diff options
258 files changed, 3653 insertions, 1511 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..a7d37e124831 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -19,3 +19,5 @@ are configurable at compile, boot or run time. l1d_flush.rst processor_mmio_stale_data.rst cross-thread-rsb.rst + srso + gather_data_sampling.rst diff --git a/Documentation/admin-guide/hw-vuln/srso.rst b/Documentation/admin-guide/hw-vuln/srso.rst new file mode 100644 index 000000000000..32eb5e6db272 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/srso.rst @@ -0,0 +1,133 @@ +.. 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. + + (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/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 49f032556cf1..d984c9a7b12c 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/ @@ -9679,6 +9679,7 @@ 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/ @@ -13804,7 +13805,7 @@ 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* @@ -13827,7 +13828,7 @@ 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 @@ -13900,7 +13901,7 @@ 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 @@ -13927,7 +13928,7 @@ 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 @@ -13966,7 +13967,7 @@ 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 @@ -13982,7 +13983,7 @@ 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 @@ -13999,7 +14000,7 @@ 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 @@ -14028,7 +14029,7 @@ 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/ @@ -18533,17 +18534,14 @@ 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) @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* 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/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/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index d818ece23b4a..3f6b507970eb 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -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/unaligned.c b/arch/parisc/kernel/unaligned.c index 033b9e50b44a..813062701922 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -337,7 +337,7 @@ 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 +473,7 @@ 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 +482,7 @@ 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 +490,12 @@ 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 +503,24 @@ 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/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..389941c7f209 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -669,6 +669,39 @@ 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 +716,7 @@ 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/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/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/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/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/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/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/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..973db0406528 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -682,9 +682,13 @@ 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); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 26ad7ca423e7..b55d8f82b621 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -75,6 +75,10 @@ static const int amd_zenbleed[] = AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 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 +1134,11 @@ 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 +1299,32 @@ 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..e76813230192 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 +523,18 @@ 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 so do: (A | B) - (A & B) in order to compute the XOR + * of the two function addresses: + */ +. = ASSERT(((srso_untrain_ret_alias | srso_safe_ret_alias) - + (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..19d9ff92d699 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -314,6 +314,8 @@ u64 __read_mostly host_xcr0; static struct kmem_cache *x86_emulator_cache; +extern bool gds_ucode_mitigated(void); + /* * When called, it means the previous get/set msr reached an invalid msr. * Return true if we want to ignore/silent this failed msr access. @@ -1616,7 +1618,7 @@ 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 +1675,9 @@ 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/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..52df435eecf8 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -577,6 +577,18 @@ ssize_t __weak cpu_show_retbleed(struct device *dev, return sysfs_emit(buf, "Not affected\n"); } +ssize_t __weak cpu_show_spec_rstack_overflow(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "Not affected\n"); +} + +ssize_t __weak cpu_show_gds(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); @@ -588,6 +600,8 @@ 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 +615,8 @@ 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/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..ac4daaf294a3 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -164,6 +164,22 @@ 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"), 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/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/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/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/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/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/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 c9b6440fbc0e..d26c69d84c1e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -5927,7 +5927,9 @@ 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/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index fd7eb4a52918..9a3e5ec16972 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1619,8 +1619,10 @@ 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/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 e5e37a33fd81..eac2d0573241 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5855,6 +5855,9 @@ 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); @@ -5883,7 +5886,16 @@ 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 83ab89f44250..437b510f2b80 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 01535b03eab6..cdf5251e5679 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]; @@ -1504,8 +1507,8 @@ 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; @@ -1526,11 +1529,9 @@ 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) { @@ -1572,10 +1573,69 @@ 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); @@ -1587,12 +1647,22 @@ 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; } @@ -4829,11 +4899,14 @@ 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; @@ -5395,6 +5468,7 @@ 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 @@ -5406,11 +5480,6 @@ 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. @@ -5446,6 +5515,23 @@ 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/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 4bffc3cb502f..1c6ab340c020 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -196,6 +196,10 @@ 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 2a10254edbbd..e7701866d8b4 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; } @@ -6170,6 +6189,7 @@ 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; @@ -6246,6 +6266,8 @@ 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. */ @@ -6270,6 +6292,8 @@ 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; @@ -6648,8 +6672,11 @@ 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]; @@ -6662,6 +6689,9 @@ 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/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 0c88cf47af01..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 @@ -1461,10 +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_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 61a5ddd6e585..bc9d5a5bea01 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5263,6 +5263,7 @@ 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; @@ -5291,9 +5292,19 @@ 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_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index a2f2f344f206..318083690fcd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1940,9 +1940,7 @@ 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); @@ -1963,12 +1961,6 @@ 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); @@ -4264,6 +4256,7 @@ 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; @@ -4281,6 +4274,18 @@ 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/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index 433541ac36a7..0313432d50a1 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/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/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 0389e84f9815..f4fe06a5042e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1998,7 +1998,7 @@ 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 d54afb07d972..8e2028d20a9e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -364,7 +364,7 @@ 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_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/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 31e2f2c74e15..48f330d59284 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> @@ -2411,9 +2412,12 @@ 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; @@ -2429,15 +2433,40 @@ 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 adc05f944c14..2c3e36b2dd7f 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/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 13c4121fa309..37fb033e1c29 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -466,21 +466,27 @@ 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) @@ -515,11 +521,11 @@ 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; } @@ -865,9 +871,6 @@ 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; @@ -884,12 +887,14 @@ 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; @@ -2113,8 +2118,6 @@ 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/tun.c b/drivers/net/tun.c index 973b2fc74de3..a05765448803 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1596,7 +1596,7 @@ 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; 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/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index 9ed33e2d6da0..cc9a377c06fd 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -2221,8 +2221,7 @@ 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/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/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c index 1efa4da3cebc..cebefa3b1db3 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/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/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/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/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/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/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/exfat/dir.c b/fs/exfat/dir.c index 598081d0d059..e1586bba6d86 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -306,10 +306,11 @@ out: 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, 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/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/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/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/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/linux/cpu.h b/include/linux/cpu.h index 6e6e57ec69e8..23ac87be1ff1 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -70,6 +70,8 @@ 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 __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, 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/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/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/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/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/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/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/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/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/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/filter.c b/net/core/filter.c index 7c37f4646c20..a094694899c9 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/skmsg.c b/net/core/skmsg.c index e6dfc846018f..a0659fc29bcc 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 51f7d94eccf7..525619776c6f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1779,7 +1779,7 @@ 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); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 08ab108206bf..8f07fea39d9e 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -146,13 +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/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/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 93f14d39fef6..09d36bcbd7d4 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3244,13 +3244,9 @@ 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; @@ -3390,25 +3386,19 @@ 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, @@ -3457,13 +3447,9 @@ 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/ipv6/ndisc.c b/net/ipv6/ndisc.c index c394799be38f..553c8664e0a7 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/mptcp/protocol.c b/net/mptcp/protocol.c index 1c079e83481e..48e649fe2360 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2334,7 +2334,7 @@ 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 */ @@ -3327,7 +3327,7 @@ 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 795f422e8597..79fc5cdb67bc 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -326,7 +326,6 @@ 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/subflow.c b/net/mptcp/subflow.c index ad7080fabb2f..9bf3c7bc1762 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/packet/af_packet.c b/net/packet/af_packet.c index 0a65e696a4c6..8f97648d652f 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(); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 0c013d2b5d8f..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); @@ -436,13 +436,60 @@ out: return rc; } +/* 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) | \ + (1UL << SOCK_LINGER) | \ + (1UL << SOCK_BROADCAST) | \ + (1UL << SOCK_TIMESTAMP) | \ + (1UL << SOCK_DBG) | \ + (1UL << SOCK_RCVTSTAMP) | \ + (1UL << SOCK_RCVTSTAMPNS) | \ + (1UL << SOCK_LOCALROUTE) | \ + (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE) | \ + (1UL << SOCK_RXQ_OVFL) | \ + (1UL << SOCK_WIFI_STATUS) | \ + (1UL << SOCK_NOFCS) | \ + (1UL << SOCK_FILTER_LOCKED) | \ + (1UL << SOCK_TSTAMP_NEW)) + +/* 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_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 = READ_ONCE(osk->sk_mark); @@ -453,26 +500,10 @@ static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, nsk->sk_flags &= ~mask; nsk->sk_flags |= osk->sk_flags & mask; + + smc_adjust_sock_bufsizes(nsk, osk, mask); } -#define SK_FLAGS_SMC_TO_CLC ((1UL << SOCK_URGINLINE) | \ - (1UL << SOCK_KEEPOPEN) | \ - (1UL << SOCK_LINGER) | \ - (1UL << SOCK_BROADCAST) | \ - (1UL << SOCK_TIMESTAMP) | \ - (1UL << SOCK_DBG) | \ - (1UL << SOCK_RCVTSTAMP) | \ - (1UL << SOCK_RCVTSTAMPNS) | \ - (1UL << SOCK_LOCALROUTE) | \ - (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE) | \ - (1UL << SOCK_RXQ_OVFL) | \ - (1UL << SOCK_WIFI_STATUS) | \ - (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) - */ 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 5df18f696d7f..2392d06845aa 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, @@ -545,18 +544,8 @@ 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, @@ -1454,14 +1443,26 @@ 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; } @@ -1470,4 +1471,5 @@ 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 7dbb8cd8f809..f550c84f3408 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/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/xdp/xsk.c b/net/xdp/xsk.c index 47796a5a79b3..fcfc8472f73d 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -1189,6 +1189,7 @@ 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/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/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/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/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/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 54ec2b7b7b8c..a6f2c0b9555d 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -2110,6 +2110,11 @@ 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 $? 0 "Maximum nexthop ID dump" + # # groups # @@ -2330,6 +2335,11 @@ basic_res() run_cmd "$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 $h1 2001:1:1::2/64 diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 71f7c0c49677..e37a15eda6c2 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -30,6 +30,7 @@ REQUIRE_MZ=${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 63658b0416fb..ee1f89a872b3 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -761,6 +761,7 @@ 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 @@ -846,10 +847,11 @@ 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 ${type} interface" } test_pmtu_ipv4_br_vxlan4_exception() { diff --git a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c index 5cbc392944a6..2c0d2b1126c1 100644 --- a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c +++ b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c @@ -1,6 +1,4 @@ // SPDX-License-Identifier: GPL-2.0-only -#include <sys/prctl.h> - #define THIS_PROGRAM "./vstate_exec_nolibc" int main(int argc, char **argv) diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index b357ba24af06..7a957c7d459a 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -4,8 +4,10 @@ ifneq ($(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" |