diff options
225 files changed, 3121 insertions, 1287 deletions
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/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/MAINTAINERS b/MAINTAINERS index 0f966f05fb0d..6dd58c05ddcd 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/ @@ -13786,7 +13786,7 @@ 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* @@ -13809,7 +13809,7 @@ 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 @@ -13882,7 +13882,7 @@ 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 @@ -13909,7 +13909,7 @@ 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 @@ -13948,7 +13948,7 @@ 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 @@ -13964,7 +13964,7 @@ 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 @@ -13981,7 +13981,7 @@ 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 @@ -14010,7 +14010,7 @@ 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/ @@ -16293,6 +16293,7 @@ F: drivers/pci/controller/dwc/pci-exynos.c PCI DRIVER FOR SYNOPSYS DESIGNWARE M: Jingoo Han <jingoohan1@gmail.com> M: Gustavo Pimentel <gustavo.pimentel@synopsys.com> +M: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org> L: linux-pci@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pci/snps,dw-pcie-ep.yaml @@ -18508,17 +18509,14 @@ 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) 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/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/Kconfig.debug b/arch/parisc/Kconfig.debug index 1401e4c5fe5f..bf2b21b96f0b 100644 --- a/arch/parisc/Kconfig.debug +++ b/arch/parisc/Kconfig.debug @@ -2,7 +2,7 @@ # config LIGHTWEIGHT_SPINLOCK_CHECK bool "Enable lightweight spinlock checks" - depends on SMP && !DEBUG_SPINLOCK + depends on DEBUG_KERNEL && SMP && !DEBUG_SPINLOCK default y help Add checks with low performance impact to the spinlock functions diff --git a/arch/parisc/boot/compressed/misc.c b/arch/parisc/boot/compressed/misc.c index 7ee49f5881d1..d389359e22ac 100644 --- a/arch/parisc/boot/compressed/misc.c +++ b/arch/parisc/boot/compressed/misc.c @@ -117,7 +117,7 @@ char *strchr(const char *s, int c) return NULL; } -int puts(const char *s) +static int puts(const char *s) { const char *nuline = s; @@ -172,7 +172,7 @@ static int print_num(unsigned long num, int base) return 0; } -int printf(const char *fmt, ...) +static int printf(const char *fmt, ...) { va_list args; int i = 0; @@ -204,13 +204,13 @@ void abort(void) } #undef malloc -void *malloc(size_t size) +static void *malloc(size_t size) { return malloc_gzip(size); } #undef free -void free(void *ptr) +static void free(void *ptr) { return free_gzip(ptr); } @@ -278,7 +278,7 @@ static void parse_elf(void *output) free(phdrs); } -unsigned long decompress_kernel(unsigned int started_wide, +asmlinkage unsigned long __visible decompress_kernel(unsigned int started_wide, unsigned int command_line, const unsigned int rd_start, const unsigned int rd_end) diff --git a/arch/parisc/include/asm/dma.h b/arch/parisc/include/asm/dma.h index 9e8c101de902..582fb5d1a5d5 100644 --- a/arch/parisc/include/asm/dma.h +++ b/arch/parisc/include/asm/dma.h @@ -14,6 +14,8 @@ #define dma_outb outb #define dma_inb inb +extern unsigned long pcxl_dma_start; + /* ** DMA_CHUNK_SIZE is used by the SCSI mid-layer to break up ** (or rather not merge) DMAs into manageable chunks. diff --git a/arch/parisc/include/asm/ftrace.h b/arch/parisc/include/asm/ftrace.h index a7cf0d05ccf4..f1cc1ee3a647 100644 --- a/arch/parisc/include/asm/ftrace.h +++ b/arch/parisc/include/asm/ftrace.h @@ -12,6 +12,10 @@ extern void mcount(void); extern unsigned long sys_call_table[]; extern unsigned long return_address(unsigned int); +struct ftrace_regs; +extern void ftrace_function_trampoline(unsigned long parent, + unsigned long self_addr, unsigned long org_sp_gr3, + struct ftrace_regs *fregs); #ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_caller(void); diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h index edfcb9858bcb..0b326e52255e 100644 --- a/arch/parisc/include/asm/spinlock.h +++ b/arch/parisc/include/asm/spinlock.h @@ -7,8 +7,6 @@ #include <asm/processor.h> #include <asm/spinlock_types.h> -#define SPINLOCK_BREAK_INSN 0x0000c006 /* break 6,6 */ - static inline void arch_spin_val_check(int lock_val) { if (IS_ENABLED(CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK)) diff --git a/arch/parisc/include/asm/spinlock_types.h b/arch/parisc/include/asm/spinlock_types.h index d65934079ebd..efd06a897c6a 100644 --- a/arch/parisc/include/asm/spinlock_types.h +++ b/arch/parisc/include/asm/spinlock_types.h @@ -4,6 +4,10 @@ #define __ARCH_SPIN_LOCK_UNLOCKED_VAL 0x1a46 +#define SPINLOCK_BREAK_INSN 0x0000c006 /* break 6,6 */ + +#ifndef __ASSEMBLY__ + typedef struct { #ifdef CONFIG_PA20 volatile unsigned int slock; @@ -27,6 +31,8 @@ typedef struct { volatile unsigned int counter; } arch_rwlock_t; +#endif /* __ASSEMBLY__ */ + #define __ARCH_RW_LOCK_UNLOCKED__ 0x01000000 #define __ARCH_RW_LOCK_UNLOCKED { .lock_mutex = __ARCH_SPIN_LOCK_UNLOCKED, \ .counter = __ARCH_RW_LOCK_UNLOCKED__ } diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 6d1c781eb1db..8f37e75f2fb9 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -74,8 +74,8 @@ static DEFINE_SPINLOCK(pdc_lock); #endif -unsigned long pdc_result[NUM_PDC_RESULT] __aligned(8); -unsigned long pdc_result2[NUM_PDC_RESULT] __aligned(8); +static unsigned long pdc_result[NUM_PDC_RESULT] __aligned(8); +static unsigned long pdc_result2[NUM_PDC_RESULT] __aligned(8); #ifdef CONFIG_64BIT #define WIDE_FIRMWARE 0x1 @@ -334,7 +334,7 @@ int __pdc_cpu_rendezvous(void) /** * pdc_cpu_rendezvous_lock - Lock PDC while transitioning to rendezvous state */ -void pdc_cpu_rendezvous_lock(void) +void pdc_cpu_rendezvous_lock(void) __acquires(&pdc_lock) { spin_lock(&pdc_lock); } @@ -342,7 +342,7 @@ void pdc_cpu_rendezvous_lock(void) /** * pdc_cpu_rendezvous_unlock - Unlock PDC after reaching rendezvous state */ -void pdc_cpu_rendezvous_unlock(void) +void pdc_cpu_rendezvous_unlock(void) __releases(&pdc_lock) { spin_unlock(&pdc_lock); } diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index 4d392e4ed358..d1defb9ede70 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -53,7 +53,7 @@ static void __hot prepare_ftrace_return(unsigned long *parent, static ftrace_func_t ftrace_func; -void notrace __hot ftrace_function_trampoline(unsigned long parent, +asmlinkage void notrace __hot ftrace_function_trampoline(unsigned long parent, unsigned long self_addr, unsigned long org_sp_gr3, struct ftrace_regs *fregs) diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index 00297e8e1c88..6f0c92e8149d 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/syscalls.h> +#include <linux/libgcc.h> #include <linux/string.h> EXPORT_SYMBOL(memset); @@ -92,12 +93,6 @@ EXPORT_SYMBOL($$divI_12); EXPORT_SYMBOL($$divI_14); EXPORT_SYMBOL($$divI_15); -extern void __ashrdi3(void); -extern void __ashldi3(void); -extern void __lshrdi3(void); -extern void __muldi3(void); -extern void __ucmpdi2(void); - EXPORT_SYMBOL(__ashrdi3); EXPORT_SYMBOL(__ashldi3); EXPORT_SYMBOL(__lshrdi3); diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index 3f6b507970eb..bf9f192c826e 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -39,7 +39,7 @@ static struct proc_dir_entry * proc_gsc_root __read_mostly = NULL; static unsigned long pcxl_used_bytes __read_mostly; static unsigned long pcxl_used_pages __read_mostly; -extern unsigned long pcxl_dma_start; /* Start of pcxl dma mapping area */ +unsigned long pcxl_dma_start __ro_after_init; /* pcxl dma mapping area start */ static DEFINE_SPINLOCK(pcxl_res_lock); static char *pcxl_res_map; static int pcxl_res_hint; @@ -381,7 +381,7 @@ pcxl_dma_init(void) pcxl_res_map = (char *)__get_free_pages(GFP_KERNEL, get_order(pcxl_res_size)); memset(pcxl_res_map, 0, pcxl_res_size); - proc_gsc_root = proc_mkdir("gsc", NULL); + proc_gsc_root = proc_mkdir("bus/gsc", NULL); if (!proc_gsc_root) printk(KERN_WARNING "pcxl_dma_init: Unable to create gsc /proc dir entry\n"); diff --git a/arch/parisc/kernel/pdt.c b/arch/parisc/kernel/pdt.c index 0d24735bd918..0f9b3b5914cf 100644 --- a/arch/parisc/kernel/pdt.c +++ b/arch/parisc/kernel/pdt.c @@ -354,10 +354,8 @@ static int __init pdt_initcall(void) return -ENODEV; kpdtd_task = kthread_run(pdt_mainloop, NULL, "kpdtd"); - if (IS_ERR(kpdtd_task)) - return PTR_ERR(kpdtd_task); - return 0; + return PTR_ERR_OR_ZERO(kpdtd_task); } late_initcall(pdt_initcall); diff --git a/arch/parisc/kernel/perf.c b/arch/parisc/kernel/perf.c index 90b04d8af212..b0f0816879df 100644 --- a/arch/parisc/kernel/perf.c +++ b/arch/parisc/kernel/perf.c @@ -57,7 +57,7 @@ struct rdr_tbl_ent { static int perf_processor_interface __read_mostly = UNKNOWN_INTF; static int perf_enabled __read_mostly; static DEFINE_SPINLOCK(perf_lock); -struct parisc_device *cpu_device __read_mostly; +static struct parisc_device *cpu_device __read_mostly; /* RDRs to write for PCX-W */ static const int perf_rdrs_W[] = diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index 00b0df97afb1..762289b9984e 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -26,6 +26,7 @@ #include <asm/processor.h> #include <asm/page.h> #include <asm/pdc.h> +#include <asm/smp.h> #include <asm/pdcpat.h> #include <asm/irq.h> /* for struct irq_region */ #include <asm/parisc-device.h> diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index 573f8303e2b0..211a4afdd282 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -40,11 +40,6 @@ static char __initdata command_line[COMMAND_LINE_SIZE]; -/* Intended for ccio/sba/cpu statistics under /proc/bus/{runway|gsc} */ -struct proc_dir_entry * proc_runway_root __read_mostly = NULL; -struct proc_dir_entry * proc_gsc_root __read_mostly = NULL; -struct proc_dir_entry * proc_mckinley_root __read_mostly = NULL; - static void __init setup_cmdline(char **cmdline_p) { extern unsigned int boot_args[]; @@ -196,48 +191,6 @@ const struct seq_operations cpuinfo_op = { .show = show_cpuinfo }; -static void __init parisc_proc_mkdir(void) -{ - /* - ** Can't call proc_mkdir() until after proc_root_init() has been - ** called by start_kernel(). In other words, this code can't - ** live in arch/.../setup.c because start_parisc() calls - ** start_kernel(). - */ - switch (boot_cpu_data.cpu_type) { - case pcxl: - case pcxl2: - if (NULL == proc_gsc_root) - { - proc_gsc_root = proc_mkdir("bus/gsc", NULL); - } - break; - case pcxt_: - case pcxu: - case pcxu_: - case pcxw: - case pcxw_: - case pcxw2: - if (NULL == proc_runway_root) - { - proc_runway_root = proc_mkdir("bus/runway", NULL); - } - break; - case mako: - case mako2: - if (NULL == proc_mckinley_root) - { - proc_mckinley_root = proc_mkdir("bus/mckinley", NULL); - } - break; - default: - /* FIXME: this was added to prevent the compiler - * complaining about missing pcx, pcxs and pcxt - * I'm assuming they have neither gsc nor runway */ - break; - } -} - static struct resource central_bus = { .name = "Central Bus", .start = F_EXTEND(0xfff80000), @@ -294,7 +247,6 @@ static int __init parisc_init(void) { u32 osid = (OS_ID_LINUX << 16); - parisc_proc_mkdir(); parisc_init_resources(); do_device_inventory(); /* probe for hardware */ diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index f886ff0c75df..e8d27def6c52 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -423,7 +423,7 @@ static void check_syscallno_in_delay_branch(struct pt_regs *regs) regs->gr[31] -= 8; /* delayed branching */ /* Get assembler opcode of code in delay branch */ - uaddr = (unsigned int *) ((regs->gr[31] & ~3) + 4); + uaddr = (u32 __user *) ((regs->gr[31] & ~3) + 4); err = get_user(opcode, uaddr); if (err) return; diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 1373e5129868..1f51aa9c8230 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -39,6 +39,7 @@ registers). #include <asm/assembly.h> #include <asm/processor.h> #include <asm/cache.h> +#include <asm/spinlock_types.h> #include <linux/linkage.h> @@ -66,6 +67,16 @@ registers). stw \reg1, 0(%sr2,\reg2) .endm + /* raise exception if spinlock content is not zero or + * __ARCH_SPIN_LOCK_UNLOCKED_VAL */ + .macro spinlock_check spin_val,tmpreg +#ifdef CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK + ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, \tmpreg + andcm,= \spin_val, \tmpreg, %r0 + .word SPINLOCK_BREAK_INSN +#endif + .endm + .text .import syscall_exit,code @@ -508,7 +519,8 @@ lws_start: lws_exit_noerror: lws_pagefault_enable %r1,%r21 - stw,ma %r20, 0(%sr2,%r20) + ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, %r21 + stw,ma %r21, 0(%sr2,%r20) ssm PSW_SM_I, %r0 b lws_exit copy %r0, %r21 @@ -521,7 +533,8 @@ lws_wouldblock: lws_pagefault: lws_pagefault_enable %r1,%r21 - stw,ma %r20, 0(%sr2,%r20) + ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, %r21 + stw,ma %r21, 0(%sr2,%r20) ssm PSW_SM_I, %r0 ldo 3(%r0),%r28 b lws_exit @@ -619,6 +632,7 @@ lws_compare_and_swap: /* Try to acquire the lock */ LDCW 0(%sr2,%r20), %r28 + spinlock_check %r28, %r21 comclr,<> %r0, %r28, %r0 b,n lws_wouldblock @@ -772,6 +786,7 @@ cas2_lock_start: /* Try to acquire the lock */ LDCW 0(%sr2,%r20), %r28 + spinlock_check %r28, %r21 comclr,<> %r0, %r28, %r0 b,n lws_wouldblock @@ -1001,6 +1016,7 @@ atomic_xchg_start: /* Try to acquire the lock */ LDCW 0(%sr2,%r20), %r28 + spinlock_check %r28, %r21 comclr,<> %r0, %r28, %r0 b,n lws_wouldblock @@ -1199,6 +1215,7 @@ atomic_store_start: /* Try to acquire the lock */ LDCW 0(%sr2,%r20), %r28 + spinlock_check %r28, %r21 comclr,<> %r0, %r28, %r0 b,n lws_wouldblock @@ -1330,7 +1347,7 @@ ENTRY(lws_lock_start) /* lws locks */ .rept 256 /* Keep locks aligned at 16-bytes */ - .word 1 + .word __ARCH_SPIN_LOCK_UNLOCKED_VAL .word 0 .word 0 .word 0 diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index 813062701922..170d0dda4213 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -11,6 +11,7 @@ #include <linux/signal.h> #include <linux/ratelimit.h> #include <linux/uaccess.h> +#include <linux/sysctl.h> #include <asm/unaligned.h> #include <asm/hardirq.h> #include <asm/traps.h> diff --git a/arch/parisc/lib/ucmpdi2.c b/arch/parisc/lib/ucmpdi2.c index 8e6014a142ef..9d8b4dbae273 100644 --- a/arch/parisc/lib/ucmpdi2.c +++ b/arch/parisc/lib/ucmpdi2.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/module.h> +#include <linux/libgcc.h> union ull_union { unsigned long long ull; @@ -9,7 +10,7 @@ union ull_union { } ui; }; -int __ucmpdi2(unsigned long long a, unsigned long long b) +word_type __ucmpdi2(unsigned long long a, unsigned long long b) { union ull_union au = {.ull = a}; union ull_union bu = {.ull = b}; diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index a4c7c7630f48..2fe5b44986e0 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -192,31 +192,31 @@ int fixup_exception(struct pt_regs *regs) * For implementation see handle_interruption() in traps.c */ static const char * const trap_description[] = { - [1] "High-priority machine check (HPMC)", - [2] "Power failure interrupt", - [3] "Recovery counter trap", - [5] "Low-priority machine check", - [6] "Instruction TLB miss fault", - [7] "Instruction access rights / protection trap", - [8] "Illegal instruction trap", - [9] "Break instruction trap", - [10] "Privileged operation trap", - [11] "Privileged register trap", - [12] "Overflow trap", - [13] "Conditional trap", - [14] "FP Assist Exception trap", - [15] "Data TLB miss fault", - [16] "Non-access ITLB miss fault", - [17] "Non-access DTLB miss fault", - [18] "Data memory protection/unaligned access trap", - [19] "Data memory break trap", - [20] "TLB dirty bit trap", - [21] "Page reference trap", - [22] "Assist emulation trap", - [25] "Taken branch trap", - [26] "Data memory access rights trap", - [27] "Data memory protection ID trap", - [28] "Unaligned data reference trap", + [1] = "High-priority machine check (HPMC)", + [2] = "Power failure interrupt", + [3] = "Recovery counter trap", + [5] = "Low-priority machine check", + [6] = "Instruction TLB miss fault", + [7] = "Instruction access rights / protection trap", + [8] = "Illegal instruction trap", + [9] = "Break instruction trap", + [10] = "Privileged operation trap", + [11] = "Privileged register trap", + [12] = "Overflow trap", + [13] = "Conditional trap", + [14] = "FP Assist Exception trap", + [15] = "Data TLB miss fault", + [16] = "Non-access ITLB miss fault", + [17] = "Non-access DTLB miss fault", + [18] = "Data memory protection/unaligned access trap", + [19] = "Data memory break trap", + [20] = "TLB dirty bit trap", + [21] = "Page reference trap", + [22] = "Assist emulation trap", + [25] = "Taken branch trap", + [26] = "Data memory access rights trap", + [27] = "Data memory protection ID trap", + [28] = "Unaligned data reference trap", }; const char *trap_name(unsigned long code) diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 389941c7f209..a088c243edea 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -523,10 +523,6 @@ void mark_rodata_ro(void) void *parisc_vmalloc_start __ro_after_init; EXPORT_SYMBOL(parisc_vmalloc_start); -#ifdef CONFIG_PA11 -unsigned long pcxl_dma_start __ro_after_init; -#endif - void __init mem_init(void) { /* Do sanity checks on IPC (compat) structures */ diff --git a/arch/parisc/mm/ioremap.c b/arch/parisc/mm/ioremap.c index 345ff0b66499..d7ee1f43d997 100644 --- a/arch/parisc/mm/ioremap.c +++ b/arch/parisc/mm/ioremap.c @@ -27,7 +27,7 @@ */ void __iomem *ioremap(unsigned long phys_addr, unsigned long size) { - void __iomem *addr; + uintptr_t addr; struct vm_struct *area; unsigned long offset, last_addr; pgprot_t pgprot; @@ -79,10 +79,9 @@ void __iomem *ioremap(unsigned long phys_addr, unsigned long size) if (!area) return NULL; - addr = (void __iomem *) area->addr; - if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size, - phys_addr, pgprot)) { - vunmap(addr); + addr = (uintptr_t) area->addr; + if (ioremap_page_range(addr, addr + size, phys_addr, pgprot)) { + vunmap(area->addr); return NULL; } diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index 8091b8bf4883..b93ffddf8a61 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -37,6 +37,10 @@ static inline void flush_dcache_page(struct page *page) #define flush_icache_user_page(vma, pg, addr, len) \ flush_icache_mm(vma->vm_mm, 0) +#ifdef CONFIG_64BIT +#define flush_cache_vmap(start, end) flush_tlb_kernel_range(start, end) +#endif + #ifndef CONFIG_SMP #define flush_icache_all() local_flush_icache_all() diff --git a/arch/riscv/include/asm/mmio.h b/arch/riscv/include/asm/mmio.h index aff6c33ab0c0..4c58ee7f95ec 100644 --- a/arch/riscv/include/asm/mmio.h +++ b/arch/riscv/include/asm/mmio.h @@ -101,9 +101,9 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) * Relaxed I/O memory access primitives. These follow the Device memory * ordering rules but do not guarantee any ordering relative to Normal memory * accesses. These are defined to order the indicated access (either a read or - * write) with all other I/O memory accesses. Since the platform specification - * defines that all I/O regions are strongly ordered on channel 2, no explicit - * fences are required to enforce this ordering. + * write) with all other I/O memory accesses to the same peripheral. Since the + * platform specification defines that all I/O regions are strongly ordered on + * channel 0, no explicit fences are required to enforce this ordering. */ /* FIXME: These are now the same as asm-generic */ #define __io_rbr() do {} while (0) @@ -125,14 +125,14 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) #endif /* - * I/O memory access primitives. Reads are ordered relative to any - * following Normal memory access. Writes are ordered relative to any prior - * Normal memory access. The memory barriers here are necessary as RISC-V + * I/O memory access primitives. Reads are ordered relative to any following + * Normal memory read and delay() loop. Writes are ordered relative to any + * prior Normal memory write. The memory barriers here are necessary as RISC-V * doesn't define any ordering between the memory space and the I/O space. */ #define __io_br() do {} while (0) -#define __io_ar(v) __asm__ __volatile__ ("fence i,r" : : : "memory") -#define __io_bw() __asm__ __volatile__ ("fence w,o" : : : "memory") +#define __io_ar(v) ({ __asm__ __volatile__ ("fence i,ir" : : : "memory"); }) +#define __io_bw() ({ __asm__ __volatile__ ("fence w,o" : : : "memory"); }) #define __io_aw() mmiowb_set_pending() #define readb(c) ({ u8 __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; }) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 75970ee2bda2..b5680c940c1e 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -188,6 +188,8 @@ extern struct pt_alloc_ops pt_ops __initdata; #define PAGE_KERNEL_IO __pgprot(_PAGE_IOREMAP) extern pgd_t swapper_pg_dir[]; +extern pgd_t trampoline_pg_dir[]; +extern pgd_t early_pg_dir[]; #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_present(pmd_t pmd) diff --git a/arch/riscv/include/asm/vmalloc.h b/arch/riscv/include/asm/vmalloc.h index 58d3e447f191..924d01b56c9a 100644 --- a/arch/riscv/include/asm/vmalloc.h +++ b/arch/riscv/include/asm/vmalloc.h @@ -3,12 +3,14 @@ #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +extern bool pgtable_l4_enabled, pgtable_l5_enabled; + #define IOREMAP_MAX_ORDER (PUD_SHIFT) #define arch_vmap_pud_supported arch_vmap_pud_supported static inline bool arch_vmap_pud_supported(pgprot_t prot) { - return true; + return pgtable_l4_enabled || pgtable_l5_enabled; } #define arch_vmap_pmd_supported arch_vmap_pmd_supported diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index a2fc952318e9..35b854cf078e 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -17,6 +17,11 @@ #include <asm/smp.h> #include <asm/pgtable.h> +bool arch_match_cpu_phys_id(int cpu, u64 phys_id) +{ + return phys_id == cpuid_to_hartid_map(cpu); +} + /* * Returns the hart ID of the given device tree node, or -ENODEV if the node * isn't an enabled and valid RISC-V hart node. diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c index 5372b708fae2..c08bb5c3b385 100644 --- a/arch/riscv/kernel/elf_kexec.c +++ b/arch/riscv/kernel/elf_kexec.c @@ -281,7 +281,7 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf, kbuf.buffer = initrd; kbuf.bufsz = kbuf.memsz = initrd_len; kbuf.buf_align = PAGE_SIZE; - kbuf.top_down = false; + kbuf.top_down = true; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) @@ -425,6 +425,7 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, * sym, instead of searching the whole relsec. */ case R_RISCV_PCREL_HI20: + case R_RISCV_CALL_PLT: case R_RISCV_CALL: *(u64 *)loc = CLEAN_IMM(UITYPE, *(u64 *)loc) | ENCODE_UJTYPE_IMM(val - addr); diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index 85bbce0f758c..40420afbb1a0 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -61,11 +61,6 @@ int riscv_hartid_to_cpuid(unsigned long hartid) return -ENOENT; } -bool arch_match_cpu_phys_id(int cpu, u64 phys_id) -{ - return phys_id == cpuid_to_hartid_map(cpu); -} - static void ipi_stop(void) { set_cpu_online(smp_processor_id(), false); diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 9ce504737d18..e4c35ac2357f 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -26,12 +26,13 @@ #include <linux/kfence.h> #include <asm/fixmap.h> -#include <asm/tlbflush.h> -#include <asm/sections.h> -#include <asm/soc.h> #include <asm/io.h> -#include <asm/ptdump.h> #include <asm/numa.h> +#include <asm/pgtable.h> +#include <asm/ptdump.h> +#include <asm/sections.h> +#include <asm/soc.h> +#include <asm/tlbflush.h> #include "../kernel/head.h" @@ -214,8 +215,13 @@ static void __init setup_bootmem(void) memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); phys_ram_end = memblock_end_of_DRAM(); + + /* + * Make sure we align the start of the memory on a PMD boundary so that + * at worst, we map the linear mapping with PMD mappings. + */ if (!IS_ENABLED(CONFIG_XIP_KERNEL)) - phys_ram_base = memblock_start_of_DRAM(); + phys_ram_base = memblock_start_of_DRAM() & PMD_MASK; /* * In 64-bit, any use of __va/__pa before this point is wrong as we diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 8fc0efcf905c..a01bc15dce24 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -22,7 +22,6 @@ * region is not and then we have to go down to the PUD level. */ -extern pgd_t early_pg_dir[PTRS_PER_PGD]; pgd_t tmp_pg_dir[PTRS_PER_PGD] __page_aligned_bss; p4d_t tmp_p4d[PTRS_PER_P4D] __page_aligned_bss; pud_t tmp_pud[PTRS_PER_PUD] __page_aligned_bss; diff --git a/arch/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/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/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/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c index 52b339aefadc..9967fcfa27ec 100644 --- a/drivers/accel/ivpu/ivpu_gem.c +++ b/drivers/accel/ivpu/ivpu_gem.c @@ -173,6 +173,9 @@ static void internal_free_pages_locked(struct ivpu_bo *bo) { unsigned int i, npages = bo->base.size >> PAGE_SHIFT; + if (ivpu_bo_cache_mode(bo) != DRM_IVPU_BO_CACHED) + set_pages_array_wb(bo->pages, bo->base.size >> PAGE_SHIFT); + for (i = 0; i < npages; i++) put_page(bo->pages[i]); @@ -587,6 +590,11 @@ ivpu_bo_alloc_internal(struct ivpu_device *vdev, u64 vpu_addr, u64 size, u32 fla if (ivpu_bo_cache_mode(bo) != DRM_IVPU_BO_CACHED) drm_clflush_pages(bo->pages, bo->base.size >> PAGE_SHIFT); + if (bo->flags & DRM_IVPU_BO_WC) + set_pages_array_wc(bo->pages, bo->base.size >> PAGE_SHIFT); + else if (bo->flags & DRM_IVPU_BO_UNCACHED) + set_pages_array_uc(bo->pages, bo->base.size >> PAGE_SHIFT); + prot = ivpu_bo_pgprot(bo, PAGE_KERNEL); bo->kvaddr = vmap(bo->pages, bo->base.size >> PAGE_SHIFT, VM_MAP, prot); if (!bo->kvaddr) { diff --git a/drivers/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/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/cpuidle/cpuidle-psci-domain.c b/drivers/cpuidle/cpuidle-psci-domain.c index c2d6d9c3c930..b88af1262f1a 100644 --- a/drivers/cpuidle/cpuidle-psci-domain.c +++ b/drivers/cpuidle/cpuidle-psci-domain.c @@ -120,20 +120,6 @@ static void psci_pd_remove(void) } } -static bool psci_pd_try_set_osi_mode(void) -{ - int ret; - - if (!psci_has_osi_support()) - return false; - - ret = psci_set_osi_mode(true); - if (ret) - return false; - - return true; -} - static void psci_cpuidle_domain_sync_state(struct device *dev) { /* @@ -152,15 +138,12 @@ static int psci_cpuidle_domain_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct device_node *node; - bool use_osi; + bool use_osi = psci_has_osi_support(); int ret = 0, pd_count = 0; if (!np) return -ENODEV; - /* If OSI mode is supported, let's try to enable it. */ - use_osi = psci_pd_try_set_osi_mode(); - /* * Parse child nodes for the "#power-domain-cells" property and * initialize a genpd/genpd-of-provider pair when it's found. @@ -170,33 +153,37 @@ static int psci_cpuidle_domain_probe(struct platform_device *pdev) continue; ret = psci_pd_init(node, use_osi); - if (ret) - goto put_node; + if (ret) { + of_node_put(node); + goto exit; + } pd_count++; } /* Bail out if not using the hierarchical CPU topology. */ if (!pd_count) - goto no_pd; + return 0; /* Link genpd masters/subdomains to model the CPU topology. */ ret = dt_idle_pd_init_topology(np); if (ret) goto remove_pd; + /* let's try to enable OSI. */ + ret = psci_set_osi_mode(use_osi); + if (ret) + goto remove_pd; + pr_info("Initialized CPU PM domain topology using %s mode\n", use_osi ? "OSI" : "PC"); return 0; -put_node: - of_node_put(node); remove_pd: + dt_idle_pd_remove_topology(np); psci_pd_remove(); +exit: pr_err("failed to create CPU PM domains ret=%d\n", ret); -no_pd: - if (use_osi) - psci_set_osi_mode(false); return ret; } diff --git a/drivers/cpuidle/dt_idle_genpd.c b/drivers/cpuidle/dt_idle_genpd.c index b37165514d4e..1af63c189039 100644 --- a/drivers/cpuidle/dt_idle_genpd.c +++ b/drivers/cpuidle/dt_idle_genpd.c @@ -152,6 +152,30 @@ int dt_idle_pd_init_topology(struct device_node *np) return 0; } +int dt_idle_pd_remove_topology(struct device_node *np) +{ + struct device_node *node; + struct of_phandle_args child, parent; + int ret; + + for_each_child_of_node(np, node) { + if (of_parse_phandle_with_args(node, "power-domains", + "#power-domain-cells", 0, &parent)) + continue; + + child.np = node; + child.args_count = 0; + ret = of_genpd_remove_subdomain(&parent, &child); + of_node_put(parent.np); + if (ret) { + of_node_put(node); + return ret; + } + } + + return 0; +} + struct device *dt_idle_attach_cpu(int cpu, const char *name) { struct device *dev; diff --git a/drivers/cpuidle/dt_idle_genpd.h b/drivers/cpuidle/dt_idle_genpd.h index a95483d08a02..3be1f70f55b5 100644 --- a/drivers/cpuidle/dt_idle_genpd.h +++ b/drivers/cpuidle/dt_idle_genpd.h @@ -14,6 +14,8 @@ struct generic_pm_domain *dt_idle_pd_alloc(struct device_node *np, int dt_idle_pd_init_topology(struct device_node *np); +int dt_idle_pd_remove_topology(struct device_node *np); + struct device *dt_idle_attach_cpu(int cpu, const char *name); void dt_idle_detach_cpu(struct device *dev); @@ -36,6 +38,11 @@ static inline int dt_idle_pd_init_topology(struct device_node *np) return 0; } +static inline int dt_idle_pd_remove_topology(struct device_node *np) +{ + return 0; +} + static inline struct device *dt_idle_attach_cpu(int cpu, const char *name) { return NULL; diff --git a/drivers/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/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index a3b86b86dc47..6dc950c1b689 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1296,6 +1296,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, void amdgpu_device_pci_config_reset(struct amdgpu_device *adev); int amdgpu_device_pci_reset(struct amdgpu_device *adev); bool amdgpu_device_need_post(struct amdgpu_device *adev); +bool amdgpu_sg_display_supported(struct amdgpu_device *adev); bool amdgpu_device_pcie_dynamic_switching_supported(void); bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev); bool amdgpu_device_aspm_support_quirk(void); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 040f4cb6ab2d..fb78a8f47587 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -295,7 +295,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, if (!p->gang_size) { ret = -EINVAL; - goto free_partial_kdata; + goto free_all_kdata; } for (i = 0; i < p->gang_size; ++i) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index a2cdde0ca0a7..45e9d737e5b8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1459,6 +1459,32 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev) } /* + * On APUs with >= 64GB white flickering has been observed w/ SG enabled. + * Disable S/G on such systems until we have a proper fix. + * https://gitlab.freedesktop.org/drm/amd/-/issues/2354 + * https://gitlab.freedesktop.org/drm/amd/-/issues/2735 + */ +bool amdgpu_sg_display_supported(struct amdgpu_device *adev) +{ + switch (amdgpu_sg_display) { + case -1: + break; + case 0: + return false; + case 1: + return true; + default: + return false; + } + if ((totalram_pages() << (PAGE_SHIFT - 10)) + + (adev->gmc.real_vram_size / 1024) >= 64000000) { + DRM_WARN("Disabling S/G due to >=64GB RAM\n"); + return false; + } + return true; +} + +/* * Intel hosts such as Raptor Lake and Sapphire Rapids don't support dynamic * speed switching. Until we have confirmation from Intel that a specific host * supports it, it's safer that we keep it disabled for all. diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 3a7af59e83ca..0451533ddde4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -471,8 +471,12 @@ static void gfx_v11_0_check_fw_cp_gfx_shadow(struct amdgpu_device *adev) case IP_VERSION(11, 0, 3): if ((adev->gfx.me_fw_version >= 1505) && (adev->gfx.pfp_fw_version >= 1600) && - (adev->gfx.mec_fw_version >= 512)) - adev->gfx.cp_gfx_shadow = true; + (adev->gfx.mec_fw_version >= 512)) { + if (amdgpu_sriov_vf(adev)) + adev->gfx.cp_gfx_shadow = true; + else + adev->gfx.cp_gfx_shadow = false; + } break; default: adev->gfx.cp_gfx_shadow = false; diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c index e1a392bcea70..af5685f4cb34 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c @@ -137,14 +137,15 @@ static int psp_v13_0_wait_for_bootloader(struct psp_context *psp) int ret; int retry_loop; + /* Wait for bootloader to signify that it is ready having bit 31 of + * C2PMSG_35 set to 1. All other bits are expected to be cleared. + * If there is an error in processing command, bits[7:0] will be set. + * This is applicable for PSP v13.0.6 and newer. + */ for (retry_loop = 0; retry_loop < 10; retry_loop++) { - /* Wait for bootloader to signify that is - ready having bit 31 of C2PMSG_35 set to 1 */ - ret = psp_wait_for(psp, - SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35), - 0x80000000, - 0x80000000, - false); + ret = psp_wait_for( + psp, SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35), + 0x80000000, 0xffffffff, false); if (ret == 0) return 0; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 49f40d9f16e8..f5a6f562e2a8 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -1543,11 +1543,7 @@ static bool kfd_ignore_crat(void) if (ignore_crat) return true; -#ifndef KFD_SUPPORT_IOMMU_V2 ret = true; -#else - ret = false; -#endif return ret; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 0b3dc754e06b..a53e0757fe64 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -194,11 +194,6 @@ static void kfd_device_info_init(struct kfd_dev *kfd, kfd_device_info_set_event_interrupt_class(kfd); - /* Raven */ - if (gc_version == IP_VERSION(9, 1, 0) || - gc_version == IP_VERSION(9, 2, 2)) - kfd->device_info.needs_iommu_device = true; - if (gc_version < IP_VERSION(11, 0, 0)) { /* Navi2x+, Navi1x+ */ if (gc_version == IP_VERSION(10, 3, 6)) @@ -233,10 +228,6 @@ static void kfd_device_info_init(struct kfd_dev *kfd, asic_type != CHIP_TONGA) kfd->device_info.supports_cwsr = true; - if (asic_type == CHIP_KAVERI || - asic_type == CHIP_CARRIZO) - kfd->device_info.needs_iommu_device = true; - if (asic_type != CHIP_HAWAII && !vf) kfd->device_info.needs_pci_atomics = true; } @@ -249,7 +240,6 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf) uint32_t gfx_target_version = 0; switch (adev->asic_type) { -#ifdef KFD_SUPPORT_IOMMU_V2 #ifdef CONFIG_DRM_AMDGPU_CIK case CHIP_KAVERI: gfx_target_version = 70000; @@ -262,7 +252,6 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf) if (!vf) f2g = &gfx_v8_kfd2kgd; break; -#endif #ifdef CONFIG_DRM_AMDGPU_CIK case CHIP_HAWAII: gfx_target_version = 70001; @@ -298,7 +287,6 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf) gfx_target_version = 90000; f2g = &gfx_v9_kfd2kgd; break; -#ifdef KFD_SUPPORT_IOMMU_V2 /* Raven */ case IP_VERSION(9, 1, 0): case IP_VERSION(9, 2, 2): @@ -306,7 +294,6 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf) if (!vf) f2g = &gfx_v9_kfd2kgd; break; -#endif /* Vega12 */ case IP_VERSION(9, 2, 1): gfx_target_version = 90004; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 2df153828ff4..01192f5abe46 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -2538,18 +2538,12 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_node *dev) } switch (dev->adev->asic_type) { - case CHIP_CARRIZO: - device_queue_manager_init_vi(&dqm->asic_ops); - break; - case CHIP_KAVERI: - device_queue_manager_init_cik(&dqm->asic_ops); - break; - case CHIP_HAWAII: device_queue_manager_init_cik_hawaii(&dqm->asic_ops); break; + case CHIP_CARRIZO: case CHIP_TONGA: case CHIP_FIJI: case CHIP_POLARIS10: diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 0fa739fd6a9c..e5554a36e8c8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1638,9 +1638,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) } break; } - if (init_data.flags.gpu_vm_support && - (amdgpu_sg_display == 0)) - init_data.flags.gpu_vm_support = false; + if (init_data.flags.gpu_vm_support) + init_data.flags.gpu_vm_support = amdgpu_sg_display_supported(adev); if (init_data.flags.gpu_vm_support) adev->mode_info.gpu_vm_support = true; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 9bc86deac9e8..b885c39bd16b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -1320,7 +1320,7 @@ int compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, if (computed_streams[i]) continue; - if (!res_pool->funcs->remove_stream_from_ctx || + if (res_pool->funcs->remove_stream_from_ctx && res_pool->funcs->remove_stream_from_ctx(stream->ctx->dc, dc_state, stream) != DC_OK) return -EINVAL; diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 20d4d08a6a2f..6966420dfbac 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -777,7 +777,8 @@ void dce110_edp_wait_for_hpd_ready( dal_gpio_destroy_irq(&hpd); /* ensure that the panel is detected */ - ASSERT(edp_hpd_high); + if (!edp_hpd_high) + DC_LOG_DC("%s: wait timed out!\n", __func__); } void dce110_edp_power_control( diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c index e5b7ef7422b8..50dc83404644 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c @@ -357,8 +357,11 @@ void dpp3_set_cursor_attributes( int cur_rom_en = 0; if (color_format == CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA || - color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA) - cur_rom_en = 1; + color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA) { + if (cursor_attributes->attribute_flags.bits.ENABLE_CURSOR_DEGAMMA) { + cur_rom_en = 1; + } + } REG_UPDATE_3(CURSOR0_CONTROL, CUR0_MODE, color_format, diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index ce41a8309582..222af2fae745 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1581,9 +1581,9 @@ static int smu_disable_dpms(struct smu_context *smu) /* * For SMU 13.0.4/11, PMFW will handle the features disablement properly - * for gpu reset case. Driver involvement is unnecessary. + * for gpu reset and S0i3 cases. Driver involvement is unnecessary. */ - if (amdgpu_in_reset(adev)) { + if (amdgpu_in_reset(adev) || adev->in_s0ix) { switch (adev->ip_versions[MP1_HWIP][0]) { case IP_VERSION(13, 0, 4): case IP_VERSION(13, 0, 11): diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 3d188616ba24..fddcd834bcec 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -331,11 +331,13 @@ static int smu_v13_0_0_check_powerplay_table(struct smu_context *smu) struct smu_13_0_0_powerplay_table *powerplay_table = table_context->power_play_table; struct smu_baco_context *smu_baco = &smu->smu_baco; +#if 0 PPTable_t *pptable = smu->smu_table.driver_pptable; const OverDriveLimits_t * const overdrive_upperlimits = &pptable->SkuTable.OverDriveLimitsBasicMax; const OverDriveLimits_t * const overdrive_lowerlimits = &pptable->SkuTable.OverDriveLimitsMin; +#endif if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_HARDWAREDC) smu->dc_controlled_by_gpio = true; @@ -347,18 +349,27 @@ static int smu_v13_0_0_check_powerplay_table(struct smu_context *smu) if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_MACO) smu_baco->maco_support = true; + /* + * We are in the transition to a new OD mechanism. + * Disable the OD feature support for SMU13 temporarily. + * TODO: get this reverted when new OD mechanism online + */ +#if 0 if (!overdrive_lowerlimits->FeatureCtrlMask || !overdrive_upperlimits->FeatureCtrlMask) smu->od_enabled = false; - table_context->thermal_controller_type = - powerplay_table->thermal_controller_type; - /* * Instead of having its own buffer space and get overdrive_table copied, * smu->od_settings just points to the actual overdrive_table */ smu->od_settings = &powerplay_table->overdrive_table; +#else + smu->od_enabled = false; +#endif + + table_context->thermal_controller_type = + powerplay_table->thermal_controller_type; return 0; } @@ -1140,7 +1151,6 @@ static int smu_v13_0_0_print_clk_levels(struct smu_context *smu, (OverDriveTableExternal_t *)smu->smu_table.overdrive_table; struct smu_13_0_dpm_table *single_dpm_table; struct smu_13_0_pcie_table *pcie_table; - const int link_width[] = {0, 1, 2, 4, 8, 12, 16}; uint32_t gen_speed, lane_width; int i, curr_freq, size = 0; int32_t min_value, max_value; @@ -1256,7 +1266,7 @@ static int smu_v13_0_0_print_clk_levels(struct smu_context *smu, (pcie_table->pcie_lane[i] == 6) ? "x16" : "", pcie_table->clk_freq[i], (gen_speed == DECODE_GEN_SPEED(pcie_table->pcie_gen[i])) && - (lane_width == DECODE_LANE_WIDTH(link_width[pcie_table->pcie_lane[i]])) ? + (lane_width == DECODE_LANE_WIDTH(pcie_table->pcie_lane[i])) ? "*" : ""); break; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 1ac552142763..fe4ee2daa5d8 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -1993,9 +1993,8 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table gpu_metrics->average_socket_power = SMUQ10_TO_UINT(metrics->SocketPower); - /* Energy is reported in 15.625mJ units */ - gpu_metrics->energy_accumulator = - SMUQ10_TO_UINT(metrics->SocketEnergyAcc); + /* Energy counter reported in 15.259uJ (2^-16) units */ + gpu_metrics->energy_accumulator = metrics->SocketEnergyAcc; gpu_metrics->current_gfxclk = SMUQ10_TO_UINT(metrics->GfxclkFrequency[xcc0]); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index b1f0937ccade..62f2886ab4df 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -323,10 +323,12 @@ static int smu_v13_0_7_check_powerplay_table(struct smu_context *smu) struct smu_baco_context *smu_baco = &smu->smu_baco; PPTable_t *smc_pptable = table_context->driver_pptable; BoardTable_t *BoardTable = &smc_pptable->BoardTable; +#if 0 const OverDriveLimits_t * const overdrive_upperlimits = &smc_pptable->SkuTable.OverDriveLimitsBasicMax; const OverDriveLimits_t * const overdrive_lowerlimits = &smc_pptable->SkuTable.OverDriveLimitsMin; +#endif if (powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_HARDWAREDC) smu->dc_controlled_by_gpio = true; @@ -338,18 +340,22 @@ static int smu_v13_0_7_check_powerplay_table(struct smu_context *smu) if (smu_baco->platform_support && (BoardTable->HsrEnabled || BoardTable->VddqOffEnabled)) smu_baco->maco_support = true; +#if 0 if (!overdrive_lowerlimits->FeatureCtrlMask || !overdrive_upperlimits->FeatureCtrlMask) smu->od_enabled = false; - table_context->thermal_controller_type = - powerplay_table->thermal_controller_type; - /* * Instead of having its own buffer space and get overdrive_table copied, * smu->od_settings just points to the actual overdrive_table */ smu->od_settings = &powerplay_table->overdrive_table; +#else + smu->od_enabled = false; +#endif + + table_context->thermal_controller_type = + powerplay_table->thermal_controller_type; return 0; } diff --git a/drivers/gpu/drm/bridge/ite-it6505.c b/drivers/gpu/drm/bridge/ite-it6505.c index 504d51c42f79..aadb396508c5 100644 --- a/drivers/gpu/drm/bridge/ite-it6505.c +++ b/drivers/gpu/drm/bridge/ite-it6505.c @@ -2517,9 +2517,11 @@ static irqreturn_t it6505_int_threaded_handler(int unused, void *data) }; int int_status[3], i; - if (it6505->enable_drv_hold || pm_runtime_get_if_in_use(dev) <= 0) + if (it6505->enable_drv_hold || !it6505->powered) return IRQ_HANDLED; + pm_runtime_get_sync(dev); + int_status[0] = it6505_read(it6505, INT_STATUS_01); int_status[1] = it6505_read(it6505, INT_STATUS_02); int_status[2] = it6505_read(it6505, INT_STATUS_03); diff --git a/drivers/gpu/drm/bridge/lontium-lt9611.c b/drivers/gpu/drm/bridge/lontium-lt9611.c index 5163e5224aad..9663601ce098 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611.c @@ -774,9 +774,7 @@ static struct mipi_dsi_device *lt9611_attach_dsi(struct lt9611 *lt9611, dsi->lanes = 4; dsi->format = MIPI_DSI_FMT_RGB888; dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE | - MIPI_DSI_MODE_VIDEO_HSE | MIPI_DSI_MODE_VIDEO_NO_HSA | - MIPI_DSI_MODE_VIDEO_NO_HFP | MIPI_DSI_MODE_VIDEO_NO_HBP | - MIPI_DSI_MODE_NO_EOT_PACKET; + MIPI_DSI_MODE_VIDEO_HSE; ret = devm_mipi_dsi_attach(dev, dsi); if (ret < 0) { diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 4ea6507a77e5..baaf0e0feb06 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -623,7 +623,13 @@ int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct int ret; if (obj->import_attach) { + /* Reset both vm_ops and vm_private_data, so we don't end up with + * vm_ops pointing to our implementation if the dma-buf backend + * doesn't set those fields. + */ vma->vm_private_data = NULL; + vma->vm_ops = NULL; + ret = dma_buf_mmap(obj->dma_buf, vma, 0); /* Drop the reference drm_gem_mmap_obj() acquired.*/ diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index f75c6f09dd2a..a2e0033e8a26 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -967,7 +967,7 @@ nouveau_connector_get_modes(struct drm_connector *connector) /* Determine display colour depth for everything except LVDS now, * DP requires this before mode_valid() is called. */ - if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS && nv_connector->native_mode) + if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS) nouveau_connector_detect_depth(connector); /* Find the native mode if this is a digital panel, if we didn't diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c index 40c8ea43c42f..b8ac66b4a2c4 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c @@ -26,6 +26,8 @@ #include "head.h" #include "ior.h" +#include <drm/display/drm_dp.h> + #include <subdev/bios.h> #include <subdev/bios/init.h> #include <subdev/gpio.h> @@ -634,6 +636,50 @@ nvkm_dp_enable_supported_link_rates(struct nvkm_outp *outp) return outp->dp.rates != 0; } +/* XXX: This is a big fat hack, and this is just drm_dp_read_dpcd_caps() + * converted to work inside nvkm. This is a temporary holdover until we start + * passing the drm_dp_aux device through NVKM + */ +static int +nvkm_dp_read_dpcd_caps(struct nvkm_outp *outp) +{ + struct nvkm_i2c_aux *aux = outp->dp.aux; + u8 dpcd_ext[DP_RECEIVER_CAP_SIZE]; + int ret; + + ret = nvkm_rdaux(aux, DPCD_RC00_DPCD_REV, outp->dp.dpcd, DP_RECEIVER_CAP_SIZE); + if (ret < 0) + return ret; + + /* + * Prior to DP1.3 the bit represented by + * DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT was reserved. + * If it is set DP_DPCD_REV at 0000h could be at a value less than + * the true capability of the panel. The only way to check is to + * then compare 0000h and 2200h. + */ + if (!(outp->dp.dpcd[DP_TRAINING_AUX_RD_INTERVAL] & + DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT)) + return 0; + + ret = nvkm_rdaux(aux, DP_DP13_DPCD_REV, dpcd_ext, sizeof(dpcd_ext)); + if (ret < 0) + return ret; + + if (outp->dp.dpcd[DP_DPCD_REV] > dpcd_ext[DP_DPCD_REV]) { + OUTP_DBG(outp, "Extended DPCD rev less than base DPCD rev (%d > %d)\n", + outp->dp.dpcd[DP_DPCD_REV], dpcd_ext[DP_DPCD_REV]); + return 0; + } + + if (!memcmp(outp->dp.dpcd, dpcd_ext, sizeof(dpcd_ext))) + return 0; + + memcpy(outp->dp.dpcd, dpcd_ext, sizeof(dpcd_ext)); + + return 0; +} + void nvkm_dp_enable(struct nvkm_outp *outp, bool auxpwr) { @@ -689,7 +735,7 @@ nvkm_dp_enable(struct nvkm_outp *outp, bool auxpwr) memset(outp->dp.lttpr, 0x00, sizeof(outp->dp.lttpr)); } - if (!nvkm_rdaux(aux, DPCD_RC00_DPCD_REV, outp->dp.dpcd, sizeof(outp->dp.dpcd))) { + if (!nvkm_dp_read_dpcd_caps(outp)) { const u8 rates[] = { 0x1e, 0x14, 0x0a, 0x06, 0 }; const u8 *rate; int rate_max; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h index 00dbeda7e346..de161e7a04aa 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h @@ -117,6 +117,7 @@ void gk104_grctx_generate_r418800(struct gf100_gr *); extern const struct gf100_grctx_func gk110_grctx; void gk110_grctx_generate_r419eb0(struct gf100_gr *); +void gk110_grctx_generate_r419f78(struct gf100_gr *); extern const struct gf100_grctx_func gk110b_grctx; extern const struct gf100_grctx_func gk208_grctx; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c index 94233d0119df..52a234b1ef01 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c @@ -906,7 +906,9 @@ static void gk104_grctx_generate_r419f78(struct gf100_gr *gr) { struct nvkm_device *device = gr->base.engine.subdev.device; - nvkm_mask(device, 0x419f78, 0x00000001, 0x00000000); + + /* bit 3 set disables loads in fp helper invocations, we need it enabled */ + nvkm_mask(device, 0x419f78, 0x00000009, 0x00000000); } void diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c index 4391458e1fb2..3acdd9eeb74a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c @@ -820,6 +820,15 @@ gk110_grctx_generate_r419eb0(struct gf100_gr *gr) nvkm_mask(device, 0x419eb0, 0x00001000, 0x00001000); } +void +gk110_grctx_generate_r419f78(struct gf100_gr *gr) +{ + struct nvkm_device *device = gr->base.engine.subdev.device; + + /* bit 3 set disables loads in fp helper invocations, we need it enabled */ + nvkm_mask(device, 0x419f78, 0x00000008, 0x00000000); +} + const struct gf100_grctx_func gk110_grctx = { .main = gf100_grctx_generate_main, @@ -854,4 +863,5 @@ gk110_grctx = { .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r418800 = gk104_grctx_generate_r418800, .r419eb0 = gk110_grctx_generate_r419eb0, + .r419f78 = gk110_grctx_generate_r419f78, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c index 7b9a34f9ec3c..5597e87624ac 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c @@ -103,4 +103,5 @@ gk110b_grctx = { .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r418800 = gk104_grctx_generate_r418800, .r419eb0 = gk110_grctx_generate_r419eb0, + .r419f78 = gk110_grctx_generate_r419f78, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c index c78d07a8bb7d..612656496541 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c @@ -568,4 +568,5 @@ gk208_grctx = { .dist_skip_table = gf117_grctx_generate_dist_skip_table, .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r418800 = gk104_grctx_generate_r418800, + .r419f78 = gk110_grctx_generate_r419f78, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c index beac66eb2a80..9906974ac3f0 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c @@ -988,4 +988,5 @@ gm107_grctx = { .r406500 = gm107_grctx_generate_r406500, .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r419e00 = gm107_grctx_generate_r419e00, + .r419f78 = gk110_grctx_generate_r419f78, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c index 3b6c8100a242..a7775aa18541 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c @@ -206,19 +206,6 @@ tu102_gr_av_to_init_veid(struct nvkm_blob *blob, struct gf100_gr_pack **ppack) return gk20a_gr_av_to_init_(blob, 64, 0x00100000, ppack); } -int -tu102_gr_load(struct gf100_gr *gr, int ver, const struct gf100_gr_fwif *fwif) -{ - int ret; - - ret = gm200_gr_load(gr, ver, fwif); - if (ret) - return ret; - - return gk20a_gr_load_net(gr, "gr/", "sw_veid_bundle_init", ver, tu102_gr_av_to_init_veid, - &gr->bundle_veid); -} - static const struct gf100_gr_fwif tu102_gr_fwif[] = { { 0, gm200_gr_load, &tu102_gr, &gp108_gr_fecs_acr, &gp108_gr_gpccs_acr }, diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index a530ecc4d207..bf34498c1b6d 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -833,12 +833,12 @@ static int vop_plane_atomic_check(struct drm_plane *plane, * need align with 2 pixel. */ if (fb->format->is_yuv && ((new_plane_state->src.x1 >> 16) % 2)) { - DRM_ERROR("Invalid Source: Yuv format not support odd xpos\n"); + DRM_DEBUG_KMS("Invalid Source: Yuv format not support odd xpos\n"); return -EINVAL; } if (fb->format->is_yuv && new_plane_state->rotation & DRM_MODE_REFLECT_Y) { - DRM_ERROR("Invalid Source: Yuv format does not support this rotation\n"); + DRM_DEBUG_KMS("Invalid Source: Yuv format does not support this rotation\n"); return -EINVAL; } @@ -846,7 +846,7 @@ static int vop_plane_atomic_check(struct drm_plane *plane, struct vop *vop = to_vop(crtc); if (!vop->data->afbc) { - DRM_ERROR("vop does not support AFBC\n"); + DRM_DEBUG_KMS("vop does not support AFBC\n"); return -EINVAL; } @@ -855,15 +855,16 @@ static int vop_plane_atomic_check(struct drm_plane *plane, return ret; if (new_plane_state->src.x1 || new_plane_state->src.y1) { - DRM_ERROR("AFBC does not support offset display, xpos=%d, ypos=%d, offset=%d\n", - new_plane_state->src.x1, - new_plane_state->src.y1, fb->offsets[0]); + DRM_DEBUG_KMS("AFBC does not support offset display, " \ + "xpos=%d, ypos=%d, offset=%d\n", + new_plane_state->src.x1, new_plane_state->src.y1, + fb->offsets[0]); return -EINVAL; } if (new_plane_state->rotation && new_plane_state->rotation != DRM_MODE_ROTATE_0) { - DRM_ERROR("No rotation support in AFBC, rotation=%d\n", - new_plane_state->rotation); + DRM_DEBUG_KMS("No rotation support in AFBC, rotation=%d\n", + new_plane_state->rotation); return -EINVAL; } } diff --git a/drivers/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/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 484c9e3e5e82..447b06ea4fc9 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -5901,7 +5901,9 @@ void bond_setup(struct net_device *bond_dev) bond_dev->hw_features = BOND_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_CTAG_FILTER; + NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_HW_VLAN_STAG_RX | + NETIF_F_HW_VLAN_STAG_FILTER; bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; bond_dev->features |= bond_dev->hw_features; diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 8da46d284e35..bef879c6d500 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1625,8 +1625,10 @@ static void felix_teardown(struct dsa_switch *ds) struct felix *felix = ocelot_to_felix(ocelot); struct dsa_port *dp; + rtnl_lock(); if (felix->tag_proto_ops) felix->tag_proto_ops->teardown(ds); + rtnl_unlock(); dsa_switch_for_each_available_port(dp, ds) ocelot_deinit_port(ocelot, dp->index); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 1416262d4296..e0a4cb7e3f50 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -1186,14 +1186,9 @@ static int enetc_init_port_rss_memory(struct enetc_si *si) static int enetc_pf_register_with_ierb(struct pci_dev *pdev) { - struct device_node *node = pdev->dev.of_node; struct platform_device *ierb_pdev; struct device_node *ierb_node; - /* Don't register with the IERB if the PF itself is disabled */ - if (!node || !of_device_is_available(node)) - return 0; - ierb_node = of_find_compatible_node(NULL, NULL, "fsl,ls1028a-enetc-ierb"); if (!ierb_node || !of_device_is_available(ierb_node)) @@ -1208,56 +1203,81 @@ static int enetc_pf_register_with_ierb(struct pci_dev *pdev) return enetc_ierb_register_pf(ierb_pdev, pdev); } -static int enetc_pf_probe(struct pci_dev *pdev, - const struct pci_device_id *ent) +static struct enetc_si *enetc_psi_create(struct pci_dev *pdev) { - struct device_node *node = pdev->dev.of_node; - struct enetc_ndev_priv *priv; - struct net_device *ndev; struct enetc_si *si; - struct enetc_pf *pf; int err; - err = enetc_pf_register_with_ierb(pdev); - if (err == -EPROBE_DEFER) - return err; - if (err) - dev_warn(&pdev->dev, - "Could not register with IERB driver: %pe, please update the device tree\n", - ERR_PTR(err)); - - err = enetc_pci_probe(pdev, KBUILD_MODNAME, sizeof(*pf)); - if (err) - return dev_err_probe(&pdev->dev, err, "PCI probing failed\n"); + err = enetc_pci_probe(pdev, KBUILD_MODNAME, sizeof(struct enetc_pf)); + if (err) { + dev_err_probe(&pdev->dev, err, "PCI probing failed\n"); + goto out; + } si = pci_get_drvdata(pdev); if (!si->hw.port || !si->hw.global) { err = -ENODEV; dev_err(&pdev->dev, "could not map PF space, probing a VF?\n"); - goto err_map_pf_space; + goto out_pci_remove; } err = enetc_setup_cbdr(&pdev->dev, &si->hw, ENETC_CBDR_DEFAULT_SIZE, &si->cbd_ring); if (err) - goto err_setup_cbdr; + goto out_pci_remove; err = enetc_init_port_rfs_memory(si); if (err) { dev_err(&pdev->dev, "Failed to initialize RFS memory\n"); - goto err_init_port_rfs; + goto out_teardown_cbdr; } err = enetc_init_port_rss_memory(si); if (err) { dev_err(&pdev->dev, "Failed to initialize RSS memory\n"); - goto err_init_port_rss; + goto out_teardown_cbdr; } - if (node && !of_device_is_available(node)) { - dev_info(&pdev->dev, "device is disabled, skipping\n"); - err = -ENODEV; - goto err_device_disabled; + return si; + +out_teardown_cbdr: + enetc_teardown_cbdr(&si->cbd_ring); +out_pci_remove: + enetc_pci_remove(pdev); +out: + return ERR_PTR(err); +} + +static void enetc_psi_destroy(struct pci_dev *pdev) +{ + struct enetc_si *si = pci_get_drvdata(pdev); + + enetc_teardown_cbdr(&si->cbd_ring); + enetc_pci_remove(pdev); +} + +static int enetc_pf_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct device_node *node = pdev->dev.of_node; + struct enetc_ndev_priv *priv; + struct net_device *ndev; + struct enetc_si *si; + struct enetc_pf *pf; + int err; + + err = enetc_pf_register_with_ierb(pdev); + if (err == -EPROBE_DEFER) + return err; + if (err) + dev_warn(&pdev->dev, + "Could not register with IERB driver: %pe, please update the device tree\n", + ERR_PTR(err)); + + si = enetc_psi_create(pdev); + if (IS_ERR(si)) { + err = PTR_ERR(si); + goto err_psi_create; } pf = enetc_si_priv(si); @@ -1339,15 +1359,9 @@ err_alloc_si_res: si->ndev = NULL; free_netdev(ndev); err_alloc_netdev: -err_init_port_rss: -err_init_port_rfs: -err_device_disabled: err_setup_mac_addresses: - enetc_teardown_cbdr(&si->cbd_ring); -err_setup_cbdr: -err_map_pf_space: - enetc_pci_remove(pdev); - + enetc_psi_destroy(pdev); +err_psi_create: return err; } @@ -1370,12 +1384,29 @@ static void enetc_pf_remove(struct pci_dev *pdev) enetc_free_msix(priv); enetc_free_si_resources(priv); - enetc_teardown_cbdr(&si->cbd_ring); free_netdev(si->ndev); - enetc_pci_remove(pdev); + enetc_psi_destroy(pdev); +} + +static void enetc_fixup_clear_rss_rfs(struct pci_dev *pdev) +{ + struct device_node *node = pdev->dev.of_node; + struct enetc_si *si; + + /* Only apply quirk for disabled functions. For the ones + * that are enabled, enetc_pf_probe() will apply it. + */ + if (node && of_device_is_available(node)) + return; + + si = enetc_psi_create(pdev); + if (si) + enetc_psi_destroy(pdev); } +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_PF, + enetc_fixup_clear_rss_rfs); static const struct pci_device_id enetc_pf_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_PF) }, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 52546f625c8b..f276b5ecb431 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -464,9 +464,9 @@ static void hns3_dbg_fill_content(char *content, u16 len, if (result) { if (item_len < strlen(result[i])) break; - strscpy(pos, result[i], strlen(result[i])); + memcpy(pos, result[i], strlen(result[i])); } else { - strscpy(pos, items[i].name, strlen(items[i].name)); + memcpy(pos, items[i].name, strlen(items[i].name)); } pos += item_len; len -= item_len; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 9f6890059666..b7b51e56b030 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5854,6 +5854,9 @@ void hns3_external_lb_prepare(struct net_device *ndev, bool if_running) if (!if_running) return; + if (test_and_set_bit(HNS3_NIC_STATE_DOWN, &priv->state)) + return; + netif_carrier_off(ndev); netif_tx_disable(ndev); @@ -5882,7 +5885,16 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running) if (!if_running) return; - hns3_nic_reset_all_ring(priv->ae_handle); + if (hns3_nic_resetting(ndev)) + return; + + if (!test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) + return; + + if (hns3_nic_reset_all_ring(priv->ae_handle)) + return; + + clear_bit(HNS3_NIC_STATE_DOWN, &priv->state); for (i = 0; i < priv->vector_num; i++) hns3_vector_enable(&priv->tqp_vector[i]); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 409db2e70965..0fb2eaee3e8a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -111,9 +111,9 @@ static void hclge_dbg_fill_content(char *content, u16 len, if (result) { if (item_len < strlen(result[i])) break; - strscpy(pos, result[i], strlen(result[i])); + memcpy(pos, result[i], strlen(result[i])); } else { - strscpy(pos, items[i].name, strlen(items[i].name)); + memcpy(pos, items[i].name, strlen(items[i].name)); } pos += item_len; len -= item_len; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index bf675c15fbb9..a940e35aef29 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -72,6 +72,8 @@ static void hclge_restore_hw_table(struct hclge_dev *hdev); static void hclge_sync_promisc_mode(struct hclge_dev *hdev); static void hclge_sync_fd_table(struct hclge_dev *hdev); static void hclge_update_fec_stats(struct hclge_dev *hdev); +static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret, + int wait_cnt); static struct hnae3_ae_algo ae_algo; @@ -7558,6 +7560,8 @@ static void hclge_enable_fd(struct hnae3_handle *handle, bool enable) static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) { +#define HCLGE_LINK_STATUS_WAIT_CNT 3 + struct hclge_desc desc; struct hclge_config_mac_mode_cmd *req = (struct hclge_config_mac_mode_cmd *)desc.data; @@ -7582,9 +7586,15 @@ static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en); ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) + if (ret) { dev_err(&hdev->pdev->dev, "mac enable fail, ret =%d.\n", ret); + return; + } + + if (!enable) + hclge_mac_link_status_wait(hdev, HCLGE_LINK_STATUS_DOWN, + HCLGE_LINK_STATUS_WAIT_CNT); } static int hclge_config_switch_param(struct hclge_dev *hdev, int vfid, @@ -7647,10 +7657,9 @@ static void hclge_phy_link_status_wait(struct hclge_dev *hdev, } while (++i < HCLGE_PHY_LINK_STATUS_NUM); } -static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret) +static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret, + int wait_cnt) { -#define HCLGE_MAC_LINK_STATUS_NUM 100 - int link_status; int i = 0; int ret; @@ -7663,13 +7672,15 @@ static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret) return 0; msleep(HCLGE_LINK_STATUS_MS); - } while (++i < HCLGE_MAC_LINK_STATUS_NUM); + } while (++i < wait_cnt); return -EBUSY; } static int hclge_mac_phy_link_status_wait(struct hclge_dev *hdev, bool en, bool is_phy) { +#define HCLGE_MAC_LINK_STATUS_NUM 100 + int link_ret; link_ret = en ? HCLGE_LINK_STATUS_UP : HCLGE_LINK_STATUS_DOWN; @@ -7677,7 +7688,8 @@ static int hclge_mac_phy_link_status_wait(struct hclge_dev *hdev, bool en, if (is_phy) hclge_phy_link_status_wait(hdev, link_ret); - return hclge_mac_link_status_wait(hdev, link_ret); + return hclge_mac_link_status_wait(hdev, link_ret, + HCLGE_MAC_LINK_STATUS_NUM); } static int hclge_set_app_loopback(struct hclge_dev *hdev, bool en) @@ -10915,9 +10927,12 @@ int hclge_cfg_flowctrl(struct hclge_dev *hdev) u32 rx_pause, tx_pause; u8 flowctl; - if (!phydev->link || !phydev->autoneg) + if (!phydev->link) return 0; + if (!phydev->autoneg) + return hclge_mac_pause_setup_hw(hdev); + local_advertising = linkmode_adv_to_lcl_adv_t(phydev->advertising); if (phydev->pause) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index de509e5751a7..c58c31221762 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -1553,7 +1553,7 @@ static int hclge_bp_setup_hw(struct hclge_dev *hdev, u8 tc) return 0; } -static int hclge_mac_pause_setup_hw(struct hclge_dev *hdev) +int hclge_mac_pause_setup_hw(struct hclge_dev *hdev) { bool tx_en, rx_en; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index 45dcfef3f90c..53eec6df5194 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -245,6 +245,7 @@ int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, u8 pfc_bitmap); int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx); int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr); +int hclge_mac_pause_setup_hw(struct hclge_dev *hdev); void hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats); void hclge_pfc_tx_stats_get(struct hclge_dev *hdev, u64 *stats); int hclge_tm_qs_shaper_cfg(struct hclge_vport *vport, int max_tx_rate); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 763d613adbcc..df76cdaddcfb 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -97,6 +97,8 @@ static int pending_scrq(struct ibmvnic_adapter *, static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *, struct ibmvnic_sub_crq_queue *); static int ibmvnic_poll(struct napi_struct *napi, int data); +static int reset_sub_crq_queues(struct ibmvnic_adapter *adapter); +static inline void reinit_init_done(struct ibmvnic_adapter *adapter); static void send_query_map(struct ibmvnic_adapter *adapter); static int send_request_map(struct ibmvnic_adapter *, dma_addr_t, u32, u8); static int send_request_unmap(struct ibmvnic_adapter *, u8); @@ -114,6 +116,7 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter, static void free_long_term_buff(struct ibmvnic_adapter *adapter, struct ibmvnic_long_term_buff *ltb); static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter); +static void flush_reset_queue(struct ibmvnic_adapter *adapter); struct ibmvnic_stat { char name[ETH_GSTRING_LEN]; @@ -1505,8 +1508,8 @@ static const char *adapter_state_to_string(enum vnic_state state) static int ibmvnic_login(struct net_device *netdev) { + unsigned long flags, timeout = msecs_to_jiffies(20000); struct ibmvnic_adapter *adapter = netdev_priv(netdev); - unsigned long timeout = msecs_to_jiffies(20000); int retry_count = 0; int retries = 10; bool retry; @@ -1527,11 +1530,9 @@ static int ibmvnic_login(struct net_device *netdev) if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { - netdev_warn(netdev, "Login timed out, retrying...\n"); - retry = true; - adapter->init_done_rc = 0; - retry_count++; - continue; + netdev_warn(netdev, "Login timed out\n"); + adapter->login_pending = false; + goto partial_reset; } if (adapter->init_done_rc == ABORTED) { @@ -1573,10 +1574,69 @@ static int ibmvnic_login(struct net_device *netdev) "SCRQ irq initialization failed\n"); return rc; } + /* Default/timeout error handling, reset and start fresh */ } else if (adapter->init_done_rc) { netdev_warn(netdev, "Adapter login failed, init_done_rc = %d\n", adapter->init_done_rc); - return -EIO; + +partial_reset: + /* adapter login failed, so free any CRQs or sub-CRQs + * and register again before attempting to login again. + * If we don't do this then the VIOS may think that + * we are already logged in and reject any subsequent + * attempts + */ + netdev_warn(netdev, + "Freeing and re-registering CRQs before attempting to login again\n"); + retry = true; + adapter->init_done_rc = 0; + release_sub_crqs(adapter, true); + /* Much of this is similar logic as ibmvnic_probe(), + * we are essentially re-initializing communication + * with the server. We really should not run any + * resets/failovers here because this is already a form + * of reset and we do not want parallel resets occurring + */ + do { + reinit_init_done(adapter); + /* Clear any failovers we got in the previous + * pass since we are re-initializing the CRQ + */ + adapter->failover_pending = false; + release_crq_queue(adapter); + /* If we don't sleep here then we risk an + * unnecessary failover event from the VIOS. + * This is a known VIOS issue caused by a vnic + * device freeing and registering a CRQ too + * quickly. + */ + msleep(1500); + /* Avoid any resets, since we are currently + * resetting. + */ + spin_lock_irqsave(&adapter->rwi_lock, flags); + flush_reset_queue(adapter); + spin_unlock_irqrestore(&adapter->rwi_lock, + flags); + + rc = init_crq_queue(adapter); + if (rc) { + netdev_err(netdev, "login recovery: init CRQ failed %d\n", + rc); + return -EIO; + } + + rc = ibmvnic_reset_init(adapter, false); + if (rc) + netdev_err(netdev, "login recovery: Reset init failed %d\n", + rc); + /* IBMVNIC_CRQ_INIT will return EAGAIN if it + * fails, since ibmvnic_reset_init will free + * irq's in failure, we won't be able to receive + * new CRQs so we need to keep trying. probe() + * handles this similarly. + */ + } while (rc == -EAGAIN && retry_count++ < retries); } } while (retry); @@ -1588,12 +1648,22 @@ static int ibmvnic_login(struct net_device *netdev) static void release_login_buffer(struct ibmvnic_adapter *adapter) { + if (!adapter->login_buf) + return; + + dma_unmap_single(&adapter->vdev->dev, adapter->login_buf_token, + adapter->login_buf_sz, DMA_TO_DEVICE); kfree(adapter->login_buf); adapter->login_buf = NULL; } static void release_login_rsp_buffer(struct ibmvnic_adapter *adapter) { + if (!adapter->login_rsp_buf) + return; + + dma_unmap_single(&adapter->vdev->dev, adapter->login_rsp_buf_token, + adapter->login_rsp_buf_sz, DMA_FROM_DEVICE); kfree(adapter->login_rsp_buf); adapter->login_rsp_buf = NULL; } @@ -4830,11 +4900,14 @@ static int send_login(struct ibmvnic_adapter *adapter) if (rc) { adapter->login_pending = false; netdev_err(adapter->netdev, "Failed to send login, rc=%d\n", rc); - goto buf_rsp_map_failed; + goto buf_send_failed; } return 0; +buf_send_failed: + dma_unmap_single(dev, rsp_buffer_token, rsp_buffer_size, + DMA_FROM_DEVICE); buf_rsp_map_failed: kfree(login_rsp_buffer); adapter->login_rsp_buf = NULL; @@ -5396,6 +5469,7 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, int num_tx_pools; int num_rx_pools; u64 *size_array; + u32 rsp_len; int i; /* CHECK: Test/set of login_pending does not need to be atomic @@ -5407,11 +5481,6 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, } adapter->login_pending = false; - dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz, - DMA_TO_DEVICE); - dma_unmap_single(dev, adapter->login_rsp_buf_token, - adapter->login_rsp_buf_sz, DMA_FROM_DEVICE); - /* If the number of queues requested can't be allocated by the * server, the login response will return with code 1. We will need * to resend the login buffer with fewer queues requested. @@ -5447,6 +5516,23 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, ibmvnic_reset(adapter, VNIC_RESET_FATAL); return -EIO; } + + rsp_len = be32_to_cpu(login_rsp->len); + if (be32_to_cpu(login->login_rsp_len) < rsp_len || + rsp_len <= be32_to_cpu(login_rsp->off_txsubm_subcrqs) || + rsp_len <= be32_to_cpu(login_rsp->off_rxadd_subcrqs) || + rsp_len <= be32_to_cpu(login_rsp->off_rxadd_buff_size) || + rsp_len <= be32_to_cpu(login_rsp->off_supp_tx_desc)) { + /* This can happen if a login request times out and there are + * 2 outstanding login requests sent, the LOGIN_RSP crq + * could have been for the older login request. So we are + * parsing the newer response buffer which may be incomplete + */ + dev_err(dev, "FATAL: Login rsp offsets/lengths invalid\n"); + ibmvnic_reset(adapter, VNIC_RESET_FATAL); + return -EIO; + } + size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size)); /* variable buffer sizes are not supported, so just read the diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 2f47cfa7f06e..460ca561819a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -1401,14 +1401,15 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx if (fsp->flow_type & FLOW_MAC_EXT) return -EINVAL; + spin_lock_bh(&adapter->fdir_fltr_lock); if (adapter->fdir_active_fltr >= IAVF_MAX_FDIR_FILTERS) { + spin_unlock_bh(&adapter->fdir_fltr_lock); dev_err(&adapter->pdev->dev, "Unable to add Flow Director filter because VF reached the limit of max allowed filters (%u)\n", IAVF_MAX_FDIR_FILTERS); return -ENOSPC; } - spin_lock_bh(&adapter->fdir_fltr_lock); if (iavf_find_fdir_fltr_by_loc(adapter, fsp->location)) { dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, it already exists\n"); spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -1781,7 +1782,9 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, case ETHTOOL_GRXCLSRLCNT: if (!FDIR_FLTR_SUPPORT(adapter)) break; + spin_lock_bh(&adapter->fdir_fltr_lock); cmd->rule_cnt = adapter->fdir_active_fltr; + spin_unlock_bh(&adapter->fdir_fltr_lock); cmd->data = IAVF_MAX_FDIR_FILTERS; ret = 0; break; diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c index 6146203efd84..505e82ebafe4 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c @@ -722,7 +722,9 @@ void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *f bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr) { struct iavf_fdir_fltr *tmp; + bool ret = false; + spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(tmp, &adapter->fdir_list_head, list) { if (tmp->flow_type != fltr->flow_type) continue; @@ -732,11 +734,14 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr * !memcmp(&tmp->ip_data, &fltr->ip_data, sizeof(fltr->ip_data)) && !memcmp(&tmp->ext_data, &fltr->ext_data, - sizeof(fltr->ext_data))) - return true; + sizeof(fltr->ext_data))) { + ret = true; + break; + } } + spin_unlock_bh(&adapter->fdir_fltr_lock); - return false; + return ret; } /** diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 9db384f66a8e..38901d2a4680 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -195,6 +195,10 @@ struct igc_adapter { u32 qbv_config_change_errors; bool qbv_transition; unsigned int qbv_count; + /* Access to oper_gate_closed, admin_gate_closed and qbv_transition + * are protected by the qbv_tx_lock. + */ + spinlock_t qbv_tx_lock; /* OS defined structs */ struct pci_dev *pdev; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index bdeb36790d77..6f557e843e49 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -4801,6 +4801,7 @@ static int igc_sw_init(struct igc_adapter *adapter) adapter->nfc_rule_count = 0; spin_lock_init(&adapter->stats64_lock); + spin_lock_init(&adapter->qbv_tx_lock); /* Assume MSI-X interrupts, will be checked during IRQ allocation */ adapter->flags |= IGC_FLAG_HAS_MSIX; @@ -6119,15 +6120,15 @@ static int igc_tsn_enable_launchtime(struct igc_adapter *adapter, return igc_tsn_offload_apply(adapter); } -static int igc_tsn_clear_schedule(struct igc_adapter *adapter) +static int igc_qbv_clear_schedule(struct igc_adapter *adapter) { + unsigned long flags; int i; adapter->base_time = 0; adapter->cycle_time = NSEC_PER_SEC; adapter->taprio_offload_enable = false; adapter->qbv_config_change_errors = 0; - adapter->qbv_transition = false; adapter->qbv_count = 0; for (i = 0; i < adapter->num_tx_queues; i++) { @@ -6136,10 +6137,28 @@ static int igc_tsn_clear_schedule(struct igc_adapter *adapter) ring->start_time = 0; ring->end_time = NSEC_PER_SEC; ring->max_sdu = 0; + } + + spin_lock_irqsave(&adapter->qbv_tx_lock, flags); + + adapter->qbv_transition = false; + + for (i = 0; i < adapter->num_tx_queues; i++) { + struct igc_ring *ring = adapter->tx_ring[i]; + ring->oper_gate_closed = false; ring->admin_gate_closed = false; } + spin_unlock_irqrestore(&adapter->qbv_tx_lock, flags); + + return 0; +} + +static int igc_tsn_clear_schedule(struct igc_adapter *adapter) +{ + igc_qbv_clear_schedule(adapter); + return 0; } @@ -6150,6 +6169,7 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, struct igc_hw *hw = &adapter->hw; u32 start_time = 0, end_time = 0; struct timespec64 now; + unsigned long flags; size_t n; int i; @@ -6217,6 +6237,8 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, start_time += e->interval; } + spin_lock_irqsave(&adapter->qbv_tx_lock, flags); + /* Check whether a queue gets configured. * If not, set the start and end time to be end time. */ @@ -6241,6 +6263,8 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, } } + spin_unlock_irqrestore(&adapter->qbv_tx_lock, flags); + for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; struct net_device *dev = adapter->netdev; @@ -6619,8 +6643,11 @@ static enum hrtimer_restart igc_qbv_scheduling_timer(struct hrtimer *timer) { struct igc_adapter *adapter = container_of(timer, struct igc_adapter, hrtimer); + unsigned long flags; unsigned int i; + spin_lock_irqsave(&adapter->qbv_tx_lock, flags); + adapter->qbv_transition = true; for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *tx_ring = adapter->tx_ring[i]; @@ -6633,6 +6660,9 @@ static enum hrtimer_restart igc_qbv_scheduling_timer(struct hrtimer *timer) } } adapter->qbv_transition = false; + + spin_unlock_irqrestore(&adapter->qbv_tx_lock, flags); + return HRTIMER_NORESTART; } diff --git a/drivers/net/ethernet/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 1c820119e438..c27df14df145 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5266,6 +5266,7 @@ void mlx5e_destroy_q_counters(struct mlx5e_priv *priv) static int mlx5e_nic_init(struct mlx5_core_dev *mdev, struct net_device *netdev) { + const bool take_rtnl = netdev->reg_state == NETREG_REGISTERED; struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_flow_steering *fs; int err; @@ -5294,9 +5295,19 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, mlx5_core_err(mdev, "TLS initialization failed, %d\n", err); mlx5e_health_create_reporters(priv); + + /* If netdev is already registered (e.g. move from uplink to nic profile), + * RTNL lock must be held before triggering netdev notifiers. + */ + if (take_rtnl) + rtnl_lock(); + /* update XDP supported features */ mlx5e_set_xdp_feature(netdev); + if (take_rtnl) + rtnl_unlock(); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 92377632f9e0..31708d5aa608 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1943,9 +1943,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_flow_attr *attr = flow->attr; - struct mlx5_esw_flow_attr *esw_attr; - esw_attr = attr->esw_attr; mlx5e_put_flow_tunnel_id(flow); remove_unready_flow(flow); @@ -1966,12 +1964,6 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, mlx5_tc_ct_match_del(get_ct_priv(priv), &flow->attr->ct_attr); - if (esw_attr->int_port) - mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(priv), esw_attr->int_port); - - if (esw_attr->dest_int_port) - mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(priv), esw_attr->dest_int_port); - if (flow_flag_test(flow, L3_TO_L2_DECAP)) mlx5e_detach_decap(priv, flow); @@ -4268,6 +4260,7 @@ static void mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr) { struct mlx5_core_dev *counter_dev = get_flow_counter_dev(flow); + struct mlx5_esw_flow_attr *esw_attr; if (!attr) return; @@ -4285,6 +4278,18 @@ mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *a mlx5e_tc_detach_mod_hdr(flow->priv, flow, attr); } + if (mlx5e_is_eswitch_flow(flow)) { + esw_attr = attr->esw_attr; + + if (esw_attr->int_port) + mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(flow->priv), + esw_attr->int_port); + + if (esw_attr->dest_int_port) + mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(flow->priv), + esw_attr->dest_int_port); + } + mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), attr); free_branch_attr(flow, attr->branch_true); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index af779c700278..fdf2be548e85 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -60,7 +60,7 @@ static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16 } else if (mlx5_core_is_ec_vf_vport(esw->dev, vport_num)) { memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len); dl_port->attrs.switch_id.id_len = ppid.id_len; - devlink_port_attrs_pci_vf_set(dl_port, controller_num, pfnum, + devlink_port_attrs_pci_vf_set(dl_port, 0, pfnum, vport_num - 1, false); } return dl_port; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/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 f42abc2ea73c..72ae560a1c68 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1989,7 +1989,7 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, mlx5_enter_error_state(dev, false); mlx5_error_sw_reset(dev); - mlx5_unload_one(dev, true); + mlx5_unload_one(dev, false); mlx5_drain_health_wq(dev); mlx5_pci_disable_device(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index c4be257c043d..682d3dc00dd1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -361,7 +361,7 @@ static inline bool mlx5_core_is_ec_vf_vport(const struct mlx5_core_dev *dev, u16 static inline int mlx5_vport_to_func_id(const struct mlx5_core_dev *dev, u16 vport, bool ec_vf_func) { - return ec_vf_func ? vport - mlx5_core_ec_vf_vport_base(dev) + return ec_vf_func ? vport - mlx5_core_ec_vf_vport_base(dev) + 1 : vport; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 4e42a3b9b8ee..a2fc937d5461 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -285,8 +285,7 @@ static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev) host_total_vfs = MLX5_GET(query_esw_functions_out, out, host_params_context.host_total_vfs); kvfree(out); - if (host_total_vfs) - return host_total_vfs; + return host_total_vfs; } done: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_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 a499e460594b..c2ad0921e893 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -8,6 +8,7 @@ #include <linux/ethtool.h> #include <linux/filter.h> #include <linux/mm.h> +#include <linux/pci.h> #include <net/checksum.h> #include <net/ip6_checksum.h> @@ -2345,9 +2346,12 @@ int mana_attach(struct net_device *ndev) static int mana_dealloc_queues(struct net_device *ndev) { struct mana_port_context *apc = netdev_priv(ndev); + unsigned long timeout = jiffies + 120 * HZ; struct gdma_dev *gd = apc->ac->gdma_dev; struct mana_txq *txq; + struct sk_buff *skb; int i, err; + u32 tsleep; if (apc->port_is_up) return -EINVAL; @@ -2363,15 +2367,40 @@ static int mana_dealloc_queues(struct net_device *ndev) * to false, but it doesn't matter since mana_start_xmit() drops any * new packets due to apc->port_is_up being false. * - * Drain all the in-flight TX packets + * Drain all the in-flight TX packets. + * A timeout of 120 seconds for all the queues is used. + * This will break the while loop when h/w is not responding. + * This value of 120 has been decided here considering max + * number of queues. */ + for (i = 0; i < apc->num_queues; i++) { txq = &apc->tx_qp[i].txq; - - while (atomic_read(&txq->pending_sends) > 0) - usleep_range(1000, 2000); + tsleep = 1000; + while (atomic_read(&txq->pending_sends) > 0 && + time_before(jiffies, timeout)) { + usleep_range(tsleep, tsleep + 1000); + tsleep <<= 1; + } + if (atomic_read(&txq->pending_sends)) { + err = pcie_flr(to_pci_dev(gd->gdma_context->dev)); + if (err) { + netdev_err(ndev, "flr failed %d with %d pkts pending in txq %u\n", + err, atomic_read(&txq->pending_sends), + txq->gdma_txq_id); + } + break; + } } + for (i = 0; i < apc->num_queues; i++) { + txq = &apc->tx_qp[i].txq; + while ((skb = skb_dequeue(&txq->pending_skbs))) { + mana_unmap_skb(skb, apc); + dev_kfree_skb_any(skb); + } + atomic_set(&txq->pending_sends, 0); + } /* We're 100% sure the queues can no longer be woken up, because * we're sure now mana_poll_tx_cq() can't be running. */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 612b0015dc43..432fb93aa801 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1817,6 +1817,7 @@ static int ionic_change_mtu(struct net_device *netdev, int new_mtu) static void ionic_tx_timeout_work(struct work_struct *ws) { struct ionic_lif *lif = container_of(ws, struct ionic_lif, tx_timeout_work); + int err; if (test_bit(IONIC_LIF_F_FW_RESET, lif->state)) return; @@ -1829,8 +1830,11 @@ static void ionic_tx_timeout_work(struct work_struct *ws) mutex_lock(&lif->queue_lock); ionic_stop_queues_reconfig(lif); - ionic_start_queues_reconfig(lif); + err = ionic_start_queues_reconfig(lif); mutex_unlock(&lif->queue_lock); + + if (err) + dev_err(lif->ionic->dev, "%s: Restarting queues failed\n", __func__); } static void ionic_tx_timeout(struct net_device *netdev, unsigned int txqueue) @@ -2800,17 +2804,22 @@ static int ionic_cmb_reconfig(struct ionic_lif *lif, if (err) { dev_err(lif->ionic->dev, "CMB restore failed: %d\n", err); - goto errout; + goto err_out; } } - ionic_start_queues_reconfig(lif); - } else { - /* This was detached in ionic_stop_queues_reconfig() */ - netif_device_attach(lif->netdev); + err = ionic_start_queues_reconfig(lif); + if (err) { + dev_err(lif->ionic->dev, + "CMB reconfig failed: %d\n", err); + goto err_out; + } } -errout: +err_out: + /* This was detached in ionic_stop_queues_reconfig() */ + netif_device_attach(lif->netdev); + return err; } diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 984dfa5d6c11..144ec756c796 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -743,7 +743,7 @@ static bool macsec_post_decrypt(struct sk_buff *skb, struct macsec_secy *secy, u u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); - secy->netdev->stats.rx_dropped++; + DEV_STATS_INC(secy->netdev, rx_dropped); return false; } @@ -767,7 +767,7 @@ static bool macsec_post_decrypt(struct sk_buff *skb, struct macsec_secy *secy, u rxsc_stats->stats.InPktsNotValid++; u64_stats_update_end(&rxsc_stats->syncp); this_cpu_inc(rx_sa->stats->InPktsNotValid); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); return false; } @@ -1069,7 +1069,7 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoTag++; u64_stats_update_end(&secy_stats->syncp); - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); continue; } @@ -1179,7 +1179,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsBadTag++; u64_stats_update_end(&secy_stats->syncp); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); goto drop_nosa; } @@ -1196,7 +1196,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsNotUsingSA++; u64_stats_update_end(&rxsc_stats->syncp); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); if (active_rx_sa) this_cpu_inc(active_rx_sa->stats->InPktsNotUsingSA); goto drop_nosa; @@ -1230,7 +1230,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); goto drop; } } @@ -1271,7 +1271,7 @@ deliver: if (ret == NET_RX_SUCCESS) count_rx(dev, len); else - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); rcu_read_unlock(); @@ -1308,7 +1308,7 @@ nosci: u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoSCI++; u64_stats_update_end(&secy_stats->syncp); - macsec->secy.netdev->stats.rx_errors++; + DEV_STATS_INC(macsec->secy.netdev, rx_errors); continue; } @@ -1327,7 +1327,7 @@ nosci: secy_stats->stats.InPktsUnknownSCI++; u64_stats_update_end(&secy_stats->syncp); } else { - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); } } @@ -3422,7 +3422,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, if (!secy->operational) { kfree_skb(skb); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -3430,7 +3430,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, skb = macsec_encrypt(skb, dev); if (IS_ERR(skb)) { if (PTR_ERR(skb) != -EINPROGRESS) - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -3667,9 +3667,9 @@ static void macsec_get_stats64(struct net_device *dev, dev_fetch_sw_netstats(s, dev->tstats); - s->rx_dropped = dev->stats.rx_dropped; - s->tx_dropped = dev->stats.tx_dropped; - s->rx_errors = dev->stats.rx_errors; + s->rx_dropped = atomic_long_read(&dev->stats.__rx_dropped); + s->tx_dropped = atomic_long_read(&dev->stats.__tx_dropped); + s->rx_errors = atomic_long_read(&dev->stats.__rx_errors); } static int macsec_get_iflink(const struct net_device *dev) diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index c1f307d90518..8a77ec33b417 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -459,21 +459,27 @@ static int at803x_set_wol(struct phy_device *phydev, phy_write_mmd(phydev, MDIO_MMD_PCS, offsets[i], mac[(i * 2) + 1] | (mac[(i * 2)] << 8)); - /* Enable WOL function */ - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL, - 0, AT803X_WOL_EN); - if (ret) - return ret; + /* Enable WOL function for 1588 */ + if (phydev->drv->phy_id == ATH8031_PHY_ID) { + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + 0, AT803X_WOL_EN); + if (ret) + return ret; + } /* Enable WOL interrupt */ ret = phy_modify(phydev, AT803X_INTR_ENABLE, 0, AT803X_INTR_ENABLE_WOL); if (ret) return ret; } else { - /* Disable WoL function */ - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL, - AT803X_WOL_EN, 0); - if (ret) - return ret; + /* Disable WoL function for 1588 */ + if (phydev->drv->phy_id == ATH8031_PHY_ID) { + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + AT803X_WOL_EN, 0); + if (ret) + return ret; + } /* Disable WOL interrupt */ ret = phy_modify(phydev, AT803X_INTR_ENABLE, AT803X_INTR_ENABLE_WOL, 0); if (ret) @@ -508,11 +514,11 @@ static void at803x_get_wol(struct phy_device *phydev, wol->supported = WAKE_MAGIC; wol->wolopts = 0; - value = phy_read_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL); + value = phy_read(phydev, AT803X_INTR_ENABLE); if (value < 0) return; - if (value & AT803X_WOL_EN) + if (value & AT803X_INTR_ENABLE_WOL) wol->wolopts |= WAKE_MAGIC; } @@ -858,9 +864,6 @@ static int at803x_probe(struct phy_device *phydev) if (phydev->drv->phy_id == ATH8031_PHY_ID) { int ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG); int mode_cfg; - struct ethtool_wolinfo wol = { - .wolopts = 0, - }; if (ccr < 0) return ccr; @@ -877,12 +880,14 @@ static int at803x_probe(struct phy_device *phydev) break; } - /* Disable WOL by default */ - ret = at803x_set_wol(phydev, &wol); - if (ret < 0) { - phydev_err(phydev, "failed to disable WOL on probe: %d\n", ret); + /* Disable WoL in 1588 register which is enabled + * by default + */ + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + AT803X_WOL_EN, 0); + if (ret) return ret; - } } return 0; @@ -2059,8 +2064,6 @@ static struct phy_driver at803x_driver[] = { .flags = PHY_POLL_CABLE_TEST, .config_init = at803x_config_init, .link_change_notify = at803x_link_change_notify, - .set_wol = at803x_set_wol, - .get_wol = at803x_get_wol, .suspend = at803x_suspend, .resume = at803x_resume, /* PHY_BASIC_FEATURES */ diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 25f0191df00b..100339bc8b04 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1594,7 +1594,7 @@ static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile, if (zerocopy) return false; - if (SKB_DATA_ALIGN(len + TUN_RX_PAD) + + if (SKB_DATA_ALIGN(len + TUN_RX_PAD + XDP_PACKET_HEADROOM) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) > PAGE_SIZE) return false; 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 6512267ae4ca..4928e4e91660 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -2144,8 +2144,7 @@ int ath12k_wmi_send_scan_start_cmd(struct ath12k *ar, struct wmi_tlv *tlv; void *ptr; int i, ret, len; - u32 *tmp_ptr; - u8 extraie_len_with_pad = 0; + u32 *tmp_ptr, extraie_len_with_pad = 0; struct ath12k_wmi_hint_short_ssid_arg *s_ssid = NULL; struct ath12k_wmi_hint_bssid_arg *hint_bssid = NULL; diff --git a/drivers/net/wireless/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 b114babec698..c93e6250cb8b 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.c +++ b/drivers/net/wireless/realtek/rtw89/mac.c @@ -2524,7 +2524,7 @@ static int cmac_dma_init(struct rtw89_dev *rtwdev, u8 mac_idx) u32 reg; int ret; - if (chip_id != RTL8852A && chip_id != RTL8852B) + if (chip_id != RTL8852B) return 0; ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index c8d20cddf658..88f760a7cbc3 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -396,7 +396,7 @@ static void xenvif_get_requests(struct xenvif_queue *queue, struct gnttab_map_grant_ref *gop = queue->tx_map_ops + *map_ops; struct xen_netif_tx_request *txp = first; - nr_slots = shinfo->nr_frags + 1; + nr_slots = shinfo->nr_frags + frag_overflow + 1; copy_count(skb) = 0; XENVIF_TX_CB(skb)->split_mask = 0; @@ -462,8 +462,8 @@ static void xenvif_get_requests(struct xenvif_queue *queue, } } - for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; - shinfo->nr_frags++, gop++) { + for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS; + shinfo->nr_frags++, gop++, nr_slots--) { index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; xenvif_tx_create_map_op(queue, pending_idx, txp, @@ -476,12 +476,12 @@ static void xenvif_get_requests(struct xenvif_queue *queue, txp++; } - if (frag_overflow) { + if (nr_slots > 0) { shinfo = skb_shinfo(nskb); frags = shinfo->frags; - for (shinfo->nr_frags = 0; shinfo->nr_frags < frag_overflow; + for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; shinfo->nr_frags++, txp++, gop++) { index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; @@ -492,6 +492,11 @@ static void xenvif_get_requests(struct xenvif_queue *queue, } skb_shinfo(skb)->frag_list = nskb; + } else if (nskb) { + /* A frag_list skb was allocated but it is no longer needed + * because enough slots were converted to copy ops above. + */ + kfree_skb(nskb); } (*copy_ops) = cop - queue->tx_copy_ops; diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c index bf3405f4289e..8b1dcd537020 100644 --- a/drivers/parisc/sba_iommu.c +++ b/drivers/parisc/sba_iommu.c @@ -121,6 +121,8 @@ module_param(sba_reserve_agpgart, int, 0444); MODULE_PARM_DESC(sba_reserve_agpgart, "Reserve half of IO pdir as AGPGART"); #endif +struct proc_dir_entry *proc_runway_root __ro_after_init; +struct proc_dir_entry *proc_mckinley_root __ro_after_init; /************************************ ** SBA register read and write support @@ -1968,11 +1970,15 @@ static int __init sba_driver_callback(struct parisc_device *dev) #ifdef CONFIG_PROC_FS switch (dev->id.hversion) { case PLUTO_MCKINLEY_PORT: + if (!proc_mckinley_root) + proc_mckinley_root = proc_mkdir("bus/mckinley", NULL); root = proc_mckinley_root; break; case ASTRO_RUNWAY_PORT: case IKE_MERCED_PORT: default: + if (!proc_runway_root) + proc_runway_root = proc_mkdir("bus/runway", NULL); root = proc_runway_root; break; } diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 5bc81cc0a2de..46b252bbe500 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -11,6 +11,7 @@ #include <linux/pci.h> #include <linux/errno.h> #include <linux/ioport.h> +#include <linux/of.h> #include <linux/proc_fs.h> #include <linux/slab.h> @@ -332,6 +333,7 @@ void __weak pcibios_bus_add_device(struct pci_dev *pdev) { } */ void pci_bus_add_device(struct pci_dev *dev) { + struct device_node *dn = dev->dev.of_node; int retval; /* @@ -344,7 +346,7 @@ void pci_bus_add_device(struct pci_dev *dev) pci_proc_attach_device(dev); pci_bridge_d3_update(dev); - dev->match_driver = true; + dev->match_driver = !dn || of_device_is_available(dn); retval = device_attach(&dev->dev); if (retval < 0 && retval != -EPROBE_DEFER) pci_warn(dev, "device attach failed (%d)\n", retval); diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig index 8d49bad7f847..0859be86e718 100644 --- a/drivers/pci/controller/Kconfig +++ b/drivers/pci/controller/Kconfig @@ -179,7 +179,6 @@ config PCI_MVEBU depends on MVEBU_MBUS depends on ARM depends on OF - depends on BROKEN select PCI_BRIDGE_EMUL help Add support for Marvell EBU PCIe controller. This PCIe controller diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index cf61733bf78d..9952057c8819 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -485,20 +485,15 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp) if (ret) goto err_remove_edma; - if (dw_pcie_link_up(pci)) { - dw_pcie_print_link_status(pci); - } else { + if (!dw_pcie_link_up(pci)) { ret = dw_pcie_start_link(pci); if (ret) goto err_remove_edma; - - if (pci->ops && pci->ops->start_link) { - ret = dw_pcie_wait_for_link(pci); - if (ret) - goto err_stop_link; - } } + /* Ignore errors, the link may come up later */ + dw_pcie_wait_for_link(pci); + bridge->sysdata = pp; ret = pci_host_probe(bridge); diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c index c87848cd8686..1f2ee71da4da 100644 --- a/drivers/pci/controller/dwc/pcie-designware.c +++ b/drivers/pci/controller/dwc/pcie-designware.c @@ -644,20 +644,9 @@ void dw_pcie_disable_atu(struct dw_pcie *pci, u32 dir, int index) dw_pcie_writel_atu(pci, dir, index, PCIE_ATU_REGION_CTRL2, 0); } -void dw_pcie_print_link_status(struct dw_pcie *pci) -{ - u32 offset, val; - - offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); - val = dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKSTA); - - dev_info(pci->dev, "PCIe Gen.%u x%u link up\n", - FIELD_GET(PCI_EXP_LNKSTA_CLS, val), - FIELD_GET(PCI_EXP_LNKSTA_NLW, val)); -} - int dw_pcie_wait_for_link(struct dw_pcie *pci) { + u32 offset, val; int retries; /* Check if the link is up or not */ @@ -673,7 +662,12 @@ int dw_pcie_wait_for_link(struct dw_pcie *pci) return -ETIMEDOUT; } - dw_pcie_print_link_status(pci); + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + val = dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKSTA); + + dev_info(pci->dev, "PCIe Gen.%u x%u link up\n", + FIELD_GET(PCI_EXP_LNKSTA_CLS, val), + FIELD_GET(PCI_EXP_LNKSTA_NLW, val)); return 0; } diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h index 615660640801..79713ce075cc 100644 --- a/drivers/pci/controller/dwc/pcie-designware.h +++ b/drivers/pci/controller/dwc/pcie-designware.h @@ -429,7 +429,6 @@ void dw_pcie_setup(struct dw_pcie *pci); void dw_pcie_iatu_detect(struct dw_pcie *pci); int dw_pcie_edma_detect(struct dw_pcie *pci); void dw_pcie_edma_remove(struct dw_pcie *pci); -void dw_pcie_print_link_status(struct dw_pcie *pci); static inline void dw_pcie_writel_dbi(struct dw_pcie *pci, u32 reg, u32 val) { diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 328d1e416014..601129772b2d 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -498,6 +498,7 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge) acpiphp_native_scan_bridge(dev); } } else { + LIST_HEAD(add_list); int max, pass; acpiphp_rescan_slot(slot); @@ -511,10 +512,15 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge) if (pass && dev->subordinate) { check_hotplug_bridge(slot, dev); pcibios_resource_survey_bus(dev->subordinate); + if (pci_is_root_bus(bus)) + __pci_bus_size_bridges(dev->subordinate, &add_list); } } } - pci_assign_unassigned_bridge_resources(bus->self); + if (pci_is_root_bus(bus)) + __pci_bus_assign_resources(bus, &add_list, NULL); + else + pci_assign_unassigned_bridge_resources(bus->self); } acpiphp_sanitize_bus(bus); diff --git a/drivers/pci/of.c b/drivers/pci/of.c index e51219f9f523..3c158b17dcb5 100644 --- a/drivers/pci/of.c +++ b/drivers/pci/of.c @@ -34,11 +34,6 @@ int pci_set_of_node(struct pci_dev *dev) if (!node) return 0; - if (!of_device_is_available(node)) { - of_node_put(node); - return -ENODEV; - } - device_set_node(&dev->dev, of_fwnode_handle(node)); return 0; } diff --git a/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/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/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/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/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/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/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/core/filter.c b/net/core/filter.c index 06ba0e56e369..28a59596987a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4116,12 +4116,6 @@ BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) if (unlikely(data_end > data_hard_end)) return -EINVAL; - /* ALL drivers MUST init xdp->frame_sz, chicken check below */ - if (unlikely(xdp->frame_sz > PAGE_SIZE)) { - WARN_ONCE(1, "Too BIG xdp->frame_sz = %d\n", xdp->frame_sz); - return -EINVAL; - } - if (unlikely(data_end < xdp->data + ETH_HLEN)) return -EINVAL; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index a29508e1ff35..ef1a2eb6520b 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1120,13 +1120,19 @@ static void sk_psock_strp_data_ready(struct sock *sk) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) { + int ret; + static const struct strp_callbacks cb = { .rcv_msg = sk_psock_strp_read, .read_sock_done = sk_psock_strp_read_done, .parse_msg = sk_psock_strp_parse, }; - return strp_init(&psock->strp, sk, &cb); + ret = strp_init(&psock->strp, sk, &cb); + if (!ret) + sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED); + + return ret; } void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) @@ -1154,7 +1160,7 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) static void sk_psock_done_strp(struct sk_psock *psock) { /* Parser has been stopped */ - if (psock->progs.stream_parser) + if (sk_psock_test_state(psock, SK_PSOCK_RX_STRP_ENABLED)) strp_done(&psock->strp); } #else diff --git a/net/core/sock.c b/net/core/sock.c index 6d4f28efe29a..732fc37a4771 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1778,7 +1778,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, spin_unlock(&sk->sk_peer_lock); if (!peer_pid) - return -ESRCH; + return -ENODATA; pidfd = pidfd_prepare(peer_pid, 0, &pidfd_file); put_pid(peer_pid); 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 f95142e56da0..be5498f5dd31 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3221,13 +3221,9 @@ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) &rtm_dump_nexthop_cb, &filter); if (err < 0) { if (likely(skb->len)) - goto out; - goto out_err; + err = skb->len; } -out: - err = skb->len; -out_err: cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; @@ -3367,25 +3363,19 @@ static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb, dd->filter.res_bucket_nh_id != nhge->nh->id) continue; + dd->ctx->bucket_index = bucket_index; err = nh_fill_res_bucket(skb, nh, bucket, bucket_index, RTM_NEWNEXTHOPBUCKET, portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->extack); - if (err < 0) { - if (likely(skb->len)) - goto out; - goto out_err; - } + if (err) + return err; } dd->ctx->done_nh_idx = dd->ctx->nh.idx + 1; - bucket_index = 0; + dd->ctx->bucket_index = 0; -out: - err = skb->len; -out_err: - dd->ctx->bucket_index = bucket_index; - return err; + return 0; } static int rtm_dump_nexthop_bucket_cb(struct sk_buff *skb, @@ -3434,13 +3424,9 @@ static int rtm_dump_nexthop_bucket(struct sk_buff *skb, if (err < 0) { if (likely(skb->len)) - goto out; - goto out_err; + err = skb->len; } -out: - err = skb->len; -out_err: cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 18634ebd20a4..a42be96ae209 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -197,7 +197,8 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, static inline int ndisc_is_useropt(const struct net_device *dev, struct nd_opt_hdr *opt) { - return opt->nd_opt_type == ND_OPT_RDNSS || + return opt->nd_opt_type == ND_OPT_PREFIX_INFO || + opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || opt->nd_opt_type == ND_OPT_PREF64 || diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 3317d1cca156..d80658547836 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2335,7 +2335,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); - if (flags & MPTCP_CF_FASTCLOSE) { + if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { /* be sure to force the tcp_disconnect() path, * to generate the egress reset */ @@ -3328,7 +3328,7 @@ static void mptcp_release_cb(struct sock *sk) if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags)) __mptcp_clean_una_wakeup(sk); - if (unlikely(&msk->cb_flags)) { + if (unlikely(msk->cb_flags)) { /* be sure to set the current sk state before tacking actions * depending on sk_state, that is processing MPTCP_ERROR_REPORT */ diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 37fbe22e2433..ba2a873a4d2e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -325,7 +325,6 @@ struct mptcp_sock { u32 subflow_id; u32 setsockopt_seq; char ca_name[TCP_CA_NAME_MAX]; - struct mptcp_sock *dl_next; }; #define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 9ee3b7abbaf6..94ae7dd01c65 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1793,16 +1793,31 @@ static void subflow_state_change(struct sock *sk) void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) { struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; - struct mptcp_sock *msk, *next, *head = NULL; - struct request_sock *req; - struct sock *sk; + struct request_sock *req, *head, *tail; + struct mptcp_subflow_context *subflow; + struct sock *sk, *ssk; - /* build a list of all unaccepted mptcp sockets */ + /* Due to lock dependencies no relevant lock can be acquired under rskq_lock. + * Splice the req list, so that accept() can not reach the pending ssk after + * the listener socket is released below. + */ spin_lock_bh(&queue->rskq_lock); - for (req = queue->rskq_accept_head; req; req = req->dl_next) { - struct mptcp_subflow_context *subflow; - struct sock *ssk = req->sk; + head = queue->rskq_accept_head; + tail = queue->rskq_accept_tail; + queue->rskq_accept_head = NULL; + queue->rskq_accept_tail = NULL; + spin_unlock_bh(&queue->rskq_lock); + + if (!head) + return; + /* can't acquire the msk socket lock under the subflow one, + * or will cause ABBA deadlock + */ + release_sock(listener_ssk); + + for (req = head; req; req = req->dl_next) { + ssk = req->sk; if (!sk_is_mptcp(ssk)) continue; @@ -1810,32 +1825,10 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s if (!subflow || !subflow->conn) continue; - /* skip if already in list */ sk = subflow->conn; - msk = mptcp_sk(sk); - if (msk->dl_next || msk == head) - continue; - sock_hold(sk); - msk->dl_next = head; - head = msk; - } - spin_unlock_bh(&queue->rskq_lock); - if (!head) - return; - - /* can't acquire the msk socket lock under the subflow one, - * or will cause ABBA deadlock - */ - release_sock(listener_ssk); - - for (msk = head; msk; msk = next) { - sk = (struct sock *)msk; lock_sock_nested(sk, SINGLE_DEPTH_NESTING); - next = msk->dl_next; - msk->dl_next = NULL; - __mptcp_unaccepted_force_close(sk); release_sock(sk); @@ -1859,6 +1852,13 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s /* we are still under the listener msk socket lock */ lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING); + + /* restore the listener queue, to let the TCP code clean it up */ + spin_lock_bh(&queue->rskq_lock); + WARN_ON_ONCE(queue->rskq_accept_head); + queue->rskq_accept_head = head; + queue->rskq_accept_tail = tail; + spin_unlock_bh(&queue->rskq_lock); } static int subflow_ulp_init(struct sock *sk) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d3c6ecd1f5a6..c62227ae7746 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -31,7 +31,9 @@ static LIST_HEAD(nf_tables_expressions); static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); static LIST_HEAD(nf_tables_destroy_list); +static LIST_HEAD(nf_tables_gc_list); static DEFINE_SPINLOCK(nf_tables_destroy_list_lock); +static DEFINE_SPINLOCK(nf_tables_gc_list_lock); enum { NFT_VALIDATE_SKIP = 0, @@ -120,6 +122,9 @@ static void nft_validate_state_update(struct nft_table *table, u8 new_validate_s static void nf_tables_trans_destroy_work(struct work_struct *w); static DECLARE_WORK(trans_destroy_work, nf_tables_trans_destroy_work); +static void nft_trans_gc_work(struct work_struct *work); +static DECLARE_WORK(trans_gc_work, nft_trans_gc_work); + static void nft_ctx_init(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, @@ -582,10 +587,6 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, return __nft_trans_set_add(ctx, msg_type, set, NULL); } -static void nft_setelem_data_deactivate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem); - static int nft_mapelem_deactivate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, @@ -5055,6 +5056,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, INIT_LIST_HEAD(&set->bindings); INIT_LIST_HEAD(&set->catchall_list); + refcount_set(&set->refs, 1); set->table = table; write_pnet(&set->net, net); set->ops = ops; @@ -5122,6 +5124,14 @@ static void nft_set_catchall_destroy(const struct nft_ctx *ctx, } } +static void nft_set_put(struct nft_set *set) +{ + if (refcount_dec_and_test(&set->refs)) { + kfree(set->name); + kvfree(set); + } +} + static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) { int i; @@ -5134,8 +5144,7 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) set->ops->destroy(ctx, set); nft_set_catchall_destroy(ctx, set); - kfree(set->name); - kvfree(set); + nft_set_put(set); } static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, @@ -5602,8 +5611,12 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_set_elem *elem) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); struct nft_set_dump_args *args; + if (nft_set_elem_expired(ext)) + return 0; + args = container_of(iter, struct nft_set_dump_args, iter); return nf_tables_fill_setelem(args->skb, set, elem, args->reset); } @@ -6274,7 +6287,8 @@ struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (nft_set_elem_active(ext, genmask) && - !nft_set_elem_expired(ext)) + !nft_set_elem_expired(ext) && + !nft_set_elem_is_dead(ext)) return ext; } @@ -6282,29 +6296,6 @@ struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, } EXPORT_SYMBOL_GPL(nft_set_catchall_lookup); -void *nft_set_catchall_gc(const struct nft_set *set) -{ - struct nft_set_elem_catchall *catchall, *next; - struct nft_set_ext *ext; - void *elem = NULL; - - list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { - ext = nft_set_elem_ext(set, catchall->elem); - - if (!nft_set_elem_expired(ext) || - nft_set_elem_mark_busy(ext)) - continue; - - elem = catchall->elem; - list_del_rcu(&catchall->list); - kfree_rcu(catchall, rcu); - break; - } - - return elem; -} -EXPORT_SYMBOL_GPL(nft_set_catchall_gc); - static int nft_setelem_catchall_insert(const struct net *net, struct nft_set *set, const struct nft_set_elem *elem, @@ -6366,7 +6357,6 @@ static void nft_setelem_activate(struct net *net, struct nft_set *set, if (nft_setelem_is_catchall(set, elem)) { nft_set_elem_change_active(net, set, ext); - nft_set_elem_clear_busy(ext); } else { set->ops->activate(net, set, elem); } @@ -6381,8 +6371,7 @@ static int nft_setelem_catchall_deactivate(const struct net *net, list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_is_active(net, ext) || - nft_set_elem_mark_busy(ext)) + if (!nft_is_active(net, ext)) continue; kfree(elem->priv); @@ -6777,7 +6766,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, goto err_elem_free; } - ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK; + ext->genmask = nft_genmask_cur(ctx->net); err = nft_setelem_insert(ctx->net, set, &elem, &ext2, flags); if (err) { @@ -6929,9 +6918,9 @@ static void nft_setelem_data_activate(const struct net *net, nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use); } -static void nft_setelem_data_deactivate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem) +void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -7095,8 +7084,7 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_active(ext, genmask) || - nft_set_elem_mark_busy(ext)) + if (!nft_set_elem_active(ext, genmask)) continue; elem.priv = catchall->elem; @@ -7170,29 +7158,6 @@ static int nf_tables_delsetelem(struct sk_buff *skb, return err; } -void nft_set_gc_batch_release(struct rcu_head *rcu) -{ - struct nft_set_gc_batch *gcb; - unsigned int i; - - gcb = container_of(rcu, struct nft_set_gc_batch, head.rcu); - for (i = 0; i < gcb->head.cnt; i++) - nft_set_elem_destroy(gcb->head.set, gcb->elems[i], true); - kfree(gcb); -} - -struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set, - gfp_t gfp) -{ - struct nft_set_gc_batch *gcb; - - gcb = kzalloc(sizeof(*gcb), gfp); - if (gcb == NULL) - return gcb; - gcb->head.set = set; - return gcb; -} - /* * Stateful objects */ @@ -9414,6 +9379,207 @@ void nft_chain_del(struct nft_chain *chain) list_del_rcu(&chain->list); } +static void nft_trans_gc_setelem_remove(struct nft_ctx *ctx, + struct nft_trans_gc *trans) +{ + void **priv = trans->priv; + unsigned int i; + + for (i = 0; i < trans->count; i++) { + struct nft_set_elem elem = { + .priv = priv[i], + }; + + nft_setelem_data_deactivate(ctx->net, trans->set, &elem); + nft_setelem_remove(ctx->net, trans->set, &elem); + } +} + +void nft_trans_gc_destroy(struct nft_trans_gc *trans) +{ + nft_set_put(trans->set); + put_net(trans->net); + kfree(trans); +} + +static void nft_trans_gc_trans_free(struct rcu_head *rcu) +{ + struct nft_set_elem elem = {}; + struct nft_trans_gc *trans; + struct nft_ctx ctx = {}; + unsigned int i; + + trans = container_of(rcu, struct nft_trans_gc, rcu); + ctx.net = read_pnet(&trans->set->net); + + for (i = 0; i < trans->count; i++) { + elem.priv = trans->priv[i]; + if (!nft_setelem_is_catchall(trans->set, &elem)) + atomic_dec(&trans->set->nelems); + + nf_tables_set_elem_destroy(&ctx, trans->set, elem.priv); + } + + nft_trans_gc_destroy(trans); +} + +static bool nft_trans_gc_work_done(struct nft_trans_gc *trans) +{ + struct nftables_pernet *nft_net; + struct nft_ctx ctx = {}; + + nft_net = nft_pernet(trans->net); + + mutex_lock(&nft_net->commit_mutex); + + /* Check for race with transaction, otherwise this batch refers to + * stale objects that might not be there anymore. Skip transaction if + * set has been destroyed from control plane transaction in case gc + * worker loses race. + */ + if (READ_ONCE(nft_net->gc_seq) != trans->seq || trans->set->dead) { + mutex_unlock(&nft_net->commit_mutex); + return false; + } + + ctx.net = trans->net; + ctx.table = trans->set->table; + + nft_trans_gc_setelem_remove(&ctx, trans); + mutex_unlock(&nft_net->commit_mutex); + + return true; +} + +static void nft_trans_gc_work(struct work_struct *work) +{ + struct nft_trans_gc *trans, *next; + LIST_HEAD(trans_gc_list); + + spin_lock(&nf_tables_destroy_list_lock); + list_splice_init(&nf_tables_gc_list, &trans_gc_list); + spin_unlock(&nf_tables_destroy_list_lock); + + list_for_each_entry_safe(trans, next, &trans_gc_list, list) { + list_del(&trans->list); + if (!nft_trans_gc_work_done(trans)) { + nft_trans_gc_destroy(trans); + continue; + } + call_rcu(&trans->rcu, nft_trans_gc_trans_free); + } +} + +struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, + unsigned int gc_seq, gfp_t gfp) +{ + struct net *net = read_pnet(&set->net); + struct nft_trans_gc *trans; + + trans = kzalloc(sizeof(*trans), gfp); + if (!trans) + return NULL; + + refcount_inc(&set->refs); + trans->set = set; + trans->net = get_net(net); + trans->seq = gc_seq; + + return trans; +} + +void nft_trans_gc_elem_add(struct nft_trans_gc *trans, void *priv) +{ + trans->priv[trans->count++] = priv; +} + +static void nft_trans_gc_queue_work(struct nft_trans_gc *trans) +{ + spin_lock(&nf_tables_gc_list_lock); + list_add_tail(&trans->list, &nf_tables_gc_list); + spin_unlock(&nf_tables_gc_list_lock); + + schedule_work(&trans_gc_work); +} + +static int nft_trans_gc_space(struct nft_trans_gc *trans) +{ + return NFT_TRANS_GC_BATCHCOUNT - trans->count; +} + +struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, + unsigned int gc_seq, gfp_t gfp) +{ + if (nft_trans_gc_space(gc)) + return gc; + + nft_trans_gc_queue_work(gc); + + return nft_trans_gc_alloc(gc->set, gc_seq, gfp); +} + +void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans) +{ + if (trans->count == 0) { + nft_trans_gc_destroy(trans); + return; + } + + nft_trans_gc_queue_work(trans); +} + +struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp) +{ + if (WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net))) + return NULL; + + if (nft_trans_gc_space(gc)) + return gc; + + call_rcu(&gc->rcu, nft_trans_gc_trans_free); + + return nft_trans_gc_alloc(gc->set, 0, gfp); +} + +void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) +{ + WARN_ON_ONCE(!lockdep_commit_lock_is_held(trans->net)); + + if (trans->count == 0) { + nft_trans_gc_destroy(trans); + return; + } + + call_rcu(&trans->rcu, nft_trans_gc_trans_free); +} + +struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, + unsigned int gc_seq) +{ + struct nft_set_elem_catchall *catchall; + const struct nft_set *set = gc->set; + struct nft_set_ext *ext; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + + if (!nft_set_elem_expired(ext)) + continue; + if (nft_set_elem_is_dead(ext)) + goto dead_elem; + + nft_set_elem_dead(ext); +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + return NULL; + + nft_trans_gc_elem_add(gc, catchall->elem); + } + + return gc; +} + static void nf_tables_module_autoload_cleanup(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); @@ -9576,11 +9742,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; + unsigned int base_seq, gc_seq; LIST_HEAD(set_update_list); struct nft_trans_elem *te; struct nft_chain *chain; struct nft_table *table; - unsigned int base_seq; LIST_HEAD(adl); int err; @@ -9657,6 +9823,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) WRITE_ONCE(nft_net->base_seq, base_seq); + /* Bump gc counter, it becomes odd, this is the busy mark. */ + gc_seq = READ_ONCE(nft_net->gc_seq); + WRITE_ONCE(nft_net->gc_seq, ++gc_seq); + /* step 3. Start new generation, rules_gen_X now in use. */ net->nft.gencursor = nft_gencursor_next(net); @@ -9764,6 +9934,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) break; case NFT_MSG_DELSET: case NFT_MSG_DESTROYSET: + nft_trans_set(trans)->dead = 1; list_del_rcu(&nft_trans_set(trans)->list); nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), trans->msg_type, GFP_KERNEL); @@ -9866,6 +10037,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); nf_tables_commit_audit_log(&adl, nft_net->base_seq); + + WRITE_ONCE(nft_net->gc_seq, ++gc_seq); nf_tables_commit_release(net); return 0; @@ -10915,6 +11088,7 @@ static int __net_init nf_tables_init_net(struct net *net) INIT_LIST_HEAD(&nft_net->notify_list); mutex_init(&nft_net->commit_mutex); nft_net->base_seq = 1; + nft_net->gc_seq = 0; return 0; } @@ -10943,10 +11117,16 @@ static void __net_exit nf_tables_exit_net(struct net *net) WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); } +static void nf_tables_exit_batch(struct list_head *net_exit_list) +{ + flush_work(&trans_gc_work); +} + static struct pernet_operations nf_tables_net_ops = { .init = nf_tables_init_net, .pre_exit = nf_tables_pre_exit_net, .exit = nf_tables_exit_net, + .exit_batch = nf_tables_exit_batch, .id = &nf_tables_net_id, .size = sizeof(struct nftables_pernet), }; @@ -11018,6 +11198,7 @@ static void __exit nf_tables_module_exit(void) nft_chain_filter_fini(); nft_chain_route_fini(); unregister_pernet_subsys(&nf_tables_net_ops); + cancel_work_sync(&trans_gc_work); cancel_work_sync(&trans_destroy_work); rcu_barrier(); rhltable_destroy(&nft_objname_ht); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 0b73cb0e752f..cef5df846000 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -59,6 +59,8 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg, if (memcmp(nft_set_ext_key(&he->ext), x->key, x->set->klen)) return 1; + if (nft_set_elem_is_dead(&he->ext)) + return 1; if (nft_set_elem_expired(&he->ext)) return 1; if (!nft_set_elem_active(&he->ext, x->genmask)) @@ -188,7 +190,6 @@ static void nft_rhash_activate(const struct net *net, const struct nft_set *set, struct nft_rhash_elem *he = elem->priv; nft_set_elem_change_active(net, set, &he->ext); - nft_set_elem_clear_busy(&he->ext); } static bool nft_rhash_flush(const struct net *net, @@ -196,12 +197,9 @@ static bool nft_rhash_flush(const struct net *net, { struct nft_rhash_elem *he = priv; - if (!nft_set_elem_mark_busy(&he->ext) || - !nft_is_active(net, &he->ext)) { - nft_set_elem_change_active(net, set, &he->ext); - return true; - } - return false; + nft_set_elem_change_active(net, set, &he->ext); + + return true; } static void *nft_rhash_deactivate(const struct net *net, @@ -218,9 +216,8 @@ static void *nft_rhash_deactivate(const struct net *net, rcu_read_lock(); he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); - if (he != NULL && - !nft_rhash_flush(net, set, he)) - he = NULL; + if (he) + nft_set_elem_change_active(net, set, &he->ext); rcu_read_unlock(); @@ -252,7 +249,9 @@ static bool nft_rhash_delete(const struct nft_set *set, if (he == NULL) return false; - return rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params) == 0; + nft_set_elem_dead(&he->ext); + + return true; } static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, @@ -278,8 +277,6 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, if (iter->count < iter->skip) goto cont; - if (nft_set_elem_expired(&he->ext)) - goto cont; if (!nft_set_elem_active(&he->ext, iter->genmask)) goto cont; @@ -314,25 +311,48 @@ static bool nft_rhash_expr_needs_gc_run(const struct nft_set *set, static void nft_rhash_gc(struct work_struct *work) { + struct nftables_pernet *nft_net; struct nft_set *set; struct nft_rhash_elem *he; struct nft_rhash *priv; - struct nft_set_gc_batch *gcb = NULL; struct rhashtable_iter hti; + struct nft_trans_gc *gc; + struct net *net; + u32 gc_seq; priv = container_of(work, struct nft_rhash, gc_work.work); set = nft_set_container_of(priv); + net = read_pnet(&set->net); + nft_net = nft_pernet(net); + gc_seq = READ_ONCE(nft_net->gc_seq); + + gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL); + if (!gc) + goto done; rhashtable_walk_enter(&priv->ht, &hti); rhashtable_walk_start(&hti); while ((he = rhashtable_walk_next(&hti))) { if (IS_ERR(he)) { - if (PTR_ERR(he) != -EAGAIN) - break; + if (PTR_ERR(he) != -EAGAIN) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } continue; } + /* Ruleset has been updated, try later. */ + if (READ_ONCE(nft_net->gc_seq) != gc_seq) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } + + if (nft_set_elem_is_dead(&he->ext)) + goto dead_elem; + if (nft_set_ext_exists(&he->ext, NFT_SET_EXT_EXPRESSIONS) && nft_rhash_expr_needs_gc_run(set, &he->ext)) goto needs_gc_run; @@ -340,26 +360,26 @@ static void nft_rhash_gc(struct work_struct *work) if (!nft_set_elem_expired(&he->ext)) continue; needs_gc_run: - if (nft_set_elem_mark_busy(&he->ext)) - continue; + nft_set_elem_dead(&he->ext); +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (gcb == NULL) - break; - rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, he); + nft_trans_gc_elem_add(gc, he); } + + gc = nft_trans_gc_catchall(gc, gc_seq); + +try_later: + /* catchall list iteration requires rcu read side lock. */ rhashtable_walk_stop(&hti); rhashtable_walk_exit(&hti); - he = nft_set_catchall_gc(set); - if (he) { - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (gcb) - nft_set_gc_batch_add(gcb, he); - } - nft_set_gc_batch_complete(gcb); + if (gc) + nft_trans_gc_queue_async_done(gc); + +done: queue_delayed_work(system_power_efficient_wq, &priv->gc_work, nft_set_gc_interval(set)); } @@ -394,7 +414,7 @@ static int nft_rhash_init(const struct nft_set *set, return err; INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rhash_gc); - if (set->flags & NFT_SET_TIMEOUT) + if (set->flags & (NFT_SET_TIMEOUT | NFT_SET_EVAL)) nft_rhash_gc_init(set); return 0; @@ -422,7 +442,6 @@ static void nft_rhash_destroy(const struct nft_ctx *ctx, }; cancel_delayed_work_sync(&priv->gc_work); - rcu_barrier(); rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, (void *)&rhash_ctx); } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 49915a2a58eb..a5b8301afe4a 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -566,8 +566,7 @@ next_match: goto out; if (last) { - if (nft_set_elem_expired(&f->mt[b].e->ext) || - (genmask && + if ((genmask && !nft_set_elem_active(&f->mt[b].e->ext, genmask))) goto next_match; @@ -601,8 +600,17 @@ out: static void *nft_pipapo_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { - return pipapo_get(net, set, (const u8 *)elem->key.val.data, - nft_genmask_cur(net)); + struct nft_pipapo_elem *ret; + + ret = pipapo_get(net, set, (const u8 *)elem->key.val.data, + nft_genmask_cur(net)); + if (IS_ERR(ret)) + return ret; + + if (nft_set_elem_expired(&ret->ext)) + return ERR_PTR(-ENOENT); + + return ret; } /** @@ -1528,16 +1536,34 @@ static void pipapo_drop(struct nft_pipapo_match *m, } } +static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set, + struct nft_pipapo_elem *e) + +{ + struct nft_set_elem elem = { + .priv = e, + }; + + nft_setelem_data_deactivate(net, set, &elem); +} + /** * pipapo_gc() - Drop expired entries from set, destroy start and end elements * @set: nftables API set representation * @m: Matching data */ -static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) +static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) { + struct nft_set *set = (struct nft_set *) _set; struct nft_pipapo *priv = nft_set_priv(set); + struct net *net = read_pnet(&set->net); int rules_f0, first_rule = 0; struct nft_pipapo_elem *e; + struct nft_trans_gc *gc; + + gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); + if (!gc) + return; while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; @@ -1561,13 +1587,20 @@ static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) f--; i--; e = f->mt[rulemap[i].to].e; - if (nft_set_elem_expired(&e->ext) && - !nft_set_elem_mark_busy(&e->ext)) { + + /* synchronous gc never fails, there is no need to set on + * NFT_SET_ELEM_DEAD_BIT. + */ + if (nft_set_elem_expired(&e->ext)) { priv->dirty = true; - pipapo_drop(m, rulemap); - rcu_barrier(); - nft_set_elem_destroy(set, e, true); + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (!gc) + break; + + nft_pipapo_gc_deactivate(net, set, e); + pipapo_drop(m, rulemap); + nft_trans_gc_elem_add(gc, e); /* And check again current first rule, which is now the * first we haven't checked. @@ -1577,11 +1610,11 @@ static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) } } - e = nft_set_catchall_gc(set); - if (e) - nft_set_elem_destroy(set, e, true); - - priv->last_gc = jiffies; + gc = nft_trans_gc_catchall(gc, 0); + if (gc) { + nft_trans_gc_queue_sync_done(gc); + priv->last_gc = jiffies; + } } /** @@ -1706,7 +1739,6 @@ static void nft_pipapo_activate(const struct net *net, return; nft_set_elem_change_active(net, set, &e->ext); - nft_set_elem_clear_busy(&e->ext); } /** @@ -2005,8 +2037,6 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, goto cont; e = f->mt[r].e; - if (nft_set_elem_expired(&e->ext)) - goto cont; elem.priv = e; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 8d73fffd2d09..f9d4c8fcbbf8 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -46,6 +46,12 @@ static int nft_rbtree_cmp(const struct nft_set *set, set->klen); } +static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe) +{ + return nft_set_elem_expired(&rbe->ext) || + nft_set_elem_is_dead(&rbe->ext); +} + static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext, unsigned int seq) @@ -80,7 +86,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set continue; } - if (nft_set_elem_expired(&rbe->ext)) + if (nft_rbtree_elem_expired(rbe)) return false; if (nft_rbtree_interval_end(rbe)) { @@ -98,7 +104,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && - !nft_set_elem_expired(&interval->ext) && + !nft_rbtree_elem_expired(interval) && nft_rbtree_interval_start(interval)) { *ext = &interval->ext; return true; @@ -215,6 +221,18 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set, return rbe; } +static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) +{ + struct nft_set_elem elem = { + .priv = rbe, + }; + + nft_setelem_data_deactivate(net, set, &elem); + rb_erase(&rbe->node, &priv->root); +} + static int nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, struct nft_rbtree_elem *rbe, @@ -222,11 +240,12 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); + struct net *net = read_pnet(&set->net); struct nft_rbtree_elem *rbe_prev; - struct nft_set_gc_batch *gcb; + struct nft_trans_gc *gc; - gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); - if (!gcb) + gc = nft_trans_gc_alloc(set, 0, GFP_ATOMIC); + if (!gc) return -ENOMEM; /* search for end interval coming before this element. @@ -244,17 +263,28 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, if (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); + nft_rbtree_gc_remove(net, set, priv, rbe_prev); - rb_erase(&rbe_prev->node, &priv->root); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe_prev); + /* There is always room in this trans gc for this element, + * memory allocation never actually happens, hence, the warning + * splat in such case. No need to set NFT_SET_ELEM_DEAD_BIT, + * this is synchronous gc which never fails. + */ + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (WARN_ON_ONCE(!gc)) + return -ENOMEM; + + nft_trans_gc_elem_add(gc, rbe_prev); } - rb_erase(&rbe->node, &priv->root); - atomic_dec(&set->nelems); + nft_rbtree_gc_remove(net, set, priv, rbe); + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (WARN_ON_ONCE(!gc)) + return -ENOMEM; + + nft_trans_gc_elem_add(gc, rbe); - nft_set_gc_batch_add(gcb, rbe); - nft_set_gc_batch_complete(gcb); + nft_trans_gc_queue_sync_done(gc); return 0; } @@ -482,7 +512,6 @@ static void nft_rbtree_activate(const struct net *net, struct nft_rbtree_elem *rbe = elem->priv; nft_set_elem_change_active(net, set, &rbe->ext); - nft_set_elem_clear_busy(&rbe->ext); } static bool nft_rbtree_flush(const struct net *net, @@ -490,12 +519,9 @@ static bool nft_rbtree_flush(const struct net *net, { struct nft_rbtree_elem *rbe = priv; - if (!nft_set_elem_mark_busy(&rbe->ext) || - !nft_is_active(net, &rbe->ext)) { - nft_set_elem_change_active(net, set, &rbe->ext); - return true; - } - return false; + nft_set_elem_change_active(net, set, &rbe->ext); + + return true; } static void *nft_rbtree_deactivate(const struct net *net, @@ -552,8 +578,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, if (iter->count < iter->skip) goto cont; - if (nft_set_elem_expired(&rbe->ext)) - goto cont; if (!nft_set_elem_active(&rbe->ext, iter->genmask)) goto cont; @@ -572,26 +596,40 @@ cont: static void nft_rbtree_gc(struct work_struct *work) { - struct nft_rbtree_elem *rbe, *rbe_end = NULL, *rbe_prev = NULL; - struct nft_set_gc_batch *gcb = NULL; + struct nft_rbtree_elem *rbe, *rbe_end = NULL; + struct nftables_pernet *nft_net; struct nft_rbtree *priv; + struct nft_trans_gc *gc; struct rb_node *node; struct nft_set *set; + unsigned int gc_seq; struct net *net; - u8 genmask; priv = container_of(work, struct nft_rbtree, gc_work.work); set = nft_set_container_of(priv); net = read_pnet(&set->net); - genmask = nft_genmask_cur(net); + nft_net = nft_pernet(net); + gc_seq = READ_ONCE(nft_net->gc_seq); + + gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL); + if (!gc) + goto done; write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { + + /* Ruleset has been updated, try later. */ + if (READ_ONCE(nft_net->gc_seq) != gc_seq) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } + rbe = rb_entry(node, struct nft_rbtree_elem, node); - if (!nft_set_elem_active(&rbe->ext, genmask)) - continue; + if (nft_set_elem_is_dead(&rbe->ext)) + goto dead_elem; /* elements are reversed in the rbtree for historical reasons, * from highest to lowest value, that is why end element is @@ -604,46 +642,36 @@ static void nft_rbtree_gc(struct work_struct *work) if (!nft_set_elem_expired(&rbe->ext)) continue; - if (nft_set_elem_mark_busy(&rbe->ext)) { - rbe_end = NULL; + nft_set_elem_dead(&rbe->ext); + + if (!rbe_end) continue; - } - if (rbe_prev) { - rb_erase(&rbe_prev->node, &priv->root); - rbe_prev = NULL; - } - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (!gcb) - break; + nft_set_elem_dead(&rbe_end->ext); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe); - rbe_prev = rbe; + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; - if (rbe_end) { - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe_end); - rb_erase(&rbe_end->node, &priv->root); - rbe_end = NULL; - } - node = rb_next(node); - if (!node) - break; + nft_trans_gc_elem_add(gc, rbe_end); + rbe_end = NULL; +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; + + nft_trans_gc_elem_add(gc, rbe); } - if (rbe_prev) - rb_erase(&rbe_prev->node, &priv->root); + + gc = nft_trans_gc_catchall(gc, gc_seq); + +try_later: write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); - rbe = nft_set_catchall_gc(set); - if (rbe) { - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (gcb) - nft_set_gc_batch_add(gcb, rbe); - } - nft_set_gc_batch_complete(gcb); - + if (gc) + nft_trans_gc_queue_async_done(gc); +done: queue_delayed_work(system_power_efficient_wq, &priv->gc_work, nft_set_gc_interval(set)); } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a4631cb457a9..a2935bd18ed9 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -401,18 +401,20 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union tpacket_uhdr h; + /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: - h.h1->tp_status = status; + WRITE_ONCE(h.h1->tp_status, status); flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: - h.h2->tp_status = status; + WRITE_ONCE(h.h2->tp_status, status); flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: - h.h3->tp_status = status; + WRITE_ONCE(h.h3->tp_status, status); flush_dcache_page(pgv_to_page(&h.h3->tp_status)); break; default: @@ -429,17 +431,19 @@ static int __packet_get_status(const struct packet_sock *po, void *frame) smp_rmb(); + /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); - return h.h1->tp_status; + return READ_ONCE(h.h1->tp_status); case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); - return h.h2->tp_status; + return READ_ONCE(h.h2->tp_status); case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); - return h.h3->tp_status; + return READ_ONCE(h.h3->tp_status); default: WARN(1, "TPACKET version not supported.\n"); BUG(); 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 2021fe557e50..529101eb20bd 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -52,6 +52,8 @@ static LIST_HEAD(tls_device_list); static LIST_HEAD(tls_device_down_list); static DEFINE_SPINLOCK(tls_device_lock); +static struct page *dummy_page; + static void tls_device_free_ctx(struct tls_context *ctx) { if (ctx->tx_conf == TLS_HW) { @@ -312,36 +314,33 @@ static int tls_push_record(struct sock *sk, return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags); } -static int tls_device_record_close(struct sock *sk, - struct tls_context *ctx, - struct tls_record_info *record, - struct page_frag *pfrag, - unsigned char record_type) +static void tls_device_record_close(struct sock *sk, + struct tls_context *ctx, + struct tls_record_info *record, + struct page_frag *pfrag, + unsigned char record_type) { struct tls_prot_info *prot = &ctx->prot_info; - int ret; + struct page_frag dummy_tag_frag; /* append tag * device will fill in the tag, we just need to append a placeholder * use socket memory to improve coalescing (re-using a single buffer * increases frag count) - * if we can't allocate memory now, steal some back from data + * if we can't allocate memory now use the dummy page */ - if (likely(skb_page_frag_refill(prot->tag_size, pfrag, - sk->sk_allocation))) { - ret = 0; - tls_append_frag(record, pfrag, prot->tag_size); - } else { - ret = prot->tag_size; - if (record->len <= prot->overhead_size) - return -ENOMEM; + if (unlikely(pfrag->size - pfrag->offset < prot->tag_size) && + !skb_page_frag_refill(prot->tag_size, pfrag, sk->sk_allocation)) { + dummy_tag_frag.page = dummy_page; + dummy_tag_frag.offset = 0; + pfrag = &dummy_tag_frag; } + tls_append_frag(record, pfrag, prot->tag_size); /* fill prepend */ tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]), record->len - prot->overhead_size, record_type); - return ret; } static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx, @@ -541,18 +540,8 @@ last_record: if (done || record->len >= max_open_record_len || (record->num_frags >= MAX_SKB_FRAGS - 1)) { - rc = tls_device_record_close(sk, tls_ctx, record, - pfrag, record_type); - if (rc) { - if (rc > 0) { - size += rc; - } else { - size = orig_size; - destroy_record(record); - ctx->open_record = NULL; - break; - } - } + tls_device_record_close(sk, tls_ctx, record, + pfrag, record_type); rc = tls_push_record(sk, tls_ctx, @@ -1450,14 +1439,26 @@ int __init tls_device_init(void) { int err; - destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); - if (!destruct_wq) + dummy_page = alloc_page(GFP_KERNEL); + if (!dummy_page) return -ENOMEM; + destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); + if (!destruct_wq) { + err = -ENOMEM; + goto err_free_dummy; + } + err = register_netdevice_notifier(&tls_dev_notifier); if (err) - destroy_workqueue(destruct_wq); + goto err_destroy_wq; + return 0; + +err_destroy_wq: + destroy_workqueue(destruct_wq); +err_free_dummy: + put_page(dummy_page); return err; } @@ -1466,4 +1467,5 @@ void __exit tls_device_cleanup(void) unregister_netdevice_notifier(&tls_dev_notifier); destroy_workqueue(destruct_wq); clean_acked_data_flush(); + put_page(dummy_page); } diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index b6896126bb92..4a8ee2f6badb 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -139,9 +139,6 @@ int tls_push_sg(struct sock *sk, ctx->splicing_pages = true; while (1) { - if (sg_is_last(sg)) - msg.msg_flags = flags; - /* is sending application-limited? */ tcp_rate_check_app_limited(sk); p = sg_page(sg); diff --git a/net/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 b89adb52a977..10ea85c03147 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -994,6 +994,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) err = xp_alloc_tx_descs(xs->pool, xs); if (err) { xp_put_pool(xs->pool); + xs->pool = NULL; sockfd_put(sock); goto out_unlock; } diff --git a/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/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/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/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 0f5e88c8f4ff..df8d90b51867 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1981,6 +1981,11 @@ basic() run_cmd "$IP link set dev lo up" + # Dump should not loop endlessly when maximum nexthop ID is configured. + run_cmd "$IP nexthop add id $((2**32-1)) blackhole" + run_cmd "timeout 5 $IP nexthop" + log_test $? 0 "Maximum nexthop ID dump" + # # groups # @@ -2201,6 +2206,11 @@ basic_res() run_cmd "$IP nexthop bucket list fdb" log_test $? 255 "Dump all nexthop buckets with invalid 'fdb' keyword" + # Dump should not loop endlessly when maximum nexthop ID is configured. + run_cmd "$IP nexthop add id $((2**32-1)) group 1/2 type resilient buckets 4" + run_cmd "timeout 5 $IP nexthop bucket" + log_test $? 0 "Maximum nexthop ID dump" + # # resilient nexthop buckets get requests # diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index ae3f9462a2b6..d0c6c499d5da 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -617,7 +617,7 @@ __cfg_test_port_ip_sg() grep -q "permanent" check_err $? "Entry not added as \"permanent\" when should" bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "0.00" + grep -q " 0.00" check_err $? "\"permanent\" entry has a pending group timer" bridge mdb del dev br0 port $swp1 $grp_key vid 10 @@ -626,7 +626,7 @@ __cfg_test_port_ip_sg() grep -q "temp" check_err $? "Entry not added as \"temp\" when should" bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "0.00" + grep -q " 0.00" check_fail $? "\"temp\" entry has an unpending group timer" bridge mdb del dev br0 port $swp1 $grp_key vid 10 @@ -659,7 +659,7 @@ __cfg_test_port_ip_sg() grep -q "permanent" check_err $? "Entry not marked as \"permanent\" after replace" bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "0.00" + grep -q " 0.00" check_err $? "Entry has a pending group timer after replace" bridge mdb replace dev br0 port $swp1 $grp_key vid 10 temp @@ -667,7 +667,7 @@ __cfg_test_port_ip_sg() grep -q "temp" check_err $? "Entry not marked as \"temp\" after replace" bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "0.00" + grep -q " 0.00" check_fail $? "Entry has an unpending group timer after replace" bridge mdb del dev br0 port $swp1 $grp_key vid 10 @@ -850,6 +850,7 @@ cfg_test() __fwd_test_host_ip() { local grp=$1; shift + local dmac=$1; shift local src=$1; shift local mode=$1; shift local name @@ -872,27 +873,27 @@ __fwd_test_host_ip() # Packet should only be flooded to multicast router ports when there is # no matching MDB entry. The bridge is not configured as a multicast # router port. - $MZ $mode $h1.10 -c 1 -p 128 -A $src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $src -B $grp -t udp -q tc_check_packets "dev br0 ingress" 1 0 check_err $? "Packet locally received after flood" # Install a regular port group entry and expect the packet to not be # locally received. bridge mdb add dev br0 port $swp2 grp $grp temp vid 10 - $MZ $mode $h1.10 -c 1 -p 128 -A $src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $src -B $grp -t udp -q tc_check_packets "dev br0 ingress" 1 0 check_err $? "Packet locally received after installing a regular entry" # Add a host entry and expect the packet to be locally received. bridge mdb add dev br0 port br0 grp $grp temp vid 10 - $MZ $mode $h1.10 -c 1 -p 128 -A $src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $src -B $grp -t udp -q tc_check_packets "dev br0 ingress" 1 1 check_err $? "Packet not locally received after adding a host entry" # Remove the host entry and expect the packet to not be locally # received. bridge mdb del dev br0 port br0 grp $grp vid 10 - $MZ $mode $h1.10 -c 1 -p 128 -A $src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $src -B $grp -t udp -q tc_check_packets "dev br0 ingress" 1 1 check_err $? "Packet locally received after removing a host entry" @@ -905,8 +906,8 @@ __fwd_test_host_ip() fwd_test_host_ip() { - __fwd_test_host_ip "239.1.1.1" "192.0.2.1" "-4" - __fwd_test_host_ip "ff0e::1" "2001:db8:1::1" "-6" + __fwd_test_host_ip "239.1.1.1" "01:00:5e:01:01:01" "192.0.2.1" "-4" + __fwd_test_host_ip "ff0e::1" "33:33:00:00:00:01" "2001:db8:1::1" "-6" } fwd_test_host_l2() @@ -966,6 +967,7 @@ fwd_test_host() __fwd_test_port_ip() { local grp=$1; shift + local dmac=$1; shift local valid_src=$1; shift local invalid_src=$1; shift local mode=$1; shift @@ -999,43 +1001,43 @@ __fwd_test_port_ip() vlan_ethtype $eth_type vlan_id 10 dst_ip $grp \ src_ip $invalid_src action drop - $MZ $mode $h1.10 -c 1 -p 128 -A $valid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $valid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 1 0 check_err $? "Packet from valid source received on H2 before adding entry" - $MZ $mode $h1.10 -c 1 -p 128 -A $invalid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $invalid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 2 0 check_err $? "Packet from invalid source received on H2 before adding entry" bridge mdb add dev br0 port $swp2 grp $grp vid 10 \ filter_mode $filter_mode source_list $src_list - $MZ $mode $h1.10 -c 1 -p 128 -A $valid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $valid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 1 1 check_err $? "Packet from valid source not received on H2 after adding entry" - $MZ $mode $h1.10 -c 1 -p 128 -A $invalid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $invalid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 2 0 check_err $? "Packet from invalid source received on H2 after adding entry" bridge mdb replace dev br0 port $swp2 grp $grp vid 10 \ filter_mode exclude - $MZ $mode $h1.10 -c 1 -p 128 -A $valid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $valid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 1 2 check_err $? "Packet from valid source not received on H2 after allowing all sources" - $MZ $mode $h1.10 -c 1 -p 128 -A $invalid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $invalid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 2 1 check_err $? "Packet from invalid source not received on H2 after allowing all sources" bridge mdb del dev br0 port $swp2 grp $grp vid 10 - $MZ $mode $h1.10 -c 1 -p 128 -A $valid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $valid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 1 2 check_err $? "Packet from valid source received on H2 after deleting entry" - $MZ $mode $h1.10 -c 1 -p 128 -A $invalid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $invalid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 2 1 check_err $? "Packet from invalid source received on H2 after deleting entry" @@ -1047,11 +1049,11 @@ __fwd_test_port_ip() fwd_test_port_ip() { - __fwd_test_port_ip "239.1.1.1" "192.0.2.1" "192.0.2.2" "-4" "exclude" - __fwd_test_port_ip "ff0e::1" "2001:db8:1::1" "2001:db8:1::2" "-6" \ + __fwd_test_port_ip "239.1.1.1" "01:00:5e:01:01:01" "192.0.2.1" "192.0.2.2" "-4" "exclude" + __fwd_test_port_ip "ff0e::1" "33:33:00:00:00:01" "2001:db8:1::1" "2001:db8:1::2" "-6" \ "exclude" - __fwd_test_port_ip "239.1.1.1" "192.0.2.1" "192.0.2.2" "-4" "include" - __fwd_test_port_ip "ff0e::1" "2001:db8:1::1" "2001:db8:1::2" "-6" \ + __fwd_test_port_ip "239.1.1.1" "01:00:5e:01:01:01" "192.0.2.1" "192.0.2.2" "-4" "include" + __fwd_test_port_ip "ff0e::1" "33:33:00:00:00:01" "2001:db8:1::1" "2001:db8:1::2" "-6" \ "include" } @@ -1127,7 +1129,7 @@ ctrl_igmpv3_is_in_test() filter_mode include source_list 192.0.2.1 # IS_IN ( 192.0.2.2 ) - $MZ $h1.10 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ + $MZ $h1.10 -c 1 -a own -b 01:00:5e:01:01:01 -A 192.0.2.1 -B 239.1.1.1 \ -t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -q 192.0.2.2 @@ -1140,7 +1142,7 @@ ctrl_igmpv3_is_in_test() filter_mode include source_list 192.0.2.1 # IS_IN ( 192.0.2.2 ) - $MZ $h1.10 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ + $MZ $h1.10 -a own -b 01:00:5e:01:01:01 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ -t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -v "src" | \ @@ -1167,7 +1169,7 @@ ctrl_mldv2_is_in_test() # IS_IN ( 2001:db8:1::2 ) local p=$(mldv2_is_in_get fe80::1 ff0e::1 2001:db8:1::2) - $MZ -6 $h1.10 -c 1 -A fe80::1 -B ff0e::1 \ + $MZ -6 $h1.10 -a own -b 33:33:00:00:00:01 -c 1 -A fe80::1 -B ff0e::1 \ -t ip hop=1,next=0,p="$p" -q bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | \ @@ -1181,7 +1183,7 @@ ctrl_mldv2_is_in_test() filter_mode include source_list 2001:db8:1::1 # IS_IN ( 2001:db8:1::2 ) - $MZ -6 $h1.10 -c 1 -A fe80::1 -B ff0e::1 \ + $MZ -6 $h1.10 -a own -b 33:33:00:00:00:01 -c 1 -A fe80::1 -B ff0e::1 \ -t ip hop=1,next=0,p="$p" -q bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | grep -v "src" | \ @@ -1206,6 +1208,11 @@ ctrl_test() ctrl_mldv2_is_in_test } +if ! bridge mdb help 2>&1 | grep -q "replace"; then + echo "SKIP: iproute2 too old, missing bridge mdb replace support" + exit $ksft_skip +fi + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh index ae255b662ba3..3da9d93ab36f 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh @@ -252,7 +252,8 @@ ctl4_entries_add() local IPs=$(seq -f 192.0.2.%g 1 $((n - 1))) local peer=$(locus_dev_peer $locus) local GRP=239.1.1.${grp} - $MZ $peer -c 1 -A 192.0.2.1 -B $GRP \ + local dmac=01:00:5e:01:01:$(printf "%02x" $grp) + $MZ $peer -a own -b $dmac -c 1 -A 192.0.2.1 -B $GRP \ -t ip proto=2,p=$(igmpv3_is_in_get $GRP $IPs) -q sleep 1 @@ -272,7 +273,8 @@ ctl4_entries_del() local peer=$(locus_dev_peer $locus) local GRP=239.1.1.${grp} - $MZ $peer -c 1 -A 192.0.2.1 -B 224.0.0.2 \ + local dmac=01:00:5e:00:00:02 + $MZ $peer -a own -b $dmac -c 1 -A 192.0.2.1 -B 224.0.0.2 \ -t ip proto=2,p=$(igmpv2_leave_get $GRP) -q sleep 1 ! bridge mdb show dev br0 | grep -q $GRP @@ -289,8 +291,10 @@ ctl6_entries_add() local peer=$(locus_dev_peer $locus) local SIP=fe80::1 local GRP=ff0e::${grp} + local dmac=33:33:00:00:00:$(printf "%02x" $grp) local p=$(mldv2_is_in_get $SIP $GRP $IPs) - $MZ -6 $peer -c 1 -A $SIP -B $GRP -t ip hop=1,next=0,p="$p" -q + $MZ -6 $peer -a own -b $dmac -c 1 -A $SIP -B $GRP \ + -t ip hop=1,next=0,p="$p" -q sleep 1 local nn=$(bridge mdb show dev br0 | grep $GRP | wc -l) @@ -310,8 +314,10 @@ ctl6_entries_del() local peer=$(locus_dev_peer $locus) local SIP=fe80::1 local GRP=ff0e::${grp} + local dmac=33:33:00:00:00:$(printf "%02x" $grp) local p=$(mldv1_done_get $SIP $GRP) - $MZ -6 $peer -c 1 -A $SIP -B $GRP -t ip hop=1,next=0,p="$p" -q + $MZ -6 $peer -a own -b $dmac -c 1 -A $SIP -B $GRP \ + -t ip hop=1,next=0,p="$p" -q sleep 1 ! bridge mdb show dev br0 | grep -q $GRP } @@ -1328,6 +1334,11 @@ test_8021qvs() switch_destroy } +if ! bridge link help 2>&1 | grep -q "mcast_max_groups"; then + echo "SKIP: iproute2 too old, missing bridge \"mcast_max_groups\" support" + exit $ksft_skip +fi + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh index dbb9fcf759e0..aa2eafb7b243 100755 --- a/tools/testing/selftests/net/forwarding/ethtool.sh +++ b/tools/testing/selftests/net/forwarding/ethtool.sh @@ -286,6 +286,8 @@ different_speeds_autoneg_on() ethtool -s $h1 autoneg on } +skip_on_veth + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh index 072faa77f53b..17f89c3b7c02 100755 --- a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh +++ b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh @@ -108,6 +108,8 @@ no_cable() ip link set dev $swp3 down } +skip_on_veth + setup_prepare tests_run diff --git a/tools/testing/selftests/net/forwarding/ethtool_mm.sh b/tools/testing/selftests/net/forwarding/ethtool_mm.sh index c580ad623848..39e736f30322 100755 --- a/tools/testing/selftests/net/forwarding/ethtool_mm.sh +++ b/tools/testing/selftests/net/forwarding/ethtool_mm.sh @@ -258,11 +258,6 @@ h2_destroy() setup_prepare() { - check_ethtool_mm_support - check_tc_fp_support - require_command lldptool - bail_on_lldpad "autoconfigure the MAC Merge layer" "configure it manually" - h1=${NETIFS[p1]} h2=${NETIFS[p2]} @@ -278,6 +273,19 @@ cleanup() h1_destroy } +check_ethtool_mm_support +check_tc_fp_support +require_command lldptool +bail_on_lldpad "autoconfigure the MAC Merge layer" "configure it manually" + +for netif in ${NETIFS[@]}; do + ethtool --show-mm $netif 2>&1 &> /dev/null + if [[ $? -ne 0 ]]; then + echo "SKIP: $netif does not support MAC Merge" + exit $ksft_skip + fi +done + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh b/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh index eb9ec4a68f84..7594bbb49029 100755 --- a/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh +++ b/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh @@ -99,6 +99,8 @@ test_stats_rx() test_stats g2a rx } +skip_on_veth + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh index 9f5b3e2e5e95..49fa94b53a1c 100755 --- a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh +++ b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh @@ -14,6 +14,8 @@ ALL_TESTS=" NUM_NETIFS=4 source lib.sh +require_command $TROUTE6 + h1_create() { simple_if_init $h1 2001:1:1::2/64 diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 9ddb68dd6a08..f69015bf2dea 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -30,6 +30,7 @@ REQUIRE_MZ=${REQUIRE_MZ:=yes} REQUIRE_MTOOLS=${REQUIRE_MTOOLS:=no} STABLE_MAC_ADDRS=${STABLE_MAC_ADDRS:=no} TCPDUMP_EXTRA_FLAGS=${TCPDUMP_EXTRA_FLAGS:=} +TROUTE6=${TROUTE6:=traceroute6} relative_path="${BASH_SOURCE%/*}" if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then @@ -163,6 +164,17 @@ check_port_mab_support() fi } +skip_on_veth() +{ + local kind=$(ip -j -d link show dev ${NETIFS[p1]} | + jq -r '.[].linkinfo.info_kind') + + if [[ $kind == veth ]]; then + echo "SKIP: Test cannot be run with veth pairs" + exit $ksft_skip + fi +} + if [[ "$(id -u)" -ne 0 ]]; then echo "SKIP: need root privileges" exit $ksft_skip @@ -225,6 +237,11 @@ create_netif_veth() for ((i = 1; i <= NUM_NETIFS; ++i)); do local j=$((i+1)) + if [ -z ${NETIFS[p$i]} ]; then + echo "SKIP: Cannot create interface. Name not specified" + exit $ksft_skip + fi + ip link show dev ${NETIFS[p$i]} &> /dev/null if [[ $? -ne 0 ]]; then ip link add ${NETIFS[p$i]} type veth \ diff --git a/tools/testing/selftests/net/forwarding/settings b/tools/testing/selftests/net/forwarding/settings new file mode 100644 index 000000000000..e7b9417537fb --- /dev/null +++ b/tools/testing/selftests/net/forwarding/settings @@ -0,0 +1 @@ +timeout=0 diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index a96cff8e7219..b0f5e55d2d0b 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -9,6 +9,8 @@ NUM_NETIFS=4 source tc_common.sh source lib.sh +require_command ncat + tcflags="skip_hw" h1_create() @@ -220,9 +222,9 @@ mirred_egress_to_ingress_tcp_test() ip_proto icmp \ action drop - ip vrf exec v$h1 nc --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & + ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & local rpid=$! - ip vrf exec v$h1 nc -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 + ip vrf exec v$h1 ncat -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 wait -n $rpid cmp -s $mirred_e2i_tf1 $mirred_e2i_tf2 check_err $? "server output check failed" diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh index 683711f41aa9..b1daad19b01e 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower.sh @@ -52,8 +52,8 @@ match_dst_mac_test() tc_check_packets "dev $h2 ingress" 101 1 check_fail $? "Matched on a wrong filter" - tc_check_packets "dev $h2 ingress" 102 1 - check_err $? "Did not match on correct filter" + tc_check_packets "dev $h2 ingress" 102 0 + check_fail $? "Did not match on correct filter" tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower @@ -78,8 +78,8 @@ match_src_mac_test() tc_check_packets "dev $h2 ingress" 101 1 check_fail $? "Matched on a wrong filter" - tc_check_packets "dev $h2 ingress" 102 1 - check_err $? "Did not match on correct filter" + tc_check_packets "dev $h2 ingress" 102 0 + check_fail $? "Did not match on correct filter" tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower diff --git a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh index e22c2d28b6eb..20a7cb7222b8 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh @@ -127,6 +127,7 @@ test_l2_miss_multicast_common() local proto=$1; shift local sip=$1; shift local dip=$1; shift + local dmac=$1; shift local mode=$1; shift local name=$1; shift @@ -142,7 +143,7 @@ test_l2_miss_multicast_common() action pass # Before adding MDB entry. - $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + $MZ $mode $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q tc_check_packets "dev $swp2 egress" 101 1 check_err $? "Unregistered multicast filter was not hit before adding MDB entry" @@ -153,7 +154,7 @@ test_l2_miss_multicast_common() # Adding MDB entry. bridge mdb replace dev br1 port $swp2 grp $dip permanent - $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + $MZ $mode $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q tc_check_packets "dev $swp2 egress" 101 1 check_err $? "Unregistered multicast filter was hit after adding MDB entry" @@ -164,7 +165,7 @@ test_l2_miss_multicast_common() # Deleting MDB entry. bridge mdb del dev br1 port $swp2 grp $dip - $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + $MZ $mode $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q tc_check_packets "dev $swp2 egress" 101 2 check_err $? "Unregistered multicast filter was not hit after deleting MDB entry" @@ -183,10 +184,11 @@ test_l2_miss_multicast_ipv4() local proto="ipv4" local sip=192.0.2.1 local dip=239.1.1.1 + local dmac=01:00:5e:01:01:01 local mode="-4" local name="IPv4" - test_l2_miss_multicast_common $proto $sip $dip $mode $name + test_l2_miss_multicast_common $proto $sip $dip $dmac $mode $name } test_l2_miss_multicast_ipv6() @@ -194,10 +196,11 @@ test_l2_miss_multicast_ipv6() local proto="ipv6" local sip=2001:db8:1::1 local dip=ff0e::1 + local dmac=33:33:00:00:00:01 local mode="-6" local name="IPv6" - test_l2_miss_multicast_common $proto $sip $dip $mode $name + test_l2_miss_multicast_common $proto $sip $dip $dmac $mode $name } test_l2_miss_multicast() diff --git a/tools/testing/selftests/net/forwarding/tc_tunnel_key.sh b/tools/testing/selftests/net/forwarding/tc_tunnel_key.sh index 5ac184d51809..5a5dd9034819 100755 --- a/tools/testing/selftests/net/forwarding/tc_tunnel_key.sh +++ b/tools/testing/selftests/net/forwarding/tc_tunnel_key.sh @@ -104,11 +104,14 @@ tunnel_key_nofrag_test() local i tc filter add dev $swp1 ingress protocol ip pref 100 handle 100 \ - flower ip_flags nofrag action drop + flower src_ip 192.0.2.1 dst_ip 192.0.2.2 ip_proto udp \ + ip_flags nofrag action drop tc filter add dev $swp1 ingress protocol ip pref 101 handle 101 \ - flower ip_flags firstfrag action drop + flower src_ip 192.0.2.1 dst_ip 192.0.2.2 ip_proto udp \ + ip_flags firstfrag action drop tc filter add dev $swp1 ingress protocol ip pref 102 handle 102 \ - flower ip_flags nofirstfrag action drop + flower src_ip 192.0.2.1 dst_ip 192.0.2.2 ip_proto udp \ + ip_flags nofirstfrag action drop # test 'nofrag' set tc filter add dev h1-et egress protocol all pref 1 handle 1 matchall $tcflags \ diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 3c2096ac97ef..d01b73a8ed0f 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -705,6 +705,7 @@ pm_nl_del_endpoint() local addr=$3 if [ $ip_mptcp -eq 1 ]; then + [ $id -ne 0 ] && addr='' ip -n $ns mptcp endpoint delete id $id $addr else ip netns exec $ns ./pm_nl_ctl del $id $addr @@ -795,10 +796,11 @@ pm_nl_check_endpoint() fi if [ $ip_mptcp -eq 1 ]; then + # get line and trim trailing whitespace line=$(ip -n $ns mptcp endpoint show $id) + line="${line% }" # the dump order is: address id flags port dev - expected_line="$addr" - [ -n "$addr" ] && expected_line="$expected_line $addr" + [ -n "$addr" ] && expected_line="$addr" expected_line="$expected_line $id" [ -n "$_flags" ] && expected_line="$expected_line ${_flags//","/" "}" [ -n "$dev" ] && expected_line="$expected_line $dev" diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index dfe3d287f01d..f838dd370f6a 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -361,6 +361,7 @@ err_buf= tcpdump_pids= nettest_pids= socat_pids= +tmpoutfile= err() { err_buf="${err_buf}${1} @@ -951,6 +952,7 @@ cleanup() { ip link del veth_A-R1 2>/dev/null ovs-vsctl --if-exists del-port vxlan_a 2>/dev/null ovs-vsctl --if-exists del-br ovs_br0 2>/dev/null + rm -f "$tmpoutfile" } mtu() { @@ -1328,6 +1330,39 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() { check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on bridged ${type} interface" pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on locally bridged ${type} interface" + + tmpoutfile=$(mktemp) + + # Flush Exceptions, retry with TCP + run_cmd ${ns_a} ip route flush cached ${dst} + run_cmd ${ns_b} ip route flush cached ${dst} + run_cmd ${ns_c} ip route flush cached ${dst} + + for target in "${ns_a}" "${ns_c}" ; do + if [ ${family} -eq 4 ]; then + TCPDST=TCP:${dst}:50000 + else + TCPDST="TCP:[${dst}]:50000" + fi + ${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000 STDOUT > $tmpoutfile & + + sleep 1 + + dd if=/dev/zero of=/dev/stdout status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3 + + size=$(du -sb $tmpoutfile) + size=${size%%/tmp/*} + + [ $size -ne 1048576 ] && err "File size $size mismatches exepcted value in locally bridged vxlan test" && return 1 + done + + rm -f "$tmpoutfile" + + # Check that exceptions were created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_c}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "tcp: exceeding link layer MTU on bridged ${type} interface" + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "tcp exceeding link layer MTU on locally bridged ${type} interface" } test_pmtu_ipv4_br_vxlan4_exception() { diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index b357ba24af06..7a957c7d459a 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -4,8 +4,10 @@ ifneq ($(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" |