diff options
606 files changed, 6079 insertions, 2924 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-cxl b/Documentation/ABI/testing/sysfs-bus-cxl index 6350dd82b9a9..087f762ebfd5 100644 --- a/Documentation/ABI/testing/sysfs-bus-cxl +++ b/Documentation/ABI/testing/sysfs-bus-cxl @@ -82,7 +82,12 @@ Description: whether it resides in persistent capacity, volatile capacity, or the LSA, is made permanently unavailable by whatever means is appropriate for the media type. This functionality requires - the device to be not be actively decoding any HPA ranges. + the device to be disabled, that is, not actively decoding any + HPA ranges. This permits avoiding explicit global CPU cache + management, relying instead for it to be done when a region + transitions between software programmed and hardware committed + states. If this file is not present, then there is no hardware + support for the operation. What /sys/bus/cxl/devices/memX/security/erase @@ -92,7 +97,13 @@ Contact: linux-cxl@vger.kernel.org Description: (WO) Write a boolean 'true' string value to this attribute to secure erase user data by changing the media encryption keys for - all user data areas of the device. + all user data areas of the device. This functionality requires + the device to be disabled, that is, not actively decoding any + HPA ranges. This permits avoiding explicit global CPU cache + management, relying instead for it to be done when a region + transitions between software programmed and hardware committed + states. If this file is not present, then there is no hardware + support for the operation. What: /sys/bus/cxl/devices/memX/firmware/ diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index ecd585ca2d50..77942eedf4f6 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -513,17 +513,18 @@ Description: information about CPUs heterogeneity. cpu_capacity: capacity of cpuX. What: /sys/devices/system/cpu/vulnerabilities + /sys/devices/system/cpu/vulnerabilities/gather_data_sampling + /sys/devices/system/cpu/vulnerabilities/itlb_multihit + /sys/devices/system/cpu/vulnerabilities/l1tf + /sys/devices/system/cpu/vulnerabilities/mds /sys/devices/system/cpu/vulnerabilities/meltdown + /sys/devices/system/cpu/vulnerabilities/mmio_stale_data + /sys/devices/system/cpu/vulnerabilities/retbleed + /sys/devices/system/cpu/vulnerabilities/spec_store_bypass /sys/devices/system/cpu/vulnerabilities/spectre_v1 /sys/devices/system/cpu/vulnerabilities/spectre_v2 - /sys/devices/system/cpu/vulnerabilities/spec_store_bypass - /sys/devices/system/cpu/vulnerabilities/l1tf - /sys/devices/system/cpu/vulnerabilities/mds /sys/devices/system/cpu/vulnerabilities/srbds /sys/devices/system/cpu/vulnerabilities/tsx_async_abort - /sys/devices/system/cpu/vulnerabilities/itlb_multihit - /sys/devices/system/cpu/vulnerabilities/mmio_stale_data - /sys/devices/system/cpu/vulnerabilities/retbleed Date: January 2018 Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> Description: Information about CPU vulnerabilities diff --git a/Documentation/ABI/testing/sysfs-platform-hidma b/Documentation/ABI/testing/sysfs-platform-hidma index fca40a54df59..a80aeda85ef6 100644 --- a/Documentation/ABI/testing/sysfs-platform-hidma +++ b/Documentation/ABI/testing/sysfs-platform-hidma @@ -2,7 +2,7 @@ What: /sys/devices/platform/hidma-*/chid /sys/devices/platform/QCOM8061:*/chid Date: Dec 2015 KernelVersion: 4.4 -Contact: "Sinan Kaya <okaya@codeaurora.org>" +Contact: "Sinan Kaya <okaya@kernel.org>" Description: Contains the ID of the channel within the HIDMA instance. It is used to associate a given HIDMA channel with the diff --git a/Documentation/ABI/testing/sysfs-platform-hidma-mgmt b/Documentation/ABI/testing/sysfs-platform-hidma-mgmt index 3b6c5c9eabdc..0373745b4e18 100644 --- a/Documentation/ABI/testing/sysfs-platform-hidma-mgmt +++ b/Documentation/ABI/testing/sysfs-platform-hidma-mgmt @@ -2,7 +2,7 @@ What: /sys/devices/platform/hidma-mgmt*/chanops/chan*/priority /sys/devices/platform/QCOM8060:*/chanops/chan*/priority Date: Nov 2015 KernelVersion: 4.4 -Contact: "Sinan Kaya <okaya@codeaurora.org>" +Contact: "Sinan Kaya <okaya@kernel.org>" Description: Contains either 0 or 1 and indicates if the DMA channel is a low priority (0) or high priority (1) channel. @@ -11,7 +11,7 @@ What: /sys/devices/platform/hidma-mgmt*/chanops/chan*/weight /sys/devices/platform/QCOM8060:*/chanops/chan*/weight Date: Nov 2015 KernelVersion: 4.4 -Contact: "Sinan Kaya <okaya@codeaurora.org>" +Contact: "Sinan Kaya <okaya@kernel.org>" Description: Contains 0..15 and indicates the weight of the channel among equal priority channels during round robin scheduling. @@ -20,7 +20,7 @@ What: /sys/devices/platform/hidma-mgmt*/chreset_timeout_cycles /sys/devices/platform/QCOM8060:*/chreset_timeout_cycles Date: Nov 2015 KernelVersion: 4.4 -Contact: "Sinan Kaya <okaya@codeaurora.org>" +Contact: "Sinan Kaya <okaya@kernel.org>" Description: Contains the platform specific cycle value to wait after a reset command is issued. If the value is chosen too short, @@ -32,7 +32,7 @@ What: /sys/devices/platform/hidma-mgmt*/dma_channels /sys/devices/platform/QCOM8060:*/dma_channels Date: Nov 2015 KernelVersion: 4.4 -Contact: "Sinan Kaya <okaya@codeaurora.org>" +Contact: "Sinan Kaya <okaya@kernel.org>" Description: Contains the number of dma channels supported by one instance of HIDMA hardware. The value may change from chip to chip. @@ -41,7 +41,7 @@ What: /sys/devices/platform/hidma-mgmt*/hw_version_major /sys/devices/platform/QCOM8060:*/hw_version_major Date: Nov 2015 KernelVersion: 4.4 -Contact: "Sinan Kaya <okaya@codeaurora.org>" +Contact: "Sinan Kaya <okaya@kernel.org>" Description: Version number major for the hardware. @@ -49,7 +49,7 @@ What: /sys/devices/platform/hidma-mgmt*/hw_version_minor /sys/devices/platform/QCOM8060:*/hw_version_minor Date: Nov 2015 KernelVersion: 4.4 -Contact: "Sinan Kaya <okaya@codeaurora.org>" +Contact: "Sinan Kaya <okaya@kernel.org>" Description: Version number minor for the hardware. @@ -57,7 +57,7 @@ What: /sys/devices/platform/hidma-mgmt*/max_rd_xactions /sys/devices/platform/QCOM8060:*/max_rd_xactions Date: Nov 2015 KernelVersion: 4.4 -Contact: "Sinan Kaya <okaya@codeaurora.org>" +Contact: "Sinan Kaya <okaya@kernel.org>" Description: Contains a value between 0 and 31. Maximum number of read transactions that can be issued back to back. @@ -69,7 +69,7 @@ What: /sys/devices/platform/hidma-mgmt*/max_read_request /sys/devices/platform/QCOM8060:*/max_read_request Date: Nov 2015 KernelVersion: 4.4 -Contact: "Sinan Kaya <okaya@codeaurora.org>" +Contact: "Sinan Kaya <okaya@kernel.org>" Description: Size of each read request. The value needs to be a power of two and can be between 128 and 1024. @@ -78,7 +78,7 @@ What: /sys/devices/platform/hidma-mgmt*/max_wr_xactions /sys/devices/platform/QCOM8060:*/max_wr_xactions Date: Nov 2015 KernelVersion: 4.4 -Contact: "Sinan Kaya <okaya@codeaurora.org>" +Contact: "Sinan Kaya <okaya@kernel.org>" Description: Contains a value between 0 and 31. Maximum number of write transactions that can be issued back to back. @@ -91,7 +91,7 @@ What: /sys/devices/platform/hidma-mgmt*/max_write_request /sys/devices/platform/QCOM8060:*/max_write_request Date: Nov 2015 KernelVersion: 4.4 -Contact: "Sinan Kaya <okaya@codeaurora.org>" +Contact: "Sinan Kaya <okaya@kernel.org>" Description: Size of each write request. The value needs to be a power of two and can be between 128 and 1024. diff --git a/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst new file mode 100644 index 000000000000..264bfa937f7d --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst @@ -0,0 +1,109 @@ +.. SPDX-License-Identifier: GPL-2.0 + +GDS - Gather Data Sampling +========================== + +Gather Data Sampling is a hardware vulnerability which allows unprivileged +speculative access to data which was previously stored in vector registers. + +Problem +------- +When a gather instruction performs loads from memory, different data elements +are merged into the destination vector register. However, when a gather +instruction that is transiently executed encounters a fault, stale data from +architectural or internal vector registers may get transiently forwarded to the +destination vector register instead. This will allow a malicious attacker to +infer stale data using typical side channel techniques like cache timing +attacks. GDS is a purely sampling-based attack. + +The attacker uses gather instructions to infer the stale vector register data. +The victim does not need to do anything special other than use the vector +registers. The victim does not need to use gather instructions to be +vulnerable. + +Because the buffers are shared between Hyper-Threads cross Hyper-Thread attacks +are possible. + +Attack scenarios +---------------- +Without mitigation, GDS can infer stale data across virtually all +permission boundaries: + + Non-enclaves can infer SGX enclave data + Userspace can infer kernel data + Guests can infer data from hosts + Guest can infer guest from other guests + Users can infer data from other users + +Because of this, it is important to ensure that the mitigation stays enabled in +lower-privilege contexts like guests and when running outside SGX enclaves. + +The hardware enforces the mitigation for SGX. Likewise, VMMs should ensure +that guests are not allowed to disable the GDS mitigation. If a host erred and +allowed this, a guest could theoretically disable GDS mitigation, mount an +attack, and re-enable it. + +Mitigation mechanism +-------------------- +This issue is mitigated in microcode. The microcode defines the following new +bits: + + ================================ === ============================ + IA32_ARCH_CAPABILITIES[GDS_CTRL] R/O Enumerates GDS vulnerability + and mitigation support. + IA32_ARCH_CAPABILITIES[GDS_NO] R/O Processor is not vulnerable. + IA32_MCU_OPT_CTRL[GDS_MITG_DIS] R/W Disables the mitigation + 0 by default. + IA32_MCU_OPT_CTRL[GDS_MITG_LOCK] R/W Locks GDS_MITG_DIS=0. Writes + to GDS_MITG_DIS are ignored + Can't be cleared once set. + ================================ === ============================ + +GDS can also be mitigated on systems that don't have updated microcode by +disabling AVX. This can be done by setting gather_data_sampling="force" or +"clearcpuid=avx" on the kernel command-line. + +If used, these options will disable AVX use by turning off XSAVE YMM support. +However, the processor will still enumerate AVX support. Userspace that +does not follow proper AVX enumeration to check both AVX *and* XSAVE YMM +support will break. + +Mitigation control on the kernel command line +--------------------------------------------- +The mitigation can be disabled by setting "gather_data_sampling=off" or +"mitigations=off" on the kernel command line. Not specifying either will default +to the mitigation being enabled. Specifying "gather_data_sampling=force" will +use the microcode mitigation when available or disable AVX on affected systems +where the microcode hasn't been updated to include the mitigation. + +GDS System Information +------------------------ +The kernel provides vulnerability status information through sysfs. For +GDS this can be accessed by the following sysfs file: + +/sys/devices/system/cpu/vulnerabilities/gather_data_sampling + +The possible values contained in this file are: + + ============================== ============================================= + Not affected Processor not vulnerable. + Vulnerable Processor vulnerable and mitigation disabled. + Vulnerable: No microcode Processor vulnerable and microcode is missing + mitigation. + Mitigation: AVX disabled, + no microcode Processor is vulnerable and microcode is missing + mitigation. AVX disabled as mitigation. + Mitigation: Microcode Processor is vulnerable and mitigation is in + effect. + Mitigation: Microcode (locked) Processor is vulnerable and mitigation is in + effect and cannot be disabled. + Unknown: Dependent on + hypervisor status Running on a virtual guest processor that is + affected but with no way to know if host + processor is mitigated or vulnerable. + ============================== ============================================= + +GDS Default mitigation +---------------------- +The updated microcode will enable the mitigation by default. The kernel's +default action is to leave the mitigation enabled. diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index e0614760a99e..de99caabf65a 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -13,9 +13,11 @@ are configurable at compile, boot or run time. l1tf mds tsx_async_abort - multihit.rst - special-register-buffer-data-sampling.rst - core-scheduling.rst - l1d_flush.rst - processor_mmio_stale_data.rst - cross-thread-rsb.rst + multihit + special-register-buffer-data-sampling + core-scheduling + l1d_flush + processor_mmio_stale_data + cross-thread-rsb + srso + gather_data_sampling diff --git a/Documentation/admin-guide/hw-vuln/srso.rst b/Documentation/admin-guide/hw-vuln/srso.rst new file mode 100644 index 000000000000..af59a9395662 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/srso.rst @@ -0,0 +1,150 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Speculative Return Stack Overflow (SRSO) +======================================== + +This is a mitigation for the speculative return stack overflow (SRSO) +vulnerability found on AMD processors. The mechanism is by now the well +known scenario of poisoning CPU functional units - the Branch Target +Buffer (BTB) and Return Address Predictor (RAP) in this case - and then +tricking the elevated privilege domain (the kernel) into leaking +sensitive data. + +AMD CPUs predict RET instructions using a Return Address Predictor (aka +Return Address Stack/Return Stack Buffer). In some cases, a non-architectural +CALL instruction (i.e., an instruction predicted to be a CALL but is +not actually a CALL) can create an entry in the RAP which may be used +to predict the target of a subsequent RET instruction. + +The specific circumstances that lead to this varies by microarchitecture +but the concern is that an attacker can mis-train the CPU BTB to predict +non-architectural CALL instructions in kernel space and use this to +control the speculative target of a subsequent kernel RET, potentially +leading to information disclosure via a speculative side-channel. + +The issue is tracked under CVE-2023-20569. + +Affected processors +------------------- + +AMD Zen, generations 1-4. That is, all families 0x17 and 0x19. Older +processors have not been investigated. + +System information and options +------------------------------ + +First of all, it is required that the latest microcode be loaded for +mitigations to be effective. + +The sysfs file showing SRSO mitigation status is: + + /sys/devices/system/cpu/vulnerabilities/spec_rstack_overflow + +The possible values in this file are: + + * 'Not affected': + + The processor is not vulnerable + + * 'Vulnerable: no microcode': + + The processor is vulnerable, no microcode extending IBPB + functionality to address the vulnerability has been applied. + + * 'Mitigation: microcode': + + Extended IBPB functionality microcode patch has been applied. It does + not address User->Kernel and Guest->Host transitions protection but it + does address User->User and VM->VM attack vectors. + + Note that User->User mitigation is controlled by how the IBPB aspect in + the Spectre v2 mitigation is selected: + + * conditional IBPB: + + where each process can select whether it needs an IBPB issued + around it PR_SPEC_DISABLE/_ENABLE etc, see :doc:`spectre` + + * strict: + + i.e., always on - by supplying spectre_v2_user=on on the kernel + command line + + (spec_rstack_overflow=microcode) + + * 'Mitigation: safe RET': + + Software-only mitigation. It complements the extended IBPB microcode + patch functionality by addressing User->Kernel and Guest->Host + transitions protection. + + Selected by default or by spec_rstack_overflow=safe-ret + + * 'Mitigation: IBPB': + + Similar protection as "safe RET" above but employs an IBPB barrier on + privilege domain crossings (User->Kernel, Guest->Host). + + (spec_rstack_overflow=ibpb) + + * 'Mitigation: IBPB on VMEXIT': + + Mitigation addressing the cloud provider scenario - the Guest->Host + transitions only. + + (spec_rstack_overflow=ibpb-vmexit) + + + +In order to exploit vulnerability, an attacker needs to: + + - gain local access on the machine + + - break kASLR + + - find gadgets in the running kernel in order to use them in the exploit + + - potentially create and pin an additional workload on the sibling + thread, depending on the microarchitecture (not necessary on fam 0x19) + + - run the exploit + +Considering the performance implications of each mitigation type, the +default one is 'Mitigation: safe RET' which should take care of most +attack vectors, including the local User->Kernel one. + +As always, the user is advised to keep her/his system up-to-date by +applying software updates regularly. + +The default setting will be reevaluated when needed and especially when +new attack vectors appear. + +As one can surmise, 'Mitigation: safe RET' does come at the cost of some +performance depending on the workload. If one trusts her/his userspace +and does not want to suffer the performance impact, one can always +disable the mitigation with spec_rstack_overflow=off. + +Similarly, 'Mitigation: IBPB' is another full mitigation type employing +an indrect branch prediction barrier after having applied the required +microcode patch for one's system. This mitigation comes also at +a performance cost. + +Mitigation: safe RET +-------------------- + +The mitigation works by ensuring all RET instructions speculate to +a controlled location, similar to how speculation is controlled in the +retpoline sequence. To accomplish this, the __x86_return_thunk forces +the CPU to mispredict every function return using a 'safe return' +sequence. + +To ensure the safety of this mitigation, the kernel must ensure that the +safe return sequence is itself free from attacker interference. In Zen3 +and Zen4, this is accomplished by creating a BTB alias between the +untraining function srso_untrain_ret_alias() and the safe return +function srso_safe_ret_alias() which results in evicting a potentially +poisoned BTB entry and using that safe one for all function returns. + +In older Zen1 and Zen2, this is accomplished using a reinterpretation +technique similar to Retbleed one: srso_untrain_ret() and +srso_safe_ret(). diff --git a/Documentation/admin-guide/kdump/vmcoreinfo.rst b/Documentation/admin-guide/kdump/vmcoreinfo.rst index c18d94fa6470..f8ebb63b6c5d 100644 --- a/Documentation/admin-guide/kdump/vmcoreinfo.rst +++ b/Documentation/admin-guide/kdump/vmcoreinfo.rst @@ -624,3 +624,9 @@ Used to get the correct ranges: * VMALLOC_START ~ VMALLOC_END : vmalloc() / ioremap() space. * VMEMMAP_START ~ VMEMMAP_END : vmemmap space, used for struct page array. * KERNEL_LINK_ADDR : start address of Kernel link and BPF + +va_kernel_pa_offset +------------------- + +Indicates the offset between the kernel virtual and physical mappings. +Used to translate virtual to physical addresses. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a1457995fd41..722b6eca2e93 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1623,6 +1623,26 @@ Format: off | on default: on + gather_data_sampling= + [X86,INTEL] Control the Gather Data Sampling (GDS) + mitigation. + + Gather Data Sampling is a hardware vulnerability which + allows unprivileged speculative access to data which was + previously stored in vector registers. + + This issue is mitigated by default in updated microcode. + The mitigation may have a performance impact but can be + disabled. On systems without the microcode mitigation + disabling AVX serves as a mitigation. + + force: Disable AVX to mitigate systems without + microcode mitigation. No effect if the microcode + mitigation is present. Known to cause crashes in + userspace with buggy AVX enumeration. + + off: Disable GDS mitigation. + gcov_persist= [GCOV] When non-zero (default), profiling data for kernel modules is saved and remains accessible via debugfs, even when the module is unloaded/reloaded. @@ -3273,24 +3293,25 @@ Disable all optional CPU mitigations. This improves system performance, but it may also expose users to several CPU vulnerabilities. - Equivalent to: nopti [X86,PPC] - if nokaslr then kpti=0 [ARM64] - nospectre_v1 [X86,PPC] - nobp=0 [S390] - nospectre_v2 [X86,PPC,S390,ARM64] - spectre_v2_user=off [X86] - spec_store_bypass_disable=off [X86,PPC] - ssbd=force-off [ARM64] - nospectre_bhb [ARM64] + Equivalent to: if nokaslr then kpti=0 [ARM64] + gather_data_sampling=off [X86] + kvm.nx_huge_pages=off [X86] l1tf=off [X86] mds=off [X86] - tsx_async_abort=off [X86] - kvm.nx_huge_pages=off [X86] - srbds=off [X86,INTEL] + mmio_stale_data=off [X86] no_entry_flush [PPC] no_uaccess_flush [PPC] - mmio_stale_data=off [X86] + nobp=0 [S390] + nopti [X86,PPC] + nospectre_bhb [ARM64] + nospectre_v1 [X86,PPC] + nospectre_v2 [X86,PPC,S390,ARM64] retbleed=off [X86] + spec_store_bypass_disable=off [X86,PPC] + spectre_v2_user=off [X86] + srbds=off [X86,INTEL] + ssbd=force-off [ARM64] + tsx_async_abort=off [X86] Exceptions: This does not have any effect on @@ -5875,6 +5896,17 @@ Not specifying this option is equivalent to spectre_v2_user=auto. + spec_rstack_overflow= + [X86] Control RAS overflow mitigation on AMD Zen CPUs + + off - Disable mitigation + microcode - Enable microcode mitigation only + safe-ret - Enable sw-only safe RET mitigation (default) + ibpb - Enable mitigation by issuing IBPB on + kernel entry + ibpb-vmexit - Issue IBPB only on VMEXIT + (cloud-specific mitigation) + spec_store_bypass_disable= [HW] Control Speculative Store Bypass (SSB) Disable mitigation (Speculative Store Bypass vulnerability) diff --git a/Documentation/devicetree/bindings/iio/addac/adi,ad74115.yaml b/Documentation/devicetree/bindings/iio/addac/adi,ad74115.yaml index 72d2e910f206..2594fa192f93 100644 --- a/Documentation/devicetree/bindings/iio/addac/adi,ad74115.yaml +++ b/Documentation/devicetree/bindings/iio/addac/adi,ad74115.yaml @@ -216,7 +216,6 @@ properties: description: Whether to enable burnout current for EXT1. adi,ext1-burnout-current-nanoamp: - $ref: /schemas/types.yaml#/definitions/uint32 description: Burnout current in nanoamps to be applied to EXT1. enum: [0, 50, 500, 1000, 10000] @@ -233,7 +232,6 @@ properties: description: Whether to enable burnout current for EXT2. adi,ext2-burnout-current-nanoamp: - $ref: /schemas/types.yaml#/definitions/uint32 description: Burnout current in nanoamps to be applied to EXT2. enum: [0, 50, 500, 1000, 10000] default: 0 @@ -249,7 +247,6 @@ properties: description: Whether to enable burnout current for VIOUT. adi,viout-burnout-current-nanoamp: - $ref: /schemas/types.yaml#/definitions/uint32 description: Burnout current in nanoamps to be applied to VIOUT. enum: [0, 1000, 10000] default: 0 diff --git a/Documentation/devicetree/bindings/net/mediatek,net.yaml b/Documentation/devicetree/bindings/net/mediatek,net.yaml index acb2b2ac4fe1..31cc0c412805 100644 --- a/Documentation/devicetree/bindings/net/mediatek,net.yaml +++ b/Documentation/devicetree/bindings/net/mediatek,net.yaml @@ -293,7 +293,7 @@ allOf: patternProperties: "^mac@[0-1]$": type: object - additionalProperties: false + unevaluatedProperties: false allOf: - $ref: ethernet-controller.yaml# description: @@ -305,14 +305,9 @@ patternProperties: reg: maxItems: 1 - phy-handle: true - - phy-mode: true - required: - reg - compatible - - phy-handle required: - compatible diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml index 176ea5f90251..7f324c6da915 100644 --- a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml +++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml @@ -91,12 +91,18 @@ properties: $ref: /schemas/types.yaml#/definitions/phandle tx_delay: - description: Delay value for TXD timing. Range value is 0~0x7F, 0x30 as default. + description: Delay value for TXD timing. $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 0 + maximum: 0x7F + default: 0x30 rx_delay: - description: Delay value for RXD timing. Range value is 0~0x7F, 0x10 as default. + description: Delay value for RXD timing. $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 0 + maximum: 0x7F + default: 0x10 phy-supply: description: PHY regulator diff --git a/Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml b/Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml index 30b2131b5860..65cb2e5c5eee 100644 --- a/Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml +++ b/Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml @@ -16,7 +16,6 @@ properties: - enum: - atmel,at91rm9200-usart - atmel,at91sam9260-usart - - microchip,sam9x60-usart - items: - const: atmel,at91rm9200-dbgu - const: atmel,at91rm9200-usart @@ -24,6 +23,9 @@ properties: - const: atmel,at91sam9260-dbgu - const: atmel,at91sam9260-usart - items: + - const: microchip,sam9x60-usart + - const: atmel,at91sam9260-usart + - items: - const: microchip,sam9x60-dbgu - const: microchip,sam9x60-usart - const: atmel,at91sam9260-dbgu diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index ed148919e11a..0ca479dbb1cd 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -551,9 +551,8 @@ mutex or just to use i_size_read() instead. Note: this does not protect the file->f_pos against concurrent modifications since this is something the userspace has to take care about. -->iterate() is called with i_rwsem exclusive. - -->iterate_shared() is called with i_rwsem at least shared. +->iterate_shared() is called with i_rwsem held for reading, and with the +file f_pos_lock held exclusively ->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags. Most instances call fasync_helper(), which does that maintenance, so it's diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index d2d684ae7798..0f5da78ef4f9 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -537,7 +537,7 @@ vfs_readdir() is gone; switch to iterate_dir() instead **mandatory** -->readdir() is gone now; switch to ->iterate() +->readdir() is gone now; switch to ->iterate_shared() **mandatory** @@ -693,24 +693,19 @@ parallel now. --- -**recommended** +**mandatory** -->iterate_shared() is added; it's a parallel variant of ->iterate(). +->iterate_shared() is added. Exclusion on struct file level is still provided (as well as that between it and lseek on the same struct file), but if your directory has been opened several times, you can get these called in parallel. Exclusion between that method and all directory-modifying ones is still provided, of course. -Often enough ->iterate() can serve as ->iterate_shared() without any -changes - it is a read-only operation, after all. If you have any -per-inode or per-dentry in-core data structures modified by ->iterate(), -you might need something to serialize the access to them. If you -do dcache pre-seeding, you'll need to switch to d_alloc_parallel() for -that; look for in-tree examples. - -Old method is only used if the new one is absent; eventually it will -be removed. Switch while you still can; the old one won't stay. +If you have any per-inode or per-dentry in-core data structures modified +by ->iterate_shared(), you might need something to serialize the access +to them. If you do dcache pre-seeding, you'll need to switch to +d_alloc_parallel() for that; look for in-tree examples. --- @@ -930,9 +925,9 @@ should be done by looking at FMODE_LSEEK in file->f_mode. filldir_t (readdir callbacks) calling conventions have changed. Instead of returning 0 or -E... it returns bool now. false means "no more" (as -E... used to) and true - "keep going" (as 0 in old calling conventions). Rationale: -callers never looked at specific -E... values anyway. ->iterate() and -->iterate_shared() instance require no changes at all, all filldir_t ones in -the tree converted. +callers never looked at specific -E... values anyway. -> iterate_shared() +instances require no changes at all, all filldir_t ones in the tree +converted. --- diff --git a/MAINTAINERS b/MAINTAINERS index 504a806f76b7..8ac89758d009 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2339,7 +2339,7 @@ F: drivers/phy/mediatek/ ARM/MICROCHIP (ARM64) SoC support M: Conor Dooley <conor@kernel.org> M: Nicolas Ferre <nicolas.ferre@microchip.com> -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported T: git https://git.kernel.org/pub/scm/linux/kernel/git/at91/linux.git @@ -2348,7 +2348,7 @@ F: arch/arm64/boot/dts/microchip/ ARM/Microchip (AT91) SoC support M: Nicolas Ferre <nicolas.ferre@microchip.com> M: Alexandre Belloni <alexandre.belloni@bootlin.com> -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported W: http://www.linux4sam.org @@ -3250,7 +3250,7 @@ F: include/uapi/linux/atm* ATMEL MACB ETHERNET DRIVER M: Nicolas Ferre <nicolas.ferre@microchip.com> -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> S: Supported F: drivers/net/ethernet/cadence/ @@ -3262,9 +3262,8 @@ F: Documentation/devicetree/bindings/input/atmel,maxtouch.yaml F: drivers/input/touchscreen/atmel_mxt_ts.c ATMEL WIRELESS DRIVER -M: Simon Kelley <simon@thekelleys.org.uk> L: linux-wireless@vger.kernel.org -S: Maintained +S: Orphan W: http://www.thekelleys.org.uk/atmel W: http://atmelwlandriver.sourceforge.net/ F: drivers/net/wireless/atmel/atmel* @@ -3394,7 +3393,7 @@ F: drivers/media/radio/radio-aztech* B43 WIRELESS DRIVER L: linux-wireless@vger.kernel.org L: b43-dev@lists.infradead.org -S: Odd Fixes +S: Orphan W: https://wireless.wiki.kernel.org/en/users/Drivers/b43 F: drivers/net/wireless/broadcom/b43/ @@ -5462,8 +5461,7 @@ F: Documentation/devicetree/bindings/net/can/ctu,ctucanfd.yaml F: drivers/net/can/ctucanfd/ CW1200 WLAN driver -M: Solomon Peachy <pizza@shaftnet.org> -S: Maintained +S: Orphan F: drivers/net/wireless/st/cw1200/ CX18 VIDEO4LINUX DRIVER @@ -9386,7 +9384,6 @@ F: drivers/crypto/hisilicon/sgl.c F: include/linux/hisi_acc_qm.h HISILICON ROCE DRIVER -M: Haoyue Xu <xuhaoyue1@hisilicon.com> M: Junxian Huang <huangjunxian6@hisilicon.com> L: linux-rdma@vger.kernel.org S: Maintained @@ -9671,6 +9668,7 @@ F: tools/hv/ HYPERBUS SUPPORT M: Vignesh Raghavendra <vigneshr@ti.com> +R: Tudor Ambarus <tudor.ambarus@linaro.org> L: linux-mtd@lists.infradead.org S: Supported Q: http://patchwork.ozlabs.org/project/linux-mtd/list/ @@ -12490,6 +12488,7 @@ F: net/mctp/ MAPLE TREE M: Liam R. Howlett <Liam.Howlett@oracle.com> +L: maple-tree@lists.infradead.org L: linux-mm@kvack.org S: Supported F: Documentation/core-api/maple_tree.rst @@ -12601,18 +12600,14 @@ F: Documentation/devicetree/bindings/net/marvell,pp2.yaml F: drivers/net/ethernet/marvell/mvpp2/ MARVELL MWIFIEX WIRELESS DRIVER -M: Amitkumar Karwar <amitkarwar@gmail.com> -M: Ganapathi Bhat <ganapathi017@gmail.com> -M: Sharvari Harisangam <sharvari.harisangam@nxp.com> -M: Xinming Hu <huxinming820@gmail.com> +M: Brian Norris <briannorris@chromium.org> L: linux-wireless@vger.kernel.org -S: Maintained +S: Odd Fixes F: drivers/net/wireless/marvell/mwifiex/ MARVELL MWL8K WIRELESS DRIVER -M: Lennert Buytenhek <buytenh@wantstofly.org> L: linux-wireless@vger.kernel.org -S: Odd Fixes +S: Orphan F: drivers/net/wireless/marvell/mwl8k.c MARVELL NAND CONTROLLER DRIVER @@ -13800,7 +13795,7 @@ F: Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml F: drivers/spi/spi-at91-usart.c MICROCHIP AUDIO ASOC DRIVERS -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Supported F: Documentation/devicetree/bindings/sound/atmel* @@ -13823,7 +13818,7 @@ S: Maintained F: drivers/crypto/atmel-ecc.* MICROCHIP EIC DRIVER -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported F: Documentation/devicetree/bindings/interrupt-controller/microchip,sama7g5-eic.yaml @@ -13896,7 +13891,7 @@ F: drivers/video/fbdev/atmel_lcdfb.c F: include/video/atmel_lcdc.h MICROCHIP MCP16502 PMIC DRIVER -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported F: Documentation/devicetree/bindings/regulator/mcp16502-regulator.txt @@ -13923,7 +13918,7 @@ F: Documentation/devicetree/bindings/mtd/atmel-nand.txt F: drivers/mtd/nand/raw/atmel/* MICROCHIP OTPC DRIVER -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported F: Documentation/devicetree/bindings/nvmem/microchip,sama7g5-otpc.yaml @@ -13964,7 +13959,7 @@ F: Documentation/devicetree/bindings/fpga/microchip,mpf-spi-fpga-mgr.yaml F: drivers/fpga/microchip-spi.c MICROCHIP PWM DRIVER -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-pwm@vger.kernel.org S: Supported @@ -13980,7 +13975,7 @@ F: drivers/iio/adc/at91-sama5d2_adc.c F: include/dt-bindings/iio/adc/at91-sama5d2_adc.h MICROCHIP SAMA5D2-COMPATIBLE SHUTDOWN CONTROLLER -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> S: Supported F: Documentation/devicetree/bindings/power/reset/atmel,sama5d2-shdwc.yaml F: drivers/power/reset/at91-sama5d2_shdwc.c @@ -13997,7 +13992,7 @@ S: Supported F: drivers/spi/spi-atmel.* MICROCHIP SSC DRIVER -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported F: Documentation/devicetree/bindings/misc/atmel-ssc.txt @@ -14026,7 +14021,7 @@ F: drivers/usb/gadget/udc/atmel_usba_udc.* MICROCHIP WILC1000 WIFI DRIVER M: Ajay Singh <ajay.kathat@microchip.com> -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: linux-wireless@vger.kernel.org S: Supported F: drivers/net/wireless/microchip/wilc1000/ @@ -16309,6 +16304,7 @@ F: drivers/pci/controller/dwc/pci-exynos.c PCI DRIVER FOR SYNOPSYS DESIGNWARE M: Jingoo Han <jingoohan1@gmail.com> M: Gustavo Pimentel <gustavo.pimentel@synopsys.com> +M: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org> L: linux-pci@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pci/snps,dw-pcie-ep.yaml @@ -17460,6 +17456,7 @@ F: drivers/media/tuners/qt1010* QUALCOMM ATH12K WIRELESS DRIVER M: Kalle Valo <kvalo@kernel.org> +M: Jeff Johnson <quic_jjohnson@quicinc.com> L: ath12k@lists.infradead.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git @@ -17467,6 +17464,7 @@ F: drivers/net/wireless/ath/ath12k/ QUALCOMM ATHEROS ATH10K WIRELESS DRIVER M: Kalle Valo <kvalo@kernel.org> +M: Jeff Johnson <quic_jjohnson@quicinc.com> L: ath10k@lists.infradead.org S: Supported W: https://wireless.wiki.kernel.org/en/users/Drivers/ath10k @@ -17476,6 +17474,7 @@ F: drivers/net/wireless/ath/ath10k/ QUALCOMM ATHEROS ATH11K WIRELESS DRIVER M: Kalle Valo <kvalo@kernel.org> +M: Jeff Johnson <quic_jjohnson@quicinc.com> L: ath11k@lists.infradead.org S: Supported W: https://wireless.wiki.kernel.org/en/users/Drivers/ath11k @@ -17996,7 +17995,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.g F: drivers/net/wireless/realtek/rtlwifi/ REALTEK WIRELESS DRIVER (rtw88) -M: Yan-Hsuan Chuang <tony0620emma@gmail.com> +M: Ping-Ke Shih <pkshih@realtek.com> L: linux-wireless@vger.kernel.org S: Maintained F: drivers/net/wireless/realtek/rtw88/ @@ -18521,17 +18520,14 @@ RTL8180 WIRELESS DRIVER L: linux-wireless@vger.kernel.org S: Orphan W: https://wireless.wiki.kernel.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git F: drivers/net/wireless/realtek/rtl818x/rtl8180/ RTL8187 WIRELESS DRIVER -M: Herton Ronaldo Krzesinski <herton@canonical.com> -M: Hin-Tak Leung <htl10@users.sourceforge.net> +M: Hin-Tak Leung <hintak.leung@gmail.com> M: Larry Finger <Larry.Finger@lwfinger.net> L: linux-wireless@vger.kernel.org S: Maintained W: https://wireless.wiki.kernel.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git F: drivers/net/wireless/realtek/rtl818x/rtl8187/ RTL8XXXU WIRELESS DRIVER (rtl8xxxu) @@ -20415,7 +20411,6 @@ F: drivers/pwm/pwm-stm32* F: include/linux/*/stm32-*tim* STMMAC ETHERNET DRIVER -M: Giuseppe Cavallaro <peppe.cavallaro@st.com> M: Alexandre Torgue <alexandre.torgue@foss.st.com> M: Jose Abreu <joabreu@synopsys.com> L: netdev@vger.kernel.org @@ -21692,11 +21687,14 @@ S: Orphan F: drivers/net/ethernet/dec/tulip/ TUN/TAP driver -M: Maxim Krasnyansky <maxk@qti.qualcomm.com> +M: Willem de Bruijn <willemdebruijn.kernel@gmail.com> +M: Jason Wang <jasowang@redhat.com> S: Maintained W: http://vtun.sourceforge.net/tun F: Documentation/networking/tuntap.rst F: arch/um/os-Linux/drivers/ +F: drivers/net/tap.c +F: drivers/net/tun.c TURBOCHANNEL SUBSYSTEM M: "Maciej W. Rozycki" <macro@orcam.me.uk> @@ -21919,9 +21917,8 @@ S: Maintained F: drivers/usb/misc/apple-mfi-fastcharge.c USB AR5523 WIRELESS DRIVER -M: Pontus Fuchs <pontus.fuchs@gmail.com> L: linux-wireless@vger.kernel.org -S: Maintained +S: Orphan F: drivers/net/wireless/ath/ar5523/ USB ATTACHED SCSI @@ -22198,9 +22195,8 @@ F: drivers/usb/gadget/legacy/webcam.c F: include/uapi/linux/usb/g_uvc.h USB WIRELESS RNDIS DRIVER (rndis_wlan) -M: Jussi Kivilinna <jussi.kivilinna@iki.fi> L: linux-wireless@vger.kernel.org -S: Maintained +S: Orphan F: drivers/net/wireless/legacy/rndis_wlan.c USB XHCI DRIVER @@ -22975,7 +22971,7 @@ F: drivers/input/misc/wistron_btns.c WL3501 WIRELESS PCMCIA CARD DRIVER L: linux-wireless@vger.kernel.org -S: Odd fixes +S: Orphan F: drivers/net/wireless/legacy/wl3501* WMI BINARY MOF DRIVER @@ -23546,11 +23542,8 @@ S: Maintained F: mm/zbud.c ZD1211RW WIRELESS DRIVER -M: Ulrich Kunitz <kune@deine-taler.de> L: linux-wireless@vger.kernel.org -L: zd1211-devs@lists.sourceforge.net (subscribers-only) -S: Maintained -W: http://zd1211.ath.cx/wiki/DriverRewrite +S: Orphan F: drivers/net/wireless/zydas/zd1211rw/ ZD1301 MEDIA DRIVER @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc6 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h index 714abe494e5f..55bb1c09fd39 100644 --- a/arch/alpha/include/asm/processor.h +++ b/arch/alpha/include/asm/processor.h @@ -47,12 +47,6 @@ unsigned long __get_wchan(struct task_struct *p); #define ARCH_HAS_PREFETCH #define ARCH_HAS_PREFETCHW -#define ARCH_HAS_SPINLOCK_PREFETCH - -#ifndef CONFIG_SMP -/* Nothing to prefetch. */ -#define spin_lock_prefetch(lock) do { } while (0) -#endif extern inline void prefetch(const void *ptr) { @@ -64,11 +58,4 @@ extern inline void prefetchw(const void *ptr) __builtin_prefetch(ptr, 1, 3); } -#ifdef CONFIG_SMP -extern inline void spin_lock_prefetch(const void *ptr) -{ - __builtin_prefetch(ptr, 1, 3); -} -#endif - #endif /* __ASM_ALPHA_PROCESSOR_H */ diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index b650ff1cb022..3d7473531ab1 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -385,8 +385,7 @@ setup_memory(void *kernel_end) #endif /* CONFIG_BLK_DEV_INITRD */ } -int __init -page_is_ram(unsigned long pfn) +int page_is_ram(unsigned long pfn) { struct memclust_struct * cluster; struct memdesc_struct * memdesc; diff --git a/arch/arm/boot/dts/microchip/sam9x60.dtsi b/arch/arm/boot/dts/microchip/sam9x60.dtsi index 8b53997675e7..73d570a17269 100644 --- a/arch/arm/boot/dts/microchip/sam9x60.dtsi +++ b/arch/arm/boot/dts/microchip/sam9x60.dtsi @@ -172,7 +172,7 @@ status = "disabled"; uart4: serial@200 { - compatible = "microchip,sam9x60-dbgu", "microchip,sam9x60-usart", "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; + compatible = "microchip,sam9x60-usart", "atmel,at91sam9260-usart"; reg = <0x200 0x200>; interrupts = <13 IRQ_TYPE_LEVEL_HIGH 7>; dmas = <&dma0 @@ -240,7 +240,7 @@ status = "disabled"; uart5: serial@200 { - compatible = "microchip,sam9x60-dbgu", "microchip,sam9x60-usart", "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; + compatible = "microchip,sam9x60-usart", "atmel,at91sam9260-usart"; reg = <0x200 0x200>; atmel,usart-mode = <AT91_USART_MODE_SERIAL>; interrupts = <14 IRQ_TYPE_LEVEL_HIGH 7>; @@ -370,7 +370,7 @@ status = "disabled"; uart11: serial@200 { - compatible = "microchip,sam9x60-dbgu", "microchip,sam9x60-usart", "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; + compatible = "microchip,sam9x60-usart", "atmel,at91sam9260-usart"; reg = <0x200 0x200>; interrupts = <32 IRQ_TYPE_LEVEL_HIGH 7>; dmas = <&dma0 @@ -419,7 +419,7 @@ status = "disabled"; uart12: serial@200 { - compatible = "microchip,sam9x60-dbgu", "microchip,sam9x60-usart", "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; + compatible = "microchip,sam9x60-usart", "atmel,at91sam9260-usart"; reg = <0x200 0x200>; interrupts = <33 IRQ_TYPE_LEVEL_HIGH 7>; dmas = <&dma0 @@ -576,7 +576,7 @@ status = "disabled"; uart6: serial@200 { - compatible = "microchip,sam9x60-dbgu", "microchip,sam9x60-usart", "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; + compatible = "microchip,sam9x60-usart", "atmel,at91sam9260-usart"; reg = <0x200 0x200>; interrupts = <9 IRQ_TYPE_LEVEL_HIGH 7>; dmas = <&dma0 @@ -625,7 +625,7 @@ status = "disabled"; uart7: serial@200 { - compatible = "microchip,sam9x60-dbgu", "microchip,sam9x60-usart", "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; + compatible = "microchip,sam9x60-usart", "atmel,at91sam9260-usart"; reg = <0x200 0x200>; interrupts = <10 IRQ_TYPE_LEVEL_HIGH 7>; dmas = <&dma0 @@ -674,7 +674,7 @@ status = "disabled"; uart8: serial@200 { - compatible = "microchip,sam9x60-dbgu", "microchip,sam9x60-usart", "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; + compatible = "microchip,sam9x60-usart", "atmel,at91sam9260-usart"; reg = <0x200 0x200>; interrupts = <11 IRQ_TYPE_LEVEL_HIGH 7>; dmas = <&dma0 @@ -723,7 +723,7 @@ status = "disabled"; uart0: serial@200 { - compatible = "microchip,sam9x60-dbgu", "microchip,sam9x60-usart", "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; + compatible = "microchip,sam9x60-usart", "atmel,at91sam9260-usart"; reg = <0x200 0x200>; interrupts = <5 IRQ_TYPE_LEVEL_HIGH 7>; dmas = <&dma0 @@ -791,7 +791,7 @@ status = "disabled"; uart1: serial@200 { - compatible = "microchip,sam9x60-dbgu", "microchip,sam9x60-usart", "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; + compatible = "microchip,sam9x60-usart", "atmel,at91sam9260-usart"; reg = <0x200 0x200>; interrupts = <6 IRQ_TYPE_LEVEL_HIGH 7>; dmas = <&dma0 @@ -859,7 +859,7 @@ status = "disabled"; uart2: serial@200 { - compatible = "microchip,sam9x60-dbgu", "microchip,sam9x60-usart", "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; + compatible = "microchip,sam9x60-usart", "atmel,at91sam9260-usart"; reg = <0x200 0x200>; interrupts = <7 IRQ_TYPE_LEVEL_HIGH 7>; dmas = <&dma0 @@ -927,7 +927,7 @@ status = "disabled"; uart3: serial@200 { - compatible = "microchip,sam9x60-dbgu", "microchip,sam9x60-usart", "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; + compatible = "microchip,sam9x60-usart", "atmel,at91sam9260-usart"; reg = <0x200 0x200>; interrupts = <8 IRQ_TYPE_LEVEL_HIGH 7>; dmas = <&dma0 @@ -1050,7 +1050,7 @@ status = "disabled"; uart9: serial@200 { - compatible = "microchip,sam9x60-dbgu", "microchip,sam9x60-usart", "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; + compatible = "microchip,sam9x60-usart", "atmel,at91sam9260-usart"; reg = <0x200 0x200>; interrupts = <15 IRQ_TYPE_LEVEL_HIGH 7>; dmas = <&dma0 @@ -1099,7 +1099,7 @@ status = "disabled"; uart10: serial@200 { - compatible = "microchip,sam9x60-dbgu", "microchip,sam9x60-usart", "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; + compatible = "microchip,sam9x60-usart", "atmel,at91sam9260-usart"; reg = <0x200 0x200>; interrupts = <16 IRQ_TYPE_LEVEL_HIGH 7>; dmas = <&dma0 diff --git a/arch/arm/boot/dts/nspire/nspire.dtsi b/arch/arm/boot/dts/nspire/nspire.dtsi index bb240e6a3a6f..088bcc38589f 100644 --- a/arch/arm/boot/dts/nspire/nspire.dtsi +++ b/arch/arm/boot/dts/nspire/nspire.dtsi @@ -161,7 +161,7 @@ }; watchdog: watchdog@90060000 { - compatible = "arm,amba-primecell"; + compatible = "arm,primecell"; reg = <0x90060000 0x1000>; interrupts = <3>; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx53-sk-imx53.dts b/arch/arm/boot/dts/nxp/imx/imx53-sk-imx53.dts index 103e73176e47..1a00d290092a 100644 --- a/arch/arm/boot/dts/nxp/imx/imx53-sk-imx53.dts +++ b/arch/arm/boot/dts/nxp/imx/imx53-sk-imx53.dts @@ -60,6 +60,16 @@ status = "okay"; }; +&cpu0 { + /* CPU rated to 800 MHz, not the default 1.2GHz. */ + operating-points = < + /* kHz uV */ + 166666 850000 + 400000 900000 + 800000 1050000 + >; +}; + &ecspi1 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_ecspi1>; diff --git a/arch/arm/boot/dts/nxp/imx/imx6sll.dtsi b/arch/arm/boot/dts/nxp/imx/imx6sll.dtsi index 2873369a57c0..3659fd5ecfa6 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6sll.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6sll.dtsi @@ -552,7 +552,7 @@ reg = <0x020ca000 0x1000>; interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6SLL_CLK_USBPHY2>; - phy-reg_3p0-supply = <®_3p0>; + phy-3p0-supply = <®_3p0>; fsl,anatop = <&anatop>; }; diff --git a/arch/arm/mach-pxa/sharpsl_pm.h b/arch/arm/mach-pxa/sharpsl_pm.h index 20e4cab64d85..623167f30ec2 100644 --- a/arch/arm/mach-pxa/sharpsl_pm.h +++ b/arch/arm/mach-pxa/sharpsl_pm.h @@ -105,5 +105,4 @@ void sharpsl_pm_led(int val); #define MAX1111_ACIN_VOLT 6u int sharpsl_pm_pxa_read_max1111(int channel); -void corgi_lcd_limit_intensity(int limit); #endif diff --git a/arch/arm/mach-pxa/spitz_pm.c b/arch/arm/mach-pxa/spitz_pm.c index 1c021cef965f..8bc4ea51a0c1 100644 --- a/arch/arm/mach-pxa/spitz_pm.c +++ b/arch/arm/mach-pxa/spitz_pm.c @@ -15,6 +15,7 @@ #include <linux/interrupt.h> #include <linux/platform_device.h> #include <linux/apm-emulation.h> +#include <linux/spi/corgi_lcd.h> #include <asm/irq.h> #include <asm/mach-types.h> diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts index 38ae674f2f02..3037f58057c9 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts @@ -145,7 +145,7 @@ status = "okay"; clock-frequency = <100000>; i2c-sda-falling-time-ns = <890>; /* hcnt */ - i2c-sdl-falling-time-ns = <890>; /* lcnt */ + i2c-scl-falling-time-ns = <890>; /* lcnt */ pinctrl-names = "default", "gpio"; pinctrl-0 = <&i2c1_pmx_func>; diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts index ede99dcc0558..f4cf30bac557 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts @@ -141,7 +141,7 @@ status = "okay"; clock-frequency = <100000>; i2c-sda-falling-time-ns = <890>; /* hcnt */ - i2c-sdl-falling-time-ns = <890>; /* lcnt */ + i2c-scl-falling-time-ns = <890>; /* lcnt */ adc@14 { compatible = "lltc,ltc2497"; diff --git a/arch/arm64/boot/dts/arm/vexpress-v2m-rs1.dtsi b/arch/arm64/boot/dts/arm/vexpress-v2m-rs1.dtsi deleted file mode 120000 index 68fd0f8f1dee..000000000000 --- a/arch/arm64/boot/dts/arm/vexpress-v2m-rs1.dtsi +++ /dev/null @@ -1 +0,0 @@ -../../../../arm/boot/dts/vexpress-v2m-rs1.dtsi
\ No newline at end of file diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts b/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts index 03e7679217b2..479948f8a4b7 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts @@ -141,7 +141,7 @@ }; &gpio1 { - gpio-line-names = "nINT_ETHPHY", "LED_RED", "WDOG_INT", "X_RTC_INT", + gpio-line-names = "", "LED_RED", "WDOG_INT", "X_RTC_INT", "", "", "", "RESET_ETHPHY", "CAN_nINT", "CAN_EN", "nENABLE_FLATLINK", "", "USB_OTG_VBUS_EN", "", "LED_GREEN", "LED_BLUE"; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi index 92616bc4f71f..847f08537b48 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi @@ -111,7 +111,7 @@ }; &gpio1 { - gpio-line-names = "nINT_ETHPHY", "", "WDOG_INT", "X_RTC_INT", + gpio-line-names = "", "", "WDOG_INT", "X_RTC_INT", "", "", "", "RESET_ETHPHY", "", "", "nENABLE_FLATLINK"; }; @@ -210,7 +210,7 @@ }; }; - reg_vdd_gpu: buck3 { + reg_vdd_vpu: buck3 { regulator-always-on; regulator-boot-on; regulator-max-microvolt = <1000000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts index 6f26914602c8..07b07dc954fd 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts @@ -567,6 +567,10 @@ status = "okay"; }; +&disp_blk_ctrl { + status = "disabled"; +}; + &pgc_mipi { status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7904.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7904.dts index 93088fa1c3b9..d5b716855812 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7904.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7904.dts @@ -628,6 +628,10 @@ status = "okay"; }; +&disp_blk_ctrl { + status = "disabled"; +}; + &pgc_mipi { status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi index d3a67109d55b..b8946edf317b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi @@ -358,7 +358,7 @@ MX8MN_IOMUXC_ENET_RXC_ENET1_RGMII_RXC 0x91 MX8MN_IOMUXC_ENET_RX_CTL_ENET1_RGMII_RX_CTL 0x91 MX8MN_IOMUXC_ENET_TX_CTL_ENET1_RGMII_TX_CTL 0x1f - MX8MN_IOMUXC_GPIO1_IO09_GPIO1_IO9 0x19 + MX8MN_IOMUXC_GPIO1_IO09_GPIO1_IO9 0x159 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 1a2d2c04db32..01eec424f7f7 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -772,7 +772,7 @@ <&clk IMX8MQ_SYS1_PLL_800M>, <&clk IMX8MQ_VPU_PLL>; assigned-clock-rates = <600000000>, - <600000000>, + <300000000>, <800000000>, <0>; }; diff --git a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi index 232910e07444..66f68fc2b241 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi @@ -223,20 +223,20 @@ <GIC_SPI 212 IRQ_TYPE_EDGE_RISING>, <GIC_SPI 213 IRQ_TYPE_EDGE_RISING>; interrupt-names = "tgia0", "tgib0", "tgic0", "tgid0", - "tgiv0", "tgie0", "tgif0", - "tgia1", "tgib1", "tgiv1", "tgiu1", - "tgia2", "tgib2", "tgiv2", "tgiu2", + "tciv0", "tgie0", "tgif0", + "tgia1", "tgib1", "tciv1", "tciu1", + "tgia2", "tgib2", "tciv2", "tciu2", "tgia3", "tgib3", "tgic3", "tgid3", - "tgiv3", + "tciv3", "tgia4", "tgib4", "tgic4", "tgid4", - "tgiv4", + "tciv4", "tgiu5", "tgiv5", "tgiw5", "tgia6", "tgib6", "tgic6", "tgid6", - "tgiv6", + "tciv6", "tgia7", "tgib7", "tgic7", "tgid7", - "tgiv7", + "tciv7", "tgia8", "tgib8", "tgic8", "tgid8", - "tgiv8", "tgiu8"; + "tciv8", "tciu8"; clocks = <&cpg CPG_MOD R9A07G044_MTU_X_MCK_MTU3>; power-domains = <&cpg>; resets = <&cpg R9A07G044_MTU_X_PRESET_MTU3>; diff --git a/arch/arm64/boot/dts/renesas/r9a07g054.dtsi b/arch/arm64/boot/dts/renesas/r9a07g054.dtsi index 2eba3a8a100d..1f1d481dc783 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g054.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g054.dtsi @@ -223,20 +223,20 @@ <GIC_SPI 212 IRQ_TYPE_EDGE_RISING>, <GIC_SPI 213 IRQ_TYPE_EDGE_RISING>; interrupt-names = "tgia0", "tgib0", "tgic0", "tgid0", - "tgiv0", "tgie0", "tgif0", - "tgia1", "tgib1", "tgiv1", "tgiu1", - "tgia2", "tgib2", "tgiv2", "tgiu2", + "tciv0", "tgie0", "tgif0", + "tgia1", "tgib1", "tciv1", "tciu1", + "tgia2", "tgib2", "tciv2", "tciu2", "tgia3", "tgib3", "tgic3", "tgid3", - "tgiv3", + "tciv3", "tgia4", "tgib4", "tgic4", "tgid4", - "tgiv4", + "tciv4", "tgiu5", "tgiv5", "tgiw5", "tgia6", "tgib6", "tgic6", "tgid6", - "tgiv6", + "tciv6", "tgia7", "tgib7", "tgic7", "tgid7", - "tgiv7", + "tciv7", "tgia8", "tgib8", "tgic8", "tgid8", - "tgiv8", "tgiu8"; + "tciv8", "tciu8"; clocks = <&cpg CPG_MOD R9A07G054_MTU_X_MCK_MTU3>; power-domains = <&cpg>; resets = <&cpg R9A07G054_MTU_X_PRESET_MTU3>; diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 8e5ffb58f83e..b7afaa026842 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -31,6 +31,13 @@ .Lskip_hcrx_\@: .endm +/* Check if running in host at EL2 mode, i.e., (h)VHE. Jump to fail if not. */ +.macro __check_hvhe fail, tmp + mrs \tmp, hcr_el2 + and \tmp, \tmp, #HCR_E2H + cbz \tmp, \fail +.endm + /* * Allow Non-secure EL1 and EL0 to access physical timer and counter. * This is not necessary for VHE, since the host kernel runs in EL2, @@ -43,9 +50,7 @@ */ .macro __init_el2_timers mov x0, #3 // Enable EL1 physical timers - mrs x1, hcr_el2 - and x1, x1, #HCR_E2H - cbz x1, .LnVHE_\@ + __check_hvhe .LnVHE_\@, x1 lsl x0, x0, #10 .LnVHE_\@: msr cnthctl_el2, x0 @@ -139,15 +144,14 @@ /* Coprocessor traps */ .macro __init_el2_cptr - mrs x1, hcr_el2 - and x1, x1, #HCR_E2H - cbz x1, .LnVHE_\@ + __check_hvhe .LnVHE_\@, x1 mov x0, #(CPACR_EL1_FPEN_EL1EN | CPACR_EL1_FPEN_EL0EN) - b .Lset_cptr_\@ + msr cpacr_el1, x0 + b .Lskip_set_cptr_\@ .LnVHE_\@: mov x0, #0x33ff -.Lset_cptr_\@: msr cptr_el2, x0 // Disable copro. traps to EL2 +.Lskip_set_cptr_\@: .endm /* Disable any fine grained traps */ @@ -268,19 +272,19 @@ check_override id_aa64pfr0, ID_AA64PFR0_EL1_SVE_SHIFT, .Linit_sve_\@, .Lskip_sve_\@, x1, x2 .Linit_sve_\@: /* SVE register access */ - mrs x0, cptr_el2 // Disable SVE traps - mrs x1, hcr_el2 - and x1, x1, #HCR_E2H - cbz x1, .Lcptr_nvhe_\@ + __check_hvhe .Lcptr_nvhe_\@, x1 - // VHE case + // (h)VHE case + mrs x0, cpacr_el1 // Disable SVE traps orr x0, x0, #(CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN) - b .Lset_cptr_\@ + msr cpacr_el1, x0 + b .Lskip_set_cptr_\@ .Lcptr_nvhe_\@: // nVHE case + mrs x0, cptr_el2 // Disable SVE traps bic x0, x0, #CPTR_EL2_TZ -.Lset_cptr_\@: msr cptr_el2, x0 +.Lskip_set_cptr_\@: isb mov x1, #ZCR_ELx_LEN_MASK // SVE: Enable full vector msr_s SYS_ZCR_EL2, x1 // length for EL1. @@ -289,9 +293,19 @@ check_override id_aa64pfr1, ID_AA64PFR1_EL1_SME_SHIFT, .Linit_sme_\@, .Lskip_sme_\@, x1, x2 .Linit_sme_\@: /* SME register access and priority mapping */ + __check_hvhe .Lcptr_nvhe_sme_\@, x1 + + // (h)VHE case + mrs x0, cpacr_el1 // Disable SME traps + orr x0, x0, #(CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN) + msr cpacr_el1, x0 + b .Lskip_set_cptr_sme_\@ + +.Lcptr_nvhe_sme_\@: // nVHE case mrs x0, cptr_el2 // Disable SME traps bic x0, x0, #CPTR_EL2_TSM msr cptr_el2, x0 +.Lskip_set_cptr_sme_\@: isb mrs x1, sctlr_el2 diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 7d170aaa2db4..24e28bb2d95b 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -278,7 +278,7 @@ asmlinkage void __noreturn hyp_panic_bad_stack(void); asmlinkage void kvm_unexpected_el2_exception(void); struct kvm_cpu_context; void handle_trap(struct kvm_cpu_context *host_ctxt); -asmlinkage void __noreturn kvm_host_psci_cpu_entry(bool is_cpu_on); +asmlinkage void __noreturn __kvm_host_psci_cpu_entry(bool is_cpu_on); void __noreturn __pkvm_init_finalise(void); void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc); void kvm_patch_vector_branch(struct alt_instr *alt, diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index efc0b45d79c3..3d6725ff0bf6 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -571,6 +571,14 @@ static inline bool vcpu_has_feature(struct kvm_vcpu *vcpu, int feature) return test_bit(feature, vcpu->arch.features); } +static __always_inline void kvm_write_cptr_el2(u64 val) +{ + if (has_vhe() || has_hvhe()) + write_sysreg(val, cpacr_el1); + else + write_sysreg(val, cptr_el2); +} + static __always_inline u64 kvm_get_reset_cptr_el2(struct kvm_vcpu *vcpu) { u64 val; @@ -578,8 +586,16 @@ static __always_inline u64 kvm_get_reset_cptr_el2(struct kvm_vcpu *vcpu) if (has_vhe()) { val = (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN | CPACR_EL1_ZEN_EL1EN); + if (cpus_have_final_cap(ARM64_SME)) + val |= CPACR_EL1_SMEN_EL1EN; } else if (has_hvhe()) { val = (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN); + + if (!vcpu_has_sve(vcpu) || + (vcpu->arch.fp_state != FP_STATE_GUEST_OWNED)) + val |= CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN; + if (cpus_have_final_cap(ARM64_SME)) + val |= CPACR_EL1_SMEN_EL1EN | CPACR_EL1_SMEN_EL0EN; } else { val = CPTR_NVHE_EL2_RES1; @@ -597,9 +613,6 @@ static __always_inline void kvm_reset_cptr_el2(struct kvm_vcpu *vcpu) { u64 val = kvm_get_reset_cptr_el2(vcpu); - if (has_vhe() || has_hvhe()) - write_sysreg(val, cpacr_el1); - else - write_sysreg(val, cptr_el2); + kvm_write_cptr_el2(val); } #endif /* __ARM64_KVM_EMULATE_H__ */ diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 3918f2a67970..e5bc54522e71 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -359,14 +359,6 @@ static inline void prefetchw(const void *ptr) asm volatile("prfm pstl1keep, %a0\n" : : "p" (ptr)); } -#define ARCH_HAS_SPINLOCK_PREFETCH -static inline void spin_lock_prefetch(const void *ptr) -{ - asm volatile(ARM64_LSE_ATOMIC_INSN( - "prfm pstl1strm, %a0", - "nop") : : "p" (ptr)); -} - extern unsigned long __ro_after_init signal_minsigstksz; /* sigframe size */ extern void __init minsigstksz_setup(void); diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 520b681a07bb..75c37b1c55aa 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -679,7 +679,7 @@ static void fpsimd_to_sve(struct task_struct *task) void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; - if (!system_supports_sve()) + if (!system_supports_sve() && !system_supports_sme()) return; vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); @@ -705,7 +705,7 @@ static void sve_to_fpsimd(struct task_struct *task) unsigned int i; __uint128_t const *p; - if (!system_supports_sve()) + if (!system_supports_sve() && !system_supports_sme()) return; vl = thread_get_cur_vl(&task->thread); @@ -835,7 +835,8 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; - if (!test_tsk_thread_flag(task, TIF_SVE)) + if (!test_tsk_thread_flag(task, TIF_SVE) && + !thread_sm_enabled(&task->thread)) return; vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); @@ -909,7 +910,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, */ task->thread.svcr &= ~(SVCR_SM_MASK | SVCR_ZA_MASK); - clear_thread_flag(TIF_SME); + clear_tsk_thread_flag(task, TIF_SME); free_sme = true; } } diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index d7f4f0d1ae12..5b9b4305248b 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -932,11 +932,13 @@ static int sve_set_common(struct task_struct *target, /* * Ensure target->thread.sve_state is up to date with target's * FPSIMD regs, so that a short copyin leaves trailing - * registers unmodified. Always enable SVE even if going into - * streaming mode. + * registers unmodified. Only enable SVE if we are + * configuring normal SVE, a system with streaming SVE may not + * have normal SVE. */ fpsimd_sync_to_sve(target); - set_tsk_thread_flag(target, TIF_SVE); + if (type == ARM64_VEC_SVE) + set_tsk_thread_flag(target, TIF_SVE); target->thread.fp_type = FP_STATE_SVE; BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); @@ -1180,6 +1182,8 @@ static int zt_set(struct task_struct *target, if (ret == 0) target->thread.svcr |= SVCR_ZA_MASK; + fpsimd_flush_task_state(target); + return ret; } diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 72dc53a75d1c..d1cb298a58a0 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -55,7 +55,7 @@ DECLARE_KVM_NVHE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt); static bool vgic_present, kvm_arm_initialised; -static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled); +static DEFINE_PER_CPU(unsigned char, kvm_hyp_initialized); DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use); bool is_kvm_arm_initialised(void) @@ -1864,18 +1864,24 @@ static void cpu_hyp_reinit(void) cpu_hyp_init_features(); } -static void _kvm_arch_hardware_enable(void *discard) +static void cpu_hyp_init(void *discard) { - if (!__this_cpu_read(kvm_arm_hardware_enabled)) { + if (!__this_cpu_read(kvm_hyp_initialized)) { cpu_hyp_reinit(); - __this_cpu_write(kvm_arm_hardware_enabled, 1); + __this_cpu_write(kvm_hyp_initialized, 1); } } -int kvm_arch_hardware_enable(void) +static void cpu_hyp_uninit(void *discard) { - int was_enabled; + if (__this_cpu_read(kvm_hyp_initialized)) { + cpu_hyp_reset(); + __this_cpu_write(kvm_hyp_initialized, 0); + } +} +int kvm_arch_hardware_enable(void) +{ /* * Most calls to this function are made with migration * disabled, but not with preemption disabled. The former is @@ -1884,36 +1890,23 @@ int kvm_arch_hardware_enable(void) */ preempt_disable(); - was_enabled = __this_cpu_read(kvm_arm_hardware_enabled); - _kvm_arch_hardware_enable(NULL); + cpu_hyp_init(NULL); - if (!was_enabled) { - kvm_vgic_cpu_up(); - kvm_timer_cpu_up(); - } + kvm_vgic_cpu_up(); + kvm_timer_cpu_up(); preempt_enable(); return 0; } -static void _kvm_arch_hardware_disable(void *discard) -{ - if (__this_cpu_read(kvm_arm_hardware_enabled)) { - cpu_hyp_reset(); - __this_cpu_write(kvm_arm_hardware_enabled, 0); - } -} - void kvm_arch_hardware_disable(void) { - if (__this_cpu_read(kvm_arm_hardware_enabled)) { - kvm_timer_cpu_down(); - kvm_vgic_cpu_down(); - } + kvm_timer_cpu_down(); + kvm_vgic_cpu_down(); if (!is_protected_kvm_enabled()) - _kvm_arch_hardware_disable(NULL); + cpu_hyp_uninit(NULL); } #ifdef CONFIG_CPU_PM @@ -1922,16 +1915,16 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self, void *v) { /* - * kvm_arm_hardware_enabled is left with its old value over + * kvm_hyp_initialized is left with its old value over * PM_ENTER->PM_EXIT. It is used to indicate PM_EXIT should * re-enable hyp. */ switch (cmd) { case CPU_PM_ENTER: - if (__this_cpu_read(kvm_arm_hardware_enabled)) + if (__this_cpu_read(kvm_hyp_initialized)) /* - * don't update kvm_arm_hardware_enabled here - * so that the hardware will be re-enabled + * don't update kvm_hyp_initialized here + * so that the hyp will be re-enabled * when we resume. See below. */ cpu_hyp_reset(); @@ -1939,8 +1932,8 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self, return NOTIFY_OK; case CPU_PM_ENTER_FAILED: case CPU_PM_EXIT: - if (__this_cpu_read(kvm_arm_hardware_enabled)) - /* The hardware was enabled before suspend. */ + if (__this_cpu_read(kvm_hyp_initialized)) + /* The hyp was enabled before suspend. */ cpu_hyp_reinit(); return NOTIFY_OK; @@ -2021,7 +2014,7 @@ static int __init init_subsystems(void) /* * Enable hardware so that subsystem initialisation can access EL2. */ - on_each_cpu(_kvm_arch_hardware_enable, NULL, 1); + on_each_cpu(cpu_hyp_init, NULL, 1); /* * Register CPU lower-power notifier @@ -2059,7 +2052,7 @@ out: hyp_cpu_pm_exit(); if (err || !is_protected_kvm_enabled()) - on_each_cpu(_kvm_arch_hardware_disable, NULL, 1); + on_each_cpu(cpu_hyp_uninit, NULL, 1); return err; } @@ -2097,7 +2090,7 @@ static int __init do_pkvm_init(u32 hyp_va_bits) * The stub hypercalls are now disabled, so set our local flag to * prevent a later re-init attempt in kvm_arch_hardware_enable(). */ - __this_cpu_write(kvm_arm_hardware_enabled, 1); + __this_cpu_write(kvm_hyp_initialized, 1); preempt_enable(); return ret; diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 4bddb8541bec..34f222af6165 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -457,6 +457,7 @@ static bool handle_ampere1_tcr(struct kvm_vcpu *vcpu) */ val &= ~(TCR_HD | TCR_HA); write_sysreg_el1(val, SYS_TCR); + __kvm_skip_instr(vcpu); return true; } diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c index 58dcd92bf346..ab4f5d160c58 100644 --- a/arch/arm64/kvm/hyp/nvhe/ffa.c +++ b/arch/arm64/kvm/hyp/nvhe/ffa.c @@ -705,7 +705,20 @@ int hyp_ffa_init(void *pages) if (res.a0 == FFA_RET_NOT_SUPPORTED) return 0; - if (res.a0 != FFA_VERSION_1_0) + /* + * Firmware returns the maximum supported version of the FF-A + * implementation. Check that the returned version is + * backwards-compatible with the hyp according to the rules in DEN0077A + * v1.1 REL0 13.2.1. + * + * Of course, things are never simple when dealing with firmware. v1.1 + * broke ABI with v1.0 on several structures, which is itself + * incompatible with the aforementioned versioning scheme. The + * expectation is that v1.x implementations that do not support the v1.0 + * ABI return NOT_SUPPORTED rather than a version number, according to + * DEN0077A v1.1 REL0 18.6.4. + */ + if (FFA_MAJOR_VERSION(res.a0) != 1) return -EOPNOTSUPP; arm_smccc_1_1_smc(FFA_ID_GET, 0, 0, 0, 0, 0, 0, 0, &res); diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 0a6271052def..e89a23153e85 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -63,7 +63,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu) __activate_traps_fpsimd32(vcpu); } - write_sysreg(val, cptr_el2); + kvm_write_cptr_el2(val); write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2); if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h index d1978e004054..47e3801b526a 100644 --- a/arch/ia64/include/asm/processor.h +++ b/arch/ia64/include/asm/processor.h @@ -634,7 +634,6 @@ ia64_imva (void *addr) #define ARCH_HAS_PREFETCH #define ARCH_HAS_PREFETCHW -#define ARCH_HAS_SPINLOCK_PREFETCH #define PREFETCH_STRIDE L1_CACHE_BYTES static inline void @@ -649,8 +648,6 @@ prefetchw (const void *x) ia64_lfetch_excl(ia64_lfhint_none, x); } -#define spin_lock_prefetch(x) prefetchw(x) - extern unsigned long boot_option_idle_override; enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_FORCE_MWAIT, diff --git a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h index 9151dcd9d0d5..af9cea21c853 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h @@ -58,8 +58,6 @@ #define cpu_has_rixi (cpu_data[0].cputype != CPU_CAVIUM_OCTEON) -#define ARCH_HAS_SPINLOCK_PREFETCH 1 -#define spin_lock_prefetch(x) prefetch(x) #define PREFETCH_STRIDE 128 #ifdef __OCTEON__ diff --git a/arch/parisc/Kconfig.debug b/arch/parisc/Kconfig.debug index 1401e4c5fe5f..bf2b21b96f0b 100644 --- a/arch/parisc/Kconfig.debug +++ b/arch/parisc/Kconfig.debug @@ -2,7 +2,7 @@ # config LIGHTWEIGHT_SPINLOCK_CHECK bool "Enable lightweight spinlock checks" - depends on SMP && !DEBUG_SPINLOCK + depends on DEBUG_KERNEL && SMP && !DEBUG_SPINLOCK default y help Add checks with low performance impact to the spinlock functions diff --git a/arch/parisc/boot/compressed/misc.c b/arch/parisc/boot/compressed/misc.c index 7ee49f5881d1..d389359e22ac 100644 --- a/arch/parisc/boot/compressed/misc.c +++ b/arch/parisc/boot/compressed/misc.c @@ -117,7 +117,7 @@ char *strchr(const char *s, int c) return NULL; } -int puts(const char *s) +static int puts(const char *s) { const char *nuline = s; @@ -172,7 +172,7 @@ static int print_num(unsigned long num, int base) return 0; } -int printf(const char *fmt, ...) +static int printf(const char *fmt, ...) { va_list args; int i = 0; @@ -204,13 +204,13 @@ void abort(void) } #undef malloc -void *malloc(size_t size) +static void *malloc(size_t size) { return malloc_gzip(size); } #undef free -void free(void *ptr) +static void free(void *ptr) { return free_gzip(ptr); } @@ -278,7 +278,7 @@ static void parse_elf(void *output) free(phdrs); } -unsigned long decompress_kernel(unsigned int started_wide, +asmlinkage unsigned long __visible decompress_kernel(unsigned int started_wide, unsigned int command_line, const unsigned int rd_start, const unsigned int rd_end) diff --git a/arch/parisc/include/asm/dma.h b/arch/parisc/include/asm/dma.h index 9e8c101de902..582fb5d1a5d5 100644 --- a/arch/parisc/include/asm/dma.h +++ b/arch/parisc/include/asm/dma.h @@ -14,6 +14,8 @@ #define dma_outb outb #define dma_inb inb +extern unsigned long pcxl_dma_start; + /* ** DMA_CHUNK_SIZE is used by the SCSI mid-layer to break up ** (or rather not merge) DMAs into manageable chunks. diff --git a/arch/parisc/include/asm/ftrace.h b/arch/parisc/include/asm/ftrace.h index a7cf0d05ccf4..f1cc1ee3a647 100644 --- a/arch/parisc/include/asm/ftrace.h +++ b/arch/parisc/include/asm/ftrace.h @@ -12,6 +12,10 @@ extern void mcount(void); extern unsigned long sys_call_table[]; extern unsigned long return_address(unsigned int); +struct ftrace_regs; +extern void ftrace_function_trampoline(unsigned long parent, + unsigned long self_addr, unsigned long org_sp_gr3, + struct ftrace_regs *fregs); #ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_caller(void); diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h index edfcb9858bcb..0b326e52255e 100644 --- a/arch/parisc/include/asm/spinlock.h +++ b/arch/parisc/include/asm/spinlock.h @@ -7,8 +7,6 @@ #include <asm/processor.h> #include <asm/spinlock_types.h> -#define SPINLOCK_BREAK_INSN 0x0000c006 /* break 6,6 */ - static inline void arch_spin_val_check(int lock_val) { if (IS_ENABLED(CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK)) diff --git a/arch/parisc/include/asm/spinlock_types.h b/arch/parisc/include/asm/spinlock_types.h index d65934079ebd..efd06a897c6a 100644 --- a/arch/parisc/include/asm/spinlock_types.h +++ b/arch/parisc/include/asm/spinlock_types.h @@ -4,6 +4,10 @@ #define __ARCH_SPIN_LOCK_UNLOCKED_VAL 0x1a46 +#define SPINLOCK_BREAK_INSN 0x0000c006 /* break 6,6 */ + +#ifndef __ASSEMBLY__ + typedef struct { #ifdef CONFIG_PA20 volatile unsigned int slock; @@ -27,6 +31,8 @@ typedef struct { volatile unsigned int counter; } arch_rwlock_t; +#endif /* __ASSEMBLY__ */ + #define __ARCH_RW_LOCK_UNLOCKED__ 0x01000000 #define __ARCH_RW_LOCK_UNLOCKED { .lock_mutex = __ARCH_SPIN_LOCK_UNLOCKED, \ .counter = __ARCH_RW_LOCK_UNLOCKED__ } diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 6d1c781eb1db..8f37e75f2fb9 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -74,8 +74,8 @@ static DEFINE_SPINLOCK(pdc_lock); #endif -unsigned long pdc_result[NUM_PDC_RESULT] __aligned(8); -unsigned long pdc_result2[NUM_PDC_RESULT] __aligned(8); +static unsigned long pdc_result[NUM_PDC_RESULT] __aligned(8); +static unsigned long pdc_result2[NUM_PDC_RESULT] __aligned(8); #ifdef CONFIG_64BIT #define WIDE_FIRMWARE 0x1 @@ -334,7 +334,7 @@ int __pdc_cpu_rendezvous(void) /** * pdc_cpu_rendezvous_lock - Lock PDC while transitioning to rendezvous state */ -void pdc_cpu_rendezvous_lock(void) +void pdc_cpu_rendezvous_lock(void) __acquires(&pdc_lock) { spin_lock(&pdc_lock); } @@ -342,7 +342,7 @@ void pdc_cpu_rendezvous_lock(void) /** * pdc_cpu_rendezvous_unlock - Unlock PDC after reaching rendezvous state */ -void pdc_cpu_rendezvous_unlock(void) +void pdc_cpu_rendezvous_unlock(void) __releases(&pdc_lock) { spin_unlock(&pdc_lock); } diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index 4d392e4ed358..d1defb9ede70 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -53,7 +53,7 @@ static void __hot prepare_ftrace_return(unsigned long *parent, static ftrace_func_t ftrace_func; -void notrace __hot ftrace_function_trampoline(unsigned long parent, +asmlinkage void notrace __hot ftrace_function_trampoline(unsigned long parent, unsigned long self_addr, unsigned long org_sp_gr3, struct ftrace_regs *fregs) diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index 00297e8e1c88..6f0c92e8149d 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/syscalls.h> +#include <linux/libgcc.h> #include <linux/string.h> EXPORT_SYMBOL(memset); @@ -92,12 +93,6 @@ EXPORT_SYMBOL($$divI_12); EXPORT_SYMBOL($$divI_14); EXPORT_SYMBOL($$divI_15); -extern void __ashrdi3(void); -extern void __ashldi3(void); -extern void __lshrdi3(void); -extern void __muldi3(void); -extern void __ucmpdi2(void); - EXPORT_SYMBOL(__ashrdi3); EXPORT_SYMBOL(__ashldi3); EXPORT_SYMBOL(__lshrdi3); diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index d818ece23b4a..bf9f192c826e 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -39,7 +39,7 @@ static struct proc_dir_entry * proc_gsc_root __read_mostly = NULL; static unsigned long pcxl_used_bytes __read_mostly; static unsigned long pcxl_used_pages __read_mostly; -extern unsigned long pcxl_dma_start; /* Start of pcxl dma mapping area */ +unsigned long pcxl_dma_start __ro_after_init; /* pcxl dma mapping area start */ static DEFINE_SPINLOCK(pcxl_res_lock); static char *pcxl_res_map; static int pcxl_res_hint; @@ -381,7 +381,7 @@ pcxl_dma_init(void) pcxl_res_map = (char *)__get_free_pages(GFP_KERNEL, get_order(pcxl_res_size)); memset(pcxl_res_map, 0, pcxl_res_size); - proc_gsc_root = proc_mkdir("gsc", NULL); + proc_gsc_root = proc_mkdir("bus/gsc", NULL); if (!proc_gsc_root) printk(KERN_WARNING "pcxl_dma_init: Unable to create gsc /proc dir entry\n"); @@ -417,14 +417,6 @@ void *arch_dma_alloc(struct device *dev, size_t size, map_uncached_pages(vaddr, size, paddr); *dma_handle = (dma_addr_t) paddr; -#if 0 -/* This probably isn't needed to support EISA cards. -** ISA cards will certainly only support 24-bit DMA addressing. -** Not clear if we can, want, or need to support ISA. -*/ - if (!dev || *dev->coherent_dma_mask < 0xffffffff) - gfp |= GFP_DMA; -#endif return (void *)vaddr; } diff --git a/arch/parisc/kernel/pdt.c b/arch/parisc/kernel/pdt.c index 0d24735bd918..0f9b3b5914cf 100644 --- a/arch/parisc/kernel/pdt.c +++ b/arch/parisc/kernel/pdt.c @@ -354,10 +354,8 @@ static int __init pdt_initcall(void) return -ENODEV; kpdtd_task = kthread_run(pdt_mainloop, NULL, "kpdtd"); - if (IS_ERR(kpdtd_task)) - return PTR_ERR(kpdtd_task); - return 0; + return PTR_ERR_OR_ZERO(kpdtd_task); } late_initcall(pdt_initcall); diff --git a/arch/parisc/kernel/perf.c b/arch/parisc/kernel/perf.c index 90b04d8af212..b0f0816879df 100644 --- a/arch/parisc/kernel/perf.c +++ b/arch/parisc/kernel/perf.c @@ -57,7 +57,7 @@ struct rdr_tbl_ent { static int perf_processor_interface __read_mostly = UNKNOWN_INTF; static int perf_enabled __read_mostly; static DEFINE_SPINLOCK(perf_lock); -struct parisc_device *cpu_device __read_mostly; +static struct parisc_device *cpu_device __read_mostly; /* RDRs to write for PCX-W */ static const int perf_rdrs_W[] = diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index 00b0df97afb1..762289b9984e 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -26,6 +26,7 @@ #include <asm/processor.h> #include <asm/page.h> #include <asm/pdc.h> +#include <asm/smp.h> #include <asm/pdcpat.h> #include <asm/irq.h> /* for struct irq_region */ #include <asm/parisc-device.h> diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index 573f8303e2b0..211a4afdd282 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -40,11 +40,6 @@ static char __initdata command_line[COMMAND_LINE_SIZE]; -/* Intended for ccio/sba/cpu statistics under /proc/bus/{runway|gsc} */ -struct proc_dir_entry * proc_runway_root __read_mostly = NULL; -struct proc_dir_entry * proc_gsc_root __read_mostly = NULL; -struct proc_dir_entry * proc_mckinley_root __read_mostly = NULL; - static void __init setup_cmdline(char **cmdline_p) { extern unsigned int boot_args[]; @@ -196,48 +191,6 @@ const struct seq_operations cpuinfo_op = { .show = show_cpuinfo }; -static void __init parisc_proc_mkdir(void) -{ - /* - ** Can't call proc_mkdir() until after proc_root_init() has been - ** called by start_kernel(). In other words, this code can't - ** live in arch/.../setup.c because start_parisc() calls - ** start_kernel(). - */ - switch (boot_cpu_data.cpu_type) { - case pcxl: - case pcxl2: - if (NULL == proc_gsc_root) - { - proc_gsc_root = proc_mkdir("bus/gsc", NULL); - } - break; - case pcxt_: - case pcxu: - case pcxu_: - case pcxw: - case pcxw_: - case pcxw2: - if (NULL == proc_runway_root) - { - proc_runway_root = proc_mkdir("bus/runway", NULL); - } - break; - case mako: - case mako2: - if (NULL == proc_mckinley_root) - { - proc_mckinley_root = proc_mkdir("bus/mckinley", NULL); - } - break; - default: - /* FIXME: this was added to prevent the compiler - * complaining about missing pcx, pcxs and pcxt - * I'm assuming they have neither gsc nor runway */ - break; - } -} - static struct resource central_bus = { .name = "Central Bus", .start = F_EXTEND(0xfff80000), @@ -294,7 +247,6 @@ static int __init parisc_init(void) { u32 osid = (OS_ID_LINUX << 16); - parisc_proc_mkdir(); parisc_init_resources(); do_device_inventory(); /* probe for hardware */ diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index f886ff0c75df..e8d27def6c52 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -423,7 +423,7 @@ static void check_syscallno_in_delay_branch(struct pt_regs *regs) regs->gr[31] -= 8; /* delayed branching */ /* Get assembler opcode of code in delay branch */ - uaddr = (unsigned int *) ((regs->gr[31] & ~3) + 4); + uaddr = (u32 __user *) ((regs->gr[31] & ~3) + 4); err = get_user(opcode, uaddr); if (err) return; diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index ca2d537e25b1..9915062d5243 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -27,17 +27,12 @@ #include <linux/elf-randomize.h> /* - * Construct an artificial page offset for the mapping based on the virtual + * Construct an artificial page offset for the mapping based on the physical * address of the kernel file mapping variable. - * If filp is zero the calculated pgoff value aliases the memory of the given - * address. This is useful for io_uring where the mapping shall alias a kernel - * address and a userspace adress where both the kernel and the userspace - * access the same memory region. */ -#define GET_FILP_PGOFF(filp, addr) \ - ((filp ? (((unsigned long) filp->f_mapping) >> 8) \ - & ((SHM_COLOUR-1) >> PAGE_SHIFT) : 0UL) \ - + (addr >> PAGE_SHIFT)) +#define GET_FILP_PGOFF(filp) \ + (filp ? (((unsigned long) filp->f_mapping) >> 8) \ + & ((SHM_COLOUR-1) >> PAGE_SHIFT) : 0UL) static unsigned long shared_align_offset(unsigned long filp_pgoff, unsigned long pgoff) @@ -117,7 +112,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, do_color_align = 0; if (filp || (flags & MAP_SHARED)) do_color_align = 1; - filp_pgoff = GET_FILP_PGOFF(filp, addr); + filp_pgoff = GET_FILP_PGOFF(filp); if (flags & MAP_FIXED) { /* Even MAP_FIXED mappings must reside within TASK_SIZE */ diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 1373e5129868..1f51aa9c8230 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -39,6 +39,7 @@ registers). #include <asm/assembly.h> #include <asm/processor.h> #include <asm/cache.h> +#include <asm/spinlock_types.h> #include <linux/linkage.h> @@ -66,6 +67,16 @@ registers). stw \reg1, 0(%sr2,\reg2) .endm + /* raise exception if spinlock content is not zero or + * __ARCH_SPIN_LOCK_UNLOCKED_VAL */ + .macro spinlock_check spin_val,tmpreg +#ifdef CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK + ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, \tmpreg + andcm,= \spin_val, \tmpreg, %r0 + .word SPINLOCK_BREAK_INSN +#endif + .endm + .text .import syscall_exit,code @@ -508,7 +519,8 @@ lws_start: lws_exit_noerror: lws_pagefault_enable %r1,%r21 - stw,ma %r20, 0(%sr2,%r20) + ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, %r21 + stw,ma %r21, 0(%sr2,%r20) ssm PSW_SM_I, %r0 b lws_exit copy %r0, %r21 @@ -521,7 +533,8 @@ lws_wouldblock: lws_pagefault: lws_pagefault_enable %r1,%r21 - stw,ma %r20, 0(%sr2,%r20) + ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, %r21 + stw,ma %r21, 0(%sr2,%r20) ssm PSW_SM_I, %r0 ldo 3(%r0),%r28 b lws_exit @@ -619,6 +632,7 @@ lws_compare_and_swap: /* Try to acquire the lock */ LDCW 0(%sr2,%r20), %r28 + spinlock_check %r28, %r21 comclr,<> %r0, %r28, %r0 b,n lws_wouldblock @@ -772,6 +786,7 @@ cas2_lock_start: /* Try to acquire the lock */ LDCW 0(%sr2,%r20), %r28 + spinlock_check %r28, %r21 comclr,<> %r0, %r28, %r0 b,n lws_wouldblock @@ -1001,6 +1016,7 @@ atomic_xchg_start: /* Try to acquire the lock */ LDCW 0(%sr2,%r20), %r28 + spinlock_check %r28, %r21 comclr,<> %r0, %r28, %r0 b,n lws_wouldblock @@ -1199,6 +1215,7 @@ atomic_store_start: /* Try to acquire the lock */ LDCW 0(%sr2,%r20), %r28 + spinlock_check %r28, %r21 comclr,<> %r0, %r28, %r0 b,n lws_wouldblock @@ -1330,7 +1347,7 @@ ENTRY(lws_lock_start) /* lws locks */ .rept 256 /* Keep locks aligned at 16-bytes */ - .word 1 + .word __ARCH_SPIN_LOCK_UNLOCKED_VAL .word 0 .word 0 .word 0 diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index 033b9e50b44a..170d0dda4213 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -11,6 +11,7 @@ #include <linux/signal.h> #include <linux/ratelimit.h> #include <linux/uaccess.h> +#include <linux/sysctl.h> #include <asm/unaligned.h> #include <asm/hardirq.h> #include <asm/traps.h> @@ -337,7 +338,7 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop) : "r19", "r20", "r21", "r22", "r1" ); #else { - unsigned long valh=(val>>32),vall=(val&0xffffffffl); + unsigned long valh = (val >> 32), vall = (val & 0xffffffffl); __asm__ __volatile__ ( " mtsp %4, %%sr1\n" " zdep %2, 29, 2, %%r19\n" @@ -473,7 +474,7 @@ void handle_unaligned(struct pt_regs *regs) case OPCODE_LDWA_I: case OPCODE_LDW_S: case OPCODE_LDWA_S: - ret = emulate_ldw(regs, R3(regs->iir),0); + ret = emulate_ldw(regs, R3(regs->iir), 0); break; case OPCODE_STH: @@ -482,7 +483,7 @@ void handle_unaligned(struct pt_regs *regs) case OPCODE_STW: case OPCODE_STWA: - ret = emulate_stw(regs, R2(regs->iir),0); + ret = emulate_stw(regs, R2(regs->iir), 0); break; #ifdef CONFIG_64BIT @@ -490,12 +491,12 @@ void handle_unaligned(struct pt_regs *regs) case OPCODE_LDDA_I: case OPCODE_LDD_S: case OPCODE_LDDA_S: - ret = emulate_ldd(regs, R3(regs->iir),0); + ret = emulate_ldd(regs, R3(regs->iir), 0); break; case OPCODE_STD: case OPCODE_STDA: - ret = emulate_std(regs, R2(regs->iir),0); + ret = emulate_std(regs, R2(regs->iir), 0); break; #endif @@ -503,24 +504,24 @@ void handle_unaligned(struct pt_regs *regs) case OPCODE_FLDWS: case OPCODE_FLDWXR: case OPCODE_FLDWSR: - ret = emulate_ldw(regs,FR3(regs->iir),1); + ret = emulate_ldw(regs, FR3(regs->iir), 1); break; case OPCODE_FLDDX: case OPCODE_FLDDS: - ret = emulate_ldd(regs,R3(regs->iir),1); + ret = emulate_ldd(regs, R3(regs->iir), 1); break; case OPCODE_FSTWX: case OPCODE_FSTWS: case OPCODE_FSTWXR: case OPCODE_FSTWSR: - ret = emulate_stw(regs,FR3(regs->iir),1); + ret = emulate_stw(regs, FR3(regs->iir), 1); break; case OPCODE_FSTDX: case OPCODE_FSTDS: - ret = emulate_std(regs,R3(regs->iir),1); + ret = emulate_std(regs, R3(regs->iir), 1); break; case OPCODE_LDCD_I: diff --git a/arch/parisc/lib/ucmpdi2.c b/arch/parisc/lib/ucmpdi2.c index 8e6014a142ef..9d8b4dbae273 100644 --- a/arch/parisc/lib/ucmpdi2.c +++ b/arch/parisc/lib/ucmpdi2.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/module.h> +#include <linux/libgcc.h> union ull_union { unsigned long long ull; @@ -9,7 +10,7 @@ union ull_union { } ui; }; -int __ucmpdi2(unsigned long long a, unsigned long long b) +word_type __ucmpdi2(unsigned long long a, unsigned long long b) { union ull_union au = {.ull = a}; union ull_union bu = {.ull = b}; diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index a4c7c7630f48..2fe5b44986e0 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -192,31 +192,31 @@ int fixup_exception(struct pt_regs *regs) * For implementation see handle_interruption() in traps.c */ static const char * const trap_description[] = { - [1] "High-priority machine check (HPMC)", - [2] "Power failure interrupt", - [3] "Recovery counter trap", - [5] "Low-priority machine check", - [6] "Instruction TLB miss fault", - [7] "Instruction access rights / protection trap", - [8] "Illegal instruction trap", - [9] "Break instruction trap", - [10] "Privileged operation trap", - [11] "Privileged register trap", - [12] "Overflow trap", - [13] "Conditional trap", - [14] "FP Assist Exception trap", - [15] "Data TLB miss fault", - [16] "Non-access ITLB miss fault", - [17] "Non-access DTLB miss fault", - [18] "Data memory protection/unaligned access trap", - [19] "Data memory break trap", - [20] "TLB dirty bit trap", - [21] "Page reference trap", - [22] "Assist emulation trap", - [25] "Taken branch trap", - [26] "Data memory access rights trap", - [27] "Data memory protection ID trap", - [28] "Unaligned data reference trap", + [1] = "High-priority machine check (HPMC)", + [2] = "Power failure interrupt", + [3] = "Recovery counter trap", + [5] = "Low-priority machine check", + [6] = "Instruction TLB miss fault", + [7] = "Instruction access rights / protection trap", + [8] = "Illegal instruction trap", + [9] = "Break instruction trap", + [10] = "Privileged operation trap", + [11] = "Privileged register trap", + [12] = "Overflow trap", + [13] = "Conditional trap", + [14] = "FP Assist Exception trap", + [15] = "Data TLB miss fault", + [16] = "Non-access ITLB miss fault", + [17] = "Non-access DTLB miss fault", + [18] = "Data memory protection/unaligned access trap", + [19] = "Data memory break trap", + [20] = "TLB dirty bit trap", + [21] = "Page reference trap", + [22] = "Assist emulation trap", + [25] = "Taken branch trap", + [26] = "Data memory access rights trap", + [27] = "Data memory protection ID trap", + [28] = "Unaligned data reference trap", }; const char *trap_name(unsigned long code) diff --git a/arch/parisc/mm/fixmap.c b/arch/parisc/mm/fixmap.c index cc15d737fda6..ae3493dae9dc 100644 --- a/arch/parisc/mm/fixmap.c +++ b/arch/parisc/mm/fixmap.c @@ -19,9 +19,6 @@ void notrace set_fixmap(enum fixed_addresses idx, phys_addr_t phys) pmd_t *pmd = pmd_offset(pud, vaddr); pte_t *pte; - if (pmd_none(*pmd)) - pte = pte_alloc_kernel(pmd, vaddr); - pte = pte_offset_kernel(pmd, vaddr); set_pte_at(&init_mm, vaddr, pte, __mk_pte(phys, PAGE_KERNEL_RWX)); flush_tlb_kernel_range(vaddr, vaddr + PAGE_SIZE); diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 406c52fe23d5..a088c243edea 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -523,10 +523,6 @@ void mark_rodata_ro(void) void *parisc_vmalloc_start __ro_after_init; EXPORT_SYMBOL(parisc_vmalloc_start); -#ifdef CONFIG_PA11 -unsigned long pcxl_dma_start __ro_after_init; -#endif - void __init mem_init(void) { /* Do sanity checks on IPC (compat) structures */ @@ -669,6 +665,39 @@ static void __init gateway_init(void) PAGE_SIZE, PAGE_GATEWAY, 1); } +static void __init fixmap_init(void) +{ + unsigned long addr = FIXMAP_START; + unsigned long end = FIXMAP_START + FIXMAP_SIZE; + pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d = p4d_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); + pmd_t *pmd; + + BUILD_BUG_ON(FIXMAP_SIZE > PMD_SIZE); + +#if CONFIG_PGTABLE_LEVELS == 3 + if (pud_none(*pud)) { + pmd = memblock_alloc(PAGE_SIZE << PMD_TABLE_ORDER, + PAGE_SIZE << PMD_TABLE_ORDER); + if (!pmd) + panic("fixmap: pmd allocation failed.\n"); + pud_populate(NULL, pud, pmd); + } +#endif + + pmd = pmd_offset(pud, addr); + do { + pte_t *pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + if (!pte) + panic("fixmap: pte allocation failed.\n"); + + pmd_populate_kernel(&init_mm, pmd, pte); + + addr += PAGE_SIZE; + } while (addr < end); +} + static void __init parisc_bootmem_free(void) { unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0, }; @@ -683,6 +712,7 @@ void __init paging_init(void) setup_bootmem(); pagetable_init(); gateway_init(); + fixmap_init(); flush_cache_all_local(); /* start with known state */ flush_tlb_all_local(NULL); diff --git a/arch/parisc/mm/ioremap.c b/arch/parisc/mm/ioremap.c index 345ff0b66499..d7ee1f43d997 100644 --- a/arch/parisc/mm/ioremap.c +++ b/arch/parisc/mm/ioremap.c @@ -27,7 +27,7 @@ */ void __iomem *ioremap(unsigned long phys_addr, unsigned long size) { - void __iomem *addr; + uintptr_t addr; struct vm_struct *area; unsigned long offset, last_addr; pgprot_t pgprot; @@ -79,10 +79,9 @@ void __iomem *ioremap(unsigned long phys_addr, unsigned long size) if (!area) return NULL; - addr = (void __iomem *) area->addr; - if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size, - phys_addr, pgprot)) { - vunmap(addr); + addr = (uintptr_t) area->addr; + if (ioremap_page_range(addr, addr + size, phys_addr, pgprot)) { + vunmap(area->addr); return NULL; } diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 8a6754ffdc7e..a6c7069bec5d 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -393,7 +393,6 @@ int validate_sp_size(unsigned long sp, struct task_struct *p, */ #define ARCH_HAS_PREFETCH #define ARCH_HAS_PREFETCHW -#define ARCH_HAS_SPINLOCK_PREFETCH static inline void prefetch(const void *x) { @@ -411,8 +410,6 @@ static inline void prefetchw(const void *x) __asm__ __volatile__ ("dcbtst 0,%0" : : "r" (x)); } -#define spin_lock_prefetch(x) prefetchw(x) - /* asm stubs */ extern unsigned long isa300_idle_stop_noloss(unsigned long psscr_val); extern unsigned long isa300_idle_stop_mayloss(unsigned long psscr_val); diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h index 46c31fb8748d..30a12d208687 100644 --- a/arch/powerpc/include/asm/word-at-a-time.h +++ b/arch/powerpc/include/asm/word-at-a-time.h @@ -34,7 +34,7 @@ static inline long find_zero(unsigned long mask) return leading_zero_bits >> 3; } -static inline bool has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) +static inline unsigned long has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) { unsigned long rhs = val | c->low_bits; *data = rhs; diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index f132d8704263..6440b1bb332a 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -375,8 +375,7 @@ _GLOBAL(generic_secondary_smp_init) beq 20f /* start the specified thread */ - LOAD_REG_ADDR(r5, fsl_secondary_thread_init) - ld r4, 0(r5) + LOAD_REG_ADDR(r5, DOTSYM(fsl_secondary_thread_init)) bl book3e_start_thread /* stop the current thread */ diff --git a/arch/powerpc/kernel/trace/ftrace_mprofile.S b/arch/powerpc/kernel/trace/ftrace_mprofile.S index ffb1db386849..1f7d86de1538 100644 --- a/arch/powerpc/kernel/trace/ftrace_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_mprofile.S @@ -33,6 +33,9 @@ * and then arrange for the ftrace function to be called. */ .macro ftrace_regs_entry allregs + /* Create a minimal stack frame for representing B */ + PPC_STLU r1, -STACK_FRAME_MIN_SIZE(r1) + /* Create our stack frame + pt_regs */ PPC_STLU r1,-SWITCH_FRAME_SIZE(r1) @@ -42,7 +45,7 @@ #ifdef CONFIG_PPC64 /* Save the original return address in A's stack frame */ - std r0, LRSAVE+SWITCH_FRAME_SIZE(r1) + std r0, LRSAVE+SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE(r1) /* Ok to continue? */ lbz r3, PACA_FTRACE_ENABLED(r13) cmpdi r3, 0 @@ -77,6 +80,8 @@ mflr r7 /* Save it as pt_regs->nip */ PPC_STL r7, _NIP(r1) + /* Also save it in B's stackframe header for proper unwind */ + PPC_STL r7, LRSAVE+SWITCH_FRAME_SIZE(r1) /* Save the read LR in pt_regs->link */ PPC_STL r0, _LINK(r1) @@ -142,7 +147,7 @@ #endif /* Pop our stack frame */ - addi r1, r1, SWITCH_FRAME_SIZE + addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE #ifdef CONFIG_LIVEPATCH_64 /* Based on the cmpd above, if the NIP was altered handle livepatch */ diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index fe1b83020e0d..0ec5b45b1e86 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -314,8 +314,7 @@ void __ref vmemmap_free(unsigned long start, unsigned long end, start = ALIGN_DOWN(start, page_size); if (altmap) { alt_start = altmap->base_pfn; - alt_end = altmap->base_pfn + altmap->reserve + - altmap->free + altmap->alloc + altmap->align; + alt_end = altmap->base_pfn + altmap->reserve + altmap->free; } pr_debug("vmemmap_free %lx...%lx\n", start, end); diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index 9c43cf32f4c9..40aa58206888 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -180,7 +180,7 @@ static void wake_hw_thread(void *info) unsigned long inia; int cpu = *(const int *)info; - inia = *(unsigned long *)fsl_secondary_thread_init; + inia = ppc_function_entry(fsl_secondary_thread_init); book3e_start_thread(cpu_thread_in_core(cpu), inia); } #endif diff --git a/arch/powerpc/platforms/powermac/time.c b/arch/powerpc/platforms/powermac/time.c index 4c5790aff1b5..8633891b7aa5 100644 --- a/arch/powerpc/platforms/powermac/time.c +++ b/arch/powerpc/platforms/powermac/time.c @@ -26,8 +26,8 @@ #include <linux/rtc.h> #include <linux/of_address.h> +#include <asm/early_ioremap.h> #include <asm/sections.h> -#include <asm/io.h> #include <asm/machdep.h> #include <asm/time.h> #include <asm/nvram.h> @@ -182,7 +182,7 @@ static int __init via_calibrate_decr(void) return 0; } of_node_put(vias); - via = ioremap(rsrc.start, resource_size(&rsrc)); + via = early_ioremap(rsrc.start, resource_size(&rsrc)); if (via == NULL) { printk(KERN_ERR "Failed to map VIA for timer calibration !\n"); return 0; @@ -207,7 +207,7 @@ static int __init via_calibrate_decr(void) ppc_tb_freq = (dstart - dend) * 100 / 6; - iounmap(via); + early_iounmap((void *)via, resource_size(&rsrc)); return 1; } diff --git a/arch/riscv/include/asm/acpi.h b/arch/riscv/include/asm/acpi.h index f71ce21ff684..d5604d2073bc 100644 --- a/arch/riscv/include/asm/acpi.h +++ b/arch/riscv/include/asm/acpi.h @@ -19,7 +19,7 @@ typedef u64 phys_cpuid_t; #define PHYS_CPUID_INVALID INVALID_HARTID /* ACPI table mapping after acpi_permanent_mmap is set */ -void *acpi_os_ioremap(acpi_physical_address phys, acpi_size size); +void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size); #define acpi_os_ioremap acpi_os_ioremap #define acpi_strict 1 /* No out-of-spec workarounds on RISC-V */ diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index 8091b8bf4883..b93ffddf8a61 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -37,6 +37,10 @@ static inline void flush_dcache_page(struct page *page) #define flush_icache_user_page(vma, pg, addr, len) \ flush_icache_mm(vma->vm_mm, 0) +#ifdef CONFIG_64BIT +#define flush_cache_vmap(start, end) flush_tlb_kernel_range(start, end) +#endif + #ifndef CONFIG_SMP #define flush_icache_all() local_flush_icache_all() diff --git a/arch/riscv/include/asm/mmio.h b/arch/riscv/include/asm/mmio.h index aff6c33ab0c0..4c58ee7f95ec 100644 --- a/arch/riscv/include/asm/mmio.h +++ b/arch/riscv/include/asm/mmio.h @@ -101,9 +101,9 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) * Relaxed I/O memory access primitives. These follow the Device memory * ordering rules but do not guarantee any ordering relative to Normal memory * accesses. These are defined to order the indicated access (either a read or - * write) with all other I/O memory accesses. Since the platform specification - * defines that all I/O regions are strongly ordered on channel 2, no explicit - * fences are required to enforce this ordering. + * write) with all other I/O memory accesses to the same peripheral. Since the + * platform specification defines that all I/O regions are strongly ordered on + * channel 0, no explicit fences are required to enforce this ordering. */ /* FIXME: These are now the same as asm-generic */ #define __io_rbr() do {} while (0) @@ -125,14 +125,14 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) #endif /* - * I/O memory access primitives. Reads are ordered relative to any - * following Normal memory access. Writes are ordered relative to any prior - * Normal memory access. The memory barriers here are necessary as RISC-V + * I/O memory access primitives. Reads are ordered relative to any following + * Normal memory read and delay() loop. Writes are ordered relative to any + * prior Normal memory write. The memory barriers here are necessary as RISC-V * doesn't define any ordering between the memory space and the I/O space. */ #define __io_br() do {} while (0) -#define __io_ar(v) __asm__ __volatile__ ("fence i,r" : : : "memory") -#define __io_bw() __asm__ __volatile__ ("fence w,o" : : : "memory") +#define __io_ar(v) ({ __asm__ __volatile__ ("fence i,ir" : : : "memory"); }) +#define __io_bw() ({ __asm__ __volatile__ ("fence w,o" : : : "memory"); }) #define __io_aw() mmiowb_set_pending() #define readb(c) ({ u8 __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; }) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 75970ee2bda2..b5680c940c1e 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -188,6 +188,8 @@ extern struct pt_alloc_ops pt_ops __initdata; #define PAGE_KERNEL_IO __pgprot(_PAGE_IOREMAP) extern pgd_t swapper_pg_dir[]; +extern pgd_t trampoline_pg_dir[]; +extern pgd_t early_pg_dir[]; #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_present(pmd_t pmd) diff --git a/arch/riscv/include/asm/vmalloc.h b/arch/riscv/include/asm/vmalloc.h index 58d3e447f191..924d01b56c9a 100644 --- a/arch/riscv/include/asm/vmalloc.h +++ b/arch/riscv/include/asm/vmalloc.h @@ -3,12 +3,14 @@ #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +extern bool pgtable_l4_enabled, pgtable_l5_enabled; + #define IOREMAP_MAX_ORDER (PUD_SHIFT) #define arch_vmap_pud_supported arch_vmap_pud_supported static inline bool arch_vmap_pud_supported(pgprot_t prot) { - return true; + return pgtable_l4_enabled || pgtable_l5_enabled; } #define arch_vmap_pmd_supported arch_vmap_pmd_supported diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c index 5ee03ebab80e..56cb2c986c48 100644 --- a/arch/riscv/kernel/acpi.c +++ b/arch/riscv/kernel/acpi.c @@ -215,9 +215,9 @@ void __init __acpi_unmap_table(void __iomem *map, unsigned long size) early_iounmap(map, size); } -void *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) +void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) { - return memremap(phys, size, MEMREMAP_WB); + return (void __iomem *)memremap(phys, size, MEMREMAP_WB); } #ifdef CONFIG_PCI diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index a2fc952318e9..35b854cf078e 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -17,6 +17,11 @@ #include <asm/smp.h> #include <asm/pgtable.h> +bool arch_match_cpu_phys_id(int cpu, u64 phys_id) +{ + return phys_id == cpuid_to_hartid_map(cpu); +} + /* * Returns the hart ID of the given device tree node, or -ENODEV if the node * isn't an enabled and valid RISC-V hart node. diff --git a/arch/riscv/kernel/crash_core.c b/arch/riscv/kernel/crash_core.c index b351a3c01355..55f1d7856b54 100644 --- a/arch/riscv/kernel/crash_core.c +++ b/arch/riscv/kernel/crash_core.c @@ -18,4 +18,6 @@ void arch_crash_save_vmcoreinfo(void) vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END); #endif vmcoreinfo_append_str("NUMBER(KERNEL_LINK_ADDR)=0x%lx\n", KERNEL_LINK_ADDR); + vmcoreinfo_append_str("NUMBER(va_kernel_pa_offset)=0x%lx\n", + kernel_map.va_kernel_pa_offset); } diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c index 5372b708fae2..c08bb5c3b385 100644 --- a/arch/riscv/kernel/elf_kexec.c +++ b/arch/riscv/kernel/elf_kexec.c @@ -281,7 +281,7 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf, kbuf.buffer = initrd; kbuf.bufsz = kbuf.memsz = initrd_len; kbuf.buf_align = PAGE_SIZE; - kbuf.top_down = false; + kbuf.top_down = true; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) @@ -425,6 +425,7 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, * sym, instead of searching the whole relsec. */ case R_RISCV_PCREL_HI20: + case R_RISCV_CALL_PLT: case R_RISCV_CALL: *(u64 *)loc = CLEAN_IMM(UITYPE, *(u64 *)loc) | ENCODE_UJTYPE_IMM(val - addr); diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index 85bbce0f758c..40420afbb1a0 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -61,11 +61,6 @@ int riscv_hartid_to_cpuid(unsigned long hartid) return -ENOENT; } -bool arch_match_cpu_phys_id(int cpu, u64 phys_id) -{ - return phys_id == cpuid_to_hartid_map(cpu); -} - static void ipi_stop(void) { set_cpu_online(smp_processor_id(), false); diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 9ce504737d18..e4c35ac2357f 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -26,12 +26,13 @@ #include <linux/kfence.h> #include <asm/fixmap.h> -#include <asm/tlbflush.h> -#include <asm/sections.h> -#include <asm/soc.h> #include <asm/io.h> -#include <asm/ptdump.h> #include <asm/numa.h> +#include <asm/pgtable.h> +#include <asm/ptdump.h> +#include <asm/sections.h> +#include <asm/soc.h> +#include <asm/tlbflush.h> #include "../kernel/head.h" @@ -214,8 +215,13 @@ static void __init setup_bootmem(void) memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); phys_ram_end = memblock_end_of_DRAM(); + + /* + * Make sure we align the start of the memory on a PMD boundary so that + * at worst, we map the linear mapping with PMD mappings. + */ if (!IS_ENABLED(CONFIG_XIP_KERNEL)) - phys_ram_base = memblock_start_of_DRAM(); + phys_ram_base = memblock_start_of_DRAM() & PMD_MASK; /* * In 64-bit, any use of __va/__pa before this point is wrong as we diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 8fc0efcf905c..a01bc15dce24 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -22,7 +22,6 @@ * region is not and then we have to go down to the PUD level. */ -extern pgd_t early_pg_dir[PTRS_PER_PGD]; pgd_t tmp_pg_dir[PTRS_PER_PGD] __page_aligned_bss; p4d_t tmp_p4d[PTRS_PER_P4D] __page_aligned_bss; pud_t tmp_pud[PTRS_PER_PUD] __page_aligned_bss; diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index d03d4cb9332c..3a6a9a88bd38 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -116,7 +116,6 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m -CONFIG_NET_TC_SKB_EXT=y CONFIG_SMC=m CONFIG_SMC_DIAG=m CONFIG_INET=y @@ -193,6 +192,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NETFILTER_XTABLES_COMPAT=y CONFIG_NETFILTER_XT_SET=m CONFIG_NETFILTER_XT_TARGET_AUDIT=m CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m @@ -379,6 +379,7 @@ CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m CONFIG_NET_ACT_GATE=m +CONFIG_NET_TC_SKB_EXT=y CONFIG_DNS_RESOLVER=y CONFIG_OPENVSWITCH=m CONFIG_VSOCKETS=m @@ -395,6 +396,7 @@ CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_SAFE=y +# CONFIG_FW_LOADER is not set CONFIG_CONNECTOR=y CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m @@ -502,7 +504,6 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_GOOGLE is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set -# CONFIG_NET_VENDOR_WANGXUN is not set # CONFIG_NET_VENDOR_LITEX is not set # CONFIG_NET_VENDOR_MARVELL is not set CONFIG_MLX4_EN=m @@ -542,6 +543,7 @@ CONFIG_MLX5_CORE_EN=y # CONFIG_NET_VENDOR_TI is not set # CONFIG_NET_VENDOR_VERTEXCOM is not set # CONFIG_NET_VENDOR_VIA is not set +# CONFIG_NET_VENDOR_WANGXUN is not set # CONFIG_NET_VENDOR_WIZNET is not set # CONFIG_NET_VENDOR_XILINX is not set CONFIG_PPP=m @@ -646,7 +648,6 @@ CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_TMPFS_INODE64=y CONFIG_HUGETLBFS=y -CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m @@ -690,7 +691,6 @@ CONFIG_HARDENED_USERCOPY=y CONFIG_FORTIFY_SOURCE=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y -CONFIG_SECURITY_SELINUX_DISABLE=y CONFIG_SECURITY_LOCKDOWN_LSM=y CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_SECURITY_LANDLOCK=y @@ -744,7 +744,6 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_SM3_GENERIC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m @@ -844,6 +843,7 @@ CONFIG_PREEMPT_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_USER_EVENTS=y CONFIG_HIST_TRIGGERS=y CONFIG_FTRACE_STARTUP_TEST=y # CONFIG_EVENT_TRACE_STARTUP_TEST is not set @@ -866,6 +866,7 @@ CONFIG_FAIL_MAKE_REQUEST=y CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y +CONFIG_FAULT_INJECTION_CONFIGFS=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LKDTM=m CONFIG_TEST_MIN_HEAP=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 1855759cdc6a..b13a5a0d99d2 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -107,7 +107,6 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m -CONFIG_NET_TC_SKB_EXT=y CONFIG_SMC=m CONFIG_SMC_DIAG=m CONFIG_INET=y @@ -184,6 +183,7 @@ CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m +CONFIG_NETFILTER_XTABLES_COMPAT=y CONFIG_NETFILTER_XT_SET=m CONFIG_NETFILTER_XT_TARGET_AUDIT=m CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m @@ -369,6 +369,7 @@ CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m CONFIG_NET_ACT_GATE=m +CONFIG_NET_TC_SKB_EXT=y CONFIG_DNS_RESOLVER=y CONFIG_OPENVSWITCH=m CONFIG_VSOCKETS=m @@ -385,6 +386,7 @@ CONFIG_HOTPLUG_PCI_S390=y CONFIG_UEVENT_HELPER=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_SAFE=y +# CONFIG_FW_LOADER is not set CONFIG_CONNECTOR=y CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m @@ -492,7 +494,6 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_GOOGLE is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set -# CONFIG_NET_VENDOR_WANGXUN is not set # CONFIG_NET_VENDOR_LITEX is not set # CONFIG_NET_VENDOR_MARVELL is not set CONFIG_MLX4_EN=m @@ -532,6 +533,7 @@ CONFIG_MLX5_CORE_EN=y # CONFIG_NET_VENDOR_TI is not set # CONFIG_NET_VENDOR_VERTEXCOM is not set # CONFIG_NET_VENDOR_VIA is not set +# CONFIG_NET_VENDOR_WANGXUN is not set # CONFIG_NET_VENDOR_WIZNET is not set # CONFIG_NET_VENDOR_XILINX is not set CONFIG_PPP=m @@ -673,7 +675,6 @@ CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y -CONFIG_SECURITY_SELINUX_DISABLE=y CONFIG_SECURITY_LOCKDOWN_LSM=y CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_SECURITY_LANDLOCK=y @@ -729,7 +730,6 @@ CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_SM3_GENERIC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m @@ -793,6 +793,7 @@ CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_USER_EVENTS=y CONFIG_HIST_TRIGGERS=y CONFIG_SAMPLES=y CONFIG_SAMPLE_TRACE_PRINTK=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 6f68b39817ef..e62fb2015102 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -53,7 +53,6 @@ CONFIG_ZFCP=y # CONFIG_HVC_IUCV is not set # CONFIG_HW_RANDOM_S390 is not set # CONFIG_HMC_DRV is not set -# CONFIG_S390_UV_UAPI is not set # CONFIG_S390_TAPE is not set # CONFIG_VMCP is not set # CONFIG_MONWRITER is not set diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h index f0fe3bcc78a8..bb0826024bb9 100644 --- a/arch/s390/include/uapi/asm/ptrace.h +++ b/arch/s390/include/uapi/asm/ptrace.h @@ -8,6 +8,8 @@ #ifndef _UAPI_S390_PTRACE_H #define _UAPI_S390_PTRACE_H +#include <linux/const.h> + /* * Offsets in the user_regs_struct. They are used for the ptrace * system call and in entry.S diff --git a/arch/s390/kernel/sthyi.c b/arch/s390/kernel/sthyi.c index 4d141e2c132e..2ea7f208f0e7 100644 --- a/arch/s390/kernel/sthyi.c +++ b/arch/s390/kernel/sthyi.c @@ -459,9 +459,9 @@ static int sthyi_update_cache(u64 *rc) * * Fills the destination with system information returned by the STHYI * instruction. The data is generated by emulation or execution of STHYI, - * if available. The return value is the condition code that would be - * returned, the rc parameter is the return code which is passed in - * register R2 + 1. + * if available. The return value is either a negative error value or + * the condition code that would be returned, the rc parameter is the + * return code which is passed in register R2 + 1. */ int sthyi_fill(void *dst, u64 *rc) { diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 954d39adf85c..341abafb96e4 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -389,8 +389,8 @@ static int handle_partial_execution(struct kvm_vcpu *vcpu) */ int handle_sthyi(struct kvm_vcpu *vcpu) { - int reg1, reg2, r = 0; - u64 code, addr, cc = 0, rc = 0; + int reg1, reg2, cc = 0, r = 0; + u64 code, addr, rc = 0; struct sthyi_sctns *sctns = NULL; if (!test_kvm_facility(vcpu->kvm, 74)) @@ -421,7 +421,10 @@ int handle_sthyi(struct kvm_vcpu *vcpu) return -ENOMEM; cc = sthyi_fill(sctns, &rc); - + if (cc < 0) { + free_page((unsigned long)sctns); + return cc; + } out: if (!cc) { if (kvm_s390_pv_cpu_is_protected(vcpu)) { diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index b26649233d12..24a66670f5c3 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -763,6 +763,8 @@ void __init vmem_map_init(void) if (static_key_enabled(&cpu_has_bear)) set_memory_nx(0, 1); set_memory_nx(PAGE_SIZE, 1); + if (debug_pagealloc_enabled()) + set_memory_4k(0, ident_map_size >> PAGE_SHIFT); pr_info("Write protected kernel read-only data: %luk\n", (unsigned long)(__end_rodata - _stext) >> 10); diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h index 2667f35d5ea5..0a0d5c3d184c 100644 --- a/arch/sparc/include/asm/processor_64.h +++ b/arch/sparc/include/asm/processor_64.h @@ -213,7 +213,6 @@ unsigned long __get_wchan(struct task_struct *task); */ #define ARCH_HAS_PREFETCH #define ARCH_HAS_PREFETCHW -#define ARCH_HAS_SPINLOCK_PREFETCH static inline void prefetch(const void *x) { @@ -239,8 +238,6 @@ static inline void prefetchw(const void *x) : "r" (x)); } -#define spin_lock_prefetch(x) prefetchw(x) - #define HAVE_ARCH_PICK_MMAP_LAYOUT int do_mathemu(struct pt_regs *regs, struct fpustate *f, bool illegal_insn_trap); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7422db409770..e36261b4ea14 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2593,6 +2593,13 @@ config CPU_IBRS_ENTRY This mitigates both spectre_v2 and retbleed at great cost to performance. +config CPU_SRSO + bool "Mitigate speculative RAS overflow on AMD" + depends on CPU_SUP_AMD && X86_64 && RETHUNK + default y + help + Enable the SRSO mitigation needed on AMD Zen1-4 machines. + config SLS bool "Mitigate Straight-Line-Speculation" depends on CC_HAS_SLS && X86_64 @@ -2603,6 +2610,25 @@ config SLS against straight line speculation. The kernel image might be slightly larger. +config GDS_FORCE_MITIGATION + bool "Force GDS Mitigation" + depends on CPU_SUP_INTEL + default n + help + Gather Data Sampling (GDS) is a hardware vulnerability which allows + unprivileged speculative access to data which was previously stored in + vector registers. + + This option is equivalent to setting gather_data_sampling=force on the + command line. The microcode mitigation is used if present, otherwise + AVX is disabled as a mitigation. On affected systems that are missing + the microcode any userspace code that unconditionally uses AVX will + break with this option set. + + Setting this option on systems not vulnerable to GDS has no effect. + + If in doubt, say N. + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 6debb816e83d..3cdf94b41456 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -63,7 +63,14 @@ void load_stage2_idt(void) set_idt_entry(X86_TRAP_PF, boot_page_fault); #ifdef CONFIG_AMD_MEM_ENCRYPT - set_idt_entry(X86_TRAP_VC, boot_stage2_vc); + /* + * Clear the second stage #VC handler in case guest types + * needing #VC have not been detected. + */ + if (sev_status & BIT(1)) + set_idt_entry(X86_TRAP_VC, boot_stage2_vc); + else + set_idt_entry(X86_TRAP_VC, NULL); #endif load_boot_idt(&boot_idt_desc); diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 09dc8c187b3c..c3e343bd4760 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -405,12 +405,45 @@ void sev_enable(struct boot_params *bp) bp->cc_blob_address = 0; /* + * Do an initial SEV capability check before snp_init() which + * loads the CPUID page and the same checks afterwards are done + * without the hypervisor and are trustworthy. + * + * If the HV fakes SEV support, the guest will crash'n'burn + * which is good enough. + */ + + /* Check for the SME/SEV support leaf */ + eax = 0x80000000; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (eax < 0x8000001f) + return; + + /* + * Check for the SME/SEV feature: + * CPUID Fn8000_001F[EAX] + * - Bit 0 - Secure Memory Encryption support + * - Bit 1 - Secure Encrypted Virtualization support + * CPUID Fn8000_001F[EBX] + * - Bits 5:0 - Pagetable bit position used to indicate encryption + */ + eax = 0x8000001f; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + /* Check whether SEV is supported */ + if (!(eax & BIT(1))) + return; + + /* * Setup/preliminary detection of SNP. This will be sanity-checked * against CPUID/MSR values later. */ snp = snp_init(bp); - /* Check for the SME/SEV support leaf */ + /* Now repeat the checks with the SNP CPUID table. */ + + /* Recheck the SME/SEV support leaf */ eax = 0x80000000; ecx = 0; native_cpuid(&eax, &ebx, &ecx, &edx); @@ -418,7 +451,7 @@ void sev_enable(struct boot_params *bp) return; /* - * Check for the SME/SEV feature: + * Recheck for the SME/SEV feature: * CPUID Fn8000_001F[EAX] * - Bit 0 - Secure Memory Encryption support * - Bit 1 - Secure Encrypted Virtualization support diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 11a5c68d1218..7645730dc228 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -299,8 +299,8 @@ static unsigned long vdso_addr(unsigned long start, unsigned len) /* Round the lowest possible end address up to a PMD boundary. */ end = (start + len + PMD_SIZE - 1) & PMD_MASK; - if (end >= TASK_SIZE_MAX) - end = TASK_SIZE_MAX; + if (end >= DEFAULT_MAP_WINDOW) + end = DEFAULT_MAP_WINDOW; end -= len; if (end > start) { diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 1fbda2f94184..b21335e6a210 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -107,7 +107,6 @@ static bool cpu_is_self(int cpu) static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, bool exclude_self) { - struct hv_send_ipi_ex **arg; struct hv_send_ipi_ex *ipi_arg; unsigned long flags; int nr_bank = 0; @@ -117,9 +116,8 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, return false; local_irq_save(flags); - arg = (struct hv_send_ipi_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); + ipi_arg = *this_cpu_ptr(hyperv_pcpu_input_arg); - ipi_arg = *arg; if (unlikely(!ipi_arg)) goto ipi_mask_ex_done; diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 6c04b52f139b..953e280c07c3 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -14,6 +14,7 @@ #include <asm/apic.h> #include <asm/desc.h> #include <asm/sev.h> +#include <asm/ibt.h> #include <asm/hypervisor.h> #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> @@ -472,6 +473,26 @@ void __init hyperv_init(void) } /* + * Some versions of Hyper-V that provide IBT in guest VMs have a bug + * in that there's no ENDBR64 instruction at the entry to the + * hypercall page. Because hypercalls are invoked via an indirect call + * to the hypercall page, all hypercall attempts fail when IBT is + * enabled, and Linux panics. For such buggy versions, disable IBT. + * + * Fixed versions of Hyper-V always provide ENDBR64 on the hypercall + * page, so if future Linux kernel versions enable IBT for 32-bit + * builds, additional hypercall page hackery will be required here + * to provide an ENDBR32. + */ +#ifdef CONFIG_X86_KERNEL_IBT + if (cpu_feature_enabled(X86_FEATURE_IBT) && + *(u32 *)hv_hypercall_pg != gen_endbr()) { + setup_clear_cpu_cap(X86_FEATURE_IBT); + pr_warn("Hyper-V: Disabling IBT because of Hyper-V bug\n"); + } +#endif + + /* * hyperv_init() is called before LAPIC is initialized: see * apic_intr_mode_init() -> x86_platform.apic_post_init() and * apic_bsp_setup() -> setup_local_APIC(). The direct-mode STIMER diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index 85d38b9f3586..db5d2ea39fc0 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -25,6 +25,10 @@ void __init hv_vtl_init_platform(void) x86_init.irqs.pre_vector_init = x86_init_noop; x86_init.timers.timer_init = x86_init_noop; + /* Avoid searching for BIOS MP tables */ + x86_init.mpparse.find_smp_config = x86_init_noop; + x86_init.mpparse.get_smp_config = x86_init_uint_noop; + x86_platform.get_wallclock = get_rtc_noop; x86_platform.set_wallclock = set_rtc_noop; x86_platform.get_nmi_reason = hv_get_nmi_reason; diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 14f46ad2ca64..28be6df88063 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -247,7 +247,7 @@ EXPORT_SYMBOL_GPL(hv_ghcb_msr_read); static int hv_mark_gpa_visibility(u16 count, const u64 pfn[], enum hv_mem_host_visibility visibility) { - struct hv_gpa_range_for_visibility **input_pcpu, *input; + struct hv_gpa_range_for_visibility *input; u16 pages_processed; u64 hv_status; unsigned long flags; @@ -263,9 +263,8 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[], } local_irq_save(flags); - input_pcpu = (struct hv_gpa_range_for_visibility **) - this_cpu_ptr(hyperv_pcpu_input_arg); - input = *input_pcpu; + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + if (unlikely(!input)) { local_irq_restore(flags); return -EINVAL; diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 8460bd35e10c..1cc113200ff5 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -61,7 +61,6 @@ static void hyperv_flush_tlb_multi(const struct cpumask *cpus, const struct flush_tlb_info *info) { int cpu, vcpu, gva_n, max_gvas; - struct hv_tlb_flush **flush_pcpu; struct hv_tlb_flush *flush; u64 status; unsigned long flags; @@ -74,10 +73,7 @@ static void hyperv_flush_tlb_multi(const struct cpumask *cpus, local_irq_save(flags); - flush_pcpu = (struct hv_tlb_flush **) - this_cpu_ptr(hyperv_pcpu_input_arg); - - flush = *flush_pcpu; + flush = *this_cpu_ptr(hyperv_pcpu_input_arg); if (unlikely(!flush)) { local_irq_restore(flags); @@ -178,17 +174,13 @@ static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus, const struct flush_tlb_info *info) { int nr_bank = 0, max_gvas, gva_n; - struct hv_tlb_flush_ex **flush_pcpu; struct hv_tlb_flush_ex *flush; u64 status; if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) return HV_STATUS_INVALID_PARAMETER; - flush_pcpu = (struct hv_tlb_flush_ex **) - this_cpu_ptr(hyperv_pcpu_input_arg); - - flush = *flush_pcpu; + flush = *this_cpu_ptr(hyperv_pcpu_input_arg); if (info->mm) { /* diff --git a/arch/x86/hyperv/nested.c b/arch/x86/hyperv/nested.c index 5d70968c8538..9dc259fa322e 100644 --- a/arch/x86/hyperv/nested.c +++ b/arch/x86/hyperv/nested.c @@ -19,7 +19,6 @@ int hyperv_flush_guest_mapping(u64 as) { - struct hv_guest_mapping_flush **flush_pcpu; struct hv_guest_mapping_flush *flush; u64 status; unsigned long flags; @@ -30,10 +29,7 @@ int hyperv_flush_guest_mapping(u64 as) local_irq_save(flags); - flush_pcpu = (struct hv_guest_mapping_flush **) - this_cpu_ptr(hyperv_pcpu_input_arg); - - flush = *flush_pcpu; + flush = *this_cpu_ptr(hyperv_pcpu_input_arg); if (unlikely(!flush)) { local_irq_restore(flags); @@ -90,7 +86,6 @@ EXPORT_SYMBOL_GPL(hyperv_fill_flush_guest_mapping_list); int hyperv_flush_guest_mapping_range(u64 as, hyperv_fill_flush_list_func fill_flush_list_func, void *data) { - struct hv_guest_mapping_flush_list **flush_pcpu; struct hv_guest_mapping_flush_list *flush; u64 status; unsigned long flags; @@ -102,10 +97,8 @@ int hyperv_flush_guest_mapping_range(u64 as, local_irq_save(flags); - flush_pcpu = (struct hv_guest_mapping_flush_list **) - this_cpu_ptr(hyperv_pcpu_input_arg); + flush = *this_cpu_ptr(hyperv_pcpu_input_arg); - flush = *flush_pcpu; if (unlikely(!flush)) { local_irq_restore(flags); goto fault; diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 8eb74cf386db..2888c0ee4df0 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -15,6 +15,7 @@ #include <asm/mpspec.h> #include <asm/x86_init.h> #include <asm/cpufeature.h> +#include <asm/irq_vectors.h> #ifdef CONFIG_ACPI_APEI # include <asm/pgtable_types.h> @@ -31,6 +32,7 @@ extern int acpi_skip_timer_override; extern int acpi_use_timer_override; extern int acpi_fix_pin2_polarity; extern int acpi_disable_cmcff; +extern bool acpi_int_src_ovr[NR_IRQS_LEGACY]; extern u8 acpi_sci_flags; extern u32 acpi_sci_override_gsi; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index cb8ca46213be..b69b0d7756aa 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -14,7 +14,7 @@ * Defines x86 CPU feature bits */ #define NCAPINTS 21 /* N 32-bit words worth of info */ -#define NBUGINTS 1 /* N 32-bit bug flags */ +#define NBUGINTS 2 /* N 32-bit bug flags */ /* * Note: If the comment begins with a quoted string, that string is used @@ -309,6 +309,10 @@ #define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ #define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ +#define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ +#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ +#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */ + /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ @@ -442,6 +446,10 @@ #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 */ +#define X86_FEATURE_SBPB (20*32+27) /* "" Selective Branch Prediction Barrier */ +#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ +#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ + /* * BUG word(s) */ @@ -483,5 +491,9 @@ #define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ #define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ +#define X86_BUG_GDS X86_BUG(30) /* CPU is affected by Gather Data Sampling */ +/* BUG word 2 */ +#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ +#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 0953aa32a324..97a3de7892d3 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -21,7 +21,7 @@ #define FUNCTION_PADDING #endif -#if (CONFIG_FUNCTION_ALIGNMENT > 8) && !defined(__DISABLE_EXPORTS) && !defined(BULID_VDSO) +#if (CONFIG_FUNCTION_ALIGNMENT > 8) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) # define __FUNC_ALIGN __ALIGN; FUNCTION_PADDING #else # define __FUNC_ALIGN __ALIGN diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 88d9ef98e087..fa83d88e4c99 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -5,7 +5,7 @@ #include <linux/types.h> #include <linux/nmi.h> #include <linux/msi.h> -#include <asm/io.h> +#include <linux/io.h> #include <asm/hyperv-tlfs.h> #include <asm/nospec-branch.h> #include <asm/paravirt.h> diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index a00a53e15ab7..1d111350197f 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -57,6 +57,7 @@ #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ +#define PRED_CMD_SBPB BIT(7) /* Selective Branch Prediction Barrier */ #define MSR_PPIN_CTL 0x0000004e #define MSR_PPIN 0x0000004f @@ -155,6 +156,15 @@ * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. */ +#define ARCH_CAP_GDS_CTRL BIT(25) /* + * CPU is vulnerable to Gather + * Data Sampling (GDS) and + * has controls for mitigation. + */ +#define ARCH_CAP_GDS_NO BIT(26) /* + * CPU is not vulnerable to Gather + * Data Sampling (GDS). + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR @@ -178,6 +188,8 @@ #define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ #define RTM_ALLOW BIT(1) /* TSX development mode */ #define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */ +#define GDS_MITG_DIS BIT(4) /* Disable GDS mitigation */ +#define GDS_MITG_LOCKED BIT(5) /* GDS mitigation locked */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 1a65cf4acb2b..3faf044569a5 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -211,7 +211,8 @@ * eventually turn into it's own annotation. */ .macro VALIDATE_UNRET_END -#if defined(CONFIG_NOINSTR_VALIDATION) && defined(CONFIG_CPU_UNRET_ENTRY) +#if defined(CONFIG_NOINSTR_VALIDATION) && \ + (defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)) ANNOTATE_RETPOLINE_SAFE nop #endif @@ -289,13 +290,18 @@ */ .macro UNTRAIN_RET #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ - defined(CONFIG_CALL_DEPTH_TRACKING) + defined(CONFIG_CALL_DEPTH_TRACKING) || defined(CONFIG_CPU_SRSO) VALIDATE_UNRET_END ALTERNATIVE_3 "", \ CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \ __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH #endif + +#ifdef CONFIG_CPU_SRSO + ALTERNATIVE_2 "", "call srso_untrain_ret", X86_FEATURE_SRSO, \ + "call srso_untrain_ret_alias", X86_FEATURE_SRSO_ALIAS +#endif .endm .macro UNTRAIN_RET_FROM_CALL @@ -307,6 +313,11 @@ "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \ __stringify(RESET_CALL_DEPTH_FROM_CALL), X86_FEATURE_CALL_DEPTH #endif + +#ifdef CONFIG_CPU_SRSO + ALTERNATIVE_2 "", "call srso_untrain_ret", X86_FEATURE_SRSO, \ + "call srso_untrain_ret_alias", X86_FEATURE_SRSO_ALIAS +#endif .endm @@ -332,6 +343,8 @@ extern retpoline_thunk_t __x86_indirect_jump_thunk_array[]; extern void __x86_return_thunk(void); extern void zen_untrain_ret(void); +extern void srso_untrain_ret(void); +extern void srso_untrain_ret_alias(void); extern void entry_ibpb(void); #ifdef CONFIG_CALL_THUNKS @@ -479,11 +492,11 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) : "memory"); } +extern u64 x86_pred_cmd; + static inline void indirect_branch_prediction_barrier(void) { - u64 val = PRED_CMD_IBPB; - - alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB); + alternative_msr_write(MSR_IA32_PRED_CMD, x86_pred_cmd, X86_FEATURE_USE_IBPB); } /* The Intel SPEC CTRL MSR base value cache */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d46300e94f85..fd750247ca89 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -586,7 +586,6 @@ extern char ignore_fpu_irq; #define HAVE_ARCH_PICK_MMAP_LAYOUT 1 #define ARCH_HAS_PREFETCHW -#define ARCH_HAS_SPINLOCK_PREFETCH #ifdef CONFIG_X86_32 # define BASE_PREFETCH "" @@ -620,11 +619,6 @@ static __always_inline void prefetchw(const void *x) "m" (*(const char *)x)); } -static inline void spin_lock_prefetch(const void *x) -{ - prefetchw(x); -} - #define TOP_OF_INIT_STACK ((unsigned long)&init_stack + sizeof(init_stack) - \ TOP_OF_KERNEL_STACK_PADDING) @@ -682,9 +676,13 @@ extern u16 get_llc_id(unsigned int cpu); #ifdef CONFIG_CPU_SUP_AMD extern u32 amd_get_nodes_per_socket(void); extern u32 amd_get_highest_perf(void); +extern bool cpu_has_ibpb_brtype_microcode(void); +extern void amd_clear_divider(void); #else static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline u32 amd_get_highest_perf(void) { return 0; } +static inline bool cpu_has_ibpb_brtype_microcode(void) { return false; } +static inline void amd_clear_divider(void) { } #endif extern unsigned long arch_align_stack(unsigned long sp); @@ -727,4 +725,6 @@ bool arch_is_platform_page(u64 paddr); #define arch_is_platform_page arch_is_platform_page #endif +extern bool gds_ucode_mitigated(void); + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 794f69625780..9d6411c65920 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -56,7 +56,7 @@ #define GDT_ENTRY_INVALID_SEG 0 -#ifdef CONFIG_X86_32 +#if defined(CONFIG_X86_32) && !defined(BUILD_VDSO32_64) /* * The layout of the per-CPU GDT under Linux: * diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 21b542a6866c..53369c57751e 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -52,6 +52,7 @@ int acpi_lapic; int acpi_ioapic; int acpi_strict; int acpi_disable_cmcff; +bool acpi_int_src_ovr[NR_IRQS_LEGACY]; /* ACPI SCI override configuration */ u8 acpi_sci_flags __initdata; @@ -588,6 +589,9 @@ acpi_parse_int_src_ovr(union acpi_subtable_headers * header, acpi_table_print_madt_entry(&header->common); + if (intsrc->source_irq < NR_IRQS_LEGACY) + acpi_int_src_ovr[intsrc->source_irq] = true; + if (intsrc->source_irq == acpi_gbl_FADT.sci_interrupt) { acpi_sci_ioapic_setup(intsrc->source_irq, intsrc->inti_flags & ACPI_MADT_POLARITY_MASK, diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 26ad7ca423e7..70f9d56f9305 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -73,8 +73,13 @@ static const int amd_erratum_1054[] = static const int amd_zenbleed[] = AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x30, 0x0, 0x4f, 0xf), AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 0xf), + AMD_MODEL_RANGE(0x17, 0x90, 0x0, 0x91, 0xf), AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf)); +static const int amd_div0[] = + AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x00, 0x0, 0x2f, 0xf), + AMD_MODEL_RANGE(0x17, 0x50, 0x0, 0x5f, 0xf)); + static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { int osvw_id = *erratum++; @@ -1130,6 +1135,11 @@ static void init_amd(struct cpuinfo_x86 *c) WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS)); zenbleed_check(c); + + if (cpu_has_amd_erratum(c, amd_div0)) { + pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n"); + setup_force_cpu_bug(X86_BUG_DIV0); + } } #ifdef CONFIG_X86_32 @@ -1290,3 +1300,32 @@ void amd_check_microcode(void) { on_each_cpu(zenbleed_check_cpu, NULL, 1); } + +bool cpu_has_ibpb_brtype_microcode(void) +{ + switch (boot_cpu_data.x86) { + /* Zen1/2 IBPB flushes branch type predictions too. */ + case 0x17: + return boot_cpu_has(X86_FEATURE_AMD_IBPB); + case 0x19: + /* Poke the MSR bit on Zen3/4 to check its presence. */ + if (!wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) { + setup_force_cpu_cap(X86_FEATURE_SBPB); + return true; + } else { + return false; + } + default: + return false; + } +} + +/* + * Issue a DIV 0/1 insn to clear any division data from previous DIV + * operations. + */ +void noinstr amd_clear_divider(void) +{ + asm volatile(ALTERNATIVE("", "div %2\n\t", X86_BUG_DIV0) + :: "a" (0), "d" (0), "r" (1)); +} diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 95507448e781..d02f73c5339d 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -47,6 +47,8 @@ static void __init taa_select_mitigation(void); static void __init mmio_select_mitigation(void); static void __init srbds_select_mitigation(void); static void __init l1d_flush_select_mitigation(void); +static void __init srso_select_mitigation(void); +static void __init gds_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -56,6 +58,9 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); DEFINE_PER_CPU(u64, x86_spec_ctrl_current); EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); +u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; +EXPORT_SYMBOL_GPL(x86_pred_cmd); + static DEFINE_MUTEX(spec_ctrl_mutex); /* Update SPEC_CTRL MSR and its cached copy unconditionally */ @@ -160,6 +165,8 @@ void __init cpu_select_mitigations(void) md_clear_select_mitigation(); srbds_select_mitigation(); l1d_flush_select_mitigation(); + srso_select_mitigation(); + gds_select_mitigation(); } /* @@ -646,6 +653,149 @@ static int __init l1d_flush_parse_cmdline(char *str) early_param("l1d_flush", l1d_flush_parse_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "GDS: " fmt + +enum gds_mitigations { + GDS_MITIGATION_OFF, + GDS_MITIGATION_UCODE_NEEDED, + GDS_MITIGATION_FORCE, + GDS_MITIGATION_FULL, + GDS_MITIGATION_FULL_LOCKED, + GDS_MITIGATION_HYPERVISOR, +}; + +#if IS_ENABLED(CONFIG_GDS_FORCE_MITIGATION) +static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FORCE; +#else +static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL; +#endif + +static const char * const gds_strings[] = { + [GDS_MITIGATION_OFF] = "Vulnerable", + [GDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", + [GDS_MITIGATION_FORCE] = "Mitigation: AVX disabled, no microcode", + [GDS_MITIGATION_FULL] = "Mitigation: Microcode", + [GDS_MITIGATION_FULL_LOCKED] = "Mitigation: Microcode (locked)", + [GDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status", +}; + +bool gds_ucode_mitigated(void) +{ + return (gds_mitigation == GDS_MITIGATION_FULL || + gds_mitigation == GDS_MITIGATION_FULL_LOCKED); +} +EXPORT_SYMBOL_GPL(gds_ucode_mitigated); + +void update_gds_msr(void) +{ + u64 mcu_ctrl_after; + u64 mcu_ctrl; + + switch (gds_mitigation) { + case GDS_MITIGATION_OFF: + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + mcu_ctrl |= GDS_MITG_DIS; + break; + case GDS_MITIGATION_FULL_LOCKED: + /* + * The LOCKED state comes from the boot CPU. APs might not have + * the same state. Make sure the mitigation is enabled on all + * CPUs. + */ + case GDS_MITIGATION_FULL: + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + mcu_ctrl &= ~GDS_MITG_DIS; + break; + case GDS_MITIGATION_FORCE: + case GDS_MITIGATION_UCODE_NEEDED: + case GDS_MITIGATION_HYPERVISOR: + return; + }; + + wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + + /* + * Check to make sure that the WRMSR value was not ignored. Writes to + * GDS_MITG_DIS will be ignored if this processor is locked but the boot + * processor was not. + */ + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl_after); + WARN_ON_ONCE(mcu_ctrl != mcu_ctrl_after); +} + +static void __init gds_select_mitigation(void) +{ + u64 mcu_ctrl; + + if (!boot_cpu_has_bug(X86_BUG_GDS)) + return; + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + gds_mitigation = GDS_MITIGATION_HYPERVISOR; + goto out; + } + + if (cpu_mitigations_off()) + gds_mitigation = GDS_MITIGATION_OFF; + /* Will verify below that mitigation _can_ be disabled */ + + /* No microcode */ + if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) { + if (gds_mitigation == GDS_MITIGATION_FORCE) { + /* + * This only needs to be done on the boot CPU so do it + * here rather than in update_gds_msr() + */ + setup_clear_cpu_cap(X86_FEATURE_AVX); + pr_warn("Microcode update needed! Disabling AVX as mitigation.\n"); + } else { + gds_mitigation = GDS_MITIGATION_UCODE_NEEDED; + } + goto out; + } + + /* Microcode has mitigation, use it */ + if (gds_mitigation == GDS_MITIGATION_FORCE) + gds_mitigation = GDS_MITIGATION_FULL; + + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + if (mcu_ctrl & GDS_MITG_LOCKED) { + if (gds_mitigation == GDS_MITIGATION_OFF) + pr_warn("Mitigation locked. Disable failed.\n"); + + /* + * The mitigation is selected from the boot CPU. All other CPUs + * _should_ have the same state. If the boot CPU isn't locked + * but others are then update_gds_msr() will WARN() of the state + * mismatch. If the boot CPU is locked update_gds_msr() will + * ensure the other CPUs have the mitigation enabled. + */ + gds_mitigation = GDS_MITIGATION_FULL_LOCKED; + } + + update_gds_msr(); +out: + pr_info("%s\n", gds_strings[gds_mitigation]); +} + +static int __init gds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_GDS)) + return 0; + + if (!strcmp(str, "off")) + gds_mitigation = GDS_MITIGATION_OFF; + else if (!strcmp(str, "force")) + gds_mitigation = GDS_MITIGATION_FORCE; + + return 0; +} +early_param("gather_data_sampling", gds_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt enum spectre_v1_mitigation { @@ -2188,6 +2338,165 @@ static int __init l1tf_cmdline(char *str) early_param("l1tf", l1tf_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "Speculative Return Stack Overflow: " fmt + +enum srso_mitigation { + SRSO_MITIGATION_NONE, + SRSO_MITIGATION_MICROCODE, + SRSO_MITIGATION_SAFE_RET, + SRSO_MITIGATION_IBPB, + SRSO_MITIGATION_IBPB_ON_VMEXIT, +}; + +enum srso_mitigation_cmd { + SRSO_CMD_OFF, + SRSO_CMD_MICROCODE, + SRSO_CMD_SAFE_RET, + SRSO_CMD_IBPB, + SRSO_CMD_IBPB_ON_VMEXIT, +}; + +static const char * const srso_strings[] = { + [SRSO_MITIGATION_NONE] = "Vulnerable", + [SRSO_MITIGATION_MICROCODE] = "Mitigation: microcode", + [SRSO_MITIGATION_SAFE_RET] = "Mitigation: safe RET", + [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB", + [SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only" +}; + +static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE; +static enum srso_mitigation_cmd srso_cmd __ro_after_init = SRSO_CMD_SAFE_RET; + +static int __init srso_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + srso_cmd = SRSO_CMD_OFF; + else if (!strcmp(str, "microcode")) + srso_cmd = SRSO_CMD_MICROCODE; + else if (!strcmp(str, "safe-ret")) + srso_cmd = SRSO_CMD_SAFE_RET; + else if (!strcmp(str, "ibpb")) + srso_cmd = SRSO_CMD_IBPB; + else if (!strcmp(str, "ibpb-vmexit")) + srso_cmd = SRSO_CMD_IBPB_ON_VMEXIT; + else + pr_err("Ignoring unknown SRSO option (%s).", str); + + return 0; +} +early_param("spec_rstack_overflow", srso_parse_cmdline); + +#define SRSO_NOTICE "WARNING: See https://kernel.org/doc/html/latest/admin-guide/hw-vuln/srso.html for mitigation options." + +static void __init srso_select_mitigation(void) +{ + bool has_microcode; + + if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off()) + goto pred_cmd; + + /* + * The first check is for the kernel running as a guest in order + * for guests to verify whether IBPB is a viable mitigation. + */ + has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) || cpu_has_ibpb_brtype_microcode(); + if (!has_microcode) { + pr_warn("IBPB-extending microcode not applied!\n"); + pr_warn(SRSO_NOTICE); + } else { + /* + * Enable the synthetic (even if in a real CPUID leaf) + * flags for guests. + */ + setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); + + /* + * Zen1/2 with SMT off aren't vulnerable after the right + * IBPB microcode has been applied. + */ + if ((boot_cpu_data.x86 < 0x19) && + (!cpu_smt_possible() || (cpu_smt_control == CPU_SMT_DISABLED))) + setup_force_cpu_cap(X86_FEATURE_SRSO_NO); + } + + if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { + if (has_microcode) { + pr_err("Retbleed IBPB mitigation enabled, using same for SRSO\n"); + srso_mitigation = SRSO_MITIGATION_IBPB; + goto pred_cmd; + } + } + + switch (srso_cmd) { + case SRSO_CMD_OFF: + return; + + case SRSO_CMD_MICROCODE: + if (has_microcode) { + srso_mitigation = SRSO_MITIGATION_MICROCODE; + pr_warn(SRSO_NOTICE); + } + break; + + case SRSO_CMD_SAFE_RET: + if (IS_ENABLED(CONFIG_CPU_SRSO)) { + /* + * Enable the return thunk for generated code + * like ftrace, static_call, etc. + */ + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + + if (boot_cpu_data.x86 == 0x19) + setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS); + else + setup_force_cpu_cap(X86_FEATURE_SRSO); + srso_mitigation = SRSO_MITIGATION_SAFE_RET; + } else { + pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); + goto pred_cmd; + } + break; + + case SRSO_CMD_IBPB: + if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) { + if (has_microcode) { + setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + srso_mitigation = SRSO_MITIGATION_IBPB; + } + } else { + pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); + goto pred_cmd; + } + break; + + case SRSO_CMD_IBPB_ON_VMEXIT: + if (IS_ENABLED(CONFIG_CPU_SRSO)) { + if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { + setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); + srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT; + } + } else { + pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); + goto pred_cmd; + } + break; + + default: + break; + } + + pr_info("%s%s\n", srso_strings[srso_mitigation], (has_microcode ? "" : ", no microcode")); + +pred_cmd: + if ((boot_cpu_has(X86_FEATURE_SRSO_NO) || srso_cmd == SRSO_CMD_OFF) && + boot_cpu_has(X86_FEATURE_SBPB)) + x86_pred_cmd = PRED_CMD_SBPB; +} + +#undef pr_fmt #define pr_fmt(fmt) fmt #ifdef CONFIG_SYSFS @@ -2385,6 +2694,18 @@ static ssize_t retbleed_show_state(char *buf) return sysfs_emit(buf, "%s\n", retbleed_strings[retbleed_mitigation]); } +static ssize_t srso_show_state(char *buf) +{ + return sysfs_emit(buf, "%s%s\n", + srso_strings[srso_mitigation], + (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode")); +} + +static ssize_t gds_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -2434,6 +2755,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_RETBLEED: return retbleed_show_state(buf); + case X86_BUG_SRSO: + return srso_show_state(buf); + + case X86_BUG_GDS: + return gds_show_state(buf); + default: break; } @@ -2498,4 +2825,14 @@ ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, cha { return cpu_show_common(dev, attr, buf, X86_BUG_RETBLEED); } + +ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_SRSO); +} + +ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_GDS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0ba1067f4e5f..e3a65e9fc750 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1250,6 +1250,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define RETBLEED BIT(3) /* CPU is affected by SMT (cross-thread) return predictions */ #define SMT_RSB BIT(4) +/* CPU is affected by SRSO */ +#define SRSO BIT(5) +/* CPU is affected by GDS */ +#define GDS BIT(6) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1262,27 +1266,30 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED), - VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS), + VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(TIGERLAKE_L, X86_STEPPING_ANY, GDS), + VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS), VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), - VULNBL_AMD(0x17, RETBLEED | SMT_RSB), + VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO), VULNBL_HYGON(0x18, RETBLEED | SMT_RSB), + VULNBL_AMD(0x19, SRSO), {} }; @@ -1406,6 +1413,21 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (cpu_matches(cpu_vuln_blacklist, SMT_RSB)) setup_force_cpu_bug(X86_BUG_SMT_RSB); + if (!cpu_has(c, X86_FEATURE_SRSO_NO)) { + if (cpu_matches(cpu_vuln_blacklist, SRSO)) + setup_force_cpu_bug(X86_BUG_SRSO); + } + + /* + * Check if CPU is vulnerable to GDS. If running in a virtual machine on + * an affected processor, the VMM may have disabled the use of GATHER by + * disabling AVX2. The only way to do this in HW is to clear XCR0[2], + * which means that AVX will be disabled. + */ + if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) && + boot_cpu_has(X86_FEATURE_AVX)) + setup_force_cpu_bug(X86_BUG_GDS); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; @@ -1962,6 +1984,8 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); update_srbds_msr(); + if (boot_cpu_has_bug(X86_BUG_GDS)) + update_gds_msr(); tsx_ap_init(); } diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 1c44630d4789..1dcd7d4e38ef 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -83,6 +83,7 @@ void cpu_select_mitigations(void); extern void x86_spec_ctrl_setup_ap(void); extern void update_srbds_msr(void); +extern void update_gds_msr(void); extern enum spectre_v2_mitigation spectre_v2_enabled; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 4a817d20ce3b..1885326a8f65 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -206,6 +206,8 @@ DEFINE_IDTENTRY(exc_divide_error) { do_error_trap(regs, 0, "divide error", X86_TRAP_DE, SIGFPE, FPE_INTDIV, error_get_trap_addr(regs)); + + amd_clear_divider(); } DEFINE_IDTENTRY(exc_overflow) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 03c885d3640f..ef06211bae4c 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -134,13 +134,27 @@ SECTIONS SOFTIRQENTRY_TEXT #ifdef CONFIG_RETPOLINE __indirect_thunk_start = .; - *(.text.__x86.*) + *(.text.__x86.indirect_thunk) + *(.text.__x86.return_thunk) __indirect_thunk_end = .; #endif STATIC_CALL_TEXT ALIGN_ENTRY_TEXT_BEGIN +#ifdef CONFIG_CPU_SRSO + *(.text.__x86.rethunk_untrain) +#endif + ENTRY_TEXT + +#ifdef CONFIG_CPU_SRSO + /* + * See the comment above srso_untrain_ret_alias()'s + * definition. + */ + . = srso_untrain_ret_alias | (1 << 2) | (1 << 8) | (1 << 14) | (1 << 20); + *(.text.__x86.rethunk_safe) +#endif ALIGN_ENTRY_TEXT_END *(.gnu.warning) @@ -509,7 +523,24 @@ INIT_PER_CPU(irq_stack_backing_store); #endif #ifdef CONFIG_RETHUNK -. = ASSERT((__x86_return_thunk & 0x3f) == 0, "__x86_return_thunk not cacheline-aligned"); +. = ASSERT((__ret & 0x3f) == 0, "__ret not cacheline-aligned"); +. = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned"); +#endif + +#ifdef CONFIG_CPU_SRSO +/* + * GNU ld cannot do XOR until 2.41. + * https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=f6f78318fca803c4907fb8d7f6ded8295f1947b1 + * + * LLVM lld cannot do XOR until lld-17. + * https://github.com/llvm/llvm-project/commit/fae96104d4378166cbe5c875ef8ed808a356f3fb + * + * Instead do: (A | B) - (A & B) in order to compute the XOR + * of the two function addresses: + */ +. = ASSERT(((ABSOLUTE(srso_untrain_ret_alias) | srso_safe_ret_alias) - + (ABSOLUTE(srso_untrain_ret_alias) & srso_safe_ret_alias)) == ((1 << 2) | (1 << 8) | (1 << 14) | (1 << 20)), + "SRSO function pair won't alias"); #endif #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 7f4d13383cf2..d3432687c9e6 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -729,6 +729,9 @@ void kvm_set_cpu_caps(void) F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ ); + if (cpu_feature_enabled(X86_FEATURE_SRSO_NO)) + kvm_cpu_cap_set(X86_FEATURE_SRSO_NO); + kvm_cpu_cap_init_kvm_defined(CPUID_8000_0022_EAX, F(PERFMON_V2) ); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 07756b7348ae..d3aec1f2cad2 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2417,15 +2417,18 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) */ memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); - vcpu->arch.regs[VCPU_REGS_RAX] = ghcb_get_rax_if_valid(ghcb); - vcpu->arch.regs[VCPU_REGS_RBX] = ghcb_get_rbx_if_valid(ghcb); - vcpu->arch.regs[VCPU_REGS_RCX] = ghcb_get_rcx_if_valid(ghcb); - vcpu->arch.regs[VCPU_REGS_RDX] = ghcb_get_rdx_if_valid(ghcb); - vcpu->arch.regs[VCPU_REGS_RSI] = ghcb_get_rsi_if_valid(ghcb); + BUILD_BUG_ON(sizeof(svm->sev_es.valid_bitmap) != sizeof(ghcb->save.valid_bitmap)); + memcpy(&svm->sev_es.valid_bitmap, &ghcb->save.valid_bitmap, sizeof(ghcb->save.valid_bitmap)); - svm->vmcb->save.cpl = ghcb_get_cpl_if_valid(ghcb); + vcpu->arch.regs[VCPU_REGS_RAX] = kvm_ghcb_get_rax_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RBX] = kvm_ghcb_get_rbx_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RCX] = kvm_ghcb_get_rcx_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RDX] = kvm_ghcb_get_rdx_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RSI] = kvm_ghcb_get_rsi_if_valid(svm, ghcb); - if (ghcb_xcr0_is_valid(ghcb)) { + svm->vmcb->save.cpl = kvm_ghcb_get_cpl_if_valid(svm, ghcb); + + if (kvm_ghcb_xcr0_is_valid(svm)) { vcpu->arch.xcr0 = ghcb_get_xcr0(ghcb); kvm_update_cpuid_runtime(vcpu); } @@ -2436,84 +2439,88 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) control->exit_code_hi = upper_32_bits(exit_code); control->exit_info_1 = ghcb_get_sw_exit_info_1(ghcb); control->exit_info_2 = ghcb_get_sw_exit_info_2(ghcb); + svm->sev_es.sw_scratch = kvm_ghcb_get_sw_scratch_if_valid(svm, ghcb); /* Clear the valid entries fields */ memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } +static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control) +{ + return (((u64)control->exit_code_hi) << 32) | control->exit_code; +} + static int sev_es_validate_vmgexit(struct vcpu_svm *svm) { - struct kvm_vcpu *vcpu; - struct ghcb *ghcb; + struct vmcb_control_area *control = &svm->vmcb->control; + struct kvm_vcpu *vcpu = &svm->vcpu; u64 exit_code; u64 reason; - ghcb = svm->sev_es.ghcb; - /* * Retrieve the exit code now even though it may not be marked valid * as it could help with debugging. */ - exit_code = ghcb_get_sw_exit_code(ghcb); + exit_code = kvm_ghcb_get_sw_exit_code(control); /* Only GHCB Usage code 0 is supported */ - if (ghcb->ghcb_usage) { + if (svm->sev_es.ghcb->ghcb_usage) { reason = GHCB_ERR_INVALID_USAGE; goto vmgexit_err; } reason = GHCB_ERR_MISSING_INPUT; - if (!ghcb_sw_exit_code_is_valid(ghcb) || - !ghcb_sw_exit_info_1_is_valid(ghcb) || - !ghcb_sw_exit_info_2_is_valid(ghcb)) + if (!kvm_ghcb_sw_exit_code_is_valid(svm) || + !kvm_ghcb_sw_exit_info_1_is_valid(svm) || + !kvm_ghcb_sw_exit_info_2_is_valid(svm)) goto vmgexit_err; - switch (ghcb_get_sw_exit_code(ghcb)) { + switch (exit_code) { case SVM_EXIT_READ_DR7: break; case SVM_EXIT_WRITE_DR7: - if (!ghcb_rax_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_RDTSC: break; case SVM_EXIT_RDPMC: - if (!ghcb_rcx_is_valid(ghcb)) + if (!kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_CPUID: - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_rcx_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; - if (ghcb_get_rax(ghcb) == 0xd) - if (!ghcb_xcr0_is_valid(ghcb)) + if (vcpu->arch.regs[VCPU_REGS_RAX] == 0xd) + if (!kvm_ghcb_xcr0_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_INVD: break; case SVM_EXIT_IOIO: - if (ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_STR_MASK) { - if (!ghcb_sw_scratch_is_valid(ghcb)) + if (control->exit_info_1 & SVM_IOIO_STR_MASK) { + if (!kvm_ghcb_sw_scratch_is_valid(svm)) goto vmgexit_err; } else { - if (!(ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_TYPE_MASK)) - if (!ghcb_rax_is_valid(ghcb)) + if (!(control->exit_info_1 & SVM_IOIO_TYPE_MASK)) + if (!kvm_ghcb_rax_is_valid(svm)) goto vmgexit_err; } break; case SVM_EXIT_MSR: - if (!ghcb_rcx_is_valid(ghcb)) + if (!kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; - if (ghcb_get_sw_exit_info_1(ghcb)) { - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_rdx_is_valid(ghcb)) + if (control->exit_info_1) { + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rdx_is_valid(svm)) goto vmgexit_err; } break; case SVM_EXIT_VMMCALL: - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_cpl_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_cpl_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_RDTSCP: @@ -2521,19 +2528,19 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) case SVM_EXIT_WBINVD: break; case SVM_EXIT_MONITOR: - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_rcx_is_valid(ghcb) || - !ghcb_rdx_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rcx_is_valid(svm) || + !kvm_ghcb_rdx_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_MWAIT: - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_rcx_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; break; case SVM_VMGEXIT_MMIO_READ: case SVM_VMGEXIT_MMIO_WRITE: - if (!ghcb_sw_scratch_is_valid(ghcb)) + if (!kvm_ghcb_sw_scratch_is_valid(svm)) goto vmgexit_err; break; case SVM_VMGEXIT_NMI_COMPLETE: @@ -2549,11 +2556,9 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) return 0; vmgexit_err: - vcpu = &svm->vcpu; - if (reason == GHCB_ERR_INVALID_USAGE) { vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n", - ghcb->ghcb_usage); + svm->sev_es.ghcb->ghcb_usage); } else if (reason == GHCB_ERR_INVALID_EVENT) { vcpu_unimpl(vcpu, "vmgexit: exit code %#llx is not valid\n", exit_code); @@ -2563,11 +2568,8 @@ vmgexit_err: dump_ghcb(svm); } - /* Clear the valid entries fields */ - memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); - - ghcb_set_sw_exit_info_1(ghcb, 2); - ghcb_set_sw_exit_info_2(ghcb, reason); + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, reason); /* Resume the guest to "return" the error code. */ return 1; @@ -2586,7 +2588,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) */ if (svm->sev_es.ghcb_sa_sync) { kvm_write_guest(svm->vcpu.kvm, - ghcb_get_sw_scratch(svm->sev_es.ghcb), + svm->sev_es.sw_scratch, svm->sev_es.ghcb_sa, svm->sev_es.ghcb_sa_len); svm->sev_es.ghcb_sa_sync = false; @@ -2632,12 +2634,11 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu) static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) { struct vmcb_control_area *control = &svm->vmcb->control; - struct ghcb *ghcb = svm->sev_es.ghcb; u64 ghcb_scratch_beg, ghcb_scratch_end; u64 scratch_gpa_beg, scratch_gpa_end; void *scratch_va; - scratch_gpa_beg = ghcb_get_sw_scratch(ghcb); + scratch_gpa_beg = svm->sev_es.sw_scratch; if (!scratch_gpa_beg) { pr_err("vmgexit: scratch gpa not provided\n"); goto e_scratch; @@ -2708,8 +2709,8 @@ static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) return 0; e_scratch: - ghcb_set_sw_exit_info_1(ghcb, 2); - ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_SCRATCH_AREA); + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_SCRATCH_AREA); return 1; } @@ -2822,7 +2823,6 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); struct vmcb_control_area *control = &svm->vmcb->control; u64 ghcb_gpa, exit_code; - struct ghcb *ghcb; int ret; /* Validate the GHCB */ @@ -2847,20 +2847,18 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) } svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva; - ghcb = svm->sev_es.ghcb_map.hva; - trace_kvm_vmgexit_enter(vcpu->vcpu_id, ghcb); - - exit_code = ghcb_get_sw_exit_code(ghcb); + trace_kvm_vmgexit_enter(vcpu->vcpu_id, svm->sev_es.ghcb); + sev_es_sync_from_ghcb(svm); ret = sev_es_validate_vmgexit(svm); if (ret) return ret; - sev_es_sync_from_ghcb(svm); - ghcb_set_sw_exit_info_1(ghcb, 0); - ghcb_set_sw_exit_info_2(ghcb, 0); + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 0); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 0); + exit_code = kvm_ghcb_get_sw_exit_code(control); switch (exit_code) { case SVM_VMGEXIT_MMIO_READ: ret = setup_vmgexit_scratch(svm, true, control->exit_info_2); @@ -2898,13 +2896,13 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) break; case 1: /* Get AP jump table address */ - ghcb_set_sw_exit_info_2(ghcb, sev->ap_jump_table); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, sev->ap_jump_table); break; default: pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n", control->exit_info_1); - ghcb_set_sw_exit_info_1(ghcb, 2); - ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_INPUT); + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_INPUT); } ret = 1; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 956726d867aa..03e852dedcc1 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1498,7 +1498,9 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (sd->current_vmcb != svm->vmcb) { sd->current_vmcb = svm->vmcb; - indirect_branch_prediction_barrier(); + + if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT)) + indirect_branch_prediction_barrier(); } if (kvm_vcpu_apicv_active(vcpu)) avic_vcpu_load(vcpu, cpu); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 18af7e712a5a..8239c8de45ac 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -190,10 +190,12 @@ struct vcpu_sev_es_state { /* SEV-ES support */ struct sev_es_save_area *vmsa; struct ghcb *ghcb; + u8 valid_bitmap[16]; struct kvm_host_map ghcb_map; bool received_first_sipi; /* SEV-ES scratch area support */ + u64 sw_scratch; void *ghcb_sa; u32 ghcb_sa_len; bool ghcb_sa_sync; @@ -744,4 +746,28 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm); void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); void __svm_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); +#define DEFINE_KVM_GHCB_ACCESSORS(field) \ + static __always_inline bool kvm_ghcb_##field##_is_valid(const struct vcpu_svm *svm) \ + { \ + return test_bit(GHCB_BITMAP_IDX(field), \ + (unsigned long *)&svm->sev_es.valid_bitmap); \ + } \ + \ + static __always_inline u64 kvm_ghcb_get_##field##_if_valid(struct vcpu_svm *svm, struct ghcb *ghcb) \ + { \ + return kvm_ghcb_##field##_is_valid(svm) ? ghcb->save.field : 0; \ + } \ + +DEFINE_KVM_GHCB_ACCESSORS(cpl) +DEFINE_KVM_GHCB_ACCESSORS(rax) +DEFINE_KVM_GHCB_ACCESSORS(rcx) +DEFINE_KVM_GHCB_ACCESSORS(rdx) +DEFINE_KVM_GHCB_ACCESSORS(rbx) +DEFINE_KVM_GHCB_ACCESSORS(rsi) +DEFINE_KVM_GHCB_ACCESSORS(sw_exit_code) +DEFINE_KVM_GHCB_ACCESSORS(sw_exit_info_1) +DEFINE_KVM_GHCB_ACCESSORS(sw_exit_info_2) +DEFINE_KVM_GHCB_ACCESSORS(sw_scratch) +DEFINE_KVM_GHCB_ACCESSORS(xcr0) + #endif diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 8e8295e774f0..265452fc9ebe 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -224,6 +224,9 @@ SYM_FUNC_START(__svm_vcpu_run) */ UNTRAIN_RET + /* SRSO */ + ALTERNATIVE "", "call entry_ibpb", X86_FEATURE_IBPB_ON_VMEXIT + /* * Clear all general purpose registers except RSP and RAX to prevent * speculative use of the guest's values, even those that are reloaded diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 278dbd37dab2..c381770bcbf1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1616,7 +1616,7 @@ static bool kvm_is_immutable_feature_msr(u32 msr) ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ - ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO) + ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO) static u64 kvm_get_arch_capabilities(void) { @@ -1673,6 +1673,9 @@ static u64 kvm_get_arch_capabilities(void) */ } + if (!boot_cpu_has_bug(X86_BUG_GDS) || gds_ucode_mitigated()) + data |= ARCH_CAP_GDS_NO; + return data; } diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 3fd066d42ec0..2cff585f22f2 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -11,6 +11,7 @@ #include <asm/unwind_hints.h> #include <asm/percpu.h> #include <asm/frame.h> +#include <asm/nops.h> .section .text.__x86.indirect_thunk @@ -131,6 +132,46 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) */ #ifdef CONFIG_RETHUNK +/* + * srso_untrain_ret_alias() and srso_safe_ret_alias() are placed at + * special addresses: + * + * - srso_untrain_ret_alias() is 2M aligned + * - srso_safe_ret_alias() is also in the same 2M page but bits 2, 8, 14 + * and 20 in its virtual address are set (while those bits in the + * srso_untrain_ret_alias() function are cleared). + * + * This guarantees that those two addresses will alias in the branch + * target buffer of Zen3/4 generations, leading to any potential + * poisoned entries at that BTB slot to get evicted. + * + * As a result, srso_safe_ret_alias() becomes a safe return. + */ +#ifdef CONFIG_CPU_SRSO + .section .text.__x86.rethunk_untrain + +SYM_START(srso_untrain_ret_alias, SYM_L_GLOBAL, SYM_A_NONE) + ANNOTATE_NOENDBR + ASM_NOP2 + lfence + jmp __x86_return_thunk +SYM_FUNC_END(srso_untrain_ret_alias) +__EXPORT_THUNK(srso_untrain_ret_alias) + + .section .text.__x86.rethunk_safe +#endif + +/* Needs a definition for the __x86_return_thunk alternative below. */ +SYM_START(srso_safe_ret_alias, SYM_L_GLOBAL, SYM_A_NONE) +#ifdef CONFIG_CPU_SRSO + add $8, %_ASM_SP + UNWIND_HINT_FUNC +#endif + ANNOTATE_UNRET_SAFE + ret + int3 +SYM_FUNC_END(srso_safe_ret_alias) + .section .text.__x86.return_thunk /* @@ -143,7 +184,7 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) * from re-poisioning the BTB prediction. */ .align 64 - .skip 64 - (__x86_return_thunk - zen_untrain_ret), 0xcc + .skip 64 - (__ret - zen_untrain_ret), 0xcc SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) ANNOTATE_NOENDBR /* @@ -175,10 +216,10 @@ SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) * evicted, __x86_return_thunk will suffer Straight Line Speculation * which will be contained safely by the INT3. */ -SYM_INNER_LABEL(__x86_return_thunk, SYM_L_GLOBAL) +SYM_INNER_LABEL(__ret, SYM_L_GLOBAL) ret int3 -SYM_CODE_END(__x86_return_thunk) +SYM_CODE_END(__ret) /* * Ensure the TEST decoding / BTB invalidation is complete. @@ -189,11 +230,45 @@ SYM_CODE_END(__x86_return_thunk) * Jump back and execute the RET in the middle of the TEST instruction. * INT3 is for SLS protection. */ - jmp __x86_return_thunk + jmp __ret int3 SYM_FUNC_END(zen_untrain_ret) __EXPORT_THUNK(zen_untrain_ret) +/* + * SRSO untraining sequence for Zen1/2, similar to zen_untrain_ret() + * above. On kernel entry, srso_untrain_ret() is executed which is a + * + * movabs $0xccccccc308c48348,%rax + * + * and when the return thunk executes the inner label srso_safe_ret() + * later, it is a stack manipulation and a RET which is mispredicted and + * thus a "safe" one to use. + */ + .align 64 + .skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc +SYM_START(srso_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) + ANNOTATE_NOENDBR + .byte 0x48, 0xb8 + +SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL) + add $8, %_ASM_SP + ret + int3 + int3 + int3 + lfence + call srso_safe_ret + int3 +SYM_CODE_END(srso_safe_ret) +SYM_FUNC_END(srso_untrain_ret) +__EXPORT_THUNK(srso_untrain_ret) + +SYM_FUNC_START(__x86_return_thunk) + ALTERNATIVE_2 "jmp __ret", "call srso_safe_ret", X86_FEATURE_SRSO, \ + "call srso_safe_ret_alias", X86_FEATURE_SRSO_ALIAS + int3 +SYM_CODE_END(__x86_return_thunk) EXPORT_SYMBOL(__x86_return_thunk) #endif /* CONFIG_RETHUNK */ diff --git a/block/blk-core.c b/block/blk-core.c index 90de50082146..9866468c72a2 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -722,14 +722,9 @@ void submit_bio_noacct(struct bio *bio) struct block_device *bdev = bio->bi_bdev; struct request_queue *q = bdev_get_queue(bdev); blk_status_t status = BLK_STS_IOERR; - struct blk_plug *plug; might_sleep(); - plug = blk_mq_plug(bio); - if (plug && plug->nowait) - bio->bi_opf |= REQ_NOWAIT; - /* * For a REQ_NOWAIT based request, return -EOPNOTSUPP * if queue does not support NOWAIT. @@ -1059,7 +1054,6 @@ void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios) plug->rq_count = 0; plug->multiple_queues = false; plug->has_elevator = false; - plug->nowait = false; INIT_LIST_HEAD(&plug->cb_list); /* diff --git a/block/blk-iocost.c b/block/blk-iocost.c index dd64e2066f01..089fcb9cfce3 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -3301,11 +3301,12 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, if (qos[QOS_MIN] > qos[QOS_MAX]) goto einval; - if (enable) { + if (enable && !ioc->enabled) { blk_stat_enable_accounting(disk->queue); blk_queue_flag_set(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue); ioc->enabled = true; - } else { + } else if (!enable && ioc->enabled) { + blk_stat_disable_accounting(disk->queue); blk_queue_flag_clear(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue); ioc->enabled = false; } diff --git a/block/fops.c b/block/fops.c index a286bf3325c5..838ffada5341 100644 --- a/block/fops.c +++ b/block/fops.c @@ -358,13 +358,14 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb, task_io_account_write(bio->bi_iter.bi_size); } + if (iocb->ki_flags & IOCB_NOWAIT) + bio->bi_opf |= REQ_NOWAIT; + if (iocb->ki_flags & IOCB_HIPRI) { - bio->bi_opf |= REQ_POLLED | REQ_NOWAIT; + bio->bi_opf |= REQ_POLLED; submit_bio(bio); WRITE_ONCE(iocb->private, bio); } else { - if (iocb->ki_flags & IOCB_NOWAIT) - bio->bi_opf |= REQ_NOWAIT; submit_bio(bio); } return -EIOCBQUEUED; diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c index 52b339aefadc..9967fcfa27ec 100644 --- a/drivers/accel/ivpu/ivpu_gem.c +++ b/drivers/accel/ivpu/ivpu_gem.c @@ -173,6 +173,9 @@ static void internal_free_pages_locked(struct ivpu_bo *bo) { unsigned int i, npages = bo->base.size >> PAGE_SHIFT; + if (ivpu_bo_cache_mode(bo) != DRM_IVPU_BO_CACHED) + set_pages_array_wb(bo->pages, bo->base.size >> PAGE_SHIFT); + for (i = 0; i < npages; i++) put_page(bo->pages[i]); @@ -587,6 +590,11 @@ ivpu_bo_alloc_internal(struct ivpu_device *vdev, u64 vpu_addr, u64 size, u32 fla if (ivpu_bo_cache_mode(bo) != DRM_IVPU_BO_CACHED) drm_clflush_pages(bo->pages, bo->base.size >> PAGE_SHIFT); + if (bo->flags & DRM_IVPU_BO_WC) + set_pages_array_wc(bo->pages, bo->base.size >> PAGE_SHIFT); + else if (bo->flags & DRM_IVPU_BO_UNCACHED) + set_pages_array_uc(bo->pages, bo->base.size >> PAGE_SHIFT); + prot = ivpu_bo_pgprot(bo, PAGE_KERNEL); bo->kvaddr = vmap(bo->pages, bo->base.size >> PAGE_SHIFT, VM_MAP, prot); if (!bo->kvaddr) { diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 1dd8d5aebf67..a4d9f149b48d 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -470,6 +470,45 @@ static const struct dmi_system_id asus_laptop[] = { { } }; +static const struct dmi_system_id tongfang_gm_rg[] = { + { + .ident = "TongFang GMxRGxx/XMG CORE 15 (M22)/TUXEDO Stellaris 15 Gen4 AMD", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GMxRGxx"), + }, + }, + { } +}; + +static const struct dmi_system_id maingear_laptop[] = { + { + .ident = "MAINGEAR Vector Pro 2 15", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Micro Electronics Inc"), + DMI_MATCH(DMI_PRODUCT_NAME, "MG-VCP2-15A3070T"), + } + }, + { + .ident = "MAINGEAR Vector Pro 2 17", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Micro Electronics Inc"), + DMI_MATCH(DMI_PRODUCT_NAME, "MG-VCP2-17A3070T"), + }, + }, + { } +}; + +static const struct dmi_system_id pcspecialist_laptop[] = { + { + .ident = "PCSpecialist Elimina Pro 16 M", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "PCSpecialist"), + DMI_MATCH(DMI_PRODUCT_NAME, "Elimina Pro 16 M"), + }, + }, + { } +}; + static const struct dmi_system_id lg_laptop[] = { { .ident = "LG Electronics 17U70P", @@ -493,6 +532,9 @@ struct irq_override_cmp { static const struct irq_override_cmp override_table[] = { { medion_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false }, { asus_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false }, + { tongfang_gm_rg, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true }, + { maingear_laptop, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true }, + { pcspecialist_laptop, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true }, { lg_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false }, }; @@ -512,6 +554,28 @@ static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity, return entry->override; } +#ifdef CONFIG_X86 + /* + * Always use the MADT override info, except for the i8042 PS/2 ctrl + * IRQs (1 and 12). For these the DSDT IRQ settings should sometimes + * be used otherwise PS/2 keyboards / mice will not work. + */ + if (gsi != 1 && gsi != 12) + return true; + + /* If the override comes from an INT_SRC_OVR MADT entry, honor it. */ + if (acpi_int_src_ovr[gsi]) + return true; + + /* + * IRQ override isn't needed on modern AMD Zen systems and + * this override breaks active low IRQs on AMD Ryzen 6000 and + * newer systems. Skip it. + */ + if (boot_cpu_has(X86_FEATURE_ZEN)) + return false; +#endif + return true; } diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 5b145f1aaa1b..87e385542576 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1714,6 +1714,7 @@ static bool acpi_device_enumeration_by_parent(struct acpi_device *device) {"BSG1160", }, {"BSG2150", }, {"CSC3551", }, + {"CSC3556", }, {"INT33FE", }, {"INT3515", }, /* Non-conforming _HID for Cirrus Logic already released */ diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 49d84a6c4594..367afac5f1bf 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -6615,6 +6615,7 @@ err_init_binder_device_failed: err_alloc_device_names_failed: debugfs_remove_recursive(binder_debugfs_dir_entry_root); + binder_alloc_shrinker_exit(); return ret; } diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 662a2a2e2e84..e3db8297095a 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -1087,6 +1087,12 @@ int binder_alloc_shrinker_init(void) return ret; } +void binder_alloc_shrinker_exit(void) +{ + unregister_shrinker(&binder_shrinker); + list_lru_destroy(&binder_alloc_lru); +} + /** * check_buffer() - verify that buffer/offset is safe to access * @alloc: binder_alloc for this proc diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h index 138d1d5af9ce..dc1e2b01dd64 100644 --- a/drivers/android/binder_alloc.h +++ b/drivers/android/binder_alloc.h @@ -129,6 +129,7 @@ extern struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc, int pid); extern void binder_alloc_init(struct binder_alloc *alloc); extern int binder_alloc_shrinker_init(void); +extern void binder_alloc_shrinker_exit(void); extern void binder_alloc_vma_close(struct binder_alloc *alloc); extern struct binder_buffer * binder_alloc_prepare_to_free(struct binder_alloc *alloc, diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 370d18aca71e..c6ece32de8e3 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1100,7 +1100,14 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev) } } else { sdev->sector_size = ata_id_logical_sector_size(dev->id); + /* + * Stop the drive on suspend but do not issue START STOP UNIT + * on resume as this is not necessary and may fail: the device + * will be woken up by ata_port_pm_resume() with a port reset + * and device revalidation. + */ sdev->manage_start_stop = 1; + sdev->no_start_on_resume = 1; } /* diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index c1815b9dae68..fe6690ecf563 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -509,73 +509,30 @@ static void __init cpu_dev_register_generic(void) } #ifdef CONFIG_GENERIC_CPU_VULNERABILITIES - -ssize_t __weak cpu_show_meltdown(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return sysfs_emit(buf, "Not affected\n"); -} - -ssize_t __weak cpu_show_spectre_v1(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return sysfs_emit(buf, "Not affected\n"); -} - -ssize_t __weak cpu_show_spectre_v2(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return sysfs_emit(buf, "Not affected\n"); -} - -ssize_t __weak cpu_show_spec_store_bypass(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return sysfs_emit(buf, "Not affected\n"); -} - -ssize_t __weak cpu_show_l1tf(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return sysfs_emit(buf, "Not affected\n"); -} - -ssize_t __weak cpu_show_mds(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return sysfs_emit(buf, "Not affected\n"); -} - -ssize_t __weak cpu_show_tsx_async_abort(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - return sysfs_emit(buf, "Not affected\n"); -} - -ssize_t __weak cpu_show_itlb_multihit(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return sysfs_emit(buf, "Not affected\n"); -} - -ssize_t __weak cpu_show_srbds(struct device *dev, +static ssize_t cpu_show_not_affected(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "Not affected\n"); } -ssize_t __weak cpu_show_mmio_stale_data(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return sysfs_emit(buf, "Not affected\n"); -} - -ssize_t __weak cpu_show_retbleed(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return sysfs_emit(buf, "Not affected\n"); -} +#define CPU_SHOW_VULN_FALLBACK(func) \ + ssize_t cpu_show_##func(struct device *, \ + struct device_attribute *, char *) \ + __attribute__((weak, alias("cpu_show_not_affected"))) + +CPU_SHOW_VULN_FALLBACK(meltdown); +CPU_SHOW_VULN_FALLBACK(spectre_v1); +CPU_SHOW_VULN_FALLBACK(spectre_v2); +CPU_SHOW_VULN_FALLBACK(spec_store_bypass); +CPU_SHOW_VULN_FALLBACK(l1tf); +CPU_SHOW_VULN_FALLBACK(mds); +CPU_SHOW_VULN_FALLBACK(tsx_async_abort); +CPU_SHOW_VULN_FALLBACK(itlb_multihit); +CPU_SHOW_VULN_FALLBACK(srbds); +CPU_SHOW_VULN_FALLBACK(mmio_stale_data); +CPU_SHOW_VULN_FALLBACK(retbleed); +CPU_SHOW_VULN_FALLBACK(spec_rstack_overflow); +CPU_SHOW_VULN_FALLBACK(gds); static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); @@ -588,6 +545,8 @@ static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL); static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL); static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); +static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL); +static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -601,6 +560,8 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_srbds.attr, &dev_attr_mmio_stale_data.attr, &dev_attr_retbleed.attr, + &dev_attr_spec_rstack_overflow.attr, + &dev_attr_gather_data_sampling.attr, NULL }; diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 24afcc93ac01..2328cc05be36 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3675,7 +3675,7 @@ static int rbd_lock(struct rbd_device *rbd_dev) ret = ceph_cls_lock(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, RBD_LOCK_NAME, CEPH_CLS_LOCK_EXCLUSIVE, cookie, RBD_LOCK_TAG, "", 0); - if (ret) + if (ret && ret != -EEXIST) return ret; __rbd_lock(rbd_dev, cookie); @@ -3878,7 +3878,7 @@ static struct ceph_locker *get_lock_owner_info(struct rbd_device *rbd_dev) &rbd_dev->header_oloc, RBD_LOCK_NAME, &lock_type, &lock_tag, &lockers, &num_lockers); if (ret) { - rbd_warn(rbd_dev, "failed to retrieve lockers: %d", ret); + rbd_warn(rbd_dev, "failed to get header lockers: %d", ret); return ERR_PTR(ret); } @@ -3940,8 +3940,10 @@ static int find_watcher(struct rbd_device *rbd_dev, ret = ceph_osdc_list_watchers(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, &watchers, &num_watchers); - if (ret) + if (ret) { + rbd_warn(rbd_dev, "failed to get watchers: %d", ret); return ret; + } sscanf(locker->id.cookie, RBD_LOCK_COOKIE_PREFIX " %llu", &cookie); for (i = 0; i < num_watchers; i++) { @@ -3985,8 +3987,12 @@ static int rbd_try_lock(struct rbd_device *rbd_dev) locker = refreshed_locker = NULL; ret = rbd_lock(rbd_dev); - if (ret != -EBUSY) + if (!ret) + goto out; + if (ret != -EBUSY) { + rbd_warn(rbd_dev, "failed to lock header: %d", ret); goto out; + } /* determine if the current lock holder is still alive */ locker = get_lock_owner_info(rbd_dev); @@ -4089,11 +4095,8 @@ static int rbd_try_acquire_lock(struct rbd_device *rbd_dev) ret = rbd_try_lock(rbd_dev); if (ret < 0) { - rbd_warn(rbd_dev, "failed to lock header: %d", ret); - if (ret == -EBLOCKLISTED) - goto out; - - ret = 1; /* request lock anyway */ + rbd_warn(rbd_dev, "failed to acquire lock: %d", ret); + goto out; } if (ret > 0) { up_write(&rbd_dev->lock_rwsem); @@ -6627,12 +6630,11 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev) cancel_delayed_work_sync(&rbd_dev->lock_dwork); if (!ret) ret = -ETIMEDOUT; - } - if (ret) { - rbd_warn(rbd_dev, "failed to acquire exclusive lock: %ld", ret); - return ret; + rbd_warn(rbd_dev, "failed to acquire lock: %ld", ret); } + if (ret) + return ret; /* * The lock may have been released by now, unless automatic lock diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 5676e6dd5b16..06673c6ca255 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1870,15 +1870,16 @@ static void zram_bio_discard(struct zram *zram, struct bio *bio) static void zram_bio_read(struct zram *zram, struct bio *bio) { - struct bvec_iter iter; - struct bio_vec bv; - unsigned long start_time; + unsigned long start_time = bio_start_io_acct(bio); + struct bvec_iter iter = bio->bi_iter; - start_time = bio_start_io_acct(bio); - bio_for_each_segment(bv, bio, iter) { + do { u32 index = iter.bi_sector >> SECTORS_PER_PAGE_SHIFT; u32 offset = (iter.bi_sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT; + struct bio_vec bv = bio_iter_iovec(bio, iter); + + bv.bv_len = min_t(u32, bv.bv_len, PAGE_SIZE - offset); if (zram_bvec_read(zram, &bv, index, offset, bio) < 0) { atomic64_inc(&zram->stats.failed_reads); @@ -1890,22 +1891,26 @@ static void zram_bio_read(struct zram *zram, struct bio *bio) zram_slot_lock(zram, index); zram_accessed(zram, index); zram_slot_unlock(zram, index); - } + + bio_advance_iter_single(bio, &iter, bv.bv_len); + } while (iter.bi_size); + bio_end_io_acct(bio, start_time); bio_endio(bio); } static void zram_bio_write(struct zram *zram, struct bio *bio) { - struct bvec_iter iter; - struct bio_vec bv; - unsigned long start_time; + unsigned long start_time = bio_start_io_acct(bio); + struct bvec_iter iter = bio->bi_iter; - start_time = bio_start_io_acct(bio); - bio_for_each_segment(bv, bio, iter) { + do { u32 index = iter.bi_sector >> SECTORS_PER_PAGE_SHIFT; u32 offset = (iter.bi_sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT; + struct bio_vec bv = bio_iter_iovec(bio, iter); + + bv.bv_len = min_t(u32, bv.bv_len, PAGE_SIZE - offset); if (zram_bvec_write(zram, &bv, index, offset, bio) < 0) { atomic64_inc(&zram->stats.failed_writes); @@ -1916,7 +1921,10 @@ static void zram_bio_write(struct zram *zram, struct bio *bio) zram_slot_lock(zram, index); zram_accessed(zram, index); zram_slot_unlock(zram, index); - } + + bio_advance_iter_single(bio, &iter, bv.bv_len); + } while (iter.bi_size); + bio_end_io_acct(bio, start_time); bio_endio(bio); } diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index cf5499e51999..ea6b4013bc38 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -510,70 +510,6 @@ static int tpm_add_legacy_sysfs(struct tpm_chip *chip) return 0; } -/* - * Some AMD fTPM versions may cause stutter - * https://www.amd.com/en/support/kb/faq/pa-410 - * - * Fixes are available in two series of fTPM firmware: - * 6.x.y.z series: 6.0.18.6 + - * 3.x.y.z series: 3.57.y.5 + - */ -#ifdef CONFIG_X86 -static bool tpm_amd_is_rng_defective(struct tpm_chip *chip) -{ - u32 val1, val2; - u64 version; - int ret; - - if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) - return false; - - ret = tpm_request_locality(chip); - if (ret) - return false; - - ret = tpm2_get_tpm_pt(chip, TPM2_PT_MANUFACTURER, &val1, NULL); - if (ret) - goto release; - if (val1 != 0x414D4400U /* AMD */) { - ret = -ENODEV; - goto release; - } - ret = tpm2_get_tpm_pt(chip, TPM2_PT_FIRMWARE_VERSION_1, &val1, NULL); - if (ret) - goto release; - ret = tpm2_get_tpm_pt(chip, TPM2_PT_FIRMWARE_VERSION_2, &val2, NULL); - -release: - tpm_relinquish_locality(chip); - - if (ret) - return false; - - version = ((u64)val1 << 32) | val2; - if ((version >> 48) == 6) { - if (version >= 0x0006000000180006ULL) - return false; - } else if ((version >> 48) == 3) { - if (version >= 0x0003005700000005ULL) - return false; - } else { - return false; - } - - dev_warn(&chip->dev, - "AMD fTPM version 0x%llx causes system stutter; hwrng disabled\n", - version); - - return true; -} -#else -static inline bool tpm_amd_is_rng_defective(struct tpm_chip *chip) -{ - return false; -} -#endif /* CONFIG_X86 */ - static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait) { struct tpm_chip *chip = container_of(rng, struct tpm_chip, hwrng); @@ -585,10 +521,20 @@ static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait) return tpm_get_random(chip, data, max); } +static bool tpm_is_hwrng_enabled(struct tpm_chip *chip) +{ + if (!IS_ENABLED(CONFIG_HW_RANDOM_TPM)) + return false; + if (tpm_is_firmware_upgrade(chip)) + return false; + if (chip->flags & TPM_CHIP_FLAG_HWRNG_DISABLED) + return false; + return true; +} + static int tpm_add_hwrng(struct tpm_chip *chip) { - if (!IS_ENABLED(CONFIG_HW_RANDOM_TPM) || tpm_is_firmware_upgrade(chip) || - tpm_amd_is_rng_defective(chip)) + if (!tpm_is_hwrng_enabled(chip)) return 0; snprintf(chip->hwrng_name, sizeof(chip->hwrng_name), @@ -693,7 +639,7 @@ int tpm_chip_register(struct tpm_chip *chip) return 0; out_hwrng: - if (IS_ENABLED(CONFIG_HW_RANDOM_TPM) && !tpm_is_firmware_upgrade(chip)) + if (tpm_is_hwrng_enabled(chip)) hwrng_unregister(&chip->hwrng); out_ppi: tpm_bios_log_teardown(chip); @@ -718,8 +664,7 @@ EXPORT_SYMBOL_GPL(tpm_chip_register); void tpm_chip_unregister(struct tpm_chip *chip) { tpm_del_legacy_sysfs(chip); - if (IS_ENABLED(CONFIG_HW_RANDOM_TPM) && !tpm_is_firmware_upgrade(chip) && - !tpm_amd_is_rng_defective(chip)) + if (tpm_is_hwrng_enabled(chip)) hwrng_unregister(&chip->hwrng); tpm_bios_log_teardown(chip); if (chip->flags & TPM_CHIP_FLAG_TPM2 && !tpm_is_firmware_upgrade(chip)) diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index 1a5d09b18513..9eb1a1859012 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -463,6 +463,28 @@ static bool crb_req_canceled(struct tpm_chip *chip, u8 status) return (cancel & CRB_CANCEL_INVOKE) == CRB_CANCEL_INVOKE; } +static int crb_check_flags(struct tpm_chip *chip) +{ + u32 val; + int ret; + + ret = crb_request_locality(chip, 0); + if (ret) + return ret; + + ret = tpm2_get_tpm_pt(chip, TPM2_PT_MANUFACTURER, &val, NULL); + if (ret) + goto release; + + if (val == 0x414D4400U /* AMD */) + chip->flags |= TPM_CHIP_FLAG_HWRNG_DISABLED; + +release: + crb_relinquish_locality(chip, 0); + + return ret; +} + static const struct tpm_class_ops tpm_crb = { .flags = TPM_OPS_AUTO_STARTUP, .status = crb_status, @@ -800,6 +822,14 @@ static int crb_acpi_add(struct acpi_device *device) chip->acpi_dev_handle = device->handle; chip->flags = TPM_CHIP_FLAG_TPM2; + rc = tpm_chip_bootstrap(chip); + if (rc) + goto out; + + rc = crb_check_flags(chip); + if (rc) + goto out; + rc = tpm_chip_register(chip); out: diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index cc42cf3de960..7fa3d91042b2 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -89,7 +89,7 @@ static inline void tpm_tis_iowrite32(u32 b, void __iomem *iobase, u32 addr) tpm_tis_flush(iobase); } -static int interrupts = -1; +static int interrupts; module_param(interrupts, int, 0444); MODULE_PARM_DESC(interrupts, "Enable interrupts"); @@ -164,10 +164,26 @@ static const struct dmi_system_id tpm_tis_dmi_table[] = { }, { .callback = tpm_tis_disable_irq, + .ident = "ThinkStation P620", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkStation P620"), + }, + }, + { + .callback = tpm_tis_disable_irq, + .ident = "TUXEDO InfinityBook S 15/17 Gen7", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_PRODUCT_NAME, "TUXEDO InfinityBook S 15/17 Gen7"), + }, + }, + { + .callback = tpm_tis_disable_irq, .ident = "UPX-TGL", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "AAEON"), - DMI_MATCH(DMI_PRODUCT_VERSION, "UPX-TGL"), + DMI_MATCH(DMI_PRODUCT_NAME, "UPX-TGL01"), }, }, {} diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index 93f38a8178ba..6b3b424addab 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -444,6 +444,7 @@ config COMMON_CLK_BD718XX config COMMON_CLK_FIXED_MMIO bool "Clock driver for Memory Mapped Fixed values" depends on COMMON_CLK && OF + depends on HAS_IOMEM help Support for Memory Mapped IO Fixed clocks diff --git a/drivers/clk/imx/clk-imx93.c b/drivers/clk/imx/clk-imx93.c index b6c7c2725906..44f435103c65 100644 --- a/drivers/clk/imx/clk-imx93.c +++ b/drivers/clk/imx/clk-imx93.c @@ -291,7 +291,7 @@ static int imx93_clocks_probe(struct platform_device *pdev) anatop_base = devm_of_iomap(dev, np, 0, NULL); of_node_put(np); if (WARN_ON(IS_ERR(anatop_base))) { - ret = PTR_ERR(base); + ret = PTR_ERR(anatop_base); goto unregister_hws; } diff --git a/drivers/clk/mediatek/clk-mt8183.c b/drivers/clk/mediatek/clk-mt8183.c index 1ba421b38ec5..e31f94387d87 100644 --- a/drivers/clk/mediatek/clk-mt8183.c +++ b/drivers/clk/mediatek/clk-mt8183.c @@ -328,6 +328,14 @@ static const char * const atb_parents[] = { "syspll_d5" }; +static const char * const sspm_parents[] = { + "clk26m", + "univpll_d2_d4", + "syspll_d2_d2", + "univpll_d2_d2", + "syspll_d3" +}; + static const char * const dpi0_parents[] = { "clk26m", "tvdpll_d2", @@ -507,6 +515,9 @@ static const struct mtk_mux top_muxes[] = { /* CLK_CFG_6 */ MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_ATB, "atb_sel", atb_parents, 0xa0, 0xa4, 0xa8, 0, 2, 7, 0x004, 24), + MUX_GATE_CLR_SET_UPD_FLAGS(CLK_TOP_MUX_SSPM, "sspm_sel", + sspm_parents, 0xa0, 0xa4, 0xa8, 8, 3, 15, 0x004, 25, + CLK_IS_CRITICAL | CLK_SET_RATE_PARENT), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_DPI0, "dpi0_sel", dpi0_parents, 0xa0, 0xa4, 0xa8, 16, 4, 23, 0x004, 26), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_SCAM, "scam_sel", @@ -673,10 +684,18 @@ static const struct mtk_gate_regs infra3_cg_regs = { GATE_MTK(_id, _name, _parent, &infra2_cg_regs, _shift, \ &mtk_clk_gate_ops_setclr) +#define GATE_INFRA2_FLAGS(_id, _name, _parent, _shift, _flag) \ + GATE_MTK_FLAGS(_id, _name, _parent, &infra2_cg_regs, \ + _shift, &mtk_clk_gate_ops_setclr, _flag) + #define GATE_INFRA3(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, &infra3_cg_regs, _shift, \ &mtk_clk_gate_ops_setclr) +#define GATE_INFRA3_FLAGS(_id, _name, _parent, _shift, _flag) \ + GATE_MTK_FLAGS(_id, _name, _parent, &infra3_cg_regs, \ + _shift, &mtk_clk_gate_ops_setclr, _flag) + static const struct mtk_gate infra_clks[] = { /* INFRA0 */ GATE_INFRA0(CLK_INFRA_PMIC_TMR, "infra_pmic_tmr", "axi_sel", 0), @@ -748,7 +767,11 @@ static const struct mtk_gate infra_clks[] = { GATE_INFRA2(CLK_INFRA_UNIPRO_TICK, "infra_unipro_tick", "fufs_sel", 12), GATE_INFRA2(CLK_INFRA_UFS_MP_SAP_BCLK, "infra_ufs_mp_sap_bck", "fufs_sel", 13), GATE_INFRA2(CLK_INFRA_MD32_BCLK, "infra_md32_bclk", "axi_sel", 14), + /* infra_sspm is main clock in co-processor, should not be closed in Linux. */ + GATE_INFRA2_FLAGS(CLK_INFRA_SSPM, "infra_sspm", "sspm_sel", 15, CLK_IS_CRITICAL), GATE_INFRA2(CLK_INFRA_UNIPRO_MBIST, "infra_unipro_mbist", "axi_sel", 16), + /* infra_sspm_bus_hclk is main clock in co-processor, should not be closed in Linux. */ + GATE_INFRA2_FLAGS(CLK_INFRA_SSPM_BUS_HCLK, "infra_sspm_bus_hclk", "axi_sel", 17, CLK_IS_CRITICAL), GATE_INFRA2(CLK_INFRA_I2C5, "infra_i2c5", "i2c_sel", 18), GATE_INFRA2(CLK_INFRA_I2C5_ARBITER, "infra_i2c5_arbiter", "i2c_sel", 19), GATE_INFRA2(CLK_INFRA_I2C5_IMM, "infra_i2c5_imm", "i2c_sel", 20), @@ -766,6 +789,10 @@ static const struct mtk_gate infra_clks[] = { GATE_INFRA3(CLK_INFRA_MSDC0_SELF, "infra_msdc0_self", "msdc50_0_sel", 0), GATE_INFRA3(CLK_INFRA_MSDC1_SELF, "infra_msdc1_self", "msdc50_0_sel", 1), GATE_INFRA3(CLK_INFRA_MSDC2_SELF, "infra_msdc2_self", "msdc50_0_sel", 2), + /* infra_sspm_26m_self is main clock in co-processor, should not be closed in Linux. */ + GATE_INFRA3_FLAGS(CLK_INFRA_SSPM_26M_SELF, "infra_sspm_26m_self", "f_f26m_ck", 3, CLK_IS_CRITICAL), + /* infra_sspm_32k_self is main clock in co-processor, should not be closed in Linux. */ + GATE_INFRA3_FLAGS(CLK_INFRA_SSPM_32K_SELF, "infra_sspm_32k_self", "f_f26m_ck", 4, CLK_IS_CRITICAL), GATE_INFRA3(CLK_INFRA_UFS_AXI, "infra_ufs_axi", "axi_sel", 5), GATE_INFRA3(CLK_INFRA_I2C6, "infra_i2c6", "i2c_sel", 6), GATE_INFRA3(CLK_INFRA_AP_MSDC0, "infra_ap_msdc0", "msdc50_hclk_sel", 7), diff --git a/drivers/clk/meson/clk-pll.c b/drivers/clk/meson/clk-pll.c index 8fef90bf962f..6fa7639a3050 100644 --- a/drivers/clk/meson/clk-pll.c +++ b/drivers/clk/meson/clk-pll.c @@ -367,9 +367,9 @@ static int meson_clk_pll_enable(struct clk_hw *hw) * 3. enable the lock detect module */ if (MESON_PARM_APPLICABLE(&pll->current_en)) { - usleep_range(10, 20); + udelay(10); meson_parm_write(clk->map, &pll->current_en, 1); - usleep_range(40, 50); + udelay(40); } if (MESON_PARM_APPLICABLE(&pll->l_detect)) { diff --git a/drivers/counter/Kconfig b/drivers/counter/Kconfig index bca21df51168..62962ae84b77 100644 --- a/drivers/counter/Kconfig +++ b/drivers/counter/Kconfig @@ -3,13 +3,6 @@ # Counter devices # -menuconfig COUNTER - tristate "Counter support" - help - This enables counter device support through the Generic Counter - interface. You only need to enable this, if you also want to enable - one or more of the counter device drivers below. - config I8254 tristate select COUNTER @@ -25,6 +18,13 @@ config I8254 If built as a module its name will be i8254. +menuconfig COUNTER + tristate "Counter support" + help + This enables counter device support through the Generic Counter + interface. You only need to enable this, if you also want to enable + one or more of the counter device drivers below. + if COUNTER config 104_QUAD_8 diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 81fba0dcbee9..9a1e194d5cf8 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -1012,8 +1012,8 @@ static int amd_pstate_update_status(const char *buf, size_t size) return 0; } -static ssize_t show_status(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) +static ssize_t status_show(struct device *dev, + struct device_attribute *attr, char *buf) { ssize_t ret; @@ -1024,7 +1024,7 @@ static ssize_t show_status(struct kobject *kobj, return ret; } -static ssize_t store_status(struct kobject *a, struct kobj_attribute *b, +static ssize_t status_store(struct device *a, struct device_attribute *b, const char *buf, size_t count) { char *p = memchr(buf, '\n', count); @@ -1043,7 +1043,7 @@ cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq); cpufreq_freq_attr_ro(amd_pstate_highest_perf); cpufreq_freq_attr_rw(energy_performance_preference); cpufreq_freq_attr_ro(energy_performance_available_preferences); -define_one_global_rw(status); +static DEVICE_ATTR_RW(status); static struct freq_attr *amd_pstate_attr[] = { &amd_pstate_max_freq, @@ -1062,7 +1062,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = { }; static struct attribute *pstate_global_attributes[] = { - &status.attr, + &dev_attr_status.attr, NULL }; diff --git a/drivers/cpuidle/cpuidle-psci-domain.c b/drivers/cpuidle/cpuidle-psci-domain.c index c2d6d9c3c930..b88af1262f1a 100644 --- a/drivers/cpuidle/cpuidle-psci-domain.c +++ b/drivers/cpuidle/cpuidle-psci-domain.c @@ -120,20 +120,6 @@ static void psci_pd_remove(void) } } -static bool psci_pd_try_set_osi_mode(void) -{ - int ret; - - if (!psci_has_osi_support()) - return false; - - ret = psci_set_osi_mode(true); - if (ret) - return false; - - return true; -} - static void psci_cpuidle_domain_sync_state(struct device *dev) { /* @@ -152,15 +138,12 @@ static int psci_cpuidle_domain_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct device_node *node; - bool use_osi; + bool use_osi = psci_has_osi_support(); int ret = 0, pd_count = 0; if (!np) return -ENODEV; - /* If OSI mode is supported, let's try to enable it. */ - use_osi = psci_pd_try_set_osi_mode(); - /* * Parse child nodes for the "#power-domain-cells" property and * initialize a genpd/genpd-of-provider pair when it's found. @@ -170,33 +153,37 @@ static int psci_cpuidle_domain_probe(struct platform_device *pdev) continue; ret = psci_pd_init(node, use_osi); - if (ret) - goto put_node; + if (ret) { + of_node_put(node); + goto exit; + } pd_count++; } /* Bail out if not using the hierarchical CPU topology. */ if (!pd_count) - goto no_pd; + return 0; /* Link genpd masters/subdomains to model the CPU topology. */ ret = dt_idle_pd_init_topology(np); if (ret) goto remove_pd; + /* let's try to enable OSI. */ + ret = psci_set_osi_mode(use_osi); + if (ret) + goto remove_pd; + pr_info("Initialized CPU PM domain topology using %s mode\n", use_osi ? "OSI" : "PC"); return 0; -put_node: - of_node_put(node); remove_pd: + dt_idle_pd_remove_topology(np); psci_pd_remove(); +exit: pr_err("failed to create CPU PM domains ret=%d\n", ret); -no_pd: - if (use_osi) - psci_set_osi_mode(false); return ret; } diff --git a/drivers/cpuidle/dt_idle_genpd.c b/drivers/cpuidle/dt_idle_genpd.c index b37165514d4e..1af63c189039 100644 --- a/drivers/cpuidle/dt_idle_genpd.c +++ b/drivers/cpuidle/dt_idle_genpd.c @@ -152,6 +152,30 @@ int dt_idle_pd_init_topology(struct device_node *np) return 0; } +int dt_idle_pd_remove_topology(struct device_node *np) +{ + struct device_node *node; + struct of_phandle_args child, parent; + int ret; + + for_each_child_of_node(np, node) { + if (of_parse_phandle_with_args(node, "power-domains", + "#power-domain-cells", 0, &parent)) + continue; + + child.np = node; + child.args_count = 0; + ret = of_genpd_remove_subdomain(&parent, &child); + of_node_put(parent.np); + if (ret) { + of_node_put(node); + return ret; + } + } + + return 0; +} + struct device *dt_idle_attach_cpu(int cpu, const char *name) { struct device *dev; diff --git a/drivers/cpuidle/dt_idle_genpd.h b/drivers/cpuidle/dt_idle_genpd.h index a95483d08a02..3be1f70f55b5 100644 --- a/drivers/cpuidle/dt_idle_genpd.h +++ b/drivers/cpuidle/dt_idle_genpd.h @@ -14,6 +14,8 @@ struct generic_pm_domain *dt_idle_pd_alloc(struct device_node *np, int dt_idle_pd_init_topology(struct device_node *np); +int dt_idle_pd_remove_topology(struct device_node *np); + struct device *dt_idle_attach_cpu(int cpu, const char *name); void dt_idle_detach_cpu(struct device *dev); @@ -36,6 +38,11 @@ static inline int dt_idle_pd_init_topology(struct device_node *np) return 0; } +static inline int dt_idle_pd_remove_topology(struct device_node *np) +{ + return 0; +} + static inline struct device *dt_idle_attach_cpu(int cpu, const char *name) { return NULL; diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index d6d067fbee97..ca60bb8114f2 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -121,6 +121,45 @@ static bool cxl_is_security_command(u16 opcode) return false; } +static void cxl_set_security_cmd_enabled(struct cxl_security_state *security, + u16 opcode) +{ + switch (opcode) { + case CXL_MBOX_OP_SANITIZE: + set_bit(CXL_SEC_ENABLED_SANITIZE, security->enabled_cmds); + break; + case CXL_MBOX_OP_SECURE_ERASE: + set_bit(CXL_SEC_ENABLED_SECURE_ERASE, + security->enabled_cmds); + break; + case CXL_MBOX_OP_GET_SECURITY_STATE: + set_bit(CXL_SEC_ENABLED_GET_SECURITY_STATE, + security->enabled_cmds); + break; + case CXL_MBOX_OP_SET_PASSPHRASE: + set_bit(CXL_SEC_ENABLED_SET_PASSPHRASE, + security->enabled_cmds); + break; + case CXL_MBOX_OP_DISABLE_PASSPHRASE: + set_bit(CXL_SEC_ENABLED_DISABLE_PASSPHRASE, + security->enabled_cmds); + break; + case CXL_MBOX_OP_UNLOCK: + set_bit(CXL_SEC_ENABLED_UNLOCK, security->enabled_cmds); + break; + case CXL_MBOX_OP_FREEZE_SECURITY: + set_bit(CXL_SEC_ENABLED_FREEZE_SECURITY, + security->enabled_cmds); + break; + case CXL_MBOX_OP_PASSPHRASE_SECURE_ERASE: + set_bit(CXL_SEC_ENABLED_PASSPHRASE_SECURE_ERASE, + security->enabled_cmds); + break; + default: + break; + } +} + static bool cxl_is_poison_command(u16 opcode) { #define CXL_MBOX_OP_POISON_CMDS 0x43 @@ -677,7 +716,8 @@ static void cxl_walk_cel(struct cxl_memdev_state *mds, size_t size, u8 *cel) u16 opcode = le16_to_cpu(cel_entry[i].opcode); struct cxl_mem_command *cmd = cxl_mem_find_command(opcode); - if (!cmd && !cxl_is_poison_command(opcode)) { + if (!cmd && (!cxl_is_poison_command(opcode) || + !cxl_is_security_command(opcode))) { dev_dbg(dev, "Opcode 0x%04x unsupported by driver\n", opcode); continue; @@ -689,6 +729,9 @@ static void cxl_walk_cel(struct cxl_memdev_state *mds, size_t size, u8 *cel) if (cxl_is_poison_command(opcode)) cxl_set_poison_cmd_enabled(&mds->poison, opcode); + if (cxl_is_security_command(opcode)) + cxl_set_security_cmd_enabled(&mds->security, opcode); + dev_dbg(dev, "Opcode 0x%04x enabled\n", opcode); } } diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index f99e7ec3cc40..14b547c07f54 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -477,9 +477,28 @@ static struct attribute_group cxl_memdev_pmem_attribute_group = { .attrs = cxl_memdev_pmem_attributes, }; +static umode_t cxl_memdev_security_visible(struct kobject *kobj, + struct attribute *a, int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct cxl_memdev *cxlmd = to_cxl_memdev(dev); + struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + + if (a == &dev_attr_security_sanitize.attr && + !test_bit(CXL_SEC_ENABLED_SANITIZE, mds->security.enabled_cmds)) + return 0; + + if (a == &dev_attr_security_erase.attr && + !test_bit(CXL_SEC_ENABLED_SECURE_ERASE, mds->security.enabled_cmds)) + return 0; + + return a->mode; +} + static struct attribute_group cxl_memdev_security_attribute_group = { .name = "security", .attrs = cxl_memdev_security_attributes, + .is_visible = cxl_memdev_security_visible, }; static const struct attribute_group *cxl_memdev_attribute_groups[] = { diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 499113328586..706f8a6d1ef4 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -244,6 +244,19 @@ enum poison_cmd_enabled_bits { CXL_POISON_ENABLED_MAX }; +/* Device enabled security commands */ +enum security_cmd_enabled_bits { + CXL_SEC_ENABLED_SANITIZE, + CXL_SEC_ENABLED_SECURE_ERASE, + CXL_SEC_ENABLED_GET_SECURITY_STATE, + CXL_SEC_ENABLED_SET_PASSPHRASE, + CXL_SEC_ENABLED_DISABLE_PASSPHRASE, + CXL_SEC_ENABLED_UNLOCK, + CXL_SEC_ENABLED_FREEZE_SECURITY, + CXL_SEC_ENABLED_PASSPHRASE_SECURE_ERASE, + CXL_SEC_ENABLED_MAX +}; + /** * struct cxl_poison_state - Driver poison state info * @@ -346,6 +359,7 @@ struct cxl_fw_state { * struct cxl_security_state - Device security state * * @state: state of last security operation + * @enabled_cmds: All security commands enabled in the CEL * @poll: polling for sanitization is enabled, device has no mbox irq support * @poll_tmo_secs: polling timeout * @poll_dwork: polling work item @@ -353,6 +367,7 @@ struct cxl_fw_state { */ struct cxl_security_state { unsigned long state; + DECLARE_BITMAP(enabled_cmds, CXL_SEC_ENABLED_MAX); bool poll; int poll_tmo_secs; struct delayed_work poll_dwork; @@ -434,6 +449,7 @@ struct cxl_dev_state { * @next_persistent_bytes: persistent capacity change pending device reset * @event: event log driver state * @poison: poison driver state info + * @security: security driver state info * @fw: firmware upload / activation state * @mbox_send: @dev specific transport for transmitting mailbox commands * diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 644c188d6a11..08fdd0e2ed1b 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -211,6 +211,7 @@ config FSL_DMA config FSL_EDMA tristate "Freescale eDMA engine support" depends on OF + depends on HAS_IOMEM select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help @@ -280,6 +281,7 @@ config IMX_SDMA config INTEL_IDMA64 tristate "Intel integrated DMA 64-bit support" + depends on HAS_IOMEM select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 5abbcc61c528..9a15f0d12c79 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -384,9 +384,7 @@ static void idxd_wq_disable_cleanup(struct idxd_wq *wq) wq->threshold = 0; wq->priority = 0; wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES; - clear_bit(WQ_FLAG_DEDICATED, &wq->flags); - clear_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags); - clear_bit(WQ_FLAG_ATS_DISABLE, &wq->flags); + wq->flags = 0; memset(wq->name, 0, WQ_NAME_SIZE); wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER; idxd_wq_set_max_batch_size(idxd->data->type, wq, WQ_DEFAULT_MAX_BATCH); diff --git a/drivers/dma/mcf-edma.c b/drivers/dma/mcf-edma.c index ebd8733f72ad..9413fad08a60 100644 --- a/drivers/dma/mcf-edma.c +++ b/drivers/dma/mcf-edma.c @@ -190,7 +190,13 @@ static int mcf_edma_probe(struct platform_device *pdev) return -EINVAL; } - chans = pdata->dma_channels; + if (!pdata->dma_channels) { + dev_info(&pdev->dev, "setting default channel number to 64"); + chans = 64; + } else { + chans = pdata->dma_channels; + } + len = sizeof(*mcf_edma) + sizeof(*mcf_chan) * chans; mcf_edma = devm_kzalloc(&pdev->dev, len, GFP_KERNEL); if (!mcf_edma) @@ -202,11 +208,6 @@ static int mcf_edma_probe(struct platform_device *pdev) mcf_edma->drvdata = &mcf_data; mcf_edma->big_endian = 1; - if (!mcf_edma->n_chans) { - dev_info(&pdev->dev, "setting default channel number to 64"); - mcf_edma->n_chans = 64; - } - mutex_init(&mcf_edma->fsl_edma_mutex); mcf_edma->membase = devm_platform_ioremap_resource(pdev, 0); diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c index 95a462a1f511..b6e0ac8314e5 100644 --- a/drivers/dma/owl-dma.c +++ b/drivers/dma/owl-dma.c @@ -192,7 +192,7 @@ struct owl_dma_pchan { }; /** - * struct owl_dma_pchan - Wrapper for DMA ENGINE channel + * struct owl_dma_vchan - Wrapper for DMA ENGINE channel * @vc: wrapped virtual channel * @pchan: the physical channel utilized by this channel * @txd: active transaction on this channel diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index b4731fe6bbc1..3cf0b38387ae 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -404,6 +404,12 @@ enum desc_status { */ BUSY, /* + * Pause was called while descriptor was BUSY. Due to hardware + * limitations, only termination is possible for descriptors + * that have been paused. + */ + PAUSED, + /* * Sitting on the channel work_list but xfer done * by PL330 core */ @@ -2041,7 +2047,7 @@ static inline void fill_queue(struct dma_pl330_chan *pch) list_for_each_entry(desc, &pch->work_list, node) { /* If already submitted */ - if (desc->status == BUSY) + if (desc->status == BUSY || desc->status == PAUSED) continue; ret = pl330_submit_req(pch->thread, desc); @@ -2326,6 +2332,7 @@ static int pl330_pause(struct dma_chan *chan) { struct dma_pl330_chan *pch = to_pchan(chan); struct pl330_dmac *pl330 = pch->dmac; + struct dma_pl330_desc *desc; unsigned long flags; pm_runtime_get_sync(pl330->ddma.dev); @@ -2335,6 +2342,10 @@ static int pl330_pause(struct dma_chan *chan) _stop(pch->thread); spin_unlock(&pl330->lock); + list_for_each_entry(desc, &pch->work_list, node) { + if (desc->status == BUSY) + desc->status = PAUSED; + } spin_unlock_irqrestore(&pch->lock, flags); pm_runtime_mark_last_busy(pl330->ddma.dev); pm_runtime_put_autosuspend(pl330->ddma.dev); @@ -2425,7 +2436,7 @@ pl330_tx_status(struct dma_chan *chan, dma_cookie_t cookie, else if (running && desc == running) transferred = pl330_get_current_xferred_count(pch, desc); - else if (desc->status == BUSY) + else if (desc->status == BUSY || desc->status == PAUSED) /* * Busy but not running means either just enqueued, * or finished and not yet marked done @@ -2442,6 +2453,9 @@ pl330_tx_status(struct dma_chan *chan, dma_cookie_t cookie, case DONE: ret = DMA_COMPLETE; break; + case PAUSED: + ret = DMA_PAUSED; + break; case PREP: case BUSY: ret = DMA_IN_PROGRESS; diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c index 93ee298d52b8..e0bfd129d563 100644 --- a/drivers/dma/xilinx/xdma.c +++ b/drivers/dma/xilinx/xdma.c @@ -668,6 +668,8 @@ static int xdma_set_vector_reg(struct xdma_device *xdev, u32 vec_tbl_start, val |= irq_start << shift; irq_start++; irq_num--; + if (!irq_num) + break; } /* write IRQ register */ @@ -715,7 +717,7 @@ static int xdma_irq_init(struct xdma_device *xdev) ret = request_irq(irq, xdma_channel_isr, 0, "xdma-c2h-channel", &xdev->c2h_chans[j]); if (ret) { - xdma_err(xdev, "H2C channel%d request irq%d failed: %d", + xdma_err(xdev, "C2H channel%d request irq%d failed: %d", j, irq, ret); goto failed_init_c2h; } @@ -892,7 +894,7 @@ static int xdma_probe(struct platform_device *pdev) } reg_base = devm_ioremap_resource(&pdev->dev, res); - if (!reg_base) { + if (IS_ERR(reg_base)) { xdma_err(xdev, "ioremap failed"); goto failed; } diff --git a/drivers/firmware/arm_scmi/mailbox.c b/drivers/firmware/arm_scmi/mailbox.c index 1efa5e9392c4..19246ed1f01f 100644 --- a/drivers/firmware/arm_scmi/mailbox.c +++ b/drivers/firmware/arm_scmi/mailbox.c @@ -166,8 +166,10 @@ static int mailbox_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, return -ENOMEM; shmem = of_parse_phandle(cdev->of_node, "shmem", idx); - if (!of_device_is_compatible(shmem, "arm,scmi-shmem")) + if (!of_device_is_compatible(shmem, "arm,scmi-shmem")) { + of_node_put(shmem); return -ENXIO; + } ret = of_address_to_resource(shmem, 0, &res); of_node_put(shmem); diff --git a/drivers/firmware/arm_scmi/raw_mode.c b/drivers/firmware/arm_scmi/raw_mode.c index 6971dcf72fb9..0493aa3c12bf 100644 --- a/drivers/firmware/arm_scmi/raw_mode.c +++ b/drivers/firmware/arm_scmi/raw_mode.c @@ -818,10 +818,13 @@ static ssize_t scmi_dbg_raw_mode_common_write(struct file *filp, * before sending it with a single RAW xfer. */ if (rd->tx_size < rd->tx_req_size) { - size_t cnt; + ssize_t cnt; cnt = simple_write_to_buffer(rd->tx.buf, rd->tx.len, ppos, buf, count); + if (cnt < 0) + return cnt; + rd->tx_size += cnt; if (cnt < count) return cnt; diff --git a/drivers/firmware/arm_scmi/smc.c b/drivers/firmware/arm_scmi/smc.c index 621c37efe3ec..c193516a254d 100644 --- a/drivers/firmware/arm_scmi/smc.c +++ b/drivers/firmware/arm_scmi/smc.c @@ -40,6 +40,7 @@ /** * struct scmi_smc - Structure representing a SCMI smc transport * + * @irq: An optional IRQ for completion * @cinfo: SCMI channel info * @shmem: Transmit/Receive shared memory area * @shmem_lock: Lock to protect access to Tx/Rx shared memory area. @@ -52,6 +53,7 @@ */ struct scmi_smc { + int irq; struct scmi_chan_info *cinfo; struct scmi_shared_mem __iomem *shmem; /* Protect access to shmem area */ @@ -127,7 +129,7 @@ static int smc_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, struct resource res; struct device_node *np; u32 func_id; - int ret, irq; + int ret; if (!tx) return -ENODEV; @@ -137,8 +139,10 @@ static int smc_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, return -ENOMEM; np = of_parse_phandle(cdev->of_node, "shmem", 0); - if (!of_device_is_compatible(np, "arm,scmi-shmem")) + if (!of_device_is_compatible(np, "arm,scmi-shmem")) { + of_node_put(np); return -ENXIO; + } ret = of_address_to_resource(np, 0, &res); of_node_put(np); @@ -167,11 +171,10 @@ static int smc_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, * completion of a message is signaled by an interrupt rather than by * the return of the SMC call. */ - irq = of_irq_get_byname(cdev->of_node, "a2p"); - if (irq > 0) { - ret = devm_request_irq(dev, irq, smc_msg_done_isr, - IRQF_NO_SUSPEND, - dev_name(dev), scmi_info); + scmi_info->irq = of_irq_get_byname(cdev->of_node, "a2p"); + if (scmi_info->irq > 0) { + ret = request_irq(scmi_info->irq, smc_msg_done_isr, + IRQF_NO_SUSPEND, dev_name(dev), scmi_info); if (ret) { dev_err(dev, "failed to setup SCMI smc irq\n"); return ret; @@ -193,6 +196,10 @@ static int smc_chan_free(int id, void *p, void *data) struct scmi_chan_info *cinfo = p; struct scmi_smc *scmi_info = cinfo->transport_info; + /* Ignore any possible further reception on the IRQ path */ + if (scmi_info->irq > 0) + free_irq(scmi_info->irq, scmi_info); + cinfo->transport_info = NULL; scmi_info->cinfo = NULL; diff --git a/drivers/firmware/smccc/soc_id.c b/drivers/firmware/smccc/soc_id.c index 890eb454599a..1990263fbba0 100644 --- a/drivers/firmware/smccc/soc_id.c +++ b/drivers/firmware/smccc/soc_id.c @@ -34,7 +34,6 @@ static struct soc_device_attribute *soc_dev_attr; static int __init smccc_soc_init(void) { - struct arm_smccc_res res; int soc_id_rev, soc_id_version; static char soc_id_str[20], soc_id_rev_str[12]; static char soc_id_jep106_id_str[12]; @@ -49,13 +48,13 @@ static int __init smccc_soc_init(void) } if (soc_id_version < 0) { - pr_err("ARCH_SOC_ID(0) returned error: %lx\n", res.a0); + pr_err("Invalid SoC Version: %x\n", soc_id_version); return -EINVAL; } soc_id_rev = arm_smccc_get_soc_id_revision(); if (soc_id_rev < 0) { - pr_err("ARCH_SOC_ID(1) returned error: %lx\n", res.a0); + pr_err("Invalid SoC Revision: %x\n", soc_id_rev); return -EINVAL; } diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index 8b49b0abacd5..f1f6f1c32987 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -429,6 +429,7 @@ static int gpio_sim_add_bank(struct fwnode_handle *swnode, struct device *dev) gc->set_config = gpio_sim_set_config; gc->to_irq = gpio_sim_to_irq; gc->free = gpio_sim_free; + gc->can_sleep = true; ret = devm_gpiochip_add_data(dev, gc, chip); if (ret) diff --git a/drivers/gpio/gpio-ws16c48.c b/drivers/gpio/gpio-ws16c48.c index e73885a4dc32..afb42a8e916f 100644 --- a/drivers/gpio/gpio-ws16c48.c +++ b/drivers/gpio/gpio-ws16c48.c @@ -18,7 +18,7 @@ #include <linux/spinlock.h> #include <linux/types.h> -#define WS16C48_EXTENT 10 +#define WS16C48_EXTENT 11 #define MAX_NUM_WS16C48 max_num_isa_dev(WS16C48_EXTENT) static unsigned int base[MAX_NUM_WS16C48]; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index a3b86b86dc47..6dc950c1b689 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1296,6 +1296,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, void amdgpu_device_pci_config_reset(struct amdgpu_device *adev); int amdgpu_device_pci_reset(struct amdgpu_device *adev); bool amdgpu_device_need_post(struct amdgpu_device *adev); +bool amdgpu_sg_display_supported(struct amdgpu_device *adev); bool amdgpu_device_pcie_dynamic_switching_supported(void); bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev); bool amdgpu_device_aspm_support_quirk(void); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 040f4cb6ab2d..fb78a8f47587 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -295,7 +295,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, if (!p->gang_size) { ret = -EINVAL; - goto free_partial_kdata; + goto free_all_kdata; } for (i = 0; i < p->gang_size; ++i) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index a2cdde0ca0a7..45e9d737e5b8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1459,6 +1459,32 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev) } /* + * On APUs with >= 64GB white flickering has been observed w/ SG enabled. + * Disable S/G on such systems until we have a proper fix. + * https://gitlab.freedesktop.org/drm/amd/-/issues/2354 + * https://gitlab.freedesktop.org/drm/amd/-/issues/2735 + */ +bool amdgpu_sg_display_supported(struct amdgpu_device *adev) +{ + switch (amdgpu_sg_display) { + case -1: + break; + case 0: + return false; + case 1: + return true; + default: + return false; + } + if ((totalram_pages() << (PAGE_SHIFT - 10)) + + (adev->gmc.real_vram_size / 1024) >= 64000000) { + DRM_WARN("Disabling S/G due to >=64GB RAM\n"); + return false; + } + return true; +} + +/* * Intel hosts such as Raptor Lake and Sapphire Rapids don't support dynamic * speed switching. Until we have confirmation from Intel that a specific host * supports it, it's safer that we keep it disabled for all. diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 3a7af59e83ca..0451533ddde4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -471,8 +471,12 @@ static void gfx_v11_0_check_fw_cp_gfx_shadow(struct amdgpu_device *adev) case IP_VERSION(11, 0, 3): if ((adev->gfx.me_fw_version >= 1505) && (adev->gfx.pfp_fw_version >= 1600) && - (adev->gfx.mec_fw_version >= 512)) - adev->gfx.cp_gfx_shadow = true; + (adev->gfx.mec_fw_version >= 512)) { + if (amdgpu_sriov_vf(adev)) + adev->gfx.cp_gfx_shadow = true; + else + adev->gfx.cp_gfx_shadow = false; + } break; default: adev->gfx.cp_gfx_shadow = false; diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c index e1a392bcea70..af5685f4cb34 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c @@ -137,14 +137,15 @@ static int psp_v13_0_wait_for_bootloader(struct psp_context *psp) int ret; int retry_loop; + /* Wait for bootloader to signify that it is ready having bit 31 of + * C2PMSG_35 set to 1. All other bits are expected to be cleared. + * If there is an error in processing command, bits[7:0] will be set. + * This is applicable for PSP v13.0.6 and newer. + */ for (retry_loop = 0; retry_loop < 10; retry_loop++) { - /* Wait for bootloader to signify that is - ready having bit 31 of C2PMSG_35 set to 1 */ - ret = psp_wait_for(psp, - SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35), - 0x80000000, - 0x80000000, - false); + ret = psp_wait_for( + psp, SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35), + 0x80000000, 0xffffffff, false); if (ret == 0) return 0; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 49f40d9f16e8..f5a6f562e2a8 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -1543,11 +1543,7 @@ static bool kfd_ignore_crat(void) if (ignore_crat) return true; -#ifndef KFD_SUPPORT_IOMMU_V2 ret = true; -#else - ret = false; -#endif return ret; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 0b3dc754e06b..a53e0757fe64 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -194,11 +194,6 @@ static void kfd_device_info_init(struct kfd_dev *kfd, kfd_device_info_set_event_interrupt_class(kfd); - /* Raven */ - if (gc_version == IP_VERSION(9, 1, 0) || - gc_version == IP_VERSION(9, 2, 2)) - kfd->device_info.needs_iommu_device = true; - if (gc_version < IP_VERSION(11, 0, 0)) { /* Navi2x+, Navi1x+ */ if (gc_version == IP_VERSION(10, 3, 6)) @@ -233,10 +228,6 @@ static void kfd_device_info_init(struct kfd_dev *kfd, asic_type != CHIP_TONGA) kfd->device_info.supports_cwsr = true; - if (asic_type == CHIP_KAVERI || - asic_type == CHIP_CARRIZO) - kfd->device_info.needs_iommu_device = true; - if (asic_type != CHIP_HAWAII && !vf) kfd->device_info.needs_pci_atomics = true; } @@ -249,7 +240,6 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf) uint32_t gfx_target_version = 0; switch (adev->asic_type) { -#ifdef KFD_SUPPORT_IOMMU_V2 #ifdef CONFIG_DRM_AMDGPU_CIK case CHIP_KAVERI: gfx_target_version = 70000; @@ -262,7 +252,6 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf) if (!vf) f2g = &gfx_v8_kfd2kgd; break; -#endif #ifdef CONFIG_DRM_AMDGPU_CIK case CHIP_HAWAII: gfx_target_version = 70001; @@ -298,7 +287,6 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf) gfx_target_version = 90000; f2g = &gfx_v9_kfd2kgd; break; -#ifdef KFD_SUPPORT_IOMMU_V2 /* Raven */ case IP_VERSION(9, 1, 0): case IP_VERSION(9, 2, 2): @@ -306,7 +294,6 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf) if (!vf) f2g = &gfx_v9_kfd2kgd; break; -#endif /* Vega12 */ case IP_VERSION(9, 2, 1): gfx_target_version = 90004; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 2df153828ff4..01192f5abe46 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -2538,18 +2538,12 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_node *dev) } switch (dev->adev->asic_type) { - case CHIP_CARRIZO: - device_queue_manager_init_vi(&dqm->asic_ops); - break; - case CHIP_KAVERI: - device_queue_manager_init_cik(&dqm->asic_ops); - break; - case CHIP_HAWAII: device_queue_manager_init_cik_hawaii(&dqm->asic_ops); break; + case CHIP_CARRIZO: case CHIP_TONGA: case CHIP_FIJI: case CHIP_POLARIS10: diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 0fa739fd6a9c..e5554a36e8c8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1638,9 +1638,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) } break; } - if (init_data.flags.gpu_vm_support && - (amdgpu_sg_display == 0)) - init_data.flags.gpu_vm_support = false; + if (init_data.flags.gpu_vm_support) + init_data.flags.gpu_vm_support = amdgpu_sg_display_supported(adev); if (init_data.flags.gpu_vm_support) adev->mode_info.gpu_vm_support = true; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 9bc86deac9e8..b885c39bd16b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -1320,7 +1320,7 @@ int compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, if (computed_streams[i]) continue; - if (!res_pool->funcs->remove_stream_from_ctx || + if (res_pool->funcs->remove_stream_from_ctx && res_pool->funcs->remove_stream_from_ctx(stream->ctx->dc, dc_state, stream) != DC_OK) return -EINVAL; diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 20d4d08a6a2f..6966420dfbac 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -777,7 +777,8 @@ void dce110_edp_wait_for_hpd_ready( dal_gpio_destroy_irq(&hpd); /* ensure that the panel is detected */ - ASSERT(edp_hpd_high); + if (!edp_hpd_high) + DC_LOG_DC("%s: wait timed out!\n", __func__); } void dce110_edp_power_control( diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c index e5b7ef7422b8..50dc83404644 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c @@ -357,8 +357,11 @@ void dpp3_set_cursor_attributes( int cur_rom_en = 0; if (color_format == CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA || - color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA) - cur_rom_en = 1; + color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA) { + if (cursor_attributes->attribute_flags.bits.ENABLE_CURSOR_DEGAMMA) { + cur_rom_en = 1; + } + } REG_UPDATE_3(CURSOR0_CONTROL, CUR0_MODE, color_format, diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index ce41a8309582..222af2fae745 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1581,9 +1581,9 @@ static int smu_disable_dpms(struct smu_context *smu) /* * For SMU 13.0.4/11, PMFW will handle the features disablement properly - * for gpu reset case. Driver involvement is unnecessary. + * for gpu reset and S0i3 cases. Driver involvement is unnecessary. */ - if (amdgpu_in_reset(adev)) { + if (amdgpu_in_reset(adev) || adev->in_s0ix) { switch (adev->ip_versions[MP1_HWIP][0]) { case IP_VERSION(13, 0, 4): case IP_VERSION(13, 0, 11): diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 3d188616ba24..fddcd834bcec 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -331,11 +331,13 @@ static int smu_v13_0_0_check_powerplay_table(struct smu_context *smu) struct smu_13_0_0_powerplay_table *powerplay_table = table_context->power_play_table; struct smu_baco_context *smu_baco = &smu->smu_baco; +#if 0 PPTable_t *pptable = smu->smu_table.driver_pptable; const OverDriveLimits_t * const overdrive_upperlimits = &pptable->SkuTable.OverDriveLimitsBasicMax; const OverDriveLimits_t * const overdrive_lowerlimits = &pptable->SkuTable.OverDriveLimitsMin; +#endif if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_HARDWAREDC) smu->dc_controlled_by_gpio = true; @@ -347,18 +349,27 @@ static int smu_v13_0_0_check_powerplay_table(struct smu_context *smu) if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_MACO) smu_baco->maco_support = true; + /* + * We are in the transition to a new OD mechanism. + * Disable the OD feature support for SMU13 temporarily. + * TODO: get this reverted when new OD mechanism online + */ +#if 0 if (!overdrive_lowerlimits->FeatureCtrlMask || !overdrive_upperlimits->FeatureCtrlMask) smu->od_enabled = false; - table_context->thermal_controller_type = - powerplay_table->thermal_controller_type; - /* * Instead of having its own buffer space and get overdrive_table copied, * smu->od_settings just points to the actual overdrive_table */ smu->od_settings = &powerplay_table->overdrive_table; +#else + smu->od_enabled = false; +#endif + + table_context->thermal_controller_type = + powerplay_table->thermal_controller_type; return 0; } @@ -1140,7 +1151,6 @@ static int smu_v13_0_0_print_clk_levels(struct smu_context *smu, (OverDriveTableExternal_t *)smu->smu_table.overdrive_table; struct smu_13_0_dpm_table *single_dpm_table; struct smu_13_0_pcie_table *pcie_table; - const int link_width[] = {0, 1, 2, 4, 8, 12, 16}; uint32_t gen_speed, lane_width; int i, curr_freq, size = 0; int32_t min_value, max_value; @@ -1256,7 +1266,7 @@ static int smu_v13_0_0_print_clk_levels(struct smu_context *smu, (pcie_table->pcie_lane[i] == 6) ? "x16" : "", pcie_table->clk_freq[i], (gen_speed == DECODE_GEN_SPEED(pcie_table->pcie_gen[i])) && - (lane_width == DECODE_LANE_WIDTH(link_width[pcie_table->pcie_lane[i]])) ? + (lane_width == DECODE_LANE_WIDTH(pcie_table->pcie_lane[i])) ? "*" : ""); break; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 1ac552142763..fe4ee2daa5d8 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -1993,9 +1993,8 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table gpu_metrics->average_socket_power = SMUQ10_TO_UINT(metrics->SocketPower); - /* Energy is reported in 15.625mJ units */ - gpu_metrics->energy_accumulator = - SMUQ10_TO_UINT(metrics->SocketEnergyAcc); + /* Energy counter reported in 15.259uJ (2^-16) units */ + gpu_metrics->energy_accumulator = metrics->SocketEnergyAcc; gpu_metrics->current_gfxclk = SMUQ10_TO_UINT(metrics->GfxclkFrequency[xcc0]); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index b1f0937ccade..62f2886ab4df 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -323,10 +323,12 @@ static int smu_v13_0_7_check_powerplay_table(struct smu_context *smu) struct smu_baco_context *smu_baco = &smu->smu_baco; PPTable_t *smc_pptable = table_context->driver_pptable; BoardTable_t *BoardTable = &smc_pptable->BoardTable; +#if 0 const OverDriveLimits_t * const overdrive_upperlimits = &smc_pptable->SkuTable.OverDriveLimitsBasicMax; const OverDriveLimits_t * const overdrive_lowerlimits = &smc_pptable->SkuTable.OverDriveLimitsMin; +#endif if (powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_HARDWAREDC) smu->dc_controlled_by_gpio = true; @@ -338,18 +340,22 @@ static int smu_v13_0_7_check_powerplay_table(struct smu_context *smu) if (smu_baco->platform_support && (BoardTable->HsrEnabled || BoardTable->VddqOffEnabled)) smu_baco->maco_support = true; +#if 0 if (!overdrive_lowerlimits->FeatureCtrlMask || !overdrive_upperlimits->FeatureCtrlMask) smu->od_enabled = false; - table_context->thermal_controller_type = - powerplay_table->thermal_controller_type; - /* * Instead of having its own buffer space and get overdrive_table copied, * smu->od_settings just points to the actual overdrive_table */ smu->od_settings = &powerplay_table->overdrive_table; +#else + smu->od_enabled = false; +#endif + + table_context->thermal_controller_type = + powerplay_table->thermal_controller_type; return 0; } diff --git a/drivers/gpu/drm/bridge/ite-it6505.c b/drivers/gpu/drm/bridge/ite-it6505.c index 504d51c42f79..aadb396508c5 100644 --- a/drivers/gpu/drm/bridge/ite-it6505.c +++ b/drivers/gpu/drm/bridge/ite-it6505.c @@ -2517,9 +2517,11 @@ static irqreturn_t it6505_int_threaded_handler(int unused, void *data) }; int int_status[3], i; - if (it6505->enable_drv_hold || pm_runtime_get_if_in_use(dev) <= 0) + if (it6505->enable_drv_hold || !it6505->powered) return IRQ_HANDLED; + pm_runtime_get_sync(dev); + int_status[0] = it6505_read(it6505, INT_STATUS_01); int_status[1] = it6505_read(it6505, INT_STATUS_02); int_status[2] = it6505_read(it6505, INT_STATUS_03); diff --git a/drivers/gpu/drm/bridge/lontium-lt9611.c b/drivers/gpu/drm/bridge/lontium-lt9611.c index 5163e5224aad..9663601ce098 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611.c @@ -774,9 +774,7 @@ static struct mipi_dsi_device *lt9611_attach_dsi(struct lt9611 *lt9611, dsi->lanes = 4; dsi->format = MIPI_DSI_FMT_RGB888; dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE | - MIPI_DSI_MODE_VIDEO_HSE | MIPI_DSI_MODE_VIDEO_NO_HSA | - MIPI_DSI_MODE_VIDEO_NO_HFP | MIPI_DSI_MODE_VIDEO_NO_HBP | - MIPI_DSI_MODE_NO_EOT_PACKET; + MIPI_DSI_MODE_VIDEO_HSE; ret = devm_mipi_dsi_attach(dev, dsi); if (ret < 0) { diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 4ea6507a77e5..baaf0e0feb06 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -623,7 +623,13 @@ int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct int ret; if (obj->import_attach) { + /* Reset both vm_ops and vm_private_data, so we don't end up with + * vm_ops pointing to our implementation if the dma-buf backend + * doesn't set those fields. + */ vma->vm_private_data = NULL; + vma->vm_ops = NULL; + ret = dma_buf_mmap(obj->dma_buf, vma, 0); /* Drop the reference drm_gem_mmap_obj() acquired.*/ diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 23857cc08eca..2702ad4c26c8 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -165,14 +165,60 @@ static u32 preparser_disable(bool state) return MI_ARB_CHECK | 1 << 8 | state; } -u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg) +static i915_reg_t gen12_get_aux_inv_reg(struct intel_engine_cs *engine) { - u32 gsi_offset = gt->uncore->gsi_offset; + switch (engine->id) { + case RCS0: + return GEN12_CCS_AUX_INV; + case BCS0: + return GEN12_BCS0_AUX_INV; + case VCS0: + return GEN12_VD0_AUX_INV; + case VCS2: + return GEN12_VD2_AUX_INV; + case VECS0: + return GEN12_VE0_AUX_INV; + case CCS0: + return GEN12_CCS0_AUX_INV; + default: + return INVALID_MMIO_REG; + } +} + +static bool gen12_needs_ccs_aux_inv(struct intel_engine_cs *engine) +{ + i915_reg_t reg = gen12_get_aux_inv_reg(engine); + + if (IS_PONTEVECCHIO(engine->i915)) + return false; + + /* + * So far platforms supported by i915 having flat ccs do not require + * AUX invalidation. Check also whether the engine requires it. + */ + return i915_mmio_reg_valid(reg) && !HAS_FLAT_CCS(engine->i915); +} + +u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs) +{ + i915_reg_t inv_reg = gen12_get_aux_inv_reg(engine); + u32 gsi_offset = engine->gt->uncore->gsi_offset; + + if (!gen12_needs_ccs_aux_inv(engine)) + return cs; *cs++ = MI_LOAD_REGISTER_IMM(1) | MI_LRI_MMIO_REMAP_EN; *cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset; *cs++ = AUX_INV; - *cs++ = MI_NOOP; + + *cs++ = MI_SEMAPHORE_WAIT_TOKEN | + MI_SEMAPHORE_REGISTER_POLL | + MI_SEMAPHORE_POLL | + MI_SEMAPHORE_SAD_EQ_SDD; + *cs++ = 0; + *cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset; + *cs++ = 0; + *cs++ = 0; return cs; } @@ -202,8 +248,13 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) { struct intel_engine_cs *engine = rq->engine; - if (mode & EMIT_FLUSH) { - u32 flags = 0; + /* + * On Aux CCS platforms the invalidation of the Aux + * table requires quiescing memory traffic beforehand + */ + if (mode & EMIT_FLUSH || gen12_needs_ccs_aux_inv(engine)) { + u32 bit_group_0 = 0; + u32 bit_group_1 = 0; int err; u32 *cs; @@ -211,32 +262,40 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) if (err) return err; - flags |= PIPE_CONTROL_TILE_CACHE_FLUSH; - flags |= PIPE_CONTROL_FLUSH_L3; - flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; - flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; + bit_group_0 |= PIPE_CONTROL0_HDC_PIPELINE_FLUSH; + + /* + * When required, in MTL and beyond platforms we + * need to set the CCS_FLUSH bit in the pipe control + */ + if (GRAPHICS_VER_FULL(rq->i915) >= IP_VER(12, 70)) + bit_group_0 |= PIPE_CONTROL_CCS_FLUSH; + + bit_group_1 |= PIPE_CONTROL_TILE_CACHE_FLUSH; + bit_group_1 |= PIPE_CONTROL_FLUSH_L3; + bit_group_1 |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; + bit_group_1 |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; /* Wa_1409600907:tgl,adl-p */ - flags |= PIPE_CONTROL_DEPTH_STALL; - flags |= PIPE_CONTROL_DC_FLUSH_ENABLE; - flags |= PIPE_CONTROL_FLUSH_ENABLE; + bit_group_1 |= PIPE_CONTROL_DEPTH_STALL; + bit_group_1 |= PIPE_CONTROL_DC_FLUSH_ENABLE; + bit_group_1 |= PIPE_CONTROL_FLUSH_ENABLE; - flags |= PIPE_CONTROL_STORE_DATA_INDEX; - flags |= PIPE_CONTROL_QW_WRITE; + bit_group_1 |= PIPE_CONTROL_STORE_DATA_INDEX; + bit_group_1 |= PIPE_CONTROL_QW_WRITE; - flags |= PIPE_CONTROL_CS_STALL; + bit_group_1 |= PIPE_CONTROL_CS_STALL; if (!HAS_3D_PIPELINE(engine->i915)) - flags &= ~PIPE_CONTROL_3D_ARCH_FLAGS; + bit_group_1 &= ~PIPE_CONTROL_3D_ARCH_FLAGS; else if (engine->class == COMPUTE_CLASS) - flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS; + bit_group_1 &= ~PIPE_CONTROL_3D_ENGINE_FLAGS; cs = intel_ring_begin(rq, 6); if (IS_ERR(cs)) return PTR_ERR(cs); - cs = gen12_emit_pipe_control(cs, - PIPE_CONTROL0_HDC_PIPELINE_FLUSH, - flags, LRC_PPHWSP_SCRATCH_ADDR); + cs = gen12_emit_pipe_control(cs, bit_group_0, bit_group_1, + LRC_PPHWSP_SCRATCH_ADDR); intel_ring_advance(rq, cs); } @@ -267,10 +326,9 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) else if (engine->class == COMPUTE_CLASS) flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS; - if (!HAS_FLAT_CCS(rq->engine->i915)) - count = 8 + 4; - else - count = 8; + count = 8; + if (gen12_needs_ccs_aux_inv(rq->engine)) + count += 8; cs = intel_ring_begin(rq, count); if (IS_ERR(cs)) @@ -285,11 +343,7 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR); - if (!HAS_FLAT_CCS(rq->engine->i915)) { - /* hsdes: 1809175790 */ - cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_GFX_CCS_AUX_NV); - } + cs = gen12_emit_aux_table_inv(engine, cs); *cs++ = preparser_disable(false); intel_ring_advance(rq, cs); @@ -300,21 +354,14 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) { - intel_engine_mask_t aux_inv = 0; - u32 cmd, *cs; + u32 cmd = 4; + u32 *cs; - cmd = 4; if (mode & EMIT_INVALIDATE) { cmd += 2; - if (!HAS_FLAT_CCS(rq->engine->i915) && - (rq->engine->class == VIDEO_DECODE_CLASS || - rq->engine->class == VIDEO_ENHANCEMENT_CLASS)) { - aux_inv = rq->engine->mask & - ~GENMASK(_BCS(I915_MAX_BCS - 1), BCS0); - if (aux_inv) - cmd += 4; - } + if (gen12_needs_ccs_aux_inv(rq->engine)) + cmd += 8; } cs = intel_ring_begin(rq, cmd); @@ -338,6 +385,10 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) cmd |= MI_INVALIDATE_TLB; if (rq->engine->class == VIDEO_DECODE_CLASS) cmd |= MI_INVALIDATE_BSD; + + if (gen12_needs_ccs_aux_inv(rq->engine) && + rq->engine->class == COPY_ENGINE_CLASS) + cmd |= MI_FLUSH_DW_CCS; } *cs++ = cmd; @@ -345,14 +396,7 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) *cs++ = 0; /* upper addr */ *cs++ = 0; /* value */ - if (aux_inv) { /* hsdes: 1809175790 */ - if (rq->engine->class == VIDEO_DECODE_CLASS) - cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_VD0_AUX_NV); - else - cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_VE0_AUX_NV); - } + cs = gen12_emit_aux_table_inv(rq->engine, cs); if (mode & EMIT_INVALIDATE) *cs++ = preparser_disable(false); diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h index 655e5c00ddc2..867ba697aceb 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h @@ -13,6 +13,7 @@ #include "intel_gt_regs.h" #include "intel_gpu_commands.h" +struct intel_engine_cs; struct intel_gt; struct i915_request; @@ -46,28 +47,32 @@ u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); -u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg); +u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs); static inline u32 * -__gen8_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset) +__gen8_emit_pipe_control(u32 *batch, u32 bit_group_0, + u32 bit_group_1, u32 offset) { memset(batch, 0, 6 * sizeof(u32)); - batch[0] = GFX_OP_PIPE_CONTROL(6) | flags0; - batch[1] = flags1; + batch[0] = GFX_OP_PIPE_CONTROL(6) | bit_group_0; + batch[1] = bit_group_1; batch[2] = offset; return batch + 6; } -static inline u32 *gen8_emit_pipe_control(u32 *batch, u32 flags, u32 offset) +static inline u32 *gen8_emit_pipe_control(u32 *batch, + u32 bit_group_1, u32 offset) { - return __gen8_emit_pipe_control(batch, 0, flags, offset); + return __gen8_emit_pipe_control(batch, 0, bit_group_1, offset); } -static inline u32 *gen12_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset) +static inline u32 *gen12_emit_pipe_control(u32 *batch, u32 bit_group_0, + u32 bit_group_1, u32 offset) { - return __gen8_emit_pipe_control(batch, flags0, flags1, offset); + return __gen8_emit_pipe_control(batch, bit_group_0, + bit_group_1, offset); } static inline u32 * diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h index 5d143e2a8db0..2bd8d98d2110 100644 --- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h +++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h @@ -121,6 +121,7 @@ #define MI_SEMAPHORE_TARGET(engine) ((engine)<<15) #define MI_SEMAPHORE_WAIT MI_INSTR(0x1c, 2) /* GEN8+ */ #define MI_SEMAPHORE_WAIT_TOKEN MI_INSTR(0x1c, 3) /* GEN12+ */ +#define MI_SEMAPHORE_REGISTER_POLL (1 << 16) #define MI_SEMAPHORE_POLL (1 << 15) #define MI_SEMAPHORE_SAD_GT_SDD (0 << 12) #define MI_SEMAPHORE_SAD_GTE_SDD (1 << 12) @@ -299,6 +300,7 @@ #define PIPE_CONTROL_QW_WRITE (1<<14) #define PIPE_CONTROL_POST_SYNC_OP_MASK (3<<14) #define PIPE_CONTROL_DEPTH_STALL (1<<13) +#define PIPE_CONTROL_CCS_FLUSH (1<<13) /* MTL+ */ #define PIPE_CONTROL_WRITE_FLUSH (1<<12) #define PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH (1<<12) /* gen6+ */ #define PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE (1<<11) /* MBZ on ILK */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index 718cb2c80f79..2cdfb2f713d0 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -332,9 +332,11 @@ #define GEN8_PRIVATE_PAT_HI _MMIO(0x40e0 + 4) #define GEN10_PAT_INDEX(index) _MMIO(0x40e0 + (index) * 4) #define BSD_HWS_PGA_GEN7 _MMIO(0x4180) -#define GEN12_GFX_CCS_AUX_NV _MMIO(0x4208) -#define GEN12_VD0_AUX_NV _MMIO(0x4218) -#define GEN12_VD1_AUX_NV _MMIO(0x4228) + +#define GEN12_CCS_AUX_INV _MMIO(0x4208) +#define GEN12_VD0_AUX_INV _MMIO(0x4218) +#define GEN12_VE0_AUX_INV _MMIO(0x4238) +#define GEN12_BCS0_AUX_INV _MMIO(0x4248) #define GEN8_RTCR _MMIO(0x4260) #define GEN8_M1TCR _MMIO(0x4264) @@ -342,14 +344,12 @@ #define GEN8_BTCR _MMIO(0x426c) #define GEN8_VTCR _MMIO(0x4270) -#define GEN12_VD2_AUX_NV _MMIO(0x4298) -#define GEN12_VD3_AUX_NV _MMIO(0x42a8) -#define GEN12_VE0_AUX_NV _MMIO(0x4238) - #define BLT_HWS_PGA_GEN7 _MMIO(0x4280) -#define GEN12_VE1_AUX_NV _MMIO(0x42b8) +#define GEN12_VD2_AUX_INV _MMIO(0x4298) +#define GEN12_CCS0_AUX_INV _MMIO(0x42c8) #define AUX_INV REG_BIT(0) + #define VEBOX_HWS_PGA_GEN7 _MMIO(0x4380) #define GEN12_AUX_ERR_DBG _MMIO(0x43f4) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index a4ec20aaafe2..9477c2422321 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1364,10 +1364,7 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs) IS_DG2_G11(ce->engine->i915)) cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0); - /* hsdes: 1809175790 */ - if (!HAS_FLAT_CCS(ce->engine->i915)) - cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_GFX_CCS_AUX_NV); + cs = gen12_emit_aux_table_inv(ce->engine, cs); /* Wa_16014892111 */ if (IS_MTL_GRAPHICS_STEP(ce->engine->i915, M, STEP_A0, STEP_B0) || @@ -1392,17 +1389,7 @@ gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs) PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0); - /* hsdes: 1809175790 */ - if (!HAS_FLAT_CCS(ce->engine->i915)) { - if (ce->engine->class == VIDEO_DECODE_CLASS) - cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_VD0_AUX_NV); - else if (ce->engine->class == VIDEO_ENHANCEMENT_CLASS) - cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_VE0_AUX_NV); - } - - return cs; + return gen12_emit_aux_table_inv(ce->engine, cs); } static void diff --git a/drivers/gpu/drm/i915/gvt/edid.c b/drivers/gpu/drm/i915/gvt/edid.c index 2a0438f12a14..af9afdb53c7f 100644 --- a/drivers/gpu/drm/i915/gvt/edid.c +++ b/drivers/gpu/drm/i915/gvt/edid.c @@ -491,7 +491,7 @@ void intel_gvt_i2c_handle_aux_ch_write(struct intel_vgpu *vgpu, return; } - msg_length = REG_FIELD_GET(DP_AUX_CH_CTL_MESSAGE_SIZE_MASK, reg); + msg_length = REG_FIELD_GET(DP_AUX_CH_CTL_MESSAGE_SIZE_MASK, value); // check the msg in DATA register. msg = vgpu_vreg(vgpu, offset + 4); diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index 8ef93889061a..5ec293011d99 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -449,8 +449,11 @@ int i915_active_add_request(struct i915_active *ref, struct i915_request *rq) } } while (unlikely(is_barrier(active))); - if (!__i915_active_fence_set(active, fence)) + fence = __i915_active_fence_set(active, fence); + if (!fence) __i915_active_acquire(ref); + else + dma_fence_put(fence); out: i915_active_release(ref); @@ -469,13 +472,9 @@ __i915_active_set_fence(struct i915_active *ref, return NULL; } - rcu_read_lock(); prev = __i915_active_fence_set(active, fence); - if (prev) - prev = dma_fence_get_rcu(prev); - else + if (!prev) __i915_active_acquire(ref); - rcu_read_unlock(); return prev; } @@ -1019,10 +1018,11 @@ void i915_request_add_active_barriers(struct i915_request *rq) * * Records the new @fence as the last active fence along its timeline in * this active tracker, moving the tracking callbacks from the previous - * fence onto this one. Returns the previous fence (if not already completed), - * which the caller must ensure is executed before the new fence. To ensure - * that the order of fences within the timeline of the i915_active_fence is - * understood, it should be locked by the caller. + * fence onto this one. Gets and returns a reference to the previous fence + * (if not already completed), which the caller must put after making sure + * that it is executed before the new fence. To ensure that the order of + * fences within the timeline of the i915_active_fence is understood, it + * should be locked by the caller. */ struct dma_fence * __i915_active_fence_set(struct i915_active_fence *active, @@ -1031,7 +1031,23 @@ __i915_active_fence_set(struct i915_active_fence *active, struct dma_fence *prev; unsigned long flags; - if (fence == rcu_access_pointer(active->fence)) + /* + * In case of fences embedded in i915_requests, their memory is + * SLAB_FAILSAFE_BY_RCU, then it can be reused right after release + * by new requests. Then, there is a risk of passing back a pointer + * to a new, completely unrelated fence that reuses the same memory + * while tracked under a different active tracker. Combined with i915 + * perf open/close operations that build await dependencies between + * engine kernel context requests and user requests from different + * timelines, this can lead to dependency loops and infinite waits. + * + * As a countermeasure, we try to get a reference to the active->fence + * first, so if we succeed and pass it back to our user then it is not + * released and potentially reused by an unrelated request before the + * user has a chance to set up an await dependency on it. + */ + prev = i915_active_fence_get(active); + if (fence == prev) return fence; GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)); @@ -1040,27 +1056,56 @@ __i915_active_fence_set(struct i915_active_fence *active, * Consider that we have two threads arriving (A and B), with * C already resident as the active->fence. * - * A does the xchg first, and so it sees C or NULL depending - * on the timing of the interrupt handler. If it is NULL, the - * previous fence must have been signaled and we know that - * we are first on the timeline. If it is still present, - * we acquire the lock on that fence and serialise with the interrupt - * handler, in the process removing it from any future interrupt - * callback. A will then wait on C before executing (if present). - * - * As B is second, it sees A as the previous fence and so waits for - * it to complete its transition and takes over the occupancy for - * itself -- remembering that it needs to wait on A before executing. + * Both A and B have got a reference to C or NULL, depending on the + * timing of the interrupt handler. Let's assume that if A has got C + * then it has locked C first (before B). * * Note the strong ordering of the timeline also provides consistent * nesting rules for the fence->lock; the inner lock is always the * older lock. */ spin_lock_irqsave(fence->lock, flags); - prev = xchg(__active_fence_slot(active), fence); - if (prev) { - GEM_BUG_ON(prev == fence); + if (prev) spin_lock_nested(prev->lock, SINGLE_DEPTH_NESTING); + + /* + * A does the cmpxchg first, and so it sees C or NULL, as before, or + * something else, depending on the timing of other threads and/or + * interrupt handler. If not the same as before then A unlocks C if + * applicable and retries, starting from an attempt to get a new + * active->fence. Meanwhile, B follows the same path as A. + * Once A succeeds with cmpxch, B fails again, retires, gets A from + * active->fence, locks it as soon as A completes, and possibly + * succeeds with cmpxchg. + */ + while (cmpxchg(__active_fence_slot(active), prev, fence) != prev) { + if (prev) { + spin_unlock(prev->lock); + dma_fence_put(prev); + } + spin_unlock_irqrestore(fence->lock, flags); + + prev = i915_active_fence_get(active); + GEM_BUG_ON(prev == fence); + + spin_lock_irqsave(fence->lock, flags); + if (prev) + spin_lock_nested(prev->lock, SINGLE_DEPTH_NESTING); + } + + /* + * If prev is NULL then the previous fence must have been signaled + * and we know that we are first on the timeline. If it is still + * present then, having the lock on that fence already acquired, we + * serialise with the interrupt handler, in the process of removing it + * from any future interrupt callback. A will then wait on C before + * executing (if present). + * + * As B is second, it sees A as the previous fence and so waits for + * it to complete its transition and takes over the occupancy for + * itself -- remembering that it needs to wait on A before executing. + */ + if (prev) { __list_del_entry(&active->cb.node); spin_unlock(prev->lock); /* serialise with prev->cb_list */ } @@ -1077,11 +1122,7 @@ int i915_active_fence_set(struct i915_active_fence *active, int err = 0; /* Must maintain timeline ordering wrt previous active requests */ - rcu_read_lock(); fence = __i915_active_fence_set(active, &rq->fence); - if (fence) /* but the previous fence may not belong to that timeline! */ - fence = dma_fence_get_rcu(fence); - rcu_read_unlock(); if (fence) { err = i915_request_await_dma_fence(rq, fence); dma_fence_put(fence); diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 894068bb37b6..833b73edefdb 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1661,6 +1661,11 @@ __i915_request_ensure_parallel_ordering(struct i915_request *rq, request_to_parent(rq)->parallel.last_rq = i915_request_get(rq); + /* + * Users have to put a reference potentially got by + * __i915_active_fence_set() to the returned request + * when no longer needed + */ return to_request(__i915_active_fence_set(&timeline->last_request, &rq->fence)); } @@ -1707,6 +1712,10 @@ __i915_request_ensure_ordering(struct i915_request *rq, 0); } + /* + * Users have to put the reference to prev potentially got + * by __i915_active_fence_set() when no longer needed + */ return prev; } @@ -1760,6 +1769,8 @@ __i915_request_add_to_timeline(struct i915_request *rq) prev = __i915_request_ensure_ordering(rq, timeline); else prev = __i915_request_ensure_parallel_ordering(rq, timeline); + if (prev) + i915_request_put(prev); /* * Make sure that no request gazumped us - if it was allocated after diff --git a/drivers/gpu/drm/imx/ipuv3/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3/ipuv3-crtc.c index 5f26090b0c98..89585b31b985 100644 --- a/drivers/gpu/drm/imx/ipuv3/ipuv3-crtc.c +++ b/drivers/gpu/drm/imx/ipuv3/ipuv3-crtc.c @@ -310,7 +310,7 @@ static void ipu_crtc_mode_set_nofb(struct drm_crtc *crtc) dev_warn(ipu_crtc->dev, "8-pixel align hactive %d -> %d\n", sig_cfg.mode.hactive, new_hactive); - sig_cfg.mode.hfront_porch = new_hactive - sig_cfg.mode.hactive; + sig_cfg.mode.hfront_porch -= new_hactive - sig_cfg.mode.hactive; sig_cfg.mode.hactive = new_hactive; } diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index f75c6f09dd2a..a2e0033e8a26 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -967,7 +967,7 @@ nouveau_connector_get_modes(struct drm_connector *connector) /* Determine display colour depth for everything except LVDS now, * DP requires this before mode_valid() is called. */ - if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS && nv_connector->native_mode) + if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS) nouveau_connector_detect_depth(connector); /* Find the native mode if this is a digital panel, if we didn't diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c index 40c8ea43c42f..b8ac66b4a2c4 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c @@ -26,6 +26,8 @@ #include "head.h" #include "ior.h" +#include <drm/display/drm_dp.h> + #include <subdev/bios.h> #include <subdev/bios/init.h> #include <subdev/gpio.h> @@ -634,6 +636,50 @@ nvkm_dp_enable_supported_link_rates(struct nvkm_outp *outp) return outp->dp.rates != 0; } +/* XXX: This is a big fat hack, and this is just drm_dp_read_dpcd_caps() + * converted to work inside nvkm. This is a temporary holdover until we start + * passing the drm_dp_aux device through NVKM + */ +static int +nvkm_dp_read_dpcd_caps(struct nvkm_outp *outp) +{ + struct nvkm_i2c_aux *aux = outp->dp.aux; + u8 dpcd_ext[DP_RECEIVER_CAP_SIZE]; + int ret; + + ret = nvkm_rdaux(aux, DPCD_RC00_DPCD_REV, outp->dp.dpcd, DP_RECEIVER_CAP_SIZE); + if (ret < 0) + return ret; + + /* + * Prior to DP1.3 the bit represented by + * DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT was reserved. + * If it is set DP_DPCD_REV at 0000h could be at a value less than + * the true capability of the panel. The only way to check is to + * then compare 0000h and 2200h. + */ + if (!(outp->dp.dpcd[DP_TRAINING_AUX_RD_INTERVAL] & + DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT)) + return 0; + + ret = nvkm_rdaux(aux, DP_DP13_DPCD_REV, dpcd_ext, sizeof(dpcd_ext)); + if (ret < 0) + return ret; + + if (outp->dp.dpcd[DP_DPCD_REV] > dpcd_ext[DP_DPCD_REV]) { + OUTP_DBG(outp, "Extended DPCD rev less than base DPCD rev (%d > %d)\n", + outp->dp.dpcd[DP_DPCD_REV], dpcd_ext[DP_DPCD_REV]); + return 0; + } + + if (!memcmp(outp->dp.dpcd, dpcd_ext, sizeof(dpcd_ext))) + return 0; + + memcpy(outp->dp.dpcd, dpcd_ext, sizeof(dpcd_ext)); + + return 0; +} + void nvkm_dp_enable(struct nvkm_outp *outp, bool auxpwr) { @@ -689,7 +735,7 @@ nvkm_dp_enable(struct nvkm_outp *outp, bool auxpwr) memset(outp->dp.lttpr, 0x00, sizeof(outp->dp.lttpr)); } - if (!nvkm_rdaux(aux, DPCD_RC00_DPCD_REV, outp->dp.dpcd, sizeof(outp->dp.dpcd))) { + if (!nvkm_dp_read_dpcd_caps(outp)) { const u8 rates[] = { 0x1e, 0x14, 0x0a, 0x06, 0 }; const u8 *rate; int rate_max; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h index 00dbeda7e346..de161e7a04aa 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h @@ -117,6 +117,7 @@ void gk104_grctx_generate_r418800(struct gf100_gr *); extern const struct gf100_grctx_func gk110_grctx; void gk110_grctx_generate_r419eb0(struct gf100_gr *); +void gk110_grctx_generate_r419f78(struct gf100_gr *); extern const struct gf100_grctx_func gk110b_grctx; extern const struct gf100_grctx_func gk208_grctx; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c index 94233d0119df..52a234b1ef01 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c @@ -906,7 +906,9 @@ static void gk104_grctx_generate_r419f78(struct gf100_gr *gr) { struct nvkm_device *device = gr->base.engine.subdev.device; - nvkm_mask(device, 0x419f78, 0x00000001, 0x00000000); + + /* bit 3 set disables loads in fp helper invocations, we need it enabled */ + nvkm_mask(device, 0x419f78, 0x00000009, 0x00000000); } void diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c index 4391458e1fb2..3acdd9eeb74a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c @@ -820,6 +820,15 @@ gk110_grctx_generate_r419eb0(struct gf100_gr *gr) nvkm_mask(device, 0x419eb0, 0x00001000, 0x00001000); } +void +gk110_grctx_generate_r419f78(struct gf100_gr *gr) +{ + struct nvkm_device *device = gr->base.engine.subdev.device; + + /* bit 3 set disables loads in fp helper invocations, we need it enabled */ + nvkm_mask(device, 0x419f78, 0x00000008, 0x00000000); +} + const struct gf100_grctx_func gk110_grctx = { .main = gf100_grctx_generate_main, @@ -854,4 +863,5 @@ gk110_grctx = { .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r418800 = gk104_grctx_generate_r418800, .r419eb0 = gk110_grctx_generate_r419eb0, + .r419f78 = gk110_grctx_generate_r419f78, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c index 7b9a34f9ec3c..5597e87624ac 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c @@ -103,4 +103,5 @@ gk110b_grctx = { .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r418800 = gk104_grctx_generate_r418800, .r419eb0 = gk110_grctx_generate_r419eb0, + .r419f78 = gk110_grctx_generate_r419f78, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c index c78d07a8bb7d..612656496541 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c @@ -568,4 +568,5 @@ gk208_grctx = { .dist_skip_table = gf117_grctx_generate_dist_skip_table, .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r418800 = gk104_grctx_generate_r418800, + .r419f78 = gk110_grctx_generate_r419f78, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c index beac66eb2a80..9906974ac3f0 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c @@ -988,4 +988,5 @@ gm107_grctx = { .r406500 = gm107_grctx_generate_r406500, .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r419e00 = gm107_grctx_generate_r419e00, + .r419f78 = gk110_grctx_generate_r419f78, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c index 3b6c8100a242..a7775aa18541 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c @@ -206,19 +206,6 @@ tu102_gr_av_to_init_veid(struct nvkm_blob *blob, struct gf100_gr_pack **ppack) return gk20a_gr_av_to_init_(blob, 64, 0x00100000, ppack); } -int -tu102_gr_load(struct gf100_gr *gr, int ver, const struct gf100_gr_fwif *fwif) -{ - int ret; - - ret = gm200_gr_load(gr, ver, fwif); - if (ret) - return ret; - - return gk20a_gr_load_net(gr, "gr/", "sw_veid_bundle_init", ver, tu102_gr_av_to_init_veid, - &gr->bundle_veid); -} - static const struct gf100_gr_fwif tu102_gr_fwif[] = { { 0, gm200_gr_load, &tu102_gr, &gp108_gr_fecs_acr, &gp108_gr_gpccs_acr }, diff --git a/drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c b/drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c index 102e1fc7ee38..be4ec5bb5223 100644 --- a/drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c +++ b/drivers/gpu/drm/panel/panel-samsung-s6d7aa0.c @@ -569,6 +569,7 @@ static const struct of_device_id s6d7aa0_of_match[] = { }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, s6d7aa0_of_match); static struct mipi_dsi_driver s6d7aa0_driver = { .probe = s6d7aa0_probe, diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index a530ecc4d207..bf34498c1b6d 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -833,12 +833,12 @@ static int vop_plane_atomic_check(struct drm_plane *plane, * need align with 2 pixel. */ if (fb->format->is_yuv && ((new_plane_state->src.x1 >> 16) % 2)) { - DRM_ERROR("Invalid Source: Yuv format not support odd xpos\n"); + DRM_DEBUG_KMS("Invalid Source: Yuv format not support odd xpos\n"); return -EINVAL; } if (fb->format->is_yuv && new_plane_state->rotation & DRM_MODE_REFLECT_Y) { - DRM_ERROR("Invalid Source: Yuv format does not support this rotation\n"); + DRM_DEBUG_KMS("Invalid Source: Yuv format does not support this rotation\n"); return -EINVAL; } @@ -846,7 +846,7 @@ static int vop_plane_atomic_check(struct drm_plane *plane, struct vop *vop = to_vop(crtc); if (!vop->data->afbc) { - DRM_ERROR("vop does not support AFBC\n"); + DRM_DEBUG_KMS("vop does not support AFBC\n"); return -EINVAL; } @@ -855,15 +855,16 @@ static int vop_plane_atomic_check(struct drm_plane *plane, return ret; if (new_plane_state->src.x1 || new_plane_state->src.y1) { - DRM_ERROR("AFBC does not support offset display, xpos=%d, ypos=%d, offset=%d\n", - new_plane_state->src.x1, - new_plane_state->src.y1, fb->offsets[0]); + DRM_DEBUG_KMS("AFBC does not support offset display, " \ + "xpos=%d, ypos=%d, offset=%d\n", + new_plane_state->src.x1, new_plane_state->src.y1, + fb->offsets[0]); return -EINVAL; } if (new_plane_state->rotation && new_plane_state->rotation != DRM_MODE_ROTATE_0) { - DRM_ERROR("No rotation support in AFBC, rotation=%d\n", - new_plane_state->rotation); + DRM_DEBUG_KMS("No rotation support in AFBC, rotation=%d\n", + new_plane_state->rotation); return -EINVAL; } } diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 7139a522b2f3..54e3083076b7 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -519,7 +519,8 @@ static bool ttm_bo_evict_swapout_allowable(struct ttm_buffer_object *bo, if (bo->pin_count) { *locked = false; - *busy = false; + if (busy) + *busy = false; return false; } diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index 5978e9dbc286..ebf15f31d97e 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -209,8 +209,7 @@ int vmbus_connect(void) * Setup the vmbus event connection for channel interrupt * abstraction stuff */ - vmbus_connection.int_page = - (void *)hv_alloc_hyperv_zeroed_page(); + vmbus_connection.int_page = hv_alloc_hyperv_zeroed_page(); if (vmbus_connection.int_page == NULL) { ret = -ENOMEM; goto cleanup; @@ -225,8 +224,8 @@ int vmbus_connect(void) * Setup the monitor notification facility. The 1st page for * parent->child and the 2nd page for child->parent */ - vmbus_connection.monitor_pages[0] = (void *)hv_alloc_hyperv_page(); - vmbus_connection.monitor_pages[1] = (void *)hv_alloc_hyperv_page(); + vmbus_connection.monitor_pages[0] = hv_alloc_hyperv_page(); + vmbus_connection.monitor_pages[1] = hv_alloc_hyperv_page(); if ((vmbus_connection.monitor_pages[0] == NULL) || (vmbus_connection.monitor_pages[1] == NULL)) { ret = -ENOMEM; @@ -333,15 +332,15 @@ void vmbus_disconnect(void) destroy_workqueue(vmbus_connection.work_queue); if (vmbus_connection.int_page) { - hv_free_hyperv_page((unsigned long)vmbus_connection.int_page); + hv_free_hyperv_page(vmbus_connection.int_page); vmbus_connection.int_page = NULL; } set_memory_encrypted((unsigned long)vmbus_connection.monitor_pages[0], 1); set_memory_encrypted((unsigned long)vmbus_connection.monitor_pages[1], 1); - hv_free_hyperv_page((unsigned long)vmbus_connection.monitor_pages[0]); - hv_free_hyperv_page((unsigned long)vmbus_connection.monitor_pages[1]); + hv_free_hyperv_page(vmbus_connection.monitor_pages[0]); + hv_free_hyperv_page(vmbus_connection.monitor_pages[1]); vmbus_connection.monitor_pages[0] = NULL; vmbus_connection.monitor_pages[1] = NULL; } diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index dffcc894f117..0d7a3ba66396 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -1628,7 +1628,7 @@ static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info, WARN_ON_ONCE(nents > HV_MEMORY_HINT_MAX_GPA_PAGE_RANGES); WARN_ON_ONCE(sgl->length < (HV_HYP_PAGE_SIZE << page_reporting_order)); local_irq_save(flags); - hint = *(struct hv_memory_hint **)this_cpu_ptr(hyperv_pcpu_input_arg); + hint = *this_cpu_ptr(hyperv_pcpu_input_arg); if (!hint) { local_irq_restore(flags); return -ENOSPC; diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 542a1d53b303..6a2258fef1fe 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -115,12 +115,12 @@ void *hv_alloc_hyperv_zeroed_page(void) } EXPORT_SYMBOL_GPL(hv_alloc_hyperv_zeroed_page); -void hv_free_hyperv_page(unsigned long addr) +void hv_free_hyperv_page(void *addr) { if (PAGE_SIZE == HV_HYP_PAGE_SIZE) - free_page(addr); + free_page((unsigned long)addr); else - kfree((void *)addr); + kfree(addr); } EXPORT_SYMBOL_GPL(hv_free_hyperv_page); @@ -253,7 +253,7 @@ static void hv_kmsg_dump_unregister(void) atomic_notifier_chain_unregister(&panic_notifier_list, &hyperv_panic_report_block); - hv_free_hyperv_page((unsigned long)hv_panic_page); + hv_free_hyperv_page(hv_panic_page); hv_panic_page = NULL; } @@ -270,7 +270,7 @@ static void hv_kmsg_dump_register(void) ret = kmsg_dump_register(&hv_kmsg_dumper); if (ret) { pr_err("Hyper-V: kmsg dump register error 0x%x\n", ret); - hv_free_hyperv_page((unsigned long)hv_panic_page); + hv_free_hyperv_page(hv_panic_page); hv_panic_page = NULL; } } diff --git a/drivers/hwmon/aquacomputer_d5next.c b/drivers/hwmon/aquacomputer_d5next.c index a997dbcb563f..023807859be7 100644 --- a/drivers/hwmon/aquacomputer_d5next.c +++ b/drivers/hwmon/aquacomputer_d5next.c @@ -13,9 +13,11 @@ #include <linux/crc16.h> #include <linux/debugfs.h> +#include <linux/delay.h> #include <linux/hid.h> #include <linux/hwmon.h> #include <linux/jiffies.h> +#include <linux/ktime.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/seq_file.h> @@ -63,6 +65,8 @@ static const char *const aqc_device_names[] = { #define CTRL_REPORT_ID 0x03 #define AQUAERO_CTRL_REPORT_ID 0x0b +#define CTRL_REPORT_DELAY 200 /* ms */ + /* The HID report that the official software always sends * after writing values, currently same for all devices */ @@ -527,6 +531,9 @@ struct aqc_data { int secondary_ctrl_report_size; u8 *secondary_ctrl_report; + ktime_t last_ctrl_report_op; + int ctrl_report_delay; /* Delay between two ctrl report operations, in ms */ + int buffer_size; u8 *buffer; int checksum_start; @@ -611,17 +618,35 @@ static int aqc_aquastreamxt_convert_fan_rpm(u16 val) return 0; } +static void aqc_delay_ctrl_report(struct aqc_data *priv) +{ + /* + * If previous read or write is too close to this one, delay the current operation + * to give the device enough time to process the previous one. + */ + if (priv->ctrl_report_delay) { + s64 delta = ktime_ms_delta(ktime_get(), priv->last_ctrl_report_op); + + if (delta < priv->ctrl_report_delay) + msleep(priv->ctrl_report_delay - delta); + } +} + /* Expects the mutex to be locked */ static int aqc_get_ctrl_data(struct aqc_data *priv) { int ret; + aqc_delay_ctrl_report(priv); + memset(priv->buffer, 0x00, priv->buffer_size); ret = hid_hw_raw_request(priv->hdev, priv->ctrl_report_id, priv->buffer, priv->buffer_size, HID_FEATURE_REPORT, HID_REQ_GET_REPORT); if (ret < 0) ret = -ENODATA; + priv->last_ctrl_report_op = ktime_get(); + return ret; } @@ -631,6 +656,8 @@ static int aqc_send_ctrl_data(struct aqc_data *priv) int ret; u16 checksum; + aqc_delay_ctrl_report(priv); + /* Checksum is not needed for Aquaero */ if (priv->kind != aquaero) { /* Init and xorout value for CRC-16/USB is 0xffff */ @@ -646,12 +673,16 @@ static int aqc_send_ctrl_data(struct aqc_data *priv) ret = hid_hw_raw_request(priv->hdev, priv->ctrl_report_id, priv->buffer, priv->buffer_size, HID_FEATURE_REPORT, HID_REQ_SET_REPORT); if (ret < 0) - return ret; + goto record_access_and_ret; /* The official software sends this report after every change, so do it here as well */ ret = hid_hw_raw_request(priv->hdev, priv->secondary_ctrl_report_id, priv->secondary_ctrl_report, priv->secondary_ctrl_report_size, HID_FEATURE_REPORT, HID_REQ_SET_REPORT); + +record_access_and_ret: + priv->last_ctrl_report_op = ktime_get(); + return ret; } @@ -1524,6 +1555,7 @@ static int aqc_probe(struct hid_device *hdev, const struct hid_device_id *id) priv->buffer_size = AQUAERO_CTRL_REPORT_SIZE; priv->temp_ctrl_offset = AQUAERO_TEMP_CTRL_OFFSET; + priv->ctrl_report_delay = CTRL_REPORT_DELAY; priv->temp_label = label_temp_sensors; priv->virtual_temp_label = label_virtual_temp_sensors; @@ -1547,6 +1579,7 @@ static int aqc_probe(struct hid_device *hdev, const struct hid_device_id *id) priv->temp_ctrl_offset = D5NEXT_TEMP_CTRL_OFFSET; priv->buffer_size = D5NEXT_CTRL_REPORT_SIZE; + priv->ctrl_report_delay = CTRL_REPORT_DELAY; priv->power_cycle_count_offset = D5NEXT_POWER_CYCLES; @@ -1597,6 +1630,7 @@ static int aqc_probe(struct hid_device *hdev, const struct hid_device_id *id) priv->temp_ctrl_offset = OCTO_TEMP_CTRL_OFFSET; priv->buffer_size = OCTO_CTRL_REPORT_SIZE; + priv->ctrl_report_delay = CTRL_REPORT_DELAY; priv->power_cycle_count_offset = OCTO_POWER_CYCLES; @@ -1624,6 +1658,7 @@ static int aqc_probe(struct hid_device *hdev, const struct hid_device_id *id) priv->temp_ctrl_offset = QUADRO_TEMP_CTRL_OFFSET; priv->buffer_size = QUADRO_CTRL_REPORT_SIZE; + priv->ctrl_report_delay = CTRL_REPORT_DELAY; priv->flow_pulses_ctrl_offset = QUADRO_FLOW_PULSES_CTRL_OFFSET; priv->power_cycle_count_offset = QUADRO_POWER_CYCLES; diff --git a/drivers/hwmon/pmbus/bel-pfe.c b/drivers/hwmon/pmbus/bel-pfe.c index fa5070ae26bc..7c5f4b10a7c1 100644 --- a/drivers/hwmon/pmbus/bel-pfe.c +++ b/drivers/hwmon/pmbus/bel-pfe.c @@ -17,12 +17,13 @@ enum chips {pfe1100, pfe3000}; /* - * Disable status check for pfe3000 devices, because some devices report - * communication error (invalid command) for VOUT_MODE command (0x20) - * although correct VOUT_MODE (0x16) is returned: it leads to incorrect - * exponent in linear mode. + * Disable status check because some devices report communication error + * (invalid command) for VOUT_MODE command (0x20) although the correct + * VOUT_MODE (0x16) is returned: it leads to incorrect exponent in linear + * mode. + * This affects both pfe3000 and pfe1100. */ -static struct pmbus_platform_data pfe3000_plat_data = { +static struct pmbus_platform_data pfe_plat_data = { .flags = PMBUS_SKIP_STATUS_CHECK, }; @@ -94,16 +95,15 @@ static int pfe_pmbus_probe(struct i2c_client *client) int model; model = (int)i2c_match_id(pfe_device_id, client)->driver_data; + client->dev.platform_data = &pfe_plat_data; /* * PFE3000-12-069RA devices may not stay in page 0 during device * probe which leads to probe failure (read status word failed). * So let's set the device to page 0 at the beginning. */ - if (model == pfe3000) { - client->dev.platform_data = &pfe3000_plat_data; + if (model == pfe3000) i2c_smbus_write_byte_data(client, PMBUS_PAGE, 0); - } return pmbus_do_probe(client, &pfe_driver_info[model]); } diff --git a/drivers/iio/adc/ad7192.c b/drivers/iio/adc/ad7192.c index 996ce7b24dce..69d1103b9508 100644 --- a/drivers/iio/adc/ad7192.c +++ b/drivers/iio/adc/ad7192.c @@ -62,7 +62,6 @@ #define AD7192_MODE_STA_MASK BIT(20) /* Status Register transmission Mask */ #define AD7192_MODE_CLKSRC(x) (((x) & 0x3) << 18) /* Clock Source Select */ #define AD7192_MODE_SINC3 BIT(15) /* SINC3 Filter Select */ -#define AD7192_MODE_ACX BIT(14) /* AC excitation enable(AD7195 only)*/ #define AD7192_MODE_ENPAR BIT(13) /* Parity Enable */ #define AD7192_MODE_CLKDIV BIT(12) /* Clock divide by 2 (AD7190/2 only)*/ #define AD7192_MODE_SCYCLE BIT(11) /* Single cycle conversion */ @@ -91,6 +90,7 @@ /* Configuration Register Bit Designations (AD7192_REG_CONF) */ #define AD7192_CONF_CHOP BIT(23) /* CHOP enable */ +#define AD7192_CONF_ACX BIT(22) /* AC excitation enable(AD7195 only) */ #define AD7192_CONF_REFSEL BIT(20) /* REFIN1/REFIN2 Reference Select */ #define AD7192_CONF_CHAN(x) ((x) << 8) /* Channel select */ #define AD7192_CONF_CHAN_MASK (0x7FF << 8) /* Channel select mask */ @@ -472,7 +472,7 @@ static ssize_t ad7192_show_ac_excitation(struct device *dev, struct iio_dev *indio_dev = dev_to_iio_dev(dev); struct ad7192_state *st = iio_priv(indio_dev); - return sysfs_emit(buf, "%d\n", !!(st->mode & AD7192_MODE_ACX)); + return sysfs_emit(buf, "%d\n", !!(st->conf & AD7192_CONF_ACX)); } static ssize_t ad7192_show_bridge_switch(struct device *dev, @@ -513,13 +513,13 @@ static ssize_t ad7192_set(struct device *dev, ad_sd_write_reg(&st->sd, AD7192_REG_GPOCON, 1, st->gpocon); break; - case AD7192_REG_MODE: + case AD7192_REG_CONF: if (val) - st->mode |= AD7192_MODE_ACX; + st->conf |= AD7192_CONF_ACX; else - st->mode &= ~AD7192_MODE_ACX; + st->conf &= ~AD7192_CONF_ACX; - ad_sd_write_reg(&st->sd, AD7192_REG_MODE, 3, st->mode); + ad_sd_write_reg(&st->sd, AD7192_REG_CONF, 3, st->conf); break; default: ret = -EINVAL; @@ -578,12 +578,11 @@ static IIO_DEVICE_ATTR(bridge_switch_en, 0644, static IIO_DEVICE_ATTR(ac_excitation_en, 0644, ad7192_show_ac_excitation, ad7192_set, - AD7192_REG_MODE); + AD7192_REG_CONF); static struct attribute *ad7192_attributes[] = { &iio_dev_attr_filter_low_pass_3db_frequency_available.dev_attr.attr, &iio_dev_attr_bridge_switch_en.dev_attr.attr, - &iio_dev_attr_ac_excitation_en.dev_attr.attr, NULL }; @@ -594,6 +593,7 @@ static const struct attribute_group ad7192_attribute_group = { static struct attribute *ad7195_attributes[] = { &iio_dev_attr_filter_low_pass_3db_frequency_available.dev_attr.attr, &iio_dev_attr_bridge_switch_en.dev_attr.attr, + &iio_dev_attr_ac_excitation_en.dev_attr.attr, NULL }; diff --git a/drivers/iio/adc/ina2xx-adc.c b/drivers/iio/adc/ina2xx-adc.c index 277574484fb1..9e52207352fb 100644 --- a/drivers/iio/adc/ina2xx-adc.c +++ b/drivers/iio/adc/ina2xx-adc.c @@ -124,6 +124,7 @@ static const struct regmap_config ina2xx_regmap_config = { enum ina2xx_ids { ina219, ina226 }; struct ina2xx_config { + const char *name; u16 config_default; int calibration_value; int shunt_voltage_lsb; /* nV */ @@ -155,6 +156,7 @@ struct ina2xx_chip_info { static const struct ina2xx_config ina2xx_config[] = { [ina219] = { + .name = "ina219", .config_default = INA219_CONFIG_DEFAULT, .calibration_value = 4096, .shunt_voltage_lsb = 10000, @@ -164,6 +166,7 @@ static const struct ina2xx_config ina2xx_config[] = { .chip_id = ina219, }, [ina226] = { + .name = "ina226", .config_default = INA226_CONFIG_DEFAULT, .calibration_value = 2048, .shunt_voltage_lsb = 2500, @@ -996,7 +999,7 @@ static int ina2xx_probe(struct i2c_client *client) /* Patch the current config register with default. */ val = chip->config->config_default; - if (id->driver_data == ina226) { + if (type == ina226) { ina226_set_average(chip, INA226_DEFAULT_AVG, &val); ina226_set_int_time_vbus(chip, INA226_DEFAULT_IT, &val); ina226_set_int_time_vshunt(chip, INA226_DEFAULT_IT, &val); @@ -1015,7 +1018,7 @@ static int ina2xx_probe(struct i2c_client *client) } indio_dev->modes = INDIO_DIRECT_MODE; - if (id->driver_data == ina226) { + if (type == ina226) { indio_dev->channels = ina226_channels; indio_dev->num_channels = ARRAY_SIZE(ina226_channels); indio_dev->info = &ina226_info; @@ -1024,7 +1027,7 @@ static int ina2xx_probe(struct i2c_client *client) indio_dev->num_channels = ARRAY_SIZE(ina219_channels); indio_dev->info = &ina219_info; } - indio_dev->name = id->name; + indio_dev->name = id ? id->name : chip->config->name; ret = devm_iio_kfifo_buffer_setup(&client->dev, indio_dev, &ina2xx_setup_ops); diff --git a/drivers/iio/adc/meson_saradc.c b/drivers/iio/adc/meson_saradc.c index c0a6eb8b6638..320e3e7e3d4d 100644 --- a/drivers/iio/adc/meson_saradc.c +++ b/drivers/iio/adc/meson_saradc.c @@ -1054,12 +1054,6 @@ static int meson_sar_adc_hw_enable(struct iio_dev *indio_dev) goto err_vref; } - ret = clk_prepare_enable(priv->core_clk); - if (ret) { - dev_err(dev, "failed to enable core clk\n"); - goto err_core_clk; - } - regval = FIELD_PREP(MESON_SAR_ADC_REG0_FIFO_CNT_IRQ_MASK, 1); regmap_update_bits(priv->regmap, MESON_SAR_ADC_REG0, MESON_SAR_ADC_REG0_FIFO_CNT_IRQ_MASK, regval); @@ -1086,8 +1080,6 @@ err_adc_clk: regmap_update_bits(priv->regmap, MESON_SAR_ADC_REG3, MESON_SAR_ADC_REG3_ADC_EN, 0); meson_sar_adc_set_bandgap(indio_dev, false); - clk_disable_unprepare(priv->core_clk); -err_core_clk: regulator_disable(priv->vref); err_vref: meson_sar_adc_unlock(indio_dev); @@ -1115,8 +1107,6 @@ static void meson_sar_adc_hw_disable(struct iio_dev *indio_dev) meson_sar_adc_set_bandgap(indio_dev, false); - clk_disable_unprepare(priv->core_clk); - regulator_disable(priv->vref); if (!ret) @@ -1378,7 +1368,7 @@ static int meson_sar_adc_probe(struct platform_device *pdev) if (IS_ERR(priv->clkin)) return dev_err_probe(dev, PTR_ERR(priv->clkin), "failed to get clkin\n"); - priv->core_clk = devm_clk_get(dev, "core"); + priv->core_clk = devm_clk_get_enabled(dev, "core"); if (IS_ERR(priv->core_clk)) return dev_err_probe(dev, PTR_ERR(priv->core_clk), "failed to get core clk\n"); @@ -1461,15 +1451,26 @@ static int meson_sar_adc_remove(struct platform_device *pdev) static int meson_sar_adc_suspend(struct device *dev) { struct iio_dev *indio_dev = dev_get_drvdata(dev); + struct meson_sar_adc_priv *priv = iio_priv(indio_dev); meson_sar_adc_hw_disable(indio_dev); + clk_disable_unprepare(priv->core_clk); + return 0; } static int meson_sar_adc_resume(struct device *dev) { struct iio_dev *indio_dev = dev_get_drvdata(dev); + struct meson_sar_adc_priv *priv = iio_priv(indio_dev); + int ret; + + ret = clk_prepare_enable(priv->core_clk); + if (ret) { + dev_err(dev, "failed to enable core clk\n"); + return ret; + } return meson_sar_adc_hw_enable(indio_dev); } diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c index 943e9e14d1e9..b72d39fc2434 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c @@ -253,7 +253,7 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, platform_set_drvdata(pdev, indio_dev); state->ec = ec->ec_dev; - state->msg = devm_kzalloc(&pdev->dev, + state->msg = devm_kzalloc(&pdev->dev, sizeof(*state->msg) + max((u16)sizeof(struct ec_params_motion_sense), state->ec->max_response), GFP_KERNEL); if (!state->msg) diff --git a/drivers/iio/frequency/admv1013.c b/drivers/iio/frequency/admv1013.c index cc01fac2dfee..6355c1f28423 100644 --- a/drivers/iio/frequency/admv1013.c +++ b/drivers/iio/frequency/admv1013.c @@ -344,9 +344,12 @@ static int admv1013_update_quad_filters(struct admv1013_state *st) static int admv1013_update_mixer_vgate(struct admv1013_state *st) { - unsigned int vcm, mixer_vgate; + unsigned int mixer_vgate; + int vcm; vcm = regulator_get_voltage(st->reg); + if (vcm < 0) + return vcm; if (vcm < 1800000) mixer_vgate = (2389 * vcm / 1000000 + 8100) / 100; diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c index 6a18b363cf73..b6e6b1df8a61 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c @@ -2687,7 +2687,7 @@ unknown_format: static int lsm6dsx_get_acpi_mount_matrix(struct device *dev, struct iio_mount_matrix *orientation) { - return false; + return -EOPNOTSUPP; } #endif diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 0d332c476813..d752e9c0499b 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1895,7 +1895,7 @@ static const struct iio_buffer_setup_ops noop_ring_setup_ops; int __iio_device_register(struct iio_dev *indio_dev, struct module *this_mod) { struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev); - struct fwnode_handle *fwnode; + struct fwnode_handle *fwnode = NULL; int ret; if (!indio_dev->info) @@ -1906,7 +1906,8 @@ int __iio_device_register(struct iio_dev *indio_dev, struct module *this_mod) /* If the calling driver did not initialize firmware node, do it here */ if (dev_fwnode(&indio_dev->dev)) fwnode = dev_fwnode(&indio_dev->dev); - else + /* The default dummy IIO device has no parent */ + else if (indio_dev->dev.parent) fwnode = dev_fwnode(indio_dev->dev.parent); device_set_node(&indio_dev->dev, fwnode); diff --git a/drivers/iio/light/rohm-bu27008.c b/drivers/iio/light/rohm-bu27008.c index 452737d7edd2..6a6d77805091 100644 --- a/drivers/iio/light/rohm-bu27008.c +++ b/drivers/iio/light/rohm-bu27008.c @@ -313,7 +313,7 @@ static const struct iio_itime_sel_mul bu27010_itimes[] = { .address = BU27008_REG_##data##_LO, \ .scan_index = BU27008_##color, \ .scan_type = { \ - .sign = 's', \ + .sign = 'u', \ .realbits = 16, \ .storagebits = 16, \ .endianness = IIO_LE, \ @@ -1057,7 +1057,7 @@ static int bu27008_try_find_new_time_gain(struct bu27008_data *data, int val, for (i = 0; i < data->gts.num_itime; i++) { new_time_sel = data->gts.itime_table[i].sel; ret = iio_gts_find_gain_sel_for_scale_using_time(&data->gts, - new_time_sel, val, val2 * 1000, gain_sel); + new_time_sel, val, val2, gain_sel); if (!ret) break; } @@ -1086,7 +1086,7 @@ static int bu27008_set_scale(struct bu27008_data *data, goto unlock_out; ret = iio_gts_find_gain_sel_for_scale_using_time(&data->gts, time_sel, - val, val2 * 1000, &gain_sel); + val, val2, &gain_sel); if (ret) { ret = bu27008_try_find_new_time_gain(data, val, val2, &gain_sel); if (ret) @@ -1101,6 +1101,21 @@ unlock_out: return ret; } +static int bu27008_write_raw_get_fmt(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + long mask) +{ + + switch (mask) { + case IIO_CHAN_INFO_SCALE: + return IIO_VAL_INT_PLUS_NANO; + case IIO_CHAN_INFO_INT_TIME: + return IIO_VAL_INT_PLUS_MICRO; + default: + return -EINVAL; + } +} + static int bu27008_write_raw(struct iio_dev *idev, struct iio_chan_spec const *chan, int val, int val2, long mask) @@ -1180,6 +1195,7 @@ static int bu27008_update_scan_mode(struct iio_dev *idev, static const struct iio_info bu27008_info = { .read_raw = &bu27008_read_raw, .write_raw = &bu27008_write_raw, + .write_raw_get_fmt = &bu27008_write_raw_get_fmt, .read_avail = &bu27008_read_avail, .update_scan_mode = bu27008_update_scan_mode, .validate_trigger = iio_validate_own_trigger, diff --git a/drivers/iio/light/rohm-bu27034.c b/drivers/iio/light/rohm-bu27034.c index e63ef5789cde..bf3de853a811 100644 --- a/drivers/iio/light/rohm-bu27034.c +++ b/drivers/iio/light/rohm-bu27034.c @@ -575,7 +575,7 @@ static int bu27034_set_scale(struct bu27034_data *data, int chan, return -EINVAL; if (chan == BU27034_CHAN_ALS) { - if (val == 0 && val2 == 1000) + if (val == 0 && val2 == 1000000) return 0; return -EINVAL; @@ -587,7 +587,7 @@ static int bu27034_set_scale(struct bu27034_data *data, int chan, goto unlock_out; ret = iio_gts_find_gain_sel_for_scale_using_time(&data->gts, time_sel, - val, val2 * 1000, &gain_sel); + val, val2, &gain_sel); if (ret) { /* * Could not support scale with given time. Need to change time. @@ -624,7 +624,7 @@ static int bu27034_set_scale(struct bu27034_data *data, int chan, /* Can we provide requested scale with this time? */ ret = iio_gts_find_gain_sel_for_scale_using_time( - &data->gts, new_time_sel, val, val2 * 1000, + &data->gts, new_time_sel, val, val2, &gain_sel); if (ret) continue; @@ -1217,6 +1217,21 @@ static int bu27034_read_raw(struct iio_dev *idev, } } +static int bu27034_write_raw_get_fmt(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + long mask) +{ + + switch (mask) { + case IIO_CHAN_INFO_SCALE: + return IIO_VAL_INT_PLUS_NANO; + case IIO_CHAN_INFO_INT_TIME: + return IIO_VAL_INT_PLUS_MICRO; + default: + return -EINVAL; + } +} + static int bu27034_write_raw(struct iio_dev *idev, struct iio_chan_spec const *chan, int val, int val2, long mask) @@ -1267,6 +1282,7 @@ static int bu27034_read_avail(struct iio_dev *idev, static const struct iio_info bu27034_info = { .read_raw = &bu27034_read_raw, .write_raw = &bu27034_write_raw, + .write_raw_get_fmt = &bu27034_write_raw_get_fmt, .read_avail = &bu27034_read_avail, }; diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 755a9c57db6f..f9ab671c8eda 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -85,6 +85,8 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, dma_addr_t mask; int i; + umem->iova = va = virt; + if (umem->is_odp) { unsigned int page_size = BIT(to_ib_umem_odp(umem)->page_shift); @@ -100,7 +102,6 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, */ pgsz_bitmap &= GENMASK(BITS_PER_LONG - 1, PAGE_SHIFT); - umem->iova = va = virt; /* The best result is the smallest page size that results in the minimum * number of required pages. Compute the largest page size that could * work based on VA address bits that don't change. diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index b42166fe7454..63e98e2d3596 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -1253,6 +1253,8 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 wqe_mode) rc = bnxt_re_setup_chip_ctx(rdev, wqe_mode); if (rc) { + bnxt_unregister_dev(rdev->en_dev); + clear_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags); ibdev_err(&rdev->ibdev, "Failed to get chip context\n"); return -EINVAL; } @@ -1526,8 +1528,8 @@ static void bnxt_re_remove(struct auxiliary_device *adev) } bnxt_re_setup_cc(rdev, false); ib_unregister_device(&rdev->ibdev); - ib_dealloc_device(&rdev->ibdev); bnxt_re_dev_uninit(rdev); + ib_dealloc_device(&rdev->ibdev); skip_remove: mutex_unlock(&bnxt_re_mutex); } diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index 5fd8f7c90bb0..739d942761d1 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -819,6 +819,7 @@ static int bnxt_qplib_alloc_dpi_tbl(struct bnxt_qplib_res *res, } memset((u8 *)dpit->tbl, 0xFF, bytes); + mutex_init(&res->dpi_tbl_lock); dpit->priv_db = dpit->ucreg.bar_reg + dpit->ucreg.offset; return 0; diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 9dbb89e9f4af..baaa4406d5e6 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -12307,6 +12307,7 @@ static void free_cntrs(struct hfi1_devdata *dd) if (dd->synth_stats_timer.function) del_timer_sync(&dd->synth_stats_timer); + cancel_work_sync(&dd->update_cntr_work); ppd = (struct hfi1_pportdata *)(dd + 1); for (i = 0; i < dd->num_pports; i++, ppd++) { kfree(ppd->cntrs); diff --git a/drivers/interconnect/qcom/bcm-voter.c b/drivers/interconnect/qcom/bcm-voter.c index 8f385f9c2dd3..d5f2a6b5376b 100644 --- a/drivers/interconnect/qcom/bcm-voter.c +++ b/drivers/interconnect/qcom/bcm-voter.c @@ -83,6 +83,11 @@ static void bcm_aggregate(struct qcom_icc_bcm *bcm) temp = agg_peak[bucket] * bcm->vote_scale; bcm->vote_y[bucket] = bcm_div(temp, bcm->aux_data.unit); + + if (bcm->enable_mask && (bcm->vote_x[bucket] || bcm->vote_y[bucket])) { + bcm->vote_x[bucket] = 0; + bcm->vote_y[bucket] = bcm->enable_mask; + } } if (bcm->keepalive && bcm->vote_x[QCOM_ICC_BUCKET_AMC] == 0 && diff --git a/drivers/interconnect/qcom/icc-rpmh.h b/drivers/interconnect/qcom/icc-rpmh.h index 04391c1ba465..7843d8864d6b 100644 --- a/drivers/interconnect/qcom/icc-rpmh.h +++ b/drivers/interconnect/qcom/icc-rpmh.h @@ -81,6 +81,7 @@ struct qcom_icc_node { * @vote_x: aggregated threshold values, represents sum_bw when @type is bw bcm * @vote_y: aggregated threshold values, represents peak_bw when @type is bw bcm * @vote_scale: scaling factor for vote_x and vote_y + * @enable_mask: optional mask to send as vote instead of vote_x/vote_y * @dirty: flag used to indicate whether the bcm needs to be committed * @keepalive: flag used to indicate whether a keepalive is required * @aux_data: auxiliary data used when calculating threshold values and @@ -97,6 +98,7 @@ struct qcom_icc_bcm { u64 vote_x[QCOM_ICC_NUM_BUCKETS]; u64 vote_y[QCOM_ICC_NUM_BUCKETS]; u64 vote_scale; + u32 enable_mask; bool dirty; bool keepalive; struct bcm_db aux_data; diff --git a/drivers/interconnect/qcom/sa8775p.c b/drivers/interconnect/qcom/sa8775p.c index da21cc31a580..f56538669de0 100644 --- a/drivers/interconnect/qcom/sa8775p.c +++ b/drivers/interconnect/qcom/sa8775p.c @@ -1873,6 +1873,7 @@ static struct qcom_icc_node srvc_snoc = { static struct qcom_icc_bcm bcm_acv = { .name = "ACV", + .enable_mask = 0x8, .num_nodes = 1, .nodes = { &ebi }, }; diff --git a/drivers/interconnect/qcom/sm8450.c b/drivers/interconnect/qcom/sm8450.c index 2d7a8e7b85ec..e64c214b4020 100644 --- a/drivers/interconnect/qcom/sm8450.c +++ b/drivers/interconnect/qcom/sm8450.c @@ -1337,6 +1337,7 @@ static struct qcom_icc_node qns_mem_noc_sf_disp = { static struct qcom_icc_bcm bcm_acv = { .name = "ACV", + .enable_mask = 0x8, .num_nodes = 1, .nodes = { &ebi }, }; @@ -1349,6 +1350,7 @@ static struct qcom_icc_bcm bcm_ce0 = { static struct qcom_icc_bcm bcm_cn0 = { .name = "CN0", + .enable_mask = 0x1, .keepalive = true, .num_nodes = 55, .nodes = { &qnm_gemnoc_cnoc, &qnm_gemnoc_pcie, @@ -1383,6 +1385,7 @@ static struct qcom_icc_bcm bcm_cn0 = { static struct qcom_icc_bcm bcm_co0 = { .name = "CO0", + .enable_mask = 0x1, .num_nodes = 2, .nodes = { &qxm_nsp, &qns_nsp_gemnoc }, }; @@ -1403,6 +1406,7 @@ static struct qcom_icc_bcm bcm_mm0 = { static struct qcom_icc_bcm bcm_mm1 = { .name = "MM1", + .enable_mask = 0x1, .num_nodes = 12, .nodes = { &qnm_camnoc_hf, &qnm_camnoc_icp, &qnm_camnoc_sf, &qnm_mdp, @@ -1445,6 +1449,7 @@ static struct qcom_icc_bcm bcm_sh0 = { static struct qcom_icc_bcm bcm_sh1 = { .name = "SH1", + .enable_mask = 0x1, .num_nodes = 7, .nodes = { &alm_gpu_tcu, &alm_sys_tcu, &qnm_nsp_gemnoc, &qnm_pcie, @@ -1461,6 +1466,7 @@ static struct qcom_icc_bcm bcm_sn0 = { static struct qcom_icc_bcm bcm_sn1 = { .name = "SN1", + .enable_mask = 0x1, .num_nodes = 4, .nodes = { &qhm_gic, &qxm_pimem, &xm_gic, &qns_gemnoc_gc }, @@ -1492,6 +1498,7 @@ static struct qcom_icc_bcm bcm_sn7 = { static struct qcom_icc_bcm bcm_acv_disp = { .name = "ACV", + .enable_mask = 0x1, .num_nodes = 1, .nodes = { &ebi_disp }, }; @@ -1510,6 +1517,7 @@ static struct qcom_icc_bcm bcm_mm0_disp = { static struct qcom_icc_bcm bcm_mm1_disp = { .name = "MM1", + .enable_mask = 0x1, .num_nodes = 3, .nodes = { &qnm_mdp_disp, &qnm_rot_disp, &qns_mem_noc_sf_disp }, @@ -1523,6 +1531,7 @@ static struct qcom_icc_bcm bcm_sh0_disp = { static struct qcom_icc_bcm bcm_sh1_disp = { .name = "SH1", + .enable_mask = 0x1, .num_nodes = 1, .nodes = { &qnm_pcie_disp }, }; diff --git a/drivers/interconnect/qcom/sm8550.c b/drivers/interconnect/qcom/sm8550.c index d823ba988ef6..0864ed285375 100644 --- a/drivers/interconnect/qcom/sm8550.c +++ b/drivers/interconnect/qcom/sm8550.c @@ -1473,6 +1473,7 @@ static struct qcom_icc_node qns_mem_noc_sf_cam_ife_2 = { static struct qcom_icc_bcm bcm_acv = { .name = "ACV", + .enable_mask = 0x8, .num_nodes = 1, .nodes = { &ebi }, }; @@ -1485,6 +1486,7 @@ static struct qcom_icc_bcm bcm_ce0 = { static struct qcom_icc_bcm bcm_cn0 = { .name = "CN0", + .enable_mask = 0x1, .keepalive = true, .num_nodes = 54, .nodes = { &qsm_cfg, &qhs_ahb2phy0, @@ -1524,6 +1526,7 @@ static struct qcom_icc_bcm bcm_cn1 = { static struct qcom_icc_bcm bcm_co0 = { .name = "CO0", + .enable_mask = 0x1, .num_nodes = 2, .nodes = { &qxm_nsp, &qns_nsp_gemnoc }, }; @@ -1549,6 +1552,7 @@ static struct qcom_icc_bcm bcm_mm0 = { static struct qcom_icc_bcm bcm_mm1 = { .name = "MM1", + .enable_mask = 0x1, .num_nodes = 8, .nodes = { &qnm_camnoc_hf, &qnm_camnoc_icp, &qnm_camnoc_sf, &qnm_vapss_hcp, @@ -1589,6 +1593,7 @@ static struct qcom_icc_bcm bcm_sh0 = { static struct qcom_icc_bcm bcm_sh1 = { .name = "SH1", + .enable_mask = 0x1, .num_nodes = 13, .nodes = { &alm_gpu_tcu, &alm_sys_tcu, &chm_apps, &qnm_gpu, @@ -1608,6 +1613,7 @@ static struct qcom_icc_bcm bcm_sn0 = { static struct qcom_icc_bcm bcm_sn1 = { .name = "SN1", + .enable_mask = 0x1, .num_nodes = 3, .nodes = { &qhm_gic, &xm_gic, &qns_gemnoc_gc }, @@ -1633,6 +1639,7 @@ static struct qcom_icc_bcm bcm_sn7 = { static struct qcom_icc_bcm bcm_acv_disp = { .name = "ACV", + .enable_mask = 0x1, .num_nodes = 1, .nodes = { &ebi_disp }, }; @@ -1657,12 +1664,14 @@ static struct qcom_icc_bcm bcm_sh0_disp = { static struct qcom_icc_bcm bcm_sh1_disp = { .name = "SH1", + .enable_mask = 0x1, .num_nodes = 2, .nodes = { &qnm_mnoc_hf_disp, &qnm_pcie_disp }, }; static struct qcom_icc_bcm bcm_acv_cam_ife_0 = { .name = "ACV", + .enable_mask = 0x0, .num_nodes = 1, .nodes = { &ebi_cam_ife_0 }, }; @@ -1681,6 +1690,7 @@ static struct qcom_icc_bcm bcm_mm0_cam_ife_0 = { static struct qcom_icc_bcm bcm_mm1_cam_ife_0 = { .name = "MM1", + .enable_mask = 0x1, .num_nodes = 4, .nodes = { &qnm_camnoc_hf_cam_ife_0, &qnm_camnoc_icp_cam_ife_0, &qnm_camnoc_sf_cam_ife_0, &qns_mem_noc_sf_cam_ife_0 }, @@ -1694,6 +1704,7 @@ static struct qcom_icc_bcm bcm_sh0_cam_ife_0 = { static struct qcom_icc_bcm bcm_sh1_cam_ife_0 = { .name = "SH1", + .enable_mask = 0x1, .num_nodes = 3, .nodes = { &qnm_mnoc_hf_cam_ife_0, &qnm_mnoc_sf_cam_ife_0, &qnm_pcie_cam_ife_0 }, @@ -1701,6 +1712,7 @@ static struct qcom_icc_bcm bcm_sh1_cam_ife_0 = { static struct qcom_icc_bcm bcm_acv_cam_ife_1 = { .name = "ACV", + .enable_mask = 0x0, .num_nodes = 1, .nodes = { &ebi_cam_ife_1 }, }; @@ -1719,6 +1731,7 @@ static struct qcom_icc_bcm bcm_mm0_cam_ife_1 = { static struct qcom_icc_bcm bcm_mm1_cam_ife_1 = { .name = "MM1", + .enable_mask = 0x1, .num_nodes = 4, .nodes = { &qnm_camnoc_hf_cam_ife_1, &qnm_camnoc_icp_cam_ife_1, &qnm_camnoc_sf_cam_ife_1, &qns_mem_noc_sf_cam_ife_1 }, @@ -1732,6 +1745,7 @@ static struct qcom_icc_bcm bcm_sh0_cam_ife_1 = { static struct qcom_icc_bcm bcm_sh1_cam_ife_1 = { .name = "SH1", + .enable_mask = 0x1, .num_nodes = 3, .nodes = { &qnm_mnoc_hf_cam_ife_1, &qnm_mnoc_sf_cam_ife_1, &qnm_pcie_cam_ife_1 }, @@ -1739,6 +1753,7 @@ static struct qcom_icc_bcm bcm_sh1_cam_ife_1 = { static struct qcom_icc_bcm bcm_acv_cam_ife_2 = { .name = "ACV", + .enable_mask = 0x0, .num_nodes = 1, .nodes = { &ebi_cam_ife_2 }, }; @@ -1757,6 +1772,7 @@ static struct qcom_icc_bcm bcm_mm0_cam_ife_2 = { static struct qcom_icc_bcm bcm_mm1_cam_ife_2 = { .name = "MM1", + .enable_mask = 0x1, .num_nodes = 4, .nodes = { &qnm_camnoc_hf_cam_ife_2, &qnm_camnoc_icp_cam_ife_2, &qnm_camnoc_sf_cam_ife_2, &qns_mem_noc_sf_cam_ife_2 }, @@ -1770,6 +1786,7 @@ static struct qcom_icc_bcm bcm_sh0_cam_ife_2 = { static struct qcom_icc_bcm bcm_sh1_cam_ife_2 = { .name = "SH1", + .enable_mask = 0x1, .num_nodes = 3, .nodes = { &qnm_mnoc_hf_cam_ife_2, &qnm_mnoc_sf_cam_ife_2, &qnm_pcie_cam_ife_2 }, diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c index c0331b268010..fe391de1aba3 100644 --- a/drivers/isdn/hardware/mISDN/hfcpci.c +++ b/drivers/isdn/hardware/mISDN/hfcpci.c @@ -839,7 +839,7 @@ hfcpci_fill_fifo(struct bchannel *bch) *z1t = cpu_to_le16(new_z1); /* now send data */ if (bch->tx_idx < bch->tx_skb->len) return; - dev_kfree_skb(bch->tx_skb); + dev_kfree_skb_any(bch->tx_skb); if (get_next_bframe(bch)) goto next_t_frame; return; @@ -895,7 +895,7 @@ hfcpci_fill_fifo(struct bchannel *bch) } bz->za[new_f1].z1 = cpu_to_le16(new_z1); /* for next buffer */ bz->f1 = new_f1; /* next frame */ - dev_kfree_skb(bch->tx_skb); + dev_kfree_skb_any(bch->tx_skb); get_next_bframe(bch); } @@ -1119,7 +1119,7 @@ tx_birq(struct bchannel *bch) if (bch->tx_skb && bch->tx_idx < bch->tx_skb->len) hfcpci_fill_fifo(bch); else { - dev_kfree_skb(bch->tx_skb); + dev_kfree_skb_any(bch->tx_skb); if (get_next_bframe(bch)) hfcpci_fill_fifo(bch); } @@ -2277,7 +2277,7 @@ _hfcpci_softirq(struct device *dev, void *unused) return 0; if (hc->hw.int_m2 & HFCPCI_IRQ_ENABLE) { - spin_lock(&hc->lock); + spin_lock_irq(&hc->lock); bch = Sel_BCS(hc, hc->hw.bswapped ? 2 : 1); if (bch && bch->state == ISDN_P_B_RAW) { /* B1 rx&tx */ main_rec_hfcpci(bch); @@ -2288,7 +2288,7 @@ _hfcpci_softirq(struct device *dev, void *unused) main_rec_hfcpci(bch); tx_birq(bch); } - spin_unlock(&hc->lock); + spin_unlock_irq(&hc->lock); } return 0; } diff --git a/drivers/isdn/mISDN/dsp.h b/drivers/isdn/mISDN/dsp.h index fa09d511a8ed..baf31258f5c9 100644 --- a/drivers/isdn/mISDN/dsp.h +++ b/drivers/isdn/mISDN/dsp.h @@ -247,7 +247,7 @@ extern void dsp_cmx_hardware(struct dsp_conf *conf, struct dsp *dsp); extern int dsp_cmx_conf(struct dsp *dsp, u32 conf_id); extern void dsp_cmx_receive(struct dsp *dsp, struct sk_buff *skb); extern void dsp_cmx_hdlc(struct dsp *dsp, struct sk_buff *skb); -extern void dsp_cmx_send(void *arg); +extern void dsp_cmx_send(struct timer_list *arg); extern void dsp_cmx_transmit(struct dsp *dsp, struct sk_buff *skb); extern int dsp_cmx_del_conf_member(struct dsp *dsp); extern int dsp_cmx_del_conf(struct dsp_conf *conf); diff --git a/drivers/isdn/mISDN/dsp_cmx.c b/drivers/isdn/mISDN/dsp_cmx.c index 357b87592eb4..61cb45c5d0d8 100644 --- a/drivers/isdn/mISDN/dsp_cmx.c +++ b/drivers/isdn/mISDN/dsp_cmx.c @@ -1614,7 +1614,7 @@ static u16 dsp_count; /* last sample count */ static int dsp_count_valid; /* if we have last sample count */ void -dsp_cmx_send(void *arg) +dsp_cmx_send(struct timer_list *arg) { struct dsp_conf *conf; struct dsp_conf_member *member; diff --git a/drivers/isdn/mISDN/dsp_core.c b/drivers/isdn/mISDN/dsp_core.c index 386084530c2f..fae95f166688 100644 --- a/drivers/isdn/mISDN/dsp_core.c +++ b/drivers/isdn/mISDN/dsp_core.c @@ -1195,7 +1195,7 @@ static int __init dsp_init(void) } /* set sample timer */ - timer_setup(&dsp_spl_tl, (void *)dsp_cmx_send, 0); + timer_setup(&dsp_spl_tl, dsp_cmx_send, 0); dsp_spl_tl.expires = jiffies + dsp_tics; dsp_spl_jiffies = dsp_spl_tl.expires; add_timer(&dsp_spl_tl); diff --git a/drivers/media/platform/qcom/venus/hfi_cmds.c b/drivers/media/platform/qcom/venus/hfi_cmds.c index 7f0802a5518c..3418d2dd9371 100644 --- a/drivers/media/platform/qcom/venus/hfi_cmds.c +++ b/drivers/media/platform/qcom/venus/hfi_cmds.c @@ -251,8 +251,8 @@ int pkt_session_unset_buffers(struct hfi_session_release_buffer_pkt *pkt, pkt->extradata_size = 0; pkt->shdr.hdr.size = - struct_size((struct hfi_session_set_buffers_pkt *)0, - buffer_info, bd->num_buffers); + struct_size_t(struct hfi_session_set_buffers_pkt, + buffer_info, bd->num_buffers); } pkt->response_req = bd->response_required; diff --git a/drivers/memory/tegra/mc.c b/drivers/memory/tegra/mc.c index 4a750da1c12a..deb6e65b59af 100644 --- a/drivers/memory/tegra/mc.c +++ b/drivers/memory/tegra/mc.c @@ -755,6 +755,43 @@ const char *const tegra_mc_error_names[8] = { [6] = "SMMU translation error", }; +struct icc_node *tegra_mc_icc_xlate(struct of_phandle_args *spec, void *data) +{ + struct tegra_mc *mc = icc_provider_to_tegra_mc(data); + struct icc_node *node; + + list_for_each_entry(node, &mc->provider.nodes, node_list) { + if (node->id == spec->args[0]) + return node; + } + + /* + * If a client driver calls devm_of_icc_get() before the MC driver + * is probed, then return EPROBE_DEFER to the client driver. + */ + return ERR_PTR(-EPROBE_DEFER); +} + +static int tegra_mc_icc_get(struct icc_node *node, u32 *average, u32 *peak) +{ + *average = 0; + *peak = 0; + + return 0; +} + +static int tegra_mc_icc_set(struct icc_node *src, struct icc_node *dst) +{ + return 0; +} + +const struct tegra_mc_icc_ops tegra_mc_icc_ops = { + .xlate = tegra_mc_icc_xlate, + .aggregate = icc_std_aggregate, + .get_bw = tegra_mc_icc_get, + .set = tegra_mc_icc_set, +}; + /* * Memory Controller (MC) has few Memory Clients that are issuing memory * bandwidth allocation requests to the MC interconnect provider. The MC diff --git a/drivers/memory/tegra/tegra194.c b/drivers/memory/tegra/tegra194.c index b2416ee3ac26..26035ac3a1eb 100644 --- a/drivers/memory/tegra/tegra194.c +++ b/drivers/memory/tegra/tegra194.c @@ -1355,6 +1355,7 @@ const struct tegra_mc_soc tegra194_mc_soc = { MC_INT_SECURITY_VIOLATION | MC_INT_DECERR_EMEM, .has_addr_hi_reg = true, .ops = &tegra186_mc_ops, + .icc_ops = &tegra_mc_icc_ops, .ch_intmask = 0x00000f00, .global_intstatus_channel_shift = 8, }; diff --git a/drivers/memory/tegra/tegra234.c b/drivers/memory/tegra/tegra234.c index 8e873a7bc34f..8fb83b39f5f5 100644 --- a/drivers/memory/tegra/tegra234.c +++ b/drivers/memory/tegra/tegra234.c @@ -827,7 +827,7 @@ static int tegra234_mc_icc_set(struct icc_node *src, struct icc_node *dst) return 0; if (!mc->bwmgr_mrq_supported) - return -EINVAL; + return 0; if (!mc->bpmp) { dev_err(mc->dev, "BPMP reference NULL\n"); @@ -874,7 +874,7 @@ static int tegra234_mc_icc_aggregate(struct icc_node *node, u32 tag, u32 avg_bw, struct tegra_mc *mc = icc_provider_to_tegra_mc(p); if (!mc->bwmgr_mrq_supported) - return -EINVAL; + return 0; if (node->id == TEGRA_ICC_MC_CPU_CLUSTER0 || node->id == TEGRA_ICC_MC_CPU_CLUSTER1 || @@ -889,27 +889,6 @@ static int tegra234_mc_icc_aggregate(struct icc_node *node, u32 tag, u32 avg_bw, return 0; } -static struct icc_node* -tegra234_mc_of_icc_xlate(struct of_phandle_args *spec, void *data) -{ - struct tegra_mc *mc = icc_provider_to_tegra_mc(data); - unsigned int cl_id = spec->args[0]; - struct icc_node *node; - - list_for_each_entry(node, &mc->provider.nodes, node_list) { - if (node->id != cl_id) - continue; - - return node; - } - - /* - * If a client driver calls devm_of_icc_get() before the MC driver - * is probed, then return EPROBE_DEFER to the client driver. - */ - return ERR_PTR(-EPROBE_DEFER); -} - static int tegra234_mc_icc_get_init_bw(struct icc_node *node, u32 *avg, u32 *peak) { *avg = 0; @@ -919,7 +898,7 @@ static int tegra234_mc_icc_get_init_bw(struct icc_node *node, u32 *avg, u32 *pea } static const struct tegra_mc_icc_ops tegra234_mc_icc_ops = { - .xlate = tegra234_mc_of_icc_xlate, + .xlate = tegra_mc_icc_xlate, .aggregate = tegra234_mc_icc_aggregate, .get_bw = tegra234_mc_icc_get_init_bw, .set = tegra234_mc_icc_set, diff --git a/drivers/misc/cardreader/rts5227.c b/drivers/misc/cardreader/rts5227.c index d676cf63a966..3dae5e3a1697 100644 --- a/drivers/misc/cardreader/rts5227.c +++ b/drivers/misc/cardreader/rts5227.c @@ -195,7 +195,7 @@ static int rts5227_extra_init_hw(struct rtsx_pcr *pcr) } } - if (option->force_clkreq_0) + if (option->force_clkreq_0 && pcr->aspm_mode == ASPM_MODE_CFG) rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG, FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); else diff --git a/drivers/misc/cardreader/rts5228.c b/drivers/misc/cardreader/rts5228.c index cfebad51d1d8..f4ab09439da7 100644 --- a/drivers/misc/cardreader/rts5228.c +++ b/drivers/misc/cardreader/rts5228.c @@ -435,17 +435,10 @@ static void rts5228_init_from_cfg(struct rtsx_pcr *pcr) option->ltr_enabled = false; } } - - if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN - | PM_L1_1_EN | PM_L1_2_EN)) - option->force_clkreq_0 = false; - else - option->force_clkreq_0 = true; } static int rts5228_extra_init_hw(struct rtsx_pcr *pcr) { - struct rtsx_cr_option *option = &pcr->option; rtsx_pci_write_register(pcr, RTS5228_AUTOLOAD_CFG1, CD_RESUME_EN_MASK, CD_RESUME_EN_MASK); @@ -476,17 +469,6 @@ static int rts5228_extra_init_hw(struct rtsx_pcr *pcr) else rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00); - /* - * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced - * to drive low, and we forcibly request clock. - */ - if (option->force_clkreq_0) - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); - else - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); - rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFB); if (pcr->rtd3_en) { diff --git a/drivers/misc/cardreader/rts5249.c b/drivers/misc/cardreader/rts5249.c index 91d240dd68fa..47ab72a43256 100644 --- a/drivers/misc/cardreader/rts5249.c +++ b/drivers/misc/cardreader/rts5249.c @@ -327,12 +327,11 @@ static int rts5249_extra_init_hw(struct rtsx_pcr *pcr) } } - /* * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced * to drive low, and we forcibly request clock. */ - if (option->force_clkreq_0) + if (option->force_clkreq_0 && pcr->aspm_mode == ASPM_MODE_CFG) rtsx_pci_write_register(pcr, PETXCFG, FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); else diff --git a/drivers/misc/cardreader/rts5260.c b/drivers/misc/cardreader/rts5260.c index 9b42b20a3e5a..79b18f6f73a8 100644 --- a/drivers/misc/cardreader/rts5260.c +++ b/drivers/misc/cardreader/rts5260.c @@ -517,17 +517,10 @@ static void rts5260_init_from_cfg(struct rtsx_pcr *pcr) option->ltr_enabled = false; } } - - if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN - | PM_L1_1_EN | PM_L1_2_EN)) - option->force_clkreq_0 = false; - else - option->force_clkreq_0 = true; } static int rts5260_extra_init_hw(struct rtsx_pcr *pcr) { - struct rtsx_cr_option *option = &pcr->option; /* Set mcu_cnt to 7 to ensure data can be sampled properly */ rtsx_pci_write_register(pcr, 0xFC03, 0x7F, 0x07); @@ -546,17 +539,6 @@ static int rts5260_extra_init_hw(struct rtsx_pcr *pcr) rts5260_init_hw(pcr); - /* - * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced - * to drive low, and we forcibly request clock. - */ - if (option->force_clkreq_0) - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); - else - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); - rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x10, 0x00); return 0; diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c index b1e76030cafd..94af6bf8a25a 100644 --- a/drivers/misc/cardreader/rts5261.c +++ b/drivers/misc/cardreader/rts5261.c @@ -498,17 +498,10 @@ static void rts5261_init_from_cfg(struct rtsx_pcr *pcr) option->ltr_enabled = false; } } - - if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN - | PM_L1_1_EN | PM_L1_2_EN)) - option->force_clkreq_0 = false; - else - option->force_clkreq_0 = true; } static int rts5261_extra_init_hw(struct rtsx_pcr *pcr) { - struct rtsx_cr_option *option = &pcr->option; u32 val; rtsx_pci_write_register(pcr, RTS5261_AUTOLOAD_CFG1, @@ -554,17 +547,6 @@ static int rts5261_extra_init_hw(struct rtsx_pcr *pcr) else rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00); - /* - * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced - * to drive low, and we forcibly request clock. - */ - if (option->force_clkreq_0) - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); - else - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); - rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFB); if (pcr->rtd3_en) { diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c index 32b7783e9d4f..a3f4b52bb159 100644 --- a/drivers/misc/cardreader/rtsx_pcr.c +++ b/drivers/misc/cardreader/rtsx_pcr.c @@ -1326,8 +1326,11 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr) return err; } - if (pcr->aspm_mode == ASPM_MODE_REG) + if (pcr->aspm_mode == ASPM_MODE_REG) { rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0x30, 0x30); + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); + } /* No CD interrupt if probing driver with card inserted. * So we need to initialize pcr->card_exist here. diff --git a/drivers/misc/tps6594-esm.c b/drivers/misc/tps6594-esm.c index e8d12e7f2d2a..b4d67a1a24e4 100644 --- a/drivers/misc/tps6594-esm.c +++ b/drivers/misc/tps6594-esm.c @@ -13,6 +13,8 @@ #include <linux/mfd/tps6594.h> +#define TPS6594_DEV_REV_1 0x08 + static irqreturn_t tps6594_esm_isr(int irq, void *dev_id) { struct platform_device *pdev = dev_id; @@ -32,11 +34,26 @@ static int tps6594_esm_probe(struct platform_device *pdev) { struct tps6594 *tps = dev_get_drvdata(pdev->dev.parent); struct device *dev = &pdev->dev; + unsigned int rev; int irq; int ret; int i; - for (i = 0 ; i < pdev->num_resources ; i++) { + /* + * Due to a bug in revision 1 of the PMIC, the GPIO3 used for the + * SoC ESM function is used to power the load switch instead. + * As a consequence, ESM can not be used on those PMIC. + * Check the version and return an error in case of revision 1. + */ + ret = regmap_read(tps->regmap, TPS6594_REG_DEV_REV, &rev); + if (ret) + return dev_err_probe(dev, ret, + "Failed to read PMIC revision\n"); + if (rev == TPS6594_DEV_REV_1) + return dev_err_probe(dev, -ENODEV, + "ESM not supported for revision 1 PMIC\n"); + + for (i = 0; i < pdev->num_resources; i++) { irq = platform_get_irq_byname(pdev, pdev->resource[i].name); if (irq < 0) return irq; diff --git a/drivers/mmc/host/moxart-mmc.c b/drivers/mmc/host/moxart-mmc.c index 2d002c81dcf3..d0d6ffcf78d4 100644 --- a/drivers/mmc/host/moxart-mmc.c +++ b/drivers/mmc/host/moxart-mmc.c @@ -338,13 +338,7 @@ static void moxart_transfer_pio(struct moxart_host *host) return; } for (len = 0; len < remain && len < host->fifo_width;) { - /* SCR data must be read in big endian. */ - if (data->mrq->cmd->opcode == SD_APP_SEND_SCR) - *sgp = ioread32be(host->base + - REG_DATA_WINDOW); - else - *sgp = ioread32(host->base + - REG_DATA_WINDOW); + *sgp = ioread32(host->base + REG_DATA_WINDOW); sgp++; len += 4; } diff --git a/drivers/mmc/host/sdhci_f_sdh30.c b/drivers/mmc/host/sdhci_f_sdh30.c index a202a69a4b08..b01ffb4d0973 100644 --- a/drivers/mmc/host/sdhci_f_sdh30.c +++ b/drivers/mmc/host/sdhci_f_sdh30.c @@ -29,9 +29,16 @@ struct f_sdhost_priv { bool enable_cmd_dat_delay; }; +static void *sdhci_f_sdhost_priv(struct sdhci_host *host) +{ + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + + return sdhci_pltfm_priv(pltfm_host); +} + static void sdhci_f_sdh30_soft_voltage_switch(struct sdhci_host *host) { - struct f_sdhost_priv *priv = sdhci_priv(host); + struct f_sdhost_priv *priv = sdhci_f_sdhost_priv(host); u32 ctrl = 0; usleep_range(2500, 3000); @@ -64,7 +71,7 @@ static unsigned int sdhci_f_sdh30_get_min_clock(struct sdhci_host *host) static void sdhci_f_sdh30_reset(struct sdhci_host *host, u8 mask) { - struct f_sdhost_priv *priv = sdhci_priv(host); + struct f_sdhost_priv *priv = sdhci_f_sdhost_priv(host); u32 ctl; if (sdhci_readw(host, SDHCI_CLOCK_CONTROL) == 0) @@ -95,30 +102,32 @@ static const struct sdhci_ops sdhci_f_sdh30_ops = { .set_uhs_signaling = sdhci_set_uhs_signaling, }; +static const struct sdhci_pltfm_data sdhci_f_sdh30_pltfm_data = { + .ops = &sdhci_f_sdh30_ops, + .quirks = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC + | SDHCI_QUIRK_INVERTED_WRITE_PROTECT, + .quirks2 = SDHCI_QUIRK2_SUPPORT_SINGLE + | SDHCI_QUIRK2_TUNING_WORK_AROUND, +}; + static int sdhci_f_sdh30_probe(struct platform_device *pdev) { struct sdhci_host *host; struct device *dev = &pdev->dev; - int irq, ctrl = 0, ret = 0; + int ctrl = 0, ret = 0; struct f_sdhost_priv *priv; + struct sdhci_pltfm_host *pltfm_host; u32 reg = 0; - irq = platform_get_irq(pdev, 0); - if (irq < 0) - return irq; - - host = sdhci_alloc_host(dev, sizeof(struct f_sdhost_priv)); + host = sdhci_pltfm_init(pdev, &sdhci_f_sdh30_pltfm_data, + sizeof(struct f_sdhost_priv)); if (IS_ERR(host)) return PTR_ERR(host); - priv = sdhci_priv(host); + pltfm_host = sdhci_priv(host); + priv = sdhci_pltfm_priv(pltfm_host); priv->dev = dev; - host->quirks = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC | - SDHCI_QUIRK_INVERTED_WRITE_PROTECT; - host->quirks2 = SDHCI_QUIRK2_SUPPORT_SINGLE | - SDHCI_QUIRK2_TUNING_WORK_AROUND; - priv->enable_cmd_dat_delay = device_property_read_bool(dev, "fujitsu,cmd-dat-delay-select"); @@ -126,18 +135,6 @@ static int sdhci_f_sdh30_probe(struct platform_device *pdev) if (ret) goto err; - platform_set_drvdata(pdev, host); - - host->hw_name = "f_sdh30"; - host->ops = &sdhci_f_sdh30_ops; - host->irq = irq; - - host->ioaddr = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(host->ioaddr)) { - ret = PTR_ERR(host->ioaddr); - goto err; - } - if (dev_of_node(dev)) { sdhci_get_of_property(pdev); @@ -204,24 +201,21 @@ err_rst: err_clk: clk_disable_unprepare(priv->clk_iface); err: - sdhci_free_host(host); + sdhci_pltfm_free(pdev); + return ret; } static int sdhci_f_sdh30_remove(struct platform_device *pdev) { struct sdhci_host *host = platform_get_drvdata(pdev); - struct f_sdhost_priv *priv = sdhci_priv(host); - - sdhci_remove_host(host, readl(host->ioaddr + SDHCI_INT_STATUS) == - 0xffffffff); + struct f_sdhost_priv *priv = sdhci_f_sdhost_priv(host); reset_control_assert(priv->rst); clk_disable_unprepare(priv->clk); clk_disable_unprepare(priv->clk_iface); - sdhci_free_host(host); - platform_set_drvdata(pdev, NULL); + sdhci_pltfm_unregister(pdev); return 0; } diff --git a/drivers/mtd/nand/raw/fsl_upm.c b/drivers/mtd/nand/raw/fsl_upm.c index 086426139173..7366e85c09fd 100644 --- a/drivers/mtd/nand/raw/fsl_upm.c +++ b/drivers/mtd/nand/raw/fsl_upm.c @@ -135,7 +135,7 @@ static int fun_exec_op(struct nand_chip *chip, const struct nand_operation *op, unsigned int i; int ret; - if (op->cs > NAND_MAX_CHIPS) + if (op->cs >= NAND_MAX_CHIPS) return -EINVAL; if (check_only) diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index d3faf8086631..b10011dec1e6 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -1278,7 +1278,6 @@ static int meson_nand_attach_chip(struct nand_chip *nand) struct meson_nfc *nfc = nand_get_controller_data(nand); struct meson_nfc_nand_chip *meson_chip = to_meson_nand(nand); struct mtd_info *mtd = nand_to_mtd(nand); - int nsectors = mtd->writesize / 1024; int raw_writesize; int ret; @@ -1304,7 +1303,7 @@ static int meson_nand_attach_chip(struct nand_chip *nand) nand->options |= NAND_NO_SUBPAGE_WRITE; ret = nand_ecc_choose_conf(nand, nfc->data->ecc_caps, - mtd->oobsize - 2 * nsectors); + mtd->oobsize - 2); if (ret) { dev_err(nfc->dev, "failed to ECC init\n"); return -EINVAL; diff --git a/drivers/mtd/nand/raw/omap_elm.c b/drivers/mtd/nand/raw/omap_elm.c index 6e1eac6644a6..4a97d4a76454 100644 --- a/drivers/mtd/nand/raw/omap_elm.c +++ b/drivers/mtd/nand/raw/omap_elm.c @@ -177,17 +177,17 @@ static void elm_load_syndrome(struct elm_info *info, switch (info->bch_type) { case BCH8_ECC: /* syndrome fragment 0 = ecc[9-12B] */ - val = cpu_to_be32(*(u32 *) &ecc[9]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[9]); elm_write_reg(info, offset, val); /* syndrome fragment 1 = ecc[5-8B] */ offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[5]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[5]); elm_write_reg(info, offset, val); /* syndrome fragment 2 = ecc[1-4B] */ offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[1]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[1]); elm_write_reg(info, offset, val); /* syndrome fragment 3 = ecc[0B] */ @@ -197,35 +197,35 @@ static void elm_load_syndrome(struct elm_info *info, break; case BCH4_ECC: /* syndrome fragment 0 = ecc[20-52b] bits */ - val = (cpu_to_be32(*(u32 *) &ecc[3]) >> 4) | + val = ((__force u32)cpu_to_be32(*(u32 *)&ecc[3]) >> 4) | ((ecc[2] & 0xf) << 28); elm_write_reg(info, offset, val); /* syndrome fragment 1 = ecc[0-20b] bits */ offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[0]) >> 12; + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[0]) >> 12; elm_write_reg(info, offset, val); break; case BCH16_ECC: - val = cpu_to_be32(*(u32 *) &ecc[22]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[22]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[18]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[18]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[14]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[14]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[10]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[10]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[6]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[6]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[2]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[2]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[0]) >> 16; + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[0]) >> 16; elm_write_reg(info, offset, val); break; default: diff --git a/drivers/mtd/nand/raw/rockchip-nand-controller.c b/drivers/mtd/nand/raw/rockchip-nand-controller.c index 2312e27362cb..5a04680342c3 100644 --- a/drivers/mtd/nand/raw/rockchip-nand-controller.c +++ b/drivers/mtd/nand/raw/rockchip-nand-controller.c @@ -562,9 +562,10 @@ static int rk_nfc_write_page_raw(struct nand_chip *chip, const u8 *buf, * BBM OOB1 OOB2 OOB3 |......| PA0 PA1 PA2 PA3 * * The rk_nfc_ooblayout_free() function already has reserved - * these 4 bytes with: + * these 4 bytes together with 2 bytes for BBM + * by reducing it's length: * - * oob_region->offset = NFC_SYS_DATA_SIZE + 2; + * oob_region->length = rknand->metadata_size - NFC_SYS_DATA_SIZE - 2; */ if (!i) memcpy(rk_nfc_oob_ptr(chip, i), @@ -597,7 +598,7 @@ static int rk_nfc_write_page_hwecc(struct nand_chip *chip, const u8 *buf, int pages_per_blk = mtd->erasesize / mtd->writesize; int ret = 0, i, boot_rom_mode = 0; dma_addr_t dma_data, dma_oob; - u32 reg; + u32 tmp; u8 *oob; nand_prog_page_begin_op(chip, page, 0, NULL, 0); @@ -624,6 +625,13 @@ static int rk_nfc_write_page_hwecc(struct nand_chip *chip, const u8 *buf, * * 0xFF 0xFF 0xFF 0xFF | BBM OOB1 OOB2 OOB3 | ... * + * The code here just swaps the first 4 bytes with the last + * 4 bytes without losing any data. + * + * The chip->oob_poi data layout: + * + * BBM OOB1 OOB2 OOB3 |......| PA0 PA1 PA2 PA3 + * * Configure the ECC algorithm supported by the boot ROM. */ if ((page < (pages_per_blk * rknand->boot_blks)) && @@ -634,21 +642,17 @@ static int rk_nfc_write_page_hwecc(struct nand_chip *chip, const u8 *buf, } for (i = 0; i < ecc->steps; i++) { - if (!i) { - reg = 0xFFFFFFFF; - } else { + if (!i) + oob = chip->oob_poi + (ecc->steps - 1) * NFC_SYS_DATA_SIZE; + else oob = chip->oob_poi + (i - 1) * NFC_SYS_DATA_SIZE; - reg = oob[0] | oob[1] << 8 | oob[2] << 16 | - oob[3] << 24; - } - if (!i && boot_rom_mode) - reg = (page & (pages_per_blk - 1)) * 4; + tmp = oob[0] | oob[1] << 8 | oob[2] << 16 | oob[3] << 24; if (nfc->cfg->type == NFC_V9) - nfc->oob_buf[i] = reg; + nfc->oob_buf[i] = tmp; else - nfc->oob_buf[i * (oob_step / 4)] = reg; + nfc->oob_buf[i * (oob_step / 4)] = tmp; } dma_data = dma_map_single(nfc->dev, (void *)nfc->page_buf, @@ -811,12 +815,17 @@ static int rk_nfc_read_page_hwecc(struct nand_chip *chip, u8 *buf, int oob_on, goto timeout_err; } - for (i = 1; i < ecc->steps; i++) { - oob = chip->oob_poi + (i - 1) * NFC_SYS_DATA_SIZE; + for (i = 0; i < ecc->steps; i++) { + if (!i) + oob = chip->oob_poi + (ecc->steps - 1) * NFC_SYS_DATA_SIZE; + else + oob = chip->oob_poi + (i - 1) * NFC_SYS_DATA_SIZE; + if (nfc->cfg->type == NFC_V9) tmp = nfc->oob_buf[i]; else tmp = nfc->oob_buf[i * (oob_step / 4)]; + *oob++ = (u8)tmp; *oob++ = (u8)(tmp >> 8); *oob++ = (u8)(tmp >> 16); @@ -933,12 +942,8 @@ static int rk_nfc_ooblayout_free(struct mtd_info *mtd, int section, if (section) return -ERANGE; - /* - * The beginning of the OOB area stores the reserved data for the NFC, - * the size of the reserved data is NFC_SYS_DATA_SIZE bytes. - */ oob_region->length = rknand->metadata_size - NFC_SYS_DATA_SIZE - 2; - oob_region->offset = NFC_SYS_DATA_SIZE + 2; + oob_region->offset = 2; return 0; } diff --git a/drivers/mtd/nand/spi/toshiba.c b/drivers/mtd/nand/spi/toshiba.c index 7380b1ebaccd..a80427c13121 100644 --- a/drivers/mtd/nand/spi/toshiba.c +++ b/drivers/mtd/nand/spi/toshiba.c @@ -73,7 +73,7 @@ static int tx58cxgxsxraix_ecc_get_status(struct spinand_device *spinand, { struct nand_device *nand = spinand_to_nand(spinand); u8 mbf = 0; - struct spi_mem_op op = SPINAND_GET_FEATURE_OP(0x30, &mbf); + struct spi_mem_op op = SPINAND_GET_FEATURE_OP(0x30, spinand->scratchbuf); switch (status & STATUS_ECC_MASK) { case STATUS_ECC_NO_BITFLIPS: @@ -92,7 +92,7 @@ static int tx58cxgxsxraix_ecc_get_status(struct spinand_device *spinand, if (spi_mem_exec_op(spinand->spimem, &op)) return nanddev_get_ecc_conf(nand)->strength; - mbf >>= 4; + mbf = *(spinand->scratchbuf) >> 4; if (WARN_ON(mbf > nanddev_get_ecc_conf(nand)->strength || !mbf)) return nanddev_get_ecc_conf(nand)->strength; diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c index 3ad58cd284d8..f507e3759301 100644 --- a/drivers/mtd/nand/spi/winbond.c +++ b/drivers/mtd/nand/spi/winbond.c @@ -108,7 +108,7 @@ static int w25n02kv_ecc_get_status(struct spinand_device *spinand, { struct nand_device *nand = spinand_to_nand(spinand); u8 mbf = 0; - struct spi_mem_op op = SPINAND_GET_FEATURE_OP(0x30, &mbf); + struct spi_mem_op op = SPINAND_GET_FEATURE_OP(0x30, spinand->scratchbuf); switch (status & STATUS_ECC_MASK) { case STATUS_ECC_NO_BITFLIPS: @@ -126,7 +126,7 @@ static int w25n02kv_ecc_get_status(struct spinand_device *spinand, if (spi_mem_exec_op(spinand->spimem, &op)) return nanddev_get_ecc_conf(nand)->strength; - mbf >>= 4; + mbf = *(spinand->scratchbuf) >> 4; if (WARN_ON(mbf > nanddev_get_ecc_conf(nand)->strength || !mbf)) return nanddev_get_ecc_conf(nand)->strength; diff --git a/drivers/mtd/spi-nor/spansion.c b/drivers/mtd/spi-nor/spansion.c index 36876aa849ed..15f9a80c10b9 100644 --- a/drivers/mtd/spi-nor/spansion.c +++ b/drivers/mtd/spi-nor/spansion.c @@ -361,7 +361,7 @@ static int cypress_nor_determine_addr_mode_by_sr1(struct spi_nor *nor, */ static int cypress_nor_set_addr_mode_nbytes(struct spi_nor *nor) { - struct spi_mem_op op = {}; + struct spi_mem_op op; u8 addr_mode; int ret; @@ -492,7 +492,7 @@ s25fs256t_post_bfpt_fixup(struct spi_nor *nor, const struct sfdp_parameter_header *bfpt_header, const struct sfdp_bfpt *bfpt) { - struct spi_mem_op op = {}; + struct spi_mem_op op; int ret; ret = cypress_nor_set_addr_mode_nbytes(nor); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 484c9e3e5e82..447b06ea4fc9 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -5901,7 +5901,9 @@ void bond_setup(struct net_device *bond_dev) bond_dev->hw_features = BOND_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_CTAG_FILTER; + NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_HW_VLAN_STAG_RX | + NETIF_F_HW_VLAN_STAG_FILTER; bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; bond_dev->features |= bond_dev->hw_features; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index cde253d27bd0..72374b066f64 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -1436,7 +1436,9 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) if (IS_ERR(priv->clk)) return PTR_ERR(priv->clk); - clk_prepare_enable(priv->clk); + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; priv->clk_mdiv = devm_clk_get_optional(&pdev->dev, "sw_switch_mdiv"); if (IS_ERR(priv->clk_mdiv)) { @@ -1444,7 +1446,9 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) goto out_clk; } - clk_prepare_enable(priv->clk_mdiv); + ret = clk_prepare_enable(priv->clk_mdiv); + if (ret) + goto out_clk; ret = bcm_sf2_sw_rst(priv); if (ret) { diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index b18cd170ec06..6c0623f88654 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -635,10 +635,9 @@ static const struct regmap_range ksz9477_valid_regs[] = { regmap_reg_range(0x1030, 0x1030), regmap_reg_range(0x1100, 0x1115), regmap_reg_range(0x111a, 0x111f), - regmap_reg_range(0x1122, 0x1127), - regmap_reg_range(0x112a, 0x112b), - regmap_reg_range(0x1136, 0x1139), - regmap_reg_range(0x113e, 0x113f), + regmap_reg_range(0x1120, 0x112b), + regmap_reg_range(0x1134, 0x113b), + regmap_reg_range(0x113c, 0x113f), regmap_reg_range(0x1400, 0x1401), regmap_reg_range(0x1403, 0x1403), regmap_reg_range(0x1410, 0x1417), @@ -669,10 +668,9 @@ static const struct regmap_range ksz9477_valid_regs[] = { regmap_reg_range(0x2030, 0x2030), regmap_reg_range(0x2100, 0x2115), regmap_reg_range(0x211a, 0x211f), - regmap_reg_range(0x2122, 0x2127), - regmap_reg_range(0x212a, 0x212b), - regmap_reg_range(0x2136, 0x2139), - regmap_reg_range(0x213e, 0x213f), + regmap_reg_range(0x2120, 0x212b), + regmap_reg_range(0x2134, 0x213b), + regmap_reg_range(0x213c, 0x213f), regmap_reg_range(0x2400, 0x2401), regmap_reg_range(0x2403, 0x2403), regmap_reg_range(0x2410, 0x2417), @@ -703,10 +701,9 @@ static const struct regmap_range ksz9477_valid_regs[] = { regmap_reg_range(0x3030, 0x3030), regmap_reg_range(0x3100, 0x3115), regmap_reg_range(0x311a, 0x311f), - regmap_reg_range(0x3122, 0x3127), - regmap_reg_range(0x312a, 0x312b), - regmap_reg_range(0x3136, 0x3139), - regmap_reg_range(0x313e, 0x313f), + regmap_reg_range(0x3120, 0x312b), + regmap_reg_range(0x3134, 0x313b), + regmap_reg_range(0x313c, 0x313f), regmap_reg_range(0x3400, 0x3401), regmap_reg_range(0x3403, 0x3403), regmap_reg_range(0x3410, 0x3417), @@ -737,10 +734,9 @@ static const struct regmap_range ksz9477_valid_regs[] = { regmap_reg_range(0x4030, 0x4030), regmap_reg_range(0x4100, 0x4115), regmap_reg_range(0x411a, 0x411f), - regmap_reg_range(0x4122, 0x4127), - regmap_reg_range(0x412a, 0x412b), - regmap_reg_range(0x4136, 0x4139), - regmap_reg_range(0x413e, 0x413f), + regmap_reg_range(0x4120, 0x412b), + regmap_reg_range(0x4134, 0x413b), + regmap_reg_range(0x413c, 0x413f), regmap_reg_range(0x4400, 0x4401), regmap_reg_range(0x4403, 0x4403), regmap_reg_range(0x4410, 0x4417), @@ -771,10 +767,9 @@ static const struct regmap_range ksz9477_valid_regs[] = { regmap_reg_range(0x5030, 0x5030), regmap_reg_range(0x5100, 0x5115), regmap_reg_range(0x511a, 0x511f), - regmap_reg_range(0x5122, 0x5127), - regmap_reg_range(0x512a, 0x512b), - regmap_reg_range(0x5136, 0x5139), - regmap_reg_range(0x513e, 0x513f), + regmap_reg_range(0x5120, 0x512b), + regmap_reg_range(0x5134, 0x513b), + regmap_reg_range(0x513c, 0x513f), regmap_reg_range(0x5400, 0x5401), regmap_reg_range(0x5403, 0x5403), regmap_reg_range(0x5410, 0x5417), diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 8da46d284e35..bef879c6d500 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1625,8 +1625,10 @@ static void felix_teardown(struct dsa_switch *ds) struct felix *felix = ocelot_to_felix(ocelot); struct dsa_port *dp; + rtnl_lock(); if (felix->tag_proto_ops) felix->tag_proto_ops->teardown(ds); + rtnl_unlock(); dsa_switch_for_each_available_port(dp, ds) ocelot_deinit_port(ocelot, dp->index); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index e5b54e6025be..1eb490c48c52 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -633,12 +633,13 @@ tx_kick_pending: return NETDEV_TX_OK; } -static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) +static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget) { struct bnxt_tx_ring_info *txr = bnapi->tx_ring; struct netdev_queue *txq = netdev_get_tx_queue(bp->dev, txr->txq_index); u16 cons = txr->tx_cons; struct pci_dev *pdev = bp->pdev; + int nr_pkts = bnapi->tx_pkts; int i; unsigned int tx_bytes = 0; @@ -688,6 +689,7 @@ next_tx_int: dev_kfree_skb_any(skb); } + bnapi->tx_pkts = 0; WRITE_ONCE(txr->tx_cons, cons); __netif_txq_completed_wake(txq, nr_pkts, tx_bytes, @@ -697,17 +699,24 @@ next_tx_int: static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping, struct bnxt_rx_ring_info *rxr, + unsigned int *offset, gfp_t gfp) { struct device *dev = &bp->pdev->dev; struct page *page; - page = page_pool_dev_alloc_pages(rxr->page_pool); + if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) { + page = page_pool_dev_alloc_frag(rxr->page_pool, offset, + BNXT_RX_PAGE_SIZE); + } else { + page = page_pool_dev_alloc_pages(rxr->page_pool); + *offset = 0; + } if (!page) return NULL; - *mapping = dma_map_page_attrs(dev, page, 0, PAGE_SIZE, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); + *mapping = dma_map_page_attrs(dev, page, *offset, BNXT_RX_PAGE_SIZE, + bp->rx_dir, DMA_ATTR_WEAK_ORDERING); if (dma_mapping_error(dev, *mapping)) { page_pool_recycle_direct(rxr->page_pool, page); return NULL; @@ -747,15 +756,16 @@ int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, dma_addr_t mapping; if (BNXT_RX_PAGE_MODE(bp)) { + unsigned int offset; struct page *page = - __bnxt_alloc_rx_page(bp, &mapping, rxr, gfp); + __bnxt_alloc_rx_page(bp, &mapping, rxr, &offset, gfp); if (!page) return -ENOMEM; mapping += bp->rx_dma_offset; rx_buf->data = page; - rx_buf->data_ptr = page_address(page) + bp->rx_offset; + rx_buf->data_ptr = page_address(page) + offset + bp->rx_offset; } else { u8 *data = __bnxt_alloc_rx_frag(bp, &mapping, gfp); @@ -815,7 +825,7 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp, unsigned int offset = 0; if (BNXT_RX_PAGE_MODE(bp)) { - page = __bnxt_alloc_rx_page(bp, &mapping, rxr, gfp); + page = __bnxt_alloc_rx_page(bp, &mapping, rxr, &offset, gfp); if (!page) return -ENOMEM; @@ -962,15 +972,15 @@ static struct sk_buff *bnxt_rx_multi_page_skb(struct bnxt *bp, return NULL; } dma_addr -= bp->rx_dma_offset; - dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); - skb = build_skb(page_address(page), PAGE_SIZE); + dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE, + bp->rx_dir, DMA_ATTR_WEAK_ORDERING); + skb = build_skb(data_ptr - bp->rx_offset, BNXT_RX_PAGE_SIZE); if (!skb) { page_pool_recycle_direct(rxr->page_pool, page); return NULL; } skb_mark_for_recycle(skb); - skb_reserve(skb, bp->rx_dma_offset); + skb_reserve(skb, bp->rx_offset); __skb_put(skb, len); return skb; @@ -996,8 +1006,8 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, return NULL; } dma_addr -= bp->rx_dma_offset; - dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); + dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE, + bp->rx_dir, DMA_ATTR_WEAK_ORDERING); if (unlikely(!payload)) payload = eth_get_headlen(bp->dev, data_ptr, len); @@ -1010,7 +1020,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, skb_mark_for_recycle(skb); off = (void *)data_ptr - page_address(page); - skb_add_rx_frag(skb, 0, page, off, len, PAGE_SIZE); + skb_add_rx_frag(skb, 0, page, off, len, BNXT_RX_PAGE_SIZE); memcpy(skb->data - NET_IP_ALIGN, data_ptr - NET_IP_ALIGN, payload + NET_IP_ALIGN); @@ -1141,7 +1151,7 @@ static struct sk_buff *bnxt_rx_agg_pages_skb(struct bnxt *bp, skb->data_len += total_frag_len; skb->len += total_frag_len; - skb->truesize += PAGE_SIZE * agg_bufs; + skb->truesize += BNXT_RX_PAGE_SIZE * agg_bufs; return skb; } @@ -2569,12 +2579,11 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, return rx_pkts; } -static void __bnxt_poll_work_done(struct bnxt *bp, struct bnxt_napi *bnapi) +static void __bnxt_poll_work_done(struct bnxt *bp, struct bnxt_napi *bnapi, + int budget) { - if (bnapi->tx_pkts) { - bnapi->tx_int(bp, bnapi, bnapi->tx_pkts); - bnapi->tx_pkts = 0; - } + if (bnapi->tx_pkts) + bnapi->tx_int(bp, bnapi, budget); if ((bnapi->events & BNXT_RX_EVENT) && !(bnapi->in_reset)) { struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; @@ -2603,7 +2612,7 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, */ bnxt_db_cq(bp, &cpr->cp_db, cpr->cp_raw_cons); - __bnxt_poll_work_done(bp, bnapi); + __bnxt_poll_work_done(bp, bnapi, budget); return rx_pkts; } @@ -2734,7 +2743,7 @@ static int __bnxt_poll_cqs(struct bnxt *bp, struct bnxt_napi *bnapi, int budget) } static void __bnxt_poll_cqs_done(struct bnxt *bp, struct bnxt_napi *bnapi, - u64 dbr_type) + u64 dbr_type, int budget) { struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; int i; @@ -2750,7 +2759,7 @@ static void __bnxt_poll_cqs_done(struct bnxt *bp, struct bnxt_napi *bnapi, cpr2->had_work_done = 0; } } - __bnxt_poll_work_done(bp, bnapi); + __bnxt_poll_work_done(bp, bnapi, budget); } static int bnxt_poll_p5(struct napi_struct *napi, int budget) @@ -2780,7 +2789,8 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget) if (cpr->has_more_work) break; - __bnxt_poll_cqs_done(bp, bnapi, DBR_TYPE_CQ_ARMALL); + __bnxt_poll_cqs_done(bp, bnapi, DBR_TYPE_CQ_ARMALL, + budget); cpr->cp_raw_cons = raw_cons; if (napi_complete_done(napi, work_done)) BNXT_DB_NQ_ARM_P5(&cpr->cp_db, @@ -2810,7 +2820,7 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget) } raw_cons = NEXT_RAW_CMP(raw_cons); } - __bnxt_poll_cqs_done(bp, bnapi, DBR_TYPE_CQ); + __bnxt_poll_cqs_done(bp, bnapi, DBR_TYPE_CQ, budget); if (raw_cons != cpr->cp_raw_cons) { cpr->cp_raw_cons = raw_cons; BNXT_DB_NQ_P5(&cpr->cp_db, raw_cons); @@ -2943,8 +2953,8 @@ skip_rx_tpa_free: rx_buf->data = NULL; if (BNXT_RX_PAGE_MODE(bp)) { mapping -= bp->rx_dma_offset; - dma_unmap_page_attrs(&pdev->dev, mapping, PAGE_SIZE, - bp->rx_dir, + dma_unmap_page_attrs(&pdev->dev, mapping, + BNXT_RX_PAGE_SIZE, bp->rx_dir, DMA_ATTR_WEAK_ORDERING); page_pool_recycle_direct(rxr->page_pool, data); } else { @@ -3213,6 +3223,8 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp, pp.napi = &rxr->bnapi->napi; pp.dev = &bp->pdev->dev; pp.dma_dir = DMA_BIDIRECTIONAL; + if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) + pp.flags |= PP_FLAG_PAGE_FRAG; rxr->page_pool = page_pool_create(&pp); if (IS_ERR(rxr->page_pool)) { @@ -3989,26 +4001,29 @@ void bnxt_set_ring_params(struct bnxt *bp) */ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode) { + struct net_device *dev = bp->dev; + if (page_mode) { bp->flags &= ~BNXT_FLAG_AGG_RINGS; bp->flags |= BNXT_FLAG_RX_PAGE_MODE; - if (bp->dev->mtu > BNXT_MAX_PAGE_MODE_MTU) { + if (bp->xdp_prog->aux->xdp_has_frags) + dev->max_mtu = min_t(u16, bp->max_mtu, BNXT_MAX_MTU); + else + dev->max_mtu = + min_t(u16, bp->max_mtu, BNXT_MAX_PAGE_MODE_MTU); + if (dev->mtu > BNXT_MAX_PAGE_MODE_MTU) { bp->flags |= BNXT_FLAG_JUMBO; bp->rx_skb_func = bnxt_rx_multi_page_skb; - bp->dev->max_mtu = - min_t(u16, bp->max_mtu, BNXT_MAX_MTU); } else { bp->flags |= BNXT_FLAG_NO_AGG_RINGS; bp->rx_skb_func = bnxt_rx_page_skb; - bp->dev->max_mtu = - min_t(u16, bp->max_mtu, BNXT_MAX_PAGE_MODE_MTU); } bp->rx_dir = DMA_BIDIRECTIONAL; /* Disable LRO or GRO_HW */ - netdev_update_features(bp->dev); + netdev_update_features(dev); } else { - bp->dev->max_mtu = bp->max_mtu; + dev->max_mtu = bp->max_mtu; bp->flags &= ~BNXT_FLAG_RX_PAGE_MODE; bp->rx_dir = DMA_FROM_DEVICE; bp->rx_skb_func = bnxt_rx_skb; @@ -9429,6 +9444,8 @@ static void bnxt_enable_napi(struct bnxt *bp) cpr->sw_stats.rx.rx_resets++; bnapi->in_reset = false; + bnapi->tx_pkts = 0; + if (bnapi->rx_ring) { INIT_WORK(&cpr->dim.work, bnxt_dim_work); cpr->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 080e73496066..bb95c3dc5270 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1005,7 +1005,7 @@ struct bnxt_napi { struct bnxt_tx_ring_info *tx_ring; void (*tx_int)(struct bnxt *, struct bnxt_napi *, - int); + int budget); int tx_pkts; u8 events; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 4efa5fe6972b..fb43232310b2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -125,16 +125,20 @@ static void __bnxt_xmit_xdp_redirect(struct bnxt *bp, dma_unmap_len_set(tx_buf, len, 0); } -void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) +void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int budget) { struct bnxt_tx_ring_info *txr = bnapi->tx_ring; struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; bool rx_doorbell_needed = false; + int nr_pkts = bnapi->tx_pkts; struct bnxt_sw_tx_bd *tx_buf; u16 tx_cons = txr->tx_cons; u16 last_tx_cons = tx_cons; int i, j, frags; + if (!budget) + return; + for (i = 0; i < nr_pkts; i++) { tx_buf = &txr->tx_buf_ring[tx_cons]; @@ -161,6 +165,8 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) } tx_cons = NEXT_TX(tx_cons); } + + bnapi->tx_pkts = 0; WRITE_ONCE(txr->tx_cons, tx_cons); if (rx_doorbell_needed) { tx_buf = &txr->tx_buf_ring[last_tx_cons]; @@ -180,8 +186,8 @@ void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, u8 *data_ptr, unsigned int len, struct xdp_buff *xdp) { + u32 buflen = BNXT_RX_PAGE_SIZE; struct bnxt_sw_rx_bd *rx_buf; - u32 buflen = PAGE_SIZE; struct pci_dev *pdev; dma_addr_t mapping; u32 offset; @@ -297,7 +303,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, rx_buf = &rxr->rx_buf_ring[cons]; mapping = rx_buf->mapping - bp->rx_dma_offset; dma_unmap_page_attrs(&pdev->dev, mapping, - PAGE_SIZE, bp->rx_dir, + BNXT_RX_PAGE_SIZE, bp->rx_dir, DMA_ATTR_WEAK_ORDERING); /* if we are unable to allocate a new buffer, abort and reuse */ @@ -480,7 +486,7 @@ bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb, u8 num_frags, } xdp_update_skb_shared_info(skb, num_frags, sinfo->xdp_frags_size, - PAGE_SIZE * sinfo->nr_frags, + BNXT_RX_PAGE_SIZE * sinfo->nr_frags, xdp_buff_is_frag_pfmemalloc(xdp)); return skb; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h index ea430d6961df..5e412c5655ba 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h @@ -16,7 +16,7 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, struct bnxt_tx_ring_info *txr, dma_addr_t mapping, u32 len, struct xdp_buff *xdp); -void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts); +void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int budget); bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, struct xdp_buff xdp, struct page *page, u8 **data_ptr, unsigned int *len, u8 *event); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 1416262d4296..e0a4cb7e3f50 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -1186,14 +1186,9 @@ static int enetc_init_port_rss_memory(struct enetc_si *si) static int enetc_pf_register_with_ierb(struct pci_dev *pdev) { - struct device_node *node = pdev->dev.of_node; struct platform_device *ierb_pdev; struct device_node *ierb_node; - /* Don't register with the IERB if the PF itself is disabled */ - if (!node || !of_device_is_available(node)) - return 0; - ierb_node = of_find_compatible_node(NULL, NULL, "fsl,ls1028a-enetc-ierb"); if (!ierb_node || !of_device_is_available(ierb_node)) @@ -1208,56 +1203,81 @@ static int enetc_pf_register_with_ierb(struct pci_dev *pdev) return enetc_ierb_register_pf(ierb_pdev, pdev); } -static int enetc_pf_probe(struct pci_dev *pdev, - const struct pci_device_id *ent) +static struct enetc_si *enetc_psi_create(struct pci_dev *pdev) { - struct device_node *node = pdev->dev.of_node; - struct enetc_ndev_priv *priv; - struct net_device *ndev; struct enetc_si *si; - struct enetc_pf *pf; int err; - err = enetc_pf_register_with_ierb(pdev); - if (err == -EPROBE_DEFER) - return err; - if (err) - dev_warn(&pdev->dev, - "Could not register with IERB driver: %pe, please update the device tree\n", - ERR_PTR(err)); - - err = enetc_pci_probe(pdev, KBUILD_MODNAME, sizeof(*pf)); - if (err) - return dev_err_probe(&pdev->dev, err, "PCI probing failed\n"); + err = enetc_pci_probe(pdev, KBUILD_MODNAME, sizeof(struct enetc_pf)); + if (err) { + dev_err_probe(&pdev->dev, err, "PCI probing failed\n"); + goto out; + } si = pci_get_drvdata(pdev); if (!si->hw.port || !si->hw.global) { err = -ENODEV; dev_err(&pdev->dev, "could not map PF space, probing a VF?\n"); - goto err_map_pf_space; + goto out_pci_remove; } err = enetc_setup_cbdr(&pdev->dev, &si->hw, ENETC_CBDR_DEFAULT_SIZE, &si->cbd_ring); if (err) - goto err_setup_cbdr; + goto out_pci_remove; err = enetc_init_port_rfs_memory(si); if (err) { dev_err(&pdev->dev, "Failed to initialize RFS memory\n"); - goto err_init_port_rfs; + goto out_teardown_cbdr; } err = enetc_init_port_rss_memory(si); if (err) { dev_err(&pdev->dev, "Failed to initialize RSS memory\n"); - goto err_init_port_rss; + goto out_teardown_cbdr; } - if (node && !of_device_is_available(node)) { - dev_info(&pdev->dev, "device is disabled, skipping\n"); - err = -ENODEV; - goto err_device_disabled; + return si; + +out_teardown_cbdr: + enetc_teardown_cbdr(&si->cbd_ring); +out_pci_remove: + enetc_pci_remove(pdev); +out: + return ERR_PTR(err); +} + +static void enetc_psi_destroy(struct pci_dev *pdev) +{ + struct enetc_si *si = pci_get_drvdata(pdev); + + enetc_teardown_cbdr(&si->cbd_ring); + enetc_pci_remove(pdev); +} + +static int enetc_pf_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct device_node *node = pdev->dev.of_node; + struct enetc_ndev_priv *priv; + struct net_device *ndev; + struct enetc_si *si; + struct enetc_pf *pf; + int err; + + err = enetc_pf_register_with_ierb(pdev); + if (err == -EPROBE_DEFER) + return err; + if (err) + dev_warn(&pdev->dev, + "Could not register with IERB driver: %pe, please update the device tree\n", + ERR_PTR(err)); + + si = enetc_psi_create(pdev); + if (IS_ERR(si)) { + err = PTR_ERR(si); + goto err_psi_create; } pf = enetc_si_priv(si); @@ -1339,15 +1359,9 @@ err_alloc_si_res: si->ndev = NULL; free_netdev(ndev); err_alloc_netdev: -err_init_port_rss: -err_init_port_rfs: -err_device_disabled: err_setup_mac_addresses: - enetc_teardown_cbdr(&si->cbd_ring); -err_setup_cbdr: -err_map_pf_space: - enetc_pci_remove(pdev); - + enetc_psi_destroy(pdev); +err_psi_create: return err; } @@ -1370,12 +1384,29 @@ static void enetc_pf_remove(struct pci_dev *pdev) enetc_free_msix(priv); enetc_free_si_resources(priv); - enetc_teardown_cbdr(&si->cbd_ring); free_netdev(si->ndev); - enetc_pci_remove(pdev); + enetc_psi_destroy(pdev); +} + +static void enetc_fixup_clear_rss_rfs(struct pci_dev *pdev) +{ + struct device_node *node = pdev->dev.of_node; + struct enetc_si *si; + + /* Only apply quirk for disabled functions. For the ones + * that are enabled, enetc_pf_probe() will apply it. + */ + if (node && of_device_is_available(node)) + return; + + si = enetc_psi_create(pdev); + if (si) + enetc_psi_destroy(pdev); } +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_PF, + enetc_fixup_clear_rss_rfs); static const struct pci_device_id enetc_pf_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_PF) }, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 52546f625c8b..f276b5ecb431 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -464,9 +464,9 @@ static void hns3_dbg_fill_content(char *content, u16 len, if (result) { if (item_len < strlen(result[i])) break; - strscpy(pos, result[i], strlen(result[i])); + memcpy(pos, result[i], strlen(result[i])); } else { - strscpy(pos, items[i].name, strlen(items[i].name)); + memcpy(pos, items[i].name, strlen(items[i].name)); } pos += item_len; len -= item_len; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 9f6890059666..b7b51e56b030 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5854,6 +5854,9 @@ void hns3_external_lb_prepare(struct net_device *ndev, bool if_running) if (!if_running) return; + if (test_and_set_bit(HNS3_NIC_STATE_DOWN, &priv->state)) + return; + netif_carrier_off(ndev); netif_tx_disable(ndev); @@ -5882,7 +5885,16 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running) if (!if_running) return; - hns3_nic_reset_all_ring(priv->ae_handle); + if (hns3_nic_resetting(ndev)) + return; + + if (!test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) + return; + + if (hns3_nic_reset_all_ring(priv->ae_handle)) + return; + + clear_bit(HNS3_NIC_STATE_DOWN, &priv->state); for (i = 0; i < priv->vector_num; i++) hns3_vector_enable(&priv->tqp_vector[i]); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 409db2e70965..0fb2eaee3e8a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -111,9 +111,9 @@ static void hclge_dbg_fill_content(char *content, u16 len, if (result) { if (item_len < strlen(result[i])) break; - strscpy(pos, result[i], strlen(result[i])); + memcpy(pos, result[i], strlen(result[i])); } else { - strscpy(pos, items[i].name, strlen(items[i].name)); + memcpy(pos, items[i].name, strlen(items[i].name)); } pos += item_len; len -= item_len; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index bf675c15fbb9..a940e35aef29 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -72,6 +72,8 @@ static void hclge_restore_hw_table(struct hclge_dev *hdev); static void hclge_sync_promisc_mode(struct hclge_dev *hdev); static void hclge_sync_fd_table(struct hclge_dev *hdev); static void hclge_update_fec_stats(struct hclge_dev *hdev); +static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret, + int wait_cnt); static struct hnae3_ae_algo ae_algo; @@ -7558,6 +7560,8 @@ static void hclge_enable_fd(struct hnae3_handle *handle, bool enable) static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) { +#define HCLGE_LINK_STATUS_WAIT_CNT 3 + struct hclge_desc desc; struct hclge_config_mac_mode_cmd *req = (struct hclge_config_mac_mode_cmd *)desc.data; @@ -7582,9 +7586,15 @@ static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en); ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) + if (ret) { dev_err(&hdev->pdev->dev, "mac enable fail, ret =%d.\n", ret); + return; + } + + if (!enable) + hclge_mac_link_status_wait(hdev, HCLGE_LINK_STATUS_DOWN, + HCLGE_LINK_STATUS_WAIT_CNT); } static int hclge_config_switch_param(struct hclge_dev *hdev, int vfid, @@ -7647,10 +7657,9 @@ static void hclge_phy_link_status_wait(struct hclge_dev *hdev, } while (++i < HCLGE_PHY_LINK_STATUS_NUM); } -static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret) +static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret, + int wait_cnt) { -#define HCLGE_MAC_LINK_STATUS_NUM 100 - int link_status; int i = 0; int ret; @@ -7663,13 +7672,15 @@ static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret) return 0; msleep(HCLGE_LINK_STATUS_MS); - } while (++i < HCLGE_MAC_LINK_STATUS_NUM); + } while (++i < wait_cnt); return -EBUSY; } static int hclge_mac_phy_link_status_wait(struct hclge_dev *hdev, bool en, bool is_phy) { +#define HCLGE_MAC_LINK_STATUS_NUM 100 + int link_ret; link_ret = en ? HCLGE_LINK_STATUS_UP : HCLGE_LINK_STATUS_DOWN; @@ -7677,7 +7688,8 @@ static int hclge_mac_phy_link_status_wait(struct hclge_dev *hdev, bool en, if (is_phy) hclge_phy_link_status_wait(hdev, link_ret); - return hclge_mac_link_status_wait(hdev, link_ret); + return hclge_mac_link_status_wait(hdev, link_ret, + HCLGE_MAC_LINK_STATUS_NUM); } static int hclge_set_app_loopback(struct hclge_dev *hdev, bool en) @@ -10915,9 +10927,12 @@ int hclge_cfg_flowctrl(struct hclge_dev *hdev) u32 rx_pause, tx_pause; u8 flowctl; - if (!phydev->link || !phydev->autoneg) + if (!phydev->link) return 0; + if (!phydev->autoneg) + return hclge_mac_pause_setup_hw(hdev); + local_advertising = linkmode_adv_to_lcl_adv_t(phydev->advertising); if (phydev->pause) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index de509e5751a7..c58c31221762 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -1553,7 +1553,7 @@ static int hclge_bp_setup_hw(struct hclge_dev *hdev, u8 tc) return 0; } -static int hclge_mac_pause_setup_hw(struct hclge_dev *hdev) +int hclge_mac_pause_setup_hw(struct hclge_dev *hdev) { bool tx_en, rx_en; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index 45dcfef3f90c..53eec6df5194 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -245,6 +245,7 @@ int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, u8 pfc_bitmap); int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx); int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr); +int hclge_mac_pause_setup_hw(struct hclge_dev *hdev); void hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats); void hclge_pfc_tx_stats_get(struct hclge_dev *hdev, u64 *stats); int hclge_tm_qs_shaper_cfg(struct hclge_vport *vport, int max_tx_rate); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 763d613adbcc..df76cdaddcfb 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -97,6 +97,8 @@ static int pending_scrq(struct ibmvnic_adapter *, static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *, struct ibmvnic_sub_crq_queue *); static int ibmvnic_poll(struct napi_struct *napi, int data); +static int reset_sub_crq_queues(struct ibmvnic_adapter *adapter); +static inline void reinit_init_done(struct ibmvnic_adapter *adapter); static void send_query_map(struct ibmvnic_adapter *adapter); static int send_request_map(struct ibmvnic_adapter *, dma_addr_t, u32, u8); static int send_request_unmap(struct ibmvnic_adapter *, u8); @@ -114,6 +116,7 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter, static void free_long_term_buff(struct ibmvnic_adapter *adapter, struct ibmvnic_long_term_buff *ltb); static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter); +static void flush_reset_queue(struct ibmvnic_adapter *adapter); struct ibmvnic_stat { char name[ETH_GSTRING_LEN]; @@ -1505,8 +1508,8 @@ static const char *adapter_state_to_string(enum vnic_state state) static int ibmvnic_login(struct net_device *netdev) { + unsigned long flags, timeout = msecs_to_jiffies(20000); struct ibmvnic_adapter *adapter = netdev_priv(netdev); - unsigned long timeout = msecs_to_jiffies(20000); int retry_count = 0; int retries = 10; bool retry; @@ -1527,11 +1530,9 @@ static int ibmvnic_login(struct net_device *netdev) if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { - netdev_warn(netdev, "Login timed out, retrying...\n"); - retry = true; - adapter->init_done_rc = 0; - retry_count++; - continue; + netdev_warn(netdev, "Login timed out\n"); + adapter->login_pending = false; + goto partial_reset; } if (adapter->init_done_rc == ABORTED) { @@ -1573,10 +1574,69 @@ static int ibmvnic_login(struct net_device *netdev) "SCRQ irq initialization failed\n"); return rc; } + /* Default/timeout error handling, reset and start fresh */ } else if (adapter->init_done_rc) { netdev_warn(netdev, "Adapter login failed, init_done_rc = %d\n", adapter->init_done_rc); - return -EIO; + +partial_reset: + /* adapter login failed, so free any CRQs or sub-CRQs + * and register again before attempting to login again. + * If we don't do this then the VIOS may think that + * we are already logged in and reject any subsequent + * attempts + */ + netdev_warn(netdev, + "Freeing and re-registering CRQs before attempting to login again\n"); + retry = true; + adapter->init_done_rc = 0; + release_sub_crqs(adapter, true); + /* Much of this is similar logic as ibmvnic_probe(), + * we are essentially re-initializing communication + * with the server. We really should not run any + * resets/failovers here because this is already a form + * of reset and we do not want parallel resets occurring + */ + do { + reinit_init_done(adapter); + /* Clear any failovers we got in the previous + * pass since we are re-initializing the CRQ + */ + adapter->failover_pending = false; + release_crq_queue(adapter); + /* If we don't sleep here then we risk an + * unnecessary failover event from the VIOS. + * This is a known VIOS issue caused by a vnic + * device freeing and registering a CRQ too + * quickly. + */ + msleep(1500); + /* Avoid any resets, since we are currently + * resetting. + */ + spin_lock_irqsave(&adapter->rwi_lock, flags); + flush_reset_queue(adapter); + spin_unlock_irqrestore(&adapter->rwi_lock, + flags); + + rc = init_crq_queue(adapter); + if (rc) { + netdev_err(netdev, "login recovery: init CRQ failed %d\n", + rc); + return -EIO; + } + + rc = ibmvnic_reset_init(adapter, false); + if (rc) + netdev_err(netdev, "login recovery: Reset init failed %d\n", + rc); + /* IBMVNIC_CRQ_INIT will return EAGAIN if it + * fails, since ibmvnic_reset_init will free + * irq's in failure, we won't be able to receive + * new CRQs so we need to keep trying. probe() + * handles this similarly. + */ + } while (rc == -EAGAIN && retry_count++ < retries); } } while (retry); @@ -1588,12 +1648,22 @@ static int ibmvnic_login(struct net_device *netdev) static void release_login_buffer(struct ibmvnic_adapter *adapter) { + if (!adapter->login_buf) + return; + + dma_unmap_single(&adapter->vdev->dev, adapter->login_buf_token, + adapter->login_buf_sz, DMA_TO_DEVICE); kfree(adapter->login_buf); adapter->login_buf = NULL; } static void release_login_rsp_buffer(struct ibmvnic_adapter *adapter) { + if (!adapter->login_rsp_buf) + return; + + dma_unmap_single(&adapter->vdev->dev, adapter->login_rsp_buf_token, + adapter->login_rsp_buf_sz, DMA_FROM_DEVICE); kfree(adapter->login_rsp_buf); adapter->login_rsp_buf = NULL; } @@ -4830,11 +4900,14 @@ static int send_login(struct ibmvnic_adapter *adapter) if (rc) { adapter->login_pending = false; netdev_err(adapter->netdev, "Failed to send login, rc=%d\n", rc); - goto buf_rsp_map_failed; + goto buf_send_failed; } return 0; +buf_send_failed: + dma_unmap_single(dev, rsp_buffer_token, rsp_buffer_size, + DMA_FROM_DEVICE); buf_rsp_map_failed: kfree(login_rsp_buffer); adapter->login_rsp_buf = NULL; @@ -5396,6 +5469,7 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, int num_tx_pools; int num_rx_pools; u64 *size_array; + u32 rsp_len; int i; /* CHECK: Test/set of login_pending does not need to be atomic @@ -5407,11 +5481,6 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, } adapter->login_pending = false; - dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz, - DMA_TO_DEVICE); - dma_unmap_single(dev, adapter->login_rsp_buf_token, - adapter->login_rsp_buf_sz, DMA_FROM_DEVICE); - /* If the number of queues requested can't be allocated by the * server, the login response will return with code 1. We will need * to resend the login buffer with fewer queues requested. @@ -5447,6 +5516,23 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, ibmvnic_reset(adapter, VNIC_RESET_FATAL); return -EIO; } + + rsp_len = be32_to_cpu(login_rsp->len); + if (be32_to_cpu(login->login_rsp_len) < rsp_len || + rsp_len <= be32_to_cpu(login_rsp->off_txsubm_subcrqs) || + rsp_len <= be32_to_cpu(login_rsp->off_rxadd_subcrqs) || + rsp_len <= be32_to_cpu(login_rsp->off_rxadd_buff_size) || + rsp_len <= be32_to_cpu(login_rsp->off_supp_tx_desc)) { + /* This can happen if a login request times out and there are + * 2 outstanding login requests sent, the LOGIN_RSP crq + * could have been for the older login request. So we are + * parsing the newer response buffer which may be incomplete + */ + dev_err(dev, "FATAL: Login rsp offsets/lengths invalid\n"); + ibmvnic_reset(adapter, VNIC_RESET_FATAL); + return -EIO; + } + size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size)); /* variable buffer sizes are not supported, so just read the diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 2f47cfa7f06e..460ca561819a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -1401,14 +1401,15 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx if (fsp->flow_type & FLOW_MAC_EXT) return -EINVAL; + spin_lock_bh(&adapter->fdir_fltr_lock); if (adapter->fdir_active_fltr >= IAVF_MAX_FDIR_FILTERS) { + spin_unlock_bh(&adapter->fdir_fltr_lock); dev_err(&adapter->pdev->dev, "Unable to add Flow Director filter because VF reached the limit of max allowed filters (%u)\n", IAVF_MAX_FDIR_FILTERS); return -ENOSPC; } - spin_lock_bh(&adapter->fdir_fltr_lock); if (iavf_find_fdir_fltr_by_loc(adapter, fsp->location)) { dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, it already exists\n"); spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -1781,7 +1782,9 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, case ETHTOOL_GRXCLSRLCNT: if (!FDIR_FLTR_SUPPORT(adapter)) break; + spin_lock_bh(&adapter->fdir_fltr_lock); cmd->rule_cnt = adapter->fdir_active_fltr; + spin_unlock_bh(&adapter->fdir_fltr_lock); cmd->data = IAVF_MAX_FDIR_FILTERS; ret = 0; break; diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c index 6146203efd84..505e82ebafe4 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c @@ -722,7 +722,9 @@ void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *f bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr) { struct iavf_fdir_fltr *tmp; + bool ret = false; + spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(tmp, &adapter->fdir_list_head, list) { if (tmp->flow_type != fltr->flow_type) continue; @@ -732,11 +734,14 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr * !memcmp(&tmp->ip_data, &fltr->ip_data, sizeof(fltr->ip_data)) && !memcmp(&tmp->ext_data, &fltr->ext_data, - sizeof(fltr->ext_data))) - return true; + sizeof(fltr->ext_data))) { + ret = true; + break; + } } + spin_unlock_bh(&adapter->fdir_fltr_lock); - return false; + return ret; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index f02d44455772..cf92c39467c8 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -8813,6 +8813,7 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type, { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_pf *pf = np->vsi->back; + bool locked = false; int err; switch (type) { @@ -8822,10 +8823,27 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type, ice_setup_tc_block_cb, np, np, true); case TC_SETUP_QDISC_MQPRIO: + if (pf->adev) { + mutex_lock(&pf->adev_mutex); + device_lock(&pf->adev->dev); + locked = true; + if (pf->adev->dev.driver) { + netdev_err(netdev, "Cannot change qdisc when RDMA is active\n"); + err = -EBUSY; + goto adev_unlock; + } + } + /* setup traffic classifier for receive side */ mutex_lock(&pf->tc_mutex); err = ice_setup_tc_mqprio_qdisc(netdev, type_data); mutex_unlock(&pf->tc_mutex); + +adev_unlock: + if (locked) { + device_unlock(&pf->adev->dev); + mutex_unlock(&pf->adev_mutex); + } return err; default: return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 9db384f66a8e..38901d2a4680 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -195,6 +195,10 @@ struct igc_adapter { u32 qbv_config_change_errors; bool qbv_transition; unsigned int qbv_count; + /* Access to oper_gate_closed, admin_gate_closed and qbv_transition + * are protected by the qbv_tx_lock. + */ + spinlock_t qbv_tx_lock; /* OS defined structs */ struct pci_dev *pdev; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index bdeb36790d77..6f557e843e49 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -4801,6 +4801,7 @@ static int igc_sw_init(struct igc_adapter *adapter) adapter->nfc_rule_count = 0; spin_lock_init(&adapter->stats64_lock); + spin_lock_init(&adapter->qbv_tx_lock); /* Assume MSI-X interrupts, will be checked during IRQ allocation */ adapter->flags |= IGC_FLAG_HAS_MSIX; @@ -6119,15 +6120,15 @@ static int igc_tsn_enable_launchtime(struct igc_adapter *adapter, return igc_tsn_offload_apply(adapter); } -static int igc_tsn_clear_schedule(struct igc_adapter *adapter) +static int igc_qbv_clear_schedule(struct igc_adapter *adapter) { + unsigned long flags; int i; adapter->base_time = 0; adapter->cycle_time = NSEC_PER_SEC; adapter->taprio_offload_enable = false; adapter->qbv_config_change_errors = 0; - adapter->qbv_transition = false; adapter->qbv_count = 0; for (i = 0; i < adapter->num_tx_queues; i++) { @@ -6136,10 +6137,28 @@ static int igc_tsn_clear_schedule(struct igc_adapter *adapter) ring->start_time = 0; ring->end_time = NSEC_PER_SEC; ring->max_sdu = 0; + } + + spin_lock_irqsave(&adapter->qbv_tx_lock, flags); + + adapter->qbv_transition = false; + + for (i = 0; i < adapter->num_tx_queues; i++) { + struct igc_ring *ring = adapter->tx_ring[i]; + ring->oper_gate_closed = false; ring->admin_gate_closed = false; } + spin_unlock_irqrestore(&adapter->qbv_tx_lock, flags); + + return 0; +} + +static int igc_tsn_clear_schedule(struct igc_adapter *adapter) +{ + igc_qbv_clear_schedule(adapter); + return 0; } @@ -6150,6 +6169,7 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, struct igc_hw *hw = &adapter->hw; u32 start_time = 0, end_time = 0; struct timespec64 now; + unsigned long flags; size_t n; int i; @@ -6217,6 +6237,8 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, start_time += e->interval; } + spin_lock_irqsave(&adapter->qbv_tx_lock, flags); + /* Check whether a queue gets configured. * If not, set the start and end time to be end time. */ @@ -6241,6 +6263,8 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, } } + spin_unlock_irqrestore(&adapter->qbv_tx_lock, flags); + for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; struct net_device *dev = adapter->netdev; @@ -6619,8 +6643,11 @@ static enum hrtimer_restart igc_qbv_scheduling_timer(struct hrtimer *timer) { struct igc_adapter *adapter = container_of(timer, struct igc_adapter, hrtimer); + unsigned long flags; unsigned int i; + spin_lock_irqsave(&adapter->qbv_tx_lock, flags); + adapter->qbv_transition = true; for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *tx_ring = adapter->tx_ring[i]; @@ -6633,6 +6660,9 @@ static enum hrtimer_restart igc_qbv_scheduling_timer(struct hrtimer *timer) } } adapter->qbv_transition = false; + + spin_unlock_irqrestore(&adapter->qbv_tx_lock, flags); + return HRTIMER_NORESTART; } diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c index 2b9335cb4bb3..8537578e1cf1 100644 --- a/drivers/net/ethernet/korina.c +++ b/drivers/net/ethernet/korina.c @@ -1302,11 +1302,10 @@ static int korina_probe(struct platform_device *pdev) else if (of_get_ethdev_address(pdev->dev.of_node, dev) < 0) eth_hw_addr_random(dev); - clk = devm_clk_get_optional(&pdev->dev, "mdioclk"); + clk = devm_clk_get_optional_enabled(&pdev->dev, "mdioclk"); if (IS_ERR(clk)) return PTR_ERR(clk); if (clk) { - clk_prepare_enable(clk); lp->mii_clock_freq = clk_get_rate(clk); } else { lp->mii_clock_freq = 200000000; /* max possible input clk */ diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.c b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.c index 035ead7935c7..dab61cc1acb5 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_ctrl_mbox.c @@ -98,6 +98,9 @@ int octep_ctrl_mbox_init(struct octep_ctrl_mbox *mbox) writeq(OCTEP_CTRL_MBOX_STATUS_INIT, OCTEP_CTRL_MBOX_INFO_HOST_STATUS(mbox->barmem)); + mutex_init(&mbox->h2fq_lock); + mutex_init(&mbox->f2hq_lock); + mbox->h2fq.sz = readl(OCTEP_CTRL_MBOX_H2FQ_SZ(mbox->barmem)); mbox->h2fq.hw_prod = OCTEP_CTRL_MBOX_H2FQ_PROD(mbox->barmem); mbox->h2fq.hw_cons = OCTEP_CTRL_MBOX_H2FQ_CONS(mbox->barmem); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c index f328d957b2db..35857dc19542 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c @@ -727,7 +727,8 @@ pick_fw_ver: err = request_firmware_direct(&fw->bin, fw_path, fw->dev.dev); if (err) { - if (ver_maj == PRESTERA_SUPP_FW_MAJ_VER) { + if (ver_maj != PRESTERA_PREV_FW_MAJ_VER || + ver_min != PRESTERA_PREV_FW_MIN_VER) { ver_maj = PRESTERA_PREV_FW_MAJ_VER; ver_min = PRESTERA_PREV_FW_MIN_VER; diff --git a/drivers/net/ethernet/marvell/prestera/prestera_router.c b/drivers/net/ethernet/marvell/prestera/prestera_router.c index a9a1028cb17b..de317179a7dc 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_router.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_router.c @@ -166,11 +166,11 @@ prestera_util_neigh2nc_key(struct prestera_switch *sw, struct neighbour *n, static bool __prestera_fi_is_direct(struct fib_info *fi) { - struct fib_nh *fib_nh; + struct fib_nh_common *fib_nhc; if (fib_info_num_path(fi) == 1) { - fib_nh = fib_info_nh(fi, 0); - if (fib_nh->fib_nh_gw_family == AF_UNSPEC) + fib_nhc = fib_info_nhc(fi, 0); + if (fib_nhc->nhc_gw_family == AF_UNSPEC) return true; } @@ -261,7 +261,7 @@ static bool __prestera_util_kern_n_is_reachable_v4(u32 tb_id, __be32 *addr, struct net_device *dev) { - struct fib_nh *fib_nh; + struct fib_nh_common *fib_nhc; struct fib_result res; bool reachable; @@ -269,8 +269,8 @@ __prestera_util_kern_n_is_reachable_v4(u32 tb_id, __be32 *addr, if (!prestera_util_kern_get_route(&res, tb_id, addr)) if (prestera_fi_is_direct(res.fi)) { - fib_nh = fib_info_nh(res.fi, 0); - if (dev == fib_nh->fib_nh_dev) + fib_nhc = fib_info_nhc(res.fi, 0); + if (dev == fib_nhc->nhc_dev) reachable = true; } @@ -324,7 +324,7 @@ prestera_kern_fib_info_nhc(struct fib_notifier_info *info, int n) if (info->family == AF_INET) { fen4_info = container_of(info, struct fib_entry_notifier_info, info); - return &fib_info_nh(fen4_info->fi, n)->nh_common; + return fib_info_nhc(fen4_info->fi, n); } else if (info->family == AF_INET6) { fen6_info = container_of(info, struct fib6_entry_notifier_info, info); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c index b0128336ff01..e869c65d8e90 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c @@ -2,6 +2,7 @@ /* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. */ #include "reporter_vnic.h" +#include "en_stats.h" #include "devlink.h" #define VNIC_ENV_GET64(vnic_env_stats, c) \ @@ -36,55 +37,72 @@ int mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev, if (err) return err; - err = devlink_fmsg_u64_pair_put(fmsg, "total_error_queues", - VNIC_ENV_GET64(&vnic, total_error_queues)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "send_queue_priority_update_flow", - VNIC_ENV_GET64(&vnic, send_queue_priority_update_flow)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "comp_eq_overrun", - VNIC_ENV_GET64(&vnic, comp_eq_overrun)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "async_eq_overrun", - VNIC_ENV_GET64(&vnic, async_eq_overrun)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "cq_overrun", - VNIC_ENV_GET64(&vnic, cq_overrun)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "invalid_command", - VNIC_ENV_GET64(&vnic, invalid_command)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "quota_exceeded_command", - VNIC_ENV_GET64(&vnic, quota_exceeded_command)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "nic_receive_steering_discard", - VNIC_ENV_GET64(&vnic, nic_receive_steering_discard)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "generated_pkt_steering_fail", - VNIC_ENV_GET64(&vnic, generated_pkt_steering_fail)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "handled_pkt_steering_fail", - VNIC_ENV_GET64(&vnic, handled_pkt_steering_fail)); - if (err) - return err; + if (MLX5_CAP_GEN(dev, vnic_env_queue_counters)) { + err = devlink_fmsg_u32_pair_put(fmsg, "total_error_queues", + VNIC_ENV_GET(&vnic, total_error_queues)); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "send_queue_priority_update_flow", + VNIC_ENV_GET(&vnic, + send_queue_priority_update_flow)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, eq_overrun_count)) { + err = devlink_fmsg_u32_pair_put(fmsg, "comp_eq_overrun", + VNIC_ENV_GET(&vnic, comp_eq_overrun)); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "async_eq_overrun", + VNIC_ENV_GET(&vnic, async_eq_overrun)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, vnic_env_cq_overrun)) { + err = devlink_fmsg_u32_pair_put(fmsg, "cq_overrun", + VNIC_ENV_GET(&vnic, cq_overrun)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, invalid_command_count)) { + err = devlink_fmsg_u32_pair_put(fmsg, "invalid_command", + VNIC_ENV_GET(&vnic, invalid_command)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, quota_exceeded_count)) { + err = devlink_fmsg_u32_pair_put(fmsg, "quota_exceeded_command", + VNIC_ENV_GET(&vnic, quota_exceeded_command)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, nic_receive_steering_discard)) { + err = devlink_fmsg_u64_pair_put(fmsg, "nic_receive_steering_discard", + VNIC_ENV_GET64(&vnic, + nic_receive_steering_discard)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, vnic_env_cnt_steering_fail)) { + err = devlink_fmsg_u64_pair_put(fmsg, "generated_pkt_steering_fail", + VNIC_ENV_GET64(&vnic, + generated_pkt_steering_fail)); + if (err) + return err; + + err = devlink_fmsg_u64_pair_put(fmsg, "handled_pkt_steering_fail", + VNIC_ENV_GET64(&vnic, handled_pkt_steering_fail)); + if (err) + return err; + } err = devlink_fmsg_obj_nest_end(fmsg); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index f0c3464f037f..1730f6a716ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -1030,9 +1030,6 @@ int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv, int out_index; int err = 0; - if (!mlx5e_is_eswitch_flow(flow)) - return 0; - parse_attr = attr->parse_attr; esw_attr = attr->esw_attr; *vf_tun = false; @@ -1464,10 +1461,12 @@ static void mlx5e_invalidate_encap(struct mlx5e_priv *priv, attr = mlx5e_tc_get_encap_attr(flow); esw_attr = attr->esw_attr; - if (flow_flag_test(flow, SLOW)) + if (flow_flag_test(flow, SLOW)) { mlx5e_tc_unoffload_from_slow_path(esw, flow); - else + } else { mlx5e_tc_unoffload_fdb_rules(esw, flow, flow->attr); + mlx5e_tc_unoffload_flow_post_acts(flow); + } mlx5e_tc_detach_mod_hdr(priv, flow, attr); attr->modify_hdr = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index d97e6df66f45..b8dd74453655 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -323,8 +323,11 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, net_prefetch(mxbuf->xdp.data); prog = rcu_dereference(rq->xdp_prog); - if (likely(prog && mlx5e_xdp_handle(rq, prog, mxbuf))) + if (likely(prog && mlx5e_xdp_handle(rq, prog, mxbuf))) { + if (likely(__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))) + wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE); return NULL; /* page/packet was consumed by XDP */ + } /* XDP_PASS: copy the data from the UMEM to a new SKB. The frame reuse * will be handled by mlx5e_free_rx_wqe. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index dbe87bf89c0d..832d36be4a17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -808,9 +808,9 @@ static void setup_fte_upper_proto_match(struct mlx5_flow_spec *spec, struct upsp } if (upspec->sport) { - MLX5_SET(fte_match_set_lyr_2_4, spec->match_criteria, udp_dport, + MLX5_SET(fte_match_set_lyr_2_4, spec->match_criteria, udp_sport, upspec->sport_mask); - MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, udp_dport, upspec->sport); + MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, udp_sport, upspec->sport); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index eab5bc718771..8d995e304869 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -58,7 +58,9 @@ static int mlx5e_ipsec_remove_trailer(struct sk_buff *skb, struct xfrm_state *x) trailer_len = alen + plen + 2; - pskb_trim(skb, skb->len - trailer_len); + ret = pskb_trim(skb, skb->len - trailer_len); + if (unlikely(ret)) + return ret; if (skb->protocol == htons(ETH_P_IP)) { ipv4hdr->tot_len = htons(ntohs(ipv4hdr->tot_len) - trailer_len); ip_send_check(ipv4hdr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c index cf704f106b7c..984fa04bd331 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c @@ -188,7 +188,6 @@ static void mlx5e_tls_debugfs_init(struct mlx5e_tls *tls, int mlx5e_ktls_init(struct mlx5e_priv *priv) { - struct mlx5_crypto_dek_pool *dek_pool; struct mlx5e_tls *tls; if (!mlx5e_is_ktls_device(priv->mdev)) @@ -199,12 +198,6 @@ int mlx5e_ktls_init(struct mlx5e_priv *priv) return -ENOMEM; tls->mdev = priv->mdev; - dek_pool = mlx5_crypto_dek_pool_create(priv->mdev, MLX5_ACCEL_OBJ_TLS_KEY); - if (IS_ERR(dek_pool)) { - kfree(tls); - return PTR_ERR(dek_pool); - } - tls->dek_pool = dek_pool; priv->tls = tls; mlx5e_tls_debugfs_init(tls, priv->dfs_root); @@ -222,7 +215,6 @@ void mlx5e_ktls_cleanup(struct mlx5e_priv *priv) debugfs_remove_recursive(tls->debugfs.dfs); tls->debugfs.dfs = NULL; - mlx5_crypto_dek_pool_destroy(tls->dek_pool); kfree(priv->tls); priv->tls = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index efb2cf74ad6a..d61be26a4df1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -908,28 +908,51 @@ static void mlx5e_tls_tx_debugfs_init(struct mlx5e_tls *tls, int mlx5e_ktls_init_tx(struct mlx5e_priv *priv) { + struct mlx5_crypto_dek_pool *dek_pool; struct mlx5e_tls *tls = priv->tls; + int err; + + if (!mlx5e_is_ktls_device(priv->mdev)) + return 0; + + /* DEK pool could be used by either or both of TX and RX. But we have to + * put the creation here to avoid syndrome when doing devlink reload. + */ + dek_pool = mlx5_crypto_dek_pool_create(priv->mdev, MLX5_ACCEL_OBJ_TLS_KEY); + if (IS_ERR(dek_pool)) + return PTR_ERR(dek_pool); + tls->dek_pool = dek_pool; if (!mlx5e_is_ktls_tx(priv->mdev)) return 0; priv->tls->tx_pool = mlx5e_tls_tx_pool_init(priv->mdev, &priv->tls->sw_stats); - if (!priv->tls->tx_pool) - return -ENOMEM; + if (!priv->tls->tx_pool) { + err = -ENOMEM; + goto err_tx_pool_init; + } mlx5e_tls_tx_debugfs_init(tls, tls->debugfs.dfs); return 0; + +err_tx_pool_init: + mlx5_crypto_dek_pool_destroy(dek_pool); + return err; } void mlx5e_ktls_cleanup_tx(struct mlx5e_priv *priv) { if (!mlx5e_is_ktls_tx(priv->mdev)) - return; + goto dek_pool_destroy; debugfs_remove_recursive(priv->tls->debugfs.dfs_tx); priv->tls->debugfs.dfs_tx = NULL; mlx5e_tls_tx_pool_cleanup(priv->tls->tx_pool); priv->tls->tx_pool = NULL; + +dek_pool_destroy: + if (mlx5e_is_ktls_device(priv->mdev)) + mlx5_crypto_dek_pool_destroy(priv->tls->dek_pool); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c index 7fc901a6ec5f..414e28584881 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c @@ -161,6 +161,7 @@ static int macsec_fs_tx_create_crypto_table_groups(struct mlx5e_flow_table *ft) if (!in) { kfree(ft->g); + ft->g = NULL; return -ENOMEM; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 933a7772a7a3..5aa51d74f8b4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -135,6 +135,16 @@ static void arfs_del_rules(struct mlx5e_flow_steering *fs); int mlx5e_arfs_disable(struct mlx5e_flow_steering *fs) { + /* Moving to switchdev mode, fs->arfs is freed by mlx5e_nic_profile + * cleanup_rx callback and it is not recreated when + * mlx5e_uplink_rep_profile is loaded as mlx5e_create_flow_steering() + * is not called by the uplink_rep profile init_rx callback. Thus, if + * ntuple is set, moving to switchdev flow will enter this function + * with fs->arfs nullified. + */ + if (!mlx5e_fs_get_arfs(fs)) + return 0; + arfs_del_rules(fs); return arfs_disable(fs); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index defb1efccb78..c27df14df145 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1036,7 +1036,23 @@ static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_s return err; } -static int mlx5e_rq_to_ready(struct mlx5e_rq *rq, int curr_state) +static void mlx5e_flush_rq_cq(struct mlx5e_rq *rq) +{ + struct mlx5_cqwq *cqwq = &rq->cq.wq; + struct mlx5_cqe64 *cqe; + + if (test_bit(MLX5E_RQ_STATE_MINI_CQE_ENHANCED, &rq->state)) { + while ((cqe = mlx5_cqwq_get_cqe_enahnced_comp(cqwq))) + mlx5_cqwq_pop(cqwq); + } else { + while ((cqe = mlx5_cqwq_get_cqe(cqwq))) + mlx5_cqwq_pop(cqwq); + } + + mlx5_cqwq_update_db_record(cqwq); +} + +int mlx5e_flush_rq(struct mlx5e_rq *rq, int curr_state) { struct net_device *dev = rq->netdev; int err; @@ -1046,6 +1062,10 @@ static int mlx5e_rq_to_ready(struct mlx5e_rq *rq, int curr_state) netdev_err(dev, "Failed to move rq 0x%x to reset\n", rq->rqn); return err; } + + mlx5e_free_rx_descs(rq); + mlx5e_flush_rq_cq(rq); + err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY); if (err) { netdev_err(dev, "Failed to move rq 0x%x to ready\n", rq->rqn); @@ -1055,13 +1075,6 @@ static int mlx5e_rq_to_ready(struct mlx5e_rq *rq, int curr_state) return 0; } -int mlx5e_flush_rq(struct mlx5e_rq *rq, int curr_state) -{ - mlx5e_free_rx_descs(rq); - - return mlx5e_rq_to_ready(rq, curr_state); -} - static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd) { struct mlx5_core_dev *mdev = rq->mdev; @@ -5253,6 +5266,7 @@ void mlx5e_destroy_q_counters(struct mlx5e_priv *priv) static int mlx5e_nic_init(struct mlx5_core_dev *mdev, struct net_device *netdev) { + const bool take_rtnl = netdev->reg_state == NETREG_REGISTERED; struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_flow_steering *fs; int err; @@ -5281,9 +5295,19 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, mlx5_core_err(mdev, "TLS initialization failed, %d\n", err); mlx5e_health_create_reporters(priv); + + /* If netdev is already registered (e.g. move from uplink to nic profile), + * RTNL lock must be held before triggering netdev notifiers. + */ + if (take_rtnl) + rtnl_lock(); + /* update XDP supported features */ mlx5e_set_xdp_feature(netdev); + if (take_rtnl) + rtnl_unlock(); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 152b62138450..99b3843396f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1012,7 +1012,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) err = mlx5e_open_drop_rq(priv, &priv->drop_rq); if (err) { mlx5_core_err(mdev, "open drop rq failed, %d\n", err); - return err; + goto err_rx_res_free; } err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0, @@ -1046,6 +1046,7 @@ err_destroy_rx_res: mlx5e_rx_res_destroy(priv->rx_res); err_close_drop_rq: mlx5e_close_drop_rq(&priv->drop_rq); +err_rx_res_free: mlx5e_rx_res_free(priv->rx_res); priv->rx_res = NULL; err_free_fs: @@ -1159,6 +1160,10 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) return err; } + err = mlx5e_rep_neigh_init(rpriv); + if (err) + goto err_neigh_init; + if (rpriv->rep->vport == MLX5_VPORT_UPLINK) { err = mlx5e_init_uplink_rep_tx(rpriv); if (err) @@ -1175,6 +1180,8 @@ err_ht_init: if (rpriv->rep->vport == MLX5_VPORT_UPLINK) mlx5e_cleanup_uplink_rep_tx(rpriv); err_init_tx: + mlx5e_rep_neigh_cleanup(rpriv); +err_neigh_init: mlx5e_destroy_tises(priv); return err; } @@ -1188,22 +1195,17 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv) if (rpriv->rep->vport == MLX5_VPORT_UPLINK) mlx5e_cleanup_uplink_rep_tx(rpriv); + mlx5e_rep_neigh_cleanup(rpriv); mlx5e_destroy_tises(priv); } static void mlx5e_rep_enable(struct mlx5e_priv *priv) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; - mlx5e_set_netdev_mtu_boundaries(priv); - mlx5e_rep_neigh_init(rpriv); } static void mlx5e_rep_disable(struct mlx5e_priv *priv) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; - - mlx5e_rep_neigh_cleanup(rpriv); } static int mlx5e_update_rep_rx(struct mlx5e_priv *priv) @@ -1253,7 +1255,6 @@ static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; u16 max_mtu; @@ -1275,7 +1276,6 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) mlx5_notifier_register(mdev, &priv->events_nb); mlx5e_dcbnl_initialize(priv); mlx5e_dcbnl_init_app(priv); - mlx5e_rep_neigh_init(rpriv); mlx5e_rep_bridge_init(priv); netdev->wanted_features |= NETIF_F_HW_TC; @@ -1290,7 +1290,6 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_core_dev *mdev = priv->mdev; rtnl_lock(); @@ -1300,7 +1299,6 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) rtnl_unlock(); mlx5e_rep_bridge_cleanup(priv); - mlx5e_rep_neigh_cleanup(rpriv); mlx5e_dcbnl_delete_app(priv); mlx5_notifier_unregister(mdev, &priv->events_nb); mlx5e_rep_tc_disable(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 8d0a3f69693e..31708d5aa608 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1725,6 +1725,19 @@ verify_attr_actions(u32 actions, struct netlink_ext_ack *extack) return 0; } +static bool +has_encap_dests(struct mlx5_flow_attr *attr) +{ + struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + int out_index; + + for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) + if (esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) + return true; + + return false; +} + static int post_process_attr(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr, @@ -1737,9 +1750,11 @@ post_process_attr(struct mlx5e_tc_flow *flow, if (err) goto err_out; - err = mlx5e_tc_tun_encap_dests_set(flow->priv, flow, attr, extack, &vf_tun); - if (err) - goto err_out; + if (mlx5e_is_eswitch_flow(flow) && has_encap_dests(attr)) { + err = mlx5e_tc_tun_encap_dests_set(flow->priv, flow, attr, extack, &vf_tun); + if (err) + goto err_out; + } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { err = mlx5e_tc_attach_mod_hdr(flow->priv, flow, attr); @@ -1928,9 +1943,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_flow_attr *attr = flow->attr; - struct mlx5_esw_flow_attr *esw_attr; - esw_attr = attr->esw_attr; mlx5e_put_flow_tunnel_id(flow); remove_unready_flow(flow); @@ -1951,12 +1964,6 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, mlx5_tc_ct_match_del(get_ct_priv(priv), &flow->attr->ct_attr); - if (esw_attr->int_port) - mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(priv), esw_attr->int_port); - - if (esw_attr->dest_int_port) - mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(priv), esw_attr->dest_int_port); - if (flow_flag_test(flow, L3_TO_L2_DECAP)) mlx5e_detach_decap(priv, flow); @@ -4253,6 +4260,7 @@ static void mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr) { struct mlx5_core_dev *counter_dev = get_flow_counter_dev(flow); + struct mlx5_esw_flow_attr *esw_attr; if (!attr) return; @@ -4270,6 +4278,18 @@ mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *a mlx5e_tc_detach_mod_hdr(flow->priv, flow, attr); } + if (mlx5e_is_eswitch_flow(flow)) { + esw_attr = attr->esw_attr; + + if (esw_attr->int_port) + mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(flow->priv), + esw_attr->int_port); + + if (esw_attr->dest_int_port) + mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(flow->priv), + esw_attr->dest_int_port); + } + mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), attr); free_branch_attr(flow, attr->branch_true); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_debugfs.c index b6a45eff28f5..dbd7cbe6cbf3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_debugfs.c @@ -64,7 +64,7 @@ void mlx5_esw_bridge_debugfs_init(struct net_device *br_netdev, struct mlx5_esw_ bridge->debugfs_dir = debugfs_create_dir(br_netdev->name, bridge->br_offloads->debugfs_root); - debugfs_create_file("fdb", 0444, bridge->debugfs_dir, bridge, + debugfs_create_file("fdb", 0400, bridge->debugfs_dir, bridge, &mlx5_esw_bridge_debugfs_fops); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index af779c700278..fdf2be548e85 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -60,7 +60,7 @@ static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16 } else if (mlx5_core_is_ec_vf_vport(esw->dev, vport_num)) { memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len); dl_port->attrs.switch_id.id_len = ppid.id_len; - devlink_port_attrs_pci_vf_set(dl_port, controller_num, pfnum, + devlink_port_attrs_pci_vf_set(dl_port, 0, pfnum, vport_num - 1, false); } return dl_port; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index bdfe609cc9ec..e59380ee1ead 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1436,7 +1436,6 @@ esw_chains_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *miss_fdb) esw_init_chains_offload_flags(esw, &attr.flags); attr.ns = MLX5_FLOW_NAMESPACE_FDB; - attr.fs_base_prio = FDB_TC_OFFLOAD; attr.max_grp_num = esw->params.large_group_num; attr.default_ft = miss_fdb; attr.mapping = esw->offloads.reg_c0_obj_pool; @@ -2779,9 +2778,9 @@ static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw, struct mlx5_eswitch *peer_esw, bool pair) { - u8 peer_idx = mlx5_get_dev_index(peer_esw->dev); + u16 peer_vhca_id = MLX5_CAP_GEN(peer_esw->dev, vhca_id); + u16 vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id); struct mlx5_flow_root_namespace *peer_ns; - u8 idx = mlx5_get_dev_index(esw->dev); struct mlx5_flow_root_namespace *ns; int err; @@ -2789,18 +2788,18 @@ static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw, ns = esw->dev->priv.steering->fdb_root_ns; if (pair) { - err = mlx5_flow_namespace_set_peer(ns, peer_ns, peer_idx); + err = mlx5_flow_namespace_set_peer(ns, peer_ns, peer_vhca_id); if (err) return err; - err = mlx5_flow_namespace_set_peer(peer_ns, ns, idx); + err = mlx5_flow_namespace_set_peer(peer_ns, ns, vhca_id); if (err) { - mlx5_flow_namespace_set_peer(ns, NULL, peer_idx); + mlx5_flow_namespace_set_peer(ns, NULL, peer_vhca_id); return err; } } else { - mlx5_flow_namespace_set_peer(ns, NULL, peer_idx); - mlx5_flow_namespace_set_peer(peer_ns, NULL, idx); + mlx5_flow_namespace_set_peer(ns, NULL, peer_vhca_id); + mlx5_flow_namespace_set_peer(peer_ns, NULL, vhca_id); } return 0; @@ -4196,7 +4195,7 @@ int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable, } hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability); - MLX5_SET(cmd_hca_cap_2, hca_caps, migratable, 1); + MLX5_SET(cmd_hca_cap_2, hca_caps, migratable, enable); err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport->vport, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE2); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 91dcb0dcad10..aab7059bf6e9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -140,7 +140,7 @@ static void mlx5_cmd_stub_modify_header_dealloc(struct mlx5_flow_root_namespace static int mlx5_cmd_stub_set_peer(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_root_namespace *peer_ns, - u8 peer_idx) + u16 peer_vhca_id) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index b6b9a5a20591..7790ae5531e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -94,7 +94,7 @@ struct mlx5_flow_cmds { int (*set_peer)(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_root_namespace *peer_ns, - u8 peer_idx); + u16 peer_vhca_id); int (*create_ns)(struct mlx5_flow_root_namespace *ns); int (*destroy_ns)(struct mlx5_flow_root_namespace *ns); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 4ef04aa28771..6b069fa411c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -889,7 +889,7 @@ static struct mlx5_flow_table *find_closest_ft_recursive(struct fs_node *root, struct fs_node *iter = list_entry(start, struct fs_node, list); struct mlx5_flow_table *ft = NULL; - if (!root || root->type == FS_TYPE_PRIO_CHAINS) + if (!root) return NULL; list_for_each_advance_continue(iter, &root->children, reverse) { @@ -905,20 +905,42 @@ static struct mlx5_flow_table *find_closest_ft_recursive(struct fs_node *root, return ft; } -/* If reverse is false then return the first flow table in next priority of - * prio in the tree, else return the last flow table in the previous priority - * of prio in the tree. +static struct fs_node *find_prio_chains_parent(struct fs_node *parent, + struct fs_node **child) +{ + struct fs_node *node = NULL; + + while (parent && parent->type != FS_TYPE_PRIO_CHAINS) { + node = parent; + parent = parent->parent; + } + + if (child) + *child = node; + + return parent; +} + +/* If reverse is false then return the first flow table next to the passed node + * in the tree, else return the last flow table before the node in the tree. + * If skip is true, skip the flow tables in the same prio_chains prio. */ -static struct mlx5_flow_table *find_closest_ft(struct fs_prio *prio, bool reverse) +static struct mlx5_flow_table *find_closest_ft(struct fs_node *node, bool reverse, + bool skip) { + struct fs_node *prio_chains_parent = NULL; struct mlx5_flow_table *ft = NULL; struct fs_node *curr_node; struct fs_node *parent; - parent = prio->node.parent; - curr_node = &prio->node; + if (skip) + prio_chains_parent = find_prio_chains_parent(node, NULL); + parent = node->parent; + curr_node = node; while (!ft && parent) { - ft = find_closest_ft_recursive(parent, &curr_node->list, reverse); + if (parent != prio_chains_parent) + ft = find_closest_ft_recursive(parent, &curr_node->list, + reverse); curr_node = parent; parent = curr_node->parent; } @@ -926,15 +948,15 @@ static struct mlx5_flow_table *find_closest_ft(struct fs_prio *prio, bool revers } /* Assuming all the tree is locked by mutex chain lock */ -static struct mlx5_flow_table *find_next_chained_ft(struct fs_prio *prio) +static struct mlx5_flow_table *find_next_chained_ft(struct fs_node *node) { - return find_closest_ft(prio, false); + return find_closest_ft(node, false, true); } /* Assuming all the tree is locked by mutex chain lock */ -static struct mlx5_flow_table *find_prev_chained_ft(struct fs_prio *prio) +static struct mlx5_flow_table *find_prev_chained_ft(struct fs_node *node) { - return find_closest_ft(prio, true); + return find_closest_ft(node, true, true); } static struct mlx5_flow_table *find_next_fwd_ft(struct mlx5_flow_table *ft, @@ -946,7 +968,7 @@ static struct mlx5_flow_table *find_next_fwd_ft(struct mlx5_flow_table *ft, next_ns = flow_act->action & MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS; fs_get_obj(prio, next_ns ? ft->ns->node.parent : ft->node.parent); - return find_next_chained_ft(prio); + return find_next_chained_ft(&prio->node); } static int connect_fts_in_prio(struct mlx5_core_dev *dev, @@ -970,21 +992,55 @@ static int connect_fts_in_prio(struct mlx5_core_dev *dev, return 0; } +static struct mlx5_flow_table *find_closet_ft_prio_chains(struct fs_node *node, + struct fs_node *parent, + struct fs_node **child, + bool reverse) +{ + struct mlx5_flow_table *ft; + + ft = find_closest_ft(node, reverse, false); + + if (ft && parent == find_prio_chains_parent(&ft->node, child)) + return ft; + + return NULL; +} + /* Connect flow tables from previous priority of prio to ft */ static int connect_prev_fts(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft, struct fs_prio *prio) { + struct fs_node *prio_parent, *parent = NULL, *child, *node; struct mlx5_flow_table *prev_ft; + int err = 0; + + prio_parent = find_prio_chains_parent(&prio->node, &child); + + /* return directly if not under the first sub ns of prio_chains prio */ + if (prio_parent && !list_is_first(&child->list, &prio_parent->children)) + return 0; - prev_ft = find_prev_chained_ft(prio); - if (prev_ft) { + prev_ft = find_prev_chained_ft(&prio->node); + while (prev_ft) { struct fs_prio *prev_prio; fs_get_obj(prev_prio, prev_ft->node.parent); - return connect_fts_in_prio(dev, prev_prio, ft); + err = connect_fts_in_prio(dev, prev_prio, ft); + if (err) + break; + + if (!parent) { + parent = find_prio_chains_parent(&prev_prio->node, &child); + if (!parent) + break; + } + + node = child; + prev_ft = find_closet_ft_prio_chains(node, parent, &child, true); } - return 0; + return err; } static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio @@ -1123,7 +1179,7 @@ static int connect_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table if (err) return err; - next_ft = first_ft ? first_ft : find_next_chained_ft(prio); + next_ft = first_ft ? first_ft : find_next_chained_ft(&prio->node); err = connect_fwd_rules(dev, ft, next_ft); if (err) return err; @@ -1198,7 +1254,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa tree_init_node(&ft->node, del_hw_flow_table, del_sw_flow_table); next_ft = unmanaged ? ft_attr->next_ft : - find_next_chained_ft(fs_prio); + find_next_chained_ft(&fs_prio->node); ft->def_miss_action = ns->def_miss_action; ft->ns = ns; err = root->cmds->create_flow_table(root, ft, ft_attr, next_ft); @@ -2195,13 +2251,20 @@ EXPORT_SYMBOL(mlx5_del_flow_rules); /* Assuming prio->node.children(flow tables) is sorted by level */ static struct mlx5_flow_table *find_next_ft(struct mlx5_flow_table *ft) { + struct fs_node *prio_parent, *child; struct fs_prio *prio; fs_get_obj(prio, ft->node.parent); if (!list_is_last(&ft->node.list, &prio->node.children)) return list_next_entry(ft, node.list); - return find_next_chained_ft(prio); + + prio_parent = find_prio_chains_parent(&prio->node, &child); + + if (prio_parent && list_is_first(&child->list, &prio_parent->children)) + return find_closest_ft(&prio->node, false, false); + + return find_next_chained_ft(&prio->node); } static int update_root_ft_destroy(struct mlx5_flow_table *ft) @@ -3621,7 +3684,7 @@ void mlx5_destroy_match_definer(struct mlx5_core_dev *dev, int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_root_namespace *peer_ns, - u8 peer_idx) + u16 peer_vhca_id) { if (peer_ns && ns->mode != peer_ns->mode) { mlx5_core_err(ns->dev, @@ -3629,7 +3692,7 @@ int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, return -EINVAL; } - return ns->cmds->set_peer(ns, peer_ns, peer_idx); + return ns->cmds->set_peer(ns, peer_ns, peer_vhca_id); } /* This function should be called only at init stage of the namespace. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 03e64c4c245d..4aed1768b85f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -303,7 +303,7 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void); int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_root_namespace *peer_ns, - u8 peer_idx); + u16 peer_vhca_id); int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns, enum mlx5_flow_steering_mode mode); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c index d3a3fe4ce670..7d9bbb494d95 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c @@ -574,7 +574,7 @@ static int __mlx5_lag_modify_definers_destinations(struct mlx5_lag *ldev, for (i = 0; i < ldev->ports; i++) { for (j = 0; j < ldev->buckets; j++) { idx = i * ldev->buckets + j; - if (ldev->v2p_map[i] == ports[i]) + if (ldev->v2p_map[idx] == ports[idx]) continue; dest.vport.vhca_id = MLX5_CAP_GEN(ldev->pf[ports[idx] - 1].dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 973babfaff25..377372f0578a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -227,10 +227,15 @@ static void mlx5_timestamp_overflow(struct work_struct *work) clock = container_of(timer, struct mlx5_clock, timer); mdev = container_of(clock, struct mlx5_core_dev, clock); + if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + goto out; + write_seqlock_irqsave(&clock->lock, flags); timecounter_read(&timer->tc); mlx5_update_clock_info_page(mdev); write_sequnlock_irqrestore(&clock->lock, flags); + +out: schedule_delayed_work(&timer->overflow_work, timer->overflow_period); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c index db9df9798ffa..a80ecb672f33 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c @@ -178,7 +178,7 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains, if (!mlx5_chains_ignore_flow_level_supported(chains) || (chain == 0 && prio == 1 && level == 0)) { ft_attr.level = chains->fs_base_level; - ft_attr.prio = chains->fs_base_prio; + ft_attr.prio = chains->fs_base_prio + prio - 1; ns = (chains->ns == MLX5_FLOW_NAMESPACE_FDB) ? mlx5_get_fdb_sub_ns(chains->dev, chain) : mlx5_get_flow_namespace(chains->dev, chains->ns); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 88dbea6631d5..72ae560a1c68 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1506,6 +1506,7 @@ void mlx5_uninit_one(struct mlx5_core_dev *dev) if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { mlx5_core_warn(dev, "%s: interface is down, NOP\n", __func__); + mlx5_devlink_params_unregister(priv_to_devlink(dev)); mlx5_cleanup_once(dev); goto out; } @@ -1988,7 +1989,7 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, mlx5_enter_error_state(dev, false); mlx5_error_sw_reset(dev); - mlx5_unload_one(dev, true); + mlx5_unload_one(dev, false); mlx5_drain_health_wq(dev); mlx5_pci_disable_device(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index c4be257c043d..682d3dc00dd1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -361,7 +361,7 @@ static inline bool mlx5_core_is_ec_vf_vport(const struct mlx5_core_dev *dev, u16 static inline int mlx5_vport_to_func_id(const struct mlx5_core_dev *dev, u16 vport, bool ec_vf_func) { - return ec_vf_func ? vport - mlx5_core_ec_vf_vport_base(dev) + return ec_vf_func ? vport - mlx5_core_ec_vf_vport_base(dev) + 1 : vport; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 4e42a3b9b8ee..a2fc937d5461 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -285,8 +285,7 @@ static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev) host_total_vfs = MLX5_GET(query_esw_functions_out, out, host_params_context.host_total_vfs); kvfree(out); - if (host_total_vfs) - return host_total_vfs; + return host_total_vfs; } done: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index e739ec6cdf90..54bb0866ed72 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -2079,7 +2079,7 @@ mlx5dr_action_create_dest_vport(struct mlx5dr_domain *dmn, peer_vport = vhca_id_valid && mlx5_core_is_pf(dmn->mdev) && (vhca_id != dmn->info.caps.gvmi); - vport_dmn = peer_vport ? dmn->peer_dmn[vhca_id] : dmn; + vport_dmn = peer_vport ? xa_load(&dmn->peer_dmn_xa, vhca_id) : dmn; if (!vport_dmn) { mlx5dr_dbg(dmn, "No peer vport domain for given vhca_id\n"); return NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 7491911ebcb5..8c2a34a0d6be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -564,11 +564,12 @@ int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev, err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out)); if (err) - return err; + goto err_free_in; *reformat_id = MLX5_GET(alloc_packet_reformat_context_out, out, packet_reformat_id); - kvfree(in); +err_free_in: + kvfree(in); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 75dc85dc24ef..3d74109f8230 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -475,6 +475,7 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type) mutex_init(&dmn->info.rx.mutex); mutex_init(&dmn->info.tx.mutex); xa_init(&dmn->definers_xa); + xa_init(&dmn->peer_dmn_xa); if (dr_domain_caps_init(mdev, dmn)) { mlx5dr_err(dmn, "Failed init domain, no caps\n"); @@ -507,6 +508,7 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type) uninit_caps: dr_domain_caps_uninit(dmn); def_xa_destroy: + xa_destroy(&dmn->peer_dmn_xa); xa_destroy(&dmn->definers_xa); kfree(dmn); return NULL; @@ -547,6 +549,7 @@ int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn) dr_domain_uninit_csum_recalc_fts(dmn); dr_domain_uninit_resources(dmn); dr_domain_caps_uninit(dmn); + xa_destroy(&dmn->peer_dmn_xa); xa_destroy(&dmn->definers_xa); mutex_destroy(&dmn->info.tx.mutex); mutex_destroy(&dmn->info.rx.mutex); @@ -556,17 +559,21 @@ int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn) void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn, struct mlx5dr_domain *peer_dmn, - u8 peer_idx) + u16 peer_vhca_id) { + struct mlx5dr_domain *peer; + mlx5dr_domain_lock(dmn); - if (dmn->peer_dmn[peer_idx]) - refcount_dec(&dmn->peer_dmn[peer_idx]->refcount); + peer = xa_load(&dmn->peer_dmn_xa, peer_vhca_id); + if (peer) + refcount_dec(&peer->refcount); - dmn->peer_dmn[peer_idx] = peer_dmn; + WARN_ON(xa_err(xa_store(&dmn->peer_dmn_xa, peer_vhca_id, peer_dmn, GFP_KERNEL))); - if (dmn->peer_dmn[peer_idx]) - refcount_inc(&dmn->peer_dmn[peer_idx]->refcount); + peer = xa_load(&dmn->peer_dmn_xa, peer_vhca_id); + if (peer) + refcount_inc(&peer->refcount); mlx5dr_domain_unlock(dmn); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c index d6947fe13d56..8ca534ef5d03 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c @@ -82,7 +82,7 @@ dr_ptrn_alloc_pattern(struct mlx5dr_ptrn_mgr *mgr, u32 chunk_size; u32 index; - chunk_size = ilog2(num_of_actions); + chunk_size = ilog2(roundup_pow_of_two(num_of_actions)); /* HW modify action index granularity is at least 64B */ chunk_size = max_t(u32, chunk_size, DR_CHUNK_SIZE_8); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c index 69d7a8f3c402..f708b029425a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c @@ -1652,17 +1652,18 @@ dr_ste_v0_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, struct mlx5dr_domain *dmn = sb->dmn; struct mlx5dr_domain *vport_dmn; u8 *bit_mask = sb->bit_mask; + struct mlx5dr_domain *peer; bool source_gvmi_set; DR_STE_SET_TAG(src_gvmi_qp, tag, source_qp, misc, source_sqn); if (sb->vhca_id_valid) { + peer = xa_load(&dmn->peer_dmn_xa, id); /* Find port GVMI based on the eswitch_owner_vhca_id */ if (id == dmn->info.caps.gvmi) vport_dmn = dmn; - else if (id < MLX5_MAX_PORTS && dmn->peer_dmn[id] && - (id == dmn->peer_dmn[id]->info.caps.gvmi)) - vport_dmn = dmn->peer_dmn[id]; + else if (peer && (id == peer->info.caps.gvmi)) + vport_dmn = peer; else return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c index f4ef0b22b991..dd856cde188d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -1984,16 +1984,17 @@ static int dr_ste_v1_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, struct mlx5dr_domain *dmn = sb->dmn; struct mlx5dr_domain *vport_dmn; u8 *bit_mask = sb->bit_mask; + struct mlx5dr_domain *peer; DR_STE_SET_TAG(src_gvmi_qp_v1, tag, source_qp, misc, source_sqn); if (sb->vhca_id_valid) { + peer = xa_load(&dmn->peer_dmn_xa, id); /* Find port GVMI based on the eswitch_owner_vhca_id */ if (id == dmn->info.caps.gvmi) vport_dmn = dmn; - else if (id < MLX5_MAX_PORTS && dmn->peer_dmn[id] && - (id == dmn->peer_dmn[id]->info.caps.gvmi)) - vport_dmn = dmn->peer_dmn[id]; + else if (peer && (id == peer->info.caps.gvmi)) + vport_dmn = peer; else return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 1622dbbe6b97..6c59de3e28f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -935,7 +935,6 @@ struct mlx5dr_domain_info { }; struct mlx5dr_domain { - struct mlx5dr_domain *peer_dmn[MLX5_MAX_PORTS]; struct mlx5_core_dev *mdev; u32 pdn; struct mlx5_uars_page *uar; @@ -956,6 +955,7 @@ struct mlx5dr_domain { struct list_head dbg_tbl_list; struct mlx5dr_dbg_dump_info dump_info; struct xarray definers_xa; + struct xarray peer_dmn_xa; /* memory management statistics */ u32 num_buddies[DR_ICM_TYPE_MAX]; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 6aac5f006bf8..feb307fb3440 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -781,14 +781,14 @@ restore_fte: static int mlx5_cmd_dr_set_peer(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_root_namespace *peer_ns, - u8 peer_idx) + u16 peer_vhca_id) { struct mlx5dr_domain *peer_domain = NULL; if (peer_ns) peer_domain = peer_ns->fs_dr_domain.dr_domain; mlx5dr_domain_set_peer(ns->fs_dr_domain.dr_domain, - peer_domain, peer_idx); + peer_domain, peer_vhca_id); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index 24cbb33ecd6c..89fced86936f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -49,7 +49,7 @@ int mlx5dr_domain_sync(struct mlx5dr_domain *domain, u32 flags); void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn, struct mlx5dr_domain *peer_dmn, - u8 peer_idx); + u16 peer_vhca_id); struct mlx5dr_table * mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level, u32 flags, diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index a499e460594b..c2ad0921e893 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -8,6 +8,7 @@ #include <linux/ethtool.h> #include <linux/filter.h> #include <linux/mm.h> +#include <linux/pci.h> #include <net/checksum.h> #include <net/ip6_checksum.h> @@ -2345,9 +2346,12 @@ int mana_attach(struct net_device *ndev) static int mana_dealloc_queues(struct net_device *ndev) { struct mana_port_context *apc = netdev_priv(ndev); + unsigned long timeout = jiffies + 120 * HZ; struct gdma_dev *gd = apc->ac->gdma_dev; struct mana_txq *txq; + struct sk_buff *skb; int i, err; + u32 tsleep; if (apc->port_is_up) return -EINVAL; @@ -2363,15 +2367,40 @@ static int mana_dealloc_queues(struct net_device *ndev) * to false, but it doesn't matter since mana_start_xmit() drops any * new packets due to apc->port_is_up being false. * - * Drain all the in-flight TX packets + * Drain all the in-flight TX packets. + * A timeout of 120 seconds for all the queues is used. + * This will break the while loop when h/w is not responding. + * This value of 120 has been decided here considering max + * number of queues. */ + for (i = 0; i < apc->num_queues; i++) { txq = &apc->tx_qp[i].txq; - - while (atomic_read(&txq->pending_sends) > 0) - usleep_range(1000, 2000); + tsleep = 1000; + while (atomic_read(&txq->pending_sends) > 0 && + time_before(jiffies, timeout)) { + usleep_range(tsleep, tsleep + 1000); + tsleep <<= 1; + } + if (atomic_read(&txq->pending_sends)) { + err = pcie_flr(to_pci_dev(gd->gdma_context->dev)); + if (err) { + netdev_err(ndev, "flr failed %d with %d pkts pending in txq %u\n", + err, atomic_read(&txq->pending_sends), + txq->gdma_txq_id); + } + break; + } } + for (i = 0; i < apc->num_queues; i++) { + txq = &apc->tx_qp[i].txq; + while ((skb = skb_dequeue(&txq->pending_skbs))) { + mana_unmap_skb(skb, apc); + dev_kfree_skb_any(skb); + } + atomic_set(&txq->pending_sends, 0); + } /* We're 100% sure the queues can no longer be woken up, because * we're sure now mana_poll_tx_cq() can't be running. */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 612b0015dc43..432fb93aa801 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1817,6 +1817,7 @@ static int ionic_change_mtu(struct net_device *netdev, int new_mtu) static void ionic_tx_timeout_work(struct work_struct *ws) { struct ionic_lif *lif = container_of(ws, struct ionic_lif, tx_timeout_work); + int err; if (test_bit(IONIC_LIF_F_FW_RESET, lif->state)) return; @@ -1829,8 +1830,11 @@ static void ionic_tx_timeout_work(struct work_struct *ws) mutex_lock(&lif->queue_lock); ionic_stop_queues_reconfig(lif); - ionic_start_queues_reconfig(lif); + err = ionic_start_queues_reconfig(lif); mutex_unlock(&lif->queue_lock); + + if (err) + dev_err(lif->ionic->dev, "%s: Restarting queues failed\n", __func__); } static void ionic_tx_timeout(struct net_device *netdev, unsigned int txqueue) @@ -2800,17 +2804,22 @@ static int ionic_cmb_reconfig(struct ionic_lif *lif, if (err) { dev_err(lif->ionic->dev, "CMB restore failed: %d\n", err); - goto errout; + goto err_out; } } - ionic_start_queues_reconfig(lif); - } else { - /* This was detached in ionic_stop_queues_reconfig() */ - netif_device_attach(lif->netdev); + err = ionic_start_queues_reconfig(lif); + if (err) { + dev_err(lif->ionic->dev, + "CMB reconfig failed: %d\n", err); + goto err_out; + } } -errout: +err_out: + /* This was detached in ionic_stop_queues_reconfig() */ + netif_device_attach(lif->netdev); + return err; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h index f8682356d0cf..94d4f9413ab7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h +++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h @@ -194,6 +194,22 @@ void qed_hw_remove(struct qed_dev *cdev); struct qed_ptt *qed_ptt_acquire(struct qed_hwfn *p_hwfn); /** + * qed_ptt_acquire_context(): Allocate a PTT window honoring the context + * atomicy. + * + * @p_hwfn: HW device data. + * @is_atomic: Hint from the caller - if the func can sleep or not. + * + * Context: The function should not sleep in case is_atomic == true. + * Return: struct qed_ptt. + * + * Should be called at the entry point to the driver + * (at the beginning of an exported function). + */ +struct qed_ptt *qed_ptt_acquire_context(struct qed_hwfn *p_hwfn, + bool is_atomic); + +/** * qed_ptt_release(): Release PTT Window. * * @p_hwfn: HW device data. diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c index 3764190b948e..04602ac94708 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c +++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c @@ -693,13 +693,14 @@ static void _qed_fcoe_get_pstats(struct qed_hwfn *p_hwfn, } static int qed_fcoe_get_stats(struct qed_hwfn *p_hwfn, - struct qed_fcoe_stats *p_stats) + struct qed_fcoe_stats *p_stats, + bool is_atomic) { struct qed_ptt *p_ptt; memset(p_stats, 0, sizeof(*p_stats)); - p_ptt = qed_ptt_acquire(p_hwfn); + p_ptt = qed_ptt_acquire_context(p_hwfn, is_atomic); if (!p_ptt) { DP_ERR(p_hwfn, "Failed to acquire ptt\n"); @@ -973,19 +974,27 @@ static int qed_fcoe_destroy_conn(struct qed_dev *cdev, QED_SPQ_MODE_EBLOCK, NULL); } +static int qed_fcoe_stats_context(struct qed_dev *cdev, + struct qed_fcoe_stats *stats, + bool is_atomic) +{ + return qed_fcoe_get_stats(QED_AFFIN_HWFN(cdev), stats, is_atomic); +} + static int qed_fcoe_stats(struct qed_dev *cdev, struct qed_fcoe_stats *stats) { - return qed_fcoe_get_stats(QED_AFFIN_HWFN(cdev), stats); + return qed_fcoe_stats_context(cdev, stats, false); } void qed_get_protocol_stats_fcoe(struct qed_dev *cdev, - struct qed_mcp_fcoe_stats *stats) + struct qed_mcp_fcoe_stats *stats, + bool is_atomic) { struct qed_fcoe_stats proto_stats; /* Retrieve FW statistics */ memset(&proto_stats, 0, sizeof(proto_stats)); - if (qed_fcoe_stats(cdev, &proto_stats)) { + if (qed_fcoe_stats_context(cdev, &proto_stats, is_atomic)) { DP_VERBOSE(cdev, QED_MSG_STORAGE, "Failed to collect FCoE statistics\n"); return; diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.h b/drivers/net/ethernet/qlogic/qed/qed_fcoe.h index 19c85adf4ceb..214e8299ecb4 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.h +++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.h @@ -28,8 +28,20 @@ int qed_fcoe_alloc(struct qed_hwfn *p_hwfn); void qed_fcoe_setup(struct qed_hwfn *p_hwfn); void qed_fcoe_free(struct qed_hwfn *p_hwfn); +/** + * qed_get_protocol_stats_fcoe(): Fills provided statistics + * struct with statistics. + * + * @cdev: Qed dev pointer. + * @stats: Points to struct that will be filled with statistics. + * @is_atomic: Hint from the caller - if the func can sleep or not. + * + * Context: The function should not sleep in case is_atomic == true. + * Return: Void. + */ void qed_get_protocol_stats_fcoe(struct qed_dev *cdev, - struct qed_mcp_fcoe_stats *stats); + struct qed_mcp_fcoe_stats *stats, + bool is_atomic); #else /* CONFIG_QED_FCOE */ static inline int qed_fcoe_alloc(struct qed_hwfn *p_hwfn) { @@ -40,7 +52,8 @@ static inline void qed_fcoe_setup(struct qed_hwfn *p_hwfn) {} static inline void qed_fcoe_free(struct qed_hwfn *p_hwfn) {} static inline void qed_get_protocol_stats_fcoe(struct qed_dev *cdev, - struct qed_mcp_fcoe_stats *stats) + struct qed_mcp_fcoe_stats *stats, + bool is_atomic) { } #endif /* CONFIG_QED_FCOE */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c index 554f30b0cfd5..6263f847b6b9 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hw.c +++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c @@ -23,7 +23,10 @@ #include "qed_reg_addr.h" #include "qed_sriov.h" -#define QED_BAR_ACQUIRE_TIMEOUT 1000 +#define QED_BAR_ACQUIRE_TIMEOUT_USLEEP_CNT 1000 +#define QED_BAR_ACQUIRE_TIMEOUT_USLEEP 1000 +#define QED_BAR_ACQUIRE_TIMEOUT_UDELAY_CNT 100000 +#define QED_BAR_ACQUIRE_TIMEOUT_UDELAY 10 /* Invalid values */ #define QED_BAR_INVALID_OFFSET (cpu_to_le32(-1)) @@ -85,11 +88,21 @@ void qed_ptt_pool_free(struct qed_hwfn *p_hwfn) struct qed_ptt *qed_ptt_acquire(struct qed_hwfn *p_hwfn) { + return qed_ptt_acquire_context(p_hwfn, false); +} + +struct qed_ptt *qed_ptt_acquire_context(struct qed_hwfn *p_hwfn, bool is_atomic) +{ struct qed_ptt *p_ptt; - unsigned int i; + unsigned int i, count; + + if (is_atomic) + count = QED_BAR_ACQUIRE_TIMEOUT_UDELAY_CNT; + else + count = QED_BAR_ACQUIRE_TIMEOUT_USLEEP_CNT; /* Take the free PTT from the list */ - for (i = 0; i < QED_BAR_ACQUIRE_TIMEOUT; i++) { + for (i = 0; i < count; i++) { spin_lock_bh(&p_hwfn->p_ptt_pool->lock); if (!list_empty(&p_hwfn->p_ptt_pool->free_list)) { @@ -105,7 +118,12 @@ struct qed_ptt *qed_ptt_acquire(struct qed_hwfn *p_hwfn) } spin_unlock_bh(&p_hwfn->p_ptt_pool->lock); - usleep_range(1000, 2000); + + if (is_atomic) + udelay(QED_BAR_ACQUIRE_TIMEOUT_UDELAY); + else + usleep_range(QED_BAR_ACQUIRE_TIMEOUT_USLEEP, + QED_BAR_ACQUIRE_TIMEOUT_USLEEP * 2); } DP_NOTICE(p_hwfn, "PTT acquire timeout - failed to allocate PTT\n"); diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c index 511ab214eb9c..980e7289b481 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c @@ -999,13 +999,14 @@ static void _qed_iscsi_get_pstats(struct qed_hwfn *p_hwfn, } static int qed_iscsi_get_stats(struct qed_hwfn *p_hwfn, - struct qed_iscsi_stats *stats) + struct qed_iscsi_stats *stats, + bool is_atomic) { struct qed_ptt *p_ptt; memset(stats, 0, sizeof(*stats)); - p_ptt = qed_ptt_acquire(p_hwfn); + p_ptt = qed_ptt_acquire_context(p_hwfn, is_atomic); if (!p_ptt) { DP_ERR(p_hwfn, "Failed to acquire ptt\n"); return -EAGAIN; @@ -1336,9 +1337,16 @@ static int qed_iscsi_destroy_conn(struct qed_dev *cdev, QED_SPQ_MODE_EBLOCK, NULL); } +static int qed_iscsi_stats_context(struct qed_dev *cdev, + struct qed_iscsi_stats *stats, + bool is_atomic) +{ + return qed_iscsi_get_stats(QED_AFFIN_HWFN(cdev), stats, is_atomic); +} + static int qed_iscsi_stats(struct qed_dev *cdev, struct qed_iscsi_stats *stats) { - return qed_iscsi_get_stats(QED_AFFIN_HWFN(cdev), stats); + return qed_iscsi_stats_context(cdev, stats, false); } static int qed_iscsi_change_mac(struct qed_dev *cdev, @@ -1358,13 +1366,14 @@ static int qed_iscsi_change_mac(struct qed_dev *cdev, } void qed_get_protocol_stats_iscsi(struct qed_dev *cdev, - struct qed_mcp_iscsi_stats *stats) + struct qed_mcp_iscsi_stats *stats, + bool is_atomic) { struct qed_iscsi_stats proto_stats; /* Retrieve FW statistics */ memset(&proto_stats, 0, sizeof(proto_stats)); - if (qed_iscsi_stats(cdev, &proto_stats)) { + if (qed_iscsi_stats_context(cdev, &proto_stats, is_atomic)) { DP_VERBOSE(cdev, QED_MSG_STORAGE, "Failed to collect ISCSI statistics\n"); return; diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h index dec2b00259d4..974cb8d26608 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h @@ -39,11 +39,14 @@ void qed_iscsi_free(struct qed_hwfn *p_hwfn); * * @cdev: Qed dev pointer. * @stats: Points to struct that will be filled with statistics. + * @is_atomic: Hint from the caller - if the func can sleep or not. * + * Context: The function should not sleep in case is_atomic == true. * Return: Void. */ void qed_get_protocol_stats_iscsi(struct qed_dev *cdev, - struct qed_mcp_iscsi_stats *stats); + struct qed_mcp_iscsi_stats *stats, + bool is_atomic); #else /* IS_ENABLED(CONFIG_QED_ISCSI) */ static inline int qed_iscsi_alloc(struct qed_hwfn *p_hwfn) { @@ -56,7 +59,8 @@ static inline void qed_iscsi_free(struct qed_hwfn *p_hwfn) {} static inline void qed_get_protocol_stats_iscsi(struct qed_dev *cdev, - struct qed_mcp_iscsi_stats *stats) {} + struct qed_mcp_iscsi_stats *stats, + bool is_atomic) {} #endif /* IS_ENABLED(CONFIG_QED_ISCSI) */ #endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 7776d3bdd459..970b9aabbc3d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -1863,7 +1863,8 @@ static void __qed_get_vport_stats(struct qed_hwfn *p_hwfn, } static void _qed_get_vport_stats(struct qed_dev *cdev, - struct qed_eth_stats *stats) + struct qed_eth_stats *stats, + bool is_atomic) { u8 fw_vport = 0; int i; @@ -1872,10 +1873,11 @@ static void _qed_get_vport_stats(struct qed_dev *cdev, for_each_hwfn(cdev, i) { struct qed_hwfn *p_hwfn = &cdev->hwfns[i]; - struct qed_ptt *p_ptt = IS_PF(cdev) ? qed_ptt_acquire(p_hwfn) - : NULL; + struct qed_ptt *p_ptt; bool b_get_port_stats; + p_ptt = IS_PF(cdev) ? qed_ptt_acquire_context(p_hwfn, is_atomic) + : NULL; if (IS_PF(cdev)) { /* The main vport index is relative first */ if (qed_fw_vport(p_hwfn, 0, &fw_vport)) { @@ -1901,6 +1903,13 @@ out: void qed_get_vport_stats(struct qed_dev *cdev, struct qed_eth_stats *stats) { + qed_get_vport_stats_context(cdev, stats, false); +} + +void qed_get_vport_stats_context(struct qed_dev *cdev, + struct qed_eth_stats *stats, + bool is_atomic) +{ u32 i; if (!cdev || cdev->recov_in_prog) { @@ -1908,7 +1917,7 @@ void qed_get_vport_stats(struct qed_dev *cdev, struct qed_eth_stats *stats) return; } - _qed_get_vport_stats(cdev, stats); + _qed_get_vport_stats(cdev, stats, is_atomic); if (!cdev->reset_stats) return; @@ -1960,7 +1969,7 @@ void qed_reset_vport_stats(struct qed_dev *cdev) if (!cdev->reset_stats) { DP_INFO(cdev, "Reset stats not allocated\n"); } else { - _qed_get_vport_stats(cdev, cdev->reset_stats); + _qed_get_vport_stats(cdev, cdev->reset_stats, false); cdev->reset_stats->common.link_change_count = 0; } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h index a538cf478c14..2d2f82c785ad 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h @@ -249,8 +249,32 @@ qed_sp_eth_rx_queues_update(struct qed_hwfn *p_hwfn, enum spq_mode comp_mode, struct qed_spq_comp_cb *p_comp_data); +/** + * qed_get_vport_stats(): Fills provided statistics + * struct with statistics. + * + * @cdev: Qed dev pointer. + * @stats: Points to struct that will be filled with statistics. + * + * Return: Void. + */ void qed_get_vport_stats(struct qed_dev *cdev, struct qed_eth_stats *stats); +/** + * qed_get_vport_stats_context(): Fills provided statistics + * struct with statistics. + * + * @cdev: Qed dev pointer. + * @stats: Points to struct that will be filled with statistics. + * @is_atomic: Hint from the caller - if the func can sleep or not. + * + * Context: The function should not sleep in case is_atomic == true. + * Return: Void. + */ +void qed_get_vport_stats_context(struct qed_dev *cdev, + struct qed_eth_stats *stats, + bool is_atomic); + void qed_reset_vport_stats(struct qed_dev *cdev); /** diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index f5af83342856..c278f8893042 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -3092,7 +3092,7 @@ void qed_get_protocol_stats(struct qed_dev *cdev, switch (type) { case QED_MCP_LAN_STATS: - qed_get_vport_stats(cdev, ð_stats); + qed_get_vport_stats_context(cdev, ð_stats, true); stats->lan_stats.ucast_rx_pkts = eth_stats.common.rx_ucast_pkts; stats->lan_stats.ucast_tx_pkts = @@ -3100,10 +3100,10 @@ void qed_get_protocol_stats(struct qed_dev *cdev, stats->lan_stats.fcs_err = -1; break; case QED_MCP_FCOE_STATS: - qed_get_protocol_stats_fcoe(cdev, &stats->fcoe_stats); + qed_get_protocol_stats_fcoe(cdev, &stats->fcoe_stats, true); break; case QED_MCP_ISCSI_STATS: - qed_get_protocol_stats_iscsi(cdev, &stats->iscsi_stats); + qed_get_protocol_stats_iscsi(cdev, &stats->iscsi_stats, true); break; default: DP_VERBOSE(cdev, QED_MSG_SP, diff --git a/drivers/net/ethernet/sfc/falcon/selftest.c b/drivers/net/ethernet/sfc/falcon/selftest.c index 9e5ce2a13787..cf1d67b6d86d 100644 --- a/drivers/net/ethernet/sfc/falcon/selftest.c +++ b/drivers/net/ethernet/sfc/falcon/selftest.c @@ -40,15 +40,16 @@ */ struct ef4_loopback_payload { char pad[2]; /* Ensures ip is 4-byte aligned */ - struct ethhdr header; - struct iphdr ip; - struct udphdr udp; - __be16 iteration; - char msg[64]; + struct_group_attr(packet, __packed, + struct ethhdr header; + struct iphdr ip; + struct udphdr udp; + __be16 iteration; + char msg[64]; + ); } __packed __aligned(4); -#define EF4_LOOPBACK_PAYLOAD_LEN (sizeof(struct ef4_loopback_payload) - \ - offsetof(struct ef4_loopback_payload, \ - header)) +#define EF4_LOOPBACK_PAYLOAD_LEN \ + sizeof_field(struct ef4_loopback_payload, packet) /* Loopback test source MAC address */ static const u8 payload_source[ETH_ALEN] __aligned(2) = { @@ -299,7 +300,7 @@ void ef4_loopback_rx_packet(struct ef4_nic *efx, payload = &state->payload; - memcpy(&received.header, buf_ptr, + memcpy(&received.packet, buf_ptr, min_t(int, pkt_len, EF4_LOOPBACK_PAYLOAD_LEN)); received.ip.saddr = payload->ip.saddr; if (state->offload_csum) @@ -370,7 +371,7 @@ void ef4_loopback_rx_packet(struct ef4_nic *efx, buf_ptr, pkt_len, 0); netif_err(efx, drv, efx->net_dev, "expected packet:\n"); print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 0x10, 1, - &state->payload.header, EF4_LOOPBACK_PAYLOAD_LEN, + &state->payload.packet, EF4_LOOPBACK_PAYLOAD_LEN, 0); } #endif @@ -440,6 +441,8 @@ static int ef4_begin_loopback(struct ef4_tx_queue *tx_queue) payload->ip.saddr = htonl(INADDR_LOOPBACK | (i << 2)); /* Strip off the leading padding */ skb_pull(skb, offsetof(struct ef4_loopback_payload, header)); + /* Strip off the trailing padding */ + skb_trim(skb, EF4_LOOPBACK_PAYLOAD_LEN); /* Ensure everything we've written is visible to the * interrupt handler. */ diff --git a/drivers/net/ethernet/sfc/selftest.c b/drivers/net/ethernet/sfc/selftest.c index 96d856b9043c..19a0b8584afb 100644 --- a/drivers/net/ethernet/sfc/selftest.c +++ b/drivers/net/ethernet/sfc/selftest.c @@ -43,15 +43,16 @@ */ struct efx_loopback_payload { char pad[2]; /* Ensures ip is 4-byte aligned */ - struct ethhdr header; - struct iphdr ip; - struct udphdr udp; - __be16 iteration; - char msg[64]; + struct_group_attr(packet, __packed, + struct ethhdr header; + struct iphdr ip; + struct udphdr udp; + __be16 iteration; + char msg[64]; + ); } __packed __aligned(4); -#define EFX_LOOPBACK_PAYLOAD_LEN (sizeof(struct efx_loopback_payload) - \ - offsetof(struct efx_loopback_payload, \ - header)) +#define EFX_LOOPBACK_PAYLOAD_LEN \ + sizeof_field(struct efx_loopback_payload, packet) /* Loopback test source MAC address */ static const u8 payload_source[ETH_ALEN] __aligned(2) = { @@ -297,7 +298,7 @@ void efx_loopback_rx_packet(struct efx_nic *efx, payload = &state->payload; - memcpy(&received.header, buf_ptr, + memcpy(&received.packet, buf_ptr, min_t(int, pkt_len, EFX_LOOPBACK_PAYLOAD_LEN)); received.ip.saddr = payload->ip.saddr; if (state->offload_csum) @@ -368,7 +369,7 @@ void efx_loopback_rx_packet(struct efx_nic *efx, buf_ptr, pkt_len, 0); netif_err(efx, drv, efx->net_dev, "expected packet:\n"); print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 0x10, 1, - &state->payload.header, EFX_LOOPBACK_PAYLOAD_LEN, + &state->payload.packet, EFX_LOOPBACK_PAYLOAD_LEN, 0); } #endif @@ -438,6 +439,8 @@ static int efx_begin_loopback(struct efx_tx_queue *tx_queue) payload->ip.saddr = htonl(INADDR_LOOPBACK | (i << 2)); /* Strip off the leading padding */ skb_pull(skb, offsetof(struct efx_loopback_payload, header)); + /* Strip off the trailing padding */ + skb_trim(skb, EFX_LOOPBACK_PAYLOAD_LEN); /* Ensure everything we've written is visible to the * interrupt handler. */ diff --git a/drivers/net/ethernet/sfc/siena/selftest.c b/drivers/net/ethernet/sfc/siena/selftest.c index 111ac17194a5..b55fd3346972 100644 --- a/drivers/net/ethernet/sfc/siena/selftest.c +++ b/drivers/net/ethernet/sfc/siena/selftest.c @@ -43,15 +43,16 @@ */ struct efx_loopback_payload { char pad[2]; /* Ensures ip is 4-byte aligned */ - struct ethhdr header; - struct iphdr ip; - struct udphdr udp; - __be16 iteration; - char msg[64]; + struct_group_attr(packet, __packed, + struct ethhdr header; + struct iphdr ip; + struct udphdr udp; + __be16 iteration; + char msg[64]; + ); } __packed __aligned(4); -#define EFX_LOOPBACK_PAYLOAD_LEN (sizeof(struct efx_loopback_payload) - \ - offsetof(struct efx_loopback_payload, \ - header)) +#define EFX_LOOPBACK_PAYLOAD_LEN \ + sizeof_field(struct efx_loopback_payload, packet) /* Loopback test source MAC address */ static const u8 payload_source[ETH_ALEN] __aligned(2) = { @@ -297,7 +298,7 @@ void efx_siena_loopback_rx_packet(struct efx_nic *efx, payload = &state->payload; - memcpy(&received.header, buf_ptr, + memcpy(&received.packet, buf_ptr, min_t(int, pkt_len, EFX_LOOPBACK_PAYLOAD_LEN)); received.ip.saddr = payload->ip.saddr; if (state->offload_csum) @@ -368,7 +369,7 @@ void efx_siena_loopback_rx_packet(struct efx_nic *efx, buf_ptr, pkt_len, 0); netif_err(efx, drv, efx->net_dev, "expected packet:\n"); print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 0x10, 1, - &state->payload.header, EFX_LOOPBACK_PAYLOAD_LEN, + &state->payload.packet, EFX_LOOPBACK_PAYLOAD_LEN, 0); } #endif @@ -438,6 +439,8 @@ static int efx_begin_loopback(struct efx_tx_queue *tx_queue) payload->ip.saddr = htonl(INADDR_LOOPBACK | (i << 2)); /* Strip off the leading padding */ skb_pull(skb, offsetof(struct efx_loopback_payload, header)); + /* Strip off the trailing padding */ + skb_trim(skb, EFX_LOOPBACK_PAYLOAD_LEN); /* Ensure everything we've written is visible to the * interrupt handler. */ diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 2d7347b71c41..0dcd6a568b06 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -1851,6 +1851,17 @@ static int netsec_of_probe(struct platform_device *pdev, return err; } + /* + * SynQuacer is physically configured with TX and RX delays + * but the standard firmware claimed otherwise for a long + * time, ignore it. + */ + if (of_machine_is_compatible("socionext,developer-box") && + priv->phy_interface != PHY_INTERFACE_MODE_RGMII_ID) { + dev_warn(&pdev->dev, "Outdated firmware reports incorrect PHY mode, overriding\n"); + priv->phy_interface = PHY_INTERFACE_MODE_RGMII_ID; + } + priv->phy_np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); if (!priv->phy_np) { dev_err(&pdev->dev, "missing required property 'phy-handle'\n"); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c index f8367c5b490b..fbb0ccf84afc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c @@ -234,7 +234,8 @@ static int tegra_mgbe_probe(struct platform_device *pdev) res.addr = mgbe->regs; res.irq = irq; - mgbe->clks = devm_kzalloc(&pdev->dev, sizeof(*mgbe->clks), GFP_KERNEL); + mgbe->clks = devm_kcalloc(&pdev->dev, ARRAY_SIZE(mgbe_clks), + sizeof(*mgbe->clks), GFP_KERNEL); if (!mgbe->clks) return -ENOMEM; diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index e0ac1bcd9925..49f303353ecb 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1567,12 +1567,16 @@ static int temac_probe(struct platform_device *pdev) } /* Error handle returned DMA RX and TX interrupts */ - if (lp->rx_irq < 0) - return dev_err_probe(&pdev->dev, lp->rx_irq, + if (lp->rx_irq <= 0) { + rc = lp->rx_irq ?: -EINVAL; + return dev_err_probe(&pdev->dev, rc, "could not get DMA RX irq\n"); - if (lp->tx_irq < 0) - return dev_err_probe(&pdev->dev, lp->tx_irq, + } + if (lp->tx_irq <= 0) { + rc = lp->tx_irq ?: -EINVAL; + return dev_err_probe(&pdev->dev, rc, "could not get DMA TX irq\n"); + } if (temac_np) { /* Retrieve the MAC address */ diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 984dfa5d6c11..144ec756c796 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -743,7 +743,7 @@ static bool macsec_post_decrypt(struct sk_buff *skb, struct macsec_secy *secy, u u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); - secy->netdev->stats.rx_dropped++; + DEV_STATS_INC(secy->netdev, rx_dropped); return false; } @@ -767,7 +767,7 @@ static bool macsec_post_decrypt(struct sk_buff *skb, struct macsec_secy *secy, u rxsc_stats->stats.InPktsNotValid++; u64_stats_update_end(&rxsc_stats->syncp); this_cpu_inc(rx_sa->stats->InPktsNotValid); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); return false; } @@ -1069,7 +1069,7 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoTag++; u64_stats_update_end(&secy_stats->syncp); - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); continue; } @@ -1179,7 +1179,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsBadTag++; u64_stats_update_end(&secy_stats->syncp); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); goto drop_nosa; } @@ -1196,7 +1196,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsNotUsingSA++; u64_stats_update_end(&rxsc_stats->syncp); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); if (active_rx_sa) this_cpu_inc(active_rx_sa->stats->InPktsNotUsingSA); goto drop_nosa; @@ -1230,7 +1230,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); goto drop; } } @@ -1271,7 +1271,7 @@ deliver: if (ret == NET_RX_SUCCESS) count_rx(dev, len); else - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); rcu_read_unlock(); @@ -1308,7 +1308,7 @@ nosci: u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoSCI++; u64_stats_update_end(&secy_stats->syncp); - macsec->secy.netdev->stats.rx_errors++; + DEV_STATS_INC(macsec->secy.netdev, rx_errors); continue; } @@ -1327,7 +1327,7 @@ nosci: secy_stats->stats.InPktsUnknownSCI++; u64_stats_update_end(&secy_stats->syncp); } else { - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); } } @@ -3422,7 +3422,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, if (!secy->operational) { kfree_skb(skb); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -3430,7 +3430,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, skb = macsec_encrypt(skb, dev); if (IS_ERR(skb)) { if (PTR_ERR(skb) != -EINPROGRESS) - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -3667,9 +3667,9 @@ static void macsec_get_stats64(struct net_device *dev, dev_fetch_sw_netstats(s, dev->tstats); - s->rx_dropped = dev->stats.rx_dropped; - s->tx_dropped = dev->stats.tx_dropped; - s->rx_errors = dev->stats.rx_errors; + s->rx_dropped = atomic_long_read(&dev->stats.__rx_dropped); + s->tx_dropped = atomic_long_read(&dev->stats.__tx_dropped); + s->rx_errors = atomic_long_read(&dev->stats.__rx_errors); } static int macsec_get_iflink(const struct net_device *dev) diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index c1f307d90518..8a77ec33b417 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -459,21 +459,27 @@ static int at803x_set_wol(struct phy_device *phydev, phy_write_mmd(phydev, MDIO_MMD_PCS, offsets[i], mac[(i * 2) + 1] | (mac[(i * 2)] << 8)); - /* Enable WOL function */ - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL, - 0, AT803X_WOL_EN); - if (ret) - return ret; + /* Enable WOL function for 1588 */ + if (phydev->drv->phy_id == ATH8031_PHY_ID) { + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + 0, AT803X_WOL_EN); + if (ret) + return ret; + } /* Enable WOL interrupt */ ret = phy_modify(phydev, AT803X_INTR_ENABLE, 0, AT803X_INTR_ENABLE_WOL); if (ret) return ret; } else { - /* Disable WoL function */ - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL, - AT803X_WOL_EN, 0); - if (ret) - return ret; + /* Disable WoL function for 1588 */ + if (phydev->drv->phy_id == ATH8031_PHY_ID) { + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + AT803X_WOL_EN, 0); + if (ret) + return ret; + } /* Disable WOL interrupt */ ret = phy_modify(phydev, AT803X_INTR_ENABLE, AT803X_INTR_ENABLE_WOL, 0); if (ret) @@ -508,11 +514,11 @@ static void at803x_get_wol(struct phy_device *phydev, wol->supported = WAKE_MAGIC; wol->wolopts = 0; - value = phy_read_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL); + value = phy_read(phydev, AT803X_INTR_ENABLE); if (value < 0) return; - if (value & AT803X_WOL_EN) + if (value & AT803X_INTR_ENABLE_WOL) wol->wolopts |= WAKE_MAGIC; } @@ -858,9 +864,6 @@ static int at803x_probe(struct phy_device *phydev) if (phydev->drv->phy_id == ATH8031_PHY_ID) { int ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG); int mode_cfg; - struct ethtool_wolinfo wol = { - .wolopts = 0, - }; if (ccr < 0) return ccr; @@ -877,12 +880,14 @@ static int at803x_probe(struct phy_device *phydev) break; } - /* Disable WOL by default */ - ret = at803x_set_wol(phydev, &wol); - if (ret < 0) { - phydev_err(phydev, "failed to disable WOL on probe: %d\n", ret); + /* Disable WoL in 1588 register which is enabled + * by default + */ + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + AT803X_WOL_EN, 0); + if (ret) return ret; - } } return 0; @@ -2059,8 +2064,6 @@ static struct phy_driver at803x_driver[] = { .flags = PHY_POLL_CABLE_TEST, .config_init = at803x_config_init, .link_change_notify = at803x_link_change_notify, - .set_wol = at803x_set_wol, - .get_wol = at803x_get_wol, .suspend = at803x_suspend, .resume = at803x_resume, /* PHY_BASIC_FEATURES */ diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 9137fb8c1c42..49d1d6acf95e 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -534,7 +534,7 @@ static int tap_open(struct inode *inode, struct file *file) q->sock.state = SS_CONNECTED; q->sock.file = file; q->sock.ops = &tap_socket_ops; - sock_init_data_uid(&q->sock, &q->sk, inode->i_uid); + sock_init_data_uid(&q->sock, &q->sk, current_fsuid()); q->sk.sk_write_space = tap_sock_write_space; q->sk.sk_destruct = tap_sock_destruct; q->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index d75456adc62a..100339bc8b04 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1594,7 +1594,7 @@ static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile, if (zerocopy) return false; - if (SKB_DATA_ALIGN(len + TUN_RX_PAD) + + if (SKB_DATA_ALIGN(len + TUN_RX_PAD + XDP_PACKET_HEADROOM) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) > PAGE_SIZE) return false; @@ -3469,7 +3469,7 @@ static int tun_chr_open(struct inode *inode, struct file * file) tfile->socket.file = file; tfile->socket.ops = &tun_socket_ops; - sock_init_data_uid(&tfile->socket, &tfile->sk, inode->i_uid); + sock_init_data_uid(&tfile->socket, &tfile->sk, current_fsuid()); tfile->sk.sk_write_space = tun_sock_write_space; tfile->sk.sk_sndbuf = INT_MAX; diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index c00a89b24df9..6d61052353f0 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -618,6 +618,13 @@ static const struct usb_device_id products[] = { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x04DD, + .idProduct = 0x8005, /* A-300 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = 0, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, .idProduct = 0x8006, /* B-500/SL-5600 */ ZAURUS_MASTER_INTERFACE, .driver_info = 0, @@ -625,11 +632,25 @@ static const struct usb_device_id products[] = { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x04DD, + .idProduct = 0x8006, /* B-500/SL-5600 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = 0, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, .idProduct = 0x8007, /* C-700 */ ZAURUS_MASTER_INTERFACE, .driver_info = 0, }, { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, + .idProduct = 0x8007, /* C-700 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = 0, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x04DD, .idProduct = 0x9031, /* C-750 C-760 */ diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index c458c030fadf..59cde06aa7f6 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -4224,8 +4224,6 @@ static void lan78xx_disconnect(struct usb_interface *intf) if (!dev) return; - set_bit(EVENT_DEV_DISCONNECT, &dev->flags); - netif_napi_del(&dev->napi); udev = interface_to_usbdev(intf); @@ -4233,6 +4231,8 @@ static void lan78xx_disconnect(struct usb_interface *intf) unregister_netdev(net); + timer_shutdown_sync(&dev->stat_monitor); + set_bit(EVENT_DEV_DISCONNECT, &dev->flags); cancel_delayed_work_sync(&dev->wq); phydev = net->phydev; @@ -4247,9 +4247,6 @@ static void lan78xx_disconnect(struct usb_interface *intf) usb_scuttle_anchored_urbs(&dev->deferred); - if (timer_pending(&dev->stat_monitor)) - del_timer_sync(&dev->stat_monitor); - lan78xx_unbind(dev, intf); lan78xx_free_tx_resources(dev); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 417f7ea1fffa..344af3c5c836 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1423,6 +1423,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)}, /* Quectel EG91 */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0195, 4)}, /* Quectel EG95 */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ + {QMI_QUIRK_SET_DTR(0x2c7c, 0x030e, 4)}, /* Quectel EM05GV2 */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */ {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ {QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/ diff --git a/drivers/net/usb/zaurus.c b/drivers/net/usb/zaurus.c index 7984f2157d22..df3617c4c44e 100644 --- a/drivers/net/usb/zaurus.c +++ b/drivers/net/usb/zaurus.c @@ -289,11 +289,25 @@ static const struct usb_device_id products [] = { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x04DD, + .idProduct = 0x8005, /* A-300 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = (unsigned long)&bogus_mdlm_info, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, .idProduct = 0x8006, /* B-500/SL-5600 */ ZAURUS_MASTER_INTERFACE, .driver_info = ZAURUS_PXA_INFO, }, { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, + .idProduct = 0x8006, /* B-500/SL-5600 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = (unsigned long)&bogus_mdlm_info, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x04DD, .idProduct = 0x8007, /* C-700 */ @@ -301,6 +315,13 @@ static const struct usb_device_id products [] = { .driver_info = ZAURUS_PXA_INFO, }, { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, + .idProduct = 0x8007, /* C-700 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = (unsigned long)&bogus_mdlm_info, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x04DD, .idProduct = 0x9031, /* C-750 C-760 */ diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c index a3de081cda5e..c3ff30ab782e 100644 --- a/drivers/net/vxlan/vxlan_vnifilter.c +++ b/drivers/net/vxlan/vxlan_vnifilter.c @@ -713,6 +713,12 @@ static struct vxlan_vni_node *vxlan_vni_alloc(struct vxlan_dev *vxlan, return vninode; } +static void vxlan_vni_free(struct vxlan_vni_node *vninode) +{ + free_percpu(vninode->stats); + kfree(vninode); +} + static int vxlan_vni_add(struct vxlan_dev *vxlan, struct vxlan_vni_group *vg, u32 vni, union vxlan_addr *group, @@ -740,7 +746,7 @@ static int vxlan_vni_add(struct vxlan_dev *vxlan, &vninode->vnode, vxlan_vni_rht_params); if (err) { - kfree(vninode); + vxlan_vni_free(vninode); return err; } @@ -763,8 +769,7 @@ static void vxlan_vni_node_rcu_free(struct rcu_head *rcu) struct vxlan_vni_node *v; v = container_of(rcu, struct vxlan_vni_node, rcu); - free_percpu(v->stats); - kfree(v); + vxlan_vni_free(v); } static int vxlan_vni_del(struct vxlan_dev *vxlan, diff --git a/drivers/net/wireguard/allowedips.c b/drivers/net/wireguard/allowedips.c index 5bf7822c53f1..0ba714ca5185 100644 --- a/drivers/net/wireguard/allowedips.c +++ b/drivers/net/wireguard/allowedips.c @@ -6,7 +6,7 @@ #include "allowedips.h" #include "peer.h" -enum { MAX_ALLOWEDIPS_BITS = 128 }; +enum { MAX_ALLOWEDIPS_DEPTH = 129 }; static struct kmem_cache *node_cache; @@ -42,7 +42,7 @@ static void push_rcu(struct allowedips_node **stack, struct allowedips_node __rcu *p, unsigned int *len) { if (rcu_access_pointer(p)) { - if (WARN_ON(IS_ENABLED(DEBUG) && *len >= MAX_ALLOWEDIPS_BITS)) + if (WARN_ON(IS_ENABLED(DEBUG) && *len >= MAX_ALLOWEDIPS_DEPTH)) return; stack[(*len)++] = rcu_dereference_raw(p); } @@ -55,7 +55,7 @@ static void node_free_rcu(struct rcu_head *rcu) static void root_free_rcu(struct rcu_head *rcu) { - struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_BITS] = { + struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_DEPTH] = { container_of(rcu, struct allowedips_node, rcu) }; unsigned int len = 1; @@ -68,7 +68,7 @@ static void root_free_rcu(struct rcu_head *rcu) static void root_remove_peer_lists(struct allowedips_node *root) { - struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_BITS] = { root }; + struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_DEPTH] = { root }; unsigned int len = 1; while (len > 0 && (node = stack[--len])) { diff --git a/drivers/net/wireguard/selftest/allowedips.c b/drivers/net/wireguard/selftest/allowedips.c index 78ebe2892a78..3d1f64ff2e12 100644 --- a/drivers/net/wireguard/selftest/allowedips.c +++ b/drivers/net/wireguard/selftest/allowedips.c @@ -593,16 +593,20 @@ bool __init wg_allowedips_selftest(void) wg_allowedips_remove_by_peer(&t, a, &mutex); test_negative(4, a, 192, 168, 0, 1); - /* These will hit the WARN_ON(len >= MAX_ALLOWEDIPS_BITS) in free_node + /* These will hit the WARN_ON(len >= MAX_ALLOWEDIPS_DEPTH) in free_node * if something goes wrong. */ - for (i = 0; i < MAX_ALLOWEDIPS_BITS; ++i) { - part = cpu_to_be64(~(1LLU << (i % 64))); - memset(&ip, 0xff, 16); - memcpy((u8 *)&ip + (i < 64) * 8, &part, 8); + for (i = 0; i < 64; ++i) { + part = cpu_to_be64(~0LLU << i); + memset(&ip, 0xff, 8); + memcpy((u8 *)&ip + 8, &part, 8); + wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex); + memcpy(&ip, &part, 8); + memset((u8 *)&ip + 8, 0, 8); wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex); } - + memset(&ip, 0, 16); + wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex); wg_allowedips_free(&t, &mutex); wg_allowedips_init(&t); diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c index 1cebba7889d7..139da578831a 100644 --- a/drivers/net/wireless/ath/ath11k/ahb.c +++ b/drivers/net/wireless/ath/ath11k/ahb.c @@ -376,7 +376,6 @@ static void ath11k_ahb_ext_irq_enable(struct ath11k_base *ab) struct ath11k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i]; if (!irq_grp->napi_enabled) { - dev_set_threaded(&irq_grp->napi_ndev, true); napi_enable(&irq_grp->napi); irq_grp->napi_enabled = true; } diff --git a/drivers/net/wireless/ath/ath11k/pcic.c b/drivers/net/wireless/ath/ath11k/pcic.c index c899616fbee4..c63083633b37 100644 --- a/drivers/net/wireless/ath/ath11k/pcic.c +++ b/drivers/net/wireless/ath/ath11k/pcic.c @@ -466,7 +466,6 @@ void ath11k_pcic_ext_irq_enable(struct ath11k_base *ab) struct ath11k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i]; if (!irq_grp->napi_enabled) { - dev_set_threaded(&irq_grp->napi_ndev, true); napi_enable(&irq_grp->napi); irq_grp->napi_enabled = true; } diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index 6512267ae4ca..4928e4e91660 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -2144,8 +2144,7 @@ int ath12k_wmi_send_scan_start_cmd(struct ath12k *ar, struct wmi_tlv *tlv; void *ptr; int i, ret, len; - u32 *tmp_ptr; - u8 extraie_len_with_pad = 0; + u32 *tmp_ptr, extraie_len_with_pad = 0; struct ath12k_wmi_hint_short_ssid_arg *s_ssid = NULL; struct ath12k_wmi_hint_bssid_arg *hint_bssid = NULL; diff --git a/drivers/net/wireless/ath/ath6kl/Makefile b/drivers/net/wireless/ath/ath6kl/Makefile index a75bfa9fd1cf..dc2b3b46781e 100644 --- a/drivers/net/wireless/ath/ath6kl/Makefile +++ b/drivers/net/wireless/ath/ath6kl/Makefile @@ -36,11 +36,6 @@ ath6kl_core-y += wmi.o ath6kl_core-y += core.o ath6kl_core-y += recovery.o -# FIXME: temporarily silence -Wdangling-pointer on non W=1+ builds -ifndef KBUILD_EXTRA_WARN -CFLAGS_htc_mbox.o += $(call cc-disable-warning, dangling-pointer) -endif - ath6kl_core-$(CONFIG_NL80211_TESTMODE) += testmode.o ath6kl_core-$(CONFIG_ATH6KL_TRACING) += trace.o diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index de8a2e27f49c..2a90bb24ba77 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -1456,6 +1456,10 @@ brcmf_run_escan(struct brcmf_cfg80211_info *cfg, struct brcmf_if *ifp, params_size -= BRCMF_SCAN_PARAMS_V2_FIXED_SIZE; params_size += BRCMF_SCAN_PARAMS_FIXED_SIZE; params_v1 = kzalloc(params_size, GFP_KERNEL); + if (!params_v1) { + err = -ENOMEM; + goto exit_params; + } params_v1->version = cpu_to_le32(BRCMF_ESCAN_REQ_VERSION); brcmf_scan_params_v2_to_v1(¶ms->params_v2_le, ¶ms_v1->params_le); kfree(params); @@ -1473,6 +1477,7 @@ brcmf_run_escan(struct brcmf_cfg80211_info *cfg, struct brcmf_if *ifp, bphy_err(drvr, "error (%d)\n", err); } +exit_params: kfree(params); exit: return err; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h index 792adaf880b4..bece26741d3a 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h @@ -398,7 +398,12 @@ struct brcmf_scan_params_le { * fixed parameter portion is assumed, otherwise * ssid in the fixed portion is ignored */ - __le16 channel_list[1]; /* list of chanspecs */ + union { + __le16 padding; /* Reserve space for at least 1 entry for abort + * which uses an on stack brcmf_scan_params_le + */ + DECLARE_FLEX_ARRAY(__le16, channel_list); /* chanspecs */ + }; }; struct brcmf_scan_params_v2_le { diff --git a/drivers/net/wireless/legacy/rayctl.h b/drivers/net/wireless/legacy/rayctl.h index 2b0f332043d7..1f3bde8ac73d 100644 --- a/drivers/net/wireless/legacy/rayctl.h +++ b/drivers/net/wireless/legacy/rayctl.h @@ -577,7 +577,7 @@ struct tx_msg { struct tib_structure tib; struct phy_header phy; struct mac_header mac; - UCHAR var[1]; + UCHAR var[]; }; /****** ECF Receive Control Structure (RCS) Area at Shared RAM offset 0x0800 */ diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c index 68e88224b8b1..ccedea7e8a50 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c @@ -128,12 +128,12 @@ mt7615_eeprom_parse_hw_band_cap(struct mt7615_dev *dev) case MT_EE_5GHZ: dev->mphy.cap.has_5ghz = true; break; - case MT_EE_2GHZ: - dev->mphy.cap.has_2ghz = true; - break; case MT_EE_DBDC: dev->dbdc_support = true; fallthrough; + case MT_EE_2GHZ: + dev->mphy.cap.has_2ghz = true; + break; default: dev->mphy.cap.has_2ghz = true; dev->mphy.cap.has_5ghz = true; diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c index b114babec698..c93e6250cb8b 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.c +++ b/drivers/net/wireless/realtek/rtw89/mac.c @@ -2524,7 +2524,7 @@ static int cmac_dma_init(struct rtw89_dev *rtwdev, u8 mac_idx) u32 reg; int ret; - if (chip_id != RTL8852A && chip_id != RTL8852B) + if (chip_id != RTL8852B) return 0; ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index c8d20cddf658..88f760a7cbc3 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -396,7 +396,7 @@ static void xenvif_get_requests(struct xenvif_queue *queue, struct gnttab_map_grant_ref *gop = queue->tx_map_ops + *map_ops; struct xen_netif_tx_request *txp = first; - nr_slots = shinfo->nr_frags + 1; + nr_slots = shinfo->nr_frags + frag_overflow + 1; copy_count(skb) = 0; XENVIF_TX_CB(skb)->split_mask = 0; @@ -462,8 +462,8 @@ static void xenvif_get_requests(struct xenvif_queue *queue, } } - for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; - shinfo->nr_frags++, gop++) { + for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS; + shinfo->nr_frags++, gop++, nr_slots--) { index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; xenvif_tx_create_map_op(queue, pending_idx, txp, @@ -476,12 +476,12 @@ static void xenvif_get_requests(struct xenvif_queue *queue, txp++; } - if (frag_overflow) { + if (nr_slots > 0) { shinfo = skb_shinfo(nskb); frags = shinfo->frags; - for (shinfo->nr_frags = 0; shinfo->nr_frags < frag_overflow; + for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; shinfo->nr_frags++, txp++, gop++) { index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; @@ -492,6 +492,11 @@ static void xenvif_get_requests(struct xenvif_queue *queue, } skb_shinfo(skb)->frag_list = nskb; + } else if (nskb) { + /* A frag_list skb was allocated but it is no longer needed + * because enough slots were converted to copy ops above. + */ + kfree_skb(nskb); } (*copy_ops) = cop - queue->tx_copy_ops; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 37b6fa746662..f3a01b79148c 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3933,6 +3933,12 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) */ nvme_mpath_clear_ctrl_paths(ctrl); + /* + * Unquiesce io queues so any pending IO won't hang, especially + * those submitted from scan work + */ + nvme_unquiesce_io_queues(ctrl); + /* prevent racing with ns scanning */ flush_work(&ctrl->scan_work); @@ -3942,10 +3948,8 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) * removing the namespaces' disks; fail all the queues now to avoid * potentially having to clean up the failed sync later. */ - if (ctrl->state == NVME_CTRL_DEAD) { + if (ctrl->state == NVME_CTRL_DEAD) nvme_mark_namespaces_dead(ctrl); - nvme_unquiesce_io_queues(ctrl); - } /* this is a no-op when called from the controller reset handler */ nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING_NOIO); diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 5c3250f36ce7..d39f3219358b 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -786,11 +786,9 @@ int nvme_ns_chr_uring_cmd_iopoll(struct io_uring_cmd *ioucmd, if (!(ioucmd->flags & IORING_URING_CMD_POLLED)) return 0; - rcu_read_lock(); req = READ_ONCE(ioucmd->cookie); if (req && blk_rq_is_poll(req)) ret = blk_rq_poll(req, iob, poll_flags); - rcu_read_unlock(); return ret; } #ifdef CONFIG_NVME_MULTIPATH diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index baf69af7ea78..2f57da12d983 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3402,7 +3402,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(0x1d97, 0x2263), /* SPCC */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x144d, 0xa80b), /* Samsung PM9B1 256G and 512G */ - .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES | + NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x144d, 0xa809), /* Samsung MZALQ256HBJD 256G */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x144d, 0xa802), /* Samsung SM953 */ diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index d433b2ec07a6..337a624a537c 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -883,6 +883,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) goto out_cleanup_tagset; if (!new) { + nvme_start_freeze(&ctrl->ctrl); nvme_unquiesce_io_queues(&ctrl->ctrl); if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) { /* @@ -891,6 +892,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) * to be safe. */ ret = -ENODEV; + nvme_unfreeze(&ctrl->ctrl); goto out_wait_freeze_timed_out; } blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset, @@ -940,7 +942,6 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl, bool remove) { if (ctrl->ctrl.queue_count > 1) { - nvme_start_freeze(&ctrl->ctrl); nvme_quiesce_io_queues(&ctrl->ctrl); nvme_sync_io_queues(&ctrl->ctrl); nvme_rdma_stop_io_queues(ctrl); diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 9ce417cd32a7..5b332d9f87fc 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1868,6 +1868,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) goto out_cleanup_connect_q; if (!new) { + nvme_start_freeze(ctrl); nvme_unquiesce_io_queues(ctrl); if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) { /* @@ -1876,6 +1877,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) * to be safe. */ ret = -ENODEV; + nvme_unfreeze(ctrl); goto out_wait_freeze_timed_out; } blk_mq_update_nr_hw_queues(ctrl->tagset, @@ -1980,7 +1982,6 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, if (ctrl->queue_count <= 1) return; nvme_quiesce_admin_queue(ctrl); - nvme_start_freeze(ctrl); nvme_quiesce_io_queues(ctrl); nvme_sync_io_queues(ctrl); nvme_tcp_stop_io_queues(ctrl); diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c index bf3405f4289e..8b1dcd537020 100644 --- a/drivers/parisc/sba_iommu.c +++ b/drivers/parisc/sba_iommu.c @@ -121,6 +121,8 @@ module_param(sba_reserve_agpgart, int, 0444); MODULE_PARM_DESC(sba_reserve_agpgart, "Reserve half of IO pdir as AGPGART"); #endif +struct proc_dir_entry *proc_runway_root __ro_after_init; +struct proc_dir_entry *proc_mckinley_root __ro_after_init; /************************************ ** SBA register read and write support @@ -1968,11 +1970,15 @@ static int __init sba_driver_callback(struct parisc_device *dev) #ifdef CONFIG_PROC_FS switch (dev->id.hversion) { case PLUTO_MCKINLEY_PORT: + if (!proc_mckinley_root) + proc_mckinley_root = proc_mkdir("bus/mckinley", NULL); root = proc_mckinley_root; break; case ASTRO_RUNWAY_PORT: case IKE_MERCED_PORT: default: + if (!proc_runway_root) + proc_runway_root = proc_mkdir("bus/runway", NULL); root = proc_runway_root; break; } diff --git a/drivers/parport/parport_gsc.c b/drivers/parport/parport_gsc.c index 0dcc497b0449..5e4475254bd0 100644 --- a/drivers/parport/parport_gsc.c +++ b/drivers/parport/parport_gsc.c @@ -28,7 +28,6 @@ #include <linux/sysctl.h> #include <asm/io.h> -#include <asm/dma.h> #include <linux/uaccess.h> #include <asm/superio.h> @@ -226,9 +225,9 @@ static int parport_PS2_supported(struct parport *pb) /* --- Initialisation code -------------------------------- */ -struct parport *parport_gsc_probe_port(unsigned long base, +static struct parport *parport_gsc_probe_port(unsigned long base, unsigned long base_hi, int irq, - int dma, struct parisc_device *padev) + struct parisc_device *padev) { struct parport_gsc_private *priv; struct parport_operations *ops; @@ -250,12 +249,9 @@ struct parport *parport_gsc_probe_port(unsigned long base, } priv->ctr = 0xc; priv->ctr_writable = 0xff; - priv->dma_buf = NULL; - priv->dma_handle = 0; p->base = base; p->base_hi = base_hi; p->irq = irq; - p->dma = dma; p->modes = PARPORT_MODE_PCSPP | PARPORT_MODE_SAFEININT; p->ops = ops; p->private_data = priv; @@ -286,17 +282,9 @@ struct parport *parport_gsc_probe_port(unsigned long base, if (p->irq == PARPORT_IRQ_AUTO) { p->irq = PARPORT_IRQ_NONE; } - if (p->irq != PARPORT_IRQ_NONE) { + if (p->irq != PARPORT_IRQ_NONE) pr_cont(", irq %d", p->irq); - if (p->dma == PARPORT_DMA_AUTO) { - p->dma = PARPORT_DMA_NONE; - } - } - if (p->dma == PARPORT_DMA_AUTO) /* To use DMA, giving the irq - is mandatory (see above) */ - p->dma = PARPORT_DMA_NONE; - pr_cont(" ["); #define printmode(x) \ do { \ @@ -321,7 +309,6 @@ do { \ pr_warn("%s: irq %d in use, resorting to polled operation\n", p->name, p->irq); p->irq = PARPORT_IRQ_NONE; - p->dma = PARPORT_DMA_NONE; } } @@ -369,8 +356,7 @@ static int __init parport_init_chip(struct parisc_device *dev) pr_info("%s: enhanced parport-modes not supported\n", __func__); } - p = parport_gsc_probe_port(port, 0, dev->irq, - /* PARPORT_IRQ_NONE */ PARPORT_DMA_NONE, dev); + p = parport_gsc_probe_port(port, 0, dev->irq, dev); if (p) parport_count++; dev_set_drvdata(&dev->dev, p); @@ -382,16 +368,10 @@ static void __exit parport_remove_chip(struct parisc_device *dev) { struct parport *p = dev_get_drvdata(&dev->dev); if (p) { - struct parport_gsc_private *priv = p->private_data; struct parport_operations *ops = p->ops; parport_remove_port(p); - if (p->dma != PARPORT_DMA_NONE) - free_dma(p->dma); if (p->irq != PARPORT_IRQ_NONE) free_irq(p->irq, p); - if (priv->dma_buf) - dma_free_coherent(&priv->dev->dev, PAGE_SIZE, - priv->dma_buf, priv->dma_handle); kfree (p->private_data); parport_put_port(p); kfree (ops); /* hope no-one cached it */ diff --git a/drivers/parport/parport_gsc.h b/drivers/parport/parport_gsc.h index 9301217edf12..d447a568c257 100644 --- a/drivers/parport/parport_gsc.h +++ b/drivers/parport/parport_gsc.h @@ -63,8 +63,6 @@ struct parport_gsc_private { int writeIntrThreshold; /* buffer suitable for DMA, if DMA enabled */ - char *dma_buf; - dma_addr_t dma_handle; struct pci_dev *dev; }; @@ -199,9 +197,4 @@ extern void parport_gsc_inc_use_count(void); extern void parport_gsc_dec_use_count(void); -extern struct parport *parport_gsc_probe_port(unsigned long base, - unsigned long base_hi, - int irq, int dma, - struct parisc_device *padev); - #endif /* __DRIVERS_PARPORT_PARPORT_GSC_H */ diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 5bc81cc0a2de..46b252bbe500 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -11,6 +11,7 @@ #include <linux/pci.h> #include <linux/errno.h> #include <linux/ioport.h> +#include <linux/of.h> #include <linux/proc_fs.h> #include <linux/slab.h> @@ -332,6 +333,7 @@ void __weak pcibios_bus_add_device(struct pci_dev *pdev) { } */ void pci_bus_add_device(struct pci_dev *dev) { + struct device_node *dn = dev->dev.of_node; int retval; /* @@ -344,7 +346,7 @@ void pci_bus_add_device(struct pci_dev *dev) pci_proc_attach_device(dev); pci_bridge_d3_update(dev); - dev->match_driver = true; + dev->match_driver = !dn || of_device_is_available(dn); retval = device_attach(&dev->dev); if (retval < 0 && retval != -EPROBE_DEFER) pci_warn(dev, "device attach failed (%d)\n", retval); diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig index 8d49bad7f847..0859be86e718 100644 --- a/drivers/pci/controller/Kconfig +++ b/drivers/pci/controller/Kconfig @@ -179,7 +179,6 @@ config PCI_MVEBU depends on MVEBU_MBUS depends on ARM depends on OF - depends on BROKEN select PCI_BRIDGE_EMUL help Add support for Marvell EBU PCIe controller. This PCIe controller diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index cf61733bf78d..9952057c8819 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -485,20 +485,15 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp) if (ret) goto err_remove_edma; - if (dw_pcie_link_up(pci)) { - dw_pcie_print_link_status(pci); - } else { + if (!dw_pcie_link_up(pci)) { ret = dw_pcie_start_link(pci); if (ret) goto err_remove_edma; - - if (pci->ops && pci->ops->start_link) { - ret = dw_pcie_wait_for_link(pci); - if (ret) - goto err_stop_link; - } } + /* Ignore errors, the link may come up later */ + dw_pcie_wait_for_link(pci); + bridge->sysdata = pp; ret = pci_host_probe(bridge); diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c index c87848cd8686..1f2ee71da4da 100644 --- a/drivers/pci/controller/dwc/pcie-designware.c +++ b/drivers/pci/controller/dwc/pcie-designware.c @@ -644,20 +644,9 @@ void dw_pcie_disable_atu(struct dw_pcie *pci, u32 dir, int index) dw_pcie_writel_atu(pci, dir, index, PCIE_ATU_REGION_CTRL2, 0); } -void dw_pcie_print_link_status(struct dw_pcie *pci) -{ - u32 offset, val; - - offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); - val = dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKSTA); - - dev_info(pci->dev, "PCIe Gen.%u x%u link up\n", - FIELD_GET(PCI_EXP_LNKSTA_CLS, val), - FIELD_GET(PCI_EXP_LNKSTA_NLW, val)); -} - int dw_pcie_wait_for_link(struct dw_pcie *pci) { + u32 offset, val; int retries; /* Check if the link is up or not */ @@ -673,7 +662,12 @@ int dw_pcie_wait_for_link(struct dw_pcie *pci) return -ETIMEDOUT; } - dw_pcie_print_link_status(pci); + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + val = dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKSTA); + + dev_info(pci->dev, "PCIe Gen.%u x%u link up\n", + FIELD_GET(PCI_EXP_LNKSTA_CLS, val), + FIELD_GET(PCI_EXP_LNKSTA_NLW, val)); return 0; } diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h index 615660640801..79713ce075cc 100644 --- a/drivers/pci/controller/dwc/pcie-designware.h +++ b/drivers/pci/controller/dwc/pcie-designware.h @@ -429,7 +429,6 @@ void dw_pcie_setup(struct dw_pcie *pci); void dw_pcie_iatu_detect(struct dw_pcie *pci); int dw_pcie_edma_detect(struct dw_pcie *pci); void dw_pcie_edma_remove(struct dw_pcie *pci); -void dw_pcie_print_link_status(struct dw_pcie *pci); static inline void dw_pcie_writel_dbi(struct dw_pcie *pci, u32 reg, u32 val) { diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 328d1e416014..601129772b2d 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -498,6 +498,7 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge) acpiphp_native_scan_bridge(dev); } } else { + LIST_HEAD(add_list); int max, pass; acpiphp_rescan_slot(slot); @@ -511,10 +512,15 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge) if (pass && dev->subordinate) { check_hotplug_bridge(slot, dev); pcibios_resource_survey_bus(dev->subordinate); + if (pci_is_root_bus(bus)) + __pci_bus_size_bridges(dev->subordinate, &add_list); } } } - pci_assign_unassigned_bridge_resources(bus->self); + if (pci_is_root_bus(bus)) + __pci_bus_assign_resources(bus, &add_list, NULL); + else + pci_assign_unassigned_bridge_resources(bus->self); } acpiphp_sanitize_bus(bus); diff --git a/drivers/pci/of.c b/drivers/pci/of.c index e51219f9f523..3c158b17dcb5 100644 --- a/drivers/pci/of.c +++ b/drivers/pci/of.c @@ -34,11 +34,6 @@ int pci_set_of_node(struct pci_dev *dev) if (!node) return 0; - if (!of_device_is_available(node)) { - of_node_put(node); - return -ENODEV; - } - device_set_node(&dev->dev, of_fwnode_handle(node)); return 0; } diff --git a/drivers/platform/x86/amd/pmf/sps.c b/drivers/platform/x86/amd/pmf/sps.c index ab69d517a36a..a70e67749be3 100644 --- a/drivers/platform/x86/amd/pmf/sps.c +++ b/drivers/platform/x86/amd/pmf/sps.c @@ -176,7 +176,8 @@ int amd_pmf_get_pprof_modes(struct amd_pmf_dev *pmf) int amd_pmf_power_slider_update_event(struct amd_pmf_dev *dev) { - u8 mode, flag = 0; + u8 flag = 0; + int mode; int src; mode = amd_pmf_get_pprof_modes(dev); diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c index 1f59ac55c5f7..a95004e3d80b 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c @@ -335,8 +335,8 @@ static struct pci_dev *_isst_if_get_pci_dev(int cpu, int bus_no, int dev, int fn node = dev_to_node(&_pci_dev->dev); if (node == NUMA_NO_NODE) { - pr_info("Fail to get numa node for CPU:%d bus:%d dev:%d fn:%d\n", - cpu, bus_no, dev, fn); + pr_info_once("Fail to get numa node for CPU:%d bus:%d dev:%d fn:%d\n", + cpu, bus_no, dev, fn); continue; } diff --git a/drivers/platform/x86/lenovo-ymc.c b/drivers/platform/x86/lenovo-ymc.c index 41676188b373..f360370d5002 100644 --- a/drivers/platform/x86/lenovo-ymc.c +++ b/drivers/platform/x86/lenovo-ymc.c @@ -24,6 +24,10 @@ static bool ec_trigger __read_mostly; module_param(ec_trigger, bool, 0444); MODULE_PARM_DESC(ec_trigger, "Enable EC triggering work-around to force emitting tablet mode events"); +static bool force; +module_param(force, bool, 0444); +MODULE_PARM_DESC(force, "Force loading on boards without a convertible DMI chassis-type"); + static const struct dmi_system_id ec_trigger_quirk_dmi_table[] = { { /* Lenovo Yoga 7 14ARB7 */ @@ -35,6 +39,20 @@ static const struct dmi_system_id ec_trigger_quirk_dmi_table[] = { { } }; +static const struct dmi_system_id allowed_chasis_types_dmi_table[] = { + { + .matches = { + DMI_EXACT_MATCH(DMI_CHASSIS_TYPE, "31" /* Convertible */), + }, + }, + { + .matches = { + DMI_EXACT_MATCH(DMI_CHASSIS_TYPE, "32" /* Detachable */), + }, + }, + { } +}; + struct lenovo_ymc_private { struct input_dev *input_dev; struct acpi_device *ec_acpi_dev; @@ -111,6 +129,13 @@ static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx) struct input_dev *input_dev; int err; + if (!dmi_check_system(allowed_chasis_types_dmi_table)) { + if (force) + dev_info(&wdev->dev, "Force loading Lenovo YMC support\n"); + else + return -ENODEV; + } + ec_trigger |= dmi_check_system(ec_trigger_quirk_dmi_table); priv = devm_kzalloc(&wdev->dev, sizeof(*priv), GFP_KERNEL); diff --git a/drivers/platform/x86/mlx-platform.c b/drivers/platform/x86/mlx-platform.c index 67367f010139..7d33977d9c60 100644 --- a/drivers/platform/x86/mlx-platform.c +++ b/drivers/platform/x86/mlx-platform.c @@ -62,10 +62,6 @@ #define MLXPLAT_CPLD_LPC_REG_PWM_CONTROL_OFFSET 0x37 #define MLXPLAT_CPLD_LPC_REG_AGGR_OFFSET 0x3a #define MLXPLAT_CPLD_LPC_REG_AGGR_MASK_OFFSET 0x3b -#define MLXPLAT_CPLD_LPC_REG_DBG1_OFFSET 0x3c -#define MLXPLAT_CPLD_LPC_REG_DBG2_OFFSET 0x3d -#define MLXPLAT_CPLD_LPC_REG_DBG3_OFFSET 0x3e -#define MLXPLAT_CPLD_LPC_REG_DBG4_OFFSET 0x3f #define MLXPLAT_CPLD_LPC_REG_AGGRLO_OFFSET 0x40 #define MLXPLAT_CPLD_LPC_REG_AGGRLO_MASK_OFFSET 0x41 #define MLXPLAT_CPLD_LPC_REG_AGGRCO_OFFSET 0x42 @@ -126,6 +122,10 @@ #define MLXPLAT_CPLD_LPC_REG_LC_SD_EVENT_OFFSET 0xaa #define MLXPLAT_CPLD_LPC_REG_LC_SD_MASK_OFFSET 0xab #define MLXPLAT_CPLD_LPC_REG_LC_PWR_ON 0xb2 +#define MLXPLAT_CPLD_LPC_REG_DBG1_OFFSET 0xb6 +#define MLXPLAT_CPLD_LPC_REG_DBG2_OFFSET 0xb7 +#define MLXPLAT_CPLD_LPC_REG_DBG3_OFFSET 0xb8 +#define MLXPLAT_CPLD_LPC_REG_DBG4_OFFSET 0xb9 #define MLXPLAT_CPLD_LPC_REG_GP4_RO_OFFSET 0xc2 #define MLXPLAT_CPLD_LPC_REG_SPI_CHNL_SELECT 0xc3 #define MLXPLAT_CPLD_LPC_REG_WD_CLEAR_OFFSET 0xc7 @@ -222,7 +222,7 @@ MLXPLAT_CPLD_AGGR_MASK_LC_SDWN) #define MLXPLAT_CPLD_LOW_AGGR_MASK_LOW 0xc1 #define MLXPLAT_CPLD_LOW_AGGR_MASK_ASIC2 BIT(2) -#define MLXPLAT_CPLD_LOW_AGGR_MASK_PWR_BUT BIT(4) +#define MLXPLAT_CPLD_LOW_AGGR_MASK_PWR_BUT GENMASK(5, 4) #define MLXPLAT_CPLD_LOW_AGGR_MASK_I2C BIT(6) #define MLXPLAT_CPLD_PSU_MASK GENMASK(1, 0) #define MLXPLAT_CPLD_PWR_MASK GENMASK(1, 0) @@ -237,7 +237,7 @@ #define MLXPLAT_CPLD_GWP_MASK GENMASK(0, 0) #define MLXPLAT_CPLD_EROT_MASK GENMASK(1, 0) #define MLXPLAT_CPLD_PWR_BUTTON_MASK BIT(0) -#define MLXPLAT_CPLD_LATCH_RST_MASK BIT(5) +#define MLXPLAT_CPLD_LATCH_RST_MASK BIT(6) #define MLXPLAT_CPLD_THERMAL1_PDB_MASK BIT(3) #define MLXPLAT_CPLD_THERMAL2_PDB_MASK BIT(4) #define MLXPLAT_CPLD_INTRUSION_MASK BIT(6) @@ -2356,7 +2356,7 @@ mlxplat_mlxcpld_l1_switch_pwr_events_handler(void *handle, enum mlxreg_hotplug_k u8 action) { dev_info(&mlxplat_dev->dev, "System shutdown due to short press of power button"); - kernel_halt(); + kernel_power_off(); return 0; } @@ -2475,7 +2475,7 @@ static struct mlxreg_core_item mlxplat_mlxcpld_l1_switch_events_items[] = { .reg = MLXPLAT_CPLD_LPC_REG_PWRB_OFFSET, .mask = MLXPLAT_CPLD_PWR_BUTTON_MASK, .count = ARRAY_SIZE(mlxplat_mlxcpld_l1_switch_pwr_events_items_data), - .inversed = 0, + .inversed = 1, .health = false, }, { @@ -2484,7 +2484,7 @@ static struct mlxreg_core_item mlxplat_mlxcpld_l1_switch_events_items[] = { .reg = MLXPLAT_CPLD_LPC_REG_BRD_OFFSET, .mask = MLXPLAT_CPLD_L1_CHA_HEALTH_MASK, .count = ARRAY_SIZE(mlxplat_mlxcpld_l1_switch_health_events_items_data), - .inversed = 0, + .inversed = 1, .health = false, .ind = 8, }, @@ -3677,7 +3677,7 @@ static struct mlxreg_core_data mlxplat_mlxcpld_default_ng_regs_io_data[] = { { .label = "latch_reset", .reg = MLXPLAT_CPLD_LPC_REG_GP1_OFFSET, - .mask = GENMASK(7, 0) & ~BIT(5), + .mask = GENMASK(7, 0) & ~BIT(6), .mode = 0200, }, { @@ -6238,8 +6238,6 @@ static void mlxplat_i2c_mux_topolgy_exit(struct mlxplat_priv *priv) if (priv->pdev_mux[i]) platform_device_unregister(priv->pdev_mux[i]); } - - mlxplat_post_exit(); } static int mlxplat_i2c_main_complition_notify(void *handle, int id) @@ -6369,6 +6367,7 @@ static void __exit mlxplat_exit(void) pm_power_off = NULL; mlxplat_pre_exit(priv); mlxplat_i2c_main_exit(priv); + mlxplat_post_exit(); } module_exit(mlxplat_exit); diff --git a/drivers/platform/x86/msi-ec.c b/drivers/platform/x86/msi-ec.c index ff93986e3d35..f26a3121092f 100644 --- a/drivers/platform/x86/msi-ec.c +++ b/drivers/platform/x86/msi-ec.c @@ -27,15 +27,15 @@ #include <linux/seq_file.h> #include <linux/string.h> -static const char *const SM_ECO_NAME = "eco"; -static const char *const SM_COMFORT_NAME = "comfort"; -static const char *const SM_SPORT_NAME = "sport"; -static const char *const SM_TURBO_NAME = "turbo"; - -static const char *const FM_AUTO_NAME = "auto"; -static const char *const FM_SILENT_NAME = "silent"; -static const char *const FM_BASIC_NAME = "basic"; -static const char *const FM_ADVANCED_NAME = "advanced"; +#define SM_ECO_NAME "eco" +#define SM_COMFORT_NAME "comfort" +#define SM_SPORT_NAME "sport" +#define SM_TURBO_NAME "turbo" + +#define FM_AUTO_NAME "auto" +#define FM_SILENT_NAME "silent" +#define FM_BASIC_NAME "basic" +#define FM_ADVANCED_NAME "advanced" static const char * const ALLOWED_FW_0[] __initconst = { "14C1EMS1.012", diff --git a/drivers/platform/x86/serial-multi-instantiate.c b/drivers/platform/x86/serial-multi-instantiate.c index 2c2abf69f049..8158e3cf5d6d 100644 --- a/drivers/platform/x86/serial-multi-instantiate.c +++ b/drivers/platform/x86/serial-multi-instantiate.c @@ -329,6 +329,19 @@ static const struct smi_node cs35l41_hda = { .bus_type = SMI_AUTO_DETECT, }; +static const struct smi_node cs35l56_hda = { + .instances = { + { "cs35l56-hda", IRQ_RESOURCE_AUTO, 0 }, + { "cs35l56-hda", IRQ_RESOURCE_AUTO, 0 }, + { "cs35l56-hda", IRQ_RESOURCE_AUTO, 0 }, + { "cs35l56-hda", IRQ_RESOURCE_AUTO, 0 }, + /* a 5th entry is an alias address, not a real device */ + { "cs35l56-hda_dummy_dev" }, + {} + }, + .bus_type = SMI_AUTO_DETECT, +}; + /* * Note new device-ids must also be added to ignore_serial_bus_ids in * drivers/acpi/scan.c: acpi_device_enumeration_by_parent(). @@ -337,6 +350,7 @@ static const struct acpi_device_id smi_acpi_ids[] = { { "BSG1160", (unsigned long)&bsg1160_data }, { "BSG2150", (unsigned long)&bsg2150_data }, { "CSC3551", (unsigned long)&cs35l41_hda }, + { "CSC3556", (unsigned long)&cs35l56_hda }, { "INT3515", (unsigned long)&int3515_data }, /* Non-conforming _HID for Cirrus Logic already released */ { "CLSA0100", (unsigned long)&cs35l41_hda }, diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index 4e646e5e48f6..8fac57b28f8a 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -818,7 +818,7 @@ static int rapl_read_data_raw(struct rapl_domain *rd, return -EINVAL; ra.reg = rd->regs[rpi->id]; - if (!ra.reg) + if (!ra.reg.val) return -EINVAL; /* non-hardware data are collected by the polling thread */ @@ -830,7 +830,7 @@ static int rapl_read_data_raw(struct rapl_domain *rd, ra.mask = rpi->mask; if (rd->rp->priv->read_raw(get_rid(rd->rp), &ra)) { - pr_debug("failed to read reg 0x%llx for %s:%s\n", ra.reg, rd->rp->name, rd->name); + pr_debug("failed to read reg 0x%llx for %s:%s\n", ra.reg.val, rd->rp->name, rd->name); return -EIO; } @@ -920,7 +920,7 @@ static int rapl_check_unit_core(struct rapl_domain *rd) ra.mask = ~0; if (rd->rp->priv->read_raw(get_rid(rd->rp), &ra)) { pr_err("Failed to read power unit REG 0x%llx on %s:%s, exit.\n", - ra.reg, rd->rp->name, rd->name); + ra.reg.val, rd->rp->name, rd->name); return -ENODEV; } @@ -948,7 +948,7 @@ static int rapl_check_unit_atom(struct rapl_domain *rd) ra.mask = ~0; if (rd->rp->priv->read_raw(get_rid(rd->rp), &ra)) { pr_err("Failed to read power unit REG 0x%llx on %s:%s, exit.\n", - ra.reg, rd->rp->name, rd->name); + ra.reg.val, rd->rp->name, rd->name); return -ENODEV; } @@ -1135,7 +1135,7 @@ static int rapl_check_unit_tpmi(struct rapl_domain *rd) ra.mask = ~0; if (rd->rp->priv->read_raw(get_rid(rd->rp), &ra)) { pr_err("Failed to read power unit REG 0x%llx on %s:%s, exit.\n", - ra.reg, rd->rp->name, rd->name); + ra.reg.val, rd->rp->name, rd->name); return -ENODEV; } @@ -1411,8 +1411,8 @@ static int rapl_get_domain_unit(struct rapl_domain *rd) struct rapl_defaults *defaults = get_defaults(rd->rp); int ret; - if (!rd->regs[RAPL_DOMAIN_REG_UNIT]) { - if (!rd->rp->priv->reg_unit) { + if (!rd->regs[RAPL_DOMAIN_REG_UNIT].val) { + if (!rd->rp->priv->reg_unit.val) { pr_err("No valid Unit register found\n"); return -ENODEV; } diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c index 569e25eab1e1..dd471021f237 100644 --- a/drivers/powercap/intel_rapl_msr.c +++ b/drivers/powercap/intel_rapl_msr.c @@ -34,28 +34,32 @@ static struct rapl_if_priv *rapl_msr_priv; static struct rapl_if_priv rapl_msr_priv_intel = { .type = RAPL_IF_MSR, - .reg_unit = MSR_RAPL_POWER_UNIT, - .regs[RAPL_DOMAIN_PACKAGE] = { - MSR_PKG_POWER_LIMIT, MSR_PKG_ENERGY_STATUS, MSR_PKG_PERF_STATUS, 0, MSR_PKG_POWER_INFO }, - .regs[RAPL_DOMAIN_PP0] = { - MSR_PP0_POWER_LIMIT, MSR_PP0_ENERGY_STATUS, 0, MSR_PP0_POLICY, 0 }, - .regs[RAPL_DOMAIN_PP1] = { - MSR_PP1_POWER_LIMIT, MSR_PP1_ENERGY_STATUS, 0, MSR_PP1_POLICY, 0 }, - .regs[RAPL_DOMAIN_DRAM] = { - MSR_DRAM_POWER_LIMIT, MSR_DRAM_ENERGY_STATUS, MSR_DRAM_PERF_STATUS, 0, MSR_DRAM_POWER_INFO }, - .regs[RAPL_DOMAIN_PLATFORM] = { - MSR_PLATFORM_POWER_LIMIT, MSR_PLATFORM_ENERGY_STATUS, 0, 0, 0}, + .reg_unit.msr = MSR_RAPL_POWER_UNIT, + .regs[RAPL_DOMAIN_PACKAGE][RAPL_DOMAIN_REG_LIMIT].msr = MSR_PKG_POWER_LIMIT, + .regs[RAPL_DOMAIN_PACKAGE][RAPL_DOMAIN_REG_STATUS].msr = MSR_PKG_ENERGY_STATUS, + .regs[RAPL_DOMAIN_PACKAGE][RAPL_DOMAIN_REG_PERF].msr = MSR_PKG_PERF_STATUS, + .regs[RAPL_DOMAIN_PACKAGE][RAPL_DOMAIN_REG_INFO].msr = MSR_PKG_POWER_INFO, + .regs[RAPL_DOMAIN_PP0][RAPL_DOMAIN_REG_LIMIT].msr = MSR_PP0_POWER_LIMIT, + .regs[RAPL_DOMAIN_PP0][RAPL_DOMAIN_REG_STATUS].msr = MSR_PP0_ENERGY_STATUS, + .regs[RAPL_DOMAIN_PP0][RAPL_DOMAIN_REG_POLICY].msr = MSR_PP0_POLICY, + .regs[RAPL_DOMAIN_PP1][RAPL_DOMAIN_REG_LIMIT].msr = MSR_PP1_POWER_LIMIT, + .regs[RAPL_DOMAIN_PP1][RAPL_DOMAIN_REG_STATUS].msr = MSR_PP1_ENERGY_STATUS, + .regs[RAPL_DOMAIN_PP1][RAPL_DOMAIN_REG_POLICY].msr = MSR_PP1_POLICY, + .regs[RAPL_DOMAIN_DRAM][RAPL_DOMAIN_REG_LIMIT].msr = MSR_DRAM_POWER_LIMIT, + .regs[RAPL_DOMAIN_DRAM][RAPL_DOMAIN_REG_STATUS].msr = MSR_DRAM_ENERGY_STATUS, + .regs[RAPL_DOMAIN_DRAM][RAPL_DOMAIN_REG_PERF].msr = MSR_DRAM_PERF_STATUS, + .regs[RAPL_DOMAIN_DRAM][RAPL_DOMAIN_REG_INFO].msr = MSR_DRAM_POWER_INFO, + .regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_LIMIT].msr = MSR_PLATFORM_POWER_LIMIT, + .regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_STATUS].msr = MSR_PLATFORM_ENERGY_STATUS, .limits[RAPL_DOMAIN_PACKAGE] = BIT(POWER_LIMIT2), .limits[RAPL_DOMAIN_PLATFORM] = BIT(POWER_LIMIT2), }; static struct rapl_if_priv rapl_msr_priv_amd = { .type = RAPL_IF_MSR, - .reg_unit = MSR_AMD_RAPL_POWER_UNIT, - .regs[RAPL_DOMAIN_PACKAGE] = { - 0, MSR_AMD_PKG_ENERGY_STATUS, 0, 0, 0 }, - .regs[RAPL_DOMAIN_PP0] = { - 0, MSR_AMD_CORE_ENERGY_STATUS, 0, 0, 0 }, + .reg_unit.msr = MSR_AMD_RAPL_POWER_UNIT, + .regs[RAPL_DOMAIN_PACKAGE][RAPL_DOMAIN_REG_STATUS].msr = MSR_AMD_PKG_ENERGY_STATUS, + .regs[RAPL_DOMAIN_PP0][RAPL_DOMAIN_REG_STATUS].msr = MSR_AMD_CORE_ENERGY_STATUS, }; /* Handles CPU hotplug on multi-socket systems. @@ -99,10 +103,8 @@ static int rapl_cpu_down_prep(unsigned int cpu) static int rapl_msr_read_raw(int cpu, struct reg_action *ra) { - u32 msr = (u32)ra->reg; - - if (rdmsrl_safe_on_cpu(cpu, msr, &ra->value)) { - pr_debug("failed to read msr 0x%x on cpu %d\n", msr, cpu); + if (rdmsrl_safe_on_cpu(cpu, ra->reg.msr, &ra->value)) { + pr_debug("failed to read msr 0x%x on cpu %d\n", ra->reg.msr, cpu); return -EIO; } ra->value &= ra->mask; @@ -112,17 +114,16 @@ static int rapl_msr_read_raw(int cpu, struct reg_action *ra) static void rapl_msr_update_func(void *info) { struct reg_action *ra = info; - u32 msr = (u32)ra->reg; u64 val; - ra->err = rdmsrl_safe(msr, &val); + ra->err = rdmsrl_safe(ra->reg.msr, &val); if (ra->err) return; val &= ~ra->mask; val |= ra->value; - ra->err = wrmsrl_safe(msr, val); + ra->err = wrmsrl_safe(ra->reg.msr, val); } static int rapl_msr_write_raw(int cpu, struct reg_action *ra) @@ -171,7 +172,7 @@ static int rapl_msr_probe(struct platform_device *pdev) if (id) { rapl_msr_priv->limits[RAPL_DOMAIN_PACKAGE] |= BIT(POWER_LIMIT4); - rapl_msr_priv->regs[RAPL_DOMAIN_PACKAGE][RAPL_DOMAIN_REG_PL4] = + rapl_msr_priv->regs[RAPL_DOMAIN_PACKAGE][RAPL_DOMAIN_REG_PL4].msr = MSR_VR_CURRENT_CONFIG; pr_info("PL4 support detected.\n"); } diff --git a/drivers/powercap/intel_rapl_tpmi.c b/drivers/powercap/intel_rapl_tpmi.c index 4f4f13ded225..891c90fefd8b 100644 --- a/drivers/powercap/intel_rapl_tpmi.c +++ b/drivers/powercap/intel_rapl_tpmi.c @@ -59,10 +59,10 @@ static struct powercap_control_type *tpmi_control_type; static int tpmi_rapl_read_raw(int id, struct reg_action *ra) { - if (!ra->reg) + if (!ra->reg.mmio) return -EINVAL; - ra->value = readq((void __iomem *)ra->reg); + ra->value = readq(ra->reg.mmio); ra->value &= ra->mask; return 0; @@ -72,15 +72,15 @@ static int tpmi_rapl_write_raw(int id, struct reg_action *ra) { u64 val; - if (!ra->reg) + if (!ra->reg.mmio) return -EINVAL; - val = readq((void __iomem *)ra->reg); + val = readq(ra->reg.mmio); val &= ~ra->mask; val |= ra->value; - writeq(val, (void __iomem *)ra->reg); + writeq(val, ra->reg.mmio); return 0; } @@ -138,8 +138,7 @@ static int parse_one_domain(struct tpmi_rapl_package *trp, u32 offset) enum tpmi_rapl_register reg_index; enum rapl_domain_reg_id reg_id; int tpmi_domain_size, tpmi_domain_flags; - u64 *tpmi_rapl_regs = trp->base + offset; - u64 tpmi_domain_header = readq((void __iomem *)tpmi_rapl_regs); + u64 tpmi_domain_header = readq(trp->base + offset); /* Domain Parent bits are ignored for now */ tpmi_domain_version = tpmi_domain_header & 0xff; @@ -180,7 +179,7 @@ static int parse_one_domain(struct tpmi_rapl_package *trp, u32 offset) return -EINVAL; } - if (trp->priv.regs[domain_type][RAPL_DOMAIN_REG_UNIT]) { + if (trp->priv.regs[domain_type][RAPL_DOMAIN_REG_UNIT].mmio) { pr_warn(FW_BUG "Duplicate Domain type %d\n", tpmi_domain_type); return -EINVAL; } @@ -218,7 +217,7 @@ static int parse_one_domain(struct tpmi_rapl_package *trp, u32 offset) default: continue; } - trp->priv.regs[domain_type][reg_id] = (u64)&tpmi_rapl_regs[reg_index]; + trp->priv.regs[domain_type][reg_id].mmio = trp->base + offset + reg_index * 8; } return 0; diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 1d195429753d..613eab729704 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -716,7 +716,6 @@ struct qeth_card_info { u16 chid; u8 ids_valid:1; /* cssid,iid,chid */ u8 dev_addr_is_registered:1; - u8 open_when_online:1; u8 promisc_mode:1; u8 use_v1_blkt:1; u8 is_vm_nic:1; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 1d5b207c2b9e..cd783290bde5 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -5373,8 +5373,6 @@ int qeth_set_offline(struct qeth_card *card, const struct qeth_discipline *disc, qeth_clear_ipacmd_list(card); rtnl_lock(); - card->info.open_when_online = card->dev->flags & IFF_UP; - dev_close(card->dev); netif_device_detach(card->dev); netif_carrier_off(card->dev); rtnl_unlock(); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 9f13ed170a43..75910c0bcc2b 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -2388,9 +2388,12 @@ static int qeth_l2_set_online(struct qeth_card *card, bool carrier_ok) qeth_enable_hw_features(dev); qeth_l2_enable_brport_features(card); - if (card->info.open_when_online) { - card->info.open_when_online = 0; - dev_open(dev, NULL); + if (netif_running(dev)) { + local_bh_disable(); + napi_schedule(&card->napi); + /* kick-start the NAPI softirq: */ + local_bh_enable(); + qeth_l2_set_rx_mode(dev); } rtnl_unlock(); } diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index af4e60d2917e..b92a32b4b114 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2018,9 +2018,11 @@ static int qeth_l3_set_online(struct qeth_card *card, bool carrier_ok) netif_device_attach(dev); qeth_enable_hw_features(dev); - if (card->info.open_when_online) { - card->info.open_when_online = 0; - dev_open(dev, NULL); + if (netif_running(dev)) { + local_bh_disable(); + napi_schedule(&card->napi); + /* kick-start the NAPI softirq: */ + local_bh_enable(); } rtnl_unlock(); } diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c index f21307537829..4f0d0e55f0d4 100644 --- a/drivers/s390/scsi/zfcp_fc.c +++ b/drivers/s390/scsi/zfcp_fc.c @@ -534,8 +534,7 @@ static void zfcp_fc_adisc_handler(void *data) /* re-init to undo drop from zfcp_fc_adisc() */ port->d_id = ntoh24(adisc_resp->adisc_port_id); - /* port is good, unblock rport without going through erp */ - zfcp_scsi_schedule_rport_register(port); + /* port is still good, nothing to do */ out: atomic_andnot(ZFCP_STATUS_PORT_LINK_TEST, &port->status); put_device(&port->dev); @@ -595,9 +594,6 @@ void zfcp_fc_link_test_work(struct work_struct *work) int retval; set_worker_desc("zadisc%16llx", port->wwpn); /* < WORKER_DESC_LEN=24 */ - get_device(&port->dev); - port->rport_task = RPORT_DEL; - zfcp_scsi_rport_work(&port->rport_work); /* only issue one test command at one time per port */ if (atomic_read(&port->status) & ZFCP_STATUS_PORT_LINK_TEST) diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c index e1e4f9d10887..857be0f3ae5b 100644 --- a/drivers/scsi/53c700.c +++ b/drivers/scsi/53c700.c @@ -1598,7 +1598,7 @@ NCR_700_intr(int irq, void *dev_id) printk("scsi%d (%d:%d) PHASE MISMATCH IN SEND MESSAGE %d remain, return %p[%04x], phase %s\n", host->host_no, pun, lun, count, (void *)temp, temp - hostdata->pScript, sbcl_to_string(NCR_700_readb(host, SBCL_REG))); #endif resume_offset = hostdata->pScript + Ent_SendMessagePhaseMismatch; - } else if(dsp >= to32bit(&slot->pSG[0].ins) && + } else if (slot && dsp >= to32bit(&slot->pSG[0].ins) && dsp <= to32bit(&slot->pSG[NCR_700_SG_SEGMENTS].ins)) { int data_transfer = NCR_700_readl(host, DBC_REG) & 0xffffff; int SGcount = (dsp - to32bit(&slot->pSG[0].ins))/sizeof(struct NCR_700_SG_List); diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h index d82de34f6fd7..e51e92f932fa 100644 --- a/drivers/scsi/fnic/fnic.h +++ b/drivers/scsi/fnic/fnic.h @@ -27,7 +27,7 @@ #define DRV_NAME "fnic" #define DRV_DESCRIPTION "Cisco FCoE HBA Driver" -#define DRV_VERSION "1.6.0.54" +#define DRV_VERSION "1.6.0.55" #define PFX DRV_NAME ": " #define DFX DRV_NAME "%d: " diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c index 26dbd347156e..be89ce96df46 100644 --- a/drivers/scsi/fnic/fnic_scsi.c +++ b/drivers/scsi/fnic/fnic_scsi.c @@ -2139,7 +2139,7 @@ static int fnic_clean_pending_aborts(struct fnic *fnic, bool new_sc) { - int ret = SUCCESS; + int ret = 0; struct fnic_pending_aborts_iter_data iter_data = { .fnic = fnic, .lun_dev = lr_sc->device, @@ -2159,9 +2159,11 @@ static int fnic_clean_pending_aborts(struct fnic *fnic, /* walk again to check, if IOs are still pending in fw */ if (fnic_is_abts_pending(fnic, lr_sc)) - ret = FAILED; + ret = 1; clean_pending_aborts_end: + FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, + "%s: exit status: %d\n", __func__, ret); return ret; } diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index a62e091894f6..d26941b131fd 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -109,8 +109,6 @@ lpfc_sli4_set_rsp_sgl_last(struct lpfc_hba *phba, } } -#define LPFC_INVALID_REFTAG ((u32)-1) - /** * lpfc_rampdown_queue_depth - Post RAMP_DOWN_QUEUE event to worker thread * @phba: The Hba for which this call is being executed. @@ -978,8 +976,6 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc, sgpe = scsi_prot_sglist(sc); lba = scsi_prot_ref_tag(sc); - if (lba == LPFC_INVALID_REFTAG) - return 0; /* First check if we need to match the LBA */ if (phba->lpfc_injerr_lba != LPFC_INJERR_LBA_OFF) { @@ -1560,8 +1556,6 @@ lpfc_bg_setup_bpl(struct lpfc_hba *phba, struct scsi_cmnd *sc, /* extract some info from the scsi command for pde*/ reftag = scsi_prot_ref_tag(sc); - if (reftag == LPFC_INVALID_REFTAG) - goto out; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS rc = lpfc_bg_err_inject(phba, sc, &reftag, NULL, 1); @@ -1723,8 +1717,6 @@ lpfc_bg_setup_bpl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, /* extract some info from the scsi command */ blksize = scsi_prot_interval(sc); reftag = scsi_prot_ref_tag(sc); - if (reftag == LPFC_INVALID_REFTAG) - goto out; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS rc = lpfc_bg_err_inject(phba, sc, &reftag, NULL, 1); @@ -1953,8 +1945,6 @@ lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc, /* extract some info from the scsi command for pde*/ reftag = scsi_prot_ref_tag(sc); - if (reftag == LPFC_INVALID_REFTAG) - goto out; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS rc = lpfc_bg_err_inject(phba, sc, &reftag, NULL, 1); @@ -2154,8 +2144,6 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, /* extract some info from the scsi command */ blksize = scsi_prot_interval(sc); reftag = scsi_prot_ref_tag(sc); - if (reftag == LPFC_INVALID_REFTAG) - goto out; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS rc = lpfc_bg_err_inject(phba, sc, &reftag, NULL, 1); @@ -2746,8 +2734,6 @@ lpfc_calc_bg_err(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd) src = (struct scsi_dif_tuple *)sg_virt(sgpe); start_ref_tag = scsi_prot_ref_tag(cmd); - if (start_ref_tag == LPFC_INVALID_REFTAG) - goto out; start_app_tag = src->app_tag; len = sgpe->length; while (src && protsegcnt) { @@ -3493,11 +3479,11 @@ err: scsi_cmnd->sc_data_direction); lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, - "9084 Cannot setup S/G List for HBA" - "IO segs %d/%d SGL %d SCSI %d: %d %d\n", + "9084 Cannot setup S/G List for HBA " + "IO segs %d/%d SGL %d SCSI %d: %d %d %d\n", lpfc_cmd->seg_cnt, lpfc_cmd->prot_seg_cnt, phba->cfg_total_seg_cnt, phba->cfg_sg_seg_cnt, - prot_group_type, num_sge); + prot_group_type, num_sge, ret); lpfc_cmd->seg_cnt = 0; lpfc_cmd->prot_seg_cnt = 0; diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c index 2e886c1d867d..4995e1ef4e0e 100644 --- a/drivers/scsi/pm8001/pm8001_init.c +++ b/drivers/scsi/pm8001/pm8001_init.c @@ -1181,7 +1181,8 @@ static int pm8001_pci_probe(struct pci_dev *pdev, pm80xx_set_thermal_config(pm8001_ha); } - if (pm8001_init_sas_add(pm8001_ha)) + rc = pm8001_init_sas_add(pm8001_ha); + if (rc) goto err_out_shost; /* phy setting support for motherboard controller */ rc = pm8001_configure_phy_settings(pm8001_ha); diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index 2a31ddc99dde..7825765c936c 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -31,6 +31,7 @@ static void qedf_remove(struct pci_dev *pdev); static void qedf_shutdown(struct pci_dev *pdev); static void qedf_schedule_recovery_handler(void *dev); static void qedf_recovery_handler(struct work_struct *work); +static int qedf_suspend(struct pci_dev *pdev, pm_message_t state); /* * Driver module parameters. @@ -3271,6 +3272,7 @@ static struct pci_driver qedf_pci_driver = { .probe = qedf_probe, .remove = qedf_remove, .shutdown = qedf_shutdown, + .suspend = qedf_suspend, }; static int __qedf_probe(struct pci_dev *pdev, int mode) @@ -4000,6 +4002,22 @@ static void qedf_shutdown(struct pci_dev *pdev) __qedf_remove(pdev, QEDF_MODE_NORMAL); } +static int qedf_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct qedf_ctx *qedf; + + if (!pdev) { + QEDF_ERR(NULL, "pdev is NULL.\n"); + return -ENODEV; + } + + qedf = pci_get_drvdata(pdev); + + QEDF_ERR(&qedf->dbg_ctx, "%s: Device does not support suspend operation\n", __func__); + + return -EPERM; +} + /* * Recovery handler code */ diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 450522b204d6..cd0180b1f5b9 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -69,6 +69,7 @@ static struct nvm_iscsi_block *qedi_get_nvram_block(struct qedi_ctx *qedi); static void qedi_recovery_handler(struct work_struct *work); static void qedi_schedule_hw_err_handler(void *dev, enum qed_hw_err_type err_type); +static int qedi_suspend(struct pci_dev *pdev, pm_message_t state); static int qedi_iscsi_event_cb(void *context, u8 fw_event_code, void *fw_handle) { @@ -1976,8 +1977,9 @@ static int qedi_cpu_offline(unsigned int cpu) struct qedi_percpu_s *p = this_cpu_ptr(&qedi_percpu); struct qedi_work *work, *tmp; struct task_struct *thread; + unsigned long flags; - spin_lock_bh(&p->p_work_lock); + spin_lock_irqsave(&p->p_work_lock, flags); thread = p->iothread; p->iothread = NULL; @@ -1988,7 +1990,7 @@ static int qedi_cpu_offline(unsigned int cpu) kfree(work); } - spin_unlock_bh(&p->p_work_lock); + spin_unlock_irqrestore(&p->p_work_lock, flags); if (thread) kthread_stop(thread); return 0; @@ -2510,6 +2512,22 @@ static void qedi_shutdown(struct pci_dev *pdev) __qedi_remove(pdev, QEDI_MODE_SHUTDOWN); } +static int qedi_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct qedi_ctx *qedi; + + if (!pdev) { + QEDI_ERR(NULL, "pdev is NULL.\n"); + return -ENODEV; + } + + qedi = pci_get_drvdata(pdev); + + QEDI_ERR(&qedi->dbg_ctx, "%s: Device does not support suspend operation\n", __func__); + + return -EPERM; +} + static int __qedi_probe(struct pci_dev *pdev, int mode) { struct qedi_ctx *qedi; @@ -2868,6 +2886,7 @@ static struct pci_driver qedi_pci_driver = { .remove = qedi_remove, .shutdown = qedi_shutdown, .err_handler = &qedi_err_handler, + .suspend = qedi_suspend, }; static int __init qedi_init(void) diff --git a/drivers/scsi/raid_class.c b/drivers/scsi/raid_class.c index 898a0bdf8df6..711252e52d8e 100644 --- a/drivers/scsi/raid_class.c +++ b/drivers/scsi/raid_class.c @@ -248,6 +248,7 @@ int raid_component_add(struct raid_template *r,struct device *raid_dev, return 0; err_out: + put_device(&rc->dev); list_del(&rc->node); rd->component_count--; put_device(component_dev); diff --git a/drivers/scsi/scsi_proc.c b/drivers/scsi/scsi_proc.c index 4a6eb1741be0..41f23cd0bfb4 100644 --- a/drivers/scsi/scsi_proc.c +++ b/drivers/scsi/scsi_proc.c @@ -406,7 +406,7 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf, size_t length, loff_t *ppos) { int host, channel, id, lun; - char *buffer, *p; + char *buffer, *end, *p; int err; if (!buf || length > PAGE_SIZE) @@ -421,10 +421,14 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf, goto out; err = -EINVAL; - if (length < PAGE_SIZE) - buffer[length] = '\0'; - else if (buffer[PAGE_SIZE-1]) - goto out; + if (length < PAGE_SIZE) { + end = buffer + length; + *end = '\0'; + } else { + end = buffer + PAGE_SIZE - 1; + if (*end) + goto out; + } /* * Usage: echo "scsi add-single-device 0 1 2 3" >/proc/scsi/scsi @@ -433,10 +437,10 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf, if (!strncmp("scsi add-single-device", buffer, 22)) { p = buffer + 23; - host = simple_strtoul(p, &p, 0); - channel = simple_strtoul(p + 1, &p, 0); - id = simple_strtoul(p + 1, &p, 0); - lun = simple_strtoul(p + 1, &p, 0); + host = (p < end) ? simple_strtoul(p, &p, 0) : 0; + channel = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; + id = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; + lun = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; err = scsi_add_single_device(host, channel, id, lun); @@ -447,10 +451,10 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf, } else if (!strncmp("scsi remove-single-device", buffer, 25)) { p = buffer + 26; - host = simple_strtoul(p, &p, 0); - channel = simple_strtoul(p + 1, &p, 0); - id = simple_strtoul(p + 1, &p, 0); - lun = simple_strtoul(p + 1, &p, 0); + host = (p < end) ? simple_strtoul(p, &p, 0) : 0; + channel = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; + id = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; + lun = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; err = scsi_remove_single_device(host, channel, id, lun); } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 68b12afa0721..3c668cfb146d 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3876,7 +3876,7 @@ static int sd_suspend_runtime(struct device *dev) static int sd_resume(struct device *dev) { struct scsi_disk *sdkp = dev_get_drvdata(dev); - int ret; + int ret = 0; if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ return 0; @@ -3884,8 +3884,11 @@ static int sd_resume(struct device *dev) if (!sdkp->device->manage_start_stop) return 0; - sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); - ret = sd_start_stop_device(sdkp, 1); + if (!sdkp->device->no_start_on_resume) { + sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); + ret = sd_start_stop_device(sdkp, 1); + } + if (!ret) opal_unlock_from_suspend(sdkp->opal_dev); return ret; diff --git a/drivers/scsi/snic/snic_disc.c b/drivers/scsi/snic/snic_disc.c index 3e2e5783924d..e429ad23c396 100644 --- a/drivers/scsi/snic/snic_disc.c +++ b/drivers/scsi/snic/snic_disc.c @@ -303,6 +303,7 @@ snic_tgt_create(struct snic *snic, struct snic_tgt_id *tgtid) "Snic Tgt: device_add, with err = %d\n", ret); + put_device(&tgt->dev); put_device(&snic->shost->shost_gendev); spin_lock_irqsave(snic->shost->host_lock, flags); list_del(&tgt->list); diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 7f12d931fe7c..047ffaf7d42a 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -366,6 +366,7 @@ static void storvsc_on_channel_callback(void *context); #define STORVSC_FC_MAX_LUNS_PER_TARGET 255 #define STORVSC_FC_MAX_TARGETS 128 #define STORVSC_FC_MAX_CHANNELS 8 +#define STORVSC_FC_MAX_XFER_SIZE ((u32)(512 * 1024)) #define STORVSC_IDE_MAX_LUNS_PER_TARGET 64 #define STORVSC_IDE_MAX_TARGETS 1 @@ -1673,10 +1674,6 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd) */ static enum scsi_timeout_action storvsc_eh_timed_out(struct scsi_cmnd *scmnd) { -#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS) - if (scmnd->device->host->transportt == fc_transport_template) - return fc_eh_timed_out(scmnd); -#endif return SCSI_EH_RESET_TIMER; } @@ -2006,6 +2003,9 @@ static int storvsc_probe(struct hv_device *device, * protecting it from any weird value. */ max_xfer_bytes = round_down(stor_device->max_transfer_bytes, HV_HYP_PAGE_SIZE); + if (is_fc) + max_xfer_bytes = min(max_xfer_bytes, STORVSC_FC_MAX_XFER_SIZE); + /* max_hw_sectors_kb */ host->max_sectors = max_xfer_bytes >> 9; /* diff --git a/drivers/soc/imx/imx8mp-blk-ctrl.c b/drivers/soc/imx/imx8mp-blk-ctrl.c index 870aecc0202a..1c1fcab4979a 100644 --- a/drivers/soc/imx/imx8mp-blk-ctrl.c +++ b/drivers/soc/imx/imx8mp-blk-ctrl.c @@ -164,7 +164,7 @@ static int imx8mp_hsio_blk_ctrl_probe(struct imx8mp_blk_ctrl *bc) clk_hsio_pll->hw.init = &init; hw = &clk_hsio_pll->hw; - ret = devm_clk_hw_register(bc->dev, hw); + ret = devm_clk_hw_register(bc->bus_power_dev, hw); if (ret) return ret; diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_rapl.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_rapl.c index 013f1633f082..2f00fc3bf274 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_rapl.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_rapl.c @@ -57,10 +57,10 @@ static int rapl_mmio_cpu_down_prep(unsigned int cpu) static int rapl_mmio_read_raw(int cpu, struct reg_action *ra) { - if (!ra->reg) + if (!ra->reg.mmio) return -EINVAL; - ra->value = readq((void __iomem *)ra->reg); + ra->value = readq(ra->reg.mmio); ra->value &= ra->mask; return 0; } @@ -69,13 +69,13 @@ static int rapl_mmio_write_raw(int cpu, struct reg_action *ra) { u64 val; - if (!ra->reg) + if (!ra->reg.mmio) return -EINVAL; - val = readq((void __iomem *)ra->reg); + val = readq(ra->reg.mmio); val &= ~ra->mask; val |= ra->value; - writeq(val, (void __iomem *)ra->reg); + writeq(val, ra->reg.mmio); return 0; } @@ -92,13 +92,13 @@ int proc_thermal_rapl_add(struct pci_dev *pdev, struct proc_thermal_device *proc for (domain = RAPL_DOMAIN_PACKAGE; domain < RAPL_DOMAIN_MAX; domain++) { for (reg = RAPL_DOMAIN_REG_LIMIT; reg < RAPL_DOMAIN_REG_MAX; reg++) if (rapl_regs->regs[domain][reg]) - rapl_mmio_priv.regs[domain][reg] = - (u64)proc_priv->mmio_base + + rapl_mmio_priv.regs[domain][reg].mmio = + proc_priv->mmio_base + rapl_regs->regs[domain][reg]; rapl_mmio_priv.limits[domain] = rapl_regs->limits[domain]; } rapl_mmio_priv.type = RAPL_IF_MMIO; - rapl_mmio_priv.reg_unit = (u64)proc_priv->mmio_base + rapl_regs->reg_unit; + rapl_mmio_priv.reg_unit.mmio = proc_priv->mmio_base + rapl_regs->reg_unit; rapl_mmio_priv.read_raw = rapl_mmio_read_raw; rapl_mmio_priv.write_raw = rapl_mmio_write_raw; diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index 62b26b7998fd..3fb4553a6442 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -1964,6 +1964,8 @@ unlock: pm_runtime_mark_last_busy(&tb->dev); pm_runtime_put_autosuspend(&tb->dev); + + kfree(ev); } static void tb_queue_dp_bandwidth_request(struct tb *tb, u64 route, u8 port) diff --git a/drivers/thunderbolt/tmu.c b/drivers/thunderbolt/tmu.c index 1269f417515b..0dfd1e083994 100644 --- a/drivers/thunderbolt/tmu.c +++ b/drivers/thunderbolt/tmu.c @@ -579,7 +579,9 @@ int tb_switch_tmu_disable(struct tb_switch *sw) * uni-directional mode and we don't want to change it's TMU * mode. */ - tb_switch_tmu_rate_write(sw, tmu_rates[TB_SWITCH_TMU_MODE_OFF]); + ret = tb_switch_tmu_rate_write(sw, tmu_rates[TB_SWITCH_TMU_MODE_OFF]); + if (ret) + return ret; tb_port_tmu_time_sync_disable(up); ret = tb_port_tmu_time_sync_disable(down); diff --git a/drivers/ufs/host/ufs-renesas.c b/drivers/ufs/host/ufs-renesas.c index f8a5e79ed3b4..ab0652d8705a 100644 --- a/drivers/ufs/host/ufs-renesas.c +++ b/drivers/ufs/host/ufs-renesas.c @@ -359,7 +359,7 @@ static int ufs_renesas_init(struct ufs_hba *hba) { struct ufs_renesas_priv *priv; - priv = devm_kmalloc(hba->dev, sizeof(*priv), GFP_KERNEL); + priv = devm_kzalloc(hba->dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; ufshcd_set_variant(hba, priv); diff --git a/drivers/usb/common/usb-conn-gpio.c b/drivers/usb/common/usb-conn-gpio.c index 766005d20bae..501e8bc9738e 100644 --- a/drivers/usb/common/usb-conn-gpio.c +++ b/drivers/usb/common/usb-conn-gpio.c @@ -42,6 +42,7 @@ struct usb_conn_info { struct power_supply_desc desc; struct power_supply *charger; + bool initial_detection; }; /* @@ -86,11 +87,13 @@ static void usb_conn_detect_cable(struct work_struct *work) dev_dbg(info->dev, "role %s -> %s, gpios: id %d, vbus %d\n", usb_role_string(info->last_role), usb_role_string(role), id, vbus); - if (info->last_role == role) { + if (!info->initial_detection && info->last_role == role) { dev_warn(info->dev, "repeated role: %s\n", usb_role_string(role)); return; } + info->initial_detection = false; + if (info->last_role == USB_ROLE_HOST && info->vbus) regulator_disable(info->vbus); @@ -258,6 +261,7 @@ static int usb_conn_probe(struct platform_device *pdev) device_set_wakeup_capable(&pdev->dev, true); /* Perform initial detection */ + info->initial_detection = true; usb_conn_queue_dwork(info, 0); return 0; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 5fd067151fbf..858fe4c299b7 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -4455,9 +4455,14 @@ static irqreturn_t dwc3_check_event_buf(struct dwc3_event_buffer *evt) u32 count; if (pm_runtime_suspended(dwc->dev)) { + dwc->pending_events = true; + /* + * Trigger runtime resume. The get() function will be balanced + * after processing the pending events in dwc3_process_pending + * events(). + */ pm_runtime_get(dwc->dev); disable_irq_nosync(dwc->irq_gadget); - dwc->pending_events = true; return IRQ_HANDLED; } @@ -4718,6 +4723,8 @@ void dwc3_gadget_process_pending_events(struct dwc3 *dwc) { if (dwc->pending_events) { dwc3_interrupt(dwc->irq_gadget, dwc->ev_buf); + dwc3_thread_interrupt(dwc->irq_gadget, dwc->ev_buf); + pm_runtime_put(dwc->dev); dwc->pending_events = false; enable_irq(dwc->irq_gadget); } diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index cd58f2a4e7f3..7d49d8a0b00c 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -822,6 +822,9 @@ EXPORT_SYMBOL_GPL(usb_gadget_disconnect); * usb_gadget_activate() is called. For example, user mode components may * need to be activated before the system can talk to hosts. * + * This routine may sleep; it must not be called in interrupt context + * (such as from within a gadget driver's disconnect() callback). + * * Returns zero on success, else negative errno. */ int usb_gadget_deactivate(struct usb_gadget *gadget) @@ -860,6 +863,8 @@ EXPORT_SYMBOL_GPL(usb_gadget_deactivate); * This routine activates gadget which was previously deactivated with * usb_gadget_deactivate() call. It calls usb_gadget_connect() if needed. * + * This routine may sleep; it must not be called in interrupt context. + * * Returns zero on success, else negative errno. */ int usb_gadget_activate(struct usb_gadget *gadget) @@ -1638,7 +1643,11 @@ static void gadget_unbind_driver(struct device *dev) usb_gadget_disable_async_callbacks(udc); if (gadget->irq) synchronize_irq(gadget->irq); + mutex_unlock(&udc->connect_lock); + udc->driver->unbind(gadget); + + mutex_lock(&udc->connect_lock); usb_gadget_udc_stop_locked(udc); mutex_unlock(&udc->connect_lock); diff --git a/drivers/usb/storage/alauda.c b/drivers/usb/storage/alauda.c index 5e912dd29b4c..115f05a6201a 100644 --- a/drivers/usb/storage/alauda.c +++ b/drivers/usb/storage/alauda.c @@ -318,7 +318,8 @@ static int alauda_get_media_status(struct us_data *us, unsigned char *data) rc = usb_stor_ctrl_transfer(us, us->recv_ctrl_pipe, command, 0xc0, 0, 1, data, 2); - usb_stor_dbg(us, "Media status %02X %02X\n", data[0], data[1]); + if (rc == USB_STOR_XFER_GOOD) + usb_stor_dbg(us, "Media status %02X %02X\n", data[0], data[1]); return rc; } @@ -454,9 +455,14 @@ static int alauda_init_media(struct us_data *us) static int alauda_check_media(struct us_data *us) { struct alauda_info *info = (struct alauda_info *) us->extra; - unsigned char status[2]; + unsigned char *status = us->iobuf; + int rc; - alauda_get_media_status(us, status); + rc = alauda_get_media_status(us, status); + if (rc != USB_STOR_XFER_GOOD) { + status[0] = 0xF0; /* Pretend there's no media */ + status[1] = 0; + } /* Check for no media or door open */ if ((status[0] & 0x80) || ((status[0] & 0x1F) == 0x10) diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 66de880b28d0..cdf8261e22db 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -60,6 +60,7 @@ struct dp_altmode { enum dp_state state; bool hpd; + bool pending_hpd; struct mutex lock; /* device lock */ struct work_struct work; @@ -144,8 +145,13 @@ static int dp_altmode_status_update(struct dp_altmode *dp) dp->state = DP_STATE_EXIT; } else if (!(con & DP_CONF_CURRENTLY(dp->data.conf))) { ret = dp_altmode_configure(dp, con); - if (!ret) + if (!ret) { dp->state = DP_STATE_CONFIGURE; + if (dp->hpd != hpd) { + dp->hpd = hpd; + dp->pending_hpd = true; + } + } } else { if (dp->hpd != hpd) { drm_connector_oob_hotplug_event(dp->connector_fwnode); @@ -161,6 +167,16 @@ static int dp_altmode_configured(struct dp_altmode *dp) { sysfs_notify(&dp->alt->dev.kobj, "displayport", "configuration"); sysfs_notify(&dp->alt->dev.kobj, "displayport", "pin_assignment"); + /* + * If the DFP_D/UFP_D sends a change in HPD when first notifying the + * DisplayPort driver that it is connected, then we wait until + * configuration is complete to signal HPD. + */ + if (dp->pending_hpd) { + drm_connector_oob_hotplug_event(dp->connector_fwnode); + sysfs_notify(&dp->alt->dev.kobj, "displayport", "hpd"); + dp->pending_hpd = false; + } return dp_altmode_notify(dp); } diff --git a/drivers/usb/typec/mux/Kconfig b/drivers/usb/typec/mux/Kconfig index 784b9d8107e9..65da61150ba7 100644 --- a/drivers/usb/typec/mux/Kconfig +++ b/drivers/usb/typec/mux/Kconfig @@ -29,6 +29,7 @@ config TYPEC_MUX_INTEL_PMC tristate "Intel PMC mux control" depends on ACPI depends on INTEL_SCU_IPC + select USB_COMMON select USB_ROLE_SWITCH help Driver for USB muxes controlled by Intel PMC FW. Intel PMC FW can diff --git a/drivers/usb/typec/mux/nb7vpq904m.c b/drivers/usb/typec/mux/nb7vpq904m.c index 80e580d50129..4d1122d95013 100644 --- a/drivers/usb/typec/mux/nb7vpq904m.c +++ b/drivers/usb/typec/mux/nb7vpq904m.c @@ -463,16 +463,18 @@ static int nb7vpq904m_probe(struct i2c_client *client) ret = nb7vpq904m_register_bridge(nb7); if (ret) - return ret; + goto err_disable_gpio; sw_desc.drvdata = nb7; sw_desc.fwnode = dev->fwnode; sw_desc.set = nb7vpq904m_sw_set; nb7->sw = typec_switch_register(dev, &sw_desc); - if (IS_ERR(nb7->sw)) - return dev_err_probe(dev, PTR_ERR(nb7->sw), - "Error registering typec switch\n"); + if (IS_ERR(nb7->sw)) { + ret = dev_err_probe(dev, PTR_ERR(nb7->sw), + "Error registering typec switch\n"); + goto err_disable_gpio; + } retimer_desc.drvdata = nb7; retimer_desc.fwnode = dev->fwnode; @@ -480,12 +482,21 @@ static int nb7vpq904m_probe(struct i2c_client *client) nb7->retimer = typec_retimer_register(dev, &retimer_desc); if (IS_ERR(nb7->retimer)) { - typec_switch_unregister(nb7->sw); - return dev_err_probe(dev, PTR_ERR(nb7->retimer), - "Error registering typec retimer\n"); + ret = dev_err_probe(dev, PTR_ERR(nb7->retimer), + "Error registering typec retimer\n"); + goto err_switch_unregister; } return 0; + +err_switch_unregister: + typec_switch_unregister(nb7->sw); + +err_disable_gpio: + gpiod_set_value(nb7->enable_gpio, 0); + regulator_disable(nb7->vcc_supply); + + return ret; } static void nb7vpq904m_remove(struct i2c_client *client) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 829d75ebab42..cc1d83926497 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -5349,6 +5349,10 @@ static void _tcpm_pd_vbus_off(struct tcpm_port *port) /* Do nothing, vbus drop expected */ break; + case SNK_HARD_RESET_WAIT_VBUS: + /* Do nothing, its OK to receive vbus off events */ + break; + default: if (port->pwr_role == TYPEC_SINK && port->attached) tcpm_set_state(port, SNK_UNATTACHED, tcpm_wait_for_discharge(port)); @@ -5395,6 +5399,9 @@ static void _tcpm_pd_vbus_vsafe0v(struct tcpm_port *port) case SNK_DEBOUNCED: /*Do nothing, still waiting for VSAFE5V for connect */ break; + case SNK_HARD_RESET_WAIT_VBUS: + /* Do nothing, its OK to receive vbus off events */ + break; default: if (port->pwr_role == TYPEC_SINK && port->auto_vbus_discharge_enabled) tcpm_set_state(port, SNK_UNATTACHED, 0); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 030ab44fce18..82324c327a50 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -441,13 +441,23 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache, u64 num_bytes) { struct btrfs_caching_control *caching_ctl; + int progress; caching_ctl = btrfs_get_caching_control(cache); if (!caching_ctl) return; + /* + * We've already failed to allocate from this block group, so even if + * there's enough space in the block group it isn't contiguous enough to + * allow for an allocation, so wait for at least the next wakeup tick, + * or for the thing to be done. + */ + progress = atomic_read(&caching_ctl->progress); + wait_event(caching_ctl->wait, btrfs_block_group_done(cache) || - (cache->free_space_ctl->free_space >= num_bytes)); + (progress != atomic_read(&caching_ctl->progress) && + (cache->free_space_ctl->free_space >= num_bytes))); btrfs_put_caching_control(caching_ctl); } @@ -802,8 +812,10 @@ next: if (total_found > CACHING_CTL_WAKE_UP) { total_found = 0; - if (wakeup) + if (wakeup) { + atomic_inc(&caching_ctl->progress); wake_up(&caching_ctl->wait); + } } } path->slots[0]++; @@ -910,6 +922,7 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait) init_waitqueue_head(&caching_ctl->wait); caching_ctl->block_group = cache; refcount_set(&caching_ctl->count, 2); + atomic_set(&caching_ctl->progress, 0); btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL); spin_lock(&cache->lock); diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index aba5dff66c19..74b61e663028 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -90,6 +90,8 @@ struct btrfs_caching_control { wait_queue_head_t wait; struct btrfs_work work; struct btrfs_block_group *block_group; + /* Track progress of caching during allocation. */ + atomic_t progress; refcount_t count; }; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 9b9914e5f03d..a9a2c5446c18 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1103,7 +1103,8 @@ static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) btrfs_drew_lock_init(&root->snapshot_lock); if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID && - !btrfs_is_data_reloc_root(root)) { + !btrfs_is_data_reloc_root(root) && + is_fstree(root->root_key.objectid)) { set_bit(BTRFS_ROOT_SHAREABLE, &root->state); btrfs_check_and_init_root_item(&root->root_item); } @@ -1300,6 +1301,16 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, root = btrfs_get_global_root(fs_info, objectid); if (root) return root; + + /* + * If we're called for non-subvolume trees, and above function didn't + * find one, do not try to read it from disk. + * + * This is namely for free-space-tree and quota tree, which can change + * at runtime and should only be grabbed from fs_info. + */ + if (!is_fstree(objectid) && objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) + return ERR_PTR(-ENOENT); again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 911908ea5f6f..f396a9afa403 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4310,8 +4310,11 @@ have_block_group: ret = 0; } - if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) + if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) { + if (!cache_block_group_error) + cache_block_group_error = -EIO; goto loop; + } if (!find_free_extent_check_size_class(ffe_ctl, block_group)) goto loop; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index a91d5ad27984..ca765d62324f 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2145,6 +2145,12 @@ retry: continue; } + if (!folio_test_dirty(folio)) { + /* Someone wrote it for us. */ + folio_unlock(folio); + continue; + } + if (wbc->sync_mode != WB_SYNC_NONE) { if (folio_test_writeback(folio)) submit_write_bio(bio_ctrl, 0); @@ -2164,11 +2170,12 @@ retry: } /* - * the filesystem may choose to bump up nr_to_write. + * The filesystem may choose to bump up nr_to_write. * We have to make sure to honor the new nr_to_write - * at any time + * at any time. */ - nr_to_write_done = wbc->nr_to_write <= 0; + nr_to_write_done = (wbc->sync_mode == WB_SYNC_NONE && + wbc->nr_to_write <= 0); } folio_batch_release(&fbatch); cond_resched(); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 49cef61f6a39..9055e19b01ef 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1654,8 +1654,6 @@ out_unlock: clear_bits, page_ops); start += cur_alloc_size; - if (start >= end) - return ret; } /* @@ -1664,9 +1662,11 @@ out_unlock: * space_info's bytes_may_use counter, reserved in * btrfs_check_data_free_space(). */ - extent_clear_unlock_delalloc(inode, start, end, locked_page, - clear_bits | EXTENT_CLEAR_DATA_RESV, - page_ops); + if (start < end) { + clear_bits |= EXTENT_CLEAR_DATA_RESV; + extent_clear_unlock_delalloc(inode, start, end, locked_page, + clear_bits, page_ops); + } return ret; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 25a3361caedc..46c3c1d57266 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1916,7 +1916,39 @@ again: err = PTR_ERR(root); break; } - ASSERT(root->reloc_root == reloc_root); + + if (unlikely(root->reloc_root != reloc_root)) { + if (root->reloc_root) { + btrfs_err(fs_info, +"reloc tree mismatch, root %lld has reloc root key (%lld %u %llu) gen %llu, expect reloc root key (%lld %u %llu) gen %llu", + root->root_key.objectid, + root->reloc_root->root_key.objectid, + root->reloc_root->root_key.type, + root->reloc_root->root_key.offset, + btrfs_root_generation( + &root->reloc_root->root_item), + reloc_root->root_key.objectid, + reloc_root->root_key.type, + reloc_root->root_key.offset, + btrfs_root_generation( + &reloc_root->root_item)); + } else { + btrfs_err(fs_info, +"reloc tree mismatch, root %lld has no reloc root, expect reloc root key (%lld %u %llu) gen %llu", + root->root_key.objectid, + reloc_root->root_key.objectid, + reloc_root->root_key.type, + reloc_root->root_key.offset, + btrfs_root_generation( + &reloc_root->root_item)); + } + list_add(&reloc_root->root_list, &reloc_roots); + btrfs_put_root(root); + btrfs_abort_transaction(trans, -EUCLEAN); + if (!err) + err = -EUCLEAN; + break; + } /* * set reference count to 1, so btrfs_recover_relocation @@ -1989,7 +2021,7 @@ again: root = btrfs_get_fs_root(fs_info, reloc_root->root_key.offset, false); if (btrfs_root_refs(&reloc_root->root_item) > 0) { - if (IS_ERR(root)) { + if (WARN_ON(IS_ERR(root))) { /* * For recovery we read the fs roots on mount, * and if we didn't find the root then we marked @@ -1998,17 +2030,14 @@ again: * memory. However there's no reason we can't * handle the error properly here just in case. */ - ASSERT(0); ret = PTR_ERR(root); goto out; } - if (root->reloc_root != reloc_root) { + if (WARN_ON(root->reloc_root != reloc_root)) { /* - * This is actually impossible without something - * going really wrong (like weird race condition - * or cosmic rays). + * This can happen if on-disk metadata has some + * corruption, e.g. bad reloc tree key offset. */ - ASSERT(0); ret = -EINVAL; goto out; } diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 038dfa8f1788..ab08a0b01311 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -446,6 +446,20 @@ static int check_root_key(struct extent_buffer *leaf, struct btrfs_key *key, btrfs_item_key_to_cpu(leaf, &item_key, slot); is_root_item = (item_key.type == BTRFS_ROOT_ITEM_KEY); + /* + * Bad rootid for reloc trees. + * + * Reloc trees are only for subvolume trees, other trees only need + * to be COWed to be relocated. + */ + if (unlikely(is_root_item && key->objectid == BTRFS_TREE_RELOC_OBJECTID && + !is_fstree(key->offset))) { + generic_err(leaf, slot, + "invalid reloc tree for root %lld, root id is not a subvolume tree", + key->offset); + return -EUCLEAN; + } + /* No such tree id */ if (unlikely(key->objectid == 0)) { if (is_root_item) diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 4a2b39d9a61a..bdcffb04513f 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -2019,9 +2019,10 @@ unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) } } +WRAP_DIR_ITER(ceph_readdir) // FIXME! const struct file_operations ceph_dir_fops = { .read = ceph_read_dir, - .iterate = ceph_readdir, + .iterate_shared = shared_ceph_readdir, .llseek = ceph_dir_llseek, .open = ceph_open, .release = ceph_release, @@ -2033,7 +2034,7 @@ const struct file_operations ceph_dir_fops = { }; const struct file_operations ceph_snapdir_fops = { - .iterate = ceph_readdir, + .iterate_shared = shared_ceph_readdir, .llseek = ceph_dir_llseek, .open = ceph_open, .release = ceph_release, diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 66048a86c480..5fb367b1d4b0 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4764,7 +4764,7 @@ static void delayed_work(struct work_struct *work) dout("mdsc delayed_work\n"); - if (mdsc->stopping) + if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED) return; mutex_lock(&mdsc->mutex); @@ -4943,7 +4943,7 @@ void send_flush_mdlog(struct ceph_mds_session *s) void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc) { dout("pre_umount\n"); - mdsc->stopping = 1; + mdsc->stopping = CEPH_MDSC_STOPPING_BEGIN; ceph_mdsc_iterate_sessions(mdsc, send_flush_mdlog, true); ceph_mdsc_iterate_sessions(mdsc, lock_unlock_session, false); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 724307ff89cd..86d2965e68a1 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -380,6 +380,11 @@ struct cap_wait { int want; }; +enum { + CEPH_MDSC_STOPPING_BEGIN = 1, + CEPH_MDSC_STOPPING_FLUSHED = 2, +}; + /* * mds client state */ diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 3fc48b43cab0..a5f52013314d 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1374,6 +1374,16 @@ static void ceph_kill_sb(struct super_block *s) ceph_mdsc_pre_umount(fsc->mdsc); flush_fs_workqueues(fsc); + /* + * Though the kill_anon_super() will finally trigger the + * sync_filesystem() anyway, we still need to do it here + * and then bump the stage of shutdown to stop the work + * queue as earlier as possible. + */ + sync_filesystem(s); + + fsc->mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED; + kill_anon_super(s); fsc->client->extra_mon_dispatch = NULL; diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 8450b1bd354b..1b960de2bf39 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -429,21 +429,14 @@ static int coda_readdir(struct file *coda_file, struct dir_context *ctx) cfi = coda_ftoc(coda_file); host_file = cfi->cfi_container; - if (host_file->f_op->iterate || host_file->f_op->iterate_shared) { + if (host_file->f_op->iterate_shared) { struct inode *host_inode = file_inode(host_file); ret = -ENOENT; if (!IS_DEADDIR(host_inode)) { - if (host_file->f_op->iterate_shared) { - inode_lock_shared(host_inode); - ret = host_file->f_op->iterate_shared(host_file, ctx); - file_accessed(host_file); - inode_unlock_shared(host_inode); - } else { - inode_lock(host_inode); - ret = host_file->f_op->iterate(host_file, ctx); - file_accessed(host_file); - inode_unlock(host_inode); - } + inode_lock_shared(host_inode); + ret = host_file->f_op->iterate_shared(host_file, ctx); + file_accessed(host_file); + inode_unlock_shared(host_inode); } return ret; } @@ -585,10 +578,11 @@ const struct inode_operations coda_dir_inode_operations = { .setattr = coda_setattr, }; +WRAP_DIR_ITER(coda_readdir) // FIXME! const struct file_operations coda_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = coda_readdir, + .iterate_shared = shared_coda_readdir, .open = coda_open, .release = coda_release, .fsync = coda_fsync, diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 9d6a3c6158bd..566f68ddfa36 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -889,8 +889,6 @@ static void erofs_kill_sb(struct super_block *sb) { struct erofs_sb_info *sbi; - WARN_ON(sb->s_magic != EROFS_SUPER_MAGIC); - /* pseudo mount for anon inodes */ if (sb->s_flags & SB_KERNMOUNT) { kill_anon_super(sb); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index b69d89a11dd0..de4f12152b62 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1144,10 +1144,11 @@ static void z_erofs_do_decompressed_bvec(struct z_erofs_decompress_backend *be, struct z_erofs_bvec *bvec) { struct z_erofs_bvec_item *item; + unsigned int pgnr; - if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK)) { - unsigned int pgnr; - + if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK) && + (bvec->end == PAGE_SIZE || + bvec->offset + bvec->end == be->pcl->length)) { pgnr = (bvec->offset + be->pcl->pageofs_out) >> PAGE_SHIFT; DBG_BUGON(pgnr >= be->nr_pages); if (!be->decompressed_pages[pgnr]) { diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c index 9f42f25fab92..e918decb3735 100644 --- a/fs/exfat/balloc.c +++ b/fs/exfat/balloc.c @@ -69,7 +69,7 @@ static int exfat_allocate_bitmap(struct super_block *sb, } sbi->map_sectors = ((need_map_size - 1) >> (sb->s_blocksize_bits)) + 1; - sbi->vol_amap = kmalloc_array(sbi->map_sectors, + sbi->vol_amap = kvmalloc_array(sbi->map_sectors, sizeof(struct buffer_head *), GFP_KERNEL); if (!sbi->vol_amap) return -ENOMEM; @@ -84,7 +84,7 @@ static int exfat_allocate_bitmap(struct super_block *sb, while (j < i) brelse(sbi->vol_amap[j++]); - kfree(sbi->vol_amap); + kvfree(sbi->vol_amap); sbi->vol_amap = NULL; return -EIO; } @@ -138,7 +138,7 @@ void exfat_free_bitmap(struct exfat_sb_info *sbi) for (i = 0; i < sbi->map_sectors; i++) __brelse(sbi->vol_amap[i]); - kfree(sbi->vol_amap); + kvfree(sbi->vol_amap); } int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync) diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index 957574180a5e..e1586bba6d86 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -34,6 +34,7 @@ static int exfat_get_uniname_from_ext_entry(struct super_block *sb, { int i, err; struct exfat_entry_set_cache es; + unsigned int uni_len = 0, len; err = exfat_get_dentry_set(&es, sb, p_dir, entry, ES_ALL_ENTRIES); if (err) @@ -52,7 +53,10 @@ static int exfat_get_uniname_from_ext_entry(struct super_block *sb, if (exfat_get_entry_type(ep) != TYPE_EXTEND) break; - exfat_extract_uni_name(ep, uniname); + len = exfat_extract_uni_name(ep, uniname); + uni_len += len; + if (len != EXFAT_FILE_NAME_LEN || uni_len >= MAX_NAME_LENGTH) + break; uniname += EXFAT_FILE_NAME_LEN; } @@ -214,7 +218,10 @@ static void exfat_free_namebuf(struct exfat_dentry_namebuf *nb) exfat_init_namebuf(nb); } -/* skip iterating emit_dots when dir is empty */ +/* + * Before calling dir_emit*(), sbi->s_lock should be released + * because page fault can occur in dir_emit*(). + */ #define ITER_POS_FILLED_DOTS (2) static int exfat_iterate(struct file *file, struct dir_context *ctx) { @@ -229,11 +236,10 @@ static int exfat_iterate(struct file *file, struct dir_context *ctx) int err = 0, fake_offset = 0; exfat_init_namebuf(nb); - mutex_lock(&EXFAT_SB(sb)->s_lock); cpos = ctx->pos; if (!dir_emit_dots(file, ctx)) - goto unlock; + goto out; if (ctx->pos == ITER_POS_FILLED_DOTS) { cpos = 0; @@ -245,16 +251,18 @@ static int exfat_iterate(struct file *file, struct dir_context *ctx) /* name buffer should be allocated before use */ err = exfat_alloc_namebuf(nb); if (err) - goto unlock; + goto out; get_new: + mutex_lock(&EXFAT_SB(sb)->s_lock); + if (ei->flags == ALLOC_NO_FAT_CHAIN && cpos >= i_size_read(inode)) goto end_of_dir; err = exfat_readdir(inode, &cpos, &de); if (err) { /* - * At least we tried to read a sector. Move cpos to next sector - * position (should be aligned). + * At least we tried to read a sector. + * Move cpos to next sector position (should be aligned). */ if (err == -EIO) { cpos += 1 << (sb->s_blocksize_bits); @@ -277,16 +285,10 @@ get_new: inum = iunique(sb, EXFAT_ROOT_INO); } - /* - * Before calling dir_emit(), sb_lock should be released. - * Because page fault can occur in dir_emit() when the size - * of buffer given from user is larger than one page size. - */ mutex_unlock(&EXFAT_SB(sb)->s_lock); if (!dir_emit(ctx, nb->lfn, strlen(nb->lfn), inum, (de.attr & ATTR_SUBDIR) ? DT_DIR : DT_REG)) - goto out_unlocked; - mutex_lock(&EXFAT_SB(sb)->s_lock); + goto out; ctx->pos = cpos; goto get_new; @@ -294,9 +296,8 @@ end_of_dir: if (!cpos && fake_offset) cpos = ITER_POS_FILLED_DOTS; ctx->pos = cpos; -unlock: mutex_unlock(&EXFAT_SB(sb)->s_lock); -out_unlocked: +out: /* * To improve performance, free namebuf after unlock sb_lock. * If namebuf is not allocated, this function do nothing @@ -305,10 +306,11 @@ out_unlocked: return err; } +WRAP_DIR_ITER(exfat_iterate) // FIXME! const struct file_operations exfat_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = exfat_iterate, + .iterate_shared = shared_exfat_iterate, .unlocked_ioctl = exfat_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = exfat_compat_ioctl, @@ -1079,7 +1081,8 @@ rewind: if (entry_type == TYPE_EXTEND) { unsigned short entry_uniname[16], unichar; - if (step != DIRENT_STEP_NAME) { + if (step != DIRENT_STEP_NAME || + name_len >= MAX_NAME_LENGTH) { step = DIRENT_STEP_FILE; continue; } diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 40e624cf7e92..d1dbe47c7975 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -315,7 +315,7 @@ static int get_name(const struct path *path, char *name, struct dentry *child) goto out; error = -EINVAL; - if (!file->f_op->iterate && !file->f_op->iterate_shared) + if (!file->f_op->iterate_shared) goto out_close; buffer.sequence = 0; diff --git a/fs/file.c b/fs/file.c index 35c62b54c9d6..3fd003a8604f 100644 --- a/fs/file.c +++ b/fs/file.c @@ -1036,12 +1036,28 @@ unsigned long __fdget_raw(unsigned int fd) return __fget_light(fd, 0); } +/* + * Try to avoid f_pos locking. We only need it if the + * file is marked for FMODE_ATOMIC_POS, and it can be + * accessed multiple ways. + * + * Always do it for directories, because pidfd_getfd() + * can make a file accessible even if it otherwise would + * not be, and for directories this is a correctness + * issue, not a "POSIX requirement". + */ +static inline bool file_needs_f_pos_lock(struct file *file) +{ + return (file->f_mode & FMODE_ATOMIC_POS) && + (file_count(file) > 1 || file->f_op->iterate_shared); +} + unsigned long __fdget_pos(unsigned int fd) { unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); - if (file && (file->f_mode & FMODE_ATOMIC_POS)) { + if (file && file_needs_f_pos_lock(file)) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 1bf3c4453516..b43fa8b8fc05 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -1578,7 +1578,7 @@ const struct file_operations gfs2_file_fops = { .fsync = gfs2_fsync, .lock = gfs2_lock, .flock = gfs2_flock, - .splice_read = filemap_splice_read, + .splice_read = copy_splice_read, .splice_write = gfs2_file_splice_write, .setlease = simple_nosetlease, .fallocate = gfs2_fallocate, @@ -1609,7 +1609,7 @@ const struct file_operations gfs2_file_fops_nolock = { .open = gfs2_open, .release = gfs2_release, .fsync = gfs2_fsync, - .splice_read = filemap_splice_read, + .splice_read = copy_splice_read, .splice_write = gfs2_file_splice_write, .setlease = generic_setlease, .fallocate = gfs2_fallocate, diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index ec1631257978..7e835be7032d 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -230,9 +230,11 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + struct super_block *sb = sdp->sd_vfs; struct gfs2_bufdata *bd; struct gfs2_meta_header *mh; struct gfs2_trans *tr = current->journal_info; + bool withdraw = false; lock_buffer(bh); if (buffer_pinned(bh)) { @@ -266,13 +268,15 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh) (unsigned long long)bd->bd_bh->b_blocknr); BUG(); } - if (unlikely(test_bit(SDF_FROZEN, &sdp->sd_flags))) { - fs_info(sdp, "GFS2:adding buf while frozen\n"); - gfs2_assert_withdraw(sdp, 0); - } if (unlikely(gfs2_withdrawn(sdp))) { fs_info(sdp, "GFS2:adding buf while withdrawn! 0x%llx\n", (unsigned long long)bd->bd_bh->b_blocknr); + goto out_unlock; + } + if (unlikely(sb->s_writers.frozen == SB_FREEZE_COMPLETE)) { + fs_info(sdp, "GFS2:adding buf while frozen\n"); + withdraw = true; + goto out_unlock; } gfs2_pin(sdp, bd->bd_bh); mh->__pad0 = cpu_to_be64(0); @@ -281,6 +285,8 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh) tr->tr_num_buf_new++; out_unlock: gfs2_log_unlock(sdp); + if (withdraw) + gfs2_assert_withdraw(sdp, 0); out: unlock_buffer(bh); } diff --git a/fs/inode.c b/fs/inode.c index 8fefb69e1f84..67611a360031 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -16,7 +16,6 @@ #include <linux/fsnotify.h> #include <linux/mount.h> #include <linux/posix_acl.h> -#include <linux/prefetch.h> #include <linux/buffer_head.h> /* for inode_has_buffers */ #include <linux/ratelimit.h> #include <linux/list_lru.h> @@ -1041,8 +1040,6 @@ struct inode *new_inode(struct super_block *sb) { struct inode *inode; - spin_lock_prefetch(&sb->s_inode_list_lock); - inode = new_inode_pseudo(sb); if (inode) inode_sb_list_add(inode); diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 9b030297aa64..e98ddb2b1cf2 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -1535,9 +1535,10 @@ const struct inode_operations jfs_dir_inode_operations = { #endif }; +WRAP_DIR_ITER(jfs_readdir) // FIXME! const struct file_operations jfs_dir_operations = { .read = generic_read_dir, - .iterate = jfs_readdir, + .iterate_shared = shared_jfs_readdir, .fsync = jfs_fsync, .unlocked_ioctl = jfs_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 8a2321d19194..2c9074ab2315 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -956,10 +956,13 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, last_page = page + (offset + sd->len - 1) / PAGE_SIZE; for (page += offset / PAGE_SIZE; page <= last_page; page++) { /* - * Skip page replacement when extending the contents - * of the current page. + * Skip page replacement when extending the contents of the + * current page. But note that we may get two zero_pages in a + * row from shmem. */ - if (page == *(rqstp->rq_next_page - 1)) + if (page == *(rqstp->rq_next_page - 1) && + offset_in_page(rqstp->rq_res.page_base + + rqstp->rq_res.page_len)) continue; if (unlikely(!svc_rqst_replace_page(rqstp, page))) return -EIO; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index a8ce522ac747..35bc79305318 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -1101,9 +1101,17 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty) int __nilfs_mark_inode_dirty(struct inode *inode, int flags) { + struct the_nilfs *nilfs = inode->i_sb->s_fs_info; struct buffer_head *ibh; int err; + /* + * Do not dirty inodes after the log writer has been detached + * and its nilfs_root struct has been freed. + */ + if (unlikely(nilfs_purging(nilfs))) + return 0; + err = nilfs_load_inode_block(inode, &ibh); if (unlikely(err)) { nilfs_warn(inode->i_sb, diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index c2553024bd25..581691e4be49 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2845,6 +2845,7 @@ void nilfs_detach_log_writer(struct super_block *sb) nilfs_segctor_destroy(nilfs->ns_writer); nilfs->ns_writer = NULL; } + set_nilfs_purging(nilfs); /* Force to free the list of dirty files */ spin_lock(&nilfs->ns_inode_lock); @@ -2857,4 +2858,5 @@ void nilfs_detach_log_writer(struct super_block *sb) up_write(&nilfs->ns_segctor_sem); nilfs_dispose_list(nilfs, &garbage_list, 1); + clear_nilfs_purging(nilfs); } diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index 47c7dfbb7ea5..cd4ae1b8ae16 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -29,6 +29,7 @@ enum { THE_NILFS_DISCONTINUED, /* 'next' pointer chain has broken */ THE_NILFS_GC_RUNNING, /* gc process is running */ THE_NILFS_SB_DIRTY, /* super block is dirty */ + THE_NILFS_PURGING, /* disposing dirty files for cleanup */ }; /** @@ -208,6 +209,7 @@ THE_NILFS_FNS(INIT, init) THE_NILFS_FNS(DISCONTINUED, discontinued) THE_NILFS_FNS(GC_RUNNING, gc_running) THE_NILFS_FNS(SB_DIRTY, sb_dirty) +THE_NILFS_FNS(PURGING, purging) /* * Mount option operations diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index 518c3a21a556..4596c90e7b7c 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -1525,10 +1525,11 @@ static int ntfs_dir_fsync(struct file *filp, loff_t start, loff_t end, #endif /* NTFS_RW */ +WRAP_DIR_ITER(ntfs_readdir) // FIXME! const struct file_operations ntfs_dir_ops = { .llseek = generic_file_llseek, /* Seek inside directory. */ .read = generic_read_dir, /* Return -EISDIR. */ - .iterate = ntfs_readdir, /* Read directory contents. */ + .iterate_shared = shared_ntfs_readdir, /* Read directory contents. */ #ifdef NTFS_RW .fsync = ntfs_dir_fsync, /* Sync a directory to disk. */ #endif /* NTFS_RW */ diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 91a194596552..bf2c17ea96a0 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2793,10 +2793,11 @@ const struct file_operations ocfs2_fops = { .remap_file_range = ocfs2_remap_file_range, }; +WRAP_DIR_ITER(ocfs2_readdir) // FIXME! const struct file_operations ocfs2_dops = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = ocfs2_readdir, + .iterate_shared = shared_ocfs2_readdir, .fsync = ocfs2_sync_file, .release = ocfs2_dir_release, .open = ocfs2_dir_open, @@ -2842,7 +2843,7 @@ const struct file_operations ocfs2_fops_no_plocks = { const struct file_operations ocfs2_dops_no_plocks = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = ocfs2_readdir, + .iterate_shared = shared_ocfs2_readdir, .fsync = ocfs2_sync_file, .release = ocfs2_dir_release, .open = ocfs2_dir_open, diff --git a/fs/open.c b/fs/open.c index 0c55c8e7f837..e6ead0f19964 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1322,7 +1322,7 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) lookup_flags |= LOOKUP_IN_ROOT; if (how->resolve & RESOLVE_CACHED) { /* Don't bother even trying for create/truncate/tmpfile open */ - if (flags & (O_TRUNC | O_CREAT | O_TMPFILE)) + if (flags & (O_TRUNC | O_CREAT | __O_TMPFILE)) return -EAGAIN; lookup_flags |= LOOKUP_CACHED; } diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index ee5c4736480f..de39e067ae65 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -954,10 +954,11 @@ static int ovl_dir_open(struct inode *inode, struct file *file) return 0; } +WRAP_DIR_ITER(ovl_iterate) // FIXME! const struct file_operations ovl_dir_operations = { .read = generic_read_dir, .open = ovl_dir_open, - .iterate = ovl_iterate, + .iterate_shared = shared_ovl_iterate, .llseek = ovl_dir_llseek, .fsync = ovl_dir_fsync, .release = ovl_dir_release, diff --git a/fs/proc/base.c b/fs/proc/base.c index 05452c3b9872..9df3f4839662 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2817,7 +2817,7 @@ static int proc_##LSM##_attr_dir_iterate(struct file *filp, \ \ static const struct file_operations proc_##LSM##_attr_dir_ops = { \ .read = generic_read_dir, \ - .iterate = proc_##LSM##_attr_dir_iterate, \ + .iterate_shared = proc_##LSM##_attr_dir_iterate, \ .llseek = default_llseek, \ }; \ \ diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 9cb32e1a78a0..23fc24d16b31 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -309,6 +309,8 @@ static void append_kcore_note(char *notes, size_t *i, const char *name, static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) { + struct file *file = iocb->ki_filp; + char *buf = file->private_data; loff_t *fpos = &iocb->ki_pos; size_t phdrs_offset, notes_offset, data_offset; size_t page_offline_frozen = 1; @@ -555,10 +557,21 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) case KCORE_VMEMMAP: case KCORE_TEXT: /* - * We use _copy_to_iter() to bypass usermode hardening - * which would otherwise prevent this operation. + * Sadly we must use a bounce buffer here to be able to + * make use of copy_from_kernel_nofault(), as these + * memory regions might not always be mapped on all + * architectures. */ - if (_copy_to_iter((char *)start, tsz, iter) != tsz) { + if (copy_from_kernel_nofault(buf, (void *)start, tsz)) { + if (iov_iter_zero(tsz, iter) != tsz) { + ret = -EFAULT; + goto out; + } + /* + * We know the bounce buffer is safe to copy from, so + * use _copy_to_iter() directly. + */ + } else if (_copy_to_iter(buf, tsz, iter) != tsz) { ret = -EFAULT; goto out; } @@ -595,6 +608,10 @@ static int open_kcore(struct inode *inode, struct file *filp) if (ret) return ret; + filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!filp->private_data) + return -ENOMEM; + if (kcore_need_update) kcore_update_ram(); if (i_size_read(inode) != proc_root_kcore->size) { @@ -605,9 +622,16 @@ static int open_kcore(struct inode *inode, struct file *filp) return 0; } +static int release_kcore(struct inode *inode, struct file *file) +{ + kfree(file->private_data); + return 0; +} + static const struct proc_ops kcore_proc_ops = { .proc_read_iter = read_kcore_iter, .proc_open = open_kcore, + .proc_release = release_kcore, .proc_lseek = default_llseek, }; diff --git a/fs/readdir.c b/fs/readdir.c index b264ce60114d..c8c46e294431 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -25,6 +25,53 @@ #include <asm/unaligned.h> /* + * Some filesystems were never converted to '->iterate_shared()' + * and their directory iterators want the inode lock held for + * writing. This wrapper allows for converting from the shared + * semantics to the exclusive inode use. + */ +int wrap_directory_iterator(struct file *file, + struct dir_context *ctx, + int (*iter)(struct file *, struct dir_context *)) +{ + struct inode *inode = file_inode(file); + int ret; + + /* + * We'd love to have an 'inode_upgrade_trylock()' operation, + * see the comment in mmap_upgrade_trylock() in mm/memory.c. + * + * But considering this is for "filesystems that never got + * converted", it really doesn't matter. + * + * Also note that since we have to return with the lock held + * for reading, we can't use the "killable()" locking here, + * since we do need to get the lock even if we're dying. + * + * We could do the write part killably and then get the read + * lock unconditionally if it mattered, but see above on why + * this does the very simplistic conversion. + */ + up_read(&inode->i_rwsem); + down_write(&inode->i_rwsem); + + /* + * Since we dropped the inode lock, we should do the + * DEADDIR test again. See 'iterate_dir()' below. + * + * Note that we don't need to re-do the f_pos games, + * since the file must be locked wrt f_pos anyway. + */ + ret = -ENOENT; + if (!IS_DEADDIR(inode)) + ret = iter(file, ctx); + + downgrade_write(&inode->i_rwsem); + return ret; +} +EXPORT_SYMBOL(wrap_directory_iterator); + +/* * Note the "unsafe_put_user() semantics: we goto a * label for errors. */ @@ -40,39 +87,28 @@ int iterate_dir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); - bool shared = false; int res = -ENOTDIR; - if (file->f_op->iterate_shared) - shared = true; - else if (!file->f_op->iterate) + + if (!file->f_op->iterate_shared) goto out; res = security_file_permission(file, MAY_READ); if (res) goto out; - if (shared) - res = down_read_killable(&inode->i_rwsem); - else - res = down_write_killable(&inode->i_rwsem); + res = down_read_killable(&inode->i_rwsem); if (res) goto out; res = -ENOENT; if (!IS_DEADDIR(inode)) { ctx->pos = file->f_pos; - if (shared) - res = file->f_op->iterate_shared(file, ctx); - else - res = file->f_op->iterate(file, ctx); + res = file->f_op->iterate_shared(file, ctx); file->f_pos = ctx->pos; fsnotify_access(file); file_accessed(file); } - if (shared) - inode_unlock_shared(inode); - else - inode_unlock(inode); + inode_unlock_shared(inode); out: return res; } diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c index df3fd3b720da..ee772c3d9f00 100644 --- a/fs/smb/client/dfs.c +++ b/fs/smb/client/dfs.c @@ -177,8 +177,12 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl); rc = dfs_get_referral(mnt_ctx, ref_path + 1, NULL, &tl); - if (rc) + if (rc) { + rc = cifs_mount_get_tcon(mnt_ctx); + if (!rc) + rc = cifs_is_path_remote(mnt_ctx); break; + } tit = dfs_cache_get_tgt_iterator(&tl); if (!tit) { diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index 33b7e6c4ceff..e881df1d10cb 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -380,13 +380,13 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) } if (smb2_req_struct_sizes[command] != pdu->StructureSize2) { - if (command == SMB2_OPLOCK_BREAK_HE && - le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_20 && - le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_21) { + if (!(command == SMB2_OPLOCK_BREAK_HE && + (le16_to_cpu(pdu->StructureSize2) == OP_BREAK_STRUCT_SIZE_20 || + le16_to_cpu(pdu->StructureSize2) == OP_BREAK_STRUCT_SIZE_21))) { /* special case for SMB2.1 lease break message */ ksmbd_debug(SMB, - "Illegal request size %d for oplock break\n", - le16_to_cpu(pdu->StructureSize2)); + "Illegal request size %u for command %d\n", + le16_to_cpu(pdu->StructureSize2), command); return 1; } } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 9849d7489345..7cc1b0c47d0a 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2324,9 +2324,16 @@ next: break; buf_len -= next; eabuf = (struct smb2_ea_info *)((char *)eabuf + next); - if (next < (u32)eabuf->EaNameLength + le16_to_cpu(eabuf->EaValueLength)) + if (buf_len < sizeof(struct smb2_ea_info)) { + rc = -EINVAL; break; + } + if (buf_len < sizeof(struct smb2_ea_info) + eabuf->EaNameLength + + le16_to_cpu(eabuf->EaValueLength)) { + rc = -EINVAL; + break; + } } while (next != 0); kfree(attr_name); diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c index 075f15c43c78..5f1a14d5b927 100644 --- a/fs/vboxsf/dir.c +++ b/fs/vboxsf/dir.c @@ -179,9 +179,10 @@ static int vboxsf_dir_iterate(struct file *dir, struct dir_context *ctx) return 0; } +WRAP_DIR_ITER(vboxsf_dir_iterate) // FIXME! const struct file_operations vboxsf_dir_fops = { .open = vboxsf_dir_open, - .iterate = vboxsf_dir_iterate, + .iterate_shared = shared_vboxsf_dir_iterate, .release = vboxsf_dir_release, .read = generic_read_dir, .llseek = generic_file_llseek, diff --git a/fs/vboxsf/shfl_hostintf.h b/fs/vboxsf/shfl_hostintf.h index aca829062c12..069a019c9247 100644 --- a/fs/vboxsf/shfl_hostintf.h +++ b/fs/vboxsf/shfl_hostintf.h @@ -68,9 +68,9 @@ struct shfl_string { /** UTF-8 or UTF-16 string. Nul terminated. */ union { - u8 utf8[2]; - u16 utf16[1]; - u16 ucs2[1]; /* misnomer, use utf16. */ + u8 legacy_padding[2]; + DECLARE_FLEX_ARRAY(u8, utf8); + DECLARE_FLEX_ARRAY(u16, utf16); } string; }; VMMDEV_ASSERT_SIZE(shfl_string, 6); diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c index 92c9aaae3663..789cfb74c146 100644 --- a/fs/zonefs/file.c +++ b/fs/zonefs/file.c @@ -341,77 +341,6 @@ static loff_t zonefs_file_llseek(struct file *file, loff_t offset, int whence) return generic_file_llseek_size(file, offset, whence, isize, isize); } -struct zonefs_zone_append_bio { - /* The target inode of the BIO */ - struct inode *inode; - - /* For sync writes, the target append write offset */ - u64 append_offset; - - /* - * This member must come last, bio_alloc_bioset will allocate enough - * bytes for entire zonefs_bio but relies on bio being last. - */ - struct bio bio; -}; - -static inline struct zonefs_zone_append_bio * -zonefs_zone_append_bio(struct bio *bio) -{ - return container_of(bio, struct zonefs_zone_append_bio, bio); -} - -static void zonefs_file_zone_append_dio_bio_end_io(struct bio *bio) -{ - struct zonefs_zone_append_bio *za_bio = zonefs_zone_append_bio(bio); - struct zonefs_zone *z = zonefs_inode_zone(za_bio->inode); - sector_t za_sector; - - if (bio->bi_status != BLK_STS_OK) - goto bio_end; - - /* - * If the file zone was written underneath the file system, the zone - * append operation can still succedd (if the zone is not full) but - * the write append location will not be where we expect it to be. - * Check that we wrote where we intended to, that is, at z->z_wpoffset. - */ - za_sector = z->z_sector + (za_bio->append_offset >> SECTOR_SHIFT); - if (bio->bi_iter.bi_sector != za_sector) { - zonefs_warn(za_bio->inode->i_sb, - "Invalid write sector %llu for zone at %llu\n", - bio->bi_iter.bi_sector, z->z_sector); - bio->bi_status = BLK_STS_IOERR; - } - -bio_end: - iomap_dio_bio_end_io(bio); -} - -static void zonefs_file_zone_append_dio_submit_io(const struct iomap_iter *iter, - struct bio *bio, - loff_t file_offset) -{ - struct zonefs_zone_append_bio *za_bio = zonefs_zone_append_bio(bio); - struct inode *inode = iter->inode; - struct zonefs_zone *z = zonefs_inode_zone(inode); - - /* - * Issue a zone append BIO to process sync dio writes. The append - * file offset is saved to check the zone append write location - * on completion of the BIO. - */ - za_bio->inode = inode; - za_bio->append_offset = file_offset; - - bio->bi_opf &= ~REQ_OP_WRITE; - bio->bi_opf |= REQ_OP_ZONE_APPEND; - bio->bi_iter.bi_sector = z->z_sector; - bio->bi_end_io = zonefs_file_zone_append_dio_bio_end_io; - - submit_bio(bio); -} - static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size, int error, unsigned int flags) { @@ -442,14 +371,6 @@ static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size, return 0; } -static struct bio_set zonefs_zone_append_bio_set; - -static const struct iomap_dio_ops zonefs_zone_append_dio_ops = { - .submit_io = zonefs_file_zone_append_dio_submit_io, - .end_io = zonefs_file_write_dio_end_io, - .bio_set = &zonefs_zone_append_bio_set, -}; - static const struct iomap_dio_ops zonefs_write_dio_ops = { .end_io = zonefs_file_write_dio_end_io, }; @@ -533,9 +454,6 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) struct zonefs_inode_info *zi = ZONEFS_I(inode); struct zonefs_zone *z = zonefs_inode_zone(inode); struct super_block *sb = inode->i_sb; - const struct iomap_dio_ops *dio_ops; - bool sync = is_sync_kiocb(iocb); - bool append = false; ssize_t ret, count; /* @@ -543,7 +461,8 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) * as this can cause write reordering (e.g. the first aio gets EAGAIN * on the inode lock but the second goes through but is now unaligned). */ - if (zonefs_zone_is_seq(z) && !sync && (iocb->ki_flags & IOCB_NOWAIT)) + if (zonefs_zone_is_seq(z) && !is_sync_kiocb(iocb) && + (iocb->ki_flags & IOCB_NOWAIT)) return -EOPNOTSUPP; if (iocb->ki_flags & IOCB_NOWAIT) { @@ -573,18 +492,6 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) goto inode_unlock; } mutex_unlock(&zi->i_truncate_mutex); - append = sync; - } - - if (append) { - unsigned int max = bdev_max_zone_append_sectors(sb->s_bdev); - - max = ALIGN_DOWN(max << SECTOR_SHIFT, sb->s_blocksize); - iov_iter_truncate(from, max); - - dio_ops = &zonefs_zone_append_dio_ops; - } else { - dio_ops = &zonefs_write_dio_ops; } /* @@ -593,7 +500,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) * the user can make sense of the error. */ ret = iomap_dio_rw(iocb, from, &zonefs_write_iomap_ops, - dio_ops, 0, NULL, 0); + &zonefs_write_dio_ops, 0, NULL, 0); if (ret == -ENOTBLK) ret = -EBUSY; @@ -938,15 +845,3 @@ const struct file_operations zonefs_file_operations = { .splice_write = iter_file_splice_write, .iopoll = iocb_bio_iopoll, }; - -int zonefs_file_bioset_init(void) -{ - return bioset_init(&zonefs_zone_append_bio_set, BIO_POOL_SIZE, - offsetof(struct zonefs_zone_append_bio, bio), - BIOSET_NEED_BVECS); -} - -void zonefs_file_bioset_exit(void) -{ - bioset_exit(&zonefs_zone_append_bio_set); -} diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index bbe44a26a8e5..9350221abfc5 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -1412,13 +1412,9 @@ static int __init zonefs_init(void) BUILD_BUG_ON(sizeof(struct zonefs_super) != ZONEFS_SUPER_SIZE); - ret = zonefs_file_bioset_init(); - if (ret) - return ret; - ret = zonefs_init_inodecache(); if (ret) - goto destroy_bioset; + return ret; ret = zonefs_sysfs_init(); if (ret) @@ -1434,8 +1430,6 @@ sysfs_exit: zonefs_sysfs_exit(); destroy_inodecache: zonefs_destroy_inodecache(); -destroy_bioset: - zonefs_file_bioset_exit(); return ret; } @@ -1445,7 +1439,6 @@ static void __exit zonefs_exit(void) unregister_filesystem(&zonefs_type); zonefs_sysfs_exit(); zonefs_destroy_inodecache(); - zonefs_file_bioset_exit(); } MODULE_AUTHOR("Damien Le Moal"); diff --git a/fs/zonefs/zonefs.h b/fs/zonefs/zonefs.h index f663b8ebc2cb..8175652241b5 100644 --- a/fs/zonefs/zonefs.h +++ b/fs/zonefs/zonefs.h @@ -279,8 +279,6 @@ extern const struct file_operations zonefs_dir_operations; extern const struct address_space_operations zonefs_file_aops; extern const struct file_operations zonefs_file_operations; int zonefs_file_truncate(struct inode *inode, loff_t isize); -int zonefs_file_bioset_init(void); -void zonefs_file_bioset_exit(void); /* In sysfs.c */ int zonefs_sysfs_register(struct super_block *sb); diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index 402a8c1c202d..a8f4b653ef4e 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -190,7 +190,7 @@ int hv_common_cpu_die(unsigned int cpu); void *hv_alloc_hyperv_page(void); void *hv_alloc_hyperv_zeroed_page(void); -void hv_free_hyperv_page(unsigned long addr); +void hv_free_hyperv_page(void *addr); /** * hv_cpu_number_to_vp_number() - Map CPU to VP. diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h index 20c93f08c993..95a1d214108a 100644 --- a/include/asm-generic/word-at-a-time.h +++ b/include/asm-generic/word-at-a-time.h @@ -38,7 +38,7 @@ static inline long find_zero(unsigned long mask) return (mask >> 8) ? byte : byte + 1; } -static inline bool has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) +static inline unsigned long has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) { unsigned long rhs = val | c->low_bits; *data = rhs; diff --git a/include/linux/bio.h b/include/linux/bio.h index c4f5b5228105..11984ed29cb8 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -791,7 +791,7 @@ static inline int bio_integrity_add_page(struct bio *bio, struct page *page, static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) { bio->bi_opf |= REQ_POLLED; - if (!is_sync_kiocb(kiocb)) + if (kiocb->ki_flags & IOCB_NOWAIT) bio->bi_opf |= REQ_NOWAIT; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ed44a997f629..87d94be7825a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -969,7 +969,6 @@ struct blk_plug { bool multiple_queues; bool has_elevator; - bool nowait; struct list_head cb_list; /* md requires an unplug callback */ }; diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 6e6e57ec69e8..e006c719182b 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -70,6 +70,10 @@ extern ssize_t cpu_show_mmio_stale_data(struct device *dev, char *buf); extern ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev, + struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_gds(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/cpumask.h b/include/linux/cpumask.h index 0d2e2a38b92d..f10fb87d49db 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -175,8 +175,8 @@ static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) /** * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 - * @src1p: the first input - * @src2p: the second input + * @srcp1: the first input + * @srcp2: the second input * * Returns >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ @@ -1197,6 +1197,10 @@ cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, /** * cpumap_print_list_to_buf - copies the cpumask into the buffer as * comma-separated list of cpus + * @buf: the buffer to copy into + * @mask: the cpumask to copy + * @off: in the string from which we are copying, we copy to @buf + * @count: the maximum number of bytes to print * * Everything is same with the above cpumap_print_bitmask_to_buf() * except the print format. diff --git a/include/linux/fs.h b/include/linux/fs.h index 6867512907d6..562f2623c9c9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1780,7 +1780,6 @@ struct file_operations { ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *, unsigned int flags); - int (*iterate) (struct file *, struct dir_context *); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); @@ -1817,6 +1816,13 @@ struct file_operations { unsigned int poll_flags); } __randomize_layout; +/* Wrap a directory iterator that needs exclusive inode access */ +int wrap_directory_iterator(struct file *, struct dir_context *, + int (*) (struct file *, struct dir_context *)); +#define WRAP_DIR_ITER(x) \ + static int shared_##x(struct file *file , struct dir_context *ctx) \ + { return wrap_directory_iterator(file, ctx, x); } + struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index bfbc37ce223b..3ac3974b3c78 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1239,9 +1239,6 @@ extern int vmbus_recvpacket_raw(struct vmbus_channel *channel, u32 *buffer_actual_len, u64 *requestid); - -extern void vmbus_ontimer(unsigned long data); - /* Base driver object */ struct hv_driver { const char *name; diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index e6936cb25047..33f21bd85dbf 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -100,10 +100,16 @@ struct rapl_package; #define RAPL_DOMAIN_NAME_LENGTH 16 +union rapl_reg { + void __iomem *mmio; + u32 msr; + u64 val; +}; + struct rapl_domain { char name[RAPL_DOMAIN_NAME_LENGTH]; enum rapl_domain_type id; - u64 regs[RAPL_DOMAIN_REG_MAX]; + union rapl_reg regs[RAPL_DOMAIN_REG_MAX]; struct powercap_zone power_zone; struct rapl_domain_data rdd; struct rapl_power_limit rpl[NR_POWER_LIMITS]; @@ -116,7 +122,7 @@ struct rapl_domain { }; struct reg_action { - u64 reg; + union rapl_reg reg; u64 mask; u64 value; int err; @@ -143,8 +149,8 @@ struct rapl_if_priv { enum rapl_if_type type; struct powercap_control_type *control_type; enum cpuhp_state pcap_rapl_online; - u64 reg_unit; - u64 regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX]; + union rapl_reg reg_unit; + union rapl_reg regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX]; int limits[RAPL_DOMAIN_MAX]; int (*read_raw)(int id, struct reg_action *ra); int (*write_raw)(int id, struct reg_action *ra); diff --git a/include/linux/prefetch.h b/include/linux/prefetch.h index b83a3f944f28..b068e2e60939 100644 --- a/include/linux/prefetch.h +++ b/include/linux/prefetch.h @@ -25,11 +25,10 @@ struct page; prefetch() should be defined by the architecture, if not, the #define below provides a no-op define. - There are 3 prefetch() macros: + There are 2 prefetch() macros: prefetch(x) - prefetches the cacheline at "x" for read prefetchw(x) - prefetches the cacheline at "x" for write - spin_lock_prefetch(x) - prefetches the spinlock *x for taking there is also PREFETCH_STRIDE which is the architecure-preferred "lookahead" size for prefetching streamed operations. @@ -44,10 +43,6 @@ struct page; #define prefetchw(x) __builtin_prefetch(x,1) #endif -#ifndef ARCH_HAS_SPINLOCK_PREFETCH -#define spin_lock_prefetch(x) prefetchw(x) -#endif - #ifndef PREFETCH_STRIDE #define PREFETCH_STRIDE (4*L1_CACHE_BYTES) #endif diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 054d7911bfc9..c1637515a8a4 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -62,6 +62,7 @@ struct sk_psock_progs { enum sk_psock_state_bits { SK_PSOCK_TX_ENABLED, + SK_PSOCK_RX_STRP_ENABLED, }; struct sk_psock_link { diff --git a/include/linux/spi/corgi_lcd.h b/include/linux/spi/corgi_lcd.h index 0b857616919c..fc6c1515dc54 100644 --- a/include/linux/spi/corgi_lcd.h +++ b/include/linux/spi/corgi_lcd.h @@ -15,4 +15,6 @@ struct corgi_lcd_platform_data { void (*kick_battery)(void); }; +void corgi_lcd_limit_intensity(int limit); + #endif /* __LINUX_SPI_CORGI_LCD_H */ diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 8e984d75f5b6..6b0a7dc48a4b 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -101,6 +101,7 @@ struct spi_mem_op { u8 nbytes; u8 buswidth; u8 dtr : 1; + u8 __pad : 7; u16 opcode; } cmd; @@ -108,6 +109,7 @@ struct spi_mem_op { u8 nbytes; u8 buswidth; u8 dtr : 1; + u8 __pad : 7; u64 val; } addr; @@ -115,12 +117,14 @@ struct spi_mem_op { u8 nbytes; u8 buswidth; u8 dtr : 1; + u8 __pad : 7; } dummy; struct { u8 buswidth; u8 dtr : 1; u8 ecc : 1; + u8 __pad : 6; enum spi_mem_data_dir dir; unsigned int nbytes; union { diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 6a1e8f157255..4ee9d13749ad 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -283,6 +283,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), TPM_CHIP_FLAG_SUSPENDED = BIT(8), + TPM_CHIP_FLAG_HWRNG_DISABLED = BIT(9), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7c7d03aa9d06..d6fa7c8767ad 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -562,6 +562,9 @@ ieee80211_get_sband_iftype_data(const struct ieee80211_supported_band *sband, if (WARN_ON(iftype >= NL80211_IFTYPE_MAX)) return NULL; + if (iftype == NL80211_IFTYPE_AP_VLAN) + iftype = NL80211_IFTYPE_AP; + for (i = 0; i < sband->n_iftype_data; i++) { const struct ieee80211_sband_iftype_data *data = &sband->iftype_data[i]; diff --git a/include/net/gro.h b/include/net/gro.h index 75efa6fb8441..88644b3ca660 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -452,6 +452,49 @@ static inline void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, gro_normal_list(napi); } +/* This function is the alternative of 'inet_iif' and 'inet_sdif' + * functions in case we can not rely on fields of IPCB. + * + * The caller must verify skb_valid_dst(skb) is false and skb->dev is initialized. + * The caller must hold the RCU read lock. + */ +static inline void inet_get_iif_sdif(const struct sk_buff *skb, int *iif, int *sdif) +{ + *iif = inet_iif(skb) ?: skb->dev->ifindex; + *sdif = 0; + +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + if (netif_is_l3_slave(skb->dev)) { + struct net_device *master = netdev_master_upper_dev_get_rcu(skb->dev); + + *sdif = *iif; + *iif = master ? master->ifindex : 0; + } +#endif +} + +/* This function is the alternative of 'inet6_iif' and 'inet6_sdif' + * functions in case we can not rely on fields of IP6CB. + * + * The caller must verify skb_valid_dst(skb) is false and skb->dev is initialized. + * The caller must hold the RCU read lock. + */ +static inline void inet6_get_iif_sdif(const struct sk_buff *skb, int *iif, int *sdif) +{ + /* using skb->dev->ifindex because skb_dst(skb) is not initialized */ + *iif = skb->dev->ifindex; + *sdif = 0; + +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + if (netif_is_l3_slave(skb->dev)) { + struct net_device *master = netdev_master_upper_dev_get_rcu(skb->dev); + + *sdif = *iif; + *iif = master ? master->ifindex : 0; + } +#endif +} + extern struct list_head offload_base; #endif /* _NET_IPV6_GRO_H */ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index caa20a905531..0bb32bfc6183 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -107,11 +107,12 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) { - if (!sk->sk_mark && - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept)) + u32 mark = READ_ONCE(sk->sk_mark); + + if (!mark && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept)) return skb->mark; - return sk->sk_mark; + return mark; } static inline int inet_request_bound_dev_if(const struct sock *sk, diff --git a/include/net/ip.h b/include/net/ip.h index 50d435855ae2..332521170d9b 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -93,7 +93,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, { ipcm_init(ipcm); - ipcm->sockc.mark = inet->sk.sk_mark; + ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark); ipcm->sockc.tsflags = inet->sk.sk_tsflags; ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 640441a2f926..35870858ddf2 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -512,6 +512,7 @@ struct nft_set_elem_expr { * * @list: table set list node * @bindings: list of set bindings + * @refs: internal refcounting for async set destruction * @table: table this set belongs to * @net: netnamespace this set belongs to * @name: name of the set @@ -541,6 +542,7 @@ struct nft_set_elem_expr { struct nft_set { struct list_head list; struct list_head bindings; + refcount_t refs; struct nft_table *table; possible_net_t net; char *name; @@ -562,7 +564,8 @@ struct nft_set { struct list_head pending_update; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; - u16 flags:14, + u16 flags:13, + dead:1, genmask:2; u8 klen; u8 dlen; @@ -596,7 +599,6 @@ struct nft_set *nft_set_lookup_global(const struct net *net, struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, const struct nft_set *set); -void *nft_set_catchall_gc(const struct nft_set *set); static inline unsigned long nft_set_gc_interval(const struct nft_set *set) { @@ -813,62 +815,6 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, const struct nft_set *set, void *elem); -/** - * struct nft_set_gc_batch_head - nf_tables set garbage collection batch - * - * @rcu: rcu head - * @set: set the elements belong to - * @cnt: count of elements - */ -struct nft_set_gc_batch_head { - struct rcu_head rcu; - const struct nft_set *set; - unsigned int cnt; -}; - -#define NFT_SET_GC_BATCH_SIZE ((PAGE_SIZE - \ - sizeof(struct nft_set_gc_batch_head)) / \ - sizeof(void *)) - -/** - * struct nft_set_gc_batch - nf_tables set garbage collection batch - * - * @head: GC batch head - * @elems: garbage collection elements - */ -struct nft_set_gc_batch { - struct nft_set_gc_batch_head head; - void *elems[NFT_SET_GC_BATCH_SIZE]; -}; - -struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set, - gfp_t gfp); -void nft_set_gc_batch_release(struct rcu_head *rcu); - -static inline void nft_set_gc_batch_complete(struct nft_set_gc_batch *gcb) -{ - if (gcb != NULL) - call_rcu(&gcb->head.rcu, nft_set_gc_batch_release); -} - -static inline struct nft_set_gc_batch * -nft_set_gc_batch_check(const struct nft_set *set, struct nft_set_gc_batch *gcb, - gfp_t gfp) -{ - if (gcb != NULL) { - if (gcb->head.cnt + 1 < ARRAY_SIZE(gcb->elems)) - return gcb; - nft_set_gc_batch_complete(gcb); - } - return nft_set_gc_batch_alloc(set, gfp); -} - -static inline void nft_set_gc_batch_add(struct nft_set_gc_batch *gcb, - void *elem) -{ - gcb->elems[gcb->head.cnt++] = elem; -} - struct nft_expr_ops; /** * struct nft_expr_type - nf_tables expression type @@ -1557,39 +1503,30 @@ static inline void nft_set_elem_change_active(const struct net *net, #endif /* IS_ENABLED(CONFIG_NF_TABLES) */ -/* - * We use a free bit in the genmask field to indicate the element - * is busy, meaning it is currently being processed either by - * the netlink API or GC. - * - * Even though the genmask is only a single byte wide, this works - * because the extension structure if fully constant once initialized, - * so there are no non-atomic write accesses unless it is already - * marked busy. - */ -#define NFT_SET_ELEM_BUSY_MASK (1 << 2) +#define NFT_SET_ELEM_DEAD_MASK (1 << 2) #if defined(__LITTLE_ENDIAN_BITFIELD) -#define NFT_SET_ELEM_BUSY_BIT 2 +#define NFT_SET_ELEM_DEAD_BIT 2 #elif defined(__BIG_ENDIAN_BITFIELD) -#define NFT_SET_ELEM_BUSY_BIT (BITS_PER_LONG - BITS_PER_BYTE + 2) +#define NFT_SET_ELEM_DEAD_BIT (BITS_PER_LONG - BITS_PER_BYTE + 2) #else #error #endif -static inline int nft_set_elem_mark_busy(struct nft_set_ext *ext) +static inline void nft_set_elem_dead(struct nft_set_ext *ext) { unsigned long *word = (unsigned long *)ext; BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); - return test_and_set_bit(NFT_SET_ELEM_BUSY_BIT, word); + set_bit(NFT_SET_ELEM_DEAD_BIT, word); } -static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext) +static inline int nft_set_elem_is_dead(const struct nft_set_ext *ext) { unsigned long *word = (unsigned long *)ext; - clear_bit(NFT_SET_ELEM_BUSY_BIT, word); + BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); + return test_bit(NFT_SET_ELEM_DEAD_BIT, word); } /** @@ -1732,6 +1669,38 @@ struct nft_trans_flowtable { #define nft_trans_flowtable_flags(trans) \ (((struct nft_trans_flowtable *)trans->data)->flags) +#define NFT_TRANS_GC_BATCHCOUNT 256 + +struct nft_trans_gc { + struct list_head list; + struct net *net; + struct nft_set *set; + u32 seq; + u8 count; + void *priv[NFT_TRANS_GC_BATCHCOUNT]; + struct rcu_head rcu; +}; + +struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, + unsigned int gc_seq, gfp_t gfp); +void nft_trans_gc_destroy(struct nft_trans_gc *trans); + +struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, + unsigned int gc_seq, gfp_t gfp); +void nft_trans_gc_queue_async_done(struct nft_trans_gc *gc); + +struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp); +void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans); + +void nft_trans_gc_elem_add(struct nft_trans_gc *gc, void *priv); + +struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, + unsigned int gc_seq); + +void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem); + int __init nft_chain_filter_init(void); void nft_chain_filter_fini(void); @@ -1758,6 +1727,7 @@ struct nftables_pernet { struct mutex commit_mutex; u64 table_handle; unsigned int base_seq; + unsigned int gc_seq; }; extern unsigned int nf_tables_net_id; diff --git a/include/net/route.h b/include/net/route.h index 5a5c726472bd..8c2a8e7d8f8e 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -168,7 +168,7 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi __be16 dport, __be16 sport, __u8 proto, __u8 tos, int oif) { - flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos, + flowi4_init_output(fl4, oif, sk ? READ_ONCE(sk->sk_mark) : 0, tos, RT_SCOPE_UNIVERSE, proto, sk ? inet_sk_flowi_flags(sk) : 0, daddr, saddr, dport, sport, sock_net_uid(net, sk)); @@ -301,7 +301,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, if (inet_sk(sk)->transparent) flow_flags |= FLOWI_FLAG_ANYSRC; - flowi4_init_output(fl4, oif, sk->sk_mark, ip_sock_rt_tos(sk), + flowi4_init_output(fl4, oif, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), protocol, flow_flags, dst, src, dport, sport, sk->sk_uid); } diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 1648240c9668..6a9f8a5f387c 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -556,12 +556,12 @@ static inline void vxlan_flag_attr_error(int attrtype, } static inline bool vxlan_fdb_nh_path_select(struct nexthop *nh, - int hash, + u32 hash, struct vxlan_rdst *rdst) { struct fib_nh_common *nhc; - nhc = nexthop_path_fdb_result(nh, hash); + nhc = nexthop_path_fdb_result(nh, hash >> 1); if (unlikely(!nhc)) return false; diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 75b2235b99e2..b9230b6add04 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -194,6 +194,7 @@ struct scsi_device { unsigned no_start_on_add:1; /* do not issue start on add */ unsigned allow_restart:1; /* issue START_UNIT in error handler */ unsigned manage_start_stop:1; /* Let HLD (sd) manage start/stop */ + unsigned no_start_on_resume:1; /* Do not issue START_STOP_UNIT on resume */ unsigned start_stop_pwr_cond:1; /* Set power cond. in START_STOP_UNIT */ unsigned no_uld_attach:1; /* disable connecting to upper level drivers */ unsigned select_no_atn:1; diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h index fc3001483e62..a5ef84944a06 100644 --- a/include/soc/tegra/mc.h +++ b/include/soc/tegra/mc.h @@ -175,6 +175,9 @@ struct tegra_mc_icc_ops { int (*get_bw)(struct icc_node *node, u32 *avg, u32 *peak); }; +struct icc_node *tegra_mc_icc_xlate(struct of_phandle_args *spec, void *data); +extern const struct tegra_mc_icc_ops tegra_mc_icc_ops; + struct tegra_mc_ops { /* * @probe: Callback to set up SoC-specific bits of the memory controller. This is called diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index bf06db8d2046..7b1ddffa3dfc 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -381,6 +381,7 @@ TRACE_EVENT(tcp_cong_state_set, __field(const void *, skaddr) __field(__u16, sport) __field(__u16, dport) + __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) @@ -396,6 +397,7 @@ TRACE_EVENT(tcp_cong_state_set, __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); + __entry->family = sk->sk_family; p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; @@ -409,7 +411,8 @@ TRACE_EVENT(tcp_cong_state_set, __entry->cong_state = ca_state; ), - TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u", + TP_printk("family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u", + show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 7865f5a9885b..4f3932bb712d 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -710,9 +710,11 @@ enum { TCA_FLOWER_KEY_CFM_OPT_UNSPEC, TCA_FLOWER_KEY_CFM_MD_LEVEL, TCA_FLOWER_KEY_CFM_OPCODE, - TCA_FLOWER_KEY_CFM_OPT_MAX, + __TCA_FLOWER_KEY_CFM_OPT_MAX, }; +#define TCA_FLOWER_KEY_CFM_OPT_MAX (__TCA_FLOWER_KEY_CFM_OPT_MAX - 1) + #define TCA_FLOWER_MASK_FLAGS_RANGE (1 << 0) /* Range-based match */ /* Match-all classifier */ diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index f4591b912ea8..93db3e4e7b68 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3470,6 +3470,8 @@ static unsigned long io_uring_mmu_get_unmapped_area(struct file *filp, * - use the kernel virtual address of the shared io_uring context * (instead of the userspace-provided address, which has to be 0UL * anyway). + * - use the same pgoff which the get_unmapped_area() uses to + * calculate the page colouring. * For architectures without such aliasing requirements, the * architecture will return any suitable mapping because addr is 0. */ @@ -3478,6 +3480,7 @@ static unsigned long io_uring_mmu_get_unmapped_area(struct file *filp, pgoff = 0; /* has been translated to ptr above */ #ifdef SHM_COLOUR addr = (uintptr_t) ptr; + pgoff = addr >> PAGE_SHIFT; #else addr = 0UL; #endif diff --git a/io_uring/openclose.c b/io_uring/openclose.c index 10ca57f5bd24..e3fae26e025d 100644 --- a/io_uring/openclose.c +++ b/io_uring/openclose.c @@ -35,9 +35,11 @@ static bool io_openat_force_async(struct io_open *open) { /* * Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open, - * it'll always -EAGAIN + * it'll always -EAGAIN. Note that we test for __O_TMPFILE because + * O_TMPFILE includes O_DIRECTORY, which isn't a flag we need to force + * async for. */ - return open->how.flags & (O_TRUNC | O_CREAT | O_TMPFILE); + return open->how.flags & (O_TRUNC | O_CREAT | __O_TMPFILE); } static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 6ae02be7a48e..286ab3db0fde 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -28,6 +28,7 @@ #include <linux/sched.h> #include <linux/workqueue.h> #include <linux/kthread.h> +#include <linux/completion.h> #include <trace/events/xdp.h> #include <linux/btf_ids.h> @@ -73,6 +74,7 @@ struct bpf_cpu_map_entry { struct rcu_head rcu; struct work_struct kthread_stop_wq; + struct completion kthread_running; }; struct bpf_cpu_map { @@ -129,11 +131,17 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring) * invoked cpu_map_kthread_stop(). Catch any broken behaviour * gracefully and warn once. */ - struct xdp_frame *xdpf; + void *ptr; - while ((xdpf = ptr_ring_consume(ring))) - if (WARN_ON_ONCE(xdpf)) - xdp_return_frame(xdpf); + while ((ptr = ptr_ring_consume(ring))) { + WARN_ON_ONCE(1); + if (unlikely(__ptr_test_bit(0, &ptr))) { + __ptr_clear_bit(0, &ptr); + kfree_skb(ptr); + continue; + } + xdp_return_frame(ptr); + } } static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) @@ -153,7 +161,6 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) static void cpu_map_kthread_stop(struct work_struct *work) { struct bpf_cpu_map_entry *rcpu; - int err; rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq); @@ -163,14 +170,7 @@ static void cpu_map_kthread_stop(struct work_struct *work) rcu_barrier(); /* kthread_stop will wake_up_process and wait for it to complete */ - err = kthread_stop(rcpu->kthread); - if (err) { - /* kthread_stop may be called before cpu_map_kthread_run - * is executed, so we need to release the memory related - * to rcpu. - */ - put_cpu_map_entry(rcpu); - } + kthread_stop(rcpu->kthread); } static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu, @@ -298,11 +298,11 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, return nframes; } - static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; + complete(&rcpu->kthread_running); set_current_state(TASK_INTERRUPTIBLE); /* When kthread gives stop order, then rcpu have been disconnected @@ -467,6 +467,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, goto free_ptr_ring; /* Setup kthread */ + init_completion(&rcpu->kthread_running); rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa, "cpumap/%d/map:%d", cpu, map->id); @@ -480,6 +481,12 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, kthread_bind(rcpu->kthread, cpu); wake_up_process(rcpu->kthread); + /* Make sure kthread has been running, so kthread_stop() will not + * stop the kthread prematurely and all pending frames or skbs + * will be handled by the kthread before kthread_stop() returns. + */ + wait_for_completion(&rcpu->kthread_running); + return rcpu; free_prog: diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index e1b4bfa938dd..2b4a946a6ff5 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -1166,7 +1166,7 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, int error; if (!hibernation_available()) - return 0; + return n; if (len && buf[len-1] == '\n') len--; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 5f2dcabad202..bd1a42b23f3f 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -661,8 +661,7 @@ static DEFINE_PER_CPU(int, bpf_trace_nest_level); BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, u64, flags, void *, data, u64, size) { - struct bpf_trace_sample_data *sds = this_cpu_ptr(&bpf_trace_sds); - int nest_level = this_cpu_inc_return(bpf_trace_nest_level); + struct bpf_trace_sample_data *sds; struct perf_raw_record raw = { .frag = { .size = size, @@ -670,7 +669,11 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, }, }; struct perf_sample_data *sd; - int err; + int nest_level, err; + + preempt_disable(); + sds = this_cpu_ptr(&bpf_trace_sds); + nest_level = this_cpu_inc_return(bpf_trace_nest_level); if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) { err = -EBUSY; @@ -688,9 +691,9 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, perf_sample_save_raw_data(sd, &raw); err = __bpf_perf_event_output(regs, map, flags, sd); - out: this_cpu_dec(bpf_trace_nest_level); + preempt_enable(); return err; } @@ -715,7 +718,6 @@ static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_misc_sds); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { - int nest_level = this_cpu_inc_return(bpf_event_output_nest_level); struct perf_raw_frag frag = { .copy = ctx_copy, .size = ctx_size, @@ -732,8 +734,12 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, }; struct perf_sample_data *sd; struct pt_regs *regs; + int nest_level; u64 ret; + preempt_disable(); + nest_level = this_cpu_inc_return(bpf_event_output_nest_level); + if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bpf_misc_sds.sds))) { ret = -EBUSY; goto out; @@ -748,6 +754,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, ret = __bpf_perf_event_output(regs, map, flags, sd); out: this_cpu_dec(bpf_event_output_nest_level); + preempt_enable(); return ret; } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 02a8f402eeb5..800b4208dba9 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -52,6 +52,7 @@ #include <linux/sched/debug.h> #include <linux/nmi.h> #include <linux/kvm_para.h> +#include <linux/delay.h> #include "workqueue_internal.h" @@ -338,8 +339,10 @@ static cpumask_var_t *wq_numa_possible_cpumask; * Per-cpu work items which run for longer than the following threshold are * automatically considered CPU intensive and excluded from concurrency * management to prevent them from noticeably delaying other per-cpu work items. + * ULONG_MAX indicates that the user hasn't overridden it with a boot parameter. + * The actual value is initialized in wq_cpu_intensive_thresh_init(). */ -static unsigned long wq_cpu_intensive_thresh_us = 10000; +static unsigned long wq_cpu_intensive_thresh_us = ULONG_MAX; module_param_named(cpu_intensive_thresh_us, wq_cpu_intensive_thresh_us, ulong, 0644); static bool wq_disable_numa; @@ -6513,6 +6516,42 @@ void __init workqueue_init_early(void) !system_freezable_power_efficient_wq); } +static void __init wq_cpu_intensive_thresh_init(void) +{ + unsigned long thresh; + unsigned long bogo; + + /* if the user set it to a specific value, keep it */ + if (wq_cpu_intensive_thresh_us != ULONG_MAX) + return; + + /* + * The default of 10ms is derived from the fact that most modern (as of + * 2023) processors can do a lot in 10ms and that it's just below what + * most consider human-perceivable. However, the kernel also runs on a + * lot slower CPUs including microcontrollers where the threshold is way + * too low. + * + * Let's scale up the threshold upto 1 second if BogoMips is below 4000. + * This is by no means accurate but it doesn't have to be. The mechanism + * is still useful even when the threshold is fully scaled up. Also, as + * the reports would usually be applicable to everyone, some machines + * operating on longer thresholds won't significantly diminish their + * usefulness. + */ + thresh = 10 * USEC_PER_MSEC; + + /* see init/calibrate.c for lpj -> BogoMIPS calculation */ + bogo = max_t(unsigned long, loops_per_jiffy / 500000 * HZ, 1); + if (bogo < 4000) + thresh = min_t(unsigned long, thresh * 4000 / bogo, USEC_PER_SEC); + + pr_debug("wq_cpu_intensive_thresh: lpj=%lu BogoMIPS=%lu thresh_us=%lu\n", + loops_per_jiffy, bogo, thresh); + + wq_cpu_intensive_thresh_us = thresh; +} + /** * workqueue_init - bring workqueue subsystem fully online * @@ -6528,6 +6567,8 @@ void __init workqueue_init(void) struct worker_pool *pool; int cpu, bkt; + wq_cpu_intensive_thresh_init(); + /* * It'd be simpler to initialize NUMA in workqueue_init_early() but * CPU to node mapping may not be available that early on some diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index fbc89baf7de6..d6798513a8c2 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1200,7 +1200,7 @@ config WQ_CPU_INTENSIVE_REPORT help Say Y here to enable reporting of concurrency-managed per-cpu work items that hog CPUs for longer than - workqueue.cpu_intensive_threshold_us. Workqueue automatically + workqueue.cpu_intensive_thresh_us. Workqueue automatically detects and excludes them from concurrency management to prevent them from stalling other per-cpu work items. Occassional triggering may not necessarily indicate a problem. Repeated diff --git a/lib/Makefile b/lib/Makefile index 42d307ade225..1ffae65bb7ee 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -82,7 +82,13 @@ obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_key_base.o obj-$(CONFIG_TEST_DYNAMIC_DEBUG) += test_dynamic_debug.o obj-$(CONFIG_TEST_PRINTF) += test_printf.o obj-$(CONFIG_TEST_SCANF) += test_scanf.o + obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o +ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_KASAN),yy) +# FIXME: Clang breaks test_bitmap_const_eval when KASAN and GCOV are enabled +GCOV_PROFILE_test_bitmap.o := n +endif + obj-$(CONFIG_TEST_UUID) += test_uuid.o obj-$(CONFIG_TEST_XARRAY) += test_xarray.o obj-$(CONFIG_TEST_MAPLE_TREE) += test_maple_tree.o diff --git a/lib/cpumask.c b/lib/cpumask.c index de356f16773a..a7fd02b5ae26 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -45,6 +45,7 @@ EXPORT_SYMBOL(cpumask_next_wrap); * alloc_cpumask_var_node - allocate a struct cpumask on a given node * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags + * @node: memory node from which to allocate or %NUMA_NO_NODE * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>) @@ -157,7 +158,9 @@ EXPORT_SYMBOL(cpumask_local_spread); static DEFINE_PER_CPU(int, distribute_cpu_mask_prev); /** - * cpumask_any_and_distribute - Return an arbitrary cpu within srcp1 & srcp2. + * cpumask_any_and_distribute - Return an arbitrary cpu within src1p & src2p. + * @src1p: first &cpumask for intersection + * @src2p: second &cpumask for intersection * * Iterated calls using the same srcp1 and srcp2 will be distributed within * their intersection. diff --git a/lib/scatterlist.c b/lib/scatterlist.c index e86231a44c3d..c65566b4dc66 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -1148,7 +1148,7 @@ static ssize_t extract_user_to_sg(struct iov_iter *iter, failed: while (sgtable->nents > sgtable->orig_nents) - put_page(sg_page(&sgtable->sgl[--sgtable->nents])); + unpin_user_page(sg_page(&sgtable->sgl[--sgtable->nents])); return res; } diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 187f5b2db4cf..f2ea9f30c7c5 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -1161,6 +1161,10 @@ static void __init test_bitmap_print_buf(void) } } +/* + * FIXME: Clang breaks compile-time evaluations when KASAN and GCOV are enabled. + * To workaround it, GCOV is force-disabled in Makefile for this configuration. + */ static void __init test_bitmap_const_eval(void) { DECLARE_BITMAP(bitmap, BITS_PER_LONG); @@ -1186,11 +1190,7 @@ static void __init test_bitmap_const_eval(void) * the compiler is fixed. */ bitmap_clear(bitmap, 0, BITS_PER_LONG); -#if defined(__s390__) && defined(__clang__) - if (!const_test_bit(7, bitmap)) -#else if (!test_bit(7, bitmap)) -#endif bitmap_set(bitmap, 5, 2); /* Equals to `unsigned long bitopvar = BIT(20)` */ diff --git a/mm/compaction.c b/mm/compaction.c index dbc9f86b1934..eacca2794e47 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -912,11 +912,12 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, /* * Check if the pageblock has already been marked skipped. - * Only the aligned PFN is checked as the caller isolates + * Only the first PFN is checked as the caller isolates * COMPACT_CLUSTER_MAX at a time so the second call must * not falsely conclude that the block should be skipped. */ - if (!valid_page && pageblock_aligned(low_pfn)) { + if (!valid_page && (pageblock_aligned(low_pfn) || + low_pfn == cc->zone->zone_start_pfn)) { if (!isolation_suitable(cc, page)) { low_pfn = end_pfn; folio = NULL; @@ -2002,7 +2003,8 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc) * before making it "skip" so other compaction instances do * not scan the same block. */ - if (pageblock_aligned(low_pfn) && + if ((pageblock_aligned(low_pfn) || + low_pfn == cc->zone->zone_start_pfn) && !fast_find_block && !isolation_suitable(cc, page)) continue; diff --git a/mm/damon/core.c b/mm/damon/core.c index 91cff7f2997e..eb9580942a5c 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -273,6 +273,7 @@ struct damos_filter *damos_new_filter(enum damos_filter_type type, return NULL; filter->type = type; filter->matching = matching; + INIT_LIST_HEAD(&filter->list); return filter; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 64a3239b6407..6da626bfb52e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1579,9 +1579,37 @@ static inline void destroy_compound_gigantic_folio(struct folio *folio, unsigned int order) { } #endif +static inline void __clear_hugetlb_destructor(struct hstate *h, + struct folio *folio) +{ + lockdep_assert_held(&hugetlb_lock); + + /* + * Very subtle + * + * For non-gigantic pages set the destructor to the normal compound + * page dtor. This is needed in case someone takes an additional + * temporary ref to the page, and freeing is delayed until they drop + * their reference. + * + * For gigantic pages set the destructor to the null dtor. This + * destructor will never be called. Before freeing the gigantic + * page destroy_compound_gigantic_folio will turn the folio into a + * simple group of pages. After this the destructor does not + * apply. + * + */ + if (hstate_is_gigantic(h)) + folio_set_compound_dtor(folio, NULL_COMPOUND_DTOR); + else + folio_set_compound_dtor(folio, COMPOUND_PAGE_DTOR); +} + /* - * Remove hugetlb folio from lists, and update dtor so that the folio appears - * as just a compound page. + * Remove hugetlb folio from lists. + * If vmemmap exists for the folio, update dtor so that the folio appears + * as just a compound page. Otherwise, wait until after allocating vmemmap + * to update dtor. * * A reference is held on the folio, except in the case of demote. * @@ -1612,31 +1640,19 @@ static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio, } /* - * Very subtle - * - * For non-gigantic pages set the destructor to the normal compound - * page dtor. This is needed in case someone takes an additional - * temporary ref to the page, and freeing is delayed until they drop - * their reference. - * - * For gigantic pages set the destructor to the null dtor. This - * destructor will never be called. Before freeing the gigantic - * page destroy_compound_gigantic_folio will turn the folio into a - * simple group of pages. After this the destructor does not - * apply. - * - * This handles the case where more than one ref is held when and - * after update_and_free_hugetlb_folio is called. - * - * In the case of demote we do not ref count the page as it will soon - * be turned into a page of smaller size. + * We can only clear the hugetlb destructor after allocating vmemmap + * pages. Otherwise, someone (memory error handling) may try to write + * to tail struct pages. + */ + if (!folio_test_hugetlb_vmemmap_optimized(folio)) + __clear_hugetlb_destructor(h, folio); + + /* + * In the case of demote we do not ref count the page as it will soon + * be turned into a page of smaller size. */ if (!demote) folio_ref_unfreeze(folio, 1); - if (hstate_is_gigantic(h)) - folio_set_compound_dtor(folio, NULL_COMPOUND_DTOR); - else - folio_set_compound_dtor(folio, COMPOUND_PAGE_DTOR); h->nr_huge_pages--; h->nr_huge_pages_node[nid]--; @@ -1705,6 +1721,7 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, { int i; struct page *subpage; + bool clear_dtor = folio_test_hugetlb_vmemmap_optimized(folio); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; @@ -1735,6 +1752,16 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, if (unlikely(folio_test_hwpoison(folio))) folio_clear_hugetlb_hwpoison(folio); + /* + * If vmemmap pages were allocated above, then we need to clear the + * hugetlb destructor under the hugetlb lock. + */ + if (clear_dtor) { + spin_lock_irq(&hugetlb_lock); + __clear_hugetlb_destructor(h, folio); + spin_unlock_irq(&hugetlb_lock); + } + for (i = 0; i < pages_per_huge_page(h); i++) { subpage = folio_page(folio, i); subpage->flags &= ~(1 << PG_locked | 1 << PG_error | @@ -2784,6 +2784,8 @@ struct page *ksm_might_need_to_copy(struct page *page, anon_vma->root == vma->anon_vma->root) { return page; /* still no need to copy it */ } + if (PageHWPoison(page)) + return ERR_PTR(-EHWPOISON); if (!PageUptodate(page)) return page; /* let do_swap_page report the error */ diff --git a/mm/memory-failure.c b/mm/memory-failure.c index ece5d481b5ff..9a285038d765 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2466,7 +2466,7 @@ int unpoison_memory(unsigned long pfn) { struct folio *folio; struct page *p; - int ret = -EBUSY; + int ret = -EBUSY, ghp; unsigned long count = 1; bool huge = false; static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL, @@ -2499,6 +2499,13 @@ int unpoison_memory(unsigned long pfn) goto unlock_mutex; } + if (folio_test_slab(folio) || PageTable(&folio->page) || folio_test_reserved(folio)) + goto unlock_mutex; + + /* + * Note that folio->_mapcount is overloaded in SLAB, so the simple test + * in folio_mapped() has to be done after folio_test_slab() is checked. + */ if (folio_mapped(folio)) { unpoison_pr_info("Unpoison: Someone maps the hwpoison page %#lx\n", pfn, &unpoison_rs); @@ -2511,32 +2518,28 @@ int unpoison_memory(unsigned long pfn) goto unlock_mutex; } - if (folio_test_slab(folio) || PageTable(&folio->page) || folio_test_reserved(folio)) - goto unlock_mutex; - - ret = get_hwpoison_page(p, MF_UNPOISON); - if (!ret) { + ghp = get_hwpoison_page(p, MF_UNPOISON); + if (!ghp) { if (PageHuge(p)) { huge = true; count = folio_free_raw_hwp(folio, false); - if (count == 0) { - ret = -EBUSY; + if (count == 0) goto unlock_mutex; - } } ret = folio_test_clear_hwpoison(folio) ? 0 : -EBUSY; - } else if (ret < 0) { - if (ret == -EHWPOISON) { + } else if (ghp < 0) { + if (ghp == -EHWPOISON) { ret = put_page_back_buddy(p) ? 0 : -EBUSY; - } else + } else { + ret = ghp; unpoison_pr_info("Unpoison: failed to grab page %#lx\n", pfn, &unpoison_rs); + } } else { if (PageHuge(p)) { huge = true; count = folio_free_raw_hwp(folio, false); if (count == 0) { - ret = -EBUSY; folio_put(folio); goto unlock_mutex; } diff --git a/mm/memory.c b/mm/memory.c index 603b2f419948..1ec1ef3418bf 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5705,6 +5705,9 @@ int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, if (mmap_read_lock_killable(mm)) return 0; + /* Untag the address before looking up the VMA */ + addr = untagged_addr_remote(mm, addr); + /* Avoid triggering the temporary warning in __get_user_pages */ if (!vma_lookup(mm, addr) && !expand_stack(mm, addr)) return 0; diff --git a/mm/swapfile.c b/mm/swapfile.c index 8e6dde68b389..b15112b1f1a8 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1746,7 +1746,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, struct page *swapcache; spinlock_t *ptl; pte_t *pte, new_pte, old_pte; - bool hwposioned = false; + bool hwpoisoned = PageHWPoison(page); int ret = 1; swapcache = page; @@ -1754,7 +1754,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, if (unlikely(!page)) return -ENOMEM; else if (unlikely(PTR_ERR(page) == -EHWPOISON)) - hwposioned = true; + hwpoisoned = true; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte), @@ -1765,11 +1765,11 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, old_pte = ptep_get(pte); - if (unlikely(hwposioned || !PageUptodate(page))) { + if (unlikely(hwpoisoned || !PageUptodate(page))) { swp_entry_t swp_entry; dec_mm_counter(vma->vm_mm, MM_SWAPENTS); - if (hwposioned) { + if (hwpoisoned) { swp_entry = make_hwpoison_entry(swapcache); page = swapcache; } else { diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 3f057970504e..32916d28d9d9 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1798,6 +1798,7 @@ static void replace_sub_page(struct size_class *class, struct zspage *zspage, static bool zs_page_isolate(struct page *page, isolate_mode_t mode) { + struct zs_pool *pool; struct zspage *zspage; /* @@ -1807,9 +1808,10 @@ static bool zs_page_isolate(struct page *page, isolate_mode_t mode) VM_BUG_ON_PAGE(PageIsolated(page), page); zspage = get_zspage(page); - migrate_write_lock(zspage); + pool = zspage->pool; + spin_lock(&pool->lock); inc_zspage_isolation(zspage); - migrate_write_unlock(zspage); + spin_unlock(&pool->lock); return true; } @@ -1875,12 +1877,12 @@ static int zs_page_migrate(struct page *newpage, struct page *page, kunmap_atomic(s_addr); replace_sub_page(class, zspage, newpage, page); + dec_zspage_isolation(zspage); /* * Since we complete the data copy and set up new zspage structure, * it's okay to release the pool's lock. */ spin_unlock(&pool->lock); - dec_zspage_isolation(zspage); migrate_write_unlock(zspage); get_page(newpage); @@ -1897,14 +1899,16 @@ static int zs_page_migrate(struct page *newpage, struct page *page, static void zs_page_putback(struct page *page) { + struct zs_pool *pool; struct zspage *zspage; VM_BUG_ON_PAGE(!PageIsolated(page), page); zspage = get_zspage(page); - migrate_write_lock(zspage); + pool = zspage->pool; + spin_lock(&pool->lock); dec_zspage_isolation(zspage); - migrate_write_unlock(zspage); + spin_unlock(&pool->lock); } static const struct movable_operations zsmalloc_mops = { diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index e40aa3e3641c..b3662119ddbc 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -384,8 +384,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, dev->name); vlan_vid_add(dev, htons(ETH_P_8021Q), 0); } - if (event == NETDEV_DOWN && - (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) + if (event == NETDEV_DOWN) vlan_vid_del(dev, htons(ETH_P_8021Q), 0); vlan_info = rtnl_dereference(dev->vlan_info); diff --git a/net/can/raw.c b/net/can/raw.c index ba6b52b1d776..e10f59375659 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -865,7 +865,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) skb->dev = dev; skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; skb_setup_tx_timestamp(skb, sockc.tsflags); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 11c04e7d928e..658a6f2320cf 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -3334,17 +3334,24 @@ static int linger_reg_commit_wait(struct ceph_osd_linger_request *lreq) int ret; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); - ret = wait_for_completion_interruptible(&lreq->reg_commit_wait); + ret = wait_for_completion_killable(&lreq->reg_commit_wait); return ret ?: lreq->reg_commit_error; } -static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq) +static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq, + unsigned long timeout) { - int ret; + long left; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); - ret = wait_for_completion_interruptible(&lreq->notify_finish_wait); - return ret ?: lreq->notify_finish_error; + left = wait_for_completion_killable_timeout(&lreq->notify_finish_wait, + ceph_timeout_jiffies(timeout)); + if (left <= 0) + left = left ?: -ETIMEDOUT; + else + left = lreq->notify_finish_error; /* completed */ + + return left; } /* @@ -4896,7 +4903,8 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, linger_submit(lreq); ret = linger_reg_commit_wait(lreq); if (!ret) - ret = linger_notify_finish_wait(lreq); + ret = linger_notify_finish_wait(lreq, + msecs_to_jiffies(2 * timeout * MSEC_PER_SEC)); else dout("lreq %p failed to initiate notify %d\n", lreq, ret); diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index d4172534dfa8..cca7594be92e 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -496,8 +496,11 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) return ERR_PTR(-EPERM); nla_for_each_nested(nla, nla_stgs, rem) { - if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) + if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) { + if (nla_len(nla) != sizeof(u32)) + return ERR_PTR(-EINVAL); nr_maps++; + } } diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL); diff --git a/net/core/filter.c b/net/core/filter.c index 06ba0e56e369..28a59596987a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4116,12 +4116,6 @@ BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) if (unlikely(data_end > data_hard_end)) return -EINVAL; - /* ALL drivers MUST init xdp->frame_sz, chicken check below */ - if (unlikely(xdp->frame_sz > PAGE_SIZE)) { - WARN_ONCE(1, "Too BIG xdp->frame_sz = %d\n", xdp->frame_sz); - return -EINVAL; - } - if (unlikely(data_end < xdp->data + ETH_HLEN)) return -EINVAL; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 3ad4e030846d..aef25aa5cf1d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -5140,13 +5140,17 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (br_spec) { nla_for_each_nested(attr, br_spec, rem) { - if (nla_type(attr) == IFLA_BRIDGE_FLAGS) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !have_flags) { if (nla_len(attr) < sizeof(flags)) return -EINVAL; have_flags = true; flags = nla_get_u16(attr); - break; + } + + if (nla_type(attr) == IFLA_BRIDGE_MODE) { + if (nla_len(attr) < sizeof(u16)) + return -EINVAL; } } } diff --git a/net/core/skmsg.c b/net/core/skmsg.c index a29508e1ff35..ef1a2eb6520b 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1120,13 +1120,19 @@ static void sk_psock_strp_data_ready(struct sock *sk) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) { + int ret; + static const struct strp_callbacks cb = { .rcv_msg = sk_psock_strp_read, .read_sock_done = sk_psock_strp_read_done, .parse_msg = sk_psock_strp_parse, }; - return strp_init(&psock->strp, sk, &cb); + ret = strp_init(&psock->strp, sk, &cb); + if (!ret) + sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED); + + return ret; } void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) @@ -1154,7 +1160,7 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) static void sk_psock_done_strp(struct sk_psock *psock) { /* Parser has been stopped */ - if (psock->progs.stream_parser) + if (sk_psock_test_state(psock, SK_PSOCK_RX_STRP_ENABLED)) strp_done(&psock->strp); } #else diff --git a/net/core/sock.c b/net/core/sock.c index 9370fd50aa2c..732fc37a4771 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -429,6 +429,7 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, { struct __kernel_sock_timeval tv; int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval); + long val; if (err) return err; @@ -439,7 +440,7 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, if (tv.tv_sec < 0) { static int warned __read_mostly; - *timeo_p = 0; + WRITE_ONCE(*timeo_p, 0); if (warned < 10 && net_ratelimit()) { warned++; pr_info("%s: `%s' (pid %d) tries to set negative timeout\n", @@ -447,11 +448,12 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, } return 0; } - *timeo_p = MAX_SCHEDULE_TIMEOUT; - if (tv.tv_sec == 0 && tv.tv_usec == 0) - return 0; - if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) - *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ); + val = MAX_SCHEDULE_TIMEOUT; + if ((tv.tv_sec || tv.tv_usec) && + (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1))) + val = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, + USEC_PER_SEC / HZ); + WRITE_ONCE(*timeo_p, val); return 0; } @@ -804,7 +806,7 @@ EXPORT_SYMBOL(sock_no_linger); void sock_set_priority(struct sock *sk, u32 priority) { lock_sock(sk); - sk->sk_priority = priority; + WRITE_ONCE(sk->sk_priority, priority); release_sock(sk); } EXPORT_SYMBOL(sock_set_priority); @@ -813,9 +815,9 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs) { lock_sock(sk); if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1) - sk->sk_sndtimeo = secs * HZ; + WRITE_ONCE(sk->sk_sndtimeo, secs * HZ); else - sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; + WRITE_ONCE(sk->sk_sndtimeo, MAX_SCHEDULE_TIMEOUT); release_sock(sk); } EXPORT_SYMBOL(sock_set_sndtimeo); @@ -988,7 +990,7 @@ EXPORT_SYMBOL(sock_set_rcvbuf); static void __sock_set_mark(struct sock *sk, u32 val) { if (val != sk->sk_mark) { - sk->sk_mark = val; + WRITE_ONCE(sk->sk_mark, val); sk_dst_reset(sk); } } @@ -1007,7 +1009,7 @@ static void sock_release_reserved_memory(struct sock *sk, int bytes) bytes = round_down(bytes, PAGE_SIZE); WARN_ON(bytes > sk->sk_reserved_mem); - sk->sk_reserved_mem -= bytes; + WRITE_ONCE(sk->sk_reserved_mem, sk->sk_reserved_mem - bytes); sk_mem_reclaim(sk); } @@ -1044,7 +1046,8 @@ static int sock_reserve_memory(struct sock *sk, int bytes) } sk->sk_forward_alloc += pages << PAGE_SHIFT; - sk->sk_reserved_mem += pages << PAGE_SHIFT; + WRITE_ONCE(sk->sk_reserved_mem, + sk->sk_reserved_mem + (pages << PAGE_SHIFT)); return 0; } @@ -1213,7 +1216,7 @@ set_sndbuf: if ((val >= 0 && val <= 6) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) - sk->sk_priority = val; + WRITE_ONCE(sk->sk_priority, val); else ret = -EPERM; break; @@ -1438,7 +1441,8 @@ set_sndbuf: cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); - sk->sk_max_pacing_rate = ulval; + /* Pairs with READ_ONCE() from sk_getsockopt() */ + WRITE_ONCE(sk->sk_max_pacing_rate, ulval); sk->sk_pacing_rate = min(sk->sk_pacing_rate, ulval); break; } @@ -1533,7 +1537,9 @@ set_sndbuf: } if ((u8)val == SOCK_TXREHASH_DEFAULT) val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); - /* Paired with READ_ONCE() in tcp_rtx_synack() */ + /* Paired with READ_ONCE() in tcp_rtx_synack() + * and sk_getsockopt(). + */ WRITE_ONCE(sk->sk_txrehash, (u8)val); break; @@ -1633,11 +1639,11 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_SNDBUF: - v.val = sk->sk_sndbuf; + v.val = READ_ONCE(sk->sk_sndbuf); break; case SO_RCVBUF: - v.val = sk->sk_rcvbuf; + v.val = READ_ONCE(sk->sk_rcvbuf); break; case SO_REUSEADDR: @@ -1679,7 +1685,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_PRIORITY: - v.val = sk->sk_priority; + v.val = READ_ONCE(sk->sk_priority); break; case SO_LINGER: @@ -1717,16 +1723,18 @@ int sk_getsockopt(struct sock *sk, int level, int optname, case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: - lv = sock_get_timeout(sk->sk_rcvtimeo, &v, SO_RCVTIMEO_OLD == optname); + lv = sock_get_timeout(READ_ONCE(sk->sk_rcvtimeo), &v, + SO_RCVTIMEO_OLD == optname); break; case SO_SNDTIMEO_OLD: case SO_SNDTIMEO_NEW: - lv = sock_get_timeout(sk->sk_sndtimeo, &v, SO_SNDTIMEO_OLD == optname); + lv = sock_get_timeout(READ_ONCE(sk->sk_sndtimeo), &v, + SO_SNDTIMEO_OLD == optname); break; case SO_RCVLOWAT: - v.val = sk->sk_rcvlowat; + v.val = READ_ONCE(sk->sk_rcvlowat); break; case SO_SNDLOWAT: @@ -1770,7 +1778,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, spin_unlock(&sk->sk_peer_lock); if (!peer_pid) - return -ESRCH; + return -ENODATA; pidfd = pidfd_prepare(peer_pid, 0, &pidfd_file); put_pid(peer_pid); @@ -1843,7 +1851,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, optval, optlen, len); case SO_MARK: - v.val = sk->sk_mark; + v.val = READ_ONCE(sk->sk_mark); break; case SO_RCVMARK: @@ -1862,7 +1870,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, if (!sock->ops->set_peek_off) return -EOPNOTSUPP; - v.val = sk->sk_peek_off; + v.val = READ_ONCE(sk->sk_peek_off); break; case SO_NOFCS: v.val = sock_flag(sk, SOCK_NOFCS); @@ -1892,7 +1900,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: - v.val = sk->sk_ll_usec; + v.val = READ_ONCE(sk->sk_ll_usec); break; case SO_PREFER_BUSY_POLL: v.val = READ_ONCE(sk->sk_prefer_busy_poll); @@ -1900,12 +1908,14 @@ int sk_getsockopt(struct sock *sk, int level, int optname, #endif case SO_MAX_PACING_RATE: + /* The READ_ONCE() pair with the WRITE_ONCE() in sk_setsockopt() */ if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) { lv = sizeof(v.ulval); - v.ulval = sk->sk_max_pacing_rate; + v.ulval = READ_ONCE(sk->sk_max_pacing_rate); } else { /* 32bit version */ - v.val = min_t(unsigned long, sk->sk_max_pacing_rate, ~0U); + v.val = min_t(unsigned long, ~0U, + READ_ONCE(sk->sk_max_pacing_rate)); } break; @@ -1973,11 +1983,12 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_RESERVE_MEM: - v.val = sk->sk_reserved_mem; + v.val = READ_ONCE(sk->sk_reserved_mem); break; case SO_TXREHASH: - v.val = sk->sk_txrehash; + /* Paired with WRITE_ONCE() in sk_setsockopt() */ + v.val = READ_ONCE(sk->sk_txrehash); break; default: @@ -3168,7 +3179,7 @@ EXPORT_SYMBOL(__sk_mem_reclaim); int sk_set_peek_off(struct sock *sk, int val) { - sk->sk_peek_off = val; + WRITE_ONCE(sk->sk_peek_off, val); return 0; } EXPORT_SYMBOL_GPL(sk_set_peek_off); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 19538d628714..8f07fea39d9e 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -115,7 +115,6 @@ static void sock_map_sk_acquire(struct sock *sk) __acquires(&sk->sk_lock.slock) { lock_sock(sk); - preempt_disable(); rcu_read_lock(); } @@ -123,7 +122,6 @@ static void sock_map_sk_release(struct sock *sk) __releases(&sk->sk_lock.slock) { rcu_read_unlock(); - preempt_enable(); release_sock(sk); } @@ -148,13 +146,13 @@ static void sock_map_del_link(struct sock *sk, list_for_each_entry_safe(link, tmp, &psock->link, list) { if (link->link_raw == link_raw) { struct bpf_map *map = link->map; - struct bpf_stab *stab = container_of(map, struct bpf_stab, - map); - if (psock->saved_data_ready && stab->progs.stream_parser) + struct sk_psock_progs *progs = sock_map_progs(map); + + if (psock->saved_data_ready && progs->stream_parser) strp_stop = true; - if (psock->saved_data_ready && stab->progs.stream_verdict) + if (psock->saved_data_ready && progs->stream_verdict) verdict_stop = true; - if (psock->saved_data_ready && stab->progs.skb_verdict) + if (psock->saved_data_ready && progs->skb_verdict) verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index c0c438128575..2e6b8c8fd2de 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -980,7 +980,7 @@ static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_BCN_ATTR_MAX, - tb[DCB_ATTR_BCN], dcbnl_pfc_up_nest, + tb[DCB_ATTR_BCN], dcbnl_bcn_nest, NULL); if (ret) return ret; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 7249ef218178..d29d1163203d 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -238,8 +238,8 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass, - sk->sk_priority); + err = ip6_xmit(sk, skb, &fl6, READ_ONCE(sk->sk_mark), opt, + np->tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } diff --git a/net/dccp/output.c b/net/dccp/output.c index b8a24734385e..fd2eb148d24d 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -187,7 +187,7 @@ unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu) /* And store cached results */ icsk->icsk_pmtu_cookie = pmtu; - dp->dccps_mss_cache = cur_mps; + WRITE_ONCE(dp->dccps_mss_cache, cur_mps); return cur_mps; } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index f331e5977a84..4e3266e4d7c3 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -630,7 +630,7 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname, return dccp_getsockopt_service(sk, len, (__be32 __user *)optval, optlen); case DCCP_SOCKOPT_GET_CUR_MPS: - val = dp->dccps_mss_cache; + val = READ_ONCE(dp->dccps_mss_cache); break; case DCCP_SOCKOPT_AVAILABLE_CCIDS: return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen); @@ -739,7 +739,7 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) trace_dccp_probe(sk, len); - if (len > dp->dccps_mss_cache) + if (len > READ_ONCE(dp->dccps_mss_cache)) return -EMSGSIZE; lock_sock(sk); @@ -772,6 +772,12 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto out_discard; } + /* We need to check dccps_mss_cache after socket is locked. */ + if (len > dp->dccps_mss_cache) { + rc = -EMSGSIZE; + goto out_discard; + } + skb_reserve(skb, sk->sk_prot->max_header); rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc != 0) diff --git a/net/dsa/port.c b/net/dsa/port.c index 0ce8fd311c78..2f6195d7b741 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -1727,8 +1727,15 @@ int dsa_port_phylink_create(struct dsa_port *dp) ds->ops->phylink_mac_an_restart) dp->pl_config.legacy_pre_march2020 = true; - if (ds->ops->phylink_get_caps) + if (ds->ops->phylink_get_caps) { ds->ops->phylink_get_caps(ds, dp->index, &dp->pl_config); + } else { + /* For legacy drivers */ + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + dp->pl_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_GMII, + dp->pl_config.supported_interfaces); + } pl = phylink_create(&dp->pl_config, of_fwnode_handle(dp->dn), mode, &dsa_port_phylink_mac_ops); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index b812eb36f0e3..f7426926a104 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -150,7 +150,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, } #endif - if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark)) + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, READ_ONCE(sk->sk_mark))) goto errout; if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || @@ -799,7 +799,7 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) entry.ifindex = sk->sk_bound_dev_if; entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0; if (sk_fullsock(sk)) - entry.mark = sk->sk_mark; + entry.mark = READ_ONCE(sk->sk_mark); else if (sk->sk_state == TCP_NEW_SYN_RECV) entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark; else if (sk->sk_state == TCP_TIME_WAIT) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 6e70839257f7..6ba1a0fafbaa 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -184,9 +184,9 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, ip_options_build(skb, &opt->opt, daddr, rt); } - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); if (!skb->mark) - skb->mark = sk->sk_mark; + skb->mark = READ_ONCE(sk->sk_mark); /* Send it out. */ return ip_local_out(net, skb->sk, skb); @@ -528,8 +528,8 @@ packet_routed: skb_shinfo(skb)->gso_segs ?: 1); /* TODO : should we use skb->sk here instead of sk ? */ - skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + skb->priority = READ_ONCE(sk->sk_priority); + skb->mark = READ_ONCE(sk->sk_mark); res = ip_local_out(net, sk, skb); rcu_read_unlock(); @@ -1158,10 +1158,15 @@ alloc_new_skb: } copy = datalen - transhdrlen - fraggap - pagedlen; + /* [!] NOTE: copy will be negative if pagedlen>0 + * because then the equation reduces to -fraggap. + */ if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; + } else if (flags & MSG_SPLICE_PAGES) { + copy = 0; } offset += copy; @@ -1209,6 +1214,10 @@ alloc_new_skb: } else if (flags & MSG_SPLICE_PAGES) { struct msghdr *msg = from; + err = -EIO; + if (WARN_ON_ONCE(copy > msg->msg_iter.count)) + goto error; + err = skb_splice_from_iter(skb, &msg->msg_iter, copy, sk->sk_allocation); if (err < 0) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 8e97d8d4cc9d..d41bce8927b2 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -592,7 +592,7 @@ void __ip_sock_set_tos(struct sock *sk, int val) } if (inet_sk(sk)->tos != val) { inet_sk(sk)->tos = val; - sk->sk_priority = rt_tos2priority(val); + WRITE_ONCE(sk->sk_priority, rt_tos2priority(val)); sk_dst_reset(sk); } } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 92c02c886fe7..586b1b3e35b8 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -224,7 +224,7 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) .un.frag.__unused = 0, .un.frag.mtu = htons(mtu), }; - icmph->checksum = ip_compute_csum(icmph, len); + icmph->checksum = csum_fold(skb_checksum(skb, 0, len, 0)); skb_reset_transport_header(skb); niph = skb_push(skb, sizeof(*niph)); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index f95142e56da0..be5498f5dd31 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3221,13 +3221,9 @@ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) &rtm_dump_nexthop_cb, &filter); if (err < 0) { if (likely(skb->len)) - goto out; - goto out_err; + err = skb->len; } -out: - err = skb->len; -out_err: cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; @@ -3367,25 +3363,19 @@ static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb, dd->filter.res_bucket_nh_id != nhge->nh->id) continue; + dd->ctx->bucket_index = bucket_index; err = nh_fill_res_bucket(skb, nh, bucket, bucket_index, RTM_NEWNEXTHOPBUCKET, portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->extack); - if (err < 0) { - if (likely(skb->len)) - goto out; - goto out_err; - } + if (err) + return err; } dd->ctx->done_nh_idx = dd->ctx->nh.idx + 1; - bucket_index = 0; + dd->ctx->bucket_index = 0; -out: - err = skb->len; -out_err: - dd->ctx->bucket_index = bucket_index; - return err; + return 0; } static int rtm_dump_nexthop_bucket_cb(struct sk_buff *skb, @@ -3434,13 +3424,9 @@ static int rtm_dump_nexthop_bucket(struct sk_buff *skb, if (err < 0) { if (likely(skb->len)) - goto out; - goto out_err; + err = skb->len; } -out: - err = skb->len; -out_err: cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 7782ff5e6539..cb381f5aa464 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -348,7 +348,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, goto error; skb_reserve(skb, hlen); - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; skb_dst_set(skb, &rt->dst); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 98d7e6ba7493..92fede388d52 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -518,7 +518,7 @@ static void __build_flow_key(const struct net *net, struct flowi4 *fl4, const struct inet_sock *inet = inet_sk(sk); oif = sk->sk_bound_dev_if; - mark = sk->sk_mark; + mark = READ_ONCE(sk->sk_mark); tos = ip_sock_rt_tos(sk); scope = ip_sock_rt_scope(sk); prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol; @@ -552,7 +552,7 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; - flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, + flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk) & IPTOS_RT_MASK, ip_sock_rt_scope(sk), inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 069642014636..a59cc4b83861 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -931,9 +931,9 @@ static void tcp_v4_send_ack(const struct sock *sk, ctl_sk = this_cpu_read(ipv4_tcp_sk); sock_net_set(ctl_sk, net); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_mark : sk->sk_mark; + inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark); ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_priority : sk->sk_priority; + inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority); transmit_time = tcp_transmit_time(sk); ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 82f4575f9cd9..99ac5efe244d 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -40,7 +40,7 @@ struct tcp_fastopen_metrics { struct tcp_metrics_block { struct tcp_metrics_block __rcu *tcpm_next; - possible_net_t tcpm_net; + struct net *tcpm_net; struct inetpeer_addr tcpm_saddr; struct inetpeer_addr tcpm_daddr; unsigned long tcpm_stamp; @@ -51,34 +51,38 @@ struct tcp_metrics_block { struct rcu_head rcu_head; }; -static inline struct net *tm_net(struct tcp_metrics_block *tm) +static inline struct net *tm_net(const struct tcp_metrics_block *tm) { - return read_pnet(&tm->tcpm_net); + /* Paired with the WRITE_ONCE() in tcpm_new() */ + return READ_ONCE(tm->tcpm_net); } static bool tcp_metric_locked(struct tcp_metrics_block *tm, enum tcp_metric_index idx) { - return tm->tcpm_lock & (1 << idx); + /* Paired with WRITE_ONCE() in tcpm_suck_dst() */ + return READ_ONCE(tm->tcpm_lock) & (1 << idx); } -static u32 tcp_metric_get(struct tcp_metrics_block *tm, +static u32 tcp_metric_get(const struct tcp_metrics_block *tm, enum tcp_metric_index idx) { - return tm->tcpm_vals[idx]; + /* Paired with WRITE_ONCE() in tcp_metric_set() */ + return READ_ONCE(tm->tcpm_vals[idx]); } static void tcp_metric_set(struct tcp_metrics_block *tm, enum tcp_metric_index idx, u32 val) { - tm->tcpm_vals[idx] = val; + /* Paired with READ_ONCE() in tcp_metric_get() */ + WRITE_ONCE(tm->tcpm_vals[idx], val); } static bool addr_same(const struct inetpeer_addr *a, const struct inetpeer_addr *b) { - return inetpeer_addr_cmp(a, b) == 0; + return (a->family == b->family) && !inetpeer_addr_cmp(a, b); } struct tcpm_hash_bucket { @@ -89,6 +93,7 @@ static struct tcpm_hash_bucket *tcp_metrics_hash __read_mostly; static unsigned int tcp_metrics_hash_log __read_mostly; static DEFINE_SPINLOCK(tcp_metrics_lock); +static DEFINE_SEQLOCK(fastopen_seqlock); static void tcpm_suck_dst(struct tcp_metrics_block *tm, const struct dst_entry *dst, @@ -97,7 +102,7 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, u32 msval; u32 val; - tm->tcpm_stamp = jiffies; + WRITE_ONCE(tm->tcpm_stamp, jiffies); val = 0; if (dst_metric_locked(dst, RTAX_RTT)) @@ -110,30 +115,42 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, val |= 1 << TCP_METRIC_CWND; if (dst_metric_locked(dst, RTAX_REORDERING)) val |= 1 << TCP_METRIC_REORDERING; - tm->tcpm_lock = val; + /* Paired with READ_ONCE() in tcp_metric_locked() */ + WRITE_ONCE(tm->tcpm_lock, val); msval = dst_metric_raw(dst, RTAX_RTT); - tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC; + tcp_metric_set(tm, TCP_METRIC_RTT, msval * USEC_PER_MSEC); msval = dst_metric_raw(dst, RTAX_RTTVAR); - tm->tcpm_vals[TCP_METRIC_RTTVAR] = msval * USEC_PER_MSEC; - tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH); - tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND); - tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING); + tcp_metric_set(tm, TCP_METRIC_RTTVAR, msval * USEC_PER_MSEC); + tcp_metric_set(tm, TCP_METRIC_SSTHRESH, + dst_metric_raw(dst, RTAX_SSTHRESH)); + tcp_metric_set(tm, TCP_METRIC_CWND, + dst_metric_raw(dst, RTAX_CWND)); + tcp_metric_set(tm, TCP_METRIC_REORDERING, + dst_metric_raw(dst, RTAX_REORDERING)); if (fastopen_clear) { + write_seqlock(&fastopen_seqlock); tm->tcpm_fastopen.mss = 0; tm->tcpm_fastopen.syn_loss = 0; tm->tcpm_fastopen.try_exp = 0; tm->tcpm_fastopen.cookie.exp = false; tm->tcpm_fastopen.cookie.len = 0; + write_sequnlock(&fastopen_seqlock); } } #define TCP_METRICS_TIMEOUT (60 * 60 * HZ) -static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst) +static void tcpm_check_stamp(struct tcp_metrics_block *tm, + const struct dst_entry *dst) { - if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT))) + unsigned long limit; + + if (!tm) + return; + limit = READ_ONCE(tm->tcpm_stamp) + TCP_METRICS_TIMEOUT; + if (unlikely(time_after(jiffies, limit))) tcpm_suck_dst(tm, dst, false); } @@ -174,20 +191,23 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, oldest = deref_locked(tcp_metrics_hash[hash].chain); for (tm = deref_locked(oldest->tcpm_next); tm; tm = deref_locked(tm->tcpm_next)) { - if (time_before(tm->tcpm_stamp, oldest->tcpm_stamp)) + if (time_before(READ_ONCE(tm->tcpm_stamp), + READ_ONCE(oldest->tcpm_stamp))) oldest = tm; } tm = oldest; } else { - tm = kmalloc(sizeof(*tm), GFP_ATOMIC); + tm = kzalloc(sizeof(*tm), GFP_ATOMIC); if (!tm) goto out_unlock; } - write_pnet(&tm->tcpm_net, net); + /* Paired with the READ_ONCE() in tm_net() */ + WRITE_ONCE(tm->tcpm_net, net); + tm->tcpm_saddr = *saddr; tm->tcpm_daddr = *daddr; - tcpm_suck_dst(tm, dst, true); + tcpm_suck_dst(tm, dst, reclaim); if (likely(!reclaim)) { tm->tcpm_next = tcp_metrics_hash[hash].chain; @@ -434,7 +454,7 @@ void tcp_update_metrics(struct sock *sk) tp->reordering); } } - tm->tcpm_stamp = jiffies; + WRITE_ONCE(tm->tcpm_stamp, jiffies); out_unlock: rcu_read_unlock(); } @@ -539,8 +559,6 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst) return ret; } -static DEFINE_SEQLOCK(fastopen_seqlock); - void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie) { @@ -647,7 +665,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, } if (nla_put_msecs(msg, TCP_METRICS_ATTR_AGE, - jiffies - tm->tcpm_stamp, + jiffies - READ_ONCE(tm->tcpm_stamp), TCP_METRICS_ATTR_PAD) < 0) goto nla_put_failure; @@ -658,7 +676,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, if (!nest) goto nla_put_failure; for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) { - u32 val = tm->tcpm_vals[i]; + u32 val = tcp_metric_get(tm, i); if (!val) continue; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 42a96b3547c9..abfa860367aa 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -114,6 +114,7 @@ #include <net/sock_reuseport.h> #include <net/addrconf.h> #include <net/udp_tunnel.h> +#include <net/gro.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6_stubs.h> #endif @@ -555,10 +556,13 @@ struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, { const struct iphdr *iph = ip_hdr(skb); struct net *net = dev_net(skb->dev); + int iif, sdif; + + inet_get_iif_sdif(skb, &iif, &sdif); return __udp4_lib_lookup(net, iph->saddr, sport, - iph->daddr, dport, inet_iif(skb), - inet_sdif(skb), net->ipv4.udp_table, NULL); + iph->daddr, dport, iif, + sdif, net->ipv4.udp_table, NULL); } /* Must be called under rcu_read_lock(). diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index f402946da344..0f46b3c2e4ac 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -609,10 +609,13 @@ static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport, { const struct iphdr *iph = skb_gro_network_header(skb); struct net *net = dev_net(skb->dev); + int iif, sdif; + + inet_get_iif_sdif(skb, &iif, &sdif); return __udp4_lib_lookup(net, iph->saddr, sport, - iph->daddr, dport, inet_iif(skb), - inet_sdif(skb), net->ipv4.udp_table, NULL); + iph->daddr, dport, iif, + sdif, net->ipv4.udp_table, NULL); } INDIRECT_CALLABLE_SCOPE diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index cc3d5ad17257..67a3b8f6e72b 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1073,7 +1073,7 @@ static int ip6mr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, And all this only to mangle msg->im6_msgtype and to set msg->im6_mbz to "mbz" :-) */ - skb_push(skb, -skb_network_offset(pkt)); + __skb_pull(skb, skb_network_offset(pkt)); skb_push(skb, sizeof(*msg)); skb_reset_transport_header(skb); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 18634ebd20a4..a42be96ae209 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -197,7 +197,8 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, static inline int ndisc_is_useropt(const struct net_device *dev, struct nd_opt_hdr *opt) { - return opt->nd_opt_type == ND_OPT_RDNSS || + return opt->nd_opt_type == ND_OPT_PREFIX_INFO || + opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || opt->nd_opt_type == ND_OPT_PREF64 || diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index f804c11e2146..c2c291827a2c 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -120,7 +120,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipcm6_init_sk(&ipc6, np); ipc6.sockc.tsflags = sk->sk_tsflags; - ipc6.sockc.mark = sk->sk_mark; + ipc6.sockc.mark = READ_ONCE(sk->sk_mark); fl6.flowi6_oif = oif; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ac1cef094c5f..49381f35b623 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -614,7 +614,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IPV6); - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; @@ -774,12 +774,12 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) */ memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_mark = sk->sk_mark; + fl6.flowi6_mark = READ_ONCE(sk->sk_mark); fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); ipc6.sockc.tsflags = sk->sk_tsflags; - ipc6.sockc.mark = sk->sk_mark; + ipc6.sockc.mark = fl6.flowi6_mark; if (sin6) { if (addr_len < SIN6_LEN_RFC2133) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 64e873f5895f..56a55585eb79 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2951,7 +2951,8 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) if (!oif && skb->dev) oif = l3mdev_master_ifindex(skb->dev); - ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark, sk->sk_uid); + ip6_update_pmtu(skb, sock_net(sk), mtu, oif, READ_ONCE(sk->sk_mark), + sk->sk_uid); dst = __sk_dst_get(sk); if (!dst || !dst->obsolete || @@ -3172,8 +3173,8 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif) void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) { - ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark, - sk->sk_uid); + ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, + READ_ONCE(sk->sk_mark), sk->sk_uid); } EXPORT_SYMBOL_GPL(ip6_sk_redirect); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4714eb695913..6e86721e1cdb 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -564,8 +564,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt, - tclass, sk->sk_priority); + err = ip6_xmit(sk, skb, fl6, skb->mark ? : READ_ONCE(sk->sk_mark), + opt, tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -939,7 +939,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 if (sk->sk_state == TCP_TIME_WAIT) mark = inet_twsk(sk)->tw_mark; else - mark = sk->sk_mark; + mark = READ_ONCE(sk->sk_mark); skb_set_delivery_time(buff, tcp_transmit_time(sk), true); } if (txhash) { @@ -1128,7 +1128,8 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), - ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority, + ipv6_get_dsfield(ipv6_hdr(skb)), 0, + READ_ONCE(sk->sk_priority), READ_ONCE(tcp_rsk(req)->txhash)); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index b7c972aa09a7..f787e6b8424c 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -51,6 +51,7 @@ #include <net/inet6_hashtables.h> #include <net/busy_poll.h> #include <net/sock_reuseport.h> +#include <net/gro.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -300,10 +301,13 @@ struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, { const struct ipv6hdr *iph = ipv6_hdr(skb); struct net *net = dev_net(skb->dev); + int iif, sdif; + + inet6_get_iif_sdif(skb, &iif, &sdif); return __udp6_lib_lookup(net, &iph->saddr, sport, - &iph->daddr, dport, inet6_iif(skb), - inet6_sdif(skb), net->ipv4.udp_table, NULL); + &iph->daddr, dport, iif, + sdif, net->ipv4.udp_table, NULL); } /* Must be called under rcu_read_lock(). @@ -624,7 +628,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type == NDISC_REDIRECT) { if (tunnel) { ip6_redirect(skb, sock_net(sk), inet6_iif(skb), - sk->sk_mark, sk->sk_uid); + READ_ONCE(sk->sk_mark), sk->sk_uid); } else { ip6_sk_redirect(skb, sk); } @@ -1356,7 +1360,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipcm6_init(&ipc6); ipc6.gso_size = READ_ONCE(up->gso_size); ipc6.sockc.tsflags = sk->sk_tsflags; - ipc6.sockc.mark = sk->sk_mark; + ipc6.sockc.mark = READ_ONCE(sk->sk_mark); /* destination address check */ if (sin6) { diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 09fa7a42cb93..6b95ba241ebe 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -118,10 +118,13 @@ static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport, { const struct ipv6hdr *iph = skb_gro_network_header(skb); struct net *net = dev_net(skb->dev); + int iif, sdif; + + inet6_get_iif_sdif(skb, &iif, &sdif); return __udp6_lib_lookup(net, &iph->saddr, sport, - &iph->daddr, dport, inet6_iif(skb), - inet6_sdif(skb), net->ipv4.udp_table, NULL); + &iph->daddr, dport, iif, + sdif, net->ipv4.udp_table, NULL); } INDIRECT_CALLABLE_SCOPE diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index b1623f9c4f92..ff78217f0cb1 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -519,7 +519,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) /* Get and verify the address */ memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_mark = sk->sk_mark; + fl6.flowi6_mark = READ_ONCE(sk->sk_mark); fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 3317d1cca156..d80658547836 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2335,7 +2335,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); - if (flags & MPTCP_CF_FASTCLOSE) { + if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { /* be sure to force the tcp_disconnect() path, * to generate the egress reset */ @@ -3328,7 +3328,7 @@ static void mptcp_release_cb(struct sock *sk) if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags)) __mptcp_clean_una_wakeup(sk); - if (unlikely(&msk->cb_flags)) { + if (unlikely(msk->cb_flags)) { /* be sure to set the current sk state before tacking actions * depending on sk_state, that is processing MPTCP_ERROR_REPORT */ diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 37fbe22e2433..ba2a873a4d2e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -325,7 +325,6 @@ struct mptcp_sock { u32 subflow_id; u32 setsockopt_seq; char ca_name[TCP_CA_NAME_MAX]; - struct mptcp_sock *dl_next; }; #define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 63f7a09335c5..a3f1fe810cc9 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -103,7 +103,7 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, in break; case SO_MARK: if (READ_ONCE(ssk->sk_mark) != sk->sk_mark) { - ssk->sk_mark = sk->sk_mark; + WRITE_ONCE(ssk->sk_mark, sk->sk_mark); sk_dst_reset(ssk); } break; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 9ee3b7abbaf6..94ae7dd01c65 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1793,16 +1793,31 @@ static void subflow_state_change(struct sock *sk) void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) { struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; - struct mptcp_sock *msk, *next, *head = NULL; - struct request_sock *req; - struct sock *sk; + struct request_sock *req, *head, *tail; + struct mptcp_subflow_context *subflow; + struct sock *sk, *ssk; - /* build a list of all unaccepted mptcp sockets */ + /* Due to lock dependencies no relevant lock can be acquired under rskq_lock. + * Splice the req list, so that accept() can not reach the pending ssk after + * the listener socket is released below. + */ spin_lock_bh(&queue->rskq_lock); - for (req = queue->rskq_accept_head; req; req = req->dl_next) { - struct mptcp_subflow_context *subflow; - struct sock *ssk = req->sk; + head = queue->rskq_accept_head; + tail = queue->rskq_accept_tail; + queue->rskq_accept_head = NULL; + queue->rskq_accept_tail = NULL; + spin_unlock_bh(&queue->rskq_lock); + + if (!head) + return; + /* can't acquire the msk socket lock under the subflow one, + * or will cause ABBA deadlock + */ + release_sock(listener_ssk); + + for (req = head; req; req = req->dl_next) { + ssk = req->sk; if (!sk_is_mptcp(ssk)) continue; @@ -1810,32 +1825,10 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s if (!subflow || !subflow->conn) continue; - /* skip if already in list */ sk = subflow->conn; - msk = mptcp_sk(sk); - if (msk->dl_next || msk == head) - continue; - sock_hold(sk); - msk->dl_next = head; - head = msk; - } - spin_unlock_bh(&queue->rskq_lock); - if (!head) - return; - - /* can't acquire the msk socket lock under the subflow one, - * or will cause ABBA deadlock - */ - release_sock(listener_ssk); - - for (msk = head; msk; msk = next) { - sk = (struct sock *)msk; lock_sock_nested(sk, SINGLE_DEPTH_NESTING); - next = msk->dl_next; - msk->dl_next = NULL; - __mptcp_unaccepted_force_close(sk); release_sock(sk); @@ -1859,6 +1852,13 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s /* we are still under the listener msk socket lock */ lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING); + + /* restore the listener queue, to let the TCP code clean it up */ + spin_lock_bh(&queue->rskq_lock); + WARN_ON_ONCE(queue->rskq_accept_head); + queue->rskq_accept_head = head; + queue->rskq_accept_tail = tail; + spin_unlock_bh(&queue->rskq_lock); } static int subflow_ulp_init(struct sock *sk) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d3c6ecd1f5a6..c62227ae7746 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -31,7 +31,9 @@ static LIST_HEAD(nf_tables_expressions); static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); static LIST_HEAD(nf_tables_destroy_list); +static LIST_HEAD(nf_tables_gc_list); static DEFINE_SPINLOCK(nf_tables_destroy_list_lock); +static DEFINE_SPINLOCK(nf_tables_gc_list_lock); enum { NFT_VALIDATE_SKIP = 0, @@ -120,6 +122,9 @@ static void nft_validate_state_update(struct nft_table *table, u8 new_validate_s static void nf_tables_trans_destroy_work(struct work_struct *w); static DECLARE_WORK(trans_destroy_work, nf_tables_trans_destroy_work); +static void nft_trans_gc_work(struct work_struct *work); +static DECLARE_WORK(trans_gc_work, nft_trans_gc_work); + static void nft_ctx_init(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, @@ -582,10 +587,6 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, return __nft_trans_set_add(ctx, msg_type, set, NULL); } -static void nft_setelem_data_deactivate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem); - static int nft_mapelem_deactivate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, @@ -5055,6 +5056,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, INIT_LIST_HEAD(&set->bindings); INIT_LIST_HEAD(&set->catchall_list); + refcount_set(&set->refs, 1); set->table = table; write_pnet(&set->net, net); set->ops = ops; @@ -5122,6 +5124,14 @@ static void nft_set_catchall_destroy(const struct nft_ctx *ctx, } } +static void nft_set_put(struct nft_set *set) +{ + if (refcount_dec_and_test(&set->refs)) { + kfree(set->name); + kvfree(set); + } +} + static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) { int i; @@ -5134,8 +5144,7 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) set->ops->destroy(ctx, set); nft_set_catchall_destroy(ctx, set); - kfree(set->name); - kvfree(set); + nft_set_put(set); } static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, @@ -5602,8 +5611,12 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_set_elem *elem) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); struct nft_set_dump_args *args; + if (nft_set_elem_expired(ext)) + return 0; + args = container_of(iter, struct nft_set_dump_args, iter); return nf_tables_fill_setelem(args->skb, set, elem, args->reset); } @@ -6274,7 +6287,8 @@ struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (nft_set_elem_active(ext, genmask) && - !nft_set_elem_expired(ext)) + !nft_set_elem_expired(ext) && + !nft_set_elem_is_dead(ext)) return ext; } @@ -6282,29 +6296,6 @@ struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, } EXPORT_SYMBOL_GPL(nft_set_catchall_lookup); -void *nft_set_catchall_gc(const struct nft_set *set) -{ - struct nft_set_elem_catchall *catchall, *next; - struct nft_set_ext *ext; - void *elem = NULL; - - list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { - ext = nft_set_elem_ext(set, catchall->elem); - - if (!nft_set_elem_expired(ext) || - nft_set_elem_mark_busy(ext)) - continue; - - elem = catchall->elem; - list_del_rcu(&catchall->list); - kfree_rcu(catchall, rcu); - break; - } - - return elem; -} -EXPORT_SYMBOL_GPL(nft_set_catchall_gc); - static int nft_setelem_catchall_insert(const struct net *net, struct nft_set *set, const struct nft_set_elem *elem, @@ -6366,7 +6357,6 @@ static void nft_setelem_activate(struct net *net, struct nft_set *set, if (nft_setelem_is_catchall(set, elem)) { nft_set_elem_change_active(net, set, ext); - nft_set_elem_clear_busy(ext); } else { set->ops->activate(net, set, elem); } @@ -6381,8 +6371,7 @@ static int nft_setelem_catchall_deactivate(const struct net *net, list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_is_active(net, ext) || - nft_set_elem_mark_busy(ext)) + if (!nft_is_active(net, ext)) continue; kfree(elem->priv); @@ -6777,7 +6766,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, goto err_elem_free; } - ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK; + ext->genmask = nft_genmask_cur(ctx->net); err = nft_setelem_insert(ctx->net, set, &elem, &ext2, flags); if (err) { @@ -6929,9 +6918,9 @@ static void nft_setelem_data_activate(const struct net *net, nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use); } -static void nft_setelem_data_deactivate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem) +void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -7095,8 +7084,7 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_active(ext, genmask) || - nft_set_elem_mark_busy(ext)) + if (!nft_set_elem_active(ext, genmask)) continue; elem.priv = catchall->elem; @@ -7170,29 +7158,6 @@ static int nf_tables_delsetelem(struct sk_buff *skb, return err; } -void nft_set_gc_batch_release(struct rcu_head *rcu) -{ - struct nft_set_gc_batch *gcb; - unsigned int i; - - gcb = container_of(rcu, struct nft_set_gc_batch, head.rcu); - for (i = 0; i < gcb->head.cnt; i++) - nft_set_elem_destroy(gcb->head.set, gcb->elems[i], true); - kfree(gcb); -} - -struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set, - gfp_t gfp) -{ - struct nft_set_gc_batch *gcb; - - gcb = kzalloc(sizeof(*gcb), gfp); - if (gcb == NULL) - return gcb; - gcb->head.set = set; - return gcb; -} - /* * Stateful objects */ @@ -9414,6 +9379,207 @@ void nft_chain_del(struct nft_chain *chain) list_del_rcu(&chain->list); } +static void nft_trans_gc_setelem_remove(struct nft_ctx *ctx, + struct nft_trans_gc *trans) +{ + void **priv = trans->priv; + unsigned int i; + + for (i = 0; i < trans->count; i++) { + struct nft_set_elem elem = { + .priv = priv[i], + }; + + nft_setelem_data_deactivate(ctx->net, trans->set, &elem); + nft_setelem_remove(ctx->net, trans->set, &elem); + } +} + +void nft_trans_gc_destroy(struct nft_trans_gc *trans) +{ + nft_set_put(trans->set); + put_net(trans->net); + kfree(trans); +} + +static void nft_trans_gc_trans_free(struct rcu_head *rcu) +{ + struct nft_set_elem elem = {}; + struct nft_trans_gc *trans; + struct nft_ctx ctx = {}; + unsigned int i; + + trans = container_of(rcu, struct nft_trans_gc, rcu); + ctx.net = read_pnet(&trans->set->net); + + for (i = 0; i < trans->count; i++) { + elem.priv = trans->priv[i]; + if (!nft_setelem_is_catchall(trans->set, &elem)) + atomic_dec(&trans->set->nelems); + + nf_tables_set_elem_destroy(&ctx, trans->set, elem.priv); + } + + nft_trans_gc_destroy(trans); +} + +static bool nft_trans_gc_work_done(struct nft_trans_gc *trans) +{ + struct nftables_pernet *nft_net; + struct nft_ctx ctx = {}; + + nft_net = nft_pernet(trans->net); + + mutex_lock(&nft_net->commit_mutex); + + /* Check for race with transaction, otherwise this batch refers to + * stale objects that might not be there anymore. Skip transaction if + * set has been destroyed from control plane transaction in case gc + * worker loses race. + */ + if (READ_ONCE(nft_net->gc_seq) != trans->seq || trans->set->dead) { + mutex_unlock(&nft_net->commit_mutex); + return false; + } + + ctx.net = trans->net; + ctx.table = trans->set->table; + + nft_trans_gc_setelem_remove(&ctx, trans); + mutex_unlock(&nft_net->commit_mutex); + + return true; +} + +static void nft_trans_gc_work(struct work_struct *work) +{ + struct nft_trans_gc *trans, *next; + LIST_HEAD(trans_gc_list); + + spin_lock(&nf_tables_destroy_list_lock); + list_splice_init(&nf_tables_gc_list, &trans_gc_list); + spin_unlock(&nf_tables_destroy_list_lock); + + list_for_each_entry_safe(trans, next, &trans_gc_list, list) { + list_del(&trans->list); + if (!nft_trans_gc_work_done(trans)) { + nft_trans_gc_destroy(trans); + continue; + } + call_rcu(&trans->rcu, nft_trans_gc_trans_free); + } +} + +struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, + unsigned int gc_seq, gfp_t gfp) +{ + struct net *net = read_pnet(&set->net); + struct nft_trans_gc *trans; + + trans = kzalloc(sizeof(*trans), gfp); + if (!trans) + return NULL; + + refcount_inc(&set->refs); + trans->set = set; + trans->net = get_net(net); + trans->seq = gc_seq; + + return trans; +} + +void nft_trans_gc_elem_add(struct nft_trans_gc *trans, void *priv) +{ + trans->priv[trans->count++] = priv; +} + +static void nft_trans_gc_queue_work(struct nft_trans_gc *trans) +{ + spin_lock(&nf_tables_gc_list_lock); + list_add_tail(&trans->list, &nf_tables_gc_list); + spin_unlock(&nf_tables_gc_list_lock); + + schedule_work(&trans_gc_work); +} + +static int nft_trans_gc_space(struct nft_trans_gc *trans) +{ + return NFT_TRANS_GC_BATCHCOUNT - trans->count; +} + +struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, + unsigned int gc_seq, gfp_t gfp) +{ + if (nft_trans_gc_space(gc)) + return gc; + + nft_trans_gc_queue_work(gc); + + return nft_trans_gc_alloc(gc->set, gc_seq, gfp); +} + +void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans) +{ + if (trans->count == 0) { + nft_trans_gc_destroy(trans); + return; + } + + nft_trans_gc_queue_work(trans); +} + +struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp) +{ + if (WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net))) + return NULL; + + if (nft_trans_gc_space(gc)) + return gc; + + call_rcu(&gc->rcu, nft_trans_gc_trans_free); + + return nft_trans_gc_alloc(gc->set, 0, gfp); +} + +void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) +{ + WARN_ON_ONCE(!lockdep_commit_lock_is_held(trans->net)); + + if (trans->count == 0) { + nft_trans_gc_destroy(trans); + return; + } + + call_rcu(&trans->rcu, nft_trans_gc_trans_free); +} + +struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, + unsigned int gc_seq) +{ + struct nft_set_elem_catchall *catchall; + const struct nft_set *set = gc->set; + struct nft_set_ext *ext; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + + if (!nft_set_elem_expired(ext)) + continue; + if (nft_set_elem_is_dead(ext)) + goto dead_elem; + + nft_set_elem_dead(ext); +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + return NULL; + + nft_trans_gc_elem_add(gc, catchall->elem); + } + + return gc; +} + static void nf_tables_module_autoload_cleanup(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); @@ -9576,11 +9742,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; + unsigned int base_seq, gc_seq; LIST_HEAD(set_update_list); struct nft_trans_elem *te; struct nft_chain *chain; struct nft_table *table; - unsigned int base_seq; LIST_HEAD(adl); int err; @@ -9657,6 +9823,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) WRITE_ONCE(nft_net->base_seq, base_seq); + /* Bump gc counter, it becomes odd, this is the busy mark. */ + gc_seq = READ_ONCE(nft_net->gc_seq); + WRITE_ONCE(nft_net->gc_seq, ++gc_seq); + /* step 3. Start new generation, rules_gen_X now in use. */ net->nft.gencursor = nft_gencursor_next(net); @@ -9764,6 +9934,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) break; case NFT_MSG_DELSET: case NFT_MSG_DESTROYSET: + nft_trans_set(trans)->dead = 1; list_del_rcu(&nft_trans_set(trans)->list); nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), trans->msg_type, GFP_KERNEL); @@ -9866,6 +10037,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); nf_tables_commit_audit_log(&adl, nft_net->base_seq); + + WRITE_ONCE(nft_net->gc_seq, ++gc_seq); nf_tables_commit_release(net); return 0; @@ -10915,6 +11088,7 @@ static int __net_init nf_tables_init_net(struct net *net) INIT_LIST_HEAD(&nft_net->notify_list); mutex_init(&nft_net->commit_mutex); nft_net->base_seq = 1; + nft_net->gc_seq = 0; return 0; } @@ -10943,10 +11117,16 @@ static void __net_exit nf_tables_exit_net(struct net *net) WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); } +static void nf_tables_exit_batch(struct list_head *net_exit_list) +{ + flush_work(&trans_gc_work); +} + static struct pernet_operations nf_tables_net_ops = { .init = nf_tables_init_net, .pre_exit = nf_tables_pre_exit_net, .exit = nf_tables_exit_net, + .exit_batch = nf_tables_exit_batch, .id = &nf_tables_net_id, .size = sizeof(struct nftables_pernet), }; @@ -11018,6 +11198,7 @@ static void __exit nf_tables_module_exit(void) nft_chain_filter_fini(); nft_chain_route_fini(); unregister_pernet_subsys(&nf_tables_net_ops); + cancel_work_sync(&trans_gc_work); cancel_work_sync(&trans_destroy_work); rcu_barrier(); rhltable_destroy(&nft_objname_ht); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 0b73cb0e752f..cef5df846000 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -59,6 +59,8 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg, if (memcmp(nft_set_ext_key(&he->ext), x->key, x->set->klen)) return 1; + if (nft_set_elem_is_dead(&he->ext)) + return 1; if (nft_set_elem_expired(&he->ext)) return 1; if (!nft_set_elem_active(&he->ext, x->genmask)) @@ -188,7 +190,6 @@ static void nft_rhash_activate(const struct net *net, const struct nft_set *set, struct nft_rhash_elem *he = elem->priv; nft_set_elem_change_active(net, set, &he->ext); - nft_set_elem_clear_busy(&he->ext); } static bool nft_rhash_flush(const struct net *net, @@ -196,12 +197,9 @@ static bool nft_rhash_flush(const struct net *net, { struct nft_rhash_elem *he = priv; - if (!nft_set_elem_mark_busy(&he->ext) || - !nft_is_active(net, &he->ext)) { - nft_set_elem_change_active(net, set, &he->ext); - return true; - } - return false; + nft_set_elem_change_active(net, set, &he->ext); + + return true; } static void *nft_rhash_deactivate(const struct net *net, @@ -218,9 +216,8 @@ static void *nft_rhash_deactivate(const struct net *net, rcu_read_lock(); he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); - if (he != NULL && - !nft_rhash_flush(net, set, he)) - he = NULL; + if (he) + nft_set_elem_change_active(net, set, &he->ext); rcu_read_unlock(); @@ -252,7 +249,9 @@ static bool nft_rhash_delete(const struct nft_set *set, if (he == NULL) return false; - return rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params) == 0; + nft_set_elem_dead(&he->ext); + + return true; } static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, @@ -278,8 +277,6 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, if (iter->count < iter->skip) goto cont; - if (nft_set_elem_expired(&he->ext)) - goto cont; if (!nft_set_elem_active(&he->ext, iter->genmask)) goto cont; @@ -314,25 +311,48 @@ static bool nft_rhash_expr_needs_gc_run(const struct nft_set *set, static void nft_rhash_gc(struct work_struct *work) { + struct nftables_pernet *nft_net; struct nft_set *set; struct nft_rhash_elem *he; struct nft_rhash *priv; - struct nft_set_gc_batch *gcb = NULL; struct rhashtable_iter hti; + struct nft_trans_gc *gc; + struct net *net; + u32 gc_seq; priv = container_of(work, struct nft_rhash, gc_work.work); set = nft_set_container_of(priv); + net = read_pnet(&set->net); + nft_net = nft_pernet(net); + gc_seq = READ_ONCE(nft_net->gc_seq); + + gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL); + if (!gc) + goto done; rhashtable_walk_enter(&priv->ht, &hti); rhashtable_walk_start(&hti); while ((he = rhashtable_walk_next(&hti))) { if (IS_ERR(he)) { - if (PTR_ERR(he) != -EAGAIN) - break; + if (PTR_ERR(he) != -EAGAIN) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } continue; } + /* Ruleset has been updated, try later. */ + if (READ_ONCE(nft_net->gc_seq) != gc_seq) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } + + if (nft_set_elem_is_dead(&he->ext)) + goto dead_elem; + if (nft_set_ext_exists(&he->ext, NFT_SET_EXT_EXPRESSIONS) && nft_rhash_expr_needs_gc_run(set, &he->ext)) goto needs_gc_run; @@ -340,26 +360,26 @@ static void nft_rhash_gc(struct work_struct *work) if (!nft_set_elem_expired(&he->ext)) continue; needs_gc_run: - if (nft_set_elem_mark_busy(&he->ext)) - continue; + nft_set_elem_dead(&he->ext); +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (gcb == NULL) - break; - rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, he); + nft_trans_gc_elem_add(gc, he); } + + gc = nft_trans_gc_catchall(gc, gc_seq); + +try_later: + /* catchall list iteration requires rcu read side lock. */ rhashtable_walk_stop(&hti); rhashtable_walk_exit(&hti); - he = nft_set_catchall_gc(set); - if (he) { - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (gcb) - nft_set_gc_batch_add(gcb, he); - } - nft_set_gc_batch_complete(gcb); + if (gc) + nft_trans_gc_queue_async_done(gc); + +done: queue_delayed_work(system_power_efficient_wq, &priv->gc_work, nft_set_gc_interval(set)); } @@ -394,7 +414,7 @@ static int nft_rhash_init(const struct nft_set *set, return err; INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rhash_gc); - if (set->flags & NFT_SET_TIMEOUT) + if (set->flags & (NFT_SET_TIMEOUT | NFT_SET_EVAL)) nft_rhash_gc_init(set); return 0; @@ -422,7 +442,6 @@ static void nft_rhash_destroy(const struct nft_ctx *ctx, }; cancel_delayed_work_sync(&priv->gc_work); - rcu_barrier(); rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, (void *)&rhash_ctx); } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 49915a2a58eb..a5b8301afe4a 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -566,8 +566,7 @@ next_match: goto out; if (last) { - if (nft_set_elem_expired(&f->mt[b].e->ext) || - (genmask && + if ((genmask && !nft_set_elem_active(&f->mt[b].e->ext, genmask))) goto next_match; @@ -601,8 +600,17 @@ out: static void *nft_pipapo_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { - return pipapo_get(net, set, (const u8 *)elem->key.val.data, - nft_genmask_cur(net)); + struct nft_pipapo_elem *ret; + + ret = pipapo_get(net, set, (const u8 *)elem->key.val.data, + nft_genmask_cur(net)); + if (IS_ERR(ret)) + return ret; + + if (nft_set_elem_expired(&ret->ext)) + return ERR_PTR(-ENOENT); + + return ret; } /** @@ -1528,16 +1536,34 @@ static void pipapo_drop(struct nft_pipapo_match *m, } } +static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set, + struct nft_pipapo_elem *e) + +{ + struct nft_set_elem elem = { + .priv = e, + }; + + nft_setelem_data_deactivate(net, set, &elem); +} + /** * pipapo_gc() - Drop expired entries from set, destroy start and end elements * @set: nftables API set representation * @m: Matching data */ -static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) +static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) { + struct nft_set *set = (struct nft_set *) _set; struct nft_pipapo *priv = nft_set_priv(set); + struct net *net = read_pnet(&set->net); int rules_f0, first_rule = 0; struct nft_pipapo_elem *e; + struct nft_trans_gc *gc; + + gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); + if (!gc) + return; while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; @@ -1561,13 +1587,20 @@ static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) f--; i--; e = f->mt[rulemap[i].to].e; - if (nft_set_elem_expired(&e->ext) && - !nft_set_elem_mark_busy(&e->ext)) { + + /* synchronous gc never fails, there is no need to set on + * NFT_SET_ELEM_DEAD_BIT. + */ + if (nft_set_elem_expired(&e->ext)) { priv->dirty = true; - pipapo_drop(m, rulemap); - rcu_barrier(); - nft_set_elem_destroy(set, e, true); + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (!gc) + break; + + nft_pipapo_gc_deactivate(net, set, e); + pipapo_drop(m, rulemap); + nft_trans_gc_elem_add(gc, e); /* And check again current first rule, which is now the * first we haven't checked. @@ -1577,11 +1610,11 @@ static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) } } - e = nft_set_catchall_gc(set); - if (e) - nft_set_elem_destroy(set, e, true); - - priv->last_gc = jiffies; + gc = nft_trans_gc_catchall(gc, 0); + if (gc) { + nft_trans_gc_queue_sync_done(gc); + priv->last_gc = jiffies; + } } /** @@ -1706,7 +1739,6 @@ static void nft_pipapo_activate(const struct net *net, return; nft_set_elem_change_active(net, set, &e->ext); - nft_set_elem_clear_busy(&e->ext); } /** @@ -2005,8 +2037,6 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, goto cont; e = f->mt[r].e; - if (nft_set_elem_expired(&e->ext)) - goto cont; elem.priv = e; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 8d73fffd2d09..f9d4c8fcbbf8 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -46,6 +46,12 @@ static int nft_rbtree_cmp(const struct nft_set *set, set->klen); } +static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe) +{ + return nft_set_elem_expired(&rbe->ext) || + nft_set_elem_is_dead(&rbe->ext); +} + static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext, unsigned int seq) @@ -80,7 +86,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set continue; } - if (nft_set_elem_expired(&rbe->ext)) + if (nft_rbtree_elem_expired(rbe)) return false; if (nft_rbtree_interval_end(rbe)) { @@ -98,7 +104,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && - !nft_set_elem_expired(&interval->ext) && + !nft_rbtree_elem_expired(interval) && nft_rbtree_interval_start(interval)) { *ext = &interval->ext; return true; @@ -215,6 +221,18 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set, return rbe; } +static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) +{ + struct nft_set_elem elem = { + .priv = rbe, + }; + + nft_setelem_data_deactivate(net, set, &elem); + rb_erase(&rbe->node, &priv->root); +} + static int nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, struct nft_rbtree_elem *rbe, @@ -222,11 +240,12 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); + struct net *net = read_pnet(&set->net); struct nft_rbtree_elem *rbe_prev; - struct nft_set_gc_batch *gcb; + struct nft_trans_gc *gc; - gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); - if (!gcb) + gc = nft_trans_gc_alloc(set, 0, GFP_ATOMIC); + if (!gc) return -ENOMEM; /* search for end interval coming before this element. @@ -244,17 +263,28 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, if (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); + nft_rbtree_gc_remove(net, set, priv, rbe_prev); - rb_erase(&rbe_prev->node, &priv->root); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe_prev); + /* There is always room in this trans gc for this element, + * memory allocation never actually happens, hence, the warning + * splat in such case. No need to set NFT_SET_ELEM_DEAD_BIT, + * this is synchronous gc which never fails. + */ + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (WARN_ON_ONCE(!gc)) + return -ENOMEM; + + nft_trans_gc_elem_add(gc, rbe_prev); } - rb_erase(&rbe->node, &priv->root); - atomic_dec(&set->nelems); + nft_rbtree_gc_remove(net, set, priv, rbe); + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (WARN_ON_ONCE(!gc)) + return -ENOMEM; + + nft_trans_gc_elem_add(gc, rbe); - nft_set_gc_batch_add(gcb, rbe); - nft_set_gc_batch_complete(gcb); + nft_trans_gc_queue_sync_done(gc); return 0; } @@ -482,7 +512,6 @@ static void nft_rbtree_activate(const struct net *net, struct nft_rbtree_elem *rbe = elem->priv; nft_set_elem_change_active(net, set, &rbe->ext); - nft_set_elem_clear_busy(&rbe->ext); } static bool nft_rbtree_flush(const struct net *net, @@ -490,12 +519,9 @@ static bool nft_rbtree_flush(const struct net *net, { struct nft_rbtree_elem *rbe = priv; - if (!nft_set_elem_mark_busy(&rbe->ext) || - !nft_is_active(net, &rbe->ext)) { - nft_set_elem_change_active(net, set, &rbe->ext); - return true; - } - return false; + nft_set_elem_change_active(net, set, &rbe->ext); + + return true; } static void *nft_rbtree_deactivate(const struct net *net, @@ -552,8 +578,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, if (iter->count < iter->skip) goto cont; - if (nft_set_elem_expired(&rbe->ext)) - goto cont; if (!nft_set_elem_active(&rbe->ext, iter->genmask)) goto cont; @@ -572,26 +596,40 @@ cont: static void nft_rbtree_gc(struct work_struct *work) { - struct nft_rbtree_elem *rbe, *rbe_end = NULL, *rbe_prev = NULL; - struct nft_set_gc_batch *gcb = NULL; + struct nft_rbtree_elem *rbe, *rbe_end = NULL; + struct nftables_pernet *nft_net; struct nft_rbtree *priv; + struct nft_trans_gc *gc; struct rb_node *node; struct nft_set *set; + unsigned int gc_seq; struct net *net; - u8 genmask; priv = container_of(work, struct nft_rbtree, gc_work.work); set = nft_set_container_of(priv); net = read_pnet(&set->net); - genmask = nft_genmask_cur(net); + nft_net = nft_pernet(net); + gc_seq = READ_ONCE(nft_net->gc_seq); + + gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL); + if (!gc) + goto done; write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { + + /* Ruleset has been updated, try later. */ + if (READ_ONCE(nft_net->gc_seq) != gc_seq) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } + rbe = rb_entry(node, struct nft_rbtree_elem, node); - if (!nft_set_elem_active(&rbe->ext, genmask)) - continue; + if (nft_set_elem_is_dead(&rbe->ext)) + goto dead_elem; /* elements are reversed in the rbtree for historical reasons, * from highest to lowest value, that is why end element is @@ -604,46 +642,36 @@ static void nft_rbtree_gc(struct work_struct *work) if (!nft_set_elem_expired(&rbe->ext)) continue; - if (nft_set_elem_mark_busy(&rbe->ext)) { - rbe_end = NULL; + nft_set_elem_dead(&rbe->ext); + + if (!rbe_end) continue; - } - if (rbe_prev) { - rb_erase(&rbe_prev->node, &priv->root); - rbe_prev = NULL; - } - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (!gcb) - break; + nft_set_elem_dead(&rbe_end->ext); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe); - rbe_prev = rbe; + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; - if (rbe_end) { - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe_end); - rb_erase(&rbe_end->node, &priv->root); - rbe_end = NULL; - } - node = rb_next(node); - if (!node) - break; + nft_trans_gc_elem_add(gc, rbe_end); + rbe_end = NULL; +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; + + nft_trans_gc_elem_add(gc, rbe); } - if (rbe_prev) - rb_erase(&rbe_prev->node, &priv->root); + + gc = nft_trans_gc_catchall(gc, gc_seq); + +try_later: write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); - rbe = nft_set_catchall_gc(set); - if (rbe) { - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (gcb) - nft_set_gc_batch_add(gcb, rbe); - } - nft_set_gc_batch_complete(gcb); - + if (gc) + nft_trans_gc_queue_async_done(gc); +done: queue_delayed_work(system_power_efficient_wq, &priv->gc_work, nft_set_gc_interval(set)); } diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 84def74698b7..9ed85be79452 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -107,7 +107,7 @@ static void nft_socket_eval(const struct nft_expr *expr, break; case NFT_SOCKET_MARK: if (sk_fullsock(sk)) { - *dest = sk->sk_mark; + *dest = READ_ONCE(sk->sk_mark); } else { regs->verdict.code = NFT_BREAK; return; diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 7013f55f05d1..76e01f292aaf 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -77,7 +77,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) - pskb->mark = sk->sk_mark; + pskb->mark = READ_ONCE(sk->sk_mark); if (sk != skb->sk) sock_gen_put(sk); @@ -138,7 +138,7 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) - pskb->mark = sk->sk_mark; + pskb->mark = READ_ONCE(sk->sk_mark); if (sk != skb->sk) sock_gen_put(sk); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 8e3ddec4c3d5..a2935bd18ed9 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -401,18 +401,20 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union tpacket_uhdr h; + /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: - h.h1->tp_status = status; + WRITE_ONCE(h.h1->tp_status, status); flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: - h.h2->tp_status = status; + WRITE_ONCE(h.h2->tp_status, status); flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: - h.h3->tp_status = status; + WRITE_ONCE(h.h3->tp_status, status); flush_dcache_page(pgv_to_page(&h.h3->tp_status)); break; default: @@ -429,17 +431,19 @@ static int __packet_get_status(const struct packet_sock *po, void *frame) smp_rmb(); + /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); - return h.h1->tp_status; + return READ_ONCE(h.h1->tp_status); case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); - return h.h2->tp_status; + return READ_ONCE(h.h2->tp_status); case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); - return h.h3->tp_status; + return READ_ONCE(h.h3->tp_status); default: WARN(1, "TPACKET version not supported.\n"); BUG(); @@ -2050,8 +2054,8 @@ retry: skb->protocol = proto; skb->dev = dev; - skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + skb->priority = READ_ONCE(sk->sk_priority); + skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; skb_setup_tx_timestamp(skb, sockc.tsflags); @@ -2585,8 +2589,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->protocol = proto; skb->dev = dev; - skb->priority = po->sk.sk_priority; - skb->mark = po->sk.sk_mark; + skb->priority = READ_ONCE(po->sk.sk_priority); + skb->mark = READ_ONCE(po->sk.sk_mark); skb->tstamp = sockc->transmit_time; skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); @@ -2988,7 +2992,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_unlock; sockcm_init(&sockc, sk); - sockc.mark = sk->sk_mark; + sockc.mark = READ_ONCE(sk->sk_mark); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) @@ -3061,7 +3065,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->protocol = proto; skb->dev = dev; - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc.mark; skb->tstamp = sockc.transmit_time; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 8da9d039d964..9f0711da9c95 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -776,7 +776,8 @@ mpls_stack_entry_policy[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1] = { [TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL] = { .type = NLA_U32 }, }; -static const struct nla_policy cfm_opt_policy[TCA_FLOWER_KEY_CFM_OPT_MAX] = { +static const struct nla_policy +cfm_opt_policy[TCA_FLOWER_KEY_CFM_OPT_MAX + 1] = { [TCA_FLOWER_KEY_CFM_MD_LEVEL] = NLA_POLICY_MAX(NLA_U8, FLOW_DIS_CFM_MDL_MAX), [TCA_FLOWER_KEY_CFM_OPCODE] = { .type = NLA_U8 }, @@ -1709,7 +1710,7 @@ static int fl_set_key_cfm(struct nlattr **tb, struct fl_flow_key *mask, struct netlink_ext_ack *extack) { - struct nlattr *nla_cfm_opt[TCA_FLOWER_KEY_CFM_OPT_MAX]; + struct nlattr *nla_cfm_opt[TCA_FLOWER_KEY_CFM_OPT_MAX + 1]; int err; if (!tb[TCA_FLOWER_KEY_CFM]) diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 8641f8059317..c49d6af0e048 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -267,7 +267,6 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, return -ENOBUFS; fnew->id = f->id; - fnew->res = f->res; fnew->ifindex = f->ifindex; fnew->tp = f->tp; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index d0c53724d3e8..1e20bbd687f1 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -513,7 +513,6 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, if (fold) { f->id = fold->id; f->iif = fold->iif; - f->res = fold->res; f->handle = fold->handle; f->tp = fold->tp; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 5abf31e432ca..da4c179a4d41 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -826,7 +826,6 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, new->ifindex = n->ifindex; new->fshift = n->fshift; - new->res = n->res; new->flags = n->flags; RCU_INIT_POINTER(new->ht_down, ht); @@ -1024,18 +1023,62 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -EINVAL; } + /* At this point, we need to derive the new handle that will be used to + * uniquely map the identity of this table match entry. The + * identity of the entry that we need to construct is 32 bits made of: + * htid(12b):bucketid(8b):node/entryid(12b) + * + * At this point _we have the table(ht)_ in which we will insert this + * entry. We carry the table's id in variable "htid". + * Note that earlier code picked the ht selection either by a) the user + * providing the htid specified via TCA_U32_HASH attribute or b) when + * no such attribute is passed then the root ht, is default to at ID + * 0x[800][00][000]. Rule: the root table has a single bucket with ID 0. + * If OTOH the user passed us the htid, they may also pass a bucketid of + * choice. 0 is fine. For example a user htid is 0x[600][01][000] it is + * indicating hash bucketid of 1. Rule: the entry/node ID _cannot_ be + * passed via the htid, so even if it was non-zero it will be ignored. + * + * We may also have a handle, if the user passed one. The handle also + * carries the same addressing of htid(12b):bucketid(8b):node/entryid(12b). + * Rule: the bucketid on the handle is ignored even if one was passed; + * rather the value on "htid" is always assumed to be the bucketid. + */ if (handle) { + /* Rule: The htid from handle and tableid from htid must match */ if (TC_U32_HTID(handle) && TC_U32_HTID(handle ^ htid)) { NL_SET_ERR_MSG_MOD(extack, "Handle specified hash table address mismatch"); return -EINVAL; } - handle = htid | TC_U32_NODE(handle); - err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, handle, - GFP_KERNEL); - if (err) - return err; - } else + /* Ok, so far we have a valid htid(12b):bucketid(8b) but we + * need to finalize the table entry identification with the last + * part - the node/entryid(12b)). Rule: Nodeid _cannot be 0_ for + * entries. Rule: nodeid of 0 is reserved only for tables(see + * earlier code which processes TC_U32_DIVISOR attribute). + * Rule: The nodeid can only be derived from the handle (and not + * htid). + * Rule: if the handle specified zero for the node id example + * 0x60000000, then pick a new nodeid from the pool of IDs + * this hash table has been allocating from. + * If OTOH it is specified (i.e for example the user passed a + * handle such as 0x60000123), then we use it generate our final + * handle which is used to uniquely identify the match entry. + */ + if (!TC_U32_NODE(handle)) { + handle = gen_new_kid(ht, htid); + } else { + handle = htid | TC_U32_NODE(handle); + err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, + handle, GFP_KERNEL); + if (err) + return err; + } + } else { + /* The user did not give us a handle; lets just generate one + * from the table's pool of nodeids. + */ handle = gen_new_kid(ht, htid); + } if (tb[TCA_U32_SEL] == NULL) { NL_SET_ERR_MSG_MOD(extack, "Selector not specified"); diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index af85a73c4c54..6fdba069f6bf 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -568,7 +568,7 @@ META_COLLECTOR(int_sk_rcvtimeo) *err = -1; return; } - dst->value = sk->sk_rcvtimeo / HZ; + dst->value = READ_ONCE(sk->sk_rcvtimeo) / HZ; } META_COLLECTOR(int_sk_sndtimeo) @@ -579,7 +579,7 @@ META_COLLECTOR(int_sk_sndtimeo) *err = -1; return; } - dst->value = sk->sk_sndtimeo / HZ; + dst->value = READ_ONCE(sk->sk_sndtimeo) / HZ; } META_COLLECTOR(int_sk_sendmsg_off) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 717ae51d94a0..8c9cfff7fd05 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1015,6 +1015,11 @@ static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { TC_FP_PREEMPTIBLE), }; +static struct netlink_range_validation_signed taprio_cycle_time_range = { + .min = 0, + .max = INT_MAX, +}; + static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_PRIOMAP] = { .len = sizeof(struct tc_mqprio_qopt) @@ -1023,7 +1028,8 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_SCHED_BASE_TIME] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] = { .type = NLA_NESTED }, [TCA_TAPRIO_ATTR_SCHED_CLOCKID] = { .type = NLA_S32 }, - [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = { .type = NLA_S64 }, + [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = + NLA_POLICY_FULL_RANGE_SIGNED(NLA_S64, &taprio_cycle_time_range), [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_FLAGS] = { .type = NLA_U32 }, [TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 }, @@ -1159,6 +1165,11 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, return -EINVAL; } + if (cycle < 0 || cycle > INT_MAX) { + NL_SET_ERR_MSG(extack, "'cycle_time' is too big"); + return -EINVAL; + } + new->cycle_time = cycle; } @@ -1347,7 +1358,7 @@ static void setup_txtime(struct taprio_sched *q, struct sched_gate_list *sched, ktime_t base) { struct sched_entry *entry; - u32 interval = 0; + u64 interval = 0; list_for_each_entry(entry, &sched->entries, list) { entry->next_txtime = ktime_add_ns(base, interval); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index a7f887d91d89..f5834af5fad5 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -378,8 +378,8 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_state = SMC_INIT; sk->sk_destruct = smc_destruct; sk->sk_protocol = protocol; - WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(net->smc.sysctl_wmem)); - WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(net->smc.sysctl_rmem)); + WRITE_ONCE(sk->sk_sndbuf, 2 * READ_ONCE(net->smc.sysctl_wmem)); + WRITE_ONCE(sk->sk_rcvbuf, 2 * READ_ONCE(net->smc.sysctl_rmem)); smc = smc_sk(sk); INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work); INIT_WORK(&smc->connect_work, smc_connect_work); @@ -436,24 +436,9 @@ out: return rc; } -static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, - unsigned long mask) -{ - /* options we don't get control via setsockopt for */ - nsk->sk_type = osk->sk_type; - nsk->sk_sndbuf = osk->sk_sndbuf; - nsk->sk_rcvbuf = osk->sk_rcvbuf; - nsk->sk_sndtimeo = osk->sk_sndtimeo; - nsk->sk_rcvtimeo = osk->sk_rcvtimeo; - nsk->sk_mark = osk->sk_mark; - nsk->sk_priority = osk->sk_priority; - nsk->sk_rcvlowat = osk->sk_rcvlowat; - nsk->sk_bound_dev_if = osk->sk_bound_dev_if; - nsk->sk_err = osk->sk_err; - - nsk->sk_flags &= ~mask; - nsk->sk_flags |= osk->sk_flags & mask; -} +/* copy only relevant settings and flags of SOL_SOCKET level from smc to + * clc socket (since smc is not called for these options from net/core) + */ #define SK_FLAGS_SMC_TO_CLC ((1UL << SOCK_URGINLINE) | \ (1UL << SOCK_KEEPOPEN) | \ @@ -470,9 +455,55 @@ static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, (1UL << SOCK_NOFCS) | \ (1UL << SOCK_FILTER_LOCKED) | \ (1UL << SOCK_TSTAMP_NEW)) -/* copy only relevant settings and flags of SOL_SOCKET level from smc to - * clc socket (since smc is not called for these options from net/core) - */ + +/* if set, use value set by setsockopt() - else use IPv4 or SMC sysctl value */ +static void smc_adjust_sock_bufsizes(struct sock *nsk, struct sock *osk, + unsigned long mask) +{ + struct net *nnet = sock_net(nsk); + + nsk->sk_userlocks = osk->sk_userlocks; + if (osk->sk_userlocks & SOCK_SNDBUF_LOCK) { + nsk->sk_sndbuf = osk->sk_sndbuf; + } else { + if (mask == SK_FLAGS_SMC_TO_CLC) + WRITE_ONCE(nsk->sk_sndbuf, + READ_ONCE(nnet->ipv4.sysctl_tcp_wmem[1])); + else + WRITE_ONCE(nsk->sk_sndbuf, + 2 * READ_ONCE(nnet->smc.sysctl_wmem)); + } + if (osk->sk_userlocks & SOCK_RCVBUF_LOCK) { + nsk->sk_rcvbuf = osk->sk_rcvbuf; + } else { + if (mask == SK_FLAGS_SMC_TO_CLC) + WRITE_ONCE(nsk->sk_rcvbuf, + READ_ONCE(nnet->ipv4.sysctl_tcp_rmem[1])); + else + WRITE_ONCE(nsk->sk_rcvbuf, + 2 * READ_ONCE(nnet->smc.sysctl_rmem)); + } +} + +static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, + unsigned long mask) +{ + /* options we don't get control via setsockopt for */ + nsk->sk_type = osk->sk_type; + nsk->sk_sndtimeo = osk->sk_sndtimeo; + nsk->sk_rcvtimeo = osk->sk_rcvtimeo; + nsk->sk_mark = READ_ONCE(osk->sk_mark); + nsk->sk_priority = osk->sk_priority; + nsk->sk_rcvlowat = osk->sk_rcvlowat; + nsk->sk_bound_dev_if = osk->sk_bound_dev_if; + nsk->sk_err = osk->sk_err; + + nsk->sk_flags &= ~mask; + nsk->sk_flags |= osk->sk_flags & mask; + + smc_adjust_sock_bufsizes(nsk, osk, mask); +} + static void smc_copy_sock_settings_to_clc(struct smc_sock *smc) { smc_copy_sock_settings(smc->clcsock->sk, &smc->sk, SK_FLAGS_SMC_TO_CLC); @@ -2479,8 +2510,6 @@ static void smc_tcp_listen_work(struct work_struct *work) sock_hold(lsk); /* sock_put in smc_listen_work */ INIT_WORK(&new_smc->smc_listen_work, smc_listen_work); smc_copy_sock_settings_to_smc(new_smc); - new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf; - new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf; sock_hold(&new_smc->sk); /* sock_put in passive closing */ if (!queue_work(smc_hs_wq, &new_smc->smc_listen_work)) sock_put(&new_smc->sk); diff --git a/net/smc/smc.h b/net/smc/smc.h index 2eeea4cdc718..1f2b912c43d1 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -161,7 +161,7 @@ struct smc_connection { struct smc_buf_desc *sndbuf_desc; /* send buffer descriptor */ struct smc_buf_desc *rmb_desc; /* RMBE descriptor */ - int rmbe_size_short;/* compressed notation */ + int rmbe_size_comp; /* compressed notation */ int rmbe_update_limit; /* lower limit for consumer * cursor update diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index b9b8b07aa702..c90d9e5dda54 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -1007,7 +1007,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, clc->d0.gid = conn->lgr->smcd->ops->get_local_gid(conn->lgr->smcd); clc->d0.token = conn->rmb_desc->token; - clc->d0.dmbe_size = conn->rmbe_size_short; + clc->d0.dmbe_size = conn->rmbe_size_comp; clc->d0.dmbe_idx = 0; memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); if (version == SMC_V1) { @@ -1050,7 +1050,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu); break; } - clc->r0.rmbe_size = conn->rmbe_size_short; + clc->r0.rmbe_size = conn->rmbe_size_comp; clc->r0.rmb_dma_addr = conn->rmb_desc->is_vm ? cpu_to_be64((uintptr_t)conn->rmb_desc->cpu_addr) : cpu_to_be64((u64)sg_dma_address diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 3f465faf2b68..6b78075404d7 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -2309,31 +2309,30 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) struct smc_connection *conn = &smc->conn; struct smc_link_group *lgr = conn->lgr; struct list_head *buf_list; - int bufsize, bufsize_short; + int bufsize, bufsize_comp; struct rw_semaphore *lock; /* lock buffer list */ bool is_dgraded = false; - int sk_buf_size; if (is_rmb) /* use socket recv buffer size (w/o overhead) as start value */ - sk_buf_size = smc->sk.sk_rcvbuf; + bufsize = smc->sk.sk_rcvbuf / 2; else /* use socket send buffer size (w/o overhead) as start value */ - sk_buf_size = smc->sk.sk_sndbuf; + bufsize = smc->sk.sk_sndbuf / 2; - for (bufsize_short = smc_compress_bufsize(sk_buf_size, is_smcd, is_rmb); - bufsize_short >= 0; bufsize_short--) { + for (bufsize_comp = smc_compress_bufsize(bufsize, is_smcd, is_rmb); + bufsize_comp >= 0; bufsize_comp--) { if (is_rmb) { lock = &lgr->rmbs_lock; - buf_list = &lgr->rmbs[bufsize_short]; + buf_list = &lgr->rmbs[bufsize_comp]; } else { lock = &lgr->sndbufs_lock; - buf_list = &lgr->sndbufs[bufsize_short]; + buf_list = &lgr->sndbufs[bufsize_comp]; } - bufsize = smc_uncompress_bufsize(bufsize_short); + bufsize = smc_uncompress_bufsize(bufsize_comp); /* check for reusable slot in the link group */ - buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list); + buf_desc = smc_buf_get_slot(bufsize_comp, lock, buf_list); if (buf_desc) { buf_desc->is_dma_need_sync = 0; SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); @@ -2377,8 +2376,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) if (is_rmb) { conn->rmb_desc = buf_desc; - conn->rmbe_size_short = bufsize_short; - smc->sk.sk_rcvbuf = bufsize; + conn->rmbe_size_comp = bufsize_comp; + smc->sk.sk_rcvbuf = bufsize * 2; atomic_set(&conn->bytes_to_rcv, 0); conn->rmbe_update_limit = smc_rmb_wnd_update_limit(buf_desc->len); @@ -2386,7 +2385,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */ } else { conn->sndbuf_desc = buf_desc; - smc->sk.sk_sndbuf = bufsize; + smc->sk.sk_sndbuf = bufsize * 2; atomic_set(&conn->sndbuf_space, bufsize); } return 0; diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c index b6f79fabb9d3..0b2a957ca5f5 100644 --- a/net/smc/smc_sysctl.c +++ b/net/smc/smc_sysctl.c @@ -21,6 +21,10 @@ static int min_sndbuf = SMC_BUF_MIN_SIZE; static int min_rcvbuf = SMC_BUF_MIN_SIZE; +static int max_sndbuf = INT_MAX / 2; +static int max_rcvbuf = INT_MAX / 2; +static const int net_smc_wmem_init = (64 * 1024); +static const int net_smc_rmem_init = (64 * 1024); static struct ctl_table smc_table[] = { { @@ -53,6 +57,7 @@ static struct ctl_table smc_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_sndbuf, + .extra2 = &max_sndbuf, }, { .procname = "rmem", @@ -61,6 +66,7 @@ static struct ctl_table smc_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_rcvbuf, + .extra2 = &max_rcvbuf, }, { } }; @@ -88,8 +94,8 @@ int __net_init smc_sysctl_net_init(struct net *net) net->smc.sysctl_autocorking_size = SMC_AUTOCORKING_DEFAULT_SIZE; net->smc.sysctl_smcr_buf_type = SMCR_PHYS_CONT_BUFS; net->smc.sysctl_smcr_testlink_time = SMC_LLC_TESTLINK_DEFAULT_TIME; - WRITE_ONCE(net->smc.sysctl_wmem, READ_ONCE(net->ipv4.sysctl_tcp_wmem[1])); - WRITE_ONCE(net->smc.sysctl_rmem, READ_ONCE(net->ipv4.sysctl_tcp_rmem[1])); + WRITE_ONCE(net->smc.sysctl_wmem, net_smc_wmem_init); + WRITE_ONCE(net->smc.sysctl_rmem, net_smc_rmem_init); return 0; diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 2021fe557e50..529101eb20bd 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -52,6 +52,8 @@ static LIST_HEAD(tls_device_list); static LIST_HEAD(tls_device_down_list); static DEFINE_SPINLOCK(tls_device_lock); +static struct page *dummy_page; + static void tls_device_free_ctx(struct tls_context *ctx) { if (ctx->tx_conf == TLS_HW) { @@ -312,36 +314,33 @@ static int tls_push_record(struct sock *sk, return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags); } -static int tls_device_record_close(struct sock *sk, - struct tls_context *ctx, - struct tls_record_info *record, - struct page_frag *pfrag, - unsigned char record_type) +static void tls_device_record_close(struct sock *sk, + struct tls_context *ctx, + struct tls_record_info *record, + struct page_frag *pfrag, + unsigned char record_type) { struct tls_prot_info *prot = &ctx->prot_info; - int ret; + struct page_frag dummy_tag_frag; /* append tag * device will fill in the tag, we just need to append a placeholder * use socket memory to improve coalescing (re-using a single buffer * increases frag count) - * if we can't allocate memory now, steal some back from data + * if we can't allocate memory now use the dummy page */ - if (likely(skb_page_frag_refill(prot->tag_size, pfrag, - sk->sk_allocation))) { - ret = 0; - tls_append_frag(record, pfrag, prot->tag_size); - } else { - ret = prot->tag_size; - if (record->len <= prot->overhead_size) - return -ENOMEM; + if (unlikely(pfrag->size - pfrag->offset < prot->tag_size) && + !skb_page_frag_refill(prot->tag_size, pfrag, sk->sk_allocation)) { + dummy_tag_frag.page = dummy_page; + dummy_tag_frag.offset = 0; + pfrag = &dummy_tag_frag; } + tls_append_frag(record, pfrag, prot->tag_size); /* fill prepend */ tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]), record->len - prot->overhead_size, record_type); - return ret; } static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx, @@ -541,18 +540,8 @@ last_record: if (done || record->len >= max_open_record_len || (record->num_frags >= MAX_SKB_FRAGS - 1)) { - rc = tls_device_record_close(sk, tls_ctx, record, - pfrag, record_type); - if (rc) { - if (rc > 0) { - size += rc; - } else { - size = orig_size; - destroy_record(record); - ctx->open_record = NULL; - break; - } - } + tls_device_record_close(sk, tls_ctx, record, + pfrag, record_type); rc = tls_push_record(sk, tls_ctx, @@ -1450,14 +1439,26 @@ int __init tls_device_init(void) { int err; - destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); - if (!destruct_wq) + dummy_page = alloc_page(GFP_KERNEL); + if (!dummy_page) return -ENOMEM; + destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); + if (!destruct_wq) { + err = -ENOMEM; + goto err_free_dummy; + } + err = register_netdevice_notifier(&tls_dev_notifier); if (err) - destroy_workqueue(destruct_wq); + goto err_destroy_wq; + return 0; + +err_destroy_wq: + destroy_workqueue(destruct_wq); +err_free_dummy: + put_page(dummy_page); return err; } @@ -1466,4 +1467,5 @@ void __exit tls_device_cleanup(void) unregister_netdevice_notifier(&tls_dev_notifier); destroy_workqueue(destruct_wq); clean_acked_data_flush(); + put_page(dummy_page); } diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index b6896126bb92..4a8ee2f6badb 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -139,9 +139,6 @@ int tls_push_sg(struct sock *sk, ctx->splicing_pages = true; while (1) { - if (sg_is_last(sg)) - msg.msg_flags = flags; - /* is sending application-limited? */ tcp_rate_check_app_limited(sk); p = sg_page(sg); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 78585217f61a..86930a8ed012 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -790,7 +790,7 @@ static int unix_set_peek_off(struct sock *sk, int val) if (mutex_lock_interruptible(&u->iolock)) return -EINTR; - sk->sk_peek_off = val; + WRITE_ONCE(sk->sk_peek_off, val); mutex_unlock(&u->iolock); return 0; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0da2e6a2a7ea..8bcf8e293308 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5430,8 +5430,11 @@ nl80211_parse_mbssid_elems(struct wiphy *wiphy, struct nlattr *attrs) if (!wiphy->mbssid_max_interfaces) return ERR_PTR(-EINVAL); - nla_for_each_nested(nl_elems, attrs, rem_elems) + nla_for_each_nested(nl_elems, attrs, rem_elems) { + if (num_elems >= 255) + return ERR_PTR(-EINVAL); num_elems++; + } elems = kzalloc(struct_size(elems, elem, num_elems), GFP_KERNEL); if (!elems) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 8bf00caf5d29..0cf1ce7b6934 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -657,7 +657,7 @@ static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies, ret = cfg80211_calc_short_ssid(ies, &ssid_elem, &s_ssid_tmp); if (ret) - return ret; + return 0; for_each_element_id(elem, WLAN_EID_REDUCED_NEIGHBOR_REPORT, ies->data, ies->len) { diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 31dca4ecb2c5..10ea85c03147 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -505,7 +505,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, skb->dev = dev; skb->priority = xs->sk.sk_priority; - skb->mark = xs->sk.sk_mark; + skb->mark = READ_ONCE(xs->sk.sk_mark); skb_shinfo(skb)->destructor_arg = (void *)(long)desc->addr; skb->destructor = xsk_destruct_skb; @@ -994,6 +994,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) err = xp_alloc_tx_descs(xs->pool, xs); if (err) { xp_put_pool(xs->pool); + xs->pool = NULL; sockfd_put(sock); goto out_unlock; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e7617c9959c3..d6b405782b63 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2250,7 +2250,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, match = xfrm_selector_match(&pol->selector, fl, family); if (match) { - if ((sk->sk_mark & pol->mark.m) != pol->mark.v || + if ((READ_ONCE(sk->sk_mark) & pol->mark.m) != pol->mark.v || pol->if_id != if_id) { pol = NULL; goto out; diff --git a/rust/Makefile b/rust/Makefile index 7c9d9f11aec5..4124bfa01798 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -257,7 +257,7 @@ bindgen_skip_c_flags := -mno-fp-ret-in-387 -mpreferred-stack-boundary=% \ -fno-partial-inlining -fplugin-arg-arm_ssp_per_task_plugin-% \ -fno-reorder-blocks -fno-allow-store-data-races -fasan-shadow-offset=% \ -fzero-call-used-regs=% -fno-stack-clash-protection \ - -fno-inline-functions-called-once \ + -fno-inline-functions-called-once -fsanitize=bounds-strict \ --param=% --param asan-% # Derived from `scripts/Makefile.clang`. diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index 3e601ce2548d..058954961bfc 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -13,5 +13,6 @@ #include <linux/sched.h> /* `bindgen` gets confused at certain things. */ +const size_t BINDINGS_ARCH_SLAB_MINALIGN = ARCH_SLAB_MINALIGN; const gfp_t BINDINGS_GFP_KERNEL = GFP_KERNEL; const gfp_t BINDINGS___GFP_ZERO = __GFP_ZERO; diff --git a/rust/kernel/allocator.rs b/rust/kernel/allocator.rs index 397a3dd57a9b..9363b527be66 100644 --- a/rust/kernel/allocator.rs +++ b/rust/kernel/allocator.rs @@ -9,6 +9,36 @@ use crate::bindings; struct KernelAllocator; +/// Calls `krealloc` with a proper size to alloc a new object aligned to `new_layout`'s alignment. +/// +/// # Safety +/// +/// - `ptr` can be either null or a pointer which has been allocated by this allocator. +/// - `new_layout` must have a non-zero size. +unsafe fn krealloc_aligned(ptr: *mut u8, new_layout: Layout, flags: bindings::gfp_t) -> *mut u8 { + // Customized layouts from `Layout::from_size_align()` can have size < align, so pad first. + let layout = new_layout.pad_to_align(); + + let mut size = layout.size(); + + if layout.align() > bindings::BINDINGS_ARCH_SLAB_MINALIGN { + // The alignment requirement exceeds the slab guarantee, thus try to enlarge the size + // to use the "power-of-two" size/alignment guarantee (see comments in `kmalloc()` for + // more information). + // + // Note that `layout.size()` (after padding) is guaranteed to be a multiple of + // `layout.align()`, so `next_power_of_two` gives enough alignment guarantee. + size = size.next_power_of_two(); + } + + // SAFETY: + // - `ptr` is either null or a pointer returned from a previous `k{re}alloc()` by the + // function safety requirement. + // - `size` is greater than 0 since it's either a `layout.size()` (which cannot be zero + // according to the function safety requirement) or a result from `next_power_of_two()`. + unsafe { bindings::krealloc(ptr as *const core::ffi::c_void, size, flags) as *mut u8 } +} + unsafe impl GlobalAlloc for KernelAllocator { unsafe fn alloc(&self, layout: Layout) -> *mut u8 { // `krealloc()` is used instead of `kmalloc()` because the latter is @@ -30,10 +60,20 @@ static ALLOCATOR: KernelAllocator = KernelAllocator; // to extract the object file that has them from the archive. For the moment, // let's generate them ourselves instead. // +// Note: Although these are *safe* functions, they are called by the compiler +// with parameters that obey the same `GlobalAlloc` function safety +// requirements: size and align should form a valid layout, and size is +// greater than 0. +// // Note that `#[no_mangle]` implies exported too, nowadays. #[no_mangle] -fn __rust_alloc(size: usize, _align: usize) -> *mut u8 { - unsafe { bindings::krealloc(core::ptr::null(), size, bindings::GFP_KERNEL) as *mut u8 } +fn __rust_alloc(size: usize, align: usize) -> *mut u8 { + // SAFETY: See assumption above. + let layout = unsafe { Layout::from_size_align_unchecked(size, align) }; + + // SAFETY: `ptr::null_mut()` is null, per assumption above the size of `layout` is greater + // than 0. + unsafe { krealloc_aligned(ptr::null_mut(), layout, bindings::GFP_KERNEL) } } #[no_mangle] @@ -42,23 +82,27 @@ fn __rust_dealloc(ptr: *mut u8, _size: usize, _align: usize) { } #[no_mangle] -fn __rust_realloc(ptr: *mut u8, _old_size: usize, _align: usize, new_size: usize) -> *mut u8 { - unsafe { - bindings::krealloc( - ptr as *const core::ffi::c_void, - new_size, - bindings::GFP_KERNEL, - ) as *mut u8 - } +fn __rust_realloc(ptr: *mut u8, _old_size: usize, align: usize, new_size: usize) -> *mut u8 { + // SAFETY: See assumption above. + let new_layout = unsafe { Layout::from_size_align_unchecked(new_size, align) }; + + // SAFETY: Per assumption above, `ptr` is allocated by `__rust_*` before, and the size of + // `new_layout` is greater than 0. + unsafe { krealloc_aligned(ptr, new_layout, bindings::GFP_KERNEL) } } #[no_mangle] -fn __rust_alloc_zeroed(size: usize, _align: usize) -> *mut u8 { +fn __rust_alloc_zeroed(size: usize, align: usize) -> *mut u8 { + // SAFETY: See assumption above. + let layout = unsafe { Layout::from_size_align_unchecked(size, align) }; + + // SAFETY: `ptr::null_mut()` is null, per assumption above the size of `layout` is greater + // than 0. unsafe { - bindings::krealloc( - core::ptr::null(), - size, + krealloc_aligned( + ptr::null_mut(), + layout, bindings::GFP_KERNEL | bindings::__GFP_ZERO, - ) as *mut u8 + ) } } diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs index a89843cacaad..172f563976a9 100644 --- a/rust/kernel/sync/arc.rs +++ b/rust/kernel/sync/arc.rs @@ -243,8 +243,7 @@ impl<T: 'static> ForeignOwnable for Arc<T> { let inner = NonNull::new(ptr as *mut ArcInner<T>).unwrap(); // SAFETY: The safety requirements of `from_foreign` ensure that the object remains alive - // for the lifetime of the returned value. Additionally, the safety requirements of - // `ForeignOwnable::borrow_mut` ensure that no new mutable references are created. + // for the lifetime of the returned value. unsafe { ArcBorrow::new(inner) } } diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs index 1e5380b16ed5..d479f8da8f38 100644 --- a/rust/kernel/types.rs +++ b/rust/kernel/types.rs @@ -35,34 +35,16 @@ pub trait ForeignOwnable: Sized { /// /// `ptr` must have been returned by a previous call to [`ForeignOwnable::into_foreign`] for /// which a previous matching [`ForeignOwnable::from_foreign`] hasn't been called yet. - /// Additionally, all instances (if any) of values returned by [`ForeignOwnable::borrow_mut`] - /// for this object must have been dropped. unsafe fn borrow<'a>(ptr: *const core::ffi::c_void) -> Self::Borrowed<'a>; - /// Mutably borrows a foreign-owned object. - /// - /// # Safety - /// - /// `ptr` must have been returned by a previous call to [`ForeignOwnable::into_foreign`] for - /// which a previous matching [`ForeignOwnable::from_foreign`] hasn't been called yet. - /// Additionally, all instances (if any) of values returned by [`ForeignOwnable::borrow`] and - /// [`ForeignOwnable::borrow_mut`] for this object must have been dropped. - unsafe fn borrow_mut(ptr: *const core::ffi::c_void) -> ScopeGuard<Self, fn(Self)> { - // SAFETY: The safety requirements ensure that `ptr` came from a previous call to - // `into_foreign`. - ScopeGuard::new_with_data(unsafe { Self::from_foreign(ptr) }, |d| { - d.into_foreign(); - }) - } - /// Converts a foreign-owned object back to a Rust-owned one. /// /// # Safety /// /// `ptr` must have been returned by a previous call to [`ForeignOwnable::into_foreign`] for /// which a previous matching [`ForeignOwnable::from_foreign`] hasn't been called yet. - /// Additionally, all instances (if any) of values returned by [`ForeignOwnable::borrow`] and - /// [`ForeignOwnable::borrow_mut`] for this object must have been dropped. + /// Additionally, all instances (if any) of values returned by [`ForeignOwnable::borrow`] for + /// this object must have been dropped. unsafe fn from_foreign(ptr: *const core::ffi::c_void) -> Self; } diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 16c87938b316..653b92f6d4c8 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -129,6 +129,7 @@ static struct sym_entry *read_symbol(FILE *in, char **buf, size_t *buf_len) ssize_t readlen; struct sym_entry *sym; + errno = 0; readlen = getline(buf, buf_len, in); if (readlen < 0) { if (errno) { diff --git a/security/keys/sysctl.c b/security/keys/sysctl.c index b72b82bb20c6..b348e1679d5d 100644 --- a/security/keys/sysctl.c +++ b/security/keys/sysctl.c @@ -9,7 +9,7 @@ #include <linux/sysctl.h> #include "internal.h" -struct ctl_table key_sysctls[] = { +static struct ctl_table key_sysctls[] = { { .procname = "maxkeys", .data = &key_quota_maxkeys, diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index cb8ca46213be..1f6d904c6481 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -14,7 +14,7 @@ * Defines x86 CPU feature bits */ #define NCAPINTS 21 /* N 32-bit words worth of info */ -#define NBUGINTS 1 /* N 32-bit bug flags */ +#define NBUGINTS 2 /* N 32-bit bug flags */ /* * Note: If the comment begins with a quoted string, that string is used diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 3aedae61af4f..a00a53e15ab7 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -545,6 +545,7 @@ #define MSR_AMD64_DE_CFG 0xc0011029 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT 1 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE BIT_ULL(MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT) +#define MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT 9 #define MSR_AMD64_BU_CFG2 0xc001102a #define MSR_AMD64_IBSFETCHCTL 0xc0011030 diff --git a/tools/counter/Makefile b/tools/counter/Makefile index a0f4cab71fe5..b2c2946f44c9 100644 --- a/tools/counter/Makefile +++ b/tools/counter/Makefile @@ -40,7 +40,8 @@ $(OUTPUT)counter_example: $(COUNTER_EXAMPLE) clean: rm -f $(ALL_PROGRAMS) rm -rf $(OUTPUT)include/linux/counter.h - rmdir -p $(OUTPUT)include/linux + rm -df $(OUTPUT)include/linux + rm -df $(OUTPUT)include find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete install: $(ALL_PROGRAMS) diff --git a/tools/hv/vmbus_testing b/tools/hv/vmbus_testing index e7212903dd1d..4467979d8f69 100755 --- a/tools/hv/vmbus_testing +++ b/tools/hv/vmbus_testing @@ -164,7 +164,7 @@ def recursive_file_lookup(path, file_map): def get_all_devices_test_status(file_map): for device in file_map: - if (get_test_state(locate_state(device, file_map)) is 1): + if (get_test_state(locate_state(device, file_map)) == 1): print("Testing = ON for: {}" .format(device.split("/")[5])) else: @@ -203,7 +203,7 @@ def write_test_files(path, value): def set_test_state(state_path, state_value, quiet): write_test_files(state_path, state_value) - if (get_test_state(state_path) is 1): + if (get_test_state(state_path) == 1): if (not quiet): print("Testing = ON for device: {}" .format(state_path.split("/")[5])) diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 2e1caabecb18..2d51fa8da9e8 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -824,5 +824,8 @@ bool arch_is_retpoline(struct symbol *sym) bool arch_is_rethunk(struct symbol *sym) { - return !strcmp(sym->name, "__x86_return_thunk"); + return !strcmp(sym->name, "__x86_return_thunk") || + !strcmp(sym->name, "srso_untrain_ret") || + !strcmp(sym->name, "srso_safe_ret") || + !strcmp(sym->name, "__ret"); } diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c index 561de0cb6b95..512a8f13c4de 100644 --- a/tools/perf/arch/arm64/util/pmu.c +++ b/tools/perf/arch/arm64/util/pmu.c @@ -54,10 +54,11 @@ double perf_pmu__cpu_slots_per_cycle(void) perf_pmu__pathname_scnprintf(path, sizeof(path), pmu->name, "caps/slots"); /* - * The value of slots is not greater than 32 bits, but sysfs__read_int - * can't read value with 0x prefix, so use sysfs__read_ull instead. + * The value of slots is not greater than 32 bits, but + * filename__read_int can't read value with 0x prefix, + * so use filename__read_ull instead. */ - sysfs__read_ull(path, &slots); + filename__read_ull(path, &slots); } return slots ? (double)slots : NAN; diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index b7223feec770..5f3edb3004d8 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -250,6 +250,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) if (!chain || chain->nr < 3) return skip_slot; + addr_location__init(&al); ip = chain->ips[1]; thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); @@ -259,6 +260,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) if (!dso) { pr_debug("%" PRIx64 " dso is NULL\n", ip); + addr_location__exit(&al); return skip_slot; } @@ -279,5 +281,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) */ skip_slot = 3; } + + addr_location__exit(&al); return skip_slot; } diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index b2f82847e4c3..658fb9599d95 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1631,6 +1631,16 @@ static bool test__pmu_cpu_valid(void) return !!perf_pmus__find("cpu"); } +static bool test__pmu_cpu_event_valid(void) +{ + struct perf_pmu *pmu = perf_pmus__find("cpu"); + + if (!pmu) + return false; + + return perf_pmu__has_format(pmu, "event"); +} + static bool test__intel_pt_valid(void) { return !!perf_pmus__find("intel_pt"); @@ -2179,7 +2189,7 @@ static const struct evlist_test test__events_pmu[] = { }, { .name = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp", - .valid = test__pmu_cpu_valid, + .valid = test__pmu_cpu_event_valid, .check = test__checkevent_complex_name, /* 3 */ }, diff --git a/tools/perf/tests/shell/test_uprobe_from_different_cu.sh b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh index 00d2e0e2e0c2..319f36ebb9a4 100755 --- a/tools/perf/tests/shell/test_uprobe_from_different_cu.sh +++ b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh @@ -4,6 +4,12 @@ set -e +# skip if there's no gcc +if ! [ -x "$(command -v gcc)" ]; then + echo "failed: no gcc compiler" + exit 2 +fi + temp_dir=$(mktemp -d /tmp/perf-uprobe-different-cu-sh.XXXXXXXXXX) cleanup() @@ -11,7 +17,7 @@ cleanup() trap - EXIT TERM INT if [[ "${temp_dir}" =~ ^/tmp/perf-uprobe-different-cu-sh.*$ ]]; then echo "--- Cleaning up ---" - perf probe -x ${temp_dir}/testfile -d foo + perf probe -x ${temp_dir}/testfile -d foo || true rm -f "${temp_dir}/"* rmdir "${temp_dir}" fi diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 4e62843d51b7..f4cb41ee23cd 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -45,7 +45,6 @@ static void __machine__remove_thread(struct machine *machine, struct thread_rb_node *nd, struct thread *th, bool lock); -static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms, u64 ip); static struct dso *machine__kernel_dso(struct machine *machine) { @@ -2385,10 +2384,6 @@ static int add_callchain_ip(struct thread *thread, ms.maps = maps__get(al.maps); ms.map = map__get(al.map); ms.sym = al.sym; - - if (!branch && append_inlines(cursor, &ms, ip) == 0) - goto out; - srcline = callchain_srcline(&ms, al.addr); err = callchain_cursor_append(cursor, ip, &ms, branch, flags, nr_loop_iter, diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index acde097e327c..c9ec0cafb69d 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2100,16 +2100,16 @@ __weak int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs) return lhs->core.idx - rhs->core.idx; } -static int evlist__cmp(void *state, const struct list_head *l, const struct list_head *r) +static int evlist__cmp(void *_fg_idx, const struct list_head *l, const struct list_head *r) { const struct perf_evsel *lhs_core = container_of(l, struct perf_evsel, node); const struct evsel *lhs = container_of(lhs_core, struct evsel, core); const struct perf_evsel *rhs_core = container_of(r, struct perf_evsel, node); const struct evsel *rhs = container_of(rhs_core, struct evsel, core); - int *leader_idx = state; - int lhs_leader_idx = *leader_idx, rhs_leader_idx = *leader_idx, ret; + int *force_grouped_idx = _fg_idx; + int lhs_sort_idx, rhs_sort_idx, ret; const char *lhs_pmu_name, *rhs_pmu_name; - bool lhs_has_group = false, rhs_has_group = false; + bool lhs_has_group, rhs_has_group; /* * First sort by grouping/leader. Read the leader idx only if the evsel @@ -2121,15 +2121,25 @@ static int evlist__cmp(void *state, const struct list_head *l, const struct list */ if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) { lhs_has_group = true; - lhs_leader_idx = lhs_core->leader->idx; + lhs_sort_idx = lhs_core->leader->idx; + } else { + lhs_has_group = false; + lhs_sort_idx = *force_grouped_idx != -1 && arch_evsel__must_be_in_group(lhs) + ? *force_grouped_idx + : lhs_core->idx; } if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) { rhs_has_group = true; - rhs_leader_idx = rhs_core->leader->idx; + rhs_sort_idx = rhs_core->leader->idx; + } else { + rhs_has_group = false; + rhs_sort_idx = *force_grouped_idx != -1 && arch_evsel__must_be_in_group(rhs) + ? *force_grouped_idx + : rhs_core->idx; } - if (lhs_leader_idx != rhs_leader_idx) - return lhs_leader_idx - rhs_leader_idx; + if (lhs_sort_idx != rhs_sort_idx) + return lhs_sort_idx - rhs_sort_idx; /* Group by PMU if there is a group. Groups can't span PMUs. */ if (lhs_has_group && rhs_has_group) { @@ -2146,10 +2156,10 @@ static int evlist__cmp(void *state, const struct list_head *l, const struct list static int parse_events__sort_events_and_fix_groups(struct list_head *list) { - int idx = 0, unsorted_idx = -1; + int idx = 0, force_grouped_idx = -1; struct evsel *pos, *cur_leader = NULL; struct perf_evsel *cur_leaders_grp = NULL; - bool idx_changed = false; + bool idx_changed = false, cur_leader_force_grouped = false; int orig_num_leaders = 0, num_leaders = 0; int ret; @@ -2174,12 +2184,14 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list) */ pos->core.idx = idx++; - if (unsorted_idx == -1 && pos == pos_leader && pos->core.nr_members < 2) - unsorted_idx = pos->core.idx; + /* Remember an index to sort all forced grouped events together to. */ + if (force_grouped_idx == -1 && pos == pos_leader && pos->core.nr_members < 2 && + arch_evsel__must_be_in_group(pos)) + force_grouped_idx = pos->core.idx; } /* Sort events. */ - list_sort(&unsorted_idx, list, evlist__cmp); + list_sort(&force_grouped_idx, list, evlist__cmp); /* * Recompute groups, splitting for PMUs and adding groups for events @@ -2189,8 +2201,9 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list) list_for_each_entry(pos, list, core.node) { const struct evsel *pos_leader = evsel__leader(pos); const char *pos_pmu_name = pos->group_pmu_name; - const char *cur_leader_pmu_name, *pos_leader_pmu_name; - bool force_grouped = arch_evsel__must_be_in_group(pos); + const char *cur_leader_pmu_name; + bool pos_force_grouped = force_grouped_idx != -1 && + arch_evsel__must_be_in_group(pos); /* Reset index and nr_members. */ if (pos->core.idx != idx) @@ -2206,7 +2219,8 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list) cur_leader = pos; cur_leader_pmu_name = cur_leader->group_pmu_name; - if ((cur_leaders_grp != pos->core.leader && !force_grouped) || + if ((cur_leaders_grp != pos->core.leader && + (!pos_force_grouped || !cur_leader_force_grouped)) || strcmp(cur_leader_pmu_name, pos_pmu_name)) { /* Event is for a different group/PMU than last. */ cur_leader = pos; @@ -2216,14 +2230,14 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list) * group. */ cur_leaders_grp = pos->core.leader; - } - pos_leader_pmu_name = pos_leader->group_pmu_name; - if (strcmp(pos_leader_pmu_name, pos_pmu_name) || force_grouped) { /* - * Event's PMU differs from its leader's. Groups can't - * span PMUs, so update leader from the group/PMU - * tracker. + * Avoid forcing events into groups with events that + * don't need to be in the group. */ + cur_leader_force_grouped = pos_force_grouped; + } + if (pos_leader != cur_leader) { + /* The leader changed so update it. */ evsel__set_leader(pos, cur_leader); } } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 7f984a7f16ca..28380e7aa8d0 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1440,6 +1440,17 @@ void perf_pmu__del_formats(struct list_head *formats) } } +bool perf_pmu__has_format(const struct perf_pmu *pmu, const char *name) +{ + struct perf_pmu_format *format; + + list_for_each_entry(format, &pmu->format, list) { + if (!strcmp(format->name, name)) + return true; + } + return false; +} + bool is_pmu_core(const char *name) { return !strcmp(name, "cpu") || !strcmp(name, "cpum_cf") || is_sysfs_pmu_core(name); diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 203b92860e3c..6b414cecbad2 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -234,6 +234,7 @@ int perf_pmu__new_format(struct list_head *list, char *name, void perf_pmu__set_format(unsigned long *bits, long from, long to); int perf_pmu__format_parse(int dirfd, struct list_head *head); void perf_pmu__del_formats(struct list_head *formats); +bool perf_pmu__has_format(const struct perf_pmu *pmu, const char *name); bool is_pmu_core(const char *name); bool perf_pmu__supports_legacy_cache(const struct perf_pmu *pmu); diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c index 3cd9de42139e..c58ba9fb6a36 100644 --- a/tools/perf/util/pmus.c +++ b/tools/perf/util/pmus.c @@ -152,16 +152,14 @@ static void pmu_read_sysfs(bool core_only) } closedir(dir); - if (core_only) { - if (!list_empty(&core_pmus)) - read_sysfs_core_pmus = true; - else { - if (perf_pmu__create_placeholder_core_pmu(&core_pmus)) - read_sysfs_core_pmus = true; - } - } else { + if (list_empty(&core_pmus)) { + if (!perf_pmu__create_placeholder_core_pmu(&core_pmus)) + pr_err("Failure to set up any core PMUs\n"); + } + if (!list_empty(&core_pmus)) { read_sysfs_core_pmus = true; - read_sysfs_all_pmus = true; + if (!core_only) + read_sysfs_all_pmus = true; } } diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 7329b3340f88..d45d5dcb0e2b 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -931,6 +931,11 @@ static bool should_skip_zero_counter(struct perf_stat_config *config, */ if (config->aggr_mode == AGGR_THREAD && config->system_wide) return true; + + /* Tool events have the software PMU but are only gathered on 1. */ + if (evsel__is_tool(counter)) + return true; + /* * Skip value 0 when it's an uncore event and the given aggr id * does not belong to the PMU cpumask. diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c index a61c7bcbc72d..63f468bf8245 100644 --- a/tools/testing/radix-tree/regression1.c +++ b/tools/testing/radix-tree/regression1.c @@ -177,7 +177,7 @@ void regression1_test(void) nr_threads = 2; pthread_barrier_init(&worker_barrier, NULL, nr_threads); - threads = malloc(nr_threads * sizeof(pthread_t *)); + threads = malloc(nr_threads * sizeof(*threads)); for (i = 0; i < nr_threads; i++) { arg = i; diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index b4f6f3a50ae5..5674a9d0cacf 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -869,6 +869,77 @@ static void test_msg_redir_to_listening(struct test_sockmap_listen *skel, xbpf_prog_detach2(verdict, sock_map, BPF_SK_MSG_VERDICT); } +static void redir_partial(int family, int sotype, int sock_map, int parser_map) +{ + int s, c0, c1, p0, p1; + int err, n, key, value; + char buf[] = "abc"; + + key = 0; + value = sizeof(buf) - 1; + err = xbpf_map_update_elem(parser_map, &key, &value, 0); + if (err) + return; + + s = socket_loopback(family, sotype | SOCK_NONBLOCK); + if (s < 0) + goto clean_parser_map; + + err = create_socket_pairs(s, family, sotype, &c0, &c1, &p0, &p1); + if (err) + goto close_srv; + + err = add_to_sockmap(sock_map, p0, p1); + if (err) + goto close; + + n = xsend(c1, buf, sizeof(buf), 0); + if (n < sizeof(buf)) + FAIL("incomplete write"); + + n = xrecv_nonblock(c0, buf, sizeof(buf), 0); + if (n != sizeof(buf) - 1) + FAIL("expect %zu, received %d", sizeof(buf) - 1, n); + +close: + xclose(c0); + xclose(p0); + xclose(c1); + xclose(p1); +close_srv: + xclose(s); + +clean_parser_map: + key = 0; + value = 0; + xbpf_map_update_elem(parser_map, &key, &value, 0); +} + +static void test_skb_redir_partial(struct test_sockmap_listen *skel, + struct bpf_map *inner_map, int family, + int sotype) +{ + int verdict = bpf_program__fd(skel->progs.prog_stream_verdict); + int parser = bpf_program__fd(skel->progs.prog_stream_parser); + int parser_map = bpf_map__fd(skel->maps.parser_map); + int sock_map = bpf_map__fd(inner_map); + int err; + + err = xbpf_prog_attach(parser, sock_map, BPF_SK_SKB_STREAM_PARSER, 0); + if (err) + return; + + err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (err) + goto detach; + + redir_partial(family, sotype, sock_map, parser_map); + + xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT); +detach: + xbpf_prog_detach2(parser, sock_map, BPF_SK_SKB_STREAM_PARSER); +} + static void test_reuseport_select_listening(int family, int sotype, int sock_map, int verd_map, int reuseport_prog) @@ -1243,6 +1314,7 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map, } tests[] = { TEST(test_skb_redir_to_connected), TEST(test_skb_redir_to_listening), + TEST(test_skb_redir_partial), TEST(test_msg_redir_to_connected), TEST(test_msg_redir_to_listening), }; @@ -1432,7 +1504,7 @@ static void vsock_unix_redir_connectible(int sock_mapfd, int verd_mapfd, if (n < 1) goto out; - n = recv(mode == REDIR_INGRESS ? u0 : u1, &b, sizeof(b), MSG_DONTWAIT); + n = xrecv_nonblock(mode == REDIR_INGRESS ? u0 : u1, &b, sizeof(b), 0); if (n < 0) FAIL("%s: recv() err, errno=%d", log_prefix, errno); if (n == 0) diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c index 325c9f193432..464d35bd57c7 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c @@ -28,12 +28,26 @@ struct { __type(value, unsigned int); } verdict_map SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} parser_map SEC(".maps"); + bool test_sockmap = false; /* toggled by user-space */ bool test_ingress = false; /* toggled by user-space */ SEC("sk_skb/stream_parser") int prog_stream_parser(struct __sk_buff *skb) { + int *value; + __u32 key = 0; + + value = bpf_map_lookup_elem(&parser_map, &key); + if (value && *value) + return *value; + return skb->len; } diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index 258ddc565deb..1b2cec9d18a4 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -70,6 +70,10 @@ static int test_kmem_basic(const char *root) goto cleanup; cg_write(cg, "memory.high", "1M"); + + /* wait for RCU freeing */ + sleep(1); + slab1 = cg_read_key_long(cg, "memory.stat", "slab "); if (slab1 <= 0) goto cleanup; diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index 435acebdc325..380b691d3eb9 100644 --- a/tools/testing/selftests/mm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c @@ -831,6 +831,7 @@ int main(int argc, char *argv[]) printf("Size must be greater than 0\n"); return KSFT_FAIL; } + break; case 't': { int tmp = atoi(optarg); diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 0f5e88c8f4ff..df8d90b51867 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1981,6 +1981,11 @@ basic() run_cmd "$IP link set dev lo up" + # Dump should not loop endlessly when maximum nexthop ID is configured. + run_cmd "$IP nexthop add id $((2**32-1)) blackhole" + run_cmd "timeout 5 $IP nexthop" + log_test $? 0 "Maximum nexthop ID dump" + # # groups # @@ -2201,6 +2206,11 @@ basic_res() run_cmd "$IP nexthop bucket list fdb" log_test $? 255 "Dump all nexthop buckets with invalid 'fdb' keyword" + # Dump should not loop endlessly when maximum nexthop ID is configured. + run_cmd "$IP nexthop add id $((2**32-1)) group 1/2 type resilient buckets 4" + run_cmd "timeout 5 $IP nexthop bucket" + log_test $? 0 "Maximum nexthop ID dump" + # # resilient nexthop buckets get requests # diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index ae3f9462a2b6..d0c6c499d5da 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -617,7 +617,7 @@ __cfg_test_port_ip_sg() grep -q "permanent" check_err $? "Entry not added as \"permanent\" when should" bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "0.00" + grep -q " 0.00" check_err $? "\"permanent\" entry has a pending group timer" bridge mdb del dev br0 port $swp1 $grp_key vid 10 @@ -626,7 +626,7 @@ __cfg_test_port_ip_sg() grep -q "temp" check_err $? "Entry not added as \"temp\" when should" bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "0.00" + grep -q " 0.00" check_fail $? "\"temp\" entry has an unpending group timer" bridge mdb del dev br0 port $swp1 $grp_key vid 10 @@ -659,7 +659,7 @@ __cfg_test_port_ip_sg() grep -q "permanent" check_err $? "Entry not marked as \"permanent\" after replace" bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "0.00" + grep -q " 0.00" check_err $? "Entry has a pending group timer after replace" bridge mdb replace dev br0 port $swp1 $grp_key vid 10 temp @@ -667,7 +667,7 @@ __cfg_test_port_ip_sg() grep -q "temp" check_err $? "Entry not marked as \"temp\" after replace" bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "0.00" + grep -q " 0.00" check_fail $? "Entry has an unpending group timer after replace" bridge mdb del dev br0 port $swp1 $grp_key vid 10 @@ -850,6 +850,7 @@ cfg_test() __fwd_test_host_ip() { local grp=$1; shift + local dmac=$1; shift local src=$1; shift local mode=$1; shift local name @@ -872,27 +873,27 @@ __fwd_test_host_ip() # Packet should only be flooded to multicast router ports when there is # no matching MDB entry. The bridge is not configured as a multicast # router port. - $MZ $mode $h1.10 -c 1 -p 128 -A $src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $src -B $grp -t udp -q tc_check_packets "dev br0 ingress" 1 0 check_err $? "Packet locally received after flood" # Install a regular port group entry and expect the packet to not be # locally received. bridge mdb add dev br0 port $swp2 grp $grp temp vid 10 - $MZ $mode $h1.10 -c 1 -p 128 -A $src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $src -B $grp -t udp -q tc_check_packets "dev br0 ingress" 1 0 check_err $? "Packet locally received after installing a regular entry" # Add a host entry and expect the packet to be locally received. bridge mdb add dev br0 port br0 grp $grp temp vid 10 - $MZ $mode $h1.10 -c 1 -p 128 -A $src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $src -B $grp -t udp -q tc_check_packets "dev br0 ingress" 1 1 check_err $? "Packet not locally received after adding a host entry" # Remove the host entry and expect the packet to not be locally # received. bridge mdb del dev br0 port br0 grp $grp vid 10 - $MZ $mode $h1.10 -c 1 -p 128 -A $src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $src -B $grp -t udp -q tc_check_packets "dev br0 ingress" 1 1 check_err $? "Packet locally received after removing a host entry" @@ -905,8 +906,8 @@ __fwd_test_host_ip() fwd_test_host_ip() { - __fwd_test_host_ip "239.1.1.1" "192.0.2.1" "-4" - __fwd_test_host_ip "ff0e::1" "2001:db8:1::1" "-6" + __fwd_test_host_ip "239.1.1.1" "01:00:5e:01:01:01" "192.0.2.1" "-4" + __fwd_test_host_ip "ff0e::1" "33:33:00:00:00:01" "2001:db8:1::1" "-6" } fwd_test_host_l2() @@ -966,6 +967,7 @@ fwd_test_host() __fwd_test_port_ip() { local grp=$1; shift + local dmac=$1; shift local valid_src=$1; shift local invalid_src=$1; shift local mode=$1; shift @@ -999,43 +1001,43 @@ __fwd_test_port_ip() vlan_ethtype $eth_type vlan_id 10 dst_ip $grp \ src_ip $invalid_src action drop - $MZ $mode $h1.10 -c 1 -p 128 -A $valid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $valid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 1 0 check_err $? "Packet from valid source received on H2 before adding entry" - $MZ $mode $h1.10 -c 1 -p 128 -A $invalid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $invalid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 2 0 check_err $? "Packet from invalid source received on H2 before adding entry" bridge mdb add dev br0 port $swp2 grp $grp vid 10 \ filter_mode $filter_mode source_list $src_list - $MZ $mode $h1.10 -c 1 -p 128 -A $valid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $valid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 1 1 check_err $? "Packet from valid source not received on H2 after adding entry" - $MZ $mode $h1.10 -c 1 -p 128 -A $invalid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $invalid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 2 0 check_err $? "Packet from invalid source received on H2 after adding entry" bridge mdb replace dev br0 port $swp2 grp $grp vid 10 \ filter_mode exclude - $MZ $mode $h1.10 -c 1 -p 128 -A $valid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $valid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 1 2 check_err $? "Packet from valid source not received on H2 after allowing all sources" - $MZ $mode $h1.10 -c 1 -p 128 -A $invalid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $invalid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 2 1 check_err $? "Packet from invalid source not received on H2 after allowing all sources" bridge mdb del dev br0 port $swp2 grp $grp vid 10 - $MZ $mode $h1.10 -c 1 -p 128 -A $valid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $valid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 1 2 check_err $? "Packet from valid source received on H2 after deleting entry" - $MZ $mode $h1.10 -c 1 -p 128 -A $invalid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $invalid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 2 1 check_err $? "Packet from invalid source received on H2 after deleting entry" @@ -1047,11 +1049,11 @@ __fwd_test_port_ip() fwd_test_port_ip() { - __fwd_test_port_ip "239.1.1.1" "192.0.2.1" "192.0.2.2" "-4" "exclude" - __fwd_test_port_ip "ff0e::1" "2001:db8:1::1" "2001:db8:1::2" "-6" \ + __fwd_test_port_ip "239.1.1.1" "01:00:5e:01:01:01" "192.0.2.1" "192.0.2.2" "-4" "exclude" + __fwd_test_port_ip "ff0e::1" "33:33:00:00:00:01" "2001:db8:1::1" "2001:db8:1::2" "-6" \ "exclude" - __fwd_test_port_ip "239.1.1.1" "192.0.2.1" "192.0.2.2" "-4" "include" - __fwd_test_port_ip "ff0e::1" "2001:db8:1::1" "2001:db8:1::2" "-6" \ + __fwd_test_port_ip "239.1.1.1" "01:00:5e:01:01:01" "192.0.2.1" "192.0.2.2" "-4" "include" + __fwd_test_port_ip "ff0e::1" "33:33:00:00:00:01" "2001:db8:1::1" "2001:db8:1::2" "-6" \ "include" } @@ -1127,7 +1129,7 @@ ctrl_igmpv3_is_in_test() filter_mode include source_list 192.0.2.1 # IS_IN ( 192.0.2.2 ) - $MZ $h1.10 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ + $MZ $h1.10 -c 1 -a own -b 01:00:5e:01:01:01 -A 192.0.2.1 -B 239.1.1.1 \ -t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -q 192.0.2.2 @@ -1140,7 +1142,7 @@ ctrl_igmpv3_is_in_test() filter_mode include source_list 192.0.2.1 # IS_IN ( 192.0.2.2 ) - $MZ $h1.10 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ + $MZ $h1.10 -a own -b 01:00:5e:01:01:01 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ -t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -v "src" | \ @@ -1167,7 +1169,7 @@ ctrl_mldv2_is_in_test() # IS_IN ( 2001:db8:1::2 ) local p=$(mldv2_is_in_get fe80::1 ff0e::1 2001:db8:1::2) - $MZ -6 $h1.10 -c 1 -A fe80::1 -B ff0e::1 \ + $MZ -6 $h1.10 -a own -b 33:33:00:00:00:01 -c 1 -A fe80::1 -B ff0e::1 \ -t ip hop=1,next=0,p="$p" -q bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | \ @@ -1181,7 +1183,7 @@ ctrl_mldv2_is_in_test() filter_mode include source_list 2001:db8:1::1 # IS_IN ( 2001:db8:1::2 ) - $MZ -6 $h1.10 -c 1 -A fe80::1 -B ff0e::1 \ + $MZ -6 $h1.10 -a own -b 33:33:00:00:00:01 -c 1 -A fe80::1 -B ff0e::1 \ -t ip hop=1,next=0,p="$p" -q bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | grep -v "src" | \ @@ -1206,6 +1208,11 @@ ctrl_test() ctrl_mldv2_is_in_test } +if ! bridge mdb help 2>&1 | grep -q "replace"; then + echo "SKIP: iproute2 too old, missing bridge mdb replace support" + exit $ksft_skip +fi + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh index ae255b662ba3..3da9d93ab36f 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh @@ -252,7 +252,8 @@ ctl4_entries_add() local IPs=$(seq -f 192.0.2.%g 1 $((n - 1))) local peer=$(locus_dev_peer $locus) local GRP=239.1.1.${grp} - $MZ $peer -c 1 -A 192.0.2.1 -B $GRP \ + local dmac=01:00:5e:01:01:$(printf "%02x" $grp) + $MZ $peer -a own -b $dmac -c 1 -A 192.0.2.1 -B $GRP \ -t ip proto=2,p=$(igmpv3_is_in_get $GRP $IPs) -q sleep 1 @@ -272,7 +273,8 @@ ctl4_entries_del() local peer=$(locus_dev_peer $locus) local GRP=239.1.1.${grp} - $MZ $peer -c 1 -A 192.0.2.1 -B 224.0.0.2 \ + local dmac=01:00:5e:00:00:02 + $MZ $peer -a own -b $dmac -c 1 -A 192.0.2.1 -B 224.0.0.2 \ -t ip proto=2,p=$(igmpv2_leave_get $GRP) -q sleep 1 ! bridge mdb show dev br0 | grep -q $GRP @@ -289,8 +291,10 @@ ctl6_entries_add() local peer=$(locus_dev_peer $locus) local SIP=fe80::1 local GRP=ff0e::${grp} + local dmac=33:33:00:00:00:$(printf "%02x" $grp) local p=$(mldv2_is_in_get $SIP $GRP $IPs) - $MZ -6 $peer -c 1 -A $SIP -B $GRP -t ip hop=1,next=0,p="$p" -q + $MZ -6 $peer -a own -b $dmac -c 1 -A $SIP -B $GRP \ + -t ip hop=1,next=0,p="$p" -q sleep 1 local nn=$(bridge mdb show dev br0 | grep $GRP | wc -l) @@ -310,8 +314,10 @@ ctl6_entries_del() local peer=$(locus_dev_peer $locus) local SIP=fe80::1 local GRP=ff0e::${grp} + local dmac=33:33:00:00:00:$(printf "%02x" $grp) local p=$(mldv1_done_get $SIP $GRP) - $MZ -6 $peer -c 1 -A $SIP -B $GRP -t ip hop=1,next=0,p="$p" -q + $MZ -6 $peer -a own -b $dmac -c 1 -A $SIP -B $GRP \ + -t ip hop=1,next=0,p="$p" -q sleep 1 ! bridge mdb show dev br0 | grep -q $GRP } @@ -1328,6 +1334,11 @@ test_8021qvs() switch_destroy } +if ! bridge link help 2>&1 | grep -q "mcast_max_groups"; then + echo "SKIP: iproute2 too old, missing bridge \"mcast_max_groups\" support" + exit $ksft_skip +fi + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh index dbb9fcf759e0..aa2eafb7b243 100755 --- a/tools/testing/selftests/net/forwarding/ethtool.sh +++ b/tools/testing/selftests/net/forwarding/ethtool.sh @@ -286,6 +286,8 @@ different_speeds_autoneg_on() ethtool -s $h1 autoneg on } +skip_on_veth + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh index 072faa77f53b..17f89c3b7c02 100755 --- a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh +++ b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh @@ -108,6 +108,8 @@ no_cable() ip link set dev $swp3 down } +skip_on_veth + setup_prepare tests_run diff --git a/tools/testing/selftests/net/forwarding/ethtool_mm.sh b/tools/testing/selftests/net/forwarding/ethtool_mm.sh index c580ad623848..39e736f30322 100755 --- a/tools/testing/selftests/net/forwarding/ethtool_mm.sh +++ b/tools/testing/selftests/net/forwarding/ethtool_mm.sh @@ -258,11 +258,6 @@ h2_destroy() setup_prepare() { - check_ethtool_mm_support - check_tc_fp_support - require_command lldptool - bail_on_lldpad "autoconfigure the MAC Merge layer" "configure it manually" - h1=${NETIFS[p1]} h2=${NETIFS[p2]} @@ -278,6 +273,19 @@ cleanup() h1_destroy } +check_ethtool_mm_support +check_tc_fp_support +require_command lldptool +bail_on_lldpad "autoconfigure the MAC Merge layer" "configure it manually" + +for netif in ${NETIFS[@]}; do + ethtool --show-mm $netif 2>&1 &> /dev/null + if [[ $? -ne 0 ]]; then + echo "SKIP: $netif does not support MAC Merge" + exit $ksft_skip + fi +done + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh b/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh index eb9ec4a68f84..7594bbb49029 100755 --- a/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh +++ b/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh @@ -99,6 +99,8 @@ test_stats_rx() test_stats g2a rx } +skip_on_veth + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh index 9f5b3e2e5e95..49fa94b53a1c 100755 --- a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh +++ b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh @@ -14,6 +14,8 @@ ALL_TESTS=" NUM_NETIFS=4 source lib.sh +require_command $TROUTE6 + h1_create() { simple_if_init $h1 2001:1:1::2/64 diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 9ddb68dd6a08..f69015bf2dea 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -30,6 +30,7 @@ REQUIRE_MZ=${REQUIRE_MZ:=yes} REQUIRE_MTOOLS=${REQUIRE_MTOOLS:=no} STABLE_MAC_ADDRS=${STABLE_MAC_ADDRS:=no} TCPDUMP_EXTRA_FLAGS=${TCPDUMP_EXTRA_FLAGS:=} +TROUTE6=${TROUTE6:=traceroute6} relative_path="${BASH_SOURCE%/*}" if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then @@ -163,6 +164,17 @@ check_port_mab_support() fi } +skip_on_veth() +{ + local kind=$(ip -j -d link show dev ${NETIFS[p1]} | + jq -r '.[].linkinfo.info_kind') + + if [[ $kind == veth ]]; then + echo "SKIP: Test cannot be run with veth pairs" + exit $ksft_skip + fi +} + if [[ "$(id -u)" -ne 0 ]]; then echo "SKIP: need root privileges" exit $ksft_skip @@ -225,6 +237,11 @@ create_netif_veth() for ((i = 1; i <= NUM_NETIFS; ++i)); do local j=$((i+1)) + if [ -z ${NETIFS[p$i]} ]; then + echo "SKIP: Cannot create interface. Name not specified" + exit $ksft_skip + fi + ip link show dev ${NETIFS[p$i]} &> /dev/null if [[ $? -ne 0 ]]; then ip link add ${NETIFS[p$i]} type veth \ diff --git a/tools/testing/selftests/net/forwarding/settings b/tools/testing/selftests/net/forwarding/settings new file mode 100644 index 000000000000..e7b9417537fb --- /dev/null +++ b/tools/testing/selftests/net/forwarding/settings @@ -0,0 +1 @@ +timeout=0 diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index a96cff8e7219..b0f5e55d2d0b 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -9,6 +9,8 @@ NUM_NETIFS=4 source tc_common.sh source lib.sh +require_command ncat + tcflags="skip_hw" h1_create() @@ -220,9 +222,9 @@ mirred_egress_to_ingress_tcp_test() ip_proto icmp \ action drop - ip vrf exec v$h1 nc --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & + ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & local rpid=$! - ip vrf exec v$h1 nc -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 + ip vrf exec v$h1 ncat -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 wait -n $rpid cmp -s $mirred_e2i_tf1 $mirred_e2i_tf2 check_err $? "server output check failed" diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh index 683711f41aa9..b1daad19b01e 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower.sh @@ -52,8 +52,8 @@ match_dst_mac_test() tc_check_packets "dev $h2 ingress" 101 1 check_fail $? "Matched on a wrong filter" - tc_check_packets "dev $h2 ingress" 102 1 - check_err $? "Did not match on correct filter" + tc_check_packets "dev $h2 ingress" 102 0 + check_fail $? "Did not match on correct filter" tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower @@ -78,8 +78,8 @@ match_src_mac_test() tc_check_packets "dev $h2 ingress" 101 1 check_fail $? "Matched on a wrong filter" - tc_check_packets "dev $h2 ingress" 102 1 - check_err $? "Did not match on correct filter" + tc_check_packets "dev $h2 ingress" 102 0 + check_fail $? "Did not match on correct filter" tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower diff --git a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh index e22c2d28b6eb..20a7cb7222b8 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh @@ -127,6 +127,7 @@ test_l2_miss_multicast_common() local proto=$1; shift local sip=$1; shift local dip=$1; shift + local dmac=$1; shift local mode=$1; shift local name=$1; shift @@ -142,7 +143,7 @@ test_l2_miss_multicast_common() action pass # Before adding MDB entry. - $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + $MZ $mode $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q tc_check_packets "dev $swp2 egress" 101 1 check_err $? "Unregistered multicast filter was not hit before adding MDB entry" @@ -153,7 +154,7 @@ test_l2_miss_multicast_common() # Adding MDB entry. bridge mdb replace dev br1 port $swp2 grp $dip permanent - $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + $MZ $mode $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q tc_check_packets "dev $swp2 egress" 101 1 check_err $? "Unregistered multicast filter was hit after adding MDB entry" @@ -164,7 +165,7 @@ test_l2_miss_multicast_common() # Deleting MDB entry. bridge mdb del dev br1 port $swp2 grp $dip - $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + $MZ $mode $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q tc_check_packets "dev $swp2 egress" 101 2 check_err $? "Unregistered multicast filter was not hit after deleting MDB entry" @@ -183,10 +184,11 @@ test_l2_miss_multicast_ipv4() local proto="ipv4" local sip=192.0.2.1 local dip=239.1.1.1 + local dmac=01:00:5e:01:01:01 local mode="-4" local name="IPv4" - test_l2_miss_multicast_common $proto $sip $dip $mode $name + test_l2_miss_multicast_common $proto $sip $dip $dmac $mode $name } test_l2_miss_multicast_ipv6() @@ -194,10 +196,11 @@ test_l2_miss_multicast_ipv6() local proto="ipv6" local sip=2001:db8:1::1 local dip=ff0e::1 + local dmac=33:33:00:00:00:01 local mode="-6" local name="IPv6" - test_l2_miss_multicast_common $proto $sip $dip $mode $name + test_l2_miss_multicast_common $proto $sip $dip $dmac $mode $name } test_l2_miss_multicast() diff --git a/tools/testing/selftests/net/forwarding/tc_tunnel_key.sh b/tools/testing/selftests/net/forwarding/tc_tunnel_key.sh index 5ac184d51809..5a5dd9034819 100755 --- a/tools/testing/selftests/net/forwarding/tc_tunnel_key.sh +++ b/tools/testing/selftests/net/forwarding/tc_tunnel_key.sh @@ -104,11 +104,14 @@ tunnel_key_nofrag_test() local i tc filter add dev $swp1 ingress protocol ip pref 100 handle 100 \ - flower ip_flags nofrag action drop + flower src_ip 192.0.2.1 dst_ip 192.0.2.2 ip_proto udp \ + ip_flags nofrag action drop tc filter add dev $swp1 ingress protocol ip pref 101 handle 101 \ - flower ip_flags firstfrag action drop + flower src_ip 192.0.2.1 dst_ip 192.0.2.2 ip_proto udp \ + ip_flags firstfrag action drop tc filter add dev $swp1 ingress protocol ip pref 102 handle 102 \ - flower ip_flags nofirstfrag action drop + flower src_ip 192.0.2.1 dst_ip 192.0.2.2 ip_proto udp \ + ip_flags nofirstfrag action drop # test 'nofrag' set tc filter add dev h1-et egress protocol all pref 1 handle 1 matchall $tcflags \ diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 3c2096ac97ef..d01b73a8ed0f 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -705,6 +705,7 @@ pm_nl_del_endpoint() local addr=$3 if [ $ip_mptcp -eq 1 ]; then + [ $id -ne 0 ] && addr='' ip -n $ns mptcp endpoint delete id $id $addr else ip netns exec $ns ./pm_nl_ctl del $id $addr @@ -795,10 +796,11 @@ pm_nl_check_endpoint() fi if [ $ip_mptcp -eq 1 ]; then + # get line and trim trailing whitespace line=$(ip -n $ns mptcp endpoint show $id) + line="${line% }" # the dump order is: address id flags port dev - expected_line="$addr" - [ -n "$addr" ] && expected_line="$expected_line $addr" + [ -n "$addr" ] && expected_line="$addr" expected_line="$expected_line $id" [ -n "$_flags" ] && expected_line="$expected_line ${_flags//","/" "}" [ -n "$dev" ] && expected_line="$expected_line $dev" diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index dfe3d287f01d..f838dd370f6a 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -361,6 +361,7 @@ err_buf= tcpdump_pids= nettest_pids= socat_pids= +tmpoutfile= err() { err_buf="${err_buf}${1} @@ -951,6 +952,7 @@ cleanup() { ip link del veth_A-R1 2>/dev/null ovs-vsctl --if-exists del-port vxlan_a 2>/dev/null ovs-vsctl --if-exists del-br ovs_br0 2>/dev/null + rm -f "$tmpoutfile" } mtu() { @@ -1328,6 +1330,39 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() { check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on bridged ${type} interface" pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on locally bridged ${type} interface" + + tmpoutfile=$(mktemp) + + # Flush Exceptions, retry with TCP + run_cmd ${ns_a} ip route flush cached ${dst} + run_cmd ${ns_b} ip route flush cached ${dst} + run_cmd ${ns_c} ip route flush cached ${dst} + + for target in "${ns_a}" "${ns_c}" ; do + if [ ${family} -eq 4 ]; then + TCPDST=TCP:${dst}:50000 + else + TCPDST="TCP:[${dst}]:50000" + fi + ${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000 STDOUT > $tmpoutfile & + + sleep 1 + + dd if=/dev/zero of=/dev/stdout status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3 + + size=$(du -sb $tmpoutfile) + size=${size%%/tmp/*} + + [ $size -ne 1048576 ] && err "File size $size mismatches exepcted value in locally bridged vxlan test" && return 1 + done + + rm -f "$tmpoutfile" + + # Check that exceptions were created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_c}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "tcp: exceeding link layer MTU on bridged ${type} interface" + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "tcp exceeding link layer MTU on locally bridged ${type} interface" } test_pmtu_ipv4_br_vxlan4_exception() { diff --git a/tools/testing/selftests/net/so_incoming_cpu.c b/tools/testing/selftests/net/so_incoming_cpu.c index 0e04f9fef986..a14818164102 100644 --- a/tools/testing/selftests/net/so_incoming_cpu.c +++ b/tools/testing/selftests/net/so_incoming_cpu.c @@ -159,7 +159,7 @@ void create_clients(struct __test_metadata *_metadata, /* Make sure SYN will be processed on the i-th CPU * and finally distributed to the i-th listener. */ - sched_setaffinity(0, sizeof(cpu_set), &cpu_set); + ret = sched_setaffinity(0, sizeof(cpu_set), &cpu_set); ASSERT_EQ(ret, 0); for (j = 0; j < CLIENT_PER_SERVER; j++) { diff --git a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c index 5cbc392944a6..2c0d2b1126c1 100644 --- a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c +++ b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c @@ -1,6 +1,4 @@ // SPDX-License-Identifier: GPL-2.0-only -#include <sys/prctl.h> - #define THIS_PROGRAM "./vstate_exec_nolibc" int main(int argc, char **argv) diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index b357ba24af06..7a957c7d459a 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -4,8 +4,10 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) CLANG_FLAGS += -no-integrated-as endif +top_srcdir = ../../../.. + CFLAGS += -O2 -Wall -g -I./ $(KHDR_INCLUDES) -L$(OUTPUT) -Wl,-rpath=./ \ - $(CLANG_FLAGS) + $(CLANG_FLAGS) -I$(top_srcdir)/tools/include LDLIBS += -lpthread -ldl # Own dependencies because we only want to build against 1st prerequisite, but diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index a723da253244..96e812bdf8a4 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -31,6 +31,8 @@ #include <sys/auxv.h> #include <linux/auxvec.h> +#include <linux/compiler.h> + #include "../kselftest.h" #include "rseq.h" diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json index a44455372646..08d4861c2e78 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json @@ -131,5 +131,30 @@ "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" ] + }, + { + "id": "3e1e", + "name": "Add taprio Qdisc with an invalid cycle-time", + "category": [ + "qdisc", + "taprio" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 8\" > /sys/bus/netdevsim/new_device", + "$TC qdisc add dev $ETH root handle 1: taprio num_tc 3 map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@0 1@0 base-time 1000000000 sched-entry S 01 300000 flags 0x1 clockid CLOCK_TAI cycle-time 4294967296 || /bin/true", + "$IP link set dev $ETH up", + "$IP addr add 10.10.10.10/24 dev $ETH" + ], + "cmdUnderTest": "/bin/true", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $ETH", + "matchPattern": "qdisc taprio 1: root refcnt", + "matchCount": "0", + "teardown": [ + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] } ] diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile index 43a254f0e14d..21a98ba565ab 100644 --- a/tools/testing/vsock/Makefile +++ b/tools/testing/vsock/Makefile @@ -8,5 +8,5 @@ vsock_perf: vsock_perf.o CFLAGS += -g -O2 -Werror -Wall -I. -I../../include -I../../../usr/include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE .PHONY: all test clean clean: - ${RM} *.o *.d vsock_test vsock_diag_test + ${RM} *.o *.d vsock_test vsock_diag_test vsock_perf -include *.d |