_data = NULL; sk->sk_data_ready = port->data_ready; - read_unlock_bh(&sk->sk_callback_lock); + write_unlock_bh(&sk->sk_callback_lock); if (!nvmet_tcp_try_peek_pdu(queue)) { if (!nvmet_tcp_tls_handshake(queue)) return; diff --git a/drivers/nvmem/imx-ocotp-ele.c b/drivers/nvmem/imx-ocotp-ele.c index ca6dd71d8a2e..7807ec0e2d18 100644 --- a/drivers/nvmem/imx-ocotp-ele.c +++ b/drivers/nvmem/imx-ocotp-ele.c @@ -12,6 +12,7 @@ #include <linux/of.h> #include <linux/platform_device.h> #include <linux/slab.h> +#include <linux/if_ether.h> /* ETH_ALEN */ enum fuse_type { FUSE_FSB = BIT(0), @@ -118,9 +119,11 @@ static int imx_ocotp_cell_pp(void *context, const char *id, int index, int i; /* Deal with some post processing of nvmem cell data */ - if (id && !strcmp(id, "mac-address")) + if (id && !strcmp(id, "mac-address")) { + bytes = min(bytes, ETH_ALEN); for (i = 0; i < bytes / 2; i++) swap(buf[i], buf[bytes - i - 1]); + } return 0; } diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c index 79dd4fda0329..7bf7656d4f96 100644 --- a/drivers/nvmem/imx-ocotp.c +++ b/drivers/nvmem/imx-ocotp.c @@ -23,6 +23,7 @@ #include <linux/platform_device.h> #include <linux/slab.h> #include <linux/delay.h> +#include <linux/if_ether.h> /* ETH_ALEN */ #define IMX_OCOTP_OFFSET_B0W0 0x400 /* Offset from base address of the * OTP Bank0 Word0 @@ -227,9 +228,11 @@ static int imx_ocotp_cell_pp(void *context, const char *id, int index, int i; /* Deal with some post processing of nvmem cell data */ - if (id && !strcmp(id, "mac-address")) + if (id && !strcmp(id, "mac-address")) { + bytes = min(bytes, ETH_ALEN); for (i = 0; i < bytes / 2; i++) swap(buf[i], buf[bytes - i - 1]); + } return 0; } diff --git a/drivers/nvmem/layouts/u-boot-env.c b/drivers/nvmem/layouts/u-boot-env.c index 436426d4e8f9..8571aac56295 100644 --- a/drivers/nvmem/layouts/u-boot-env.c +++ b/drivers/nvmem/layouts/u-boot-env.c @@ -92,7 +92,7 @@ int u_boot_env_parse(struct device *dev, struct nvmem_device *nvmem, size_t crc32_data_offset; size_t crc32_data_len; size_t crc32_offset; - __le32 *crc32_addr; + uint32_t *crc32_addr; size_t data_offset; size_t data_len; size_t dev_size; @@ -143,8 +143,8 @@ int u_boot_env_parse(struct device *dev, struct nvmem_device *nvmem, goto err_kfree; } - crc32_addr = (__le32 *)(buf + crc32_offset); - crc32 = le32_to_cpu(*crc32_addr); + crc32_addr = (uint32_t *)(buf + crc32_offset); + crc32 = *crc32_addr; crc32_data_len = dev_size - crc32_data_offset; data_len = dev_size - data_offset; diff --git a/drivers/pci/controller/pci-host-common.c b/drivers/pci/controller/pci-host-common.c index b0992325dd65..b37052863847 100644 --- a/drivers/pci/controller/pci-host-common.c +++ b/drivers/pci/controller/pci-host-common.c @@ -64,13 +64,13 @@ int pci_host_common_init(struct platform_device *pdev, of_pci_check_probe_only(); + platform_set_drvdata(pdev, bridge); + /* Parse and map our Configuration Space windows */ cfg = gen_pci_init(dev, bridge, ops); if (IS_ERR(cfg)) return PTR_ERR(cfg); - platform_set_drvdata(pdev, bridge); - bridge->sysdata = cfg; bridge->ops = (struct pci_ops *)&ops->pci_ops; bridge->enable_device = ops->enable_device; diff --git a/drivers/pci/controller/pci-hyperv-intf.c b/drivers/pci/controller/pci-hyperv-intf.c index cc96be450360..28b3e93d31c0 100644 --- a/drivers/pci/controller/pci-hyperv-intf.c +++ b/drivers/pci/controller/pci-hyperv-intf.c @@ -14,6 +14,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/hyperv.h> +#include <linux/export.h> struct hyperv_pci_block_ops hvpci_block_ops; EXPORT_SYMBOL_GPL(hvpci_block_ops); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index ef5d655a0052..13680363ff19 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -600,7 +600,7 @@ static unsigned int hv_msi_get_int_vector(struct irq_data *data) #define hv_msi_prepare pci_msi_prepare /** - * hv_arch_irq_unmask() - "Unmask" the IRQ by setting its current + * hv_irq_retarget_interrupt() - "Unmask" the IRQ by setting its current * affinity. * @data: Describes the IRQ * @@ -609,7 +609,7 @@ static unsigned int hv_msi_get_int_vector(struct irq_data *data) * is built out of this PCI bus's instance GUID and the function * number of the device. */ -static void hv_arch_irq_unmask(struct irq_data *data) +static void hv_irq_retarget_interrupt(struct irq_data *data) { struct msi_desc *msi_desc = irq_data_get_msi_desc(data); struct hv_retarget_device_interrupt *params; @@ -714,6 +714,20 @@ out: dev_err(&hbus->hdev->device, "%s() failed: %#llx", __func__, res); } + +static void hv_arch_irq_unmask(struct irq_data *data) +{ + if (hv_root_partition()) + /* + * In case of the nested root partition, the nested hypervisor + * is taking care of interrupt remapping and thus the + * MAP_DEVICE_INTERRUPT hypercall is required instead of + * RETARGET_INTERRUPT. + */ + (void)hv_map_msi_interrupt(data, NULL); + else + hv_irq_retarget_interrupt(data); +} #elif defined(CONFIG_ARM64) /* * SPI vectors to use for vPCI; arch SPIs range is [32, 1019], but leaving a bit @@ -4144,6 +4158,9 @@ static int __init init_hv_pci_drv(void) if (!hv_is_hyperv_initialized()) return -ENODEV; + if (hv_root_partition() && !hv_nested) + return -ENODEV; + ret = hv_pci_irqchip_init(); if (ret) return ret; diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c index 77fe73976654..0380d300adca 100644 --- a/drivers/pci/controller/pcie-apple.c +++ b/drivers/pci/controller/pcie-apple.c @@ -187,6 +187,7 @@ struct apple_pcie { const struct hw_info *hw; unsigned long *bitmap; struct list_head ports; + struct list_head entry; struct completion event; struct irq_fwspec fwspec; u32 nvecs; @@ -205,6 +206,9 @@ struct apple_pcie_port { int idx; }; +static LIST_HEAD(pcie_list); +static DEFINE_MUTEX(pcie_list_lock); + static void rmw_set(u32 set, void __iomem *addr) { writel_relaxed(readl_relaxed(addr) | set, addr); @@ -720,13 +724,45 @@ static int apple_msi_init(struct apple_pcie *pcie) return 0; } +static void apple_pcie_register(struct apple_pcie *pcie) +{ + guard(mutex)(&pcie_list_lock); + + list_add_tail(&pcie->entry, &pcie_list); +} + +static void apple_pcie_unregister(struct apple_pcie *pcie) +{ + guard(mutex)(&pcie_list_lock); + + list_del(&pcie->entry); +} + +static struct apple_pcie *apple_pcie_lookup(struct device *dev) +{ + struct apple_pcie *pcie; + + guard(mutex)(&pcie_list_lock); + + list_for_each_entry(pcie, &pcie_list, entry) { + if (pcie->dev == dev) + return pcie; + } + + return NULL; +} + static struct apple_pcie_port *apple_pcie_get_port(struct pci_dev *pdev) { struct pci_config_window *cfg = pdev->sysdata; - struct apple_pcie *pcie = cfg->priv; + struct apple_pcie *pcie; struct pci_dev *port_pdev; struct apple_pcie_port *port; + pcie = apple_pcie_lookup(cfg->parent); + if (WARN_ON(!pcie)) + return NULL; + /* Find the root port this device is on */ port_pdev = pcie_find_root_port(pdev); @@ -806,10 +842,14 @@ static void apple_pcie_disable_device(struct pci_host_bridge *bridge, struct pci static int apple_pcie_init(struct pci_config_window *cfg) { - struct apple_pcie *pcie = cfg->priv; struct device *dev = cfg->parent; + struct apple_pcie *pcie; int ret; + pcie = apple_pcie_lookup(dev); + if (WARN_ON(!pcie)) + return -ENOENT; + for_each_available_child_of_node_scoped(dev->of_node, of_port) { ret = apple_pcie_setup_port(pcie, of_port); if (ret) { @@ -852,13 +892,18 @@ static int apple_pcie_probe(struct platform_device *pdev) mutex_init(&pcie->lock); INIT_LIST_HEAD(&pcie->ports); - dev_set_drvdata(dev, pcie); ret = apple_msi_init(pcie); if (ret) return ret; - return pci_host_common_init(pdev, &apple_pcie_cfg_ecam_ops); + apple_pcie_register(pcie); + + ret = pci_host_common_init(pdev, &apple_pcie_cfg_ecam_ops); + if (ret) + apple_pcie_unregister(pcie); + + return ret; } static const struct of_device_id apple_pcie_of_match[] = { diff --git a/drivers/pci/ecam.c b/drivers/pci/ecam.c index 2c5e6446e00e..260b7de2dbd5 100644 --- a/drivers/pci/ecam.c +++ b/drivers/pci/ecam.c @@ -84,8 +84,6 @@ struct pci_config_window *pci_ecam_create(struct device *dev, goto err_exit_iomap; } - cfg->priv = dev_get_drvdata(dev); - if (ops->init) { err = ops->init(cfg); if (err) diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 6ede55a7c5e6..d686488f4111 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -934,10 +934,12 @@ int pci_msix_write_tph_tag(struct pci_dev *pdev, unsigned int index, u16 tag) if (!pdev->msix_enabled) return -ENXIO; - guard(msi_descs_lock)(&pdev->dev); virq = msi_get_virq(&pdev->dev, index); if (!virq) return -ENXIO; + + guard(msi_descs_lock)(&pdev->dev); + /* * This is a horrible hack, but short of implementing a PCI * specific interrupt chip callback and a huge pile of diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 4b8693ec9e4c..e6a34db77826 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2508,6 +2508,7 @@ bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l, } EXPORT_SYMBOL(pci_bus_read_dev_vendor_id); +#if IS_ENABLED(CONFIG_PCI_PWRCTRL) static struct platform_device *pci_pwrctrl_create_device(struct pci_bus *bus, int devfn) { struct pci_host_bridge *host = pci_find_host_bridge(bus); @@ -2537,6 +2538,12 @@ static struct platform_device *pci_pwrctrl_create_device(struct pci_bus *bus, in return pdev; } +#else +static struct platform_device *pci_pwrctrl_create_device(struct pci_bus *bus, int devfn) +{ + return NULL; +} +#endif /* * Read the config data for a PCI device, sanity-check it, diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index 8e2daea81666..04a5a34e7a95 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -994,7 +994,8 @@ struct phy *phy_create(struct device *dev, struct device_node *node, } device_initialize(&phy->dev); - mutex_init(&phy->mutex); + lockdep_register_key(&phy->lockdep_key); + mutex_init_with_key(&phy->mutex, &phy->lockdep_key); phy->dev.class = &phy_class; phy->dev.parent = dev; @@ -1259,6 +1260,8 @@ static void phy_release(struct device *dev) dev_vdbg(dev, "releasing '%s'\n", dev_name(dev)); debugfs_remove_recursive(phy->debugfs); regulator_put(phy->pwr); + mutex_destroy(&phy->mutex); + lockdep_unregister_key(&phy->lockdep_key); ida_free(&phy_ida, phy->id); kfree(phy); } diff --git a/drivers/phy/phy-snps-eusb2.c b/drivers/phy/phy-snps-eusb2.c index b73a1d7e57b3..751b6d8ba2be 100644 --- a/drivers/phy/phy-snps-eusb2.c +++ b/drivers/phy/phy-snps-eusb2.c @@ -567,9 +567,11 @@ static int snps_eusb2_hsphy_probe(struct platform_device *pdev) } } - if (IS_ERR_OR_NULL(phy->ref_clk)) - return dev_err_probe(dev, PTR_ERR(phy->ref_clk), + if (IS_ERR_OR_NULL(phy->ref_clk)) { + ret = phy->ref_clk ? PTR_ERR(phy->ref_clk) : -ENOENT; + return dev_err_probe(dev, ret, "failed to get ref clk\n"); + } num = ARRAY_SIZE(phy->vregs); for (i = 0; i < num; i++) diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c index 23a23f2d64e5..e818f6c3980e 100644 --- a/drivers/phy/tegra/xusb-tegra186.c +++ b/drivers/phy/tegra/xusb-tegra186.c @@ -648,14 +648,15 @@ static void tegra186_utmi_bias_pad_power_on(struct tegra_xusb_padctl *padctl) udelay(100); } - if (padctl->soc->trk_hw_mode) { - value = padctl_readl(padctl, XUSB_PADCTL_USB2_BIAS_PAD_CTL2); - value |= USB2_TRK_HW_MODE; + value = padctl_readl(padctl, XUSB_PADCTL_USB2_BIAS_PAD_CTL2); + if (padctl->soc->trk_update_on_idle) value &= ~CYA_TRK_CODE_UPDATE_ON_IDLE; - padctl_writel(padctl, value, XUSB_PADCTL_USB2_BIAS_PAD_CTL2); - } else { + if (padctl->soc->trk_hw_mode) + value |= USB2_TRK_HW_MODE; + padctl_writel(padctl, value, XUSB_PADCTL_USB2_BIAS_PAD_CTL2); + + if (!padctl->soc->trk_hw_mode) clk_disable_unprepare(priv->usb2_trk_clk); - } } static void tegra186_utmi_bias_pad_power_off(struct tegra_xusb_padctl *padctl) @@ -782,13 +783,15 @@ static int tegra186_xusb_padctl_vbus_override(struct tegra_xusb_padctl *padctl, } static int tegra186_xusb_padctl_id_override(struct tegra_xusb_padctl *padctl, - bool status) + struct tegra_xusb_usb2_port *port, bool status) { - u32 value; + u32 value, id_override; + int err = 0; dev_dbg(padctl->dev, "%s id override\n", status ? "set" : "clear"); value = padctl_readl(padctl, USB2_VBUS_ID); + id_override = value & ID_OVERRIDE(~0); if (status) { if (value & VBUS_OVERRIDE) { @@ -799,15 +802,35 @@ static int tegra186_xusb_padctl_id_override(struct tegra_xusb_padctl *padctl, value = padctl_readl(padctl, USB2_VBUS_ID); } - value &= ~ID_OVERRIDE(~0); - value |= ID_OVERRIDE_GROUNDED; + if (id_override != ID_OVERRIDE_GROUNDED) { + value &= ~ID_OVERRIDE(~0); + value |= ID_OVERRIDE_GROUNDED; + padctl_writel(padctl, value, USB2_VBUS_ID); + + err = regulator_enable(port->supply); + if (err) { + dev_err(padctl->dev, "Failed to enable regulator: %d\n", err); + return err; + } + } } else { - value &= ~ID_OVERRIDE(~0); - value |= ID_OVERRIDE_FLOATING; + if (id_override == ID_OVERRIDE_GROUNDED) { + /* + * The regulator is disabled only when the role transitions + * from USB_ROLE_HOST to USB_ROLE_NONE. + */ + err = regulator_disable(port->supply); + if (err) { + dev_err(padctl->dev, "Failed to disable regulator: %d\n", err); + return err; + } + + value &= ~ID_OVERRIDE(~0); + value |= ID_OVERRIDE_FLOATING; + padctl_writel(padctl, value, USB2_VBUS_ID); + } } - padctl_writel(padctl, value, USB2_VBUS_ID); - return 0; } @@ -826,27 +849,20 @@ static int tegra186_utmi_phy_set_mode(struct phy *phy, enum phy_mode mode, if (mode == PHY_MODE_USB_OTG) { if (submode == USB_ROLE_HOST) { - tegra186_xusb_padctl_id_override(padctl, true); - - err = regulator_enable(port->supply); + err = tegra186_xusb_padctl_id_override(padctl, port, true); + if (err) + goto out; } else if (submode == USB_ROLE_DEVICE) { tegra186_xusb_padctl_vbus_override(padctl, true); } else if (submode == USB_ROLE_NONE) { - /* - * When port is peripheral only or role transitions to - * USB_ROLE_NONE from USB_ROLE_DEVICE, regulator is not - * enabled. - */ - if (regulator_is_enabled(port->supply)) - regulator_disable(port->supply); - - tegra186_xusb_padctl_id_override(padctl, false); + err = tegra186_xusb_padctl_id_override(padctl, port, false); + if (err) + goto out; tegra186_xusb_padctl_vbus_override(padctl, false); } } - +out: mutex_unlock(&padctl->lock); - return err; } @@ -1710,7 +1726,8 @@ const struct tegra_xusb_padctl_soc tegra234_xusb_padctl_soc = { .num_supplies = ARRAY_SIZE(tegra194_xusb_padctl_supply_names), .supports_gen2 = true, .poll_trk_completed = true, - .trk_hw_mode = true, + .trk_hw_mode = false, + .trk_update_on_idle = true, .supports_lp_cfg_en = true, }; EXPORT_SYMBOL_GPL(tegra234_xusb_padctl_soc); diff --git a/drivers/phy/tegra/xusb.h b/drivers/phy/tegra/xusb.h index 6e45d194c689..d2b5f9565132 100644 --- a/drivers/phy/tegra/xusb.h +++ b/drivers/phy/tegra/xusb.h @@ -434,6 +434,7 @@ struct tegra_xusb_padctl_soc { bool need_fake_usb3_port; bool poll_trk_completed; bool trk_hw_mode; + bool trk_update_on_idle; bool supports_lp_cfg_en; }; diff --git a/drivers/pinctrl/nuvoton/pinctrl-ma35.c b/drivers/pinctrl/nuvoton/pinctrl-ma35.c index 06ae1fe8b8c5..b51704bafd81 100644 --- a/drivers/pinctrl/nuvoton/pinctrl-ma35.c +++ b/drivers/pinctrl/nuvoton/pinctrl-ma35.c @@ -1074,7 +1074,10 @@ static int ma35_pinctrl_probe_dt(struct platform_device *pdev, struct ma35_pinct u32 idx = 0; int ret; - for_each_gpiochip_node(dev, child) { + device_for_each_child_node(dev, child) { + if (fwnode_property_present(child, "gpio-controller")) + continue; + npctl->nfunctions++; npctl->ngroups += of_get_child_count(to_of_node(child)); } @@ -1092,7 +1095,10 @@ static int ma35_pinctrl_probe_dt(struct platform_device *pdev, struct ma35_pinct if (!npctl->groups) return -ENOMEM; - for_each_gpiochip_node(dev, child) { + device_for_each_child_node(dev, child) { + if (fwnode_property_present(child, "gpio-controller")) + continue; + ret = ma35_pinctrl_parse_functions(child, npctl, idx++); if (ret) { fwnode_handle_put(child); diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 5cf3db6d78b7..b3f0d02aeeb3 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -979,6 +979,17 @@ static int amd_gpio_suspend_hibernate_common(struct device *dev, bool is_suspend pin, is_suspend ? "suspend" : "hibernate"); } + /* + * debounce enabled over suspend has shown issues with a GPIO + * being unable to wake the system, as we're only interested in + * the actual wakeup event, clear it. + */ + if (gpio_dev->saved_regs[i] & (DB_CNTRl_MASK << DB_CNTRL_OFF)) { + amd_gpio_set_debounce(gpio_dev, pin, 0); + pm_pr_dbg("Clearing debounce for GPIO #%d during %s.\n", + pin, is_suspend ? "suspend" : "hibernate"); + } + raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); } diff --git a/drivers/pinctrl/pinctrl-aw9523.c b/drivers/pinctrl/pinctrl-aw9523.c index 9bf53de20be8..04afb344e9e5 100644 --- a/drivers/pinctrl/pinctrl-aw9523.c +++ b/drivers/pinctrl/pinctrl-aw9523.c @@ -784,7 +784,7 @@ static int aw9523_init_gpiochip(struct aw9523 *awi, unsigned int npins) gc->set_config = gpiochip_generic_config; gc->parent = dev; gc->owner = THIS_MODULE; - gc->can_sleep = false; + gc->can_sleep = true; return 0; } diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 5c4687de1464..f713c80d7f3e 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -1038,6 +1038,25 @@ static bool msm_gpio_needs_dual_edge_parent_workaround(struct irq_data *d, test_bit(d->hwirq, pctrl->skip_wake_irqs); } +static void msm_gpio_irq_init_valid_mask(struct gpio_chip *gc, + unsigned long *valid_mask, + unsigned int ngpios) +{ + struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + const struct msm_pingroup *g; + int i; + + bitmap_fill(valid_mask, ngpios); + + for (i = 0; i < ngpios; i++) { + g = &pctrl->soc->groups[i]; + + if (g->intr_detection_width != 1 && + g->intr_detection_width != 2) + clear_bit(i, valid_mask); + } +} + static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); @@ -1441,6 +1460,7 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_bad_irq; girq->parents[0] = pctrl->irq; + girq->init_valid_mask = msm_gpio_irq_init_valid_mask; ret = devm_gpiochip_add_data(pctrl->dev, &pctrl->chip, pctrl); if (ret) { diff --git a/drivers/platform/arm64/huawei-gaokun-ec.c b/drivers/platform/arm64/huawei-gaokun-ec.c index 7e5aa7ca2403..7170f8eb76f7 100644 --- a/drivers/platform/arm64/huawei-gaokun-ec.c +++ b/drivers/platform/arm64/huawei-gaokun-ec.c @@ -662,6 +662,7 @@ static void gaokun_aux_release(struct device *dev) { struct auxiliary_device *adev = to_auxiliary_dev(dev); + of_node_put(dev->of_node); kfree(adev); } @@ -693,6 +694,7 @@ static int gaokun_aux_init(struct device *parent, const char *name, ret = auxiliary_device_init(adev); if (ret) { + of_node_put(adev->dev.of_node); kfree(adev); return ret; } diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c index a1c529f1ff1a..4776013e0764 100644 --- a/drivers/platform/mellanox/mlxbf-pmc.c +++ b/drivers/platform/mellanox/mlxbf-pmc.c @@ -15,6 +15,7 @@ #include <linux/hwmon.h> #include <linux/platform_device.h> #include <linux/string.h> +#include <linux/string_helpers.h> #include <uapi/linux/psci.h> #define MLXBF_PMC_WRITE_REG_32 0x82000009 @@ -1222,7 +1223,7 @@ static int mlxbf_pmc_get_event_num(const char *blk, const char *evt) return -ENODEV; } -/* Get the event number given the name */ +/* Get the event name given the number */ static char *mlxbf_pmc_get_event_name(const char *blk, u32 evt) { const struct mlxbf_pmc_events *events; @@ -1784,6 +1785,7 @@ static ssize_t mlxbf_pmc_event_store(struct device *dev, attr, struct mlxbf_pmc_attribute, dev_attr); unsigned int blk_num, cnt_num; bool is_l3 = false; + char *evt_name; int evt_num; int err; @@ -1791,14 +1793,23 @@ static ssize_t mlxbf_pmc_event_store(struct device *dev, cnt_num = attr_event->index; if (isalpha(buf[0])) { + /* Remove the trailing newline character if present */ + evt_name = kstrdup_and_replace(buf, '\n', '\0', GFP_KERNEL); + if (!evt_name) + return -ENOMEM; + evt_num = mlxbf_pmc_get_event_num(pmc->block_name[blk_num], - buf); + evt_name); + kfree(evt_name); if (evt_num < 0) return -EINVAL; } else { err = kstrtouint(buf, 0, &evt_num); if (err < 0) return err; + + if (!mlxbf_pmc_get_event_name(pmc->block_name[blk_num], evt_num)) + return -EINVAL; } if (strstr(pmc->block_name[blk_num], "l3cache")) @@ -1879,13 +1890,14 @@ static ssize_t mlxbf_pmc_enable_store(struct device *dev, { struct mlxbf_pmc_attribute *attr_enable = container_of( attr, struct mlxbf_pmc_attribute, dev_attr); - unsigned int en, blk_num; + unsigned int blk_num; u32 word; int err; + bool en; blk_num = attr_enable->nr; - err = kstrtouint(buf, 0, &en); + err = kstrtobool(buf, &en); if (err < 0) return err; @@ -1905,14 +1917,11 @@ static ssize_t mlxbf_pmc_enable_store(struct device *dev, MLXBF_PMC_CRSPACE_PERFMON_CTL(pmc->block[blk_num].counters), MLXBF_PMC_WRITE_REG_32, word); } else { - if (en && en != 1) - return -EINVAL; - err = mlxbf_pmc_config_l3_counters(blk_num, false, !!en); if (err) return err; - if (en == 1) { + if (en) { err = mlxbf_pmc_config_l3_counters(blk_num, true, false); if (err) return err; diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile index abbc2644ff6d..bea87a85ae75 100644 --- a/drivers/platform/x86/Makefile +++ b/drivers/platform/x86/Makefile @@ -58,6 +58,8 @@ obj-$(CONFIG_X86_PLATFORM_DRIVERS_HP) += hp/ # Hewlett Packard Enterprise obj-$(CONFIG_UV_SYSFS) += uv_sysfs.o +obj-$(CONFIG_FW_ATTR_CLASS) += firmware_attributes_class.o + # IBM Thinkpad and Lenovo obj-$(CONFIG_IBM_RTL) += ibm_rtl.o obj-$(CONFIG_IDEAPAD_LAPTOP) += ideapad-laptop.o @@ -128,7 +130,6 @@ obj-$(CONFIG_SYSTEM76_ACPI) += system76_acpi.o obj-$(CONFIG_TOPSTAR_LAPTOP) += topstar-laptop.o # Platform drivers -obj-$(CONFIG_FW_ATTR_CLASS) += firmware_attributes_class.o obj-$(CONFIG_SERIAL_MULTI_INSTANTIATE) += serial-multi-instantiate.o obj-$(CONFIG_TOUCHSCREEN_DMI) += touchscreen_dmi.o obj-$(CONFIG_WIRELESS_HOTKEY) += wireless-hotkey.o diff --git a/drivers/platform/x86/dell/alienware-wmi-wmax.c b/drivers/platform/x86/dell/alienware-wmi-wmax.c index 20ec122a9fe0..b58cf74197f0 100644 --- a/drivers/platform/x86/dell/alienware-wmi-wmax.c +++ b/drivers/platform/x86/dell/alienware-wmi-wmax.c @@ -90,6 +90,14 @@ static struct awcc_quirks empty_quirks; static const struct dmi_system_id awcc_dmi_table[] __initconst = { { + .ident = "Alienware Area-51m", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware Area-51m"), + }, + .driver_data = &generic_quirks, + }, + { .ident = "Alienware Area-51m R2", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), @@ -98,6 +106,14 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = { .driver_data = &generic_quirks, }, { + .ident = "Alienware m15 R5", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m15 R5"), + }, + .driver_data = &generic_quirks, + }, + { .ident = "Alienware m15 R7", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), @@ -233,6 +249,7 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = { }, .driver_data = &g_series_quirks, }, + {} }; enum AWCC_GET_FAN_SENSORS_OPERATIONS { diff --git a/drivers/platform/x86/dell/dell-lis3lv02d.c b/drivers/platform/x86/dell/dell-lis3lv02d.c index 0791118dd6b7..732de5f556f8 100644 --- a/drivers/platform/x86/dell/dell-lis3lv02d.c +++ b/drivers/platform/x86/dell/dell-lis3lv02d.c @@ -49,6 +49,7 @@ static const struct dmi_system_id lis3lv02d_devices[] __initconst = { DELL_LIS3LV02D_DMI_ENTRY("Latitude E6330", 0x29), DELL_LIS3LV02D_DMI_ENTRY("Latitude E6430", 0x29), DELL_LIS3LV02D_DMI_ENTRY("Precision 3540", 0x29), + DELL_LIS3LV02D_DMI_ENTRY("Precision 3551", 0x29), DELL_LIS3LV02D_DMI_ENTRY("Precision M6800", 0x29), DELL_LIS3LV02D_DMI_ENTRY("Vostro V131", 0x1d), DELL_LIS3LV02D_DMI_ENTRY("Vostro 5568", 0x29), diff --git a/drivers/platform/x86/dell/dell-wmi-ddv.c b/drivers/platform/x86/dell/dell-wmi-ddv.c index 67f3d7158403..62e3d060f038 100644 --- a/drivers/platform/x86/dell/dell-wmi-ddv.c +++ b/drivers/platform/x86/dell/dell-wmi-ddv.c @@ -689,9 +689,13 @@ static int dell_wmi_ddv_battery_translate(struct dell_wmi_ddv_data *data, dev_dbg(&data->wdev->dev, "Translation cache miss\n"); - /* Perform a translation between a ACPI battery and a battery index */ - - ret = power_supply_get_property(battery, POWER_SUPPLY_PROP_SERIAL_NUMBER, &val); + /* + * Perform a translation between a ACPI battery and a battery index. + * We have to use power_supply_get_property_direct() here because this + * function will also get called from the callbacks of the power supply + * extension. + */ + ret = power_supply_get_property_direct(battery, POWER_SUPPLY_PROP_SERIAL_NUMBER, &val); if (ret < 0) return ret; diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index b5e4da6a6779..edb9d2fb02ec 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -1669,7 +1669,7 @@ static int ideapad_kbd_bl_init(struct ideapad_private *priv) priv->kbd_bl.led.name = "platform::" LED_FUNCTION_KBD_BACKLIGHT; priv->kbd_bl.led.brightness_get = ideapad_kbd_bl_led_cdev_brightness_get; priv->kbd_bl.led.brightness_set_blocking = ideapad_kbd_bl_led_cdev_brightness_set; - priv->kbd_bl.led.flags = LED_BRIGHT_HW_CHANGED; + priv->kbd_bl.led.flags = LED_BRIGHT_HW_CHANGED | LED_RETAIN_AT_SHUTDOWN; err = led_classdev_register(&priv->platform_device->dev, &priv->kbd_bl.led); if (err) @@ -1728,7 +1728,7 @@ static int ideapad_fn_lock_led_init(struct ideapad_private *priv) priv->fn_lock.led.name = "platform::" LED_FUNCTION_FNLOCK; priv->fn_lock.led.brightness_get = ideapad_fn_lock_led_cdev_get; priv->fn_lock.led.brightness_set_blocking = ideapad_fn_lock_led_cdev_set; - priv->fn_lock.led.flags = LED_BRIGHT_HW_CHANGED; + priv->fn_lock.led.flags = LED_BRIGHT_HW_CHANGED | LED_RETAIN_AT_SHUTDOWN; err = led_classdev_register(&priv->platform_device->dev, &priv->fn_lock.led); if (err) diff --git a/drivers/platform/x86/lenovo-wmi-hotkey-utilities.c b/drivers/platform/x86/lenovo-wmi-hotkey-utilities.c index 89153afd7015..7b9bad1978ff 100644 --- a/drivers/platform/x86/lenovo-wmi-hotkey-utilities.c +++ b/drivers/platform/x86/lenovo-wmi-hotkey-utilities.c @@ -122,26 +122,35 @@ static int lenovo_super_hotkey_wmi_led_init(enum mute_led_type led_type, struct return -EIO; union acpi_object *obj __free(kfree) = output.pointer; - if (obj && obj->type == ACPI_TYPE_INTEGER) - led_version = obj->integer.value; - else + if (!obj || obj->type != ACPI_TYPE_INTEGER) return -EIO; - wpriv->cdev[led_type].max_brightness = LED_ON; - wpriv->cdev[led_type].flags = LED_CORE_SUSPENDRESUME; + led_version = obj->integer.value; + + /* + * Output parameters define: 0 means mute LED is not supported, Non-zero means + * mute LED can be supported. + */ + if (led_version == 0) + return 0; + switch (led_type) { case MIC_MUTE: - if (led_version != WMI_LUD_SUPPORT_MICMUTE_LED_VER) - return -EIO; + if (led_version != WMI_LUD_SUPPORT_MICMUTE_LED_VER) { + pr_warn("The MIC_MUTE LED of this device isn't supported.\n"); + return 0; + } wpriv->cdev[led_type].name = "platform::micmute"; wpriv->cdev[led_type].brightness_set_blocking = &lsh_wmi_micmute_led_set; wpriv->cdev[led_type].default_trigger = "audio-micmute"; break; case AUDIO_MUTE: - if (led_version != WMI_LUD_SUPPORT_AUDIOMUTE_LED_VER) - return -EIO; + if (led_version != WMI_LUD_SUPPORT_AUDIOMUTE_LED_VER) { + pr_warn("The AUDIO_MUTE LED of this device isn't supported.\n"); + return 0; + } wpriv->cdev[led_type].name = "platform::mute"; wpriv->cdev[led_type].brightness_set_blocking = &lsh_wmi_audiomute_led_set; @@ -152,6 +161,9 @@ static int lenovo_super_hotkey_wmi_led_init(enum mute_led_type led_type, struct return -EINVAL; } + wpriv->cdev[led_type].max_brightness = LED_ON; + wpriv->cdev[led_type].flags = LED_CORE_SUSPENDRESUME; + err = devm_led_classdev_register(dev, &wpriv->cdev[led_type]); if (err < 0) { dev_err(dev, "Could not register mute LED %d : %d\n", led_type, err); diff --git a/drivers/pmdomain/governor.c b/drivers/pmdomain/governor.c index c1e148657c87..39359811a930 100644 --- a/drivers/pmdomain/governor.c +++ b/drivers/pmdomain/governor.c @@ -8,6 +8,7 @@ #include <linux/pm_domain.h> #include <linux/pm_qos.h> #include <linux/hrtimer.h> +#include <linux/cpu.h> #include <linux/cpuidle.h> #include <linux/cpumask.h> #include <linux/ktime.h> @@ -349,6 +350,8 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd) struct cpuidle_device *dev; ktime_t domain_wakeup, next_hrtimer; ktime_t now = ktime_get(); + struct device *cpu_dev; + s64 cpu_constraint, global_constraint; s64 idle_duration_ns; int cpu, i; @@ -359,6 +362,7 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd) if (!(genpd->flags & GENPD_FLAG_CPU_DOMAIN)) return true; + global_constraint = cpu_latency_qos_limit(); /* * Find the next wakeup for any of the online CPUs within the PM domain * and its subdomains. Note, we only need the genpd->cpus, as it already @@ -372,8 +376,16 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd) if (ktime_before(next_hrtimer, domain_wakeup)) domain_wakeup = next_hrtimer; } + + cpu_dev = get_cpu_device(cpu); + if (cpu_dev) { + cpu_constraint = dev_pm_qos_raw_resume_latency(cpu_dev); + if (cpu_constraint < global_constraint) + global_constraint = cpu_constraint; + } } + global_constraint *= NSEC_PER_USEC; /* The minimum idle duration is from now - until the next wakeup. */ idle_duration_ns = ktime_to_ns(ktime_sub(domain_wakeup, now)); if (idle_duration_ns <= 0) @@ -389,8 +401,10 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd) */ i = genpd->state_idx; do { - if (idle_duration_ns >= (genpd->states[i].residency_ns + - genpd->states[i].power_off_latency_ns)) { + if ((idle_duration_ns >= (genpd->states[i].residency_ns + + genpd->states[i].power_off_latency_ns)) && + (global_constraint >= (genpd->states[i].power_on_latency_ns + + genpd->states[i].power_off_latency_ns))) { genpd->state_idx = i; genpd->gd->last_enter = now; genpd->gd->reflect_residency = true; diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index 33a5bfce4604..cfb0e3e0d4aa 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -1235,9 +1235,8 @@ bool power_supply_has_property(struct power_supply *psy, return false; } -int power_supply_get_property(struct power_supply *psy, - enum power_supply_property psp, - union power_supply_propval *val) +static int __power_supply_get_property(struct power_supply *psy, enum power_supply_property psp, + union power_supply_propval *val, bool use_extensions) { struct power_supply_ext_registration *reg; @@ -1247,10 +1246,14 @@ int power_supply_get_property(struct power_supply *psy, return -ENODEV; } - scoped_guard(rwsem_read, &psy->extensions_sem) { - power_supply_for_each_extension(reg, psy) { - if (power_supply_ext_has_property(reg->ext, psp)) + if (use_extensions) { + scoped_guard(rwsem_read, &psy->extensions_sem) { + power_supply_for_each_extension(reg, psy) { + if (!power_supply_ext_has_property(reg->ext, psp)) + continue; + return reg->ext->get_property(psy, reg->ext, reg->data, psp, val); + } } } @@ -1261,20 +1264,49 @@ int power_supply_get_property(struct power_supply *psy, else return -EINVAL; } + +int power_supply_get_property(struct power_supply *psy, enum power_supply_property psp, + union power_supply_propval *val) +{ + return __power_supply_get_property(psy, psp, val, true); +} EXPORT_SYMBOL_GPL(power_supply_get_property); -int power_supply_set_property(struct power_supply *psy, - enum power_supply_property psp, - const union power_supply_propval *val) +/** + * power_supply_get_property_direct - Read a power supply property without checking for extensions + * @psy: The power supply + * @psp: The power supply property to read + * @val: The resulting value of the power supply property + * + * Read a power supply property without taking into account any power supply extensions registered + * on the given power supply. This is mostly useful for power supply extensions that want to access + * their own power supply as using power_supply_get_property() directly will result in a potential + * deadlock. + * + * Return: 0 on success or negative error code on failure. + */ +int power_supply_get_property_direct(struct power_supply *psy, enum power_supply_property psp, + union power_supply_propval *val) +{ + return __power_supply_get_property(psy, psp, val, false); +} +EXPORT_SYMBOL_GPL(power_supply_get_property_direct); + + +static int __power_supply_set_property(struct power_supply *psy, enum power_supply_property psp, + const union power_supply_propval *val, bool use_extensions) { struct power_supply_ext_registration *reg; if (atomic_read(&psy->use_cnt) <= 0) return -ENODEV; - scoped_guard(rwsem_read, &psy->extensions_sem) { - power_supply_for_each_extension(reg, psy) { - if (power_supply_ext_has_property(reg->ext, psp)) { + if (use_extensions) { + scoped_guard(rwsem_read, &psy->extensions_sem) { + power_supply_for_each_extension(reg, psy) { + if (!power_supply_ext_has_property(reg->ext, psp)) + continue; + if (reg->ext->set_property) return reg->ext->set_property(psy, reg->ext, reg->data, psp, val); @@ -1289,8 +1321,34 @@ int power_supply_set_property(struct power_supply *psy, return psy->desc->set_property(psy, psp, val); } + +int power_supply_set_property(struct power_supply *psy, enum power_supply_property psp, + const union power_supply_propval *val) +{ + return __power_supply_set_property(psy, psp, val, true); +} EXPORT_SYMBOL_GPL(power_supply_set_property); +/** + * power_supply_set_property_direct - Write a power supply property without checking for extensions + * @psy: The power supply + * @psp: The power supply property to write + * @val: The value to write to the power supply property + * + * Write a power supply property without taking into account any power supply extensions registered + * on the given power supply. This is mostly useful for power supply extensions that want to access + * their own power supply as using power_supply_set_property() directly will result in a potential + * deadlock. + * + * Return: 0 on success or negative error code on failure. + */ +int power_supply_set_property_direct(struct power_supply *psy, enum power_supply_property psp, + const union power_supply_propval *val) +{ + return __power_supply_set_property(psy, psp, val, false); +} +EXPORT_SYMBOL_GPL(power_supply_set_property_direct); + int power_supply_property_is_writeable(struct power_supply *psy, enum power_supply_property psp) { diff --git a/drivers/power/supply/test_power.c b/drivers/power/supply/test_power.c index 5bfdfcf6013b..2c0e9ad820c0 100644 --- a/drivers/power/supply/test_power.c +++ b/drivers/power/supply/test_power.c @@ -259,6 +259,7 @@ static const struct power_supply_config test_power_configs[] = { static int test_power_battery_extmanufacture_year = 1234; static int test_power_battery_exttemp_max = 1000; static const enum power_supply_property test_power_battery_extprops[] = { + POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW, POWER_SUPPLY_PROP_MANUFACTURE_YEAR, POWER_SUPPLY_PROP_TEMP_MAX, }; @@ -270,6 +271,9 @@ static int test_power_battery_extget_property(struct power_supply *psy, union power_supply_propval *val) { switch (psp) { + case POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW: + return power_supply_get_property_direct(psy, POWER_SUPPLY_PROP_TIME_TO_EMPTY_AVG, + val); case POWER_SUPPLY_PROP_MANUFACTURE_YEAR: val->intval = test_power_battery_extmanufacture_year; break; diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index 4d842c692194..edf776b8ad53 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -596,7 +596,7 @@ static bool pwm_state_valid(const struct pwm_state *state) * and supposed to be ignored. So also ignore any strange values and * consider the state ok. */ - if (state->enabled) + if (!state->enabled) return true; if (!state->period) diff --git a/drivers/pwm/pwm-mediatek.c b/drivers/pwm/pwm-mediatek.c index 7eaab5831499..33d3554b9197 100644 --- a/drivers/pwm/pwm-mediatek.c +++ b/drivers/pwm/pwm-mediatek.c @@ -130,8 +130,10 @@ static int pwm_mediatek_config(struct pwm_chip *chip, struct pwm_device *pwm, return ret; clk_rate = clk_get_rate(pc->clk_pwms[pwm->hwpwm]); - if (!clk_rate) - return -EINVAL; + if (!clk_rate) { + ret = -EINVAL; + goto out; + } /* Make sure we use the bus clock and not the 26MHz clock */ if (pc->soc->has_ck_26m_sel) @@ -150,9 +152,9 @@ static int pwm_mediatek_config(struct pwm_chip *chip, struct pwm_device *pwm, } if (clkdiv > PWM_CLK_DIV_MAX) { - pwm_mediatek_clk_disable(chip, pwm); dev_err(pwmchip_parent(chip), "period of %d ns not supported\n", period_ns); - return -EINVAL; + ret = -EINVAL; + goto out; } if (pc->soc->pwm45_fixup && pwm->hwpwm > 2) { @@ -169,9 +171,10 @@ static int pwm_mediatek_config(struct pwm_chip *chip, struct pwm_device *pwm, pwm_mediatek_writel(pc, pwm->hwpwm, reg_width, cnt_period); pwm_mediatek_writel(pc, pwm->hwpwm, reg_thres, cnt_duty); +out: pwm_mediatek_clk_disable(chip, pwm); - return 0; + return ret; } static int pwm_mediatek_enable(struct pwm_chip *chip, struct pwm_device *pwm) diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index b7f15f303ea2..967dc4f9eea8 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -130,6 +130,7 @@ static int ism_cmd(struct ism_dev *ism, void *cmd) struct ism_req_hdr *req = cmd; struct ism_resp_hdr *resp = cmd; + spin_lock(&ism->cmd_lock); __ism_write_cmd(ism, req + 1, sizeof(*req), req->len - sizeof(*req)); __ism_write_cmd(ism, req, 0, sizeof(*req)); @@ -143,6 +144,7 @@ static int ism_cmd(struct ism_dev *ism, void *cmd) } __ism_read_cmd(ism, resp + 1, sizeof(*resp), resp->len - sizeof(*resp)); out: + spin_unlock(&ism->cmd_lock); return resp->ret; } @@ -606,6 +608,7 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) return -ENOMEM; spin_lock_init(&ism->lock); + spin_lock_init(&ism->cmd_lock); dev_set_drvdata(&pdev->dev, ism); ism->pdev = pdev; ism->dev.parent = &pdev->dev; diff --git a/drivers/soc/aspeed/aspeed-lpc-snoop.c b/drivers/soc/aspeed/aspeed-lpc-snoop.c index ef8f355589a5..fc3a2c41cc10 100644 --- a/drivers/soc/aspeed/aspeed-lpc-snoop.c +++ b/drivers/soc/aspeed/aspeed-lpc-snoop.c @@ -58,6 +58,7 @@ struct aspeed_lpc_snoop_model_data { }; struct aspeed_lpc_snoop_channel { + bool enabled; struct kfifo fifo; wait_queue_head_t wq; struct miscdevice miscdev; @@ -190,6 +191,9 @@ static int aspeed_lpc_enable_snoop(struct aspeed_lpc_snoop *lpc_snoop, const struct aspeed_lpc_snoop_model_data *model_data = of_device_get_match_data(dev); + if (WARN_ON(lpc_snoop->chan[channel].enabled)) + return -EBUSY; + init_waitqueue_head(&lpc_snoop->chan[channel].wq); /* Create FIFO datastructure */ rc = kfifo_alloc(&lpc_snoop->chan[channel].fifo, @@ -236,6 +240,8 @@ static int aspeed_lpc_enable_snoop(struct aspeed_lpc_snoop *lpc_snoop, regmap_update_bits(lpc_snoop->regmap, HICRB, hicrb_en, hicrb_en); + lpc_snoop->chan[channel].enabled = true; + return 0; err_misc_deregister: @@ -248,6 +254,9 @@ err_free_fifo: static void aspeed_lpc_disable_snoop(struct aspeed_lpc_snoop *lpc_snoop, int channel) { + if (!lpc_snoop->chan[channel].enabled) + return; + switch (channel) { case 0: regmap_update_bits(lpc_snoop->regmap, HICR5, @@ -263,8 +272,10 @@ static void aspeed_lpc_disable_snoop(struct aspeed_lpc_snoop *lpc_snoop, return; } - kfifo_free(&lpc_snoop->chan[channel].fifo); + lpc_snoop->chan[channel].enabled = false; + /* Consider improving safety wrt concurrent reader(s) */ misc_deregister(&lpc_snoop->chan[channel].miscdev); + kfifo_free(&lpc_snoop->chan[channel].fifo); } static int aspeed_lpc_snoop_probe(struct platform_device *pdev) diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c index a12c68b93b1c..7a671a786197 100644 --- a/drivers/soundwire/amd_manager.c +++ b/drivers/soundwire/amd_manager.c @@ -238,7 +238,7 @@ static u64 amd_sdw_send_cmd_get_resp(struct amd_sdw_manager *amd_manager, u32 lo if (sts & AMD_SDW_IMM_RES_VALID) { dev_err(amd_manager->dev, "SDW%x manager is in bad state\n", amd_manager->instance); - writel(0x00, amd_manager->mmio + ACP_SW_IMM_CMD_STS); + writel(AMD_SDW_IMM_RES_VALID, amd_manager->mmio + ACP_SW_IMM_CMD_STS); } writel(upper_data, amd_manager->mmio + ACP_SW_IMM_CMD_UPPER_WORD); writel(lower_data, amd_manager->mmio + ACP_SW_IMM_CMD_LOWER_QWORD); @@ -1209,6 +1209,7 @@ static int __maybe_unused amd_suspend(struct device *dev) } if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) { + cancel_work_sync(&amd_manager->amd_sdw_work); amd_sdw_wake_enable(amd_manager, false); if (amd_manager->acp_rev >= ACP70_PCI_REV_ID) { ret = amd_sdw_host_wake_enable(amd_manager, false); @@ -1219,6 +1220,7 @@ static int __maybe_unused amd_suspend(struct device *dev) if (ret) return ret; } else if (amd_manager->power_mode_mask & AMD_SDW_POWER_OFF_MODE) { + cancel_work_sync(&amd_manager->amd_sdw_work); amd_sdw_wake_enable(amd_manager, false); if (amd_manager->acp_rev >= ACP70_PCI_REV_ID) { ret = amd_sdw_host_wake_enable(amd_manager, false); diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c index 295a46dc2be7..0f45e3404756 100644 --- a/drivers/soundwire/qcom.c +++ b/drivers/soundwire/qcom.c @@ -156,7 +156,6 @@ struct qcom_swrm_port_config { u8 word_length; u8 blk_group_count; u8 lane_control; - u8 ch_mask; }; /* @@ -1049,13 +1048,9 @@ static int qcom_swrm_port_enable(struct sdw_bus *bus, { u32 reg = SWRM_DP_PORT_CTRL_BANK(enable_ch->port_num, bank); struct qcom_swrm_ctrl *ctrl = to_qcom_sdw(bus); - struct qcom_swrm_port_config *pcfg; u32 val; - pcfg = &ctrl->pconfig[enable_ch->port_num]; ctrl->reg_read(ctrl, reg, &val); - if (pcfg->ch_mask != SWR_INVALID_PARAM && pcfg->ch_mask != 0) - enable_ch->ch_mask = pcfg->ch_mask; if (enable_ch->enable) val |= (enable_ch->ch_mask << SWRM_DP_PORT_CTRL_EN_CHAN_SHFT); @@ -1275,26 +1270,6 @@ static void *qcom_swrm_get_sdw_stream(struct snd_soc_dai *dai, int direction) return ctrl->sruntime[dai->id]; } -static int qcom_swrm_set_channel_map(struct snd_soc_dai *dai, - unsigned int tx_num, const unsigned int *tx_slot, - unsigned int rx_num, const unsigned int *rx_slot) -{ - struct qcom_swrm_ctrl *ctrl = dev_get_drvdata(dai->dev); - int i; - - if (tx_slot) { - for (i = 0; i < tx_num; i++) - ctrl->pconfig[i].ch_mask = tx_slot[i]; - } - - if (rx_slot) { - for (i = 0; i < rx_num; i++) - ctrl->pconfig[i].ch_mask = rx_slot[i]; - } - - return 0; -} - static int qcom_swrm_startup(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { @@ -1331,7 +1306,6 @@ static const struct snd_soc_dai_ops qcom_swrm_pdm_dai_ops = { .shutdown = qcom_swrm_shutdown, .set_stream = qcom_swrm_set_sdw_stream, .get_stream = qcom_swrm_get_sdw_stream, - .set_channel_map = qcom_swrm_set_channel_map, }; static const struct snd_soc_component_driver qcom_swrm_dai_component = { diff --git a/drivers/spi/spi-qpic-snand.c b/drivers/spi/spi-qpic-snand.c index f2e1a27b410d..3b757e3d00c0 100644 --- a/drivers/spi/spi-qpic-snand.c +++ b/drivers/spi/spi-qpic-snand.c @@ -308,7 +308,7 @@ static int qcom_spi_ecc_init_ctx_pipelined(struct nand_device *nand) ecc_cfg->bch_enabled = true; ecc_cfg->bytes = ecc_cfg->ecc_bytes_hw + ecc_cfg->spare_bytes + ecc_cfg->bbm_size; - ecc_cfg->steps = 4; + ecc_cfg->steps = cwperpage; ecc_cfg->cw_data = 516; ecc_cfg->cw_size = ecc_cfg->cw_data + ecc_cfg->bytes; bad_block_byte = mtd->writesize - ecc_cfg->cw_size * (cwperpage - 1) + 1; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 1bc0fdbb1bd7..0ffa3f9f2870 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -4138,10 +4138,13 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) xfer->tx_nbits != SPI_NBITS_OCTAL) return -EINVAL; if ((xfer->tx_nbits == SPI_NBITS_DUAL) && - !(spi->mode & (SPI_TX_DUAL | SPI_TX_QUAD))) + !(spi->mode & (SPI_TX_DUAL | SPI_TX_QUAD | SPI_TX_OCTAL))) return -EINVAL; if ((xfer->tx_nbits == SPI_NBITS_QUAD) && - !(spi->mode & SPI_TX_QUAD)) + !(spi->mode & (SPI_TX_QUAD | SPI_TX_OCTAL))) + return -EINVAL; + if ((xfer->tx_nbits == SPI_NBITS_OCTAL) && + !(spi->mode & SPI_TX_OCTAL)) return -EINVAL; } /* Check transfer rx_nbits */ @@ -4154,10 +4157,13 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) xfer->rx_nbits != SPI_NBITS_OCTAL) return -EINVAL; if ((xfer->rx_nbits == SPI_NBITS_DUAL) && - !(spi->mode & (SPI_RX_DUAL | SPI_RX_QUAD))) + !(spi->mode & (SPI_RX_DUAL | SPI_RX_QUAD | SPI_RX_OCTAL))) return -EINVAL; if ((xfer->rx_nbits == SPI_NBITS_QUAD) && - !(spi->mode & SPI_RX_QUAD)) + !(spi->mode & (SPI_RX_QUAD | SPI_RX_OCTAL))) + return -EINVAL; + if ((xfer->rx_nbits == SPI_NBITS_OCTAL) && + !(spi->mode & SPI_RX_OCTAL)) return -EINVAL; } diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c index 5dbf8d53db09..721b15b7e13b 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c @@ -97,6 +97,13 @@ struct vchiq_arm_state { * tracked separately with the state. */ int peer_use_count; + + /* + * Flag to indicate that the first vchiq connect has made it through. + * This means that both sides should be fully ready, and we should + * be able to suspend after this point. + */ + int first_connect; }; static int @@ -273,6 +280,29 @@ static int vchiq_platform_init(struct platform_device *pdev, struct vchiq_state return 0; } +int +vchiq_platform_init_state(struct vchiq_state *state) +{ + struct vchiq_arm_state *platform_state; + + platform_state = devm_kzalloc(state->dev, sizeof(*platform_state), GFP_KERNEL); + if (!platform_state) + return -ENOMEM; + + rwlock_init(&platform_state->susp_res_lock); + + init_completion(&platform_state->ka_evt); + atomic_set(&platform_state->ka_use_count, 0); + atomic_set(&platform_state->ka_use_ack_count, 0); + atomic_set(&platform_state->ka_release_count, 0); + + platform_state->state = state; + + state->platform_state = (struct opaque_platform_state *)platform_state; + + return 0; +} + static struct vchiq_arm_state *vchiq_platform_get_arm_state(struct vchiq_state *state) { return (struct vchiq_arm_state *)state->platform_state; @@ -363,8 +393,7 @@ int vchiq_shutdown(struct vchiq_instance *instance) struct vchiq_state *state = instance->state; int ret = 0; - if (mutex_lock_killable(&state->mutex)) - return -EAGAIN; + mutex_lock(&state->mutex); /* Remove all services */ vchiq_shutdown_internal(state, instance); @@ -982,39 +1011,6 @@ exit: } int -vchiq_platform_init_state(struct vchiq_state *state) -{ - struct vchiq_arm_state *platform_state; - char threadname[16]; - - platform_state = devm_kzalloc(state->dev, sizeof(*platform_state), GFP_KERNEL); - if (!platform_state) - return -ENOMEM; - - snprintf(threadname, sizeof(threadname), "vchiq-keep/%d", - state->id); - platform_state->ka_thread = kthread_create(&vchiq_keepalive_thread_func, - (void *)state, threadname); - if (IS_ERR(platform_state->ka_thread)) { - dev_err(state->dev, "couldn't create thread %s\n", threadname); - return PTR_ERR(platform_state->ka_thread); - } - - rwlock_init(&platform_state->susp_res_lock); - - init_completion(&platform_state->ka_evt); - atomic_set(&platform_state->ka_use_count, 0); - atomic_set(&platform_state->ka_use_ack_count, 0); - atomic_set(&platform_state->ka_release_count, 0); - - platform_state->state = state; - - state->platform_state = (struct opaque_platform_state *)platform_state; - - return 0; -} - -int vchiq_use_internal(struct vchiq_state *state, struct vchiq_service *service, enum USE_TYPE_E use_type) { @@ -1329,19 +1325,37 @@ out: return ret; } -void vchiq_platform_connected(struct vchiq_state *state) -{ - struct vchiq_arm_state *arm_state = vchiq_platform_get_arm_state(state); - - wake_up_process(arm_state->ka_thread); -} - void vchiq_platform_conn_state_changed(struct vchiq_state *state, enum vchiq_connstate oldstate, enum vchiq_connstate newstate) { + struct vchiq_arm_state *arm_state = vchiq_platform_get_arm_state(state); + char threadname[16]; + dev_dbg(state->dev, "suspend: %d: %s->%s\n", state->id, get_conn_state_name(oldstate), get_conn_state_name(newstate)); + if (state->conn_state != VCHIQ_CONNSTATE_CONNECTED) + return; + + write_lock_bh(&arm_state->susp_res_lock); + if (arm_state->first_connect) { + write_unlock_bh(&arm_state->susp_res_lock); + return; + } + + arm_state->first_connect = 1; + write_unlock_bh(&arm_state->susp_res_lock); + snprintf(threadname, sizeof(threadname), "vchiq-keep/%d", + state->id); + arm_state->ka_thread = kthread_create(&vchiq_keepalive_thread_func, + (void *)state, + threadname); + if (IS_ERR(arm_state->ka_thread)) { + dev_err(state->dev, "suspend: Couldn't create thread %s\n", + threadname); + } else { + wake_up_process(arm_state->ka_thread); + } } static const struct of_device_id vchiq_of_match[] = { diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c index e7b0c800a205..e2cac0898b8f 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c @@ -3343,7 +3343,6 @@ vchiq_connect_internal(struct vchiq_state *state, struct vchiq_instance *instanc return -EAGAIN; vchiq_set_conn_state(state, VCHIQ_CONNSTATE_CONNECTED); - vchiq_platform_connected(state); complete(&state->connect); } diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h index 3b5c0618e567..9b4e766990a4 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h @@ -575,8 +575,6 @@ int vchiq_send_remote_use(struct vchiq_state *state); int vchiq_send_remote_use_active(struct vchiq_state *state); -void vchiq_platform_connected(struct vchiq_state *state); - void vchiq_platform_conn_state_changed(struct vchiq_state *state, enum vchiq_connstate oldstate, enum vchiq_connstate newstate); diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 28febb95f8fa..b6c58a7e7b6a 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -1450,7 +1450,7 @@ int tb_dp_port_set_hops(struct tb_port *port, unsigned int video, return ret; data[0] &= ~ADP_DP_CS_0_VIDEO_HOPID_MASK; - data[1] &= ~ADP_DP_CS_1_AUX_RX_HOPID_MASK; + data[1] &= ~ADP_DP_CS_1_AUX_TX_HOPID_MASK; data[1] &= ~ADP_DP_CS_1_AUX_RX_HOPID_MASK; data[0] |= (video << ADP_DP_CS_0_VIDEO_HOPID_SHIFT) & @@ -3437,7 +3437,7 @@ void tb_sw_set_unplugged(struct tb_switch *sw) } } -static int tb_switch_set_wake(struct tb_switch *sw, unsigned int flags) +static int tb_switch_set_wake(struct tb_switch *sw, unsigned int flags, bool runtime) { if (flags) tb_sw_dbg(sw, "enabling wakeup: %#x\n", flags); @@ -3445,7 +3445,7 @@ static int tb_switch_set_wake(struct tb_switch *sw, unsigned int flags) tb_sw_dbg(sw, "disabling wakeup\n"); if (tb_switch_is_usb4(sw)) - return usb4_switch_set_wake(sw, flags); + return usb4_switch_set_wake(sw, flags, runtime); return tb_lc_set_wake(sw, flags); } @@ -3521,7 +3521,7 @@ int tb_switch_resume(struct tb_switch *sw, bool runtime) tb_switch_check_wakes(sw); /* Disable wakes */ - tb_switch_set_wake(sw, 0); + tb_switch_set_wake(sw, 0, true); err = tb_switch_tmu_init(sw); if (err) @@ -3603,7 +3603,7 @@ void tb_switch_suspend(struct tb_switch *sw, bool runtime) flags |= TB_WAKE_ON_USB4 | TB_WAKE_ON_USB3 | TB_WAKE_ON_PCIE; } - tb_switch_set_wake(sw, flags); + tb_switch_set_wake(sw, flags, runtime); if (tb_switch_is_usb4(sw)) usb4_switch_set_sleep(sw); diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 87afd5a7c504..f503bad86413 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -1317,7 +1317,7 @@ int usb4_switch_read_uid(struct tb_switch *sw, u64 *uid); int usb4_switch_drom_read(struct tb_switch *sw, unsigned int address, void *buf, size_t size); bool usb4_switch_lane_bonding_possible(struct tb_switch *sw); -int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags); +int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags, bool runtime); int usb4_switch_set_sleep(struct tb_switch *sw); int usb4_switch_nvm_sector_size(struct tb_switch *sw); int usb4_switch_nvm_read(struct tb_switch *sw, unsigned int address, void *buf, diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index fce3c0f2354a..fdae76c8f728 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -403,12 +403,12 @@ bool usb4_switch_lane_bonding_possible(struct tb_switch *sw) * usb4_switch_set_wake() - Enabled/disable wake * @sw: USB4 router * @flags: Wakeup flags (%0 to disable) + * @runtime: Wake is being programmed during system runtime * * Enables/disables router to wake up from sleep. */ -int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags) +int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags, bool runtime) { - struct usb4_port *usb4; struct tb_port *port; u64 route = tb_route(sw); u32 val; @@ -438,13 +438,11 @@ int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags) val |= PORT_CS_19_WOU4; } else { bool configured = val & PORT_CS_19_PC; - usb4 = port->usb4; + bool wakeup = runtime || device_may_wakeup(&port->usb4->dev); - if (((flags & TB_WAKE_ON_CONNECT) && - device_may_wakeup(&usb4->dev)) && !configured) + if ((flags & TB_WAKE_ON_CONNECT) && wakeup && !configured) val |= PORT_CS_19_WOC; - if (((flags & TB_WAKE_ON_DISCONNECT) && - device_may_wakeup(&usb4->dev)) && configured) + if ((flags & TB_WAKE_ON_DISCONNECT) && wakeup && configured) val |= PORT_CS_19_WOD; if ((flags & TB_WAKE_ON_USB4) && configured) val |= PORT_CS_19_WOU4; diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c index 508e8c6f01d4..884fefbfd5a1 100644 --- a/drivers/tty/serial/pch_uart.c +++ b/drivers/tty/serial/pch_uart.c @@ -954,7 +954,7 @@ static unsigned int dma_handle_tx(struct eg20t_port *priv) __func__); return 0; } - dma_sync_sg_for_device(port->dev, priv->sg_tx_p, nent, DMA_TO_DEVICE); + dma_sync_sg_for_device(port->dev, priv->sg_tx_p, num, DMA_TO_DEVICE); priv->desc_tx = desc; desc->callback = pch_dma_tx_complete; desc->callback_param = priv; diff --git a/drivers/tty/serial/serial_base_bus.c b/drivers/tty/serial/serial_base_bus.c index cb3b127b06b6..22749ab0428a 100644 --- a/drivers/tty/serial/serial_base_bus.c +++ b/drivers/tty/serial/serial_base_bus.c @@ -13,6 +13,7 @@ #include <linux/device.h> #include <linux/idr.h> #include <linux/module.h> +#include <linux/of.h> #include <linux/serial_core.h> #include <linux/slab.h> #include <linux/spinlock.h> @@ -93,6 +94,7 @@ static void serial_base_ctrl_release(struct device *dev) { struct serial_ctrl_device *ctrl_dev = to_serial_base_ctrl_device(dev); + of_node_put(dev->of_node); kfree(ctrl_dev); } @@ -140,6 +142,7 @@ static void serial_base_port_release(struct device *dev) { struct serial_port_device *port_dev = to_serial_base_port_device(dev); + of_node_put(dev->of_node); kfree(port_dev); } diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 3e1215f7a9a0..256fe8c86828 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -5751,6 +5751,7 @@ static void port_event(struct usb_hub *hub, int port1) struct usb_device *hdev = hub->hdev; u16 portstatus, portchange; int i = 0; + int err; connect_change = test_bit(port1, hub->change_bits); clear_bit(port1, hub->event_bits); @@ -5847,8 +5848,11 @@ static void port_event(struct usb_hub *hub, int port1) } else if (!udev || !(portstatus & USB_PORT_STAT_CONNECTION) || udev->state == USB_STATE_NOTATTACHED) { dev_dbg(&port_dev->dev, "do warm reset, port only\n"); - if (hub_port_reset(hub, port1, NULL, - HUB_BH_RESET_TIME, true) < 0) + err = hub_port_reset(hub, port1, NULL, + HUB_BH_RESET_TIME, true); + if (!udev && err == -ENOTCONN) + connect_change = 0; + else if (err < 0) hub_port_disable(hub, port1, 1); } else { dev_dbg(&port_dev->dev, "do warm reset, full device\n"); diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index d5b622f78cf3..0637bfbc054e 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -5389,20 +5389,34 @@ int dwc2_gadget_enter_hibernation(struct dwc2_hsotg *hsotg) if (gusbcfg & GUSBCFG_ULPI_UTMI_SEL) { /* ULPI interface */ gpwrdn |= GPWRDN_ULPI_LATCH_EN_DURING_HIB_ENTRY; - } - dwc2_writel(hsotg, gpwrdn, GPWRDN); - udelay(10); + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); - /* Suspend the Phy Clock */ - pcgcctl = dwc2_readl(hsotg, PCGCTL); - pcgcctl |= PCGCTL_STOPPCLK; - dwc2_writel(hsotg, pcgcctl, PCGCTL); - udelay(10); + /* Suspend the Phy Clock */ + pcgcctl = dwc2_readl(hsotg, PCGCTL); + pcgcctl |= PCGCTL_STOPPCLK; + dwc2_writel(hsotg, pcgcctl, PCGCTL); + udelay(10); - gpwrdn = dwc2_readl(hsotg, GPWRDN); - gpwrdn |= GPWRDN_PMUACTV; - dwc2_writel(hsotg, gpwrdn, GPWRDN); - udelay(10); + gpwrdn = dwc2_readl(hsotg, GPWRDN); + gpwrdn |= GPWRDN_PMUACTV; + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + } else { + /* UTMI+ Interface */ + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + + gpwrdn = dwc2_readl(hsotg, GPWRDN); + gpwrdn |= GPWRDN_PMUACTV; + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + + pcgcctl = dwc2_readl(hsotg, PCGCTL); + pcgcctl |= PCGCTL_STOPPCLK; + dwc2_writel(hsotg, pcgcctl, PCGCTL); + udelay(10); + } /* Set flag to indicate that we are in hibernation */ hsotg->hibernated = 1; diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index 7334de85ad10..ca7e1c02773a 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -680,12 +680,12 @@ static int dwc3_qcom_probe(struct platform_device *pdev) ret = reset_control_deassert(qcom->resets); if (ret) { dev_err(&pdev->dev, "failed to deassert resets, err=%d\n", ret); - goto reset_assert; + return ret; } ret = clk_bulk_prepare_enable(qcom->num_clocks, qcom->clks); if (ret < 0) - goto reset_assert; + return ret; r = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!r) { @@ -755,8 +755,6 @@ remove_core: dwc3_core_remove(&qcom->dwc); clk_disable: clk_bulk_disable_unprepare(qcom->num_clocks, qcom->clks); -reset_assert: - reset_control_assert(qcom->resets); return ret; } @@ -771,7 +769,6 @@ static void dwc3_qcom_remove(struct platform_device *pdev) clk_bulk_disable_unprepare(qcom->num_clocks, qcom->clks); dwc3_qcom_interconnect_exit(qcom); - reset_control_assert(qcom->resets); } static int dwc3_qcom_pm_suspend(struct device *dev) diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index fba2a56dae97..f94ea196ce54 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -1065,6 +1065,8 @@ static ssize_t webusb_landingPage_store(struct config_item *item, const char *pa unsigned int bytes_to_strip = 0; int l = len; + if (!len) + return len; if (page[l - 1] == '\n') { --l; ++bytes_to_strip; @@ -1188,6 +1190,8 @@ static ssize_t os_desc_qw_sign_store(struct config_item *item, const char *page, struct gadget_info *gi = os_desc_item_to_gadget_info(item); int res, l; + if (!len) + return len; l = min_t(int, len, OS_STRING_QW_SIGN_LEN >> 1); if (page[l - 1] == '\n') --l; diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index 6869c58367f2..caf4d4cd4b75 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -1913,6 +1913,7 @@ static int musb_gadget_stop(struct usb_gadget *g) * gadget driver here and have everything work; * that currently misbehaves. */ + usb_gadget_set_state(g, USB_STATE_NOTATTACHED); /* Force check of devctl register for PM runtime */ pm_runtime_mark_last_busy(musb->controller); @@ -2019,6 +2020,7 @@ void musb_g_disconnect(struct musb *musb) case OTG_STATE_B_PERIPHERAL: case OTG_STATE_B_IDLE: musb_set_state(musb, OTG_STATE_B_IDLE); + usb_gadget_set_state(&musb->g, USB_STATE_NOTATTACHED); break; case OTG_STATE_B_SRP_INIT: break; diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 6ac7a0a5cf07..abfcfca3f971 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -803,6 +803,8 @@ static const struct usb_device_id id_table_combined[] = { .driver_info = (kernel_ulong_t)&ftdi_NDI_device_quirk }, { USB_DEVICE(FTDI_VID, FTDI_NDI_AURORA_SCU_PID), .driver_info = (kernel_ulong_t)&ftdi_NDI_device_quirk }, + { USB_DEVICE(FTDI_NDI_VID, FTDI_NDI_EMGUIDE_GEMINI_PID), + .driver_info = (kernel_ulong_t)&ftdi_NDI_device_quirk }, { USB_DEVICE(TELLDUS_VID, TELLDUS_TELLSTICK_PID) }, { USB_DEVICE(NOVITUS_VID, NOVITUS_BONO_E_PID) }, { USB_DEVICE(FTDI_VID, RTSYSTEMS_USB_VX8_PID) }, diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 9acb6f837327..4cc1fae8acb9 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -204,6 +204,9 @@ #define FTDI_NDI_FUTURE_3_PID 0xDA73 /* NDI future device #3 */ #define FTDI_NDI_AURORA_SCU_PID 0xDA74 /* NDI Aurora SCU */ +#define FTDI_NDI_VID 0x23F2 +#define FTDI_NDI_EMGUIDE_GEMINI_PID 0x0003 /* NDI Emguide Gemini */ + /* * ChamSys Limited (www.chamsys.co.uk) USB wing/interface product IDs */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 27879cc57536..147ca50c94be 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1415,6 +1415,9 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(5) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d0, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d0, 0xff, 0xff, 0x60) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10c7, 0xff, 0xff, 0x30), /* Telit FE910C04 (ECM) */ + .driver_info = NCTRL(4) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10c7, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d1, 0xff, 0xff, 0x30), /* Telit FN990B (MBIM) */ .driver_info = NCTRL(6) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d1, 0xff, 0xff, 0x40) }, @@ -2343,6 +2346,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe145, 0xff), /* Foxconn T99W651 RNDIS */ .driver_info = RSVD(5) | RSVD(6) }, + { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe167, 0xff), /* Foxconn T99W640 MBIM */ + .driver_info = RSVD(3) }, { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 (IOT version) */ .driver_info = RSVD(4) | RSVD(5) | RSVD(6) }, { USB_DEVICE(0x1782, 0x4d10) }, /* Fibocom L610 (AT mode) */ diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 565966351dfa..123298a4dc8f 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -505,15 +505,11 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_core_device *vdev, if (ret) goto out_put_eventfd_ctx; - ctx->producer.token = trigger; - ctx->producer.irq = irq; - ret = irq_bypass_register_producer(&ctx->producer); + ret = irq_bypass_register_producer(&ctx->producer, trigger, irq); if (unlikely(ret)) { dev_info(&pdev->dev, - "irq bypass producer (token %p) registration fails: %d\n", - ctx->producer.token, ret); - - ctx->producer.token = NULL; + "irq bypass producer (eventfd %p) registration fails: %d\n", + trigger, ret); } ctx->trigger = trigger; diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 5a49b5a6d496..af1e1fdfd9ed 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -212,11 +212,11 @@ static void vhost_vdpa_setup_vq_irq(struct vhost_vdpa *v, u16 qid) if (!vq->call_ctx.ctx) return; - vq->call_ctx.producer.irq = irq; - ret = irq_bypass_register_producer(&vq->call_ctx.producer); + ret = irq_bypass_register_producer(&vq->call_ctx.producer, + vq->call_ctx.ctx, irq); if (unlikely(ret)) - dev_info(&v->dev, "vq %u, irq bypass producer (token %p) registration fails, ret = %d\n", - qid, vq->call_ctx.producer.token, ret); + dev_info(&v->dev, "vq %u, irq bypass producer (eventfd %p) registration fails, ret = %d\n", + qid, vq->call_ctx.ctx, ret); } static void vhost_vdpa_unsetup_vq_irq(struct vhost_vdpa *v, u16 qid) @@ -712,7 +712,6 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, if (ops->get_status(vdpa) & VIRTIO_CONFIG_S_DRIVER_OK) vhost_vdpa_unsetup_vq_irq(v, idx); - vq->call_ctx.producer.token = NULL; } break; } @@ -753,7 +752,6 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, cb.callback = vhost_vdpa_virtqueue_cb; cb.private = vq; cb.trigger = vq->call_ctx.ctx; - vq->call_ctx.producer.token = vq->call_ctx.ctx; if (ops->get_status(vdpa) & VIRTIO_CONFIG_S_DRIVER_OK) vhost_vdpa_setup_vq_irq(v, idx); diff --git a/fs/afs/addr_prefs.c b/fs/afs/addr_prefs.c index c0384201b8fe..133736412c3d 100644 --- a/fs/afs/addr_prefs.c +++ b/fs/afs/addr_prefs.c @@ -48,7 +48,7 @@ static int afs_split_string(char **pbuf, char *strv[], unsigned int maxstrv) strv[count++] = p; /* Skip over word */ - while (!isspace(*p)) + while (!isspace(*p) && *p) p++; if (!*p) break; diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 0168bbf53fe0..f31359922e98 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -177,6 +177,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, VL_SERVICE, AFS_VL_PORT); if (IS_ERR(vllist)) { ret = PTR_ERR(vllist); + vllist = NULL; goto parse_failed; } diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c index b375ad610acd..b58525ec7b4d 100644 --- a/fs/bcachefs/alloc_foreground.c +++ b/fs/bcachefs/alloc_foreground.c @@ -511,7 +511,8 @@ again: bch2_dev_usage_read_fast(ca, &req->usage); avail = dev_buckets_free(ca, req->usage, req->watermark); - if (req->usage.buckets[BCH_DATA_need_discard] > avail) + if (req->usage.buckets[BCH_DATA_need_discard] > + min(avail, ca->mi.nbuckets >> 7)) bch2_dev_do_discards(ca); if (req->usage.buckets[BCH_DATA_need_gc_gens] > avail) diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c index 91e0aa796e6b..83c9860e6b82 100644 --- a/fs/bcachefs/btree_cache.c +++ b/fs/bcachefs/btree_cache.c @@ -85,7 +85,7 @@ void bch2_btree_node_to_freelist(struct bch_fs *c, struct btree *b) six_unlock_intent(&b->c.lock); } -static void __btree_node_data_free(struct btree_cache *bc, struct btree *b) +void __btree_node_data_free(struct btree *b) { BUG_ON(!list_empty(&b->list)); BUG_ON(btree_node_hashed(b)); @@ -112,16 +112,17 @@ static void __btree_node_data_free(struct btree_cache *bc, struct btree *b) munmap(b->aux_data, btree_aux_data_bytes(b)); #endif b->aux_data = NULL; - - btree_node_to_freedlist(bc, b); } static void btree_node_data_free(struct btree_cache *bc, struct btree *b) { BUG_ON(list_empty(&b->list)); list_del_init(&b->list); + + __btree_node_data_free(b); + --bc->nr_freeable; - __btree_node_data_free(bc, b); + btree_node_to_freedlist(bc, b); } static int bch2_btree_cache_cmp_fn(struct rhashtable_compare_arg *arg, @@ -185,10 +186,7 @@ static struct btree *__btree_node_mem_alloc(struct bch_fs *c, gfp_t gfp) struct btree *__bch2_btree_node_mem_alloc(struct bch_fs *c) { - struct btree_cache *bc = &c->btree_cache; - struct btree *b; - - b = __btree_node_mem_alloc(c, GFP_KERNEL); + struct btree *b = __btree_node_mem_alloc(c, GFP_KERNEL); if (!b) return NULL; @@ -198,8 +196,6 @@ struct btree *__bch2_btree_node_mem_alloc(struct bch_fs *c) } bch2_btree_lock_init(&b->c, 0, GFP_KERNEL); - - __bch2_btree_node_to_freelist(bc, b); return b; } @@ -524,7 +520,8 @@ restart: --touched;; } else if (!btree_node_reclaim(c, b)) { __bch2_btree_node_hash_remove(bc, b); - __btree_node_data_free(bc, b); + __btree_node_data_free(b); + btree_node_to_freedlist(bc, b); freed++; bc->nr_freed++; @@ -652,9 +649,12 @@ int bch2_fs_btree_cache_init(struct bch_fs *c) bch2_recalc_btree_reserve(c); - for (i = 0; i < bc->nr_reserve; i++) - if (!__bch2_btree_node_mem_alloc(c)) + for (i = 0; i < bc->nr_reserve; i++) { + struct btree *b = __bch2_btree_node_mem_alloc(c); + if (!b) goto err; + __bch2_btree_node_to_freelist(bc, b); + } list_splice_init(&bc->live[0].list, &bc->freeable); diff --git a/fs/bcachefs/btree_cache.h b/fs/bcachefs/btree_cache.h index ca3c1b145330..be275f87a60e 100644 --- a/fs/bcachefs/btree_cache.h +++ b/fs/bcachefs/btree_cache.h @@ -30,6 +30,7 @@ void bch2_btree_node_update_key_early(struct btree_trans *, enum btree_id, unsig void bch2_btree_cache_cannibalize_unlock(struct btree_trans *); int bch2_btree_cache_cannibalize_lock(struct btree_trans *, struct closure *); +void __btree_node_data_free(struct btree *); struct btree *__bch2_btree_node_mem_alloc(struct bch_fs *); struct btree *bch2_btree_node_mem_alloc(struct btree_trans *, bool); diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index e874a4357f64..590cd29f3e86 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -568,9 +568,9 @@ static int __btree_err(int ret, bch2_mark_btree_validate_failure(failed, ca->dev_idx); struct extent_ptr_decoded pick; - have_retry = !bch2_bkey_pick_read_device(c, + have_retry = bch2_bkey_pick_read_device(c, bkey_i_to_s_c(&b->key), - failed, &pick, -1); + failed, &pick, -1) == 1; } if (!have_retry && ret == -BCH_ERR_btree_node_read_err_want_retry) @@ -615,7 +615,6 @@ static int __btree_err(int ret, goto out; case -BCH_ERR_btree_node_read_err_bad_node: prt_str(&out, ", "); - ret = __bch2_topology_error(c, &out); break; } @@ -644,7 +643,6 @@ static int __btree_err(int ret, goto out; case -BCH_ERR_btree_node_read_err_bad_node: prt_str(&out, ", "); - ret = __bch2_topology_error(c, &out); break; } print: @@ -1297,9 +1295,6 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, btree_bounce_free(c, btree_buf_bytes(b), used_mempool, sorted); - if (updated_range) - bch2_btree_node_drop_keys_outside_node(b); - i = &b->data->keys; for (k = i->start; k != vstruct_last(i);) { struct bkey tmp; @@ -1337,6 +1332,9 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, btree_node_reset_sib_u64s(b); + if (updated_range) + bch2_btree_node_drop_keys_outside_node(b); + /* * XXX: * @@ -1408,7 +1406,7 @@ static void btree_node_read_work(struct work_struct *work) ret = bch2_bkey_pick_read_device(c, bkey_i_to_s_c(&b->key), &failed, &rb->pick, -1); - if (ret) { + if (ret <= 0) { set_btree_node_read_error(b); break; } diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c index 23d8c62ea4b6..a3fb07c60e25 100644 --- a/fs/bcachefs/btree_node_scan.c +++ b/fs/bcachefs/btree_node_scan.c @@ -75,39 +75,6 @@ static inline u64 bkey_journal_seq(struct bkey_s_c k) } } -static bool found_btree_node_is_readable(struct btree_trans *trans, - struct found_btree_node *f) -{ - struct { __BKEY_PADDED(k, BKEY_BTREE_PTR_VAL_U64s_MAX); } tmp; - - found_btree_node_to_key(&tmp.k, f); - - struct btree *b = bch2_btree_node_get_noiter(trans, &tmp.k, f->btree_id, f->level, false); - bool ret = !IS_ERR_OR_NULL(b); - if (!ret) - return ret; - - f->sectors_written = b->written; - f->journal_seq = le64_to_cpu(b->data->keys.journal_seq); - - struct bkey_s_c k; - struct bkey unpacked; - struct btree_node_iter iter; - for_each_btree_node_key_unpack(b, k, &iter, &unpacked) - f->journal_seq = max(f->journal_seq, bkey_journal_seq(k)); - - six_unlock_read(&b->c.lock); - - /* - * We might update this node's range; if that happens, we need the node - * to be re-read so the read path can trim keys that are no longer in - * this node - */ - if (b != btree_node_root(trans->c, b)) - bch2_btree_node_evict(trans, &tmp.k); - return ret; -} - static int found_btree_node_cmp_cookie(const void *_l, const void *_r) { const struct found_btree_node *l = _l; @@ -159,17 +126,17 @@ static const struct min_heap_callbacks found_btree_node_heap_cbs = { }; static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca, - struct bio *bio, struct btree_node *bn, u64 offset) + struct btree *b, struct bio *bio, u64 offset) { struct bch_fs *c = container_of(f, struct bch_fs, found_btree_nodes); + struct btree_node *bn = b->data; bio_reset(bio, ca->disk_sb.bdev, REQ_OP_READ); bio->bi_iter.bi_sector = offset; - bch2_bio_map(bio, bn, PAGE_SIZE); + bch2_bio_map(bio, b->data, c->opts.block_size); u64 submit_time = local_clock(); submit_bio_wait(bio); - bch2_account_io_completion(ca, BCH_MEMBER_ERROR_read, submit_time, !bio->bi_status); if (bio->bi_status) { @@ -217,7 +184,28 @@ static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca, }; rcu_read_unlock(); - if (bch2_trans_run(c, found_btree_node_is_readable(trans, &n))) { + bio_reset(bio, ca->disk_sb.bdev, REQ_OP_READ); + bio->bi_iter.bi_sector = offset; + bch2_bio_map(bio, b->data, c->opts.btree_node_size); + + submit_time = local_clock(); + submit_bio_wait(bio); + bch2_account_io_completion(ca, BCH_MEMBER_ERROR_read, submit_time, !bio->bi_status); + + found_btree_node_to_key(&b->key, &n); + + CLASS(printbuf, buf)(); + if (!bch2_btree_node_read_done(c, ca, b, NULL, &buf)) { + /* read_done will swap out b->data for another buffer */ + bn = b->data; + /* + * Grab journal_seq here because we want the max journal_seq of + * any bset; read_done sorts down to a single set and picks the + * max journal_seq + */ + n.journal_seq = le64_to_cpu(bn->keys.journal_seq), + n.sectors_written = b->written; + mutex_lock(&f->lock); if (BSET_BIG_ENDIAN(&bn->keys) != CPU_BIG_ENDIAN) { bch_err(c, "try_read_btree_node() can't handle endian conversion"); @@ -237,12 +225,20 @@ static int read_btree_nodes_worker(void *p) struct find_btree_nodes_worker *w = p; struct bch_fs *c = container_of(w->f, struct bch_fs, found_btree_nodes); struct bch_dev *ca = w->ca; - void *buf = (void *) __get_free_page(GFP_KERNEL); - struct bio *bio = bio_alloc(NULL, 1, 0, GFP_KERNEL); unsigned long last_print = jiffies; + struct btree *b = NULL; + struct bio *bio = NULL; + + b = __bch2_btree_node_mem_alloc(c); + if (!b) { + bch_err(c, "read_btree_nodes_worker: error allocating buf"); + w->f->ret = -ENOMEM; + goto err; + } - if (!buf || !bio) { - bch_err(c, "read_btree_nodes_worker: error allocating bio/buf"); + bio = bio_alloc(NULL, buf_pages(b->data, c->opts.btree_node_size), 0, GFP_KERNEL); + if (!bio) { + bch_err(c, "read_btree_nodes_worker: error allocating bio"); w->f->ret = -ENOMEM; goto err; } @@ -266,11 +262,13 @@ static int read_btree_nodes_worker(void *p) !bch2_dev_btree_bitmap_marked_sectors(ca, sector, btree_sectors(c))) continue; - try_read_btree_node(w->f, ca, bio, buf, sector); + try_read_btree_node(w->f, ca, b, bio, sector); } err: + if (b) + __btree_node_data_free(b); + kfree(b); bio_put(bio); - free_page((unsigned long) buf); enumerated_ref_put(&ca->io_ref[READ], BCH_DEV_READ_REF_btree_node_scan); closure_put(w->cl); kfree(w); diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c index 901f643ead83..07c2a0f73cc2 100644 --- a/fs/bcachefs/debug.c +++ b/fs/bcachefs/debug.c @@ -153,8 +153,6 @@ void __bch2_btree_verify(struct bch_fs *c, struct btree *b) c->verify_data = __bch2_btree_node_mem_alloc(c); if (!c->verify_data) goto out; - - list_del_init(&c->verify_data->list); } BUG_ON(b->nsets != 1); @@ -586,6 +584,8 @@ static ssize_t bch2_btree_transactions_read(struct file *file, char __user *buf, i->ubuf = buf; i->size = size; i->ret = 0; + + int srcu_idx = srcu_read_lock(&c->btree_trans_barrier); restart: seqmutex_lock(&c->btree_trans_lock); list_sort(&c->btree_trans_list, list_ptr_order_cmp); @@ -599,6 +599,11 @@ restart: if (!closure_get_not_zero(&trans->ref)) continue; + if (!trans->srcu_held) { + closure_put(&trans->ref); + continue; + } + u32 seq = seqmutex_unlock(&c->btree_trans_lock); bch2_btree_trans_to_text(&i->buf, trans); @@ -620,6 +625,8 @@ restart: } seqmutex_unlock(&c->btree_trans_lock); unlocked: + srcu_read_unlock(&c->btree_trans_barrier, srcu_idx); + if (i->buf.allocation_failure) ret = -ENOMEM; diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c index a18d0f78704d..28875c5c86ad 100644 --- a/fs/bcachefs/dirent.c +++ b/fs/bcachefs/dirent.c @@ -13,6 +13,7 @@ #include <linux/dcache.h> +#ifdef CONFIG_UNICODE int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info, const struct qstr *str, struct qstr *out_cf) { @@ -33,6 +34,7 @@ int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info, *out_cf = (struct qstr) QSTR_INIT(buf, ret); return 0; } +#endif static unsigned bch2_dirent_name_bytes(struct bkey_s_c_dirent d) { @@ -254,6 +256,7 @@ int bch2_dirent_init_name(struct bch_fs *c, if (!bch2_fs_casefold_enabled(c)) return -EOPNOTSUPP; +#ifdef CONFIG_UNICODE memcpy(&dirent->v.d_cf_name_block.d_names[0], name->name, name->len); char *cf_out = &dirent->v.d_cf_name_block.d_names[name->len]; @@ -279,6 +282,7 @@ int bch2_dirent_init_name(struct bch_fs *c, dirent->v.d_cf_name_block.d_cf_name_len = cpu_to_le16(cf_len); EBUG_ON(bch2_dirent_get_casefold_name(dirent_i_to_s_c(dirent)).len != cf_len); +#endif } unsigned u64s = dirent_val_u64s(name->len, cf_len); diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h index 1e17199cc5c7..0417608c18d5 100644 --- a/fs/bcachefs/dirent.h +++ b/fs/bcachefs/dirent.h @@ -23,8 +23,16 @@ struct bch_fs; struct bch_hash_info; struct bch_inode_info; +#ifdef CONFIG_UNICODE int bch2_casefold(struct btree_trans *, const struct bch_hash_info *, const struct qstr *, struct qstr *); +#else +static inline int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info, + const struct qstr *str, struct qstr *out_cf) +{ + return -EOPNOTSUPP; +} +#endif static inline int bch2_maybe_casefold(struct btree_trans *trans, const struct bch_hash_info *info, diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h index 86a842f1e88e..acc3b7b67704 100644 --- a/fs/bcachefs/errcode.h +++ b/fs/bcachefs/errcode.h @@ -282,7 +282,6 @@ x(EIO, sb_not_downgraded) \ x(EIO, btree_node_write_all_failed) \ x(EIO, btree_node_read_error) \ - x(EIO, btree_node_read_validate_error) \ x(EIO, btree_need_topology_repair) \ x(EIO, bucket_ref_update) \ x(EIO, trigger_alloc) \ diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c index b2a6c041e165..267e73d9d7e6 100644 --- a/fs/bcachefs/error.c +++ b/fs/bcachefs/error.c @@ -103,7 +103,7 @@ int __bch2_topology_error(struct bch_fs *c, struct printbuf *out) return bch_err_throw(c, btree_need_topology_repair); } else { return bch2_run_explicit_recovery_pass(c, out, BCH_RECOVERY_PASS_check_topology, 0) ?: - bch_err_throw(c, btree_node_read_validate_error); + bch_err_throw(c, btree_need_topology_repair); } } @@ -633,7 +633,9 @@ err: * log_fsck_err()s: that would require us to track for every error type * which recovery pass corrects it, to get the fsck exit status correct: */ - if (bch2_err_matches(ret, BCH_ERR_fsck_fix)) { + if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) { + /* nothing */ + } else if (bch2_err_matches(ret, BCH_ERR_fsck_fix)) { set_bit(BCH_FS_errors_fixed, &c->flags); } else { set_bit(BCH_FS_errors_not_fixed, &c->flags); diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index 036e4ad95987..83cbd77dcb9c 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -50,19 +50,17 @@ void bch2_io_failures_to_text(struct printbuf *out, struct bch_io_failures *failed) { static const char * const error_types[] = { - "io", "checksum", "ec reconstruct", NULL + "btree validate", "io", "checksum", "ec reconstruct", NULL }; for (struct bch_dev_io_failures *f = failed->devs; f < failed->devs + failed->nr; f++) { unsigned errflags = - ((!!f->failed_io) << 0) | - ((!!f->failed_csum_nr) << 1) | - ((!!f->failed_ec) << 2); - - if (!errflags) - continue; + ((!!f->failed_btree_validate) << 0) | + ((!!f->failed_io) << 1) | + ((!!f->failed_csum_nr) << 2) | + ((!!f->failed_ec) << 3); bch2_printbuf_make_room(out, 1024); out->atomic++; @@ -77,7 +75,9 @@ void bch2_io_failures_to_text(struct printbuf *out, prt_char(out, ' '); - if (is_power_of_2(errflags)) { + if (!errflags) { + prt_str(out, "no error - confused"); + } else if (is_power_of_2(errflags)) { prt_bitflags(out, error_types, errflags); prt_str(out, " error"); } else { diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index dbf161e4311a..15c1e890d299 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -12,6 +12,7 @@ #include "fs.h" #include "fsck.h" #include "inode.h" +#include "io_misc.h" #include "keylist.h" #include "namei.h" #include "recovery_passes.h" @@ -1919,33 +1920,12 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, "extent type past end of inode %llu:%u, i_size %llu\n%s", i->inode.bi_inum, i->inode.bi_snapshot, i->inode.bi_size, (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { - struct bkey_i *whiteout = bch2_trans_kmalloc(trans, sizeof(*whiteout)); - ret = PTR_ERR_OR_ZERO(whiteout); - if (ret) - goto err; - - bkey_init(&whiteout->k); - whiteout->k.p = SPOS(k.k->p.inode, - last_block, - i->inode.bi_snapshot); - bch2_key_resize(&whiteout->k, - min(KEY_SIZE_MAX & (~0 << c->block_bits), - U64_MAX - whiteout->k.p.offset)); - - - /* - * Need a normal (not BTREE_ITER_all_snapshots) - * iterator, if we're deleting in a different - * snapshot and need to emit a whiteout - */ - struct btree_iter iter2; - bch2_trans_iter_init(trans, &iter2, BTREE_ID_extents, - bkey_start_pos(&whiteout->k), - BTREE_ITER_intent); - ret = bch2_btree_iter_traverse(trans, &iter2) ?: - bch2_trans_update(trans, &iter2, whiteout, - BTREE_UPDATE_internal_snapshot_node); - bch2_trans_iter_exit(trans, &iter2); + ret = snapshots_seen_add_inorder(c, s, i->inode.bi_snapshot) ?: + bch2_fpunch_snapshot(trans, + SPOS(i->inode.bi_inum, + last_block, + i->inode.bi_snapshot), + POS(i->inode.bi_inum, U64_MAX)); if (ret) goto err; diff --git a/fs/bcachefs/io_misc.c b/fs/bcachefs/io_misc.c index bf72b1d2e2cb..07023667a475 100644 --- a/fs/bcachefs/io_misc.c +++ b/fs/bcachefs/io_misc.c @@ -135,6 +135,33 @@ err_noprint: return ret; } +/* For fsck */ +int bch2_fpunch_snapshot(struct btree_trans *trans, struct bpos start, struct bpos end) +{ + u32 restart_count = trans->restart_count; + struct bch_fs *c = trans->c; + struct disk_reservation disk_res = bch2_disk_reservation_init(c, 0); + unsigned max_sectors = KEY_SIZE_MAX & (~0 << c->block_bits); + struct bkey_i delete; + + int ret = for_each_btree_key_max_commit(trans, iter, BTREE_ID_extents, + start, end, 0, k, + &disk_res, NULL, BCH_TRANS_COMMIT_no_enospc, ({ + bkey_init(&delete.k); + delete.k.p = iter.pos; + + /* create the biggest key we can */ + bch2_key_resize(&delete.k, max_sectors); + bch2_cut_back(end, &delete); + + bch2_extent_trim_atomic(trans, &iter, &delete) ?: + bch2_trans_update(trans, &iter, &delete, 0); + })); + + bch2_disk_reservation_put(c, &disk_res); + return ret ?: trans_was_restarted(trans, restart_count); +} + /* * Returns -BCH_ERR_transacton_restart if we had to drop locks: */ diff --git a/fs/bcachefs/io_misc.h b/fs/bcachefs/io_misc.h index 9cb44a7c43c1..b93e4d4b3c0c 100644 --- a/fs/bcachefs/io_misc.h +++ b/fs/bcachefs/io_misc.h @@ -5,6 +5,8 @@ int bch2_extent_fallocate(struct btree_trans *, subvol_inum, struct btree_iter *, u64, struct bch_io_opts, s64 *, struct write_point_specifier); + +int bch2_fpunch_snapshot(struct btree_trans *, struct bpos, struct bpos); int bch2_fpunch_at(struct btree_trans *, struct btree_iter *, subvol_inum, u64, s64 *); int bch2_fpunch(struct bch_fs *c, subvol_inum, u64, u64, s64 *); diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c index cd184b219a65..e0874ad9a6cf 100644 --- a/fs/bcachefs/io_read.c +++ b/fs/bcachefs/io_read.c @@ -166,6 +166,7 @@ static noinline void promote_free(struct bch_read_bio *rbio) BUG_ON(ret); async_object_list_del(c, promote, op->list_idx); + async_object_list_del(c, rbio, rbio->list_idx); bch2_data_update_exit(&op->write); @@ -456,6 +457,10 @@ static void bch2_rbio_done(struct bch_read_bio *rbio) if (rbio->start_time) bch2_time_stats_update(&rbio->c->times[BCH_TIME_data_read], rbio->start_time); +#ifdef CONFIG_BCACHEFS_ASYNC_OBJECT_LISTS + if (rbio->list_idx) + async_object_list_del(rbio->c, rbio, rbio->list_idx); +#endif bio_endio(&rbio->bio); } diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c index f22b05e02c1e..ddfeb0dafc9d 100644 --- a/fs/bcachefs/journal.c +++ b/fs/bcachefs/journal.c @@ -1082,6 +1082,7 @@ static struct journal_buf *__bch2_next_write_buffer_flush_journal_buf(struct jou if (open && !*blocked) { __bch2_journal_block(j); + s.v = atomic64_read_acquire(&j->reservations.counter); *blocked = true; } diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index dd3f3434c1b0..9e028dbcc3d0 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -1767,6 +1767,7 @@ static CLOSURE_CALLBACK(journal_write_done) closure_wake_up(&c->freelist_wait); bch2_reset_alloc_cursors(c); + do_discards = true; } j->seq_ondisk = seq; diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c index cd6201741c59..0042d43b8e57 100644 --- a/fs/bcachefs/journal_reclaim.c +++ b/fs/bcachefs/journal_reclaim.c @@ -170,6 +170,12 @@ static struct journal_space __journal_space_available(struct journal *j, unsigne return (struct journal_space) { 0, 0 }; /* + * It's possible for bucket size to be misaligned w.r.t. the filesystem + * block size: + */ + min_bucket_size = round_down(min_bucket_size, block_sectors(c)); + + /* * We sorted largest to smallest, and we want the smallest out of the * @nr_devs_want largest devices: */ diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c index 27e68d470ad0..5e6de91a8763 100644 --- a/fs/bcachefs/movinggc.c +++ b/fs/bcachefs/movinggc.c @@ -71,7 +71,7 @@ static int bch2_bucket_is_movable(struct btree_trans *trans, if (ret) return ret; - struct bch_dev *ca = bch2_dev_tryget(c, k.k->p.inode); + struct bch_dev *ca = bch2_dev_bucket_tryget(c, k.k->p); if (!ca) goto out; diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index d0b7e3a36a54..c94debb12d2f 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -273,24 +273,35 @@ static int bch2_journal_replay_key(struct btree_trans *trans, goto out; struct btree_path *path = btree_iter_path(trans, &iter); - if (unlikely(!btree_path_node(path, k->level) && - !k->allocated)) { + if (unlikely(!btree_path_node(path, k->level))) { struct bch_fs *c = trans->c; + CLASS(printbuf, buf)(); + prt_str(&buf, "btree="); + bch2_btree_id_to_text(&buf, k->btree_id); + prt_printf(&buf, " level=%u ", k->level); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(k->k)); + if (!(c->recovery.passes_complete & (BIT_ULL(BCH_RECOVERY_PASS_scan_for_btree_nodes)| BIT_ULL(BCH_RECOVERY_PASS_check_topology)))) { - bch_err(c, "have key in journal replay for btree depth that does not exist, confused"); + bch_err(c, "have key in journal replay for btree depth that does not exist, confused\n%s", + buf.buf); ret = -EINVAL; } -#if 0 + + if (!k->allocated) { + bch_notice(c, "dropping key in journal replay for depth that does not exist because we're recovering from scan\n%s", + buf.buf); + k->overwritten = true; + goto out; + } + bch2_trans_iter_exit(trans, &iter); bch2_trans_node_iter_init(trans, &iter, k->btree_id, k->k->k.p, BTREE_MAX_DEPTH, 0, iter_flags); ret = bch2_btree_iter_traverse(trans, &iter) ?: bch2_btree_increase_depth(trans, iter.path, 0) ?: -BCH_ERR_transaction_restart_nested; -#endif - k->overwritten = true; goto out; } diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c index c09ed2dd4639..6a039e011064 100644 --- a/fs/bcachefs/recovery_passes.c +++ b/fs/bcachefs/recovery_passes.c @@ -360,7 +360,7 @@ int __bch2_run_explicit_recovery_pass(struct bch_fs *c, !(r->passes_complete & BIT_ULL(pass)); bool ratelimit = flags & RUN_RECOVERY_PASS_ratelimit; - if (!(in_recovery && (flags & RUN_RECOVERY_PASS_nopersistent))) { + if (!(flags & RUN_RECOVERY_PASS_nopersistent)) { struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); __set_bit_le64(bch2_recovery_pass_to_stable(pass), ext->recovery_passes_required); } diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index c08e4a66ac07..3e0576d9db1d 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -347,8 +347,6 @@ int __cachefiles_write(struct cachefiles_object *object, default: ki->was_async = false; cachefiles_write_complete(&ki->iocb, ret); - if (ret > 0) - ret = 0; break; } diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index d9bc67176128..a7ed86fa98bb 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -83,10 +83,8 @@ static ssize_t cachefiles_ondemand_fd_write_iter(struct kiocb *kiocb, trace_cachefiles_ondemand_fd_write(object, file_inode(file), pos, len); ret = __cachefiles_write(object, file, pos, iter, NULL, NULL); - if (!ret) { - ret = len; + if (ret > 0) kiocb->ki_pos += ret; - } out: fput(file); diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index c900d98bf494..284d6dbba2ec 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -390,10 +390,16 @@ static int efivarfs_reconfigure(struct fs_context *fc) return 0; } +static void efivarfs_free(struct fs_context *fc) +{ + kfree(fc->s_fs_info); +} + static const struct fs_context_operations efivarfs_context_ops = { .get_tree = efivarfs_get_tree, .parse_param = efivarfs_parse_param, .reconfigure = efivarfs_reconfigure, + .free = efivarfs_free, }; static int efivarfs_check_missing(efi_char16_t *name16, efi_guid_t vendor, diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 6a329c329f43..16e4a6bd9b97 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -214,9 +214,11 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) /* * bit 30: I/O error occurred on this folio + * bit 29: CPU has dirty data in D-cache (needs aliasing handling); * bit 0 - 29: remaining parts to complete this folio */ -#define EROFS_ONLINEFOLIO_EIO (1 << 30) +#define EROFS_ONLINEFOLIO_EIO 30 +#define EROFS_ONLINEFOLIO_DIRTY 29 void erofs_onlinefolio_init(struct folio *folio) { @@ -233,19 +235,23 @@ void erofs_onlinefolio_split(struct folio *folio) atomic_inc((atomic_t *)&folio->private); } -void erofs_onlinefolio_end(struct folio *folio, int err) +void erofs_onlinefolio_end(struct folio *folio, int err, bool dirty) { int orig, v; do { orig = atomic_read((atomic_t *)&folio->private); - v = (orig - 1) | (err ? EROFS_ONLINEFOLIO_EIO : 0); + DBG_BUGON(orig <= 0); + v = dirty << EROFS_ONLINEFOLIO_DIRTY; + v |= (orig - 1) | (!!err << EROFS_ONLINEFOLIO_EIO); } while (atomic_cmpxchg((atomic_t *)&folio->private, orig, v) != orig); - if (v & ~EROFS_ONLINEFOLIO_EIO) + if (v & (BIT(EROFS_ONLINEFOLIO_DIRTY) - 1)) return; folio->private = 0; - folio_end_read(folio, !(v & EROFS_ONLINEFOLIO_EIO)); + if (v & BIT(EROFS_ONLINEFOLIO_DIRTY)) + flush_dcache_folio(folio); + folio_end_read(folio, !(v & BIT(EROFS_ONLINEFOLIO_EIO))); } static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, @@ -351,11 +357,16 @@ int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, */ static int erofs_read_folio(struct file *file, struct folio *folio) { + trace_erofs_read_folio(folio, true); + return iomap_read_folio(folio, &erofs_iomap_ops); } static void erofs_readahead(struct readahead_control *rac) { + trace_erofs_readahead(rac->mapping->host, readahead_index(rac), + readahead_count(rac), true); + return iomap_readahead(rac, &erofs_iomap_ops); } diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index bf62e2836b60..358061d7b660 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -301,13 +301,11 @@ static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq, cur = min(cur, rq->outputsize); if (cur && rq->out[0]) { kin = kmap_local_page(rq->in[nrpages_in - 1]); - if (rq->out[0] == rq->in[nrpages_in - 1]) { + if (rq->out[0] == rq->in[nrpages_in - 1]) memmove(kin + rq->pageofs_out, kin + pi, cur); - flush_dcache_page(rq->out[0]); - } else { + else memcpy_to_page(rq->out[0], rq->pageofs_out, kin + pi, cur); - } kunmap_local(kin); } rq->outputsize -= cur; @@ -325,14 +323,12 @@ static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq, po = (rq->pageofs_out + cur + pi) & ~PAGE_MASK; DBG_BUGON(no >= nrpages_out); cnt = min(insz - pi, PAGE_SIZE - po); - if (rq->out[no] == rq->in[ni]) { + if (rq->out[no] == rq->in[ni]) memmove(kin + po, kin + rq->pageofs_in + pi, cnt); - flush_dcache_page(rq->out[no]); - } else if (rq->out[no]) { + else if (rq->out[no]) memcpy_to_page(rq->out[no], po, kin + rq->pageofs_in + pi, cnt); - } pi += cnt; } while (pi < insz); kunmap_local(kin); diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c index 2fae209d0274..3e4b38bec0aa 100644 --- a/fs/erofs/dir.c +++ b/fs/erofs/dir.c @@ -58,6 +58,11 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx) struct erofs_dirent *de; unsigned int nameoff, maxsize; + if (fatal_signal_pending(current)) { + err = -ERESTARTSYS; + break; + } + de = erofs_bread(&buf, dbstart, true); if (IS_ERR(de)) { erofs_err(sb, "failed to readdir of logical block %llu of nid %llu", @@ -88,6 +93,7 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx) break; ctx->pos = dbstart + maxsize; ofs = 0; + cond_resched(); } erofs_put_metabuf(&buf); if (EROFS_I(dir)->dot_omitted && ctx->pos == dir->i_size) { diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c index df5cc63f2c01..91781718199e 100644 --- a/fs/erofs/fileio.c +++ b/fs/erofs/fileio.c @@ -38,7 +38,7 @@ static void erofs_fileio_ki_complete(struct kiocb *iocb, long ret) } else { bio_for_each_folio_all(fi, &rq->bio) { DBG_BUGON(folio_test_uptodate(fi.folio)); - erofs_onlinefolio_end(fi.folio, ret); + erofs_onlinefolio_end(fi.folio, ret, false); } } bio_uninit(&rq->bio); @@ -96,8 +96,6 @@ static int erofs_fileio_scan_folio(struct erofs_fileio *io, struct folio *folio) struct erofs_map_blocks *map = &io->map; unsigned int cur = 0, end = folio_size(folio), len, attached = 0; loff_t pos = folio_pos(folio), ofs; - struct iov_iter iter; - struct bio_vec bv; int err = 0; erofs_onlinefolio_init(folio); @@ -122,13 +120,7 @@ static int erofs_fileio_scan_folio(struct erofs_fileio *io, struct folio *folio) err = PTR_ERR(src); break; } - bvec_set_folio(&bv, folio, len, cur); - iov_iter_bvec(&iter, ITER_DEST, &bv, 1, len); - if (copy_to_iter(src, len, &iter) != len) { - erofs_put_metabuf(&buf); - err = -EIO; - break; - } + memcpy_to_folio(folio, cur, src, len); erofs_put_metabuf(&buf); } else if (!(map->m_flags & EROFS_MAP_MAPPED)) { folio_zero_segment(folio, cur, cur + len); @@ -162,7 +154,7 @@ io_retry: } cur += len; } - erofs_onlinefolio_end(folio, err); + erofs_onlinefolio_end(folio, err, false); return err; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index a32c03a80c70..06b867d2fc3b 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -315,10 +315,12 @@ static inline struct folio *erofs_grab_folio_nowait(struct address_space *as, /* The length of extent is full */ #define EROFS_MAP_FULL_MAPPED 0x0008 /* Located in the special packed inode */ -#define EROFS_MAP_FRAGMENT 0x0010 +#define __EROFS_MAP_FRAGMENT 0x0010 /* The extent refers to partial decompressed data */ #define EROFS_MAP_PARTIAL_REF 0x0020 +#define EROFS_MAP_FRAGMENT (EROFS_MAP_MAPPED | __EROFS_MAP_FRAGMENT) + struct erofs_map_blocks { struct erofs_buf buf; @@ -390,7 +392,7 @@ int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map); void erofs_onlinefolio_init(struct folio *folio); void erofs_onlinefolio_split(struct folio *folio); -void erofs_onlinefolio_end(struct folio *folio, int err); +void erofs_onlinefolio_end(struct folio *folio, int err, bool dirty); struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid); int erofs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index fe8071844724..e3f28a1bb945 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1034,7 +1034,7 @@ static int z_erofs_scan_folio(struct z_erofs_frontend *f, if (!(map->m_flags & EROFS_MAP_MAPPED)) { folio_zero_segment(folio, cur, end); tight = false; - } else if (map->m_flags & EROFS_MAP_FRAGMENT) { + } else if (map->m_flags & __EROFS_MAP_FRAGMENT) { erofs_off_t fpos = offset + cur - map->m_la; err = z_erofs_read_fragment(inode->i_sb, folio, cur, @@ -1091,7 +1091,7 @@ static int z_erofs_scan_folio(struct z_erofs_frontend *f, tight = (bs == PAGE_SIZE); } } while ((end = cur) > 0); - erofs_onlinefolio_end(folio, err); + erofs_onlinefolio_end(folio, err, false); return err; } @@ -1196,7 +1196,7 @@ static void z_erofs_fill_other_copies(struct z_erofs_backend *be, int err) cur += len; } kunmap_local(dst); - erofs_onlinefolio_end(page_folio(bvi->bvec.page), err); + erofs_onlinefolio_end(page_folio(bvi->bvec.page), err, true); list_del(p); kfree(bvi); } @@ -1355,7 +1355,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err) DBG_BUGON(z_erofs_page_is_invalidated(page)); if (!z_erofs_is_shortlived_page(page)) { - erofs_onlinefolio_end(page_folio(page), err); + erofs_onlinefolio_end(page_folio(page), err, true); continue; } if (pcl->algorithmformat != Z_EROFS_COMPRESSION_LZ4) { diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 0bebc6e3a4d7..f1a15ff22147 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -413,8 +413,7 @@ static int z_erofs_map_blocks_fo(struct inode *inode, !vi->z_tailextent_headlcn) { map->m_la = 0; map->m_llen = inode->i_size; - map->m_flags = EROFS_MAP_MAPPED | - EROFS_MAP_FULL_MAPPED | EROFS_MAP_FRAGMENT; + map->m_flags = EROFS_MAP_FRAGMENT; return 0; } initial_lcn = ofs >> lclusterbits; @@ -489,7 +488,7 @@ static int z_erofs_map_blocks_fo(struct inode *inode, goto unmap_out; } } else if (fragment && m.lcn == vi->z_tailextent_headlcn) { - map->m_flags |= EROFS_MAP_FRAGMENT; + map->m_flags = EROFS_MAP_FRAGMENT; } else { map->m_pa = erofs_pos(sb, m.pblk); err = z_erofs_get_extent_compressedlen(&m, initial_lcn); @@ -617,7 +616,7 @@ static int z_erofs_map_blocks_ext(struct inode *inode, if (lstart < lend) { map->m_la = lstart; if (last && (vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER)) { - map->m_flags |= EROFS_MAP_MAPPED | EROFS_MAP_FRAGMENT; + map->m_flags = EROFS_MAP_FRAGMENT; vi->z_fragmentoff = map->m_plen; if (recsz > offsetof(struct z_erofs_extent, pstart_lo)) vi->z_fragmentoff |= map->m_pa << 32; @@ -797,7 +796,7 @@ static int z_erofs_iomap_begin_report(struct inode *inode, loff_t offset, iomap->length = map.m_llen; if (map.m_flags & EROFS_MAP_MAPPED) { iomap->type = IOMAP_MAPPED; - iomap->addr = map.m_flags & EROFS_MAP_FRAGMENT ? + iomap->addr = map.m_flags & __EROFS_MAP_FRAGMENT ? IOMAP_NULL_ADDR : map.m_pa; } else { iomap->type = IOMAP_HOLE; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index a97a771a459c..0fbf5dfedb24 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -137,7 +137,13 @@ struct epitem { }; /* List header used to link this structure to the eventpoll ready list */ - struct llist_node rdllink; + struct list_head rdllink; + + /* + * Works together "struct eventpoll"->ovflist in keeping the + * single linked chain of items. + */ + struct epitem *next; /* The file descriptor information this item refers to */ struct epoll_filefd ffd; @@ -185,15 +191,22 @@ struct eventpoll { /* Wait queue used by file->poll() */ wait_queue_head_t poll_wait; - /* - * List of ready file descriptors. Adding to this list is lockless. Items can be removed - * only with eventpoll::mtx - */ - struct llist_head rdllist; + /* List of ready file descriptors */ + struct list_head rdllist; + + /* Lock which protects rdllist and ovflist */ + rwlock_t lock; /* RB tree root used to store monitored fd structs */ struct rb_root_cached rbr; + /* + * This is a single linked list that chains all the "struct epitem" that + * happened while transferring ready events to userspace w/out + * holding ->lock. + */ + struct epitem *ovflist; + /* wakeup_source used when ep_send_events or __ep_eventpoll_poll is running */ struct wakeup_source *ws; @@ -348,14 +361,10 @@ static inline int ep_cmp_ffd(struct epoll_filefd *p1, (p1->file < p2->file ? -1 : p1->fd - p2->fd)); } -/* - * Add the item to its container eventpoll's rdllist; do nothing if the item is already on rdllist. - */ -static void epitem_ready(struct epitem *epi) +/* Tells us if the item is currently linked */ +static inline int ep_is_linked(struct epitem *epi) { - if (&epi->rdllink == cmpxchg(&epi->rdllink.next, &epi->rdllink, NULL)) - llist_add(&epi->rdllink, &epi->ep->rdllist); - + return !list_empty(&epi->rdllink); } static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p) @@ -374,26 +383,13 @@ static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p) * * @ep: Pointer to the eventpoll context. * - * Return: true if ready events might be available, false otherwise. + * Return: a value different than %zero if ready events are available, + * or %zero otherwise. */ -static inline bool ep_events_available(struct eventpoll *ep) +static inline int ep_events_available(struct eventpoll *ep) { - bool available; - int locked; - - locked = mutex_trylock(&ep->mtx); - if (!locked) { - /* - * The lock held and someone might have removed all items while inspecting it. The - * llist_empty() check in this case is futile. Assume that something is enqueued and - * let ep_try_send_events() figure it out. - */ - return true; - } - - available = !llist_empty(&ep->rdllist); - mutex_unlock(&ep->mtx); - return available; + return !list_empty_careful(&ep->rdllist) || + READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR; } #ifdef CONFIG_NET_RX_BUSY_POLL @@ -728,6 +724,77 @@ static inline void ep_pm_stay_awake_rcu(struct epitem *epi) rcu_read_unlock(); } + +/* + * ep->mutex needs to be held because we could be hit by + * eventpoll_release_file() and epoll_ctl(). + */ +static void ep_start_scan(struct eventpoll *ep, struct list_head *txlist) +{ + /* + * Steal the ready list, and re-init the original one to the + * empty list. Also, set ep->ovflist to NULL so that events + * happening while looping w/out locks, are not lost. We cannot + * have the poll callback to queue directly on ep->rdllist, + * because we want the "sproc" callback to be able to do it + * in a lockless way. + */ + lockdep_assert_irqs_enabled(); + write_lock_irq(&ep->lock); + list_splice_init(&ep->rdllist, txlist); + WRITE_ONCE(ep->ovflist, NULL); + write_unlock_irq(&ep->lock); +} + +static void ep_done_scan(struct eventpoll *ep, + struct list_head *txlist) +{ + struct epitem *epi, *nepi; + + write_lock_irq(&ep->lock); + /* + * During the time we spent inside the "sproc" callback, some + * other events might have been queued by the poll callback. + * We re-insert them inside the main ready-list here. + */ + for (nepi = READ_ONCE(ep->ovflist); (epi = nepi) != NULL; + nepi = epi->next, epi->next = EP_UNACTIVE_PTR) { + /* + * We need to check if the item is already in the list. + * During the "sproc" callback execution time, items are + * queued into ->ovflist but the "txlist" might already + * contain them, and the list_splice() below takes care of them. + */ + if (!ep_is_linked(epi)) { + /* + * ->ovflist is LIFO, so we have to reverse it in order + * to keep in FIFO. + */ + list_add(&epi->rdllink, &ep->rdllist); + ep_pm_stay_awake(epi); + } + } + /* + * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after + * releasing the lock, events will be queued in the normal way inside + * ep->rdllist. + */ + WRITE_ONCE(ep->ovflist, EP_UNACTIVE_PTR); + + /* + * Quickly re-inject items left on "txlist". + */ + list_splice(txlist, &ep->rdllist); + __pm_relax(ep->ws); + + if (!list_empty(&ep->rdllist)) { + if (waitqueue_active(&ep->wq)) + wake_up(&ep->wq); + } + + write_unlock_irq(&ep->lock); +} + static void ep_get(struct eventpoll *ep) { refcount_inc(&ep->refcount); @@ -765,12 +832,10 @@ static void ep_free(struct eventpoll *ep) static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) { struct file *file = epi->ffd.file; - struct llist_node *put_back_last; struct epitems_head *to_free; struct hlist_head *head; - LLIST_HEAD(put_back); - lockdep_assert_held(&ep->mtx); + lockdep_assert_irqs_enabled(); /* * Removes poll wait queue hooks. @@ -802,20 +867,10 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) rb_erase_cached(&epi->rbn, &ep->rbr); - if (llist_on_list(&epi->rdllink)) { - put_back_last = NULL; - while (true) { - struct llist_node *n = llist_del_first(&ep->rdllist); - - if (&epi->rdllink == n || WARN_ON(!n)) - break; - if (!put_back_last) - put_back_last = n; - __llist_add(n, &put_back); - } - if (put_back_last) - llist_add_batch(put_back.first, put_back_last, &ep->rdllist); - } + write_lock_irq(&ep->lock); + if (ep_is_linked(epi)) + list_del_init(&epi->rdllink); + write_unlock_irq(&ep->lock); wakeup_source_unregister(ep_wakeup_source(epi)); /* @@ -828,7 +883,7 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) kfree_rcu(epi, rcu); percpu_counter_dec(&ep->user->epoll_watches); - return ep_refcount_dec_and_test(ep); + return true; } /* @@ -836,14 +891,14 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) */ static void ep_remove_safe(struct eventpoll *ep, struct epitem *epi) { - WARN_ON_ONCE(__ep_remove(ep, epi, false)); + if (__ep_remove(ep, epi, false)) + WARN_ON_ONCE(ep_refcount_dec_and_test(ep)); } static void ep_clear_and_put(struct eventpoll *ep) { struct rb_node *rbp, *next; struct epitem *epi; - bool dispose; /* We need to release all tasks waiting for these file */ if (waitqueue_active(&ep->poll_wait)) @@ -876,10 +931,8 @@ static void ep_clear_and_put(struct eventpoll *ep) cond_resched(); } - dispose = ep_refcount_dec_and_test(ep); mutex_unlock(&ep->mtx); - - if (dispose) + if (ep_refcount_dec_and_test(ep)) ep_free(ep); } @@ -919,9 +972,8 @@ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int depth) { struct eventpoll *ep = file->private_data; - struct wakeup_source *ws; - struct llist_node *n; - struct epitem *epi; + LIST_HEAD(txlist); + struct epitem *epi, *tmp; poll_table pt; __poll_t res = 0; @@ -935,39 +987,22 @@ static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int dep * the ready list. */ mutex_lock_nested(&ep->mtx, depth); - while (true) { - n = llist_del_first_init(&ep->rdllist); - if (!n) - break; - - epi = llist_entry(n, struct epitem, rdllink); - + ep_start_scan(ep, &txlist); + list_for_each_entry_safe(epi, tmp, &txlist, rdllink) { if (ep_item_poll(epi, &pt, depth + 1)) { res = EPOLLIN | EPOLLRDNORM; - epitem_ready(epi); break; } else { /* - * We need to activate ep before deactivating epi, to prevent autosuspend - * just in case epi becomes active after ep_item_poll() above. - * - * This is similar to ep_send_events(). + * Item has been dropped into the ready list by the poll + * callback, but it's not actually ready, as far as + * caller requested events goes. We can remove it here. */ - ws = ep_wakeup_source(epi); - if (ws) { - if (ws->active) - __pm_stay_awake(ep->ws); - __pm_relax(ws); - } __pm_relax(ep_wakeup_source(epi)); - - /* Just in case epi becomes active right before __pm_relax() */ - if (unlikely(ep_item_poll(epi, &pt, depth + 1))) - ep_pm_stay_awake(epi); - - __pm_relax(ep->ws); + list_del_init(&epi->rdllink); } } + ep_done_scan(ep, &txlist); mutex_unlock(&ep->mtx); return res; } @@ -1100,7 +1135,7 @@ again: dispose = __ep_remove(ep, epi, true); mutex_unlock(&ep->mtx); - if (dispose) + if (dispose && ep_refcount_dec_and_test(ep)) ep_free(ep); goto again; } @@ -1116,10 +1151,12 @@ static int ep_alloc(struct eventpoll **pep) return -ENOMEM; mutex_init(&ep->mtx); + rwlock_init(&ep->lock); init_waitqueue_head(&ep->wq); init_waitqueue_head(&ep->poll_wait); - init_llist_head(&ep->rdllist); + INIT_LIST_HEAD(&ep->rdllist); ep->rbr = RB_ROOT_CACHED; + ep->ovflist = EP_UNACTIVE_PTR; ep->user = get_current_user(); refcount_set(&ep->refcount, 1); @@ -1202,10 +1239,93 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, #endif /* CONFIG_KCMP */ /* + * Adds a new entry to the tail of the list in a lockless way, i.e. + * multiple CPUs are allowed to call this function concurrently. + * + * Beware: it is necessary to prevent any other modifications of the + * existing list until all changes are completed, in other words + * concurrent list_add_tail_lockless() calls should be protected + * with a read lock, where write lock acts as a barrier which + * makes sure all list_add_tail_lockless() calls are fully + * completed. + * + * Also an element can be locklessly added to the list only in one + * direction i.e. either to the tail or to the head, otherwise + * concurrent access will corrupt the list. + * + * Return: %false if element has been already added to the list, %true + * otherwise. + */ +static inline bool list_add_tail_lockless(struct list_head *new, + struct list_head *head) +{ + struct list_head *prev; + + /* + * This is simple 'new->next = head' operation, but cmpxchg() + * is used in order to detect that same element has been just + * added to the list from another CPU: the winner observes + * new->next == new. + */ + if (!try_cmpxchg(&new->next, &new, head)) + return false; + + /* + * Initially ->next of a new element must be updated with the head + * (we are inserting to the tail) and only then pointers are atomically + * exchanged. XCHG guarantees memory ordering, thus ->next should be + * updated before pointers are actually swapped and pointers are + * swapped before prev->next is updated. + */ + + prev = xchg(&head->prev, new); + + /* + * It is safe to modify prev->next and new->prev, because a new element + * is added only to the tail and new->next is updated before XCHG. + */ + + prev->next = new; + new->prev = prev; + + return true; +} + +/* + * Chains a new epi entry to the tail of the ep->ovflist in a lockless way, + * i.e. multiple CPUs are allowed to call this function concurrently. + * + * Return: %false if epi element has been already chained, %true otherwise. + */ +static inline bool chain_epi_lockless(struct epitem *epi) +{ + struct eventpoll *ep = epi->ep; + + /* Fast preliminary check */ + if (epi->next != EP_UNACTIVE_PTR) + return false; + + /* Check that the same epi has not been just chained from another CPU */ + if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR) + return false; + + /* Atomically exchange tail */ + epi->next = xchg(&ep->ovflist, epi); + + return true; +} + +/* * This is the callback that is passed to the wait queue wakeup * mechanism. It is called by the stored file descriptors when they * have events to report. * + * This callback takes a read lock in order not to contend with concurrent + * events from another file descriptor, thus all modifications to ->rdllist + * or ->ovflist are lockless. Read lock is paired with the write lock from + * ep_start/done_scan(), which stops all list modifications and guarantees + * that lists state is seen correctly. + * * Another thing worth to mention is that ep_poll_callback() can be called * concurrently for the same @epi from different CPUs if poll table was inited * with several wait queues entries. Plural wakeup from different CPUs of a @@ -1215,11 +1335,15 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, */ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { + int pwake = 0; struct epitem *epi = ep_item_from_wait(wait); struct eventpoll *ep = epi->ep; __poll_t pollflags = key_to_poll(key); + unsigned long flags; int ewake = 0; + read_lock_irqsave(&ep->lock, flags); + ep_set_busy_poll_napi_id(epi); /* @@ -1229,7 +1353,7 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v * until the next EPOLL_CTL_MOD will be issued. */ if (!(epi->event.events & ~EP_PRIVATE_BITS)) - goto out; + goto out_unlock; /* * Check the events coming with the callback. At this stage, not @@ -1238,10 +1362,22 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v * test for "key" != NULL before the event match test. */ if (pollflags && !(pollflags & epi->event.events)) - goto out; + goto out_unlock; - ep_pm_stay_awake_rcu(epi); - epitem_ready(epi); + /* + * If we are transferring events to userspace, we can hold no locks + * (because we're accessing user memory, and because of linux f_op->poll() + * semantics). All the events that happen during that period of time are + * chained in ep->ovflist and requeued later on. + */ + if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) { + if (chain_epi_lockless(epi)) + ep_pm_stay_awake_rcu(epi); + } else if (!ep_is_linked(epi)) { + /* In the usual case, add event to ready list. */ + if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) + ep_pm_stay_awake_rcu(epi); + } /* * Wake up ( if active ) both the eventpoll wait list and the ->poll() @@ -1270,9 +1406,15 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v wake_up(&ep->wq); } if (waitqueue_active(&ep->poll_wait)) + pwake++; + +out_unlock: + read_unlock_irqrestore(&ep->lock, flags); + + /* We have to call this outside the lock */ + if (pwake) ep_poll_safewake(ep, epi, pollflags & EPOLL_URING_WAKE); -out: if (!(epi->event.events & EPOLLEXCLUSIVE)) ewake = 1; @@ -1517,6 +1659,8 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, if (is_file_epoll(tfile)) tep = tfile->private_data; + lockdep_assert_irqs_enabled(); + if (unlikely(percpu_counter_compare(&ep->user->epoll_watches, max_user_watches) >= 0)) return -ENOSPC; @@ -1528,10 +1672,11 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, } /* Item initialization follow here ... */ - init_llist_node(&epi->rdllink); + INIT_LIST_HEAD(&epi->rdllink); epi->ep = ep; ep_set_ffd(&epi->ffd, tfile, fd); epi->event = *event; + epi->next = EP_UNACTIVE_PTR; if (tep) mutex_lock_nested(&tep->mtx, 1); @@ -1598,13 +1743,16 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, return -ENOMEM; } + /* We have to drop the new item inside our item list to keep track of it */ + write_lock_irq(&ep->lock); + /* record NAPI ID of new item if present */ ep_set_busy_poll_napi_id(epi); /* If the file is already "ready" we drop it inside the ready list */ - if (revents) { + if (revents && !ep_is_linked(epi)) { + list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); - epitem_ready(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) @@ -1613,6 +1761,8 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, pwake++; } + write_unlock_irq(&ep->lock); + /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, NULL, 0); @@ -1627,8 +1777,11 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, static int ep_modify(struct eventpoll *ep, struct epitem *epi, const struct epoll_event *event) { + int pwake = 0; poll_table pt; + lockdep_assert_irqs_enabled(); + init_poll_funcptr(&pt, NULL); /* @@ -1672,16 +1825,24 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, * list, push it inside. */ if (ep_item_poll(epi, &pt, 1)) { - ep_pm_stay_awake(epi); - epitem_ready(epi); + write_lock_irq(&ep->lock); + if (!ep_is_linked(epi)) { + list_add_tail(&epi->rdllink, &ep->rdllist); + ep_pm_stay_awake(epi); - /* Notify waiting tasks that events are available */ - if (waitqueue_active(&ep->wq)) - wake_up(&ep->wq); - if (waitqueue_active(&ep->poll_wait)) - ep_poll_safewake(ep, NULL, 0); + /* Notify waiting tasks that events are available */ + if (waitqueue_active(&ep->wq)) + wake_up(&ep->wq); + if (waitqueue_active(&ep->poll_wait)) + pwake++; + } + write_unlock_irq(&ep->lock); } + /* We have to call this outside the lock */ + if (pwake) + ep_poll_safewake(ep, NULL, 0); + return 0; } @@ -1689,7 +1850,7 @@ static int ep_send_events(struct eventpoll *ep, struct epoll_event __user *events, int maxevents) { struct epitem *epi, *tmp; - LLIST_HEAD(txlist); + LIST_HEAD(txlist); poll_table pt; int res = 0; @@ -1704,18 +1865,19 @@ static int ep_send_events(struct eventpoll *ep, init_poll_funcptr(&pt, NULL); mutex_lock(&ep->mtx); + ep_start_scan(ep, &txlist); - while (res < maxevents) { + /* + * We can loop without lock because we are passed a task private list. + * Items cannot vanish during the loop we are holding ep->mtx. + */ + list_for_each_entry_safe(epi, tmp, &txlist, rdllink) { struct wakeup_source *ws; - struct llist_node *n; __poll_t revents; - n = llist_del_first(&ep->rdllist); - if (!n) + if (res >= maxevents) break; - epi = llist_entry(n, struct epitem, rdllink); - /* * Activate ep->ws before deactivating epi->ws to prevent * triggering auto-suspend here (in case we reactive epi->ws @@ -1732,30 +1894,21 @@ static int ep_send_events(struct eventpoll *ep, __pm_relax(ws); } + list_del_init(&epi->rdllink); + /* * If the event mask intersect the caller-requested one, * deliver the event to userspace. Again, we are holding ep->mtx, * so no operations coming from userspace can change the item. */ revents = ep_item_poll(epi, &pt, 1); - if (!revents) { - init_llist_node(n); - - /* - * Just in case epi becomes ready after ep_item_poll() above, but before - * init_llist_node(). Make sure to add it to the ready list, otherwise an - * event may be lost. - */ - if (unlikely(ep_item_poll(epi, &pt, 1))) { - ep_pm_stay_awake(epi); - epitem_ready(epi); - } + if (!revents) continue; - } events = epoll_put_uevent(revents, epi->event.data, events); if (!events) { - llist_add(&epi->rdllink, &ep->rdllist); + list_add(&epi->rdllink, &txlist); + ep_pm_stay_awake(epi); if (!res) res = -EFAULT; break; @@ -1763,31 +1916,25 @@ static int ep_send_events(struct eventpoll *ep, res++; if (epi->event.events & EPOLLONESHOT) epi->event.events &= EP_PRIVATE_BITS; - __llist_add(n, &txlist); - } - - llist_for_each_entry_safe(epi, tmp, txlist.first, rdllink) { - init_llist_node(&epi->rdllink); - - if (!(epi->event.events & EPOLLET)) { + else if (!(epi->event.events & EPOLLET)) { /* - * If this file has been added with Level Trigger mode, we need to insert - * back inside the ready list, so that the next call to epoll_wait() will - * check again the events availability. + * If this file has been added with Level + * Trigger mode, we need to insert back inside + * the ready list, so that the next call to + * epoll_wait() will check again the events + * availability. At this point, no one can insert + * into ep->rdllist besides us. The epoll_ctl() + * callers are locked out by + * ep_send_events() holding "mtx" and the + * poll callback will queue them in ep->ovflist. */ + list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); - epitem_ready(epi); } } - - __pm_relax(ep->ws); + ep_done_scan(ep, &txlist); mutex_unlock(&ep->mtx); - if (!llist_empty(&ep->rdllist)) { - if (waitqueue_active(&ep->wq)) - wake_up(&ep->wq); - } - return res; } @@ -1880,6 +2027,8 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, wait_queue_entry_t wait; ktime_t expires, *to = NULL; + lockdep_assert_irqs_enabled(); + if (timeout && (timeout->tv_sec | timeout->tv_nsec)) { slack = select_estimate_accuracy(timeout); to = &expires; @@ -1939,15 +2088,54 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, init_wait(&wait); wait.func = ep_autoremove_wake_function; - prepare_to_wait_exclusive(&ep->wq, &wait, TASK_INTERRUPTIBLE); + write_lock_irq(&ep->lock); + /* + * Barrierless variant, waitqueue_active() is called under + * the same lock on wakeup ep_poll_callback() side, so it + * is safe to avoid an explicit barrier. + */ + __set_current_state(TASK_INTERRUPTIBLE); + + /* + * Do the final check under the lock. ep_start/done_scan() + * plays with two lists (->rdllist and ->ovflist) and there + * is always a race when both lists are empty for short + * period of time although events are pending, so lock is + * important. + */ + eavail = ep_events_available(ep); + if (!eavail) + __add_wait_queue_exclusive(&ep->wq, &wait); + + write_unlock_irq(&ep->lock); - if (!ep_events_available(ep)) + if (!eavail) timed_out = !ep_schedule_timeout(to) || !schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS); + __set_current_state(TASK_RUNNING); - finish_wait(&ep->wq, &wait); - eavail = ep_events_available(ep); + /* + * We were woken up, thus go and try to harvest some events. + * If timed out and still on the wait queue, recheck eavail + * carefully under lock, below. + */ + eavail = 1; + + if (!list_empty_careful(&wait.entry)) { + write_lock_irq(&ep->lock); + /* + * If the thread timed out and is not on the wait queue, + * it means that the thread was woken up after its + * timeout expired before it could reacquire the lock. + * Thus, when wait.entry is empty, it needs to harvest + * events. + */ + if (timed_out) + eavail = list_empty(&wait.entry); + __remove_wait_queue(&ep->wq, &wait); + write_unlock_irq(&ep->lock); + } } } diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 3729391a18f3..fb4519158f3a 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -71,6 +71,9 @@ static void iomap_set_range_uptodate(struct folio *folio, size_t off, unsigned long flags; bool uptodate = true; + if (folio_test_uptodate(folio)) + return; + if (ifs) { spin_lock_irqsave(&ifs->state_lock, flags); uptodate = ifs_set_range_uptodate(folio, ifs, off, len); diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index d5da9817df9b..33e6a620c103 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -1440,9 +1440,16 @@ static int isofs_read_inode(struct inode *inode, int relocated) inode->i_op = &page_symlink_inode_operations; inode_nohighmem(inode); inode->i_data.a_ops = &isofs_symlink_aops; - } else + } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || + S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { /* XXX - parse_rock_ridge_inode() had already set i_rdev. */ init_special_inode(inode, inode->i_mode, inode->i_rdev); + } else { + printk(KERN_DEBUG "ISOFS: Invalid file type 0%04o for inode %lu.\n", + inode->i_mode, inode->i_ino); + ret = -EIO; + goto fail; + } ret = 0; out: diff --git a/fs/netfs/read_pgpriv2.c b/fs/netfs/read_pgpriv2.c index 5bbe906a551d..8097bc069c1d 100644 --- a/fs/netfs/read_pgpriv2.c +++ b/fs/netfs/read_pgpriv2.c @@ -110,6 +110,8 @@ static struct netfs_io_request *netfs_pgpriv2_begin_copy_to_cache( if (!creq->io_streams[1].avail) goto cancel_put; + __set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &creq->flags); + trace_netfs_copy2cache(rreq, creq); trace_netfs_write(creq, netfs_write_trace_copy_to_cache); netfs_stat(&netfs_n_wh_copy_to_cache); rreq->copy_to_cache = creq; @@ -154,6 +156,9 @@ void netfs_pgpriv2_end_copy_to_cache(struct netfs_io_request *rreq) netfs_issue_write(creq, &creq->io_streams[1]); smp_wmb(); /* Write lists before ALL_QUEUED. */ set_bit(NETFS_RREQ_ALL_QUEUED, &creq->flags); + trace_netfs_rreq(rreq, netfs_rreq_trace_end_copy_to_cache); + if (list_empty_careful(&creq->io_streams[1].subrequests)) + netfs_wake_collector(creq); netfs_put_request(creq, netfs_rreq_trace_put_return); creq->copy_to_cache = NULL; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 6613b8fcceb0..5cf7328d5360 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -472,11 +472,18 @@ static int __nilfs_read_inode(struct super_block *sb, inode->i_op = &nilfs_symlink_inode_operations; inode_nohighmem(inode); inode->i_mapping->a_ops = &nilfs_aops; - } else { + } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || + S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { inode->i_op = &nilfs_special_inode_operations; init_special_inode( inode, inode->i_mode, huge_decode_dev(le64_to_cpu(raw_inode->i_device_code))); + } else { + nilfs_error(sb, + "invalid file type bits in mode 0%o for inode %lu", + inode->i_mode, ino); + err = -EIO; + goto failed_unmap; } nilfs_ifile_unmap_inode(raw_inode); brelse(bh); diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index c4cdaf5fa7ed..9fb73bafd41d 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -308,6 +308,10 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) goto out_err; } + error = file_f_owner_allocate(filp); + if (error) + goto out_err; + /* new fsnotify mark, we expect most fcntl calls to add a new mark */ new_dn_mark = kmem_cache_alloc(dnotify_mark_cache, GFP_KERNEL); if (!new_dn_mark) { @@ -315,10 +319,6 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) goto out_err; } - error = file_f_owner_allocate(filp); - if (error) - goto out_err; - /* set up the new_fsn_mark and new_dn_mark */ new_fsn_mark = &new_dn_mark->fsn_mark; fsnotify_init_mark(new_fsn_mark, dnotify_group); diff --git a/fs/pidfs.c b/fs/pidfs.c index 69919be1c9d8..4625e097e3a0 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -319,7 +319,7 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) if (!c) return -ESRCH; - if (!(kinfo.mask & PIDFD_INFO_COREDUMP)) { + if ((kinfo.mask & PIDFD_INFO_COREDUMP) && !(kinfo.coredump_mask)) { task_lock(task); if (task->mm) kinfo.coredump_mask = pidfs_coredump_mask(task->mm->flags); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 4be91eb6ea5c..751479eb128f 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -36,9 +36,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) unsigned long text, lib, swap, anon, file, shmem; unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss; - anon = get_mm_counter(mm, MM_ANONPAGES); - file = get_mm_counter(mm, MM_FILEPAGES); - shmem = get_mm_counter(mm, MM_SHMEMPAGES); + anon = get_mm_counter_sum(mm, MM_ANONPAGES); + file = get_mm_counter_sum(mm, MM_FILEPAGES); + shmem = get_mm_counter_sum(mm, MM_SHMEMPAGES); /* * Note: to minimize their overhead, mm maintains hiwater_vm and @@ -59,7 +59,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) text = min(text, mm->exec_vm << PAGE_SHIFT); lib = (mm->exec_vm << PAGE_SHIFT) - text; - swap = get_mm_counter(mm, MM_SWAPENTS); + swap = get_mm_counter_sum(mm, MM_SWAPENTS); SEQ_PUT_DEC("VmPeak:\t", hiwater_vm); SEQ_PUT_DEC(" kB\nVmSize:\t", total_vm); SEQ_PUT_DEC(" kB\nVmLck:\t", mm->locked_vm); @@ -92,12 +92,12 @@ unsigned long task_statm(struct mm_struct *mm, unsigned long *shared, unsigned long *text, unsigned long *data, unsigned long *resident) { - *shared = get_mm_counter(mm, MM_FILEPAGES) + - get_mm_counter(mm, MM_SHMEMPAGES); + *shared = get_mm_counter_sum(mm, MM_FILEPAGES) + + get_mm_counter_sum(mm, MM_SHMEMPAGES); *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> PAGE_SHIFT; *data = mm->data_vm + mm->stack_vm; - *resident = *shared + get_mm_counter(mm, MM_ANONPAGES); + *resident = *shared + get_mm_counter_sum(mm, MM_ANONPAGES); return mm->total_vm; } diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index 1c6e5389c51f..5223edf6d11a 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -190,6 +190,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int disposition; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; + struct cached_fid *parent_cfid = NULL; int rdwr_for_fscache = 0; __le32 lease_flags = 0; @@ -313,10 +314,10 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned if (!tcon->unix_ext && (mode & S_IWUGO) == 0) create_options |= CREATE_OPTION_READONLY; + retry_open: if (tcon->cfids && direntry->d_parent && server->dialect >= SMB30_PROT_ID) { - struct cached_fid *parent_cfid; - + parent_cfid = NULL; spin_lock(&tcon->cfids->cfid_list_lock); list_for_each_entry(parent_cfid, &tcon->cfids->entries, entry) { if (parent_cfid->dentry == direntry->d_parent) { @@ -327,6 +328,7 @@ retry_open: memcpy(fid->parent_lease_key, parent_cfid->fid.lease_key, SMB2_LEASE_KEY_SIZE); + parent_cfid->dirents.is_valid = false; } break; } diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index e9212da32f01..1421bde045c2 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -3088,7 +3088,8 @@ void cifs_oplock_break(struct work_struct *work) struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo, oplock_break); struct inode *inode = d_inode(cfile->dentry); - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct super_block *sb = inode->i_sb; + struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct cifsInodeInfo *cinode = CIFS_I(inode); struct cifs_tcon *tcon; struct TCP_Server_Info *server; @@ -3098,6 +3099,12 @@ void cifs_oplock_break(struct work_struct *work) __u64 persistent_fid, volatile_fid; __u16 net_fid; + /* + * Hold a reference to the superblock to prevent it and its inodes from + * being freed while we are accessing cinode. Otherwise, _cifsFileInfo_put() + * may release the last reference to the sb and trigger inode eviction. + */ + cifs_sb_active(sb); wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); @@ -3170,6 +3177,7 @@ oplock_break_ack: cifs_put_tlink(tlink); out: cifs_done_oplock_break(cinode); + cifs_sb_deactive(sb); } static int cifs_swap_activate(struct swap_info_struct *sis, diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 2a3e46b8e15a..a11a2a693c51 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -1346,7 +1346,8 @@ struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data, * empty object on the server. */ if (!(le32_to_cpu(tcon->fsAttrInfo.Attributes) & FILE_SUPPORTS_REPARSE_POINTS)) - return ERR_PTR(-EOPNOTSUPP); + if (!tcon->posix_extensions) + return ERR_PTR(-EOPNOTSUPP); oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, SYNCHRONIZE | DELETE | diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 1468c16ea9b8..938a8a7c5d21 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -4316,6 +4316,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, u8 key[SMB3_ENC_DEC_KEY_SIZE]; struct aead_request *req; u8 *iv; + DECLARE_CRYPTO_WAIT(wait); unsigned int crypt_len = le32_to_cpu(tr_hdr->OriginalMessageSize); void *creq; size_t sensitive_size; @@ -4366,7 +4367,11 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, aead_request_set_crypt(req, sg, sg, crypt_len, iv); aead_request_set_ad(req, assoc_data_len); - rc = enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req); + aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, + crypto_req_done, &wait); + + rc = crypto_wait_req(enc ? crypto_aead_encrypt(req) + : crypto_aead_decrypt(req), &wait); if (!rc && enc) memcpy(&tr_hdr->Signature, sign, SMB2_SIGNATURE_SIZE); @@ -5255,7 +5260,8 @@ static int smb2_make_node(unsigned int xid, struct inode *inode, if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) { rc = cifs_sfu_make_node(xid, inode, dentry, tcon, full_path, mode, dev); - } else if (le32_to_cpu(tcon->fsAttrInfo.Attributes) & FILE_SUPPORTS_REPARSE_POINTS) { + } else if ((le32_to_cpu(tcon->fsAttrInfo.Attributes) & FILE_SUPPORTS_REPARSE_POINTS) + || (tcon->posix_extensions)) { rc = smb2_mknod_reparse(xid, inode, dentry, tcon, full_path, mode, dev); } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index fafa86273f12..63d17cea2e95 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -8573,11 +8573,6 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) goto err_out; } - opinfo->op_state = OPLOCK_STATE_NONE; - wake_up_interruptible_all(&opinfo->oplock_q); - opinfo_put(opinfo); - ksmbd_fd_put(work, fp); - rsp->StructureSize = cpu_to_le16(24); rsp->OplockLevel = rsp_oplevel; rsp->Reserved = 0; @@ -8585,16 +8580,15 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) rsp->VolatileFid = volatile_id; rsp->PersistentFid = persistent_id; ret = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_oplock_break)); - if (!ret) - return; - + if (ret) { err_out: + smb2_set_err_rsp(work); + } + opinfo->op_state = OPLOCK_STATE_NONE; wake_up_interruptible_all(&opinfo->oplock_q); - opinfo_put(opinfo); ksmbd_fd_put(work, fp); - smb2_set_err_rsp(work); } static int check_lease_state(struct lease *lease, __le32 req_state) @@ -8724,11 +8718,6 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) } lease_state = lease->state; - opinfo->op_state = OPLOCK_STATE_NONE; - wake_up_interruptible_all(&opinfo->oplock_q); - atomic_dec(&opinfo->breaking_cnt); - wake_up_interruptible_all(&opinfo->oplock_brk); - opinfo_put(opinfo); rsp->StructureSize = cpu_to_le16(36); rsp->Reserved = 0; @@ -8737,16 +8726,16 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) rsp->LeaseState = lease_state; rsp->LeaseDuration = 0; ret = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_lease_ack)); - if (!ret) - return; - + if (ret) { err_out: + smb2_set_err_rsp(work); + } + + opinfo->op_state = OPLOCK_STATE_NONE; wake_up_interruptible_all(&opinfo->oplock_q); atomic_dec(&opinfo->breaking_cnt); wake_up_interruptible_all(&opinfo->oplock_brk); - opinfo_put(opinfo); - smb2_set_err_rsp(work); } /** diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 64a428a06ace..c6cbe0d56e32 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -433,7 +433,8 @@ static void free_transport(struct smb_direct_transport *t) if (t->qp) { ib_drain_qp(t->qp); ib_mr_pool_destroy(t->qp, &t->qp->rdma_mrs); - ib_destroy_qp(t->qp); + t->qp = NULL; + rdma_destroy_qp(t->cm_id); } ksmbd_debug(RDMA, "drain the reassembly queue\n"); @@ -1940,8 +1941,8 @@ static int smb_direct_create_qpair(struct smb_direct_transport *t, return 0; err: if (t->qp) { - ib_destroy_qp(t->qp); t->qp = NULL; + rdma_destroy_qp(t->cm_id); } if (t->recv_cq) { ib_destroy_cq(t->recv_cq); diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 0f3aad12e495..d3437f6644e3 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -1282,6 +1282,7 @@ out1: err = ksmbd_vfs_lock_parent(parent_path->dentry, path->dentry); if (err) { + mnt_drop_write(parent_path->mnt); path_put(path); path_put(parent_path); } diff --git a/fs/ufs/super.c b/fs/ufs/super.c index eea718ac66b4..6e4585169f94 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -397,7 +397,7 @@ static int ufs_parse_param(struct fs_context *fc, struct fs_parameter *param) pr_err("ufstype can't be changed during remount\n"); return -EINVAL; } - if (!ctx->flavour) { + if (ctx->flavour) { pr_err("conflicting ufstype options\n"); return -EINVAL; } diff --git a/fs/xfs/libxfs/xfs_group.c b/fs/xfs/libxfs/xfs_group.c index e9d76bcdc820..20ad7c309489 100644 --- a/fs/xfs/libxfs/xfs_group.c +++ b/fs/xfs/libxfs/xfs_group.c @@ -163,7 +163,8 @@ xfs_group_free( xfs_defer_drain_free(&xg->xg_intents_drain); #ifdef __KERNEL__ - kfree(xg->xg_busy_extents); + if (xfs_group_has_extent_busy(xg->xg_mount, xg->xg_type)) + kfree(xg->xg_busy_extents); #endif if (uninit) @@ -189,9 +190,11 @@ xfs_group_insert( xg->xg_type = type; #ifdef __KERNEL__ - xg->xg_busy_extents = xfs_extent_busy_alloc(); - if (!xg->xg_busy_extents) - return -ENOMEM; + if (xfs_group_has_extent_busy(mp, type)) { + xg->xg_busy_extents = xfs_extent_busy_alloc(); + if (!xg->xg_busy_extents) + return -ENOMEM; + } spin_lock_init(&xg->xg_state_lock); xfs_hooks_init(&xg->xg_rmap_update_hooks); #endif @@ -210,7 +213,8 @@ xfs_group_insert( out_drain: xfs_defer_drain_free(&xg->xg_intents_drain); #ifdef __KERNEL__ - kfree(xg->xg_busy_extents); + if (xfs_group_has_extent_busy(xg->xg_mount, xg->xg_type)) + kfree(xg->xg_busy_extents); #endif return error; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index ba5bd6031ece..f9ef3b2a332a 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1683,7 +1683,7 @@ xfs_free_buftarg( fs_put_dax(btp->bt_daxdev, btp->bt_mount); /* the main block device is closed by kill_block_super */ if (btp->bt_bdev != btp->bt_mount->m_super->s_bdev) - bdev_fput(btp->bt_bdev_file); + bdev_fput(btp->bt_file); kfree(btp); } @@ -1712,8 +1712,8 @@ xfs_configure_buftarg_atomic_writes( max_bytes = 0; } - btp->bt_bdev_awu_min = min_bytes; - btp->bt_bdev_awu_max = max_bytes; + btp->bt_awu_min = min_bytes; + btp->bt_awu_max = max_bytes; } /* Configure a buffer target that abstracts a block device. */ @@ -1738,14 +1738,9 @@ xfs_configure_buftarg( return -EINVAL; } - /* - * Flush the block device pagecache so our bios see anything dirtied - * before mount. - */ if (bdev_can_atomic_write(btp->bt_bdev)) xfs_configure_buftarg_atomic_writes(btp); - - return sync_blockdev(btp->bt_bdev); + return 0; } int @@ -1803,7 +1798,7 @@ xfs_alloc_buftarg( btp = kzalloc(sizeof(*btp), GFP_KERNEL | __GFP_NOFAIL); btp->bt_mount = mp; - btp->bt_bdev_file = bdev_file; + btp->bt_file = bdev_file; btp->bt_bdev = file_bdev(bdev_file); btp->bt_dev = btp->bt_bdev->bd_dev; btp->bt_daxdev = fs_dax_get_by_bdev(btp->bt_bdev, &btp->bt_dax_part_off, diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 15fc56948346..b269e115d9ac 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -94,7 +94,6 @@ void xfs_buf_cache_destroy(struct xfs_buf_cache *bch); */ struct xfs_buftarg { dev_t bt_dev; - struct file *bt_bdev_file; struct block_device *bt_bdev; struct dax_device *bt_daxdev; struct file *bt_file; @@ -112,9 +111,9 @@ struct xfs_buftarg { struct percpu_counter bt_readahead_count; struct ratelimit_state bt_ioerror_rl; - /* Atomic write unit values, bytes */ - unsigned int bt_bdev_awu_min; - unsigned int bt_bdev_awu_max; + /* Hardware atomic write unit values, bytes */ + unsigned int bt_awu_min; + unsigned int bt_awu_max; /* built-in cache, if we're not using the perag one */ struct xfs_buf_cache bt_cache[]; @@ -375,7 +374,6 @@ extern void xfs_buftarg_wait(struct xfs_buftarg *); extern void xfs_buftarg_drain(struct xfs_buftarg *); int xfs_configure_buftarg(struct xfs_buftarg *btp, unsigned int sectorsize); -#define xfs_getsize_buftarg(buftarg) block_size((buftarg)->bt_bdev) #define xfs_readonly_buftarg(buftarg) bdev_read_only((buftarg)->bt_bdev) int xfs_buf_reverify(struct xfs_buf *bp, const struct xfs_buf_ops *ops); diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index 94d0873bcd62..603d51365645 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -103,24 +103,6 @@ xfs_discard_endio( bio_put(bio); } -static inline struct block_device * -xfs_group_bdev( - const struct xfs_group *xg) -{ - struct xfs_mount *mp = xg->xg_mount; - - switch (xg->xg_type) { - case XG_TYPE_AG: - return mp->m_ddev_targp->bt_bdev; - case XG_TYPE_RTG: - return mp->m_rtdev_targp->bt_bdev; - default: - ASSERT(0); - break; - } - return NULL; -} - /* * Walk the discard list and issue discards on all the busy extents in the * list. We plug and chain the bios so that we only need a single completion @@ -138,11 +120,14 @@ xfs_discard_extents( blk_start_plug(&plug); list_for_each_entry(busyp, &extents->extent_list, list) { - trace_xfs_discard_extent(busyp->group, busyp->bno, - busyp->length); + struct xfs_group *xg = busyp->group; + struct xfs_buftarg *btp = + xfs_group_type_buftarg(xg->xg_mount, xg->xg_type); + + trace_xfs_discard_extent(xg, busyp->bno, busyp->length); - error = __blkdev_issue_discard(xfs_group_bdev(busyp->group), - xfs_gbno_to_daddr(busyp->group, busyp->bno), + error = __blkdev_issue_discard(btp->bt_bdev, + xfs_gbno_to_daddr(xg, busyp->bno), XFS_FSB_TO_BB(mp, busyp->length), GFP_KERNEL, &bio); if (error && error != -EOPNOTSUPP) { diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h index f069b04e8ea1..3e6e019b6146 100644 --- a/fs/xfs/xfs_extent_busy.h +++ b/fs/xfs/xfs_extent_busy.h @@ -68,4 +68,12 @@ static inline void xfs_extent_busy_sort(struct list_head *list) list_sort(NULL, list, xfs_extent_busy_ag_cmp); } +/* + * Zoned RTGs don't need to track busy extents, as the actual block freeing only + * happens by a zone reset, which forces out all transactions that touched the + * to be reset zone first. + */ +#define xfs_group_has_extent_busy(mp, type) \ + ((type) == XG_TYPE_AG || !xfs_has_zoned((mp))) + #endif /* __XFS_EXTENT_BUSY_H__ */ diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 0b41b18debf3..38e365b16348 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -752,7 +752,7 @@ xfs_file_dio_write_atomic( * HW offload should be faster, so try that first if it is already * known that the write length is not too large. */ - if (ocount > xfs_inode_buftarg(ip)->bt_bdev_awu_max) + if (ocount > xfs_inode_buftarg(ip)->bt_awu_max) dops = &xfs_atomic_write_cow_iomap_ops; else dops = &xfs_direct_write_iomap_ops; diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index d7e2b902ef5c..07fbdcc4cbf5 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -358,7 +358,7 @@ static inline bool xfs_inode_has_bigrtalloc(const struct xfs_inode *ip) static inline bool xfs_inode_can_hw_atomic_write(const struct xfs_inode *ip) { - return xfs_inode_buftarg(ip)->bt_bdev_awu_max > 0; + return xfs_inode_buftarg(ip)->bt_awu_max > 0; } /* diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index ff05e6b1b0bb..ec30b78bf5c4 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -827,7 +827,7 @@ xfs_bmap_hw_atomic_write_possible( /* * The ->iomap_begin caller should ensure this, but check anyway. */ - return len <= xfs_inode_buftarg(ip)->bt_bdev_awu_max; + return len <= xfs_inode_buftarg(ip)->bt_awu_max; } static int diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 8cddbb7c149b..01e597290eb5 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -665,7 +665,7 @@ xfs_get_atomic_write_max_opt( * less than our out of place write limit, but we don't want to exceed * the awu_max. */ - return min(awu_max, xfs_inode_buftarg(ip)->bt_bdev_awu_max); + return min(awu_max, xfs_inode_buftarg(ip)->bt_awu_max); } static void diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 29276fe60df9..0b690bc119d7 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -171,19 +171,16 @@ xfs_readsb( ASSERT(mp->m_ddev_targp != NULL); /* - * For the initial read, we must guess at the sector - * size based on the block device. It's enough to - * get the sb_sectsize out of the superblock and - * then reread with the proper length. - * We don't verify it yet, because it may not be complete. + * In the first pass, use the device sector size to just read enough + * of the superblock to extract the XFS sector size. + * + * The device sector size must be smaller than or equal to the XFS + * sector size and thus we can always read the superblock. Once we know + * the XFS sector size, re-read it and run the buffer verifier. */ - sector_size = xfs_getsize_buftarg(mp->m_ddev_targp); + sector_size = mp->m_ddev_targp->bt_logical_sectorsize; buf_ops = NULL; - /* - * Allocate a (locked) buffer to hold the superblock. This will be kept - * around at all times to optimize access to the superblock. - */ reread: error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR, BTOBB(sector_size), &bp, buf_ops); @@ -247,6 +244,10 @@ reread: /* no need to be quiet anymore, so reset the buf ops */ bp->b_ops = &xfs_sb_buf_ops; + /* + * Keep a pointer of the sb buffer around instead of caching it in the + * buffer cache because we access it frequently. + */ mp->m_sb_bp = bp; xfs_buf_unlock(bp); return 0; @@ -678,68 +679,46 @@ static inline unsigned int max_pow_of_two_factor(const unsigned int nr) } /* - * If the data device advertises atomic write support, limit the size of data - * device atomic writes to the greatest power-of-two factor of the AG size so - * that every atomic write unit aligns with the start of every AG. This is - * required so that the per-AG allocations for an atomic write will always be + * If the underlying device advertises atomic write support, limit the size of + * atomic writes to the greatest power-of-two factor of the group size so + * that every atomic write unit aligns with the start of every group. This is + * required so that the allocations for an atomic write will always be * aligned compatibly with the alignment requirements of the storage. * - * If the data device doesn't advertise atomic writes, then there are no - * alignment restrictions and the largest out-of-place write we can do - * ourselves is the number of blocks that user files can allocate from any AG. - */ -static inline xfs_extlen_t xfs_calc_perag_awu_max(struct xfs_mount *mp) -{ - if (mp->m_ddev_targp->bt_bdev_awu_min > 0) - return max_pow_of_two_factor(mp->m_sb.sb_agblocks); - return rounddown_pow_of_two(mp->m_ag_max_usable); -} - -/* - * Reflink on the realtime device requires rtgroups, and atomic writes require - * reflink. - * - * If the realtime device advertises atomic write support, limit the size of - * data device atomic writes to the greatest power-of-two factor of the rtgroup - * size so that every atomic write unit aligns with the start of every rtgroup. - * This is required so that the per-rtgroup allocations for an atomic write - * will always be aligned compatibly with the alignment requirements of the - * storage. - * - * If the rt device doesn't advertise atomic writes, then there are no - * alignment restrictions and the largest out-of-place write we can do - * ourselves is the number of blocks that user files can allocate from any - * rtgroup. + * If the device doesn't advertise atomic writes, then there are no alignment + * restrictions and the largest out-of-place write we can do ourselves is the + * number of blocks that user files can allocate from any group. */ -static inline xfs_extlen_t xfs_calc_rtgroup_awu_max(struct xfs_mount *mp) +static xfs_extlen_t +xfs_calc_group_awu_max( + struct xfs_mount *mp, + enum xfs_group_type type) { - struct xfs_groups *rgs = &mp->m_groups[XG_TYPE_RTG]; + struct xfs_groups *g = &mp->m_groups[type]; + struct xfs_buftarg *btp = xfs_group_type_buftarg(mp, type); - if (rgs->blocks == 0) + if (g->blocks == 0) return 0; - if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_bdev_awu_min > 0) - return max_pow_of_two_factor(rgs->blocks); - return rounddown_pow_of_two(rgs->blocks); + if (btp && btp->bt_awu_min > 0) + return max_pow_of_two_factor(g->blocks); + return rounddown_pow_of_two(g->blocks); } /* Compute the maximum atomic write unit size for each section. */ static inline void xfs_calc_atomic_write_unit_max( - struct xfs_mount *mp) + struct xfs_mount *mp, + enum xfs_group_type type) { - struct xfs_groups *ags = &mp->m_groups[XG_TYPE_AG]; - struct xfs_groups *rgs = &mp->m_groups[XG_TYPE_RTG]; + struct xfs_groups *g = &mp->m_groups[type]; const xfs_extlen_t max_write = xfs_calc_atomic_write_max(mp); const xfs_extlen_t max_ioend = xfs_reflink_max_atomic_cow(mp); - const xfs_extlen_t max_agsize = xfs_calc_perag_awu_max(mp); - const xfs_extlen_t max_rgsize = xfs_calc_rtgroup_awu_max(mp); - - ags->awu_max = min3(max_write, max_ioend, max_agsize); - rgs->awu_max = min3(max_write, max_ioend, max_rgsize); + const xfs_extlen_t max_gsize = xfs_calc_group_awu_max(mp, type); - trace_xfs_calc_atomic_write_unit_max(mp, max_write, max_ioend, - max_agsize, max_rgsize); + g->awu_max = min3(max_write, max_ioend, max_gsize); + trace_xfs_calc_atomic_write_unit_max(mp, type, max_write, max_ioend, + max_gsize, g->awu_max); } /* @@ -757,7 +736,8 @@ xfs_set_max_atomic_write_opt( max(mp->m_groups[XG_TYPE_AG].blocks, mp->m_groups[XG_TYPE_RTG].blocks); const xfs_extlen_t max_group_write = - max(xfs_calc_perag_awu_max(mp), xfs_calc_rtgroup_awu_max(mp)); + max(xfs_calc_group_awu_max(mp, XG_TYPE_AG), + xfs_calc_group_awu_max(mp, XG_TYPE_RTG)); int error; if (new_max_bytes == 0) @@ -813,7 +793,8 @@ set_limit: return error; } - xfs_calc_atomic_write_unit_max(mp); + xfs_calc_atomic_write_unit_max(mp, XG_TYPE_AG); + xfs_calc_atomic_write_unit_max(mp, XG_TYPE_RTG); mp->m_awu_max_bytes = new_max_bytes; return 0; } diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index d85084f9f317..97de44c32272 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -802,4 +802,21 @@ static inline void xfs_mod_sb_delalloc(struct xfs_mount *mp, int64_t delta) int xfs_set_max_atomic_write_opt(struct xfs_mount *mp, unsigned long long new_max_bytes); +static inline struct xfs_buftarg * +xfs_group_type_buftarg( + struct xfs_mount *mp, + enum xfs_group_type type) +{ + switch (type) { + case XG_TYPE_AG: + return mp->m_ddev_targp; + case XG_TYPE_RTG: + return mp->m_rtdev_targp; + default: + ASSERT(0); + break; + } + return NULL; +} + #endif /* __XFS_MOUNT_H__ */ diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c index 3545dc1d953c..42e9c72b85c0 100644 --- a/fs/xfs/xfs_notify_failure.c +++ b/fs/xfs/xfs_notify_failure.c @@ -253,8 +253,7 @@ xfs_dax_notify_dev_failure( return -EOPNOTSUPP; } - error = xfs_dax_translate_range(type == XG_TYPE_RTG ? - mp->m_rtdev_targp : mp->m_ddev_targp, + error = xfs_dax_translate_range(xfs_group_type_buftarg(mp, type), offset, len, &daddr, &bblen); if (error) return error; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index ba45d801df1c..78be223b13b2 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -171,36 +171,33 @@ DEFINE_ATTR_LIST_EVENT(xfs_attr_leaf_list); DEFINE_ATTR_LIST_EVENT(xfs_attr_node_list); TRACE_EVENT(xfs_calc_atomic_write_unit_max, - TP_PROTO(struct xfs_mount *mp, unsigned int max_write, - unsigned int max_ioend, unsigned int max_agsize, - unsigned int max_rgsize), - TP_ARGS(mp, max_write, max_ioend, max_agsize, max_rgsize), + TP_PROTO(struct xfs_mount *mp, enum xfs_group_type type, + unsigned int max_write, unsigned int max_ioend, + unsigned int max_gsize, unsigned int awu_max), + TP_ARGS(mp, type, max_write, max_ioend, max_gsize, awu_max), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(unsigned int, max_write) __field(unsigned int, max_ioend) - __field(unsigned int, max_agsize) - __field(unsigned int, max_rgsize) - __field(unsigned int, data_awu_max) - __field(unsigned int, rt_awu_max) + __field(unsigned int, max_gsize) + __field(unsigned int, awu_max) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; + __entry->type = type; __entry->max_write = max_write; __entry->max_ioend = max_ioend; - __entry->max_agsize = max_agsize; - __entry->max_rgsize = max_rgsize; - __entry->data_awu_max = mp->m_groups[XG_TYPE_AG].awu_max; - __entry->rt_awu_max = mp->m_groups[XG_TYPE_RTG].awu_max; + __entry->max_gsize = max_gsize; + __entry->awu_max = awu_max; ), - TP_printk("dev %d:%d max_write %u max_ioend %u max_agsize %u max_rgsize %u data_awu_max %u rt_awu_max %u", + TP_printk("dev %d:%d %s max_write %u max_ioend %u max_gsize %u awu_max %u", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->max_write, __entry->max_ioend, - __entry->max_agsize, - __entry->max_rgsize, - __entry->data_awu_max, - __entry->rt_awu_max) + __entry->max_gsize, + __entry->awu_max) ); TRACE_EVENT(xfs_calc_max_atomic_write_fsblocks, diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index 0f641a9091ec..ac5cecec9aa1 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -243,7 +243,7 @@ __xfs_xattr_put_listent( offset = context->buffer + context->count; memcpy(offset, prefix, prefix_len); offset += prefix_len; - strncpy(offset, (char *)name, namelen); /* real name */ + memcpy(offset, (char *)name, namelen); /* real name */ offset += namelen; *offset = '\0'; diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h index 9689a7c5dd36..513837632b7d 100644 --- a/include/drm/drm_buddy.h +++ b/include/drm/drm_buddy.h @@ -160,6 +160,8 @@ int drm_buddy_block_trim(struct drm_buddy *mm, u64 new_size, struct list_head *blocks); +void drm_buddy_reset_clear(struct drm_buddy *mm, bool is_clear); + void drm_buddy_free_block(struct drm_buddy *mm, struct drm_buddy_block *block); void drm_buddy_free_list(struct drm_buddy *mm, diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h index 5c3b2aa3e69d..d344d41e6cfe 100644 --- a/include/drm/drm_file.h +++ b/include/drm/drm_file.h @@ -300,6 +300,9 @@ struct drm_file { * * Mapping of mm object handles to object pointers. Used by the GEM * subsystem. Protected by @table_lock. + * + * Note that allocated entries might be NULL as a transient state when + * creating or deleting a handle. */ struct idr object_idr; diff --git a/include/drm/drm_framebuffer.h b/include/drm/drm_framebuffer.h index 668077009fce..38b24fc8978d 100644 --- a/include/drm/drm_framebuffer.h +++ b/include/drm/drm_framebuffer.h @@ -23,6 +23,7 @@ #ifndef __DRM_FRAMEBUFFER_H__ #define __DRM_FRAMEBUFFER_H__ +#include <linux/bits.h> #include <linux/ctype.h> #include <linux/list.h> #include <linux/sched.h> @@ -100,6 +101,8 @@ struct drm_framebuffer_funcs { unsigned num_clips); }; +#define DRM_FRAMEBUFFER_HAS_HANDLE_REF(_i) BIT(0u + (_i)) + /** * struct drm_framebuffer - frame buffer object * @@ -189,6 +192,10 @@ struct drm_framebuffer { */ int flags; /** + * @internal_flags: Framebuffer flags like DRM_FRAMEBUFFER_HAS_HANDLE_REF. + */ + unsigned int internal_flags; + /** * @filp_head: Placed on &drm_file.fbs, protected by &drm_file.fbs_lock. */ struct list_head filp_head; diff --git a/include/dt-bindings/clock/sun8i-v3s-ccu.h b/include/dt-bindings/clock/sun8i-v3s-ccu.h index 014ac6123d17..c4055629c9f9 100644 --- a/include/dt-bindings/clock/sun8i-v3s-ccu.h +++ b/include/dt-bindings/clock/sun8i-v3s-ccu.h @@ -96,7 +96,7 @@ #define CLK_TCON0 64 #define CLK_CSI_MISC 65 #define CLK_CSI0_MCLK 66 -#define CLK_CSI1_SCLK 67 +#define CLK_CSI_SCLK 67 #define CLK_CSI1_MCLK 68 #define CLK_VE 69 #define CLK_AC_DIG 70 diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 4a34f7f0a864..b2a04481de1a 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -434,7 +434,7 @@ struct kvm_kernel_irq_routing_entry; int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int irq, struct kvm_kernel_irq_routing_entry *irq_entry); -int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int host_irq); +void kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int host_irq); int vgic_v4_load(struct kvm_vcpu *vcpu); void vgic_v4_commit(struct kvm_vcpu *vcpu); diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h index 062fbd4c9b77..8cced632ecd0 100644 --- a/include/linux/amd-iommu.h +++ b/include/linux/amd-iommu.h @@ -12,20 +12,6 @@ struct amd_iommu; -/* - * This is mainly used to communicate information back-and-forth - * between SVM and IOMMU for setting up and tearing down posted - * interrupt - */ -struct amd_iommu_pi_data { - u32 ga_tag; - u32 prev_ga_tag; - u64 base; - bool is_guest_mode; - struct vcpu_data *vcpu_data; - void *ir_data; -}; - #ifdef CONFIG_AMD_IOMMU struct task_struct; @@ -44,10 +30,8 @@ static inline void amd_iommu_detect(void) { } /* IOMMU AVIC Function */ extern int amd_iommu_register_ga_log_notifier(int (*notifier)(u32)); -extern int -amd_iommu_update_ga(int cpu, bool is_run, void *data); - -extern int amd_iommu_activate_guest_mode(void *data); +extern int amd_iommu_update_ga(void *data, int cpu, bool ga_log_intr); +extern int amd_iommu_activate_guest_mode(void *data, int cpu, bool ga_log_intr); extern int amd_iommu_deactivate_guest_mode(void *data); #else /* defined(CONFIG_AMD_IOMMU) && defined(CONFIG_IRQ_REMAP) */ @@ -58,13 +42,12 @@ amd_iommu_register_ga_log_notifier(int (*notifier)(u32)) return 0; } -static inline int -amd_iommu_update_ga(int cpu, bool is_run, void *data) +static inline int amd_iommu_update_ga(void *data, int cpu, bool ga_log_intr) { return 0; } -static inline int amd_iommu_activate_guest_mode(void *data) +static inline int amd_iommu_activate_guest_mode(void *data, int cpu, bool ga_log_intr) { return 0; } diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 784ebe4607a4..50b47eba7d01 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -113,7 +113,7 @@ /* KVM UID value: 28b46fb6-2ec5-11e9-a9ca-4b564d003a74 */ #define ARM_SMCCC_VENDOR_HYP_UID_KVM UUID_INIT(\ - 0xb66fb428, 0xc52e, 0xe911, \ + 0x28b46fb6, 0x2ec5, 0x11e9, \ 0xa9, 0xca, 0x4b, 0x56, \ 0x4d, 0x00, 0x3a, 0x74) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a59880c809c7..181a0deadc9e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -269,11 +269,16 @@ static inline dev_t disk_devt(struct gendisk *disk) return MKDEV(disk->major, disk->first_minor); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * We should strive for 1 << (PAGE_SHIFT + MAX_PAGECACHE_ORDER) * however we constrain this to what we can validate and test. */ #define BLK_MAX_BLOCK_SIZE SZ_64K +#else +#define BLK_MAX_BLOCK_SIZE PAGE_SIZE +#endif + /* blk_validate_limits() validates bsize, so drivers don't usually need to */ static inline int blk_validate_block_size(unsigned long bsize) diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 96a3a0d6a60e..6378370a952f 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -82,6 +82,7 @@ extern ssize_t cpu_show_old_microcode(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 22f39e5e2ff1..996be3c2cff0 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -663,18 +663,6 @@ static inline bool ieee80211_s1g_has_cssid(__le16 fc) } /** - * ieee80211_is_s1g_short_beacon - check if frame is an S1G short beacon - * @fc: frame control bytes in little-endian byteorder - * Return: whether or not the frame is an S1G short beacon, - * i.e. it is an S1G beacon with 'next TBTT' flag set - */ -static inline bool ieee80211_is_s1g_short_beacon(__le16 fc) -{ - return ieee80211_is_s1g_beacon(fc) && - (fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT)); -} - -/** * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is an ATIM frame @@ -4901,6 +4889,39 @@ static inline bool ieee80211_is_ftm(struct sk_buff *skb) return false; } +/** + * ieee80211_is_s1g_short_beacon - check if frame is an S1G short beacon + * @fc: frame control bytes in little-endian byteorder + * @variable: pointer to the beacon frame elements + * @variable_len: length of the frame elements + * Return: whether or not the frame is an S1G short beacon. As per + * IEEE80211-2024 11.1.3.10.1, The S1G beacon compatibility element shall + * always be present as the first element in beacon frames generated at a + * TBTT (Target Beacon Transmission Time), so any frame not containing + * this element must have been generated at a TSBTT (Target Short Beacon + * Transmission Time) that is not a TBTT. Additionally, short beacons are + * prohibited from containing the S1G beacon compatibility element as per + * IEEE80211-2024 9.3.4.3 Table 9-76, so if we have an S1G beacon with + * either no elements or the first element is not the beacon compatibility + * element, we have a short beacon. + */ +static inline bool ieee80211_is_s1g_short_beacon(__le16 fc, const u8 *variable, + size_t variable_len) +{ + if (!ieee80211_is_s1g_beacon(fc)) + return false; + + /* + * If the frame does not contain at least 1 element (this is perfectly + * valid in a short beacon) and is an S1G beacon, we have a short + * beacon. + */ + if (variable_len < 2) + return true; + + return variable[0] != WLAN_EID_S1G_BCN_COMPAT; +} + struct element { u8 id; u8 datalen; diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index 55cfebc658e6..8a2f652a05ff 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -119,6 +119,7 @@ int icc_std_aggregate(struct icc_node *node, u32 tag, u32 avg_bw, struct icc_node *icc_node_create_dyn(void); struct icc_node *icc_node_create(int id); void icc_node_destroy(int id); +int icc_node_set_name(struct icc_node *node, const struct icc_provider *provider, const char *name); int icc_link_nodes(struct icc_node *src_node, struct icc_node **dst_node); int icc_link_create(struct icc_node *node, const int dst_id); void icc_node_add(struct icc_node *node, struct icc_provider *provider); @@ -152,6 +153,12 @@ static inline void icc_node_destroy(int id) { } +static inline int icc_node_set_name(struct icc_node *node, const struct icc_provider *provider, + const char *name) +{ + return -EOPNOTSUPP; +} + static inline int icc_link_nodes(struct icc_node *src_node, struct icc_node **dst_node) { return -EOPNOTSUPP; diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 2922635986f5..a7efcec2e3d0 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -698,6 +698,8 @@ struct io_kiocb { struct hlist_node hash_node; /* For IOPOLL setup queues, with hybrid polling */ u64 iopoll_start; + /* for private io_kiocb freeing */ + struct rcu_head rcu_head; }; /* internal polling, see IORING_FEAT_FAST_POLL */ struct async_poll *apoll; diff --git a/include/linux/irqbypass.h b/include/linux/irqbypass.h index 9bdb2a781841..ede1fa938152 100644 --- a/include/linux/irqbypass.h +++ b/include/linux/irqbypass.h @@ -10,6 +10,7 @@ #include <linux/list.h> +struct eventfd_ctx; struct irq_bypass_consumer; /* @@ -18,20 +19,22 @@ struct irq_bypass_consumer; * The IRQ bypass manager is a simple set of lists and callbacks that allows * IRQ producers (ex. physical interrupt sources) to be matched to IRQ * consumers (ex. virtualization hardware that allows IRQ bypass or offload) - * via a shared token (ex. eventfd_ctx). Producers and consumers register - * independently. When a token match is found, the optional @stop callback - * will be called for each participant. The pair will then be connected via - * the @add_* callbacks, and finally the optional @start callback will allow - * any final coordination. When either participant is unregistered, the - * process is repeated using the @del_* callbacks in place of the @add_* - * callbacks. Match tokens must be unique per producer/consumer, 1:N pairings - * are not supported. + * via a shared eventfd_ctx. Producers and consumers register independently. + * When a producer and consumer are paired, i.e. an eventfd match is found, the + * optional @stop callback will be called for each participant. The pair will + * then be connected via the @add_* callbacks, and finally the optional @start + * callback will allow any final coordination. When either participant is + * unregistered, the process is repeated using the @del_* callbacks in place of + * the @add_* callbacks. eventfds must be unique per producer/consumer, 1:N + * pairings are not supported. */ +struct irq_bypass_consumer; + /** * struct irq_bypass_producer - IRQ bypass producer definition - * @node: IRQ bypass manager private list management - * @token: opaque token to match between producer and consumer (non-NULL) + * @eventfd: eventfd context used to match producers and consumers + * @consumer: The connected consumer (NULL if no connection) * @irq: Linux IRQ number for the producer device * @add_consumer: Connect the IRQ producer to an IRQ consumer (optional) * @del_consumer: Disconnect the IRQ producer from an IRQ consumer (optional) @@ -43,8 +46,8 @@ struct irq_bypass_consumer; * for a physical device assigned to a VM. */ struct irq_bypass_producer { - struct list_head node; - void *token; + struct eventfd_ctx *eventfd; + struct irq_bypass_consumer *consumer; int irq; int (*add_consumer)(struct irq_bypass_producer *, struct irq_bypass_consumer *); @@ -56,8 +59,8 @@ struct irq_bypass_producer { /** * struct irq_bypass_consumer - IRQ bypass consumer definition - * @node: IRQ bypass manager private list management - * @token: opaque token to match between producer and consumer (non-NULL) + * @eventfd: eventfd context used to match producers and consumers + * @producer: The connected producer (NULL if no connection) * @add_producer: Connect the IRQ consumer to an IRQ producer * @del_producer: Disconnect the IRQ consumer from an IRQ producer * @stop: Perform any quiesce operations necessary prior to add/del (optional) @@ -69,8 +72,9 @@ struct irq_bypass_producer { * portions of the interrupt handling to the VM. */ struct irq_bypass_consumer { - struct list_head node; - void *token; + struct eventfd_ctx *eventfd; + struct irq_bypass_producer *producer; + int (*add_producer)(struct irq_bypass_consumer *, struct irq_bypass_producer *); void (*del_producer)(struct irq_bypass_consumer *, @@ -79,9 +83,11 @@ struct irq_bypass_consumer { void (*start)(struct irq_bypass_consumer *); }; -int irq_bypass_register_producer(struct irq_bypass_producer *); -void irq_bypass_unregister_producer(struct irq_bypass_producer *); -int irq_bypass_register_consumer(struct irq_bypass_consumer *); -void irq_bypass_unregister_consumer(struct irq_bypass_consumer *); +int irq_bypass_register_producer(struct irq_bypass_producer *producer, + struct eventfd_ctx *eventfd, int irq); +void irq_bypass_unregister_producer(struct irq_bypass_producer *producer); +int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer, + struct eventfd_ctx *eventfd); +void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer); #endif /* IRQBYPASS_H */ diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index 7f1f11a5e4e4..0b0887099fd7 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -146,7 +146,7 @@ int its_commit_vpe(struct its_vpe *vpe); int its_invall_vpe(struct its_vpe *vpe); int its_map_vlpi(int irq, struct its_vlpi_map *map); int its_get_vlpi(int irq, struct its_vlpi_map *map); -int its_unmap_vlpi(int irq); +void its_unmap_vlpi(int irq); int its_prop_update_vlpi(int irq, u8 config, bool inv); int its_prop_update_vsgi(int irq, u8 priority, bool group); diff --git a/include/linux/irqchip/irq-msi-lib.h b/include/linux/irqchip/irq-msi-lib.h index dd8d1d138544..224ac28e88d7 100644 --- a/include/linux/irqchip/irq-msi-lib.h +++ b/include/linux/irqchip/irq-msi-lib.h @@ -17,6 +17,7 @@ #define MATCH_PLATFORM_MSI BIT(DOMAIN_BUS_PLATFORM_MSI) +struct msi_domain_info; int msi_lib_irq_domain_select(struct irq_domain *d, struct irq_fwspec *fwspec, enum irq_domain_bus_token bus_token); diff --git a/include/linux/ism.h b/include/linux/ism.h index 5428edd90982..8358b4cd7ba6 100644 --- a/include/linux/ism.h +++ b/include/linux/ism.h @@ -28,6 +28,7 @@ struct ism_dmb { struct ism_dev { spinlock_t lock; /* protects the ism device */ + spinlock_t cmd_lock; /* serializes cmds */ struct list_head list; struct pci_dev *pdev; diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h index da4d9b5f58f1..eb10d87adf7d 100644 --- a/include/linux/kvm_dirty_ring.h +++ b/include/linux/kvm_dirty_ring.h @@ -49,9 +49,10 @@ static inline int kvm_dirty_ring_alloc(struct kvm *kvm, struct kvm_dirty_ring *r } static inline int kvm_dirty_ring_reset(struct kvm *kvm, - struct kvm_dirty_ring *ring) + struct kvm_dirty_ring *ring, + int *nr_entries_reset) { - return 0; + return -ENOENT; } static inline void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, @@ -77,17 +78,8 @@ bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm); u32 kvm_dirty_ring_get_rsvd_entries(struct kvm *kvm); int kvm_dirty_ring_alloc(struct kvm *kvm, struct kvm_dirty_ring *ring, int index, u32 size); - -/* - * called with kvm->slots_lock held, returns the number of - * processed pages. - */ -int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring); - -/* - * returns =0: successfully pushed - * <0: unable to push, need to wait - */ +int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring, + int *nr_entries_reset); void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, u32 slot, u64 offset); bool kvm_dirty_ring_check_request(struct kvm_vcpu *vcpu); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3bde4fb5c6aa..15656b7fba6c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -190,6 +190,7 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 +#define KVM_PIT_IRQ_SOURCE_ID 2 extern struct mutex kvm_lock; extern struct list_head vm_list; @@ -1022,16 +1023,12 @@ void kvm_unlock_all_vcpus(struct kvm *kvm); void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); -#ifdef __KVM_HAVE_IOAPIC +#ifdef CONFIG_KVM_IOAPIC void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm); -void kvm_arch_post_irq_routing_update(struct kvm *kvm); #else static inline void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm) { } -static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm) -{ -} #endif #ifdef CONFIG_HAVE_KVM_IRQCHIP @@ -1693,24 +1690,6 @@ static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) return false; } #endif -#ifdef __KVM_HAVE_ARCH_ASSIGNED_DEVICE -void kvm_arch_start_assignment(struct kvm *kvm); -void kvm_arch_end_assignment(struct kvm *kvm); -bool kvm_arch_has_assigned_device(struct kvm *kvm); -#else -static inline void kvm_arch_start_assignment(struct kvm *kvm) -{ -} - -static inline void kvm_arch_end_assignment(struct kvm *kvm) -{ -} - -static __always_inline bool kvm_arch_has_assigned_device(struct kvm *kvm) -{ - return false; -} -#endif static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) { @@ -1788,8 +1767,6 @@ void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); void kvm_unregister_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); -int kvm_request_irq_source_id(struct kvm *kvm); -void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args); /* @@ -2406,6 +2383,8 @@ struct kvm_vcpu *kvm_get_running_vcpu(void); struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); #if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS) +struct kvm_kernel_irqfd; + bool kvm_arch_has_irq_bypass(void); int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *, struct irq_bypass_producer *); @@ -2413,10 +2392,9 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *, struct irq_bypass_producer *); void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *); void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *); -int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set); -bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *, - struct kvm_kernel_irq_routing_entry *); +void kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd, + struct kvm_kernel_irq_routing_entry *old, + struct kvm_kernel_irq_routing_entry *new); #endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */ #ifdef CONFIG_HAVE_KVM_INVALID_WAKEUPS diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h index 8ad43692e3bb..ef8c134ded8a 100644 --- a/include/linux/kvm_irqfd.h +++ b/include/linux/kvm_irqfd.h @@ -55,10 +55,13 @@ struct kvm_kernel_irqfd { /* Used for setup/shutdown */ struct eventfd_ctx *eventfd; struct list_head list; - poll_table pt; struct work_struct shutdown; struct irq_bypass_consumer consumer; struct irq_bypass_producer *producer; + + struct kvm_vcpu *irq_bypass_vcpu; + struct list_head vcpu_list; + void *irq_bypass_data; }; #endif /* __LINUX_KVM_IRQFD_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 0ef2ba0c667a..fa538feaa8d9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2568,6 +2568,11 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) return percpu_counter_read_positive(&mm->rss_stat[member]); } +static inline unsigned long get_mm_counter_sum(struct mm_struct *mm, int member) +{ + return percpu_counter_sum_positive(&mm->rss_stat[member]); +} + void mm_trace_rss_stat(struct mm_struct *mm, int member); static inline void add_mm_counter(struct mm_struct *mm, int member, long value) diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 437769e061b7..13add0c2c407 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -154,6 +154,7 @@ struct phy_attrs { * @id: id of the phy device * @ops: function pointers for performing phy operations * @mutex: mutex to protect phy_ops + * @lockdep_key: lockdep information for this mutex * @init_count: used to protect when the PHY is used by multiple consumers * @power_count: used to protect when the PHY is used by multiple consumers * @attrs: used to specify PHY specific attributes @@ -165,6 +166,7 @@ struct phy { int id; const struct phy_ops *ops; struct mutex mutex; + struct lock_class_key lockdep_key; int init_count; int power_count; struct phy_attrs attrs; diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 7803edaa8ff8..0cca01b5607b 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -888,15 +888,23 @@ static inline int power_supply_is_system_supplied(void) { return -ENOSYS; } extern int power_supply_get_property(struct power_supply *psy, enum power_supply_property psp, union power_supply_propval *val); +int power_supply_get_property_direct(struct power_supply *psy, enum power_supply_property psp, + union power_supply_propval *val); #if IS_ENABLED(CONFIG_POWER_SUPPLY) extern int power_supply_set_property(struct power_supply *psy, enum power_supply_property psp, const union power_supply_propval *val); +int power_supply_set_property_direct(struct power_supply *psy, enum power_supply_property psp, + const union power_supply_propval *val); #else static inline int power_supply_set_property(struct power_supply *psy, enum power_supply_property psp, const union power_supply_propval *val) { return 0; } +static inline int power_supply_set_property_direct(struct power_supply *psy, + enum power_supply_property psp, + const union power_supply_propval *val) +{ return 0; } #endif extern void power_supply_external_power_changed(struct power_supply *psy); diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 0b3a36bdaa90..0f5f94137f6d 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -594,6 +594,7 @@ struct sev_data_snp_addr { * @imi_en: launch flow is launching an IMI (Incoming Migration Image) for the * purpose of guest-assisted migration. * @rsvd: reserved + * @desired_tsc_khz: hypervisor desired mean TSC freq in kHz of the guest * @gosvw: guest OS-visible workarounds, as defined by hypervisor */ struct sev_data_snp_launch_start { @@ -603,6 +604,7 @@ struct sev_data_snp_launch_start { u32 ma_en:1; /* In */ u32 imi_en:1; /* In */ u32 rsvd:30; + u32 desired_tsc_khz; /* In */ u8 gosvw[16]; /* In */ } __packed; diff --git a/include/linux/sched.h b/include/linux/sched.h index 4f78a64beb52..aa9c5be7a632 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -548,10 +548,6 @@ struct sched_statistics { u64 nr_failed_migrations_running; u64 nr_failed_migrations_hot; u64 nr_forced_migrations; -#ifdef CONFIG_NUMA_BALANCING - u64 numa_task_migrated; - u64 numa_task_swapped; -#endif u64 nr_wakeups; u64 nr_wakeups_sync; diff --git a/include/linux/sprintf.h b/include/linux/sprintf.h index 51cab2def9ec..876130091384 100644 --- a/include/linux/sprintf.h +++ b/include/linux/sprintf.h @@ -4,6 +4,7 @@ #include <linux/compiler_attributes.h> #include <linux/types.h> +#include <linux/stdarg.h> int num_to_str(char *buf, int size, unsigned long long num, unsigned int width); diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 91a3ce9a2687..9e15a088ba38 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -66,8 +66,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, NUMA_HINT_FAULTS, NUMA_HINT_FAULTS_LOCAL, NUMA_PAGE_MIGRATE, - NUMA_TASK_MIGRATE, - NUMA_TASK_SWAP, #endif #ifdef CONFIG_MIGRATION PGMIGRATE_SUCCESS, PGMIGRATE_FAIL, diff --git a/include/linux/wait.h b/include/linux/wait.h index 965a19809c7e..09855d819418 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -164,6 +164,8 @@ static inline bool wq_has_sleeper(struct wait_queue_head *wq_head) extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); +extern int add_wait_queue_priority_exclusive(struct wait_queue_head *wq_head, + struct wait_queue_entry *wq_entry); extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index d56e6e135158..d40e978126e3 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -243,8 +243,8 @@ int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); -#ifdef CONFIG_BPF_SYSCALL extern struct proto vsock_proto; +#ifdef CONFIG_BPF_SYSCALL int vsock_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void __init vsock_bpf_build_proto(void); #else diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 82cbd54443ac..c79901f2dc2a 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -377,6 +377,8 @@ enum { * This quirk must be set before hci_register_dev is called. */ HCI_QUIRK_BROKEN_READ_PAGE_SCAN_TYPE, + + __HCI_NUM_QUIRKS, }; /* HCI device flags */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 9fc8f544e20e..f79f59e67114 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -464,7 +464,7 @@ struct hci_dev { unsigned int auto_accept_delay; - unsigned long quirks; + DECLARE_BITMAP(quirk_flags, __HCI_NUM_QUIRKS); atomic_t cmd_cnt; unsigned int acl_cnt; @@ -656,6 +656,10 @@ struct hci_dev { u8 (*classify_pkt_type)(struct hci_dev *hdev, struct sk_buff *skb); }; +#define hci_set_quirk(hdev, nr) set_bit((nr), (hdev)->quirk_flags) +#define hci_clear_quirk(hdev, nr) clear_bit((nr), (hdev)->quirk_flags) +#define hci_test_quirk(hdev, nr) test_bit((nr), (hdev)->quirk_flags) + #define HCI_PHY_HANDLE(handle) (handle & 0xff) enum conn_reasons { @@ -829,20 +833,20 @@ extern struct mutex hci_cb_list_lock; #define hci_dev_test_and_clear_flag(hdev, nr) test_and_clear_bit((nr), (hdev)->dev_flags) #define hci_dev_test_and_change_flag(hdev, nr) test_and_change_bit((nr), (hdev)->dev_flags) -#define hci_dev_clear_volatile_flags(hdev) \ - do { \ - hci_dev_clear_flag(hdev, HCI_LE_SCAN); \ - hci_dev_clear_flag(hdev, HCI_LE_ADV); \ - hci_dev_clear_flag(hdev, HCI_LL_RPA_RESOLUTION);\ - hci_dev_clear_flag(hdev, HCI_PERIODIC_INQ); \ - hci_dev_clear_flag(hdev, HCI_QUALITY_REPORT); \ +#define hci_dev_clear_volatile_flags(hdev) \ + do { \ + hci_dev_clear_flag((hdev), HCI_LE_SCAN); \ + hci_dev_clear_flag((hdev), HCI_LE_ADV); \ + hci_dev_clear_flag((hdev), HCI_LL_RPA_RESOLUTION); \ + hci_dev_clear_flag((hdev), HCI_PERIODIC_INQ); \ + hci_dev_clear_flag((hdev), HCI_QUALITY_REPORT); \ } while (0) #define hci_dev_le_state_simultaneous(hdev) \ - (!test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) && \ - (hdev->le_states[4] & 0x08) && /* Central */ \ - (hdev->le_states[4] & 0x40) && /* Peripheral */ \ - (hdev->le_states[3] & 0x10)) /* Simultaneous */ + (!hci_test_quirk((hdev), HCI_QUIRK_BROKEN_LE_STATES) && \ + ((hdev)->le_states[4] & 0x08) && /* Central */ \ + ((hdev)->le_states[4] & 0x40) && /* Peripheral */ \ + ((hdev)->le_states[3] & 0x10)) /* Simultaneous */ /* ----- HCI interface to upper protocols ----- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); @@ -1350,8 +1354,7 @@ hci_conn_hash_lookup_big_state(struct hci_dev *hdev, __u8 handle, __u16 state) rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (c->type != BIS_LINK || bacmp(&c->dst, BDADDR_ANY) || - c->state != state) + if (c->type != BIS_LINK || c->state != state) continue; if (handle == c->iso_qos.bcast.big) { @@ -1932,8 +1935,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn); ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_2M)) #define le_coded_capable(dev) (((dev)->le_features[1] & HCI_LE_PHY_CODED) && \ - !test_bit(HCI_QUIRK_BROKEN_LE_CODED, \ - &(dev)->quirks)) + !hci_test_quirk((dev), \ + HCI_QUIRK_BROKEN_LE_CODED)) #define scan_coded(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_CODED) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED)) @@ -1941,31 +1944,31 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define ll_privacy_capable(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY) #define privacy_mode_capable(dev) (ll_privacy_capable(dev) && \ - (hdev->commands[39] & 0x04)) + ((dev)->commands[39] & 0x04)) #define read_key_size_capable(dev) \ ((dev)->commands[20] & 0x10 && \ - !test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks)) + !hci_test_quirk((dev), HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE)) #define read_voice_setting_capable(dev) \ ((dev)->commands[9] & 0x04 && \ - !test_bit(HCI_QUIRK_BROKEN_READ_VOICE_SETTING, &(dev)->quirks)) + !hci_test_quirk((dev), HCI_QUIRK_BROKEN_READ_VOICE_SETTING)) /* Use enhanced synchronous connection if command is supported and its quirk * has not been set. */ #define enhanced_sync_conn_capable(dev) \ (((dev)->commands[29] & 0x08) && \ - !test_bit(HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, &(dev)->quirks)) + !hci_test_quirk((dev), HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN)) /* Use ext scanning if set ext scan param and ext scan enable is supported */ #define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \ ((dev)->commands[37] & 0x40) && \ - !test_bit(HCI_QUIRK_BROKEN_EXT_SCAN, &(dev)->quirks)) + !hci_test_quirk((dev), HCI_QUIRK_BROKEN_EXT_SCAN)) /* Use ext create connection if command is supported */ #define use_ext_conn(dev) (((dev)->commands[37] & 0x80) && \ - !test_bit(HCI_QUIRK_BROKEN_EXT_CREATE_CONN, &(dev)->quirks)) + !hci_test_quirk((dev), HCI_QUIRK_BROKEN_EXT_CREATE_CONN)) /* Extended advertising support */ #define ext_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_EXT_ADV)) @@ -1980,8 +1983,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn); */ #define use_enhanced_conn_complete(dev) ((ll_privacy_capable(dev) || \ ext_adv_capable(dev)) && \ - !test_bit(HCI_QUIRK_BROKEN_EXT_CREATE_CONN, \ - &(dev)->quirks)) + !hci_test_quirk((dev), \ + HCI_QUIRK_BROKEN_EXT_CREATE_CONN)) /* Periodic advertising support */ #define per_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_PERIODIC_ADV)) @@ -1998,7 +2001,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define sync_recv_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER) #define mws_transport_config_capable(dev) (((dev)->commands[30] & 0x08) && \ - (!test_bit(HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG, &(dev)->quirks))) + (!hci_test_quirk((dev), HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG))) /* ----- HCI protocols ----- */ #define HCI_PROTO_DEFER 0x01 diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index d1848dc8ec99..10248d527616 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2690,7 +2690,7 @@ struct cfg80211_scan_request { s8 tsf_report_link_id; /* keep last */ - struct ieee80211_channel *channels[] __counted_by(n_channels); + struct ieee80211_channel *channels[]; }; static inline void get_random_mask_addr(u8 *buf, const u8 *addr, const u8 *mask) diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 3f02a45773e8..ca26274196b9 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -306,8 +306,19 @@ static inline bool nf_ct_is_expired(const struct nf_conn *ct) /* use after obtaining a reference count */ static inline bool nf_ct_should_gc(const struct nf_conn *ct) { - return nf_ct_is_expired(ct) && nf_ct_is_confirmed(ct) && - !nf_ct_is_dying(ct); + if (!nf_ct_is_confirmed(ct)) + return false; + + /* load ct->timeout after is_confirmed() test. + * Pairs with __nf_conntrack_confirm() which: + * 1. Increases ct->timeout value + * 2. Inserts ct into rcu hlist + * 3. Sets the confirmed bit + * 4. Unlocks the hlist lock + */ + smp_acquire__after_ctrl_dep(); + + return nf_ct_is_expired(ct) && !nf_ct_is_dying(ct); } #define NF_CT_DAY (86400 * HZ) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index d711642e78b5..c003cd194fa2 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -370,7 +370,7 @@ static inline __be16 __nf_flow_pppoe_proto(const struct sk_buff *skb) static inline bool nf_flow_pppoe_proto(struct sk_buff *skb, __be16 *inner_proto) { - if (!pskb_may_pull(skb, PPPOE_SES_HLEN)) + if (!pskb_may_pull(skb, ETH_HLEN + PPPOE_SES_HLEN)) return false; *inner_proto = __nf_flow_pppoe_proto(skb); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index e4d8e451e935..5e49619ae49c 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1142,11 +1142,6 @@ int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set); int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); -struct nft_hook; -void nf_tables_chain_device_notify(const struct nft_chain *chain, - const struct nft_hook *hook, - const struct net_device *dev, int event); - enum nft_chain_types { NFT_CHAIN_T_DEFAULT = 0, NFT_CHAIN_T_ROUTE, diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index d7b7b6cd4aa1..8a75c73fc555 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -114,7 +114,6 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct netlink_ext_ack *extack); void qdisc_put_rtab(struct qdisc_rate_table *tab); void qdisc_put_stab(struct qdisc_size_table *tab); -void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc); bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq, spinlock_t *root_lock, bool validate); @@ -290,4 +289,28 @@ static inline bool tc_qdisc_stats_dump(struct Qdisc *sch, return true; } +static inline void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc) +{ + if (!(qdisc->flags & TCQ_F_WARN_NONWC)) { + pr_warn("%s: %s qdisc %X: is non-work-conserving?\n", + txt, qdisc->ops->id, qdisc->handle >> 16); + qdisc->flags |= TCQ_F_WARN_NONWC; + } +} + +static inline unsigned int qdisc_peek_len(struct Qdisc *sch) +{ + struct sk_buff *skb; + unsigned int len; + + skb = sch->ops->peek(sch); + if (unlikely(skb == NULL)) { + qdisc_warn_nonwc("qdisc_peek_len", sch); + return 0; + } + len = qdisc_pkt_len(skb); + + return len; +} + #endif diff --git a/include/net/xfrm.h b/include/net/xfrm.h index a21e276dbe44..f3014e4f54fc 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -441,7 +441,6 @@ int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo); int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo); void xfrm_flush_gc(void); -void xfrm_state_delete_tunnel(struct xfrm_state *x); struct xfrm_type { struct module *owner; @@ -474,7 +473,7 @@ struct xfrm_type_offload { int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family); void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family); -void xfrm_set_type_offload(struct xfrm_state *x); +void xfrm_set_type_offload(struct xfrm_state *x, bool try_load); static inline void xfrm_unset_type_offload(struct xfrm_state *x) { if (!x->type_offload) @@ -916,7 +915,7 @@ static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) xfrm_pol_put(pols[i]); } -void __xfrm_state_destroy(struct xfrm_state *, bool); +void __xfrm_state_destroy(struct xfrm_state *); static inline void __xfrm_state_put(struct xfrm_state *x) { @@ -926,13 +925,7 @@ static inline void __xfrm_state_put(struct xfrm_state *x) static inline void xfrm_state_put(struct xfrm_state *x) { if (refcount_dec_and_test(&x->refcnt)) - __xfrm_state_destroy(x, false); -} - -static inline void xfrm_state_put_sync(struct xfrm_state *x) -{ - if (refcount_dec_and_test(&x->refcnt)) - __xfrm_state_destroy(x, true); + __xfrm_state_destroy(x); } static inline void xfrm_state_hold(struct xfrm_state *x) @@ -1770,7 +1763,7 @@ struct xfrmk_spdinfo { struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num); int xfrm_state_delete(struct xfrm_state *x); -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync); +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); int xfrm_dev_policy_flush(struct net *net, struct net_device *dev, bool task_valid); diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index fc7d0f8ff078..8b7252b8d751 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -82,95 +82,15 @@ TRACE_EVENT(kvm_set_irq, TP_printk("gsi %u level %d source %d", __entry->gsi, __entry->level, __entry->irq_source_id) ); -#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */ - -#if defined(__KVM_HAVE_IOAPIC) -#define kvm_deliver_mode \ - {0x0, "Fixed"}, \ - {0x1, "LowPrio"}, \ - {0x2, "SMI"}, \ - {0x3, "Res3"}, \ - {0x4, "NMI"}, \ - {0x5, "INIT"}, \ - {0x6, "SIPI"}, \ - {0x7, "ExtINT"} - -TRACE_EVENT(kvm_ioapic_set_irq, - TP_PROTO(__u64 e, int pin, bool coalesced), - TP_ARGS(e, pin, coalesced), - - TP_STRUCT__entry( - __field( __u64, e ) - __field( int, pin ) - __field( bool, coalesced ) - ), - - TP_fast_assign( - __entry->e = e; - __entry->pin = pin; - __entry->coalesced = coalesced; - ), - - TP_printk("pin %u dst %x vec %u (%s|%s|%s%s)%s", - __entry->pin, (u8)(__entry->e >> 56), (u8)__entry->e, - __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode), - (__entry->e & (1<<11)) ? "logical" : "physical", - (__entry->e & (1<<15)) ? "level" : "edge", - (__entry->e & (1<<16)) ? "|masked" : "", - __entry->coalesced ? " (coalesced)" : "") -); -TRACE_EVENT(kvm_ioapic_delayed_eoi_inj, - TP_PROTO(__u64 e), - TP_ARGS(e), - - TP_STRUCT__entry( - __field( __u64, e ) - ), - - TP_fast_assign( - __entry->e = e; - ), - - TP_printk("dst %x vec %u (%s|%s|%s%s)", - (u8)(__entry->e >> 56), (u8)__entry->e, - __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode), - (__entry->e & (1<<11)) ? "logical" : "physical", - (__entry->e & (1<<15)) ? "level" : "edge", - (__entry->e & (1<<16)) ? "|masked" : "") -); - -TRACE_EVENT(kvm_msi_set_irq, - TP_PROTO(__u64 address, __u64 data), - TP_ARGS(address, data), - - TP_STRUCT__entry( - __field( __u64, address ) - __field( __u64, data ) - ), - - TP_fast_assign( - __entry->address = address; - __entry->data = data; - ), - - TP_printk("dst %llx vec %u (%s|%s|%s%s)", - (u8)(__entry->address >> 12) | ((__entry->address >> 32) & 0xffffff00), - (u8)__entry->data, - __print_symbolic((__entry->data >> 8 & 0x7), kvm_deliver_mode), - (__entry->address & (1<<2)) ? "logical" : "physical", - (__entry->data & (1<<15)) ? "level" : "edge", - (__entry->address & (1<<3)) ? "|rh" : "") -); +#ifdef CONFIG_KVM_IOAPIC #define kvm_irqchips \ {KVM_IRQCHIP_PIC_MASTER, "PIC master"}, \ {KVM_IRQCHIP_PIC_SLAVE, "PIC slave"}, \ {KVM_IRQCHIP_IOAPIC, "IOAPIC"} -#endif /* defined(__KVM_HAVE_IOAPIC) */ - -#if defined(CONFIG_HAVE_KVM_IRQCHIP) +#endif /* CONFIG_KVM_IOAPIC */ #ifdef kvm_irqchips #define kvm_ack_irq_string "irqchip %s pin %u" @@ -473,6 +393,33 @@ TRACE_EVENT(kvm_dirty_ring_exit, TP_printk("vcpu %d", __entry->vcpu_id) ); +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +/* + * @start: Starting address of guest memory range + * @end: End address of guest memory range + * @attr: The value of the attribute being set. + */ +TRACE_EVENT(kvm_vm_set_mem_attributes, + TP_PROTO(gfn_t start, gfn_t end, unsigned long attr), + TP_ARGS(start, end, attr), + + TP_STRUCT__entry( + __field(gfn_t, start) + __field(gfn_t, end) + __field(unsigned long, attr) + ), + + TP_fast_assign( + __entry->start = start; + __entry->end = end; + __entry->attr = attr; + ), + + TP_printk("%#016llx -- %#016llx [0x%lx]", + __entry->start, __entry->end, __entry->attr) +); +#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ + TRACE_EVENT(kvm_unmap_hva_range, TP_PROTO(unsigned long start, unsigned long end), TP_ARGS(start, end), diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 73e96ccbe830..64a382fbc31a 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -55,6 +55,7 @@ EM(netfs_rreq_trace_copy, "COPY ") \ EM(netfs_rreq_trace_dirty, "DIRTY ") \ EM(netfs_rreq_trace_done, "DONE ") \ + EM(netfs_rreq_trace_end_copy_to_cache, "END-C2C") \ EM(netfs_rreq_trace_free, "FREE ") \ EM(netfs_rreq_trace_ki_complete, "KI-CMPL") \ EM(netfs_rreq_trace_recollect, "RECLLCT") \ @@ -559,6 +560,35 @@ TRACE_EVENT(netfs_write, __entry->start, __entry->start + __entry->len - 1) ); +TRACE_EVENT(netfs_copy2cache, + TP_PROTO(const struct netfs_io_request *rreq, + const struct netfs_io_request *creq), + + TP_ARGS(rreq, creq), + + TP_STRUCT__entry( + __field(unsigned int, rreq) + __field(unsigned int, creq) + __field(unsigned int, cookie) + __field(unsigned int, ino) + ), + + TP_fast_assign( + struct netfs_inode *__ctx = netfs_inode(rreq->inode); + struct fscache_cookie *__cookie = netfs_i_cookie(__ctx); + __entry->rreq = rreq->debug_id; + __entry->creq = creq->debug_id; + __entry->cookie = __cookie ? __cookie->debug_id : 0; + __entry->ino = rreq->inode->i_ino; + ), + + TP_printk("R=%08x CR=%08x c=%08x i=%x ", + __entry->rreq, + __entry->creq, + __entry->cookie, + __entry->ino) + ); + TRACE_EVENT(netfs_collect, TP_PROTO(const struct netfs_io_request *wreq), diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 378d2dfc7392..de6f6d25767c 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -322,20 +322,24 @@ EM(rxrpc_call_put_kernel, "PUT kernel ") \ EM(rxrpc_call_put_poke, "PUT poke ") \ EM(rxrpc_call_put_recvmsg, "PUT recvmsg ") \ + EM(rxrpc_call_put_release_recvmsg_q, "PUT rls-rcmq") \ EM(rxrpc_call_put_release_sock, "PUT rls-sock") \ EM(rxrpc_call_put_release_sock_tba, "PUT rls-sk-a") \ EM(rxrpc_call_put_sendmsg, "PUT sendmsg ") \ - EM(rxrpc_call_put_unnotify, "PUT unnotify") \ EM(rxrpc_call_put_userid_exists, "PUT u-exists") \ EM(rxrpc_call_put_userid, "PUT user-id ") \ EM(rxrpc_call_see_accept, "SEE accept ") \ EM(rxrpc_call_see_activate_client, "SEE act-clnt") \ + EM(rxrpc_call_see_already_released, "SEE alrdy-rl") \ EM(rxrpc_call_see_connect_failed, "SEE con-fail") \ EM(rxrpc_call_see_connected, "SEE connect ") \ EM(rxrpc_call_see_conn_abort, "SEE conn-abt") \ + EM(rxrpc_call_see_discard, "SEE discard ") \ EM(rxrpc_call_see_disconnected, "SEE disconn ") \ EM(rxrpc_call_see_distribute_error, "SEE dist-err") \ EM(rxrpc_call_see_input, "SEE input ") \ + EM(rxrpc_call_see_notify_released, "SEE nfy-rlsd") \ + EM(rxrpc_call_see_recvmsg, "SEE recvmsg ") \ EM(rxrpc_call_see_release, "SEE release ") \ EM(rxrpc_call_see_userid_exists, "SEE u-exists") \ EM(rxrpc_call_see_waiting_call, "SEE q-conn ") \ diff --git a/include/uapi/linux/bits.h b/include/uapi/linux/bits.h index 682b406e1067..a04afef9efca 100644 --- a/include/uapi/linux/bits.h +++ b/include/uapi/linux/bits.h @@ -4,9 +4,9 @@ #ifndef _UAPI_LINUX_BITS_H #define _UAPI_LINUX_BITS_H -#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (BITS_PER_LONG - 1 - (h)))) +#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (__BITS_PER_LONG - 1 - (h)))) -#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h)))) +#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) #define __GENMASK_U128(h, l) \ ((_BIT128((h)) << 1) - (_BIT128(l))) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 37891580d05d..aeb2ca10b190 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -467,6 +467,10 @@ struct kvm_run { __u64 leaf; __u64 r11, r12, r13, r14; } get_tdvmcall_info; + struct { + __u64 ret; + __u64 vector; + } setup_event_notify; }; } tdx; /* Fix the size of the union. */ @@ -640,6 +644,7 @@ struct kvm_ioeventfd { #define KVM_X86_DISABLE_EXITS_HLT (1 << 1) #define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) #define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3) +#define KVM_X86_DISABLE_EXITS_APERFMPERF (1 << 4) /* for KVM_ENABLE_CAP */ struct kvm_enable_cap { diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 518ba144544c..2beb30be2c5f 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -142,8 +142,6 @@ enum nf_tables_msg_types { NFT_MSG_DESTROYOBJ, NFT_MSG_DESTROYFLOWTABLE, NFT_MSG_GETSETELEM_RESET, - NFT_MSG_NEWDEV, - NFT_MSG_DELDEV, NFT_MSG_MAX, }; @@ -1786,18 +1784,10 @@ enum nft_synproxy_attributes { * enum nft_device_attributes - nf_tables device netlink attributes * * @NFTA_DEVICE_NAME: name of this device (NLA_STRING) - * @NFTA_DEVICE_TABLE: table containing the flowtable or chain hooking into the device (NLA_STRING) - * @NFTA_DEVICE_FLOWTABLE: flowtable hooking into the device (NLA_STRING) - * @NFTA_DEVICE_CHAIN: chain hooking into the device (NLA_STRING) - * @NFTA_DEVICE_SPEC: hook spec matching the device (NLA_STRING) */ enum nft_devices_attributes { NFTA_DEVICE_UNSPEC, NFTA_DEVICE_NAME, - NFTA_DEVICE_TABLE, - NFTA_DEVICE_FLOWTABLE, - NFTA_DEVICE_CHAIN, - NFTA_DEVICE_SPEC, __NFTA_DEVICE_MAX }; #define NFTA_DEVICE_MAX (__NFTA_DEVICE_MAX - 1) diff --git a/include/uapi/linux/netfilter/nfnetlink.h b/include/uapi/linux/netfilter/nfnetlink.h index 50d807af2649..6cd58cd2a6f0 100644 --- a/include/uapi/linux/netfilter/nfnetlink.h +++ b/include/uapi/linux/netfilter/nfnetlink.h @@ -25,8 +25,6 @@ enum nfnetlink_groups { #define NFNLGRP_ACCT_QUOTA NFNLGRP_ACCT_QUOTA NFNLGRP_NFTRACE, #define NFNLGRP_NFTRACE NFNLGRP_NFTRACE - NFNLGRP_NFT_DEV, -#define NFNLGRP_NFT_DEV NFNLGRP_NFT_DEV __NFNLGRP_MAX, }; #define NFNLGRP_MAX (__NFNLGRP_MAX - 1) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 73648d26a622..5111ec040c53 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1666,12 +1666,11 @@ static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags) io_req_flags_t io_file_get_flags(struct file *file) { - struct inode *inode = file_inode(file); io_req_flags_t res = 0; BUILD_BUG_ON(REQ_F_ISREG_BIT != REQ_F_SUPPORT_NOWAIT_BIT + 1); - if (S_ISREG(inode->i_mode) && !(inode->i_flags & S_ANON_INODE)) + if (S_ISREG(file_inode(file)->i_mode)) res |= REQ_F_ISREG; if ((file->f_flags & O_NONBLOCK) || (file->f_mode & FMODE_NOWAIT)) res |= REQ_F_SUPPORT_NOWAIT; diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index 71400d6cefc8..4c2578f2efcb 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -82,7 +82,7 @@ static void io_msg_tw_complete(struct io_kiocb *req, io_tw_token_t tw) spin_unlock(&ctx->msg_lock); } if (req) - kmem_cache_free(req_cachep, req); + kfree_rcu(req, rcu_head); percpu_ref_put(&ctx->refs); } @@ -90,7 +90,7 @@ static int io_msg_remote_post(struct io_ring_ctx *ctx, struct io_kiocb *req, int res, u32 cflags, u64 user_data) { if (!READ_ONCE(ctx->submitter_task)) { - kmem_cache_free(req_cachep, req); + kfree_rcu(req, rcu_head); return -EOWNERDEAD; } req->opcode = IORING_OP_NOP; diff --git a/io_uring/net.c b/io_uring/net.c index 43a43522f406..bec8c6ed0a93 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -1738,9 +1738,11 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags) int ret; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; - if (unlikely(req->flags & REQ_F_FAIL)) { - ret = -ECONNRESET; - goto out; + if (connect->in_progress) { + struct poll_table_struct pt = { ._key = EPOLLERR }; + + if (vfs_poll(req->file, &pt) & EPOLLERR) + goto get_sock_err; } file_flags = force_nonblock ? O_NONBLOCK : 0; @@ -1765,8 +1767,10 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags) * which means the previous result is good. For both of these, * grab the sock_error() and use that for the completion. */ - if (ret == -EBADFD || ret == -EISCONN) + if (ret == -EBADFD || ret == -EISCONN) { +get_sock_err: ret = sock_error(sock_from_file(req->file)->sk); + } } if (ret == -ERESTARTSYS) ret = -EINTR; diff --git a/io_uring/poll.c b/io_uring/poll.c index 0526062e2f81..20e9b46a4adf 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -273,8 +273,6 @@ static int io_poll_check_events(struct io_kiocb *req, io_tw_token_t tw) return IOU_POLL_REISSUE; } } - if (unlikely(req->cqe.res & EPOLLERR)) - req_set_fail(req); if (req->apoll_events & EPOLLONESHOT) return IOU_POLL_DONE; diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 085eeed8cd50..4a7011c799f0 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -76,6 +76,8 @@ static int io_import_dmabuf(struct io_zcrx_ifq *ifq, int dmabuf_fd = area_reg->dmabuf_fd; int i, ret; + if (off) + return -EINVAL; if (WARN_ON_ONCE(!ifq->dev)) return -EFAULT; if (!IS_ENABLED(CONFIG_DMA_SHARED_BUFFER)) @@ -106,7 +108,7 @@ static int io_import_dmabuf(struct io_zcrx_ifq *ifq, for_each_sgtable_dma_sg(mem->sgt, sg, i) total_size += sg_dma_len(sg); - if (total_size < off + len) { + if (total_size != len) { ret = -EINVAL; goto err; } @@ -863,10 +865,7 @@ static int io_pp_zc_init(struct page_pool *pp) static void io_pp_zc_destroy(struct page_pool *pp) { struct io_zcrx_ifq *ifq = io_pp_to_ifq(pp); - struct io_zcrx_area *area = ifq->area; - if (WARN_ON_ONCE(area->free_count != area->nia.num_niovs)) - return; percpu_ref_put(&ifq->ctx->refs); } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index b71e428ad936..ad6df48b540c 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -884,6 +884,13 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, if (fmt[i] == 'p') { sizeof_cur_arg = sizeof(long); + if (fmt[i + 1] == 0 || isspace(fmt[i + 1]) || + ispunct(fmt[i + 1])) { + if (tmp_buf) + cur_arg = raw_args[num_spec]; + goto nocopy_fmt; + } + if ((fmt[i + 1] == 'k' || fmt[i + 1] == 'u') && fmt[i + 2] == 's') { fmt_ptype = fmt[i + 1]; @@ -891,11 +898,9 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, goto fmt_str; } - if (fmt[i + 1] == 0 || isspace(fmt[i + 1]) || - ispunct(fmt[i + 1]) || fmt[i + 1] == 'K' || + if (fmt[i + 1] == 'K' || fmt[i + 1] == 'x' || fmt[i + 1] == 's' || fmt[i + 1] == 'S') { - /* just kernel pointers */ if (tmp_buf) cur_arg = raw_args[num_spec]; i++; diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c index 941d0d2427e3..8e61dc555415 100644 --- a/kernel/bpf/sysfs_btf.c +++ b/kernel/bpf/sysfs_btf.c @@ -21,7 +21,7 @@ static int btf_sysfs_vmlinux_mmap(struct file *filp, struct kobject *kobj, { unsigned long pages = PAGE_ALIGN(attr->size) >> PAGE_SHIFT; size_t vm_size = vma->vm_end - vma->vm_start; - phys_addr_t addr = virt_to_phys(__start_BTF); + phys_addr_t addr = __pa_symbol(__start_BTF); unsigned long pfn = addr >> PAGE_SHIFT; if (attr->private != __start_BTF || !PAGE_ALIGNED(addr)) diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c index 507b8f19a262..dd9417425d92 100644 --- a/kernel/cgroup/legacy_freezer.c +++ b/kernel/cgroup/legacy_freezer.c @@ -66,15 +66,9 @@ static struct freezer *parent_freezer(struct freezer *freezer) bool cgroup_freezing(struct task_struct *task) { bool ret; - unsigned int state; rcu_read_lock(); - /* Check if the cgroup is still FREEZING, but not FROZEN. The extra - * !FROZEN check is required, because the FREEZING bit is not cleared - * when the state FROZEN is reached. - */ - state = task_freezer(task)->state; - ret = (state & CGROUP_FREEZING) && !(state & CGROUP_FROZEN); + ret = task_freezer(task)->state & CGROUP_FREEZING; rcu_read_unlock(); return ret; diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index 8df0dfaaca18..67af8a55185d 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -222,7 +222,10 @@ void __init dma_contiguous_reserve(phys_addr_t limit) if (size_cmdline != -1) { selected_size = size_cmdline; selected_base = base_cmdline; - selected_limit = min_not_zero(limit_cmdline, limit); + + /* Hornor the user setup dma address limit */ + selected_limit = limit_cmdline ?: limit; + if (base_cmdline + size_cmdline == limit_cmdline) fixed = true; } else { diff --git a/kernel/events/core.c b/kernel/events/core.c index 0db36b2b2448..22fdf0c187cd 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7204,18 +7204,18 @@ void perf_event_wakeup(struct perf_event *event) static void perf_sigtrap(struct perf_event *event) { /* - * We'd expect this to only occur if the irq_work is delayed and either - * ctx->task or current has changed in the meantime. This can be the - * case on architectures that do not implement arch_irq_work_raise(). + * Both perf_pending_task() and perf_pending_irq() can race with the + * task exiting. */ - if (WARN_ON_ONCE(event->ctx->task != current)) + if (current->flags & PF_EXITING) return; /* - * Both perf_pending_task() and perf_pending_irq() can race with the - * task exiting. + * We'd expect this to only occur if the irq_work is delayed and either + * ctx->task or current has changed in the meantime. This can be the + * case on architectures that do not implement arch_irq_work_raise(). */ - if (current->flags & PF_EXITING) + if (WARN_ON_ONCE(event->ctx->task != current)) return; send_sig_perf((void __user *)event->pending_addr, diff --git a/kernel/freezer.c b/kernel/freezer.c index 8d530d0949ff..6a96149aede9 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -201,18 +201,9 @@ static int __restore_freezer_state(struct task_struct *p, void *arg) void __thaw_task(struct task_struct *p) { - unsigned long flags; - - spin_lock_irqsave(&freezer_lock, flags); - if (WARN_ON_ONCE(freezing(p))) - goto unlock; - - if (!frozen(p) || task_call_func(p, __restore_freezer_state, NULL)) - goto unlock; - - wake_up_state(p, TASK_FROZEN); -unlock: - spin_unlock_irqrestore(&freezer_lock, flags); + guard(spinlock_irqsave)(&freezer_lock); + if (frozen(p) && !task_call_func(p, __restore_freezer_state, NULL)) + wake_up_state(p, TASK_FROZEN); } /** diff --git a/kernel/module/main.c b/kernel/module/main.c index 413ac6ea3702..c2c08007029d 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1573,8 +1573,14 @@ static int apply_relocations(struct module *mod, const struct load_info *info) if (infosec >= info->hdr->e_shnum) continue; - /* Don't bother with non-allocated sections */ - if (!(info->sechdrs[infosec].sh_flags & SHF_ALLOC)) + /* + * Don't bother with non-allocated sections. + * An exception is the percpu section, which has separate allocations + * for individual CPUs. We relocate the percpu section in the initial + * ELF template and subsequently copy it to the per-CPU destinations. + */ + if (!(info->sechdrs[infosec].sh_flags & SHF_ALLOC) && + (!infosec || infosec != info->index.pcpu)) continue; if (info->sechdrs[i].sh_flags & SHF_RELA_LIVEPATCH) @@ -2696,9 +2702,8 @@ static int find_module_sections(struct module *mod, struct load_info *info) static int move_module(struct module *mod, struct load_info *info) { - int i; - enum mod_mem_type t = 0; - int ret = -ENOMEM; + int i, ret; + enum mod_mem_type t = MOD_MEM_NUM_TYPES; bool codetag_section_found = false; for_each_mod_mem_type(type) { @@ -2776,7 +2781,7 @@ static int move_module(struct module *mod, struct load_info *info) return 0; out_err: module_memory_restore_rox(mod); - for (t--; t >= 0; t--) + while (t--) module_memory_free(mod, t); if (codetag_section_found) codetag_free_module_sections(mod); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index bb608b68fb30..b4ca17c2fecf 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -384,6 +384,7 @@ static int suspend_prepare(suspend_state_t state) return 0; dpm_save_failed_step(SUSPEND_FREEZE); + filesystems_thaw(); pm_notifier_call_chain(PM_POST_SUSPEND); Restore: pm_restore_console(); @@ -540,7 +541,6 @@ int suspend_devices_and_enter(suspend_state_t state) return error; Recover_platform: - pm_restore_gfp_mask(); platform_recover(state); goto Resume_devices; } @@ -593,8 +593,6 @@ static int enter_state(suspend_state_t state) ksys_sync_helper(); trace_suspend_resume(TPS("sync_filesystems"), 0, false); } - if (filesystem_freeze_enabled) - filesystems_freeze(); pm_pr_dbg("Preparing system for sleep (%s)\n", mem_sleep_labels[state]); pm_suspend_clear_flags(); @@ -614,7 +612,6 @@ static int enter_state(suspend_state_t state) pm_pr_dbg("Finishing wakeup.\n"); suspend_finish(); Unlock: - filesystems_thaw(); mutex_unlock(&system_transition_mutex); return error; } diff --git a/kernel/resource.c b/kernel/resource.c index 8d3e6ed0bdc1..f9bb5481501a 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1279,8 +1279,9 @@ static int __request_region_locked(struct resource *res, struct resource *parent * become unavailable to other users. Conflicts are * not expected. Warn to aid debugging if encountered. */ - if (conflict->desc == IORES_DESC_DEVICE_PRIVATE_MEMORY) { - pr_warn("Unaddressable device %s %pR conflicts with %pR", + if (parent == &iomem_resource && + conflict->desc == IORES_DESC_DEVICE_PRIVATE_MEMORY) { + pr_warn("Unaddressable device %s %pR conflicts with %pR\n", conflict->name, conflict, res); } if (conflict != parent) { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ec68fc686bd7..81c6df746df1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3362,10 +3362,6 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) #ifdef CONFIG_NUMA_BALANCING static void __migrate_swap_task(struct task_struct *p, int cpu) { - __schedstat_inc(p->stats.numa_task_swapped); - count_vm_numa_event(NUMA_TASK_SWAP); - count_memcg_event_mm(p->mm, NUMA_TASK_SWAP); - if (task_on_rq_queued(p)) { struct rq *src_rq, *dst_rq; struct rq_flags srf, drf; @@ -7939,9 +7935,8 @@ int migrate_task_to(struct task_struct *p, int target_cpu) if (!cpumask_test_cpu(target_cpu, p->cpus_ptr)) return -EINVAL; - __schedstat_inc(p->stats.numa_task_migrated); - count_vm_numa_event(NUMA_TASK_MIGRATE); - count_memcg_event_mm(p->mm, NUMA_TASK_MIGRATE); + /* TODO: This is not properly updating schedstats */ + trace_sched_move_numa(p, curr_cpu, target_cpu); return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg); } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 9d71baf08075..557246880a7e 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -1210,10 +1210,6 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, P_SCHEDSTAT(nr_failed_migrations_running); P_SCHEDSTAT(nr_failed_migrations_hot); P_SCHEDSTAT(nr_forced_migrations); -#ifdef CONFIG_NUMA_BALANCING - P_SCHEDSTAT(numa_task_migrated); - P_SCHEDSTAT(numa_task_swapped); -#endif P_SCHEDSTAT(nr_wakeups); P_SCHEDSTAT(nr_wakeups_sync); P_SCHEDSTAT(nr_wakeups_migrate); diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index b498d867ba21..7dd5cbcb7a06 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1272,7 +1272,8 @@ static inline struct rq *scx_locked_rq(void) #define SCX_CALL_OP(sch, mask, op, rq, args...) \ do { \ - update_locked_rq(rq); \ + if (rq) \ + update_locked_rq(rq); \ if (mask) { \ scx_kf_allow(mask); \ (sch)->ops.op(args); \ @@ -1280,14 +1281,16 @@ do { \ } else { \ (sch)->ops.op(args); \ } \ - update_locked_rq(NULL); \ + if (rq) \ + update_locked_rq(NULL); \ } while (0) #define SCX_CALL_OP_RET(sch, mask, op, rq, args...) \ ({ \ __typeof__((sch)->ops.op(args)) __ret; \ \ - update_locked_rq(rq); \ + if (rq) \ + update_locked_rq(rq); \ if (mask) { \ scx_kf_allow(mask); \ __ret = (sch)->ops.op(args); \ @@ -1295,7 +1298,8 @@ do { \ } else { \ __ret = (sch)->ops.op(args); \ } \ - update_locked_rq(NULL); \ + if (rq) \ + update_locked_rq(NULL); \ __ret; \ }) diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c index 6d29d3cbc670..001fb88a8481 100644 --- a/kernel/sched/ext_idle.c +++ b/kernel/sched/ext_idle.c @@ -903,7 +903,7 @@ s32 select_cpu_from_kfunc(struct task_struct *p, s32 prev_cpu, u64 wake_flags, * selection optimizations and simply check whether the previously * used CPU is idle and within the allowed cpumask. */ - if (p->nr_cpus_allowed == 1) { + if (p->nr_cpus_allowed == 1 || is_migration_disabled(p)) { if (cpumask_test_cpu(prev_cpu, allowed ?: p->cpus_ptr) && scx_idle_test_and_clear_cpu(prev_cpu)) cpu = prev_cpu; diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index c48900b856a2..52ca8e268cfc 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -80,7 +80,7 @@ long calc_load_fold_active(struct rq *this_rq, long adjust) long nr_active, delta = 0; nr_active = this_rq->nr_running - adjust; - nr_active += (int)this_rq->nr_uninterruptible; + nr_active += (long)this_rq->nr_uninterruptible; if (nr_active != this_rq->calc_load_active) { delta = nr_active - this_rq->calc_load_active; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 475bb5998295..83e3aa917142 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1149,7 +1149,7 @@ struct rq { * one CPU and if it got migrated afterwards it may decrease * it on another CPU. Always updated under the runqueue lock: */ - unsigned int nr_uninterruptible; + unsigned long nr_uninterruptible; union { struct task_struct __rcu *donor; /* Scheduler context */ diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 51e38f5f4701..15632c89c4f2 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -40,13 +40,31 @@ void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_ { unsigned long flags; - wq_entry->flags |= WQ_FLAG_EXCLUSIVE | WQ_FLAG_PRIORITY; + wq_entry->flags |= WQ_FLAG_PRIORITY; spin_lock_irqsave(&wq_head->lock, flags); __add_wait_queue(wq_head, wq_entry); spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL_GPL(add_wait_queue_priority); +int add_wait_queue_priority_exclusive(struct wait_queue_head *wq_head, + struct wait_queue_entry *wq_entry) +{ + struct list_head *head = &wq_head->head; + + wq_entry->flags |= WQ_FLAG_EXCLUSIVE | WQ_FLAG_PRIORITY; + + guard(spinlock_irqsave)(&wq_head->lock); + + if (!list_empty(head) && + (list_first_entry(head, typeof(*wq_entry), entry)->flags & WQ_FLAG_PRIORITY)) + return -EBUSY; + + list_add(&wq_entry->entry, head); + return 0; +} +EXPORT_SYMBOL_GPL(add_wait_queue_priority_exclusive); + void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { unsigned long flags; @@ -64,7 +82,7 @@ EXPORT_SYMBOL(remove_wait_queue); * the non-exclusive tasks. Normally, exclusive tasks will be at the end of * the list and any non-exclusive tasks will be woken first. A priority task * may be at the head of the list, and can consume the event without any other - * tasks being woken. + * tasks being woken if it's also an exclusive task. * * There are circumstances in which we can try to wake a task which has already * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index a009c91f7b05..83c65f3afcca 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1256,7 +1256,7 @@ int get_device_system_crosststamp(int (*get_time_fn) struct system_time_snapshot *history_begin, struct system_device_crosststamp *xtstamp) { - struct system_counterval_t system_counterval; + struct system_counterval_t system_counterval = {}; struct timekeeper *tk = &tk_core.timekeeper; u64 cycles, now, interval_start; unsigned int clock_was_set_seq = 0; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 120531268abf..d01e5c910ce1 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -3136,7 +3136,10 @@ __register_event(struct trace_event_call *call, struct module *mod) if (ret < 0) return ret; + down_write(&trace_event_sem); list_add(&call->list, &ftrace_events); + up_write(&trace_event_sem); + if (call->flags & TRACE_EVENT_FL_DYNAMIC) atomic_set(&call->refcnt, 0); else @@ -3750,6 +3753,8 @@ __trace_add_event_dirs(struct trace_array *tr) struct trace_event_call *call; int ret; + lockdep_assert_held(&trace_event_sem); + list_for_each_entry(call, &ftrace_events, list) { ret = __trace_add_new_event(call, tr); if (ret < 0) diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 6819b93309ce..fd259da0aa64 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -637,8 +637,8 @@ __timerlat_dump_stack(struct trace_buffer *buffer, struct trace_stack *fstack, u entry = ring_buffer_event_data(event); - memcpy(&entry->caller, fstack->calls, size); entry->size = fstack->nr_entries; + memcpy(&entry->caller, fstack->calls, size); trace_buffer_unlock_commit_nostack(buffer, event); } diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 424751cdf31f..40830a3ecd96 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -657,7 +657,7 @@ static int parse_btf_arg(char *varname, ret = query_btf_context(ctx); if (ret < 0 || ctx->nr_params == 0) { trace_probe_log_err(ctx->offset, NO_BTF_ENTRY); - return PTR_ERR(params); + return -ENOENT; } } params = ctx->params; diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 3a74d63a959e..0142bc916f73 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -135,6 +135,9 @@ size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sl struct codetag_bytes n; unsigned int i, nr = 0; + if (IS_ERR_OR_NULL(alloc_tag_cttype)) + return 0; + if (can_sleep) codetag_lock_module_list(alloc_tag_cttype, true); else if (!codetag_trylock_module_list(alloc_tag_cttype)) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 00524e55a21e..ef66be963798 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5319,6 +5319,7 @@ static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, struct maple_enode *start; if (mte_is_leaf(enode)) { + mte_set_node_dead(enode); node->type = mte_node_type(enode); goto free_leaf; } diff --git a/mm/damon/core.c b/mm/damon/core.c index b217e0120e09..339116ea30e3 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -754,6 +754,19 @@ static struct damos_quota_goal *damos_nth_quota_goal( return NULL; } +static void damos_commit_quota_goal_union( + struct damos_quota_goal *dst, struct damos_quota_goal *src) +{ + switch (dst->metric) { + case DAMOS_QUOTA_NODE_MEM_USED_BP: + case DAMOS_QUOTA_NODE_MEM_FREE_BP: + dst->nid = src->nid; + break; + default: + break; + } +} + static void damos_commit_quota_goal( struct damos_quota_goal *dst, struct damos_quota_goal *src) { @@ -762,6 +775,7 @@ static void damos_commit_quota_goal( if (dst->metric == DAMOS_QUOTA_USER_INPUT) dst->current_value = src->current_value; /* keep last_psi_total as is, since it will be updated in next cycle */ + damos_commit_quota_goal_union(dst, src); } /** @@ -795,6 +809,7 @@ int damos_commit_quota_goals(struct damos_quota *dst, struct damos_quota *src) src_goal->metric, src_goal->target_value); if (!new_goal) return -ENOMEM; + damos_commit_quota_goal_union(new_goal, src_goal); damos_add_quota_goal(dst, new_goal); } return 0; @@ -1449,6 +1464,7 @@ static unsigned long damon_get_intervals_score(struct damon_ctx *c) } } target_access_events = max_access_events * goal_bp / 10000; + target_access_events = target_access_events ? : 1; return access_events * 10000 / target_access_events; } @@ -2355,9 +2371,8 @@ static void kdamond_usleep(unsigned long usecs) * * If there is a &struct damon_call_control request that registered via * &damon_call() on @ctx, do or cancel the invocation of the function depending - * on @cancel. @cancel is set when the kdamond is deactivated by DAMOS - * watermarks, or the kdamond is already out of the main loop and therefore - * will be terminated. + * on @cancel. @cancel is set when the kdamond is already out of the main loop + * and therefore will be terminated. */ static void kdamond_call(struct damon_ctx *ctx, bool cancel) { @@ -2405,7 +2420,7 @@ static int kdamond_wait_activation(struct damon_ctx *ctx) if (ctx->callback.after_wmarks_check && ctx->callback.after_wmarks_check(ctx)) break; - kdamond_call(ctx, true); + kdamond_call(ctx, false); damos_walk_cancel(ctx); } return -EBUSY; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9dc95eac558c..a0d285d20992 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2340,12 +2340,15 @@ struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, struct folio *folio; spin_lock_irq(&hugetlb_lock); + if (!h->resv_huge_pages) { + spin_unlock_irq(&hugetlb_lock); + return NULL; + } + folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid, nmask); - if (folio) { - VM_BUG_ON(!h->resv_huge_pages); + if (folio) h->resv_huge_pages--; - } spin_unlock_irq(&hugetlb_lock); return folio; diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 8357e1a33699..62c01b4527eb 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -370,36 +370,6 @@ static inline bool init_task_stack_addr(const void *addr) sizeof(init_thread_union.stack)); } -/* - * This function is invoked with report_lock (a raw_spinlock) held. A - * PREEMPT_RT kernel cannot call find_vm_area() as it will acquire a sleeping - * rt_spinlock. - * - * For !RT kernel, the PROVE_RAW_LOCK_NESTING config option will print a - * lockdep warning for this raw_spinlock -> spinlock dependency. This config - * option is enabled by default to ensure better test coverage to expose this - * kind of RT kernel problem. This lockdep splat, however, can be suppressed - * by using DEFINE_WAIT_OVERRIDE_MAP() if it serves a useful purpose and the - * invalid PREEMPT_RT case has been taken care of. - */ -static inline struct vm_struct *kasan_find_vm_area(void *addr) -{ - static DEFINE_WAIT_OVERRIDE_MAP(vmalloc_map, LD_WAIT_SLEEP); - struct vm_struct *va; - - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - return NULL; - - /* - * Suppress lockdep warning and fetch vmalloc area of the - * offending address. - */ - lock_map_acquire_try(&vmalloc_map); - va = find_vm_area(addr); - lock_map_release(&vmalloc_map); - return va; -} - static void print_address_description(void *addr, u8 tag, struct kasan_report_info *info) { @@ -429,19 +399,10 @@ static void print_address_description(void *addr, u8 tag, } if (is_vmalloc_addr(addr)) { - struct vm_struct *va = kasan_find_vm_area(addr); - - if (va) { - pr_err("The buggy address belongs to the virtual mapping at\n" - " [%px, %px) created by:\n" - " %pS\n", - va->addr, va->addr + va->size, va->caller); - pr_err("\n"); - - page = vmalloc_to_page(addr); - } else { - pr_err("The buggy address %px belongs to a vmalloc virtual mapping\n", addr); - } + pr_err("The buggy address belongs to a"); + if (!vmalloc_dump_obj(addr)) + pr_cont(" vmalloc virtual mapping\n"); + page = vmalloc_to_page(addr); } if (page) { @@ -3669,10 +3669,10 @@ static ssize_t advisor_mode_show(struct kobject *kobj, { const char *output; - if (ksm_advisor == KSM_ADVISOR_NONE) - output = "[none] scan-time"; - else if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) + if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) output = "none [scan-time]"; + else + output = "[none] scan-time"; return sysfs_emit(buf, "%s\n", output); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 902da8a9c643..70fdeda1120b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -474,8 +474,6 @@ static const unsigned int memcg_vm_event_stat[] = { NUMA_PAGE_MIGRATE, NUMA_PTE_UPDATES, NUMA_HINT_FAULTS, - NUMA_TASK_MIGRATE, - NUMA_TASK_SWAP, #endif }; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index b91a33fb6c69..225dddff091d 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1561,6 +1561,10 @@ static int get_hwpoison_page(struct page *p, unsigned long flags) return ret; } +/* + * The caller must guarantee the folio isn't large folio, except hugetlb. + * try_to_unmap() can't handle it. + */ int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill) { enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON; diff --git a/mm/migrate.c b/mm/migrate.c index 8cf0f9c9599d..2c88f3b33833 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2399,6 +2399,7 @@ set_status: static int get_compat_pages_array(const void __user *chunk_pages[], const void __user * __user *pages, + unsigned long chunk_offset, unsigned long chunk_nr) { compat_uptr_t __user *pages32 = (compat_uptr_t __user *)pages; @@ -2406,7 +2407,7 @@ static int get_compat_pages_array(const void __user *chunk_pages[], int i; for (i = 0; i < chunk_nr; i++) { - if (get_user(p, pages32 + i)) + if (get_user(p, pages32 + chunk_offset + i)) return -EFAULT; chunk_pages[i] = compat_ptr(p); } @@ -2425,27 +2426,28 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages, #define DO_PAGES_STAT_CHUNK_NR 16UL const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR]; int chunk_status[DO_PAGES_STAT_CHUNK_NR]; + unsigned long chunk_offset = 0; while (nr_pages) { unsigned long chunk_nr = min(nr_pages, DO_PAGES_STAT_CHUNK_NR); if (in_compat_syscall()) { if (get_compat_pages_array(chunk_pages, pages, - chunk_nr)) + chunk_offset, chunk_nr)) break; } else { - if (copy_from_user(chunk_pages, pages, + if (copy_from_user(chunk_pages, pages + chunk_offset, chunk_nr * sizeof(*chunk_pages))) break; } do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status); - if (copy_to_user(status, chunk_status, chunk_nr * sizeof(*status))) + if (copy_to_user(status + chunk_offset, chunk_status, + chunk_nr * sizeof(*status))) break; - pages += chunk_nr; - status += chunk_nr; + chunk_offset += chunk_nr; nr_pages -= chunk_nr; } return nr_pages ? -EFAULT : 0; diff --git a/mm/rmap.c b/mm/rmap.c index fb63d9256f09..1320b88fab74 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1845,23 +1845,32 @@ void folio_remove_rmap_pud(struct folio *folio, struct page *page, #endif } -/* We support batch unmapping of PTEs for lazyfree large folios */ -static inline bool can_batch_unmap_folio_ptes(unsigned long addr, - struct folio *folio, pte_t *ptep) +static inline unsigned int folio_unmap_pte_batch(struct folio *folio, + struct page_vma_mapped_walk *pvmw, + enum ttu_flags flags, pte_t pte) { const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; - int max_nr = folio_nr_pages(folio); - pte_t pte = ptep_get(ptep); + unsigned long end_addr, addr = pvmw->address; + struct vm_area_struct *vma = pvmw->vma; + unsigned int max_nr; + + if (flags & TTU_HWPOISON) + return 1; + if (!folio_test_large(folio)) + return 1; + /* We may only batch within a single VMA and a single page table. */ + end_addr = pmd_addr_end(addr, vma->vm_end); + max_nr = (end_addr - addr) >> PAGE_SHIFT; + + /* We only support lazyfree batching for now ... */ if (!folio_test_anon(folio) || folio_test_swapbacked(folio)) - return false; + return 1; if (pte_unused(pte)) - return false; - if (pte_pfn(pte) != folio_pfn(folio)) - return false; + return 1; - return folio_pte_batch(folio, addr, ptep, pte, max_nr, fpb_flags, NULL, - NULL, NULL) == max_nr; + return folio_pte_batch(folio, addr, pvmw->pte, pte, max_nr, fpb_flags, + NULL, NULL, NULL); } /* @@ -2024,9 +2033,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, if (pte_dirty(pteval)) folio_mark_dirty(folio); } else if (likely(pte_present(pteval))) { - if (folio_test_large(folio) && !(flags & TTU_HWPOISON) && - can_batch_unmap_folio_ptes(address, folio, pvmw.pte)) - nr_pages = folio_nr_pages(folio); + nr_pages = folio_unmap_pte_batch(folio, &pvmw, flags, pteval); end_addr = address + nr_pages * PAGE_SIZE; flush_cache_range(vma, address, end_addr); @@ -2206,13 +2213,16 @@ discard: hugetlb_remove_rmap(folio); } else { folio_remove_rmap_ptes(folio, subpage, nr_pages, vma); - folio_ref_sub(folio, nr_pages - 1); } if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); - folio_put(folio); - /* We have already batched the entire folio */ - if (nr_pages > 1) + folio_put_refs(folio, nr_pages); + + /* + * If we are sure that we batched the entire folio and cleared + * all PTEs, we can just optimize and stop right here. + */ + if (nr_pages == folio_nr_pages(folio)) goto walk_done; continue; walk_abort: diff --git a/mm/secretmem.c b/mm/secretmem.c index 9a11a38a6770..e042a4a0bc0c 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -261,7 +261,15 @@ err_put_fd: static int secretmem_init_fs_context(struct fs_context *fc) { - return init_pseudo(fc, SECRETMEM_MAGIC) ? 0 : -ENOMEM; + struct pseudo_fs_context *ctx; + + ctx = init_pseudo(fc, SECRETMEM_MAGIC); + if (!ctx) + return -ENOMEM; + + fc->s_iflags |= SB_I_NOEXEC; + fc->s_iflags |= SB_I_NODEV; + return 0; } static struct file_system_type secretmem_fs = { @@ -279,9 +287,6 @@ static int __init secretmem_init(void) if (IS_ERR(secretmem_mnt)) return PTR_ERR(secretmem_mnt); - /* prevent secretmem mappings from ever getting PROT_EXEC */ - secretmem_mnt->mnt_flags |= MNT_NOEXEC; - return 0; } fs_initcall(secretmem_init); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index ab986dd09b6a..6dbcdceecae1 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -514,6 +514,7 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { + int err = 0; pte_t *pte; /* @@ -530,12 +531,18 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, do { struct page *page = pages[*nr]; - if (WARN_ON(!pte_none(ptep_get(pte)))) - return -EBUSY; - if (WARN_ON(!page)) - return -ENOMEM; - if (WARN_ON(!pfn_valid(page_to_pfn(page)))) - return -EINVAL; + if (WARN_ON(!pte_none(ptep_get(pte)))) { + err = -EBUSY; + break; + } + if (WARN_ON(!page)) { + err = -ENOMEM; + break; + } + if (WARN_ON(!pfn_valid(page_to_pfn(page)))) { + err = -EINVAL; + break; + } set_pte_at(&init_mm, addr, pte, mk_pte(page, prot)); (*nr)++; @@ -543,7 +550,8 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, arch_leave_lazy_mmu_mode(); *mask |= PGTBL_PTE_MODIFIED; - return 0; + + return err; } static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr, diff --git a/mm/vmscan.c b/mm/vmscan.c index f8dfd2864bbf..424412680cfc 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1138,6 +1138,14 @@ retry: goto keep; if (folio_contain_hwpoisoned_page(folio)) { + /* + * unmap_poisoned_folio() can't handle large + * folio, just skip it. memory_failure() will + * handle it if the UCE is triggered again. + */ + if (folio_test_large(folio)) + goto keep_locked; + unmap_poisoned_folio(folio, folio_pfn(folio), false); folio_unlock(folio); folio_put(folio); diff --git a/mm/vmstat.c b/mm/vmstat.c index 429ae5339bfe..a78d70ddeacd 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1346,8 +1346,6 @@ const char * const vmstat_text[] = { "numa_hint_faults", "numa_hint_faults_local", "numa_pages_migrated", - "numa_task_migrated", - "numa_task_swapped", #endif #ifdef CONFIG_MIGRATION "pgmigrate_success", diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 999b513c7fdf..f3e2215f95eb 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1043,6 +1043,9 @@ static struct zspage *alloc_zspage(struct zs_pool *pool, if (!zspage) return NULL; + if (!IS_ENABLED(CONFIG_COMPACTION)) + gfp &= ~__GFP_MOVABLE; + zspage->magic = ZSPAGE_MAGIC; zspage->pool = pool; zspage->class = class->index; diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 06908e37c3d9..9a6df8c1daf9 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -357,6 +357,35 @@ static int __vlan_device_event(struct net_device *dev, unsigned long event) return err; } +static void vlan_vid0_add(struct net_device *dev) +{ + struct vlan_info *vlan_info; + int err; + + if (!(dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) + return; + + pr_info("adding VLAN 0 to HW filter on device %s\n", dev->name); + + err = vlan_vid_add(dev, htons(ETH_P_8021Q), 0); + if (err) + return; + + vlan_info = rtnl_dereference(dev->vlan_info); + vlan_info->auto_vid0 = true; +} + +static void vlan_vid0_del(struct net_device *dev) +{ + struct vlan_info *vlan_info = rtnl_dereference(dev->vlan_info); + + if (!vlan_info || !vlan_info->auto_vid0) + return; + + vlan_info->auto_vid0 = false; + vlan_vid_del(dev, htons(ETH_P_8021Q), 0); +} + static int vlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { @@ -378,15 +407,10 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, return notifier_from_errno(err); } - if ((event == NETDEV_UP) && - (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) { - pr_info("adding VLAN 0 to HW filter on device %s\n", - dev->name); - vlan_vid_add(dev, htons(ETH_P_8021Q), 0); - } - if (event == NETDEV_DOWN && - (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) - vlan_vid_del(dev, htons(ETH_P_8021Q), 0); + if (event == NETDEV_UP) + vlan_vid0_add(dev); + else if (event == NETDEV_DOWN) + vlan_vid0_del(dev); vlan_info = rtnl_dereference(dev->vlan_info); if (!vlan_info) diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 5eaf38875554..c7ffe591d593 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -33,6 +33,7 @@ struct vlan_info { struct vlan_group grp; struct list_head vid_list; unsigned int nr_vids; + bool auto_vid0; struct rcu_head rcu; }; diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index 9c787e2e4b17..4744e3fd4544 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -35,6 +35,7 @@ #include <linux/seq_file.h> #include <linux/export.h> #include <linux/etherdevice.h> +#include <linux/refcount.h> int sysctl_aarp_expiry_time = AARP_EXPIRY_TIME; int sysctl_aarp_tick_time = AARP_TICK_TIME; @@ -44,6 +45,7 @@ int sysctl_aarp_resolve_time = AARP_RESOLVE_TIME; /* Lists of aarp entries */ /** * struct aarp_entry - AARP entry + * @refcnt: Reference count * @last_sent: Last time we xmitted the aarp request * @packet_queue: Queue of frames wait for resolution * @status: Used for proxy AARP @@ -55,6 +57,7 @@ int sysctl_aarp_resolve_time = AARP_RESOLVE_TIME; * @next: Next entry in chain */ struct aarp_entry { + refcount_t refcnt; /* These first two are only used for unresolved entries */ unsigned long last_sent; struct sk_buff_head packet_queue; @@ -79,6 +82,17 @@ static DEFINE_RWLOCK(aarp_lock); /* Used to walk the list and purge/kick entries. */ static struct timer_list aarp_timer; +static inline void aarp_entry_get(struct aarp_entry *a) +{ + refcount_inc(&a->refcnt); +} + +static inline void aarp_entry_put(struct aarp_entry *a) +{ + if (refcount_dec_and_test(&a->refcnt)) + kfree(a); +} + /* * Delete an aarp queue * @@ -87,7 +101,7 @@ static struct timer_list aarp_timer; static void __aarp_expire(struct aarp_entry *a) { skb_queue_purge(&a->packet_queue); - kfree(a); + aarp_entry_put(a); } /* @@ -380,9 +394,11 @@ static void aarp_purge(void) static struct aarp_entry *aarp_alloc(void) { struct aarp_entry *a = kmalloc(sizeof(*a), GFP_ATOMIC); + if (!a) + return NULL; - if (a) - skb_queue_head_init(&a->packet_queue); + refcount_set(&a->refcnt, 1); + skb_queue_head_init(&a->packet_queue); return a; } @@ -477,6 +493,7 @@ int aarp_proxy_probe_network(struct atalk_iface *atif, struct atalk_addr *sa) entry->dev = atif->dev; write_lock_bh(&aarp_lock); + aarp_entry_get(entry); hash = sa->s_node % (AARP_HASH_SIZE - 1); entry->next = proxies[hash]; @@ -502,6 +519,7 @@ int aarp_proxy_probe_network(struct atalk_iface *atif, struct atalk_addr *sa) retval = 1; } + aarp_entry_put(entry); write_unlock_bh(&aarp_lock); out: return retval; diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 73ea7e67f05a..30242fe10341 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -576,6 +576,7 @@ static int atrtr_create(struct rtentry *r, struct net_device *devhint) /* Fill in the routing entry */ rt->target = ta->sat_addr; + dev_put(rt->dev); /* Release old device */ dev_hold(devhint); rt->dev = devhint; rt->flags = r->rt_flags; diff --git a/net/atm/clip.c b/net/atm/clip.c index b234dc3bcb0d..f7a5565e794e 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -45,7 +45,8 @@ #include <net/atmclip.h> static struct net_device *clip_devs; -static struct atm_vcc *atmarpd; +static struct atm_vcc __rcu *atmarpd; +static DEFINE_MUTEX(atmarpd_lock); static struct timer_list idle_timer; static const struct neigh_ops clip_neigh_ops; @@ -53,24 +54,35 @@ static int to_atmarpd(enum atmarp_ctrl_type type, int itf, __be32 ip) { struct sock *sk; struct atmarp_ctrl *ctrl; + struct atm_vcc *vcc; struct sk_buff *skb; + int err = 0; pr_debug("(%d)\n", type); - if (!atmarpd) - return -EUNATCH; + + rcu_read_lock(); + vcc = rcu_dereference(atmarpd); + if (!vcc) { + err = -EUNATCH; + goto unlock; + } skb = alloc_skb(sizeof(struct atmarp_ctrl), GFP_ATOMIC); - if (!skb) - return -ENOMEM; + if (!skb) { + err = -ENOMEM; + goto unlock; + } ctrl = skb_put(skb, sizeof(struct atmarp_ctrl)); ctrl->type = type; ctrl->itf_num = itf; ctrl->ip = ip; - atm_force_charge(atmarpd, skb->truesize); + atm_force_charge(vcc, skb->truesize); - sk = sk_atm(atmarpd); + sk = sk_atm(vcc); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk); - return 0; +unlock: + rcu_read_unlock(); + return err; } static void link_vcc(struct clip_vcc *clip_vcc, struct atmarp_entry *entry) @@ -417,6 +429,8 @@ static int clip_mkip(struct atm_vcc *vcc, int timeout) if (!vcc->push) return -EBADFD; + if (vcc->user_back) + return -EINVAL; clip_vcc = kmalloc(sizeof(struct clip_vcc), GFP_KERNEL); if (!clip_vcc) return -ENOMEM; @@ -607,17 +621,27 @@ static void atmarpd_close(struct atm_vcc *vcc) { pr_debug("\n"); - rtnl_lock(); - atmarpd = NULL; + mutex_lock(&atmarpd_lock); + RCU_INIT_POINTER(atmarpd, NULL); + mutex_unlock(&atmarpd_lock); + + synchronize_rcu(); skb_queue_purge(&sk_atm(vcc)->sk_receive_queue); - rtnl_unlock(); pr_debug("(done)\n"); module_put(THIS_MODULE); } +static int atmarpd_send(struct atm_vcc *vcc, struct sk_buff *skb) +{ + atm_return_tx(vcc, skb); + dev_kfree_skb_any(skb); + return 0; +} + static const struct atmdev_ops atmarpd_dev_ops = { - .close = atmarpd_close + .close = atmarpd_close, + .send = atmarpd_send }; @@ -631,15 +655,18 @@ static struct atm_dev atmarpd_dev = { static int atm_init_atmarp(struct atm_vcc *vcc) { - rtnl_lock(); + if (vcc->push == clip_push) + return -EINVAL; + + mutex_lock(&atmarpd_lock); if (atmarpd) { - rtnl_unlock(); + mutex_unlock(&atmarpd_lock); return -EADDRINUSE; } mod_timer(&idle_timer, jiffies + CLIP_CHECK_INTERVAL * HZ); - atmarpd = vcc; + rcu_assign_pointer(atmarpd, vcc); set_bit(ATM_VF_META, &vcc->flags); set_bit(ATM_VF_READY, &vcc->flags); /* allow replies and avoid getting closed if signaling dies */ @@ -648,13 +675,14 @@ static int atm_init_atmarp(struct atm_vcc *vcc) vcc->push = NULL; vcc->pop = NULL; /* crash */ vcc->push_oam = NULL; /* crash */ - rtnl_unlock(); + mutex_unlock(&atmarpd_lock); return 0; } static int clip_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct atm_vcc *vcc = ATM_SD(sock); + struct sock *sk = sock->sk; int err = 0; switch (cmd) { @@ -675,14 +703,18 @@ static int clip_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) err = clip_create(arg); break; case ATMARPD_CTRL: + lock_sock(sk); err = atm_init_atmarp(vcc); if (!err) { sock->state = SS_CONNECTED; __module_get(THIS_MODULE); } + release_sock(sk); break; case ATMARP_MKIP: + lock_sock(sk); err = clip_mkip(vcc, arg); + release_sock(sk); break; case ATMARP_SETENTRY: err = clip_setentry(vcc, (__force __be32)arg); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 14d7221b8ac0..441cb1700f99 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2654,7 +2654,7 @@ int hci_register_dev(struct hci_dev *hdev) /* Devices that are marked for raw-only usage are unconfigured * and should not be included in normal operation. */ - if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) + if (hci_test_quirk(hdev, HCI_QUIRK_RAW_DEVICE)) hci_dev_set_flag(hdev, HCI_UNCONFIGURED); /* Mark Remote Wakeup connection flag as supported if driver has wakeup @@ -2784,7 +2784,7 @@ int hci_register_suspend_notifier(struct hci_dev *hdev) int ret = 0; if (!hdev->suspend_notifier.notifier_call && - !test_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks)) { + !hci_test_quirk(hdev, HCI_QUIRK_NO_SUSPEND_NOTIFIER)) { hdev->suspend_notifier.notifier_call = hci_suspend_notifier; ret = register_pm_notifier(&hdev->suspend_notifier); } diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index f625074d1f00..99e2e9fc70e8 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -38,7 +38,7 @@ static ssize_t __name ## _read(struct file *file, \ struct hci_dev *hdev = file->private_data; \ char buf[3]; \ \ - buf[0] = test_bit(__quirk, &hdev->quirks) ? 'Y' : 'N'; \ + buf[0] = test_bit(__quirk, hdev->quirk_flags) ? 'Y' : 'N'; \ buf[1] = '\n'; \ buf[2] = '\0'; \ return simple_read_from_buffer(user_buf, count, ppos, buf, 2); \ @@ -59,10 +59,10 @@ static ssize_t __name ## _write(struct file *file, \ if (err) \ return err; \ \ - if (enable == test_bit(__quirk, &hdev->quirks)) \ + if (enable == test_bit(__quirk, hdev->quirk_flags)) \ return -EALREADY; \ \ - change_bit(__quirk, &hdev->quirks); \ + change_bit(__quirk, hdev->quirk_flags); \ \ return count; \ } \ @@ -1356,7 +1356,7 @@ static ssize_t vendor_diag_write(struct file *file, const char __user *user_buf, * for the vendor callback. Instead just store the desired value and * the setting will be programmed when the controller gets powered on. */ - if (test_bit(HCI_QUIRK_NON_PERSISTENT_DIAG, &hdev->quirks) && + if (hci_test_quirk(hdev, HCI_QUIRK_NON_PERSISTENT_DIAG) && (!test_bit(HCI_RUNNING, &hdev->flags) || hci_dev_test_flag(hdev, HCI_USER_CHANNEL))) goto done; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 4d5ace9d245d..cf4b30ac9e0e 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -908,8 +908,8 @@ static u8 hci_cc_read_local_ext_features(struct hci_dev *hdev, void *data, return rp->status; if (hdev->max_page < rp->max_page) { - if (test_bit(HCI_QUIRK_BROKEN_LOCAL_EXT_FEATURES_PAGE_2, - &hdev->quirks)) + if (hci_test_quirk(hdev, + HCI_QUIRK_BROKEN_LOCAL_EXT_FEATURES_PAGE_2)) bt_dev_warn(hdev, "broken local ext features page 2"); else hdev->max_page = rp->max_page; @@ -936,7 +936,7 @@ static u8 hci_cc_read_buffer_size(struct hci_dev *hdev, void *data, hdev->acl_pkts = __le16_to_cpu(rp->acl_max_pkt); hdev->sco_pkts = __le16_to_cpu(rp->sco_max_pkt); - if (test_bit(HCI_QUIRK_FIXUP_BUFFER_SIZE, &hdev->quirks)) { + if (hci_test_quirk(hdev, HCI_QUIRK_FIXUP_BUFFER_SIZE)) { hdev->sco_mtu = 64; hdev->sco_pkts = 8; } @@ -2971,7 +2971,7 @@ static void hci_inquiry_complete_evt(struct hci_dev *hdev, void *data, * state to indicate completion. */ if (!hci_dev_test_flag(hdev, HCI_LE_SCAN) || - !test_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks)) + !hci_test_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY)) hci_discovery_set_state(hdev, DISCOVERY_STOPPED); goto unlock; } @@ -2990,7 +2990,7 @@ static void hci_inquiry_complete_evt(struct hci_dev *hdev, void *data, * state to indicate completion. */ if (!hci_dev_test_flag(hdev, HCI_LE_SCAN) || - !test_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks)) + !hci_test_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY)) hci_discovery_set_state(hdev, DISCOVERY_STOPPED); } @@ -3614,8 +3614,7 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data, /* We skip the WRITE_AUTH_PAYLOAD_TIMEOUT for ATS2851 based controllers * to avoid unexpected SMP command errors when pairing. */ - if (test_bit(HCI_QUIRK_BROKEN_WRITE_AUTH_PAYLOAD_TIMEOUT, - &hdev->quirks)) + if (hci_test_quirk(hdev, HCI_QUIRK_BROKEN_WRITE_AUTH_PAYLOAD_TIMEOUT)) goto notify; /* Set the default Authenticated Payload Timeout after @@ -5914,7 +5913,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, * while we have an existing one in peripheral role. */ if (hdev->conn_hash.le_num_peripheral > 0 && - (test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) || + (hci_test_quirk(hdev, HCI_QUIRK_BROKEN_LE_STATES) || !(hdev->le_states[3] & 0x10))) return NULL; @@ -6310,8 +6309,8 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, void *data, evt_type = __le16_to_cpu(info->type) & LE_EXT_ADV_EVT_TYPE_MASK; legacy_evt_type = ext_evt_type_to_legacy(hdev, evt_type); - if (test_bit(HCI_QUIRK_FIXUP_LE_EXT_ADV_REPORT_PHY, - &hdev->quirks)) { + if (hci_test_quirk(hdev, + HCI_QUIRK_FIXUP_LE_EXT_ADV_REPORT_PHY)) { info->primary_phy &= 0x1f; info->secondary_phy &= 0x1f; } @@ -6966,7 +6965,10 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, bis->iso_qos.bcast.in.sdu = le16_to_cpu(ev->max_pdu); if (!ev->status) { + bis->state = BT_CONNECTED; set_bit(HCI_CONN_BIG_SYNC, &bis->flags); + hci_debugfs_create_conn(bis); + hci_conn_add_sysfs(bis); hci_iso_setup_path(bis); } } diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 77b3691f3423..7938c004071c 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -393,7 +393,7 @@ static void le_scan_disable(struct work_struct *work) if (hdev->discovery.type != DISCOV_TYPE_INTERLEAVED) goto _return; - if (test_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks)) { + if (hci_test_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY)) { if (!test_bit(HCI_INQUIRY, &hdev->flags) && hdev->discovery.state != DISCOVERY_RESOLVING) goto discov_stopped; @@ -1345,7 +1345,7 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) * Command Disallowed error, so we must first disable the * instance if it is active. */ - if (adv && !adv->pending) { + if (adv) { err = hci_disable_ext_adv_instance_sync(hdev, instance); if (err) return err; @@ -3587,7 +3587,7 @@ static void hci_dev_get_bd_addr_from_property(struct hci_dev *hdev) if (ret < 0 || !bacmp(&ba, BDADDR_ANY)) return; - if (test_bit(HCI_QUIRK_BDADDR_PROPERTY_BROKEN, &hdev->quirks)) + if (hci_test_quirk(hdev, HCI_QUIRK_BDADDR_PROPERTY_BROKEN)) baswap(&hdev->public_addr, &ba); else bacpy(&hdev->public_addr, &ba); @@ -3662,7 +3662,7 @@ static int hci_init0_sync(struct hci_dev *hdev) bt_dev_dbg(hdev, ""); /* Reset */ - if (!test_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks)) { + if (!hci_test_quirk(hdev, HCI_QUIRK_RESET_ON_CLOSE)) { err = hci_reset_sync(hdev); if (err) return err; @@ -3675,7 +3675,7 @@ static int hci_unconf_init_sync(struct hci_dev *hdev) { int err; - if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) + if (hci_test_quirk(hdev, HCI_QUIRK_RAW_DEVICE)) return 0; err = hci_init0_sync(hdev); @@ -3718,7 +3718,7 @@ static int hci_read_local_cmds_sync(struct hci_dev *hdev) * supported commands. */ if (hdev->hci_ver > BLUETOOTH_VER_1_1 && - !test_bit(HCI_QUIRK_BROKEN_LOCAL_COMMANDS, &hdev->quirks)) + !hci_test_quirk(hdev, HCI_QUIRK_BROKEN_LOCAL_COMMANDS)) return __hci_cmd_sync_status(hdev, HCI_OP_READ_LOCAL_COMMANDS, 0, NULL, HCI_CMD_TIMEOUT); @@ -3732,7 +3732,7 @@ static int hci_init1_sync(struct hci_dev *hdev) bt_dev_dbg(hdev, ""); /* Reset */ - if (!test_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks)) { + if (!hci_test_quirk(hdev, HCI_QUIRK_RESET_ON_CLOSE)) { err = hci_reset_sync(hdev); if (err) return err; @@ -3795,7 +3795,7 @@ static int hci_set_event_filter_sync(struct hci_dev *hdev, u8 flt_type, if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) return 0; - if (test_bit(HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL, &hdev->quirks)) + if (hci_test_quirk(hdev, HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL)) return 0; memset(&cp, 0, sizeof(cp)); @@ -3822,7 +3822,7 @@ static int hci_clear_event_filter_sync(struct hci_dev *hdev) * a hci_set_event_filter_sync() call succeeds, but we do * the check both for parity and as a future reminder. */ - if (test_bit(HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL, &hdev->quirks)) + if (hci_test_quirk(hdev, HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL)) return 0; return hci_set_event_filter_sync(hdev, HCI_FLT_CLEAR_ALL, 0x00, @@ -3846,7 +3846,7 @@ static int hci_write_sync_flowctl_sync(struct hci_dev *hdev) /* Check if the controller supports SCO and HCI_OP_WRITE_SYNC_FLOWCTL */ if (!lmp_sco_capable(hdev) || !(hdev->commands[10] & BIT(4)) || - !test_bit(HCI_QUIRK_SYNC_FLOWCTL_SUPPORTED, &hdev->quirks)) + !hci_test_quirk(hdev, HCI_QUIRK_SYNC_FLOWCTL_SUPPORTED)) return 0; memset(&cp, 0, sizeof(cp)); @@ -3921,7 +3921,7 @@ static int hci_write_inquiry_mode_sync(struct hci_dev *hdev) u8 mode; if (!lmp_inq_rssi_capable(hdev) && - !test_bit(HCI_QUIRK_FIXUP_INQUIRY_MODE, &hdev->quirks)) + !hci_test_quirk(hdev, HCI_QUIRK_FIXUP_INQUIRY_MODE)) return 0; /* If Extended Inquiry Result events are supported, then @@ -4111,7 +4111,7 @@ static int hci_set_event_mask_sync(struct hci_dev *hdev) } if (lmp_inq_rssi_capable(hdev) || - test_bit(HCI_QUIRK_FIXUP_INQUIRY_MODE, &hdev->quirks)) + hci_test_quirk(hdev, HCI_QUIRK_FIXUP_INQUIRY_MODE)) events[4] |= 0x02; /* Inquiry Result with RSSI */ if (lmp_ext_feat_capable(hdev)) @@ -4163,7 +4163,7 @@ static int hci_read_stored_link_key_sync(struct hci_dev *hdev) struct hci_cp_read_stored_link_key cp; if (!(hdev->commands[6] & 0x20) || - test_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks)) + hci_test_quirk(hdev, HCI_QUIRK_BROKEN_STORED_LINK_KEY)) return 0; memset(&cp, 0, sizeof(cp)); @@ -4212,7 +4212,7 @@ static int hci_read_def_err_data_reporting_sync(struct hci_dev *hdev) { if (!(hdev->commands[18] & 0x04) || !(hdev->features[0][6] & LMP_ERR_DATA_REPORTING) || - test_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks)) + hci_test_quirk(hdev, HCI_QUIRK_BROKEN_ERR_DATA_REPORTING)) return 0; return __hci_cmd_sync_status(hdev, HCI_OP_READ_DEF_ERR_DATA_REPORTING, @@ -4226,7 +4226,7 @@ static int hci_read_page_scan_type_sync(struct hci_dev *hdev) * this command in the bit mask of supported commands. */ if (!(hdev->commands[13] & 0x01) || - test_bit(HCI_QUIRK_BROKEN_READ_PAGE_SCAN_TYPE, &hdev->quirks)) + hci_test_quirk(hdev, HCI_QUIRK_BROKEN_READ_PAGE_SCAN_TYPE)) return 0; return __hci_cmd_sync_status(hdev, HCI_OP_READ_PAGE_SCAN_TYPE, @@ -4421,7 +4421,7 @@ static int hci_le_read_adv_tx_power_sync(struct hci_dev *hdev) static int hci_le_read_tx_power_sync(struct hci_dev *hdev) { if (!(hdev->commands[38] & 0x80) || - test_bit(HCI_QUIRK_BROKEN_READ_TRANSMIT_POWER, &hdev->quirks)) + hci_test_quirk(hdev, HCI_QUIRK_BROKEN_READ_TRANSMIT_POWER)) return 0; return __hci_cmd_sync_status(hdev, HCI_OP_LE_READ_TRANSMIT_POWER, @@ -4464,7 +4464,7 @@ static int hci_le_set_rpa_timeout_sync(struct hci_dev *hdev) __le16 timeout = cpu_to_le16(hdev->rpa_timeout); if (!(hdev->commands[35] & 0x04) || - test_bit(HCI_QUIRK_BROKEN_SET_RPA_TIMEOUT, &hdev->quirks)) + hci_test_quirk(hdev, HCI_QUIRK_BROKEN_SET_RPA_TIMEOUT)) return 0; return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_RPA_TIMEOUT, @@ -4609,7 +4609,7 @@ static int hci_delete_stored_link_key_sync(struct hci_dev *hdev) * just disable this command. */ if (!(hdev->commands[6] & 0x80) || - test_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks)) + hci_test_quirk(hdev, HCI_QUIRK_BROKEN_STORED_LINK_KEY)) return 0; memset(&cp, 0, sizeof(cp)); @@ -4735,7 +4735,7 @@ static int hci_set_err_data_report_sync(struct hci_dev *hdev) if (!(hdev->commands[18] & 0x08) || !(hdev->features[0][6] & LMP_ERR_DATA_REPORTING) || - test_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks)) + hci_test_quirk(hdev, HCI_QUIRK_BROKEN_ERR_DATA_REPORTING)) return 0; if (enabled == hdev->err_data_reporting) @@ -4948,7 +4948,7 @@ static int hci_dev_setup_sync(struct hci_dev *hdev) size_t i; if (!hci_dev_test_flag(hdev, HCI_SETUP) && - !test_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks)) + !hci_test_quirk(hdev, HCI_QUIRK_NON_PERSISTENT_SETUP)) return 0; bt_dev_dbg(hdev, ""); @@ -4959,7 +4959,7 @@ static int hci_dev_setup_sync(struct hci_dev *hdev) ret = hdev->setup(hdev); for (i = 0; i < ARRAY_SIZE(hci_broken_table); i++) { - if (test_bit(hci_broken_table[i].quirk, &hdev->quirks)) + if (hci_test_quirk(hdev, hci_broken_table[i].quirk)) bt_dev_warn(hdev, "%s", hci_broken_table[i].desc); } @@ -4967,10 +4967,10 @@ static int hci_dev_setup_sync(struct hci_dev *hdev) * BD_ADDR invalid before creating the HCI device or in * its setup callback. */ - invalid_bdaddr = test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks) || - test_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); + invalid_bdaddr = hci_test_quirk(hdev, HCI_QUIRK_INVALID_BDADDR) || + hci_test_quirk(hdev, HCI_QUIRK_USE_BDADDR_PROPERTY); if (!ret) { - if (test_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks) && + if (hci_test_quirk(hdev, HCI_QUIRK_USE_BDADDR_PROPERTY) && !bacmp(&hdev->public_addr, BDADDR_ANY)) hci_dev_get_bd_addr_from_property(hdev); @@ -4992,7 +4992,7 @@ static int hci_dev_setup_sync(struct hci_dev *hdev) * In case any of them is set, the controller has to * start up as unconfigured. */ - if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) || + if (hci_test_quirk(hdev, HCI_QUIRK_EXTERNAL_CONFIG) || invalid_bdaddr) hci_dev_set_flag(hdev, HCI_UNCONFIGURED); @@ -5052,7 +5052,7 @@ static int hci_dev_init_sync(struct hci_dev *hdev) * then they need to be reprogrammed after the init procedure * completed. */ - if (test_bit(HCI_QUIRK_NON_PERSISTENT_DIAG, &hdev->quirks) && + if (hci_test_quirk(hdev, HCI_QUIRK_NON_PERSISTENT_DIAG) && !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && hci_dev_test_flag(hdev, HCI_VENDOR_DIAG) && hdev->set_diag) ret = hdev->set_diag(hdev, true); @@ -5309,7 +5309,7 @@ int hci_dev_close_sync(struct hci_dev *hdev) /* Reset device */ skb_queue_purge(&hdev->cmd_q); atomic_set(&hdev->cmd_cnt, 1); - if (test_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks) && + if (hci_test_quirk(hdev, HCI_QUIRK_RESET_ON_CLOSE) && !auto_off && !hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { set_bit(HCI_INIT, &hdev->flags); hci_reset_sync(hdev); @@ -5493,7 +5493,7 @@ static int hci_disconnect_sync(struct hci_dev *hdev, struct hci_conn *conn, { struct hci_cp_disconnect cp; - if (test_bit(HCI_CONN_BIG_CREATED, &conn->flags)) { + if (conn->type == BIS_LINK) { /* This is a BIS connection, hci_conn_del will * do the necessary cleanup. */ @@ -5959,7 +5959,7 @@ static int hci_active_scan_sync(struct hci_dev *hdev, uint16_t interval) own_addr_type = ADDR_LE_DEV_PUBLIC; if (hci_is_adv_monitoring(hdev) || - (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks) && + (hci_test_quirk(hdev, HCI_QUIRK_STRICT_DUPLICATE_FILTER) && hdev->discovery.result_filtering)) { /* Duplicate filter should be disabled when some advertisement * monitor is activated, otherwise AdvMon can only receive one @@ -6022,8 +6022,7 @@ int hci_start_discovery_sync(struct hci_dev *hdev) * and LE scanning are done sequentially with separate * timeouts. */ - if (test_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, - &hdev->quirks)) { + if (hci_test_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY)) { timeout = msecs_to_jiffies(DISCOV_LE_TIMEOUT); /* During simultaneous discovery, we double LE scan * interval. We must leave some time for the controller @@ -6100,7 +6099,7 @@ static int hci_update_event_filter_sync(struct hci_dev *hdev) /* Some fake CSR controllers lock up after setting this type of * filter, so avoid sending the request altogether. */ - if (test_bit(HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL, &hdev->quirks)) + if (hci_test_quirk(hdev, HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL)) return 0; /* Always clear event filter when starting */ @@ -6815,8 +6814,8 @@ int hci_get_random_address(struct hci_dev *hdev, bool require_privacy, return 0; } - /* No privacy so use a public address. */ - *own_addr_type = ADDR_LE_DEV_PUBLIC; + /* No privacy, use the current address */ + hci_copy_identity_address(hdev, rand_addr, own_addr_type); return 0; } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 40daa38276f3..805c752ac0a9 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -3520,12 +3520,28 @@ done: /* Configure output options and let the other side know * which ones we don't like. */ - /* If MTU is not provided in configure request, use the most recently - * explicitly or implicitly accepted value for the other direction, - * or the default value. + /* If MTU is not provided in configure request, try adjusting it + * to the current output MTU if it has been set + * + * Bluetooth Core 6.1, Vol 3, Part A, Section 4.5 + * + * Each configuration parameter value (if any is present) in an + * L2CAP_CONFIGURATION_RSP packet reflects an ‘adjustment’ to a + * configuration parameter value that has been sent (or, in case + * of default values, implied) in the corresponding + * L2CAP_CONFIGURATION_REQ packet. */ - if (mtu == 0) - mtu = chan->imtu ? chan->imtu : L2CAP_DEFAULT_MTU; + if (!mtu) { + /* Only adjust for ERTM channels as for older modes the + * remote stack may not be able to detect that the + * adjustment causing it to silently drop packets. + */ + if (chan->mode == L2CAP_MODE_ERTM && + chan->omtu && chan->omtu != L2CAP_DEFAULT_MTU) + mtu = chan->omtu; + else + mtu = L2CAP_DEFAULT_MTU; + } if (mtu < L2CAP_DEFAULT_MIN_MTU) result = L2CAP_CONF_UNACCEPT; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 5aa55fa69594..82d943c4cb50 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1703,6 +1703,9 @@ static void l2cap_sock_resume_cb(struct l2cap_chan *chan) { struct sock *sk = chan->data; + if (!sk) + return; + if (test_and_clear_bit(FLAG_PENDING_SECURITY, &chan->flags)) { sk->sk_state = BT_CONNECTED; chan->state = BT_CONNECTED; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 1485b455ade4..63dba0503653 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -464,7 +464,7 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data, /* Devices marked as raw-only are neither configured * nor unconfigured controllers. */ - if (test_bit(HCI_QUIRK_RAW_DEVICE, &d->quirks)) + if (hci_test_quirk(d, HCI_QUIRK_RAW_DEVICE)) continue; if (!hci_dev_test_flag(d, HCI_UNCONFIGURED)) { @@ -522,7 +522,7 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev, /* Devices marked as raw-only are neither configured * nor unconfigured controllers. */ - if (test_bit(HCI_QUIRK_RAW_DEVICE, &d->quirks)) + if (hci_test_quirk(d, HCI_QUIRK_RAW_DEVICE)) continue; if (hci_dev_test_flag(d, HCI_UNCONFIGURED)) { @@ -576,7 +576,7 @@ static int read_ext_index_list(struct sock *sk, struct hci_dev *hdev, /* Devices marked as raw-only are neither configured * nor unconfigured controllers. */ - if (test_bit(HCI_QUIRK_RAW_DEVICE, &d->quirks)) + if (hci_test_quirk(d, HCI_QUIRK_RAW_DEVICE)) continue; if (hci_dev_test_flag(d, HCI_UNCONFIGURED)) @@ -612,12 +612,12 @@ static int read_ext_index_list(struct sock *sk, struct hci_dev *hdev, static bool is_configured(struct hci_dev *hdev) { - if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) && + if (hci_test_quirk(hdev, HCI_QUIRK_EXTERNAL_CONFIG) && !hci_dev_test_flag(hdev, HCI_EXT_CONFIGURED)) return false; - if ((test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks) || - test_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks)) && + if ((hci_test_quirk(hdev, HCI_QUIRK_INVALID_BDADDR) || + hci_test_quirk(hdev, HCI_QUIRK_USE_BDADDR_PROPERTY)) && !bacmp(&hdev->public_addr, BDADDR_ANY)) return false; @@ -628,12 +628,12 @@ static __le32 get_missing_options(struct hci_dev *hdev) { u32 options = 0; - if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) && + if (hci_test_quirk(hdev, HCI_QUIRK_EXTERNAL_CONFIG) && !hci_dev_test_flag(hdev, HCI_EXT_CONFIGURED)) options |= MGMT_OPTION_EXTERNAL_CONFIG; - if ((test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks) || - test_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks)) && + if ((hci_test_quirk(hdev, HCI_QUIRK_INVALID_BDADDR) || + hci_test_quirk(hdev, HCI_QUIRK_USE_BDADDR_PROPERTY)) && !bacmp(&hdev->public_addr, BDADDR_ANY)) options |= MGMT_OPTION_PUBLIC_ADDRESS; @@ -669,7 +669,7 @@ static int read_config_info(struct sock *sk, struct hci_dev *hdev, memset(&rp, 0, sizeof(rp)); rp.manufacturer = cpu_to_le16(hdev->manufacturer); - if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks)) + if (hci_test_quirk(hdev, HCI_QUIRK_EXTERNAL_CONFIG)) options |= MGMT_OPTION_EXTERNAL_CONFIG; if (hdev->set_bdaddr) @@ -828,8 +828,7 @@ static u32 get_supported_settings(struct hci_dev *hdev) if (lmp_sc_capable(hdev)) settings |= MGMT_SETTING_SECURE_CONN; - if (test_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, - &hdev->quirks)) + if (hci_test_quirk(hdev, HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED)) settings |= MGMT_SETTING_WIDEBAND_SPEECH; } @@ -841,8 +840,7 @@ static u32 get_supported_settings(struct hci_dev *hdev) settings |= MGMT_SETTING_ADVERTISING; } - if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) || - hdev->set_bdaddr) + if (hci_test_quirk(hdev, HCI_QUIRK_EXTERNAL_CONFIG) || hdev->set_bdaddr) settings |= MGMT_SETTING_CONFIGURATION; if (cis_central_capable(hdev)) @@ -4307,7 +4305,7 @@ static int set_wideband_speech(struct sock *sk, struct hci_dev *hdev, bt_dev_dbg(hdev, "sock %p", sk); - if (!test_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks)) + if (!hci_test_quirk(hdev, HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED)) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_WIDEBAND_SPEECH, MGMT_STATUS_NOT_SUPPORTED); @@ -7935,7 +7933,7 @@ static int set_external_config(struct sock *sk, struct hci_dev *hdev, return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_EXTERNAL_CONFIG, MGMT_STATUS_INVALID_PARAMS); - if (!test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks)) + if (!hci_test_quirk(hdev, HCI_QUIRK_EXTERNAL_CONFIG)) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_EXTERNAL_CONFIG, MGMT_STATUS_NOT_SUPPORTED); @@ -9338,7 +9336,7 @@ void mgmt_index_added(struct hci_dev *hdev) { struct mgmt_ev_ext_index ev; - if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) + if (hci_test_quirk(hdev, HCI_QUIRK_RAW_DEVICE)) return; if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { @@ -9362,7 +9360,7 @@ void mgmt_index_removed(struct hci_dev *hdev) struct mgmt_ev_ext_index ev; struct cmd_lookup match = { NULL, hdev, MGMT_STATUS_INVALID_INDEX }; - if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) + if (hci_test_quirk(hdev, HCI_QUIRK_RAW_DEVICE)) return; mgmt_pending_foreach(0, hdev, true, cmd_complete_rsp, &match); @@ -10089,7 +10087,7 @@ static bool is_filter_match(struct hci_dev *hdev, s8 rssi, u8 *eir, if (hdev->discovery.rssi != HCI_RSSI_INVALID && (rssi == HCI_RSSI_INVALID || (rssi < hdev->discovery.rssi && - !test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks)))) + !hci_test_quirk(hdev, HCI_QUIRK_STRICT_DUPLICATE_FILTER)))) return false; if (hdev->discovery.uuid_count != 0) { @@ -10107,7 +10105,7 @@ static bool is_filter_match(struct hci_dev *hdev, s8 rssi, u8 *eir, /* If duplicate filtering does not report RSSI changes, then restart * scanning to ensure updated result with updated RSSI values. */ - if (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks)) { + if (hci_test_quirk(hdev, HCI_QUIRK_STRICT_DUPLICATE_FILTER)) { /* Validate RSSI value against the RSSI threshold once more. */ if (hdev->discovery.rssi != HCI_RSSI_INVALID && rssi < hdev->discovery.rssi) diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index 5a8ccc491b14..c560d8467669 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -989,7 +989,7 @@ static void msft_monitor_device_evt(struct hci_dev *hdev, struct sk_buff *skb) handle_data = msft_find_handle_data(hdev, ev->monitor_handle, false); - if (!test_bit(HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER, &hdev->quirks)) { + if (!hci_test_quirk(hdev, HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER)) { if (!handle_data) return; mgmt_handle = handle_data->mgmt_handle; diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 47f359f24d1f..8115d42fc15b 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -1379,7 +1379,7 @@ static void smp_timeout(struct work_struct *work) bt_dev_dbg(conn->hcon->hdev, "conn %p", conn); - hci_disconnect(conn->hcon, HCI_ERROR_REMOTE_USER_TERM); + hci_disconnect(conn->hcon, HCI_ERROR_AUTH_FAILURE); } static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) @@ -2977,8 +2977,25 @@ static int smp_sig_channel(struct l2cap_chan *chan, struct sk_buff *skb) if (code > SMP_CMD_MAX) goto drop; - if (smp && !test_and_clear_bit(code, &smp->allow_cmd)) + if (smp && !test_and_clear_bit(code, &smp->allow_cmd)) { + /* If there is a context and the command is not allowed consider + * it a failure so the session is cleanup properly. + */ + switch (code) { + case SMP_CMD_IDENT_INFO: + case SMP_CMD_IDENT_ADDR_INFO: + case SMP_CMD_SIGN_INFO: + /* 3.6.1. Key distribution and generation + * + * A device may reject a distributed key by sending the + * Pairing Failed command with the reason set to + * "Key Rejected". + */ + smp_failure(conn, SMP_KEY_REJECTED); + break; + } goto drop; + } /* If we don't have a context the only allowed commands are * pairing request and security request. diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h index 87a59ec2c9f0..c5da53dfab04 100644 --- a/net/bluetooth/smp.h +++ b/net/bluetooth/smp.h @@ -138,6 +138,7 @@ struct smp_cmd_keypress_notify { #define SMP_NUMERIC_COMP_FAILED 0x0c #define SMP_BREDR_PAIRING_IN_PROGRESS 0x0d #define SMP_CROSS_TRANSP_NOT_ALLOWED 0x0e +#define SMP_KEY_REJECTED 0x0f #define SMP_MIN_ENC_KEY_SIZE 7 #define SMP_MAX_ENC_KEY_SIZE 16 diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 95d7355a0407..9a910cf0256e 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -17,6 +17,9 @@ static bool nbp_switchdev_can_offload_tx_fwd(const struct net_bridge_port *p, if (!static_branch_unlikely(&br_switchdev_tx_fwd_offload)) return false; + if (br_multicast_igmp_type(skb)) + return false; + return (p->flags & BR_TX_FWD_OFFLOAD) && (p->hwdom != BR_INPUT_SKB_CB(skb)->src_hwdom); } diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 5a4fb2539b08..9a45aed508d1 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -54,6 +54,7 @@ static int ipcomp4_err(struct sk_buff *skb, u32 info) } /* We always hold one tunnel user reference to indicate a tunnel */ +static struct lock_class_key xfrm_state_lock_key; static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x) { struct net *net = xs_net(x); @@ -62,6 +63,7 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x) t = xfrm_state_alloc(net); if (!t) goto out; + lockdep_set_class(&t->lock, &xfrm_state_lock_key); t->id.proto = IPPROTO_IPIP; t->id.spi = x->props.saddr.a4; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f64f8276a73c..461a9ab540af 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1176,7 +1176,7 @@ restart: goto do_error; while (msg_data_left(msg)) { - ssize_t copy = 0; + int copy = 0; skb = tcp_write_queue_tail(sk); if (skb) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 12c2e6fc85c6..68bc79eb9019 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5181,7 +5181,9 @@ end: skb_condense(skb); skb_set_owner_r(skb, sk); } - tcp_rcvbuf_grow(sk); + /* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */ + if (sk->sk_socket) + tcp_rcvbuf_grow(sk); } static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index d293087b426d..be5c2294610e 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -359,6 +359,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, flush |= skb->ip_summed != p->ip_summed; flush |= skb->csum_level != p->csum_level; flush |= NAPI_GRO_CB(p)->count >= 64; + skb_set_network_header(skb, skb_gro_receive_network_offset(skb)); if (flush || skb_gro_receive_list(p, skb)) mss = 1; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 85b5aa82d7d7..e0a6bfa95118 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -767,6 +767,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, NAPI_GRO_CB(skb)->flush = 1; return NULL; } + skb_set_network_header(skb, skb_gro_receive_network_offset(skb)); ret = skb_gro_receive_list(p, skb); } else { skb_gro_postpull_rcsum(skb, uh, diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 0d31a8c108d4..f28cfd88eaf5 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -202,6 +202,9 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0) goto out; + /* set the transport header to ESP */ + skb_set_transport_header(skb, offset); + NAPI_GRO_CB(skb)->proto = IPPROTO_UDP; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ba2ec7c870cc..870a0bd6c2ba 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3525,11 +3525,9 @@ static void addrconf_gre_config(struct net_device *dev) ASSERT_RTNL(); - idev = ipv6_find_idev(dev); - if (IS_ERR(idev)) { - pr_debug("%s: add_dev failed\n", __func__); + idev = addrconf_add_dev(dev); + if (IS_ERR(idev)) return; - } /* Generate the IPv6 link-local address using addrconf_addr_gen(), * unless we have an IPv4 GRE device not bound to an IP address and @@ -3543,9 +3541,6 @@ static void addrconf_gre_config(struct net_device *dev) } add_v4_addrs(idev); - - if (dev->flags & IFF_POINTOPOINT) - addrconf_add_mroute(dev); } #endif diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 72d4858dec18..8607569de34f 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -71,6 +71,7 @@ static int ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return 0; } +static struct lock_class_key xfrm_state_lock_key; static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) { struct net *net = xs_net(x); @@ -79,6 +80,7 @@ static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) t = xfrm_state_alloc(net); if (!t) goto out; + lockdep_set_class(&t->lock, &xfrm_state_lock_key); t->id.proto = IPPROTO_IPV6; t->id.spi = xfrm6_tunnel_alloc_spi(net, (xfrm_address_t *)&x->props.saddr); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 65831b4fee1f..616bf4c0c8fd 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -807,8 +807,8 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) } else { im->mca_crcount = idev->mc_qrv; } - in6_dev_put(pmc->idev); ip6_mc_clear_src(pmc); + in6_dev_put(pmc->idev); kfree_rcu(pmc, rcu); } } diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c index 7c05ac846646..eccfa4203e96 100644 --- a/net/ipv6/rpl_iptunnel.c +++ b/net/ipv6/rpl_iptunnel.c @@ -129,13 +129,13 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt, struct dst_entry *cache_dst) { struct ipv6_rpl_sr_hdr *isrh, *csrh; - const struct ipv6hdr *oldhdr; + struct ipv6hdr oldhdr; struct ipv6hdr *hdr; unsigned char *buf; size_t hdrlen; int err; - oldhdr = ipv6_hdr(skb); + memcpy(&oldhdr, ipv6_hdr(skb), sizeof(oldhdr)); buf = kcalloc(struct_size(srh, segments.addr, srh->segments_left), 2, GFP_ATOMIC); if (!buf) @@ -147,7 +147,7 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt, memcpy(isrh, srh, sizeof(*isrh)); memcpy(isrh->rpl_segaddr, &srh->rpl_segaddr[1], (srh->segments_left - 1) * 16); - isrh->rpl_segaddr[srh->segments_left - 1] = oldhdr->daddr; + isrh->rpl_segaddr[srh->segments_left - 1] = oldhdr.daddr; ipv6_rpl_srh_compress(csrh, isrh, &srh->rpl_segaddr[0], isrh->segments_left - 1); @@ -169,7 +169,7 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt, skb_mac_header_rebuild(skb); hdr = ipv6_hdr(skb); - memmove(hdr, oldhdr, sizeof(*hdr)); + memmove(hdr, &oldhdr, sizeof(*hdr)); isrh = (void *)hdr + sizeof(*hdr); memcpy(isrh, csrh, hdrlen); diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 841c81abaaf4..9005fc156a20 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -202,6 +202,9 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0) goto out; + /* set the transport header to ESP */ + skb_set_transport_header(skb, offset); + NAPI_GRO_CB(skb)->proto = IPPROTO_UDP; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index bf140ef781c1..5120a763da0d 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -334,8 +334,8 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; + xfrm_state_flush(net, IPSEC_PROTO_ANY, false); xfrm_flush_gc(); - xfrm_state_flush(net, 0, false, true); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i])); diff --git a/net/key/af_key.c b/net/key/af_key.c index efc2a91f4c48..b5d761700776 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1766,7 +1766,7 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m if (proto == 0) return -EINVAL; - err = xfrm_state_flush(net, proto, true, false); + err = xfrm_state_flush(net, proto, true); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - go quietly */ diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index d9d88f2f2831..954795b0fe48 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1959,6 +1959,20 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, ieee80211_sta_init_nss(link_sta); if (params->opmode_notif_used) { + enum nl80211_chan_width width = link->conf->chanreq.oper.width; + + switch (width) { + case NL80211_CHAN_WIDTH_20: + case NL80211_CHAN_WIDTH_40: + case NL80211_CHAN_WIDTH_80: + case NL80211_CHAN_WIDTH_160: + case NL80211_CHAN_WIDTH_80P80: + case NL80211_CHAN_WIDTH_320: /* not VHT, allowed for HE/EHT */ + break; + default: + return -EINVAL; + } + /* returned value is only needed for rc update, but the * rc isn't initialized here yet, so ignore it */ diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 7c27f3cd841c..c01634fdba78 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1150,6 +1150,8 @@ static void ieee80211_sdata_init(struct ieee80211_local *local, { sdata->local = local; + INIT_LIST_HEAD(&sdata->key_list); + /* * Initialize the default link, so we can use link_id 0 for non-MLD, * and that continues to work for non-MLD-aware drivers that use just @@ -2210,8 +2212,6 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ieee80211_init_frag_cache(&sdata->frags); - INIT_LIST_HEAD(&sdata->key_list); - wiphy_delayed_work_init(&sdata->dec_tailroom_needed_wk, ieee80211_delayed_tailroom_dec); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 2d46d4af60d7..0ed68182f79b 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -3934,6 +3934,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, lockdep_assert_wiphy(local->hw.wiphy); + if (frame_buf) + memset(frame_buf, 0, IEEE80211_DEAUTH_FRAME_LEN); + if (WARN_ON(!ap_sta)) return; @@ -7195,6 +7198,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, struct ieee80211_bss_conf *bss_conf = link->conf; struct ieee80211_vif_cfg *vif_cfg = &sdata->vif.cfg; struct ieee80211_mgmt *mgmt = (void *) hdr; + struct ieee80211_ext *ext = NULL; size_t baselen; struct ieee802_11_elems *elems; struct ieee80211_local *local = sdata->local; @@ -7220,7 +7224,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, /* Process beacon from the current BSS */ bssid = ieee80211_get_bssid(hdr, len, sdata->vif.type); if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { - struct ieee80211_ext *ext = (void *) mgmt; + ext = (void *)mgmt; variable = ext->u.s1g_beacon.variable + ieee80211_s1g_optional_len(ext->frame_control); } @@ -7407,7 +7411,9 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, } if ((ncrc == link->u.mgd.beacon_crc && link->u.mgd.beacon_crc_valid) || - ieee80211_is_s1g_short_beacon(mgmt->frame_control)) + (ext && ieee80211_is_s1g_short_beacon(ext->frame_control, + parse_params.start, + parse_params.len))) goto free; link->u.mgd.beacon_crc = ncrc; link->u.mgd.beacon_crc_valid = true; @@ -10699,8 +10705,8 @@ static void ieee80211_ml_epcs(struct ieee80211_sub_if_data *sdata, */ for_each_mle_subelement(sub, (const u8 *)elems->ml_epcs, elems->ml_epcs_len) { + struct ieee802_11_elems *link_elems __free(kfree) = NULL; struct ieee80211_link_data *link; - struct ieee802_11_elems *link_elems __free(kfree); u8 *pos = (void *)sub->data; u16 control; ssize_t len; diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c index 96584b39215e..c5e0f7f46004 100644 --- a/net/mac80211/parse.c +++ b/net/mac80211/parse.c @@ -758,7 +758,6 @@ static size_t ieee802_11_find_bssid_profile(const u8 *start, size_t len, { const struct element *elem, *sub; size_t profile_len = 0; - bool found = false; if (!bss || !bss->transmitted_bss) return profile_len; @@ -809,15 +808,14 @@ static size_t ieee802_11_find_bssid_profile(const u8 *start, size_t len, index[2], new_bssid); if (ether_addr_equal(new_bssid, bss->bssid)) { - found = true; elems->bssid_index_len = index[1]; elems->bssid_index = (void *)&index[2]; - break; + return profile_len; } } } - return found ? profile_len : 0; + return 0; } static void diff --git a/net/mac80211/util.c b/net/mac80211/util.c index a125995ed252..e66da651678a 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2144,11 +2144,6 @@ int ieee80211_reconfig(struct ieee80211_local *local) cfg80211_sched_scan_stopped_locked(local->hw.wiphy, 0); wake_up: - - if (local->virt_monitors > 0 && - local->virt_monitors == local->open_count) - ieee80211_add_virtual_monitor(local); - /* * Clear the WLAN_STA_BLOCK_BA flag so new aggregation * sessions can be established after a resume. @@ -2202,6 +2197,10 @@ int ieee80211_reconfig(struct ieee80211_local *local) } } + if (local->virt_monitors > 0 && + local->virt_monitors == local->open_count) + ieee80211_add_virtual_monitor(local); + if (!suspended) return 0; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 421ced031289..1f898888b223 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -978,8 +978,9 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, if (subflow->mp_join) goto reset; subflow->mp_capable = 0; + if (!mptcp_try_fallback(ssk)) + goto reset; pr_fallback(msk); - mptcp_do_fallback(ssk); return false; } diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index feb01747d7d8..420d416e2603 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -765,8 +765,14 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq) pr_debug("fail_seq=%llu\n", fail_seq); - if (!READ_ONCE(msk->allow_infinite_fallback)) + /* After accepting the fail, we can't create any other subflows */ + spin_lock_bh(&msk->fallback_lock); + if (!msk->allow_infinite_fallback) { + spin_unlock_bh(&msk->fallback_lock); return; + } + msk->allow_subflows = false; + spin_unlock_bh(&msk->fallback_lock); if (!subflow->fail_tout) { pr_debug("send MP_FAIL response and infinite map\n"); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index edf14c2c2062..6a817a13b154 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -560,10 +560,9 @@ static bool mptcp_check_data_fin(struct sock *sk) static void mptcp_dss_corruption(struct mptcp_sock *msk, struct sock *ssk) { - if (READ_ONCE(msk->allow_infinite_fallback)) { + if (mptcp_try_fallback(ssk)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSCORRUPTIONFALLBACK); - mptcp_do_fallback(ssk); } else { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSCORRUPTIONRESET); mptcp_subflow_reset(ssk); @@ -792,7 +791,7 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) static void mptcp_subflow_joined(struct mptcp_sock *msk, struct sock *ssk) { mptcp_subflow_ctx(ssk)->map_seq = READ_ONCE(msk->ack_seq); - WRITE_ONCE(msk->allow_infinite_fallback, false); + msk->allow_infinite_fallback = false; mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC); } @@ -803,6 +802,14 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) if (sk->sk_state != TCP_ESTABLISHED) return false; + spin_lock_bh(&msk->fallback_lock); + if (!msk->allow_subflows) { + spin_unlock_bh(&msk->fallback_lock); + return false; + } + mptcp_subflow_joined(msk, ssk); + spin_unlock_bh(&msk->fallback_lock); + /* attach to msk socket only after we are sure we will deal with it * at close time */ @@ -811,7 +818,6 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) mptcp_subflow_ctx(ssk)->subflow_id = msk->subflow_id++; mptcp_sockopt_sync_locked(msk, ssk); - mptcp_subflow_joined(msk, ssk); mptcp_stop_tout_timer(sk); __mptcp_propagate_sndbuf(sk, ssk); return true; @@ -1136,10 +1142,14 @@ static void mptcp_update_infinite_map(struct mptcp_sock *msk, mpext->infinite_map = 1; mpext->data_len = 0; + if (!mptcp_try_fallback(ssk)) { + mptcp_subflow_reset(ssk); + return; + } + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPTX); mptcp_subflow_ctx(ssk)->send_infinite_map = 0; pr_fallback(msk); - mptcp_do_fallback(ssk); } #define MPTCP_MAX_GSO_SIZE (GSO_LEGACY_MAX_SIZE - (MAX_TCP_HEADER + 1)) @@ -2543,9 +2553,9 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk) static void __mptcp_retrans(struct sock *sk) { + struct mptcp_sendmsg_info info = { .data_lock_held = true, }; struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_subflow_context *subflow; - struct mptcp_sendmsg_info info = {}; struct mptcp_data_frag *dfrag; struct sock *ssk; int ret, err; @@ -2590,6 +2600,18 @@ static void __mptcp_retrans(struct sock *sk) info.sent = 0; info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent; + + /* + * make the whole retrans decision, xmit, disallow + * fallback atomic + */ + spin_lock_bh(&msk->fallback_lock); + if (__mptcp_check_fallback(msk)) { + spin_unlock_bh(&msk->fallback_lock); + release_sock(ssk); + return; + } + while (info.sent < info.limit) { ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info); if (ret <= 0) @@ -2603,8 +2625,9 @@ static void __mptcp_retrans(struct sock *sk) len = max(copied, len); tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); - WRITE_ONCE(msk->allow_infinite_fallback, false); + msk->allow_infinite_fallback = false; } + spin_unlock_bh(&msk->fallback_lock); release_sock(ssk); } @@ -2730,7 +2753,8 @@ static void __mptcp_init_sock(struct sock *sk) WRITE_ONCE(msk->first, NULL); inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); - WRITE_ONCE(msk->allow_infinite_fallback, true); + msk->allow_infinite_fallback = true; + msk->allow_subflows = true; msk->recovery = false; msk->subflow_id = 1; msk->last_data_sent = tcp_jiffies32; @@ -2738,6 +2762,7 @@ static void __mptcp_init_sock(struct sock *sk) msk->last_ack_recv = tcp_jiffies32; mptcp_pm_data_init(msk); + spin_lock_init(&msk->fallback_lock); /* re-use the csk retrans timer for MPTCP-level retrans */ timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0); @@ -3117,7 +3142,16 @@ static int mptcp_disconnect(struct sock *sk, int flags) * subflow */ mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE); + + /* The first subflow is already in TCP_CLOSE status, the following + * can't overlap with a fallback anymore + */ + spin_lock_bh(&msk->fallback_lock); + msk->allow_subflows = true; + msk->allow_infinite_fallback = true; WRITE_ONCE(msk->flags, 0); + spin_unlock_bh(&msk->fallback_lock); + msk->cb_flags = 0; msk->recovery = false; WRITE_ONCE(msk->can_ack, false); @@ -3524,7 +3558,13 @@ bool mptcp_finish_join(struct sock *ssk) /* active subflow, already present inside the conn_list */ if (!list_empty(&subflow->node)) { + spin_lock_bh(&msk->fallback_lock); + if (!msk->allow_subflows) { + spin_unlock_bh(&msk->fallback_lock); + return false; + } mptcp_subflow_joined(msk, ssk); + spin_unlock_bh(&msk->fallback_lock); mptcp_propagate_sndbuf(parent, ssk); return true; } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 3dd11dd3ba16..6ec245fd2778 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -346,10 +346,16 @@ struct mptcp_sock { u64 rtt_us; /* last maximum rtt of subflows */ } rcvq_space; u8 scaling_ratio; + bool allow_subflows; u32 subflow_id; u32 setsockopt_seq; char ca_name[TCP_CA_NAME_MAX]; + + spinlock_t fallback_lock; /* protects fallback, + * allow_infinite_fallback and + * allow_join + */ }; #define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock) @@ -1216,15 +1222,22 @@ static inline bool mptcp_check_fallback(const struct sock *sk) return __mptcp_check_fallback(msk); } -static inline void __mptcp_do_fallback(struct mptcp_sock *msk) +static inline bool __mptcp_try_fallback(struct mptcp_sock *msk) { if (__mptcp_check_fallback(msk)) { pr_debug("TCP fallback already done (msk=%p)\n", msk); - return; + return true; } - if (WARN_ON_ONCE(!READ_ONCE(msk->allow_infinite_fallback))) - return; + spin_lock_bh(&msk->fallback_lock); + if (!msk->allow_infinite_fallback) { + spin_unlock_bh(&msk->fallback_lock); + return false; + } + + msk->allow_subflows = false; set_bit(MPTCP_FALLBACK_DONE, &msk->flags); + spin_unlock_bh(&msk->fallback_lock); + return true; } static inline bool __mptcp_has_initial_subflow(const struct mptcp_sock *msk) @@ -1236,14 +1249,15 @@ static inline bool __mptcp_has_initial_subflow(const struct mptcp_sock *msk) TCPF_SYN_RECV | TCPF_LISTEN)); } -static inline void mptcp_do_fallback(struct sock *ssk) +static inline bool mptcp_try_fallback(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = subflow->conn; struct mptcp_sock *msk; msk = mptcp_sk(sk); - __mptcp_do_fallback(msk); + if (!__mptcp_try_fallback(msk)) + return false; if (READ_ONCE(msk->snd_data_fin_enable) && !(ssk->sk_shutdown & SEND_SHUTDOWN)) { gfp_t saved_allocation = ssk->sk_allocation; @@ -1255,6 +1269,7 @@ static inline void mptcp_do_fallback(struct sock *ssk) tcp_shutdown(ssk, SEND_SHUTDOWN); ssk->sk_allocation = saved_allocation; } + return true; } #define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)\n", __func__, a) @@ -1264,7 +1279,7 @@ static inline void mptcp_subflow_early_fallback(struct mptcp_sock *msk, { pr_fallback(msk); subflow->request_mptcp = 0; - __mptcp_do_fallback(msk); + WARN_ON_ONCE(!__mptcp_try_fallback(msk)); } static inline bool mptcp_check_infinite_map(struct sk_buff *skb) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 15613d691bfe..1802bc5435a1 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -544,9 +544,11 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) mptcp_get_options(skb, &mp_opt); if (subflow->request_mptcp) { if (!(mp_opt.suboptions & OPTION_MPTCP_MPC_SYNACK)) { + if (!mptcp_try_fallback(sk)) + goto do_reset; + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEFALLBACK); - mptcp_do_fallback(sk); pr_fallback(msk); goto fallback; } @@ -1300,20 +1302,29 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss mptcp_schedule_work(sk); } -static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk) +static bool mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); unsigned long fail_tout; + /* we are really failing, prevent any later subflow join */ + spin_lock_bh(&msk->fallback_lock); + if (!msk->allow_infinite_fallback) { + spin_unlock_bh(&msk->fallback_lock); + return false; + } + msk->allow_subflows = false; + spin_unlock_bh(&msk->fallback_lock); + /* graceful failure can happen only on the MPC subflow */ if (WARN_ON_ONCE(ssk != READ_ONCE(msk->first))) - return; + return false; /* since the close timeout take precedence on the fail one, * no need to start the latter when the first is already set */ if (sock_flag((struct sock *)msk, SOCK_DEAD)) - return; + return true; /* we don't need extreme accuracy here, use a zero fail_tout as special * value meaning no fail timeout at all; @@ -1325,6 +1336,7 @@ static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk) tcp_send_ack(ssk); mptcp_reset_tout_timer(msk, subflow->fail_tout); + return true; } static bool subflow_check_data_avail(struct sock *ssk) @@ -1385,17 +1397,16 @@ fallback: (subflow->mp_join || subflow->valid_csum_seen)) { subflow->send_mp_fail = 1; - if (!READ_ONCE(msk->allow_infinite_fallback)) { + if (!mptcp_subflow_fail(msk, ssk)) { subflow->reset_transient = 0; subflow->reset_reason = MPTCP_RST_EMIDDLEBOX; goto reset; } - mptcp_subflow_fail(msk, ssk); WRITE_ONCE(subflow->data_avail, true); return true; } - if (!READ_ONCE(msk->allow_infinite_fallback)) { + if (!mptcp_try_fallback(ssk)) { /* fatal protocol error, close the socket. * subflow_error_report() will introduce the appropriate barriers */ @@ -1413,8 +1424,6 @@ reset: WRITE_ONCE(subflow->data_avail, false); return false; } - - mptcp_do_fallback(ssk); } skb = skb_peek(&ssk->sk_receive_queue); @@ -1679,7 +1688,6 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_pm_local *local, /* discard the subflow socket */ mptcp_sock_graft(ssk, sk->sk_socket); iput(SOCK_INODE(sf)); - WRITE_ONCE(msk->allow_infinite_fallback, false); mptcp_stop_tout_timer(sk); return 0; @@ -1851,7 +1859,7 @@ static void subflow_state_change(struct sock *sk) msk = mptcp_sk(parent); if (subflow_simultaneous_connect(sk)) { - mptcp_do_fallback(sk); + WARN_ON_ONCE(!mptcp_try_fallback(sk)); pr_fallback(msk); subflow->conn_finished = 1; mptcp_propagate_state(parent, sk, subflow, NULL); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 201d3c4ec623..e51f0b441109 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1124,6 +1124,12 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx) hlist_nulls_add_head_rcu(&loser_ct->tuplehash[IP_CT_DIR_REPLY].hnnode, &nf_conntrack_hash[repl_idx]); + /* confirmed bit must be set after hlist add, not before: + * loser_ct can still be visible to other cpu due to + * SLAB_TYPESAFE_BY_RCU. + */ + smp_mb__before_atomic(); + set_bit(IPS_CONFIRMED_BIT, &loser_ct->status); NF_CT_STAT_INC(net, clash_resolve); return NF_ACCEPT; @@ -1260,8 +1266,6 @@ __nf_conntrack_confirm(struct sk_buff *skb) * user context, else we insert an already 'dead' hash, blocking * further use of that particular connection -JM. */ - ct->status |= IPS_CONFIRMED; - if (unlikely(nf_ct_is_dying(ct))) { NF_CT_STAT_INC(net, insert_failed); goto dying; @@ -1293,7 +1297,7 @@ chaintoolong: } } - /* Timer relative to confirmation time, not original + /* Timeout is relative to confirmation time, not original setting time, otherwise we'd get timer wrap in weird delay cases. */ ct->timeout += nfct_time_stamp; @@ -1301,11 +1305,21 @@ chaintoolong: __nf_conntrack_insert_prepare(ct); /* Since the lookup is lockless, hash insertion must be done after - * starting the timer and setting the CONFIRMED bit. The RCU barriers - * guarantee that no other CPU can find the conntrack before the above - * stores are visible. + * setting ct->timeout. The RCU barriers guarantee that no other CPU + * can find the conntrack before the above stores are visible. */ __nf_conntrack_hash_insert(ct, hash, reply_hash); + + /* IPS_CONFIRMED unset means 'ct not (yet) in hash', conntrack lookups + * skip entries that lack this bit. This happens when a CPU is looking + * at a stale entry that is being recycled due to SLAB_TYPESAFE_BY_RCU + * or when another CPU encounters this entry right after the insertion + * but before the set-confirm-bit below. This bit must not be set until + * after __nf_conntrack_hash_insert(). + */ + smp_mb__before_atomic(); + set_bit(IPS_CONFIRMED_BIT, &ct->status); + nf_conntrack_double_unlock(hash, reply_hash); local_bh_enable(); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 24c71ecb2179..a7240736f98e 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9686,64 +9686,6 @@ struct nf_hook_ops *nft_hook_find_ops_rcu(const struct nft_hook *hook, } EXPORT_SYMBOL_GPL(nft_hook_find_ops_rcu); -static void -nf_tables_device_notify(const struct nft_table *table, int attr, - const char *name, const struct nft_hook *hook, - const struct net_device *dev, int event) -{ - struct net *net = dev_net(dev); - struct nlmsghdr *nlh; - struct sk_buff *skb; - u16 flags = 0; - - if (!nfnetlink_has_listeners(net, NFNLGRP_NFT_DEV)) - return; - - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!skb) - goto err; - - event = event == NETDEV_REGISTER ? NFT_MSG_NEWDEV : NFT_MSG_DELDEV; - event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nfnl_msg_put(skb, 0, 0, event, flags, table->family, - NFNETLINK_V0, nft_base_seq(net)); - if (!nlh) - goto err; - - if (nla_put_string(skb, NFTA_DEVICE_TABLE, table->name) || - nla_put_string(skb, attr, name) || - nla_put(skb, NFTA_DEVICE_SPEC, hook->ifnamelen, hook->ifname) || - nla_put_string(skb, NFTA_DEVICE_NAME, dev->name)) - goto err; - - nlmsg_end(skb, nlh); - nfnetlink_send(skb, net, 0, NFNLGRP_NFT_DEV, - nlmsg_report(nlh), GFP_KERNEL); - return; -err: - if (skb) - kfree_skb(skb); - nfnetlink_set_err(net, 0, NFNLGRP_NFT_DEV, -ENOBUFS); -} - -void -nf_tables_chain_device_notify(const struct nft_chain *chain, - const struct nft_hook *hook, - const struct net_device *dev, int event) -{ - nf_tables_device_notify(chain->table, NFTA_DEVICE_CHAIN, - chain->name, hook, dev, event); -} - -static void -nf_tables_flowtable_device_notify(const struct nft_flowtable *ft, - const struct nft_hook *hook, - const struct net_device *dev, int event) -{ - nf_tables_device_notify(ft->table, NFTA_DEVICE_FLOWTABLE, - ft->name, hook, dev, event); -} - static int nft_flowtable_event(unsigned long event, struct net_device *dev, struct nft_flowtable *flowtable, bool changename) { @@ -9791,7 +9733,6 @@ static int nft_flowtable_event(unsigned long event, struct net_device *dev, list_add_tail_rcu(&ops->list, &hook->ops_list); break; } - nf_tables_flowtable_device_notify(flowtable, hook, dev, event); break; } return 0; diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index ae3fe87195ab..a88abae5a9de 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -127,6 +127,9 @@ static int nf_trace_fill_ct_info(struct sk_buff *nlskb, if (nla_put_be32(nlskb, NFTA_TRACE_CT_ID, (__force __be32)id)) return -1; + /* Kernel implementation detail, withhold this from userspace for now */ + status &= ~IPS_NAT_CLASH; + if (status && nla_put_be32(nlskb, NFTA_TRACE_CT_STATUS, htonl(status))) return -1; } diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index ac77fc21632d..e598a2a252b0 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -86,7 +86,6 @@ static const int nfnl_group2type[NFNLGRP_MAX+1] = { [NFNLGRP_NFTABLES] = NFNL_SUBSYS_NFTABLES, [NFNLGRP_ACCT_QUOTA] = NFNL_SUBSYS_ACCT, [NFNLGRP_NFTRACE] = NFNL_SUBSYS_NFTABLES, - [NFNLGRP_NFT_DEV] = NFNL_SUBSYS_NFTABLES, }; static struct nfnl_net *nfnl_pernet(struct net *net) diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 846d48ba8965..b16185e9a6dd 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -363,8 +363,6 @@ static int nft_netdev_event(unsigned long event, struct net_device *dev, list_add_tail_rcu(&ops->list, &hook->ops_list); break; } - nf_tables_chain_device_notify(&basechain->chain, - hook, dev, event); break; } return 0; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index e8972a857e51..6332a0e06596 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -387,7 +387,6 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) WARN_ON(skb->sk != NULL); skb->sk = sk; skb->destructor = netlink_skb_destructor; - atomic_add(skb->truesize, &sk->sk_rmem_alloc); sk_mem_charge(sk, skb->truesize); } @@ -1212,41 +1211,48 @@ struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast) int netlink_attachskb(struct sock *sk, struct sk_buff *skb, long *timeo, struct sock *ssk) { + DECLARE_WAITQUEUE(wait, current); struct netlink_sock *nlk; + unsigned int rmem; nlk = nlk_sk(sk); + rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc); - if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || - test_bit(NETLINK_S_CONGESTED, &nlk->state))) { - DECLARE_WAITQUEUE(wait, current); - if (!*timeo) { - if (!ssk || netlink_is_kernel(ssk)) - netlink_overrun(sk); - sock_put(sk); - kfree_skb(skb); - return -EAGAIN; - } - - __set_current_state(TASK_INTERRUPTIBLE); - add_wait_queue(&nlk->wait, &wait); + if ((rmem == skb->truesize || rmem < READ_ONCE(sk->sk_rcvbuf)) && + !test_bit(NETLINK_S_CONGESTED, &nlk->state)) { + netlink_skb_set_owner_r(skb, sk); + return 0; + } - if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || - test_bit(NETLINK_S_CONGESTED, &nlk->state)) && - !sock_flag(sk, SOCK_DEAD)) - *timeo = schedule_timeout(*timeo); + atomic_sub(skb->truesize, &sk->sk_rmem_alloc); - __set_current_state(TASK_RUNNING); - remove_wait_queue(&nlk->wait, &wait); + if (!*timeo) { + if (!ssk || netlink_is_kernel(ssk)) + netlink_overrun(sk); sock_put(sk); + kfree_skb(skb); + return -EAGAIN; + } - if (signal_pending(current)) { - kfree_skb(skb); - return sock_intr_errno(*timeo); - } - return 1; + __set_current_state(TASK_INTERRUPTIBLE); + add_wait_queue(&nlk->wait, &wait); + rmem = atomic_read(&sk->sk_rmem_alloc); + + if (((rmem && rmem + skb->truesize > READ_ONCE(sk->sk_rcvbuf)) || + test_bit(NETLINK_S_CONGESTED, &nlk->state)) && + !sock_flag(sk, SOCK_DEAD)) + *timeo = schedule_timeout(*timeo); + + __set_current_state(TASK_RUNNING); + remove_wait_queue(&nlk->wait, &wait); + sock_put(sk); + + if (signal_pending(current)) { + kfree_skb(skb); + return sock_intr_errno(*timeo); } - netlink_skb_set_owner_r(skb, sk); - return 0; + + return 1; } static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb) @@ -1307,6 +1313,7 @@ static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb, ret = -ECONNREFUSED; if (nlk->netlink_rcv != NULL) { ret = skb->len; + atomic_add(skb->truesize, &sk->sk_rmem_alloc); netlink_skb_set_owner_r(skb, sk); NETLINK_CB(skb).sk = ssk; netlink_deliver_tap_kernel(sk, ssk, skb); @@ -1383,13 +1390,19 @@ EXPORT_SYMBOL_GPL(netlink_strict_get_check); static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) { struct netlink_sock *nlk = nlk_sk(sk); + unsigned int rmem, rcvbuf; - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && + rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc); + rcvbuf = READ_ONCE(sk->sk_rcvbuf); + + if ((rmem == skb->truesize || rmem <= rcvbuf) && !test_bit(NETLINK_S_CONGESTED, &nlk->state)) { netlink_skb_set_owner_r(skb, sk); __netlink_sendskb(sk, skb); - return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1); + return rmem > (rcvbuf >> 1); } + + atomic_sub(skb->truesize, &sk->sk_rmem_alloc); return -1; } @@ -2245,6 +2258,7 @@ static int netlink_dump(struct sock *sk, bool lock_taken) struct netlink_ext_ack extack = {}; struct netlink_callback *cb; struct sk_buff *skb = NULL; + unsigned int rmem, rcvbuf; size_t max_recvmsg_len; struct module *module; int err = -ENOBUFS; @@ -2258,9 +2272,6 @@ static int netlink_dump(struct sock *sk, bool lock_taken) goto errout_skb; } - if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) - goto errout_skb; - /* NLMSG_GOODSIZE is small to avoid high order allocations being * required, but it makes sense to _attempt_ a 32KiB allocation * to reduce number of system calls on dump operations, if user @@ -2283,6 +2294,13 @@ static int netlink_dump(struct sock *sk, bool lock_taken) if (!skb) goto errout_skb; + rcvbuf = READ_ONCE(sk->sk_rcvbuf); + rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc); + if (rmem != skb->truesize && rmem >= rcvbuf) { + atomic_sub(skb->truesize, &sk->sk_rmem_alloc); + goto errout_skb; + } + /* Trim skb to allocated size. User is expected to provide buffer as * large as max(min_dump_alloc, 32KiB (max_recvmsg_len capped at * netlink_recvmsg())). dump will pack as many smaller messages as diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 3d43f3eae759..be608f07441f 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2785,7 +2785,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) int len_sum = 0; int status = TP_STATUS_AVAILABLE; int hlen, tlen, copylen = 0; - long timeo = 0; + long timeo; mutex_lock(&po->pg_vec_lock); @@ -2839,22 +2839,28 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if ((size_max > dev->mtu + reserve + VLAN_HLEN) && !vnet_hdr_sz) size_max = dev->mtu + reserve + VLAN_HLEN; + timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT); reinit_completion(&po->skb_completion); do { ph = packet_current_frame(po, &po->tx_ring, TP_STATUS_SEND_REQUEST); if (unlikely(ph == NULL)) { - if (need_wait && skb) { - timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT); + /* Note: packet_read_pending() might be slow if we + * have to call it as it's per_cpu variable, but in + * fast-path we don't have to call it, only when ph + * is NULL, we need to check the pending_refcnt. + */ + if (need_wait && packet_read_pending(&po->tx_ring)) { timeo = wait_for_completion_interruptible_timeout(&po->skb_completion, timeo); if (timeo <= 0) { err = !timeo ? -ETIMEDOUT : -ERESTARTSYS; goto out_put; } - } - /* check for additional frames */ - continue; + /* check for additional frames */ + continue; + } else + break; } skb = NULL; @@ -2943,14 +2949,7 @@ tpacket_error: } packet_increment_head(&po->tx_ring); len_sum += tp_len; - } while (likely((ph != NULL) || - /* Note: packet_read_pending() might be slow if we have - * to call it as it's per_cpu variable, but in fast-path - * we already short-circuit the loop with the first - * condition, and luckily don't have to go that path - * anyway. - */ - (need_wait && packet_read_pending(&po->tx_ring)))); + } while (1); err = len_sum; goto out_put; diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 53a858478e22..62527e1ebb88 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -826,6 +826,7 @@ static struct sock *pep_sock_accept(struct sock *sk, } /* Check for duplicate pipe handle */ + pn_skb_get_dst_sockaddr(skb, &dst); newsk = pep_find_pipe(&pn->hlist, &dst, pipe_handle); if (unlikely(newsk)) { __sock_put(newsk); @@ -850,7 +851,6 @@ static struct sock *pep_sock_accept(struct sock *sk, newsk->sk_destruct = pipe_destruct; newpn = pep_sk(newsk); - pn_skb_get_dst_sockaddr(skb, &dst); pn_skb_get_src_sockaddr(skb, &src); newpn->pn_sk.sobject = pn_sockaddr_get_object(&dst); newpn->pn_sk.dobject = pn_sockaddr_get_object(&src); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5bd3922c310d..5b7342d43486 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -44,6 +44,7 @@ enum rxrpc_skb_mark { RXRPC_SKB_MARK_SERVICE_CONN_SECURED, /* Service connection response has been verified */ RXRPC_SKB_MARK_REJECT_BUSY, /* Reject with BUSY */ RXRPC_SKB_MARK_REJECT_ABORT, /* Reject with ABORT (code in skb->priority) */ + RXRPC_SKB_MARK_REJECT_CONN_ABORT, /* Reject with connection ABORT (code in skb->priority) */ }; /* @@ -361,12 +362,15 @@ struct rxrpc_local { struct list_head new_client_calls; /* Newly created client calls need connection */ spinlock_t client_call_lock; /* Lock for ->new_client_calls */ struct sockaddr_rxrpc srx; /* local address */ - /* Provide a kvec table sufficiently large to manage either a DATA - * packet with a maximum set of jumbo subpackets or a PING ACK padded - * out to 64K with zeropages for PMTUD. - */ - struct kvec kvec[1 + RXRPC_MAX_NR_JUMBO > 3 + 16 ? - 1 + RXRPC_MAX_NR_JUMBO : 3 + 16]; + union { + /* Provide a kvec table sufficiently large to manage either a + * DATA packet with a maximum set of jumbo subpackets or a PING + * ACK padded out to 64K with zeropages for PMTUD. + */ + struct kvec kvec[1 + RXRPC_MAX_NR_JUMBO > 3 + 16 ? + 1 + RXRPC_MAX_NR_JUMBO : 3 + 16]; + struct bio_vec bvec[3 + 16]; + }; }; /* @@ -1250,6 +1254,8 @@ int rxrpc_encap_rcv(struct sock *, struct sk_buff *); void rxrpc_error_report(struct sock *); bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why, s32 abort_code, int err); +bool rxrpc_direct_conn_abort(struct sk_buff *skb, enum rxrpc_abort_reason why, + s32 abort_code, int err); int rxrpc_io_thread(void *data); void rxrpc_post_response(struct rxrpc_connection *conn, struct sk_buff *skb); static inline void rxrpc_wake_up_io_thread(struct rxrpc_local *local) @@ -1380,6 +1386,7 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *, const struct sockaddr_rxrpc *); struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, struct sockaddr_rxrpc *srx, gfp_t gfp); +void rxrpc_assess_MTU_size(struct rxrpc_local *local, struct rxrpc_peer *peer); struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t, enum rxrpc_peer_trace); void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index a4b363b47cca..00982a030744 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -149,6 +149,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, id_in_use: write_unlock(&rx->call_lock); + rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, -EBADSLT); rxrpc_cleanup_call(call); _leave(" = -EBADSLT"); return -EBADSLT; @@ -218,6 +219,7 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) tail = b->call_backlog_tail; while (CIRC_CNT(head, tail, size) > 0) { struct rxrpc_call *call = b->call_backlog[tail]; + rxrpc_see_call(call, rxrpc_call_see_discard); rcu_assign_pointer(call->socket, rx); if (rx->app_ops && rx->app_ops->discard_new_call) { @@ -254,6 +256,9 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, unsigned short call_tail, conn_tail, peer_tail; unsigned short call_count, conn_count; + if (!b) + return NULL; + /* #calls >= #conns >= #peers must hold true. */ call_head = smp_load_acquire(&b->call_backlog_head); call_tail = b->call_backlog_tail; @@ -369,8 +374,8 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local, spin_lock(&rx->incoming_lock); if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED || rx->sk.sk_state == RXRPC_CLOSE) { - rxrpc_direct_abort(skb, rxrpc_abort_shut_down, - RX_INVALID_OPERATION, -ESHUTDOWN); + rxrpc_direct_conn_abort(skb, rxrpc_abort_shut_down, + RX_INVALID_OPERATION, -ESHUTDOWN); goto no_call; } @@ -402,6 +407,7 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local, spin_unlock(&rx->incoming_lock); read_unlock_irq(&local->services_lock); + rxrpc_assess_MTU_size(local, call->peer); if (hlist_unhashed(&call->error_link)) { spin_lock_irq(&call->peer->lock); @@ -416,12 +422,12 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local, unsupported_service: read_unlock_irq(&local->services_lock); - return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered, - RX_INVALID_OPERATION, -EOPNOTSUPP); + return rxrpc_direct_conn_abort(skb, rxrpc_abort_service_not_offered, + RX_INVALID_OPERATION, -EOPNOTSUPP); unsupported_security: read_unlock_irq(&local->services_lock); - return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered, - RX_INVALID_OPERATION, -EKEYREJECTED); + return rxrpc_direct_conn_abort(skb, rxrpc_abort_service_not_offered, + RX_INVALID_OPERATION, -EKEYREJECTED); no_call: spin_unlock(&rx->incoming_lock); read_unlock_irq(&local->services_lock); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 15067ff7b1f2..918f41d97a2f 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -561,7 +561,7 @@ static void rxrpc_cleanup_rx_buffers(struct rxrpc_call *call) void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) { struct rxrpc_connection *conn = call->conn; - bool put = false, putu = false; + bool putu = false; _enter("{%d,%d}", call->debug_id, refcount_read(&call->ref)); @@ -573,23 +573,13 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) rxrpc_put_call_slot(call); - /* Make sure we don't get any more notifications */ + /* Note that at this point, the call may still be on or may have been + * added back on to the socket receive queue. recvmsg() must discard + * released calls. The CALL_RELEASED flag should prevent further + * notifications. + */ spin_lock_irq(&rx->recvmsg_lock); - - if (!list_empty(&call->recvmsg_link)) { - _debug("unlinking once-pending call %p { e=%lx f=%lx }", - call, call->events, call->flags); - list_del(&call->recvmsg_link); - put = true; - } - - /* list_empty() must return false in rxrpc_notify_socket() */ - call->recvmsg_link.next = NULL; - call->recvmsg_link.prev = NULL; - spin_unlock_irq(&rx->recvmsg_lock); - if (put) - rxrpc_put_call(call, rxrpc_call_put_unnotify); write_lock(&rx->call_lock); @@ -638,6 +628,12 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) rxrpc_put_call(call, rxrpc_call_put_release_sock); } + while ((call = list_first_entry_or_null(&rx->recvmsg_q, + struct rxrpc_call, recvmsg_link))) { + list_del_init(&call->recvmsg_link); + rxrpc_put_call(call, rxrpc_call_put_release_recvmsg_q); + } + _leave(""); } diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 27b650d30f4d..e939ecf417c4 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -97,6 +97,20 @@ bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why, return false; } +/* + * Directly produce a connection abort from a packet. + */ +bool rxrpc_direct_conn_abort(struct sk_buff *skb, enum rxrpc_abort_reason why, + s32 abort_code, int err) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + trace_rxrpc_abort(0, why, sp->hdr.cid, 0, sp->hdr.seq, abort_code, err); + skb->mark = RXRPC_SKB_MARK_REJECT_CONN_ABORT; + skb->priority = abort_code; + return false; +} + static bool rxrpc_bad_message(struct sk_buff *skb, enum rxrpc_abort_reason why) { return rxrpc_direct_abort(skb, why, RX_PROTOCOL_ERROR, -EBADMSG); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 0af19bcdc80a..8b5903b6e481 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -814,6 +814,9 @@ void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) __be32 code; int ret, ioc; + if (sp->hdr.type == RXRPC_PACKET_TYPE_ABORT) + return; /* Never abort an abort. */ + rxrpc_see_skb(skb, rxrpc_skb_see_reject); iov[0].iov_base = &whdr; @@ -826,7 +829,13 @@ void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) msg.msg_controllen = 0; msg.msg_flags = 0; - memset(&whdr, 0, sizeof(whdr)); + whdr = (struct rxrpc_wire_header) { + .epoch = htonl(sp->hdr.epoch), + .cid = htonl(sp->hdr.cid), + .callNumber = htonl(sp->hdr.callNumber), + .serviceId = htons(sp->hdr.serviceId), + .flags = ~sp->hdr.flags & RXRPC_CLIENT_INITIATED, + }; switch (skb->mark) { case RXRPC_SKB_MARK_REJECT_BUSY: @@ -834,6 +843,9 @@ void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) size = sizeof(whdr); ioc = 1; break; + case RXRPC_SKB_MARK_REJECT_CONN_ABORT: + whdr.callNumber = 0; + fallthrough; case RXRPC_SKB_MARK_REJECT_ABORT: whdr.type = RXRPC_PACKET_TYPE_ABORT; code = htonl(skb->priority); @@ -847,14 +859,6 @@ void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) if (rxrpc_extract_addr_from_skb(&srx, skb) == 0) { msg.msg_namelen = srx.transport_len; - whdr.epoch = htonl(sp->hdr.epoch); - whdr.cid = htonl(sp->hdr.cid); - whdr.callNumber = htonl(sp->hdr.callNumber); - whdr.serviceId = htons(sp->hdr.serviceId); - whdr.flags = sp->hdr.flags; - whdr.flags ^= RXRPC_CLIENT_INITIATED; - whdr.flags &= RXRPC_CLIENT_INITIATED; - iov_iter_kvec(&msg.msg_iter, WRITE, iov, ioc, size); ret = do_udp_sendmsg(local->socket, &msg, size); if (ret < 0) @@ -924,7 +928,7 @@ void rxrpc_send_response(struct rxrpc_connection *conn, struct sk_buff *response { struct rxrpc_skb_priv *sp = rxrpc_skb(response); struct scatterlist sg[16]; - struct bio_vec bvec[16]; + struct bio_vec *bvec = conn->local->bvec; struct msghdr msg; size_t len = sp->resp.len; __be32 wserial; @@ -938,6 +942,9 @@ void rxrpc_send_response(struct rxrpc_connection *conn, struct sk_buff *response if (ret < 0) goto fail; nr_sg = ret; + ret = -EIO; + if (WARN_ON_ONCE(nr_sg > ARRAY_SIZE(conn->local->bvec))) + goto fail; for (int i = 0; i < nr_sg; i++) bvec_set_page(&bvec[i], sg_page(&sg[i]), sg[i].length, sg[i].offset); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index e2f35e6c04d6..366431b0736c 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -149,8 +149,7 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local, * assess the MTU size for the network interface through which this peer is * reached */ -static void rxrpc_assess_MTU_size(struct rxrpc_local *local, - struct rxrpc_peer *peer) +void rxrpc_assess_MTU_size(struct rxrpc_local *local, struct rxrpc_peer *peer) { struct net *net = local->net; struct dst_entry *dst; @@ -277,8 +276,6 @@ static void rxrpc_init_peer(struct rxrpc_local *local, struct rxrpc_peer *peer, peer->hdrsize += sizeof(struct rxrpc_wire_header); peer->max_data = peer->if_mtu - peer->hdrsize; - - rxrpc_assess_MTU_size(local, peer); } /* @@ -297,6 +294,7 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local, if (peer) { memcpy(&peer->srx, srx, sizeof(*srx)); rxrpc_init_peer(local, peer, hash_key); + rxrpc_assess_MTU_size(local, peer); } _leave(" = %p", peer); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 86a27fb55a1c..7fa7e77f6bb9 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -29,6 +29,10 @@ void rxrpc_notify_socket(struct rxrpc_call *call) if (!list_empty(&call->recvmsg_link)) return; + if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) { + rxrpc_see_call(call, rxrpc_call_see_notify_released); + return; + } rcu_read_lock(); @@ -447,6 +451,16 @@ try_again: goto try_again; } + rxrpc_see_call(call, rxrpc_call_see_recvmsg); + if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) { + rxrpc_see_call(call, rxrpc_call_see_already_released); + list_del_init(&call->recvmsg_link); + spin_unlock_irq(&rx->recvmsg_lock); + release_sock(&rx->sk); + trace_rxrpc_recvmsg(call->debug_id, rxrpc_recvmsg_unqueue, 0); + rxrpc_put_call(call, rxrpc_call_put_recvmsg); + goto try_again; + } if (!(flags & MSG_PEEK)) list_del_init(&call->recvmsg_link); else @@ -470,8 +484,13 @@ try_again: release_sock(&rx->sk); - if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) - BUG(); + if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) { + rxrpc_see_call(call, rxrpc_call_see_already_released); + mutex_unlock(&call->user_mutex); + if (!(flags & MSG_PEEK)) + rxrpc_put_call(call, rxrpc_call_put_recvmsg); + goto try_again; + } ret = rxrpc_recvmsg_user_id(call, msg, flags); if (ret < 0) diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c index 078d91a6b77f..2bfbf2b2bb37 100644 --- a/net/rxrpc/security.c +++ b/net/rxrpc/security.c @@ -140,15 +140,15 @@ const struct rxrpc_security *rxrpc_get_incoming_security(struct rxrpc_sock *rx, sec = rxrpc_security_lookup(sp->hdr.securityIndex); if (!sec) { - rxrpc_direct_abort(skb, rxrpc_abort_unsupported_security, - RX_INVALID_OPERATION, -EKEYREJECTED); + rxrpc_direct_conn_abort(skb, rxrpc_abort_unsupported_security, + RX_INVALID_OPERATION, -EKEYREJECTED); return NULL; } if (sp->hdr.securityIndex != RXRPC_SECURITY_NONE && !rx->securities) { - rxrpc_direct_abort(skb, rxrpc_abort_no_service_key, - sec->no_key_abort, -EKEYREJECTED); + rxrpc_direct_conn_abort(skb, rxrpc_abort_no_service_key, + sec->no_key_abort, -EKEYREJECTED); return NULL; } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index d8a33486c511..d7c767b861a4 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -336,17 +336,22 @@ out: return q; } -static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid) +static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid, + struct netlink_ext_ack *extack) { unsigned long cl; const struct Qdisc_class_ops *cops = p->ops->cl_ops; - if (cops == NULL) - return NULL; + if (cops == NULL) { + NL_SET_ERR_MSG(extack, "Parent qdisc is not classful"); + return ERR_PTR(-EOPNOTSUPP); + } cl = cops->find(p, classid); - if (cl == 0) - return NULL; + if (cl == 0) { + NL_SET_ERR_MSG(extack, "Specified class not found"); + return ERR_PTR(-ENOENT); + } return cops->leaf(p, cl); } @@ -596,16 +601,6 @@ out: qdisc_skb_cb(skb)->pkt_len = pkt_len; } -void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc) -{ - if (!(qdisc->flags & TCQ_F_WARN_NONWC)) { - pr_warn("%s: %s qdisc %X: is non-work-conserving?\n", - txt, qdisc->ops->id, qdisc->handle >> 16); - qdisc->flags |= TCQ_F_WARN_NONWC; - } -} -EXPORT_SYMBOL(qdisc_warn_nonwc); - static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) { struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog, @@ -1490,7 +1485,7 @@ static int __tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified classid"); return -ENOENT; } - q = qdisc_leaf(p, clid); + q = qdisc_leaf(p, clid, extack); } else if (dev_ingress_queue(dev)) { q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping); } @@ -1501,6 +1496,8 @@ static int __tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device"); return -ENOENT; } + if (IS_ERR(q)) + return PTR_ERR(q); if (tcm->tcm_handle && q->handle != tcm->tcm_handle) { NL_SET_ERR_MSG(extack, "Invalid handle"); @@ -1602,7 +1599,9 @@ static int __tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, NL_SET_ERR_MSG(extack, "Failed to find specified qdisc"); return -ENOENT; } - q = qdisc_leaf(p, clid); + q = qdisc_leaf(p, clid, extack); + if (IS_ERR(q)) + return PTR_ERR(q); } else if (dev_ingress_queue_create(dev)) { q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping); } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 5a7745170e84..d8fd35da32a7 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -835,22 +835,6 @@ update_vf(struct hfsc_class *cl, unsigned int len, u64 cur_time) } } -static unsigned int -qdisc_peek_len(struct Qdisc *sch) -{ - struct sk_buff *skb; - unsigned int len; - - skb = sch->ops->peek(sch); - if (unlikely(skb == NULL)) { - qdisc_warn_nonwc("qdisc_peek_len", sch); - return 0; - } - len = qdisc_pkt_len(skb); - - return len; -} - static void hfsc_adjust_levels(struct hfsc_class *cl) { diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 14bf71f57057..c968ea763774 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -821,7 +821,9 @@ static struct htb_class *htb_lookup_leaf(struct htb_prio *hprio, const int prio) u32 *pid; } stk[TC_HTB_MAXDEPTH], *sp = stk; - BUG_ON(!hprio->row.rb_node); + if (unlikely(!hprio->row.rb_node)) + return NULL; + sp->root = hprio->row.rb_node; sp->pptr = &hprio->ptr; sp->pid = &hprio->last_ptr_id; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index bf1282cb22eb..2255355e51d3 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -412,7 +412,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, bool existing = false; struct nlattr *tb[TCA_QFQ_MAX + 1]; struct qfq_aggregate *new_agg = NULL; - u32 weight, lmax, inv_w; + u32 weight, lmax, inv_w, old_weight, old_lmax; int err; int delta_w; @@ -443,12 +443,16 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; - if (cl != NULL && - lmax == cl->agg->lmax && - weight == cl->agg->class_weight) - return 0; /* nothing to change */ + if (cl != NULL) { + sch_tree_lock(sch); + old_weight = cl->agg->class_weight; + old_lmax = cl->agg->lmax; + sch_tree_unlock(sch); + if (lmax == old_lmax && weight == old_weight) + return 0; /* nothing to change */ + } - delta_w = weight - (cl ? cl->agg->class_weight : 0); + delta_w = weight - (cl ? old_weight : 0); if (q->wsum + delta_w > QFQ_MAX_WSUM) { NL_SET_ERR_MSG_FMT_MOD(extack, @@ -532,9 +536,6 @@ destroy_class: static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl) { - struct qfq_sched *q = qdisc_priv(sch); - - qfq_rm_from_agg(q, cl); gen_kill_estimator(&cl->rate_est); qdisc_put(cl->qdisc); kfree(cl); @@ -555,6 +556,7 @@ static int qfq_delete_class(struct Qdisc *sch, unsigned long arg, qdisc_purge_queue(cl->qdisc); qdisc_class_hash_remove(&q->clhash, &cl->common); + qfq_rm_from_agg(q, cl); sch_tree_unlock(sch); @@ -625,6 +627,7 @@ static int qfq_dump_class(struct Qdisc *sch, unsigned long arg, { struct qfq_class *cl = (struct qfq_class *)arg; struct nlattr *nest; + u32 class_weight, lmax; tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle = cl->common.classid; @@ -633,8 +636,13 @@ static int qfq_dump_class(struct Qdisc *sch, unsigned long arg, nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; - if (nla_put_u32(skb, TCA_QFQ_WEIGHT, cl->agg->class_weight) || - nla_put_u32(skb, TCA_QFQ_LMAX, cl->agg->lmax)) + + sch_tree_lock(sch); + class_weight = cl->agg->class_weight; + lmax = cl->agg->lmax; + sch_tree_unlock(sch); + if (nla_put_u32(skb, TCA_QFQ_WEIGHT, class_weight) || + nla_put_u32(skb, TCA_QFQ_LMAX, lmax)) goto nla_put_failure; return nla_nest_end(skb, nest); @@ -651,8 +659,10 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg, memset(&xstats, 0, sizeof(xstats)); + sch_tree_lock(sch); xstats.weight = cl->agg->class_weight; xstats.lmax = cl->agg->lmax; + sch_tree_unlock(sch); if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || @@ -989,7 +999,7 @@ static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg, if (cl->qdisc->q.qlen == 0) /* no more packets, remove from list */ list_del_init(&cl->alist); - else if (cl->deficit < qdisc_pkt_len(cl->qdisc->ops->peek(cl->qdisc))) { + else if (cl->deficit < qdisc_peek_len(cl->qdisc)) { cl->deficit += agg->lmax; list_move_tail(&cl->alist, &agg->active); } @@ -1491,6 +1501,7 @@ static void qfq_destroy_qdisc(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], common.hnode) { + qfq_rm_from_agg(q, cl); qfq_destroy_class(sch, cl); } } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 3760131f1484..1882bab8e00e 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -30,6 +30,10 @@ #include <linux/splice.h> #include <net/sock.h> +#include <net/inet_common.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/ipv6.h> +#endif #include <net/tcp.h> #include <net/smc.h> #include <asm/ioctls.h> @@ -360,6 +364,16 @@ static void smc_destruct(struct sock *sk) return; if (!sock_flag(sk, SOCK_DEAD)) return; + switch (sk->sk_family) { + case AF_INET: + inet_sock_destruct(sk); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + inet6_sock_destruct(sk); + break; +#endif + } } static struct lock_class_key smc_key; diff --git a/net/smc/smc.h b/net/smc/smc.h index 78ae10d06ed2..2c9084963739 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -283,10 +283,10 @@ struct smc_connection { }; struct smc_sock { /* smc sock container */ - struct sock sk; -#if IS_ENABLED(CONFIG_IPV6) - struct ipv6_pinfo *pinet6; -#endif + union { + struct sock sk; + struct inet_sock icsk_inet; + }; struct socket *clcsock; /* internal tcp socket */ void (*clcsk_state_change)(struct sock *sk); /* original stat_change fct. */ diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 8ee0c07d00e9..ffe577bf6b51 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -704,8 +704,10 @@ static void tipc_topsrv_stop(struct net *net) for (id = 0; srv->idr_in_use; id++) { con = idr_find(&srv->conn_idr, id); if (con) { + conn_get(con); spin_unlock_bh(&srv->idr_lock); tipc_conn_close(con); + conn_put(con); spin_lock_bh(&srv->idr_lock); } } diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 65b0da6fdf6a..095cf31bae0b 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -512,9 +512,8 @@ static int tls_strp_read_sock(struct tls_strparser *strp) if (inq < strp->stm.full_len) return tls_strp_read_copy(strp, true); + tls_strp_load_anchor_with_queue(strp, inq); if (!strp->stm.full_len) { - tls_strp_load_anchor_with_queue(strp, inq); - sz = tls_rx_msg_size(strp, strp->anchor); if (sz < 0) { tls_strp_abort_strp(strp, sz); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 2e7a3034e965..1053662725f8 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -407,6 +407,8 @@ EXPORT_SYMBOL_GPL(vsock_enqueue_accept); static bool vsock_use_local_transport(unsigned int remote_cid) { + lockdep_assert_held(&vsock_register_mutex); + if (!transport_local) return false; @@ -464,6 +466,8 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) remote_flags = vsk->remote_addr.svm_flags; + mutex_lock(&vsock_register_mutex); + switch (sk->sk_type) { case SOCK_DGRAM: new_transport = transport_dgram; @@ -479,12 +483,15 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) new_transport = transport_h2g; break; default: - return -ESOCKTNOSUPPORT; + ret = -ESOCKTNOSUPPORT; + goto err; } if (vsk->transport) { - if (vsk->transport == new_transport) - return 0; + if (vsk->transport == new_transport) { + ret = 0; + goto err; + } /* transport->release() must be called with sock lock acquired. * This path can only be taken during vsock_connect(), where we @@ -508,8 +515,16 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) /* We increase the module refcnt to prevent the transport unloading * while there are open sockets assigned to it. */ - if (!new_transport || !try_module_get(new_transport->module)) - return -ENODEV; + if (!new_transport || !try_module_get(new_transport->module)) { + ret = -ENODEV; + goto err; + } + + /* It's safe to release the mutex after a successful try_module_get(). + * Whichever transport `new_transport` points at, it won't go away until + * the last module_put() below or in vsock_deassign_transport(). + */ + mutex_unlock(&vsock_register_mutex); if (sk->sk_type == SOCK_SEQPACKET) { if (!new_transport->seqpacket_allow || @@ -528,12 +543,31 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) vsk->transport = new_transport; return 0; +err: + mutex_unlock(&vsock_register_mutex); + return ret; } EXPORT_SYMBOL_GPL(vsock_assign_transport); +/* + * Provide safe access to static transport_{h2g,g2h,dgram,local} callbacks. + * Otherwise we may race with module removal. Do not use on `vsk->transport`. + */ +static u32 vsock_registered_transport_cid(const struct vsock_transport **transport) +{ + u32 cid = VMADDR_CID_ANY; + + mutex_lock(&vsock_register_mutex); + if (*transport) + cid = (*transport)->get_local_cid(); + mutex_unlock(&vsock_register_mutex); + + return cid; +} + bool vsock_find_cid(unsigned int cid) { - if (transport_g2h && cid == transport_g2h->get_local_cid()) + if (cid == vsock_registered_transport_cid(&transport_g2h)) return true; if (transport_h2g && cid == VMADDR_CID_HOST) @@ -2536,18 +2570,19 @@ static long vsock_dev_do_ioctl(struct file *filp, unsigned int cmd, void __user *ptr) { u32 __user *p = ptr; - u32 cid = VMADDR_CID_ANY; int retval = 0; + u32 cid; switch (cmd) { case IOCTL_VM_SOCKETS_GET_LOCAL_CID: /* To be compatible with the VMCI behavior, we prioritize the * guest CID instead of well-know host CID (VMADDR_CID_HOST). */ - if (transport_g2h) - cid = transport_g2h->get_local_cid(); - else if (transport_h2g) - cid = transport_h2g->get_local_cid(); + cid = vsock_registered_transport_cid(&transport_g2h); + if (cid == VMADDR_CID_ANY) + cid = vsock_registered_transport_cid(&transport_h2g); + if (cid == VMADDR_CID_ANY) + cid = vsock_registered_transport_cid(&transport_local); if (put_user(cid, p) != 0) retval = -EFAULT; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 85f139016da2..50202d170f3a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -229,6 +229,7 @@ static int validate_beacon_head(const struct nlattr *attr, unsigned int len = nla_len(attr); const struct element *elem; const struct ieee80211_mgmt *mgmt = (void *)data; + const struct ieee80211_ext *ext; unsigned int fixedlen, hdrlen; bool s1g_bcn; @@ -237,8 +238,10 @@ static int validate_beacon_head(const struct nlattr *attr, s1g_bcn = ieee80211_is_s1g_beacon(mgmt->frame_control); if (s1g_bcn) { - fixedlen = offsetof(struct ieee80211_ext, - u.s1g_beacon.variable); + ext = (struct ieee80211_ext *)mgmt; + fixedlen = + offsetof(struct ieee80211_ext, u.s1g_beacon.variable) + + ieee80211_s1g_optional_len(ext->frame_control); hdrlen = offsetof(struct ieee80211_ext, u.s1g_beacon); } else { fixedlen = offsetof(struct ieee80211_mgmt, diff --git a/net/wireless/util.c b/net/wireless/util.c index ed868c0f7ca8..1ad5a6bdfd75 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -820,6 +820,52 @@ bool ieee80211_is_valid_amsdu(struct sk_buff *skb, u8 mesh_hdr) } EXPORT_SYMBOL(ieee80211_is_valid_amsdu); + +/* + * Detects if an MSDU frame was maliciously converted into an A-MSDU + * frame by an adversary. This is done by parsing the received frame + * as if it were a regular MSDU, even though the A-MSDU flag is set. + * + * For non-mesh interfaces, detection involves checking whether the + * payload, when interpreted as an MSDU, begins with a valid RFC1042 + * header. This is done by comparing the A-MSDU subheader's destination + * address to the start of the RFC1042 header. + * + * For mesh interfaces, the MSDU includes a 6-byte Mesh Control field + * and an optional variable-length Mesh Address Extension field before + * the RFC1042 header. The position of the RFC1042 header must therefore + * be calculated based on the mesh header length. + * + * Since this function intentionally parses an A-MSDU frame as an MSDU, + * it only assumes that the A-MSDU subframe header is present, and + * beyond this it performs its own bounds checks under the assumption + * that the frame is instead parsed as a non-aggregated MSDU. + */ +static bool +is_amsdu_aggregation_attack(struct ethhdr *eth, struct sk_buff *skb, + enum nl80211_iftype iftype) +{ + int offset; + + /* Non-mesh case can be directly compared */ + if (iftype != NL80211_IFTYPE_MESH_POINT) + return ether_addr_equal(eth->h_dest, rfc1042_header); + + offset = __ieee80211_get_mesh_hdrlen(eth->h_dest[0]); + if (offset == 6) { + /* Mesh case with empty address extension field */ + return ether_addr_equal(eth->h_source, rfc1042_header); + } else if (offset + ETH_ALEN <= skb->len) { + /* Mesh case with non-empty address extension field */ + u8 temp[ETH_ALEN]; + + skb_copy_bits(skb, offset, temp, ETH_ALEN); + return ether_addr_equal(temp, rfc1042_header); + } + + return false; +} + void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, const u8 *addr, enum nl80211_iftype iftype, const unsigned int extra_headroom, @@ -861,8 +907,10 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, /* the last MSDU has no padding */ if (subframe_len > remaining) goto purge; - /* mitigate A-MSDU aggregation injection attacks */ - if (ether_addr_equal(hdr.eth.h_dest, rfc1042_header)) + /* mitigate A-MSDU aggregation injection attacks, to be + * checked when processing first subframe (offset == 0). + */ + if (offset == 0 && is_amsdu_aggregation_attack(&hdr.eth, skb, iftype)) goto purge; offset += sizeof(struct ethhdr); diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 81fd486b5e56..d2819baea414 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -305,7 +305,6 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, return -EINVAL; } - xfrm_set_type_offload(x); if (!x->type_offload) { NL_SET_ERR_MSG(extack, "Type doesn't support offload"); dev_put(dev); diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index cb1e12740c87..330a05286a56 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -875,7 +875,7 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[], return -EINVAL; } - if (p.collect_md) { + if (p.collect_md || xi->p.collect_md) { NL_SET_ERR_MSG(extack, "collect_md can't be changed"); return -EINVAL; } @@ -886,11 +886,6 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[], } else { if (xi->dev != dev) return -EEXIST; - if (xi->p.collect_md) { - NL_SET_ERR_MSG(extack, - "device can't be changed to collect_md"); - return -EINVAL; - } } return xfrmi_update(xi, &p); diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index 907c3ccb440d..43fdc6ed8dd1 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -97,7 +97,7 @@ static int ipcomp_input_done2(struct sk_buff *skb, int err) struct ip_comp_hdr *ipch = ip_comp_hdr(skb); const int plen = skb->len; - skb_reset_transport_header(skb); + skb->transport_header = skb->network_header + sizeof(*ipch); return ipcomp_post_acomp(skb, err, 0) ?: skb->len < (plen + sizeof(ip_comp_hdr)) ? -EINVAL : @@ -313,7 +313,6 @@ void ipcomp_destroy(struct xfrm_state *x) struct ipcomp_data *ipcd = x->data; if (!ipcd) return; - xfrm_state_delete_tunnel(x); ipcomp_free_data(ipcd); kfree(ipcd); } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 77cc418ad69e..97ff756191ba 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -424,11 +424,10 @@ void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, } EXPORT_SYMBOL(xfrm_unregister_type_offload); -void xfrm_set_type_offload(struct xfrm_state *x) +void xfrm_set_type_offload(struct xfrm_state *x, bool try_load) { const struct xfrm_type_offload *type = NULL; struct xfrm_state_afinfo *afinfo; - bool try_load = true; retry: afinfo = xfrm_state_get_afinfo(x->props.family); @@ -593,7 +592,7 @@ void xfrm_state_free(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_free); -static void ___xfrm_state_destroy(struct xfrm_state *x) +static void xfrm_state_gc_destroy(struct xfrm_state *x) { if (x->mode_cbs && x->mode_cbs->destroy_state) x->mode_cbs->destroy_state(x); @@ -607,6 +606,7 @@ static void ___xfrm_state_destroy(struct xfrm_state *x) kfree(x->coaddr); kfree(x->replay_esn); kfree(x->preplay_esn); + xfrm_unset_type_offload(x); if (x->type) { x->type->destructor(x); xfrm_put_type(x->type); @@ -631,7 +631,7 @@ static void xfrm_state_gc_task(struct work_struct *work) synchronize_rcu(); hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) - ___xfrm_state_destroy(x); + xfrm_state_gc_destroy(x); } static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) @@ -780,8 +780,6 @@ void xfrm_dev_state_free(struct xfrm_state *x) struct xfrm_dev_offload *xso = &x->xso; struct net_device *dev = READ_ONCE(xso->dev); - xfrm_unset_type_offload(x); - if (dev && dev->xfrmdev_ops) { spin_lock_bh(&xfrm_state_dev_gc_lock); if (!hlist_unhashed(&x->dev_gclist)) @@ -797,22 +795,18 @@ void xfrm_dev_state_free(struct xfrm_state *x) } #endif -void __xfrm_state_destroy(struct xfrm_state *x, bool sync) +void __xfrm_state_destroy(struct xfrm_state *x) { WARN_ON(x->km.state != XFRM_STATE_DEAD); - if (sync) { - synchronize_rcu(); - ___xfrm_state_destroy(x); - } else { - spin_lock_bh(&xfrm_state_gc_lock); - hlist_add_head(&x->gclist, &xfrm_state_gc_list); - spin_unlock_bh(&xfrm_state_gc_lock); - schedule_work(&xfrm_state_gc_work); - } + spin_lock_bh(&xfrm_state_gc_lock); + hlist_add_head(&x->gclist, &xfrm_state_gc_list); + spin_unlock_bh(&xfrm_state_gc_lock); + schedule_work(&xfrm_state_gc_work); } EXPORT_SYMBOL(__xfrm_state_destroy); +static void xfrm_state_delete_tunnel(struct xfrm_state *x); int __xfrm_state_delete(struct xfrm_state *x) { struct net *net = xs_net(x); @@ -840,6 +834,8 @@ int __xfrm_state_delete(struct xfrm_state *x) xfrm_dev_state_delete(x); + xfrm_state_delete_tunnel(x); + /* All xfrm_state objects are created by xfrm_state_alloc. * The xfrm_state_alloc call gives a reference, and that * is what we are dropping here. @@ -921,7 +917,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool } #endif -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync) +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) { int i, err = 0, cnt = 0; @@ -943,10 +939,7 @@ restart: err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); - if (sync) - xfrm_state_put_sync(x); - else - xfrm_state_put(x); + xfrm_state_put(x); if (!err) cnt++; @@ -1307,14 +1300,8 @@ static void xfrm_hash_grow_check(struct net *net, int have_hash_collision) static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x, const struct flowi *fl, unsigned short family, struct xfrm_state **best, int *acq_in_progress, - int *error) + int *error, unsigned int pcpu_id) { - /* We need the cpu id just as a lookup key, - * we don't require it to be stable. - */ - unsigned int pcpu_id = get_cpu(); - put_cpu(); - /* Resolution logic: * 1. There is a valid state with matching selector. Done. * 2. Valid state with inappropriate selector. Skip. @@ -1381,14 +1368,15 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, /* We need the cpu id just as a lookup key, * we don't require it to be stable. */ - pcpu_id = get_cpu(); - put_cpu(); + pcpu_id = raw_smp_processor_id(); to_put = NULL; sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); rcu_read_lock(); + xfrm_hash_ptrs_get(net, &state_ptrs); + hlist_for_each_entry_rcu(x, &pol->state_cache_list, state_cache) { if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && @@ -1400,7 +1388,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, encap_family, - &best, &acquire_in_progress, &error); + &best, &acquire_in_progress, &error, pcpu_id); } if (best) @@ -1417,7 +1405,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, - &best, &acquire_in_progress, &error); + &best, &acquire_in_progress, &error, pcpu_id); } cached: @@ -1429,8 +1417,6 @@ cached: else if (acquire_in_progress) /* XXX: acquire_in_progress should not happen */ WARN_ON(1); - xfrm_hash_ptrs_get(net, &state_ptrs); - h = __xfrm_dst_hash(daddr, saddr, tmpl->reqid, encap_family, state_ptrs.hmask); hlist_for_each_entry_rcu(x, state_ptrs.bydst + h, bydst) { #ifdef CONFIG_XFRM_OFFLOAD @@ -1460,7 +1446,7 @@ cached: tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, - &best, &acquire_in_progress, &error); + &best, &acquire_in_progress, &error, pcpu_id); } if (best || acquire_in_progress) goto found; @@ -1495,7 +1481,7 @@ cached: tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, - &best, &acquire_in_progress, &error); + &best, &acquire_in_progress, &error, pcpu_id); } found: @@ -3077,20 +3063,17 @@ void xfrm_flush_gc(void) } EXPORT_SYMBOL(xfrm_flush_gc); -/* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */ -void xfrm_state_delete_tunnel(struct xfrm_state *x) +static void xfrm_state_delete_tunnel(struct xfrm_state *x) { if (x->tunnel) { struct xfrm_state *t = x->tunnel; - if (atomic_read(&t->tunnel_users) == 2) + if (atomic_dec_return(&t->tunnel_users) == 1) xfrm_state_delete(t); - atomic_dec(&t->tunnel_users); - xfrm_state_put_sync(t); + xfrm_state_put(t); x->tunnel = NULL; } } -EXPORT_SYMBOL(xfrm_state_delete_tunnel); u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) { @@ -3295,8 +3278,8 @@ void xfrm_state_fini(struct net *net) unsigned int sz; flush_work(&net->xfrm.state_hash_work); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false); flush_work(&xfrm_state_gc_work); - xfrm_state_flush(net, 0, false, true); WARN_ON(!list_empty(&net->xfrm.state_all)); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 59f258daf830..684239018bec 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -977,6 +977,7 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, /* override default values from above */ xfrm_update_ae_params(x, attrs, 0); + xfrm_set_type_offload(x, attrs[XFRMA_OFFLOAD_DEV]); /* configure the hardware if offload is requested */ if (attrs[XFRMA_OFFLOAD_DEV]) { err = xfrm_dev_state_add(net, x, @@ -2634,7 +2635,7 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_usersa_flush *p = nlmsg_data(nlh); int err; - err = xfrm_state_flush(net, p->proto, true, false); + err = xfrm_state_flush(net, p->proto, true); if (err) { if (err == -ESRCH) /* empty table */ return 0; diff --git a/rust/Makefile b/rust/Makefile index 27dec7904c3a..115b63b7d1e3 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -194,6 +194,7 @@ quiet_cmd_rustdoc_test = RUSTDOC T $< RUST_MODFILE=test.rs \ OBJTREE=$(abspath $(objtree)) \ $(RUSTDOC) --test $(rust_common_flags) \ + -Zcrate-attr='feature(used_with_arg)' \ @$(objtree)/include/generated/rustc_cfg \ $(rustc_target_flags) $(rustdoc_test_target_flags) \ $(rustdoc_test_quiet) \ diff --git a/rust/kernel/drm/device.rs b/rust/kernel/drm/device.rs index 624d7a4c83ea..14c1aa402951 100644 --- a/rust/kernel/drm/device.rs +++ b/rust/kernel/drm/device.rs @@ -66,7 +66,7 @@ impl<T: drm::Driver> Device<T> { open: Some(drm::File::<T::File>::open_callback), postclose: Some(drm::File::<T::File>::postclose_callback), unload: None, - release: None, + release: Some(Self::release), master_set: None, master_drop: None, debugfs_init: None, @@ -162,6 +162,16 @@ impl<T: drm::Driver> Device<T> { // SAFETY: `ptr` is valid by the safety requirements of this function. unsafe { &*ptr.cast() } } + + extern "C" fn release(ptr: *mut bindings::drm_device) { + // SAFETY: `ptr` is a valid pointer to a `struct drm_device` and embedded in `Self`. + let this = unsafe { Self::from_drm_device(ptr) }; + + // SAFETY: + // - When `release` runs it is guaranteed that there is no further access to `this`. + // - `this` is valid for dropping. + unsafe { core::ptr::drop_in_place(this) }; + } } impl<T: drm::Driver> Deref for Device<T> { diff --git a/rust/kernel/drm/driver.rs b/rust/kernel/drm/driver.rs index acb638086131..af93d46d03d3 100644 --- a/rust/kernel/drm/driver.rs +++ b/rust/kernel/drm/driver.rs @@ -10,7 +10,6 @@ use crate::{ drm, error::{to_result, Result}, prelude::*, - str::CStr, types::ARef, }; use macros::vtable; diff --git a/rust/kernel/firmware.rs b/rust/kernel/firmware.rs index 2494c96e105f..4fe621f35716 100644 --- a/rust/kernel/firmware.rs +++ b/rust/kernel/firmware.rs @@ -202,7 +202,7 @@ macro_rules! module_firmware { }; #[link_section = ".modinfo"] - #[used] + #[used(compiler)] static __MODULE_FIRMWARE: [u8; $($builder)*::create(__MODULE_FIRMWARE_PREFIX) .build_length()] = $($builder)*::create(__MODULE_FIRMWARE_PREFIX).build(); }; diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index 8d228c237954..21ef202ab0db 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -231,14 +231,14 @@ macro_rules! try_init { ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { $($fields:tt)* }) => { - ::pin_init::try_init!($(&$this in)? $t $(::<$($generics),* $(,)?>)? { + ::pin_init::try_init!($(&$this in)? $t $(::<$($generics),*>)? { $($fields)* }? $crate::error::Error) }; ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { $($fields:tt)* }? $err:ty) => { - ::pin_init::try_init!($(&$this in)? $t $(::<$($generics),* $(,)?>)? { + ::pin_init::try_init!($(&$this in)? $t $(::<$($generics),*>)? { $($fields)* }? $err) }; @@ -291,14 +291,14 @@ macro_rules! try_pin_init { ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { $($fields:tt)* }) => { - ::pin_init::try_pin_init!($(&$this in)? $t $(::<$($generics),* $(,)?>)? { + ::pin_init::try_pin_init!($(&$this in)? $t $(::<$($generics),*>)? { $($fields)* }? $crate::error::Error) }; ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { $($fields:tt)* }? $err:ty) => { - ::pin_init::try_pin_init!($(&$this in)? $t $(::<$($generics),* $(,)?>)? { + ::pin_init::try_pin_init!($(&$this in)? $t $(::<$($generics),*>)? { $($fields)* }? $err) }; diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs index 4b8cdcb21e77..b9e65905e121 100644 --- a/rust/kernel/kunit.rs +++ b/rust/kernel/kunit.rs @@ -302,7 +302,7 @@ macro_rules! kunit_unsafe_test_suite { is_init: false, }; - #[used] + #[used(compiler)] #[allow(unused_unsafe)] #[cfg_attr(not(target_os = "macos"), link_section = ".kunit_test_suites")] static mut KUNIT_TEST_SUITE_ENTRY: *const ::kernel::bindings::kunit_suite = diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 6b4774b2b1c3..e13d6ed88fa6 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -34,6 +34,9 @@ // Expected to become stable. #![feature(arbitrary_self_types)] // +// To be determined. +#![feature(used_with_arg)] +// // `feature(derive_coerce_pointee)` is expected to become stable. Before Rust // 1.84.0, it did not exist, so enable the predecessor features. #![cfg_attr(CONFIG_RUSTC_HAS_COERCE_POINTEE, feature(derive_coerce_pointee))] diff --git a/rust/macros/module.rs b/rust/macros/module.rs index 2ddd2eeb2852..75efc6eeeafc 100644 --- a/rust/macros/module.rs +++ b/rust/macros/module.rs @@ -57,7 +57,7 @@ impl<'a> ModInfoBuilder<'a> { {cfg} #[doc(hidden)] #[cfg_attr(not(target_os = \"macos\"), link_section = \".modinfo\")] - #[used] + #[used(compiler)] pub static __{module}_{counter}: [u8; {length}] = *{string}; ", cfg = if builtin { @@ -249,7 +249,7 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { // key or a new section. For the moment, keep it simple. #[cfg(MODULE)] #[doc(hidden)] - #[used] + #[used(compiler)] static __IS_RUST_MODULE: () = (); static mut __MOD: ::core::mem::MaybeUninit<{type_}> = @@ -273,7 +273,7 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { #[cfg(MODULE)] #[doc(hidden)] - #[used] + #[used(compiler)] #[link_section = \".init.data\"] static __UNIQUE_ID___addressable_init_module: unsafe extern \"C\" fn() -> i32 = init_module; @@ -293,7 +293,7 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { #[cfg(MODULE)] #[doc(hidden)] - #[used] + #[used(compiler)] #[link_section = \".exit.data\"] static __UNIQUE_ID___addressable_cleanup_module: extern \"C\" fn() = cleanup_module; @@ -303,7 +303,7 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { #[cfg(not(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS))] #[doc(hidden)] #[link_section = \"{initcall_section}\"] - #[used] + #[used(compiler)] pub static __{ident}_initcall: extern \"C\" fn() -> ::kernel::ffi::c_int = __{ident}_init; diff --git a/samples/damon/mtier.c b/samples/damon/mtier.c index 36d2cd933f5a..c94254b77fc9 100644 --- a/samples/damon/mtier.c +++ b/samples/damon/mtier.c @@ -164,8 +164,12 @@ static int damon_sample_mtier_enable_store( if (enable == enabled) return 0; - if (enable) - return damon_sample_mtier_start(); + if (enable) { + err = damon_sample_mtier_start(); + if (err) + enable = false; + return err; + } damon_sample_mtier_stop(); return 0; } diff --git a/samples/damon/prcl.c b/samples/damon/prcl.c index 056b1b21a0fe..5597e6a08ab2 100644 --- a/samples/damon/prcl.c +++ b/samples/damon/prcl.c @@ -122,8 +122,12 @@ static int damon_sample_prcl_enable_store( if (enable == enabled) return 0; - if (enable) - return damon_sample_prcl_start(); + if (enable) { + err = damon_sample_prcl_start(); + if (err) + enable = false; + return err; + } damon_sample_prcl_stop(); return 0; } diff --git a/samples/damon/wsse.c b/samples/damon/wsse.c index 11be25803274..e20238a249e7 100644 --- a/samples/damon/wsse.c +++ b/samples/damon/wsse.c @@ -102,8 +102,12 @@ static int damon_sample_wsse_enable_store( if (enable == enabled) return 0; - if (enable) - return damon_sample_wsse_start(); + if (enable) { + err = damon_sample_wsse_start(); + if (err) + enable = false; + return err; + } damon_sample_wsse_stop(); return 0; } diff --git a/scripts/Makefile.build b/scripts/Makefile.build index a6461ea411f7..ba71b27aa363 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -312,10 +312,11 @@ $(obj)/%.lst: $(obj)/%.c FORCE # - Stable since Rust 1.82.0: `feature(asm_const)`, `feature(raw_ref_op)`. # - 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,raw_ref_op +rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,lint_reasons,raw_ref_op,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/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in index fd6bd69c5096..f795302ddfa8 100644 --- a/scripts/gdb/linux/constants.py.in +++ b/scripts/gdb/linux/constants.py.in @@ -20,6 +20,7 @@ #include <linux/of_fdt.h> #include <linux/page_ext.h> #include <linux/radix-tree.h> +#include <linux/maple_tree.h> #include <linux/slab.h> #include <linux/threads.h> #include <linux/vmalloc.h> @@ -93,6 +94,12 @@ LX_GDBPARSED(RADIX_TREE_MAP_SIZE) LX_GDBPARSED(RADIX_TREE_MAP_SHIFT) LX_GDBPARSED(RADIX_TREE_MAP_MASK) +/* linux/maple_tree.h */ +LX_VALUE(MAPLE_NODE_SLOTS) +LX_VALUE(MAPLE_RANGE64_SLOTS) +LX_VALUE(MAPLE_ARANGE64_SLOTS) +LX_GDBPARSED(MAPLE_NODE_MASK) + /* linux/vmalloc.h */ LX_VALUE(VM_IOREMAP) LX_VALUE(VM_ALLOC) diff --git a/scripts/gdb/linux/interrupts.py b/scripts/gdb/linux/interrupts.py index 616a5f26377a..f4f715a8f0e3 100644 --- a/scripts/gdb/linux/interrupts.py +++ b/scripts/gdb/linux/interrupts.py @@ -7,7 +7,7 @@ import gdb from linux import constants from linux import cpus from linux import utils -from linux import radixtree +from linux import mapletree irq_desc_type = utils.CachedType("struct irq_desc") @@ -23,12 +23,12 @@ def irqd_is_level(desc): def show_irq_desc(prec, irq): text = "" - desc = radixtree.lookup(gdb.parse_and_eval("&irq_desc_tree"), irq) + desc = mapletree.mtree_load(gdb.parse_and_eval("&sparse_irqs"), irq) if desc is None: return text - desc = desc.cast(irq_desc_type.get_type()) - if desc is None: + desc = desc.cast(irq_desc_type.get_type().pointer()) + if desc == 0: return text if irq_settings_is_hidden(desc): @@ -110,7 +110,7 @@ def x86_show_mce(prec, var, pfx, desc): pvar = gdb.parse_and_eval(var) text = "%*s: " % (prec, pfx) for cpu in cpus.each_online_cpu(): - text += "%10u " % (cpus.per_cpu(pvar, cpu)) + text += "%10u " % (cpus.per_cpu(pvar, cpu).dereference()) text += " %s\n" % (desc) return text @@ -142,7 +142,7 @@ def x86_show_interupts(prec): if constants.LX_CONFIG_X86_MCE: text += x86_show_mce(prec, "&mce_exception_count", "MCE", "Machine check exceptions") - text == x86_show_mce(prec, "&mce_poll_count", "MCP", "Machine check polls") + text += x86_show_mce(prec, "&mce_poll_count", "MCP", "Machine check polls") text += show_irq_err_count(prec) @@ -221,8 +221,8 @@ class LxInterruptList(gdb.Command): gdb.write("CPU%-8d" % cpu) gdb.write("\n") - if utils.gdb_eval_or_none("&irq_desc_tree") is None: - return + if utils.gdb_eval_or_none("&sparse_irqs") is None: + raise gdb.GdbError("Unable to find the sparse IRQ tree, is CONFIG_SPARSE_IRQ enabled?") for irq in range(nr_irqs): gdb.write(show_irq_desc(prec, irq)) diff --git a/scripts/gdb/linux/mapletree.py b/scripts/gdb/linux/mapletree.py new file mode 100644 index 000000000000..d52d51c0a03f --- /dev/null +++ b/scripts/gdb/linux/mapletree.py @@ -0,0 +1,252 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Maple tree helpers +# +# Copyright (c) 2025 Broadcom +# +# Authors: +# Florian Fainelli <florian.fainelli@broadcom.com> + +import gdb + +from linux import utils +from linux import constants +from linux import xarray + +maple_tree_root_type = utils.CachedType("struct maple_tree") +maple_node_type = utils.CachedType("struct maple_node") +maple_enode_type = utils.CachedType("void") + +maple_dense = 0 +maple_leaf_64 = 1 +maple_range_64 = 2 +maple_arange_64 = 3 + +class Mas(object): + ma_active = 0 + ma_start = 1 + ma_root = 2 + ma_none = 3 + ma_pause = 4 + ma_overflow = 5 + ma_underflow = 6 + ma_error = 7 + + def __init__(self, mt, first, end): + if mt.type == maple_tree_root_type.get_type().pointer(): + self.tree = mt.dereference() + elif mt.type != maple_tree_root_type.get_type(): + raise gdb.GdbError("must be {} not {}" + .format(maple_tree_root_type.get_type().pointer(), mt.type)) + self.tree = mt + self.index = first + self.last = end + self.node = None + self.status = self.ma_start + self.min = 0 + self.max = -1 + + def is_start(self): + # mas_is_start() + return self.status == self.ma_start + + def is_ptr(self): + # mas_is_ptr() + return self.status == self.ma_root + + def is_none(self): + # mas_is_none() + return self.status == self.ma_none + + def root(self): + # mas_root() + return self.tree['ma_root'].cast(maple_enode_type.get_type().pointer()) + + def start(self): + # mas_start() + if self.is_start() is False: + return None + + self.min = 0 + self.max = ~0 + + while True: + self.depth = 0 + root = self.root() + if xarray.xa_is_node(root): + self.depth = 0 + self.status = self.ma_active + self.node = mte_safe_root(root) + self.offset = 0 + if mte_dead_node(self.node) is True: + continue + + return None + + self.node = None + # Empty tree + if root is None: + self.status = self.ma_none + self.offset = constants.LX_MAPLE_NODE_SLOTS + return None + + # Single entry tree + self.status = self.ma_root + self.offset = constants.LX_MAPLE_NODE_SLOTS + + if self.index != 0: + return None + + return root + + return None + + def reset(self): + # mas_reset() + self.status = self.ma_start + self.node = None + +def mte_safe_root(node): + if node.type != maple_enode_type.get_type().pointer(): + raise gdb.GdbError("{} must be {} not {}" + .format(mte_safe_root.__name__, maple_enode_type.get_type().pointer(), node.type)) + ulong_type = utils.get_ulong_type() + indirect_ptr = node.cast(ulong_type) & ~0x2 + val = indirect_ptr.cast(maple_enode_type.get_type().pointer()) + return val + +def mte_node_type(entry): + ulong_type = utils.get_ulong_type() + val = None + if entry.type == maple_enode_type.get_type().pointer(): + val = entry.cast(ulong_type) + elif entry.type == ulong_type: + val = entry + else: + raise gdb.GdbError("{} must be {} not {}" + .format(mte_node_type.__name__, maple_enode_type.get_type().pointer(), entry.type)) + return (val >> 0x3) & 0xf + +def ma_dead_node(node): + if node.type != maple_node_type.get_type().pointer(): + raise gdb.GdbError("{} must be {} not {}" + .format(ma_dead_node.__name__, maple_node_type.get_type().pointer(), node.type)) + ulong_type = utils.get_ulong_type() + parent = node['parent'] + indirect_ptr = node['parent'].cast(ulong_type) & ~constants.LX_MAPLE_NODE_MASK + return indirect_ptr == node + +def mte_to_node(enode): + ulong_type = utils.get_ulong_type() + if enode.type == maple_enode_type.get_type().pointer(): + indirect_ptr = enode.cast(ulong_type) + elif enode.type == ulong_type: + indirect_ptr = enode + else: + raise gdb.GdbError("{} must be {} not {}" + .format(mte_to_node.__name__, maple_enode_type.get_type().pointer(), enode.type)) + indirect_ptr = indirect_ptr & ~constants.LX_MAPLE_NODE_MASK + return indirect_ptr.cast(maple_node_type.get_type().pointer()) + +def mte_dead_node(enode): + if enode.type != maple_enode_type.get_type().pointer(): + raise gdb.GdbError("{} must be {} not {}" + .format(mte_dead_node.__name__, maple_enode_type.get_type().pointer(), enode.type)) + node = mte_to_node(enode) + return ma_dead_node(node) + +def ma_is_leaf(tp): + result = tp < maple_range_64 + return tp < maple_range_64 + +def mt_pivots(t): + if t == maple_dense: + return 0 + elif t == maple_leaf_64 or t == maple_range_64: + return constants.LX_MAPLE_RANGE64_SLOTS - 1 + elif t == maple_arange_64: + return constants.LX_MAPLE_ARANGE64_SLOTS - 1 + +def ma_pivots(node, t): + if node.type != maple_node_type.get_type().pointer(): + raise gdb.GdbError("{}: must be {} not {}" + .format(ma_pivots.__name__, maple_node_type.get_type().pointer(), node.type)) + if t == maple_arange_64: + return node['ma64']['pivot'] + elif t == maple_leaf_64 or t == maple_range_64: + return node['mr64']['pivot'] + else: + return None + +def ma_slots(node, tp): + if node.type != maple_node_type.get_type().pointer(): + raise gdb.GdbError("{}: must be {} not {}" + .format(ma_slots.__name__, maple_node_type.get_type().pointer(), node.type)) + if tp == maple_arange_64: + return node['ma64']['slot'] + elif tp == maple_range_64 or tp == maple_leaf_64: + return node['mr64']['slot'] + elif tp == maple_dense: + return node['slot'] + else: + return None + +def mt_slot(mt, slots, offset): + ulong_type = utils.get_ulong_type() + return slots[offset].cast(ulong_type) + +def mtree_lookup_walk(mas): + ulong_type = utils.get_ulong_type() + n = mas.node + + while True: + node = mte_to_node(n) + tp = mte_node_type(n) + pivots = ma_pivots(node, tp) + end = mt_pivots(tp) + offset = 0 + while True: + if pivots[offset] >= mas.index: + break + if offset >= end: + break + offset += 1 + + slots = ma_slots(node, tp) + n = mt_slot(mas.tree, slots, offset) + if ma_dead_node(node) is True: + mas.reset() + return None + break + + if ma_is_leaf(tp) is True: + break + + return n + +def mtree_load(mt, index): + ulong_type = utils.get_ulong_type() + # MT_STATE(...) + mas = Mas(mt, index, index) + entry = None + + while True: + entry = mas.start() + if mas.is_none(): + return None + + if mas.is_ptr(): + if index != 0: + entry = None + return entry + + entry = mtree_lookup_walk(mas) + if entry is None and mas.is_start(): + continue + else: + break + + if xarray.xa_is_zero(entry): + return None + + return entry diff --git a/scripts/gdb/linux/vfs.py b/scripts/gdb/linux/vfs.py index b5fbb18ccb77..9e921b645a68 100644 --- a/scripts/gdb/linux/vfs.py +++ b/scripts/gdb/linux/vfs.py @@ -22,7 +22,7 @@ def dentry_name(d): if parent == d or parent == 0: return "" p = dentry_name(d['d_parent']) + "/" - return p + d['d_shortname']['string'].string() + return p + d['d_name']['name'].string() class DentryName(gdb.Function): """Return string of the full path of a dentry. diff --git a/scripts/gdb/linux/xarray.py b/scripts/gdb/linux/xarray.py new file mode 100644 index 000000000000..f4477b5def75 --- /dev/null +++ b/scripts/gdb/linux/xarray.py @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Xarray helpers +# +# Copyright (c) 2025 Broadcom +# +# Authors: +# Florian Fainelli <florian.fainelli@broadcom.com> + +import gdb + +from linux import utils +from linux import constants + +def xa_is_internal(entry): + ulong_type = utils.get_ulong_type() + return ((entry.cast(ulong_type) & 3) == 2) + +def xa_mk_internal(v): + return ((v << 2) | 2) + +def xa_is_zero(entry): + ulong_type = utils.get_ulong_type() + return entry.cast(ulong_type) == xa_mk_internal(257) + +def xa_is_node(entry): + ulong_type = utils.get_ulong_type() + return xa_is_internal(entry) and (entry.cast(ulong_type) > 4096) diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index 840bb9cfe789..a66f258cafaa 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -1269,62 +1269,62 @@ static long snd_compr_ioctl(struct file *f, unsigned int cmd, unsigned long arg) stream = &data->stream; guard(mutex)(&stream->device->lock); - switch (_IOC_NR(cmd)) { - case _IOC_NR(SNDRV_COMPRESS_IOCTL_VERSION): + switch (cmd) { + case SNDRV_COMPRESS_IOCTL_VERSION: return put_user(SNDRV_COMPRESS_VERSION, (int __user *)arg) ? -EFAULT : 0; - case _IOC_NR(SNDRV_COMPRESS_GET_CAPS): + case SNDRV_COMPRESS_GET_CAPS: return snd_compr_get_caps(stream, arg); #ifndef COMPR_CODEC_CAPS_OVERFLOW - case _IOC_NR(SNDRV_COMPRESS_GET_CODEC_CAPS): + case SNDRV_COMPRESS_GET_CODEC_CAPS: return snd_compr_get_codec_caps(stream, arg); #endif - case _IOC_NR(SNDRV_COMPRESS_SET_PARAMS): + case SNDRV_COMPRESS_SET_PARAMS: return snd_compr_set_params(stream, arg); - case _IOC_NR(SNDRV_COMPRESS_GET_PARAMS): + case SNDRV_COMPRESS_GET_PARAMS: return snd_compr_get_params(stream, arg); - case _IOC_NR(SNDRV_COMPRESS_SET_METADATA): + case SNDRV_COMPRESS_SET_METADATA: return snd_compr_set_metadata(stream, arg); - case _IOC_NR(SNDRV_COMPRESS_GET_METADATA): + case SNDRV_COMPRESS_GET_METADATA: return snd_compr_get_metadata(stream, arg); } if (stream->direction == SND_COMPRESS_ACCEL) { #if IS_ENABLED(CONFIG_SND_COMPRESS_ACCEL) - switch (_IOC_NR(cmd)) { - case _IOC_NR(SNDRV_COMPRESS_TASK_CREATE): + switch (cmd) { + case SNDRV_COMPRESS_TASK_CREATE: return snd_compr_task_create(stream, arg); - case _IOC_NR(SNDRV_COMPRESS_TASK_FREE): + case SNDRV_COMPRESS_TASK_FREE: return snd_compr_task_seq(stream, arg, snd_compr_task_free_one); - case _IOC_NR(SNDRV_COMPRESS_TASK_START): + case SNDRV_COMPRESS_TASK_START: return snd_compr_task_start_ioctl(stream, arg); - case _IOC_NR(SNDRV_COMPRESS_TASK_STOP): + case SNDRV_COMPRESS_TASK_STOP: return snd_compr_task_seq(stream, arg, snd_compr_task_stop_one); - case _IOC_NR(SNDRV_COMPRESS_TASK_STATUS): + case SNDRV_COMPRESS_TASK_STATUS: return snd_compr_task_status_ioctl(stream, arg); } #endif return -ENOTTY; } - switch (_IOC_NR(cmd)) { - case _IOC_NR(SNDRV_COMPRESS_TSTAMP): + switch (cmd) { + case SNDRV_COMPRESS_TSTAMP: return snd_compr_tstamp(stream, arg); - case _IOC_NR(SNDRV_COMPRESS_AVAIL): + case SNDRV_COMPRESS_AVAIL: return snd_compr_ioctl_avail(stream, arg); - case _IOC_NR(SNDRV_COMPRESS_PAUSE): + case SNDRV_COMPRESS_PAUSE: return snd_compr_pause(stream); - case _IOC_NR(SNDRV_COMPRESS_RESUME): + case SNDRV_COMPRESS_RESUME: return snd_compr_resume(stream); - case _IOC_NR(SNDRV_COMPRESS_START): + case SNDRV_COMPRESS_START: return snd_compr_start(stream); - case _IOC_NR(SNDRV_COMPRESS_STOP): + case SNDRV_COMPRESS_STOP: return snd_compr_stop(stream); - case _IOC_NR(SNDRV_COMPRESS_DRAIN): + case SNDRV_COMPRESS_DRAIN: return snd_compr_drain(stream); - case _IOC_NR(SNDRV_COMPRESS_PARTIAL_DRAIN): + case SNDRV_COMPRESS_PARTIAL_DRAIN: return snd_compr_partial_drain(stream); - case _IOC_NR(SNDRV_COMPRESS_NEXT_TRACK): + case SNDRV_COMPRESS_NEXT_TRACK: return snd_compr_next_track(stream); } diff --git a/sound/isa/ad1816a/ad1816a.c b/sound/isa/ad1816a/ad1816a.c index 99006dc4777e..5c9e2d41d900 100644 --- a/sound/isa/ad1816a/ad1816a.c +++ b/sound/isa/ad1816a/ad1816a.c @@ -98,7 +98,7 @@ static int snd_card_ad1816a_pnp(int dev, struct pnp_card_link *card, pdev = pnp_request_card_device(card, id->devs[1].id, NULL); if (pdev == NULL) { mpu_port[dev] = -1; - dev_warn(&pdev->dev, "MPU401 device busy, skipping.\n"); + pr_warn("MPU401 device busy, skipping.\n"); return 0; } diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c index 3f2fd32f4ad9..886c53184fec 100644 --- a/sound/pci/hda/cs35l56_hda.c +++ b/sound/pci/hda/cs35l56_hda.c @@ -873,6 +873,52 @@ static int cs35l56_hda_system_resume(struct device *dev) return 0; } +static int cs35l56_hda_fixup_yoga9(struct cs35l56_hda *cs35l56, int *bus_addr) +{ + /* The cirrus,dev-index property has the wrong values */ + switch (*bus_addr) { + case 0x30: + cs35l56->index = 1; + return 0; + case 0x31: + cs35l56->index = 0; + return 0; + default: + /* There is a pseudo-address for broadcast to both amps - ignore it */ + dev_dbg(cs35l56->base.dev, "Ignoring I2C address %#x\n", *bus_addr); + return 0; + } +} + +static const struct { + const char *sub; + int (*fixup_fn)(struct cs35l56_hda *cs35l56, int *bus_addr); +} cs35l56_hda_fixups[] = { + { + .sub = "17AA390B", /* Lenovo Yoga Book 9i GenX */ + .fixup_fn = cs35l56_hda_fixup_yoga9, + }, +}; + +static int cs35l56_hda_apply_platform_fixups(struct cs35l56_hda *cs35l56, const char *sub, + int *bus_addr) +{ + int i; + + if (IS_ERR(sub)) + return 0; + + for (i = 0; i < ARRAY_SIZE(cs35l56_hda_fixups); i++) { + if (strcasecmp(cs35l56_hda_fixups[i].sub, sub) == 0) { + dev_dbg(cs35l56->base.dev, "Applying fixup for %s\n", + cs35l56_hda_fixups[i].sub); + return (cs35l56_hda_fixups[i].fixup_fn)(cs35l56, bus_addr); + } + } + + return 0; +} + static int cs35l56_hda_read_acpi(struct cs35l56_hda *cs35l56, int hid, int id) { u32 values[HDA_MAX_COMPONENTS]; @@ -897,39 +943,47 @@ static int cs35l56_hda_read_acpi(struct cs35l56_hda *cs35l56, int hid, int id) ACPI_COMPANION_SET(cs35l56->base.dev, adev); } - property = "cirrus,dev-index"; - ret = device_property_count_u32(cs35l56->base.dev, property); - if (ret <= 0) - goto err; - - if (ret > ARRAY_SIZE(values)) { - ret = -EINVAL; - goto err; - } - nval = ret; + /* Initialize things that could be overwritten by a fixup */ + cs35l56->index = -1; - ret = device_property_read_u32_array(cs35l56->base.dev, property, values, nval); + sub = acpi_get_subsystem_id(ACPI_HANDLE(cs35l56->base.dev)); + ret = cs35l56_hda_apply_platform_fixups(cs35l56, sub, &id); if (ret) - goto err; + return ret; - cs35l56->index = -1; - for (i = 0; i < nval; i++) { - if (values[i] == id) { - cs35l56->index = i; - break; - } - } - /* - * It's not an error for the ID to be missing: for I2C there can be - * an alias address that is not a real device. So reject silently. - */ if (cs35l56->index == -1) { - dev_dbg(cs35l56->base.dev, "No index found in %s\n", property); - ret = -ENODEV; - goto err; - } + property = "cirrus,dev-index"; + ret = device_property_count_u32(cs35l56->base.dev, property); + if (ret <= 0) + goto err; - sub = acpi_get_subsystem_id(ACPI_HANDLE(cs35l56->base.dev)); + if (ret > ARRAY_SIZE(values)) { + ret = -EINVAL; + goto err; + } + nval = ret; + + ret = device_property_read_u32_array(cs35l56->base.dev, property, values, nval); + if (ret) + goto err; + + for (i = 0; i < nval; i++) { + if (values[i] == id) { + cs35l56->index = i; + break; + } + } + + /* + * It's not an error for the ID to be missing: for I2C there can be + * an alias address that is not a real device. So reject silently. + */ + if (cs35l56->index == -1) { + dev_dbg(cs35l56->base.dev, "No index found in %s\n", property); + ret = -ENODEV; + goto err; + } + } if (IS_ERR(sub)) { dev_info(cs35l56->base.dev, diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 08308231b4ed..9a7793eb16e9 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4551,7 +4551,9 @@ HDA_CODEC_ENTRY(0x10de002e, "Tegra186 HDMI/DP1", patch_tegra_hdmi), HDA_CODEC_ENTRY(0x10de002f, "Tegra194 HDMI/DP2", patch_tegra_hdmi), HDA_CODEC_ENTRY(0x10de0030, "Tegra194 HDMI/DP3", patch_tegra_hdmi), HDA_CODEC_ENTRY(0x10de0031, "Tegra234 HDMI/DP", patch_tegra234_hdmi), +HDA_CODEC_ENTRY(0x10de0033, "SoC 33 HDMI/DP", patch_tegra234_hdmi), HDA_CODEC_ENTRY(0x10de0034, "Tegra264 HDMI/DP", patch_tegra234_hdmi), +HDA_CODEC_ENTRY(0x10de0035, "SoC 35 HDMI/DP", patch_tegra234_hdmi), HDA_CODEC_ENTRY(0x10de0040, "GPU 40 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0041, "GPU 41 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0042, "GPU 42 HDMI/DP", patch_nvhdmi), @@ -4590,15 +4592,32 @@ HDA_CODEC_ENTRY(0x10de0097, "GPU 97 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0098, "GPU 98 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0099, "GPU 99 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009a, "GPU 9a HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de009b, "GPU 9b HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de009c, "GPU 9c HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009d, "GPU 9d HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009e, "GPU 9e HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009f, "GPU 9f HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a0, "GPU a0 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a1, "GPU a1 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a3, "GPU a3 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a4, "GPU a4 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a5, "GPU a5 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a6, "GPU a6 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a7, "GPU a7 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a8, "GPU a8 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a9, "GPU a9 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00aa, "GPU aa HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00ab, "GPU ab HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00ad, "GPU ad HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00ae, "GPU ae HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00af, "GPU af HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00b0, "GPU b0 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00b1, "GPU b1 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00c0, "GPU c0 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00c1, "GPU c1 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00c3, "GPU c3 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00c4, "GPU c4 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00c5, "GPU c5 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x10de8067, "MCP67/68 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x67663d82, "Arise 82 HDMI/DP", patch_gf_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 5d6d01ecfee2..2627e2f49316 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4753,7 +4753,7 @@ static void alc245_fixup_hp_mute_led_v1_coefbit(struct hda_codec *codec, if (action == HDA_FIXUP_ACT_PRE_PROBE) { spec->mute_led_polarity = 0; spec->mute_led_coef.idx = 0x0b; - spec->mute_led_coef.mask = 1 << 3; + spec->mute_led_coef.mask = 3 << 2; spec->mute_led_coef.on = 1 << 3; spec->mute_led_coef.off = 0; snd_hda_gen_add_mute_led_cdev(codec, coef_mute_led_set); @@ -7497,6 +7497,9 @@ static void alc287_fixup_yoga9_14iap7_bass_spk_pin(struct hda_codec *codec, }; struct alc_spec *spec = codec->spec; + /* Support Audio mute LED and Mic mute LED on keyboard */ + hda_fixup_ideapad_acpi(codec, fix, action); + switch (action) { case HDA_FIXUP_ACT_PRE_PROBE: snd_hda_apply_pincfgs(codec, pincfgs); @@ -10691,6 +10694,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8788, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x87b7, "HP Laptop 14-fq0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x87cc, "HP Pavilion 15-eg0xxx", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87d3, "HP Laptop 15-gw0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x87df, "HP ProBook 430 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87e5, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), @@ -10769,6 +10773,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8a2e, "HP Envy 16", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8a30, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8a31, "HP Envy 15", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8a4f, "HP Victus 15-fa0xxx (MB 8A4F)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a6e, "HP EDNA 360", ALC287_FIXUP_CS35L41_I2C_4), SND_PCI_QUIRK(0x103c, 0x8a74, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8a78, "HP Dev One", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), @@ -10814,6 +10819,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b97, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8bb3, "HP Slim OMEN", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8bb4, "HP Slim OMEN", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8bbe, "HP Victus 16-r0xxx (MB 8BBE)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8bc8, "HP Victus 15-fa1xxx", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8bcd, "HP Omen 16-xd0xxx", ALC245_FIXUP_HP_MUTE_LED_V1_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8bdd, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2), @@ -10881,6 +10887,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8ce0, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8d01, "HP ZBook Power 14 G12", ALC285_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8d07, "HP Victus 15-fb2xxx (MB 8D07)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8d18, "HP EliteStudio 8 AIO", ALC274_FIXUP_HP_AIO_BIND_DACS), SND_PCI_QUIRK(0x103c, 0x8d84, "HP EliteBook X G1i", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8d85, "HP EliteBook 14 G12", ALC285_FIXUP_HP_GPIO_LED), @@ -11005,6 +11012,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW), SND_PCI_QUIRK(0x1043, 0x1a63, "ASUS UX3405MA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1a83, "ASUS UM5302LA", ALC294_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x1043, 0x1a8e, "ASUS G712LWS", ALC294_FIXUP_LENOVO_MIC_LOCATION), SND_PCI_QUIRK(0x1043, 0x1a8f, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B), SND_PCI_QUIRK(0x1043, 0x1b13, "ASUS U41SV/GA403U", ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC), @@ -11040,6 +11048,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1e63, "ASUS H7606W", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1), SND_PCI_QUIRK(0x1043, 0x1e83, "ASUS GA605W", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1), SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401), + 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), SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2), @@ -11424,6 +11433,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x2782, 0x0228, "Infinix ZERO BOOK 13", ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13), SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO), SND_PCI_QUIRK(0x2782, 0x1407, "Positivo P15X", ALC269_FIXUP_POSITIVO_P15X_HEADSET_MIC), + SND_PCI_QUIRK(0x2782, 0x1409, "Positivo K116J", ALC269_FIXUP_POSITIVO_P15X_HEADSET_MIC), SND_PCI_QUIRK(0x2782, 0x1701, "Infinix Y4 Max", ALC269VC_FIXUP_INFINIX_Y4_MAX), SND_PCI_QUIRK(0x2782, 0x1705, "MEDION E15433", ALC269VC_FIXUP_INFINIX_Y4_MAX), SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME), diff --git a/sound/pci/hda/tas2781_hda.c b/sound/pci/hda/tas2781_hda.c index 5f1d4b3e9688..34217ce9f28e 100644 --- a/sound/pci/hda/tas2781_hda.c +++ b/sound/pci/hda/tas2781_hda.c @@ -44,7 +44,7 @@ static void tas2781_apply_calib(struct tasdevice_priv *p) TASDEVICE_REG(0, 0x13, 0x70), TASDEVICE_REG(0, 0x18, 0x7c), }; - unsigned int crc, oft; + unsigned int crc, oft, node_num; unsigned char *buf; int i, j, k, l; @@ -80,8 +80,9 @@ static void tas2781_apply_calib(struct tasdevice_priv *p) dev_err(p->dev, "%s: CRC error\n", __func__); return; } + node_num = tmp_val[1]; - for (j = 0, k = 0; j < tmp_val[1]; j++) { + for (j = 0, k = 0; j < node_num; j++) { oft = j * 6 + 3; if (tmp_val[oft] == TASDEV_UEFI_CALI_REG_ADDR_FLG) { for (i = 0; i < TASDEV_CALIB_N; i++) { @@ -99,8 +100,9 @@ static void tas2781_apply_calib(struct tasdevice_priv *p) } data[l] = k; + oft++; for (i = 0; i < TASDEV_CALIB_N * 4; i++) - data[l + i] = data[4 * oft + i]; + data[l + i + 1] = data[4 * oft + i]; k++; } } diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 97e340140d0c..f210a253da9f 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -420,6 +420,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "M6501RM"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "E1404FA"), } }, @@ -539,6 +546,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "Victus by HP Gaming Laptop 15-fb1xxx"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "HP"), DMI_MATCH(DMI_PRODUCT_NAME, "Victus by HP Gaming Laptop 15-fb2xxx"), } }, @@ -588,6 +602,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "HP"), + DMI_MATCH(DMI_BOARD_NAME, "8A81"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "HP"), DMI_MATCH(DMI_BOARD_NAME, "8B27"), } }, diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c index d0831d609584..ba653f6ccfae 100644 --- a/sound/soc/codecs/cs35l56-shared.c +++ b/sound/soc/codecs/cs35l56-shared.c @@ -980,7 +980,7 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base) break; default: dev_err(cs35l56_base->dev, "Unknown device %x\n", devid); - return ret; + return -ENODEV; } cs35l56_base->type = devid & 0xFF; diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index 08df87238eee..29a403526cd9 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -82,6 +82,7 @@ static const struct reg_sequence rt5650_init_list[] = { {0xf6, 0x0100}, {RT5645_PWR_ANLG1, 0x02}, {RT5645_IL_CMD3, 0x6728}, + {RT5645_PR_BASE + 0x3a, 0x0000}, }; static const struct reg_default rt5645_reg[] = { diff --git a/sound/soc/codecs/rt5660.c b/sound/soc/codecs/rt5660.c index 82b92e83be4c..44c3a3b92f98 100644 --- a/sound/soc/codecs/rt5660.c +++ b/sound/soc/codecs/rt5660.c @@ -1315,14 +1315,17 @@ static int rt5660_i2c_probe(struct i2c_client *i2c) regmap_update_bits(rt5660->regmap, RT5660_GPIO_CTRL1, RT5660_GP1_PIN_MASK, RT5660_GP1_PIN_DMIC1_SCL); - if (rt5660->pdata.dmic1_data_pin == RT5660_DMIC1_DATA_GPIO2) + if (rt5660->pdata.dmic1_data_pin == RT5660_DMIC1_DATA_GPIO2) { regmap_update_bits(rt5660->regmap, RT5660_DMIC_CTRL1, RT5660_SEL_DMIC_DATA_MASK, RT5660_SEL_DMIC_DATA_GPIO2); - else if (rt5660->pdata.dmic1_data_pin == RT5660_DMIC1_DATA_IN1P) + regmap_update_bits(rt5660->regmap, RT5660_GPIO_CTRL1, + RT5660_GP2_PIN_MASK, RT5660_GP2_PIN_DMIC1_SDA); + } else if (rt5660->pdata.dmic1_data_pin == RT5660_DMIC1_DATA_IN1P) { regmap_update_bits(rt5660->regmap, RT5660_DMIC_CTRL1, RT5660_SEL_DMIC_DATA_MASK, RT5660_SEL_DMIC_DATA_IN1P); + } } return devm_snd_soc_register_component(&i2c->dev, diff --git a/sound/soc/fsl/fsl_asrc.c b/sound/soc/fsl/fsl_asrc.c index 677529916dc0..745532ccbdba 100644 --- a/sound/soc/fsl/fsl_asrc.c +++ b/sound/soc/fsl/fsl_asrc.c @@ -517,7 +517,8 @@ static int fsl_asrc_config_pair(struct fsl_asrc_pair *pair, bool use_ideal_rate) regmap_update_bits(asrc->regmap, REG_ASRCTR, ASRCTR_ATSi_MASK(index), ASRCTR_ATS(index)); regmap_update_bits(asrc->regmap, REG_ASRCTR, - ASRCTR_USRi_MASK(index), 0); + ASRCTR_IDRi_MASK(index) | ASRCTR_USRi_MASK(index), + ASRCTR_USR(index)); /* Set the input and output clock sources */ regmap_update_bits(asrc->regmap, REG_ASRCSR, diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index af1a168d35e3..50af6b725670 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -803,13 +803,15 @@ static void fsl_sai_config_disable(struct fsl_sai *sai, int dir) * anymore. Add software reset to fix this issue. * This is a hardware bug, and will be fix in the * next sai version. + * + * In consumer mode, this can happen even after a + * single open/close, especially if both tx and rx + * are running concurrently. */ - if (!sai->is_consumer_mode[tx]) { - /* Software Reset */ - regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs), FSL_SAI_CSR_SR); - /* Clear SR bit to finish the reset */ - regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs), 0); - } + /* Software Reset */ + regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs), FSL_SAI_CSR_SR); + /* Clear SR bit to finish the reset */ + regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs), 0); } static int fsl_sai_trigger(struct snd_pcm_substream *substream, int cmd, diff --git a/sound/soc/intel/avs/pcm.c b/sound/soc/intel/avs/pcm.c index ccf90428126d..0efe490024b0 100644 --- a/sound/soc/intel/avs/pcm.c +++ b/sound/soc/intel/avs/pcm.c @@ -1570,11 +1570,13 @@ static void avs_component_hda_unregister_dais(struct snd_soc_component *componen { struct snd_soc_acpi_mach *mach; struct snd_soc_dai *dai, *save; + struct avs_mach_pdata *pdata; struct hda_codec *codec; char name[32]; mach = dev_get_platdata(component->card->dev); - codec = mach->pdata; + pdata = mach->pdata; + codec = pdata->codec; snprintf(name, sizeof(name), "%s-cpu", dev_name(&codec->core.dev)); for_each_component_dais_safe(component, dai, save) { diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig index 2df7afa2f469..c23fdb6aad4c 100644 --- a/sound/soc/intel/boards/Kconfig +++ b/sound/soc/intel/boards/Kconfig @@ -11,7 +11,7 @@ menuconfig SND_SOC_INTEL_MACH kernel: saying N will just cause the configurator to skip all the questions about Intel ASoC machine drivers. -if SND_SOC_INTEL_MACH +if SND_SOC_INTEL_MACH && (SND_SOC_SOF_INTEL_COMMON || !SND_SOC_SOF_INTEL_COMMON) config SND_SOC_INTEL_USER_FRIENDLY_LONG_NAMES bool "Use more user friendly long card names" @@ -42,6 +42,7 @@ config SND_SOC_INTEL_SOF_NUVOTON_COMMON tristate config SND_SOC_INTEL_SOF_BOARD_HELPERS + select SND_SOC_ACPI_INTEL_MATCH tristate if SND_SOC_INTEL_CATPT diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 81a914bd7ec2..504887505e68 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -783,6 +783,9 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { static const struct snd_pci_quirk sof_sdw_ssid_quirk_table[] = { SND_PCI_QUIRK(0x1043, 0x1e13, "ASUS Zenbook S14", SOC_SDW_CODEC_MIC), SND_PCI_QUIRK(0x1043, 0x1f43, "ASUS Zenbook S16", SOC_SDW_CODEC_MIC), + SND_PCI_QUIRK(0x17aa, 0x2347, "Lenovo P16", SOC_SDW_CODEC_MIC), + SND_PCI_QUIRK(0x17aa, 0x2348, "Lenovo P16", SOC_SDW_CODEC_MIC), + SND_PCI_QUIRK(0x17aa, 0x2349, "Lenovo P1", SOC_SDW_CODEC_MIC), {} }; diff --git a/sound/soc/intel/common/soc-acpi-intel-arl-match.c b/sound/soc/intel/common/soc-acpi-intel-arl-match.c index 73e581e93755..6bf7a6250ddc 100644 --- a/sound/soc/intel/common/soc-acpi-intel-arl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-arl-match.c @@ -238,6 +238,15 @@ static const struct snd_soc_acpi_adr_device rt722_0_single_adr[] = { } }; +static const struct snd_soc_acpi_adr_device rt1316_3_single_adr[] = { + { + .adr = 0x000330025D131601ull, + .num_endpoints = 1, + .endpoints = &single_endpoint, + .name_prefix = "rt1316-1" + } +}; + static const struct snd_soc_acpi_adr_device rt1320_2_single_adr[] = { { .adr = 0x000230025D132001ull, @@ -368,6 +377,20 @@ static const struct snd_soc_acpi_link_adr arl_sdca_rvp[] = { {} }; +static const struct snd_soc_acpi_link_adr arl_rt711_l0_rt1316_l3[] = { + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(rt711_sdca_0_adr), + .adr_d = rt711_sdca_0_adr, + }, + { + .mask = BIT(3), + .num_adr = ARRAY_SIZE(rt1316_3_single_adr), + .adr_d = rt1316_3_single_adr, + }, + {} +}; + static const struct snd_soc_acpi_link_adr arl_rt722_l0_rt1320_l2[] = { { .mask = BIT(0), @@ -468,6 +491,13 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_arl_sdw_machines[] = { .get_function_tplg_files = sof_sdw_get_tplg_files, }, { + .link_mask = BIT(2) | BIT(3), + .links = arl_cs42l43_l2_cs35l56_l3, + .drv_name = "sof_sdw", + .sof_tplg_filename = "sof-arl-cs42l43-l2-cs35l56-l3.tplg", + .get_function_tplg_files = sof_sdw_get_tplg_files, + }, + { .link_mask = BIT(2), .links = arl_cs42l43_l2, .drv_name = "sof_sdw", @@ -475,11 +505,10 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_arl_sdw_machines[] = { .get_function_tplg_files = sof_sdw_get_tplg_files, }, { - .link_mask = BIT(2) | BIT(3), - .links = arl_cs42l43_l2_cs35l56_l3, + .link_mask = BIT(0) | BIT(3), + .links = arl_rt711_l0_rt1316_l3, .drv_name = "sof_sdw", - .sof_tplg_filename = "sof-arl-cs42l43-l2-cs35l56-l3.tplg", - .get_function_tplg_files = sof_sdw_get_tplg_files, + .sof_tplg_filename = "sof-arl-rt711-l0-rt1316-l3.tplg", }, { .link_mask = 0x1, /* link0 required */ diff --git a/sound/soc/mediatek/common/mtk-soundcard-driver.c b/sound/soc/mediatek/common/mtk-soundcard-driver.c index 713a368f79cf..95a083939f3e 100644 --- a/sound/soc/mediatek/common/mtk-soundcard-driver.c +++ b/sound/soc/mediatek/common/mtk-soundcard-driver.c @@ -262,9 +262,13 @@ int mtk_soundcard_common_probe(struct platform_device *pdev) soc_card_data->accdet = accdet_comp; else dev_err(&pdev->dev, "No sound component found from mediatek,accdet property\n"); + + put_device(&accdet_pdev->dev); } else { dev_err(&pdev->dev, "No device found from mediatek,accdet property\n"); } + + of_node_put(accdet_node); } platform_node = of_parse_phandle(pdev->dev.of_node, "mediatek,platform", 0); diff --git a/sound/soc/mediatek/mt8365/mt8365-dai-i2s.c b/sound/soc/mediatek/mt8365/mt8365-dai-i2s.c index cae51756cead..cb9beb172ed5 100644 --- a/sound/soc/mediatek/mt8365/mt8365-dai-i2s.c +++ b/sound/soc/mediatek/mt8365/mt8365-dai-i2s.c @@ -812,11 +812,10 @@ static const struct snd_soc_dapm_route mtk_dai_i2s_routes[] = { static int mt8365_dai_i2s_set_priv(struct mtk_base_afe *afe) { int i, ret; - struct mt8365_afe_private *afe_priv = afe->platform_priv; for (i = 0; i < DAI_I2S_NUM; i++) { ret = mt8365_dai_set_priv(afe, mt8365_i2s_priv[i].id, - sizeof(*afe_priv), + sizeof(mt8365_i2s_priv[i]), &mt8365_i2s_priv[i]); if (ret) return ret; diff --git a/sound/soc/sdca/sdca_functions.c b/sound/soc/sdca/sdca_functions.c index 64ac26443890..de213a69e0da 100644 --- a/sound/soc/sdca/sdca_functions.c +++ b/sound/soc/sdca/sdca_functions.c @@ -211,7 +211,7 @@ static int find_sdca_init_table(struct device *dev, } else if (num_init_writes % sizeof(*raw) != 0) { dev_err(dev, "%pfwP: init table size invalid\n", function_node); return -EINVAL; - } else if (num_init_writes > SDCA_MAX_INIT_COUNT) { + } else if ((num_init_writes / sizeof(*raw)) > SDCA_MAX_INIT_COUNT) { dev_err(dev, "%pfwP: maximum init table size exceeded\n", function_node); return -EINVAL; } diff --git a/sound/soc/sof/intel/ptl.c b/sound/soc/sof/intel/ptl.c index 875d18193b05..1bc1f54c470d 100644 --- a/sound/soc/sof/intel/ptl.c +++ b/sound/soc/sof/intel/ptl.c @@ -117,6 +117,7 @@ const struct sof_intel_dsp_desc ptl_chip_info = { .read_sdw_lcount = hda_sdw_check_lcount_ext, .check_sdw_irq = lnl_dsp_check_sdw_irq, .check_sdw_wakeen_irq = lnl_sdw_check_wakeen_irq, + .sdw_process_wakeen = hda_sdw_process_wakeen_common, .check_ipc_irq = mtl_dsp_check_ipc_irq, .check_mic_privacy_irq = sof_ptl_check_mic_privacy_irq, .process_mic_privacy = sof_ptl_process_mic_privacy, diff --git a/sound/usb/format.c b/sound/usb/format.c index 8cd54f7bf33a..0ee532acbb60 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -310,16 +310,14 @@ static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip, struct audioformat *fp, unsigned int rate) { - struct usb_interface *iface; struct usb_host_interface *alts; unsigned char *fmt; unsigned int max_rate; - iface = usb_ifnum_to_if(chip->dev, fp->iface); - if (!iface) + alts = snd_usb_get_host_interface(chip, fp->iface, fp->altsetting); + if (!alts) return true; - alts = &iface->altsetting[fp->altset_idx]; fmt = snd_usb_find_csint_desc(alts->extra, alts->extralen, NULL, UAC_FORMAT_TYPE); if (!fmt) @@ -328,20 +326,20 @@ static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip, if (fmt[0] == 10) { /* bLength */ max_rate = combine_quad(&fmt[6]); - /* Validate max rate */ - if (max_rate != 48000 && - max_rate != 96000 && - max_rate != 192000 && - max_rate != 384000) { - + switch (max_rate) { + case 48000: + return (rate == 44100 || rate == 48000); + case 96000: + return (rate == 88200 || rate == 96000); + case 192000: + return (rate == 176400 || rate == 192000); + default: usb_audio_info(chip, "%u:%d : unexpected max rate: %u\n", fp->iface, fp->altsetting, max_rate); return true; } - - return rate <= max_rate; } return true; diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c index 3543b5a53592..a25c5a531690 100644 --- a/sound/usb/qcom/qc_audio_offload.c +++ b/sound/usb/qcom/qc_audio_offload.c @@ -825,8 +825,8 @@ static int uaudio_sideband_notifier(struct usb_interface *intf, } } - mutex_unlock(&qdev_mutex); mutex_unlock(&chip->mutex); + mutex_unlock(&qdev_mutex); return 0; } @@ -1865,8 +1865,8 @@ static void qc_usb_audio_offload_disconnect(struct snd_usb_audio *chip) /* Device has already been cleaned up, or never populated */ if (!dev->chip) { - mutex_unlock(&qdev_mutex); mutex_unlock(&chip->mutex); + mutex_unlock(&qdev_mutex); return; } @@ -1921,8 +1921,8 @@ static void qc_usb_audio_offload_suspend(struct usb_interface *intf, uaudio_send_disconnect_ind(chip); - mutex_unlock(&qdev_mutex); mutex_unlock(&chip->mutex); + mutex_unlock(&qdev_mutex); } static struct snd_usb_platform_ops offload_ops = { diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index b7dded3c8113..5cfb5d74dd5f 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -628,6 +628,7 @@ #define MSR_AMD64_OSVW_STATUS 0xc0010141 #define MSR_AMD_PPIN_CTL 0xc00102f0 #define MSR_AMD_PPIN 0xc00102f1 +#define MSR_AMD64_CPUID_FN_7 0xc0011002 #define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c index 0198321d14a2..92e8307b2a46 100644 --- a/tools/hv/hv_fcopy_uio_daemon.c +++ b/tools/hv/hv_fcopy_uio_daemon.c @@ -35,7 +35,10 @@ #define WIN8_SRV_MINOR 1 #define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR) -#define FCOPY_UIO "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/uio" +#define FCOPY_DEVICE_PATH(subdir) \ + "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/" #subdir +#define FCOPY_UIO_PATH FCOPY_DEVICE_PATH(uio) +#define FCOPY_CHANNELS_PATH FCOPY_DEVICE_PATH(channels) #define FCOPY_VER_COUNT 1 static const int fcopy_versions[] = { @@ -47,9 +50,62 @@ static const int fw_versions[] = { UTIL_FW_VERSION }; -#define HV_RING_SIZE 0x4000 /* 16KB ring buffer size */ +static uint32_t get_ring_buffer_size(void) +{ + char ring_path[PATH_MAX]; + DIR *dir; + struct dirent *entry; + struct stat st; + uint32_t ring_size = 0; + int retry_count = 0; + + /* Find the channel directory */ + dir = opendir(FCOPY_CHANNELS_PATH); + if (!dir) { + usleep(100 * 1000); /* Avoid race with kernel, wait 100ms and retry once */ + dir = opendir(FCOPY_CHANNELS_PATH); + if (!dir) { + syslog(LOG_ERR, "Failed to open channels directory: %s", strerror(errno)); + return 0; + } + } + +retry_once: + while ((entry = readdir(dir)) != NULL) { + if (entry->d_type == DT_DIR && strcmp(entry->d_name, ".") != 0 && + strcmp(entry->d_name, "..") != 0) { + snprintf(ring_path, sizeof(ring_path), "%s/%s/ring", + FCOPY_CHANNELS_PATH, entry->d_name); + + if (stat(ring_path, &st) == 0) { + /* + * stat returns size of Tx, Rx rings combined, + * so take half of it for individual ring size. + */ + ring_size = (uint32_t)st.st_size / 2; + syslog(LOG_INFO, "Ring buffer size from %s: %u bytes", + ring_path, ring_size); + break; + } + } + } + + if (!ring_size && retry_count == 0) { + retry_count = 1; + rewinddir(dir); + usleep(100 * 1000); /* Wait 100ms and retry once */ + goto retry_once; + } + + closedir(dir); -static unsigned char desc[HV_RING_SIZE]; + if (!ring_size) + syslog(LOG_ERR, "Could not determine ring size"); + + return ring_size; +} + +static unsigned char *desc; static int target_fd; static char target_fname[PATH_MAX]; @@ -62,8 +118,11 @@ static int hv_fcopy_create_file(char *file_name, char *path_name, __u32 flags) filesize = 0; p = path_name; - snprintf(target_fname, sizeof(target_fname), "%s/%s", - path_name, file_name); + if (snprintf(target_fname, sizeof(target_fname), "%s/%s", + path_name, file_name) >= sizeof(target_fname)) { + syslog(LOG_ERR, "target file name is too long: %s/%s", path_name, file_name); + goto done; + } /* * Check to see if the path is already in place; if not, @@ -270,7 +329,7 @@ static void wcstoutf8(char *dest, const __u16 *src, size_t dest_size) { size_t len = 0; - while (len < dest_size) { + while (len < dest_size && *src) { if (src[len] < 0x80) dest[len++] = (char)(*src++); else @@ -282,27 +341,15 @@ static void wcstoutf8(char *dest, const __u16 *src, size_t dest_size) static int hv_fcopy_start(struct hv_start_fcopy *smsg_in) { - setlocale(LC_ALL, "en_US.utf8"); - size_t file_size, path_size; - char *file_name, *path_name; - char *in_file_name = (char *)smsg_in->file_name; - char *in_path_name = (char *)smsg_in->path_name; - - file_size = wcstombs(NULL, (const wchar_t *restrict)in_file_name, 0) + 1; - path_size = wcstombs(NULL, (const wchar_t *restrict)in_path_name, 0) + 1; - - file_name = (char *)malloc(file_size * sizeof(char)); - path_name = (char *)malloc(path_size * sizeof(char)); - - if (!file_name || !path_name) { - free(file_name); - free(path_name); - syslog(LOG_ERR, "Can't allocate memory for file name and/or path name"); - return HV_E_FAIL; - } + /* + * file_name and path_name should have same length with appropriate + * member of hv_start_fcopy. + */ + char file_name[W_MAX_PATH], path_name[W_MAX_PATH]; - wcstoutf8(file_name, (__u16 *)in_file_name, file_size); - wcstoutf8(path_name, (__u16 *)in_path_name, path_size); + setlocale(LC_ALL, "en_US.utf8"); + wcstoutf8(file_name, smsg_in->file_name, W_MAX_PATH - 1); + wcstoutf8(path_name, smsg_in->path_name, W_MAX_PATH - 1); return hv_fcopy_create_file(file_name, path_name, smsg_in->copy_flags); } @@ -406,7 +453,7 @@ int main(int argc, char *argv[]) int daemonize = 1, long_index = 0, opt, ret = -EINVAL; struct vmbus_br txbr, rxbr; void *ring; - uint32_t len = HV_RING_SIZE; + uint32_t ring_size, len; char uio_name[NAME_MAX] = {0}; char uio_dev_path[PATH_MAX] = {0}; @@ -437,7 +484,20 @@ int main(int argc, char *argv[]) openlog("HV_UIO_FCOPY", 0, LOG_USER); syslog(LOG_INFO, "starting; pid is:%d", getpid()); - fcopy_get_first_folder(FCOPY_UIO, uio_name); + ring_size = get_ring_buffer_size(); + if (!ring_size) { + ret = -ENODEV; + goto exit; + } + + desc = malloc(ring_size * sizeof(unsigned char)); + if (!desc) { + syslog(LOG_ERR, "malloc failed for desc buffer"); + ret = -ENOMEM; + goto exit; + } + + fcopy_get_first_folder(FCOPY_UIO_PATH, uio_name); snprintf(uio_dev_path, sizeof(uio_dev_path), "/dev/%s", uio_name); fcopy_fd = open(uio_dev_path, O_RDWR); @@ -445,17 +505,17 @@ int main(int argc, char *argv[]) syslog(LOG_ERR, "open %s failed; error: %d %s", uio_dev_path, errno, strerror(errno)); ret = fcopy_fd; - goto exit; + goto free_desc; } - ring = vmbus_uio_map(&fcopy_fd, HV_RING_SIZE); + ring = vmbus_uio_map(&fcopy_fd, ring_size); if (!ring) { ret = errno; syslog(LOG_ERR, "mmap ringbuffer failed; error: %d %s", ret, strerror(ret)); goto close; } - vmbus_br_setup(&txbr, ring, HV_RING_SIZE); - vmbus_br_setup(&rxbr, (char *)ring + HV_RING_SIZE, HV_RING_SIZE); + vmbus_br_setup(&txbr, ring, ring_size); + vmbus_br_setup(&rxbr, (char *)ring + ring_size, ring_size); rxbr.vbr->imask = 0; @@ -472,7 +532,7 @@ int main(int argc, char *argv[]) goto close; } - len = HV_RING_SIZE; + len = ring_size; ret = rte_vmbus_chan_recv_raw(&rxbr, desc, &len); if (unlikely(ret <= 0)) { /* This indicates a failure to communicate (or worse) */ @@ -492,6 +552,8 @@ int main(int argc, char *argv[]) } close: close(fcopy_fd); +free_desc: + free(desc); exit: return ret; } diff --git a/tools/include/linux/kallsyms.h b/tools/include/linux/kallsyms.h index 5a37ccbec54f..f61a01dd7eb7 100644 --- a/tools/include/linux/kallsyms.h +++ b/tools/include/linux/kallsyms.h @@ -18,6 +18,7 @@ static inline const char *kallsyms_lookup(unsigned long addr, return NULL; } +#ifdef HAVE_BACKTRACE_SUPPORT #include <execinfo.h> #include <stdlib.h> static inline void print_ip_sym(const char *loglvl, unsigned long ip) @@ -30,5 +31,8 @@ static inline void print_ip_sym(const char *loglvl, unsigned long ip) free(name); } +#else +static inline void print_ip_sym(const char *loglvl, unsigned long ip) {} +#endif #endif diff --git a/tools/include/uapi/linux/bits.h b/tools/include/uapi/linux/bits.h index 682b406e1067..a04afef9efca 100644 --- a/tools/include/uapi/linux/bits.h +++ b/tools/include/uapi/linux/bits.h @@ -4,9 +4,9 @@ #ifndef _UAPI_LINUX_BITS_H #define _UAPI_LINUX_BITS_H -#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (BITS_PER_LONG - 1 - (h)))) +#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (__BITS_PER_LONG - 1 - (h)))) -#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h)))) +#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) #define __GENMASK_U128(h, l) \ ((_BIT128((h)) << 1) - (_BIT128(l))) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index d00b85cb168c..7415a3863891 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -618,6 +618,7 @@ struct kvm_ioeventfd { #define KVM_X86_DISABLE_EXITS_HLT (1 << 1) #define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) #define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3) +#define KVM_X86_DISABLE_EXITS_APERFMPERF (1 << 4) /* for KVM_ENABLE_CAP */ struct kvm_enable_cap { diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 52e353368f58..d41ee26b9443 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -735,7 +735,7 @@ struct bpf_object { struct usdt_manager *usdt_man; - struct bpf_map *arena_map; + int arena_map_idx; void *arena_data; size_t arena_data_sz; @@ -1517,6 +1517,7 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.obj_buf_sz = obj_buf_sz; obj->efile.btf_maps_shndx = -1; obj->kconfig_map_idx = -1; + obj->arena_map_idx = -1; obj->kern_version = get_kernel_version(); obj->state = OBJ_OPEN; @@ -2964,7 +2965,7 @@ static int init_arena_map_data(struct bpf_object *obj, struct bpf_map *map, const long page_sz = sysconf(_SC_PAGE_SIZE); size_t mmap_sz; - mmap_sz = bpf_map_mmap_sz(obj->arena_map); + mmap_sz = bpf_map_mmap_sz(map); if (roundup(data_sz, page_sz) > mmap_sz) { pr_warn("elf: sec '%s': declared ARENA map size (%zu) is too small to hold global __arena variables of size %zu\n", sec_name, mmap_sz, data_sz); @@ -3038,12 +3039,12 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, if (map->def.type != BPF_MAP_TYPE_ARENA) continue; - if (obj->arena_map) { + if (obj->arena_map_idx >= 0) { pr_warn("map '%s': only single ARENA map is supported (map '%s' is also ARENA)\n", - map->name, obj->arena_map->name); + map->name, obj->maps[obj->arena_map_idx].name); return -EINVAL; } - obj->arena_map = map; + obj->arena_map_idx = i; if (obj->efile.arena_data) { err = init_arena_map_data(obj, map, ARENA_SEC, obj->efile.arena_data_shndx, @@ -3053,7 +3054,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, return err; } } - if (obj->efile.arena_data && !obj->arena_map) { + if (obj->efile.arena_data && obj->arena_map_idx < 0) { pr_warn("elf: sec '%s': to use global __arena variables the ARENA map should be explicitly declared in SEC(\".maps\")\n", ARENA_SEC); return -ENOENT; @@ -4583,8 +4584,13 @@ static int bpf_program__record_reloc(struct bpf_program *prog, if (shdr_idx == obj->efile.arena_data_shndx) { reloc_desc->type = RELO_DATA; reloc_desc->insn_idx = insn_idx; - reloc_desc->map_idx = obj->arena_map - obj->maps; + reloc_desc->map_idx = obj->arena_map_idx; reloc_desc->sym_off = sym->st_value; + + map = &obj->maps[obj->arena_map_idx]; + pr_debug("prog '%s': found arena map %d (%s, sec %d, off %zu) for insn %u\n", + prog->name, obj->arena_map_idx, map->name, map->sec_idx, + map->sec_offset, insn_idx); return 0; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index d967ac001498..67d76f3a1dce 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -224,6 +224,7 @@ static bool is_rust_noreturn(const struct symbol *func) str_ends_with(func->name, "_4core9panicking14panic_explicit") || str_ends_with(func->name, "_4core9panicking14panic_nounwind") || str_ends_with(func->name, "_4core9panicking18panic_bounds_check") || + str_ends_with(func->name, "_4core9panicking18panic_nounwind_fmt") || str_ends_with(func->name, "_4core9panicking19assert_failed_inner") || str_ends_with(func->name, "_4core9panicking30panic_null_pointer_dereference") || str_ends_with(func->name, "_4core9panicking36panic_misaligned_pointer_dereference") || diff --git a/tools/perf/arch/riscv/util/kvm-stat.c b/tools/perf/arch/riscv/util/kvm-stat.c index 491aef449d1a..3ea7acb5e159 100644 --- a/tools/perf/arch/riscv/util/kvm-stat.c +++ b/tools/perf/arch/riscv/util/kvm-stat.c @@ -9,10 +9,10 @@ #include <memory.h> #include "../../../util/evsel.h" #include "../../../util/kvm-stat.h" -#include "riscv_exception_types.h" +#include "riscv_trap_types.h" #include "debug.h" -define_exit_reasons_table(riscv_exit_reasons, kvm_riscv_exception_class); +define_exit_reasons_table(riscv_exit_reasons, kvm_riscv_trap_class); const char *vcpu_id_str = "id"; const char *kvm_exit_reason = "scause"; @@ -30,7 +30,7 @@ static void event_get_key(struct evsel *evsel, struct event_key *key) { key->info = 0; - key->key = evsel__intval(evsel, sample, kvm_exit_reason); + key->key = evsel__intval(evsel, sample, kvm_exit_reason) & ~CAUSE_IRQ_FLAG; key->exit_reasons = riscv_exit_reasons; } diff --git a/tools/perf/arch/riscv/util/riscv_exception_types.h b/tools/perf/arch/riscv/util/riscv_exception_types.h deleted file mode 100644 index c49b8fa5e847..000000000000 --- a/tools/perf/arch/riscv/util/riscv_exception_types.h +++ /dev/null @@ -1,35 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#ifndef ARCH_PERF_RISCV_EXCEPTION_TYPES_H -#define ARCH_PERF_RISCV_EXCEPTION_TYPES_H - -#define EXC_INST_MISALIGNED 0 -#define EXC_INST_ACCESS 1 -#define EXC_INST_ILLEGAL 2 -#define EXC_BREAKPOINT 3 -#define EXC_LOAD_MISALIGNED 4 -#define EXC_LOAD_ACCESS 5 -#define EXC_STORE_MISALIGNED 6 -#define EXC_STORE_ACCESS 7 -#define EXC_SYSCALL 8 -#define EXC_HYPERVISOR_SYSCALL 9 -#define EXC_SUPERVISOR_SYSCALL 10 -#define EXC_INST_PAGE_FAULT 12 -#define EXC_LOAD_PAGE_FAULT 13 -#define EXC_STORE_PAGE_FAULT 15 -#define EXC_INST_GUEST_PAGE_FAULT 20 -#define EXC_LOAD_GUEST_PAGE_FAULT 21 -#define EXC_VIRTUAL_INST_FAULT 22 -#define EXC_STORE_GUEST_PAGE_FAULT 23 - -#define EXC(x) {EXC_##x, #x } - -#define kvm_riscv_exception_class \ - EXC(INST_MISALIGNED), EXC(INST_ACCESS), EXC(INST_ILLEGAL), \ - EXC(BREAKPOINT), EXC(LOAD_MISALIGNED), EXC(LOAD_ACCESS), \ - EXC(STORE_MISALIGNED), EXC(STORE_ACCESS), EXC(SYSCALL), \ - EXC(HYPERVISOR_SYSCALL), EXC(SUPERVISOR_SYSCALL), \ - EXC(INST_PAGE_FAULT), EXC(LOAD_PAGE_FAULT), EXC(STORE_PAGE_FAULT), \ - EXC(INST_GUEST_PAGE_FAULT), EXC(LOAD_GUEST_PAGE_FAULT), \ - EXC(VIRTUAL_INST_FAULT), EXC(STORE_GUEST_PAGE_FAULT) - -#endif /* ARCH_PERF_RISCV_EXCEPTION_TYPES_H */ diff --git a/tools/perf/arch/riscv/util/riscv_trap_types.h b/tools/perf/arch/riscv/util/riscv_trap_types.h new file mode 100644 index 000000000000..6cc71eb01fca --- /dev/null +++ b/tools/perf/arch/riscv/util/riscv_trap_types.h @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef ARCH_PERF_RISCV_TRAP_TYPES_H +#define ARCH_PERF_RISCV_TRAP_TYPES_H + +/* Exception cause high bit - is an interrupt if set */ +#define CAUSE_IRQ_FLAG (_AC(1, UL) << (__riscv_xlen - 1)) + +/* Interrupt causes (minus the high bit) */ +#define IRQ_S_SOFT 1 +#define IRQ_VS_SOFT 2 +#define IRQ_M_SOFT 3 +#define IRQ_S_TIMER 5 +#define IRQ_VS_TIMER 6 +#define IRQ_M_TIMER 7 +#define IRQ_S_EXT 9 +#define IRQ_VS_EXT 10 +#define IRQ_M_EXT 11 +#define IRQ_S_GEXT 12 +#define IRQ_PMU_OVF 13 + +/* Exception causes */ +#define EXC_INST_MISALIGNED 0 +#define EXC_INST_ACCESS 1 +#define EXC_INST_ILLEGAL 2 +#define EXC_BREAKPOINT 3 +#define EXC_LOAD_MISALIGNED 4 +#define EXC_LOAD_ACCESS 5 +#define EXC_STORE_MISALIGNED 6 +#define EXC_STORE_ACCESS 7 +#define EXC_SYSCALL 8 +#define EXC_HYPERVISOR_SYSCALL 9 +#define EXC_SUPERVISOR_SYSCALL 10 +#define EXC_INST_PAGE_FAULT 12 +#define EXC_LOAD_PAGE_FAULT 13 +#define EXC_STORE_PAGE_FAULT 15 +#define EXC_INST_GUEST_PAGE_FAULT 20 +#define EXC_LOAD_GUEST_PAGE_FAULT 21 +#define EXC_VIRTUAL_INST_FAULT 22 +#define EXC_STORE_GUEST_PAGE_FAULT 23 + +#define TRAP(x) { x, #x } + +#define kvm_riscv_trap_class \ + TRAP(IRQ_S_SOFT), TRAP(IRQ_VS_SOFT), TRAP(IRQ_M_SOFT), \ + TRAP(IRQ_S_TIMER), TRAP(IRQ_VS_TIMER), TRAP(IRQ_M_TIMER), \ + TRAP(IRQ_S_EXT), TRAP(IRQ_VS_EXT), TRAP(IRQ_M_EXT), \ + TRAP(IRQ_S_GEXT), TRAP(IRQ_PMU_OVF), \ + TRAP(EXC_INST_MISALIGNED), TRAP(EXC_INST_ACCESS), TRAP(EXC_INST_ILLEGAL), \ + TRAP(EXC_BREAKPOINT), TRAP(EXC_LOAD_MISALIGNED), TRAP(EXC_LOAD_ACCESS), \ + TRAP(EXC_STORE_MISALIGNED), TRAP(EXC_STORE_ACCESS), TRAP(EXC_SYSCALL), \ + TRAP(EXC_HYPERVISOR_SYSCALL), TRAP(EXC_SUPERVISOR_SYSCALL), \ + TRAP(EXC_INST_PAGE_FAULT), TRAP(EXC_LOAD_PAGE_FAULT), \ + TRAP(EXC_STORE_PAGE_FAULT), TRAP(EXC_INST_GUEST_PAGE_FAULT), \ + TRAP(EXC_LOAD_GUEST_PAGE_FAULT), TRAP(EXC_VIRTUAL_INST_FAULT), \ + TRAP(EXC_STORE_GUEST_PAGE_FAULT) + +#endif /* ARCH_PERF_RISCV_TRAP_TYPES_H */ diff --git a/tools/testing/selftests/bpf/prog_tests/recursive_attach.c b/tools/testing/selftests/bpf/prog_tests/recursive_attach.c index 8100509e561b..0ffa01d54ce2 100644 --- a/tools/testing/selftests/bpf/prog_tests/recursive_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/recursive_attach.c @@ -149,3 +149,70 @@ close_prog: fentry_recursive_target__destroy(target_skel); fentry_recursive__destroy(tracing_skel); } + +static void *fentry_target_test_run(void *arg) +{ + for (;;) { + int prog_fd = __atomic_load_n((int *)arg, __ATOMIC_SEQ_CST); + LIBBPF_OPTS(bpf_test_run_opts, topts); + int err; + + if (prog_fd == -1) + break; + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "fentry_target test_run")) + break; + } + + return NULL; +} + +void test_fentry_attach_stress(void) +{ + struct fentry_recursive_target *target_skel = NULL; + struct fentry_recursive *tracing_skel = NULL; + struct bpf_program *prog; + int err, i, tgt_prog_fd; + pthread_t thread; + + target_skel = fentry_recursive_target__open_and_load(); + if (!ASSERT_OK_PTR(target_skel, + "fentry_recursive_target__open_and_load")) + goto close_prog; + tgt_prog_fd = bpf_program__fd(target_skel->progs.fentry_target); + err = pthread_create(&thread, NULL, + fentry_target_test_run, &tgt_prog_fd); + if (!ASSERT_OK(err, "bpf_program__set_attach_target")) + goto close_prog; + + for (i = 0; i < 1000; i++) { + tracing_skel = fentry_recursive__open(); + if (!ASSERT_OK_PTR(tracing_skel, "fentry_recursive__open")) + goto stop_thread; + + prog = tracing_skel->progs.recursive_attach; + err = bpf_program__set_attach_target(prog, tgt_prog_fd, + "fentry_target"); + if (!ASSERT_OK(err, "bpf_program__set_attach_target")) + goto stop_thread; + + err = fentry_recursive__load(tracing_skel); + if (!ASSERT_OK(err, "fentry_recursive__load")) + goto stop_thread; + + err = fentry_recursive__attach(tracing_skel); + if (!ASSERT_OK(err, "fentry_recursive__attach")) + goto stop_thread; + + fentry_recursive__destroy(tracing_skel); + tracing_skel = NULL; + } + +stop_thread: + __atomic_store_n(&tgt_prog_fd, -1, __ATOMIC_SEQ_CST); + err = pthread_join(thread, NULL); + ASSERT_OK(err, "pthread_join"); +close_prog: + fentry_recursive__destroy(tracing_skel); + fentry_recursive_target__destroy(target_skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf.c b/tools/testing/selftests/bpf/prog_tests/snprintf.c index 4be6fdb78c6a..594441acb707 100644 --- a/tools/testing/selftests/bpf/prog_tests/snprintf.c +++ b/tools/testing/selftests/bpf/prog_tests/snprintf.c @@ -116,6 +116,8 @@ static void test_snprintf_negative(void) ASSERT_ERR(load_single_snprintf("%llc"), "invalid specifier 7"); ASSERT_ERR(load_single_snprintf("\x80"), "non ascii character"); ASSERT_ERR(load_single_snprintf("\x1"), "non printable character"); + ASSERT_ERR(load_single_snprintf("%p%"), "invalid specifier 8"); + ASSERT_ERR(load_single_snprintf("%s%"), "invalid specifier 9"); } void test_snprintf(void) diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py index d9c10613ae67..44151b7b1a24 100644 --- a/tools/testing/selftests/drivers/net/lib/py/load.py +++ b/tools/testing/selftests/drivers/net/lib/py/load.py @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 +import re import time from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen @@ -10,12 +11,11 @@ class GenerateTraffic: self.env = env - if port is None: - port = rand_port() - self._iperf_server = cmd(f"iperf3 -s -1 -p {port}", background=True) - wait_port_listen(port) + self.port = rand_port() if port is None else port + self._iperf_server = cmd(f"iperf3 -s -1 -p {self.port}", background=True) + wait_port_listen(self.port) time.sleep(0.1) - self._iperf_client = cmd(f"iperf3 -c {env.addr} -P 16 -p {port} -t 86400", + self._iperf_client = cmd(f"iperf3 -c {env.addr} -P 16 -p {self.port} -t 86400", background=True, host=env.remote) # Wait for traffic to ramp up @@ -56,3 +56,16 @@ class GenerateTraffic: ksft_pr(">> Server:") ksft_pr(self._iperf_server.stdout) ksft_pr(self._iperf_server.stderr) + self._wait_client_stopped() + + def _wait_client_stopped(self, sleep=0.005, timeout=5): + end = time.monotonic() + timeout + + live_port_pattern = re.compile(fr":{self.port:04X} 0[^6] ") + + while time.monotonic() < end: + data = cmd("cat /proc/net/tcp*", host=self.env.remote).stdout + if not live_port_pattern.search(data): + return + time.sleep(sleep) + raise Exception(f"Waiting for client to stop timed out after {timeout}s") diff --git a/tools/testing/selftests/futex/include/futex2test.h b/tools/testing/selftests/futex/include/futex2test.h index ea79662405bc..1f625b39948a 100644 --- a/tools/testing/selftests/futex/include/futex2test.h +++ b/tools/testing/selftests/futex/include/futex2test.h @@ -4,6 +4,7 @@ * * Copyright 2021 Collabora Ltd. */ +#include <linux/time_types.h> #include <stdint.h> #define u64_to_ptr(x) ((void *)(uintptr_t)(x)) @@ -65,7 +66,12 @@ struct futex32_numa { static inline int futex_waitv(volatile struct futex_waitv *waiters, unsigned long nr_waiters, unsigned long flags, struct timespec *timo, clockid_t clockid) { - return syscall(__NR_futex_waitv, waiters, nr_waiters, flags, timo, clockid); + struct __kernel_timespec ts = { + .tv_sec = timo->tv_sec, + .tv_nsec = timo->tv_nsec, + }; + + return syscall(__NR_futex_waitv, waiters, nr_waiters, flags, &ts, clockid); } /* diff --git a/tools/testing/selftests/hid/tests/test_mouse.py b/tools/testing/selftests/hid/tests/test_mouse.py index 66daf7e5975c..eb4e15a0e53b 100644 --- a/tools/testing/selftests/hid/tests/test_mouse.py +++ b/tools/testing/selftests/hid/tests/test_mouse.py @@ -439,6 +439,68 @@ class BadResolutionMultiplierMouse(ResolutionMultiplierMouse): return 32 # EPIPE +class BadReportDescriptorMouse(BaseMouse): + """ + This "device" was one autogenerated by syzbot. There are a lot of issues in + it, and the most problematic is that it declares features that have no + size. + + This leads to report->size being set to 0 and can mess up with usbhid + internals. Fortunately, uhid merely passes the incoming buffer, without + touching it so a buffer of size 0 will be translated to [] without + triggering a kernel oops. + + Because the report descriptor is wrong, no input are created, and we need + to tweak a little bit the parameters to make it look correct. + """ + + # fmt: off + report_descriptor = [ + 0x96, 0x01, 0x00, # Report Count (1) 0 + 0x06, 0x01, 0x00, # Usage Page (Generic Desktop) 3 + # 0x03, 0x00, 0x00, 0x00, 0x00, # Ignored by the kernel somehow + 0x2a, 0x90, 0xa0, # Usage Maximum (41104) 6 + 0x27, 0x00, 0x00, 0x00, 0x00, # Logical Maximum (0) 9 + 0xb3, 0x81, 0x3e, 0x25, 0x03, # Feature (Cnst,Arr,Abs,Vol) 14 + 0x1b, 0xdd, 0xe8, 0x40, 0x50, # Usage Minimum (1346431197) 19 + 0x3b, 0x5d, 0x8c, 0x3d, 0xda, # Designator Index 24 + ] + # fmt: on + + def __init__( + self, rdesc=report_descriptor, name=None, input_info=(3, 0x045E, 0x07DA) + ): + super().__init__(rdesc, name, input_info) + self.high_resolution_report_called = False + + def get_evdev(self, application=None): + assert self._input_nodes is None + return ( + "Ok" # should be a list or None, but both would fail, so abusing the system + ) + + def next_sync_events(self, application=None): + # there are no evdev nodes, so no events + return [] + + def is_ready(self): + # we wait for the SET_REPORT command to come + return self.high_resolution_report_called + + def set_report(self, req, rnum, rtype, data): + if rtype != self.UHID_FEATURE_REPORT: + raise InvalidHIDCommunication(f"Unexpected report type: {rtype}") + if rnum != 0x0: + raise InvalidHIDCommunication(f"Unexpected report number: {rnum}") + + if len(data) != 1: + raise InvalidHIDCommunication(f"Unexpected data: {data}, expected '[0]'") + + self.high_resolution_report_called = True + + return 0 + + class ResolutionMultiplierHWheelMouse(TwoWheelMouse): # fmt: off report_descriptor = [ @@ -975,3 +1037,11 @@ class TestMiMouse(TestWheelMouse): # assert below print out the real error pass assert remaining == [] + + +class TestBadReportDescriptorMouse(base.BaseTestCase.TestUhid): + def create_device(self): + return BadReportDescriptorMouse() + + def assertName(self, uhdev): + pass diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index 38b95998e1e6..40920445bfbe 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -59,6 +59,7 @@ TEST_PROGS_x86 += x86/nx_huge_pages_test.sh TEST_GEN_PROGS_COMMON = demand_paging_test TEST_GEN_PROGS_COMMON += dirty_log_test TEST_GEN_PROGS_COMMON += guest_print_test +TEST_GEN_PROGS_COMMON += irqfd_test TEST_GEN_PROGS_COMMON += kvm_binary_stats_test TEST_GEN_PROGS_COMMON += kvm_create_max_vcpus TEST_GEN_PROGS_COMMON += kvm_page_table_test @@ -134,6 +135,7 @@ TEST_GEN_PROGS_x86 += x86/amx_test TEST_GEN_PROGS_x86 += x86/max_vcpuid_cap_test TEST_GEN_PROGS_x86 += x86/triple_fault_event_test TEST_GEN_PROGS_x86 += x86/recalc_apic_map_test +TEST_GEN_PROGS_x86 += x86/aperfmperf_test TEST_GEN_PROGS_x86 += access_tracking_perf_test TEST_GEN_PROGS_x86 += coalesced_io_test TEST_GEN_PROGS_x86 += dirty_log_perf_test diff --git a/tools/testing/selftests/kvm/arch_timer.c b/tools/testing/selftests/kvm/arch_timer.c index acb2cb596332..cf8fb67104f1 100644 --- a/tools/testing/selftests/kvm/arch_timer.c +++ b/tools/testing/selftests/kvm/arch_timer.c @@ -98,16 +98,11 @@ static uint32_t test_get_pcpu(void) static int test_migrate_vcpu(unsigned int vcpu_idx) { int ret; - cpu_set_t cpuset; uint32_t new_pcpu = test_get_pcpu(); - CPU_ZERO(&cpuset); - CPU_SET(new_pcpu, &cpuset); - pr_debug("Migrating vCPU: %u to pCPU: %u\n", vcpu_idx, new_pcpu); - ret = pthread_setaffinity_np(pt_vcpu_run[vcpu_idx], - sizeof(cpuset), &cpuset); + ret = __pin_task_to_cpu(pt_vcpu_run[vcpu_idx], new_pcpu); /* Allow the error where the vCPU thread is already finished */ TEST_ASSERT(ret == 0 || ret == ESRCH, diff --git a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c index 4e71740a098b..ce74d069cb7b 100644 --- a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c +++ b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c @@ -862,25 +862,6 @@ static uint32_t next_pcpu(void) return next; } -static void migrate_self(uint32_t new_pcpu) -{ - int ret; - cpu_set_t cpuset; - pthread_t thread; - - thread = pthread_self(); - - CPU_ZERO(&cpuset); - CPU_SET(new_pcpu, &cpuset); - - pr_debug("Migrating from %u to %u\n", sched_getcpu(), new_pcpu); - - ret = pthread_setaffinity_np(thread, sizeof(cpuset), &cpuset); - - TEST_ASSERT(ret == 0, "Failed to migrate to pCPU: %u; ret: %d\n", - new_pcpu, ret); -} - static void kvm_set_cntxct(struct kvm_vcpu *vcpu, uint64_t cnt, enum arch_timer timer) { @@ -907,7 +888,7 @@ static void handle_sync(struct kvm_vcpu *vcpu, struct ucall *uc) sched_yield(); break; case USERSPACE_MIGRATE_SELF: - migrate_self(next_pcpu()); + pin_self_to_cpu(next_pcpu()); break; default: break; @@ -919,7 +900,7 @@ static void test_run(struct kvm_vm *vm, struct kvm_vcpu *vcpu) struct ucall uc; /* Start on CPU 0 */ - migrate_self(0); + pin_self_to_cpu(0); while (true) { vcpu_run(vcpu); diff --git a/tools/testing/selftests/kvm/arm64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c index f4ac28d53747..a09dd423c2d7 100644 --- a/tools/testing/selftests/kvm/arm64/vgic_irq.c +++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c @@ -620,18 +620,12 @@ static void kvm_routing_and_irqfd_check(struct kvm_vm *vm, * that no actual interrupt was injected for those cases. */ - for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) { - fd[f] = eventfd(0, 0); - TEST_ASSERT(fd[f] != -1, __KVM_SYSCALL_ERROR("eventfd()", fd[f])); - } + for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) + fd[f] = kvm_new_eventfd(); for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) { - struct kvm_irqfd irqfd = { - .fd = fd[f], - .gsi = i - MIN_SPI, - }; assert(i <= (uint64_t)UINT_MAX); - vm_ioctl(vm, KVM_IRQFD, &irqfd); + kvm_assign_irqfd(vm, i - MIN_SPI, fd[f]); } for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) { diff --git a/tools/testing/selftests/kvm/config b/tools/testing/selftests/kvm/config index 8835fed09e9f..96d874b239eb 100644 --- a/tools/testing/selftests/kvm/config +++ b/tools/testing/selftests/kvm/config @@ -1,5 +1,6 @@ CONFIG_KVM=y CONFIG_KVM_INTEL=y CONFIG_KVM_AMD=y +CONFIG_EVENTFD=y CONFIG_USERFAULTFD=y CONFIG_IDLE_PAGE_TRACKING=y diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index bee65ca08721..e18d4bb1372f 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -18,8 +18,11 @@ #include <asm/atomic.h> #include <asm/kvm.h> +#include <sys/eventfd.h> #include <sys/ioctl.h> +#include <pthread.h> + #include "kvm_util_arch.h" #include "kvm_util_types.h" #include "sparsebit.h" @@ -502,6 +505,45 @@ static inline int vm_get_stats_fd(struct kvm_vm *vm) return fd; } +static inline int __kvm_irqfd(struct kvm_vm *vm, uint32_t gsi, int eventfd, + uint32_t flags) +{ + struct kvm_irqfd irqfd = { + .fd = eventfd, + .gsi = gsi, + .flags = flags, + .resamplefd = -1, + }; + + return __vm_ioctl(vm, KVM_IRQFD, &irqfd); +} + +static inline void kvm_irqfd(struct kvm_vm *vm, uint32_t gsi, int eventfd, + uint32_t flags) +{ + int ret = __kvm_irqfd(vm, gsi, eventfd, flags); + + TEST_ASSERT_VM_VCPU_IOCTL(!ret, KVM_IRQFD, ret, vm); +} + +static inline void kvm_assign_irqfd(struct kvm_vm *vm, uint32_t gsi, int eventfd) +{ + kvm_irqfd(vm, gsi, eventfd, 0); +} + +static inline void kvm_deassign_irqfd(struct kvm_vm *vm, uint32_t gsi, int eventfd) +{ + kvm_irqfd(vm, gsi, eventfd, KVM_IRQFD_FLAG_DEASSIGN); +} + +static inline int kvm_new_eventfd(void) +{ + int fd = eventfd(0, 0); + + TEST_ASSERT(fd >= 0, __KVM_SYSCALL_ERROR("eventfd()", fd)); + return fd; +} + static inline void read_stats_header(int stats_fd, struct kvm_stats_header *header) { ssize_t ret; @@ -1013,7 +1055,34 @@ struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm); void kvm_set_files_rlimit(uint32_t nr_vcpus); -void kvm_pin_this_task_to_pcpu(uint32_t pcpu); +int __pin_task_to_cpu(pthread_t task, int cpu); + +static inline void pin_task_to_cpu(pthread_t task, int cpu) +{ + int r; + + r = __pin_task_to_cpu(task, cpu); + TEST_ASSERT(!r, "Failed to set thread affinity to pCPU '%u'", cpu); +} + +static inline int pin_task_to_any_cpu(pthread_t task) +{ + int cpu = sched_getcpu(); + + pin_task_to_cpu(task, cpu); + return cpu; +} + +static inline void pin_self_to_cpu(int cpu) +{ + pin_task_to_cpu(pthread_self(), cpu); +} + +static inline int pin_self_to_any_cpu(void) +{ + return pin_task_to_any_cpu(pthread_self()); +} + void kvm_print_vcpu_pinning_help(void); void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[], int nr_vcpus); diff --git a/tools/testing/selftests/kvm/irqfd_test.c b/tools/testing/selftests/kvm/irqfd_test.c new file mode 100644 index 000000000000..7c301b4c7005 --- /dev/null +++ b/tools/testing/selftests/kvm/irqfd_test.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <errno.h> +#include <pthread.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <signal.h> +#include <stdint.h> +#include <sys/sysinfo.h> + +#include "kvm_util.h" + +static struct kvm_vm *vm1; +static struct kvm_vm *vm2; +static int __eventfd; +static bool done; + +/* + * KVM de-assigns based on eventfd *and* GSI, but requires unique eventfds when + * assigning (the API isn't symmetrical). Abuse the oddity and use a per-task + * GSI base to avoid false failures due to cross-task de-assign, i.e. so that + * the secondary doesn't de-assign the primary's eventfd and cause assign to + * unexpectedly succeed on the primary. + */ +#define GSI_BASE_PRIMARY 0x20 +#define GSI_BASE_SECONDARY 0x30 + +static void juggle_eventfd_secondary(struct kvm_vm *vm, int eventfd) +{ + int r, i; + + /* + * The secondary task can encounter EBADF since the primary can close + * the eventfd at any time. And because the primary can recreate the + * eventfd, at the safe fd in the file table, the secondary can also + * encounter "unexpected" success, e.g. if the close+recreate happens + * between the first and second assignments. The secondary's role is + * mostly to antagonize KVM, not to detect bugs. + */ + for (i = 0; i < 2; i++) { + r = __kvm_irqfd(vm, GSI_BASE_SECONDARY, eventfd, 0); + TEST_ASSERT(!r || errno == EBUSY || errno == EBADF, + "Wanted success, EBUSY, or EBADF, r = %d, errno = %d", + r, errno); + + /* De-assign should succeed unless the eventfd was closed. */ + r = __kvm_irqfd(vm, GSI_BASE_SECONDARY + i, eventfd, KVM_IRQFD_FLAG_DEASSIGN); + TEST_ASSERT(!r || errno == EBADF, + "De-assign should succeed unless the fd was closed"); + } +} + +static void *secondary_irqfd_juggler(void *ign) +{ + while (!READ_ONCE(done)) { + juggle_eventfd_secondary(vm1, READ_ONCE(__eventfd)); + juggle_eventfd_secondary(vm2, READ_ONCE(__eventfd)); + } + + return NULL; +} + +static void juggle_eventfd_primary(struct kvm_vm *vm, int eventfd) +{ + int r1, r2; + + /* + * At least one of the assigns should fail. KVM disallows assigning a + * single eventfd to multiple GSIs (or VMs), so it's possible that both + * assignments can fail, too. + */ + r1 = __kvm_irqfd(vm, GSI_BASE_PRIMARY, eventfd, 0); + TEST_ASSERT(!r1 || errno == EBUSY, + "Wanted success or EBUSY, r = %d, errno = %d", r1, errno); + + r2 = __kvm_irqfd(vm, GSI_BASE_PRIMARY + 1, eventfd, 0); + TEST_ASSERT(r1 || (r2 && errno == EBUSY), + "Wanted failure (EBUSY), r1 = %d, r2 = %d, errno = %d", + r1, r2, errno); + + /* + * De-assign should always succeed, even if the corresponding assign + * failed. + */ + kvm_irqfd(vm, GSI_BASE_PRIMARY, eventfd, KVM_IRQFD_FLAG_DEASSIGN); + kvm_irqfd(vm, GSI_BASE_PRIMARY + 1, eventfd, KVM_IRQFD_FLAG_DEASSIGN); +} + +int main(int argc, char *argv[]) +{ + pthread_t racing_thread; + int r, i; + + /* Create "full" VMs, as KVM_IRQFD requires an in-kernel IRQ chip. */ + vm1 = vm_create(1); + vm2 = vm_create(1); + + WRITE_ONCE(__eventfd, kvm_new_eventfd()); + + kvm_irqfd(vm1, 10, __eventfd, 0); + + r = __kvm_irqfd(vm1, 11, __eventfd, 0); + TEST_ASSERT(r && errno == EBUSY, + "Wanted EBUSY, r = %d, errno = %d", r, errno); + + r = __kvm_irqfd(vm2, 12, __eventfd, 0); + TEST_ASSERT(r && errno == EBUSY, + "Wanted EBUSY, r = %d, errno = %d", r, errno); + + /* + * De-assign all eventfds, along with multiple eventfds that were never + * assigned. KVM's ABI is that de-assign is allowed so long as the + * eventfd itself is valid. + */ + kvm_irqfd(vm1, 11, READ_ONCE(__eventfd), KVM_IRQFD_FLAG_DEASSIGN); + kvm_irqfd(vm1, 12, READ_ONCE(__eventfd), KVM_IRQFD_FLAG_DEASSIGN); + kvm_irqfd(vm1, 13, READ_ONCE(__eventfd), KVM_IRQFD_FLAG_DEASSIGN); + kvm_irqfd(vm1, 14, READ_ONCE(__eventfd), KVM_IRQFD_FLAG_DEASSIGN); + kvm_irqfd(vm1, 10, READ_ONCE(__eventfd), KVM_IRQFD_FLAG_DEASSIGN); + + close(__eventfd); + + pthread_create(&racing_thread, NULL, secondary_irqfd_juggler, vm2); + + for (i = 0; i < 10000; i++) { + WRITE_ONCE(__eventfd, kvm_new_eventfd()); + + juggle_eventfd_primary(vm1, __eventfd); + juggle_eventfd_primary(vm2, __eventfd); + close(__eventfd); + } + + WRITE_ONCE(done, true); + pthread_join(racing_thread, NULL); +} diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index a055343a7bf7..76a20cfe78d6 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -605,15 +605,14 @@ struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm) return vm_vcpu_recreate(vm, 0); } -void kvm_pin_this_task_to_pcpu(uint32_t pcpu) +int __pin_task_to_cpu(pthread_t task, int cpu) { - cpu_set_t mask; - int r; + cpu_set_t cpuset; + + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); - CPU_ZERO(&mask); - CPU_SET(pcpu, &mask); - r = sched_setaffinity(0, sizeof(mask), &mask); - TEST_ASSERT(!r, "sched_setaffinity() failed for pCPU '%u'.", pcpu); + return pthread_setaffinity_np(task, sizeof(cpuset), &cpuset); } static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask) @@ -667,7 +666,7 @@ void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[], /* 2. Check if the main worker needs to be pinned. */ if (cpu) { - kvm_pin_this_task_to_pcpu(parse_pcpu(cpu, &allowed_mask)); + pin_self_to_cpu(parse_pcpu(cpu, &allowed_mask)); cpu = strtok(NULL, delim); } @@ -1716,7 +1715,18 @@ void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa) /* Create an interrupt controller chip for the specified VM. */ void vm_create_irqchip(struct kvm_vm *vm) { - vm_ioctl(vm, KVM_CREATE_IRQCHIP, NULL); + int r; + + /* + * Allocate a fully in-kernel IRQ chip by default, but fall back to a + * split model (x86 only) if that fails (KVM x86 allows compiling out + * support for KVM_CREATE_IRQCHIP). + */ + r = __vm_ioctl(vm, KVM_CREATE_IRQCHIP, NULL); + if (r && errno == ENOTTY && kvm_has_cap(KVM_CAP_SPLIT_IRQCHIP)) + vm_enable_cap(vm, KVM_CAP_SPLIT_IRQCHIP, 24); + else + TEST_ASSERT_VM_VCPU_IOCTL(!r, KVM_CREATE_IRQCHIP, r, vm); vm->has_irqchip = true; } diff --git a/tools/testing/selftests/kvm/lib/memstress.c b/tools/testing/selftests/kvm/lib/memstress.c index 313277486a1d..557c0a0a5658 100644 --- a/tools/testing/selftests/kvm/lib/memstress.c +++ b/tools/testing/selftests/kvm/lib/memstress.c @@ -265,7 +265,7 @@ static void *vcpu_thread_main(void *data) int vcpu_idx = vcpu->vcpu_idx; if (memstress_args.pin_vcpus) - kvm_pin_this_task_to_pcpu(memstress_args.vcpu_to_pcpu[vcpu_idx]); + pin_self_to_cpu(memstress_args.vcpu_to_pcpu[vcpu_idx]); WRITE_ONCE(vcpu->running, true); diff --git a/tools/testing/selftests/kvm/x86/aperfmperf_test.c b/tools/testing/selftests/kvm/x86/aperfmperf_test.c new file mode 100644 index 000000000000..8b15a13df939 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/aperfmperf_test.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test for KVM_X86_DISABLE_EXITS_APERFMPERF + * + * Copyright (C) 2025, Google LLC. + * + * Test the ability to disable VM-exits for rdmsr of IA32_APERF and + * IA32_MPERF. When these VM-exits are disabled, reads of these MSRs + * return the host's values. + * + * Note: Requires read access to /dev/cpu/<lpu>/msr to read host MSRs. + */ + +#include <fcntl.h> +#include <limits.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdint.h> +#include <unistd.h> +#include <asm/msr-index.h> + +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "test_util.h" +#include "vmx.h" + +#define NUM_ITERATIONS 10000 + +static int open_dev_msr(int cpu) +{ + char path[PATH_MAX]; + + snprintf(path, sizeof(path), "/dev/cpu/%d/msr", cpu); + return open_path_or_exit(path, O_RDONLY); +} + +static uint64_t read_dev_msr(int msr_fd, uint32_t msr) +{ + uint64_t data; + ssize_t rc; + + rc = pread(msr_fd, &data, sizeof(data), msr); + TEST_ASSERT(rc == sizeof(data), "Read of MSR 0x%x failed", msr); + + return data; +} + +static void guest_read_aperf_mperf(void) +{ + int i; + + for (i = 0; i < NUM_ITERATIONS; i++) + GUEST_SYNC2(rdmsr(MSR_IA32_APERF), rdmsr(MSR_IA32_MPERF)); +} + +#define L2_GUEST_STACK_SIZE 64 + +static void l2_guest_code(void) +{ + guest_read_aperf_mperf(); + GUEST_DONE(); +} + +static void l1_svm_code(struct svm_test_data *svm) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + + generic_svm_setup(svm, l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + run_guest(vmcb, svm->vmcb_gpa); +} + +static void l1_vmx_code(struct vmx_pages *vmx) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + GUEST_ASSERT_EQ(prepare_for_vmx_operation(vmx), true); + GUEST_ASSERT_EQ(load_vmcs(vmx), true); + + prepare_vmcs(vmx, NULL, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* + * Enable MSR bitmaps (the bitmap itself is allocated, zeroed, and set + * in the VMCS by prepare_vmcs()), as MSR exiting mandatory on Intel. + */ + vmwrite(CPU_BASED_VM_EXEC_CONTROL, + vmreadz(CPU_BASED_VM_EXEC_CONTROL) | CPU_BASED_USE_MSR_BITMAPS); + + GUEST_ASSERT(!vmwrite(GUEST_RIP, (u64)l2_guest_code)); + GUEST_ASSERT(!vmlaunch()); +} + +static void guest_code(void *nested_test_data) +{ + guest_read_aperf_mperf(); + + if (this_cpu_has(X86_FEATURE_SVM)) + l1_svm_code(nested_test_data); + else if (this_cpu_has(X86_FEATURE_VMX)) + l1_vmx_code(nested_test_data); + else + GUEST_DONE(); + + TEST_FAIL("L2 should have signaled 'done'"); +} + +static void guest_no_aperfmperf(void) +{ + uint64_t msr_val; + uint8_t vector; + + vector = rdmsr_safe(MSR_IA32_APERF, &msr_val); + GUEST_ASSERT(vector == GP_VECTOR); + + vector = rdmsr_safe(MSR_IA32_APERF, &msr_val); + GUEST_ASSERT(vector == GP_VECTOR); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + const bool has_nested = kvm_cpu_has(X86_FEATURE_SVM) || kvm_cpu_has(X86_FEATURE_VMX); + uint64_t host_aperf_before, host_mperf_before; + vm_vaddr_t nested_test_data_gva; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int msr_fd, cpu, i; + + /* Sanity check that APERF/MPERF are unsupported by default. */ + vm = vm_create_with_one_vcpu(&vcpu, guest_no_aperfmperf); + vcpu_run(vcpu); + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); + kvm_vm_free(vm); + + cpu = pin_self_to_any_cpu(); + + msr_fd = open_dev_msr(cpu); + + /* + * This test requires a non-standard VM initialization, because + * KVM_ENABLE_CAP cannot be used on a VM file descriptor after + * a VCPU has been created. + */ + vm = vm_create(1); + + TEST_REQUIRE(vm_check_cap(vm, KVM_CAP_X86_DISABLE_EXITS) & + KVM_X86_DISABLE_EXITS_APERFMPERF); + + vm_enable_cap(vm, KVM_CAP_X86_DISABLE_EXITS, + KVM_X86_DISABLE_EXITS_APERFMPERF); + + vcpu = vm_vcpu_add(vm, 0, guest_code); + + if (!has_nested) + nested_test_data_gva = NONCANONICAL; + else if (kvm_cpu_has(X86_FEATURE_SVM)) + vcpu_alloc_svm(vm, &nested_test_data_gva); + else + vcpu_alloc_vmx(vm, &nested_test_data_gva); + + vcpu_args_set(vcpu, 1, nested_test_data_gva); + + host_aperf_before = read_dev_msr(msr_fd, MSR_IA32_APERF); + host_mperf_before = read_dev_msr(msr_fd, MSR_IA32_MPERF); + + for (i = 0; i <= NUM_ITERATIONS * (1 + has_nested); i++) { + uint64_t host_aperf_after, host_mperf_after; + uint64_t guest_aperf, guest_mperf; + struct ucall uc; + + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_DONE: + goto done; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + case UCALL_SYNC: + guest_aperf = uc.args[0]; + guest_mperf = uc.args[1]; + + host_aperf_after = read_dev_msr(msr_fd, MSR_IA32_APERF); + host_mperf_after = read_dev_msr(msr_fd, MSR_IA32_MPERF); + + TEST_ASSERT(host_aperf_before < guest_aperf, + "APERF: host_before (0x%" PRIx64 ") >= guest (0x%" PRIx64 ")", + host_aperf_before, guest_aperf); + TEST_ASSERT(guest_aperf < host_aperf_after, + "APERF: guest (0x%" PRIx64 ") >= host_after (0x%" PRIx64 ")", + guest_aperf, host_aperf_after); + TEST_ASSERT(host_mperf_before < guest_mperf, + "MPERF: host_before (0x%" PRIx64 ") >= guest (0x%" PRIx64 ")", + host_mperf_before, guest_mperf); + TEST_ASSERT(guest_mperf < host_mperf_after, + "MPERF: guest (0x%" PRIx64 ") >= host_after (0x%" PRIx64 ")", + guest_mperf, host_mperf_after); + + host_aperf_before = host_aperf_after; + host_mperf_before = host_mperf_after; + + break; + } + } + TEST_FAIL("Didn't receive UCALL_DONE\n"); +done: + kvm_vm_free(vm); + close(msr_fd); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c index 390ae2d87493..0eb371c62ab8 100644 --- a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c +++ b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c @@ -74,6 +74,7 @@ int main(int argc, char *argv[]) int testcase; char test[80]; + TEST_REQUIRE(this_cpu_has(X86_FEATURE_MWAIT)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_DISABLE_QUIRKS2)); ksft_print_header(); diff --git a/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c index 32b2794b78fe..8463a9956410 100644 --- a/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c +++ b/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c @@ -343,6 +343,12 @@ static void guest_code_permission_bitmap(void) data = test_rdmsr(MSR_GS_BASE); GUEST_ASSERT(data == MSR_GS_BASE); + /* Access the MSRs again to ensure KVM has disabled interception.*/ + data = test_rdmsr(MSR_FS_BASE); + GUEST_ASSERT(data != MSR_FS_BASE); + data = test_rdmsr(MSR_GS_BASE); + GUEST_ASSERT(data != MSR_GS_BASE); + GUEST_DONE(); } @@ -682,6 +688,8 @@ KVM_ONE_VCPU_TEST(user_msr, msr_permission_bitmap, guest_code_permission_bitmap) "Expected ucall state to be UCALL_SYNC."); vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_gs); run_guest_then_process_rdmsr(vcpu, MSR_GS_BASE); + + vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_allow); run_guest_then_process_ucall_done(vcpu); } diff --git a/tools/testing/selftests/kvm/x86/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86/xen_shinfo_test.c index 287829f850f7..23909b501ac2 100644 --- a/tools/testing/selftests/kvm/x86/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86/xen_shinfo_test.c @@ -547,15 +547,9 @@ int main(int argc, char *argv[]) int irq_fd[2] = { -1, -1 }; if (do_eventfd_tests) { - irq_fd[0] = eventfd(0, 0); - irq_fd[1] = eventfd(0, 0); + irq_fd[0] = kvm_new_eventfd(); + irq_fd[1] = kvm_new_eventfd(); - /* Unexpected, but not a KVM failure */ - if (irq_fd[0] == -1 || irq_fd[1] == -1) - do_evtchn_tests = do_eventfd_tests = false; - } - - if (do_eventfd_tests) { irq_routes.info.nr = 2; irq_routes.entries[0].gsi = 32; @@ -572,15 +566,8 @@ int main(int argc, char *argv[]) vm_ioctl(vm, KVM_SET_GSI_ROUTING, &irq_routes.info); - struct kvm_irqfd ifd = { }; - - ifd.fd = irq_fd[0]; - ifd.gsi = 32; - vm_ioctl(vm, KVM_IRQFD, &ifd); - - ifd.fd = irq_fd[1]; - ifd.gsi = 33; - vm_ioctl(vm, KVM_IRQFD, &ifd); + kvm_assign_irqfd(vm, 32, irq_fd[0]); + kvm_assign_irqfd(vm, 33, irq_fd[1]); struct sigaction sa = { }; sa.sa_handler = handle_alrm; diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index aa7400ed0e99..f0d9c035641d 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -31,6 +31,7 @@ uint64_t pmd_pagesize; #define INPUT_MAX 80 #define PID_FMT "%d,0x%lx,0x%lx,%d" +#define PID_FMT_OFFSET "%d,0x%lx,0x%lx,%d,%d" #define PATH_FMT "%s,0x%lx,0x%lx,%d" #define PFN_MASK ((1UL<<55)-1) @@ -483,7 +484,7 @@ void split_thp_in_pagecache_to_order_at(size_t fd_size, const char *fs_loc, write_debugfs(PID_FMT, getpid(), (uint64_t)addr, (uint64_t)addr + fd_size, order); else - write_debugfs(PID_FMT, getpid(), (uint64_t)addr, + write_debugfs(PID_FMT_OFFSET, getpid(), (uint64_t)addr, (uint64_t)addr + fd_size, order, offset); for (i = 0; i < fd_size; i++) diff --git a/tools/testing/selftests/net/gre_ipv6_lladdr.sh b/tools/testing/selftests/net/gre_ipv6_lladdr.sh index 5b34f6e1f831..48eb999a3120 100755 --- a/tools/testing/selftests/net/gre_ipv6_lladdr.sh +++ b/tools/testing/selftests/net/gre_ipv6_lladdr.sh @@ -24,7 +24,10 @@ setup_basenet() ip -netns "${NS0}" address add dev lo 2001:db8::10/64 nodad } -# Check if network device has an IPv6 link-local address assigned. +# Check the IPv6 configuration of a network device. +# +# We currently check the generation of the link-local IPv6 address and the +# creation of the ff00::/8 multicast route. # # Parameters: # @@ -35,7 +38,7 @@ setup_basenet() # a link-local address) # * $4: The user visible name for the scenario being tested # -check_ipv6_ll_addr() +check_ipv6_device_config() { local DEV="$1" local EXTRA_MATCH="$2" @@ -45,7 +48,11 @@ check_ipv6_ll_addr() RET=0 set +e ip -netns "${NS0}" -6 address show dev "${DEV}" scope link | grep "fe80::" | grep -q "${EXTRA_MATCH}" - check_err_fail "${XRET}" $? "" + check_err_fail "${XRET}" $? "IPv6 link-local address generation" + + ip -netns "${NS0}" -6 route show table local type multicast ff00::/8 proto kernel | grep -q "${DEV}" + check_err_fail 0 $? "IPv6 multicast route creation" + log_test "${MSG}" set -e } @@ -102,20 +109,20 @@ test_gre_device() ;; esac - # Check that IPv6 link-local address is generated when device goes up + # Check the IPv6 device configuration when it goes up ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}" ip -netns "${NS0}" link set dev gretest up - check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "config: ${MSG}" + check_ipv6_device_config gretest "${MATCH_REGEXP}" "${XRET}" "config: ${MSG}" # Now disable link-local address generation ip -netns "${NS0}" link set dev gretest down ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode=1 ip -netns "${NS0}" link set dev gretest up - # Check that link-local address generation works when re-enabled while - # the device is already up + # Check the IPv6 device configuration when link-local address + # generation is re-enabled while the device is already up ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}" - check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "update: ${MSG}" + check_ipv6_device_config gretest "${MATCH_REGEXP}" "${XRET}" "update: ${MSG}" ip -netns "${NS0}" link del dev gretest } @@ -126,7 +133,7 @@ test_gre4() local MODE for GRE_TYPE in "gre" "gretap"; do - printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n" + printf "\n####\nTesting IPv6 configuration of ${GRE_TYPE} devices\n####\n\n" for MODE in "eui64" "none" "stable-privacy" "random"; do test_gre_device "${GRE_TYPE}" 192.0.2.10 192.0.2.11 "${MODE}" @@ -142,7 +149,7 @@ test_gre6() local MODE for GRE_TYPE in "ip6gre" "ip6gretap"; do - printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n" + printf "\n####\nTesting IPv6 configuration of ${GRE_TYPE} devices\n####\n\n" for MODE in "eui64" "none" "stable-privacy" "random"; do test_gre_device "${GRE_TYPE}" 2001:db8::10 2001:db8::11 "${MODE}" diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 006fdadcc4b9..86a216e9aca8 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -312,7 +312,7 @@ log_test_result() local test_name=$1; shift local opt_str=$1; shift local result=$1; shift - local retmsg=$1; shift + local retmsg=$1 printf "TEST: %-60s [%s]\n" "$test_name $opt_str" "$result" if [[ $retmsg ]]; then diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index e47788bfa671..4c7e51336ab2 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -4,7 +4,8 @@ top_srcdir = ../../../../.. CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) -TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ +TEST_PROGS := mptcp_connect.sh mptcp_connect_mmap.sh mptcp_connect_sendfile.sh \ + mptcp_connect_checksum.sh pm_netlink.sh mptcp_join.sh diag.sh \ simult_flows.sh mptcp_sockopt.sh userspace_pm.sh TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq mptcp_diag diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh b/tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh new file mode 100755 index 000000000000..ce93ec2f107f --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh @@ -0,0 +1,5 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \ + "$(dirname "${0}")/mptcp_connect.sh" -C "${@}" diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh b/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh new file mode 100755 index 000000000000..5dd30f9394af --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh @@ -0,0 +1,5 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \ + "$(dirname "${0}")/mptcp_connect.sh" -m mmap "${@}" diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh b/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh new file mode 100755 index 000000000000..1d16fb1cc9bb --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh @@ -0,0 +1,5 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \ + "$(dirname "${0}")/mptcp_connect.sh" -m sendfile "${@}" diff --git a/tools/testing/selftests/net/netfilter/.gitignore b/tools/testing/selftests/net/netfilter/.gitignore index 64c4f8d9aa6c..5d2be9a00627 100644 --- a/tools/testing/selftests/net/netfilter/.gitignore +++ b/tools/testing/selftests/net/netfilter/.gitignore @@ -5,3 +5,4 @@ conntrack_dump_flush conntrack_reverse_clash sctp_collision nf_queue +udpclash diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile index e9b2f553588d..a98ed892f55f 100644 --- a/tools/testing/selftests/net/netfilter/Makefile +++ b/tools/testing/selftests/net/netfilter/Makefile @@ -15,6 +15,7 @@ TEST_PROGS += conntrack_tcp_unreplied.sh TEST_PROGS += conntrack_resize.sh TEST_PROGS += conntrack_sctp_collision.sh TEST_PROGS += conntrack_vrf.sh +TEST_PROGS += conntrack_clash.sh TEST_PROGS += conntrack_reverse_clash.sh TEST_PROGS += ipvs.sh TEST_PROGS += nf_conntrack_packetdrill.sh @@ -44,6 +45,7 @@ TEST_GEN_FILES += connect_close nf_queue TEST_GEN_FILES += conntrack_dump_flush TEST_GEN_FILES += conntrack_reverse_clash TEST_GEN_FILES += sctp_collision +TEST_GEN_FILES += udpclash include ../../lib.mk @@ -52,6 +54,7 @@ $(OUTPUT)/nf_queue: LDLIBS += $(MNL_LDLIBS) $(OUTPUT)/conntrack_dump_flush: CFLAGS += $(MNL_CFLAGS) $(OUTPUT)/conntrack_dump_flush: LDLIBS += $(MNL_LDLIBS) +$(OUTPUT)/udpclash: LDLIBS += -lpthread TEST_FILES := lib.sh TEST_FILES += packetdrill diff --git a/tools/testing/selftests/net/netfilter/conntrack_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_clash.sh new file mode 100755 index 000000000000..606a43a60f73 --- /dev/null +++ b/tools/testing/selftests/net/netfilter/conntrack_clash.sh @@ -0,0 +1,174 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh + +clash_resolution_active=0 +dport=22111 +ret=0 + +cleanup() +{ + # netns cleanup also zaps any remaining socat echo server. + cleanup_all_ns +} + +checktool "nft --version" "run test without nft" +checktool "conntrack --version" "run test without conntrack" +checktool "socat -h" "run test without socat" + +trap cleanup EXIT + +setup_ns nsclient1 nsclient2 nsrouter + +ip netns exec "$nsrouter" nft -f -<<EOF +table ip t { + chain lb { + meta l4proto udp dnat to numgen random mod 3 map { 0 : 10.0.2.1 . 9000, 1 : 10.0.2.1 . 9001, 2 : 10.0.2.1 . 9002 } + } + + chain prerouting { + type nat hook prerouting priority dstnat + + udp dport $dport counter jump lb + } + + chain output { + type nat hook output priority dstnat + + udp dport $dport counter jump lb + } +} +EOF + +load_simple_ruleset() +{ +ip netns exec "$1" nft -f -<<EOF +table ip t { + chain forward { + type filter hook forward priority 0 + + ct state new counter + } +} +EOF +} + +spawn_servers() +{ + local ns="$1" + local ports="9000 9001 9002" + + for port in $ports; do + ip netns exec "$ns" socat UDP-RECVFROM:$port,fork PIPE 2>/dev/null & + done + + for port in $ports; do + wait_local_port_listen "$ns" $port udp + done +} + +add_addr() +{ + local ns="$1" + local dev="$2" + local i="$3" + local j="$4" + + ip -net "$ns" link set "$dev" up + ip -net "$ns" addr add "10.0.$i.$j/24" dev "$dev" +} + +ping_test() +{ + local ns="$1" + local daddr="$2" + + if ! ip netns exec "$ns" ping -q -c 1 $daddr > /dev/null;then + echo "FAIL: ping from $ns to $daddr" + exit 1 + fi +} + +run_one_clash_test() +{ + local ns="$1" + local ctns="$2" + local daddr="$3" + local dport="$4" + local entries + local cre + + if ! ip netns exec "$ns" ./udpclash $daddr $dport;then + echo "INFO: did not receive expected number of replies for $daddr:$dport" + ip netns exec "$ctns" conntrack -S + # don't fail: check if clash resolution triggered after all. + fi + + entries=$(ip netns exec "$ctns" conntrack -S | wc -l) + cre=$(ip netns exec "$ctns" conntrack -S | grep "clash_resolve=0" | wc -l) + + if [ "$cre" -ne "$entries" ];then + clash_resolution_active=1 + return 0 + fi + + # not a failure: clash resolution logic did not trigger. + # With right timing, xmit completed sequentially and + # no parallel insertion occurs. + return $ksft_skip +} + +run_clash_test() +{ + local ns="$1" + local ctns="$2" + local daddr="$3" + local dport="$4" + local softerr=0 + + for i in $(seq 1 10);do + run_one_clash_test "$ns" "$ctns" "$daddr" "$dport" + local rv=$? + if [ $rv -eq 0 ];then + echo "PASS: clash resolution test for $daddr:$dport on attempt $i" + return 0 + elif [ $rv -eq $ksft_skip ]; then + softerr=1 + fi + done + + [ $softerr -eq 1 ] && echo "SKIP: clash resolution for $daddr:$dport did not trigger" +} + +ip link add veth0 netns "$nsclient1" type veth peer name veth0 netns "$nsrouter" +ip link add veth0 netns "$nsclient2" type veth peer name veth1 netns "$nsrouter" +add_addr "$nsclient1" veth0 1 1 +add_addr "$nsclient2" veth0 2 1 +add_addr "$nsrouter" veth0 1 99 +add_addr "$nsrouter" veth1 2 99 + +ip -net "$nsclient1" route add default via 10.0.1.99 +ip -net "$nsclient2" route add default via 10.0.2.99 +ip netns exec "$nsrouter" sysctl -q net.ipv4.ip_forward=1 + +ping_test "$nsclient1" 10.0.1.99 +ping_test "$nsclient1" 10.0.2.1 +ping_test "$nsclient2" 10.0.1.1 + +spawn_servers "$nsclient2" + +# exercise clash resolution with nat: +# nsrouter is supposed to dnat to 10.0.2.1:900{0,1,2,3}. +run_clash_test "$nsclient1" "$nsrouter" 10.0.1.99 "$dport" + +# exercise clash resolution without nat. +load_simple_ruleset "$nsclient2" +run_clash_test "$nsclient2" "$nsclient2" 127.0.0.1 9001 + +if [ $clash_resolution_active -eq 0 ];then + [ "$ret" -eq 0 ] && ret=$ksft_skip + echo "SKIP: Clash resolution did not trigger" +fi + +exit $ret diff --git a/tools/testing/selftests/net/netfilter/conntrack_resize.sh b/tools/testing/selftests/net/netfilter/conntrack_resize.sh index 9e033e80219e..788cd56ea4a0 100755 --- a/tools/testing/selftests/net/netfilter/conntrack_resize.sh +++ b/tools/testing/selftests/net/netfilter/conntrack_resize.sh @@ -12,6 +12,9 @@ tmpfile="" tmpfile_proc="" tmpfile_uniq="" ret=0 +have_socat=0 + +socat -h > /dev/null && have_socat=1 insert_count=2000 [ "$KSFT_MACHINE_SLOW" = "yes" ] && insert_count=400 @@ -123,7 +126,7 @@ ctflush() { done } -ctflood() +ct_pingflood() { local ns="$1" local duration="$2" @@ -152,6 +155,44 @@ ctflood() wait } +ct_udpflood() +{ + local ns="$1" + local duration="$2" + local now=$(date +%s) + local end=$((now + duration)) + + [ $have_socat -ne "1" ] && return + + while [ $now -lt $end ]; do +ip netns exec "$ns" bash<<"EOF" + for i in $(seq 1 100);do + dport=$(((RANDOM%65536)+1)) + + echo bar | socat -u STDIN UDP:"127.0.0.1:$dport" & + done > /dev/null 2>&1 + wait +EOF + now=$(date +%s) + done +} + +ct_udpclash() +{ + local ns="$1" + local duration="$2" + local now=$(date +%s) + local end=$((now + duration)) + + [ -x udpclash ] || return + + while [ $now -lt $end ]; do + ip netns exec "$ns" ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1 + + now=$(date +%s) + done +} + # dump to /dev/null. We don't want dumps to cause infinite loops # or use-after-free even when conntrack table is altered while dumps # are in progress. @@ -169,6 +210,48 @@ ct_nulldump() wait } +ct_nulldump_loop() +{ + local ns="$1" + local duration="$2" + local now=$(date +%s) + local end=$((now + duration)) + + while [ $now -lt $end ]; do + ct_nulldump "$ns" + sleep $((RANDOM%2)) + now=$(date +%s) + done +} + +change_timeouts() +{ + local ns="$1" + local r1=$((RANDOM%2)) + local r2=$((RANDOM%2)) + + [ "$r1" -eq 1 ] && ip netns exec "$ns" sysctl -q net.netfilter.nf_conntrack_icmp_timeout=$((RANDOM%5)) + [ "$r2" -eq 1 ] && ip netns exec "$ns" sysctl -q net.netfilter.nf_conntrack_udp_timeout=$((RANDOM%5)) +} + +ct_change_timeouts_loop() +{ + local ns="$1" + local duration="$2" + local now=$(date +%s) + local end=$((now + duration)) + + while [ $now -lt $end ]; do + change_timeouts "$ns" + sleep $((RANDOM%2)) + now=$(date +%s) + done + + # restore defaults + ip netns exec "$ns" sysctl -q net.netfilter.nf_conntrack_icmp_timeout=30 + ip netns exec "$ns" sysctl -q net.netfilter.nf_conntrack_udp_timeout=30 +} + check_taint() { local tainted_then="$1" @@ -198,10 +281,14 @@ insert_flood() r=$((RANDOM%$insert_count)) - ctflood "$n" "$timeout" "floodresize" & + ct_pingflood "$n" "$timeout" "floodresize" & + ct_udpflood "$n" "$timeout" & + ct_udpclash "$n" "$timeout" & + insert_ctnetlink "$n" "$r" & ctflush "$n" "$timeout" & - ct_nulldump "$n" & + ct_nulldump_loop "$n" "$timeout" & + ct_change_timeouts_loop "$n" "$timeout" & wait } @@ -306,7 +393,7 @@ test_dump_all() ip netns exec "$nsclient1" sysctl -q net.netfilter.nf_conntrack_icmp_timeout=3600 - ctflood "$nsclient1" $timeout "dumpall" & + ct_pingflood "$nsclient1" $timeout "dumpall" & insert_ctnetlink "$nsclient2" $insert_count wait @@ -368,7 +455,7 @@ test_conntrack_disable() ct_flush_once "$nsclient1" ct_flush_once "$nsclient2" - ctflood "$nsclient1" "$timeout" "conntrack disable" + ct_pingflood "$nsclient1" "$timeout" "conntrack disable" ip netns exec "$nsclient2" ping -q -c 1 127.0.0.1 >/dev/null 2>&1 # Disabled, should not have picked up any connection. diff --git a/tools/testing/selftests/net/netfilter/nft_concat_range.sh b/tools/testing/selftests/net/netfilter/nft_concat_range.sh index cd12b8b5ac0e..20e76b395c85 100755 --- a/tools/testing/selftests/net/netfilter/nft_concat_range.sh +++ b/tools/testing/selftests/net/netfilter/nft_concat_range.sh @@ -1311,6 +1311,9 @@ maybe_send_match() { # - remove some elements, check that packets don't match anymore test_correctness_main() { range_size=1 + + send_nomatch $((end + 1)) $((end + 1 + src_delta)) || return 1 + for i in $(seq "${start}" $((start + count))); do local elem="" diff --git a/tools/testing/selftests/net/netfilter/udpclash.c b/tools/testing/selftests/net/netfilter/udpclash.c new file mode 100644 index 000000000000..85c7b906ad08 --- /dev/null +++ b/tools/testing/selftests/net/netfilter/udpclash.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Usage: ./udpclash <IP> <PORT> + * + * Emit THREAD_COUNT UDP packets sharing the same saddr:daddr pair. + * + * This mimics DNS resolver libraries that emit A and AAAA requests + * in parallel. + * + * This exercises conntrack clash resolution logic added and later + * refined in + * + * 71d8c47fc653 ("netfilter: conntrack: introduce clash resolution on insertion race") + * ed07d9a021df ("netfilter: nf_conntrack: resolve clash for matching conntracks") + * 6a757c07e51f ("netfilter: conntrack: allow insertion of clashing entries") + */ +#include <stdio.h> +#include <string.h> +#include <stdlib.h> +#include <unistd.h> +#include <arpa/inet.h> +#include <sys/socket.h> +#include <pthread.h> + +#define THREAD_COUNT 128 + +struct thread_args { + const struct sockaddr_in *si_remote; + int sockfd; +}; + +static int wait = 1; + +static void *thread_main(void *varg) +{ + const struct sockaddr_in *si_remote; + const struct thread_args *args = varg; + static const char msg[] = "foo"; + + si_remote = args->si_remote; + + while (wait == 1) + ; + + if (sendto(args->sockfd, msg, strlen(msg), MSG_NOSIGNAL, + (struct sockaddr *)si_remote, sizeof(*si_remote)) < 0) + exit(111); + + return varg; +} + +static int run_test(int fd, const struct sockaddr_in *si_remote) +{ + struct thread_args thread_args = { + .si_remote = si_remote, + .sockfd = fd, + }; + pthread_t *tid = calloc(THREAD_COUNT, sizeof(pthread_t)); + unsigned int repl_count = 0, timeout = 0; + int i; + + if (!tid) { + perror("calloc"); + return 1; + } + + for (i = 0; i < THREAD_COUNT; i++) { + int err = pthread_create(&tid[i], NULL, &thread_main, &thread_args); + + if (err != 0) { + perror("pthread_create"); + exit(1); + } + } + + wait = 0; + + for (i = 0; i < THREAD_COUNT; i++) + pthread_join(tid[i], NULL); + + while (repl_count < THREAD_COUNT) { + struct sockaddr_in si_repl; + socklen_t si_repl_len = sizeof(si_repl); + char repl[512]; + ssize_t ret; + + ret = recvfrom(fd, repl, sizeof(repl), MSG_NOSIGNAL, + (struct sockaddr *) &si_repl, &si_repl_len); + if (ret < 0) { + if (timeout++ > 5000) { + fputs("timed out while waiting for reply from thread\n", stderr); + break; + } + + /* give reply time to pass though the stack */ + usleep(1000); + continue; + } + + if (si_repl_len != sizeof(*si_remote)) { + fprintf(stderr, "warning: reply has unexpected repl_len %d vs %d\n", + (int)si_repl_len, (int)sizeof(si_repl)); + } else if (si_remote->sin_addr.s_addr != si_repl.sin_addr.s_addr || + si_remote->sin_port != si_repl.sin_port) { + char a[64], b[64]; + + inet_ntop(AF_INET, &si_remote->sin_addr, a, sizeof(a)); + inet_ntop(AF_INET, &si_repl.sin_addr, b, sizeof(b)); + + fprintf(stderr, "reply from wrong source: want %s:%d got %s:%d\n", + a, ntohs(si_remote->sin_port), b, ntohs(si_repl.sin_port)); + } + + repl_count++; + } + + printf("got %d of %d replies\n", repl_count, THREAD_COUNT); + + free(tid); + + return repl_count == THREAD_COUNT ? 0 : 1; +} + +int main(int argc, char *argv[]) +{ + struct sockaddr_in si_local = { + .sin_family = AF_INET, + }; + struct sockaddr_in si_remote = { + .sin_family = AF_INET, + }; + int fd, ret; + + if (argc < 3) { + fputs("Usage: send_udp <daddr> <dport>\n", stderr); + return 1; + } + + si_remote.sin_port = htons(atoi(argv[2])); + si_remote.sin_addr.s_addr = inet_addr(argv[1]); + + fd = socket(AF_INET, SOCK_DGRAM|SOCK_CLOEXEC|SOCK_NONBLOCK, IPPROTO_UDP); + if (fd < 0) { + perror("socket"); + return 1; + } + + if (bind(fd, (struct sockaddr *)&si_local, sizeof(si_local)) < 0) { + perror("bind"); + return 1; + } + + ret = run_test(fd, &si_remote); + + close(fd); + + return ret; +} diff --git a/tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt b/tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt new file mode 100644 index 000000000000..09aabc775e80 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 + +--mss=1000 + +`./defaults.sh +sysctl -q net.ipv4.tcp_rmem="4096 131072 $((32*1024*1024))"` + +// Test that a not-yet-accepted socket does not change +// its initial sk_rcvbuf (tcp_rmem[1]) when receiving ooo packets. + + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 65535 <mss 1000,nop,nop,sackOK,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 10> + +.1 < . 1:1(0) ack 1 win 257 + +0 < . 2001:41001(39000) ack 1 win 257 + +0 > . 1:1(0) ack 1 <nop,nop,sack 2001:41001> + +0 < . 41001:101001(60000) ack 1 win 257 + +0 > . 1:1(0) ack 1 <nop,nop,sack 2001:101001> + +0 < . 1:1001(1000) ack 1 win 257 + +0 > . 1:1(0) ack 1001 <nop,nop,sack 2001:101001> + +0 < . 1001:2001(1000) ack 1 win 257 + +0 > . 1:1(0) ack 101001 + + +0 accept(3, ..., ...) = 4 + + +0 %{ assert SK_MEMINFO_RCVBUF == 131072, SK_MEMINFO_RCVBUF }% + + +0 close(4) = 0 + +0 close(3) = 0 + +// Test that ooo packets for accepted sockets do increase sk_rcvbuf + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 65535 <mss 1000,nop,nop,sackOK,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 10> + +.1 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + + +0 < . 2001:41001(39000) ack 1 win 257 + +0 > . 1:1(0) ack 1 <nop,nop,sack 2001:41001> + +0 < . 41001:101001(60000) ack 1 win 257 + +0 > . 1:1(0) ack 1 <nop,nop,sack 2001:101001> + + +0 %{ assert SK_MEMINFO_RCVBUF > 131072, SK_MEMINFO_RCVBUF }% + diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index 1dc337c709f8..b17e032a6d75 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -48,7 +48,7 @@ run_one() { cfg_veth - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 100 ${rx_args} & local PID1=$! wait_local_port_listen ${PEER_NS} 8000 udp @@ -95,7 +95,7 @@ run_one_nat() { # will land on the 'plain' one ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 & local PID1=$! - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 100 ${family} -b ${addr2%/*} ${rx_args} & local PID2=$! wait_local_port_listen "${PEER_NS}" 8000 udp @@ -117,9 +117,9 @@ run_one_2sock() { cfg_veth - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} -p 12345 & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 100 ${rx_args} -p 12345 & local PID1=$! - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 100 ${rx_args} & local PID2=$! wait_local_port_listen "${PEER_NS}" 12345 udp diff --git a/tools/testing/selftests/net/vlan_hw_filter.sh b/tools/testing/selftests/net/vlan_hw_filter.sh index 7bc804ffaf7c..0fb56baf28e4 100755 --- a/tools/testing/selftests/net/vlan_hw_filter.sh +++ b/tools/testing/selftests/net/vlan_hw_filter.sh @@ -3,27 +3,101 @@ readonly NETNS="ns-$(mktemp -u XXXXXX)" +ALL_TESTS=" + test_vlan_filter_check + test_vlan0_del_crash_01 + test_vlan0_del_crash_02 + test_vlan0_del_crash_03 + test_vid0_memleak +" + ret=0 +setup() { + ip netns add ${NETNS} +} + cleanup() { - ip netns del $NETNS + ip netns del $NETNS 2>/dev/null } trap cleanup EXIT fail() { - echo "ERROR: ${1:-unexpected return code} (ret: $_)" >&2 - ret=1 + echo "ERROR: ${1:-unexpected return code} (ret: $_)" >&2 + ret=1 +} + +tests_run() +{ + local current_test + for current_test in ${TESTS:-$ALL_TESTS}; do + $current_test + done +} + +test_vlan_filter_check() { + setup + ip netns exec ${NETNS} ip link add bond0 type bond mode 0 + ip netns exec ${NETNS} ip link add bond_slave_1 type veth peer veth2 + ip netns exec ${NETNS} ip link set bond_slave_1 master bond0 + ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off + ip netns exec ${NETNS} ip link add link bond_slave_1 name bond_slave_1.0 type vlan id 0 + ip netns exec ${NETNS} ip link add link bond0 name bond0.0 type vlan id 0 + ip netns exec ${NETNS} ip link set bond_slave_1 nomaster + ip netns exec ${NETNS} ip link del veth2 || fail "Please check vlan HW filter function" + cleanup } -ip netns add ${NETNS} -ip netns exec ${NETNS} ip link add bond0 type bond mode 0 -ip netns exec ${NETNS} ip link add bond_slave_1 type veth peer veth2 -ip netns exec ${NETNS} ip link set bond_slave_1 master bond0 -ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off -ip netns exec ${NETNS} ip link add link bond_slave_1 name bond_slave_1.0 type vlan id 0 -ip netns exec ${NETNS} ip link add link bond0 name bond0.0 type vlan id 0 -ip netns exec ${NETNS} ip link set bond_slave_1 nomaster -ip netns exec ${NETNS} ip link del veth2 || fail "Please check vlan HW filter function" +#enable vlan_filter feature of real_dev with vlan0 during running time +test_vlan0_del_crash_01() { + setup + ip netns exec ${NETNS} ip link add bond0 type bond mode 0 + ip netns exec ${NETNS} ip link add link bond0 name vlan0 type vlan id 0 protocol 802.1q + ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off + ip netns exec ${NETNS} ifconfig bond0 up + ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter on + ip netns exec ${NETNS} ifconfig bond0 down + ip netns exec ${NETNS} ifconfig bond0 up + ip netns exec ${NETNS} ip link del vlan0 || fail "Please check vlan HW filter function" + cleanup +} + +#enable vlan_filter feature and add vlan0 for real_dev during running time +test_vlan0_del_crash_02() { + setup + ip netns exec ${NETNS} ip link add bond0 type bond mode 0 + ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off + ip netns exec ${NETNS} ifconfig bond0 up + ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter on + ip netns exec ${NETNS} ip link add link bond0 name vlan0 type vlan id 0 protocol 802.1q + ip netns exec ${NETNS} ifconfig bond0 down + ip netns exec ${NETNS} ifconfig bond0 up + ip netns exec ${NETNS} ip link del vlan0 || fail "Please check vlan HW filter function" + cleanup +} + +#enable vlan_filter feature of real_dev during running time +#test kernel_bug of vlan unregister +test_vlan0_del_crash_03() { + setup + ip netns exec ${NETNS} ip link add bond0 type bond mode 0 + ip netns exec ${NETNS} ip link add link bond0 name vlan0 type vlan id 0 protocol 802.1q + ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off + ip netns exec ${NETNS} ifconfig bond0 up + ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter on + ip netns exec ${NETNS} ifconfig bond0 down + ip netns exec ${NETNS} ip link del vlan0 || fail "Please check vlan HW filter function" + cleanup +} + +test_vid0_memleak() { + setup + ip netns exec ${NETNS} ip link add bond0 up type bond mode 0 + ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off + ip netns exec ${NETNS} ip link del dev bond0 || fail "Please check vlan HW filter function" + cleanup +} +tests_run exit $ret diff --git a/tools/testing/selftests/sched_ext/exit.c b/tools/testing/selftests/sched_ext/exit.c index 9451782689de..ee25824b1cbe 100644 --- a/tools/testing/selftests/sched_ext/exit.c +++ b/tools/testing/selftests/sched_ext/exit.c @@ -22,6 +22,14 @@ static enum scx_test_status run(void *ctx) struct bpf_link *link; char buf[16]; + /* + * On single-CPU systems, ops.select_cpu() is never + * invoked, so skip this test to avoid getting stuck + * indefinitely. + */ + if (tc == EXIT_SELECT_CPU && libbpf_num_possible_cpus() == 1) + continue; + skel = exit__open(); SCX_ENUM_INIT(skel); skel->rodata->exit_point = tc; diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index 9aa44d8176d9..c6db7fa94f55 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -128,6 +128,32 @@ ] }, { + "id": "5456", + "name": "Test htb_dequeue_tree with deactivation and row emptying", + "category": [ + "qdisc", + "htb" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: htb default 1", + "$TC class add dev $DUMMY parent 1: classid 1:1 htb rate 64bit ", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2: netem", + "$TC qdisc add dev $DUMMY parent 2:1 handle 3: blackhole" + ], + "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.11.11", + "expExitCode": "1", + "verifyCmd": "$TC -j qdisc show dev $DUMMY", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DUMMY root" + ] + }, + { "id": "c024", "name": "Test TBF with SKBPRIO - catch qlen corner cases", "category": [ @@ -635,5 +661,108 @@ "$TC qdisc del dev $DUMMY handle 1:0 root", "$IP addr del 10.10.10.10/24 dev $DUMMY || true" ] + }, + { + "id": "d74b", + "name": "Test use-after-free with DRR/NETEM/BLACKHOLE chain", + "category": [ + "qdisc", + "hfsc", + "drr", + "netem", + "blackhole" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: drr", + "$TC filter add dev $DUMMY parent 1: basic classid 1:1", + "$TC class add dev $DUMMY parent 1: classid 1:1 drr", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2: hfsc def 1", + "$TC class add dev $DUMMY parent 2: classid 2:1 hfsc rt m1 8 d 1 m2 0", + "$TC qdisc add dev $DUMMY parent 2:1 handle 3: netem", + "$TC qdisc add dev $DUMMY parent 3:1 handle 4: blackhole", + "ping -c1 -W0.01 -I $DUMMY 10.10.11.11 || true", + "$TC class del dev $DUMMY classid 1:1" + ], + "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.11.11", + "expExitCode": "1", + "verifyCmd": "$TC -j class ls dev $DUMMY classid 1:1", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: drr" + ] + }, + { + "id": "be28", + "name": "Try to add fq_codel qdisc as a child of an hhf qdisc", + "category": [ + "qdisc", + "fq_codel", + "hhf" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle a: hhf" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent a: handle b: fq_codel", + "expExitCode": "2", + "verifyCmd": "$TC -j qdisc ls dev $DUMMY handle b:", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DUMMY root" + ] + }, + { + "id": "fcb5", + "name": "Try to add pie qdisc as a child of a drr qdisc", + "category": [ + "qdisc", + "pie", + "drr" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle a: drr" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent a: handle b: pie", + "expExitCode": "2", + "verifyCmd": "$TC -j qdisc ls dev $DUMMY handle b:", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DUMMY root" + ] + }, + { + "id": "7801", + "name": "Try to add fq qdisc as a child of an inexistent hfsc class", + "category": [ + "qdisc", + "sfq", + "hfsc" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle a: hfsc" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent a:fff2 sfq limit 4", + "expExitCode": "2", + "verifyCmd": "$TC -j qdisc ls dev $DUMMY handle b:", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DUMMY root" + ] } ] diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c index d14ffc7513ee..02bc6b00d76c 100644 --- a/virt/kvm/dirty_ring.c +++ b/virt/kvm/dirty_ring.c @@ -55,9 +55,6 @@ static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask) struct kvm_memory_slot *memslot; int as_id, id; - if (!mask) - return; - as_id = slot >> 16; id = (u16)slot; @@ -105,19 +102,38 @@ static inline bool kvm_dirty_gfn_harvested(struct kvm_dirty_gfn *gfn) return smp_load_acquire(&gfn->flags) & KVM_DIRTY_GFN_F_RESET; } -int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring) +int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring, + int *nr_entries_reset) { + /* + * To minimize mmu_lock contention, batch resets for harvested entries + * whose gfns are in the same slot, and are within N frame numbers of + * each other, where N is the number of bits in an unsigned long. For + * simplicity, process the current set of entries when the next entry + * can't be included in the batch. + * + * Track the current batch slot, the gfn offset into the slot for the + * batch, and the bitmask of gfns that need to be reset (relative to + * offset). Note, the offset may be adjusted backwards, e.g. so that + * a sequence of gfns X, X-1, ... X-N-1 can be batched. + */ u32 cur_slot, next_slot; u64 cur_offset, next_offset; - unsigned long mask; - int count = 0; + unsigned long mask = 0; struct kvm_dirty_gfn *entry; - bool first_round = true; - /* This is only needed to make compilers happy */ - cur_slot = cur_offset = mask = 0; + /* + * Ensure concurrent calls to KVM_RESET_DIRTY_RINGS are serialized, + * e.g. so that KVM fully resets all entries processed by a given call + * before returning to userspace. Holding slots_lock also protects + * the various memslot accesses. + */ + lockdep_assert_held(&kvm->slots_lock); + + while (likely((*nr_entries_reset) < INT_MAX)) { + if (signal_pending(current)) + return -EINTR; - while (true) { entry = &ring->dirty_gfns[ring->reset_index & (ring->size - 1)]; if (!kvm_dirty_gfn_harvested(entry)) @@ -130,35 +146,64 @@ int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring) kvm_dirty_gfn_set_invalid(entry); ring->reset_index++; - count++; - /* - * Try to coalesce the reset operations when the guest is - * scanning pages in the same slot. - */ - if (!first_round && next_slot == cur_slot) { - s64 delta = next_offset - cur_offset; - - if (delta >= 0 && delta < BITS_PER_LONG) { - mask |= 1ull << delta; - continue; + (*nr_entries_reset)++; + + if (mask) { + /* + * While the size of each ring is fixed, it's possible + * for the ring to be constantly re-dirtied/harvested + * while the reset is in-progress (the hard limit exists + * only to guard against the count becoming negative). + */ + cond_resched(); + + /* + * Try to coalesce the reset operations when the guest + * is scanning pages in the same slot. + */ + if (next_slot == cur_slot) { + s64 delta = next_offset - cur_offset; + + if (delta >= 0 && delta < BITS_PER_LONG) { + mask |= 1ull << delta; + continue; + } + + /* Backwards visit, careful about overflows! */ + if (delta > -BITS_PER_LONG && delta < 0 && + (mask << -delta >> -delta) == mask) { + cur_offset = next_offset; + mask = (mask << -delta) | 1; + continue; + } } - /* Backwards visit, careful about overflows! */ - if (delta > -BITS_PER_LONG && delta < 0 && - (mask << -delta >> -delta) == mask) { - cur_offset = next_offset; - mask = (mask << -delta) | 1; - continue; - } + /* + * Reset the slot for all the harvested entries that + * have been gathered, but not yet fully processed. + */ + kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask); } - kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask); + + /* + * The current slot was reset or this is the first harvested + * entry, (re)initialize the metadata. + */ cur_slot = next_slot; cur_offset = next_offset; mask = 1; - first_round = false; } - kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask); + /* + * Perform a final reset if there are harvested entries that haven't + * been processed, which is guaranteed if at least one harvested was + * found. The loop only performs a reset when the "next" entry can't + * be batched with the "current" entry(s), and that reset processes the + * _current_ entry(s); i.e. the last harvested entry, a.k.a. next, will + * always be left pending. + */ + if (mask) + kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask); /* * The request KVM_REQ_DIRTY_RING_SOFT_FULL will be cleared @@ -167,7 +212,7 @@ int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring) trace_kvm_dirty_ring_reset(ring); - return count; + return 0; } void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, u32 slot, u64 offset) diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 11e5d1e3f12e..6b1133a6617f 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -204,6 +204,11 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) int ret = 0; if (flags & EPOLLIN) { + /* + * WARNING: Do NOT take irqfds.lock in any path except EPOLLHUP, + * as KVM holds irqfds.lock when registering the irqfd with the + * eventfd. + */ u64 cnt; eventfd_ctx_do_read(irqfd->eventfd, &cnt); @@ -225,6 +230,11 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) /* The eventfd is closing, detach from KVM */ unsigned long iflags; + /* + * Taking irqfds.lock is safe here, as KVM holds a reference to + * the eventfd when registering the irqfd, i.e. this path can't + * be reached while kvm_irqfd_add() is running. + */ spin_lock_irqsave(&kvm->irqfds.lock, iflags); /* @@ -245,22 +255,14 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) return ret; } -static void -irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh, - poll_table *pt) -{ - struct kvm_kernel_irqfd *irqfd = - container_of(pt, struct kvm_kernel_irqfd, pt); - add_wait_queue_priority(wqh, &irqfd->wait); -} - -/* Must be called under irqfds.lock */ static void irqfd_update(struct kvm *kvm, struct kvm_kernel_irqfd *irqfd) { struct kvm_kernel_irq_routing_entry *e; struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS]; int n_entries; + lockdep_assert_held(&kvm->irqfds.lock); + n_entries = kvm_irq_map_gsi(kvm, entries, irqfd->gsi); write_seqcount_begin(&irqfd->irq_entry_sc); @@ -274,6 +276,63 @@ static void irqfd_update(struct kvm *kvm, struct kvm_kernel_irqfd *irqfd) write_seqcount_end(&irqfd->irq_entry_sc); } +struct kvm_irqfd_pt { + struct kvm_kernel_irqfd *irqfd; + struct kvm *kvm; + poll_table pt; + int ret; +}; + +static void kvm_irqfd_register(struct file *file, wait_queue_head_t *wqh, + poll_table *pt) +{ + struct kvm_irqfd_pt *p = container_of(pt, struct kvm_irqfd_pt, pt); + struct kvm_kernel_irqfd *irqfd = p->irqfd; + struct kvm *kvm = p->kvm; + + /* + * Note, irqfds.lock protects the irqfd's irq_entry, i.e. its routing, + * and irqfds.items. It does NOT protect registering with the eventfd. + */ + spin_lock_irq(&kvm->irqfds.lock); + + /* + * Initialize the routing information prior to adding the irqfd to the + * eventfd's waitqueue, as irqfd_wakeup() can be invoked as soon as the + * irqfd is registered. + */ + irqfd_update(kvm, irqfd); + + /* + * Add the irqfd as a priority waiter on the eventfd, with a custom + * wake-up handler, so that KVM *and only KVM* is notified whenever the + * underlying eventfd is signaled. + */ + init_waitqueue_func_entry(&irqfd->wait, irqfd_wakeup); + + /* + * Temporarily lie to lockdep about holding irqfds.lock to avoid a + * false positive regarding potential deadlock with irqfd_wakeup() + * (see irqfd_wakeup() for details). + * + * Adding to the wait queue will fail if there is already a priority + * waiter, i.e. if the eventfd is associated with another irqfd (in any + * VM). Note, kvm_irqfd_deassign() waits for all in-flight shutdown + * jobs to complete, i.e. ensures the irqfd has been removed from the + * eventfd's waitqueue before returning to userspace. + */ + spin_release(&kvm->irqfds.lock.dep_map, _RET_IP_); + p->ret = add_wait_queue_priority_exclusive(wqh, &irqfd->wait); + spin_acquire(&kvm->irqfds.lock.dep_map, 0, 0, _RET_IP_); + if (p->ret) + goto out; + + list_add_tail(&irqfd->list, &kvm->irqfds.items); + +out: + spin_unlock_irq(&kvm->irqfds.lock); +} + #if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS) void __attribute__((weak)) kvm_arch_irq_bypass_stop( struct irq_bypass_consumer *cons) @@ -285,26 +344,20 @@ void __attribute__((weak)) kvm_arch_irq_bypass_start( { } -int __attribute__((weak)) kvm_arch_update_irqfd_routing( - struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set) +void __weak kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd, + struct kvm_kernel_irq_routing_entry *old, + struct kvm_kernel_irq_routing_entry *new) { - return 0; -} -bool __attribute__((weak)) kvm_arch_irqfd_route_changed( - struct kvm_kernel_irq_routing_entry *old, - struct kvm_kernel_irq_routing_entry *new) -{ - return true; } #endif static int kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) { - struct kvm_kernel_irqfd *irqfd, *tmp; + struct kvm_kernel_irqfd *irqfd; struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL; + struct kvm_irqfd_pt irqfd_pt; int ret; __poll_t events; int idx; @@ -390,57 +443,54 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) } /* - * Install our own custom wake-up handling so we are notified via - * a callback whenever someone signals the underlying eventfd + * Set the irqfd routing and add it to KVM's list before registering + * the irqfd with the eventfd, so that the routing information is valid + * and stays valid, e.g. if there are GSI routing changes, prior to + * making the irqfd visible, i.e. before it might be signaled. + * + * Note, holding SRCU ensures a stable read of routing information, and + * also prevents irqfd_shutdown() from freeing the irqfd before it's + * fully initialized. */ - init_waitqueue_func_entry(&irqfd->wait, irqfd_wakeup); - init_poll_funcptr(&irqfd->pt, irqfd_ptable_queue_proc); - - spin_lock_irq(&kvm->irqfds.lock); - - ret = 0; - list_for_each_entry(tmp, &kvm->irqfds.items, list) { - if (irqfd->eventfd != tmp->eventfd) - continue; - /* This fd is used for another irq already. */ - ret = -EBUSY; - spin_unlock_irq(&kvm->irqfds.lock); - goto fail; - } - idx = srcu_read_lock(&kvm->irq_srcu); - irqfd_update(kvm, irqfd); - - list_add_tail(&irqfd->list, &kvm->irqfds.items); - - spin_unlock_irq(&kvm->irqfds.lock); /* - * Check if there was an event already pending on the eventfd - * before we registered, and trigger it as if we didn't miss it. + * Register the irqfd with the eventfd by polling on the eventfd, and + * simultaneously and the irqfd to KVM's list. If there was en event + * pending on the eventfd prior to registering, manually trigger IRQ + * injection. */ - events = vfs_poll(fd_file(f), &irqfd->pt); + irqfd_pt.irqfd = irqfd; + irqfd_pt.kvm = kvm; + init_poll_funcptr(&irqfd_pt.pt, kvm_irqfd_register); + + events = vfs_poll(fd_file(f), &irqfd_pt.pt); + + ret = irqfd_pt.ret; + if (ret) + goto fail_poll; if (events & EPOLLIN) schedule_work(&irqfd->inject); #if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS) if (kvm_arch_has_irq_bypass()) { - irqfd->consumer.token = (void *)irqfd->eventfd; irqfd->consumer.add_producer = kvm_arch_irq_bypass_add_producer; irqfd->consumer.del_producer = kvm_arch_irq_bypass_del_producer; irqfd->consumer.stop = kvm_arch_irq_bypass_stop; irqfd->consumer.start = kvm_arch_irq_bypass_start; - ret = irq_bypass_register_consumer(&irqfd->consumer); + ret = irq_bypass_register_consumer(&irqfd->consumer, irqfd->eventfd); if (ret) - pr_info("irq bypass consumer (token %p) registration fails: %d\n", - irqfd->consumer.token, ret); + pr_info("irq bypass consumer (eventfd %p) registration fails: %d\n", + irqfd->eventfd, ret); } #endif srcu_read_unlock(&kvm->irq_srcu, idx); return 0; +fail_poll: + srcu_read_unlock(&kvm->irq_srcu, idx); fail: if (irqfd->resampler) irqfd_resampler_shutdown(irqfd); @@ -617,13 +667,8 @@ void kvm_irq_routing_update(struct kvm *kvm) irqfd_update(kvm, irqfd); #if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS) - if (irqfd->producer && - kvm_arch_irqfd_route_changed(&old, &irqfd->irq_entry)) { - int ret = kvm_arch_update_irqfd_routing( - irqfd->kvm, irqfd->producer->irq, - irqfd->gsi, 1); - WARN_ON(ret); - } + if (irqfd->producer) + kvm_arch_update_irqfd_routing(irqfd, &old, &irqfd->irq_entry); #endif } diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index b2aa6bf24d3a..7d85cc33c0bb 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -382,23 +382,12 @@ static const struct address_space_operations kvm_gmem_aops = { #endif }; -static int kvm_gmem_getattr(struct mnt_idmap *idmap, const struct path *path, - struct kstat *stat, u32 request_mask, - unsigned int query_flags) -{ - struct inode *inode = path->dentry->d_inode; - - generic_fillattr(idmap, request_mask, inode, stat); - return 0; -} - static int kvm_gmem_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { return -EINVAL; } static const struct inode_operations kvm_gmem_iops = { - .getattr = kvm_gmem_getattr, .setattr = kvm_gmem_setattr, }; diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c index 162d8ed889f2..6ccabfd32287 100644 --- a/virt/kvm/irqchip.c +++ b/virt/kvm/irqchip.c @@ -222,8 +222,6 @@ int kvm_set_irq_routing(struct kvm *kvm, kvm_arch_irq_routing_update(kvm); mutex_unlock(&kvm->irq_lock); - kvm_arch_post_irq_routing_update(kvm); - synchronize_srcu_expedited(&kvm->irq_srcu); new = old; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index eec82775c5bf..6c07dd423458 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2558,9 +2558,11 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end, entry = attributes ? xa_mk_value(attributes) : NULL; + trace_kvm_vm_set_mem_attributes(start, end, attributes); + mutex_lock(&kvm->slots_lock); - /* Nothing to do if the entire range as the desired attributes. */ + /* Nothing to do if the entire range has the desired attributes. */ if (kvm_range_has_memory_attributes(kvm, start, end, ~0, attributes)) goto out_unlock; @@ -2572,6 +2574,8 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end, r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT); if (r) goto out_unlock; + + cond_resched(); } kvm_handle_gfn_range(kvm, &pre_set_range); @@ -2580,6 +2584,7 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end, r = xa_err(xa_store(&kvm->mem_attr_array, i, entry, GFP_KERNEL_ACCOUNT)); KVM_BUG_ON(r, kvm); + cond_resched(); } kvm_handle_gfn_range(kvm, &post_set_range); @@ -4962,15 +4967,18 @@ static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm) { unsigned long i; struct kvm_vcpu *vcpu; - int cleared = 0; + int cleared = 0, r; if (!kvm->dirty_ring_size) return -EINVAL; mutex_lock(&kvm->slots_lock); - kvm_for_each_vcpu(i, vcpu, kvm) - cleared += kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring); + kvm_for_each_vcpu(i, vcpu, kvm) { + r = kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring, &cleared); + if (r) + break; + } mutex_unlock(&kvm->slots_lock); diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c index 196a102e34fb..be50514bbd11 100644 --- a/virt/kvm/vfio.c +++ b/virt/kvm/vfio.c @@ -175,7 +175,6 @@ static int kvm_vfio_file_add(struct kvm_device *dev, unsigned int fd) kvf->file = get_file(filp); list_add_tail(&kvf->node, &kv->file_list); - kvm_arch_start_assignment(dev->kvm); kvm_vfio_file_set_kvm(kvf->file, dev->kvm); kvm_vfio_update_coherency(dev); @@ -205,7 +204,6 @@ static int kvm_vfio_file_del(struct kvm_device *dev, unsigned int fd) continue; list_del(&kvf->node); - kvm_arch_end_assignment(dev->kvm); #ifdef CONFIG_SPAPR_TCE_IOMMU kvm_spapr_tce_release_vfio_group(dev->kvm, kvf); #endif @@ -336,7 +334,6 @@ static void kvm_vfio_release(struct kvm_device *dev) fput(kvf->file); list_del(&kvf->node); kfree(kvf); - kvm_arch_end_assignment(dev->kvm); } kvm_vfio_update_coherency(dev); diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c index 28fda42e471b..62c160200be9 100644 --- a/virt/lib/irqbypass.c +++ b/virt/lib/irqbypass.c @@ -22,8 +22,8 @@ MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("IRQ bypass manager utility module"); -static LIST_HEAD(producers); -static LIST_HEAD(consumers); +static DEFINE_XARRAY(producers); +static DEFINE_XARRAY(consumers); static DEFINE_MUTEX(lock); /* @lock must be held when calling connect */ @@ -51,6 +51,10 @@ static int __connect(struct irq_bypass_producer *prod, if (prod->start) prod->start(prod); + if (!ret) { + prod->consumer = cons; + cons->producer = prod; + } return ret; } @@ -72,56 +76,49 @@ static void __disconnect(struct irq_bypass_producer *prod, cons->start(cons); if (prod->start) prod->start(prod); + + prod->consumer = NULL; + cons->producer = NULL; } /** * irq_bypass_register_producer - register IRQ bypass producer * @producer: pointer to producer structure + * @eventfd: pointer to the eventfd context associated with the producer + * @irq: Linux IRQ number of the underlying producer device * - * Add the provided IRQ producer to the list of producers and connect - * with any matching token found on the IRQ consumers list. + * Add the provided IRQ producer to the set of producers and connect with the + * consumer with a matching eventfd, if one exists. */ -int irq_bypass_register_producer(struct irq_bypass_producer *producer) +int irq_bypass_register_producer(struct irq_bypass_producer *producer, + struct eventfd_ctx *eventfd, int irq) { - struct irq_bypass_producer *tmp; + unsigned long index = (unsigned long)eventfd; struct irq_bypass_consumer *consumer; int ret; - if (!producer->token) + if (WARN_ON_ONCE(producer->eventfd)) return -EINVAL; - might_sleep(); - - if (!try_module_get(THIS_MODULE)) - return -ENODEV; + producer->irq = irq; - mutex_lock(&lock); + guard(mutex)(&lock); - list_for_each_entry(tmp, &producers, node) { - if (tmp->token == producer->token) { - ret = -EBUSY; - goto out_err; - } - } + ret = xa_insert(&producers, index, producer, GFP_KERNEL); + if (ret) + return ret; - list_for_each_entry(consumer, &consumers, node) { - if (consumer->token == producer->token) { - ret = __connect(producer, consumer); - if (ret) - goto out_err; - break; + consumer = xa_load(&consumers, index); + if (consumer) { + ret = __connect(producer, consumer); + if (ret) { + WARN_ON_ONCE(xa_erase(&producers, index) != producer); + return ret; } } - list_add(&producer->node, &producers); - - mutex_unlock(&lock); - + producer->eventfd = eventfd; return 0; -out_err: - mutex_unlock(&lock); - module_put(THIS_MODULE); - return ret; } EXPORT_SYMBOL_GPL(irq_bypass_register_producer); @@ -129,95 +126,65 @@ EXPORT_SYMBOL_GPL(irq_bypass_register_producer); * irq_bypass_unregister_producer - unregister IRQ bypass producer * @producer: pointer to producer structure * - * Remove a previously registered IRQ producer from the list of producers - * and disconnect it from any connected IRQ consumer. + * Remove a previously registered IRQ producer (note, it's safe to call this + * even if registration was unsuccessful). Disconnect from the associated + * consumer, if one exists. */ void irq_bypass_unregister_producer(struct irq_bypass_producer *producer) { - struct irq_bypass_producer *tmp; - struct irq_bypass_consumer *consumer; + unsigned long index = (unsigned long)producer->eventfd; - if (!producer->token) + if (!producer->eventfd) return; - might_sleep(); - - if (!try_module_get(THIS_MODULE)) - return; /* nothing in the list anyway */ - - mutex_lock(&lock); - - list_for_each_entry(tmp, &producers, node) { - if (tmp->token != producer->token) - continue; - - list_for_each_entry(consumer, &consumers, node) { - if (consumer->token == producer->token) { - __disconnect(producer, consumer); - break; - } - } - - list_del(&producer->node); - module_put(THIS_MODULE); - break; - } + guard(mutex)(&lock); - mutex_unlock(&lock); + if (producer->consumer) + __disconnect(producer, producer->consumer); - module_put(THIS_MODULE); + WARN_ON_ONCE(xa_erase(&producers, index) != producer); + producer->eventfd = NULL; } EXPORT_SYMBOL_GPL(irq_bypass_unregister_producer); /** * irq_bypass_register_consumer - register IRQ bypass consumer * @consumer: pointer to consumer structure + * @eventfd: pointer to the eventfd context associated with the consumer * - * Add the provided IRQ consumer to the list of consumers and connect - * with any matching token found on the IRQ producer list. + * Add the provided IRQ consumer to the set of consumers and connect with the + * producer with a matching eventfd, if one exists. */ -int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer) +int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer, + struct eventfd_ctx *eventfd) { - struct irq_bypass_consumer *tmp; + unsigned long index = (unsigned long)eventfd; struct irq_bypass_producer *producer; int ret; - if (!consumer->token || - !consumer->add_producer || !consumer->del_producer) + if (WARN_ON_ONCE(consumer->eventfd)) return -EINVAL; - might_sleep(); - - if (!try_module_get(THIS_MODULE)) - return -ENODEV; + if (!consumer->add_producer || !consumer->del_producer) + return -EINVAL; - mutex_lock(&lock); + guard(mutex)(&lock); - list_for_each_entry(tmp, &consumers, node) { - if (tmp->token == consumer->token || tmp == consumer) { - ret = -EBUSY; - goto out_err; - } - } + ret = xa_insert(&consumers, index, consumer, GFP_KERNEL); + if (ret) + return ret; - list_for_each_entry(producer, &producers, node) { - if (producer->token == consumer->token) { - ret = __connect(producer, consumer); - if (ret) - goto out_err; - break; + producer = xa_load(&producers, index); + if (producer) { + ret = __connect(producer, consumer); + if (ret) { + WARN_ON_ONCE(xa_erase(&consumers, index) != consumer); + return ret; } } - list_add(&consumer->node, &consumers); - - mutex_unlock(&lock); - + consumer->eventfd = eventfd; return 0; -out_err: - mutex_unlock(&lock); - module_put(THIS_MODULE); - return ret; } EXPORT_SYMBOL_GPL(irq_bypass_register_consumer); @@ -225,42 +192,23 @@ EXPORT_SYMBOL_GPL(irq_bypass_register_consumer); * irq_bypass_unregister_consumer - unregister IRQ bypass consumer * @consumer: pointer to consumer structure * - * Remove a previously registered IRQ consumer from the list of consumers - * and disconnect it from any connected IRQ producer. + * Remove a previously registered IRQ consumer (note, it's safe to call this + * even if registration was unsuccessful). Disconnect from the associated + * producer, if one exists. */ void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer) { - struct irq_bypass_consumer *tmp; - struct irq_bypass_producer *producer; + unsigned long index = (unsigned long)consumer->eventfd; - if (!consumer->token) + if (!consumer->eventfd) return; - might_sleep(); - - if (!try_module_get(THIS_MODULE)) - return; /* nothing in the list anyway */ - - mutex_lock(&lock); - - list_for_each_entry(tmp, &consumers, node) { - if (tmp != consumer) - continue; - - list_for_each_entry(producer, &producers, node) { - if (producer->token == consumer->token) { - __disconnect(producer, consumer); - break; - } - } - - list_del(&consumer->node); - module_put(THIS_MODULE); - break; - } + guard(mutex)(&lock); - mutex_unlock(&lock); + if (consumer->producer) + __disconnect(consumer->producer, consumer); - module_put(THIS_MODULE); + WARN_ON_ONCE(xa_erase(&consumers, index) != consumer); + consumer->eventfd = NULL; } EXPORT_SYMBOL_GPL(irq_bypass_unregister_consumer); |