diff --git a/.mailmap b/.mailmap index 7d5a6cc3909f..5ac7074c455f 100644 --- a/.mailmap +++ b/.mailmap @@ -219,6 +219,7 @@ Daniele Alessandrelli David Brownell David Collins +David Gow David Heidelberg David Hildenbrand David Rheinsberg @@ -353,6 +354,7 @@ Jarkko Sakkinen Jason Gunthorpe Jason Gunthorpe Jason Gunthorpe +Jason Xing Javi Merino Jayachandran C @@ -401,6 +403,7 @@ Jiri Slaby Jisheng Zhang Jisheng Zhang Jishnu Prakash +Joe Damato Joel Granados Johan Hovold Johan Hovold diff --git a/CREDITS b/CREDITS index d74c8b2b7ed3..9091bac3d2da 100644 --- a/CREDITS +++ b/CREDITS @@ -1242,6 +1242,10 @@ N: Veaceslav Falico E: vfalico@gmail.com D: Co-maintainer and co-author of the network bonding driver. +N: Thomas Falcon +E: tlfalcon@linux.ibm.com +D: Initial author of the IBM ibmvnic network driver + N: János Farkas E: chexum@shadow.banki.hu D: romfs, various (mostly networking) fixes @@ -2415,6 +2419,10 @@ S: Am Muehlenweg 38 S: D53424 Remagen S: Germany +N: Jonathan Lemon +E: jonathan.lemon@gmail.com +D: OpenCompute PTP clock driver (ptp_ocp) + N: Colin Leroy E: colin@colino.net W: http://www.geekounet.org/ diff --git a/Documentation/ABI/testing/sysfs-driver-uniwill-laptop b/Documentation/ABI/testing/sysfs-driver-uniwill-laptop index eaeb659793d2..2df70792968f 100644 --- a/Documentation/ABI/testing/sysfs-driver-uniwill-laptop +++ b/Documentation/ABI/testing/sysfs-driver-uniwill-laptop @@ -1,4 +1,4 @@ -What: /sys/bus/platform/devices/INOU0000:XX/fn_lock_toggle_enable +What: /sys/bus/platform/devices/INOU0000:XX/fn_lock Date: November 2025 KernelVersion: 6.19 Contact: Armin Wolf @@ -8,15 +8,15 @@ Description: Reading this file returns the current enable status of the FN lock functionality. -What: /sys/bus/platform/devices/INOU0000:XX/super_key_toggle_enable +What: /sys/bus/platform/devices/INOU0000:XX/super_key_enable Date: November 2025 KernelVersion: 6.19 Contact: Armin Wolf Description: - Allows userspace applications to enable/disable the super key functionality - of the integrated keyboard by writing "1"/"0" into this file. + Allows userspace applications to enable/disable the super key of the integrated + keyboard by writing "1"/"0" into this file. - Reading this file returns the current enable status of the super key functionality. + Reading this file returns the current enable status of the super key. What: /sys/bus/platform/devices/INOU0000:XX/touchpad_toggle_enable Date: November 2025 diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index cb850e5290c2..55ffc0f8858a 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -74,6 +74,7 @@ TPM TPM drivers are enabled. UMS USB Mass Storage support is enabled. USB USB support is enabled. + NVME NVMe support is enabled USBHID USB Human Interface Device support is enabled. V4L Video For Linux support is enabled. VGA The VGA console has been enabled. @@ -4787,6 +4788,18 @@ Kernel parameters This can be set from sysctl after boot. See Documentation/admin-guide/sysctl/vm.rst for details. + nvme.quirks= [NVME] A list of quirk entries to augment the built-in + nvme quirk list. List entries are separated by a + '-' character. + Each entry has the form VendorID:ProductID:quirk_names. + The IDs are 4-digits hex numbers and quirk_names is a + list of quirk names separated by commas. A quirk name + can be prefixed by '^', meaning that the specified + quirk must be disabled. + + Example: + nvme.quirks=7710:2267:bogus_nid,^identify_cns-9900:7711:broken_msi + ohci1394_dma=early [HW,EARLY] enable debugging via the ohci1394 driver. See Documentation/core-api/debugging-via-ohci1394.rst for more info. diff --git a/Documentation/admin-guide/laptops/uniwill-laptop.rst b/Documentation/admin-guide/laptops/uniwill-laptop.rst index a16baf15516b..aff5f57a6bd4 100644 --- a/Documentation/admin-guide/laptops/uniwill-laptop.rst +++ b/Documentation/admin-guide/laptops/uniwill-laptop.rst @@ -24,7 +24,7 @@ Keyboard settings The ``uniwill-laptop`` driver allows the user to enable/disable: - - the FN and super key lock functionality of the integrated keyboard + - the FN lock and super key of the integrated keyboard - the touchpad toggle functionality of the integrated touchpad See Documentation/ABI/testing/sysfs-driver-uniwill-laptop for details. diff --git a/Documentation/devicetree/bindings/hwmon/kontron,sl28cpld-hwmon.yaml b/Documentation/devicetree/bindings/hwmon/kontron,sl28cpld-hwmon.yaml index 966b221b6caa..5803a1770cad 100644 --- a/Documentation/devicetree/bindings/hwmon/kontron,sl28cpld-hwmon.yaml +++ b/Documentation/devicetree/bindings/hwmon/kontron,sl28cpld-hwmon.yaml @@ -16,7 +16,6 @@ description: | properties: compatible: enum: - - kontron,sa67mcu-hwmon - kontron,sl28cpld-fan reg: diff --git a/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml b/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml index ec0c2168e4b9..6bcfff970117 100644 --- a/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml +++ b/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml @@ -87,6 +87,7 @@ required: allOf: - $ref: can-controller.yaml# + - $ref: /schemas/memory-controllers/mc-peripheral-props.yaml - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-graph-card.yaml b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-graph-card.yaml index da89523ccf5f..92bc3ef56f2c 100644 --- a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-graph-card.yaml +++ b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-graph-card.yaml @@ -23,6 +23,7 @@ properties: enum: - nvidia,tegra210-audio-graph-card - nvidia,tegra186-audio-graph-card + - nvidia,tegra238-audio-graph-card - nvidia,tegra264-audio-graph-card clocks: diff --git a/Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml b/Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml index e4cdbf2202b9..1394f78281fc 100644 --- a/Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml +++ b/Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml @@ -20,6 +20,7 @@ properties: - renesas,r9a07g044-ssi # RZ/G2{L,LC} - renesas,r9a07g054-ssi # RZ/V2L - renesas,r9a08g045-ssi # RZ/G3S + - renesas,r9a08g046-ssi # RZ/G3L - const: renesas,rz-ssi reg: diff --git a/Documentation/hwmon/emc1403.rst b/Documentation/hwmon/emc1403.rst index 57f833b1a800..77060d515323 100644 --- a/Documentation/hwmon/emc1403.rst +++ b/Documentation/hwmon/emc1403.rst @@ -57,7 +57,7 @@ Supported chips: - https://ww1.microchip.com/downloads/en/DeviceDoc/EMC1438%20DS%20Rev.%201.0%20(04-29-10).pdf Author: - Kalhan Trisal Description diff --git a/Documentation/hwmon/index.rst b/Documentation/hwmon/index.rst index d91dbb20c7dc..b2ca8513cfcd 100644 --- a/Documentation/hwmon/index.rst +++ b/Documentation/hwmon/index.rst @@ -220,7 +220,6 @@ Hardware Monitoring Kernel Drivers q54sj108a2 qnap-mcu-hwmon raspberrypi-hwmon - sa67 sbrmi sbtsi_temp sch5627 diff --git a/Documentation/hwmon/sa67.rst b/Documentation/hwmon/sa67.rst deleted file mode 100644 index 029c7c169b7f..000000000000 --- a/Documentation/hwmon/sa67.rst +++ /dev/null @@ -1,41 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0-only - -Kernel driver sa67mcu -===================== - -Supported chips: - - * Kontron sa67mcu - - Prefix: 'sa67mcu' - - Datasheet: not available - -Authors: Michael Walle - -Description ------------ - -The sa67mcu is a board management controller which also exposes a hardware -monitoring controller. - -The controller has two voltage and one temperature sensor. The values are -hold in two 8 bit registers to form one 16 bit value. Reading the lower byte -will also capture the high byte to make the access atomic. The unit of the -volatge sensors are 1mV and the unit of the temperature sensor is 0.1degC. - -Sysfs entries -------------- - -The following attributes are supported. - -======================= ======================================================== -in0_label "VDDIN" -in0_input Measured VDDIN voltage. - -in1_label "VDD_RTC" -in1_input Measured VDD_RTC voltage. - -temp1_input MCU temperature. Roughly the board temperature. -======================= ======================================================== - diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml index badb2fe57c98..f87b5a05e5e9 100644 --- a/Documentation/netlink/specs/nfsd.yaml +++ b/Documentation/netlink/specs/nfsd.yaml @@ -152,7 +152,7 @@ operations: - compound-ops - name: threads-set - doc: set the number of running threads + doc: set the maximum number of running threads attribute-set: server flags: [admin-perm] do: @@ -165,7 +165,7 @@ operations: - min-threads - name: threads-get - doc: get the number of running threads + doc: get the maximum number of running threads attribute-set: server do: reply: diff --git a/Documentation/sound/alsa-configuration.rst b/Documentation/sound/alsa-configuration.rst index 0a4eaa7d66dd..55b845d38236 100644 --- a/Documentation/sound/alsa-configuration.rst +++ b/Documentation/sound/alsa-configuration.rst @@ -2372,6 +2372,10 @@ quirk_flags audible volume * bit 25: ``mixer_capture_min_mute`` Similar to bit 24 but for capture streams + * bit 26: ``skip_iface_setup`` + Skip the probe-time interface setup (usb_set_interface, + init_pitch, init_sample_rate); redundant with + snd_usb_endpoint_prepare() at stream-open time This module supports multiple devices, autoprobe and hotplugging. diff --git a/MAINTAINERS b/MAINTAINERS index 61bf550fd37c..77fdfcb55f06 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -993,10 +993,8 @@ F: Documentation/devicetree/bindings/thermal/amazon,al-thermal.yaml F: drivers/thermal/thermal_mmio.c AMAZON ETHERNET DRIVERS -M: Shay Agroskin M: Arthur Kiyanovski -R: David Arinzon -R: Saeed Bishara +M: David Arinzon L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/device_drivers/ethernet/amazon/ena.rst @@ -4617,7 +4615,6 @@ F: drivers/bluetooth/ BLUETOOTH SUBSYSTEM M: Marcel Holtmann -M: Johan Hedberg M: Luiz Augusto von Dentz L: linux-bluetooth@vger.kernel.org S: Supported @@ -10171,8 +10168,8 @@ F: drivers/i2c/busses/i2c-cpm.c FREESCALE IMX / MXC FEC DRIVER M: Wei Fang +R: Frank Li R: Shenwei Wang -R: Clark Wang L: imx@lists.linux.dev L: netdev@vger.kernel.org S: Maintained @@ -10484,7 +10481,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git F: Documentation/trace/ftrace* F: arch/*/*/*/*ftrace* F: arch/*/*/*ftrace* -F: include/*/ftrace.h +F: include/*/*ftrace* F: kernel/trace/fgraph.c F: kernel/trace/ftrace* F: samples/ftrace @@ -12216,7 +12213,6 @@ IBM Power SRIOV Virtual NIC Device Driver M: Haren Myneni M: Rick Lindsley R: Nick Child -R: Thomas Falcon L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/ibm/ibmvnic.* @@ -13942,7 +13938,7 @@ F: fs/smb/server/ KERNEL UNIT TESTING FRAMEWORK (KUnit) M: Brendan Higgins -M: David Gow +M: David Gow R: Rae Moar L: linux-kselftest@vger.kernel.org L: kunit-dev@googlegroups.com @@ -14762,7 +14758,7 @@ F: drivers/misc/lis3lv02d/ F: drivers/platform/x86/hp/hp_accel.c LIST KUNIT TEST -M: David Gow +M: David Gow L: linux-kselftest@vger.kernel.org L: kunit-dev@googlegroups.com S: Maintained @@ -15375,10 +15371,8 @@ F: drivers/crypto/marvell/ F: include/linux/soc/marvell/octeontx2/ MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2) -M: Mirko Lindner -M: Stephen Hemminger L: netdev@vger.kernel.org -S: Odd fixes +S: Orphan F: drivers/net/ethernet/marvell/sk* MARVELL LIBERTAS WIRELESS DRIVER @@ -15475,7 +15469,6 @@ MARVELL OCTEONTX2 RVU ADMIN FUNCTION DRIVER M: Sunil Goutham M: Linu Cherian M: Geetha sowjanya -M: Jerin Jacob M: hariprasad M: Subbaraya Sundeep L: netdev@vger.kernel.org @@ -15490,7 +15483,7 @@ S: Supported F: drivers/perf/marvell_pem_pmu.c MARVELL PRESTERA ETHERNET SWITCH DRIVER -M: Taras Chornyi +M: Elad Nachman S: Supported W: https://github.com/Marvell-switching/switchdev-prestera F: drivers/net/ethernet/marvell/prestera/ @@ -16164,7 +16157,6 @@ F: drivers/dma/mediatek/ MEDIATEK ETHERNET DRIVER M: Felix Fietkau -M: Sean Wang M: Lorenzo Bianconi L: netdev@vger.kernel.org S: Maintained @@ -16357,8 +16349,6 @@ F: include/soc/mediatek/smi.h MEDIATEK SWITCH DRIVER M: Chester A. Unal M: Daniel Golle -M: DENG Qingfang -M: Sean Wang L: netdev@vger.kernel.org S: Maintained F: drivers/net/dsa/mt7530-mdio.c @@ -19226,8 +19216,6 @@ F: tools/objtool/ OCELOT ETHERNET SWITCH DRIVER M: Vladimir Oltean -M: Claudiu Manoil -M: Alexandre Belloni M: UNGLinuxDriver@microchip.com L: netdev@vger.kernel.org S: Supported @@ -19813,7 +19801,6 @@ F: arch/*/boot/dts/ F: include/dt-bindings/ OPENCOMPUTE PTP CLOCK DRIVER -M: Jonathan Lemon M: Vadim Fedorenko L: netdev@vger.kernel.org S: Maintained @@ -20121,9 +20108,8 @@ F: Documentation/devicetree/bindings/pci/marvell,armada-3700-pcie.yaml F: drivers/pci/controller/pci-aardvark.c PCI DRIVER FOR ALTERA PCIE IP -M: Joyce Ooi L: linux-pci@vger.kernel.org -S: Supported +S: Orphan F: Documentation/devicetree/bindings/pci/altr,pcie-root-port.yaml F: drivers/pci/controller/pcie-altera.c @@ -20368,9 +20354,8 @@ S: Supported F: Documentation/PCI/pci-error-recovery.rst PCI MSI DRIVER FOR ALTERA MSI IP -M: Joyce Ooi L: linux-pci@vger.kernel.org -S: Supported +S: Orphan F: Documentation/devicetree/bindings/interrupt-controller/altr,msi-controller.yaml F: drivers/pci/controller/pcie-altera-msi.c @@ -21457,9 +21442,8 @@ S: Supported F: drivers/scsi/qedi/ QLOGIC QL4xxx ETHERNET DRIVER -M: Manish Chopra L: netdev@vger.kernel.org -S: Maintained +S: Orphan F: drivers/net/ethernet/qlogic/qed/ F: drivers/net/ethernet/qlogic/qede/ F: include/linux/qed/ @@ -24336,7 +24320,6 @@ F: Documentation/devicetree/bindings/interrupt-controller/kontron,sl28cpld-intc. F: Documentation/devicetree/bindings/pwm/kontron,sl28cpld-pwm.yaml F: Documentation/devicetree/bindings/watchdog/kontron,sl28cpld-wdt.yaml F: drivers/gpio/gpio-sl28cpld.c -F: drivers/hwmon/sa67mcu-hwmon.c F: drivers/hwmon/sl28cpld-hwmon.c F: drivers/irqchip/irq-sl28cpld.c F: drivers/pwm/pwm-sl28cpld.c diff --git a/Makefile b/Makefile index 2446085983f7..4b54a5c74332 100644 --- a/Makefile +++ b/Makefile @@ -1497,13 +1497,13 @@ ifneq ($(wildcard $(resolve_btfids_O)),) $(Q)$(MAKE) -sC $(srctree)/tools/bpf/resolve_btfids O=$(resolve_btfids_O) clean endif -PHONY += objtool_clean +PHONY += objtool_clean objtool_mrproper objtool_O = $(abspath $(objtree))/tools/objtool -objtool_clean: +objtool_clean objtool_mrproper: ifneq ($(wildcard $(objtool_O)),) - $(Q)$(MAKE) -sC $(abs_srctree)/tools/objtool O=$(objtool_O) srctree=$(abs_srctree) clean + $(Q)$(MAKE) -sC $(abs_srctree)/tools/objtool O=$(objtool_O) srctree=$(abs_srctree) $(patsubst objtool_%,%,$@) endif tools/: FORCE @@ -1686,7 +1686,7 @@ PHONY += $(mrproper-dirs) mrproper $(mrproper-dirs): $(Q)$(MAKE) $(clean)=$(patsubst _mrproper_%,%,$@) -mrproper: clean $(mrproper-dirs) +mrproper: clean objtool_mrproper $(mrproper-dirs) $(call cmd,rmfiles) @find . $(RCS_FIND_IGNORE) \ \( -name '*.rmeta' \) \ diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S index 2efa7dfc798a..2d136c63db16 100644 --- a/arch/alpha/kernel/vmlinux.lds.S +++ b/arch/alpha/kernel/vmlinux.lds.S @@ -71,6 +71,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S index 61a1b2b96e1d..6af63084ff28 100644 --- a/arch/arc/kernel/vmlinux.lds.S +++ b/arch/arc/kernel/vmlinux.lds.S @@ -123,6 +123,7 @@ SECTIONS _end = . ; STABS_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/arm/boot/compressed/vmlinux.lds.S b/arch/arm/boot/compressed/vmlinux.lds.S index d411abd4310e..2d916647df03 100644 --- a/arch/arm/boot/compressed/vmlinux.lds.S +++ b/arch/arm/boot/compressed/vmlinux.lds.S @@ -21,6 +21,7 @@ SECTIONS COMMON_DISCARDS *(.ARM.exidx*) *(.ARM.extab*) + *(.modinfo) *(.note.*) *(.rel.*) *(.printk_index) diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S index f2e8d4fac068..5afb725998ec 100644 --- a/arch/arm/kernel/vmlinux-xip.lds.S +++ b/arch/arm/kernel/vmlinux-xip.lds.S @@ -154,6 +154,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ARM_DETAILS ARM_ASSERTS diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index d592a203f9c6..c07843c3c53d 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -153,6 +153,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ARM_DETAILS ARM_ASSERTS diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index d7a540736741..6cf3cd6873f5 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -91,8 +91,9 @@ __XCHG_GEN(_mb) #define __xchg_wrapper(sfx, ptr, x) \ ({ \ __typeof__(*(ptr)) __ret; \ - __ret = (__typeof__(*(ptr))) \ - __arch_xchg##sfx((unsigned long)(x), (ptr), sizeof(*(ptr))); \ + __ret = (__force __typeof__(*(ptr))) \ + __arch_xchg##sfx((__force unsigned long)(x), (ptr), \ + sizeof(*(ptr))); \ __ret; \ }) @@ -175,9 +176,10 @@ __CMPXCHG_GEN(_mb) #define __cmpxchg_wrapper(sfx, ptr, o, n) \ ({ \ __typeof__(*(ptr)) __ret; \ - __ret = (__typeof__(*(ptr))) \ - __cmpxchg##sfx((ptr), (unsigned long)(o), \ - (unsigned long)(n), sizeof(*(ptr))); \ + __ret = (__force __typeof__(*(ptr))) \ + __cmpxchg##sfx((ptr), (__force unsigned long)(o), \ + (__force unsigned long)(n), \ + sizeof(*(ptr))); \ __ret; \ }) diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 2b32639160de..f560e6420267 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -50,11 +50,11 @@ #define _PAGE_DEFAULT (_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL)) -#define _PAGE_KERNEL (PROT_NORMAL) -#define _PAGE_KERNEL_RO ((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY) -#define _PAGE_KERNEL_ROX ((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY) -#define _PAGE_KERNEL_EXEC (PROT_NORMAL & ~PTE_PXN) -#define _PAGE_KERNEL_EXEC_CONT ((PROT_NORMAL & ~PTE_PXN) | PTE_CONT) +#define _PAGE_KERNEL (PROT_NORMAL | PTE_DIRTY) +#define _PAGE_KERNEL_RO ((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY | PTE_DIRTY) +#define _PAGE_KERNEL_ROX ((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY | PTE_DIRTY) +#define _PAGE_KERNEL_EXEC ((PROT_NORMAL & ~PTE_PXN) | PTE_DIRTY) +#define _PAGE_KERNEL_EXEC_CONT ((PROT_NORMAL & ~PTE_PXN) | PTE_CONT | PTE_DIRTY) #define _PAGE_SHARED (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) #define _PAGE_SHARED_EXEC (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE) diff --git a/arch/arm64/include/asm/runtime-const.h b/arch/arm64/include/asm/runtime-const.h index be5915669d23..c3dbd3ae68f6 100644 --- a/arch/arm64/include/asm/runtime-const.h +++ b/arch/arm64/include/asm/runtime-const.h @@ -2,6 +2,10 @@ #ifndef _ASM_RUNTIME_CONST_H #define _ASM_RUNTIME_CONST_H +#ifdef MODULE + #error "Cannot use runtime-const infrastructure from modules" +#endif + #include /* Sigh. You can still run arm64 in BE mode */ diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index ad6133b89e7a..2964aad0362e 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -349,6 +349,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS HEAD_SYMBOLS diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c index b929a455103f..1519d090d5ea 100644 --- a/arch/arm64/mm/contpte.c +++ b/arch/arm64/mm/contpte.c @@ -599,6 +599,27 @@ void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, } EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes); +static bool contpte_all_subptes_match_access_flags(pte_t *ptep, pte_t entry) +{ + pte_t *cont_ptep = contpte_align_down(ptep); + /* + * PFNs differ per sub-PTE. Match only bits consumed by + * __ptep_set_access_flags(): AF, DIRTY and write permission. + */ + const pteval_t cmp_mask = PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY; + pteval_t entry_cmp = pte_val(entry) & cmp_mask; + int i; + + for (i = 0; i < CONT_PTES; i++) { + pteval_t pte_cmp = pte_val(__ptep_get(cont_ptep + i)) & cmp_mask; + + if (pte_cmp != entry_cmp) + return false; + } + + return true; +} + int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty) @@ -608,13 +629,37 @@ int contpte_ptep_set_access_flags(struct vm_area_struct *vma, int i; /* - * Gather the access/dirty bits for the contiguous range. If nothing has - * changed, its a noop. + * Check whether all sub-PTEs in the CONT block already match the + * requested access flags/write permission, using raw per-PTE values + * rather than the gathered ptep_get() view. + * + * __ptep_set_access_flags() can update AF, dirty and write + * permission, but only to make the mapping more permissive. + * + * ptep_get() gathers AF/dirty state across the whole CONT block, + * which is correct for a CPU with FEAT_HAFDBS. But page-table + * walkers that evaluate each descriptor individually (e.g. a CPU + * without DBM support, or an SMMU without HTTU, or with HA/HD + * disabled in CD.TCR) can keep faulting on the target sub-PTE if + * only a sibling has been updated. Gathering can therefore cause + * false no-ops when only a sibling has been updated: + * - write faults: target still has PTE_RDONLY (needs PTE_RDONLY cleared) + * - read faults: target still lacks PTE_AF + * + * Per Arm ARM (DDI 0487) D8.7.1, any sub-PTE in a CONT range may + * become the effective cached translation, so all entries must have + * consistent attributes. Check the full CONT block before returning + * no-op, and when any sub-PTE mismatches, proceed to update the whole + * range. */ - orig_pte = pte_mknoncont(ptep_get(ptep)); - if (pte_val(orig_pte) == pte_val(entry)) + if (contpte_all_subptes_match_access_flags(ptep, entry)) return 0; + /* + * Use raw target pte (not gathered) for write-bit unfold decision. + */ + orig_pte = pte_mknoncont(__ptep_get(ptep)); + /* * We can fix up access/dirty bits without having to unfold the contig * range. But if the write bit is changing, we must unfold. diff --git a/arch/csky/kernel/vmlinux.lds.S b/arch/csky/kernel/vmlinux.lds.S index d718961786d2..81943981b3af 100644 --- a/arch/csky/kernel/vmlinux.lds.S +++ b/arch/csky/kernel/vmlinux.lds.S @@ -109,6 +109,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S index 1150b77fa281..aae22283b5e0 100644 --- a/arch/hexagon/kernel/vmlinux.lds.S +++ b/arch/hexagon/kernel/vmlinux.lds.S @@ -62,6 +62,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS .hexagon.attributes 0 : { *(.hexagon.attributes) } diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S index 08ea921cdec1..d0e1377a041d 100644 --- a/arch/loongarch/kernel/vmlinux.lds.S +++ b/arch/loongarch/kernel/vmlinux.lds.S @@ -147,6 +147,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS #ifdef CONFIG_EFI_STUB diff --git a/arch/m68k/kernel/vmlinux-nommu.lds b/arch/m68k/kernel/vmlinux-nommu.lds index 2624fc18c131..45d7f4b0177b 100644 --- a/arch/m68k/kernel/vmlinux-nommu.lds +++ b/arch/m68k/kernel/vmlinux-nommu.lds @@ -85,6 +85,7 @@ SECTIONS { _end = .; STABS_DEBUG + MODINFO ELF_DETAILS /* Sections to be discarded */ diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds index 1ccdd04ae462..7326586afe15 100644 --- a/arch/m68k/kernel/vmlinux-std.lds +++ b/arch/m68k/kernel/vmlinux-std.lds @@ -58,6 +58,7 @@ SECTIONS _end = . ; STABS_DEBUG + MODINFO ELF_DETAILS /* Sections to be discarded */ diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds index f13ddcc2af5c..1b19fef201fb 100644 --- a/arch/m68k/kernel/vmlinux-sun3.lds +++ b/arch/m68k/kernel/vmlinux-sun3.lds @@ -51,6 +51,7 @@ __init_begin = .; _end = . ; STABS_DEBUG + MODINFO ELF_DETAILS /* Sections to be discarded */ diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index 2b708fac8d2c..579b2cc1995a 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -217,6 +217,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS /* These must appear regardless of . */ diff --git a/arch/nios2/kernel/vmlinux.lds.S b/arch/nios2/kernel/vmlinux.lds.S index 37b958055064..206f92445bfa 100644 --- a/arch/nios2/kernel/vmlinux.lds.S +++ b/arch/nios2/kernel/vmlinux.lds.S @@ -57,6 +57,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S index 049bff45f612..9b29c3211774 100644 --- a/arch/openrisc/kernel/vmlinux.lds.S +++ b/arch/openrisc/kernel/vmlinux.lds.S @@ -101,6 +101,7 @@ SECTIONS /* Throw in the debugging sections */ STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS /* Sections to be discarded -- must be last */ diff --git a/arch/parisc/boot/compressed/vmlinux.lds.S b/arch/parisc/boot/compressed/vmlinux.lds.S index ab7b43990857..87d24cc824b6 100644 --- a/arch/parisc/boot/compressed/vmlinux.lds.S +++ b/arch/parisc/boot/compressed/vmlinux.lds.S @@ -90,6 +90,7 @@ SECTIONS /* Sections to be discarded */ DISCARDS /DISCARD/ : { + *(.modinfo) #ifdef CONFIG_64BIT /* temporary hack until binutils is fixed to not emit these * for static binaries diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 2c139a4dbf4b..17afe7a59edf 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -85,7 +85,7 @@ extern void __update_cache(pte_t pte); printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, (unsigned long)pgd_val(e)) /* This is the size of the initially mapped kernel memory */ -#if defined(CONFIG_64BIT) +#if defined(CONFIG_64BIT) || defined(CONFIG_KALLSYMS) #define KERNEL_INITIAL_ORDER 26 /* 1<<26 = 64MB */ #else #define KERNEL_INITIAL_ORDER 25 /* 1<<25 = 32MB */ diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S index 96e0264ac961..9188c8d87437 100644 --- a/arch/parisc/kernel/head.S +++ b/arch/parisc/kernel/head.S @@ -56,6 +56,7 @@ ENTRY(parisc_kernel_start) .import __bss_start,data .import __bss_stop,data + .import __end,data load32 PA(__bss_start),%r3 load32 PA(__bss_stop),%r4 @@ -149,7 +150,11 @@ $cpu_ok: * everything ... it will get remapped correctly later */ ldo 0+_PAGE_KERNEL_RWX(%r0),%r3 /* Hardwired 0 phys addr start */ load32 (1<<(KERNEL_INITIAL_ORDER-PAGE_SHIFT)),%r11 /* PFN count */ - load32 PA(pg0),%r1 + load32 PA(_end),%r1 + SHRREG %r1,PAGE_SHIFT,%r1 /* %r1 is PFN count for _end symbol */ + cmpb,<<,n %r11,%r1,1f + copy %r1,%r11 /* %r1 PFN count smaller than %r11 */ +1: load32 PA(pg0),%r1 $pgt_fill_loop: STREGM %r3,ASM_PTE_ENTRY_SIZE(%r1) diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index ace483b6f19a..d3e17a7a8901 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -120,14 +120,6 @@ void __init setup_arch(char **cmdline_p) #endif printk(KERN_CONT ".\n"); - /* - * Check if initial kernel page mappings are sufficient. - * panic early if not, else we may access kernel functions - * and variables which can't be reached. - */ - if (__pa((unsigned long) &_end) >= KERNEL_INITIAL_SIZE) - panic("KERNEL_INITIAL_ORDER too small!"); - #ifdef CONFIG_64BIT if(parisc_narrow_firmware) { printk(KERN_INFO "Kernel is using PDC in 32-bit mode.\n"); @@ -279,6 +271,18 @@ void __init start_parisc(void) int ret, cpunum; struct pdc_coproc_cfg coproc_cfg; + /* + * Check if initial kernel page mapping is sufficient. + * Print warning if not, because we may access kernel functions and + * variables which can't be reached yet through the initial mappings. + * Note that the panic() and printk() functions are not functional + * yet, so we need to use direct iodc() firmware calls instead. + */ + const char warn1[] = "CRITICAL: Kernel may crash because " + "KERNEL_INITIAL_ORDER is too small.\n"; + if (__pa((unsigned long) &_end) >= KERNEL_INITIAL_SIZE) + pdc_iodc_print(warn1, sizeof(warn1) - 1); + /* check QEMU/SeaBIOS marker in PAGE0 */ running_on_qemu = (memcmp(&PAGE0->pad0, "SeaBIOS", 8) == 0); diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index b445e47903cf..0ca93d6d7235 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -165,6 +165,7 @@ SECTIONS _end = . ; STABS_DEBUG + MODINFO ELF_DETAILS .note 0 : { *(.note) } diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 756043dd06e9..fb9fbf0d1796 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -212,6 +212,13 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, dev->error_state = pci_channel_io_normal; dev->dma_mask = 0xffffffff; + /* + * Assume 64-bit addresses for MSI initially. Will be changed to 32-bit + * if MSI (rather than MSI-X) capability does not have + * PCI_MSI_FLAGS_64BIT. Can also be overridden by driver. + */ + dev->msi_addr_mask = DMA_BIT_MASK(64); + /* Early fixups, before probing the BARs */ pci_fixup_device(pci_fixup_early, dev); diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 15850296c0a9..8fc11d6565bf 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -397,6 +397,7 @@ SECTIONS _end = . ; DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 61bd5ba6680a..997f9eb3b22b 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -170,6 +170,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS .riscv.attributes 0 : { *(.riscv.attributes) } diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index cc187afa07b3..78195ee5e99f 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -159,7 +159,7 @@ static __always_inline void __stackleak_poison(unsigned long erase_low, " j 4f\n" "3: mvc 8(1,%[addr]),0(%[addr])\n" "4:" - : [addr] "+&a" (erase_low), [count] "+&d" (count), [tmp] "=&a" (tmp) + : [addr] "+&a" (erase_low), [count] "+&a" (count), [tmp] "=&a" (tmp) : [poison] "d" (poison) : "memory", "cc" ); diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 53bcbb91bb9b..2b62395e35bf 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -221,6 +221,7 @@ SECTIONS /* Debugging sections. */ STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS /* diff --git a/arch/s390/lib/xor.c b/arch/s390/lib/xor.c index 1721b73b7803..5363e4c2462d 100644 --- a/arch/s390/lib/xor.c +++ b/arch/s390/lib/xor.c @@ -28,8 +28,8 @@ static void xor_xc_2(unsigned long bytes, unsigned long * __restrict p1, " j 3f\n" "2: xc 0(1,%1),0(%2)\n" "3:" - : : "d" (bytes), "a" (p1), "a" (p2) - : "0", "cc", "memory"); + : "+a" (bytes), "+a" (p1), "+a" (p2) + : : "0", "cc", "memory"); } static void xor_xc_3(unsigned long bytes, unsigned long * __restrict p1, @@ -54,7 +54,7 @@ static void xor_xc_3(unsigned long bytes, unsigned long * __restrict p1, "2: xc 0(1,%1),0(%2)\n" "3: xc 0(1,%1),0(%3)\n" "4:" - : "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3) + : "+a" (bytes), "+a" (p1), "+a" (p2), "+a" (p3) : : "0", "cc", "memory"); } @@ -85,7 +85,7 @@ static void xor_xc_4(unsigned long bytes, unsigned long * __restrict p1, "3: xc 0(1,%1),0(%3)\n" "4: xc 0(1,%1),0(%4)\n" "5:" - : "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4) + : "+a" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4) : : "0", "cc", "memory"); } @@ -96,7 +96,6 @@ static void xor_xc_5(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p5) { asm volatile( - " larl 1,2f\n" " aghi %0,-1\n" " jm 6f\n" " srlg 0,%0,8\n" @@ -122,7 +121,7 @@ static void xor_xc_5(unsigned long bytes, unsigned long * __restrict p1, "4: xc 0(1,%1),0(%4)\n" "5: xc 0(1,%1),0(%5)\n" "6:" - : "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4), + : "+a" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4), "+a" (p5) : : "0", "cc", "memory"); } diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S index 008c30289eaa..169c63fb3c1d 100644 --- a/arch/sh/kernel/vmlinux.lds.S +++ b/arch/sh/kernel/vmlinux.lds.S @@ -89,6 +89,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index 7e41574634b3..1603d50fdcad 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -355,6 +355,13 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, dev->error_state = pci_channel_io_normal; dev->dma_mask = 0xffffffff; + /* + * Assume 64-bit addresses for MSI initially. Will be changed to 32-bit + * if MSI (rather than MSI-X) capability does not have + * PCI_MSI_FLAGS_64BIT. Can also be overridden by driver. + */ + dev->msi_addr_mask = DMA_BIT_MASK(64); + if (of_node_name_eq(node, "pci")) { /* a PCI-PCI bridge */ dev->hdr_type = PCI_HEADER_TYPE_BRIDGE; diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index f1b86eb30340..7ea510d9b42f 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -191,6 +191,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S index a36b7918a011..ad3cefeff2ac 100644 --- a/arch/um/kernel/dyn.lds.S +++ b/arch/um/kernel/dyn.lds.S @@ -172,6 +172,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S index a409d4b66114..30aa24348d60 100644 --- a/arch/um/kernel/uml.lds.S +++ b/arch/um/kernel/uml.lds.S @@ -113,6 +113,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 68f9d7a1683b..b8b2b7bea1d3 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -113,6 +113,7 @@ vmlinux-objs-$(CONFIG_EFI_SBAT) += $(obj)/sbat.o ifdef CONFIG_EFI_SBAT $(obj)/sbat.o: $(CONFIG_EFI_SBAT_FILE) +AFLAGS_sbat.o += -I $(srctree) endif $(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index c8c1464b3a56..e468476e9e4a 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -28,17 +28,17 @@ #include "sev.h" static struct ghcb boot_ghcb_page __aligned(PAGE_SIZE); -struct ghcb *boot_ghcb; +struct ghcb *boot_ghcb __section(".data"); #undef __init #define __init #define __BOOT_COMPRESSED -u8 snp_vmpl; -u16 ghcb_version; +u8 snp_vmpl __section(".data"); +u16 ghcb_version __section(".data"); -u64 boot_svsm_caa_pa; +u64 boot_svsm_caa_pa __section(".data"); /* Include code for early handlers */ #include "../../boot/startup/sev-shared.c" @@ -188,6 +188,7 @@ bool sev_es_check_ghcb_fault(unsigned long address) MSR_AMD64_SNP_RESERVED_BIT13 | \ MSR_AMD64_SNP_RESERVED_BIT15 | \ MSR_AMD64_SNP_SECURE_AVIC | \ + MSR_AMD64_SNP_RESERVED_BITS19_22 | \ MSR_AMD64_SNP_RESERVED_MASK) #ifdef CONFIG_AMD_SECURE_AVIC diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index 587ce3e7c504..e0b152715d9c 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -88,7 +88,7 @@ SECTIONS /DISCARD/ : { *(.dynamic) *(.dynsym) *(.dynstr) *(.dynbss) *(.hash) *(.gnu.hash) - *(.note.*) + *(.note.*) *(.modinfo) } .got.plt (INFO) : { diff --git a/arch/x86/boot/startup/sev-shared.c b/arch/x86/boot/startup/sev-shared.c index a0fa8bb2b945..d9ac3a929d33 100644 --- a/arch/x86/boot/startup/sev-shared.c +++ b/arch/x86/boot/startup/sev-shared.c @@ -31,7 +31,7 @@ static u32 cpuid_std_range_max __ro_after_init; static u32 cpuid_hyp_range_max __ro_after_init; static u32 cpuid_ext_range_max __ro_after_init; -bool sev_snp_needs_sfw; +bool sev_snp_needs_sfw __section(".data"); void __noreturn sev_es_terminate(unsigned int set, unsigned int reason) diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c index 907981b94c40..7ed3da998489 100644 --- a/arch/x86/coco/sev/core.c +++ b/arch/x86/coco/sev/core.c @@ -89,6 +89,7 @@ static const char * const sev_status_feat_names[] = { [MSR_AMD64_SNP_VMSA_REG_PROT_BIT] = "VMSARegProt", [MSR_AMD64_SNP_SMT_PROT_BIT] = "SMTProt", [MSR_AMD64_SNP_SECURE_AVIC_BIT] = "SecureAVIC", + [MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT] = "IBPBOnEntry", }; /* diff --git a/arch/x86/entry/vdso/vdso32/sigreturn.S b/arch/x86/entry/vdso/vdso32/sigreturn.S index b433353bc8e3..b33fcc501ba3 100644 --- a/arch/x86/entry/vdso/vdso32/sigreturn.S +++ b/arch/x86/entry/vdso/vdso32/sigreturn.S @@ -35,9 +35,38 @@ #endif .endm +/* + * WARNING: + * + * A bug in the libgcc unwinder as of at least gcc 15.2 (2026) means that + * the unwinder fails to recognize the signal frame flag. + * + * There is a hacky legacy fallback path in libgcc which ends up + * getting invoked instead. It happens to work as long as BOTH of the + * following conditions are true: + * + * 1. There is at least one byte before the each of the sigreturn + * functions which falls outside any function. This is enforced by + * an explicit nop instruction before the ALIGN. + * 2. The code sequences between the entry point up to and including + * the int $0x80 below need to match EXACTLY. Do not change them + * in any way. The exact byte sequences are: + * + * __kernel_sigreturn: + * 0: 58 pop %eax + * 1: b8 77 00 00 00 mov $0x77,%eax + * 6: cd 80 int $0x80 + * + * __kernel_rt_sigreturn: + * 0: b8 ad 00 00 00 mov $0xad,%eax + * 5: cd 80 int $0x80 + * + * For details, see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=124050 + */ .text .globl __kernel_sigreturn .type __kernel_sigreturn,@function + nop /* libgcc hack: see comment above */ ALIGN __kernel_sigreturn: STARTPROC_SIGNAL_FRAME IA32_SIGFRAME_sigcontext @@ -52,6 +81,7 @@ SYM_INNER_LABEL(vdso32_sigreturn_landing_pad, SYM_L_GLOBAL) .globl __kernel_rt_sigreturn .type __kernel_rt_sigreturn,@function + nop /* libgcc hack: see comment above */ ALIGN __kernel_rt_sigreturn: STARTPROC_SIGNAL_FRAME IA32_RT_SIGFRAME_sigcontext diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index da5275d8eda6..6673601246b3 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -740,7 +740,10 @@ #define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT) #define MSR_AMD64_SNP_SECURE_AVIC_BIT 18 #define MSR_AMD64_SNP_SECURE_AVIC BIT_ULL(MSR_AMD64_SNP_SECURE_AVIC_BIT) -#define MSR_AMD64_SNP_RESV_BIT 19 +#define MSR_AMD64_SNP_RESERVED_BITS19_22 GENMASK_ULL(22, 19) +#define MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT 23 +#define MSR_AMD64_SNP_IBPB_ON_ENTRY BIT_ULL(MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT) +#define MSR_AMD64_SNP_RESV_BIT 24 #define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT) #define MSR_AMD64_SAVIC_CONTROL 0xc0010138 #define MSR_AMD64_SAVIC_EN_BIT 0 diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h index 53ba39ce010c..a9063f332fa6 100644 --- a/arch/x86/include/asm/numa.h +++ b/arch/x86/include/asm/numa.h @@ -22,6 +22,7 @@ extern int numa_off; */ extern s16 __apicid_to_node[MAX_LOCAL_APIC]; extern nodemask_t numa_nodes_parsed __initdata; +extern nodemask_t numa_phys_nodes_parsed __initdata; static inline void set_apicid_to_node(int apicid, s16 node) { @@ -48,6 +49,7 @@ extern void __init init_cpu_to_node(void); extern void numa_add_cpu(unsigned int cpu); extern void numa_remove_cpu(unsigned int cpu); extern void init_gi_nodes(void); +extern int num_phys_nodes(void); #else /* CONFIG_NUMA */ static inline void numa_set_node(int cpu, int node) { } static inline void numa_clear_node(int cpu) { } @@ -55,6 +57,10 @@ static inline void init_cpu_to_node(void) { } static inline void numa_add_cpu(unsigned int cpu) { } static inline void numa_remove_cpu(unsigned int cpu) { } static inline void init_gi_nodes(void) { } +static inline int num_phys_nodes(void) +{ + return 1; +} #endif /* CONFIG_NUMA */ #ifdef CONFIG_DEBUG_PER_CPU_MAPS diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index f06e5d6a2747..ce45882ccd07 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -19,10 +19,8 @@ extern p4d_t level4_kernel_pgt[512]; extern p4d_t level4_ident_pgt[512]; extern pud_t level3_kernel_pgt[512]; -extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; -extern pmd_t level2_ident_pgt[512]; extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM]; extern pgd_t init_top_pgt[]; diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 1fadf0cf520c..0ba9bdb99871 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -155,6 +155,7 @@ extern unsigned int __max_logical_packages; extern unsigned int __max_threads_per_core; extern unsigned int __num_threads_per_package; extern unsigned int __num_cores_per_package; +extern unsigned int __num_nodes_per_package; const char *get_topology_cpu_type_name(struct cpuinfo_x86 *c); enum x86_topology_cpu_type get_topology_cpu_type(struct cpuinfo_x86 *c); @@ -179,6 +180,11 @@ static inline unsigned int topology_num_threads_per_package(void) return __num_threads_per_package; } +static inline unsigned int topology_num_nodes_per_package(void) +{ + return __num_nodes_per_package; +} + #ifdef CONFIG_X86_LOCAL_APIC int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level); #else diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 1c3261cae40c..a8ff4376c286 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -95,6 +95,9 @@ EXPORT_SYMBOL(__max_dies_per_package); unsigned int __max_logical_packages __ro_after_init = 1; EXPORT_SYMBOL(__max_logical_packages); +unsigned int __num_nodes_per_package __ro_after_init = 1; +EXPORT_SYMBOL(__num_nodes_per_package); + unsigned int __num_cores_per_package __ro_after_init = 1; EXPORT_SYMBOL(__num_cores_per_package); diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index e6a154240b8d..9bd87bae4983 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -364,7 +364,7 @@ void arch_mon_domain_online(struct rdt_resource *r, struct rdt_l3_mon_domain *d) msr_clear_bit(MSR_RMID_SNC_CONFIG, 0); } -/* CPU models that support MSR_RMID_SNC_CONFIG */ +/* CPU models that support SNC and MSR_RMID_SNC_CONFIG */ static const struct x86_cpu_id snc_cpu_ids[] __initconst = { X86_MATCH_VFM(INTEL_ICELAKE_X, 0), X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, 0), @@ -375,40 +375,14 @@ static const struct x86_cpu_id snc_cpu_ids[] __initconst = { {} }; -/* - * There isn't a simple hardware bit that indicates whether a CPU is running - * in Sub-NUMA Cluster (SNC) mode. Infer the state by comparing the - * number of CPUs sharing the L3 cache with CPU0 to the number of CPUs in - * the same NUMA node as CPU0. - * It is not possible to accurately determine SNC state if the system is - * booted with a maxcpus=N parameter. That distorts the ratio of SNC nodes - * to L3 caches. It will be OK if system is booted with hyperthreading - * disabled (since this doesn't affect the ratio). - */ static __init int snc_get_config(void) { - struct cacheinfo *ci = get_cpu_cacheinfo_level(0, RESCTRL_L3_CACHE); - const cpumask_t *node0_cpumask; - int cpus_per_node, cpus_per_l3; - int ret; + int ret = topology_num_nodes_per_package(); - if (!x86_match_cpu(snc_cpu_ids) || !ci) + if (ret > 1 && !x86_match_cpu(snc_cpu_ids)) { + pr_warn("CoD enabled system? Resctrl not supported\n"); return 1; - - cpus_read_lock(); - if (num_online_cpus() != num_present_cpus()) - pr_warn("Some CPUs offline, SNC detection may be incorrect\n"); - cpus_read_unlock(); - - node0_cpumask = cpumask_of_node(cpu_to_node(0)); - - cpus_per_node = cpumask_weight(node0_cpumask); - cpus_per_l3 = cpumask_weight(&ci->shared_cpu_map); - - if (!cpus_per_node || !cpus_per_l3) - return 1; - - ret = cpus_per_l3 / cpus_per_node; + } /* sanity check: Only valid results are 1, 2, 3, 4, 6 */ switch (ret) { diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 23190a786d31..eafcb1fc185a 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -31,6 +31,7 @@ #include #include #include +#include #include "cpu.h" @@ -492,11 +493,19 @@ void __init topology_init_possible_cpus(void) set_nr_cpu_ids(allowed); cnta = domain_weight(TOPO_PKG_DOMAIN); - cntb = domain_weight(TOPO_DIE_DOMAIN); __max_logical_packages = cnta; + + pr_info("Max. logical packages: %3u\n", __max_logical_packages); + + cntb = num_phys_nodes(); + __num_nodes_per_package = DIV_ROUND_UP(cntb, cnta); + + pr_info("Max. logical nodes: %3u\n", cntb); + pr_info("Num. nodes per package:%3u\n", __num_nodes_per_package); + + cntb = domain_weight(TOPO_DIE_DOMAIN); __max_dies_per_package = 1U << (get_count_order(cntb) - get_count_order(cnta)); - pr_info("Max. logical packages: %3u\n", cnta); pr_info("Max. logical dies: %3u\n", cntb); pr_info("Max. dies per package: %3u\n", __max_dies_per_package); diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 21816b48537c..85d4a5094f6b 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -616,38 +616,10 @@ SYM_DATA(early_recursion_flag, .long 0) .data -#if defined(CONFIG_XEN_PV) || defined(CONFIG_PVH) -SYM_DATA_START_PTI_ALIGNED(init_top_pgt) - .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC - .org init_top_pgt + L4_PAGE_OFFSET*8, 0 - .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC - .org init_top_pgt + L4_START_KERNEL*8, 0 - /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ - .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC - .fill PTI_USER_PGD_FILL,8,0 -SYM_DATA_END(init_top_pgt) - -SYM_DATA_START_PAGE_ALIGNED(level3_ident_pgt) - .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC - .fill 511, 8, 0 -SYM_DATA_END(level3_ident_pgt) -SYM_DATA_START_PAGE_ALIGNED(level2_ident_pgt) - /* - * Since I easily can, map the first 1G. - * Don't set NX because code runs from these pages. - * - * Note: This sets _PAGE_GLOBAL despite whether - * the CPU supports it or it is enabled. But, - * the CPU should ignore the bit. - */ - PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) -SYM_DATA_END(level2_ident_pgt) -#else SYM_DATA_START_PTI_ALIGNED(init_top_pgt) .fill 512,8,0 .fill PTI_USER_PGD_FILL,8,0 SYM_DATA_END(init_top_pgt) -#endif SYM_DATA_START_PAGE_ALIGNED(level4_kernel_pgt) .fill 511,8,0 diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 5cd6950ab672..294a8ea60298 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -468,13 +468,6 @@ static int x86_cluster_flags(void) } #endif -/* - * Set if a package/die has multiple NUMA nodes inside. - * AMD Magny-Cours, Intel Cluster-on-Die, and Intel - * Sub-NUMA Clustering have this. - */ -static bool x86_has_numa_in_package; - static struct sched_domain_topology_level x86_topology[] = { SDTL_INIT(tl_smt_mask, cpu_smt_flags, SMT), #ifdef CONFIG_SCHED_CLUSTER @@ -496,7 +489,7 @@ static void __init build_sched_topology(void) * PKG domain since the NUMA domains will auto-magically create the * right spanning domains based on the SLIT. */ - if (x86_has_numa_in_package) { + if (topology_num_nodes_per_package() > 1) { unsigned int pkgdom = ARRAY_SIZE(x86_topology) - 2; memset(&x86_topology[pkgdom], 0, sizeof(x86_topology[pkgdom])); @@ -513,33 +506,149 @@ static void __init build_sched_topology(void) } #ifdef CONFIG_NUMA -static int sched_avg_remote_distance; -static int avg_remote_numa_distance(void) +/* + * Test if the on-trace cluster at (N,N) is symmetric. + * Uses upper triangle iteration to avoid obvious duplicates. + */ +static bool slit_cluster_symmetric(int N) { - int i, j; - int distance, nr_remote, total_distance; + int u = topology_num_nodes_per_package(); - if (sched_avg_remote_distance > 0) - return sched_avg_remote_distance; - - nr_remote = 0; - total_distance = 0; - for_each_node_state(i, N_CPU) { - for_each_node_state(j, N_CPU) { - distance = node_distance(i, j); - - if (distance >= REMOTE_DISTANCE) { - nr_remote++; - total_distance += distance; - } + for (int k = 0; k < u; k++) { + for (int l = k; l < u; l++) { + if (node_distance(N + k, N + l) != + node_distance(N + l, N + k)) + return false; } } - if (nr_remote) - sched_avg_remote_distance = total_distance / nr_remote; - else - sched_avg_remote_distance = REMOTE_DISTANCE; - return sched_avg_remote_distance; + return true; +} + +/* + * Return the package-id of the cluster, or ~0 if indeterminate. + * Each node in the on-trace cluster should have the same package-id. + */ +static u32 slit_cluster_package(int N) +{ + int u = topology_num_nodes_per_package(); + u32 pkg_id = ~0; + + for (int n = 0; n < u; n++) { + const struct cpumask *cpus = cpumask_of_node(N + n); + int cpu; + + for_each_cpu(cpu, cpus) { + u32 id = topology_logical_package_id(cpu); + + if (pkg_id == ~0) + pkg_id = id; + if (pkg_id != id) + return ~0; + } + } + + return pkg_id; +} + +/* + * Validate the SLIT table is of the form expected for SNC, specifically: + * + * - each on-trace cluster should be symmetric, + * - each on-trace cluster should have a unique package-id. + * + * If you NUMA_EMU on top of SNC, you get to keep the pieces. + */ +static bool slit_validate(void) +{ + int u = topology_num_nodes_per_package(); + u32 pkg_id, prev_pkg_id = ~0; + + for (int pkg = 0; pkg < topology_max_packages(); pkg++) { + int n = pkg * u; + + /* + * Ensure the on-trace cluster is symmetric and each cluster + * has a different package id. + */ + if (!slit_cluster_symmetric(n)) + return false; + pkg_id = slit_cluster_package(n); + if (pkg_id == ~0) + return false; + if (pkg && pkg_id == prev_pkg_id) + return false; + + prev_pkg_id = pkg_id; + } + + return true; +} + +/* + * Compute a sanitized SLIT table for SNC; notably SNC-3 can end up with + * asymmetric off-trace clusters, reflecting physical assymmetries. However + * this leads to 'unfortunate' sched_domain configurations. + * + * For example dual socket GNR with SNC-3: + * + * node distances: + * node 0 1 2 3 4 5 + * 0: 10 15 17 21 28 26 + * 1: 15 10 15 23 26 23 + * 2: 17 15 10 26 23 21 + * 3: 21 28 26 10 15 17 + * 4: 23 26 23 15 10 15 + * 5: 26 23 21 17 15 10 + * + * Fix things up by averaging out the off-trace clusters; resulting in: + * + * node 0 1 2 3 4 5 + * 0: 10 15 17 24 24 24 + * 1: 15 10 15 24 24 24 + * 2: 17 15 10 24 24 24 + * 3: 24 24 24 10 15 17 + * 4: 24 24 24 15 10 15 + * 5: 24 24 24 17 15 10 + */ +static int slit_cluster_distance(int i, int j) +{ + static int slit_valid = -1; + int u = topology_num_nodes_per_package(); + long d = 0; + int x, y; + + if (slit_valid < 0) { + slit_valid = slit_validate(); + if (!slit_valid) + pr_err(FW_BUG "SLIT table doesn't have the expected form for SNC -- fixup disabled!\n"); + else + pr_info("Fixing up SNC SLIT table.\n"); + } + + /* + * Is this a unit cluster on the trace? + */ + if ((i / u) == (j / u) || !slit_valid) + return node_distance(i, j); + + /* + * Off-trace cluster. + * + * Notably average out the symmetric pair of off-trace clusters to + * ensure the resulting SLIT table is symmetric. + */ + x = i - (i % u); + y = j - (j % u); + + for (i = x; i < x + u; i++) { + for (j = y; j < y + u; j++) { + d += node_distance(i, j); + d += node_distance(j, i); + } + } + + return d / (2*u*u); } int arch_sched_node_distance(int from, int to) @@ -549,34 +658,14 @@ int arch_sched_node_distance(int from, int to) switch (boot_cpu_data.x86_vfm) { case INTEL_GRANITERAPIDS_X: case INTEL_ATOM_DARKMONT_X: - - if (!x86_has_numa_in_package || topology_max_packages() == 1 || - d < REMOTE_DISTANCE) + if (topology_max_packages() == 1 || + topology_num_nodes_per_package() < 3) return d; /* - * With SNC enabled, there could be too many levels of remote - * NUMA node distances, creating NUMA domain levels - * including local nodes and partial remote nodes. - * - * Trim finer distance tuning for NUMA nodes in remote package - * for the purpose of building sched domains. Group NUMA nodes - * in the remote package in the same sched group. - * Simplify NUMA domains and avoid extra NUMA levels including - * different remote NUMA nodes and local nodes. - * - * GNR and CWF don't expect systems with more than 2 packages - * and more than 2 hops between packages. Single average remote - * distance won't be appropriate if there are more than 2 - * packages as average distance to different remote packages - * could be different. + * Handle SNC-3 asymmetries. */ - WARN_ONCE(topology_max_packages() > 2, - "sched: Expect only up to 2 packages for GNR or CWF, " - "but saw %d packages when building sched domains.", - topology_max_packages()); - - d = avg_remote_numa_distance(); + return slit_cluster_distance(from, to); } return d; } @@ -606,7 +695,7 @@ void set_cpu_sibling_map(int cpu) o = &cpu_data(i); if (match_pkg(c, o) && !topology_same_node(c, o)) - x86_has_numa_in_package = true; + WARN_ON_ONCE(topology_num_nodes_per_package() == 1); if ((i == cpu) || (has_smt && match_smt(c, o))) link_mask(topology_sibling_cpumask, cpu, i); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 3a24a3fc55f5..4711a35e706c 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -427,6 +427,7 @@ SECTIONS .llvm_bb_addr_map : { *(.llvm_bb_addr_map) } #endif + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 7a97327140df..99d0a9332c14 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -48,6 +48,8 @@ s16 __apicid_to_node[MAX_LOCAL_APIC] = { [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE }; +nodemask_t numa_phys_nodes_parsed __initdata; + int numa_cpu_node(int cpu) { u32 apicid = early_per_cpu(x86_cpu_to_apicid, cpu); @@ -57,6 +59,11 @@ int numa_cpu_node(int cpu) return NUMA_NO_NODE; } +int __init num_phys_nodes(void) +{ + return bitmap_weight(numa_phys_nodes_parsed.bits, MAX_NUMNODES); +} + cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; EXPORT_SYMBOL(node_to_cpumask_map); @@ -210,6 +217,7 @@ static int __init dummy_numa_init(void) 0LLU, PFN_PHYS(max_pfn) - 1); node_set(0, numa_nodes_parsed); + node_set(0, numa_phys_nodes_parsed); numa_add_memblk(0, 0, PFN_PHYS(max_pfn)); return 0; diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 6f8e0f21c710..44ca66651756 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -57,6 +57,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) } set_apicid_to_node(apic_id, node); node_set(node, numa_nodes_parsed); + node_set(node, numa_phys_nodes_parsed); pr_debug("SRAT: PXM %u -> APIC 0x%04x -> Node %u\n", pxm, apic_id, node); } @@ -97,6 +98,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) set_apicid_to_node(apic_id, node); node_set(node, numa_nodes_parsed); + node_set(node, numa_phys_nodes_parsed); pr_debug("SRAT: PXM %u -> APIC 0x%02x -> Node %u\n", pxm, apic_id, node); } diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c index 2263885d16ba..f2053cbe9b0c 100644 --- a/arch/x86/platform/pvh/enlighten.c +++ b/arch/x86/platform/pvh/enlighten.c @@ -25,11 +25,6 @@ struct hvm_start_info __initdata pvh_start_info; const unsigned int __initconst pvh_start_info_sz = sizeof(pvh_start_info); -static u64 __init pvh_get_root_pointer(void) -{ - return pvh_start_info.rsdp_paddr; -} - /* * Xen guests are able to obtain the memory map from the hypervisor via the * HYPERVISOR_memory_op hypercall. @@ -95,7 +90,7 @@ static void __init init_pvh_bootparams(bool xen_guest) pvh_bootparams.hdr.version = (2 << 8) | 12; pvh_bootparams.hdr.type_of_loader = ((xen_guest ? 0x9 : 0xb) << 4) | 0; - x86_init.acpi.get_root_pointer = pvh_get_root_pointer; + pvh_bootparams.acpi_rsdp_addr = pvh_start_info.rsdp_paddr; } /* diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 6e459e47cafd..eaad22b47206 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -392,7 +392,7 @@ static void __init xen_init_capabilities(void) /* * Xen PV would need some work to support PCID: CR3 handling as well - * as xen_flush_tlb_others() would need updating. + * as xen_flush_tlb_multi() would need updating. */ setup_clear_cpu_cap(X86_FEATURE_PCID); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 3254eaa88471..c80d0058efd1 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -105,6 +105,9 @@ pte_t xen_make_pte_init(pteval_t pte); static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss; #endif +static pud_t level3_ident_pgt[PTRS_PER_PUD] __page_aligned_bss; +static pmd_t level2_ident_pgt[PTRS_PER_PMD] __page_aligned_bss; + /* * Protects atomic reservation decrease/increase against concurrent increases. * Also protects non-atomic updates of current_pages and balloon lists. @@ -1777,6 +1780,12 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* Zap identity mapping */ init_top_pgt[0] = __pgd(0); + init_top_pgt[pgd_index(__PAGE_OFFSET_BASE_L4)].pgd = + __pa_symbol(level3_ident_pgt) + _KERNPG_TABLE_NOENC; + init_top_pgt[pgd_index(__START_KERNEL_map)].pgd = + __pa_symbol(level3_kernel_pgt) + _PAGE_TABLE_NOENC; + level3_ident_pgt[0].pud = __pa_symbol(level2_ident_pgt) + _KERNPG_TABLE_NOENC; + /* Pre-constructed entries are in pfn, so convert to mfn */ /* L4[273] -> level3_ident_pgt */ /* L4[511] -> level3_kernel_pgt */ diff --git a/block/blk-map.c b/block/blk-map.c index 53bdd100aa4b..768549f19f97 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -398,8 +398,7 @@ static struct bio *bio_copy_kern(struct request *rq, void *data, unsigned int le if (op_is_write(op)) memcpy(page_address(page), p, bytes); - if (bio_add_page(bio, page, bytes, 0) < bytes) - break; + __bio_add_page(bio, page, bytes, 0); len -= bytes; p += bytes; diff --git a/block/blk-mq.c b/block/blk-mq.c index 9af8c3dec3f6..3da2215b2912 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -4793,38 +4793,45 @@ static void blk_mq_update_queue_map(struct blk_mq_tag_set *set) } } -static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set, - int new_nr_hw_queues) +static struct blk_mq_tags **blk_mq_prealloc_tag_set_tags( + struct blk_mq_tag_set *set, + int new_nr_hw_queues) { struct blk_mq_tags **new_tags; int i; if (set->nr_hw_queues >= new_nr_hw_queues) - goto done; + return NULL; new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *), GFP_KERNEL, set->numa_node); if (!new_tags) - return -ENOMEM; + return ERR_PTR(-ENOMEM); if (set->tags) memcpy(new_tags, set->tags, set->nr_hw_queues * sizeof(*set->tags)); - kfree(set->tags); - set->tags = new_tags; for (i = set->nr_hw_queues; i < new_nr_hw_queues; i++) { - if (!__blk_mq_alloc_map_and_rqs(set, i)) { - while (--i >= set->nr_hw_queues) - __blk_mq_free_map_and_rqs(set, i); - return -ENOMEM; + if (blk_mq_is_shared_tags(set->flags)) { + new_tags[i] = set->shared_tags; + } else { + new_tags[i] = blk_mq_alloc_map_and_rqs(set, i, + set->queue_depth); + if (!new_tags[i]) + goto out_unwind; } cond_resched(); } -done: - set->nr_hw_queues = new_nr_hw_queues; - return 0; + return new_tags; +out_unwind: + while (--i >= set->nr_hw_queues) { + if (!blk_mq_is_shared_tags(set->flags)) + blk_mq_free_map_and_rqs(set, new_tags[i], i); + } + kfree(new_tags); + return ERR_PTR(-ENOMEM); } /* @@ -5113,6 +5120,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, unsigned int memflags; int i; struct xarray elv_tbl; + struct blk_mq_tags **new_tags; bool queues_frozen = false; lockdep_assert_held(&set->tag_list_lock); @@ -5147,11 +5155,18 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, if (blk_mq_elv_switch_none(q, &elv_tbl)) goto switch_back; + new_tags = blk_mq_prealloc_tag_set_tags(set, nr_hw_queues); + if (IS_ERR(new_tags)) + goto switch_back; + list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_freeze_queue_nomemsave(q); queues_frozen = true; - if (blk_mq_realloc_tag_set_tags(set, nr_hw_queues) < 0) - goto switch_back; + if (new_tags) { + kfree(set->tags); + set->tags = new_tags; + } + set->nr_hw_queues = nr_hw_queues; fallback: blk_mq_update_queue_map(set); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index f3b1968c80ce..55a1bbfef7d4 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -78,8 +78,14 @@ queue_requests_store(struct gendisk *disk, const char *page, size_t count) /* * Serialize updating nr_requests with concurrent queue_requests_store() * and switching elevator. + * + * Use trylock to avoid circular lock dependency with kernfs active + * reference during concurrent disk deletion: + * update_nr_hwq_lock -> kn->active (via del_gendisk -> kobject_del) + * kn->active -> update_nr_hwq_lock (via this sysfs write path) */ - down_write(&set->update_nr_hwq_lock); + if (!down_write_trylock(&set->update_nr_hwq_lock)) + return -EBUSY; if (nr == q->nr_requests) goto unlock; diff --git a/block/elevator.c b/block/elevator.c index ebe2a1fcf011..3bcd37c2aa34 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -807,7 +807,16 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf, elv_iosched_load_module(ctx.name); ctx.type = elevator_find_get(ctx.name); - down_read(&set->update_nr_hwq_lock); + /* + * Use trylock to avoid circular lock dependency with kernfs active + * reference during concurrent disk deletion: + * update_nr_hwq_lock -> kn->active (via del_gendisk -> kobject_del) + * kn->active -> update_nr_hwq_lock (via this sysfs write path) + */ + if (!down_read_trylock(&set->update_nr_hwq_lock)) { + ret = -EBUSY; + goto out; + } if (!blk_queue_no_elv_switch(q)) { ret = elevator_change(q, &ctx); if (!ret) @@ -817,6 +826,7 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf, } up_read(&set->update_nr_hwq_lock); +out: if (ctx.type) elevator_put(ctx.type); return ret; diff --git a/crypto/Kconfig b/crypto/Kconfig index e2b4106ac961..b4bb85e8e226 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -876,8 +876,6 @@ config CRYPTO_BLAKE2B - blake2b-384 - blake2b-512 - Used by the btrfs filesystem. - See https://blake2.net for further information. config CRYPTO_CMAC @@ -965,7 +963,6 @@ config CRYPTO_SHA256 10118-3), including HMAC support. This is required for IPsec AH (XFRM_AH) and IPsec ESP (XFRM_ESP). - Used by the btrfs filesystem, Ceph, NFS, and SMB. config CRYPTO_SHA512 tristate "SHA-384 and SHA-512" @@ -1039,8 +1036,6 @@ config CRYPTO_XXHASH Extremely fast, working at speeds close to RAM limits. - Used by the btrfs filesystem. - endmenu menu "CRCs (cyclic redundancy checks)" @@ -1058,8 +1053,6 @@ config CRYPTO_CRC32C on Communications, Vol. 41, No. 6, June 1993, selected for use with iSCSI. - Used by btrfs, ext4, jbd2, NVMeoF/TCP, and iSCSI. - config CRYPTO_CRC32 tristate "CRC32" select CRYPTO_HASH @@ -1067,8 +1060,6 @@ config CRYPTO_CRC32 help CRC32 CRC algorithm (IEEE 802.3) - Used by RoCEv2 and f2fs. - endmenu menu "Compression" diff --git a/crypto/testmgr.c b/crypto/testmgr.c index 49b607f65f63..4985411dedae 100644 --- a/crypto/testmgr.c +++ b/crypto/testmgr.c @@ -4132,7 +4132,7 @@ static const struct alg_test_desc alg_test_descs[] = { .fips_allowed = 1, }, { .alg = "authenc(hmac(sha224),cbc(aes))", - .generic_driver = "authenc(hmac-sha224-lib,cbc(aes-generic))", + .generic_driver = "authenc(hmac-sha224-lib,cbc(aes-lib))", .test = alg_test_aead, .suite = { .aead = __VECS(hmac_sha224_aes_cbc_tv_temp) @@ -4194,7 +4194,7 @@ static const struct alg_test_desc alg_test_descs[] = { .fips_allowed = 1, }, { .alg = "authenc(hmac(sha384),cbc(aes))", - .generic_driver = "authenc(hmac-sha384-lib,cbc(aes-generic))", + .generic_driver = "authenc(hmac-sha384-lib,cbc(aes-lib))", .test = alg_test_aead, .suite = { .aead = __VECS(hmac_sha384_aes_cbc_tv_temp) diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c index 25845bd5e507..afee5e667f77 100644 --- a/drivers/accel/amdxdna/aie2_ctx.c +++ b/drivers/accel/amdxdna/aie2_ctx.c @@ -186,13 +186,13 @@ aie2_sched_resp_handler(void *handle, void __iomem *data, size_t size) cmd_abo = job->cmd_bo; if (unlikely(job->job_timeout)) { - amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_TIMEOUT); + amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_TIMEOUT); ret = -EINVAL; goto out; } if (unlikely(!data) || unlikely(size != sizeof(u32))) { - amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT); + amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_ABORT); ret = -EINVAL; goto out; } @@ -202,7 +202,7 @@ aie2_sched_resp_handler(void *handle, void __iomem *data, size_t size) if (status == AIE2_STATUS_SUCCESS) amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_COMPLETED); else - amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ERROR); + amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_ERROR); out: aie2_sched_notify(job); @@ -244,13 +244,13 @@ aie2_sched_cmdlist_resp_handler(void *handle, void __iomem *data, size_t size) cmd_abo = job->cmd_bo; if (unlikely(job->job_timeout)) { - amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_TIMEOUT); + amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_TIMEOUT); ret = -EINVAL; goto out; } if (unlikely(!data) || unlikely(size != sizeof(u32) * 3)) { - amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT); + amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_ABORT); ret = -EINVAL; goto out; } @@ -270,19 +270,12 @@ aie2_sched_cmdlist_resp_handler(void *handle, void __iomem *data, size_t size) fail_cmd_idx, fail_cmd_status); if (fail_cmd_status == AIE2_STATUS_SUCCESS) { - amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT); + amdxdna_cmd_set_error(cmd_abo, job, fail_cmd_idx, ERT_CMD_STATE_ABORT); ret = -EINVAL; - goto out; + } else { + amdxdna_cmd_set_error(cmd_abo, job, fail_cmd_idx, ERT_CMD_STATE_ERROR); } - amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ERROR); - if (amdxdna_cmd_get_op(cmd_abo) == ERT_CMD_CHAIN) { - struct amdxdna_cmd_chain *cc = amdxdna_cmd_get_payload(cmd_abo, NULL); - - cc->error_index = fail_cmd_idx; - if (cc->error_index >= cc->command_count) - cc->error_index = 0; - } out: aie2_sched_notify(job); return ret; diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c index 277a27bce850..ffcf3be79e23 100644 --- a/drivers/accel/amdxdna/aie2_message.c +++ b/drivers/accel/amdxdna/aie2_message.c @@ -40,11 +40,8 @@ static int aie2_send_mgmt_msg_wait(struct amdxdna_dev_hdl *ndev, return -ENODEV; ret = xdna_send_msg_wait(xdna, ndev->mgmt_chann, msg); - if (ret == -ETIME) { - xdna_mailbox_stop_channel(ndev->mgmt_chann); - xdna_mailbox_destroy_channel(ndev->mgmt_chann); - ndev->mgmt_chann = NULL; - } + if (ret == -ETIME) + aie2_destroy_mgmt_chann(ndev); if (!ret && *hdl->status != AIE2_STATUS_SUCCESS) { XDNA_ERR(xdna, "command opcode 0x%x failed, status 0x%x", @@ -296,13 +293,20 @@ int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwct } intr_reg = i2x.mb_head_ptr_reg + 4; - hwctx->priv->mbox_chann = xdna_mailbox_create_channel(ndev->mbox, &x2i, &i2x, - intr_reg, ret); + hwctx->priv->mbox_chann = xdna_mailbox_alloc_channel(ndev->mbox); if (!hwctx->priv->mbox_chann) { XDNA_ERR(xdna, "Not able to create channel"); ret = -EINVAL; goto del_ctx_req; } + + ret = xdna_mailbox_start_channel(hwctx->priv->mbox_chann, &x2i, &i2x, + intr_reg, ret); + if (ret) { + XDNA_ERR(xdna, "Not able to create channel"); + ret = -EINVAL; + goto free_channel; + } ndev->hwctx_num++; XDNA_DBG(xdna, "Mailbox channel irq: %d, msix_id: %d", ret, resp.msix_id); @@ -310,6 +314,8 @@ int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwct return 0; +free_channel: + xdna_mailbox_free_channel(hwctx->priv->mbox_chann); del_ctx_req: aie2_destroy_context_req(ndev, hwctx->fw_ctx_id); return ret; @@ -325,7 +331,7 @@ int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwc xdna_mailbox_stop_channel(hwctx->priv->mbox_chann); ret = aie2_destroy_context_req(ndev, hwctx->fw_ctx_id); - xdna_mailbox_destroy_channel(hwctx->priv->mbox_chann); + xdna_mailbox_free_channel(hwctx->priv->mbox_chann); XDNA_DBG(xdna, "Destroyed fw ctx %d", hwctx->fw_ctx_id); hwctx->priv->mbox_chann = NULL; hwctx->fw_ctx_id = -1; @@ -914,6 +920,20 @@ void aie2_msg_init(struct amdxdna_dev_hdl *ndev) ndev->exec_msg_ops = &legacy_exec_message_ops; } +void aie2_destroy_mgmt_chann(struct amdxdna_dev_hdl *ndev) +{ + struct amdxdna_dev *xdna = ndev->xdna; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + + if (!ndev->mgmt_chann) + return; + + xdna_mailbox_stop_channel(ndev->mgmt_chann); + xdna_mailbox_free_channel(ndev->mgmt_chann); + ndev->mgmt_chann = NULL; +} + static inline struct amdxdna_gem_obj * aie2_cmdlist_get_cmd_buf(struct amdxdna_sched_job *job) { diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c index 85079b6fc5d9..4924a9da55b6 100644 --- a/drivers/accel/amdxdna/aie2_pci.c +++ b/drivers/accel/amdxdna/aie2_pci.c @@ -330,9 +330,7 @@ static void aie2_hw_stop(struct amdxdna_dev *xdna) aie2_runtime_cfg(ndev, AIE2_RT_CFG_CLK_GATING, NULL); aie2_mgmt_fw_fini(ndev); - xdna_mailbox_stop_channel(ndev->mgmt_chann); - xdna_mailbox_destroy_channel(ndev->mgmt_chann); - ndev->mgmt_chann = NULL; + aie2_destroy_mgmt_chann(ndev); drmm_kfree(&xdna->ddev, ndev->mbox); ndev->mbox = NULL; aie2_psp_stop(ndev->psp_hdl); @@ -363,10 +361,29 @@ static int aie2_hw_start(struct amdxdna_dev *xdna) } pci_set_master(pdev); + mbox_res.ringbuf_base = ndev->sram_base; + mbox_res.ringbuf_size = pci_resource_len(pdev, xdna->dev_info->sram_bar); + mbox_res.mbox_base = ndev->mbox_base; + mbox_res.mbox_size = MBOX_SIZE(ndev); + mbox_res.name = "xdna_mailbox"; + ndev->mbox = xdnam_mailbox_create(&xdna->ddev, &mbox_res); + if (!ndev->mbox) { + XDNA_ERR(xdna, "failed to create mailbox device"); + ret = -ENODEV; + goto disable_dev; + } + + ndev->mgmt_chann = xdna_mailbox_alloc_channel(ndev->mbox); + if (!ndev->mgmt_chann) { + XDNA_ERR(xdna, "failed to alloc channel"); + ret = -ENODEV; + goto disable_dev; + } + ret = aie2_smu_init(ndev); if (ret) { XDNA_ERR(xdna, "failed to init smu, ret %d", ret); - goto disable_dev; + goto free_channel; } ret = aie2_psp_start(ndev->psp_hdl); @@ -381,18 +398,6 @@ static int aie2_hw_start(struct amdxdna_dev *xdna) goto stop_psp; } - mbox_res.ringbuf_base = ndev->sram_base; - mbox_res.ringbuf_size = pci_resource_len(pdev, xdna->dev_info->sram_bar); - mbox_res.mbox_base = ndev->mbox_base; - mbox_res.mbox_size = MBOX_SIZE(ndev); - mbox_res.name = "xdna_mailbox"; - ndev->mbox = xdnam_mailbox_create(&xdna->ddev, &mbox_res); - if (!ndev->mbox) { - XDNA_ERR(xdna, "failed to create mailbox device"); - ret = -ENODEV; - goto stop_psp; - } - mgmt_mb_irq = pci_irq_vector(pdev, ndev->mgmt_chan_idx); if (mgmt_mb_irq < 0) { ret = mgmt_mb_irq; @@ -401,13 +406,13 @@ static int aie2_hw_start(struct amdxdna_dev *xdna) } xdna_mailbox_intr_reg = ndev->mgmt_i2x.mb_head_ptr_reg + 4; - ndev->mgmt_chann = xdna_mailbox_create_channel(ndev->mbox, - &ndev->mgmt_x2i, - &ndev->mgmt_i2x, - xdna_mailbox_intr_reg, - mgmt_mb_irq); - if (!ndev->mgmt_chann) { - XDNA_ERR(xdna, "failed to create management mailbox channel"); + ret = xdna_mailbox_start_channel(ndev->mgmt_chann, + &ndev->mgmt_x2i, + &ndev->mgmt_i2x, + xdna_mailbox_intr_reg, + mgmt_mb_irq); + if (ret) { + XDNA_ERR(xdna, "failed to start management mailbox channel"); ret = -EINVAL; goto stop_psp; } @@ -415,38 +420,41 @@ static int aie2_hw_start(struct amdxdna_dev *xdna) ret = aie2_mgmt_fw_init(ndev); if (ret) { XDNA_ERR(xdna, "initial mgmt firmware failed, ret %d", ret); - goto destroy_mgmt_chann; + goto stop_fw; } ret = aie2_pm_init(ndev); if (ret) { XDNA_ERR(xdna, "failed to init pm, ret %d", ret); - goto destroy_mgmt_chann; + goto stop_fw; } ret = aie2_mgmt_fw_query(ndev); if (ret) { XDNA_ERR(xdna, "failed to query fw, ret %d", ret); - goto destroy_mgmt_chann; + goto stop_fw; } ret = aie2_error_async_events_alloc(ndev); if (ret) { XDNA_ERR(xdna, "Allocate async events failed, ret %d", ret); - goto destroy_mgmt_chann; + goto stop_fw; } ndev->dev_status = AIE2_DEV_START; return 0; -destroy_mgmt_chann: +stop_fw: + aie2_suspend_fw(ndev); xdna_mailbox_stop_channel(ndev->mgmt_chann); - xdna_mailbox_destroy_channel(ndev->mgmt_chann); stop_psp: aie2_psp_stop(ndev->psp_hdl); fini_smu: aie2_smu_fini(ndev); +free_channel: + xdna_mailbox_free_channel(ndev->mgmt_chann); + ndev->mgmt_chann = NULL; disable_dev: pci_disable_device(pdev); diff --git a/drivers/accel/amdxdna/aie2_pci.h b/drivers/accel/amdxdna/aie2_pci.h index b20a3661078c..e72311c77996 100644 --- a/drivers/accel/amdxdna/aie2_pci.h +++ b/drivers/accel/amdxdna/aie2_pci.h @@ -303,6 +303,7 @@ int aie2_get_array_async_error(struct amdxdna_dev_hdl *ndev, /* aie2_message.c */ void aie2_msg_init(struct amdxdna_dev_hdl *ndev); +void aie2_destroy_mgmt_chann(struct amdxdna_dev_hdl *ndev); int aie2_suspend_fw(struct amdxdna_dev_hdl *ndev); int aie2_resume_fw(struct amdxdna_dev_hdl *ndev); int aie2_set_runtime_cfg(struct amdxdna_dev_hdl *ndev, u32 type, u64 value); diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c index 263d36072540..666dfd7b2a80 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.c +++ b/drivers/accel/amdxdna/amdxdna_ctx.c @@ -135,6 +135,33 @@ u32 amdxdna_cmd_get_cu_idx(struct amdxdna_gem_obj *abo) return INVALID_CU_IDX; } +int amdxdna_cmd_set_error(struct amdxdna_gem_obj *abo, + struct amdxdna_sched_job *job, u32 cmd_idx, + enum ert_cmd_state error_state) +{ + struct amdxdna_client *client = job->hwctx->client; + struct amdxdna_cmd *cmd = abo->mem.kva; + struct amdxdna_cmd_chain *cc = NULL; + + cmd->header &= ~AMDXDNA_CMD_STATE; + cmd->header |= FIELD_PREP(AMDXDNA_CMD_STATE, error_state); + + if (amdxdna_cmd_get_op(abo) == ERT_CMD_CHAIN) { + cc = amdxdna_cmd_get_payload(abo, NULL); + cc->error_index = (cmd_idx < cc->command_count) ? cmd_idx : 0; + abo = amdxdna_gem_get_obj(client, cc->data[0], AMDXDNA_BO_CMD); + if (!abo) + return -EINVAL; + cmd = abo->mem.kva; + } + + memset(cmd->data, 0xff, abo->mem.size - sizeof(*cmd)); + if (cc) + amdxdna_gem_put_obj(abo); + + return 0; +} + /* * This should be called in close() and remove(). DO NOT call in other syscalls. * This guarantee that when hwctx and resources will be released, if user diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h b/drivers/accel/amdxdna/amdxdna_ctx.h index 16c85f08f03c..fbdf9d000871 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.h +++ b/drivers/accel/amdxdna/amdxdna_ctx.h @@ -167,6 +167,9 @@ amdxdna_cmd_get_state(struct amdxdna_gem_obj *abo) void *amdxdna_cmd_get_payload(struct amdxdna_gem_obj *abo, u32 *size); u32 amdxdna_cmd_get_cu_idx(struct amdxdna_gem_obj *abo); +int amdxdna_cmd_set_error(struct amdxdna_gem_obj *abo, + struct amdxdna_sched_job *job, u32 cmd_idx, + enum ert_cmd_state error_state); void amdxdna_sched_job_cleanup(struct amdxdna_sched_job *job); void amdxdna_hwctx_remove_all(struct amdxdna_client *client); diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.c b/drivers/accel/amdxdna/amdxdna_mailbox.c index 235a94047530..46d844a73a94 100644 --- a/drivers/accel/amdxdna/amdxdna_mailbox.c +++ b/drivers/accel/amdxdna/amdxdna_mailbox.c @@ -460,26 +460,49 @@ msg_id_failed: return ret; } -struct mailbox_channel * -xdna_mailbox_create_channel(struct mailbox *mb, - const struct xdna_mailbox_chann_res *x2i, - const struct xdna_mailbox_chann_res *i2x, - u32 iohub_int_addr, - int mb_irq) +struct mailbox_channel *xdna_mailbox_alloc_channel(struct mailbox *mb) { struct mailbox_channel *mb_chann; - int ret; - - if (!is_power_of_2(x2i->rb_size) || !is_power_of_2(i2x->rb_size)) { - pr_err("Ring buf size must be power of 2"); - return NULL; - } mb_chann = kzalloc_obj(*mb_chann); if (!mb_chann) return NULL; + INIT_WORK(&mb_chann->rx_work, mailbox_rx_worker); + mb_chann->work_q = create_singlethread_workqueue(MAILBOX_NAME); + if (!mb_chann->work_q) { + MB_ERR(mb_chann, "Create workqueue failed"); + goto free_chann; + } mb_chann->mb = mb; + + return mb_chann; + +free_chann: + kfree(mb_chann); + return NULL; +} + +void xdna_mailbox_free_channel(struct mailbox_channel *mb_chann) +{ + destroy_workqueue(mb_chann->work_q); + kfree(mb_chann); +} + +int +xdna_mailbox_start_channel(struct mailbox_channel *mb_chann, + const struct xdna_mailbox_chann_res *x2i, + const struct xdna_mailbox_chann_res *i2x, + u32 iohub_int_addr, + int mb_irq) +{ + int ret; + + if (!is_power_of_2(x2i->rb_size) || !is_power_of_2(i2x->rb_size)) { + pr_err("Ring buf size must be power of 2"); + return -EINVAL; + } + mb_chann->msix_irq = mb_irq; mb_chann->iohub_int_addr = iohub_int_addr; memcpy(&mb_chann->res[CHAN_RES_X2I], x2i, sizeof(*x2i)); @@ -489,61 +512,37 @@ xdna_mailbox_create_channel(struct mailbox *mb, mb_chann->x2i_tail = mailbox_get_tailptr(mb_chann, CHAN_RES_X2I); mb_chann->i2x_head = mailbox_get_headptr(mb_chann, CHAN_RES_I2X); - INIT_WORK(&mb_chann->rx_work, mailbox_rx_worker); - mb_chann->work_q = create_singlethread_workqueue(MAILBOX_NAME); - if (!mb_chann->work_q) { - MB_ERR(mb_chann, "Create workqueue failed"); - goto free_and_out; - } - /* Everything look good. Time to enable irq handler */ ret = request_irq(mb_irq, mailbox_irq_handler, 0, MAILBOX_NAME, mb_chann); if (ret) { MB_ERR(mb_chann, "Failed to request irq %d ret %d", mb_irq, ret); - goto destroy_wq; + return ret; } mb_chann->bad_state = false; mailbox_reg_write(mb_chann, mb_chann->iohub_int_addr, 0); - MB_DBG(mb_chann, "Mailbox channel created (irq: %d)", mb_chann->msix_irq); - return mb_chann; - -destroy_wq: - destroy_workqueue(mb_chann->work_q); -free_and_out: - kfree(mb_chann); - return NULL; -} - -int xdna_mailbox_destroy_channel(struct mailbox_channel *mb_chann) -{ - struct mailbox_msg *mb_msg; - unsigned long msg_id; - - MB_DBG(mb_chann, "IRQ disabled and RX work cancelled"); - free_irq(mb_chann->msix_irq, mb_chann); - destroy_workqueue(mb_chann->work_q); - /* We can clean up and release resources */ - - xa_for_each(&mb_chann->chan_xa, msg_id, mb_msg) - mailbox_release_msg(mb_chann, mb_msg); - - xa_destroy(&mb_chann->chan_xa); - - MB_DBG(mb_chann, "Mailbox channel destroyed, irq: %d", mb_chann->msix_irq); - kfree(mb_chann); + MB_DBG(mb_chann, "Mailbox channel started (irq: %d)", mb_chann->msix_irq); return 0; } void xdna_mailbox_stop_channel(struct mailbox_channel *mb_chann) { + struct mailbox_msg *mb_msg; + unsigned long msg_id; + /* Disable an irq and wait. This might sleep. */ - disable_irq(mb_chann->msix_irq); + free_irq(mb_chann->msix_irq, mb_chann); /* Cancel RX work and wait for it to finish */ - cancel_work_sync(&mb_chann->rx_work); - MB_DBG(mb_chann, "IRQ disabled and RX work cancelled"); + drain_workqueue(mb_chann->work_q); + + /* We can clean up and release resources */ + xa_for_each(&mb_chann->chan_xa, msg_id, mb_msg) + mailbox_release_msg(mb_chann, mb_msg); + xa_destroy(&mb_chann->chan_xa); + + MB_DBG(mb_chann, "Mailbox channel stopped, irq: %d", mb_chann->msix_irq); } struct mailbox *xdnam_mailbox_create(struct drm_device *ddev, diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.h b/drivers/accel/amdxdna/amdxdna_mailbox.h index ea367f2fb738..8b1e00945da4 100644 --- a/drivers/accel/amdxdna/amdxdna_mailbox.h +++ b/drivers/accel/amdxdna/amdxdna_mailbox.h @@ -74,9 +74,16 @@ struct mailbox *xdnam_mailbox_create(struct drm_device *ddev, const struct xdna_mailbox_res *res); /* - * xdna_mailbox_create_channel() -- Create a mailbox channel instance + * xdna_mailbox_alloc_channel() -- alloc a mailbox channel * - * @mailbox: the handle return from xdna_mailbox_create() + * @mb: mailbox handle + */ +struct mailbox_channel *xdna_mailbox_alloc_channel(struct mailbox *mb); + +/* + * xdna_mailbox_start_channel() -- start a mailbox channel instance + * + * @mb_chann: the handle return from xdna_mailbox_alloc_channel() * @x2i: host to firmware mailbox resources * @i2x: firmware to host mailbox resources * @xdna_mailbox_intr_reg: register addr of MSI-X interrupt @@ -84,28 +91,24 @@ struct mailbox *xdnam_mailbox_create(struct drm_device *ddev, * * Return: If success, return a handle of mailbox channel. Otherwise, return NULL. */ -struct mailbox_channel * -xdna_mailbox_create_channel(struct mailbox *mailbox, - const struct xdna_mailbox_chann_res *x2i, - const struct xdna_mailbox_chann_res *i2x, - u32 xdna_mailbox_intr_reg, - int mb_irq); +int +xdna_mailbox_start_channel(struct mailbox_channel *mb_chann, + const struct xdna_mailbox_chann_res *x2i, + const struct xdna_mailbox_chann_res *i2x, + u32 xdna_mailbox_intr_reg, + int mb_irq); /* - * xdna_mailbox_destroy_channel() -- destroy mailbox channel + * xdna_mailbox_free_channel() -- free mailbox channel * * @mailbox_chann: the handle return from xdna_mailbox_create_channel() - * - * Return: if success, return 0. otherwise return error code */ -int xdna_mailbox_destroy_channel(struct mailbox_channel *mailbox_chann); +void xdna_mailbox_free_channel(struct mailbox_channel *mailbox_chann); /* * xdna_mailbox_stop_channel() -- stop mailbox channel * * @mailbox_chann: the handle return from xdna_mailbox_create_channel() - * - * Return: if success, return 0. otherwise return error code */ void xdna_mailbox_stop_channel(struct mailbox_channel *mailbox_chann); diff --git a/drivers/accel/amdxdna/npu1_regs.c b/drivers/accel/amdxdna/npu1_regs.c index 6e3d3ca69c04..1320e924e548 100644 --- a/drivers/accel/amdxdna/npu1_regs.c +++ b/drivers/accel/amdxdna/npu1_regs.c @@ -67,7 +67,7 @@ const struct dpm_clk_freq npu1_dpm_clk_table[] = { static const struct aie2_fw_feature_tbl npu1_fw_feature_table[] = { { .major = 5, .min_minor = 7 }, - { .features = BIT_U64(AIE2_NPU_COMMAND), .min_minor = 8 }, + { .features = BIT_U64(AIE2_NPU_COMMAND), .major = 5, .min_minor = 8 }, { 0 } }; diff --git a/drivers/accel/ethosu/ethosu_gem.c b/drivers/accel/ethosu/ethosu_gem.c index 668c71d5ff45..7994e7073903 100644 --- a/drivers/accel/ethosu/ethosu_gem.c +++ b/drivers/accel/ethosu/ethosu_gem.c @@ -245,11 +245,14 @@ static int calc_sizes(struct drm_device *ddev, ((st->ifm.stride_kernel >> 1) & 0x1) + 1; u32 stride_x = ((st->ifm.stride_kernel >> 5) & 0x2) + (st->ifm.stride_kernel & 0x1) + 1; - u32 ifm_height = st->ofm.height[2] * stride_y + + s32 ifm_height = st->ofm.height[2] * stride_y + st->ifm.height[2] - (st->ifm.pad_top + st->ifm.pad_bottom); - u32 ifm_width = st->ofm.width * stride_x + + s32 ifm_width = st->ofm.width * stride_x + st->ifm.width - (st->ifm.pad_left + st->ifm.pad_right); + if (ifm_height < 0 || ifm_width < 0) + return -EINVAL; + len = feat_matrix_length(info, &st->ifm, ifm_width, ifm_height, st->ifm.depth); dev_dbg(ddev->dev, "op %d: IFM:%d:0x%llx-0x%llx\n", @@ -417,7 +420,10 @@ static int ethosu_gem_cmdstream_copy_and_validate(struct drm_device *ddev, return ret; break; case NPU_OP_ELEMENTWISE: - use_ifm2 = !((st.ifm2.broadcast == 8) || (param == 5) || + use_scale = ethosu_is_u65(edev) ? + (st.ifm2.broadcast & 0x80) : + (st.ifm2.broadcast == 8); + use_ifm2 = !(use_scale || (param == 5) || (param == 6) || (param == 7) || (param == 0x24)); use_ifm = st.ifm.broadcast != 8; ret = calc_sizes_elemwise(ddev, info, cmd, &st, use_ifm, use_ifm2); diff --git a/drivers/accel/ethosu/ethosu_job.c b/drivers/accel/ethosu/ethosu_job.c index 8598a3634340..ec85f4156744 100644 --- a/drivers/accel/ethosu/ethosu_job.c +++ b/drivers/accel/ethosu/ethosu_job.c @@ -143,17 +143,10 @@ out: return ret; } -static void ethosu_job_cleanup(struct kref *ref) +static void ethosu_job_err_cleanup(struct ethosu_job *job) { - struct ethosu_job *job = container_of(ref, struct ethosu_job, - refcount); unsigned int i; - pm_runtime_put_autosuspend(job->dev->base.dev); - - dma_fence_put(job->done_fence); - dma_fence_put(job->inference_done_fence); - for (i = 0; i < job->region_cnt; i++) drm_gem_object_put(job->region_bo[i]); @@ -162,6 +155,19 @@ static void ethosu_job_cleanup(struct kref *ref) kfree(job); } +static void ethosu_job_cleanup(struct kref *ref) +{ + struct ethosu_job *job = container_of(ref, struct ethosu_job, + refcount); + + pm_runtime_put_autosuspend(job->dev->base.dev); + + dma_fence_put(job->done_fence); + dma_fence_put(job->inference_done_fence); + + ethosu_job_err_cleanup(job); +} + static void ethosu_job_put(struct ethosu_job *job) { kref_put(&job->refcount, ethosu_job_cleanup); @@ -454,12 +460,16 @@ static int ethosu_ioctl_submit_job(struct drm_device *dev, struct drm_file *file } } ret = ethosu_job_push(ejob); + if (!ret) { + ethosu_job_put(ejob); + return 0; + } out_cleanup_job: if (ret) drm_sched_job_cleanup(&ejob->base); out_put_job: - ethosu_job_put(ejob); + ethosu_job_err_cleanup(ejob); return ret; } diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h index 5f70b196e0aa..6c9b5bf7d392 100644 --- a/drivers/acpi/acpica/acpredef.h +++ b/drivers/acpi/acpica/acpredef.h @@ -379,8 +379,9 @@ const union acpi_predefined_info acpi_gbl_predefined_methods[] = { {{"_CPC", METHOD_0ARGS, METHOD_RETURNS(ACPI_RTYPE_PACKAGE)}}, /* Variable-length (Ints/Bufs) */ - PACKAGE_INFO(ACPI_PTYPE1_VAR, ACPI_RTYPE_INTEGER | ACPI_RTYPE_BUFFER, 0, - 0, 0, 0), + PACKAGE_INFO(ACPI_PTYPE1_VAR, + ACPI_RTYPE_INTEGER | ACPI_RTYPE_BUFFER | + ACPI_RTYPE_PACKAGE, 0, 0, 0, 0), {{"_CR3", METHOD_0ARGS, /* ACPI 6.0 */ METHOD_RETURNS(ACPI_RTYPE_INTEGER)}}, diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index f2579611e0a5..aa55ecfc2923 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -1456,15 +1456,6 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on) if (!adev || !acpi_match_device_ids(adev, special_pm_ids)) return 0; - /* - * Skip devices whose ACPI companions don't support power management and - * don't have a wakeup GPE. - */ - if (!acpi_device_power_manageable(adev) && !acpi_device_can_wakeup(adev)) { - dev_dbg(dev, "No ACPI power management or wakeup GPE\n"); - return 0; - } - /* * Only attach the power domain to the first device if the * companion is shared by multiple. This is to prevent doing power diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index ccbf320524da..6c4e567b6582 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4189,6 +4189,7 @@ static const struct ata_dev_quirks_entry __ata_dev_quirks[] = { ATA_QUIRK_FIRMWARE_WARN }, /* Seagate disks with LPM issues */ + { "ST1000DM010-2EP102", NULL, ATA_QUIRK_NOLPM }, { "ST2000DM008-2FR102", NULL, ATA_QUIRK_NOLPM }, /* drives which fail FPDMA_AA activation (some may freeze afterwards) @@ -4231,6 +4232,7 @@ static const struct ata_dev_quirks_entry __ata_dev_quirks[] = { /* Devices that do not need bridging limits applied */ { "MTRON MSP-SATA*", NULL, ATA_QUIRK_BRIDGE_OK }, { "BUFFALO HD-QSU2/R5", NULL, ATA_QUIRK_BRIDGE_OK }, + { "QEMU HARDDISK", "2.5+", ATA_QUIRK_BRIDGE_OK }, /* Devices which aren't very happy with higher link speeds */ { "WD My Book", NULL, ATA_QUIRK_1_5_GBPS }, diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index b373cceb95d2..23be85418b3b 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -647,7 +647,7 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, break; } - if (qc == ap->deferred_qc) { + if (i < ATA_MAX_QUEUE && qc == ap->deferred_qc) { /* * This is a deferred command that timed out while * waiting for the command queue to drain. Since the qc @@ -659,6 +659,7 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, */ WARN_ON_ONCE(qc->flags & ATA_QCFLAG_ACTIVE); ap->deferred_qc = NULL; + cancel_work(&ap->deferred_qc_work); set_host_byte(scmd, DID_TIME_OUT); scsi_eh_finish_cmd(scmd, &ap->eh_done_q); } else if (i < ATA_MAX_QUEUE) { diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index c0dd75a0287c..ad798e5246b4 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1699,6 +1699,7 @@ void ata_scsi_requeue_deferred_qc(struct ata_port *ap) scmd = qc->scsicmd; ap->deferred_qc = NULL; + cancel_work(&ap->deferred_qc_work); ata_qc_free(qc); scmd->result = (DID_SOFT_ERROR << 16); scsi_done(scmd); diff --git a/drivers/base/base.h b/drivers/base/base.h index 79d031d2d845..1af95ac68b77 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -179,19 +179,10 @@ void device_release_driver_internal(struct device *dev, const struct device_driv void driver_detach(const struct device_driver *drv); void driver_deferred_probe_del(struct device *dev); void device_set_deferred_probe_reason(const struct device *dev, struct va_format *vaf); -static inline int driver_match_device_locked(const struct device_driver *drv, - struct device *dev) -{ - device_lock_assert(dev); - - return drv->bus->match ? drv->bus->match(dev, drv) : 1; -} - static inline int driver_match_device(const struct device_driver *drv, struct device *dev) { - guard(device)(dev); - return driver_match_device_locked(drv, dev); + return drv->bus->match ? drv->bus->match(dev, drv) : 1; } static inline void dev_sync_state(struct device *dev) diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 0354f209529c..bea8da5f8a3a 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -928,7 +928,7 @@ static int __device_attach_driver(struct device_driver *drv, void *_data) bool async_allowed; int ret; - ret = driver_match_device_locked(drv, dev); + ret = driver_match_device(drv, dev); if (ret == 0) { /* no match */ return 0; diff --git a/drivers/crypto/atmel-sha204a.c b/drivers/crypto/atmel-sha204a.c index 8adc7fe71c04..98d1023007e3 100644 --- a/drivers/crypto/atmel-sha204a.c +++ b/drivers/crypto/atmel-sha204a.c @@ -52,9 +52,10 @@ static int atmel_sha204a_rng_read_nonblocking(struct hwrng *rng, void *data, rng->priv = 0; } else { work_data = kmalloc_obj(*work_data, GFP_ATOMIC); - if (!work_data) + if (!work_data) { + atomic_dec(&i2c_priv->tfm_count); return -ENOMEM; - + } work_data->ctx = i2c_priv; work_data->client = i2c_priv->client; diff --git a/drivers/crypto/ccp/sev-dev-tsm.c b/drivers/crypto/ccp/sev-dev-tsm.c index adc9542ae806..b07ae529b591 100644 --- a/drivers/crypto/ccp/sev-dev-tsm.c +++ b/drivers/crypto/ccp/sev-dev-tsm.c @@ -378,9 +378,9 @@ void sev_tsm_init_locked(struct sev_device *sev, void *tio_status_page) return; error_exit: - kfree(t); pr_err("Failed to enable SEV-TIO: ret=%d en=%d initdone=%d SEV=%d\n", ret, t->tio_en, t->tio_init_done, boot_cpu_has(X86_FEATURE_SEV)); + kfree(t); } void sev_tsm_uninit(struct sev_device *sev) diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 096f993974d1..8b2dfc11289b 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -1105,15 +1105,12 @@ struct page *snp_alloc_hv_fixed_pages(unsigned int num_2mb_pages) { struct psp_device *psp_master = psp_get_master_device(); struct snp_hv_fixed_pages_entry *entry; - struct sev_device *sev; unsigned int order; struct page *page; - if (!psp_master || !psp_master->sev_data) + if (!psp_master) return NULL; - sev = psp_master->sev_data; - order = get_order(PMD_SIZE * num_2mb_pages); /* @@ -1126,7 +1123,8 @@ struct page *snp_alloc_hv_fixed_pages(unsigned int num_2mb_pages) * This API uses SNP_INIT_EX to transition allocated pages to HV_Fixed * page state, fail if SNP is already initialized. */ - if (sev->snp_initialized) + if (psp_master->sev_data && + ((struct sev_device *)psp_master->sev_data)->snp_initialized) return NULL; /* Re-use freed pages that match the request */ @@ -1162,7 +1160,7 @@ void snp_free_hv_fixed_pages(struct page *page) struct psp_device *psp_master = psp_get_master_device(); struct snp_hv_fixed_pages_entry *entry, *nentry; - if (!psp_master || !psp_master->sev_data) + if (!psp_master) return; /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 06c1913d5a3f..29b400cdd6d5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1439,7 +1439,10 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info, *process_info = info; } - vm->process_info = *process_info; + if (cmpxchg(&vm->process_info, NULL, *process_info) != NULL) { + ret = -EINVAL; + goto already_acquired; + } /* Validate page directory and attach eviction fence */ ret = amdgpu_bo_reserve(vm->root.bo, true); @@ -1479,6 +1482,7 @@ validate_pd_fail: amdgpu_bo_unreserve(vm->root.bo); reserve_pd_fail: vm->process_info = NULL; +already_acquired: if (info) { dma_fence_put(&info->eviction_fence->base); *process_info = NULL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index 9d67b770bcc2..7c450350847d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -446,8 +446,7 @@ static int amdgpu_userq_wait_for_last_fence(struct amdgpu_usermode_queue *queue) return ret; } -static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue, - int queue_id) +static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue) { struct amdgpu_userq_mgr *uq_mgr = queue->userq_mgr; struct amdgpu_device *adev = uq_mgr->adev; @@ -461,7 +460,6 @@ static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue, uq_funcs->mqd_destroy(queue); amdgpu_userq_fence_driver_free(queue); /* Use interrupt-safe locking since IRQ handlers may access these XArrays */ - xa_erase_irq(&uq_mgr->userq_xa, (unsigned long)queue_id); xa_erase_irq(&adev->userq_doorbell_xa, queue->doorbell_index); queue->userq_mgr = NULL; list_del(&queue->userq_va_list); @@ -470,12 +468,6 @@ static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue, up_read(&adev->reset_domain->sem); } -static struct amdgpu_usermode_queue * -amdgpu_userq_find(struct amdgpu_userq_mgr *uq_mgr, int qid) -{ - return xa_load(&uq_mgr->userq_xa, qid); -} - void amdgpu_userq_ensure_ev_fence(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_eviction_fence_mgr *evf_mgr) @@ -625,22 +617,13 @@ unref_bo: } static int -amdgpu_userq_destroy(struct drm_file *filp, int queue_id) +amdgpu_userq_destroy(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_usermode_queue *queue) { - struct amdgpu_fpriv *fpriv = filp->driver_priv; - struct amdgpu_userq_mgr *uq_mgr = &fpriv->userq_mgr; struct amdgpu_device *adev = uq_mgr->adev; - struct amdgpu_usermode_queue *queue; int r = 0; cancel_delayed_work_sync(&uq_mgr->resume_work); mutex_lock(&uq_mgr->userq_mutex); - queue = amdgpu_userq_find(uq_mgr, queue_id); - if (!queue) { - drm_dbg_driver(adev_to_drm(uq_mgr->adev), "Invalid queue id to destroy\n"); - mutex_unlock(&uq_mgr->userq_mutex); - return -EINVAL; - } amdgpu_userq_wait_for_last_fence(queue); /* Cancel any pending hang detection work and cleanup */ if (queue->hang_detect_fence) { @@ -672,7 +655,7 @@ amdgpu_userq_destroy(struct drm_file *filp, int queue_id) drm_warn(adev_to_drm(uq_mgr->adev), "trying to destroy a HW mapping userq\n"); queue->state = AMDGPU_USERQ_STATE_HUNG; } - amdgpu_userq_cleanup(queue, queue_id); + amdgpu_userq_cleanup(queue); mutex_unlock(&uq_mgr->userq_mutex); pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); @@ -680,6 +663,37 @@ amdgpu_userq_destroy(struct drm_file *filp, int queue_id) return r; } +static void amdgpu_userq_kref_destroy(struct kref *kref) +{ + int r; + struct amdgpu_usermode_queue *queue = + container_of(kref, struct amdgpu_usermode_queue, refcount); + struct amdgpu_userq_mgr *uq_mgr = queue->userq_mgr; + + r = amdgpu_userq_destroy(uq_mgr, queue); + if (r) + drm_file_err(uq_mgr->file, "Failed to destroy usermode queue %d\n", r); +} + +struct amdgpu_usermode_queue *amdgpu_userq_get(struct amdgpu_userq_mgr *uq_mgr, u32 qid) +{ + struct amdgpu_usermode_queue *queue; + + xa_lock(&uq_mgr->userq_xa); + queue = xa_load(&uq_mgr->userq_xa, qid); + if (queue) + kref_get(&queue->refcount); + xa_unlock(&uq_mgr->userq_xa); + + return queue; +} + +void amdgpu_userq_put(struct amdgpu_usermode_queue *queue) +{ + if (queue) + kref_put(&queue->refcount, amdgpu_userq_kref_destroy); +} + static int amdgpu_userq_priority_permit(struct drm_file *filp, int priority) { @@ -834,6 +848,9 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args) goto unlock; } + /* drop this refcount during queue destroy */ + kref_init(&queue->refcount); + /* Wait for mode-1 reset to complete */ down_read(&adev->reset_domain->sem); r = xa_err(xa_store_irq(&adev->userq_doorbell_xa, index, queue, GFP_KERNEL)); @@ -985,7 +1002,9 @@ int amdgpu_userq_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) { union drm_amdgpu_userq *args = data; - int r; + struct amdgpu_fpriv *fpriv = filp->driver_priv; + struct amdgpu_usermode_queue *queue; + int r = 0; if (!amdgpu_userq_enabled(dev)) return -ENOTSUPP; @@ -1000,11 +1019,16 @@ int amdgpu_userq_ioctl(struct drm_device *dev, void *data, drm_file_err(filp, "Failed to create usermode queue\n"); break; - case AMDGPU_USERQ_OP_FREE: - r = amdgpu_userq_destroy(filp, args->in.queue_id); - if (r) - drm_file_err(filp, "Failed to destroy usermode queue\n"); + case AMDGPU_USERQ_OP_FREE: { + xa_lock(&fpriv->userq_mgr.userq_xa); + queue = __xa_erase(&fpriv->userq_mgr.userq_xa, args->in.queue_id); + xa_unlock(&fpriv->userq_mgr.userq_xa); + if (!queue) + return -ENOENT; + + amdgpu_userq_put(queue); break; + } default: drm_dbg_driver(dev, "Invalid user queue op specified: %d\n", args->in.op); @@ -1023,16 +1047,23 @@ amdgpu_userq_restore_all(struct amdgpu_userq_mgr *uq_mgr) /* Resume all the queues for this process */ xa_for_each(&uq_mgr->userq_xa, queue_id, queue) { + queue = amdgpu_userq_get(uq_mgr, queue_id); + if (!queue) + continue; + if (!amdgpu_userq_buffer_vas_mapped(queue)) { drm_file_err(uq_mgr->file, "trying restore queue without va mapping\n"); queue->state = AMDGPU_USERQ_STATE_INVALID_VA; + amdgpu_userq_put(queue); continue; } r = amdgpu_userq_restore_helper(queue); if (r) ret = r; + + amdgpu_userq_put(queue); } if (ret) @@ -1266,9 +1297,13 @@ amdgpu_userq_evict_all(struct amdgpu_userq_mgr *uq_mgr) amdgpu_userq_detect_and_reset_queues(uq_mgr); /* Try to unmap all the queues in this process ctx */ xa_for_each(&uq_mgr->userq_xa, queue_id, queue) { + queue = amdgpu_userq_get(uq_mgr, queue_id); + if (!queue) + continue; r = amdgpu_userq_preempt_helper(queue); if (r) ret = r; + amdgpu_userq_put(queue); } if (ret) @@ -1301,16 +1336,24 @@ amdgpu_userq_wait_for_signal(struct amdgpu_userq_mgr *uq_mgr) int ret; xa_for_each(&uq_mgr->userq_xa, queue_id, queue) { + queue = amdgpu_userq_get(uq_mgr, queue_id); + if (!queue) + continue; + struct dma_fence *f = queue->last_fence; - if (!f || dma_fence_is_signaled(f)) + if (!f || dma_fence_is_signaled(f)) { + amdgpu_userq_put(queue); continue; + } ret = dma_fence_wait_timeout(f, true, msecs_to_jiffies(100)); if (ret <= 0) { drm_file_err(uq_mgr->file, "Timed out waiting for fence=%llu:%llu\n", f->context, f->seqno); + amdgpu_userq_put(queue); return -ETIMEDOUT; } + amdgpu_userq_put(queue); } return 0; @@ -1361,20 +1404,23 @@ int amdgpu_userq_mgr_init(struct amdgpu_userq_mgr *userq_mgr, struct drm_file *f void amdgpu_userq_mgr_fini(struct amdgpu_userq_mgr *userq_mgr) { struct amdgpu_usermode_queue *queue; - unsigned long queue_id; + unsigned long queue_id = 0; - cancel_delayed_work_sync(&userq_mgr->resume_work); + for (;;) { + xa_lock(&userq_mgr->userq_xa); + queue = xa_find(&userq_mgr->userq_xa, &queue_id, ULONG_MAX, + XA_PRESENT); + if (queue) + __xa_erase(&userq_mgr->userq_xa, queue_id); + xa_unlock(&userq_mgr->userq_xa); - mutex_lock(&userq_mgr->userq_mutex); - amdgpu_userq_detect_and_reset_queues(userq_mgr); - xa_for_each(&userq_mgr->userq_xa, queue_id, queue) { - amdgpu_userq_wait_for_last_fence(queue); - amdgpu_userq_unmap_helper(queue); - amdgpu_userq_cleanup(queue, queue_id); + if (!queue) + break; + + amdgpu_userq_put(queue); } xa_destroy(&userq_mgr->userq_xa); - mutex_unlock(&userq_mgr->userq_mutex); mutex_destroy(&userq_mgr->userq_mutex); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h index 5845d8959034..736c1d38297c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h @@ -74,6 +74,7 @@ struct amdgpu_usermode_queue { struct dentry *debugfs_queue; struct delayed_work hang_detect_work; struct dma_fence *hang_detect_fence; + struct kref refcount; struct list_head userq_va_list; }; @@ -112,6 +113,9 @@ struct amdgpu_db_info { struct amdgpu_userq_obj *db_obj; }; +struct amdgpu_usermode_queue *amdgpu_userq_get(struct amdgpu_userq_mgr *uq_mgr, u32 qid); +void amdgpu_userq_put(struct amdgpu_usermode_queue *queue); + int amdgpu_userq_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); int amdgpu_userq_mgr_init(struct amdgpu_userq_mgr *userq_mgr, struct drm_file *file_priv, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c index 7e9cf1868cc9..5239b06b9ab0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c @@ -466,7 +466,7 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data, struct drm_amdgpu_userq_signal *args = data; struct drm_gem_object **gobj_write = NULL; struct drm_gem_object **gobj_read = NULL; - struct amdgpu_usermode_queue *queue; + struct amdgpu_usermode_queue *queue = NULL; struct amdgpu_userq_fence *userq_fence; struct drm_syncobj **syncobj = NULL; u32 *bo_handles_write, num_write_bo_handles; @@ -553,7 +553,7 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data, } /* Retrieve the user queue */ - queue = xa_load(&userq_mgr->userq_xa, args->queue_id); + queue = amdgpu_userq_get(userq_mgr, args->queue_id); if (!queue) { r = -ENOENT; goto put_gobj_write; @@ -648,6 +648,9 @@ free_syncobj: free_syncobj_handles: kfree(syncobj_handles); + if (queue) + amdgpu_userq_put(queue); + return r; } @@ -660,7 +663,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data, struct drm_amdgpu_userq_wait *wait_info = data; struct amdgpu_fpriv *fpriv = filp->driver_priv; struct amdgpu_userq_mgr *userq_mgr = &fpriv->userq_mgr; - struct amdgpu_usermode_queue *waitq; + struct amdgpu_usermode_queue *waitq = NULL; struct drm_gem_object **gobj_write; struct drm_gem_object **gobj_read; struct dma_fence **fences = NULL; @@ -926,7 +929,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data, */ num_fences = dma_fence_dedup_array(fences, num_fences); - waitq = xa_load(&userq_mgr->userq_xa, wait_info->waitq_id); + waitq = amdgpu_userq_get(userq_mgr, wait_info->waitq_id); if (!waitq) { r = -EINVAL; goto free_fences; @@ -983,32 +986,14 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data, r = -EFAULT; goto free_fences; } - - kfree(fences); - kfree(fence_info); } - drm_exec_fini(&exec); - for (i = 0; i < num_read_bo_handles; i++) - drm_gem_object_put(gobj_read[i]); - kfree(gobj_read); - - for (i = 0; i < num_write_bo_handles; i++) - drm_gem_object_put(gobj_write[i]); - kfree(gobj_write); - - kfree(timeline_points); - kfree(timeline_handles); - kfree(syncobj_handles); - kfree(bo_handles_write); - kfree(bo_handles_read); - - return 0; - free_fences: - while (num_fences-- > 0) - dma_fence_put(fences[num_fences]); - kfree(fences); + if (fences) { + while (num_fences-- > 0) + dma_fence_put(fences[num_fences]); + kfree(fences); + } free_fence_info: kfree(fence_info); exec_fini: @@ -1032,5 +1017,8 @@ free_bo_handles_write: free_bo_handles_read: kfree(bo_handles_read); + if (waitq) + amdgpu_userq_put(waitq); + return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c index 723ddae17644..73a709773e85 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c @@ -69,12 +69,12 @@ static int psp_v15_0_0_ring_stop(struct psp_context *psp, 0x80000000, 0x80000000, false); } else { /* Write the ring destroy command*/ - WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_64, + WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64, GFX_CTRL_CMD_ID_DESTROY_RINGS); /* there might be handshake issue with hardware which needs delay */ mdelay(20); /* Wait for response flag (bit 31) */ - ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_SMN_C2PMSG_64), + ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64), 0x80000000, 0x80000000, false); } @@ -116,7 +116,7 @@ static int psp_v15_0_0_ring_create(struct psp_context *psp, } else { /* Wait for sOS ready for ring creation */ - ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_SMN_C2PMSG_64), + ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64), 0x80000000, 0x80000000, false); if (ret) { DRM_ERROR("Failed to wait for trust OS ready for ring creation\n"); @@ -125,23 +125,23 @@ static int psp_v15_0_0_ring_create(struct psp_context *psp, /* Write low address of the ring to C2PMSG_69 */ psp_ring_reg = lower_32_bits(ring->ring_mem_mc_addr); - WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_69, psp_ring_reg); + WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_69, psp_ring_reg); /* Write high address of the ring to C2PMSG_70 */ psp_ring_reg = upper_32_bits(ring->ring_mem_mc_addr); - WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_70, psp_ring_reg); + WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_70, psp_ring_reg); /* Write size of ring to C2PMSG_71 */ psp_ring_reg = ring->ring_size; - WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_71, psp_ring_reg); + WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_71, psp_ring_reg); /* Write the ring initialization command to C2PMSG_64 */ psp_ring_reg = ring_type; psp_ring_reg = psp_ring_reg << 16; - WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_64, psp_ring_reg); + WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64, psp_ring_reg); /* there might be handshake issue with hardware which needs delay */ mdelay(20); /* Wait for response flag (bit 31) in C2PMSG_64 */ - ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_SMN_C2PMSG_64), + ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64), 0x80000000, 0x8000FFFF, false); } @@ -174,7 +174,7 @@ static uint32_t psp_v15_0_0_ring_get_wptr(struct psp_context *psp) if (amdgpu_sriov_vf(adev)) data = RREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_102); else - data = RREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_67); + data = RREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_67); return data; } @@ -188,7 +188,7 @@ static void psp_v15_0_0_ring_set_wptr(struct psp_context *psp, uint32_t value) WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_101, GFX_CTRL_CMD_ID_CONSUME_CMD); } else - WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_67, value); + WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_67, value); } static const struct psp_funcs psp_v15_0_0_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 8122a5cacf07..a0ad1f8a76f0 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -858,7 +858,9 @@ static int soc21_common_early_init(struct amdgpu_ip_block *ip_block) AMD_CG_SUPPORT_IH_CG | AMD_CG_SUPPORT_BIF_MGCG | AMD_CG_SUPPORT_BIF_LS; - adev->pg_flags = AMD_PG_SUPPORT_VCN | + adev->pg_flags = AMD_PG_SUPPORT_VCN_DPG | + AMD_PG_SUPPORT_VCN | + AMD_PG_SUPPORT_JPEG_DPG | AMD_PG_SUPPORT_JPEG | AMD_PG_SUPPORT_GFX_PG; adev->external_rev_id = adev->rev_id + 0x1; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c index 2ba98f384685..cd1e58b8defc 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c @@ -1706,6 +1706,7 @@ __set_dm_plane_colorop_3dlut(struct drm_plane_state *plane_state, struct dc_transfer_func *tf = &dc_plane_state->in_shaper_func; struct drm_atomic_state *state = plane_state->state; const struct amdgpu_device *adev = drm_to_adev(colorop->dev); + bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut || adev->dm.dc->caps.color.mpc.preblend; const struct drm_device *dev = colorop->dev; const struct drm_color_lut32 *lut3d; uint32_t lut3d_size; @@ -1722,7 +1723,7 @@ __set_dm_plane_colorop_3dlut(struct drm_plane_state *plane_state, } if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_3D_LUT) { - if (!adev->dm.dc->caps.color.dpp.hw_3d_lut) { + if (!has_3dlut) { drm_dbg(dev, "3D LUT is not supported by hardware\n"); return -EINVAL; } @@ -1875,6 +1876,7 @@ amdgpu_dm_plane_set_colorop_properties(struct drm_plane_state *plane_state, struct drm_colorop *colorop = plane_state->color_pipeline; struct drm_device *dev = plane_state->plane->dev; struct amdgpu_device *adev = drm_to_adev(dev); + bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut || adev->dm.dc->caps.color.mpc.preblend; int ret; /* 1D Curve - DEGAM TF */ @@ -1907,7 +1909,7 @@ amdgpu_dm_plane_set_colorop_properties(struct drm_plane_state *plane_state, if (ret) return ret; - if (adev->dm.dc->caps.color.dpp.hw_3d_lut) { + if (has_3dlut) { /* 1D Curve & LUT - SHAPER TF & LUT */ colorop = colorop->next; if (!colorop) { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c index f25c0ede7199..d59ba82d3d7c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c @@ -60,6 +60,7 @@ int amdgpu_dm_initialize_default_pipeline(struct drm_plane *plane, struct drm_pr struct drm_colorop *ops[MAX_COLOR_PIPELINE_OPS]; struct drm_device *dev = plane->dev; struct amdgpu_device *adev = drm_to_adev(dev); + bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut || adev->dm.dc->caps.color.mpc.preblend; int ret; int i = 0; @@ -112,7 +113,7 @@ int amdgpu_dm_initialize_default_pipeline(struct drm_plane *plane, struct drm_pr i++; - if (adev->dm.dc->caps.color.dpp.hw_3d_lut) { + if (has_3dlut) { /* 1D curve - SHAPER TF */ ops[i] = kzalloc_obj(*ops[0]); if (!ops[i]) { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index 130190e8a1b2..304437c2284d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -765,15 +765,15 @@ int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm, dm->adev->mode_info.crtcs[crtc_index] = acrtc; /* Don't enable DRM CRTC degamma property for - * 1. Degamma is replaced by color pipeline. - * 2. DCE since it doesn't support programmable degamma anywhere. - * 3. DCN401 since pre-blending degamma LUT doesn't apply to cursor. + * 1. DCE since it doesn't support programmable degamma anywhere. + * 2. DCN401 since pre-blending degamma LUT doesn't apply to cursor. + * Note: DEGAMMA properties are created even if the primary plane has the + * COLOR_PIPELINE property. User space can use either the DEGAMMA properties + * or the COLOR_PIPELINE property. An atomic commit which attempts to enable + * both is rejected. */ - if (plane->color_pipeline_property) - has_degamma = false; - else - has_degamma = dm->adev->dm.dc->caps.color.dpp.dcn_arch && - dm->adev->dm.dc->ctx->dce_version != DCN_VERSION_4_01; + has_degamma = dm->adev->dm.dc->caps.color.dpp.dcn_arch && + dm->adev->dm.dc->ctx->dce_version != DCN_VERSION_4_01; drm_crtc_enable_color_mgmt(&acrtc->base, has_degamma ? MAX_COLOR_LUT_ENTRIES : 0, true, MAX_COLOR_LUT_ENTRIES); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index 70587e5a8d46..127207e18dcb 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -1256,6 +1256,14 @@ static int amdgpu_dm_plane_atomic_check(struct drm_plane *plane, if (ret) return ret; + /* Reject commits that attempt to use both COLOR_PIPELINE and CRTC DEGAMMA_LUT */ + if (new_plane_state->color_pipeline && new_crtc_state->degamma_lut) { + drm_dbg_atomic(plane->dev, + "[PLANE:%d:%s] COLOR_PIPELINE and CRTC DEGAMMA_LUT cannot be enabled simultaneously\n", + plane->base.id, plane->name); + return -EINVAL; + } + ret = amdgpu_dm_plane_fill_dc_scaling_info(adev, new_plane_state, &scaling_info); if (ret) return ret; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c index b91517b9fedc..eb198d52a115 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c @@ -72,7 +72,11 @@ void dcn401_initialize_min_clocks(struct dc *dc) * audio corruption. Read current DISPCLK from DENTIST and request the same * freq to ensure that the timing is valid and unchanged. */ - clocks->dispclk_khz = dc->clk_mgr->funcs->get_dispclk_from_dentist(dc->clk_mgr); + if (dc->clk_mgr->funcs->get_dispclk_from_dentist) { + clocks->dispclk_khz = dc->clk_mgr->funcs->get_dispclk_from_dentist(dc->clk_mgr); + } else { + clocks->dispclk_khz = dc->clk_mgr->boot_snapshot.dispclk * 1000; + } } clocks->ref_dtbclk_khz = dc->clk_mgr->bw_params->clk_table.entries[0].dtbclk_mhz * 1000; clocks->fclk_p_state_change_support = true; diff --git a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h index 0e4c195297a4..fe97943b9b97 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h @@ -82,6 +82,24 @@ #define regMPASP_SMN_IH_SW_INT_CTRL 0x0142 #define regMPASP_SMN_IH_SW_INT_CTRL_BASE_IDX 0 +// addressBlock: mp_SmuMpASPPub_PcruDec +// base address: 0x3800000 +#define regMPASP_PCRU1_MPASP_C2PMSG_64 0x4280 +#define regMPASP_PCRU1_MPASP_C2PMSG_64_BASE_IDX 3 +#define regMPASP_PCRU1_MPASP_C2PMSG_65 0x4281 +#define regMPASP_PCRU1_MPASP_C2PMSG_65_BASE_IDX 3 +#define regMPASP_PCRU1_MPASP_C2PMSG_66 0x4282 +#define regMPASP_PCRU1_MPASP_C2PMSG_66_BASE_IDX 3 +#define regMPASP_PCRU1_MPASP_C2PMSG_67 0x4283 +#define regMPASP_PCRU1_MPASP_C2PMSG_67_BASE_IDX 3 +#define regMPASP_PCRU1_MPASP_C2PMSG_68 0x4284 +#define regMPASP_PCRU1_MPASP_C2PMSG_68_BASE_IDX 3 +#define regMPASP_PCRU1_MPASP_C2PMSG_69 0x4285 +#define regMPASP_PCRU1_MPASP_C2PMSG_69_BASE_IDX 3 +#define regMPASP_PCRU1_MPASP_C2PMSG_70 0x4286 +#define regMPASP_PCRU1_MPASP_C2PMSG_70_BASE_IDX 3 +#define regMPASP_PCRU1_MPASP_C2PMSG_71 0x4287 +#define regMPASP_PCRU1_MPASP_C2PMSG_71_BASE_IDX 3 // addressBlock: mp_SmuMp1_SmnDec // base address: 0x0 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 e030f1e186cb..b32c053950c9 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 @@ -2034,6 +2034,7 @@ static ssize_t smu_v13_0_0_get_gpu_metrics(struct smu_context *smu, smu, SMU_DRIVER_TABLE_GPU_METRICS); SmuMetricsExternal_t metrics_ext; SmuMetrics_t *metrics = &metrics_ext.SmuMetrics; + uint32_t mp1_ver = amdgpu_ip_version(smu->adev, MP1_HWIP, 0); int ret = 0; ret = smu_cmn_get_metrics_table(smu, @@ -2058,7 +2059,12 @@ static ssize_t smu_v13_0_0_get_gpu_metrics(struct smu_context *smu, metrics->Vcn1ActivityPercentage); gpu_metrics->average_socket_power = metrics->AverageSocketPower; - gpu_metrics->energy_accumulator = metrics->EnergyAccumulator; + + if ((mp1_ver == IP_VERSION(13, 0, 0) && smu->smc_fw_version <= 0x004e1e00) || + (mp1_ver == IP_VERSION(13, 0, 10) && smu->smc_fw_version <= 0x00500800)) + gpu_metrics->energy_accumulator = metrics->EnergyAccumulator; + else + gpu_metrics->energy_accumulator = UINT_MAX; if (metrics->AverageGfxActivity <= SMU_13_0_0_BUSY_THRESHOLD) gpu_metrics->average_gfxclk_frequency = metrics->AverageGfxclkFrequencyPostDs; 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 af0482c9caa7..f08cfa510a8a 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 @@ -2065,7 +2065,8 @@ static ssize_t smu_v13_0_7_get_gpu_metrics(struct smu_context *smu, metrics->Vcn1ActivityPercentage); gpu_metrics->average_socket_power = metrics->AverageSocketPower; - gpu_metrics->energy_accumulator = metrics->EnergyAccumulator; + gpu_metrics->energy_accumulator = smu->smc_fw_version <= 0x00521400 ? + metrics->EnergyAccumulator : UINT_MAX; if (metrics->AverageGfxActivity <= SMU_13_0_7_BUSY_THRESHOLD) gpu_metrics->average_gfxclk_frequency = metrics->AverageGfxclkFrequencyPostDs; diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c index bdc79140875c..862675ac5bb2 100644 --- a/drivers/gpu/drm/drm_pagemap.c +++ b/drivers/gpu/drm/drm_pagemap.c @@ -480,18 +480,8 @@ int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation, .start = start, .end = end, .pgmap_owner = pagemap->owner, - /* - * FIXME: MIGRATE_VMA_SELECT_DEVICE_PRIVATE intermittently - * causes 'xe_exec_system_allocator --r *race*no*' to trigger aa - * engine reset and a hard hang due to getting stuck on a folio - * lock. This should work and needs to be root-caused. The only - * downside of not selecting MIGRATE_VMA_SELECT_DEVICE_PRIVATE - * is that device-to-device migrations won’t work; instead, - * memory will bounce through system memory. This path should be - * rare and only occur when the madvise attributes of memory are - * changed or atomics are being used. - */ - .flags = MIGRATE_VMA_SELECT_SYSTEM | MIGRATE_VMA_SELECT_DEVICE_COHERENT, + .flags = MIGRATE_VMA_SELECT_SYSTEM | MIGRATE_VMA_SELECT_DEVICE_COHERENT | + MIGRATE_VMA_SELECT_DEVICE_PRIVATE, }; unsigned long i, npages = npages_in_range(start, end); unsigned long own_pages = 0, migrated_pages = 0; diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 62208ffc5101..4ce1173a2e91 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -1307,9 +1307,14 @@ static bool psr2_granularity_check(struct intel_crtc_state *crtc_state, u16 sink_y_granularity = crtc_state->has_panel_replay ? connector->dp.panel_replay_caps.su_y_granularity : connector->dp.psr_caps.su_y_granularity; - u16 sink_w_granularity = crtc_state->has_panel_replay ? - connector->dp.panel_replay_caps.su_w_granularity : - connector->dp.psr_caps.su_w_granularity; + u16 sink_w_granularity; + + if (crtc_state->has_panel_replay) + sink_w_granularity = connector->dp.panel_replay_caps.su_w_granularity == + DP_PANEL_REPLAY_FULL_LINE_GRANULARITY ? + crtc_hdisplay : connector->dp.panel_replay_caps.su_w_granularity; + else + sink_w_granularity = connector->dp.psr_caps.su_w_granularity; /* PSR2 HW only send full lines so we only need to validate the width */ if (crtc_hdisplay % sink_w_granularity) diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 00d4530aea71..cc239492c7f0 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -1230,6 +1230,9 @@ nouveau_connector_aux_xfer(struct drm_dp_aux *obj, struct drm_dp_aux_msg *msg) u8 size = msg->size; int ret; + if (pm_runtime_suspended(nv_connector->base.dev->dev)) + return -EBUSY; + nv_encoder = find_encoder(&nv_connector->base, DCB_OUTPUT_DP); if (!nv_encoder) return -ENODEV; diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c index bd703a2904a1..a70f1db0764e 100644 --- a/drivers/gpu/drm/panthor/panthor_sched.c +++ b/drivers/gpu/drm/panthor/panthor_sched.c @@ -893,14 +893,15 @@ panthor_queue_get_syncwait_obj(struct panthor_group *group, struct panthor_queue out_sync: /* Make sure the CPU caches are invalidated before the seqno is read. - * drm_gem_shmem_sync() is a NOP if map_wc=true, so no need to check + * panthor_gem_sync() is a NOP if map_wc=true, so no need to check * it here. */ - panthor_gem_sync(&bo->base.base, queue->syncwait.offset, + panthor_gem_sync(&bo->base.base, + DRM_PANTHOR_BO_SYNC_CPU_CACHE_FLUSH_AND_INVALIDATE, + queue->syncwait.offset, queue->syncwait.sync64 ? sizeof(struct panthor_syncobj_64b) : - sizeof(struct panthor_syncobj_32b), - DRM_PANTHOR_BO_SYNC_CPU_CACHE_FLUSH_AND_INVALIDATE); + sizeof(struct panthor_syncobj_32b)); return queue->syncwait.kmap + queue->syncwait.offset; diff --git a/drivers/gpu/drm/renesas/rz-du/rzg2l_mipi_dsi.c b/drivers/gpu/drm/renesas/rz-du/rzg2l_mipi_dsi.c index f74a0aa85ba8..29f2b7d24fe5 100644 --- a/drivers/gpu/drm/renesas/rz-du/rzg2l_mipi_dsi.c +++ b/drivers/gpu/drm/renesas/rz-du/rzg2l_mipi_dsi.c @@ -1122,6 +1122,7 @@ static int rzg2l_mipi_dsi_host_attach(struct mipi_dsi_host *host, struct mipi_dsi_device *device) { struct rzg2l_mipi_dsi *dsi = host_to_rzg2l_mipi_dsi(host); + int bpp; int ret; if (device->lanes > dsi->num_data_lanes) { @@ -1131,7 +1132,8 @@ static int rzg2l_mipi_dsi_host_attach(struct mipi_dsi_host *host, return -EINVAL; } - switch (mipi_dsi_pixel_format_to_bpp(device->format)) { + bpp = mipi_dsi_pixel_format_to_bpp(device->format); + switch (bpp) { case 24: break; case 18: @@ -1162,6 +1164,18 @@ static int rzg2l_mipi_dsi_host_attach(struct mipi_dsi_host *host, drm_bridge_add(&dsi->bridge); + /* + * Report the required division ratio setting for the MIPI clock dividers. + * + * vclk * bpp = hsclk * 8 * num_lanes + * + * vclk * DSI_AB_divider = hsclk * 16 + * + * which simplifies to... + * DSI_AB_divider = bpp * 2 / num_lanes + */ + rzg2l_cpg_dsi_div_set_divider(bpp * 2 / dsi->lanes, PLL5_TARGET_DSI); + return 0; } diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index e6ee35406165..2d5cb21a05b6 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -361,6 +361,7 @@ static void drm_sched_run_free_queue(struct drm_gpu_scheduler *sched) /** * drm_sched_job_done - complete a job * @s_job: pointer to the job which is done + * @result: 0 on success, -ERRNO on error * * Finish the job's fence and resubmit the work items. */ diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c index 6ecf9e2ff61b..c77455b1834d 100644 --- a/drivers/gpu/drm/solomon/ssd130x.c +++ b/drivers/gpu/drm/solomon/ssd130x.c @@ -737,6 +737,7 @@ static int ssd130x_update_rect(struct ssd130x_device *ssd130x, unsigned int height = drm_rect_height(rect); unsigned int line_length = DIV_ROUND_UP(width, 8); unsigned int page_height = SSD130X_PAGE_HEIGHT; + u8 page_start = ssd130x->page_offset + y / page_height; unsigned int pages = DIV_ROUND_UP(height, page_height); struct drm_device *drm = &ssd130x->drm; u32 array_idx = 0; @@ -774,14 +775,11 @@ static int ssd130x_update_rect(struct ssd130x_device *ssd130x, */ if (!ssd130x->page_address_mode) { - u8 page_start; - /* Set address range for horizontal addressing mode */ ret = ssd130x_set_col_range(ssd130x, ssd130x->col_offset + x, width); if (ret < 0) return ret; - page_start = ssd130x->page_offset + y / page_height; ret = ssd130x_set_page_range(ssd130x, page_start, pages); if (ret < 0) return ret; @@ -813,7 +811,7 @@ static int ssd130x_update_rect(struct ssd130x_device *ssd130x, */ if (ssd130x->page_address_mode) { ret = ssd130x_set_page_pos(ssd130x, - ssd130x->page_offset + i, + page_start + i, ssd130x->col_offset + x); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/ttm/tests/ttm_bo_test.c b/drivers/gpu/drm/ttm/tests/ttm_bo_test.c index d468f8322072..f3103307b5df 100644 --- a/drivers/gpu/drm/ttm/tests/ttm_bo_test.c +++ b/drivers/gpu/drm/ttm/tests/ttm_bo_test.c @@ -222,13 +222,13 @@ static void ttm_bo_reserve_interrupted(struct kunit *test) KUNIT_FAIL(test, "Couldn't create ttm bo reserve task\n"); /* Take a lock so the threaded reserve has to wait */ - mutex_lock(&bo->base.resv->lock.base); + dma_resv_lock(bo->base.resv, NULL); wake_up_process(task); msleep(20); err = kthread_stop(task); - mutex_unlock(&bo->base.resv->lock.base); + dma_resv_unlock(bo->base.resv); KUNIT_ASSERT_EQ(test, err, -ERESTARTSYS); } diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index acb9197db879..0765d69423d2 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1107,8 +1107,7 @@ struct ttm_bo_swapout_walk { static s64 ttm_bo_swapout_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object *bo) { - struct ttm_resource *res = bo->resource; - struct ttm_place place = { .mem_type = res->mem_type }; + struct ttm_place place = { .mem_type = bo->resource->mem_type }; struct ttm_bo_swapout_walk *swapout_walk = container_of(walk, typeof(*swapout_walk), walk); struct ttm_operation_ctx *ctx = walk->arg.ctx; @@ -1148,7 +1147,7 @@ ttm_bo_swapout_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object *bo) /* * Move to system cached */ - if (res->mem_type != TTM_PL_SYSTEM) { + if (bo->resource->mem_type != TTM_PL_SYSTEM) { struct ttm_resource *evict_mem; struct ttm_place hop; @@ -1180,15 +1179,15 @@ ttm_bo_swapout_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object *bo) if (ttm_tt_is_populated(tt)) { spin_lock(&bdev->lru_lock); - ttm_resource_del_bulk_move(res, bo); + ttm_resource_del_bulk_move(bo->resource, bo); spin_unlock(&bdev->lru_lock); ret = ttm_tt_swapout(bdev, tt, swapout_walk->gfp_flags); spin_lock(&bdev->lru_lock); if (ret) - ttm_resource_add_bulk_move(res, bo); - ttm_resource_move_to_lru_tail(res); + ttm_resource_add_bulk_move(bo->resource, bo); + ttm_resource_move_to_lru_tail(bo->resource); spin_unlock(&bdev->lru_lock); } diff --git a/drivers/gpu/drm/ttm/ttm_pool_internal.h b/drivers/gpu/drm/ttm/ttm_pool_internal.h index 82c4b7e56a99..24c179fd69d1 100644 --- a/drivers/gpu/drm/ttm/ttm_pool_internal.h +++ b/drivers/gpu/drm/ttm/ttm_pool_internal.h @@ -17,7 +17,7 @@ static inline bool ttm_pool_uses_dma32(struct ttm_pool *pool) return pool->alloc_flags & TTM_ALLOCATION_POOL_USE_DMA32; } -static inline bool ttm_pool_beneficial_order(struct ttm_pool *pool) +static inline unsigned int ttm_pool_beneficial_order(struct ttm_pool *pool) { return pool->alloc_flags & 0xff; } diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c index c59b1414df22..7fd07d1280bb 100644 --- a/drivers/gpu/drm/xe/xe_configfs.c +++ b/drivers/gpu/drm/xe/xe_configfs.c @@ -830,6 +830,7 @@ static void xe_config_device_release(struct config_item *item) mutex_destroy(&dev->lock); + kfree(dev->config.ctx_restore_mid_bb[0].cs); kfree(dev->config.ctx_restore_post_bb[0].cs); kfree(dev); } diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 0ddae7fcfc97..8ecdf949f9e4 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -266,6 +266,16 @@ static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe, return q; } +static void __xe_exec_queue_fini(struct xe_exec_queue *q) +{ + int i; + + q->ops->fini(q); + + for (i = 0; i < q->width; ++i) + xe_lrc_put(q->lrc[i]); +} + static int __xe_exec_queue_init(struct xe_exec_queue *q, u32 exec_queue_flags) { int i, err; @@ -320,21 +330,10 @@ static int __xe_exec_queue_init(struct xe_exec_queue *q, u32 exec_queue_flags) return 0; err_lrc: - for (i = i - 1; i >= 0; --i) - xe_lrc_put(q->lrc[i]); + __xe_exec_queue_fini(q); return err; } -static void __xe_exec_queue_fini(struct xe_exec_queue *q) -{ - int i; - - q->ops->fini(q); - - for (i = 0; i < q->width; ++i) - xe_lrc_put(q->lrc[i]); -} - struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *vm, u32 logical_mask, u16 width, struct xe_hw_engine *hwe, u32 flags, diff --git a/drivers/gpu/drm/xe/xe_gsc_proxy.c b/drivers/gpu/drm/xe/xe_gsc_proxy.c index 42438b21f235..707db650a2ae 100644 --- a/drivers/gpu/drm/xe/xe_gsc_proxy.c +++ b/drivers/gpu/drm/xe/xe_gsc_proxy.c @@ -435,15 +435,11 @@ static int proxy_channel_alloc(struct xe_gsc *gsc) return 0; } -static void xe_gsc_proxy_remove(void *arg) +static void xe_gsc_proxy_stop(struct xe_gsc *gsc) { - struct xe_gsc *gsc = arg; struct xe_gt *gt = gsc_to_gt(gsc); struct xe_device *xe = gt_to_xe(gt); - if (!gsc->proxy.component_added) - return; - /* disable HECI2 IRQs */ scoped_guard(xe_pm_runtime, xe) { CLASS(xe_force_wake, fw_ref)(gt_to_fw(gt), XE_FW_GSC); @@ -455,6 +451,30 @@ static void xe_gsc_proxy_remove(void *arg) } xe_gsc_wait_for_worker_completion(gsc); + gsc->proxy.started = false; +} + +static void xe_gsc_proxy_remove(void *arg) +{ + struct xe_gsc *gsc = arg; + struct xe_gt *gt = gsc_to_gt(gsc); + struct xe_device *xe = gt_to_xe(gt); + + if (!gsc->proxy.component_added) + return; + + /* + * GSC proxy start is an async process that can be ongoing during + * Xe module load/unload. Using devm managed action to register + * xe_gsc_proxy_stop could cause issues if Xe module unload has + * already started when the action is registered, potentially leading + * to the cleanup being called at the wrong time. Therefore, instead + * of registering a separate devm action to undo what is done in + * proxy start, we call it from here, but only if the start has + * completed successfully (tracked with the 'started' flag). + */ + if (gsc->proxy.started) + xe_gsc_proxy_stop(gsc); component_del(xe->drm.dev, &xe_gsc_proxy_component_ops); gsc->proxy.component_added = false; @@ -510,6 +530,7 @@ int xe_gsc_proxy_init(struct xe_gsc *gsc) */ int xe_gsc_proxy_start(struct xe_gsc *gsc) { + struct xe_gt *gt = gsc_to_gt(gsc); int err; /* enable the proxy interrupt in the GSC shim layer */ @@ -521,12 +542,18 @@ int xe_gsc_proxy_start(struct xe_gsc *gsc) */ err = xe_gsc_proxy_request_handler(gsc); if (err) - return err; + goto err_irq_disable; if (!xe_gsc_proxy_init_done(gsc)) { - xe_gt_err(gsc_to_gt(gsc), "GSC FW reports proxy init not completed\n"); - return -EIO; + xe_gt_err(gt, "GSC FW reports proxy init not completed\n"); + err = -EIO; + goto err_irq_disable; } + gsc->proxy.started = true; return 0; + +err_irq_disable: + gsc_proxy_irq_toggle(gsc, false); + return err; } diff --git a/drivers/gpu/drm/xe/xe_gsc_types.h b/drivers/gpu/drm/xe/xe_gsc_types.h index 97c056656df0..5aaa2a75861f 100644 --- a/drivers/gpu/drm/xe/xe_gsc_types.h +++ b/drivers/gpu/drm/xe/xe_gsc_types.h @@ -58,6 +58,8 @@ struct xe_gsc { struct mutex mutex; /** @proxy.component_added: whether the component has been added */ bool component_added; + /** @proxy.started: whether the proxy has been started */ + bool started; /** @proxy.bo: object to store message to and from the GSC */ struct xe_bo *bo; /** @proxy.to_gsc: map of the memory used to send messages to the GSC */ diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h index c307a3fd9ea2..c1c615447c85 100644 --- a/drivers/gpu/drm/xe/xe_lrc.h +++ b/drivers/gpu/drm/xe/xe_lrc.h @@ -75,7 +75,8 @@ static inline struct xe_lrc *xe_lrc_get(struct xe_lrc *lrc) */ static inline void xe_lrc_put(struct xe_lrc *lrc) { - kref_put(&lrc->refcount, xe_lrc_destroy); + if (lrc) + kref_put(&lrc->refcount, xe_lrc_destroy); } /** diff --git a/drivers/gpu/drm/xe/xe_reg_sr.c b/drivers/gpu/drm/xe/xe_reg_sr.c index 2e5c78940b41..a07be161cfa2 100644 --- a/drivers/gpu/drm/xe/xe_reg_sr.c +++ b/drivers/gpu/drm/xe/xe_reg_sr.c @@ -98,10 +98,12 @@ int xe_reg_sr_add(struct xe_reg_sr *sr, *pentry = *e; ret = xa_err(xa_store(&sr->xa, idx, pentry, GFP_KERNEL)); if (ret) - goto fail; + goto fail_free; return 0; +fail_free: + kfree(pentry); fail: xe_gt_err(gt, "discarding save-restore reg %04lx (clear: %08x, set: %08x, masked: %s, mcr: %s): ret=%d\n", diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c index 248620b0901d..53d420d72164 100644 --- a/drivers/gpu/drm/xe/xe_ring_ops.c +++ b/drivers/gpu/drm/xe/xe_ring_ops.c @@ -280,6 +280,9 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc i = emit_bb_start(batch_addr, ppgtt_flag, dw, i); + /* Don't preempt fence signaling */ + dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE; + if (job->user_fence.used) { i = emit_flush_dw(dw, i); i = emit_store_imm_ppgtt_posted(job->user_fence.addr, @@ -345,6 +348,9 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc, i = emit_bb_start(batch_addr, ppgtt_flag, dw, i); + /* Don't preempt fence signaling */ + dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE; + if (job->user_fence.used) { i = emit_flush_dw(dw, i); i = emit_store_imm_ppgtt_posted(job->user_fence.addr, @@ -397,6 +403,9 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job, i = emit_bb_start(batch_addr, ppgtt_flag, dw, i); + /* Don't preempt fence signaling */ + dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE; + i = emit_render_cache_flush(job, dw, i); if (job->user_fence.used) diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c index 95bf53cc29e3..bc39a9a9790c 100644 --- a/drivers/gpu/drm/xe/xe_vm_madvise.c +++ b/drivers/gpu/drm/xe/xe_vm_madvise.c @@ -453,7 +453,7 @@ int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *fil madvise_range.num_vmas, args->atomic.val)) { err = -EINVAL; - goto madv_fini; + goto free_vmas; } } @@ -490,6 +490,7 @@ int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *fil err_fini: if (madvise_range.has_bo_vmas) drm_exec_fini(&exec); +free_vmas: kfree(madvise_range.vmas); madvise_range.vmas = NULL; madv_fini: diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c index c7b1bd79ab17..462c2fa712e0 100644 --- a/drivers/gpu/drm/xe/xe_wa.c +++ b/drivers/gpu/drm/xe/xe_wa.c @@ -241,12 +241,13 @@ static const struct xe_rtp_entry_sr gt_was[] = { { XE_RTP_NAME("16025250150"), XE_RTP_RULES(GRAPHICS_VERSION(2001)), - XE_RTP_ACTIONS(SET(LSN_VC_REG2, - LSN_LNI_WGT(1) | - LSN_LNE_WGT(1) | - LSN_DIM_X_WGT(1) | - LSN_DIM_Y_WGT(1) | - LSN_DIM_Z_WGT(1))) + XE_RTP_ACTIONS(FIELD_SET(LSN_VC_REG2, + LSN_LNI_WGT_MASK | LSN_LNE_WGT_MASK | + LSN_DIM_X_WGT_MASK | LSN_DIM_Y_WGT_MASK | + LSN_DIM_Z_WGT_MASK, + LSN_LNI_WGT(1) | LSN_LNE_WGT(1) | + LSN_DIM_X_WGT(1) | LSN_DIM_Y_WGT(1) | + LSN_DIM_Z_WGT(1))) }, /* Xe2_HPM */ diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index b949b767cf08..fc5897a6bb53 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -365,6 +365,9 @@ static const struct apple_non_apple_keyboard non_apple_keyboards[] = { { "A3R" }, { "hfd.cn" }, { "WKB603" }, + { "TH87" }, /* EPOMAKER TH87 BT mode */ + { "HFD Epomaker TH87" }, /* EPOMAKER TH87 USB mode */ + { "2.4G Wireless Receiver" }, /* EPOMAKER TH87 dongle */ }; static bool apple_is_non_apple_keyboard(struct hid_device *hdev) @@ -686,9 +689,7 @@ static const __u8 *apple_report_fixup(struct hid_device *hdev, __u8 *rdesc, hid_info(hdev, "fixing up Magic Keyboard battery report descriptor\n"); *rsize = *rsize - 1; - rdesc = kmemdup(rdesc + 1, *rsize, GFP_KERNEL); - if (!rdesc) - return NULL; + rdesc = rdesc + 1; rdesc[0] = 0x05; rdesc[1] = 0x01; diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 8ffcd12038e8..687b785e2d0c 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -1399,14 +1399,21 @@ static const __u8 *asus_report_fixup(struct hid_device *hdev, __u8 *rdesc, */ if (*rsize == rsize_orig && rdesc[offs] == 0x09 && rdesc[offs + 1] == 0x76) { - *rsize = rsize_orig + 1; - rdesc = kmemdup(rdesc, *rsize, GFP_KERNEL); - if (!rdesc) - return NULL; + __u8 *new_rdesc; + + new_rdesc = devm_kzalloc(&hdev->dev, rsize_orig + 1, + GFP_KERNEL); + if (!new_rdesc) + return rdesc; hid_info(hdev, "Fixing up %s keyb report descriptor\n", drvdata->quirks & QUIRK_T100CHI ? "T100CHI" : "T90CHI"); + + memcpy(new_rdesc, rdesc, rsize_orig); + *rsize = rsize_orig + 1; + rdesc = new_rdesc; + memmove(rdesc + offs + 4, rdesc + offs + 2, 12); rdesc[offs] = 0x19; rdesc[offs + 1] = 0x00; @@ -1490,6 +1497,9 @@ static const struct hid_device_id asus_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X), QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD | QUIRK_ROG_ALLY_XPAD }, + { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, + USB_DEVICE_ID_ASUSTEK_XGM_2023), + }, { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD), QUIRK_ROG_CLAYMORE_II_KEYBOARD }, diff --git a/drivers/hid/hid-cmedia.c b/drivers/hid/hid-cmedia.c index 6bc50df9b3e1..7b3dd4197875 100644 --- a/drivers/hid/hid-cmedia.c +++ b/drivers/hid/hid-cmedia.c @@ -99,7 +99,7 @@ static int cmhid_raw_event(struct hid_device *hid, struct hid_report *report, { struct cmhid *cm = hid_get_drvdata(hid); - if (len != CM6533_JD_RAWEV_LEN) + if (len != CM6533_JD_RAWEV_LEN || !(hid->claimed & HID_CLAIMED_INPUT)) goto out; if (memcmp(data+CM6533_JD_SFX_OFFSET, ji_sfx, sizeof(ji_sfx))) goto out; diff --git a/drivers/hid/hid-creative-sb0540.c b/drivers/hid/hid-creative-sb0540.c index b4c8e7a5d3e0..dfd6add353d1 100644 --- a/drivers/hid/hid-creative-sb0540.c +++ b/drivers/hid/hid-creative-sb0540.c @@ -153,7 +153,7 @@ static int creative_sb0540_raw_event(struct hid_device *hid, u64 code, main_code; int key; - if (len != 6) + if (len != 6 || !(hid->claimed & HID_CLAIMED_INPUT)) return 0; /* From daemons/hw_hiddev.c sb0540_rec() in lirc */ diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 3e299a30dcde..4ab7640b119a 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -229,6 +229,7 @@ #define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X 0x1b4c #define USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD 0x196b #define USB_DEVICE_ID_ASUSTEK_FX503VD_KEYBOARD 0x1869 +#define USB_DEVICE_ID_ASUSTEK_XGM_2023 0x1a9a #define USB_VENDOR_ID_ATEN 0x0557 #define USB_DEVICE_ID_ATEN_UC100KM 0x2004 diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index 91f621ceb924..9eadf3252d0d 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -990,13 +990,11 @@ static const __u8 *magicmouse_report_fixup(struct hid_device *hdev, __u8 *rdesc, */ if ((is_usb_magicmouse2(hdev->vendor, hdev->product) || is_usb_magictrackpad2(hdev->vendor, hdev->product)) && - *rsize == 83 && rdesc[46] == 0x84 && rdesc[58] == 0x85) { + *rsize >= 83 && rdesc[46] == 0x84 && rdesc[58] == 0x85) { hid_info(hdev, "fixing up magicmouse battery report descriptor\n"); *rsize = *rsize - 1; - rdesc = kmemdup(rdesc + 1, *rsize, GFP_KERNEL); - if (!rdesc) - return NULL; + rdesc = rdesc + 1; rdesc[0] = 0x05; rdesc[1] = 0x01; diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c index 33603b019f97..ef3b5c77c38e 100644 --- a/drivers/hid/hid-mcp2221.c +++ b/drivers/hid/hid-mcp2221.c @@ -353,6 +353,8 @@ static int mcp_i2c_smbus_read(struct mcp2221 *mcp, usleep_range(90, 100); retries++; } else { + usleep_range(980, 1000); + mcp_cancel_last_cmd(mcp); return ret; } } else { diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 7daa8f6d8187..b8a748bbf0fd 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -77,6 +77,7 @@ MODULE_LICENSE("GPL"); #define MT_QUIRK_ORIENTATION_INVERT BIT(22) #define MT_QUIRK_APPLE_TOUCHBAR BIT(23) #define MT_QUIRK_YOGABOOK9I BIT(24) +#define MT_QUIRK_KEEP_LATENCY_ON_CLOSE BIT(25) #define MT_INPUTMODE_TOUCHSCREEN 0x02 #define MT_INPUTMODE_TOUCHPAD 0x03 @@ -214,6 +215,7 @@ static void mt_post_parse(struct mt_device *td, struct mt_application *app); #define MT_CLS_WIN_8_DISABLE_WAKEUP 0x0016 #define MT_CLS_WIN_8_NO_STICKY_FINGERS 0x0017 #define MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU 0x0018 +#define MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE 0x0019 /* vendor specific classes */ #define MT_CLS_3M 0x0101 @@ -233,6 +235,7 @@ static void mt_post_parse(struct mt_device *td, struct mt_application *app); #define MT_CLS_SMART_TECH 0x0113 #define MT_CLS_APPLE_TOUCHBAR 0x0114 #define MT_CLS_YOGABOOK9I 0x0115 +#define MT_CLS_EGALAX_P80H84 0x0116 #define MT_CLS_SIS 0x0457 #define MT_DEFAULT_MAXCONTACT 10 @@ -334,6 +337,15 @@ static const struct mt_class mt_classes[] = { MT_QUIRK_CONTACT_CNT_ACCURATE | MT_QUIRK_WIN8_PTP_BUTTONS, .export_all_inputs = true }, + { .name = MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE, + .quirks = MT_QUIRK_ALWAYS_VALID | + MT_QUIRK_IGNORE_DUPLICATES | + MT_QUIRK_HOVERING | + MT_QUIRK_CONTACT_CNT_ACCURATE | + MT_QUIRK_STICKY_FINGERS | + MT_QUIRK_WIN8_PTP_BUTTONS | + MT_QUIRK_KEEP_LATENCY_ON_CLOSE, + .export_all_inputs = true }, /* * vendor specific classes @@ -438,6 +450,11 @@ static const struct mt_class mt_classes[] = { MT_QUIRK_YOGABOOK9I, .export_all_inputs = true }, + { .name = MT_CLS_EGALAX_P80H84, + .quirks = MT_QUIRK_ALWAYS_VALID | + MT_QUIRK_IGNORE_DUPLICATES | + MT_QUIRK_CONTACT_CNT_ACCURATE, + }, { } }; @@ -849,7 +866,8 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi, if ((cls->name == MT_CLS_WIN_8 || cls->name == MT_CLS_WIN_8_FORCE_MULTI_INPUT || cls->name == MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU || - cls->name == MT_CLS_WIN_8_DISABLE_WAKEUP) && + cls->name == MT_CLS_WIN_8_DISABLE_WAKEUP || + cls->name == MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE) && (field->application == HID_DG_TOUCHPAD || field->application == HID_DG_TOUCHSCREEN)) app->quirks |= MT_QUIRK_CONFIDENCE; @@ -1762,7 +1780,8 @@ static int mt_input_configured(struct hid_device *hdev, struct hid_input *hi) int ret; if (td->is_haptic_touchpad && (td->mtclass.name == MT_CLS_WIN_8 || - td->mtclass.name == MT_CLS_WIN_8_FORCE_MULTI_INPUT)) { + td->mtclass.name == MT_CLS_WIN_8_FORCE_MULTI_INPUT || + td->mtclass.name == MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE)) { if (hid_haptic_input_configured(hdev, td->haptic, hi) == 0) td->is_haptic_touchpad = false; } else { @@ -2075,7 +2094,12 @@ static void mt_on_hid_hw_open(struct hid_device *hdev) static void mt_on_hid_hw_close(struct hid_device *hdev) { - mt_set_modes(hdev, HID_LATENCY_HIGH, TOUCHPAD_REPORT_NONE); + struct mt_device *td = hid_get_drvdata(hdev); + + if (td->mtclass.quirks & MT_QUIRK_KEEP_LATENCY_ON_CLOSE) + mt_set_modes(hdev, HID_LATENCY_NORMAL, TOUCHPAD_REPORT_NONE); + else + mt_set_modes(hdev, HID_LATENCY_HIGH, TOUCHPAD_REPORT_NONE); } /* @@ -2215,8 +2239,9 @@ static const struct hid_device_id mt_devices[] = { { .driver_data = MT_CLS_EGALAX_SERIAL, MT_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C000) }, - { .driver_data = MT_CLS_EGALAX, - MT_USB_DEVICE(USB_VENDOR_ID_DWAV, + { .driver_data = MT_CLS_EGALAX_P80H84, + HID_DEVICE(HID_BUS_ANY, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002) }, /* Elan devices */ @@ -2461,6 +2486,14 @@ static const struct hid_device_id mt_devices[] = { MT_USB_DEVICE(USB_VENDOR_ID_UNITEC, USB_DEVICE_ID_UNITEC_USB_TOUCH_0A19) }, + /* Uniwill touchpads */ + { .driver_data = MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE, + HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_PIXART, 0x0255) }, + { .driver_data = MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE, + HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_PIXART, 0x0274) }, + /* VTL panels */ { .driver_data = MT_CLS_VTL, MT_USB_DEVICE(USB_VENDOR_ID_VTL, diff --git a/drivers/hid/hid-zydacron.c b/drivers/hid/hid-zydacron.c index 3bdb26f45592..1aae80f848f5 100644 --- a/drivers/hid/hid-zydacron.c +++ b/drivers/hid/hid-zydacron.c @@ -114,7 +114,7 @@ static int zc_raw_event(struct hid_device *hdev, struct hid_report *report, unsigned key; unsigned short index; - if (report->id == data[0]) { + if (report->id == data[0] && (hdev->claimed & HID_CLAIMED_INPUT)) { /* break keys */ for (index = 0; index < 4; index++) { diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h index fa5d68c36313..27389971b96c 100644 --- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h +++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h @@ -39,6 +39,8 @@ #define PCI_DEVICE_ID_INTEL_ISH_PTL_H 0xE345 #define PCI_DEVICE_ID_INTEL_ISH_PTL_P 0xE445 #define PCI_DEVICE_ID_INTEL_ISH_WCL 0x4D45 +#define PCI_DEVICE_ID_INTEL_ISH_NVL_H 0xD354 +#define PCI_DEVICE_ID_INTEL_ISH_NVL_S 0x6E78 #define REVISION_ID_CHT_A0 0x6 #define REVISION_ID_CHT_Ax_SI 0x0 diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index 1612e8cb23f0..ed3405c05e73 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -28,11 +28,15 @@ enum ishtp_driver_data_index { ISHTP_DRIVER_DATA_LNL_M, ISHTP_DRIVER_DATA_PTL, ISHTP_DRIVER_DATA_WCL, + ISHTP_DRIVER_DATA_NVL_H, + ISHTP_DRIVER_DATA_NVL_S, }; #define ISH_FW_GEN_LNL_M "lnlm" #define ISH_FW_GEN_PTL "ptl" #define ISH_FW_GEN_WCL "wcl" +#define ISH_FW_GEN_NVL_H "nvlh" +#define ISH_FW_GEN_NVL_S "nvls" #define ISH_FIRMWARE_PATH(gen) "intel/ish/ish_" gen ".bin" #define ISH_FIRMWARE_PATH_ALL "intel/ish/ish_*.bin" @@ -47,6 +51,12 @@ static struct ishtp_driver_data ishtp_driver_data[] = { [ISHTP_DRIVER_DATA_WCL] = { .fw_generation = ISH_FW_GEN_WCL, }, + [ISHTP_DRIVER_DATA_NVL_H] = { + .fw_generation = ISH_FW_GEN_NVL_H, + }, + [ISHTP_DRIVER_DATA_NVL_S] = { + .fw_generation = ISH_FW_GEN_NVL_S, + }, }; static const struct pci_device_id ish_pci_tbl[] = { @@ -76,6 +86,8 @@ static const struct pci_device_id ish_pci_tbl[] = { {PCI_DEVICE_DATA(INTEL, ISH_PTL_H, ISHTP_DRIVER_DATA_PTL)}, {PCI_DEVICE_DATA(INTEL, ISH_PTL_P, ISHTP_DRIVER_DATA_PTL)}, {PCI_DEVICE_DATA(INTEL, ISH_WCL, ISHTP_DRIVER_DATA_WCL)}, + {PCI_DEVICE_DATA(INTEL, ISH_NVL_H, ISHTP_DRIVER_DATA_NVL_H)}, + {PCI_DEVICE_DATA(INTEL, ISH_NVL_S, ISHTP_DRIVER_DATA_NVL_S)}, {} }; MODULE_DEVICE_TABLE(pci, ish_pci_tbl); diff --git a/drivers/hid/usbhid/hid-pidff.c b/drivers/hid/usbhid/hid-pidff.c index fdcf03408f47..fbf3dbc92e66 100644 --- a/drivers/hid/usbhid/hid-pidff.c +++ b/drivers/hid/usbhid/hid-pidff.c @@ -1452,10 +1452,13 @@ static int pidff_init_fields(struct pidff_device *pidff, struct input_dev *dev) hid_warn(pidff->hid, "unknown ramp effect layout\n"); if (PIDFF_FIND_FIELDS(set_condition, PID_SET_CONDITION, 1)) { - if (test_and_clear_bit(FF_SPRING, dev->ffbit) || - test_and_clear_bit(FF_DAMPER, dev->ffbit) || - test_and_clear_bit(FF_FRICTION, dev->ffbit) || - test_and_clear_bit(FF_INERTIA, dev->ffbit)) + bool test = false; + + test |= test_and_clear_bit(FF_SPRING, dev->ffbit); + test |= test_and_clear_bit(FF_DAMPER, dev->ffbit); + test |= test_and_clear_bit(FF_FRICTION, dev->ffbit); + test |= test_and_clear_bit(FF_INERTIA, dev->ffbit); + if (test) hid_warn(pidff->hid, "unknown condition effect layout\n"); } diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 41c381764c2b..486152a8ea77 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -1927,16 +1927,6 @@ config SENSORS_RASPBERRYPI_HWMON This driver can also be built as a module. If so, the module will be called raspberrypi-hwmon. -config SENSORS_SA67MCU - tristate "Kontron sa67mcu hardware monitoring driver" - depends on MFD_SL28CPLD || COMPILE_TEST - help - If you say yes here you get support for the voltage and temperature - monitor of the sa67 board management controller. - - This driver can also be built as a module. If so, the module - will be called sa67mcu-hwmon. - config SENSORS_SL28CPLD tristate "Kontron sl28cpld hardware monitoring driver" depends on MFD_SL28CPLD || COMPILE_TEST diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile index eade8e3b1bde..5833c807c688 100644 --- a/drivers/hwmon/Makefile +++ b/drivers/hwmon/Makefile @@ -199,7 +199,6 @@ obj-$(CONFIG_SENSORS_PT5161L) += pt5161l.o obj-$(CONFIG_SENSORS_PWM_FAN) += pwm-fan.o obj-$(CONFIG_SENSORS_QNAP_MCU_HWMON) += qnap-mcu-hwmon.o obj-$(CONFIG_SENSORS_RASPBERRYPI_HWMON) += raspberrypi-hwmon.o -obj-$(CONFIG_SENSORS_SA67MCU) += sa67mcu-hwmon.o obj-$(CONFIG_SENSORS_SBTSI) += sbtsi_temp.o obj-$(CONFIG_SENSORS_SBRMI) += sbrmi.o obj-$(CONFIG_SENSORS_SCH56XX_COMMON)+= sch56xx-common.o diff --git a/drivers/hwmon/aht10.c b/drivers/hwmon/aht10.c index 007befdba977..4ce019d2cc80 100644 --- a/drivers/hwmon/aht10.c +++ b/drivers/hwmon/aht10.c @@ -37,7 +37,9 @@ #define AHT10_CMD_MEAS 0b10101100 #define AHT10_CMD_RST 0b10111010 -#define DHT20_CMD_INIT 0x71 +#define AHT20_CMD_INIT 0b10111110 + +#define DHT20_CMD_INIT 0b01110001 /* * Flags in the answer byte/command @@ -341,7 +343,7 @@ static int aht10_probe(struct i2c_client *client) data->meas_size = AHT20_MEAS_SIZE; data->crc8 = true; crc8_populate_msb(crc8_table, AHT20_CRC8_POLY); - data->init_cmd = AHT10_CMD_INIT; + data->init_cmd = AHT20_CMD_INIT; break; case dht20: data->meas_size = AHT20_MEAS_SIZE; diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c index e233aafa8856..5cfb98a0512f 100644 --- a/drivers/hwmon/it87.c +++ b/drivers/hwmon/it87.c @@ -3590,10 +3590,13 @@ static int it87_resume(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct it87_data *data = dev_get_drvdata(dev); + int err; it87_resume_sio(pdev); - it87_lock(data); + err = it87_lock(data); + if (err) + return err; it87_check_pwm(dev); it87_check_limit_regs(data); diff --git a/drivers/hwmon/macsmc-hwmon.c b/drivers/hwmon/macsmc-hwmon.c index 1c0bbec7e8eb..1500ec2cc9f8 100644 --- a/drivers/hwmon/macsmc-hwmon.c +++ b/drivers/hwmon/macsmc-hwmon.c @@ -22,6 +22,7 @@ #include #include +#include #include #include #include @@ -130,7 +131,7 @@ static int macsmc_hwmon_read_ioft_scaled(struct apple_smc *smc, smc_key key, if (ret < 0) return ret; - *p = mult_frac(val, scale, 65536); + *p = mul_u64_u32_div(val, scale, 65536); return 0; } @@ -140,7 +141,7 @@ static int macsmc_hwmon_read_ioft_scaled(struct apple_smc *smc, smc_key key, * them. */ static int macsmc_hwmon_read_f32_scaled(struct apple_smc *smc, smc_key key, - int *p, int scale) + long *p, int scale) { u32 fval; u64 val; @@ -162,21 +163,21 @@ static int macsmc_hwmon_read_f32_scaled(struct apple_smc *smc, smc_key key, val = 0; else if (exp < 0) val >>= -exp; - else if (exp != 0 && (val & ~((1UL << (64 - exp)) - 1))) /* overflow */ + else if (exp != 0 && (val & ~((1ULL << (64 - exp)) - 1))) /* overflow */ val = U64_MAX; else val <<= exp; if (fval & FLT_SIGN_MASK) { - if (val > (-(s64)INT_MIN)) - *p = INT_MIN; + if (val > (u64)LONG_MAX + 1) + *p = LONG_MIN; else - *p = -val; + *p = -(long)val; } else { - if (val > INT_MAX) - *p = INT_MAX; + if (val > (u64)LONG_MAX) + *p = LONG_MAX; else - *p = val; + *p = (long)val; } return 0; @@ -195,7 +196,7 @@ static int macsmc_hwmon_read_key(struct apple_smc *smc, switch (sensor->info.type_code) { /* 32-bit IEEE 754 float */ case __SMC_KEY('f', 'l', 't', ' '): { - u32 flt_ = 0; + long flt_ = 0; ret = macsmc_hwmon_read_f32_scaled(smc, sensor->macsmc_key, &flt_, scale); @@ -214,7 +215,10 @@ static int macsmc_hwmon_read_key(struct apple_smc *smc, if (ret) return ret; - *val = (long)ioft; + if (ioft > LONG_MAX) + *val = LONG_MAX; + else + *val = (long)ioft; break; } default: @@ -224,29 +228,26 @@ static int macsmc_hwmon_read_key(struct apple_smc *smc, return 0; } -static int macsmc_hwmon_write_f32(struct apple_smc *smc, smc_key key, int value) +static int macsmc_hwmon_write_f32(struct apple_smc *smc, smc_key key, long value) { u64 val; u32 fval = 0; - int exp = 0, neg; + int exp, neg; + neg = value < 0; val = abs(value); - neg = val != value; if (val) { - int msb = __fls(val) - exp; + exp = __fls(val); - if (msb > 23) { - val >>= msb - FLT_MANT_BIAS; - exp -= msb - FLT_MANT_BIAS; - } else if (msb < 23) { - val <<= FLT_MANT_BIAS - msb; - exp += msb; - } + if (exp > 23) + val >>= exp - 23; + else + val <<= 23 - exp; fval = FIELD_PREP(FLT_SIGN_MASK, neg) | FIELD_PREP(FLT_EXP_MASK, exp + FLT_EXP_BIAS) | - FIELD_PREP(FLT_MANT_MASK, val); + FIELD_PREP(FLT_MANT_MASK, val & FLT_MANT_MASK); } return apple_smc_write_u32(smc, key, fval); @@ -663,8 +664,8 @@ static int macsmc_hwmon_populate_sensors(struct macsmc_hwmon *hwmon, if (!hwmon->volt.sensors) return -ENOMEM; - for_each_child_of_node_with_prefix(hwmon_node, key_node, "volt-") { - sensor = &hwmon->temp.sensors[hwmon->temp.count]; + for_each_child_of_node_with_prefix(hwmon_node, key_node, "voltage-") { + sensor = &hwmon->volt.sensors[hwmon->volt.count]; if (!macsmc_hwmon_create_sensor(hwmon->dev, hwmon->smc, key_node, sensor)) { sensor->attrs = HWMON_I_INPUT; diff --git a/drivers/hwmon/max6639.c b/drivers/hwmon/max6639.c index a0a1dbbda887..9a3c515efe2e 100644 --- a/drivers/hwmon/max6639.c +++ b/drivers/hwmon/max6639.c @@ -607,7 +607,7 @@ static int max6639_init_client(struct i2c_client *client, return err; /* Fans PWM polarity high by default */ - err = regmap_write(data->regmap, MAX6639_REG_FAN_CONFIG2a(i), 0x00); + err = regmap_write(data->regmap, MAX6639_REG_FAN_CONFIG2a(i), 0x02); if (err) return err; diff --git a/drivers/hwmon/pmbus/q54sj108a2.c b/drivers/hwmon/pmbus/q54sj108a2.c index fc030ca34480..d5d60a9af8c5 100644 --- a/drivers/hwmon/pmbus/q54sj108a2.c +++ b/drivers/hwmon/pmbus/q54sj108a2.c @@ -79,7 +79,8 @@ static ssize_t q54sj108a2_debugfs_read(struct file *file, char __user *buf, int idx = *idxp; struct q54sj108a2_data *psu = to_psu(idxp, idx); char data[I2C_SMBUS_BLOCK_MAX + 2] = { 0 }; - char data_char[I2C_SMBUS_BLOCK_MAX + 2] = { 0 }; + char data_char[I2C_SMBUS_BLOCK_MAX * 2 + 2] = { 0 }; + char *out = data; char *res; switch (idx) { @@ -150,27 +151,27 @@ static ssize_t q54sj108a2_debugfs_read(struct file *file, char __user *buf, if (rc < 0) return rc; - res = bin2hex(data, data_char, 32); - rc = res - data; - + res = bin2hex(data_char, data, rc); + rc = res - data_char; + out = data_char; break; case Q54SJ108A2_DEBUGFS_FLASH_KEY: rc = i2c_smbus_read_block_data(psu->client, PMBUS_FLASH_KEY_WRITE, data); if (rc < 0) return rc; - res = bin2hex(data, data_char, 4); - rc = res - data; - + res = bin2hex(data_char, data, rc); + rc = res - data_char; + out = data_char; break; default: return -EINVAL; } - data[rc] = '\n'; + out[rc] = '\n'; rc += 2; - return simple_read_from_buffer(buf, count, ppos, data, rc); + return simple_read_from_buffer(buf, count, ppos, out, rc); } static ssize_t q54sj108a2_debugfs_write(struct file *file, const char __user *buf, diff --git a/drivers/hwmon/sa67mcu-hwmon.c b/drivers/hwmon/sa67mcu-hwmon.c deleted file mode 100644 index 22f703b7b256..000000000000 --- a/drivers/hwmon/sa67mcu-hwmon.c +++ /dev/null @@ -1,161 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * sl67mcu hardware monitoring driver - * - * Copyright 2025 Kontron Europe GmbH - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#define SA67MCU_VOLTAGE(n) (0x00 + ((n) * 2)) -#define SA67MCU_TEMP(n) (0x04 + ((n) * 2)) - -struct sa67mcu_hwmon { - struct regmap *regmap; - u32 offset; -}; - -static int sa67mcu_hwmon_read(struct device *dev, - enum hwmon_sensor_types type, u32 attr, - int channel, long *input) -{ - struct sa67mcu_hwmon *hwmon = dev_get_drvdata(dev); - unsigned int offset; - u8 reg[2]; - int ret; - - switch (type) { - case hwmon_in: - switch (attr) { - case hwmon_in_input: - offset = hwmon->offset + SA67MCU_VOLTAGE(channel); - break; - default: - return -EOPNOTSUPP; - } - break; - case hwmon_temp: - switch (attr) { - case hwmon_temp_input: - offset = hwmon->offset + SA67MCU_TEMP(channel); - break; - default: - return -EOPNOTSUPP; - } - break; - default: - return -EOPNOTSUPP; - } - - /* Reading the low byte will capture the value */ - ret = regmap_bulk_read(hwmon->regmap, offset, reg, ARRAY_SIZE(reg)); - if (ret) - return ret; - - *input = reg[1] << 8 | reg[0]; - - /* Temperatures are s16 and in 0.1degC steps. */ - if (type == hwmon_temp) - *input = sign_extend32(*input, 15) * 100; - - return 0; -} - -static const struct hwmon_channel_info * const sa67mcu_hwmon_info[] = { - HWMON_CHANNEL_INFO(in, - HWMON_I_INPUT | HWMON_I_LABEL, - HWMON_I_INPUT | HWMON_I_LABEL), - HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT), - NULL -}; - -static const char *const sa67mcu_hwmon_in_labels[] = { - "VDDIN", - "VDD_RTC", -}; - -static int sa67mcu_hwmon_read_string(struct device *dev, - enum hwmon_sensor_types type, u32 attr, - int channel, const char **str) -{ - switch (type) { - case hwmon_in: - switch (attr) { - case hwmon_in_label: - *str = sa67mcu_hwmon_in_labels[channel]; - return 0; - default: - return -EOPNOTSUPP; - } - default: - return -EOPNOTSUPP; - } -} - -static const struct hwmon_ops sa67mcu_hwmon_ops = { - .visible = 0444, - .read = sa67mcu_hwmon_read, - .read_string = sa67mcu_hwmon_read_string, -}; - -static const struct hwmon_chip_info sa67mcu_hwmon_chip_info = { - .ops = &sa67mcu_hwmon_ops, - .info = sa67mcu_hwmon_info, -}; - -static int sa67mcu_hwmon_probe(struct platform_device *pdev) -{ - struct sa67mcu_hwmon *hwmon; - struct device *hwmon_dev; - int ret; - - if (!pdev->dev.parent) - return -ENODEV; - - hwmon = devm_kzalloc(&pdev->dev, sizeof(*hwmon), GFP_KERNEL); - if (!hwmon) - return -ENOMEM; - - hwmon->regmap = dev_get_regmap(pdev->dev.parent, NULL); - if (!hwmon->regmap) - return -ENODEV; - - ret = device_property_read_u32(&pdev->dev, "reg", &hwmon->offset); - if (ret) - return -EINVAL; - - hwmon_dev = devm_hwmon_device_register_with_info(&pdev->dev, - "sa67mcu_hwmon", hwmon, - &sa67mcu_hwmon_chip_info, - NULL); - if (IS_ERR(hwmon_dev)) - dev_err(&pdev->dev, "failed to register as hwmon device"); - - return PTR_ERR_OR_ZERO(hwmon_dev); -} - -static const struct of_device_id sa67mcu_hwmon_of_match[] = { - { .compatible = "kontron,sa67mcu-hwmon", }, - {} -}; -MODULE_DEVICE_TABLE(of, sa67mcu_hwmon_of_match); - -static struct platform_driver sa67mcu_hwmon_driver = { - .probe = sa67mcu_hwmon_probe, - .driver = { - .name = "sa67mcu-hwmon", - .of_match_table = sa67mcu_hwmon_of_match, - }, -}; -module_platform_driver(sa67mcu_hwmon_driver); - -MODULE_DESCRIPTION("sa67mcu Hardware Monitoring Driver"); -MODULE_AUTHOR("Michael Walle "); -MODULE_LICENSE("GPL"); diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c index 8bb8dd34c223..a2159b2bc176 100644 --- a/drivers/media/dvb-core/dvb_net.c +++ b/drivers/media/dvb-core/dvb_net.c @@ -228,6 +228,9 @@ static int handle_one_ule_extension( struct dvb_net_priv *p ) unsigned char hlen = (p->ule_sndu_type & 0x0700) >> 8; unsigned char htype = p->ule_sndu_type & 0x00FF; + if (htype >= ARRAY_SIZE(ule_mandatory_ext_handlers)) + return -1; + /* Discriminate mandatory and optional extension headers. */ if (hlen == 0) { /* Mandatory extension header */ diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index a1de08ee3815..14ed91391fcc 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -324,7 +324,7 @@ static bool bond_sk_check(struct bonding *bond) } } -bool bond_xdp_check(struct bonding *bond, int mode) +bool __bond_xdp_check(int mode, int xmit_policy) { switch (mode) { case BOND_MODE_ROUNDROBIN: @@ -335,7 +335,7 @@ bool bond_xdp_check(struct bonding *bond, int mode) /* vlan+srcmac is not supported with XDP as in most cases the 802.1q * payload is not in the packet due to hardware offload. */ - if (bond->params.xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC) + if (xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC) return true; fallthrough; default: @@ -343,6 +343,11 @@ bool bond_xdp_check(struct bonding *bond, int mode) } } +bool bond_xdp_check(struct bonding *bond, int mode) +{ + return __bond_xdp_check(mode, bond->params.xmit_policy); +} + /*---------------------------------- VLAN -----------------------------------*/ /* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid, diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index dcee384c2f06..7380cc4ee75a 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1575,6 +1575,8 @@ static int bond_option_fail_over_mac_set(struct bonding *bond, static int bond_option_xmit_hash_policy_set(struct bonding *bond, const struct bond_opt_value *newval) { + if (bond->xdp_prog && !__bond_xdp_check(BOND_MODE(bond), newval->value)) + return -EOPNOTSUPP; netdev_dbg(bond->dev, "Setting xmit hash policy to %s (%llu)\n", newval->string, newval->value); bond->params.xmit_policy = newval->value; diff --git a/drivers/net/can/dummy_can.c b/drivers/net/can/dummy_can.c index 41953655e3d3..cd23de488edc 100644 --- a/drivers/net/can/dummy_can.c +++ b/drivers/net/can/dummy_can.c @@ -241,6 +241,7 @@ static int __init dummy_can_init(void) dev->netdev_ops = &dummy_can_netdev_ops; dev->ethtool_ops = &dummy_can_ethtool_ops; + dev->flags |= IFF_ECHO; /* enable echo handling */ priv = netdev_priv(dev); priv->can.bittiming_const = &dummy_can_bittiming_const; priv->can.bitrate_max = 20 * MEGA /* BPS */; diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index fa97adf25b73..bb7782582f40 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -1214,6 +1214,7 @@ static int mcp251x_open(struct net_device *net) { struct mcp251x_priv *priv = netdev_priv(net); struct spi_device *spi = priv->spi; + bool release_irq = false; unsigned long flags = 0; int ret; @@ -1257,12 +1258,24 @@ static int mcp251x_open(struct net_device *net) return 0; out_free_irq: - free_irq(spi->irq, priv); + /* The IRQ handler might be running, and if so it will be waiting + * for the lock. But free_irq() must wait for the handler to finish + * so calling it here would deadlock. + * + * Setting priv->force_quit will let the handler exit right away + * without any access to the hardware. This make it safe to call + * free_irq() after the lock is released. + */ + priv->force_quit = 1; + release_irq = true; + mcp251x_hw_sleep(spi); out_close: mcp251x_power_enable(priv->transceiver, 0); close_candev(net); mutex_unlock(&priv->mcp_lock); + if (release_irq) + free_irq(spi->irq, priv); return ret; } diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index 4c219a5b139b..9b25dda7c183 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -445,6 +445,11 @@ static void ems_usb_read_bulk_callback(struct urb *urb) start = CPC_HEADER_SIZE; while (msg_count) { + if (start + CPC_MSG_HEADER_LEN > urb->actual_length) { + netdev_err(netdev, "format error\n"); + break; + } + msg = (struct ems_cpc_msg *)&ibuf[start]; switch (msg->type) { @@ -474,7 +479,7 @@ static void ems_usb_read_bulk_callback(struct urb *urb) start += CPC_MSG_HEADER_LEN + msg->length; msg_count--; - if (start > urb->transfer_buffer_length) { + if (start > urb->actual_length) { netdev_err(netdev, "format error\n"); break; } diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c index 2892a68f510a..d257440fa01f 100644 --- a/drivers/net/can/usb/esd_usb.c +++ b/drivers/net/can/usb/esd_usb.c @@ -272,6 +272,9 @@ struct esd_usb { struct usb_anchor rx_submitted; + unsigned int rx_pipe; + unsigned int tx_pipe; + int net_count; u32 version; int rxinitdone; @@ -537,7 +540,7 @@ static void esd_usb_read_bulk_callback(struct urb *urb) } resubmit_urb: - usb_fill_bulk_urb(urb, dev->udev, usb_rcvbulkpipe(dev->udev, 1), + usb_fill_bulk_urb(urb, dev->udev, dev->rx_pipe, urb->transfer_buffer, ESD_USB_RX_BUFFER_SIZE, esd_usb_read_bulk_callback, dev); @@ -626,9 +629,7 @@ static int esd_usb_send_msg(struct esd_usb *dev, union esd_usb_msg *msg) { int actual_length; - return usb_bulk_msg(dev->udev, - usb_sndbulkpipe(dev->udev, 2), - msg, + return usb_bulk_msg(dev->udev, dev->tx_pipe, msg, msg->hdr.len * sizeof(u32), /* convert to # of bytes */ &actual_length, 1000); @@ -639,12 +640,8 @@ static int esd_usb_wait_msg(struct esd_usb *dev, { int actual_length; - return usb_bulk_msg(dev->udev, - usb_rcvbulkpipe(dev->udev, 1), - msg, - sizeof(*msg), - &actual_length, - 1000); + return usb_bulk_msg(dev->udev, dev->rx_pipe, msg, + sizeof(*msg), &actual_length, 1000); } static int esd_usb_setup_rx_urbs(struct esd_usb *dev) @@ -677,8 +674,7 @@ static int esd_usb_setup_rx_urbs(struct esd_usb *dev) urb->transfer_dma = buf_dma; - usb_fill_bulk_urb(urb, dev->udev, - usb_rcvbulkpipe(dev->udev, 1), + usb_fill_bulk_urb(urb, dev->udev, dev->rx_pipe, buf, ESD_USB_RX_BUFFER_SIZE, esd_usb_read_bulk_callback, dev); urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; @@ -903,7 +899,7 @@ static netdev_tx_t esd_usb_start_xmit(struct sk_buff *skb, /* hnd must not be 0 - MSB is stripped in txdone handling */ msg->tx.hnd = BIT(31) | i; /* returned in TX done message */ - usb_fill_bulk_urb(urb, dev->udev, usb_sndbulkpipe(dev->udev, 2), buf, + usb_fill_bulk_urb(urb, dev->udev, dev->tx_pipe, buf, msg->hdr.len * sizeof(u32), /* convert to # of bytes */ esd_usb_write_bulk_callback, context); @@ -1298,10 +1294,16 @@ done: static int esd_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) { + struct usb_endpoint_descriptor *ep_in, *ep_out; struct esd_usb *dev; union esd_usb_msg *msg; int i, err; + err = usb_find_common_endpoints(intf->cur_altsetting, &ep_in, &ep_out, + NULL, NULL); + if (err) + return err; + dev = kzalloc_obj(*dev); if (!dev) { err = -ENOMEM; @@ -1309,6 +1311,8 @@ static int esd_usb_probe(struct usb_interface *intf, } dev->udev = interface_to_usbdev(intf); + dev->rx_pipe = usb_rcvbulkpipe(dev->udev, ep_in->bEndpointAddress); + dev->tx_pipe = usb_sndbulkpipe(dev->udev, ep_out->bEndpointAddress); init_usb_anchor(&dev->rx_submitted); diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c index 2d248deb69dc..b259f6109808 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_core.c +++ b/drivers/net/can/usb/etas_es58x/es58x_core.c @@ -1461,12 +1461,18 @@ static void es58x_read_bulk_callback(struct urb *urb) } resubmit_urb: + usb_anchor_urb(urb, &es58x_dev->rx_urbs); ret = usb_submit_urb(urb, GFP_ATOMIC); + if (!ret) + return; + + usb_unanchor_urb(urb); + if (ret == -ENODEV) { for (i = 0; i < es58x_dev->num_can_ch; i++) if (es58x_dev->netdev[i]) netif_device_detach(es58x_dev->netdev[i]); - } else if (ret) + } else dev_err_ratelimited(dev, "Failed resubmitting read bulk urb: %pe\n", ERR_PTR(ret)); diff --git a/drivers/net/can/usb/f81604.c b/drivers/net/can/usb/f81604.c index 76578063ac82..f12318268e46 100644 --- a/drivers/net/can/usb/f81604.c +++ b/drivers/net/can/usb/f81604.c @@ -413,6 +413,7 @@ static void f81604_read_bulk_callback(struct urb *urb) { struct f81604_can_frame *frame = urb->transfer_buffer; struct net_device *netdev = urb->context; + struct f81604_port_priv *priv = netdev_priv(netdev); int ret; if (!netif_device_present(netdev)) @@ -445,10 +446,15 @@ static void f81604_read_bulk_callback(struct urb *urb) f81604_process_rx_packet(netdev, frame); resubmit_urb: + usb_anchor_urb(urb, &priv->urbs_anchor); ret = usb_submit_urb(urb, GFP_ATOMIC); + if (!ret) + return; + usb_unanchor_urb(urb); + if (ret == -ENODEV) netif_device_detach(netdev); - else if (ret) + else netdev_err(netdev, "%s: failed to resubmit read bulk urb: %pe\n", __func__, ERR_PTR(ret)); @@ -620,6 +626,12 @@ static void f81604_read_int_callback(struct urb *urb) netdev_info(netdev, "%s: Int URB aborted: %pe\n", __func__, ERR_PTR(urb->status)); + if (urb->actual_length < sizeof(*data)) { + netdev_warn(netdev, "%s: short int URB: %u < %zu\n", + __func__, urb->actual_length, sizeof(*data)); + goto resubmit_urb; + } + switch (urb->status) { case 0: /* success */ break; @@ -646,10 +658,15 @@ static void f81604_read_int_callback(struct urb *urb) f81604_handle_tx(priv, data); resubmit_urb: + usb_anchor_urb(urb, &priv->urbs_anchor); ret = usb_submit_urb(urb, GFP_ATOMIC); + if (!ret) + return; + usb_unanchor_urb(urb); + if (ret == -ENODEV) netif_device_detach(netdev); - else if (ret) + else netdev_err(netdev, "%s: failed to resubmit int urb: %pe\n", __func__, ERR_PTR(ret)); } @@ -874,9 +891,27 @@ static void f81604_write_bulk_callback(struct urb *urb) if (!netif_device_present(netdev)) return; - if (urb->status) - netdev_info(netdev, "%s: Tx URB error: %pe\n", __func__, - ERR_PTR(urb->status)); + if (!urb->status) + return; + + switch (urb->status) { + case -ENOENT: + case -ECONNRESET: + case -ESHUTDOWN: + return; + default: + break; + } + + if (net_ratelimit()) + netdev_err(netdev, "%s: Tx URB error: %pe\n", __func__, + ERR_PTR(urb->status)); + + can_free_echo_skb(netdev, 0, NULL); + netdev->stats.tx_dropped++; + netdev->stats.tx_errors++; + + netif_wake_queue(netdev); } static void f81604_clear_reg_work(struct work_struct *work) diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 9d27d6f0c0b5..ec9a7cbbbc69 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -772,9 +772,8 @@ device_detach: } } -static int gs_usb_set_bittiming(struct net_device *netdev) +static int gs_usb_set_bittiming(struct gs_can *dev) { - struct gs_can *dev = netdev_priv(netdev); struct can_bittiming *bt = &dev->can.bittiming; struct gs_device_bittiming dbt = { .prop_seg = cpu_to_le32(bt->prop_seg), @@ -791,9 +790,8 @@ static int gs_usb_set_bittiming(struct net_device *netdev) GFP_KERNEL); } -static int gs_usb_set_data_bittiming(struct net_device *netdev) +static int gs_usb_set_data_bittiming(struct gs_can *dev) { - struct gs_can *dev = netdev_priv(netdev); struct can_bittiming *bt = &dev->can.fd.data_bittiming; struct gs_device_bittiming dbt = { .prop_seg = cpu_to_le32(bt->prop_seg), @@ -1057,6 +1055,20 @@ static int gs_can_open(struct net_device *netdev) if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) flags |= GS_CAN_MODE_HW_TIMESTAMP; + rc = gs_usb_set_bittiming(dev); + if (rc) { + netdev_err(netdev, "failed to set bittiming: %pe\n", ERR_PTR(rc)); + goto out_usb_kill_anchored_urbs; + } + + if (ctrlmode & CAN_CTRLMODE_FD) { + rc = gs_usb_set_data_bittiming(dev); + if (rc) { + netdev_err(netdev, "failed to set data bittiming: %pe\n", ERR_PTR(rc)); + goto out_usb_kill_anchored_urbs; + } + } + /* finally start device */ dev->can.state = CAN_STATE_ERROR_ACTIVE; dm.flags = cpu_to_le32(flags); @@ -1370,7 +1382,6 @@ static struct gs_can *gs_make_candev(unsigned int channel, dev->can.state = CAN_STATE_STOPPED; dev->can.clock.freq = le32_to_cpu(bt_const.fclk_can); dev->can.bittiming_const = &dev->bt_const; - dev->can.do_set_bittiming = gs_usb_set_bittiming; dev->can.ctrlmode_supported = CAN_CTRLMODE_CC_LEN8_DLC; @@ -1394,7 +1405,6 @@ static struct gs_can *gs_make_candev(unsigned int channel, * GS_CAN_FEATURE_BT_CONST_EXT is set. */ dev->can.fd.data_bittiming_const = &dev->bt_const; - dev->can.fd.do_set_data_bittiming = gs_usb_set_data_bittiming; } if (feature & GS_CAN_FEATURE_TERMINATION) { diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c index c79508b1c43e..0ea0ac75e42f 100644 --- a/drivers/net/can/usb/ucan.c +++ b/drivers/net/can/usb/ucan.c @@ -748,7 +748,7 @@ static void ucan_read_bulk_callback(struct urb *urb) len = le16_to_cpu(m->len); /* check sanity (length of content) */ - if (urb->actual_length - pos < len) { + if ((len == 0) || (urb->actual_length - pos < len)) { netdev_warn(up->netdev, "invalid message (short; no data; l:%d)\n", urb->actual_length); diff --git a/drivers/net/dsa/realtek/rtl8365mb.c b/drivers/net/dsa/realtek/rtl8365mb.c index c575e164368c..f938a3f701cc 100644 --- a/drivers/net/dsa/realtek/rtl8365mb.c +++ b/drivers/net/dsa/realtek/rtl8365mb.c @@ -769,7 +769,7 @@ static int rtl8365mb_phy_ocp_write(struct realtek_priv *priv, int phy, out: rtl83xx_unlock(priv); - return 0; + return ret; } static int rtl8365mb_phy_read(struct realtek_priv *priv, int phy, int regnum) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h index 711f295eb777..80c2c27ac9dc 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h @@ -431,7 +431,7 @@ #define MAC_SSIR_SSINC_INDEX 16 #define MAC_SSIR_SSINC_WIDTH 8 #define MAC_TCR_SS_INDEX 29 -#define MAC_TCR_SS_WIDTH 2 +#define MAC_TCR_SS_WIDTH 3 #define MAC_TCR_TE_INDEX 0 #define MAC_TCR_TE_WIDTH 1 #define MAC_TCR_VNE_INDEX 24 diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 62bb4b8a68e1..8b79d88480db 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1120,7 +1120,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller) { struct xgbe_prv_data *pdata = netdev_priv(netdev); struct xgbe_hw_if *hw_if = &pdata->hw_if; - unsigned long flags; DBGPR("-->xgbe_powerdown\n"); @@ -1131,8 +1130,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller) return -EINVAL; } - spin_lock_irqsave(&pdata->lock, flags); - if (caller == XGMAC_DRIVER_CONTEXT) netif_device_detach(netdev); @@ -1148,8 +1145,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller) pdata->power_down = 1; - spin_unlock_irqrestore(&pdata->lock, flags); - DBGPR("<--xgbe_powerdown\n"); return 0; @@ -1159,7 +1154,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller) { struct xgbe_prv_data *pdata = netdev_priv(netdev); struct xgbe_hw_if *hw_if = &pdata->hw_if; - unsigned long flags; DBGPR("-->xgbe_powerup\n"); @@ -1170,8 +1164,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller) return -EINVAL; } - spin_lock_irqsave(&pdata->lock, flags); - pdata->power_down = 0; xgbe_napi_enable(pdata, 0); @@ -1186,8 +1178,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller) xgbe_start_timers(pdata); - spin_unlock_irqrestore(&pdata->lock, flags); - DBGPR("<--xgbe_powerup\n"); return 0; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index d1f0419edb23..7d45ea22a02e 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -76,7 +76,6 @@ struct xgbe_prv_data *xgbe_alloc_pdata(struct device *dev) pdata->netdev = netdev; pdata->dev = dev; - spin_lock_init(&pdata->lock); spin_lock_init(&pdata->xpcs_lock); mutex_init(&pdata->rss_mutex); spin_lock_init(&pdata->tstamp_lock); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 1269b8ce9249..e1d7d7150e16 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -1004,9 +1004,6 @@ struct xgbe_prv_data { unsigned int pp3; unsigned int pp4; - /* Overall device lock */ - spinlock_t lock; - /* XPCS indirect addressing lock */ spinlock_t xpcs_lock; unsigned int xpcs_window_def_reg; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index fc0e0f36186e..52c1cb9cb7e0 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1533,7 +1533,7 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg) if_id = (status & 0xFFFF0000) >> 16; if (if_id >= ethsw->sw_attr.num_ifs) { dev_err(dev, "Invalid if_id %d in IRQ status\n", if_id); - goto out; + goto out_clear; } port_priv = ethsw->ports[if_id]; @@ -1553,6 +1553,7 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg) dpaa2_switch_port_connect_mac(port_priv); } +out_clear: err = dpsw_clear_irq_status(ethsw->mc_io, 0, ethsw->dpsw_handle, DPSW_IRQ_INDEX_IF, status); if (err) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 70768392912c..a146ceaf2ed6 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -3467,7 +3467,7 @@ static int enetc_int_vector_init(struct enetc_ndev_priv *priv, int i, priv->rx_ring[i] = bdr; err = __xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0, - ENETC_RXB_DMA_SIZE_XDP); + ENETC_RXB_TRUESIZE); if (err) goto free_vector; diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index ba331899d186..d4a1041e456d 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -33,6 +33,7 @@ /* Extended Device Control */ #define E1000_CTRL_EXT_LPCD 0x00000004 /* LCD Power Cycle Done */ +#define E1000_CTRL_EXT_DPG_EN 0x00000008 /* Dynamic Power Gating Enable */ #define E1000_CTRL_EXT_SDP3_DATA 0x00000080 /* Value of SW Definable Pin 3 */ #define E1000_CTRL_EXT_FORCE_SMBUS 0x00000800 /* Force SMBus mode */ #define E1000_CTRL_EXT_EE_RST 0x00002000 /* Reinitialize from EEPROM */ diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index aa08f397988e..63ebe00376f5 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -117,7 +117,8 @@ enum e1000_boards { board_pch_cnp, board_pch_tgp, board_pch_adp, - board_pch_mtp + board_pch_mtp, + board_pch_ptp }; struct e1000_ps_page { @@ -527,6 +528,7 @@ extern const struct e1000_info e1000_pch_cnp_info; extern const struct e1000_info e1000_pch_tgp_info; extern const struct e1000_info e1000_pch_adp_info; extern const struct e1000_info e1000_pch_mtp_info; +extern const struct e1000_info e1000_pch_ptp_info; extern const struct e1000_info e1000_es2_info; void e1000e_ptp_init(struct e1000_adapter *adapter); diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index fc8ed38aa095..c7ac599e5a7a 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -118,8 +118,6 @@ struct e1000_hw; #define E1000_DEV_ID_PCH_ARL_I219_V24 0x57A1 #define E1000_DEV_ID_PCH_PTP_I219_LM25 0x57B3 #define E1000_DEV_ID_PCH_PTP_I219_V25 0x57B4 -#define E1000_DEV_ID_PCH_PTP_I219_LM26 0x57B5 -#define E1000_DEV_ID_PCH_PTP_I219_V26 0x57B6 #define E1000_DEV_ID_PCH_PTP_I219_LM27 0x57B7 #define E1000_DEV_ID_PCH_PTP_I219_V27 0x57B8 #define E1000_DEV_ID_PCH_NVL_I219_LM29 0x57B9 diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 0ff8688ac3b8..dea208db1be5 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -528,7 +528,7 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw) phy->id = e1000_phy_unknown; - if (hw->mac.type == e1000_pch_mtp) { + if (hw->mac.type == e1000_pch_mtp || hw->mac.type == e1000_pch_ptp) { phy->retry_count = 2; e1000e_enable_phy_retry(hw); } @@ -4932,6 +4932,15 @@ static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw) reg |= E1000_KABGTXD_BGSQLBIAS; ew32(KABGTXD, reg); + /* The hardware reset value of the DPG_EN bit is 1. + * Clear DPG_EN to prevent unexpected autonomous power gating. + */ + if (hw->mac.type >= e1000_pch_ptp) { + reg = er32(CTRL_EXT); + reg &= ~E1000_CTRL_EXT_DPG_EN; + ew32(CTRL_EXT, reg); + } + return 0; } @@ -6208,3 +6217,23 @@ const struct e1000_info e1000_pch_mtp_info = { .phy_ops = &ich8_phy_ops, .nvm_ops = &spt_nvm_ops, }; + +const struct e1000_info e1000_pch_ptp_info = { + .mac = e1000_pch_ptp, + .flags = FLAG_IS_ICH + | FLAG_HAS_WOL + | FLAG_HAS_HW_TIMESTAMP + | FLAG_HAS_CTRLEXT_ON_LOAD + | FLAG_HAS_AMT + | FLAG_HAS_FLASH + | FLAG_HAS_JUMBO_FRAMES + | FLAG_APME_IN_WUC, + .flags2 = FLAG2_HAS_PHY_STATS + | FLAG2_HAS_EEE, + .pba = 26, + .max_hw_frame_size = 9022, + .get_variants = e1000_get_variants_ich8lan, + .mac_ops = &ich8_mac_ops, + .phy_ops = &ich8_phy_ops, + .nvm_ops = &spt_nvm_ops, +}; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index fd4b117ed20f..35dab1e3132f 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -55,6 +55,7 @@ static const struct e1000_info *e1000_info_tbl[] = { [board_pch_tgp] = &e1000_pch_tgp_info, [board_pch_adp] = &e1000_pch_adp_info, [board_pch_mtp] = &e1000_pch_mtp_info, + [board_pch_ptp] = &e1000_pch_ptp_info, }; struct e1000_reg_info { @@ -7922,14 +7923,12 @@ static const struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_mtp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ARL_I219_LM24), board_pch_mtp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ARL_I219_V24), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM25), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V25), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM26), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V26), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM27), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V27), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_LM29), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_V29), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM25), board_pch_ptp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V25), board_pch_ptp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM27), board_pch_ptp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V27), board_pch_ptp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_LM29), board_pch_ptp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_V29), board_pch_ptp }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 7b9e147d7365..926d001b2150 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3569,6 +3569,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) u16 pf_q = vsi->base_queue + ring->queue_index; struct i40e_hw *hw = &vsi->back->hw; struct i40e_hmc_obj_rxq rx_ctx; + u32 xdp_frame_sz; int err = 0; bool ok; @@ -3578,49 +3579,47 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) memset(&rx_ctx, 0, sizeof(rx_ctx)); ring->rx_buf_len = vsi->rx_buf_len; + xdp_frame_sz = i40e_rx_pg_size(ring) / 2; /* XDP RX-queue info only needed for RX rings exposed to XDP */ if (ring->vsi->type != I40E_VSI_MAIN) goto skip; - if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { - err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, - ring->queue_index, - ring->q_vector->napi.napi_id, - ring->rx_buf_len); - if (err) - return err; - } - ring->xsk_pool = i40e_xsk_pool(ring); if (ring->xsk_pool) { - xdp_rxq_info_unreg(&ring->xdp_rxq); + xdp_frame_sz = xsk_pool_get_rx_frag_step(ring->xsk_pool); ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->queue_index, ring->q_vector->napi.napi_id, - ring->rx_buf_len); + xdp_frame_sz); if (err) return err; err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL); if (err) - return err; + goto unreg_xdp; dev_info(&vsi->back->pdev->dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->queue_index); } else { + err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, + ring->queue_index, + ring->q_vector->napi.napi_id, + xdp_frame_sz); + if (err) + return err; err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL); if (err) - return err; + goto unreg_xdp; } skip: - xdp_init_buff(&ring->xdp, i40e_rx_pg_size(ring) / 2, &ring->xdp_rxq); + xdp_init_buff(&ring->xdp, xdp_frame_sz, &ring->xdp_rxq); rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len, BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT)); @@ -3654,7 +3653,8 @@ skip: dev_info(&vsi->back->pdev->dev, "Failed to clear LAN Rx queue context on Rx ring %d (pf_q %d), error: %d\n", ring->queue_index, pf_q, err); - return -ENOMEM; + err = -ENOMEM; + goto unreg_xdp; } /* set the context in the HMC */ @@ -3663,7 +3663,8 @@ skip: dev_info(&vsi->back->pdev->dev, "Failed to set LAN Rx queue context on Rx ring %d (pf_q %d), error: %d\n", ring->queue_index, pf_q, err); - return -ENOMEM; + err = -ENOMEM; + goto unreg_xdp; } /* configure Rx buffer alignment */ @@ -3671,7 +3672,8 @@ skip: if (I40E_2K_TOO_SMALL_WITH_PADDING) { dev_info(&vsi->back->pdev->dev, "2k Rx buffer is too small to fit standard MTU and skb_shared_info\n"); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto unreg_xdp; } clear_ring_build_skb_enabled(ring); } else { @@ -3701,6 +3703,11 @@ skip: } return 0; +unreg_xdp: + if (ring->vsi->type == I40E_VSI_MAIN) + xdp_rxq_info_unreg(&ring->xdp_rxq); + + return err; } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_trace.h b/drivers/net/ethernet/intel/i40e/i40e_trace.h index 759f3d1c4c8f..dde0ccd789ed 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_trace.h +++ b/drivers/net/ethernet/intel/i40e/i40e_trace.h @@ -88,7 +88,7 @@ TRACE_EVENT(i40e_napi_poll, __entry->rx_clean_complete = rx_clean_complete; __entry->tx_clean_complete = tx_clean_complete; __entry->irq_num = q->irq_num; - __entry->curr_cpu = get_cpu(); + __entry->curr_cpu = smp_processor_id(); __assign_str(qname); __assign_str(dev_name); __assign_bitmask(irq_affinity, cpumask_bits(&q->affinity_mask), diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 34db7d8866b0..894f2d06d39d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1470,6 +1470,9 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) if (!rx_ring->rx_bi) return; + if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + if (rx_ring->xsk_pool) { i40e_xsk_clean_rx_ring(rx_ring); goto skip_free; @@ -1527,8 +1530,6 @@ skip_free: void i40e_free_rx_resources(struct i40e_ring *rx_ring) { i40e_clean_rx_ring(rx_ring); - if (rx_ring->vsi->type == I40E_VSI_MAIN) - xdp_rxq_info_unreg(&rx_ring->xdp_rxq); rx_ring->xdp_prog = NULL; kfree(rx_ring->rx_bi); rx_ring->rx_bi = NULL; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index bceaf4b1b85d..86c1964f42e1 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2793,7 +2793,22 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) netdev->watchdog_timeo = 5 * HZ; netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = LIBIE_MAX_MTU; + + /* PF/VF API: vf_res->max_mtu is max frame size (not MTU). + * Convert to MTU. + */ + if (!adapter->vf_res->max_mtu) { + netdev->max_mtu = LIBIE_MAX_MTU; + } else if (adapter->vf_res->max_mtu < LIBETH_RX_LL_LEN + ETH_MIN_MTU || + adapter->vf_res->max_mtu > + LIBETH_RX_LL_LEN + LIBIE_MAX_MTU) { + netdev_warn_once(adapter->netdev, + "invalid max frame size %d from PF, using default MTU %d", + adapter->vf_res->max_mtu, LIBIE_MAX_MTU); + netdev->max_mtu = LIBIE_MAX_MTU; + } else { + netdev->max_mtu = adapter->vf_res->max_mtu - LIBETH_RX_LL_LEN; + } if (!is_valid_ether_addr(adapter->hw.mac.addr)) { dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n", diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index def7efa15447..2b2b22af42be 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -987,6 +987,7 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset); void ice_print_link_msg(struct ice_vsi *vsi, bool isup); int ice_plug_aux_dev(struct ice_pf *pf); void ice_unplug_aux_dev(struct ice_pf *pf); +void ice_rdma_finalize_setup(struct ice_pf *pf); int ice_init_rdma(struct ice_pf *pf); void ice_deinit_rdma(struct ice_pf *pf); bool ice_is_wol_supported(struct ice_hw *hw); diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index eb77dfa934aa..1667f686ff75 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -124,6 +124,8 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx) if (vsi->type == ICE_VSI_VF) { ice_calc_vf_reg_idx(vsi->vf, q_vector); goto out; + } else if (vsi->type == ICE_VSI_LB) { + goto skip_alloc; } else if (vsi->type == ICE_VSI_CTRL && vsi->vf) { struct ice_vsi *ctrl_vsi = ice_get_vf_ctrl_vsi(pf, vsi); @@ -659,33 +661,22 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) { struct device *dev = ice_pf_to_dev(ring->vsi->back); u32 num_bufs = ICE_DESC_UNUSED(ring); - u32 rx_buf_len; int err; - if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF) { - if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { - err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, - ring->q_index, - ring->q_vector->napi.napi_id, - ring->rx_buf_len); - if (err) - return err; - } - + if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF || + ring->vsi->type == ICE_VSI_LB) { ice_rx_xsk_pool(ring); err = ice_realloc_rx_xdp_bufs(ring, ring->xsk_pool); if (err) return err; if (ring->xsk_pool) { - xdp_rxq_info_unreg(&ring->xdp_rxq); - - rx_buf_len = - xsk_pool_get_rx_frame_size(ring->xsk_pool); + u32 frag_size = + xsk_pool_get_rx_frag_step(ring->xsk_pool); err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->q_index, ring->q_vector->napi.napi_id, - rx_buf_len); + frag_size); if (err) return err; err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, @@ -702,14 +693,13 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) if (err) return err; - if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { - err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, - ring->q_index, - ring->q_vector->napi.napi_id, - ring->rx_buf_len); - if (err) - goto err_destroy_fq; - } + err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, + ring->q_index, + ring->q_vector->napi.napi_id, + ring->truesize); + if (err) + goto err_destroy_fq; + xdp_rxq_info_attach_page_pool(&ring->xdp_rxq, ring->pp); } diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 6cd63190f55d..ce11fea122d0 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1816,6 +1816,7 @@ static bool ice_should_retry_sq_send_cmd(u16 opcode) case ice_aqc_opc_lldp_stop: case ice_aqc_opc_lldp_start: case ice_aqc_opc_lldp_filter_ctrl: + case ice_aqc_opc_sff_eeprom: return true; } @@ -1841,6 +1842,7 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, { struct libie_aq_desc desc_cpy; bool is_cmd_for_retry; + u8 *buf_cpy = NULL; u8 idx = 0; u16 opcode; int status; @@ -1850,8 +1852,11 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, memset(&desc_cpy, 0, sizeof(desc_cpy)); if (is_cmd_for_retry) { - /* All retryable cmds are direct, without buf. */ - WARN_ON(buf); + if (buf) { + buf_cpy = kmemdup(buf, buf_size, GFP_KERNEL); + if (!buf_cpy) + return -ENOMEM; + } memcpy(&desc_cpy, desc, sizeof(desc_cpy)); } @@ -1863,12 +1868,14 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, hw->adminq.sq_last_status != LIBIE_AQ_RC_EBUSY) break; + if (buf_cpy) + memcpy(buf, buf_cpy, buf_size); memcpy(desc, &desc_cpy, sizeof(desc_cpy)); - msleep(ICE_SQ_SEND_DELAY_TIME_MS); } while (++idx < ICE_SQ_SEND_MAX_EXECUTE); + kfree(buf_cpy); return status; } @@ -6391,7 +6398,7 @@ int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add) struct ice_aqc_lldp_filter_ctrl *cmd; struct libie_aq_desc desc; - if (vsi->type != ICE_VSI_PF || !ice_fw_supports_lldp_fltr_ctrl(hw)) + if (!ice_fw_supports_lldp_fltr_ctrl(hw)) return -EOPNOTSUPP; cmd = libie_aq_raw(&desc); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 0ea64b330614..301947d53ede 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1289,6 +1289,10 @@ static u64 ice_loopback_test(struct net_device *netdev) test_vsi->netdev = netdev; tx_ring = test_vsi->tx_rings[0]; rx_ring = test_vsi->rx_rings[0]; + /* Dummy q_vector and napi. Fill the minimum required for + * ice_rxq_pp_create(). + */ + rx_ring->q_vector->napi.dev = netdev; if (ice_lbtest_prepare_rings(test_vsi)) { ret = 2; @@ -3328,7 +3332,7 @@ process_rx: rx_rings = kzalloc_objs(*rx_rings, vsi->num_rxq); if (!rx_rings) { err = -ENOMEM; - goto done; + goto free_xdp; } ice_for_each_rxq(vsi, i) { @@ -3338,6 +3342,7 @@ process_rx: rx_rings[i].cached_phctime = pf->ptp.cached_phc_time; rx_rings[i].desc = NULL; rx_rings[i].xdp_buf = NULL; + rx_rings[i].xdp_rxq = (struct xdp_rxq_info){ }; /* this is to allow wr32 to have something to write to * during early allocation of Rx buffers @@ -3355,7 +3360,7 @@ rx_unwind: } kfree(rx_rings); err = -ENOMEM; - goto free_tx; + goto free_xdp; } } @@ -3407,6 +3412,13 @@ process_link: } goto done; +free_xdp: + if (xdp_rings) { + ice_for_each_xdp_txq(vsi, i) + ice_free_tx_ring(&xdp_rings[i]); + kfree(xdp_rings); + } + free_tx: /* error cleanup if the Rx allocations failed after getting Tx */ if (tx_rings) { @@ -4505,7 +4517,7 @@ ice_get_module_eeprom(struct net_device *netdev, u8 addr = ICE_I2C_EEPROM_DEV_ADDR; struct ice_hw *hw = &pf->hw; bool is_sfp = false; - unsigned int i, j; + unsigned int i; u16 offset = 0; u8 page = 0; int status; @@ -4547,26 +4559,19 @@ ice_get_module_eeprom(struct net_device *netdev, if (page == 0 || !(data[0x2] & 0x4)) { u32 copy_len; - /* If i2c bus is busy due to slow page change or - * link management access, call can fail. This is normal. - * So we retry this a few times. - */ - for (j = 0; j < 4; j++) { - status = ice_aq_sff_eeprom(hw, 0, addr, offset, page, - !is_sfp, value, - SFF_READ_BLOCK_SIZE, - 0, NULL); - netdev_dbg(netdev, "SFF %02X %02X %02X %X = %02X%02X%02X%02X.%02X%02X%02X%02X (%X)\n", - addr, offset, page, is_sfp, - value[0], value[1], value[2], value[3], - value[4], value[5], value[6], value[7], - status); - if (status) { - usleep_range(1500, 2500); - memset(value, 0, SFF_READ_BLOCK_SIZE); - continue; - } - break; + status = ice_aq_sff_eeprom(hw, 0, addr, offset, page, + !is_sfp, value, + SFF_READ_BLOCK_SIZE, + 0, NULL); + netdev_dbg(netdev, "SFF %02X %02X %02X %X = %02X%02X%02X%02X.%02X%02X%02X%02X (%pe)\n", + addr, offset, page, is_sfp, + value[0], value[1], value[2], value[3], + value[4], value[5], value[6], value[7], + ERR_PTR(status)); + if (status) { + netdev_err(netdev, "%s: error reading module EEPROM: status %pe\n", + __func__, ERR_PTR(status)); + return status; } /* Make sure we have enough room for the new block */ diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index 3572b0e1d49f..102d63c3018b 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -360,6 +360,39 @@ void ice_unplug_aux_dev(struct ice_pf *pf) auxiliary_device_uninit(adev); } +/** + * ice_rdma_finalize_setup - Complete RDMA setup after VSI is ready + * @pf: ptr to ice_pf + * + * Sets VSI-dependent information and plugs aux device. + * Must be called after ice_init_rdma(), ice_vsi_rebuild(), and + * ice_dcb_rebuild() complete. + */ +void ice_rdma_finalize_setup(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + struct iidc_rdma_priv_dev_info *privd; + int ret; + + if (!ice_is_rdma_ena(pf) || !pf->cdev_info) + return; + + privd = pf->cdev_info->iidc_priv; + if (!privd || !pf->vsi || !pf->vsi[0] || !pf->vsi[0]->netdev) + return; + + /* Assign VSI info now that VSI is valid */ + privd->netdev = pf->vsi[0]->netdev; + privd->vport_id = pf->vsi[0]->vsi_num; + + /* Update QoS info after DCB has been rebuilt */ + ice_setup_dcb_qos_info(pf, &privd->qos_info); + + ret = ice_plug_aux_dev(pf); + if (ret) + dev_warn(dev, "Failed to plug RDMA aux device: %d\n", ret); +} + /** * ice_init_rdma - initializes PF for RDMA use * @pf: ptr to ice_pf @@ -398,22 +431,14 @@ int ice_init_rdma(struct ice_pf *pf) } cdev->iidc_priv = privd; - privd->netdev = pf->vsi[0]->netdev; privd->hw_addr = (u8 __iomem *)pf->hw.hw_addr; cdev->pdev = pf->pdev; - privd->vport_id = pf->vsi[0]->vsi_num; pf->cdev_info->rdma_protocol |= IIDC_RDMA_PROTOCOL_ROCEV2; - ice_setup_dcb_qos_info(pf, &privd->qos_info); - ret = ice_plug_aux_dev(pf); - if (ret) - goto err_plug_aux_dev; + return 0; -err_plug_aux_dev: - pf->cdev_info->adev = NULL; - xa_erase(&ice_aux_id, pf->aux_idx); err_alloc_xa: kfree(privd); err_privd_alloc: @@ -432,7 +457,6 @@ void ice_deinit_rdma(struct ice_pf *pf) if (!ice_is_rdma_ena(pf)) return; - ice_unplug_aux_dev(pf); xa_erase(&ice_aux_id, pf->aux_idx); kfree(pf->cdev_info->iidc_priv); kfree(pf->cdev_info); diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index f91f8b672b02..689c6025ea82 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -107,10 +107,6 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) if (!vsi->rxq_map) goto err_rxq_map; - /* There is no need to allocate q_vectors for a loopback VSI. */ - if (vsi->type == ICE_VSI_LB) - return 0; - /* allocate memory for q_vector pointers */ vsi->q_vectors = devm_kcalloc(dev, vsi->num_q_vectors, sizeof(*vsi->q_vectors), GFP_KERNEL); @@ -241,6 +237,8 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi) case ICE_VSI_LB: vsi->alloc_txq = 1; vsi->alloc_rxq = 1; + /* A dummy q_vector, no actual IRQ. */ + vsi->num_q_vectors = 1; break; default: dev_warn(ice_pf_to_dev(pf), "Unknown VSI type %d\n", vsi_type); @@ -2426,14 +2424,21 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi) } break; case ICE_VSI_LB: - ret = ice_vsi_alloc_rings(vsi); + ret = ice_vsi_alloc_q_vectors(vsi); if (ret) goto unroll_vsi_init; + ret = ice_vsi_alloc_rings(vsi); + if (ret) + goto unroll_alloc_q_vector; + ret = ice_vsi_alloc_ring_stats(vsi); if (ret) goto unroll_vector_base; + /* Simply map the dummy q_vector to the only rx_ring */ + vsi->rx_rings[0]->q_vector = vsi->q_vectors[0]; + break; default: /* clean up the resources and exit */ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index ebf48feffb30..e7308e381e2f 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -5138,6 +5138,9 @@ int ice_load(struct ice_pf *pf) if (err) goto err_init_rdma; + /* Finalize RDMA: VSI already created, assign info and plug device */ + ice_rdma_finalize_setup(pf); + ice_service_task_restart(pf); clear_bit(ICE_DOWN, pf->state); @@ -5169,6 +5172,7 @@ void ice_unload(struct ice_pf *pf) devl_assert_locked(priv_to_devlink(pf)); + ice_unplug_aux_dev(pf); ice_deinit_rdma(pf); ice_deinit_features(pf); ice_tc_indir_block_unregister(vsi); @@ -5595,6 +5599,7 @@ static int ice_suspend(struct device *dev) */ disabled = ice_service_task_stop(pf); + ice_unplug_aux_dev(pf); ice_deinit_rdma(pf); /* Already suspended?, then there is nothing to do */ @@ -7859,7 +7864,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) ice_health_clear(pf); - ice_plug_aux_dev(pf); + ice_rdma_finalize_setup(pf); if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) ice_lag_rebuild(pf); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index a5bbce68f76c..a2cd4cf37734 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -560,7 +560,9 @@ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring) i = 0; } - if (rx_ring->vsi->type == ICE_VSI_PF && + if ((rx_ring->vsi->type == ICE_VSI_PF || + rx_ring->vsi->type == ICE_VSI_SF || + rx_ring->vsi->type == ICE_VSI_LB) && xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) { xdp_rxq_info_detach_mem_model(&rx_ring->xdp_rxq); xdp_rxq_info_unreg(&rx_ring->xdp_rxq); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index c673094663a3..0643017541c3 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -899,6 +899,9 @@ void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) u16 ntc = rx_ring->next_to_clean; u16 ntu = rx_ring->next_to_use; + if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + while (ntc != ntu) { struct xdp_buff *xdp = *ice_xdp_buf(rx_ring, ntc); diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c index 40e08a71d2d3..bb99d9e7c65d 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c @@ -307,9 +307,6 @@ static int idpf_del_flow_steer(struct net_device *netdev, vport_config = vport->adapter->vport_config[np->vport_idx]; user_config = &vport_config->user_config; - if (!idpf_sideband_action_ena(vport, fsp)) - return -EOPNOTSUPP; - rule = kzalloc_flex(*rule, rule_info, 1); if (!rule) return -ENOMEM; diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index de3df705a7e6..cf966fe6c759 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -1318,6 +1318,7 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, free_rss_key: kfree(rss_data->rss_key); + rss_data->rss_key = NULL; free_qreg_chunks: idpf_vport_deinit_queue_reg_chunks(adapter->vport_config[idx]); free_vector_idxs: diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 05a162094d10..252259993022 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -1314,6 +1314,9 @@ static void idpf_txq_group_rel(struct idpf_q_vec_rsrc *rsrc) struct idpf_txq_group *txq_grp = &rsrc->txq_grps[i]; for (unsigned int j = 0; j < txq_grp->num_txq; j++) { + if (!txq_grp->txqs[j]) + continue; + if (idpf_queue_has(FLOW_SCH_EN, txq_grp->txqs[j])) { kfree(txq_grp->txqs[j]->refillq); txq_grp->txqs[j]->refillq = NULL; @@ -1339,6 +1342,9 @@ static void idpf_txq_group_rel(struct idpf_q_vec_rsrc *rsrc) */ static void idpf_rxq_sw_queue_rel(struct idpf_rxq_group *rx_qgrp) { + if (!rx_qgrp->splitq.bufq_sets) + return; + for (unsigned int i = 0; i < rx_qgrp->splitq.num_bufq_sets; i++) { struct idpf_bufq_set *bufq_set = &rx_qgrp->splitq.bufq_sets[i]; @@ -2336,7 +2342,7 @@ void idpf_wait_for_sw_marker_completion(const struct idpf_tx_queue *txq) do { struct idpf_splitq_4b_tx_compl_desc *tx_desc; - struct idpf_tx_queue *target; + struct idpf_tx_queue *target = NULL; u32 ctype_gen, id; tx_desc = flow ? &complq->comp[ntc].common : @@ -2356,14 +2362,14 @@ void idpf_wait_for_sw_marker_completion(const struct idpf_tx_queue *txq) target = complq->txq_grp->txqs[id]; idpf_queue_clear(SW_MARKER, target); - if (target == txq) - break; next: if (unlikely(++ntc == complq->desc_count)) { ntc = 0; gen_flag = !gen_flag; } + if (target == txq) + break; } while (time_before(jiffies, timeout)); idpf_queue_assign(GEN_CHK, complq, gen_flag); @@ -4059,7 +4065,7 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport, continue; name = kasprintf(GFP_KERNEL, "%s-%s-%s-%d", drv_name, if_name, - vec_name, vidx); + vec_name, vector); err = request_irq(irq_num, idpf_vport_intr_clean_queues, 0, name, q_vector); diff --git a/drivers/net/ethernet/intel/idpf/xdp.c b/drivers/net/ethernet/intel/idpf/xdp.c index 6ac9c6624c2a..cbccd4546768 100644 --- a/drivers/net/ethernet/intel/idpf/xdp.c +++ b/drivers/net/ethernet/intel/idpf/xdp.c @@ -47,12 +47,16 @@ static int __idpf_xdp_rxq_info_init(struct idpf_rx_queue *rxq, void *arg) { const struct idpf_vport *vport = rxq->q_vector->vport; const struct idpf_q_vec_rsrc *rsrc; + u32 frag_size = 0; bool split; int err; + if (idpf_queue_has(XSK, rxq)) + frag_size = rxq->bufq_sets[0].bufq.truesize; + err = __xdp_rxq_info_reg(&rxq->xdp_rxq, vport->netdev, rxq->idx, rxq->q_vector->napi.napi_id, - rxq->rx_buf_size); + frag_size); if (err) return err; diff --git a/drivers/net/ethernet/intel/idpf/xsk.c b/drivers/net/ethernet/intel/idpf/xsk.c index 676cbd80774d..d95d3efdfd36 100644 --- a/drivers/net/ethernet/intel/idpf/xsk.c +++ b/drivers/net/ethernet/intel/idpf/xsk.c @@ -403,6 +403,7 @@ int idpf_xskfq_init(struct idpf_buf_queue *bufq) bufq->pending = fq.pending; bufq->thresh = fq.thresh; bufq->rx_buf_size = fq.buf_len; + bufq->truesize = fq.truesize; if (!idpf_xskfq_refill(bufq)) netdev_err(bufq->pool->netdev, diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c index 30ce5fbb5b77..ce4a7b58cad2 100644 --- a/drivers/net/ethernet/intel/igb/igb_xsk.c +++ b/drivers/net/ethernet/intel/igb/igb_xsk.c @@ -524,6 +524,16 @@ bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool) return nb_pkts < budget; } +static u32 igb_sw_irq_prep(struct igb_q_vector *q_vector) +{ + u32 eics = 0; + + if (!napi_if_scheduled_mark_missed(&q_vector->napi)) + eics = q_vector->eims_value; + + return eics; +} + int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) { struct igb_adapter *adapter = netdev_priv(dev); @@ -542,20 +552,32 @@ int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) ring = adapter->tx_ring[qid]; - if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags)) - return -ENETDOWN; - if (!READ_ONCE(ring->xsk_pool)) return -EINVAL; - if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) { + if (flags & XDP_WAKEUP_TX) { + if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags)) + return -ENETDOWN; + + eics |= igb_sw_irq_prep(ring->q_vector); + } + + if (flags & XDP_WAKEUP_RX) { + /* If IGB_FLAG_QUEUE_PAIRS is active, the q_vector + * and NAPI is shared between RX and TX. + * If NAPI is already running it would be marked as missed + * from the TX path, making this RX call a NOP + */ + ring = adapter->rx_ring[qid]; + eics |= igb_sw_irq_prep(ring->q_vector); + } + + if (eics) { /* Cause software interrupt */ - if (adapter->flags & IGB_FLAG_HAS_MSIX) { - eics |= ring->q_vector->eims_value; + if (adapter->flags & IGB_FLAG_HAS_MSIX) wr32(E1000_EICS, eics); - } else { + else wr32(E1000_ICS, E1000_ICS_RXDMT0); - } } return 0; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 27e5c2109138..b2e8d0c0f827 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6906,28 +6906,29 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, return nxmit; } -static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter, - struct igc_q_vector *q_vector) +static u32 igc_sw_irq_prep(struct igc_q_vector *q_vector) { - struct igc_hw *hw = &adapter->hw; u32 eics = 0; - eics |= q_vector->eims_value; - wr32(IGC_EICS, eics); + if (!napi_if_scheduled_mark_missed(&q_vector->napi)) + eics = q_vector->eims_value; + + return eics; } int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) { struct igc_adapter *adapter = netdev_priv(dev); - struct igc_q_vector *q_vector; + struct igc_hw *hw = &adapter->hw; struct igc_ring *ring; + u32 eics = 0; if (test_bit(__IGC_DOWN, &adapter->state)) return -ENETDOWN; if (!igc_xdp_is_enabled(adapter)) return -ENXIO; - + /* Check if queue_id is valid. Tx and Rx queue numbers are always same */ if (queue_id >= adapter->num_rx_queues) return -EINVAL; @@ -6936,9 +6937,22 @@ int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) if (!ring->xsk_pool) return -ENXIO; - q_vector = adapter->q_vector[queue_id]; - if (!napi_if_scheduled_mark_missed(&q_vector->napi)) - igc_trigger_rxtxq_interrupt(adapter, q_vector); + if (flags & XDP_WAKEUP_RX) + eics |= igc_sw_irq_prep(ring->q_vector); + + if (flags & XDP_WAKEUP_TX) { + /* If IGC_FLAG_QUEUE_PAIRS is active, the q_vector + * and NAPI is shared between RX and TX. + * If NAPI is already running it would be marked as missed + * from the RX path, making this TX call a NOP + */ + ring = adapter->tx_ring[queue_id]; + eics |= igc_sw_irq_prep(ring->q_vector); + } + + if (eics) + /* Cause software interrupt */ + wr32(IGC_EICS, eics); return 0; } diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 7aae83c108fd..44ee19386766 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -550,7 +550,8 @@ static void igc_ptp_free_tx_buffer(struct igc_adapter *adapter, tstamp->buffer_type = 0; /* Trigger txrx interrupt for transmit completion */ - igc_xsk_wakeup(adapter->netdev, tstamp->xsk_queue_index, 0); + igc_xsk_wakeup(adapter->netdev, tstamp->xsk_queue_index, + XDP_WAKEUP_TX); return; } diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index 74d320879513..b67b580f7f1c 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -852,7 +852,8 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw, if (!mac->get_link_status) goto out; - if (hw->mac.type == ixgbe_mac_e610_vf) { + if (hw->mac.type == ixgbe_mac_e610_vf && + hw->api_version >= ixgbe_mbox_api_16) { ret_val = ixgbevf_get_pf_link_state(hw, speed, link_up); if (ret_val) goto out; diff --git a/drivers/net/ethernet/intel/libeth/xsk.c b/drivers/net/ethernet/intel/libeth/xsk.c index 846e902e31b6..4882951d5c9c 100644 --- a/drivers/net/ethernet/intel/libeth/xsk.c +++ b/drivers/net/ethernet/intel/libeth/xsk.c @@ -167,6 +167,7 @@ int libeth_xskfq_create(struct libeth_xskfq *fq) fq->pending = fq->count; fq->thresh = libeth_xdp_queue_threshold(fq->count); fq->buf_len = xsk_pool_get_rx_frame_size(fq->pool); + fq->truesize = xsk_pool_get_rx_frag_step(fq->pool); return 0; } diff --git a/drivers/net/ethernet/intel/libie/fwlog.c b/drivers/net/ethernet/intel/libie/fwlog.c index 79020d990859..4d0c8370386b 100644 --- a/drivers/net/ethernet/intel/libie/fwlog.c +++ b/drivers/net/ethernet/intel/libie/fwlog.c @@ -1049,6 +1049,10 @@ void libie_fwlog_deinit(struct libie_fwlog *fwlog) { int status; + /* if FW logging isn't supported it means no configuration was done */ + if (!libie_fwlog_supported(fwlog)) + return; + /* make sure FW logging is disabled to not put the FW in a weird state * for the next driver load */ diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index ec55eb2a6c04..028dd55604ea 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -553,6 +553,36 @@ static void octep_clean_irqs(struct octep_device *oct) octep_free_ioq_vectors(oct); } +/** + * octep_update_pkt() - Update IQ/OQ IN/OUT_CNT registers. + * + * @iq: Octeon Tx queue data structure. + * @oq: Octeon Rx queue data structure. + */ +static void octep_update_pkt(struct octep_iq *iq, struct octep_oq *oq) +{ + u32 pkts_pend = READ_ONCE(oq->pkts_pending); + u32 last_pkt_count = READ_ONCE(oq->last_pkt_count); + u32 pkts_processed = READ_ONCE(iq->pkts_processed); + u32 pkt_in_done = READ_ONCE(iq->pkt_in_done); + + netdev_dbg(iq->netdev, "enabling intr for Q-%u\n", iq->q_no); + if (pkts_processed) { + writel(pkts_processed, iq->inst_cnt_reg); + readl(iq->inst_cnt_reg); + WRITE_ONCE(iq->pkt_in_done, (pkt_in_done - pkts_processed)); + WRITE_ONCE(iq->pkts_processed, 0); + } + if (last_pkt_count - pkts_pend) { + writel(last_pkt_count - pkts_pend, oq->pkts_sent_reg); + readl(oq->pkts_sent_reg); + WRITE_ONCE(oq->last_pkt_count, pkts_pend); + } + + /* Flush the previous wrties before writing to RESEND bit */ + smp_wmb(); +} + /** * octep_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue. * @@ -561,21 +591,6 @@ static void octep_clean_irqs(struct octep_device *oct) */ static void octep_enable_ioq_irq(struct octep_iq *iq, struct octep_oq *oq) { - u32 pkts_pend = oq->pkts_pending; - - netdev_dbg(iq->netdev, "enabling intr for Q-%u\n", iq->q_no); - if (iq->pkts_processed) { - writel(iq->pkts_processed, iq->inst_cnt_reg); - iq->pkt_in_done -= iq->pkts_processed; - iq->pkts_processed = 0; - } - if (oq->last_pkt_count - pkts_pend) { - writel(oq->last_pkt_count - pkts_pend, oq->pkts_sent_reg); - oq->last_pkt_count = pkts_pend; - } - - /* Flush the previous wrties before writing to RESEND bit */ - wmb(); writeq(1UL << OCTEP_OQ_INTR_RESEND_BIT, oq->pkts_sent_reg); writeq(1UL << OCTEP_IQ_INTR_RESEND_BIT, iq->inst_cnt_reg); } @@ -601,7 +616,8 @@ static int octep_napi_poll(struct napi_struct *napi, int budget) if (tx_pending || rx_done >= budget) return budget; - napi_complete(napi); + octep_update_pkt(ioq_vector->iq, ioq_vector->oq); + napi_complete_done(napi, rx_done); octep_enable_ioq_irq(ioq_vector->iq, ioq_vector->oq); return rx_done; } diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c index f2a7c6a76c74..74de19166488 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c @@ -324,10 +324,16 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct, struct octep_oq *oq) { u32 pkt_count, new_pkts; + u32 last_pkt_count, pkts_pending; pkt_count = readl(oq->pkts_sent_reg); - new_pkts = pkt_count - oq->last_pkt_count; + last_pkt_count = READ_ONCE(oq->last_pkt_count); + new_pkts = pkt_count - last_pkt_count; + if (pkt_count < last_pkt_count) { + dev_err(oq->dev, "OQ-%u pkt_count(%u) < oq->last_pkt_count(%u)\n", + oq->q_no, pkt_count, last_pkt_count); + } /* Clear the hardware packets counter register if the rx queue is * being processed continuously with-in a single interrupt and * reached half its max value. @@ -338,8 +344,9 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct, pkt_count = readl(oq->pkts_sent_reg); new_pkts += pkt_count; } - oq->last_pkt_count = pkt_count; - oq->pkts_pending += new_pkts; + WRITE_ONCE(oq->last_pkt_count, pkt_count); + pkts_pending = READ_ONCE(oq->pkts_pending); + WRITE_ONCE(oq->pkts_pending, (pkts_pending + new_pkts)); return new_pkts; } @@ -414,7 +421,7 @@ static int __octep_oq_process_rx(struct octep_device *oct, u16 rx_ol_flags; u32 read_idx; - read_idx = oq->host_read_idx; + read_idx = READ_ONCE(oq->host_read_idx); rx_bytes = 0; desc_used = 0; for (pkt = 0; pkt < pkts_to_process; pkt++) { @@ -499,7 +506,7 @@ static int __octep_oq_process_rx(struct octep_device *oct, napi_gro_receive(oq->napi, skb); } - oq->host_read_idx = read_idx; + WRITE_ONCE(oq->host_read_idx, read_idx); oq->refill_count += desc_used; oq->stats->packets += pkt; oq->stats->bytes += rx_bytes; @@ -522,22 +529,26 @@ int octep_oq_process_rx(struct octep_oq *oq, int budget) { u32 pkts_available, pkts_processed, total_pkts_processed; struct octep_device *oct = oq->octep_dev; + u32 pkts_pending; pkts_available = 0; pkts_processed = 0; total_pkts_processed = 0; while (total_pkts_processed < budget) { /* update pending count only when current one exhausted */ - if (oq->pkts_pending == 0) + pkts_pending = READ_ONCE(oq->pkts_pending); + if (pkts_pending == 0) octep_oq_check_hw_for_pkts(oct, oq); + pkts_pending = READ_ONCE(oq->pkts_pending); pkts_available = min(budget - total_pkts_processed, - oq->pkts_pending); + pkts_pending); if (!pkts_available) break; pkts_processed = __octep_oq_process_rx(oct, oq, pkts_available); - oq->pkts_pending -= pkts_processed; + pkts_pending = READ_ONCE(oq->pkts_pending); + WRITE_ONCE(oq->pkts_pending, (pkts_pending - pkts_processed)); total_pkts_processed += pkts_processed; } diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c index 562fe945b422..7f1b93cffb98 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c @@ -285,29 +285,46 @@ static void octep_vf_clean_irqs(struct octep_vf_device *oct) octep_vf_free_ioq_vectors(oct); } +/** + * octep_vf_update_pkt() - Update IQ/OQ IN/OUT_CNT registers. + * + * @iq: Octeon Tx queue data structure. + * @oq: Octeon Rx queue data structure. + */ + +static void octep_vf_update_pkt(struct octep_vf_iq *iq, struct octep_vf_oq *oq) +{ + u32 pkts_pend = READ_ONCE(oq->pkts_pending); + u32 last_pkt_count = READ_ONCE(oq->last_pkt_count); + u32 pkts_processed = READ_ONCE(iq->pkts_processed); + u32 pkt_in_done = READ_ONCE(iq->pkt_in_done); + + netdev_dbg(iq->netdev, "enabling intr for Q-%u\n", iq->q_no); + if (pkts_processed) { + writel(pkts_processed, iq->inst_cnt_reg); + readl(iq->inst_cnt_reg); + WRITE_ONCE(iq->pkt_in_done, (pkt_in_done - pkts_processed)); + WRITE_ONCE(iq->pkts_processed, 0); + } + if (last_pkt_count - pkts_pend) { + writel(last_pkt_count - pkts_pend, oq->pkts_sent_reg); + readl(oq->pkts_sent_reg); + WRITE_ONCE(oq->last_pkt_count, pkts_pend); + } + + /* Flush the previous wrties before writing to RESEND bit */ + smp_wmb(); +} + /** * octep_vf_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue. * * @iq: Octeon Tx queue data structure. * @oq: Octeon Rx queue data structure. */ -static void octep_vf_enable_ioq_irq(struct octep_vf_iq *iq, struct octep_vf_oq *oq) +static void octep_vf_enable_ioq_irq(struct octep_vf_iq *iq, + struct octep_vf_oq *oq) { - u32 pkts_pend = oq->pkts_pending; - - netdev_dbg(iq->netdev, "enabling intr for Q-%u\n", iq->q_no); - if (iq->pkts_processed) { - writel(iq->pkts_processed, iq->inst_cnt_reg); - iq->pkt_in_done -= iq->pkts_processed; - iq->pkts_processed = 0; - } - if (oq->last_pkt_count - pkts_pend) { - writel(oq->last_pkt_count - pkts_pend, oq->pkts_sent_reg); - oq->last_pkt_count = pkts_pend; - } - - /* Flush the previous wrties before writing to RESEND bit */ - smp_wmb(); writeq(1UL << OCTEP_VF_OQ_INTR_RESEND_BIT, oq->pkts_sent_reg); writeq(1UL << OCTEP_VF_IQ_INTR_RESEND_BIT, iq->inst_cnt_reg); } @@ -333,6 +350,7 @@ static int octep_vf_napi_poll(struct napi_struct *napi, int budget) if (tx_pending || rx_done >= budget) return budget; + octep_vf_update_pkt(ioq_vector->iq, ioq_vector->oq); if (likely(napi_complete_done(napi, rx_done))) octep_vf_enable_ioq_irq(ioq_vector->iq, ioq_vector->oq); diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c index 6f865dbbba6c..b579d5b545c4 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c @@ -325,9 +325,16 @@ static int octep_vf_oq_check_hw_for_pkts(struct octep_vf_device *oct, struct octep_vf_oq *oq) { u32 pkt_count, new_pkts; + u32 last_pkt_count, pkts_pending; pkt_count = readl(oq->pkts_sent_reg); - new_pkts = pkt_count - oq->last_pkt_count; + last_pkt_count = READ_ONCE(oq->last_pkt_count); + new_pkts = pkt_count - last_pkt_count; + + if (pkt_count < last_pkt_count) { + dev_err(oq->dev, "OQ-%u pkt_count(%u) < oq->last_pkt_count(%u)\n", + oq->q_no, pkt_count, last_pkt_count); + } /* Clear the hardware packets counter register if the rx queue is * being processed continuously with-in a single interrupt and @@ -339,8 +346,9 @@ static int octep_vf_oq_check_hw_for_pkts(struct octep_vf_device *oct, pkt_count = readl(oq->pkts_sent_reg); new_pkts += pkt_count; } - oq->last_pkt_count = pkt_count; - oq->pkts_pending += new_pkts; + WRITE_ONCE(oq->last_pkt_count, pkt_count); + pkts_pending = READ_ONCE(oq->pkts_pending); + WRITE_ONCE(oq->pkts_pending, (pkts_pending + new_pkts)); return new_pkts; } @@ -369,7 +377,7 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct, struct sk_buff *skb; u32 read_idx; - read_idx = oq->host_read_idx; + read_idx = READ_ONCE(oq->host_read_idx); rx_bytes = 0; desc_used = 0; for (pkt = 0; pkt < pkts_to_process; pkt++) { @@ -463,7 +471,7 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct, napi_gro_receive(oq->napi, skb); } - oq->host_read_idx = read_idx; + WRITE_ONCE(oq->host_read_idx, read_idx); oq->refill_count += desc_used; oq->stats->packets += pkt; oq->stats->bytes += rx_bytes; @@ -486,22 +494,26 @@ int octep_vf_oq_process_rx(struct octep_vf_oq *oq, int budget) { u32 pkts_available, pkts_processed, total_pkts_processed; struct octep_vf_device *oct = oq->octep_vf_dev; + u32 pkts_pending; pkts_available = 0; pkts_processed = 0; total_pkts_processed = 0; while (total_pkts_processed < budget) { /* update pending count only when current one exhausted */ - if (oq->pkts_pending == 0) + pkts_pending = READ_ONCE(oq->pkts_pending); + if (pkts_pending == 0) octep_vf_oq_check_hw_for_pkts(oct, oq); + pkts_pending = READ_ONCE(oq->pkts_pending); pkts_available = min(budget - total_pkts_processed, - oq->pkts_pending); + pkts_pending); if (!pkts_available) break; pkts_processed = __octep_vf_oq_process_rx(oct, oq, pkts_available); - oq->pkts_pending -= pkts_processed; + pkts_pending = READ_ONCE(oq->pkts_pending); + WRITE_ONCE(oq->pkts_pending, (pkts_pending - pkts_processed)); total_pkts_processed += pkts_processed; } diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index e5e2ffa9c542..ddc321a02fda 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -3748,12 +3748,21 @@ static int mtk_xdp_setup(struct net_device *dev, struct bpf_prog *prog, mtk_stop(dev); old_prog = rcu_replace_pointer(eth->prog, prog, lockdep_rtnl_is_held()); + + if (netif_running(dev) && need_update) { + int err; + + err = mtk_open(dev); + if (err) { + rcu_assign_pointer(eth->prog, old_prog); + + return err; + } + } + if (old_prog) bpf_prog_put(old_prog); - if (netif_running(dev) && need_update) - return mtk_open(dev); - return 0; } diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 933e9d681ded..9017e806ecda 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1770,8 +1770,14 @@ static void mana_poll_tx_cq(struct mana_cq *cq) ndev = txq->ndev; apc = netdev_priv(ndev); + /* Limit CQEs polled to 4 wraparounds of the CQ to ensure the + * doorbell can be rung in time for the hardware's requirement + * of at least one doorbell ring every 8 wraparounds. + */ comp_read = mana_gd_poll_cq(cq->gdma_cq, completions, - CQE_POLLING_BUFFER); + min((cq->gdma_cq->queue_size / + COMP_ENTRY_SIZE) * 4, + CQE_POLLING_BUFFER)); if (comp_read < 1) return; @@ -2156,7 +2162,14 @@ static void mana_poll_rx_cq(struct mana_cq *cq) struct mana_rxq *rxq = cq->rxq; int comp_read, i; - comp_read = mana_gd_poll_cq(cq->gdma_cq, comp, CQE_POLLING_BUFFER); + /* Limit CQEs polled to 4 wraparounds of the CQ to ensure the + * doorbell can be rung in time for the hardware's requirement + * of at least one doorbell ring every 8 wraparounds. + */ + comp_read = mana_gd_poll_cq(cq->gdma_cq, comp, + min((cq->gdma_cq->queue_size / + COMP_ENTRY_SIZE) * 4, + CQE_POLLING_BUFFER)); WARN_ON_ONCE(comp_read > CQE_POLLING_BUFFER); rxq->xdp_flush = false; @@ -2201,11 +2214,11 @@ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) mana_gd_ring_cq(gdma_queue, SET_ARM_BIT); cq->work_done_since_doorbell = 0; napi_complete_done(&cq->napi, w); - } else if (cq->work_done_since_doorbell > - cq->gdma_cq->queue_size / COMP_ENTRY_SIZE * 4) { + } else if (cq->work_done_since_doorbell >= + (cq->gdma_cq->queue_size / COMP_ENTRY_SIZE) * 4) { /* MANA hardware requires at least one doorbell ring every 8 * wraparounds of CQ even if there is no need to arm the CQ. - * This driver rings the doorbell as soon as we have exceeded + * This driver rings the doorbell as soon as it has processed * 4 wraparounds. */ mana_gd_ring_cq(gdma_queue, 0); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 51c96a738151..33667a26708c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -323,6 +323,7 @@ struct stmmac_priv { void __iomem *ptpaddr; void __iomem *estaddr; unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + unsigned int num_double_vlans; int sfty_irq; int sfty_ce_irq; int sfty_ue_irq; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index e00aa42a1961..6827c99bde8c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -156,6 +156,7 @@ static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue); static void stmmac_flush_tx_descriptors(struct stmmac_priv *priv, int queue); static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode, u32 rxmode, u32 chan); +static int stmmac_vlan_restore(struct stmmac_priv *priv); #ifdef CONFIG_DEBUG_FS static const struct net_device_ops stmmac_netdev_ops; @@ -4107,6 +4108,8 @@ static int __stmmac_open(struct net_device *dev, phylink_start(priv->phylink); + stmmac_vlan_restore(priv); + ret = stmmac_request_irq(dev); if (ret) goto irq_error; @@ -6766,6 +6769,9 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double) hash = 0; } + if (!netif_running(priv->dev)) + return 0; + return stmmac_update_vlan_hash(priv, priv->hw, hash, pmatch, is_double); } @@ -6775,6 +6781,7 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double) static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid) { struct stmmac_priv *priv = netdev_priv(ndev); + unsigned int num_double_vlans; bool is_double = false; int ret; @@ -6786,7 +6793,8 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid is_double = true; set_bit(vid, priv->active_vlans); - ret = stmmac_vlan_update(priv, is_double); + num_double_vlans = priv->num_double_vlans + is_double; + ret = stmmac_vlan_update(priv, num_double_vlans); if (ret) { clear_bit(vid, priv->active_vlans); goto err_pm_put; @@ -6794,9 +6802,15 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid if (priv->hw->num_vlan) { ret = stmmac_add_hw_vlan_rx_fltr(priv, ndev, priv->hw, proto, vid); - if (ret) + if (ret) { + clear_bit(vid, priv->active_vlans); + stmmac_vlan_update(priv, priv->num_double_vlans); goto err_pm_put; + } } + + priv->num_double_vlans = num_double_vlans; + err_pm_put: pm_runtime_put(priv->device); @@ -6809,6 +6823,7 @@ err_pm_put: static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid) { struct stmmac_priv *priv = netdev_priv(ndev); + unsigned int num_double_vlans; bool is_double = false; int ret; @@ -6820,14 +6835,23 @@ static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vi is_double = true; clear_bit(vid, priv->active_vlans); + num_double_vlans = priv->num_double_vlans - is_double; + ret = stmmac_vlan_update(priv, num_double_vlans); + if (ret) { + set_bit(vid, priv->active_vlans); + goto del_vlan_error; + } if (priv->hw->num_vlan) { ret = stmmac_del_hw_vlan_rx_fltr(priv, ndev, priv->hw, proto, vid); - if (ret) + if (ret) { + set_bit(vid, priv->active_vlans); + stmmac_vlan_update(priv, priv->num_double_vlans); goto del_vlan_error; + } } - ret = stmmac_vlan_update(priv, is_double); + priv->num_double_vlans = num_double_vlans; del_vlan_error: pm_runtime_put(priv->device); @@ -6835,6 +6859,23 @@ del_vlan_error: return ret; } +static int stmmac_vlan_restore(struct stmmac_priv *priv) +{ + int ret; + + if (!(priv->dev->features & NETIF_F_VLAN_FEATURES)) + return 0; + + if (priv->hw->num_vlan) + stmmac_restore_hw_vlan_rx_fltr(priv, priv->dev, priv->hw); + + ret = stmmac_vlan_update(priv, priv->num_double_vlans); + if (ret) + netdev_err(priv->dev, "Failed to restore VLANs\n"); + + return ret; +} + static int stmmac_bpf(struct net_device *dev, struct netdev_bpf *bpf) { struct stmmac_priv *priv = netdev_priv(dev); @@ -8259,10 +8300,10 @@ int stmmac_resume(struct device *dev) stmmac_init_coalesce(priv); phylink_rx_clk_stop_block(priv->phylink); stmmac_set_rx_mode(ndev); - - stmmac_restore_hw_vlan_rx_fltr(priv, ndev, priv->hw); phylink_rx_clk_stop_unblock(priv->phylink); + stmmac_vlan_restore(priv); + stmmac_enable_all_queues(priv); stmmac_enable_all_dma_irq(priv); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c index b18404dd5a8b..e24efe3bfedb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c @@ -76,7 +76,9 @@ static int vlan_add_hw_rx_fltr(struct net_device *dev, } hw->vlan_filter[0] = vid; - vlan_write_single(dev, vid); + + if (netif_running(dev)) + vlan_write_single(dev, vid); return 0; } @@ -97,12 +99,15 @@ static int vlan_add_hw_rx_fltr(struct net_device *dev, return -EPERM; } - ret = vlan_write_filter(dev, hw, index, val); + if (netif_running(dev)) { + ret = vlan_write_filter(dev, hw, index, val); + if (ret) + return ret; + } - if (!ret) - hw->vlan_filter[index] = val; + hw->vlan_filter[index] = val; - return ret; + return 0; } static int vlan_del_hw_rx_fltr(struct net_device *dev, @@ -115,7 +120,9 @@ static int vlan_del_hw_rx_fltr(struct net_device *dev, if (hw->num_vlan == 1) { if ((hw->vlan_filter[0] & VLAN_TAG_VID) == vid) { hw->vlan_filter[0] = 0; - vlan_write_single(dev, 0); + + if (netif_running(dev)) + vlan_write_single(dev, 0); } return 0; } @@ -124,25 +131,23 @@ static int vlan_del_hw_rx_fltr(struct net_device *dev, for (i = 0; i < hw->num_vlan; i++) { if ((hw->vlan_filter[i] & VLAN_TAG_DATA_VEN) && ((hw->vlan_filter[i] & VLAN_TAG_DATA_VID) == vid)) { - ret = vlan_write_filter(dev, hw, i, 0); - if (!ret) - hw->vlan_filter[i] = 0; - else - return ret; + if (netif_running(dev)) { + ret = vlan_write_filter(dev, hw, i, 0); + if (ret) + return ret; + } + + hw->vlan_filter[i] = 0; } } - return ret; + return 0; } static void vlan_restore_hw_rx_fltr(struct net_device *dev, struct mac_device_info *hw) { - void __iomem *ioaddr = hw->pcsr; - u32 value; - u32 hash; - u32 val; int i; /* Single Rx VLAN Filter */ @@ -152,19 +157,8 @@ static void vlan_restore_hw_rx_fltr(struct net_device *dev, } /* Extended Rx VLAN Filter Enable */ - for (i = 0; i < hw->num_vlan; i++) { - if (hw->vlan_filter[i] & VLAN_TAG_DATA_VEN) { - val = hw->vlan_filter[i]; - vlan_write_filter(dev, hw, i, val); - } - } - - hash = readl(ioaddr + VLAN_HASH_TABLE); - if (hash & VLAN_VLHT) { - value = readl(ioaddr + VLAN_TAG); - value |= VLAN_VTHM; - writel(value, ioaddr + VLAN_TAG); - } + for (i = 0; i < hw->num_vlan; i++) + vlan_write_filter(dev, hw, i, hw->vlan_filter[i]); } static void vlan_update_hash(struct mac_device_info *hw, u32 hash, @@ -183,6 +177,10 @@ static void vlan_update_hash(struct mac_device_info *hw, u32 hash, value |= VLAN_EDVLP; value |= VLAN_ESVL; value |= VLAN_DOVLTC; + } else { + value &= ~VLAN_EDVLP; + value &= ~VLAN_ESVL; + value &= ~VLAN_DOVLTC; } writel(value, ioaddr + VLAN_TAG); @@ -193,6 +191,10 @@ static void vlan_update_hash(struct mac_device_info *hw, u32 hash, value |= VLAN_EDVLP; value |= VLAN_ESVL; value |= VLAN_DOVLTC; + } else { + value &= ~VLAN_EDVLP; + value &= ~VLAN_ESVL; + value &= ~VLAN_DOVLTC; } writel(value | perfect_match, ioaddr + VLAN_TAG); diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 5924db6be3fe..967918050433 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -391,7 +391,7 @@ static void am65_cpsw_nuss_ndo_slave_set_rx_mode(struct net_device *ndev) cpsw_ale_set_allmulti(common->ale, ndev->flags & IFF_ALLMULTI, port->port_id); - port_mask = ALE_PORT_HOST; + port_mask = BIT(port->port_id) | ALE_PORT_HOST; /* Clear all mcast from ALE */ cpsw_ale_flush_multicast(common->ale, port_mask, -1); diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index bb969dd435b4..be7b69319221 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -450,14 +450,13 @@ static void cpsw_ale_flush_mcast(struct cpsw_ale *ale, u32 *ale_entry, ale->port_mask_bits); if ((mask & port_mask) == 0) return; /* ports dont intersect, not interested */ - mask &= ~port_mask; + mask &= (~port_mask | ALE_PORT_HOST); - /* free if only remaining port is host port */ - if (mask) + if (mask == 0x0 || mask == ALE_PORT_HOST) + cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE); + else cpsw_ale_set_port_mask(ale_entry, mask, ale->port_mask_bits); - else - cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE); } int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid) diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 0939994c932f..42a881bee109 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -273,6 +273,14 @@ static int prueth_emac_common_start(struct prueth *prueth) if (ret) goto disable_class; + /* Reset link state to force reconfiguration in + * emac_adjust_link(). Without this, if the link was already up + * before restart, emac_adjust_link() won't detect any state + * change and will skip critical configuration like writing + * speed to firmware. + */ + emac->link = 0; + mutex_lock(&emac->ndev->phydev->lock); emac_adjust_link(emac->ndev); mutex_unlock(&emac->ndev->phydev->lock); diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 2db116fb1a7c..3c9acd6e49e8 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -617,7 +617,7 @@ static ssize_t sysdata_release_enabled_show(struct config_item *item, bool release_enabled; dynamic_netconsole_mutex_lock(); - release_enabled = !!(nt->sysdata_fields & SYSDATA_TASKNAME); + release_enabled = !!(nt->sysdata_fields & SYSDATA_RELEASE); dynamic_netconsole_mutex_unlock(); return sysfs_emit(buf, "%d\n", release_enabled); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 4af85728ac4f..0c83bbbea2e7 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -10054,6 +10054,7 @@ static const struct usb_device_id rtl8152_table[] = { { USB_DEVICE(VENDOR_ID_DLINK, 0xb301) }, { USB_DEVICE(VENDOR_ID_DELL, 0xb097) }, { USB_DEVICE(VENDOR_ID_ASUS, 0x1976) }, + { USB_DEVICE(VENDOR_ID_TRENDNET, 0xe02b) }, {} }; diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 05558b6afecd..17c941aac32d 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -2130,6 +2130,11 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) { struct ipv6hdr *pip6; + /* check if nd_tbl is not initiliazed due to + * ipv6.disable=1 set during boot + */ + if (!ipv6_stub->nd_tbl) + return false; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) return false; pip6 = ipv6_hdr(skb); diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index c6b88909b6b7..b253d1e3f405 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -5430,7 +5430,7 @@ int ath12k_mac_op_get_txpower(struct ieee80211_hw *hw, ar->last_tx_power_update)) goto send_tx_power; - params.pdev_id = ar->pdev->pdev_id; + params.pdev_id = ath12k_mac_get_target_pdev_id(ar); params.vdev_id = arvif->vdev_id; params.stats_id = WMI_REQUEST_PDEV_STAT; ret = ath12k_mac_get_fw_stats(ar, ¶ms); @@ -13452,7 +13452,7 @@ void ath12k_mac_op_sta_statistics(struct ieee80211_hw *hw, /* TODO: Use real NF instead of default one. */ signal = rate_info.rssi_comb; - params.pdev_id = ar->pdev->pdev_id; + params.pdev_id = ath12k_mac_get_target_pdev_id(ar); params.vdev_id = 0; params.stats_id = WMI_REQUEST_VDEV_STAT; @@ -13580,7 +13580,7 @@ void ath12k_mac_op_link_sta_statistics(struct ieee80211_hw *hw, spin_unlock_bh(&ar->ab->dp->dp_lock); if (!signal && ahsta->ahvif->vdev_type == WMI_VDEV_TYPE_STA) { - params.pdev_id = ar->pdev->pdev_id; + params.pdev_id = ath12k_mac_get_target_pdev_id(ar); params.vdev_id = 0; params.stats_id = WMI_REQUEST_VDEV_STAT; diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index eb7615a289f7..48fee9346de8 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -8241,8 +8241,6 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab, struct ath12k_fw_stats *stats = parse->stats; struct ath12k *ar; struct ath12k_link_vif *arvif; - struct ieee80211_sta *sta; - struct ath12k_sta *ahsta; struct ath12k_link_sta *arsta; int i, ret = 0; const void *data = ptr; @@ -8278,21 +8276,19 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab, arvif = ath12k_mac_get_arvif(ar, le32_to_cpu(src->vdev_id)); if (arvif) { - sta = ieee80211_find_sta_by_ifaddr(ath12k_ar_to_hw(ar), - arvif->bssid, - NULL); - if (sta) { - ahsta = ath12k_sta_to_ahsta(sta); - arsta = &ahsta->deflink; + spin_lock_bh(&ab->base_lock); + arsta = ath12k_link_sta_find_by_addr(ab, arvif->bssid); + if (arsta) { arsta->rssi_beacon = le32_to_cpu(src->beacon_snr); ath12k_dbg(ab, ATH12K_DBG_WMI, "wmi stats vdev id %d snr %d\n", src->vdev_id, src->beacon_snr); } else { - ath12k_dbg(ab, ATH12K_DBG_WMI, - "not found station bssid %pM for vdev stat\n", - arvif->bssid); + ath12k_warn(ab, + "not found link sta with bssid %pM for vdev stat\n", + arvif->bssid); } + spin_unlock_bh(&ab->base_lock); } data += sizeof(*src); @@ -8363,8 +8359,6 @@ static int ath12k_wmi_tlv_rssi_chain_parse(struct ath12k_base *ab, struct ath12k_fw_stats *stats = parse->stats; struct ath12k_link_vif *arvif; struct ath12k_link_sta *arsta; - struct ieee80211_sta *sta; - struct ath12k_sta *ahsta; struct ath12k *ar; int vdev_id; int j; @@ -8400,19 +8394,15 @@ static int ath12k_wmi_tlv_rssi_chain_parse(struct ath12k_base *ab, "stats bssid %pM vif %p\n", arvif->bssid, arvif->ahvif->vif); - sta = ieee80211_find_sta_by_ifaddr(ath12k_ar_to_hw(ar), - arvif->bssid, - NULL); - if (!sta) { - ath12k_dbg(ab, ATH12K_DBG_WMI, - "not found station of bssid %pM for rssi chain\n", - arvif->bssid); + guard(spinlock_bh)(&ab->base_lock); + arsta = ath12k_link_sta_find_by_addr(ab, arvif->bssid); + if (!arsta) { + ath12k_warn(ab, + "not found link sta with bssid %pM for rssi chain\n", + arvif->bssid); return -EPROTO; } - ahsta = ath12k_sta_to_ahsta(sta); - arsta = &ahsta->deflink; - BUILD_BUG_ON(ARRAY_SIZE(arsta->chain_signal) > ARRAY_SIZE(stats_rssi->rssi_avg_beacon)); diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c index 3304b5971be0..b41ca1410da9 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c @@ -413,6 +413,7 @@ mt76_connac2_mac_write_txwi_80211(struct mt76_dev *dev, __le32 *txwi, u32 val; if (ieee80211_is_action(fc) && + skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 + 1 + 2 && mgmt->u.action.category == WLAN_CATEGORY_BACK && mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ) { u16 capab = le16_to_cpu(mgmt->u.action.u.addba_req.capab); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c index 871b67101976..0d9435900423 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c @@ -668,6 +668,7 @@ mt7925_mac_write_txwi_80211(struct mt76_dev *dev, __le32 *txwi, u32 val; if (ieee80211_is_action(fc) && + skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 && mgmt->u.action.category == WLAN_CATEGORY_BACK && mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ) tid = MT_TX_ADDBA; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 2560e2f46e89..d4f3ee943b47 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -800,6 +800,7 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi, u32 val; if (ieee80211_is_action(fc) && + skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 && mgmt->u.action.category == WLAN_CATEGORY_BACK && mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ) { if (is_mt7990(&dev->mt76)) diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c index 8c8e074a3a70..c7ae8031436a 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c +++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c @@ -668,7 +668,7 @@ static int rsi_mac80211_config(struct ieee80211_hw *hw, struct rsi_hw *adapter = hw->priv; struct rsi_common *common = adapter->priv; struct ieee80211_conf *conf = &hw->conf; - int status = -EOPNOTSUPP; + int status = 0; mutex_lock(&common->mutex); diff --git a/drivers/net/wireless/st/cw1200/pm.c b/drivers/net/wireless/st/cw1200/pm.c index 120f0379f81d..84eb15d729c7 100644 --- a/drivers/net/wireless/st/cw1200/pm.c +++ b/drivers/net/wireless/st/cw1200/pm.c @@ -264,12 +264,14 @@ int cw1200_wow_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) wiphy_err(priv->hw->wiphy, "PM request failed: %d. WoW is disabled.\n", ret); cw1200_wow_resume(hw); + mutex_unlock(&priv->conf_mutex); return -EBUSY; } /* Force resume if event is coming from the device. */ if (atomic_read(&priv->bh_rx)) { cw1200_wow_resume(hw); + mutex_unlock(&priv->conf_mutex); return -EAGAIN; } diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index 17dd417756f2..1c340a4a0930 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -1875,6 +1875,8 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw) wl->wow_enabled); WARN_ON(!wl->wow_enabled); + mutex_lock(&wl->mutex); + ret = pm_runtime_force_resume(wl->dev); if (ret < 0) { wl1271_error("ELP wakeup failure!"); @@ -1891,8 +1893,6 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw) run_irq_work = true; spin_unlock_irqrestore(&wl->wl_lock, flags); - mutex_lock(&wl->mutex); - /* test the recovery flag before calling any SDIO functions */ pending_recovery = test_bit(WL1271_FLAG_RECOVERY_IN_PROGRESS, &wl->flags); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index d316b35f404b..2ed673649c48 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1646,7 +1646,7 @@ static int xennet_xdp_set(struct net_device *dev, struct bpf_prog *prog, /* avoid the race with XDP headroom adjustment */ wait_event(module_wq, - xenbus_read_driver_state(np->xbdev->otherend) == + xenbus_read_driver_state(np->xbdev, np->xbdev->otherend) == XenbusStateReconfigured); np->netfront_xdp_enabled = true; @@ -1764,9 +1764,9 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev) do { xenbus_switch_state(dev, XenbusStateInitialising); err = wait_event_timeout(module_wq, - xenbus_read_driver_state(dev->otherend) != + xenbus_read_driver_state(dev, dev->otherend) != XenbusStateClosed && - xenbus_read_driver_state(dev->otherend) != + xenbus_read_driver_state(dev, dev->otherend) != XenbusStateUnknown, XENNET_TIMEOUT); } while (!err); @@ -2626,31 +2626,31 @@ static void xennet_bus_close(struct xenbus_device *dev) { int ret; - if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed) + if (xenbus_read_driver_state(dev, dev->otherend) == XenbusStateClosed) return; do { xenbus_switch_state(dev, XenbusStateClosing); ret = wait_event_timeout(module_wq, - xenbus_read_driver_state(dev->otherend) == - XenbusStateClosing || - xenbus_read_driver_state(dev->otherend) == - XenbusStateClosed || - xenbus_read_driver_state(dev->otherend) == - XenbusStateUnknown, - XENNET_TIMEOUT); + xenbus_read_driver_state(dev, dev->otherend) == + XenbusStateClosing || + xenbus_read_driver_state(dev, dev->otherend) == + XenbusStateClosed || + xenbus_read_driver_state(dev, dev->otherend) == + XenbusStateUnknown, + XENNET_TIMEOUT); } while (!ret); - if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed) + if (xenbus_read_driver_state(dev, dev->otherend) == XenbusStateClosed) return; do { xenbus_switch_state(dev, XenbusStateClosed); ret = wait_event_timeout(module_wq, - xenbus_read_driver_state(dev->otherend) == - XenbusStateClosed || - xenbus_read_driver_state(dev->otherend) == - XenbusStateUnknown, - XENNET_TIMEOUT); + xenbus_read_driver_state(dev, dev->otherend) == + XenbusStateClosed || + xenbus_read_driver_state(dev, dev->otherend) == + XenbusStateUnknown, + XENNET_TIMEOUT); } while (!ret); } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f5ebcaa2f859..58bf432ec5e6 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2046,14 +2046,10 @@ static u32 nvme_configure_atomic_write(struct nvme_ns *ns, if (id->nabspf) boundary = (le16_to_cpu(id->nabspf) + 1) * bs; } else { - /* - * Use the controller wide atomic write unit. This sucks - * because the limit is defined in terms of logical blocks while - * namespaces can have different formats, and because there is - * no clear language in the specification prohibiting different - * values for different controllers in the subsystem. - */ - atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs; + if (ns->ctrl->awupf) + dev_info_once(ns->ctrl->device, + "AWUPF ignored, only NAWUPF accepted\n"); + atomic_bs = bs; } lim->atomic_write_hw_max = atomic_bs; @@ -3222,7 +3218,6 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) memcpy(subsys->model, id->mn, sizeof(subsys->model)); subsys->vendor_id = le16_to_cpu(id->vid); subsys->cmic = id->cmic; - subsys->awupf = le16_to_cpu(id->awupf); /* Versions prior to 1.4 don't necessarily report a valid type */ if (id->cntrltype == NVME_CTRL_DISC || @@ -3655,6 +3650,7 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) dev_pm_qos_expose_latency_tolerance(ctrl->device); else if (!ctrl->apst_enabled && prev_apst_enabled) dev_pm_qos_hide_latency_tolerance(ctrl->device); + ctrl->awupf = le16_to_cpu(id->awupf); out_free: kfree(id); return ret; @@ -4186,13 +4182,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) nvme_mpath_add_disk(ns, info->anagrpid); nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name); - /* - * Set ns->disk->device->driver_data to ns so we can access - * ns->head->passthru_err_log_enabled in - * nvme_io_passthru_err_log_enabled_[store | show](). - */ - dev_set_drvdata(disk_to_dev(ns->disk), ns); - return; out_cleanup_ns_from_list: @@ -4865,6 +4854,13 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, if (ret) return ret; + /* + * If a previous admin queue exists (e.g., from before a reset), + * put it now before allocating a new one to avoid orphaning it. + */ + if (ctrl->admin_q) + blk_put_queue(ctrl->admin_q); + ctrl->admin_q = blk_mq_alloc_queue(set, &lim, NULL); if (IS_ERR(ctrl->admin_q)) { ret = PTR_ERR(ctrl->admin_q); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 5fe09e327b3d..ac3d4f400601 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -1290,8 +1290,8 @@ void nvmf_free_options(struct nvmf_ctrl_options *opts) kfree(opts->subsysnqn); kfree(opts->host_traddr); kfree(opts->host_iface); - kfree(opts->dhchap_secret); - kfree(opts->dhchap_ctrl_secret); + kfree_sensitive(opts->dhchap_secret); + kfree_sensitive(opts->dhchap_ctrl_secret); kfree(opts); } EXPORT_SYMBOL_GPL(nvmf_free_options); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 174027d1cc19..fc6800a9f7f9 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -1300,7 +1300,7 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) mutex_lock(&head->subsys->lock); /* * We are called when all paths have been removed, and at that point - * head->list is expected to be empty. However, nvme_remove_ns() and + * head->list is expected to be empty. However, nvme_ns_remove() and * nvme_init_ns_head() can run concurrently and so if head->delayed_ * removal_secs is configured, it is possible that by the time we reach * this point, head->list may no longer be empty. Therefore, we recheck @@ -1310,13 +1310,11 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) if (!list_empty(&head->list)) goto out; - if (head->delayed_removal_secs) { - /* - * Ensure that no one could remove this module while the head - * remove work is pending. - */ - if (!try_module_get(THIS_MODULE)) - goto out; + /* + * Ensure that no one could remove this module while the head + * remove work is pending. + */ + if (head->delayed_removal_secs && try_module_get(THIS_MODULE)) { mod_delayed_work(nvme_wq, &head->remove_work, head->delayed_removal_secs * HZ); } else { diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 9a5f28c5103c..9971045dbc05 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -180,6 +180,60 @@ enum nvme_quirks { NVME_QUIRK_DMAPOOL_ALIGN_512 = (1 << 22), }; +static inline char *nvme_quirk_name(enum nvme_quirks q) +{ + switch (q) { + case NVME_QUIRK_STRIPE_SIZE: + return "stripe_size"; + case NVME_QUIRK_IDENTIFY_CNS: + return "identify_cns"; + case NVME_QUIRK_DEALLOCATE_ZEROES: + return "deallocate_zeroes"; + case NVME_QUIRK_DELAY_BEFORE_CHK_RDY: + return "delay_before_chk_rdy"; + case NVME_QUIRK_NO_APST: + return "no_apst"; + case NVME_QUIRK_NO_DEEPEST_PS: + return "no_deepest_ps"; + case NVME_QUIRK_QDEPTH_ONE: + return "qdepth_one"; + case NVME_QUIRK_MEDIUM_PRIO_SQ: + return "medium_prio_sq"; + case NVME_QUIRK_IGNORE_DEV_SUBNQN: + return "ignore_dev_subnqn"; + case NVME_QUIRK_DISABLE_WRITE_ZEROES: + return "disable_write_zeroes"; + case NVME_QUIRK_SIMPLE_SUSPEND: + return "simple_suspend"; + case NVME_QUIRK_SINGLE_VECTOR: + return "single_vector"; + case NVME_QUIRK_128_BYTES_SQES: + return "128_bytes_sqes"; + case NVME_QUIRK_SHARED_TAGS: + return "shared_tags"; + case NVME_QUIRK_NO_TEMP_THRESH_CHANGE: + return "no_temp_thresh_change"; + case NVME_QUIRK_NO_NS_DESC_LIST: + return "no_ns_desc_list"; + case NVME_QUIRK_DMA_ADDRESS_BITS_48: + return "dma_address_bits_48"; + case NVME_QUIRK_SKIP_CID_GEN: + return "skip_cid_gen"; + case NVME_QUIRK_BOGUS_NID: + return "bogus_nid"; + case NVME_QUIRK_NO_SECONDARY_TEMP_THRESH: + return "no_secondary_temp_thresh"; + case NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND: + return "force_no_simple_suspend"; + case NVME_QUIRK_BROKEN_MSI: + return "broken_msi"; + case NVME_QUIRK_DMAPOOL_ALIGN_512: + return "dmapool_align_512"; + } + + return "unknown"; +} + /* * Common request structure for NVMe passthrough. All drivers must have * this structure as the first member of their request-private data. @@ -410,6 +464,8 @@ struct nvme_ctrl { enum nvme_ctrl_type cntrltype; enum nvme_dctype dctype; + + u16 awupf; /* 0's based value. */ }; static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl) @@ -442,7 +498,6 @@ struct nvme_subsystem { u8 cmic; enum nvme_subsys_type subtype; u16 vendor_id; - u16 awupf; /* 0's based value. */ struct ida ns_ida; #ifdef CONFIG_NVME_MULTIPATH enum nvme_iopolicy iopolicy; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 2f0c05719316..8d09fa7d7ff9 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -72,6 +72,13 @@ static_assert(MAX_PRP_RANGE / NVME_CTRL_PAGE_SIZE <= (1 /* prp1 */ + NVME_MAX_NR_DESCRIPTORS * PRPS_PER_PAGE)); +struct quirk_entry { + u16 vendor_id; + u16 dev_id; + u32 enabled_quirks; + u32 disabled_quirks; +}; + static int use_threaded_interrupts; module_param(use_threaded_interrupts, int, 0444); @@ -102,6 +109,143 @@ static unsigned int io_queue_depth = 1024; module_param_cb(io_queue_depth, &io_queue_depth_ops, &io_queue_depth, 0644); MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2 and < 4096"); +static struct quirk_entry *nvme_pci_quirk_list; +static unsigned int nvme_pci_quirk_count; + +/* Helper to parse individual quirk names */ +static int nvme_parse_quirk_names(char *quirk_str, struct quirk_entry *entry) +{ + int i; + size_t field_len; + bool disabled, found; + char *p = quirk_str, *field; + + while ((field = strsep(&p, ",")) && *field) { + disabled = false; + found = false; + + if (*field == '^') { + /* Skip the '^' character */ + disabled = true; + field++; + } + + field_len = strlen(field); + for (i = 0; i < 32; i++) { + unsigned int bit = 1U << i; + char *q_name = nvme_quirk_name(bit); + size_t q_len = strlen(q_name); + + if (!strcmp(q_name, "unknown")) + break; + + if (!strcmp(q_name, field) && + q_len == field_len) { + if (disabled) + entry->disabled_quirks |= bit; + else + entry->enabled_quirks |= bit; + found = true; + break; + } + } + + if (!found) { + pr_err("nvme: unrecognized quirk %s\n", field); + return -EINVAL; + } + } + return 0; +} + +/* Helper to parse a single VID:DID:quirk_names entry */ +static int nvme_parse_quirk_entry(char *s, struct quirk_entry *entry) +{ + char *field; + + field = strsep(&s, ":"); + if (!field || kstrtou16(field, 16, &entry->vendor_id)) + return -EINVAL; + + field = strsep(&s, ":"); + if (!field || kstrtou16(field, 16, &entry->dev_id)) + return -EINVAL; + + field = strsep(&s, ":"); + if (!field) + return -EINVAL; + + return nvme_parse_quirk_names(field, entry); +} + +static int quirks_param_set(const char *value, const struct kernel_param *kp) +{ + int count, err, i; + struct quirk_entry *qlist; + char *field, *val, *sep_ptr; + + err = param_set_copystring(value, kp); + if (err) + return err; + + val = kstrdup(value, GFP_KERNEL); + if (!val) + return -ENOMEM; + + if (!*val) + goto out_free_val; + + count = 1; + for (i = 0; val[i]; i++) { + if (val[i] == '-') + count++; + } + + qlist = kcalloc(count, sizeof(*qlist), GFP_KERNEL); + if (!qlist) { + err = -ENOMEM; + goto out_free_val; + } + + i = 0; + sep_ptr = val; + while ((field = strsep(&sep_ptr, "-"))) { + if (nvme_parse_quirk_entry(field, &qlist[i])) { + pr_err("nvme: failed to parse quirk string %s\n", + value); + goto out_free_qlist; + } + + i++; + } + + kfree(nvme_pci_quirk_list); + nvme_pci_quirk_count = count; + nvme_pci_quirk_list = qlist; + goto out_free_val; + +out_free_qlist: + kfree(qlist); +out_free_val: + kfree(val); + return err; +} + +static char quirks_param[128]; +static const struct kernel_param_ops quirks_param_ops = { + .set = quirks_param_set, + .get = param_get_string, +}; + +static struct kparam_string quirks_param_string = { + .maxlen = sizeof(quirks_param), + .string = quirks_param, +}; + +module_param_cb(quirks, &quirks_param_ops, &quirks_param_string, 0444); +MODULE_PARM_DESC(quirks, "Enable/disable NVMe quirks by specifying " + "quirks=VID:DID:quirk_names"); + static int io_queue_count_set(const char *val, const struct kernel_param *kp) { unsigned int n; @@ -1496,7 +1640,8 @@ static int nvme_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) struct nvme_queue *nvmeq = hctx->driver_data; bool found; - if (!nvme_cqe_pending(nvmeq)) + if (!test_bit(NVMEQ_POLLED, &nvmeq->flags) || + !nvme_cqe_pending(nvmeq)) return 0; spin_lock(&nvmeq->cq_poll_lock); @@ -2774,7 +2919,25 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) dev->nr_write_queues = write_queues; dev->nr_poll_queues = poll_queues; - nr_io_queues = dev->nr_allocated_queues - 1; + if (dev->ctrl.tagset) { + /* + * The set's maps are allocated only once at initialization + * time. We can't add special queues later if their mq_map + * wasn't preallocated. + */ + if (dev->ctrl.tagset->nr_maps < 3) + dev->nr_poll_queues = 0; + if (dev->ctrl.tagset->nr_maps < 2) + dev->nr_write_queues = 0; + } + + /* + * The initial number of allocated queue slots may be too large if the + * user reduced the special queue parameters. Cap the value to the + * number we need for this round. + */ + nr_io_queues = min(nvme_max_io_queues(dev), + dev->nr_allocated_queues - 1); result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues); if (result < 0) return result; @@ -3458,12 +3621,25 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev) return 0; } +static struct quirk_entry *detect_dynamic_quirks(struct pci_dev *pdev) +{ + int i; + + for (i = 0; i < nvme_pci_quirk_count; i++) + if (pdev->vendor == nvme_pci_quirk_list[i].vendor_id && + pdev->device == nvme_pci_quirk_list[i].dev_id) + return &nvme_pci_quirk_list[i]; + + return NULL; +} + static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev, const struct pci_device_id *id) { unsigned long quirks = id->driver_data; int node = dev_to_node(&pdev->dev); struct nvme_dev *dev; + struct quirk_entry *qentry; int ret = -ENOMEM; dev = kzalloc_node(struct_size(dev, descriptor_pools, nr_node_ids), @@ -3495,6 +3671,11 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev, "platform quirk: setting simple suspend\n"); quirks |= NVME_QUIRK_SIMPLE_SUSPEND; } + qentry = detect_dynamic_quirks(pdev); + if (qentry) { + quirks |= qentry->enabled_quirks; + quirks &= ~qentry->disabled_quirks; + } ret = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops, quirks); if (ret) @@ -4095,6 +4276,7 @@ static int __init nvme_init(void) static void __exit nvme_exit(void) { + kfree(nvme_pci_quirk_list); pci_unregister_driver(&nvme_driver); flush_workqueue(nvme_wq); } diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c index ad2ecc2f49a9..fe7dbe264815 100644 --- a/drivers/nvme/host/pr.c +++ b/drivers/nvme/host/pr.c @@ -242,7 +242,7 @@ static int nvme_pr_read_keys(struct block_device *bdev, if (rse_len > U32_MAX) return -EINVAL; - rse = kzalloc(rse_len, GFP_KERNEL); + rse = kvzalloc(rse_len, GFP_KERNEL); if (!rse) return -ENOMEM; @@ -267,7 +267,7 @@ static int nvme_pr_read_keys(struct block_device *bdev, } free_rse: - kfree(rse); + kvfree(rse); return ret; } diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c index 29430949ce2f..16c6fea4b2db 100644 --- a/drivers/nvme/host/sysfs.c +++ b/drivers/nvme/host/sysfs.c @@ -601,6 +601,28 @@ static ssize_t dctype_show(struct device *dev, } static DEVICE_ATTR_RO(dctype); +static ssize_t quirks_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + int count = 0, i; + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + unsigned long quirks = ctrl->quirks; + + if (!quirks) + return sysfs_emit(buf, "none\n"); + + for (i = 0; quirks; ++i) { + if (quirks & 1) { + count += sysfs_emit_at(buf, count, "%s\n", + nvme_quirk_name(BIT(i))); + } + quirks >>= 1; + } + + return count; +} +static DEVICE_ATTR_RO(quirks); + #ifdef CONFIG_NVME_HOST_AUTH static ssize_t nvme_ctrl_dhchap_secret_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -742,6 +764,7 @@ static struct attribute *nvme_dev_attrs[] = { &dev_attr_kato.attr, &dev_attr_cntrltype.attr, &dev_attr_dctype.attr, + &dev_attr_quirks.attr, #ifdef CONFIG_NVME_HOST_AUTH &dev_attr_dhchap_secret.attr, &dev_attr_dhchap_ctrl_secret.attr, diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 9ab3f61196a3..243dab830dc8 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -25,7 +25,8 @@ struct nvme_tcp_queue; -/* Define the socket priority to use for connections were it is desirable +/* + * Define the socket priority to use for connections where it is desirable * that the NIC consider performing optimized packet processing or filtering. * A non-zero value being sufficient to indicate general consideration of any * possible optimization. Making it a module param allows for alternative @@ -926,7 +927,7 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb, req->curr_bio = req->curr_bio->bi_next; /* - * If we don`t have any bios it means that controller + * If we don't have any bios it means the controller * sent more data than we requested, hence error */ if (!req->curr_bio) { diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 866048f07e61..b63af3b643a6 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -491,6 +491,7 @@ fcloop_t2h_xmt_ls_rsp(struct nvme_fc_local_port *localport, struct fcloop_rport *rport = remoteport->private; struct nvmet_fc_target_port *targetport = rport->targetport; struct fcloop_tport *tport; + int ret = 0; if (!targetport) { /* @@ -500,12 +501,18 @@ fcloop_t2h_xmt_ls_rsp(struct nvme_fc_local_port *localport, * We end up here from delete association exchange: * nvmet_fc_xmt_disconnect_assoc sends an async request. * - * Return success because this is what LLDDs do; silently - * drop the response. + * Return success when remoteport is still online because this + * is what LLDDs do and silently drop the response. Otherwise, + * return with error to signal upper layer to perform the lsrsp + * resource cleanup. */ - lsrsp->done(lsrsp); + if (remoteport->port_state == FC_OBJSTATE_ONLINE) + lsrsp->done(lsrsp); + else + ret = -ENODEV; + kmem_cache_free(lsreq_cache, tls_req); - return 0; + return ret; } memcpy(lsreq->rspaddr, lsrsp->rspbuf, diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index b8aaa292c3e7..cffc32d66032 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -856,7 +856,7 @@ static void pcifront_try_connect(struct pcifront_device *pdev) int err; /* Only connect once */ - if (xenbus_read_driver_state(pdev->xdev->nodename) != + if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename) != XenbusStateInitialised) return; @@ -876,7 +876,7 @@ static int pcifront_try_disconnect(struct pcifront_device *pdev) enum xenbus_state prev_state; - prev_state = xenbus_read_driver_state(pdev->xdev->nodename); + prev_state = xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename); if (prev_state >= XenbusStateClosing) goto out; @@ -895,7 +895,7 @@ out: static void pcifront_attach_devices(struct pcifront_device *pdev) { - if (xenbus_read_driver_state(pdev->xdev->nodename) == + if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename) == XenbusStateReconfiguring) pcifront_connect(pdev); } @@ -909,7 +909,7 @@ static int pcifront_detach_devices(struct pcifront_device *pdev) struct pci_dev *pci_dev; char str[64]; - state = xenbus_read_driver_state(pdev->xdev->nodename); + state = xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename); if (state == XenbusStateInitialised) { dev_dbg(&pdev->xdev->dev, "Handle skipped connect.\n"); /* We missed Connected and need to initialize. */ diff --git a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c index a8f82104a384..227c37c360e1 100644 --- a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c +++ b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c @@ -574,10 +574,9 @@ static int cs42l43_pin_probe(struct platform_device *pdev) if (child) { ret = devm_add_action_or_reset(&pdev->dev, cs42l43_fwnode_put, child); - if (ret) { - fwnode_handle_put(child); + if (ret) return ret; - } + if (!child->dev) child->dev = priv->dev; fwnode = child; diff --git a/drivers/pinctrl/cix/pinctrl-sky1.c b/drivers/pinctrl/cix/pinctrl-sky1.c index 5d0d8be815b2..938894058d86 100644 --- a/drivers/pinctrl/cix/pinctrl-sky1.c +++ b/drivers/pinctrl/cix/pinctrl-sky1.c @@ -522,11 +522,10 @@ static int __maybe_unused sky1_pinctrl_resume(struct device *dev) return pinctrl_force_default(spctl->pctl); } -const struct dev_pm_ops sky1_pinctrl_pm_ops = { +static const struct dev_pm_ops sky1_pinctrl_pm_ops = { SET_LATE_SYSTEM_SLEEP_PM_OPS(sky1_pinctrl_suspend, sky1_pinctrl_resume) }; -EXPORT_SYMBOL_GPL(sky1_pinctrl_pm_ops); static int sky1_pinctrl_probe(struct platform_device *pdev) { diff --git a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c index dfa32b11555c..e2293a872dcb 100644 --- a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c +++ b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c @@ -679,7 +679,6 @@ static int aml_dt_node_to_map_pinmux(struct pinctrl_dev *pctldev, unsigned int *num_maps) { struct device *dev = pctldev->dev; - struct device_node *pnode; unsigned long *configs = NULL; unsigned int num_configs = 0; struct property *prop; @@ -693,7 +692,7 @@ static int aml_dt_node_to_map_pinmux(struct pinctrl_dev *pctldev, return -ENOENT; } - pnode = of_get_parent(np); + struct device_node *pnode __free(device_node) = of_get_parent(np); if (!pnode) { dev_info(dev, "Missing function node\n"); return -EINVAL; diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c index 94b1d057197c..2b030bd0e6ad 100644 --- a/drivers/pinctrl/pinconf-generic.c +++ b/drivers/pinctrl/pinconf-generic.c @@ -351,13 +351,13 @@ int pinconf_generic_parse_dt_config(struct device_node *np, ret = parse_dt_cfg(np, dt_params, ARRAY_SIZE(dt_params), cfg, &ncfg); if (ret) - return ret; + goto out; if (pctldev && pctldev->desc->num_custom_params && pctldev->desc->custom_params) { ret = parse_dt_cfg(np, pctldev->desc->custom_params, pctldev->desc->num_custom_params, cfg, &ncfg); if (ret) - return ret; + goto out; } /* no configs found at all */ diff --git a/drivers/pinctrl/pinctrl-amdisp.c b/drivers/pinctrl/pinctrl-amdisp.c index efbf40c776ea..e0874cc086a7 100644 --- a/drivers/pinctrl/pinctrl-amdisp.c +++ b/drivers/pinctrl/pinctrl-amdisp.c @@ -80,7 +80,7 @@ static int amdisp_get_group_pins(struct pinctrl_dev *pctldev, return 0; } -const struct pinctrl_ops amdisp_pinctrl_ops = { +static const struct pinctrl_ops amdisp_pinctrl_ops = { .get_groups_count = amdisp_get_groups_count, .get_group_name = amdisp_get_group_name, .get_group_pins = amdisp_get_group_pins, diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c index a4b04bf6d081..5c055d344ac9 100644 --- a/drivers/pinctrl/pinctrl-cy8c95x0.c +++ b/drivers/pinctrl/pinctrl-cy8c95x0.c @@ -627,7 +627,7 @@ static int cy8c95x0_write_regs_mask(struct cy8c95x0_pinctrl *chip, int reg, bitmap_scatter(tmask, mask, chip->map, MAX_LINE); bitmap_scatter(tval, val, chip->map, MAX_LINE); - for_each_set_clump8(offset, bits, tmask, chip->tpin) { + for_each_set_clump8(offset, bits, tmask, chip->nport * BANK_SZ) { unsigned int i = offset / 8; write_val = bitmap_get_value8(tval, offset); @@ -655,7 +655,7 @@ static int cy8c95x0_read_regs_mask(struct cy8c95x0_pinctrl *chip, int reg, bitmap_scatter(tmask, mask, chip->map, MAX_LINE); bitmap_scatter(tval, val, chip->map, MAX_LINE); - for_each_set_clump8(offset, bits, tmask, chip->tpin) { + for_each_set_clump8(offset, bits, tmask, chip->nport * BANK_SZ) { unsigned int i = offset / 8; ret = cy8c95x0_regmap_read_bits(chip, reg, i, bits, &read_val); diff --git a/drivers/pinctrl/pinctrl-equilibrium.c b/drivers/pinctrl/pinctrl-equilibrium.c index 48b55c5bf8d4..ba1c867b7b89 100644 --- a/drivers/pinctrl/pinctrl-equilibrium.c +++ b/drivers/pinctrl/pinctrl-equilibrium.c @@ -23,7 +23,7 @@ #define PIN_NAME_LEN 10 #define PAD_REG_OFF 0x100 -static void eqbr_gpio_disable_irq(struct irq_data *d) +static void eqbr_irq_mask(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc); @@ -36,7 +36,7 @@ static void eqbr_gpio_disable_irq(struct irq_data *d) gpiochip_disable_irq(gc, offset); } -static void eqbr_gpio_enable_irq(struct irq_data *d) +static void eqbr_irq_unmask(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc); @@ -50,7 +50,7 @@ static void eqbr_gpio_enable_irq(struct irq_data *d) raw_spin_unlock_irqrestore(&gctrl->lock, flags); } -static void eqbr_gpio_ack_irq(struct irq_data *d) +static void eqbr_irq_ack(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc); @@ -62,10 +62,17 @@ static void eqbr_gpio_ack_irq(struct irq_data *d) raw_spin_unlock_irqrestore(&gctrl->lock, flags); } -static void eqbr_gpio_mask_ack_irq(struct irq_data *d) +static void eqbr_irq_mask_ack(struct irq_data *d) { - eqbr_gpio_disable_irq(d); - eqbr_gpio_ack_irq(d); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc); + unsigned int offset = irqd_to_hwirq(d); + unsigned long flags; + + raw_spin_lock_irqsave(&gctrl->lock, flags); + writel(BIT(offset), gctrl->membase + GPIO_IRNENCLR); + writel(BIT(offset), gctrl->membase + GPIO_IRNCR); + raw_spin_unlock_irqrestore(&gctrl->lock, flags); } static inline void eqbr_cfg_bit(void __iomem *addr, @@ -92,7 +99,7 @@ static int eqbr_irq_type_cfg(struct gpio_irq_type *type, return 0; } -static int eqbr_gpio_set_irq_type(struct irq_data *d, unsigned int type) +static int eqbr_irq_set_type(struct irq_data *d, unsigned int type) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc); @@ -166,11 +173,11 @@ static void eqbr_irq_handler(struct irq_desc *desc) static const struct irq_chip eqbr_irq_chip = { .name = "gpio_irq", - .irq_mask = eqbr_gpio_disable_irq, - .irq_unmask = eqbr_gpio_enable_irq, - .irq_ack = eqbr_gpio_ack_irq, - .irq_mask_ack = eqbr_gpio_mask_ack_irq, - .irq_set_type = eqbr_gpio_set_irq_type, + .irq_ack = eqbr_irq_ack, + .irq_mask = eqbr_irq_mask, + .irq_mask_ack = eqbr_irq_mask_ack, + .irq_unmask = eqbr_irq_unmask, + .irq_set_type = eqbr_irq_set_type, .flags = IRQCHIP_IMMUTABLE, GPIOCHIP_IRQ_RESOURCE_HELPERS, }; diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index d87c0b1de616..f15b18f334ee 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -3640,14 +3640,10 @@ static int rockchip_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, * or the gpio driver hasn't probed yet. */ scoped_guard(mutex, &bank->deferred_lock) { - if (!gpio || !gpio->direction_output) { - rc = rockchip_pinconf_defer_pin(bank, - pin - bank->pin_base, - param, arg); - if (rc) - return rc; - break; - } + if (!gpio || !gpio->direction_output) + return rockchip_pinconf_defer_pin(bank, + pin - bank->pin_base, + param, arg); } } diff --git a/drivers/pinctrl/qcom/pinctrl-qcs615.c b/drivers/pinctrl/qcom/pinctrl-qcs615.c index 4dfa820d4e77..f1c827ddbfbf 100644 --- a/drivers/pinctrl/qcom/pinctrl-qcs615.c +++ b/drivers/pinctrl/qcom/pinctrl-qcs615.c @@ -1067,6 +1067,7 @@ static const struct msm_pinctrl_soc_data qcs615_tlmm = { .ntiles = ARRAY_SIZE(qcs615_tiles), .wakeirq_map = qcs615_pdc_map, .nwakeirq_map = ARRAY_SIZE(qcs615_pdc_map), + .wakeirq_dual_edge_errata = true, }; static const struct of_device_id qcs615_tlmm_of_match[] = { diff --git a/drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c index d93af5f0e8d3..65411abfbfac 100644 --- a/drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c +++ b/drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c @@ -76,7 +76,7 @@ static const char * const pdm_clk_groups[] = { "gpio18" }; static const char * const pdm_rx_groups[] = { "gpio21", "gpio23", "gpio25" }; static const char * const pdm_sync_groups[] = { "gpio19" }; -const struct lpi_pingroup sdm660_lpi_pinctrl_groups[] = { +static const struct lpi_pingroup sdm660_lpi_pinctrl_groups[] = { LPI_PINGROUP_OFFSET(0, LPI_NO_SLEW, _, _, _, _, 0x0000), LPI_PINGROUP_OFFSET(1, LPI_NO_SLEW, _, _, _, _, 0x1000), LPI_PINGROUP_OFFSET(2, LPI_NO_SLEW, _, _, _, _, 0x2000), @@ -113,7 +113,7 @@ const struct lpi_pingroup sdm660_lpi_pinctrl_groups[] = { LPI_PINGROUP_OFFSET(31, LPI_NO_SLEW, _, _, _, _, 0xb010), }; -const struct lpi_function sdm660_lpi_pinctrl_functions[] = { +static const struct lpi_function sdm660_lpi_pinctrl_functions[] = { LPI_FUNCTION(comp_rx), LPI_FUNCTION(dmic1_clk), LPI_FUNCTION(dmic1_data), diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index 48434292a39b..c990b6118172 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -204,6 +204,32 @@ sunxi_pinctrl_desc_find_function_by_pin(struct sunxi_pinctrl *pctl, return NULL; } +static struct sunxi_desc_function * +sunxi_pinctrl_desc_find_function_by_pin_and_mux(struct sunxi_pinctrl *pctl, + const u16 pin_num, + const u8 muxval) +{ + for (unsigned int i = 0; i < pctl->desc->npins; i++) { + const struct sunxi_desc_pin *pin = pctl->desc->pins + i; + struct sunxi_desc_function *func = pin->functions; + + if (pin->pin.number != pin_num) + continue; + + if (pin->variant && !(pctl->variant & pin->variant)) + continue; + + while (func->name) { + if (func->muxval == muxval) + return func; + + func++; + } + } + + return NULL; +} + static int sunxi_pctrl_get_groups_count(struct pinctrl_dev *pctldev) { struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); @@ -930,6 +956,30 @@ static const struct pinmux_ops sunxi_pmx_ops = { .strict = true, }; +static int sunxi_pinctrl_gpio_get_direction(struct gpio_chip *chip, + unsigned int offset) +{ + struct sunxi_pinctrl *pctl = gpiochip_get_data(chip); + const struct sunxi_desc_function *func; + u32 pin = offset + chip->base; + u32 reg, shift, mask; + u8 muxval; + + sunxi_mux_reg(pctl, offset, ®, &shift, &mask); + + muxval = (readl(pctl->membase + reg) & mask) >> shift; + + func = sunxi_pinctrl_desc_find_function_by_pin_and_mux(pctl, pin, muxval); + if (!func) + return -ENODEV; + + if (!strcmp(func->name, "gpio_out")) + return GPIO_LINE_DIRECTION_OUT; + if (!strcmp(func->name, "gpio_in") || !strcmp(func->name, "irq")) + return GPIO_LINE_DIRECTION_IN; + return -EINVAL; +} + static int sunxi_pinctrl_gpio_direction_input(struct gpio_chip *chip, unsigned offset) { @@ -1599,6 +1649,7 @@ int sunxi_pinctrl_init_with_flags(struct platform_device *pdev, pctl->chip->request = gpiochip_generic_request; pctl->chip->free = gpiochip_generic_free; pctl->chip->set_config = gpiochip_generic_config; + pctl->chip->get_direction = sunxi_pinctrl_gpio_get_direction; pctl->chip->direction_input = sunxi_pinctrl_gpio_direction_input; pctl->chip->direction_output = sunxi_pinctrl_gpio_direction_output; pctl->chip->get = sunxi_pinctrl_gpio_get; diff --git a/drivers/platform/x86/asus-armoury.h b/drivers/platform/x86/asus-armoury.h index 6e9703bd5017..208f6fe16168 100644 --- a/drivers/platform/x86/asus-armoury.h +++ b/drivers/platform/x86/asus-armoury.h @@ -346,6 +346,35 @@ struct power_data { * _def is not required and will be assumed to be default == max if missing. */ static const struct dmi_system_id power_limits[] = { + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "FA401UM"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_max = 80, + .ppt_pl2_sppt_min = 35, + .ppt_pl2_sppt_max = 80, + .ppt_pl3_fppt_min = 35, + .ppt_pl3_fppt_max = 80, + .nv_dynamic_boost_min = 5, + .nv_dynamic_boost_max = 15, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + }, + .dc_data = &(struct power_limits) { + .ppt_pl1_spl_min = 25, + .ppt_pl1_spl_max = 35, + .ppt_pl2_sppt_min = 31, + .ppt_pl2_sppt_max = 44, + .ppt_pl3_fppt_min = 45, + .ppt_pl3_fppt_max = 65, + .nv_temp_target_min = 75, + .nv_temp_target_max = 87, + }, + }, + }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "FA401UV"), @@ -1457,6 +1486,38 @@ static const struct dmi_system_id power_limits[] = { }, }, }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GX650RX"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 28, + .ppt_pl1_spl_def = 70, + .ppt_pl1_spl_max = 90, + .ppt_pl2_sppt_min = 28, + .ppt_pl2_sppt_def = 70, + .ppt_pl2_sppt_max = 100, + .ppt_pl3_fppt_min = 28, + .ppt_pl3_fppt_def = 110, + .ppt_pl3_fppt_max = 125, + .nv_dynamic_boost_min = 5, + .nv_dynamic_boost_max = 25, + .nv_temp_target_min = 76, + .nv_temp_target_max = 87, + }, + .dc_data = &(struct power_limits) { + .ppt_pl1_spl_min = 28, + .ppt_pl1_spl_max = 50, + .ppt_pl2_sppt_min = 28, + .ppt_pl2_sppt_max = 50, + .ppt_pl3_fppt_min = 28, + .ppt_pl3_fppt_max = 65, + .nv_temp_target_min = 76, + .nv_temp_target_max = 87, + }, + }, + }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "G513I"), @@ -1708,6 +1769,20 @@ static const struct dmi_system_id power_limits[] = { .requires_fan_curve = true, }, }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "G733QS"), + }, + .driver_data = &(struct power_data) { + .ac_data = &(struct power_limits) { + .ppt_pl1_spl_min = 15, + .ppt_pl1_spl_max = 80, + .ppt_pl2_sppt_min = 15, + .ppt_pl2_sppt_max = 80, + }, + .requires_fan_curve = false, + }, + }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "G814J"), diff --git a/drivers/platform/x86/dell/alienware-wmi-wmax.c b/drivers/platform/x86/dell/alienware-wmi-wmax.c index e69b50162bb1..d1b4df91401b 100644 --- a/drivers/platform/x86/dell/alienware-wmi-wmax.c +++ b/drivers/platform/x86/dell/alienware-wmi-wmax.c @@ -175,7 +175,7 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m18"), }, - .driver_data = &generic_quirks, + .driver_data = &g_series_quirks, }, { .ident = "Alienware x15", diff --git a/drivers/platform/x86/dell/dell-wmi-base.c b/drivers/platform/x86/dell/dell-wmi-base.c index 4eefbade2f5e..e7a411ae9ca1 100644 --- a/drivers/platform/x86/dell/dell-wmi-base.c +++ b/drivers/platform/x86/dell/dell-wmi-base.c @@ -80,6 +80,12 @@ static const struct dmi_system_id dell_wmi_smbios_list[] __initconst = { static const struct key_entry dell_wmi_keymap_type_0000[] = { { KE_IGNORE, 0x003a, { KEY_CAPSLOCK } }, + /* Audio mute toggle */ + { KE_KEY, 0x0109, { KEY_MUTE } }, + + /* Mic mute toggle */ + { KE_KEY, 0x0150, { KEY_MICMUTE } }, + /* Meta key lock */ { KE_IGNORE, 0xe000, { KEY_RIGHTMETA } }, diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c b/drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c index 86ec962aace9..e586f7957946 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c @@ -93,7 +93,6 @@ int set_new_password(const char *password_type, const char *new) if (ret < 0) goto out; - print_hex_dump_bytes("set new password data: ", DUMP_PREFIX_NONE, buffer, buffer_size); ret = call_password_interface(wmi_priv.password_attr_wdev, buffer, buffer_size); /* on success copy the new password to current password */ if (!ret) diff --git a/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c index 470b9f44ed7a..af4d1920d488 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c @@ -94,8 +94,11 @@ int hp_alloc_enumeration_data(void) bioscfg_drv.enumeration_instances_count = hp_get_instance_count(HP_WMI_BIOS_ENUMERATION_GUID); - bioscfg_drv.enumeration_data = kzalloc_objs(*bioscfg_drv.enumeration_data, - bioscfg_drv.enumeration_instances_count); + if (!bioscfg_drv.enumeration_instances_count) + return -EINVAL; + bioscfg_drv.enumeration_data = kvcalloc(bioscfg_drv.enumeration_instances_count, + sizeof(*bioscfg_drv.enumeration_data), GFP_KERNEL); + if (!bioscfg_drv.enumeration_data) { bioscfg_drv.enumeration_instances_count = 0; return -ENOMEM; @@ -444,6 +447,6 @@ void hp_exit_enumeration_attributes(void) } bioscfg_drv.enumeration_instances_count = 0; - kfree(bioscfg_drv.enumeration_data); + kvfree(bioscfg_drv.enumeration_data); bioscfg_drv.enumeration_data = NULL; } diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index 304d9ac63c8a..68ede7e5757a 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -146,6 +146,7 @@ static const char * const omen_thermal_profile_boards[] = { "8900", "8901", "8902", "8912", "8917", "8918", "8949", "894A", "89EB", "8A15", "8A42", "8BAD", + "8E41", }; /* DMI Board names of Omen laptops that are specifically set to be thermal @@ -166,17 +167,26 @@ static const char * const omen_timed_thermal_profile_boards[] = { "8BAD", }; -/* DMI Board names of Victus 16-d1xxx laptops */ +/* DMI Board names of Victus 16-d laptops */ static const char * const victus_thermal_profile_boards[] = { + "88F8", "8A25", }; /* DMI Board names of Victus 16-r and Victus 16-s laptops */ static const struct dmi_system_id victus_s_thermal_profile_boards[] __initconst = { + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BAB") }, + .driver_data = (void *)&omen_v1_thermal_params, + }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BBE") }, .driver_data = (void *)&victus_s_thermal_params, }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BCD") }, + .driver_data = (void *)&omen_v1_thermal_params, + }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BD4") }, .driver_data = (void *)&victus_s_thermal_params, diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c index 0f8684f4464b..95c405c8bac0 100644 --- a/drivers/platform/x86/intel/hid.c +++ b/drivers/platform/x86/intel/hid.c @@ -135,6 +135,13 @@ static const struct dmi_system_id button_array_table[] = { DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Tablet Gen 2"), }, }, + { + .ident = "Lenovo ThinkPad X1 Fold 16 Gen 1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Fold 16 Gen 1"), + }, + }, { .ident = "Microsoft Surface Go 3", .matches = { @@ -189,6 +196,18 @@ static const struct dmi_system_id dmi_vgbs_allow_list[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Dell Pro Rugged 12 Tablet RA02260"), }, }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell 14 Plus 2-in-1 DB04250"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell 16 Plus 2-in-1 DB06250"), + }, + }, { } }; diff --git a/drivers/platform/x86/intel/int3472/discrete.c b/drivers/platform/x86/intel/int3472/discrete.c index 1455d9a7afca..1c65ce87cde0 100644 --- a/drivers/platform/x86/intel/int3472/discrete.c +++ b/drivers/platform/x86/intel/int3472/discrete.c @@ -223,6 +223,10 @@ static void int3472_get_con_id_and_polarity(struct int3472_discrete_device *int3 *con_id = "avdd"; *gpio_flags = GPIO_ACTIVE_HIGH; break; + case INT3472_GPIO_TYPE_DOVDD: + *con_id = "dovdd"; + *gpio_flags = GPIO_ACTIVE_HIGH; + break; case INT3472_GPIO_TYPE_HANDSHAKE: *con_id = "dvdd"; *gpio_flags = GPIO_ACTIVE_HIGH; @@ -251,6 +255,7 @@ static void int3472_get_con_id_and_polarity(struct int3472_discrete_device *int3 * 0x0b Power enable * 0x0c Clock enable * 0x0d Privacy LED + * 0x10 DOVDD (digital I/O voltage) * 0x13 Hotplug detect * * There are some known platform specific quirks where that does not quite @@ -332,6 +337,7 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares, case INT3472_GPIO_TYPE_CLK_ENABLE: case INT3472_GPIO_TYPE_PRIVACY_LED: case INT3472_GPIO_TYPE_POWER_ENABLE: + case INT3472_GPIO_TYPE_DOVDD: case INT3472_GPIO_TYPE_HANDSHAKE: gpio = skl_int3472_gpiod_get_from_temp_lookup(int3472, agpio, con_id, gpio_flags); if (IS_ERR(gpio)) { @@ -356,6 +362,7 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares, case INT3472_GPIO_TYPE_POWER_ENABLE: second_sensor = int3472->quirks.avdd_second_sensor; fallthrough; + case INT3472_GPIO_TYPE_DOVDD: case INT3472_GPIO_TYPE_HANDSHAKE: ret = skl_int3472_register_regulator(int3472, gpio, enable_time_us, con_id, second_sensor); diff --git a/drivers/platform/x86/lenovo/thinkpad_acpi.c b/drivers/platform/x86/lenovo/thinkpad_acpi.c index f9c736777908..8982d92dfd97 100644 --- a/drivers/platform/x86/lenovo/thinkpad_acpi.c +++ b/drivers/platform/x86/lenovo/thinkpad_acpi.c @@ -9525,14 +9525,16 @@ static int tpacpi_battery_get(int what, int battery, int *ret) { switch (what) { case THRESHOLD_START: - if ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_START, ret, battery)) + if (!battery_info.batteries[battery].start_support || + ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_START, ret, battery))) return -ENODEV; /* The value is in the low 8 bits of the response */ *ret = *ret & 0xFF; return 0; case THRESHOLD_STOP: - if ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_STOP, ret, battery)) + if (!battery_info.batteries[battery].stop_support || + ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_STOP, ret, battery))) return -ENODEV; /* Value is in lower 8 bits */ *ret = *ret & 0xFF; diff --git a/drivers/platform/x86/oxpec.c b/drivers/platform/x86/oxpec.c index 144a454103b9..6d4a53a2ed60 100644 --- a/drivers/platform/x86/oxpec.c +++ b/drivers/platform/x86/oxpec.c @@ -11,7 +11,7 @@ * * Copyright (C) 2022 Joaquín I. Aramendía * Copyright (C) 2024 Derek J. Clark - * Copyright (C) 2025 Antheas Kapenekakis + * Copyright (C) 2025-2026 Antheas Kapenekakis */ #include @@ -114,6 +114,13 @@ static const struct dmi_system_id dmi_table[] = { }, .driver_data = (void *)aok_zoe_a1, }, + { + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "AOKZOE"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "AOKZOE A2 Pro"), + }, + .driver_data = (void *)aok_zoe_a1, + }, { .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "AOKZOE"), @@ -142,6 +149,13 @@ static const struct dmi_system_id dmi_table[] = { }, .driver_data = (void *)oxp_2, }, + { + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "ONEXPLAYER APEX"), + }, + .driver_data = (void *)oxp_fly, + }, { .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"), @@ -212,6 +226,13 @@ static const struct dmi_system_id dmi_table[] = { }, .driver_data = (void *)oxp_mini_amd_pro, }, + { + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "ONEXPLAYER X1z"), + }, + .driver_data = (void *)oxp_x1, + }, { .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"), @@ -226,6 +247,13 @@ static const struct dmi_system_id dmi_table[] = { }, .driver_data = (void *)oxp_x1, }, + { + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "ONEXPLAYER X1Air"), + }, + .driver_data = (void *)oxp_x1, + }, { .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"), diff --git a/drivers/platform/x86/redmi-wmi.c b/drivers/platform/x86/redmi-wmi.c index 949236b93a32..e5cb348e3a39 100644 --- a/drivers/platform/x86/redmi-wmi.c +++ b/drivers/platform/x86/redmi-wmi.c @@ -20,7 +20,10 @@ static const struct key_entry redmi_wmi_keymap[] = { {KE_KEY, 0x00000201, {KEY_SELECTIVE_SCREENSHOT}}, {KE_KEY, 0x00000301, {KEY_ALL_APPLICATIONS}}, - {KE_KEY, 0x00001b01, {KEY_SETUP}}, + {KE_KEY, 0x00001b01, {KEY_CONFIG}}, + {KE_KEY, 0x00011b01, {KEY_CONFIG}}, + {KE_KEY, 0x00010101, {KEY_SWITCHVIDEOMODE}}, + {KE_KEY, 0x00001a01, {KEY_REFRESH_RATE_TOGGLE}}, /* AI button has code for each position */ {KE_KEY, 0x00011801, {KEY_ASSISTANT}}, @@ -32,6 +35,26 @@ static const struct key_entry redmi_wmi_keymap[] = { {KE_IGNORE, 0x00050501, {}}, {KE_IGNORE, 0x000a0501, {}}, + /* Xiaomi G Command Center */ + {KE_KEY, 0x00010a01, {KEY_VENDOR}}, + + /* OEM preset power mode */ + {KE_IGNORE, 0x00011601, {}}, + {KE_IGNORE, 0x00021601, {}}, + {KE_IGNORE, 0x00031601, {}}, + {KE_IGNORE, 0x00041601, {}}, + + /* Fn Lock state */ + {KE_IGNORE, 0x00000701, {}}, + {KE_IGNORE, 0x00010701, {}}, + + /* Fn+`/1/2/3/4 */ + {KE_KEY, 0x00011101, {KEY_F13}}, + {KE_KEY, 0x00011201, {KEY_F14}}, + {KE_KEY, 0x00011301, {KEY_F15}}, + {KE_KEY, 0x00011401, {KEY_F16}}, + {KE_KEY, 0x00011501, {KEY_F17}}, + {KE_END} }; diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index bdc19cd8d3ed..d83c387821ea 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -410,6 +410,16 @@ static const struct ts_dmi_data gdix1002_upside_down_data = { .properties = gdix1001_upside_down_props, }; +static const struct property_entry gdix1001_y_inverted_props[] = { + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + { } +}; + +static const struct ts_dmi_data gdix1001_y_inverted_data = { + .acpi_name = "GDIX1001", + .properties = gdix1001_y_inverted_props, +}; + static const struct property_entry gp_electronic_t701_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 960), PROPERTY_ENTRY_U32("touchscreen-size-y", 640), @@ -1658,6 +1668,14 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_SKU, "PN20170413488"), }, }, + { + /* SUPI S10 */ + .driver_data = (void *)&gdix1001_y_inverted_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SUPI"), + DMI_MATCH(DMI_PRODUCT_NAME, "S10"), + }, + }, { /* Techbite Arc 11.6 */ .driver_data = (void *)&techbite_arc_11_6_data, diff --git a/drivers/platform/x86/uniwill/uniwill-acpi.c b/drivers/platform/x86/uniwill/uniwill-acpi.c index fee93537aa43..6341dca20b76 100644 --- a/drivers/platform/x86/uniwill/uniwill-acpi.c +++ b/drivers/platform/x86/uniwill/uniwill-acpi.c @@ -314,8 +314,8 @@ #define LED_CHANNELS 3 #define LED_MAX_BRIGHTNESS 200 -#define UNIWILL_FEATURE_FN_LOCK_TOGGLE BIT(0) -#define UNIWILL_FEATURE_SUPER_KEY_TOGGLE BIT(1) +#define UNIWILL_FEATURE_FN_LOCK BIT(0) +#define UNIWILL_FEATURE_SUPER_KEY BIT(1) #define UNIWILL_FEATURE_TOUCHPAD_TOGGLE BIT(2) #define UNIWILL_FEATURE_LIGHTBAR BIT(3) #define UNIWILL_FEATURE_BATTERY BIT(4) @@ -330,6 +330,7 @@ struct uniwill_data { struct acpi_battery_hook hook; unsigned int last_charge_ctrl; struct mutex battery_lock; /* Protects the list of currently registered batteries */ + unsigned int last_status; unsigned int last_switch_status; struct mutex super_key_lock; /* Protects the toggling of the super key lock state */ struct list_head batteries; @@ -377,11 +378,15 @@ static const struct key_entry uniwill_keymap[] = { { KE_IGNORE, UNIWILL_OSD_CAPSLOCK, { KEY_CAPSLOCK }}, { KE_IGNORE, UNIWILL_OSD_NUMLOCK, { KEY_NUMLOCK }}, - /* Reported when the user locks/unlocks the super key */ - { KE_IGNORE, UNIWILL_OSD_SUPER_KEY_LOCK_ENABLE, { KEY_UNKNOWN }}, - { KE_IGNORE, UNIWILL_OSD_SUPER_KEY_LOCK_DISABLE, { KEY_UNKNOWN }}, + /* + * Reported when the user enables/disables the super key. + * Those events might even be reported when the change was done + * using the sysfs attribute! + */ + { KE_IGNORE, UNIWILL_OSD_SUPER_KEY_DISABLE, { KEY_UNKNOWN }}, + { KE_IGNORE, UNIWILL_OSD_SUPER_KEY_ENABLE, { KEY_UNKNOWN }}, /* Optional, might not be reported by all devices */ - { KE_IGNORE, UNIWILL_OSD_SUPER_KEY_LOCK_CHANGED, { KEY_UNKNOWN }}, + { KE_IGNORE, UNIWILL_OSD_SUPER_KEY_STATE_CHANGED, { KEY_UNKNOWN }}, /* Reported in manual mode when toggling the airplane mode status */ { KE_KEY, UNIWILL_OSD_RFKILL, { KEY_RFKILL }}, @@ -401,9 +406,6 @@ static const struct key_entry uniwill_keymap[] = { /* Reported when the user wants to toggle the mute status */ { KE_IGNORE, UNIWILL_OSD_MUTE, { KEY_MUTE }}, - /* Reported when the user locks/unlocks the Fn key */ - { KE_IGNORE, UNIWILL_OSD_FN_LOCK, { KEY_FN_ESC }}, - /* Reported when the user wants to toggle the brightness of the keyboard */ { KE_KEY, UNIWILL_OSD_KBDILLUMTOGGLE, { KEY_KBDILLUMTOGGLE }}, { KE_KEY, UNIWILL_OSD_KB_LED_LEVEL0, { KEY_KBDILLUMTOGGLE }}, @@ -576,6 +578,7 @@ static bool uniwill_volatile_reg(struct device *dev, unsigned int reg) case EC_ADDR_SECOND_FAN_RPM_1: case EC_ADDR_SECOND_FAN_RPM_2: case EC_ADDR_BAT_ALERT: + case EC_ADDR_BIOS_OEM: case EC_ADDR_PWM_1: case EC_ADDR_PWM_2: case EC_ADDR_TRIGGER: @@ -600,8 +603,8 @@ static const struct regmap_config uniwill_ec_config = { .use_single_write = true, }; -static ssize_t fn_lock_toggle_enable_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t fn_lock_store(struct device *dev, struct device_attribute *attr, const char *buf, + size_t count) { struct uniwill_data *data = dev_get_drvdata(dev); unsigned int value; @@ -624,8 +627,7 @@ static ssize_t fn_lock_toggle_enable_store(struct device *dev, struct device_att return count; } -static ssize_t fn_lock_toggle_enable_show(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t fn_lock_show(struct device *dev, struct device_attribute *attr, char *buf) { struct uniwill_data *data = dev_get_drvdata(dev); unsigned int value; @@ -638,10 +640,10 @@ static ssize_t fn_lock_toggle_enable_show(struct device *dev, struct device_attr return sysfs_emit(buf, "%d\n", !!(value & FN_LOCK_STATUS)); } -static DEVICE_ATTR_RW(fn_lock_toggle_enable); +static DEVICE_ATTR_RW(fn_lock); -static ssize_t super_key_toggle_enable_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t super_key_enable_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct uniwill_data *data = dev_get_drvdata(dev); unsigned int value; @@ -673,8 +675,7 @@ static ssize_t super_key_toggle_enable_store(struct device *dev, struct device_a return count; } -static ssize_t super_key_toggle_enable_show(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t super_key_enable_show(struct device *dev, struct device_attribute *attr, char *buf) { struct uniwill_data *data = dev_get_drvdata(dev); unsigned int value; @@ -687,7 +688,7 @@ static ssize_t super_key_toggle_enable_show(struct device *dev, struct device_at return sysfs_emit(buf, "%d\n", !(value & SUPER_KEY_LOCK_STATUS)); } -static DEVICE_ATTR_RW(super_key_toggle_enable); +static DEVICE_ATTR_RW(super_key_enable); static ssize_t touchpad_toggle_enable_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -881,8 +882,8 @@ static int uniwill_nvidia_ctgp_init(struct uniwill_data *data) static struct attribute *uniwill_attrs[] = { /* Keyboard-related */ - &dev_attr_fn_lock_toggle_enable.attr, - &dev_attr_super_key_toggle_enable.attr, + &dev_attr_fn_lock.attr, + &dev_attr_super_key_enable.attr, &dev_attr_touchpad_toggle_enable.attr, /* Lightbar-related */ &dev_attr_rainbow_animation.attr, @@ -897,13 +898,13 @@ static umode_t uniwill_attr_is_visible(struct kobject *kobj, struct attribute *a struct device *dev = kobj_to_dev(kobj); struct uniwill_data *data = dev_get_drvdata(dev); - if (attr == &dev_attr_fn_lock_toggle_enable.attr) { - if (uniwill_device_supports(data, UNIWILL_FEATURE_FN_LOCK_TOGGLE)) + if (attr == &dev_attr_fn_lock.attr) { + if (uniwill_device_supports(data, UNIWILL_FEATURE_FN_LOCK)) return attr->mode; } - if (attr == &dev_attr_super_key_toggle_enable.attr) { - if (uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY_TOGGLE)) + if (attr == &dev_attr_super_key_enable.attr) { + if (uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY)) return attr->mode; } @@ -1357,6 +1358,9 @@ static int uniwill_notifier_call(struct notifier_block *nb, unsigned long action switch (action) { case UNIWILL_OSD_BATTERY_ALERT: + if (!uniwill_device_supports(data, UNIWILL_FEATURE_BATTERY)) + return NOTIFY_DONE; + mutex_lock(&data->battery_lock); list_for_each_entry(entry, &data->batteries, head) { power_supply_changed(entry->battery); @@ -1369,6 +1373,13 @@ static int uniwill_notifier_call(struct notifier_block *nb, unsigned long action * gets implemented. */ + return NOTIFY_OK; + case UNIWILL_OSD_FN_LOCK: + if (!uniwill_device_supports(data, UNIWILL_FEATURE_FN_LOCK)) + return NOTIFY_DONE; + + sysfs_notify(&data->dev->kobj, NULL, "fn_lock"); + return NOTIFY_OK; default: mutex_lock(&data->input_lock); @@ -1503,9 +1514,21 @@ static void uniwill_shutdown(struct platform_device *pdev) regmap_clear_bits(data->regmap, EC_ADDR_AP_OEM, ENABLE_MANUAL_CTRL); } -static int uniwill_suspend_keyboard(struct uniwill_data *data) +static int uniwill_suspend_fn_lock(struct uniwill_data *data) { - if (!uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY_TOGGLE)) + if (!uniwill_device_supports(data, UNIWILL_FEATURE_FN_LOCK)) + return 0; + + /* + * The EC_ADDR_BIOS_OEM is marked as volatile, so we have to restore it + * ourselves. + */ + return regmap_read(data->regmap, EC_ADDR_BIOS_OEM, &data->last_status); +} + +static int uniwill_suspend_super_key(struct uniwill_data *data) +{ + if (!uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY)) return 0; /* @@ -1542,7 +1565,11 @@ static int uniwill_suspend(struct device *dev) struct uniwill_data *data = dev_get_drvdata(dev); int ret; - ret = uniwill_suspend_keyboard(data); + ret = uniwill_suspend_fn_lock(data); + if (ret < 0) + return ret; + + ret = uniwill_suspend_super_key(data); if (ret < 0) return ret; @@ -1560,12 +1587,21 @@ static int uniwill_suspend(struct device *dev) return 0; } -static int uniwill_resume_keyboard(struct uniwill_data *data) +static int uniwill_resume_fn_lock(struct uniwill_data *data) +{ + if (!uniwill_device_supports(data, UNIWILL_FEATURE_FN_LOCK)) + return 0; + + return regmap_update_bits(data->regmap, EC_ADDR_BIOS_OEM, FN_LOCK_STATUS, + data->last_status); +} + +static int uniwill_resume_super_key(struct uniwill_data *data) { unsigned int value; int ret; - if (!uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY_TOGGLE)) + if (!uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY)) return 0; ret = regmap_read(data->regmap, EC_ADDR_SWITCH_STATUS, &value); @@ -1608,7 +1644,11 @@ static int uniwill_resume(struct device *dev) if (ret < 0) return ret; - ret = uniwill_resume_keyboard(data); + ret = uniwill_resume_fn_lock(data); + if (ret < 0) + return ret; + + ret = uniwill_resume_super_key(data); if (ret < 0) return ret; @@ -1643,16 +1683,16 @@ static struct platform_driver uniwill_driver = { }; static struct uniwill_device_descriptor lapac71h_descriptor __initdata = { - .features = UNIWILL_FEATURE_FN_LOCK_TOGGLE | - UNIWILL_FEATURE_SUPER_KEY_TOGGLE | + .features = UNIWILL_FEATURE_FN_LOCK | + UNIWILL_FEATURE_SUPER_KEY | UNIWILL_FEATURE_TOUCHPAD_TOGGLE | UNIWILL_FEATURE_BATTERY | UNIWILL_FEATURE_HWMON, }; static struct uniwill_device_descriptor lapkc71f_descriptor __initdata = { - .features = UNIWILL_FEATURE_FN_LOCK_TOGGLE | - UNIWILL_FEATURE_SUPER_KEY_TOGGLE | + .features = UNIWILL_FEATURE_FN_LOCK | + UNIWILL_FEATURE_SUPER_KEY | UNIWILL_FEATURE_TOUCHPAD_TOGGLE | UNIWILL_FEATURE_LIGHTBAR | UNIWILL_FEATURE_BATTERY | diff --git a/drivers/platform/x86/uniwill/uniwill-wmi.h b/drivers/platform/x86/uniwill/uniwill-wmi.h index 48783b2e9ffb..fb1910c0f741 100644 --- a/drivers/platform/x86/uniwill/uniwill-wmi.h +++ b/drivers/platform/x86/uniwill/uniwill-wmi.h @@ -64,8 +64,8 @@ #define UNIWILL_OSD_KB_LED_LEVEL3 0x3E #define UNIWILL_OSD_KB_LED_LEVEL4 0x3F -#define UNIWILL_OSD_SUPER_KEY_LOCK_ENABLE 0x40 -#define UNIWILL_OSD_SUPER_KEY_LOCK_DISABLE 0x41 +#define UNIWILL_OSD_SUPER_KEY_DISABLE 0x40 +#define UNIWILL_OSD_SUPER_KEY_ENABLE 0x41 #define UNIWILL_OSD_MENU_JP 0x42 @@ -74,7 +74,7 @@ #define UNIWILL_OSD_RFKILL 0xA4 -#define UNIWILL_OSD_SUPER_KEY_LOCK_CHANGED 0xA5 +#define UNIWILL_OSD_SUPER_KEY_STATE_CHANGED 0xA5 #define UNIWILL_OSD_LIGHTBAR_STATE_CHANGED 0xA6 diff --git a/drivers/pmdomain/bcm/bcm2835-power.c b/drivers/pmdomain/bcm/bcm2835-power.c index 1d29addfe036..0450202bbee2 100644 --- a/drivers/pmdomain/bcm/bcm2835-power.c +++ b/drivers/pmdomain/bcm/bcm2835-power.c @@ -580,11 +580,11 @@ static int bcm2835_reset_status(struct reset_controller_dev *rcdev, switch (id) { case BCM2835_RESET_V3D: - return !PM_READ(PM_GRAFX & PM_V3DRSTN); + return !(PM_READ(PM_GRAFX) & PM_V3DRSTN); case BCM2835_RESET_H264: - return !PM_READ(PM_IMAGE & PM_H264RSTN); + return !(PM_READ(PM_IMAGE) & PM_H264RSTN); case BCM2835_RESET_ISP: - return !PM_READ(PM_IMAGE & PM_ISPRSTN); + return !(PM_READ(PM_IMAGE) & PM_ISPRSTN); default: return -EINVAL; } diff --git a/drivers/pmdomain/rockchip/pm-domains.c b/drivers/pmdomain/rockchip/pm-domains.c index 997e93c12951..44d34840ede7 100644 --- a/drivers/pmdomain/rockchip/pm-domains.c +++ b/drivers/pmdomain/rockchip/pm-domains.c @@ -1311,7 +1311,7 @@ static const struct rockchip_domain_info rk3576_pm_domains[] = { static const struct rockchip_domain_info rk3588_pm_domains[] = { [RK3588_PD_GPU] = DOMAIN_RK3588("gpu", 0x0, BIT(0), 0, 0x0, 0, BIT(1), 0x0, BIT(0), BIT(0), false, true), [RK3588_PD_NPU] = DOMAIN_RK3588("npu", 0x0, BIT(1), BIT(1), 0x0, 0, 0, 0x0, 0, 0, false, true), - [RK3588_PD_VCODEC] = DOMAIN_RK3588("vcodec", 0x0, BIT(2), BIT(2), 0x0, 0, 0, 0x0, 0, 0, false, false), + [RK3588_PD_VCODEC] = DOMAIN_RK3588("vcodec", 0x0, BIT(2), BIT(2), 0x0, 0, 0, 0x0, 0, 0, false, true), [RK3588_PD_NPUTOP] = DOMAIN_RK3588("nputop", 0x0, BIT(3), 0, 0x0, BIT(11), BIT(2), 0x0, BIT(1), BIT(1), false, false), [RK3588_PD_NPU1] = DOMAIN_RK3588("npu1", 0x0, BIT(4), 0, 0x0, BIT(12), BIT(3), 0x0, BIT(2), BIT(2), false, false), [RK3588_PD_NPU2] = DOMAIN_RK3588("npu2", 0x0, BIT(5), 0, 0x0, BIT(13), BIT(4), 0x0, BIT(3), BIT(3), false, false), diff --git a/drivers/regulator/mt6363-regulator.c b/drivers/regulator/mt6363-regulator.c index 03af5fa53600..0aebcbda0a19 100644 --- a/drivers/regulator/mt6363-regulator.c +++ b/drivers/regulator/mt6363-regulator.c @@ -899,10 +899,8 @@ static int mt6363_regulator_probe(struct platform_device *pdev) "Failed to map IRQ%d\n", info->hwirq); ret = devm_add_action_or_reset(dev, mt6363_irq_remove, &info->virq); - if (ret) { - irq_dispose_mapping(info->hwirq); + if (ret) return ret; - } config.driver_data = info; INIT_DELAYED_WORK(&info->oc_work, mt6363_oc_irq_enable_work); diff --git a/drivers/regulator/pf9453-regulator.c b/drivers/regulator/pf9453-regulator.c index 779a6fdb0574..eed3055d1c1c 100644 --- a/drivers/regulator/pf9453-regulator.c +++ b/drivers/regulator/pf9453-regulator.c @@ -809,7 +809,7 @@ static int pf9453_i2c_probe(struct i2c_client *i2c) } ret = devm_request_threaded_irq(pf9453->dev, pf9453->irq, NULL, pf9453_irq_handler, - (IRQF_TRIGGER_FALLING | IRQF_ONESHOT), + IRQF_ONESHOT, "pf9453-irq", pf9453); if (ret) return dev_err_probe(pf9453->dev, ret, "Failed to request IRQ: %d\n", pf9453->irq); diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index 5875065e2849..c744210cc901 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -1618,6 +1618,7 @@ retry_bring_ioc_ready: ioc_info(mrioc, "successfully transitioned to %s state\n", mpi3mr_iocstate_name(ioc_state)); + mpi3mr_clear_reset_history(mrioc); return 0; } ioc_status = readl(&mrioc->sysif_regs->ioc_status); @@ -1637,6 +1638,15 @@ retry_bring_ioc_ready: elapsed_time_sec = jiffies_to_msecs(jiffies - start_time)/1000; } while (elapsed_time_sec < mrioc->ready_timeout); + ioc_state = mpi3mr_get_iocstate(mrioc); + if (ioc_state == MRIOC_STATE_READY) { + ioc_info(mrioc, + "successfully transitioned to %s state after %llu seconds\n", + mpi3mr_iocstate_name(ioc_state), elapsed_time_sec); + mpi3mr_clear_reset_history(mrioc); + return 0; + } + out_failed: elapsed_time_sec = jiffies_to_msecs(jiffies - start_time)/1000; if ((retry < 2) && (elapsed_time_sec < (mrioc->ready_timeout - 60))) { diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index 0dada89d8d99..68a992494b12 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -190,7 +190,7 @@ static struct { {"IBM", "2076", NULL, BLIST_NO_VPD_SIZE}, {"IBM", "2105", NULL, BLIST_RETRY_HWERROR}, {"iomega", "jaz 1GB", "J.86", BLIST_NOTQ | BLIST_NOLUN}, - {"IOMEGA", "ZIP", NULL, BLIST_NOTQ | BLIST_NOLUN}, + {"IOMEGA", "ZIP", NULL, BLIST_NOTQ | BLIST_NOLUN | BLIST_SKIP_IO_HINTS}, {"IOMEGA", "Io20S *F", NULL, BLIST_KEY}, {"INSITE", "Floptical F*8I", NULL, BLIST_KEY}, {"INSITE", "I325VM", NULL, BLIST_KEY}, diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 60c06fa4ec32..2cfcf1f5d6a4 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -361,6 +361,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget, * since we use this queue depth most of times. */ if (scsi_realloc_sdev_budget_map(sdev, depth)) { + kref_put(&sdev->host->tagset_refcnt, scsi_mq_free_tags); put_device(&starget->dev); kfree(sdev); goto out; diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c index 42cde0017f12..989bcaee42ca 100644 --- a/drivers/scsi/xen-scsifront.c +++ b/drivers/scsi/xen-scsifront.c @@ -1175,7 +1175,7 @@ static void scsifront_backend_changed(struct xenbus_device *dev, return; } - if (xenbus_read_driver_state(dev->nodename) == + if (xenbus_read_driver_state(dev, dev->nodename) == XenbusStateInitialised) scsifront_do_lun_hotplug(info, VSCSIFRONT_OP_ADD_LUN); diff --git a/drivers/spi/spi-dw-dma.c b/drivers/spi/spi-dw-dma.c index 65adec7c7524..fe726b9b1780 100644 --- a/drivers/spi/spi-dw-dma.c +++ b/drivers/spi/spi-dw-dma.c @@ -271,7 +271,7 @@ static int dw_spi_dma_wait(struct dw_spi *dws, unsigned int len, u32 speed) msecs_to_jiffies(ms)); if (ms == 0) { - dev_err(&dws->ctlr->cur_msg->spi->dev, + dev_err(&dws->ctlr->dev, "DMA transaction timed out\n"); return -ETIMEDOUT; } diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 17608ea39d5a..a1c91d4515bc 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -108,8 +108,8 @@ static ssize_t target_core_item_dbroot_store(struct config_item *item, const char *page, size_t count) { ssize_t read_bytes; - struct file *fp; ssize_t r = -EINVAL; + struct path path = {}; mutex_lock(&target_devices_lock); if (target_devices) { @@ -131,17 +131,14 @@ static ssize_t target_core_item_dbroot_store(struct config_item *item, db_root_stage[read_bytes - 1] = '\0'; /* validate new db root before accepting it */ - fp = filp_open(db_root_stage, O_RDONLY, 0); - if (IS_ERR(fp)) { + r = kern_path(db_root_stage, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path); + if (r) { pr_err("db_root: cannot open: %s\n", db_root_stage); + if (r == -ENOTDIR) + pr_err("db_root: not a directory: %s\n", db_root_stage); goto unlock; } - if (!S_ISDIR(file_inode(fp)->i_mode)) { - filp_close(fp, NULL); - pr_err("db_root: not a directory: %s\n", db_root_stage); - goto unlock; - } - filp_close(fp, NULL); + path_put(&path); strscpy(db_root, db_root_stage); pr_debug("Target_Core_ConfigFS: db_root set to %s\n", db_root); diff --git a/drivers/video/fbdev/au1100fb.c b/drivers/video/fbdev/au1100fb.c index 1a04154bc535..c54cfcd832bb 100644 --- a/drivers/video/fbdev/au1100fb.c +++ b/drivers/video/fbdev/au1100fb.c @@ -380,8 +380,12 @@ static struct au1100fb_panel known_lcd_panels[] = #define panel_is_color(panel) (panel->control_base & LCD_CONTROL_PC) #define panel_swap_rgb(panel) (panel->control_base & LCD_CONTROL_CCO) -#if defined(CONFIG_COMPILE_TEST) && !defined(CONFIG_MIPS) -/* This is only defined to be able to compile this driver on non-mips platforms */ +#if defined(CONFIG_COMPILE_TEST) && (!defined(CONFIG_MIPS) || defined(CONFIG_64BIT)) +/* + * KSEG1ADDR() is defined in arch/mips/include/asm/addrspace.h + * for 32 bit configurations. Provide a stub for compile testing + * on other platforms. + */ #define KSEG1ADDR(x) (x) #endif diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c index 31903bfdce9f..897ae2a0b5a0 100644 --- a/drivers/xen/xen-acpi-processor.c +++ b/drivers/xen/xen-acpi-processor.c @@ -378,11 +378,8 @@ read_acpi_id(acpi_handle handle, u32 lvl, void *context, void **rv) acpi_psd[acpi_id].domain); } - status = acpi_evaluate_object(handle, "_CST", NULL, &buffer); - if (ACPI_FAILURE(status)) { - if (!pblk) - return AE_OK; - } + if (!pblk && !acpi_has_method(handle, "_CST")) + return AE_OK; /* .. and it has a C-state */ __set_bit(acpi_id, acpi_id_cst_present); diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c index 22ff9cf35fc4..b34785ba72e1 100644 --- a/drivers/xen/xen-pciback/xenbus.c +++ b/drivers/xen/xen-pciback/xenbus.c @@ -149,12 +149,12 @@ static int xen_pcibk_attach(struct xen_pcibk_device *pdev) mutex_lock(&pdev->dev_lock); /* Make sure we only do this setup once */ - if (xenbus_read_driver_state(pdev->xdev->nodename) != + if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename) != XenbusStateInitialised) goto out; /* Wait for frontend to state that it has published the configuration */ - if (xenbus_read_driver_state(pdev->xdev->otherend) != + if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->otherend) != XenbusStateInitialised) goto out; @@ -374,7 +374,7 @@ static int xen_pcibk_reconfigure(struct xen_pcibk_device *pdev, dev_dbg(&pdev->xdev->dev, "Reconfiguring device ...\n"); mutex_lock(&pdev->dev_lock); - if (xenbus_read_driver_state(pdev->xdev->nodename) != state) + if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename) != state) goto out; err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename, "num_devs", "%d", @@ -572,7 +572,7 @@ static int xen_pcibk_setup_backend(struct xen_pcibk_device *pdev) /* It's possible we could get the call to setup twice, so make sure * we're not already connected. */ - if (xenbus_read_driver_state(pdev->xdev->nodename) != + if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename) != XenbusStateInitWait) goto out; @@ -662,7 +662,7 @@ static void xen_pcibk_be_watch(struct xenbus_watch *watch, struct xen_pcibk_device *pdev = container_of(watch, struct xen_pcibk_device, be_watch); - switch (xenbus_read_driver_state(pdev->xdev->nodename)) { + switch (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename)) { case XenbusStateInitWait: xen_pcibk_setup_backend(pdev); break; diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 0ab1329e79de..27682cb5e58a 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -226,8 +226,9 @@ __xenbus_switch_state(struct xenbus_device *dev, struct xenbus_transaction xbt; int current_state; int err, abort; + bool vanished = false; - if (state == dev->state) + if (state == dev->state || dev->vanished) return 0; again: @@ -242,6 +243,10 @@ again: err = xenbus_scanf(xbt, dev->nodename, "state", "%d", ¤t_state); if (err != 1) goto abort; + if (current_state != dev->state && current_state == XenbusStateInitialising) { + vanished = true; + goto abort; + } err = xenbus_printf(xbt, dev->nodename, "state", "%d", state); if (err) { @@ -256,7 +261,7 @@ abort: if (err == -EAGAIN && !abort) goto again; xenbus_switch_fatal(dev, depth, err, "ending transaction"); - } else + } else if (!vanished) dev->state = state; return 0; @@ -931,14 +936,20 @@ static int xenbus_unmap_ring_hvm(struct xenbus_device *dev, void *vaddr) /** * xenbus_read_driver_state - read state from a store path + * @dev: xenbus device pointer * @path: path for driver * * Returns: the state of the driver rooted at the given store path, or * XenbusStateUnknown if no state can be read. */ -enum xenbus_state xenbus_read_driver_state(const char *path) +enum xenbus_state xenbus_read_driver_state(const struct xenbus_device *dev, + const char *path) { enum xenbus_state result; + + if (dev && dev->vanished) + return XenbusStateUnknown; + int err = xenbus_gather(XBT_NIL, path, "state", "%d", &result, NULL); if (err) result = XenbusStateUnknown; diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 9f9011cd7447..eb260eceb4d2 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -191,7 +191,7 @@ void xenbus_otherend_changed(struct xenbus_watch *watch, return; } - state = xenbus_read_driver_state(dev->otherend); + state = xenbus_read_driver_state(dev, dev->otherend); dev_dbg(&dev->dev, "state is %d, (%s), %s, %s\n", state, xenbus_strstate(state), dev->otherend_watch.node, path); @@ -364,7 +364,7 @@ void xenbus_dev_remove(struct device *_dev) * closed. */ if (!drv->allow_rebind || - xenbus_read_driver_state(dev->nodename) == XenbusStateClosing) + xenbus_read_driver_state(dev, dev->nodename) == XenbusStateClosing) xenbus_switch_state(dev, XenbusStateClosed); } EXPORT_SYMBOL_GPL(xenbus_dev_remove); @@ -444,6 +444,9 @@ static void xenbus_cleanup_devices(const char *path, struct bus_type *bus) info.dev = NULL; bus_for_each_dev(bus, NULL, &info, cleanup_dev); if (info.dev) { + dev_warn(&info.dev->dev, + "device forcefully removed from xenstore\n"); + info.dev->vanished = true; device_unregister(&info.dev->dev); put_device(&info.dev->dev); } @@ -514,7 +517,7 @@ int xenbus_probe_node(struct xen_bus_type *bus, size_t stringlen; char *tmpstring; - enum xenbus_state state = xenbus_read_driver_state(nodename); + enum xenbus_state state = xenbus_read_driver_state(NULL, nodename); if (state != XenbusStateInitialising) { /* Device is not new, so ignore it. This can happen if a @@ -659,6 +662,39 @@ void xenbus_dev_changed(const char *node, struct xen_bus_type *bus) return; dev = xenbus_device_find(root, &bus->bus); + /* + * Backend domain crash results in not coordinated frontend removal, + * without going through XenbusStateClosing. If this is a new instance + * of the same device Xen tools will have reset the state to + * XenbusStateInitializing. + * It might be that the backend crashed early during the init phase of + * device setup, in which case the known state would have been + * XenbusStateInitializing. So test the backend domid to match the + * saved one. In case the new backend happens to have the same domid as + * the old one, we can just carry on, as there is no inconsistency + * resulting in this case. + */ + if (dev && !strcmp(bus->root, "device")) { + enum xenbus_state state = xenbus_read_driver_state(dev, dev->nodename); + unsigned int backend = xenbus_read_unsigned(root, "backend-id", + dev->otherend_id); + + if (state == XenbusStateInitialising && + (state != dev->state || backend != dev->otherend_id)) { + /* + * State has been reset, assume the old one vanished + * and new one needs to be probed. + */ + dev_warn(&dev->dev, + "state reset occurred, reconnecting\n"); + dev->vanished = true; + } + if (dev->vanished) { + device_unregister(&dev->dev); + put_device(&dev->dev); + dev = NULL; + } + } if (!dev) xenbus_probe_node(bus, type, root); else diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c index f04707d1f667..ca04609730df 100644 --- a/drivers/xen/xenbus/xenbus_probe_frontend.c +++ b/drivers/xen/xenbus/xenbus_probe_frontend.c @@ -253,7 +253,7 @@ static int print_device_status(struct device *dev, void *data) } else if (xendev->state < XenbusStateConnected) { enum xenbus_state rstate = XenbusStateUnknown; if (xendev->otherend) - rstate = xenbus_read_driver_state(xendev->otherend); + rstate = xenbus_read_driver_state(xendev, xendev->otherend); pr_warn("Timeout connecting to device: %s (local state %d, remote state %d)\n", xendev->nodename, xendev->state, rstate); } diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index c284f48cfae4..2a886bece810 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -3340,7 +3340,6 @@ again: btrfs_abort_transaction(trans, ret); goto out_put; } - WARN_ON(ret); /* We've already setup this transaction, go ahead and exit */ if (block_group->cache_generation == trans->transid && diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index d97bbbd045e0..56ff8afe9a22 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1657,7 +1657,7 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans, if (unlikely(ret)) { btrfs_err(trans->fs_info, "failed to add delayed dir index item, root: %llu, inode: %llu, index: %llu, error: %d", - index, btrfs_root_id(node->root), node->inode_id, ret); + btrfs_root_id(node->root), node->inode_id, index, ret); btrfs_delayed_item_release_metadata(dir->root, item); btrfs_release_delayed_item(item); } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index f6fa15a1193f..e4fad777b034 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1994,7 +1994,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, int level = btrfs_super_log_root_level(disk_super); if (unlikely(fs_devices->rw_devices == 0)) { - btrfs_warn(fs_info, "log replay required on RO media"); + btrfs_err(fs_info, "log replay required on RO media"); return -EIO; } @@ -2008,9 +2008,9 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, check.owner_root = BTRFS_TREE_LOG_OBJECTID; log_tree_root->node = read_tree_block(fs_info, bytenr, &check); if (IS_ERR(log_tree_root->node)) { - btrfs_warn(fs_info, "failed to read log tree"); ret = PTR_ERR(log_tree_root->node); log_tree_root->node = NULL; + btrfs_err(fs_info, "failed to read log tree with error: %d", ret); btrfs_put_root(log_tree_root); return ret; } @@ -2023,9 +2023,9 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, /* returns with log_tree_root freed on success */ ret = btrfs_recover_log_trees(log_tree_root); btrfs_put_root(log_tree_root); - if (ret) { - btrfs_handle_fs_error(fs_info, ret, - "Failed to recover log tree"); + if (unlikely(ret)) { + ASSERT(BTRFS_FS_ERROR(fs_info) != 0); + btrfs_err(fs_info, "failed to recover log trees with error: %d", ret); return ret; } @@ -2972,7 +2972,6 @@ static int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info) task = kthread_run(btrfs_uuid_rescan_kthread, fs_info, "btrfs-uuid"); if (IS_ERR(task)) { /* fs_info->update_uuid_tree_gen remains 0 in all error case */ - btrfs_warn(fs_info, "failed to start uuid_rescan task"); up(&fs_info->uuid_tree_rescan_sem); return PTR_ERR(task); } @@ -3188,7 +3187,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount) if (incompat & ~BTRFS_FEATURE_INCOMPAT_SUPP) { btrfs_err(fs_info, "cannot mount because of unknown incompat features (0x%llx)", - incompat); + incompat & ~BTRFS_FEATURE_INCOMPAT_SUPP); return -EINVAL; } @@ -3220,7 +3219,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount) if (compat_ro_unsupp && is_rw_mount) { btrfs_err(fs_info, "cannot mount read-write because of unknown compat_ro features (0x%llx)", - compat_ro); + compat_ro_unsupp); return -EINVAL; } @@ -3233,7 +3232,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount) !btrfs_test_opt(fs_info, NOLOGREPLAY)) { btrfs_err(fs_info, "cannot replay dirty log with unsupported compat_ro features (0x%llx), try rescue=nologreplay", - compat_ro); + compat_ro_unsupp); return -EINVAL; } @@ -3642,7 +3641,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device fs_info->fs_root = btrfs_get_fs_root(fs_info, BTRFS_FS_TREE_OBJECTID, true); if (IS_ERR(fs_info->fs_root)) { ret = PTR_ERR(fs_info->fs_root); - btrfs_warn(fs_info, "failed to read fs tree: %d", ret); + btrfs_err(fs_info, "failed to read fs tree: %d", ret); fs_info->fs_root = NULL; goto fail_qgroup; } @@ -3663,8 +3662,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device btrfs_info(fs_info, "checking UUID tree"); ret = btrfs_check_uuid_tree(fs_info); if (ret) { - btrfs_warn(fs_info, - "failed to check the UUID tree: %d", ret); + btrfs_err(fs_info, "failed to check the UUID tree: %d", ret); close_ctree(fs_info); return ret; } @@ -4399,9 +4397,17 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) */ btrfs_flush_workqueue(fs_info->delayed_workers); - ret = btrfs_commit_super(fs_info); - if (ret) - btrfs_err(fs_info, "commit super ret %d", ret); + /* + * If the filesystem is shutdown, then an attempt to commit the + * super block (or any write) will just fail. Since we freeze + * the filesystem before shutting it down, the filesystem is in + * a consistent state and we don't need to commit super blocks. + */ + if (!btrfs_is_shutdown(fs_info)) { + ret = btrfs_commit_super(fs_info); + if (ret) + btrfs_err(fs_info, "commit super block returned %d", ret); + } } kthread_stop(fs_info->transaction_kthread); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 03cf9f242c70..b0d9baf5b412 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2933,9 +2933,15 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans) while (!TRANS_ABORTED(trans) && cached_state) { struct extent_state *next_state; - if (btrfs_test_opt(fs_info, DISCARD_SYNC)) + if (btrfs_test_opt(fs_info, DISCARD_SYNC)) { ret = btrfs_discard_extent(fs_info, start, end + 1 - start, NULL, true); + if (ret) { + btrfs_warn(fs_info, + "discard failed for extent [%llu, %llu]: errno=%d %s", + start, end, ret, btrfs_decode_error(ret)); + } + } next_state = btrfs_next_extent_state(unpin, cached_state); btrfs_clear_extent_dirty(unpin, start, end, &cached_state); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6efb543f1c24..a11fcc9e9f50 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1392,10 +1392,25 @@ static int cow_one_range(struct btrfs_inode *inode, struct folio *locked_folio, return ret; free_reserved: + /* + * If we have reserved an extent for the current range and failed to + * create the respective extent map or ordered extent, it means that + * when we reserved the extent we decremented the extent's size from + * the data space_info's bytes_may_use counter and + * incremented the space_info's bytes_reserved counter by the same + * amount. + * + * We must make sure extent_clear_unlock_delalloc() does not try + * to decrement again the data space_info's bytes_may_use counter, which + * will be handled by btrfs_free_reserved_extent(). + * + * Therefore we do not pass it the flag EXTENT_CLEAR_DATA_RESV, but only + * EXTENT_CLEAR_META_RESV. + */ extent_clear_unlock_delalloc(inode, file_offset, cur_end, locked_folio, cached, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | - EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, + EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV, PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); btrfs_qgroup_free_data(inode, NULL, file_offset, cur_len, NULL); @@ -4764,7 +4779,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry) spin_unlock(&dest->root_item_lock); btrfs_warn(fs_info, "attempt to delete subvolume %llu with active swapfile", - btrfs_root_id(root)); + btrfs_root_id(dest)); ret = -EPERM; goto out_up_write; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ae2173235c4d..a1fd44c44ecf 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4581,7 +4581,7 @@ static int btrfs_uring_read_extent(struct kiocb *iocb, struct iov_iter *iter, { struct btrfs_inode *inode = BTRFS_I(file_inode(iocb->ki_filp)); struct extent_io_tree *io_tree = &inode->io_tree; - struct page **pages; + struct page **pages = NULL; struct btrfs_uring_priv *priv = NULL; unsigned long nr_pages; int ret; @@ -4639,6 +4639,11 @@ out_fail: btrfs_unlock_extent(io_tree, start, lockend, &cached_state); btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); kfree(priv); + for (int i = 0; i < nr_pages; i++) { + if (pages[i]) + __free_page(pages[i]); + } + kfree(pages); return ret; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 3cdd9755dc52..3b2a6517d0b5 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -370,7 +370,7 @@ static bool squota_check_parent_usage(struct btrfs_fs_info *fs_info, struct btrf nr_members++; } mismatch = (parent->excl != excl_sum || parent->rfer != rfer_sum || - parent->excl_cmpr != excl_cmpr_sum || parent->rfer_cmpr != excl_cmpr_sum); + parent->excl_cmpr != excl_cmpr_sum || parent->rfer_cmpr != rfer_cmpr_sum); WARN(mismatch, "parent squota qgroup %hu/%llu has mismatched usage from its %d members. " diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 95db7c48fbad..a330d8624b83 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4723,6 +4723,7 @@ int btrfs_last_identity_remap_gone(struct btrfs_chunk_map *chunk_map, ret = btrfs_remove_dev_extents(trans, chunk_map); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); return ret; } @@ -4732,6 +4733,7 @@ int btrfs_last_identity_remap_gone(struct btrfs_chunk_map *chunk_map, if (unlikely(ret)) { mutex_unlock(&trans->fs_info->chunk_mutex); btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); return ret; } } @@ -4750,6 +4752,7 @@ int btrfs_last_identity_remap_gone(struct btrfs_chunk_map *chunk_map, ret = remove_chunk_stripes(trans, chunk_map, path); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); return ret; } @@ -5982,6 +5985,9 @@ static int remove_range_from_remap_tree(struct btrfs_trans_handle *trans, struct btrfs_block_group *dest_bg; dest_bg = btrfs_lookup_block_group(fs_info, new_addr); + if (unlikely(!dest_bg)) + return -EUCLEAN; + adjust_block_group_remap_bytes(trans, dest_bg, -overlap_length); btrfs_put_block_group(dest_bg); ret = btrfs_add_to_free_space_tree(trans, diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 81022d912abb..bc94bbc00772 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -743,7 +743,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr btrfs_warn_rl(fs_info, "scrub: tree block %llu mirror %u has bad fsid, has %pU want %pU", logical, stripe->mirror_num, - header->fsid, fs_info->fs_devices->fsid); + header->fsid, fs_info->fs_devices->metadata_uuid); return; } if (memcmp(header->chunk_tree_uuid, fs_info->chunk_tree_uuid, diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 452394b34d01..ac4c4573ee39 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1740,7 +1740,7 @@ static int check_extent_data_ref(struct extent_buffer *leaf, objectid > BTRFS_LAST_FREE_OBJECTID)) { extent_err(leaf, slot, "invalid extent data backref objectid value %llu", - root); + objectid); return -EUCLEAN; } if (unlikely(!IS_ALIGNED(offset, leaf->fs_info->sectorsize))) { @@ -1921,7 +1921,7 @@ static int check_dev_extent_item(const struct extent_buffer *leaf, if (unlikely(prev_key->offset + prev_len > key->offset)) { generic_err(leaf, slot, "dev extent overlap, prev offset %llu len %llu current offset %llu", - prev_key->objectid, prev_len, key->offset); + prev_key->offset, prev_len, key->offset); return -EUCLEAN; } } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 6fb0c4cd50ff..648bb09fc416 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6907,7 +6907,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, ret = btrfs_translate_remap(fs_info, &new_logical, length); if (ret) - return ret; + goto out; if (new_logical != logical) { btrfs_free_chunk_map(map); @@ -6921,8 +6921,10 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, } num_copies = btrfs_chunk_map_num_copies(map); - if (io_geom.mirror_num > num_copies) - return -EINVAL; + if (io_geom.mirror_num > num_copies) { + ret = -EINVAL; + goto out; + } map_offset = logical - map->start; io_geom.raid56_full_stripe_start = (u64)-1; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index bc82083e420a..00f0efaf12b2 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -80,18 +80,27 @@ static void iomap_set_range_uptodate(struct folio *folio, size_t off, { struct iomap_folio_state *ifs = folio->private; unsigned long flags; - bool uptodate = true; + bool mark_uptodate = true; if (folio_test_uptodate(folio)) return; if (ifs) { spin_lock_irqsave(&ifs->state_lock, flags); - uptodate = ifs_set_range_uptodate(folio, ifs, off, len); + /* + * If a read with bytes pending is in progress, we must not call + * folio_mark_uptodate(). The read completion path + * (iomap_read_end()) will call folio_end_read(), which uses XOR + * semantics to set the uptodate bit. If we set it here, the XOR + * in folio_end_read() will clear it, leaving the folio not + * uptodate. + */ + mark_uptodate = ifs_set_range_uptodate(folio, ifs, off, len) && + !ifs->read_bytes_pending; spin_unlock_irqrestore(&ifs->state_lock, flags); } - if (uptodate) + if (mark_uptodate) folio_mark_uptodate(folio); } diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 95254aa1b654..e911daedff65 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -87,6 +87,19 @@ static inline enum fserror_type iomap_dio_err_type(const struct iomap_dio *dio) return FSERR_DIRECTIO_READ; } +static inline bool should_report_dio_fserror(const struct iomap_dio *dio) +{ + switch (dio->error) { + case 0: + case -EAGAIN: + case -ENOTBLK: + /* don't send fsnotify for success or magic retry codes */ + return false; + default: + return true; + } +} + ssize_t iomap_dio_complete(struct iomap_dio *dio) { const struct iomap_dio_ops *dops = dio->dops; @@ -96,7 +109,7 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio) if (dops && dops->end_io) ret = dops->end_io(iocb, dio->size, ret, dio->flags); - if (dio->error) + if (should_report_dio_fserror(dio)) fserror_report_io(file_inode(iocb->ki_filp), iomap_dio_err_type(dio), offset, dio->size, dio->error, GFP_NOFS); diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c index 4d1ef8a2cee9..60546fa14dfe 100644 --- a/fs/iomap/ioend.c +++ b/fs/iomap/ioend.c @@ -215,17 +215,18 @@ ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio, WARN_ON_ONCE(!folio->private && map_len < dirty_len); switch (wpc->iomap.type) { - case IOMAP_INLINE: - WARN_ON_ONCE(1); - return -EIO; + case IOMAP_UNWRITTEN: + ioend_flags |= IOMAP_IOEND_UNWRITTEN; + break; + case IOMAP_MAPPED: + break; case IOMAP_HOLE: return map_len; default: - break; + WARN_ON_ONCE(1); + return -EIO; } - if (wpc->iomap.type == IOMAP_UNWRITTEN) - ioend_flags |= IOMAP_IOEND_UNWRITTEN; if (wpc->iomap.flags & IOMAP_F_SHARED) ioend_flags |= IOMAP_IOEND_SHARED; if (folio_test_dropbehind(folio)) diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index a9d1c3b2c084..dd1451bf7543 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -9,6 +9,202 @@ #include #include "internal.h" +/* + * Perform the cleanup rituals after an unbuffered write is complete. + */ +static void netfs_unbuffered_write_done(struct netfs_io_request *wreq) +{ + struct netfs_inode *ictx = netfs_inode(wreq->inode); + + _enter("R=%x", wreq->debug_id); + + /* Okay, declare that all I/O is complete. */ + trace_netfs_rreq(wreq, netfs_rreq_trace_write_done); + + if (!wreq->error) + netfs_update_i_size(ictx, &ictx->inode, wreq->start, wreq->transferred); + + if (wreq->origin == NETFS_DIO_WRITE && + wreq->mapping->nrpages) { + /* mmap may have got underfoot and we may now have folios + * locally covering the region we just wrote. Attempt to + * discard the folios, but leave in place any modified locally. + * ->write_iter() is prevented from interfering by the DIO + * counter. + */ + pgoff_t first = wreq->start >> PAGE_SHIFT; + pgoff_t last = (wreq->start + wreq->transferred - 1) >> PAGE_SHIFT; + + invalidate_inode_pages2_range(wreq->mapping, first, last); + } + + if (wreq->origin == NETFS_DIO_WRITE) + inode_dio_end(wreq->inode); + + _debug("finished"); + netfs_wake_rreq_flag(wreq, NETFS_RREQ_IN_PROGRESS, netfs_rreq_trace_wake_ip); + /* As we cleared NETFS_RREQ_IN_PROGRESS, we acquired its ref. */ + + if (wreq->iocb) { + size_t written = umin(wreq->transferred, wreq->len); + + wreq->iocb->ki_pos += written; + if (wreq->iocb->ki_complete) { + trace_netfs_rreq(wreq, netfs_rreq_trace_ki_complete); + wreq->iocb->ki_complete(wreq->iocb, wreq->error ?: written); + } + wreq->iocb = VFS_PTR_POISON; + } + + netfs_clear_subrequests(wreq); +} + +/* + * Collect the subrequest results of unbuffered write subrequests. + */ +static void netfs_unbuffered_write_collect(struct netfs_io_request *wreq, + struct netfs_io_stream *stream, + struct netfs_io_subrequest *subreq) +{ + trace_netfs_collect_sreq(wreq, subreq); + + spin_lock(&wreq->lock); + list_del_init(&subreq->rreq_link); + spin_unlock(&wreq->lock); + + wreq->transferred += subreq->transferred; + iov_iter_advance(&wreq->buffer.iter, subreq->transferred); + + stream->collected_to = subreq->start + subreq->transferred; + wreq->collected_to = stream->collected_to; + netfs_put_subrequest(subreq, netfs_sreq_trace_put_done); + + trace_netfs_collect_stream(wreq, stream); + trace_netfs_collect_state(wreq, wreq->collected_to, 0); +} + +/* + * Write data to the server without going through the pagecache and without + * writing it to the local cache. We dispatch the subrequests serially and + * wait for each to complete before dispatching the next, lest we leave a gap + * in the data written due to a failure such as ENOSPC. We could, however + * attempt to do preparation such as content encryption for the next subreq + * whilst the current is in progress. + */ +static int netfs_unbuffered_write(struct netfs_io_request *wreq) +{ + struct netfs_io_subrequest *subreq = NULL; + struct netfs_io_stream *stream = &wreq->io_streams[0]; + int ret; + + _enter("%llx", wreq->len); + + if (wreq->origin == NETFS_DIO_WRITE) + inode_dio_begin(wreq->inode); + + stream->collected_to = wreq->start; + + for (;;) { + bool retry = false; + + if (!subreq) { + netfs_prepare_write(wreq, stream, wreq->start + wreq->transferred); + subreq = stream->construct; + stream->construct = NULL; + stream->front = NULL; + } + + /* Check if (re-)preparation failed. */ + if (unlikely(test_bit(NETFS_SREQ_FAILED, &subreq->flags))) { + netfs_write_subrequest_terminated(subreq, subreq->error); + wreq->error = subreq->error; + break; + } + + iov_iter_truncate(&subreq->io_iter, wreq->len - wreq->transferred); + if (!iov_iter_count(&subreq->io_iter)) + break; + + subreq->len = netfs_limit_iter(&subreq->io_iter, 0, + stream->sreq_max_len, + stream->sreq_max_segs); + iov_iter_truncate(&subreq->io_iter, subreq->len); + stream->submit_extendable_to = subreq->len; + + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); + stream->issue_write(subreq); + + /* Async, need to wait. */ + netfs_wait_for_in_progress_stream(wreq, stream); + + if (test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { + retry = true; + } else if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) { + ret = subreq->error; + wreq->error = ret; + netfs_see_subrequest(subreq, netfs_sreq_trace_see_failed); + subreq = NULL; + break; + } + ret = 0; + + if (!retry) { + netfs_unbuffered_write_collect(wreq, stream, subreq); + subreq = NULL; + if (wreq->transferred >= wreq->len) + break; + if (!wreq->iocb && signal_pending(current)) { + ret = wreq->transferred ? -EINTR : -ERESTARTSYS; + trace_netfs_rreq(wreq, netfs_rreq_trace_intr); + break; + } + continue; + } + + /* We need to retry the last subrequest, so first reset the + * iterator, taking into account what, if anything, we managed + * to transfer. + */ + subreq->error = -EAGAIN; + trace_netfs_sreq(subreq, netfs_sreq_trace_retry); + if (subreq->transferred > 0) + iov_iter_advance(&wreq->buffer.iter, subreq->transferred); + + if (stream->source == NETFS_UPLOAD_TO_SERVER && + wreq->netfs_ops->retry_request) + wreq->netfs_ops->retry_request(wreq, stream); + + __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + __clear_bit(NETFS_SREQ_BOUNDARY, &subreq->flags); + __clear_bit(NETFS_SREQ_FAILED, &subreq->flags); + subreq->io_iter = wreq->buffer.iter; + subreq->start = wreq->start + wreq->transferred; + subreq->len = wreq->len - wreq->transferred; + subreq->transferred = 0; + subreq->retry_count += 1; + stream->sreq_max_len = UINT_MAX; + stream->sreq_max_segs = INT_MAX; + + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + stream->prepare_write(subreq); + + __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + netfs_stat(&netfs_n_wh_retry_write_subreq); + } + + netfs_unbuffered_write_done(wreq); + _leave(" = %d", ret); + return ret; +} + +static void netfs_unbuffered_write_async(struct work_struct *work) +{ + struct netfs_io_request *wreq = container_of(work, struct netfs_io_request, work); + + netfs_unbuffered_write(wreq); + netfs_put_request(wreq, netfs_rreq_trace_put_complete); +} + /* * Perform an unbuffered write where we may have to do an RMW operation on an * encrypted file. This can also be used for direct I/O writes. @@ -70,35 +266,35 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * */ wreq->buffer.iter = *iter; } + + wreq->len = iov_iter_count(&wreq->buffer.iter); } __set_bit(NETFS_RREQ_USE_IO_ITER, &wreq->flags); - if (async) - __set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &wreq->flags); /* Copy the data into the bounce buffer and encrypt it. */ // TODO /* Dispatch the write. */ __set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags); - if (async) + + if (async) { + INIT_WORK(&wreq->work, netfs_unbuffered_write_async); wreq->iocb = iocb; - wreq->len = iov_iter_count(&wreq->buffer.iter); - ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), wreq->len); - if (ret < 0) { - _debug("begin = %zd", ret); - goto out; - } - - if (!async) { - ret = netfs_wait_for_write(wreq); - if (ret > 0) - iocb->ki_pos += ret; - } else { + queue_work(system_dfl_wq, &wreq->work); ret = -EIOCBQUEUED; + } else { + ret = netfs_unbuffered_write(wreq); + if (ret < 0) { + _debug("begin = %zd", ret); + } else { + iocb->ki_pos += wreq->transferred; + ret = wreq->transferred ?: wreq->error; + } + + netfs_put_request(wreq, netfs_rreq_trace_put_complete); } -out: netfs_put_request(wreq, netfs_rreq_trace_put_return); return ret; diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index 4319611f5354..d436e20d3418 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -198,6 +198,9 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, struct file *file, loff_t start, enum netfs_io_origin origin); +void netfs_prepare_write(struct netfs_io_request *wreq, + struct netfs_io_stream *stream, + loff_t start); void netfs_reissue_write(struct netfs_io_stream *stream, struct netfs_io_subrequest *subreq, struct iov_iter *source); @@ -212,7 +215,6 @@ int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_c struct folio **writethrough_cache); ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_control *wbc, struct folio *writethrough_cache); -int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t len); /* * write_retry.c diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 61eab34ea67e..83eb3dc1adf8 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -399,27 +399,6 @@ bool netfs_write_collection(struct netfs_io_request *wreq) ictx->ops->invalidate_cache(wreq); } - if ((wreq->origin == NETFS_UNBUFFERED_WRITE || - wreq->origin == NETFS_DIO_WRITE) && - !wreq->error) - netfs_update_i_size(ictx, &ictx->inode, wreq->start, wreq->transferred); - - if (wreq->origin == NETFS_DIO_WRITE && - wreq->mapping->nrpages) { - /* mmap may have got underfoot and we may now have folios - * locally covering the region we just wrote. Attempt to - * discard the folios, but leave in place any modified locally. - * ->write_iter() is prevented from interfering by the DIO - * counter. - */ - pgoff_t first = wreq->start >> PAGE_SHIFT; - pgoff_t last = (wreq->start + wreq->transferred - 1) >> PAGE_SHIFT; - invalidate_inode_pages2_range(wreq->mapping, first, last); - } - - if (wreq->origin == NETFS_DIO_WRITE) - inode_dio_end(wreq->inode); - _debug("finished"); netfs_wake_rreq_flag(wreq, NETFS_RREQ_IN_PROGRESS, netfs_rreq_trace_wake_ip); /* As we cleared NETFS_RREQ_IN_PROGRESS, we acquired its ref. */ diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 34894da5a23e..437268f65640 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -154,9 +154,9 @@ EXPORT_SYMBOL(netfs_prepare_write_failed); * Prepare a write subrequest. We need to allocate a new subrequest * if we don't have one. */ -static void netfs_prepare_write(struct netfs_io_request *wreq, - struct netfs_io_stream *stream, - loff_t start) +void netfs_prepare_write(struct netfs_io_request *wreq, + struct netfs_io_stream *stream, + loff_t start) { struct netfs_io_subrequest *subreq; struct iov_iter *wreq_iter = &wreq->buffer.iter; @@ -698,41 +698,6 @@ ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_c return ret; } -/* - * Write data to the server without going through the pagecache and without - * writing it to the local cache. - */ -int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t len) -{ - struct netfs_io_stream *upload = &wreq->io_streams[0]; - ssize_t part; - loff_t start = wreq->start; - int error = 0; - - _enter("%zx", len); - - if (wreq->origin == NETFS_DIO_WRITE) - inode_dio_begin(wreq->inode); - - while (len) { - // TODO: Prepare content encryption - - _debug("unbuffered %zx", len); - part = netfs_advance_write(wreq, upload, start, len, false); - start += part; - len -= part; - rolling_buffer_advance(&wreq->buffer, part); - if (test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) - netfs_wait_for_paused_write(wreq); - if (test_bit(NETFS_RREQ_FAILED, &wreq->flags)) - break; - } - - netfs_end_issue_write(wreq); - _leave(" = %d", error); - return error; -} - /* * Write some of a pending folio data back to the server and/or the cache. */ diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index e9acd2cd602c..4cc8a58fa56a 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -377,15 +377,15 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) } /* - * write_threads - Start NFSD, or report the current number of running threads + * write_threads - Start NFSD, or report the configured number of threads * * Input: * buf: ignored * size: zero * Output: * On success: passed-in buffer filled with '\n'-terminated C - * string numeric value representing the number of - * running NFSD threads; + * string numeric value representing the configured + * number of NFSD threads; * return code is the size in bytes of the string * On error: return code is zero * @@ -399,8 +399,8 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) * Output: * On success: NFS service is started; * passed-in buffer filled with '\n'-terminated C - * string numeric value representing the number of - * running NFSD threads; + * string numeric value representing the configured + * number of NFSD threads; * return code is the size in bytes of the string * On error: return code is zero or a negative errno value */ @@ -430,7 +430,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) } /* - * write_pool_threads - Set or report the current number of threads per pool + * write_pool_threads - Set or report the configured number of threads per pool * * Input: * buf: ignored @@ -447,7 +447,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) * Output: * On success: passed-in buffer filled with '\n'-terminated C * string containing integer values representing the - * number of NFSD threads in each pool; + * configured number of NFSD threads in each pool; * return code is the size in bytes of the string * On error: return code is zero or a negative errno value */ @@ -1647,7 +1647,7 @@ int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info) if (attr) nn->min_threads = nla_get_u32(attr); - ret = nfsd_svc(nrpools, nthreads, net, get_current_cred(), scope); + ret = nfsd_svc(nrpools, nthreads, net, current_cred(), scope); if (ret > 0) ret = 0; out_unlock: @@ -1657,7 +1657,7 @@ out_unlock: } /** - * nfsd_nl_threads_get_doit - get the number of running threads + * nfsd_nl_threads_get_doit - get the maximum number of running threads * @skb: reply buffer * @info: netlink metadata and command arguments * @@ -1700,7 +1700,7 @@ int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info) struct svc_pool *sp = &nn->nfsd_serv->sv_pools[i]; err = nla_put_u32(skb, NFSD_A_SERVER_THREADS, - sp->sp_nrthreads); + sp->sp_nrthrmax); if (err) goto err_unlock; } @@ -2000,7 +2000,7 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info) } ret = svc_xprt_create_from_sa(serv, xcl_name, net, sa, 0, - get_current_cred()); + current_cred()); /* always save the latest error */ if (ret < 0) err = ret; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 0887ee601d3c..4a04208393b8 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -239,12 +239,13 @@ static void nfsd_net_free(struct percpu_ref *ref) int nfsd_nrthreads(struct net *net) { - int rv = 0; + int i, rv = 0; struct nfsd_net *nn = net_generic(net, nfsd_net_id); mutex_lock(&nfsd_mutex); if (nn->nfsd_serv) - rv = nn->nfsd_serv->sv_nrthreads; + for (i = 0; i < nn->nfsd_serv->sv_nrpools; ++i) + rv += nn->nfsd_serv->sv_pools[i].sp_nrthrmax; mutex_unlock(&nfsd_mutex); return rv; } @@ -659,7 +660,7 @@ int nfsd_get_nrthreads(int n, int *nthreads, struct net *net) if (serv) for (i = 0; i < serv->sv_nrpools && i < n; i++) - nthreads[i] = serv->sv_pools[i].sp_nrthreads; + nthreads[i] = serv->sv_pools[i].sp_nrthrmax; return 0; } diff --git a/fs/nsfs.c b/fs/nsfs.c index db91de208645..c215878d55e8 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -199,6 +199,17 @@ static bool nsfs_ioctl_valid(unsigned int cmd) return false; } +static bool may_use_nsfs_ioctl(unsigned int cmd) +{ + switch (_IOC_NR(cmd)) { + case _IOC_NR(NS_MNT_GET_NEXT): + fallthrough; + case _IOC_NR(NS_MNT_GET_PREV): + return may_see_all_namespaces(); + } + return true; +} + static long ns_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -214,6 +225,8 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, if (!nsfs_ioctl_valid(ioctl)) return -ENOIOCTLCMD; + if (!may_use_nsfs_ioctl(ioctl)) + return -EPERM; ns = get_proc_ns(file_inode(filp)); switch (ioctl) { @@ -614,7 +627,7 @@ static struct dentry *nsfs_fh_to_dentry(struct super_block *sb, struct fid *fh, return ERR_PTR(-EOPNOTSUPP); } - if (owning_ns && !ns_capable(owning_ns, CAP_SYS_ADMIN)) { + if (owning_ns && !may_see_all_namespaces()) { ns->ops->put(ns); return ERR_PTR(-EPERM); } diff --git a/fs/smb/client/Makefile b/fs/smb/client/Makefile index 3abd357d6df6..26b6105f04d1 100644 --- a/fs/smb/client/Makefile +++ b/fs/smb/client/Makefile @@ -56,4 +56,6 @@ $(obj)/smb2maperror.o: $(obj)/smb2_mapping_table.c quiet_cmd_gen_smb2_mapping = GEN $@ cmd_gen_smb2_mapping = perl $(src)/gen_smb2_mapping $< $@ +obj-$(CONFIG_SMB_KUNIT_TESTS) += smb2maperror_test.o + clean-files += smb2_mapping_table.c diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 427558404aa5..b6e3db993cc6 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -332,10 +332,14 @@ static void cifs_kill_sb(struct super_block *sb) /* * We need to release all dentries for the cached directories - * before we kill the sb. + * and close all deferred file handles before we kill the sb. */ if (cifs_sb->root) { close_all_cached_dirs(cifs_sb); + cifs_close_all_deferred_files_sb(cifs_sb); + + /* Wait for all pending oplock breaks to complete */ + flush_workqueue(cifsoplockd_wq); /* finally release root dentry */ dput(cifs_sb->root); @@ -868,7 +872,6 @@ static void cifs_umount_begin(struct super_block *sb) spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); - cifs_close_all_deferred_files(tcon); /* cancel_brl_requests(tcon); */ /* BB mark all brl mids as exiting */ /* cancel_notify_requests(tcon); */ if (tcon->ses && tcon->ses->server) { diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 96d6b5325aa3..800a7e418c32 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -261,6 +261,7 @@ void cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode); void cifs_close_all_deferred_files(struct cifs_tcon *tcon); +void cifs_close_all_deferred_files_sb(struct cifs_sb_info *cifs_sb); void cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, struct dentry *dentry); diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index f3ddcdf406c8..cffcf82c1b69 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -711,8 +711,6 @@ struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, mutex_init(&cfile->fh_mutex); spin_lock_init(&cfile->file_info_lock); - cifs_sb_active(inode->i_sb); - /* * If the server returned a read oplock and we have mandatory brlocks, * set oplock level to None. @@ -767,7 +765,6 @@ static void cifsFileInfo_put_final(struct cifsFileInfo *cifs_file) struct inode *inode = d_inode(cifs_file->dentry); struct cifsInodeInfo *cifsi = CIFS_I(inode); struct cifsLockInfo *li, *tmp; - struct super_block *sb = inode->i_sb; /* * Delete any outstanding lock records. We'll lose them when the file @@ -785,7 +782,6 @@ static void cifsFileInfo_put_final(struct cifsFileInfo *cifs_file) cifs_put_tlink(cifs_file->tlink); dput(cifs_file->dentry); - cifs_sb_deactive(sb); kfree(cifs_file->symlink_target); kfree(cifs_file); } @@ -3163,12 +3159,6 @@ void cifs_oplock_break(struct work_struct *work) __u64 persistent_fid, volatile_fid; __u16 net_fid; - /* - * Hold a reference to the superblock to prevent it and its inodes from - * being freed while we are accessing cinode. Otherwise, _cifsFileInfo_put() - * may release the last reference to the sb and trigger inode eviction. - */ - cifs_sb_active(sb); wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); @@ -3253,7 +3243,6 @@ oplock_break_ack: cifs_put_tlink(tlink); out: cifs_done_oplock_break(cinode); - cifs_sb_deactive(sb); } static int cifs_swap_activate(struct swap_info_struct *sis, diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index bc24c92b8b95..2aff1cab6c31 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -28,6 +28,11 @@ #include "fs_context.h" #include "cached_dir.h" +struct tcon_list { + struct list_head entry; + struct cifs_tcon *tcon; +}; + /* The xid serves as a useful identifier for each incoming vfs request, in a similar way to the mid which is useful to track each sent smb, and CurrentXid can also provide a running counter (although it @@ -554,6 +559,43 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon) } } +void cifs_close_all_deferred_files_sb(struct cifs_sb_info *cifs_sb) +{ + struct rb_root *root = &cifs_sb->tlink_tree; + struct rb_node *node; + struct cifs_tcon *tcon; + struct tcon_link *tlink; + struct tcon_list *tmp_list, *q; + LIST_HEAD(tcon_head); + + spin_lock(&cifs_sb->tlink_tree_lock); + for (node = rb_first(root); node; node = rb_next(node)) { + tlink = rb_entry(node, struct tcon_link, tl_rbnode); + tcon = tlink_tcon(tlink); + if (IS_ERR(tcon)) + continue; + tmp_list = kmalloc_obj(struct tcon_list, GFP_ATOMIC); + if (tmp_list == NULL) + break; + tmp_list->tcon = tcon; + /* Take a reference on tcon to prevent it from being freed */ + spin_lock(&tcon->tc_lock); + ++tcon->tc_count; + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, + netfs_trace_tcon_ref_get_close_defer_files); + spin_unlock(&tcon->tc_lock); + list_add_tail(&tmp_list->entry, &tcon_head); + } + spin_unlock(&cifs_sb->tlink_tree_lock); + + list_for_each_entry_safe(tmp_list, q, &tcon_head, entry) { + cifs_close_all_deferred_files(tmp_list->tcon); + list_del(&tmp_list->entry); + cifs_put_tcon(tmp_list->tcon, netfs_trace_tcon_ref_put_close_defer_files); + kfree(tmp_list); + } +} + void cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, struct dentry *dentry) { diff --git a/fs/smb/client/smb1encrypt.c b/fs/smb/client/smb1encrypt.c index 0dbbce2431ff..bf10fdeeedca 100644 --- a/fs/smb/client/smb1encrypt.c +++ b/fs/smb/client/smb1encrypt.c @@ -11,6 +11,7 @@ #include #include +#include #include "cifsproto.h" #include "smb1proto.h" #include "cifs_debug.h" @@ -131,7 +132,7 @@ int cifs_verify_signature(struct smb_rqst *rqst, /* cifs_dump_mem("what we think it should be: ", what_we_think_sig_should_be, 16); */ - if (memcmp(server_response_sig, what_we_think_sig_should_be, 8)) + if (crypto_memneq(server_response_sig, what_we_think_sig_should_be, 8)) return -EACCES; else return 0; diff --git a/fs/smb/client/smb2glob.h b/fs/smb/client/smb2glob.h index e56e4d402f13..19da74b1edab 100644 --- a/fs/smb/client/smb2glob.h +++ b/fs/smb/client/smb2glob.h @@ -46,4 +46,16 @@ enum smb2_compound_ops { #define END_OF_CHAIN 4 #define RELATED_REQUEST 8 +/* + ***************************************************************** + * Struct definitions go here + ***************************************************************** + */ + +struct status_to_posix_error { + __u32 smb2_status; + int posix_error; + char *status_string; +}; + #endif /* _SMB2_GLOB_H */ diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 195a38fd61e8..5280c5c869ad 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -325,7 +325,7 @@ replay_again: cfile->fid.volatile_fid, SMB_FIND_FILE_POSIX_INFO, SMB2_O_INFO_FILE, 0, - sizeof(struct smb311_posix_qinfo *) + + sizeof(struct smb311_posix_qinfo) + (PATH_MAX * 2) + (sizeof(struct smb_sid) * 2), 0, NULL); } else { @@ -335,7 +335,7 @@ replay_again: COMPOUND_FID, SMB_FIND_FILE_POSIX_INFO, SMB2_O_INFO_FILE, 0, - sizeof(struct smb311_posix_qinfo *) + + sizeof(struct smb311_posix_qinfo) + (PATH_MAX * 2) + (sizeof(struct smb_sid) * 2), 0, NULL); } @@ -1216,6 +1216,7 @@ again: memset(resp_buftype, 0, sizeof(resp_buftype)); memset(rsp_iov, 0, sizeof(rsp_iov)); + memset(open_iov, 0, sizeof(open_iov)); rqst[0].rq_iov = open_iov; rqst[0].rq_nvec = ARRAY_SIZE(open_iov); @@ -1240,14 +1241,15 @@ again: creq = rqst[0].rq_iov[0].iov_base; creq->ShareAccess = FILE_SHARE_DELETE_LE; + memset(&close_iov, 0, sizeof(close_iov)); rqst[1].rq_iov = &close_iov; rqst[1].rq_nvec = 1; rc = SMB2_close_init(tcon, server, &rqst[1], COMPOUND_FID, COMPOUND_FID, false); - smb2_set_related(&rqst[1]); if (rc) goto err_free; + smb2_set_related(&rqst[1]); if (retries) { /* Back-off before retry */ diff --git a/fs/smb/client/smb2maperror.c b/fs/smb/client/smb2maperror.c index cd036365201f..f4cff44e2796 100644 --- a/fs/smb/client/smb2maperror.c +++ b/fs/smb/client/smb2maperror.c @@ -8,7 +8,6 @@ * */ #include -#include "cifsglob.h" #include "cifsproto.h" #include "cifs_debug.h" #include "smb2proto.h" @@ -16,12 +15,6 @@ #include "../common/smb2status.h" #include "trace.h" -struct status_to_posix_error { - __u32 smb2_status; - int posix_error; - char *status_string; -}; - static const struct status_to_posix_error smb2_error_map_table[] = { /* * Automatically generated by the `gen_smb2_mapping` script, @@ -115,10 +108,19 @@ int __init smb2_init_maperror(void) return 0; } -#define SMB_CLIENT_KUNIT_AVAILABLE \ - ((IS_MODULE(CONFIG_CIFS) && IS_ENABLED(CONFIG_KUNIT)) || \ - (IS_BUILTIN(CONFIG_CIFS) && IS_BUILTIN(CONFIG_KUNIT))) +#if IS_ENABLED(CONFIG_SMB_KUNIT_TESTS) +/* Previous prototype for eliminating the build warning. */ +const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status); -#if SMB_CLIENT_KUNIT_AVAILABLE && IS_ENABLED(CONFIG_SMB_KUNIT_TESTS) -#include "smb2maperror_test.c" -#endif /* CONFIG_SMB_KUNIT_TESTS */ +const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status) +{ + return smb2_get_err_map(smb2_status); +} +EXPORT_SYMBOL_GPL(smb2_get_err_map_test); + +const struct status_to_posix_error *smb2_error_map_table_test = smb2_error_map_table; +EXPORT_SYMBOL_GPL(smb2_error_map_table_test); + +unsigned int smb2_error_map_num = ARRAY_SIZE(smb2_error_map_table); +EXPORT_SYMBOL_GPL(smb2_error_map_num); +#endif diff --git a/fs/smb/client/smb2maperror_test.c b/fs/smb/client/smb2maperror_test.c index 38ea6b846a99..8c47dea7a2c1 100644 --- a/fs/smb/client/smb2maperror_test.c +++ b/fs/smb/client/smb2maperror_test.c @@ -9,13 +9,18 @@ */ #include +#include "smb2glob.h" + +const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status); +extern const struct status_to_posix_error *smb2_error_map_table_test; +extern unsigned int smb2_error_map_num; static void test_cmp_map(struct kunit *test, const struct status_to_posix_error *expect) { const struct status_to_posix_error *result; - result = smb2_get_err_map(expect->smb2_status); + result = smb2_get_err_map_test(expect->smb2_status); KUNIT_EXPECT_PTR_NE(test, NULL, result); KUNIT_EXPECT_EQ(test, expect->smb2_status, result->smb2_status); KUNIT_EXPECT_EQ(test, expect->posix_error, result->posix_error); @@ -26,8 +31,8 @@ static void maperror_test_check_search(struct kunit *test) { unsigned int i; - for (i = 0; i < ARRAY_SIZE(smb2_error_map_table); i++) - test_cmp_map(test, &smb2_error_map_table[i]); + for (i = 0; i < smb2_error_map_num; i++) + test_cmp_map(test, &smb2_error_map_table_test[i]); } static struct kunit_case maperror_test_cases[] = { @@ -43,3 +48,4 @@ static struct kunit_suite maperror_suite = { kunit_test_suite(maperror_suite); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit tests of SMB2 maperror"); diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 04e361ed2356..c43ca74e8704 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3989,24 +3989,6 @@ int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon, NULL); } -#if 0 -/* currently unused, as now we are doing compounding instead (see smb311_posix_query_path_info) */ -int -SMB311_posix_query_info(const unsigned int xid, struct cifs_tcon *tcon, - u64 persistent_fid, u64 volatile_fid, - struct smb311_posix_qinfo *data, u32 *plen) -{ - size_t output_len = sizeof(struct smb311_posix_qinfo *) + - (sizeof(struct smb_sid) * 2) + (PATH_MAX * 2); - *plen = 0; - - return query_info(xid, tcon, persistent_fid, volatile_fid, - SMB_FIND_FILE_POSIX_INFO, SMB2_O_INFO_FILE, 0, - output_len, sizeof(struct smb311_posix_qinfo), (void **)&data, plen); - /* Note caller must free "data" (passed in above). It may be allocated in query_info call */ -} -#endif - int SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h index 78bb99f29d38..30d70097fe2f 100644 --- a/fs/smb/client/smb2pdu.h +++ b/fs/smb/client/smb2pdu.h @@ -224,7 +224,7 @@ struct smb2_file_reparse_point_info { __le32 Tag; } __packed; -/* See MS-FSCC 2.4.21 */ +/* See MS-FSCC 2.4.26 */ struct smb2_file_id_information { __le64 VolumeSerialNumber; __u64 PersistentFileId; /* opaque endianness */ @@ -251,7 +251,10 @@ struct smb2_file_id_extd_directory_info { extern char smb2_padding[7]; -/* equivalent of the contents of SMB3.1.1 POSIX open context response */ +/* + * See POSIX-SMB2 2.2.14.2.16 + * Link: https://gitlab.com/samba-team/smb3-posix-spec/-/blob/master/smb3_posix_extensions.md + */ struct create_posix_rsp { u32 nlink; u32 reparse_tag; diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index 881e42cf66ce..230bb1e9f4e1 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -167,9 +167,6 @@ int SMB2_flush_init(const unsigned int xid, struct smb_rqst *rqst, struct cifs_tcon *tcon, struct TCP_Server_Info *server, u64 persistent_fid, u64 volatile_fid); void SMB2_flush_free(struct smb_rqst *rqst); -int SMB311_posix_query_info(const unsigned int xid, struct cifs_tcon *tcon, - u64 persistent_fid, u64 volatile_fid, - struct smb311_posix_qinfo *data, u32 *plen); int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, struct smb2_file_all_info *data); diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index 8b9000a83181..81be2b226e26 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "cifsglob.h" #include "cifsproto.h" #include "smb2proto.h" @@ -617,7 +618,8 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) if (rc) return rc; - if (memcmp(server_response_sig, shdr->Signature, SMB2_SIGNATURE_SIZE)) { + if (crypto_memneq(server_response_sig, shdr->Signature, + SMB2_SIGNATURE_SIZE)) { cifs_dbg(VFS, "sign fail cmd 0x%x message id 0x%llx\n", shdr->Command, shdr->MessageId); return -EACCES; diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index 9228f95cae2b..acfbb63086ea 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -176,6 +176,7 @@ EM(netfs_trace_tcon_ref_get_cached_laundromat, "GET Ch-Lau") \ EM(netfs_trace_tcon_ref_get_cached_lease_break, "GET Ch-Lea") \ EM(netfs_trace_tcon_ref_get_cancelled_close, "GET Cn-Cls") \ + EM(netfs_trace_tcon_ref_get_close_defer_files, "GET Cl-Def") \ EM(netfs_trace_tcon_ref_get_dfs_refer, "GET DfsRef") \ EM(netfs_trace_tcon_ref_get_find, "GET Find ") \ EM(netfs_trace_tcon_ref_get_find_sess_tcon, "GET FndSes") \ @@ -187,6 +188,7 @@ EM(netfs_trace_tcon_ref_put_cancelled_close, "PUT Cn-Cls") \ EM(netfs_trace_tcon_ref_put_cancelled_close_fid, "PUT Cn-Fid") \ EM(netfs_trace_tcon_ref_put_cancelled_mid, "PUT Cn-Mid") \ + EM(netfs_trace_tcon_ref_put_close_defer_files, "PUT Cl-Def") \ EM(netfs_trace_tcon_ref_put_mnt_ctx, "PUT MntCtx") \ EM(netfs_trace_tcon_ref_put_dfs_refer, "PUT DfsRfr") \ EM(netfs_trace_tcon_ref_put_reconnect_server, "PUT Reconn") \ diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h index 257c6d26df26..8b6eafb70dca 100644 --- a/fs/smb/server/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h @@ -83,7 +83,10 @@ struct create_durable_rsp { } Data; } __packed; -/* equivalent of the contents of SMB3.1.1 POSIX open context response */ +/* + * See POSIX-SMB2 2.2.14.2.16 + * Link: https://gitlab.com/samba-team/smb3-posix-spec/-/blob/master/smb3_posix_extensions.md + */ struct create_posix_rsp { struct create_context_hdr ccontext; __u8 Name[16]; diff --git a/fs/verity/Kconfig b/fs/verity/Kconfig index 76d1c5971b82..b20882963ffb 100644 --- a/fs/verity/Kconfig +++ b/fs/verity/Kconfig @@ -2,6 +2,9 @@ config FS_VERITY bool "FS Verity (read-only file-based authenticity protection)" + # Filesystems cache the Merkle tree at a 64K aligned offset in the + # pagecache. That approach assumes the page size is at most 64K. + depends on PAGE_SHIFT <= 16 select CRYPTO_HASH_INFO select CRYPTO_LIB_SHA256 select CRYPTO_LIB_SHA512 diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index eeb070f330bd..1e1580febe4b 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -848,12 +848,14 @@ /* Required sections not related to debugging. */ #define ELF_DETAILS \ - .modinfo : { *(.modinfo) . = ALIGN(8); } \ .comment 0 : { *(.comment) } \ .symtab 0 : { *(.symtab) } \ .strtab 0 : { *(.strtab) } \ .shstrtab 0 : { *(.shstrtab) } +#define MODINFO \ + .modinfo : { *(.modinfo) . = ALIGN(8); } + #ifdef CONFIG_GENERIC_BUG #define BUG_TABLE \ . = ALIGN(8); \ diff --git a/include/drm/display/drm_dp.h b/include/drm/display/drm_dp.h index e4eebabab975..8b15d3eeb716 100644 --- a/include/drm/display/drm_dp.h +++ b/include/drm/display/drm_dp.h @@ -571,6 +571,8 @@ # define DP_PANEL_REPLAY_LINK_OFF_SUPPORTED_IN_PR_AFTER_ADAPTIVE_SYNC_SDP (1 << 7) #define DP_PANEL_REPLAY_CAP_X_GRANULARITY 0xb2 +# define DP_PANEL_REPLAY_FULL_LINE_GRANULARITY 0xffff + #define DP_PANEL_REPLAY_CAP_Y_GRANULARITY 0xb4 /* Link Configuration */ diff --git a/include/kunit/run-in-irq-context.h b/include/kunit/run-in-irq-context.h index c89b1b1b12dd..bfe60d6cf28d 100644 --- a/include/kunit/run-in-irq-context.h +++ b/include/kunit/run-in-irq-context.h @@ -12,16 +12,16 @@ #include #include -#define KUNIT_IRQ_TEST_HRTIMER_INTERVAL us_to_ktime(5) - struct kunit_irq_test_state { bool (*func)(void *test_specific_state); void *test_specific_state; bool task_func_reported_failure; bool hardirq_func_reported_failure; bool softirq_func_reported_failure; + atomic_t task_func_calls; atomic_t hardirq_func_calls; atomic_t softirq_func_calls; + ktime_t interval; struct hrtimer timer; struct work_struct bh_work; }; @@ -30,14 +30,25 @@ static enum hrtimer_restart kunit_irq_test_timer_func(struct hrtimer *timer) { struct kunit_irq_test_state *state = container_of(timer, typeof(*state), timer); + int task_calls, hardirq_calls, softirq_calls; WARN_ON_ONCE(!in_hardirq()); - atomic_inc(&state->hardirq_func_calls); + task_calls = atomic_read(&state->task_func_calls); + hardirq_calls = atomic_inc_return(&state->hardirq_func_calls); + softirq_calls = atomic_read(&state->softirq_func_calls); + + /* + * If the timer is firing too often for the softirq or task to ever have + * a chance to run, increase the timer interval. This is needed on very + * slow systems. + */ + if (hardirq_calls >= 20 && (softirq_calls == 0 || task_calls == 0)) + state->interval = ktime_add_ns(state->interval, 250); if (!state->func(state->test_specific_state)) state->hardirq_func_reported_failure = true; - hrtimer_forward_now(&state->timer, KUNIT_IRQ_TEST_HRTIMER_INTERVAL); + hrtimer_forward_now(&state->timer, state->interval); queue_work(system_bh_wq, &state->bh_work); return HRTIMER_RESTART; } @@ -86,10 +97,14 @@ static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *), struct kunit_irq_test_state state = { .func = func, .test_specific_state = test_specific_state, + /* + * Start with a 5us timer interval. If the system can't keep + * up, kunit_irq_test_timer_func() will increase it. + */ + .interval = us_to_ktime(5), }; unsigned long end_jiffies; - int hardirq_calls, softirq_calls; - bool allctx = false; + int task_calls, hardirq_calls, softirq_calls; /* * Set up a hrtimer (the way we access hardirq context) and a work @@ -104,21 +119,18 @@ static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *), * and hardirq), or 1 second, whichever comes first. */ end_jiffies = jiffies + HZ; - hrtimer_start(&state.timer, KUNIT_IRQ_TEST_HRTIMER_INTERVAL, - HRTIMER_MODE_REL_HARD); - for (int task_calls = 0, calls = 0; - ((calls < max_iterations) || !allctx) && - !time_after(jiffies, end_jiffies); - task_calls++) { + hrtimer_start(&state.timer, state.interval, HRTIMER_MODE_REL_HARD); + do { if (!func(test_specific_state)) state.task_func_reported_failure = true; + task_calls = atomic_inc_return(&state.task_func_calls); hardirq_calls = atomic_read(&state.hardirq_func_calls); softirq_calls = atomic_read(&state.softirq_func_calls); - calls = task_calls + hardirq_calls + softirq_calls; - allctx = (task_calls > 0) && (hardirq_calls > 0) && - (softirq_calls > 0); - } + } while ((task_calls + hardirq_calls + softirq_calls < max_iterations || + (task_calls == 0 || hardirq_calls == 0 || + softirq_calls == 0)) && + !time_after(jiffies, end_jiffies)); /* Cancel the timer and work. */ hrtimer_cancel(&state.timer); diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 99c3c83ea520..63de5f053c33 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -35,6 +35,8 @@ struct fwnode_handle; * otherwise. It may also return error code if determining that * the driver supports the device is not possible. In case of * -EPROBE_DEFER it will queue the device for deferred probing. + * Note: This callback may be invoked with or without the device + * lock held. * @uevent: Called when a device is added, removed, or a few other things * that generate uevents to add the environment variables. * @probe: Called when a new device or driver add to this bus, and callback diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index ccb478eb174b..ea9ca0e4172a 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -82,11 +82,14 @@ static inline struct epoll_event __user * epoll_put_uevent(__poll_t revents, __u64 data, struct epoll_event __user *uevent) { - if (__put_user(revents, &uevent->events) || - __put_user(data, &uevent->data)) - return NULL; - + scoped_user_write_access_size(uevent, sizeof(*uevent), efault) { + unsafe_put_user(revents, &uevent->events, efault); + unsafe_put_user(data, &uevent->data, efault); + } return uevent+1; + +efault: + return NULL; } #endif diff --git a/include/linux/hid.h b/include/linux/hid.h index dce862cafbbd..2990b9f94cb5 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -836,6 +836,12 @@ struct hid_usage_id { * raw_event and event should return negative on error, any other value will * pass the event on to .event() typically return 0 for success. * + * report_fixup must return a report descriptor pointer whose lifetime is at + * least that of the input rdesc. This is usually done by mutating the input + * rdesc and returning it or a sub-portion of it. In case a new buffer is + * allocated and returned, the implementation of report_fixup is responsible for + * freeing it later. + * * input_mapping shall return a negative value to completely ignore this usage * (e.g. doubled or invalid usage), zero to continue with parsing of this * usage by generic code (no special handling needed) or positive to skip diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index 35227d47cfc9..dc272b514a01 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -16,22 +16,26 @@ */ #define INDIRECT_CALL_1(f, f1, ...) \ ({ \ - likely(f == f1) ? f1(__VA_ARGS__) : f(__VA_ARGS__); \ + typeof(f) __f1 = (f); \ + likely(__f1 == f1) ? f1(__VA_ARGS__) : __f1(__VA_ARGS__); \ }) #define INDIRECT_CALL_2(f, f2, f1, ...) \ ({ \ - likely(f == f2) ? f2(__VA_ARGS__) : \ - INDIRECT_CALL_1(f, f1, __VA_ARGS__); \ + typeof(f) __f2 = (f); \ + likely(__f2 == f2) ? f2(__VA_ARGS__) : \ + INDIRECT_CALL_1(__f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALL_3(f, f3, f2, f1, ...) \ ({ \ - likely(f == f3) ? f3(__VA_ARGS__) : \ - INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__); \ + typeof(f) __f3 = (f); \ + likely(__f3 == f3) ? f3(__VA_ARGS__) : \ + INDIRECT_CALL_2(__f3, f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...) \ ({ \ - likely(f == f4) ? f4(__VA_ARGS__) : \ - INDIRECT_CALL_3(f, f3, f2, f1, __VA_ARGS__); \ + typeof(f) __f4 = (f); \ + likely(__f4 == f4) ? f4(__VA_ARGS__) : \ + INDIRECT_CALL_3(__f4, f3, f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALLABLE_DECLARE(f) f diff --git a/include/linux/kthread.h b/include/linux/kthread.h index c92c1149ee6e..a01a474719a7 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -7,6 +7,24 @@ struct mm_struct; +/* opaque kthread data */ +struct kthread; + +/* + * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will + * always remain a kthread. For kthreads p->worker_private always + * points to a struct kthread. For tasks that are not kthreads + * p->worker_private is used to point to other things. + * + * Return NULL for any task that is not a kthread. + */ +static inline struct kthread *tsk_is_kthread(struct task_struct *p) +{ + if (p->flags & PF_KTHREAD) + return p->worker_private; + return NULL; +} + __printf(4, 5) struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), void *data, @@ -98,9 +116,10 @@ void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); -void kthread_exit(long result) __noreturn; +#define kthread_exit(result) do_exit(result) void kthread_complete_and_exit(struct completion *, long) __noreturn; int kthreads_update_housekeeping(void); +void kthread_do_exit(struct kthread *, long); int kthreadd(void *unused); extern struct task_struct *kthreadd_task; diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 26ca00c325d9..d5af2b7f577b 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -65,7 +65,7 @@ bool isolate_folio_to_list(struct folio *folio, struct list_head *list); int migrate_huge_page_move_mapping(struct address_space *mapping, struct folio *dst, struct folio *src); -void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) +void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) __releases(ptl); void folio_migrate_flags(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, @@ -97,6 +97,14 @@ static inline int set_movable_ops(const struct movable_operations *ops, enum pag return -ENOSYS; } +static inline void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) + __releases(ptl) +{ + WARN_ON_ONCE(1); + + spin_unlock(ptl); +} + #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_NUMA_BALANCING diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d4e6e00bb90a..67e25f6d15a4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4711,7 +4711,7 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) { spin_lock(&txq->_xmit_lock); - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, cpu); } @@ -4729,7 +4729,7 @@ static inline void __netif_tx_release(struct netdev_queue *txq) static inline void __netif_tx_lock_bh(struct netdev_queue *txq) { spin_lock_bh(&txq->_xmit_lock); - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } @@ -4738,7 +4738,7 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq) bool ok = spin_trylock(&txq->_xmit_lock); if (likely(ok)) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } return ok; @@ -4746,14 +4746,14 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq) static inline void __netif_tx_unlock(struct netdev_queue *txq) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock(&txq->_xmit_lock); } static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock_bh(&txq->_xmit_lock); } @@ -4846,6 +4846,23 @@ static inline void netif_tx_disable(struct net_device *dev) local_bh_enable(); } +#ifndef CONFIG_PREEMPT_RT +static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu) +{ + /* Other cpus might concurrently change txq->xmit_lock_owner + * to -1 or to their cpu id, but not to our id. + */ + return READ_ONCE(txq->xmit_lock_owner) == cpu; +} + +#else +static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu) +{ + return rt_mutex_owner(&txq->_xmit_lock.lock) == current; +} + +#endif + static inline void netif_addr_lock(struct net_device *dev) { unsigned char nest_level = 0; diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h index 825f5865bfc5..c8e227a3f9e2 100644 --- a/include/linux/ns_common.h +++ b/include/linux/ns_common.h @@ -55,6 +55,8 @@ static __always_inline bool is_ns_init_id(const struct ns_common *ns) #define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns))) +bool may_see_all_namespaces(void); + static __always_inline __must_check int __ns_ref_active_read(const struct ns_common *ns) { return atomic_read(&ns->__ns_ref_active); diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index f6cca7a035c7..50b6be57da66 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -13,10 +13,10 @@ /** * enum mlxreg_wdt_type - type of HW watchdog * - * TYPE1 HW watchdog implementation exist in old systems. - * All new systems have TYPE2 HW watchdog. - * TYPE3 HW watchdog can exist on all systems with new CPLD. - * TYPE3 is selected by WD capability bit. + * @MLX_WDT_TYPE1: HW watchdog implementation in old systems. + * @MLX_WDT_TYPE2: All new systems have TYPE2 HW watchdog. + * @MLX_WDT_TYPE3: HW watchdog that can exist on all systems with new CPLD. + * TYPE3 is selected by WD capability bit. */ enum mlxreg_wdt_type { MLX_WDT_TYPE1, @@ -35,7 +35,7 @@ enum mlxreg_wdt_type { * @MLXREG_HOTPLUG_LC_SYNCED: entry for line card synchronization events, coming * after hardware-firmware synchronization handshake; * @MLXREG_HOTPLUG_LC_READY: entry for line card ready events, indicating line card - PHYs ready / unready state; + * PHYs ready / unready state; * @MLXREG_HOTPLUG_LC_ACTIVE: entry for line card active events, indicating firmware * availability / unavailability for the ports on line card; * @MLXREG_HOTPLUG_LC_THERMAL: entry for line card thermal shutdown events, positive @@ -123,8 +123,8 @@ struct mlxreg_hotplug_device { * @reg_pwr: attribute power register; * @reg_ena: attribute enable register; * @mode: access mode; - * @np - pointer to node platform associated with attribute; - * @hpdev - hotplug device data; + * @np: pointer to node platform associated with attribute; + * @hpdev: hotplug device data; * @notifier: pointer to event notifier block; * @health_cntr: dynamic device health indication counter; * @attached: true if device has been attached after good health indication; diff --git a/include/linux/platform_data/x86/int3472.h b/include/linux/platform_data/x86/int3472.h index b1b837583d54..dbe745dc88d5 100644 --- a/include/linux/platform_data/x86/int3472.h +++ b/include/linux/platform_data/x86/int3472.h @@ -26,6 +26,7 @@ #define INT3472_GPIO_TYPE_POWER_ENABLE 0x0b #define INT3472_GPIO_TYPE_CLK_ENABLE 0x0c #define INT3472_GPIO_TYPE_PRIVACY_LED 0x0d +#define INT3472_GPIO_TYPE_DOVDD 0x10 #define INT3472_GPIO_TYPE_HANDSHAKE 0x12 #define INT3472_GPIO_TYPE_HOTPLUG_DETECT 0x13 @@ -33,8 +34,8 @@ #define INT3472_MAX_SENSOR_GPIOS 3 #define INT3472_MAX_REGULATORS 3 -/* E.g. "avdd\0" */ -#define GPIO_SUPPLY_NAME_LENGTH 5 +/* E.g. "dovdd\0" */ +#define GPIO_SUPPLY_NAME_LENGTH 6 /* 12 chars for acpi_dev_name() + "-", e.g. "ABCD1234:00-" */ #define GPIO_REGULATOR_NAME_LENGTH (12 + GPIO_SUPPLY_NAME_LENGTH) /* lower- and upper-case mapping */ diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 876358cfe1b1..d862fa610270 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -248,6 +248,7 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node); int ring_buffer_map(struct trace_buffer *buffer, int cpu, struct vm_area_struct *vma); +void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu); int ring_buffer_unmap(struct trace_buffer *buffer, int cpu); int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu); #endif /* _LINUX_RING_BUFFER_H */ diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 1f3804245c06..809e4f7dfdbd 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -647,36 +647,22 @@ static inline void user_access_restore(unsigned long flags) { } /* Define RW variant so the below _mode macro expansion works */ #define masked_user_rw_access_begin(u) masked_user_access_begin(u) #define user_rw_access_begin(u, s) user_access_begin(u, s) -#define user_rw_access_end() user_access_end() /* Scoped user access */ -#define USER_ACCESS_GUARD(_mode) \ -static __always_inline void __user * \ -class_user_##_mode##_begin(void __user *ptr) \ -{ \ - return ptr; \ -} \ - \ -static __always_inline void \ -class_user_##_mode##_end(void __user *ptr) \ -{ \ - user_##_mode##_access_end(); \ -} \ - \ -DEFINE_CLASS(user_ ##_mode## _access, void __user *, \ - class_user_##_mode##_end(_T), \ - class_user_##_mode##_begin(ptr), void __user *ptr) \ - \ -static __always_inline class_user_##_mode##_access_t \ -class_user_##_mode##_access_ptr(void __user *scope) \ -{ \ - return scope; \ -} -USER_ACCESS_GUARD(read) -USER_ACCESS_GUARD(write) -USER_ACCESS_GUARD(rw) -#undef USER_ACCESS_GUARD +/* Cleanup wrapper functions */ +static __always_inline void __scoped_user_read_access_end(const void *p) +{ + user_read_access_end(); +}; +static __always_inline void __scoped_user_write_access_end(const void *p) +{ + user_write_access_end(); +}; +static __always_inline void __scoped_user_rw_access_end(const void *p) +{ + user_access_end(); +}; /** * __scoped_user_access_begin - Start a scoped user access @@ -750,13 +736,13 @@ USER_ACCESS_GUARD(rw) * * Don't use directly. Use scoped_masked_user_$MODE_access() instead. */ -#define __scoped_user_access(mode, uptr, size, elbl) \ -for (bool done = false; !done; done = true) \ - for (void __user *_tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \ - !done; done = true) \ - for (CLASS(user_##mode##_access, scope)(_tmpptr); !done; done = true) \ - /* Force modified pointer usage within the scope */ \ - for (const typeof(uptr) uptr = _tmpptr; !done; done = true) +#define __scoped_user_access(mode, uptr, size, elbl) \ +for (bool done = false; !done; done = true) \ + for (auto _tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \ + !done; done = true) \ + /* Force modified pointer usage within the scope */ \ + for (const auto uptr __cleanup(__scoped_user_##mode##_access_end) = \ + _tmpptr; !done; done = true) /** * scoped_user_read_access_size - Start a scoped user read access with given size diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h index 2ca60828f28b..1502b2a355f9 100644 --- a/include/linux/usb/r8152.h +++ b/include/linux/usb/r8152.h @@ -32,6 +32,7 @@ #define VENDOR_ID_DLINK 0x2001 #define VENDOR_ID_DELL 0x413c #define VENDOR_ID_ASUS 0x0b05 +#define VENDOR_ID_TRENDNET 0x20f4 #if IS_REACHABLE(CONFIG_USB_RTL8152) extern u8 rtl8152_get_version(struct usb_interface *intf); diff --git a/include/net/act_api.h b/include/net/act_api.h index e1e8f0f7dacb..d11b79107930 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -70,6 +70,7 @@ struct tc_action { #define TCA_ACT_FLAGS_REPLACE (1U << (TCA_ACT_FLAGS_USER_BITS + 2)) #define TCA_ACT_FLAGS_NO_RTNL (1U << (TCA_ACT_FLAGS_USER_BITS + 3)) #define TCA_ACT_FLAGS_AT_INGRESS (1U << (TCA_ACT_FLAGS_USER_BITS + 4)) +#define TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT (1U << (TCA_ACT_FLAGS_USER_BITS + 5)) /* Update lastuse only if needed, to avoid dirtying a cache line. * We use a temp variable to avoid fetching jiffies twice. diff --git a/include/net/bonding.h b/include/net/bonding.h index 4ad5521e7731..395c6e281c5f 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -699,6 +699,7 @@ void bond_debug_register(struct bonding *bond); void bond_debug_unregister(struct bonding *bond); void bond_debug_reregister(struct bonding *bond); const char *bond_mode_name(int mode); +bool __bond_xdp_check(int mode, int xmit_policy); bool bond_xdp_check(struct bonding *bond, int mode); void bond_setup(struct net_device *bond_dev); unsigned int bond_get_num_tx_queues(void); diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 282e29237d93..c16de5b7963f 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -175,7 +175,7 @@ static inline bool inet6_match(const struct net *net, const struct sock *sk, { if (!net_eq(sock_net(sk), net) || sk->sk_family != AF_INET6 || - sk->sk_portpair != ports || + READ_ONCE(sk->sk_portpair) != ports || !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) || !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return false; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index ac05a52d9e13..5a979dcab538 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -345,7 +345,7 @@ static inline bool inet_match(const struct net *net, const struct sock *sk, int dif, int sdif) { if (!net_eq(sock_net(sk), net) || - sk->sk_portpair != ports || + READ_ONCE(sk->sk_portpair) != ports || sk->sk_addrpair != cookie) return false; diff --git a/include/net/ip.h b/include/net/ip.h index 69d5cef46004..7f9abd457e01 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -101,7 +101,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; - ipcm->protocol = inet->inet_num; + ipcm->protocol = READ_ONCE(inet->inet_num); } #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index b4495c38e0a0..318593743b6e 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -559,7 +559,7 @@ static inline u32 fib_multipath_hash_from_keys(const struct net *net, siphash_aligned_key_t hash_key; u32 mp_seed; - mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed; + mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.mp_seed); fib_multipath_hash_construct_key(&hash_key, mp_seed); return flow_hash_from_keys_seed(keys, &hash_key); diff --git a/include/net/libeth/xsk.h b/include/net/libeth/xsk.h index 481a7b28e6f2..82b5d21aae87 100644 --- a/include/net/libeth/xsk.h +++ b/include/net/libeth/xsk.h @@ -597,6 +597,7 @@ __libeth_xsk_run_pass(struct libeth_xdp_buff *xdp, * @pending: current number of XSkFQEs to refill * @thresh: threshold below which the queue is refilled * @buf_len: HW-writeable length per each buffer + * @truesize: step between consecutive buffers, 0 if none exists * @nid: ID of the closest NUMA node with memory */ struct libeth_xskfq { @@ -614,6 +615,8 @@ struct libeth_xskfq { u32 thresh; u32 buf_len; + u32 truesize; + int nid; }; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 426534a711b0..e2d2bfc1f989 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -320,11 +320,13 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv) * @NFT_ITER_UNSPEC: unspecified, to catch errors * @NFT_ITER_READ: read-only iteration over set elements * @NFT_ITER_UPDATE: iteration under mutex to update set element state + * @NFT_ITER_UPDATE_CLONE: clone set before iteration under mutex to update element */ enum nft_iter_type { NFT_ITER_UNSPEC, NFT_ITER_READ, NFT_ITER_UPDATE, + NFT_ITER_UPDATE_CLONE, }; struct nft_set; @@ -1861,6 +1863,11 @@ struct nft_trans_gc { struct rcu_head rcu; }; +static inline int nft_trans_gc_space(const struct nft_trans_gc *trans) +{ + return NFT_TRANS_GC_BATCHCOUNT - trans->count; +} + static inline void nft_ctx_update(struct nft_ctx *ctx, const struct nft_trans *trans) { diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index c3a7268b567e..d5d55cb21686 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -778,13 +778,23 @@ static inline bool skb_skip_tc_classify(struct sk_buff *skb) static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) { struct Qdisc *qdisc; + bool nolock; for (; i < dev->num_tx_queues; i++) { qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc); if (qdisc) { + nolock = qdisc->flags & TCQ_F_NOLOCK; + + if (nolock) + spin_lock_bh(&qdisc->seqlock); spin_lock_bh(qdisc_lock(qdisc)); qdisc_reset(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); + if (nolock) { + clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); + spin_unlock_bh(&qdisc->seqlock); + } } } } diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index cddebafb9f77..6f996229167b 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -5,16 +5,47 @@ #include struct net; +extern struct net init_net; + +union tcp_seq_and_ts_off { + struct { + u32 seq; + u32 ts_off; + }; + u64 hash64; +}; u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); -u32 secure_tcp_seq(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport); -u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr); -u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, - __be16 sport, __be16 dport); -u32 secure_tcpv6_ts_off(const struct net *net, - const __be32 *saddr, const __be32 *daddr); +union tcp_seq_and_ts_off +secure_tcp_seq_and_ts_off(const struct net *net, __be32 saddr, __be32 daddr, + __be16 sport, __be16 dport); +static inline u32 secure_tcp_seq(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) +{ + union tcp_seq_and_ts_off ts; + + ts = secure_tcp_seq_and_ts_off(&init_net, saddr, daddr, + sport, dport); + + return ts.seq; +} + +union tcp_seq_and_ts_off +secure_tcpv6_seq_and_ts_off(const struct net *net, const __be32 *saddr, + const __be32 *daddr, + __be16 sport, __be16 dport); + +static inline u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, + __be16 sport, __be16 dport) +{ + union tcp_seq_and_ts_off ts; + + ts = secure_tcpv6_seq_and_ts_off(&init_net, saddr, daddr, + sport, dport); + + return ts.seq; +} #endif /* _NET_SECURE_SEQ */ diff --git a/include/net/tc_act/tc_gate.h b/include/net/tc_act/tc_gate.h index b147a3bb1a46..e0fded18e18c 100644 --- a/include/net/tc_act/tc_gate.h +++ b/include/net/tc_act/tc_gate.h @@ -32,6 +32,7 @@ struct tcf_gate_params { s32 tcfg_clockid; size_t num_entries; struct list_head entries; + struct rcu_head rcu; }; #define GATE_ACT_GATE_OPEN BIT(0) @@ -39,7 +40,7 @@ struct tcf_gate_params { struct tcf_gate { struct tc_action common; - struct tcf_gate_params param; + struct tcf_gate_params __rcu *param; u8 current_gate_status; ktime_t current_close_time; u32 current_entry_octets; @@ -51,47 +52,65 @@ struct tcf_gate { #define to_gate(a) ((struct tcf_gate *)a) +static inline struct tcf_gate_params *tcf_gate_params_locked(const struct tc_action *a) +{ + struct tcf_gate *gact = to_gate(a); + + return rcu_dereference_protected(gact->param, + lockdep_is_held(&gact->tcf_lock)); +} + static inline s32 tcf_gate_prio(const struct tc_action *a) { + struct tcf_gate_params *p; s32 tcfg_prio; - tcfg_prio = to_gate(a)->param.tcfg_priority; + p = tcf_gate_params_locked(a); + tcfg_prio = p->tcfg_priority; return tcfg_prio; } static inline u64 tcf_gate_basetime(const struct tc_action *a) { + struct tcf_gate_params *p; u64 tcfg_basetime; - tcfg_basetime = to_gate(a)->param.tcfg_basetime; + p = tcf_gate_params_locked(a); + tcfg_basetime = p->tcfg_basetime; return tcfg_basetime; } static inline u64 tcf_gate_cycletime(const struct tc_action *a) { + struct tcf_gate_params *p; u64 tcfg_cycletime; - tcfg_cycletime = to_gate(a)->param.tcfg_cycletime; + p = tcf_gate_params_locked(a); + tcfg_cycletime = p->tcfg_cycletime; return tcfg_cycletime; } static inline u64 tcf_gate_cycletimeext(const struct tc_action *a) { + struct tcf_gate_params *p; u64 tcfg_cycletimeext; - tcfg_cycletimeext = to_gate(a)->param.tcfg_cycletime_ext; + p = tcf_gate_params_locked(a); + tcfg_cycletimeext = p->tcfg_cycletime_ext; return tcfg_cycletimeext; } static inline u32 tcf_gate_num_entries(const struct tc_action *a) { + struct tcf_gate_params *p; u32 num_entries; - num_entries = to_gate(a)->param.num_entries; + p = tcf_gate_params_locked(a); + num_entries = p->num_entries; return num_entries; } @@ -105,7 +124,7 @@ static inline struct action_gate_entry u32 num_entries; int i = 0; - p = &to_gate(a)->param; + p = tcf_gate_params_locked(a); num_entries = p->num_entries; list_for_each_entry(entry, &p->entries, list) diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h index c7f24a2da1ca..24d4d5a62b3c 100644 --- a/include/net/tc_act/tc_ife.h +++ b/include/net/tc_act/tc_ife.h @@ -13,15 +13,13 @@ struct tcf_ife_params { u8 eth_src[ETH_ALEN]; u16 eth_type; u16 flags; - + struct list_head metalist; struct rcu_head rcu; }; struct tcf_ife_info { struct tc_action common; struct tcf_ife_params __rcu *params; - /* list of metaids allowed */ - struct list_head metalist; }; #define to_ife(a) ((struct tcf_ife_info *)a) diff --git a/include/net/tcp.h b/include/net/tcp.h index eb8bf63fdafc..978eea2d5df0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -43,6 +43,7 @@ #include #include #include +#include #include #include @@ -2464,8 +2465,9 @@ struct tcp_request_sock_ops { struct flowi *fl, struct request_sock *req, u32 tw_isn); - u32 (*init_seq)(const struct sk_buff *skb); - u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb); + union tcp_seq_and_ts_off (*init_seq_and_ts_off)( + const struct net *net, + const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 242e34f771cc..6b9ebae2dc95 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -51,6 +51,11 @@ static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool); } +static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool) +{ + return pool->unaligned ? 0 : xsk_pool_get_chunk_size(pool); +} + static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { @@ -122,7 +127,7 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) goto out; list_for_each_entry_safe(pos, tmp, xskb_list, list_node) { - list_del(&pos->list_node); + list_del_init(&pos->list_node); xp_free(pos); } @@ -157,7 +162,7 @@ static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first) frag = list_first_entry_or_null(&xskb->pool->xskb_list, struct xdp_buff_xsk, list_node); if (frag) { - list_del(&frag->list_node); + list_del_init(&frag->list_node); ret = &frag->xdp; } @@ -168,7 +173,7 @@ static inline void xsk_buff_del_frag(struct xdp_buff *xdp) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); - list_del(&xskb->list_node); + list_del_init(&xskb->list_node); } static inline struct xdp_buff *xsk_buff_get_head(struct xdp_buff *first) @@ -337,6 +342,11 @@ static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) return 0; } +static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool) +{ + return 0; +} + static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h index ae1e1489b671..28f9f5940ab6 100644 --- a/include/sound/cs35l56.h +++ b/include/sound/cs35l56.h @@ -406,6 +406,7 @@ extern const char * const cs35l56_cal_set_status_text[3]; extern const char * const cs35l56_tx_input_texts[CS35L56_NUM_INPUT_SRC]; extern const unsigned int cs35l56_tx_input_values[CS35L56_NUM_INPUT_SRC]; +int cs35l56_set_asp_patch(struct cs35l56_base *cs35l56_base); int cs35l56_set_patch(struct cs35l56_base *cs35l56_base); int cs35l56_mbox_send(struct cs35l56_base *cs35l56_base, unsigned int command); int cs35l56_firmware_shutdown(struct cs35l56_base *cs35l56_base); diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h index 7c03bdc951bb..e847cf51878c 100644 --- a/include/sound/tas2781.h +++ b/include/sound/tas2781.h @@ -151,6 +151,7 @@ struct tasdevice { struct bulk_reg_val *cali_data_backup; struct bulk_reg_val alp_cali_bckp; struct tasdevice_fw *cali_data_fmw; + void *cali_specific; unsigned int dev_addr; unsigned int err_code; unsigned char cur_book; diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 64a382fbc31a..2d366be46a1c 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -57,6 +57,7 @@ EM(netfs_rreq_trace_done, "DONE ") \ EM(netfs_rreq_trace_end_copy_to_cache, "END-C2C") \ EM(netfs_rreq_trace_free, "FREE ") \ + EM(netfs_rreq_trace_intr, "INTR ") \ EM(netfs_rreq_trace_ki_complete, "KI-CMPL") \ EM(netfs_rreq_trace_recollect, "RECLLCT") \ EM(netfs_rreq_trace_redirty, "REDIRTY") \ @@ -169,7 +170,8 @@ EM(netfs_sreq_trace_put_oom, "PUT OOM ") \ EM(netfs_sreq_trace_put_wip, "PUT WIP ") \ EM(netfs_sreq_trace_put_work, "PUT WORK ") \ - E_(netfs_sreq_trace_put_terminated, "PUT TERM ") + EM(netfs_sreq_trace_put_terminated, "PUT TERM ") \ + E_(netfs_sreq_trace_see_failed, "SEE FAILED ") #define netfs_folio_traces \ EM(netfs_folio_is_uptodate, "mod-uptodate") \ diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h index 5a6fda66d9ad..e827c9d20c5d 100644 --- a/include/uapi/linux/dma-buf.h +++ b/include/uapi/linux/dma-buf.h @@ -20,6 +20,7 @@ #ifndef _DMA_BUF_UAPI_H_ #define _DMA_BUF_UAPI_H_ +#include #include /** diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 6750c383a2ab..1ff16141c8a5 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -188,7 +188,8 @@ enum io_uring_sqe_flags_bit { /* * If COOP_TASKRUN is set, get notified if task work is available for * running and a kernel transition would be needed to run it. This sets - * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN. + * IORING_SQ_TASKRUN in the sq ring flags. Not valid without COOP_TASKRUN + * or DEFER_TASKRUN. */ #define IORING_SETUP_TASKRUN_FLAG (1U << 9) #define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */ diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index c94caf852aea..8ca15743af7f 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -80,6 +80,7 @@ struct xenbus_device { const char *devicetype; const char *nodename; const char *otherend; + bool vanished; int otherend_id; struct xenbus_watch otherend_watch; struct device dev; @@ -228,7 +229,8 @@ int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr); int xenbus_alloc_evtchn(struct xenbus_device *dev, evtchn_port_t *port); int xenbus_free_evtchn(struct xenbus_device *dev, evtchn_port_t port); -enum xenbus_state xenbus_read_driver_state(const char *path); +enum xenbus_state xenbus_read_driver_state(const struct xenbus_device *dev, + const char *path); __printf(3, 4) void xenbus_dev_error(struct xenbus_device *dev, int err, const char *fmt, ...); diff --git a/init/Kconfig b/init/Kconfig index b55deae9256c..444ce811ea67 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1902,7 +1902,7 @@ config IO_URING_MOCK_FILE default n depends on IO_URING help - Enable mock files for io_uring subststem testing. The ABI might + Enable mock files for io_uring subsystem testing. The ABI might still change, so it's still experimental and should only be enabled for specific test purposes. diff --git a/io_uring/net.c b/io_uring/net.c index 8576c6cb2236..d27adbe3f20b 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -375,6 +375,8 @@ static int io_send_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe) kmsg->msg.msg_namelen = addr_len; } if (sr->flags & IORING_RECVSEND_FIXED_BUF) { + if (sr->flags & IORING_SEND_VECTORIZED) + return -EINVAL; req->flags |= REQ_F_IMPORT_BUFFER; return 0; } diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index cf5bec065aaf..62d693287457 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -837,7 +837,8 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx, if (ret) goto netdev_put_unlock; - mp_param.rx_page_size = 1U << ifq->niov_shift; + if (reg.rx_buf_len) + mp_param.rx_page_size = 1U << ifq->niov_shift; mp_param.mp_ops = &io_uring_pp_zc_ops; mp_param.mp_priv = ifq; ret = __net_mp_open_rxq(ifq->netdev, reg.if_rxq, &mp_param, NULL); @@ -926,11 +927,12 @@ static inline bool io_parse_rqe(struct io_uring_zcrx_rqe *rqe, struct io_zcrx_ifq *ifq, struct net_iov **ret_niov) { + __u64 off = READ_ONCE(rqe->off); unsigned niov_idx, area_idx; struct io_zcrx_area *area; - area_idx = rqe->off >> IORING_ZCRX_AREA_SHIFT; - niov_idx = (rqe->off & ~IORING_ZCRX_AREA_MASK) >> ifq->niov_shift; + area_idx = off >> IORING_ZCRX_AREA_SHIFT; + niov_idx = (off & ~IORING_ZCRX_AREA_MASK) >> ifq->niov_shift; if (unlikely(rqe->__pad || area_idx)) return false; diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 84db9e658e52..f02254a21585 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -1002,10 +1002,8 @@ int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, mutex_lock(&tr->mutex); shim_link = cgroup_shim_find(tr, bpf_func); - if (shim_link) { + if (shim_link && !IS_ERR(bpf_link_inc_not_zero(&shim_link->link.link))) { /* Reusing existing shim attached by the other program. */ - bpf_link_inc(&shim_link->link.link); - mutex_unlock(&tr->mutex); bpf_trampoline_put(tr); /* bpf_trampoline_get above */ return 0; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 401d6c4960ec..159b25f8269d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2511,6 +2511,30 @@ static void __reg32_deduce_bounds(struct bpf_reg_state *reg) if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) { reg->u32_min_value = max_t(u32, reg->s32_min_value, reg->u32_min_value); reg->u32_max_value = min_t(u32, reg->s32_max_value, reg->u32_max_value); + } else { + if (reg->u32_max_value < (u32)reg->s32_min_value) { + /* See __reg64_deduce_bounds() for detailed explanation. + * Refine ranges in the following situation: + * + * 0 U32_MAX + * | [xxxxxxxxxxxxxx u32 range xxxxxxxxxxxxxx] | + * |----------------------------|----------------------------| + * |xxxxx s32 range xxxxxxxxx] [xxxxxxx| + * 0 S32_MAX S32_MIN -1 + */ + reg->s32_min_value = (s32)reg->u32_min_value; + reg->u32_max_value = min_t(u32, reg->u32_max_value, reg->s32_max_value); + } else if ((u32)reg->s32_max_value < reg->u32_min_value) { + /* + * 0 U32_MAX + * | [xxxxxxxxxxxxxx u32 range xxxxxxxxxxxxxx] | + * |----------------------------|----------------------------| + * |xxxxxxxxx] [xxxxxxxxxxxx s32 range | + * 0 S32_MAX S32_MIN -1 + */ + reg->s32_max_value = (s32)reg->u32_max_value; + reg->u32_min_value = max_t(u32, reg->u32_min_value, reg->s32_min_value); + } } } @@ -17335,17 +17359,24 @@ static void __collect_linked_regs(struct linked_regs *reg_set, struct bpf_reg_st * in verifier state, save R in linked_regs if R->id == id. * If there are too many Rs sharing same id, reset id for leftover Rs. */ -static void collect_linked_regs(struct bpf_verifier_state *vstate, u32 id, +static void collect_linked_regs(struct bpf_verifier_env *env, + struct bpf_verifier_state *vstate, + u32 id, struct linked_regs *linked_regs) { + struct bpf_insn_aux_data *aux = env->insn_aux_data; struct bpf_func_state *func; struct bpf_reg_state *reg; + u16 live_regs; int i, j; id = id & ~BPF_ADD_CONST; for (i = vstate->curframe; i >= 0; i--) { + live_regs = aux[frame_insn_idx(vstate, i)].live_regs_before; func = vstate->frame[i]; for (j = 0; j < BPF_REG_FP; j++) { + if (!(live_regs & BIT(j))) + continue; reg = &func->regs[j]; __collect_linked_regs(linked_regs, reg, id, i, j, true); } @@ -17560,9 +17591,9 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, * if parent state is created. */ if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id) - collect_linked_regs(this_branch, src_reg->id, &linked_regs); + collect_linked_regs(env, this_branch, src_reg->id, &linked_regs); if (dst_reg->type == SCALAR_VALUE && dst_reg->id) - collect_linked_regs(this_branch, dst_reg->id, &linked_regs); + collect_linked_regs(env, this_branch, dst_reg->id, &linked_regs); if (linked_regs.cnt > 1) { err = push_jmp_history(env, this_branch, 0, linked_regs_pack(&linked_regs)); if (err) @@ -25261,7 +25292,6 @@ BTF_ID(func, __x64_sys_exit_group) BTF_ID(func, do_exit) BTF_ID(func, do_group_exit) BTF_ID(func, kthread_complete_and_exit) -BTF_ID(func, kthread_exit) BTF_ID(func, make_task_dead) BTF_SET_END(noreturn_deny) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c22cda7766d8..be1d71dda317 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2608,6 +2608,7 @@ static void cgroup_migrate_add_task(struct task_struct *task, mgctx->tset.nr_tasks++; + css_set_skip_task_iters(cset, task); list_move_tail(&task->cg_list, &cset->mg_tasks); if (list_empty(&cset->mg_node)) list_add_tail(&cset->mg_node, diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 9faf34377a88..e200de7c60b6 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -61,6 +61,75 @@ static const char * const perr_strings[] = { [PERR_REMOTE] = "Have remote partition underneath", }; +/* + * CPUSET Locking Convention + * ------------------------- + * + * Below are the four global/local locks guarding cpuset structures in lock + * acquisition order: + * - cpuset_top_mutex + * - cpu_hotplug_lock (cpus_read_lock/cpus_write_lock) + * - cpuset_mutex + * - callback_lock (raw spinlock) + * + * As cpuset will now indirectly flush a number of different workqueues in + * housekeeping_update() to update housekeeping cpumasks when the set of + * isolated CPUs is going to be changed, it may be vulnerable to deadlock + * if we hold cpus_read_lock while calling into housekeeping_update(). + * + * The first cpuset_top_mutex will be held except when calling into + * cpuset_handle_hotplug() from the CPU hotplug code where cpus_write_lock + * and cpuset_mutex will be held instead. The main purpose of this mutex + * is to prevent regular cpuset control file write actions from interfering + * with the call to housekeeping_update(), though CPU hotplug operation can + * still happen in parallel. This mutex also provides protection for some + * internal variables. + * + * A task must hold all the remaining three locks to modify externally visible + * or used fields of cpusets, though some of the internally used cpuset fields + * and internal variables can be modified without holding callback_lock. If only + * reliable read access of the externally used fields are needed, a task can + * hold either cpuset_mutex or callback_lock which are exposed to other + * external subsystems. + * + * If a task holds cpu_hotplug_lock and cpuset_mutex, it blocks others, + * ensuring that it is the only task able to also acquire callback_lock and + * be able to modify cpusets. It can perform various checks on the cpuset + * structure first, knowing nothing will change. It can also allocate memory + * without holding callback_lock. While it is performing these checks, various + * callback routines can briefly acquire callback_lock to query cpusets. Once + * it is ready to make the changes, it takes callback_lock, blocking everyone + * else. + * + * Calls to the kernel memory allocator cannot be made while holding + * callback_lock which is a spinlock, as the memory allocator may sleep or + * call back into cpuset code and acquire callback_lock. + * + * Now, the task_struct fields mems_allowed and mempolicy may be changed + * by other task, we use alloc_lock in the task_struct fields to protect + * them. + * + * The cpuset_common_seq_show() handlers only hold callback_lock across + * small pieces of code, such as when reading out possibly multi-word + * cpumasks and nodemasks. + */ + +static DEFINE_MUTEX(cpuset_top_mutex); +static DEFINE_MUTEX(cpuset_mutex); + +/* + * File level internal variables below follow one of the following exclusion + * rules. + * + * RWCS: Read/write-able by holding either cpus_write_lock (and optionally + * cpuset_mutex) or both cpus_read_lock and cpuset_mutex. + * + * CSCB: Readable by holding either cpuset_mutex or callback_lock. Writable + * by holding both cpuset_mutex and callback_lock. + * + * T: Read/write-able by holding the cpuset_top_mutex. + */ + /* * For local partitions, update to subpartitions_cpus & isolated_cpus is done * in update_parent_effective_cpumask(). For remote partitions, it is done in @@ -70,19 +139,22 @@ static const char * const perr_strings[] = { * Exclusive CPUs distributed out to local or remote sub-partitions of * top_cpuset */ -static cpumask_var_t subpartitions_cpus; +static cpumask_var_t subpartitions_cpus; /* RWCS */ /* - * Exclusive CPUs in isolated partitions + * Exclusive CPUs in isolated partitions (shown in cpuset.cpus.isolated) */ -static cpumask_var_t isolated_cpus; +static cpumask_var_t isolated_cpus; /* CSCB */ /* - * isolated_cpus updating flag (protected by cpuset_mutex) - * Set if isolated_cpus is going to be updated in the current - * cpuset_mutex crtical section. + * Set if housekeeping cpumasks are to be updated. */ -static bool isolated_cpus_updating; +static bool update_housekeeping; /* RWCS */ + +/* + * Copy of isolated_cpus to be passed to housekeeping_update() + */ +static cpumask_var_t isolated_hk_cpus; /* T */ /* * A flag to force sched domain rebuild at the end of an operation. @@ -98,7 +170,7 @@ static bool isolated_cpus_updating; * Note that update_relax_domain_level() in cpuset-v1.c can still call * rebuild_sched_domains_locked() directly without using this flag. */ -static bool force_sd_rebuild; +static bool force_sd_rebuild; /* RWCS */ /* * Partition root states: @@ -218,42 +290,6 @@ struct cpuset top_cpuset = { .partition_root_state = PRS_ROOT, }; -/* - * There are two global locks guarding cpuset structures - cpuset_mutex and - * callback_lock. The cpuset code uses only cpuset_mutex. Other kernel - * subsystems can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset - * structures. Note that cpuset_mutex needs to be a mutex as it is used in - * paths that rely on priority inheritance (e.g. scheduler - on RT) for - * correctness. - * - * A task must hold both locks to modify cpusets. If a task holds - * cpuset_mutex, it blocks others, ensuring that it is the only task able to - * also acquire callback_lock and be able to modify cpusets. It can perform - * various checks on the cpuset structure first, knowing nothing will change. - * It can also allocate memory while just holding cpuset_mutex. While it is - * performing these checks, various callback routines can briefly acquire - * callback_lock to query cpusets. Once it is ready to make the changes, it - * takes callback_lock, blocking everyone else. - * - * Calls to the kernel memory allocator can not be made while holding - * callback_lock, as that would risk double tripping on callback_lock - * from one of the callbacks into the cpuset code from within - * __alloc_pages(). - * - * If a task is only holding callback_lock, then it has read-only - * access to cpusets. - * - * Now, the task_struct fields mems_allowed and mempolicy may be changed - * by other task, we use alloc_lock in the task_struct fields to protect - * them. - * - * The cpuset_common_seq_show() handlers only hold callback_lock across - * small pieces of code, such as when reading out possibly multi-word - * cpumasks and nodemasks. - */ - -static DEFINE_MUTEX(cpuset_mutex); - /** * cpuset_lock - Acquire the global cpuset mutex * @@ -283,6 +319,7 @@ void lockdep_assert_cpuset_lock_held(void) */ void cpuset_full_lock(void) { + mutex_lock(&cpuset_top_mutex); cpus_read_lock(); mutex_lock(&cpuset_mutex); } @@ -291,12 +328,14 @@ void cpuset_full_unlock(void) { mutex_unlock(&cpuset_mutex); cpus_read_unlock(); + mutex_unlock(&cpuset_top_mutex); } #ifdef CONFIG_LOCKDEP bool lockdep_is_cpuset_held(void) { - return lockdep_is_held(&cpuset_mutex); + return lockdep_is_held(&cpuset_mutex) || + lockdep_is_held(&cpuset_top_mutex); } #endif @@ -961,7 +1000,7 @@ void rebuild_sched_domains_locked(void) * offline CPUs, a warning is emitted and we return directly to * prevent the panic. */ - for (i = 0; i < ndoms; ++i) { + for (i = 0; doms && i < ndoms; i++) { if (WARN_ON_ONCE(!cpumask_subset(doms[i], cpu_active_mask))) return; } @@ -1161,12 +1200,18 @@ static void reset_partition_data(struct cpuset *cs) static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus) { WARN_ON_ONCE(old_prs == new_prs); - if (new_prs == PRS_ISOLATED) + lockdep_assert_held(&callback_lock); + lockdep_assert_held(&cpuset_mutex); + if (new_prs == PRS_ISOLATED) { + if (cpumask_subset(xcpus, isolated_cpus)) + return; cpumask_or(isolated_cpus, isolated_cpus, xcpus); - else + } else { + if (!cpumask_intersects(xcpus, isolated_cpus)) + return; cpumask_andnot(isolated_cpus, isolated_cpus, xcpus); - - isolated_cpus_updating = true; + } + update_housekeeping = true; } /* @@ -1219,8 +1264,8 @@ static void partition_xcpus_del(int old_prs, struct cpuset *parent, isolated_cpus_update(old_prs, parent->partition_root_state, xcpus); - cpumask_and(xcpus, xcpus, cpu_active_mask); cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus); + cpumask_and(parent->effective_cpus, parent->effective_cpus, cpu_active_mask); } /* @@ -1284,22 +1329,43 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus) } /* - * update_isolation_cpumasks - Update external isolation related CPU masks + * update_hk_sched_domains - Update HK cpumasks & rebuild sched domains * - * The following external CPU masks will be updated if necessary: - * - workqueue unbound cpumask + * Update housekeeping cpumasks and rebuild sched domains if necessary. + * This should be called at the end of cpuset or hotplug actions. */ -static void update_isolation_cpumasks(void) +static void update_hk_sched_domains(void) { - int ret; + if (update_housekeeping) { + /* Updating HK cpumasks implies rebuild sched domains */ + update_housekeeping = false; + force_sd_rebuild = true; + cpumask_copy(isolated_hk_cpus, isolated_cpus); - if (!isolated_cpus_updating) - return; + /* + * housekeeping_update() is now called without holding + * cpus_read_lock and cpuset_mutex. Only cpuset_top_mutex + * is still being held for mutual exclusion. + */ + mutex_unlock(&cpuset_mutex); + cpus_read_unlock(); + WARN_ON_ONCE(housekeeping_update(isolated_hk_cpus)); + cpus_read_lock(); + mutex_lock(&cpuset_mutex); + } + /* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */ + if (force_sd_rebuild) + rebuild_sched_domains_locked(); +} - ret = housekeeping_update(isolated_cpus); - WARN_ON_ONCE(ret < 0); - - isolated_cpus_updating = false; +/* + * Work function to invoke update_hk_sched_domains() + */ +static void hk_sd_workfn(struct work_struct *work) +{ + cpuset_full_lock(); + update_hk_sched_domains(); + cpuset_full_unlock(); } /** @@ -1450,7 +1516,6 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs, cs->remote_partition = true; cpumask_copy(cs->effective_xcpus, tmp->new_cpus); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); cpuset_force_rebuild(); cs->prs_err = 0; @@ -1495,7 +1560,6 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp) compute_excpus(cs, cs->effective_xcpus); reset_partition_data(cs); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); cpuset_force_rebuild(); /* @@ -1566,7 +1630,6 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus, if (xcpus) cpumask_copy(cs->exclusive_cpus, xcpus); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); if (adding || deleting) cpuset_force_rebuild(); @@ -1910,7 +1973,6 @@ write_error: partition_xcpus_add(new_prs, parent, tmp->delmask); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); if ((old_prs != new_prs) && (cmd == partcmd_update)) update_partition_exclusive_flag(cs, new_prs); @@ -2155,7 +2217,7 @@ get_css: WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); - cpuset_update_tasks_cpumask(cp, cp->effective_cpus); + cpuset_update_tasks_cpumask(cp, tmp->new_cpus); /* * On default hierarchy, inherit the CS_SCHED_LOAD_BALANCE @@ -2878,7 +2940,6 @@ out: else if (isolcpus_updated) isolated_cpus_update(old_prs, new_prs, cs->effective_xcpus); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); /* Force update if switching back to member & update effective_xcpus */ update_cpumasks_hier(cs, &tmpmask, !new_prs); @@ -3168,9 +3229,8 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of, } free_cpuset(trialcs); - if (force_sd_rebuild) - rebuild_sched_domains_locked(); out_unlock: + update_hk_sched_domains(); cpuset_full_unlock(); if (of_cft(of)->private == FILE_MEMLIST) schedule_flush_migrate_mm(); @@ -3278,6 +3338,7 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf, cpuset_full_lock(); if (is_cpuset_online(cs)) retval = update_prstate(cs, val); + update_hk_sched_domains(); cpuset_full_unlock(); return retval ?: nbytes; } @@ -3452,6 +3513,7 @@ static void cpuset_css_killed(struct cgroup_subsys_state *css) /* Reset valid partition back to member */ if (is_partition_valid(cs)) update_prstate(cs, PRS_MEMBER); + update_hk_sched_domains(); cpuset_full_unlock(); } @@ -3607,6 +3669,7 @@ int __init cpuset_init(void) BUG_ON(!alloc_cpumask_var(&top_cpuset.exclusive_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&subpartitions_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&isolated_cpus, GFP_KERNEL)); + BUG_ON(!zalloc_cpumask_var(&isolated_hk_cpus, GFP_KERNEL)); cpumask_setall(top_cpuset.cpus_allowed); nodes_setall(top_cpuset.mems_allowed); @@ -3778,6 +3841,7 @@ unlock: */ static void cpuset_handle_hotplug(void) { + static DECLARE_WORK(hk_sd_work, hk_sd_workfn); static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated, mems_updated; @@ -3859,9 +3923,21 @@ static void cpuset_handle_hotplug(void) rcu_read_unlock(); } - /* rebuild sched domains if necessary */ - if (force_sd_rebuild) - rebuild_sched_domains_cpuslocked(); + + /* + * Queue a work to call housekeeping_update() & rebuild_sched_domains() + * There will be a slight delay before the HK_TYPE_DOMAIN housekeeping + * cpumask can correctly reflect what is in isolated_cpus. + * + * We rely on WORK_STRUCT_PENDING_BIT to not requeue a work item that + * is still pending. Before the pending bit is cleared, the work data + * is copied out and work item dequeued. So it is possible to queue + * the work again before the hk_sd_workfn() is invoked to process the + * previously queued work. Since hk_sd_workfn() doesn't use the work + * item at all, this is not a problem. + */ + if (update_housekeeping || force_sd_rebuild) + queue_work(system_unbound_wq, &hk_sd_work); free_tmpmasks(ptmp); } diff --git a/kernel/exit.c b/kernel/exit.c index 8a87021211ae..ede3117fa7d4 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -896,11 +896,16 @@ static void synchronize_group_exit(struct task_struct *tsk, long code) void __noreturn do_exit(long code) { struct task_struct *tsk = current; + struct kthread *kthread; int group_dead; WARN_ON(irqs_disabled()); WARN_ON(tsk->plug); + kthread = tsk_is_kthread(tsk); + if (unlikely(kthread)) + kthread_do_exit(kthread, code); + kcov_task_exit(tsk); kmsan_task_exit(tsk); @@ -1013,6 +1018,7 @@ void __noreturn do_exit(long code) lockdep_free_task(tsk); do_task_dead(); } +EXPORT_SYMBOL(do_exit); void __noreturn make_task_dead(int signr) { diff --git a/kernel/kthread.c b/kernel/kthread.c index 20451b624b67..791210daf8b4 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -85,24 +85,6 @@ static inline struct kthread *to_kthread(struct task_struct *k) return k->worker_private; } -/* - * Variant of to_kthread() that doesn't assume @p is a kthread. - * - * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will - * always remain a kthread. For kthreads p->worker_private always - * points to a struct kthread. For tasks that are not kthreads - * p->worker_private is used to point to other things. - * - * Return NULL for any task that is not a kthread. - */ -static inline struct kthread *__to_kthread(struct task_struct *p) -{ - void *kthread = p->worker_private; - if (kthread && !(p->flags & PF_KTHREAD)) - kthread = NULL; - return kthread; -} - void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk) { struct kthread *kthread = to_kthread(tsk); @@ -193,7 +175,7 @@ EXPORT_SYMBOL_GPL(kthread_should_park); bool kthread_should_stop_or_park(void) { - struct kthread *kthread = __to_kthread(current); + struct kthread *kthread = tsk_is_kthread(current); if (!kthread) return false; @@ -234,7 +216,7 @@ EXPORT_SYMBOL_GPL(kthread_freezable_should_stop); */ void *kthread_func(struct task_struct *task) { - struct kthread *kthread = __to_kthread(task); + struct kthread *kthread = tsk_is_kthread(task); if (kthread) return kthread->threadfn; return NULL; @@ -266,7 +248,7 @@ EXPORT_SYMBOL_GPL(kthread_data); */ void *kthread_probe_data(struct task_struct *task) { - struct kthread *kthread = __to_kthread(task); + struct kthread *kthread = tsk_is_kthread(task); void *data = NULL; if (kthread) @@ -309,19 +291,8 @@ void kthread_parkme(void) } EXPORT_SYMBOL_GPL(kthread_parkme); -/** - * kthread_exit - Cause the current kthread return @result to kthread_stop(). - * @result: The integer value to return to kthread_stop(). - * - * While kthread_exit can be called directly, it exists so that - * functions which do some additional work in non-modular code such as - * module_put_and_kthread_exit can be implemented. - * - * Does not return. - */ -void __noreturn kthread_exit(long result) +void kthread_do_exit(struct kthread *kthread, long result) { - struct kthread *kthread = to_kthread(current); kthread->result = result; if (!list_empty(&kthread->affinity_node)) { mutex_lock(&kthread_affinity_lock); @@ -333,9 +304,7 @@ void __noreturn kthread_exit(long result) kthread->preferred_affinity = NULL; } } - do_exit(0); } -EXPORT_SYMBOL(kthread_exit); /** * kthread_complete_and_exit - Exit the current kthread. @@ -683,7 +652,7 @@ void kthread_set_per_cpu(struct task_struct *k, int cpu) bool kthread_is_per_cpu(struct task_struct *p) { - struct kthread *kthread = __to_kthread(p); + struct kthread *kthread = tsk_is_kthread(p); if (!kthread) return false; diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index be74917802ad..43b1bb01fd27 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -169,9 +169,10 @@ config MODVERSIONS make them incompatible with the kernel you are running. If unsure, say N. +if MODVERSIONS + choice prompt "Module versioning implementation" - depends on MODVERSIONS help Select the tool used to calculate symbol versions for modules. @@ -206,7 +207,7 @@ endchoice config ASM_MODVERSIONS bool - default HAVE_ASM_MODVERSIONS && MODVERSIONS + default HAVE_ASM_MODVERSIONS help This enables module versioning for exported symbols also from assembly. This can be enabled only when the target architecture @@ -214,7 +215,6 @@ config ASM_MODVERSIONS config EXTENDED_MODVERSIONS bool "Extended Module Versioning Support" - depends on MODVERSIONS help This enables extended MODVERSIONs support, allowing long symbol names to be versioned. @@ -224,7 +224,6 @@ config EXTENDED_MODVERSIONS config BASIC_MODVERSIONS bool "Basic Module Versioning Support" - depends on MODVERSIONS default y help This enables basic MODVERSIONS support, allowing older tools or @@ -237,6 +236,8 @@ config BASIC_MODVERSIONS This is enabled by default when MODVERSIONS are enabled. If unsure, say Y. +endif # MODVERSIONS + config MODULE_SRCVERSION_ALL bool "Source checksum for all modules" help @@ -277,10 +278,11 @@ config MODULE_SIG_FORCE Reject unsigned modules or signed modules for which we don't have a key. Without this, such modules will simply taint the kernel. +if MODULE_SIG || IMA_APPRAISE_MODSIG + config MODULE_SIG_ALL bool "Automatically sign all modules" default y - depends on MODULE_SIG || IMA_APPRAISE_MODSIG help Sign all modules during make modules_install. Without this option, modules must be signed manually, using the scripts/sign-file tool. @@ -290,7 +292,6 @@ comment "Do not forget to sign required modules with scripts/sign-file" choice prompt "Hash algorithm to sign modules" - depends on MODULE_SIG || IMA_APPRAISE_MODSIG default MODULE_SIG_SHA512 help This determines which sort of hashing algorithm will be used during @@ -327,7 +328,6 @@ endchoice config MODULE_SIG_HASH string - depends on MODULE_SIG || IMA_APPRAISE_MODSIG default "sha256" if MODULE_SIG_SHA256 default "sha384" if MODULE_SIG_SHA384 default "sha512" if MODULE_SIG_SHA512 @@ -335,6 +335,8 @@ config MODULE_SIG_HASH default "sha3-384" if MODULE_SIG_SHA3_384 default "sha3-512" if MODULE_SIG_SHA3_512 +endif # MODULE_SIG || IMA_APPRAISE_MODSIG + config MODULE_COMPRESS bool "Module compression" help @@ -350,9 +352,10 @@ config MODULE_COMPRESS If unsure, say N. +if MODULE_COMPRESS + choice prompt "Module compression type" - depends on MODULE_COMPRESS help Choose the supported algorithm for module compression. @@ -379,7 +382,6 @@ endchoice config MODULE_COMPRESS_ALL bool "Automatically compress all modules" default y - depends on MODULE_COMPRESS help Compress all modules during 'make modules_install'. @@ -389,7 +391,6 @@ config MODULE_COMPRESS_ALL config MODULE_DECOMPRESS bool "Support in-kernel module decompression" - depends on MODULE_COMPRESS select ZLIB_INFLATE if MODULE_COMPRESS_GZIP select XZ_DEC if MODULE_COMPRESS_XZ select ZSTD_DECOMPRESS if MODULE_COMPRESS_ZSTD @@ -400,6 +401,8 @@ config MODULE_DECOMPRESS If unsure, say N. +endif # MODULE_COMPRESS + config MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS bool "Allow loading of modules with missing namespace imports" help diff --git a/kernel/module/main.c b/kernel/module/main.c index 2bac4c7cd019..c3ce106c70af 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1568,6 +1568,13 @@ static int simplify_symbols(struct module *mod, const struct load_info *info) break; default: + if (sym[i].st_shndx >= info->hdr->e_shnum) { + pr_err("%s: Symbol %s has an invalid section index %u (max %u)\n", + mod->name, name, sym[i].st_shndx, info->hdr->e_shnum - 1); + ret = -ENOEXEC; + break; + } + /* Divert to percpu allocation if a percpu var. */ if (sym[i].st_shndx == info->index.pcpu) secbase = (unsigned long)mod_percpu(mod); @@ -3544,12 +3551,6 @@ static int load_module(struct load_info *info, const char __user *uargs, mutex_unlock(&module_mutex); free_module: mod_stat_bump_invalid(info, flags); - /* Free lock-classes; relies on the preceding sync_rcu() */ - for_class_mod_mem_type(type, core_data) { - lockdep_free_key_range(mod->mem[type].base, - mod->mem[type].size); - } - module_memory_restore_rox(mod); module_deallocate(mod, info); free_copy: diff --git a/kernel/nscommon.c b/kernel/nscommon.c index bdc3c86231d3..3166c1fd844a 100644 --- a/kernel/nscommon.c +++ b/kernel/nscommon.c @@ -309,3 +309,9 @@ void __ns_ref_active_get(struct ns_common *ns) return; } } + +bool may_see_all_namespaces(void) +{ + return (task_active_pid_ns(current) == &init_pid_ns) && + ns_capable_noaudit(init_pid_ns.user_ns, CAP_SYS_ADMIN); +} diff --git a/kernel/nstree.c b/kernel/nstree.c index f36c59e6951d..6d12e5900ac0 100644 --- a/kernel/nstree.c +++ b/kernel/nstree.c @@ -515,32 +515,11 @@ static inline bool __must_check ns_requested(const struct klistns *kls, static inline bool __must_check may_list_ns(const struct klistns *kls, struct ns_common *ns) { - if (kls->user_ns) { - if (kls->userns_capable) - return true; - } else { - struct ns_common *owner; - struct user_namespace *user_ns; - - owner = ns_owner(ns); - if (owner) - user_ns = to_user_ns(owner); - else - user_ns = &init_user_ns; - if (ns_capable_noaudit(user_ns, CAP_SYS_ADMIN)) - return true; - } - + if (kls->user_ns && kls->userns_capable) + return true; if (is_current_namespace(ns)) return true; - - if (ns->ns_type != CLONE_NEWUSER) - return false; - - if (ns_capable_noaudit(to_user_ns(ns), CAP_SYS_ADMIN)) - return true; - - return false; + return may_see_all_namespaces(); } static inline void ns_put(struct ns_common *ns) @@ -600,7 +579,7 @@ static ssize_t do_listns_userns(struct klistns *kls) ret = 0; head = &to_ns_common(kls->user_ns)->ns_owner_root.ns_list_head; - kls->userns_capable = ns_capable_noaudit(kls->user_ns, CAP_SYS_ADMIN); + kls->userns_capable = may_see_all_namespaces(); rcu_read_lock(); diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 06cc0a4aec66..1594987d637b 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -976,8 +976,12 @@ static bool scx_dsq_priq_less(struct rb_node *node_a, static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta) { - /* scx_bpf_dsq_nr_queued() reads ->nr without locking, use WRITE_ONCE() */ - WRITE_ONCE(dsq->nr, dsq->nr + delta); + /* + * scx_bpf_dsq_nr_queued() reads ->nr without locking. Use READ_ONCE() + * on the read side and WRITE_ONCE() on the write side to properly + * annotate the concurrent lockless access and avoid KCSAN warnings. + */ + WRITE_ONCE(dsq->nr, READ_ONCE(dsq->nr) + delta); } static void refill_task_slice_dfl(struct scx_sched *sch, struct task_struct *p) @@ -2735,7 +2739,7 @@ static bool check_rq_for_timeouts(struct rq *rq) unsigned long last_runnable = p->scx.runnable_at; if (unlikely(time_after(jiffies, - last_runnable + scx_watchdog_timeout))) { + last_runnable + READ_ONCE(scx_watchdog_timeout)))) { u32 dur_ms = jiffies_to_msecs(jiffies - last_runnable); scx_exit(sch, SCX_EXIT_ERROR_STALL, 0, @@ -2763,7 +2767,7 @@ static void scx_watchdog_workfn(struct work_struct *work) cond_resched(); } queue_delayed_work(system_unbound_wq, to_delayed_work(work), - scx_watchdog_timeout / 2); + READ_ONCE(scx_watchdog_timeout) / 2); } void scx_tick(struct rq *rq) @@ -3585,7 +3589,6 @@ static int scx_cgroup_init(struct scx_sched *sch) ret = SCX_CALL_OP_RET(sch, SCX_KF_UNLOCKED, cgroup_init, NULL, css->cgroup, &args); if (ret) { - css_put(css); scx_error(sch, "ops.cgroup_init() failed (%d)", ret); return ret; } @@ -3708,7 +3711,9 @@ static void scx_kobj_release(struct kobject *kobj) static ssize_t scx_attr_ops_show(struct kobject *kobj, struct kobj_attribute *ka, char *buf) { - return sysfs_emit(buf, "%s\n", scx_root->ops.name); + struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj); + + return sysfs_emit(buf, "%s\n", sch->ops.name); } SCX_ATTR(ops); @@ -3752,7 +3757,9 @@ static const struct kobj_type scx_ktype = { static int scx_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) { - return add_uevent_var(env, "SCXOPS=%s", scx_root->ops.name); + const struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj); + + return add_uevent_var(env, "SCXOPS=%s", sch->ops.name); } static const struct kset_uevent_ops scx_uevent_ops = { @@ -4423,10 +4430,19 @@ done: scx_bypass(false); } +/* + * Claim the exit on @sch. The caller must ensure that the helper kthread work + * is kicked before the current task can be preempted. Once exit_kind is + * claimed, scx_error() can no longer trigger, so if the current task gets + * preempted and the BPF scheduler fails to schedule it back, the helper work + * will never be kicked and the whole system can wedge. + */ static bool scx_claim_exit(struct scx_sched *sch, enum scx_exit_kind kind) { int none = SCX_EXIT_NONE; + lockdep_assert_preemption_disabled(); + if (!atomic_try_cmpxchg(&sch->exit_kind, &none, kind)) return false; @@ -4449,6 +4465,7 @@ static void scx_disable(enum scx_exit_kind kind) rcu_read_lock(); sch = rcu_dereference(scx_root); if (sch) { + guard(preempt)(); scx_claim_exit(sch, kind); kthread_queue_work(sch->helper, &sch->disable_work); } @@ -4771,6 +4788,8 @@ static bool scx_vexit(struct scx_sched *sch, { struct scx_exit_info *ei = sch->exit_info; + guard(preempt)(); + if (!scx_claim_exit(sch, kind)) return false; @@ -4955,20 +4974,30 @@ static int validate_ops(struct scx_sched *sch, const struct sched_ext_ops *ops) return 0; } -static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) +/* + * scx_enable() is offloaded to a dedicated system-wide RT kthread to avoid + * starvation. During the READY -> ENABLED task switching loop, the calling + * thread's sched_class gets switched from fair to ext. As fair has higher + * priority than ext, the calling thread can be indefinitely starved under + * fair-class saturation, leading to a system hang. + */ +struct scx_enable_cmd { + struct kthread_work work; + struct sched_ext_ops *ops; + int ret; +}; + +static void scx_enable_workfn(struct kthread_work *work) { + struct scx_enable_cmd *cmd = + container_of(work, struct scx_enable_cmd, work); + struct sched_ext_ops *ops = cmd->ops; struct scx_sched *sch; struct scx_task_iter sti; struct task_struct *p; unsigned long timeout; int i, cpu, ret; - if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN), - cpu_possible_mask)) { - pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n"); - return -EINVAL; - } - mutex_lock(&scx_enable_mutex); if (scx_enable_state() != SCX_DISABLED) { @@ -5060,7 +5089,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) WRITE_ONCE(scx_watchdog_timeout, timeout); WRITE_ONCE(scx_watchdog_timestamp, jiffies); queue_delayed_work(system_unbound_wq, &scx_watchdog_work, - scx_watchdog_timeout / 2); + READ_ONCE(scx_watchdog_timeout) / 2); /* * Once __scx_enabled is set, %current can be switched to SCX anytime. @@ -5185,13 +5214,15 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) atomic_long_inc(&scx_enable_seq); - return 0; + cmd->ret = 0; + return; err_free_ksyncs: free_kick_syncs(); err_unlock: mutex_unlock(&scx_enable_mutex); - return ret; + cmd->ret = ret; + return; err_disable_unlock_all: scx_cgroup_unlock(); @@ -5210,7 +5241,41 @@ err_disable: */ scx_error(sch, "scx_enable() failed (%d)", ret); kthread_flush_work(&sch->disable_work); - return 0; + cmd->ret = 0; +} + +static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) +{ + static struct kthread_worker *helper; + static DEFINE_MUTEX(helper_mutex); + struct scx_enable_cmd cmd; + + if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN), + cpu_possible_mask)) { + pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n"); + return -EINVAL; + } + + if (!READ_ONCE(helper)) { + mutex_lock(&helper_mutex); + if (!helper) { + helper = kthread_run_worker(0, "scx_enable_helper"); + if (IS_ERR_OR_NULL(helper)) { + helper = NULL; + mutex_unlock(&helper_mutex); + return -ENOMEM; + } + sched_set_fifo(helper->task); + } + mutex_unlock(&helper_mutex); + } + + kthread_init_work(&cmd.work, scx_enable_workfn); + cmd.ops = ops; + + kthread_queue_work(READ_ONCE(helper), &cmd.work); + kthread_flush_work(&cmd.work); + return cmd.ret; } diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c index c5a3b0bac7c3..ba298ac3ce6c 100644 --- a/kernel/sched/ext_idle.c +++ b/kernel/sched/ext_idle.c @@ -663,9 +663,8 @@ void scx_idle_init_masks(void) BUG_ON(!alloc_cpumask_var(&scx_idle_global_masks.cpu, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&scx_idle_global_masks.smt, GFP_KERNEL)); - /* Allocate per-node idle cpumasks */ - scx_idle_node_masks = kzalloc_objs(*scx_idle_node_masks, - num_possible_nodes()); + /* Allocate per-node idle cpumasks (use nr_node_ids for non-contiguous NUMA nodes) */ + scx_idle_node_masks = kzalloc_objs(*scx_idle_node_masks, nr_node_ids); BUG_ON(!scx_idle_node_masks); for_each_node(i) { diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h index 386c677e4c9a..11ebb744d893 100644 --- a/kernel/sched/ext_internal.h +++ b/kernel/sched/ext_internal.h @@ -74,7 +74,7 @@ enum scx_exit_flags { * info communication. The following flag indicates whether ops.init() * finished successfully. */ - SCX_EFLAG_INITIALIZED, + SCX_EFLAG_INITIALIZED = 1LLU << 0, }; /* diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 3b725d39c06e..ef152d401fe2 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -123,8 +123,6 @@ int housekeeping_update(struct cpumask *isol_mask) struct cpumask *trial, *old = NULL; int err; - lockdep_assert_cpus_held(); - trial = kmalloc(cpumask_size(), GFP_KERNEL); if (!trial) return -ENOMEM; @@ -136,7 +134,7 @@ int housekeeping_update(struct cpumask *isol_mask) } if (!housekeeping.flags) - static_branch_enable_cpuslocked(&housekeeping_overridden); + static_branch_enable(&housekeeping_overridden); if (housekeeping.flags & HK_FLAG_DOMAIN) old = housekeeping_cpumask_dereference(HK_TYPE_DOMAIN); diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index 6f10db3646e7..cadb0e9fe19b 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -284,6 +284,35 @@ static bool check_same_owner(struct task_struct *p) uid_eq(cred->euid, pcred->uid)); } +#ifdef CONFIG_RT_MUTEXES +static inline void __setscheduler_dl_pi(int newprio, int policy, + struct task_struct *p, + struct sched_change_ctx *scope) +{ + /* + * In case a DEADLINE task (either proper or boosted) gets + * setscheduled to a lower priority class, check if it neeeds to + * inherit parameters from a potential pi_task. In that case make + * sure replenishment happens with the next enqueue. + */ + + if (dl_prio(newprio) && !dl_policy(policy)) { + struct task_struct *pi_task = rt_mutex_get_top_task(p); + + if (pi_task) { + p->dl.pi_se = pi_task->dl.pi_se; + scope->flags |= ENQUEUE_REPLENISH; + } + } +} +#else /* !CONFIG_RT_MUTEXES */ +static inline void __setscheduler_dl_pi(int newprio, int policy, + struct task_struct *p, + struct sched_change_ctx *scope) +{ +} +#endif /* !CONFIG_RT_MUTEXES */ + #ifdef CONFIG_UCLAMP_TASK static int uclamp_validate(struct task_struct *p, @@ -655,6 +684,7 @@ change: __setscheduler_params(p, attr); p->sched_class = next_class; p->prio = newprio; + __setscheduler_dl_pi(newprio, policy, p, scope); } __setscheduler_uclamp(p, attr); diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index a5c7d15fce72..9daf8c5d9687 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -256,8 +256,6 @@ EXPORT_SYMBOL(proc_dointvec_jiffies); int proc_dointvec_userhz_jiffies(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { - if (SYSCTL_USER_TO_KERN(dir) && USER_HZ < HZ) - return -EINVAL; return proc_dointvec_conv(table, dir, buffer, lenp, ppos, do_proc_int_conv_userhz_jiffies); } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 91fa2003351c..c07e562ee4c1 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -2653,7 +2653,8 @@ static int timekeeping_validate_timex(const struct __kernel_timex *txc, bool aux if (aux_clock) { /* Auxiliary clocks are similar to TAI and do not have leap seconds */ - if (txc->status & (STA_INS | STA_DEL)) + if (txc->modes & ADJ_STATUS && + txc->status & (STA_INS | STA_DEL)) return -EINVAL; /* No TAI offset setting */ @@ -2661,7 +2662,8 @@ static int timekeeping_validate_timex(const struct __kernel_timex *txc, bool aux return -EINVAL; /* No PPS support either */ - if (txc->status & (STA_PPSFREQ | STA_PPSTIME)) + if (txc->modes & ADJ_STATUS && + txc->status & (STA_PPSFREQ | STA_PPSTIME)) return -EINVAL; } diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index c1ed0d5e8de6..155eeaea4113 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -1559,8 +1559,6 @@ int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask) cpumask_var_t cpumask __free(free_cpumask_var) = CPUMASK_VAR_NULL; int cpu; - lockdep_assert_cpus_held(); - if (!works) return -ENOMEM; if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) @@ -1570,6 +1568,7 @@ int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask) * First set previously isolated CPUs as available (unisolate). * This cpumask contains only CPUs that switched to available now. */ + guard(cpus_read_lock)(); cpumask_andnot(cpumask, cpu_online_mask, exclude_cpumask); cpumask_andnot(cpumask, cpumask, tmigr_available_cpumask); @@ -1626,7 +1625,6 @@ static int __init tmigr_init_isolation(void) cpumask_andnot(cpumask, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); /* Protect against RCU torture hotplug testing */ - guard(cpus_read_lock)(); return tmigr_isolated_exclude_cpumask(cpumask); } late_initcall(tmigr_init_isolation); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 30259dcaa838..8cd2520b4c99 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -383,8 +383,6 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, cpu = raw_smp_processor_id(); if (blk_tracer) { - tracing_record_cmdline(current); - buffer = blk_tr->array_buffer.buffer; trace_ctx = tracing_gen_ctx_flags(0); switch (bt->version) { @@ -419,6 +417,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, if (!event) return; + tracing_record_cmdline(current); switch (bt->version) { case 1: record_blktrace_event(ring_buffer_event_data(event), diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 827fb9a0bf0d..8df69e702706 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -6404,6 +6404,7 @@ int update_ftrace_direct_add(struct ftrace_ops *ops, struct ftrace_hash *hash) new_filter_hash = old_filter_hash; } } else { + guard(mutex)(&ftrace_lock); err = ftrace_update_ops(ops, new_filter_hash, EMPTY_HASH); /* * new_filter_hash is dup-ed, so we need to release it anyway, @@ -6530,6 +6531,7 @@ int update_ftrace_direct_del(struct ftrace_ops *ops, struct ftrace_hash *hash) ops->func_hash->filter_hash = NULL; } } else { + guard(mutex)(&ftrace_lock); err = ftrace_update_ops(ops, new_filter_hash, EMPTY_HASH); /* * new_filter_hash is dup-ed, so we need to release it anyway, @@ -8611,6 +8613,7 @@ ftrace_pid_follow_sched_process_fork(void *data, struct trace_pid_list *pid_list; struct trace_array *tr = data; + guard(preempt)(); pid_list = rcu_dereference_sched(tr->function_pids); trace_filter_add_remove_task(pid_list, self, task); @@ -8624,6 +8627,7 @@ ftrace_pid_follow_sched_process_exit(void *data, struct task_struct *task) struct trace_pid_list *pid_list; struct trace_array *tr = data; + guard(preempt)(); pid_list = rcu_dereference_sched(tr->function_pids); trace_filter_add_remove_task(pid_list, NULL, task); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f16f053ef77d..17d0ea0cc3e6 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7310,6 +7310,27 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu, return err; } +/* + * This is called when a VMA is duplicated (e.g., on fork()) to increment + * the user_mapped counter without remapping pages. + */ +void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + + if (WARN_ON(!cpumask_test_cpu(cpu, buffer->cpumask))) + return; + + cpu_buffer = buffer->buffers[cpu]; + + guard(mutex)(&cpu_buffer->mapping_lock); + + if (cpu_buffer->user_mapped) + __rb_inc_dec_mapped(cpu_buffer, true); + else + WARN(1, "Unexpected buffer stat, it should be mapped"); +} + int ring_buffer_unmap(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 23de3719f495..ebd996f8710e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8213,6 +8213,18 @@ static inline int get_snapshot_map(struct trace_array *tr) { return 0; } static inline void put_snapshot_map(struct trace_array *tr) { } #endif +/* + * This is called when a VMA is duplicated (e.g., on fork()) to increment + * the user_mapped counter without remapping pages. + */ +static void tracing_buffers_mmap_open(struct vm_area_struct *vma) +{ + struct ftrace_buffer_info *info = vma->vm_file->private_data; + struct trace_iterator *iter = &info->iter; + + ring_buffer_map_dup(iter->array_buffer->buffer, iter->cpu_file); +} + static void tracing_buffers_mmap_close(struct vm_area_struct *vma) { struct ftrace_buffer_info *info = vma->vm_file->private_data; @@ -8232,6 +8244,7 @@ static int tracing_buffers_may_split(struct vm_area_struct *vma, unsigned long a } static const struct vm_operations_struct tracing_buffers_vmops = { + .open = tracing_buffers_mmap_open, .close = tracing_buffers_mmap_close, .may_split = tracing_buffers_may_split, }; @@ -9337,7 +9350,7 @@ static void setup_trace_scratch(struct trace_array *tr, } static int -allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, int size) +allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, unsigned long size) { enum ring_buffer_flags rb_flags; struct trace_scratch *tscratch; @@ -9392,7 +9405,7 @@ static void free_trace_buffer(struct array_buffer *buf) } } -static int allocate_trace_buffers(struct trace_array *tr, int size) +static int allocate_trace_buffers(struct trace_array *tr, unsigned long size) { int ret; @@ -10756,7 +10769,7 @@ __init static void enable_instances(void) __init static int tracer_alloc_buffers(void) { - int ring_buf_size; + unsigned long ring_buf_size; int ret = -ENOMEM; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 9928da636c9d..249d1cba72c0 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1039,6 +1039,7 @@ event_filter_pid_sched_process_exit(void *data, struct task_struct *task) struct trace_pid_list *pid_list; struct trace_array *tr = data; + guard(preempt)(); pid_list = rcu_dereference_raw(tr->filtered_pids); trace_filter_add_remove_task(pid_list, NULL, task); @@ -1054,6 +1055,7 @@ event_filter_pid_sched_process_fork(void *data, struct trace_pid_list *pid_list; struct trace_array *tr = data; + guard(preempt)(); pid_list = rcu_dereference_sched(tr->filtered_pids); trace_filter_add_remove_task(pid_list, self, task); @@ -4491,7 +4493,11 @@ static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata; static __init int setup_trace_event(char *str) { - strscpy(bootup_event_buf, str, COMMAND_LINE_SIZE); + if (bootup_event_buf[0] != '\0') + strlcat(bootup_event_buf, ",", COMMAND_LINE_SIZE); + + strlcat(bootup_event_buf, str, COMMAND_LINE_SIZE); + trace_set_ring_buffer_expanded(NULL); disable_tracing_selftest("running event tracing"); @@ -4668,26 +4674,22 @@ static __init int event_trace_memsetup(void) return 0; } -__init void -early_enable_events(struct trace_array *tr, char *buf, bool disable_first) +/* + * Helper function to enable or disable a comma-separated list of events + * from the bootup buffer. + */ +static __init void __early_set_events(struct trace_array *tr, char *buf, bool enable) { char *token; - int ret; - - while (true) { - token = strsep(&buf, ","); - - if (!token) - break; + while ((token = strsep(&buf, ","))) { if (*token) { - /* Restarting syscalls requires that we stop them first */ - if (disable_first) + if (enable) { + if (ftrace_set_clr_event(tr, token, 1)) + pr_warn("Failed to enable trace event: %s\n", token); + } else { ftrace_set_clr_event(tr, token, 0); - - ret = ftrace_set_clr_event(tr, token, 1); - if (ret) - pr_warn("Failed to enable trace event: %s\n", token); + } } /* Put back the comma to allow this to be called again */ @@ -4696,6 +4698,32 @@ early_enable_events(struct trace_array *tr, char *buf, bool disable_first) } } +/** + * early_enable_events - enable events from the bootup buffer + * @tr: The trace array to enable the events in + * @buf: The buffer containing the comma separated list of events + * @disable_first: If true, disable all events in @buf before enabling them + * + * This function enables events from the bootup buffer. If @disable_first + * is true, it will first disable all events in the buffer before enabling + * them. + * + * For syscall events, which rely on a global refcount to register the + * SYSCALL_WORK_SYSCALL_TRACEPOINT flag (especially for pid 1), we must + * ensure the refcount hits zero before re-enabling them. A simple + * "disable then enable" per-event is not enough if multiple syscalls are + * used, as the refcount will stay above zero. Thus, we need a two-phase + * approach: disable all, then enable all. + */ +__init void +early_enable_events(struct trace_array *tr, char *buf, bool disable_first) +{ + if (disable_first) + __early_set_events(tr, buf, false); + + __early_set_events(tr, buf, true); +} + static __init int event_trace_enable(void) { struct trace_array *tr = top_trace_array(); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index fecbd679d432..d5230b759a2d 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -50,6 +50,9 @@ static int trigger_kthread_fn(void *ignore) void trigger_data_free(struct event_trigger_data *data) { + if (!data) + return; + if (data->cmd_ops->set_filter) data->cmd_ops->set_filter(NULL, data, NULL); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 3d8239fee004..0d2d3a2ea7dd 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -400,14 +400,19 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops, struct ftrace_regs *fregs) { + unsigned long *task_var = fgraph_get_task_var(gops); struct fgraph_times *ftimes; struct trace_array *tr; + unsigned int trace_ctx; + u64 calltime, rettime; int size; + rettime = trace_clock_local(); + ftrace_graph_addr_finish(gops, trace); - if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) { - trace_recursion_clear(TRACE_GRAPH_NOTRACE_BIT); + if (*task_var & TRACE_GRAPH_NOTRACE) { + *task_var &= ~TRACE_GRAPH_NOTRACE; return; } @@ -418,11 +423,13 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, tr = gops->private; handle_nosleeptime(tr, trace, ftimes, size); - if (tracing_thresh && - (trace_clock_local() - ftimes->calltime < tracing_thresh)) + calltime = ftimes->calltime; + + if (tracing_thresh && (rettime - calltime < tracing_thresh)) return; - else - trace_graph_return(trace, gops, fregs); + + trace_ctx = tracing_gen_ctx(); + __trace_graph_return(tr, trace, trace_ctx, calltime, rettime); } static struct fgraph_ops funcgraph_ops = { diff --git a/lib/crypto/.kunitconfig b/lib/crypto/.kunitconfig new file mode 100644 index 000000000000..6b2ce28ae509 --- /dev/null +++ b/lib/crypto/.kunitconfig @@ -0,0 +1,34 @@ +CONFIG_KUNIT=y + +# These kconfig options select all the CONFIG_CRYPTO_LIB_* symbols that have a +# corresponding KUnit test. Those symbols cannot be directly enabled here, +# since they are hidden symbols. +CONFIG_CRYPTO=y +CONFIG_CRYPTO_ADIANTUM=y +CONFIG_CRYPTO_BLAKE2B=y +CONFIG_CRYPTO_CHACHA20POLY1305=y +CONFIG_CRYPTO_HCTR2=y +CONFIG_CRYPTO_MD5=y +CONFIG_CRYPTO_MLDSA=y +CONFIG_CRYPTO_SHA1=y +CONFIG_CRYPTO_SHA256=y +CONFIG_CRYPTO_SHA512=y +CONFIG_CRYPTO_SHA3=y +CONFIG_INET=y +CONFIG_IPV6=y +CONFIG_NET=y +CONFIG_NETDEVICES=y +CONFIG_WIREGUARD=y + +CONFIG_CRYPTO_LIB_BLAKE2B_KUNIT_TEST=y +CONFIG_CRYPTO_LIB_BLAKE2S_KUNIT_TEST=y +CONFIG_CRYPTO_LIB_CURVE25519_KUNIT_TEST=y +CONFIG_CRYPTO_LIB_MD5_KUNIT_TEST=y +CONFIG_CRYPTO_LIB_MLDSA_KUNIT_TEST=y +CONFIG_CRYPTO_LIB_NH_KUNIT_TEST=y +CONFIG_CRYPTO_LIB_POLY1305_KUNIT_TEST=y +CONFIG_CRYPTO_LIB_POLYVAL_KUNIT_TEST=y +CONFIG_CRYPTO_LIB_SHA1_KUNIT_TEST=y +CONFIG_CRYPTO_LIB_SHA256_KUNIT_TEST=y +CONFIG_CRYPTO_LIB_SHA512_KUNIT_TEST=y +CONFIG_CRYPTO_LIB_SHA3_KUNIT_TEST=y diff --git a/lib/crypto/tests/Kconfig b/lib/crypto/tests/Kconfig index 4970463ea0aa..0de289b429a9 100644 --- a/lib/crypto/tests/Kconfig +++ b/lib/crypto/tests/Kconfig @@ -2,10 +2,9 @@ config CRYPTO_LIB_BLAKE2B_KUNIT_TEST tristate "KUnit tests for BLAKE2b" if !KUNIT_ALL_TESTS - depends on KUNIT + depends on KUNIT && CRYPTO_LIB_BLAKE2B default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE - select CRYPTO_LIB_BLAKE2B help KUnit tests for the BLAKE2b cryptographic hash function. @@ -14,71 +13,64 @@ config CRYPTO_LIB_BLAKE2S_KUNIT_TEST depends on KUNIT default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE - # No need to select CRYPTO_LIB_BLAKE2S here, as that option doesn't + # No need to depend on CRYPTO_LIB_BLAKE2S here, as that option doesn't # exist; the BLAKE2s code is always built-in for the /dev/random driver. help KUnit tests for the BLAKE2s cryptographic hash function. config CRYPTO_LIB_CURVE25519_KUNIT_TEST tristate "KUnit tests for Curve25519" if !KUNIT_ALL_TESTS - depends on KUNIT + depends on KUNIT && CRYPTO_LIB_CURVE25519 default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE - select CRYPTO_LIB_CURVE25519 help KUnit tests for the Curve25519 Diffie-Hellman function. config CRYPTO_LIB_MD5_KUNIT_TEST tristate "KUnit tests for MD5" if !KUNIT_ALL_TESTS - depends on KUNIT + depends on KUNIT && CRYPTO_LIB_MD5 default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE - select CRYPTO_LIB_MD5 help KUnit tests for the MD5 cryptographic hash function and its corresponding HMAC. config CRYPTO_LIB_MLDSA_KUNIT_TEST tristate "KUnit tests for ML-DSA" if !KUNIT_ALL_TESTS - depends on KUNIT + depends on KUNIT && CRYPTO_LIB_MLDSA default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE - select CRYPTO_LIB_MLDSA help KUnit tests for the ML-DSA digital signature algorithm. config CRYPTO_LIB_NH_KUNIT_TEST tristate "KUnit tests for NH" if !KUNIT_ALL_TESTS - depends on KUNIT + depends on KUNIT && CRYPTO_LIB_NH default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS - select CRYPTO_LIB_NH help KUnit tests for the NH almost-universal hash function. config CRYPTO_LIB_POLY1305_KUNIT_TEST tristate "KUnit tests for Poly1305" if !KUNIT_ALL_TESTS - depends on KUNIT + depends on KUNIT && CRYPTO_LIB_POLY1305 default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE - select CRYPTO_LIB_POLY1305 help KUnit tests for the Poly1305 library functions. config CRYPTO_LIB_POLYVAL_KUNIT_TEST tristate "KUnit tests for POLYVAL" if !KUNIT_ALL_TESTS - depends on KUNIT + depends on KUNIT && CRYPTO_LIB_POLYVAL default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE - select CRYPTO_LIB_POLYVAL help KUnit tests for the POLYVAL library functions. config CRYPTO_LIB_SHA1_KUNIT_TEST tristate "KUnit tests for SHA-1" if !KUNIT_ALL_TESTS - depends on KUNIT + depends on KUNIT && CRYPTO_LIB_SHA1 default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE - select CRYPTO_LIB_SHA1 help KUnit tests for the SHA-1 cryptographic hash function and its corresponding HMAC. @@ -87,10 +79,9 @@ config CRYPTO_LIB_SHA1_KUNIT_TEST # included, for consistency with the naming used elsewhere (e.g. CRYPTO_SHA256). config CRYPTO_LIB_SHA256_KUNIT_TEST tristate "KUnit tests for SHA-224 and SHA-256" if !KUNIT_ALL_TESTS - depends on KUNIT + depends on KUNIT && CRYPTO_LIB_SHA256 default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE - select CRYPTO_LIB_SHA256 help KUnit tests for the SHA-224 and SHA-256 cryptographic hash functions and their corresponding HMACs. @@ -99,20 +90,18 @@ config CRYPTO_LIB_SHA256_KUNIT_TEST # included, for consistency with the naming used elsewhere (e.g. CRYPTO_SHA512). config CRYPTO_LIB_SHA512_KUNIT_TEST tristate "KUnit tests for SHA-384 and SHA-512" if !KUNIT_ALL_TESTS - depends on KUNIT + depends on KUNIT && CRYPTO_LIB_SHA512 default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE - select CRYPTO_LIB_SHA512 help KUnit tests for the SHA-384 and SHA-512 cryptographic hash functions and their corresponding HMACs. config CRYPTO_LIB_SHA3_KUNIT_TEST tristate "KUnit tests for SHA-3" if !KUNIT_ALL_TESTS - depends on KUNIT + depends on KUNIT && CRYPTO_LIB_SHA3 default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE - select CRYPTO_LIB_SHA3 help KUnit tests for the SHA3 cryptographic hash and XOF functions, including SHA3-224, SHA3-256, SHA3-384, SHA3-512, SHAKE128 and diff --git a/lib/kunit/test.c b/lib/kunit/test.c index 62eb529824c6..41e1c89799b6 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -94,7 +94,7 @@ struct kunit_result_stats { unsigned long total; }; -static bool kunit_should_print_stats(struct kunit_result_stats stats) +static bool kunit_should_print_stats(struct kunit_result_stats *stats) { if (kunit_stats_enabled == 0) return false; @@ -102,11 +102,11 @@ static bool kunit_should_print_stats(struct kunit_result_stats stats) if (kunit_stats_enabled == 2) return true; - return (stats.total > 1); + return (stats->total > 1); } static void kunit_print_test_stats(struct kunit *test, - struct kunit_result_stats stats) + struct kunit_result_stats *stats) { if (!kunit_should_print_stats(stats)) return; @@ -115,10 +115,10 @@ static void kunit_print_test_stats(struct kunit *test, KUNIT_SUBTEST_INDENT "# %s: pass:%lu fail:%lu skip:%lu total:%lu", test->name, - stats.passed, - stats.failed, - stats.skipped, - stats.total); + stats->passed, + stats->failed, + stats->skipped, + stats->total); } /* Append formatted message to log. */ @@ -600,26 +600,26 @@ static void kunit_run_case_catch_errors(struct kunit_suite *suite, } static void kunit_print_suite_stats(struct kunit_suite *suite, - struct kunit_result_stats suite_stats, - struct kunit_result_stats param_stats) + struct kunit_result_stats *suite_stats, + struct kunit_result_stats *param_stats) { if (kunit_should_print_stats(suite_stats)) { kunit_log(KERN_INFO, suite, "# %s: pass:%lu fail:%lu skip:%lu total:%lu", suite->name, - suite_stats.passed, - suite_stats.failed, - suite_stats.skipped, - suite_stats.total); + suite_stats->passed, + suite_stats->failed, + suite_stats->skipped, + suite_stats->total); } if (kunit_should_print_stats(param_stats)) { kunit_log(KERN_INFO, suite, "# Totals: pass:%lu fail:%lu skip:%lu total:%lu", - param_stats.passed, - param_stats.failed, - param_stats.skipped, - param_stats.total); + param_stats->passed, + param_stats->failed, + param_stats->skipped, + param_stats->total); } } @@ -681,13 +681,116 @@ static void kunit_init_parent_param_test(struct kunit_case *test_case, struct ku } } -int kunit_run_tests(struct kunit_suite *suite) +static noinline_for_stack void +kunit_run_param_test(struct kunit_suite *suite, struct kunit_case *test_case, + struct kunit *test, + struct kunit_result_stats *suite_stats, + struct kunit_result_stats *total_stats, + struct kunit_result_stats *param_stats) { char param_desc[KUNIT_PARAM_DESC_SIZE]; + const void *curr_param; + + kunit_init_parent_param_test(test_case, test); + if (test_case->status == KUNIT_FAILURE) { + kunit_update_stats(param_stats, test->status); + return; + } + /* Get initial param. */ + param_desc[0] = '\0'; + /* TODO: Make generate_params try-catch */ + curr_param = test_case->generate_params(test, NULL, param_desc); + test_case->status = KUNIT_SKIPPED; + kunit_log(KERN_INFO, test, KUNIT_SUBTEST_INDENT KUNIT_SUBTEST_INDENT + "KTAP version 1\n"); + kunit_log(KERN_INFO, test, KUNIT_SUBTEST_INDENT KUNIT_SUBTEST_INDENT + "# Subtest: %s", test_case->name); + if (test->params_array.params && + test_case->generate_params == kunit_array_gen_params) { + kunit_log(KERN_INFO, test, KUNIT_SUBTEST_INDENT + KUNIT_SUBTEST_INDENT "1..%zd\n", + test->params_array.num_params); + } + + while (curr_param) { + struct kunit param_test = { + .param_value = curr_param, + .param_index = ++test->param_index, + .parent = test, + }; + kunit_init_test(¶m_test, test_case->name, NULL); + param_test.log = test_case->log; + kunit_run_case_catch_errors(suite, test_case, ¶m_test); + + if (param_desc[0] == '\0') { + snprintf(param_desc, sizeof(param_desc), + "param-%d", param_test.param_index); + } + + kunit_print_ok_not_ok(¶m_test, KUNIT_LEVEL_CASE_PARAM, + param_test.status, + param_test.param_index, + param_desc, + param_test.status_comment); + + kunit_update_stats(param_stats, param_test.status); + + /* Get next param. */ + param_desc[0] = '\0'; + curr_param = test_case->generate_params(test, curr_param, + param_desc); + } + /* + * TODO: Put into a try catch. Since we don't need suite->exit + * for it we can't reuse kunit_try_run_cleanup for this yet. + */ + if (test_case->param_exit) + test_case->param_exit(test); + /* TODO: Put this kunit_cleanup into a try-catch. */ + kunit_cleanup(test); +} + +static noinline_for_stack void +kunit_run_one_test(struct kunit_suite *suite, struct kunit_case *test_case, + struct kunit_result_stats *suite_stats, + struct kunit_result_stats *total_stats) +{ + struct kunit test = { .param_value = NULL, .param_index = 0 }; + struct kunit_result_stats param_stats = { 0 }; + + kunit_init_test(&test, test_case->name, test_case->log); + if (test_case->status == KUNIT_SKIPPED) { + /* Test marked as skip */ + test.status = KUNIT_SKIPPED; + kunit_update_stats(¶m_stats, test.status); + } else if (!test_case->generate_params) { + /* Non-parameterised test. */ + test_case->status = KUNIT_SKIPPED; + kunit_run_case_catch_errors(suite, test_case, &test); + kunit_update_stats(¶m_stats, test.status); + } else { + kunit_run_param_test(suite, test_case, &test, suite_stats, + total_stats, ¶m_stats); + } + kunit_print_attr((void *)test_case, true, KUNIT_LEVEL_CASE); + + kunit_print_test_stats(&test, ¶m_stats); + + kunit_print_ok_not_ok(&test, KUNIT_LEVEL_CASE, test_case->status, + kunit_test_case_num(suite, test_case), + test_case->name, + test.status_comment); + + kunit_update_stats(suite_stats, test_case->status); + kunit_accumulate_stats(total_stats, param_stats); +} + + +int kunit_run_tests(struct kunit_suite *suite) +{ struct kunit_case *test_case; struct kunit_result_stats suite_stats = { 0 }; struct kunit_result_stats total_stats = { 0 }; - const void *curr_param; /* Taint the kernel so we know we've run tests. */ add_taint(TAINT_TEST, LOCKDEP_STILL_OK); @@ -703,97 +806,13 @@ int kunit_run_tests(struct kunit_suite *suite) kunit_print_suite_start(suite); - kunit_suite_for_each_test_case(suite, test_case) { - struct kunit test = { .param_value = NULL, .param_index = 0 }; - struct kunit_result_stats param_stats = { 0 }; - - kunit_init_test(&test, test_case->name, test_case->log); - if (test_case->status == KUNIT_SKIPPED) { - /* Test marked as skip */ - test.status = KUNIT_SKIPPED; - kunit_update_stats(¶m_stats, test.status); - } else if (!test_case->generate_params) { - /* Non-parameterised test. */ - test_case->status = KUNIT_SKIPPED; - kunit_run_case_catch_errors(suite, test_case, &test); - kunit_update_stats(¶m_stats, test.status); - } else { - kunit_init_parent_param_test(test_case, &test); - if (test_case->status == KUNIT_FAILURE) { - kunit_update_stats(¶m_stats, test.status); - goto test_case_end; - } - /* Get initial param. */ - param_desc[0] = '\0'; - /* TODO: Make generate_params try-catch */ - curr_param = test_case->generate_params(&test, NULL, param_desc); - test_case->status = KUNIT_SKIPPED; - kunit_log(KERN_INFO, &test, KUNIT_SUBTEST_INDENT KUNIT_SUBTEST_INDENT - "KTAP version 1\n"); - kunit_log(KERN_INFO, &test, KUNIT_SUBTEST_INDENT KUNIT_SUBTEST_INDENT - "# Subtest: %s", test_case->name); - if (test.params_array.params && - test_case->generate_params == kunit_array_gen_params) { - kunit_log(KERN_INFO, &test, KUNIT_SUBTEST_INDENT - KUNIT_SUBTEST_INDENT "1..%zd\n", - test.params_array.num_params); - } - - while (curr_param) { - struct kunit param_test = { - .param_value = curr_param, - .param_index = ++test.param_index, - .parent = &test, - }; - kunit_init_test(¶m_test, test_case->name, NULL); - param_test.log = test_case->log; - kunit_run_case_catch_errors(suite, test_case, ¶m_test); - - if (param_desc[0] == '\0') { - snprintf(param_desc, sizeof(param_desc), - "param-%d", param_test.param_index); - } - - kunit_print_ok_not_ok(¶m_test, KUNIT_LEVEL_CASE_PARAM, - param_test.status, - param_test.param_index, - param_desc, - param_test.status_comment); - - kunit_update_stats(¶m_stats, param_test.status); - - /* Get next param. */ - param_desc[0] = '\0'; - curr_param = test_case->generate_params(&test, curr_param, - param_desc); - } - /* - * TODO: Put into a try catch. Since we don't need suite->exit - * for it we can't reuse kunit_try_run_cleanup for this yet. - */ - if (test_case->param_exit) - test_case->param_exit(&test); - /* TODO: Put this kunit_cleanup into a try-catch. */ - kunit_cleanup(&test); - } -test_case_end: - kunit_print_attr((void *)test_case, true, KUNIT_LEVEL_CASE); - - kunit_print_test_stats(&test, param_stats); - - kunit_print_ok_not_ok(&test, KUNIT_LEVEL_CASE, test_case->status, - kunit_test_case_num(suite, test_case), - test_case->name, - test.status_comment); - - kunit_update_stats(&suite_stats, test_case->status); - kunit_accumulate_stats(&total_stats, param_stats); - } + kunit_suite_for_each_test_case(suite, test_case) + kunit_run_one_test(suite, test_case, &suite_stats, &total_stats); if (suite->suite_exit) suite->suite_exit(suite); - kunit_print_suite_stats(suite, suite_stats, total_stats); + kunit_print_suite_stats(suite, &suite_stats, &total_stats); suite_end: kunit_print_suite_end(suite); diff --git a/mm/filemap.c b/mm/filemap.c index 6cd7974d4ada..406cef06b684 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1379,14 +1379,16 @@ repeat: #ifdef CONFIG_MIGRATION /** - * migration_entry_wait_on_locked - Wait for a migration entry to be removed - * @entry: migration swap entry. + * softleaf_entry_wait_on_locked - Wait for a migration entry or + * device_private entry to be removed. + * @entry: migration or device_private swap entry. * @ptl: already locked ptl. This function will drop the lock. * - * Wait for a migration entry referencing the given page to be removed. This is + * Wait for a migration entry referencing the given page, or device_private + * entry referencing a dvice_private page to be unlocked. This is * equivalent to folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE) except * this can be called without taking a reference on the page. Instead this - * should be called while holding the ptl for the migration entry referencing + * should be called while holding the ptl for @entry referencing * the page. * * Returns after unlocking the ptl. @@ -1394,7 +1396,7 @@ repeat: * This follows the same logic as folio_wait_bit_common() so see the comments * there. */ -void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) +void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) __releases(ptl) { struct wait_page_queue wait_page; @@ -1428,6 +1430,9 @@ void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) * If a migration entry exists for the page the migration path must hold * a valid reference to the page, and it must take the ptl to remove the * migration entry. So the page is valid until the ptl is dropped. + * Similarly any path attempting to drop the last reference to a + * device-private page needs to grab the ptl to remove the device-private + * entry. */ spin_unlock(ptl); diff --git a/mm/madvise.c b/mm/madvise.c index c0370d9b4e23..dbb69400786d 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -1389,7 +1389,7 @@ static int madvise_vma_behavior(struct madvise_behavior *madv_behavior) new_flags |= VM_DONTCOPY; break; case MADV_DOFORK: - if (new_flags & VM_IO) + if (new_flags & VM_SPECIAL) return -EINVAL; new_flags &= ~VM_DONTCOPY; break; diff --git a/mm/memory.c b/mm/memory.c index 07778814b4a8..2f815a34d924 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4763,7 +4763,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) unlock_page(vmf->page); put_page(vmf->page); } else { - pte_unmap_unlock(vmf->pte, vmf->ptl); + pte_unmap(vmf->pte); + softleaf_entry_wait_on_locked(entry, vmf->ptl); } } else if (softleaf_is_hwpoison(entry)) { ret = VM_FAULT_HWPOISON; diff --git a/mm/migrate.c b/mm/migrate.c index 1bf2cf8c44dd..2c3d489ecf51 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -500,7 +500,7 @@ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, if (!softleaf_is_migration(entry)) goto out; - migration_entry_wait_on_locked(entry, ptl); + softleaf_entry_wait_on_locked(entry, ptl); return; out: spin_unlock(ptl); @@ -532,10 +532,10 @@ void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, p * If migration entry existed, safe to release vma lock * here because the pgtable page won't be freed without the * pgtable lock released. See comment right above pgtable - * lock release in migration_entry_wait_on_locked(). + * lock release in softleaf_entry_wait_on_locked(). */ hugetlb_vma_unlock_read(vma); - migration_entry_wait_on_locked(entry, ptl); + softleaf_entry_wait_on_locked(entry, ptl); return; } @@ -553,7 +553,7 @@ void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd) ptl = pmd_lock(mm, pmd); if (!pmd_is_migration_entry(*pmd)) goto unlock; - migration_entry_wait_on_locked(softleaf_from_pmd(*pmd), ptl); + softleaf_entry_wait_on_locked(softleaf_from_pmd(*pmd), ptl); return; unlock: spin_unlock(ptl); diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 0a8b31939640..8079676c8f1f 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -176,7 +176,7 @@ static int migrate_vma_collect_huge_pmd(pmd_t *pmdp, unsigned long start, } if (softleaf_is_migration(entry)) { - migration_entry_wait_on_locked(entry, ptl); + softleaf_entry_wait_on_locked(entry, ptl); spin_unlock(ptl); return -EAGAIN; } diff --git a/mm/slab.h b/mm/slab.h index f6ef862b60ef..e9ab292acd22 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -59,7 +59,7 @@ struct freelist_counters { * to save memory. In case ->stride field is not available, * such optimizations are disabled. */ - unsigned short stride; + unsigned int stride; #endif }; }; @@ -559,20 +559,20 @@ static inline void put_slab_obj_exts(unsigned long obj_exts) } #ifdef CONFIG_64BIT -static inline void slab_set_stride(struct slab *slab, unsigned short stride) +static inline void slab_set_stride(struct slab *slab, unsigned int stride) { slab->stride = stride; } -static inline unsigned short slab_get_stride(struct slab *slab) +static inline unsigned int slab_get_stride(struct slab *slab) { return slab->stride; } #else -static inline void slab_set_stride(struct slab *slab, unsigned short stride) +static inline void slab_set_stride(struct slab *slab, unsigned int stride) { VM_WARN_ON_ONCE(stride != sizeof(struct slabobj_ext)); } -static inline unsigned short slab_get_stride(struct slab *slab) +static inline unsigned int slab_get_stride(struct slab *slab) { return sizeof(struct slabobj_ext); } diff --git a/mm/slub.c b/mm/slub.c index 0c906fefc31b..20cb4f3b636d 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2858,19 +2858,19 @@ static void __kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p); * object pointers are moved to a on-stack array under the lock. To bound the * stack usage, limit each batch to PCS_BATCH_MAX. * - * returns true if at least partially flushed + * Must be called with s->cpu_sheaves->lock locked, returns with the lock + * unlocked. + * + * Returns how many objects are remaining to be flushed */ -static bool sheaf_flush_main(struct kmem_cache *s) +static unsigned int __sheaf_flush_main_batch(struct kmem_cache *s) { struct slub_percpu_sheaves *pcs; unsigned int batch, remaining; void *objects[PCS_BATCH_MAX]; struct slab_sheaf *sheaf; - bool ret = false; -next_batch: - if (!local_trylock(&s->cpu_sheaves->lock)) - return ret; + lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock)); pcs = this_cpu_ptr(s->cpu_sheaves); sheaf = pcs->main; @@ -2888,10 +2888,37 @@ next_batch: stat_add(s, SHEAF_FLUSH, batch); - ret = true; + return remaining; +} - if (remaining) - goto next_batch; +static void sheaf_flush_main(struct kmem_cache *s) +{ + unsigned int remaining; + + do { + local_lock(&s->cpu_sheaves->lock); + + remaining = __sheaf_flush_main_batch(s); + + } while (remaining); +} + +/* + * Returns true if the main sheaf was at least partially flushed. + */ +static bool sheaf_try_flush_main(struct kmem_cache *s) +{ + unsigned int remaining; + bool ret = false; + + do { + if (!local_trylock(&s->cpu_sheaves->lock)) + return ret; + + ret = true; + remaining = __sheaf_flush_main_batch(s); + + } while (remaining); return ret; } @@ -4540,7 +4567,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs, struct slab_sheaf *empty = NULL; struct slab_sheaf *full; struct node_barn *barn; - bool can_alloc; + bool allow_spin; lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock)); @@ -4561,8 +4588,9 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs, return NULL; } - full = barn_replace_empty_sheaf(barn, pcs->main, - gfpflags_allow_spinning(gfp)); + allow_spin = gfpflags_allow_spinning(gfp); + + full = barn_replace_empty_sheaf(barn, pcs->main, allow_spin); if (full) { stat(s, BARN_GET); @@ -4572,9 +4600,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs, stat(s, BARN_GET_FAIL); - can_alloc = gfpflags_allow_blocking(gfp); - - if (can_alloc) { + if (allow_spin) { if (pcs->spare) { empty = pcs->spare; pcs->spare = NULL; @@ -4584,8 +4610,9 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs, } local_unlock(&s->cpu_sheaves->lock); + pcs = NULL; - if (!can_alloc) + if (!allow_spin) return NULL; if (empty) { @@ -4605,11 +4632,8 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs, if (!full) return NULL; - /* - * we can reach here only when gfpflags_allow_blocking - * so this must not be an irq - */ - local_lock(&s->cpu_sheaves->lock); + if (!local_trylock(&s->cpu_sheaves->lock)) + goto barn_put; pcs = this_cpu_ptr(s->cpu_sheaves); /* @@ -4640,6 +4664,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs, return pcs; } +barn_put: barn_put_full_sheaf(barn, full); stat(s, BARN_PUT); @@ -5704,7 +5729,7 @@ alloc_empty: if (put_fail) stat(s, BARN_PUT_FAIL); - if (!sheaf_flush_main(s)) + if (!sheaf_try_flush_main(s)) return NULL; if (!local_trylock(&s->cpu_sheaves->lock)) diff --git a/net/atm/lec.c b/net/atm/lec.c index a107375c0629..fb93c6e1c329 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1260,24 +1260,28 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry) struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); struct net_device *dev = (struct net_device *)vcc->proto_data; - vcc->pop = vpriv->old_pop; - if (vpriv->xoff) - netif_wake_queue(dev); - kfree(vpriv); - vcc->user_back = NULL; - vcc->push = entry->old_push; - vcc_release_async(vcc, -EPIPE); + if (vpriv) { + vcc->pop = vpriv->old_pop; + if (vpriv->xoff) + netif_wake_queue(dev); + kfree(vpriv); + vcc->user_back = NULL; + vcc->push = entry->old_push; + vcc_release_async(vcc, -EPIPE); + } entry->vcc = NULL; } if (entry->recv_vcc) { struct atm_vcc *vcc = entry->recv_vcc; struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); - kfree(vpriv); - vcc->user_back = NULL; + if (vpriv) { + kfree(vpriv); + vcc->user_back = NULL; - entry->recv_vcc->push = entry->old_recv_push; - vcc_release_async(entry->recv_vcc, -EPIPE); + entry->recv_vcc->push = entry->old_recv_push; + vcc_release_async(entry->recv_vcc, -EPIPE); + } entry->recv_vcc = NULL; } } diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 2ce4e5bf9292..fdc2abe96d77 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -111,7 +111,15 @@ static bool batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh, /* unsupported WiFi driver version */ goto default_throughput; - real_netdev = batadv_get_real_netdev(hard_iface->net_dev); + /* only use rtnl_trylock because the elp worker will be cancelled while + * the rntl_lock is held. the cancel_delayed_work_sync() would otherwise + * wait forever when the elp work_item was started and it is then also + * trying to rtnl_lock + */ + if (!rtnl_trylock()) + return false; + real_netdev = __batadv_get_real_netdev(hard_iface->net_dev); + rtnl_unlock(); if (!real_netdev) goto default_throughput; diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 7b7640f3ffe2..d6732c34aeaf 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -204,7 +204,7 @@ static bool batadv_is_valid_iface(const struct net_device *net_dev) } /** - * batadv_get_real_netdevice() - check if the given netdev struct is a virtual + * __batadv_get_real_netdev() - check if the given netdev struct is a virtual * interface on top of another 'real' interface * @netdev: the device to check * @@ -214,7 +214,7 @@ static bool batadv_is_valid_iface(const struct net_device *net_dev) * Return: the 'real' net device or the original net device and NULL in case * of an error. */ -static struct net_device *batadv_get_real_netdevice(struct net_device *netdev) +struct net_device *__batadv_get_real_netdev(struct net_device *netdev) { struct batadv_hard_iface *hard_iface = NULL; struct net_device *real_netdev = NULL; @@ -267,7 +267,7 @@ struct net_device *batadv_get_real_netdev(struct net_device *net_device) struct net_device *real_netdev; rtnl_lock(); - real_netdev = batadv_get_real_netdevice(net_device); + real_netdev = __batadv_get_real_netdev(net_device); rtnl_unlock(); return real_netdev; @@ -336,7 +336,7 @@ static u32 batadv_wifi_flags_evaluate(struct net_device *net_device) if (batadv_is_cfg80211_netdev(net_device)) wifi_flags |= BATADV_HARDIF_WIFI_CFG80211_DIRECT; - real_netdev = batadv_get_real_netdevice(net_device); + real_netdev = __batadv_get_real_netdev(net_device); if (!real_netdev) return wifi_flags; diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 9db8a310961e..9ba8fb2bdceb 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -67,6 +67,7 @@ enum batadv_hard_if_bcast { extern struct notifier_block batadv_hard_if_notifier; +struct net_device *__batadv_get_real_netdev(struct net_device *net_device); struct net_device *batadv_get_real_netdev(struct net_device *net_device); bool batadv_is_cfg80211_hardif(struct batadv_hard_iface *hard_iface); bool batadv_is_wifi_hardif(struct batadv_hard_iface *hard_iface); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index ee01122f466f..f7502e62dd35 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -74,7 +74,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) eth_hdr(skb)->h_proto == htons(ETH_P_RARP)) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) { br_do_proxy_suppress_arp(skb, br, vid, NULL); - } else if (IS_ENABLED(CONFIG_IPV6) && + } else if (ipv6_mod_enabled() && skb->protocol == htons(ETH_P_IPV6) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) && pskb_may_pull(skb, sizeof(struct ipv6hdr) + diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 1405f1061a54..2cbae0f9ae1f 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -170,7 +170,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb (skb->protocol == htons(ETH_P_ARP) || skb->protocol == htons(ETH_P_RARP))) { br_do_proxy_suppress_arp(skb, br, vid, p); - } else if (IS_ENABLED(CONFIG_IPV6) && + } else if (ipv6_mod_enabled() && skb->protocol == htons(ETH_P_IPV6) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) && pskb_may_pull(skb, sizeof(struct ipv6hdr) + diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index b9b2981c4841..9b55d38ea9ed 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1344,6 +1344,16 @@ br_multicast_ctx_options_equal(const struct net_bridge_mcast *brmctx1, true; } +static inline bool +br_multicast_port_ctx_options_equal(const struct net_bridge_mcast_port *pmctx1, + const struct net_bridge_mcast_port *pmctx2) +{ + return br_multicast_ngroups_get(pmctx1) == + br_multicast_ngroups_get(pmctx2) && + br_multicast_ngroups_get_max(pmctx1) == + br_multicast_ngroups_get_max(pmctx2); +} + static inline bool br_multicast_ctx_matches_vlan_snooping(const struct net_bridge_mcast *brmctx) { diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c index 8fa89b04ee94..5514e1fc8d1f 100644 --- a/net/bridge/br_vlan_options.c +++ b/net/bridge/br_vlan_options.c @@ -43,9 +43,29 @@ bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr, u8 range_mc_rtr = br_vlan_multicast_router(range_end); u8 curr_mc_rtr = br_vlan_multicast_router(v_curr); - return v_curr->state == range_end->state && - __vlan_tun_can_enter_range(v_curr, range_end) && - curr_mc_rtr == range_mc_rtr; + if (v_curr->state != range_end->state) + return false; + + if (!__vlan_tun_can_enter_range(v_curr, range_end)) + return false; + + if (curr_mc_rtr != range_mc_rtr) + return false; + + /* Check user-visible priv_flags that affect output */ + if ((v_curr->priv_flags ^ range_end->priv_flags) & + (BR_VLFLAG_NEIGH_SUPPRESS_ENABLED | BR_VLFLAG_MCAST_ENABLED)) + return false; + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (!br_vlan_is_master(v_curr) && + !br_multicast_port_ctx_vlan_disabled(&v_curr->port_mcast_ctx) && + !br_multicast_port_ctx_options_equal(&v_curr->port_mcast_ctx, + &range_end->port_mcast_ctx)) + return false; +#endif + + return true; } bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v, diff --git a/net/can/bcm.c b/net/can/bcm.c index b7324e9c955b..fd9fa072881e 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1176,6 +1176,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (!op) return -ENOMEM; + spin_lock_init(&op->bcm_tx_lock); op->can_id = msg_head->can_id; op->nframes = msg_head->nframes; op->cfsiz = CFSIZ(msg_head->flags); diff --git a/net/core/dev.c b/net/core/dev.c index c1a9f7fdcffa..14a83f2035b9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3987,7 +3987,7 @@ static struct sk_buff *validate_xmit_unreadable_skb(struct sk_buff *skb, if (shinfo->nr_frags > 0) { niov = netmem_to_net_iov(skb_frag_netmem(&shinfo->frags[0])); if (net_is_devmem_iov(niov) && - net_devmem_iov_binding(niov)->dev != dev) + READ_ONCE(net_devmem_iov_binding(niov)->dev) != dev) goto out_free; } @@ -4818,10 +4818,7 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ - /* Other cpus might concurrently change txq->xmit_lock_owner - * to -1 or to their cpu id, but not to our id. - */ - if (READ_ONCE(txq->xmit_lock_owner) != cpu) { + if (!netif_tx_owned(txq, cpu)) { bool is_list = false; if (dev_xmit_recursion()) @@ -7794,11 +7791,12 @@ static int napi_thread_wait(struct napi_struct *napi) return -1; } -static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll) +static void napi_threaded_poll_loop(struct napi_struct *napi, + unsigned long *busy_poll_last_qs) { + unsigned long last_qs = busy_poll_last_qs ? *busy_poll_last_qs : jiffies; struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct softnet_data *sd; - unsigned long last_qs = jiffies; for (;;) { bool repoll = false; @@ -7827,12 +7825,12 @@ static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll) /* When busy poll is enabled, the old packets are not flushed in * napi_complete_done. So flush them here. */ - if (busy_poll) + if (busy_poll_last_qs) gro_flush_normal(&napi->gro, HZ >= 1000); local_bh_enable(); /* Call cond_resched here to avoid watchdog warnings. */ - if (repoll || busy_poll) { + if (repoll || busy_poll_last_qs) { rcu_softirq_qs_periodic(last_qs); cond_resched(); } @@ -7840,11 +7838,15 @@ static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll) if (!repoll) break; } + + if (busy_poll_last_qs) + *busy_poll_last_qs = last_qs; } static int napi_threaded_poll(void *data) { struct napi_struct *napi = data; + unsigned long last_qs = jiffies; bool want_busy_poll; bool in_busy_poll; unsigned long val; @@ -7862,7 +7864,7 @@ static int napi_threaded_poll(void *data) assign_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state, want_busy_poll); - napi_threaded_poll_loop(napi, want_busy_poll); + napi_threaded_poll_loop(napi, want_busy_poll ? &last_qs : NULL); } return 0; @@ -13175,7 +13177,7 @@ static void run_backlog_napi(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); - napi_threaded_poll_loop(&sd->backlog, false); + napi_threaded_poll_loop(&sd->backlog, NULL); } static void backlog_napi_setup(unsigned int cpu) diff --git a/net/core/devmem.c b/net/core/devmem.c index 8c9aad776bf4..69d79aee07ef 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -396,7 +396,8 @@ struct net_devmem_dmabuf_binding *net_devmem_get_binding(struct sock *sk, * net_device. */ dst_dev = dst_dev_rcu(dst); - if (unlikely(!dst_dev) || unlikely(dst_dev != binding->dev)) { + if (unlikely(!dst_dev) || + unlikely(dst_dev != READ_ONCE(binding->dev))) { err = -ENODEV; goto out_unlock; } @@ -513,7 +514,8 @@ static void mp_dmabuf_devmem_uninstall(void *mp_priv, xa_erase(&binding->bound_rxqs, xa_idx); if (xa_empty(&binding->bound_rxqs)) { mutex_lock(&binding->lock); - binding->dev = NULL; + ASSERT_EXCLUSIVE_WRITER(binding->dev); + WRITE_ONCE(binding->dev, NULL); mutex_unlock(&binding->lock); } break; diff --git a/net/core/filter.c b/net/core/filter.c index 0d5d5a17acb2..a77d23fe2359 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4150,12 +4150,14 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset) struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags - 1]; struct xdp_rxq_info *rxq = xdp->rxq; - unsigned int tailroom; + int tailroom; if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz) return -EOPNOTSUPP; - tailroom = rxq->frag_size - skb_frag_size(frag) - skb_frag_off(frag); + tailroom = rxq->frag_size - skb_frag_size(frag) - + skb_frag_off(frag) % rxq->frag_size; + WARN_ON_ONCE(tailroom < 0); if (unlikely(offset > tailroom)) return -EINVAL; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index a8558a52884f..cd74beffd209 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -132,7 +132,7 @@ static int netif_local_xmit_active(struct net_device *dev) for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - if (READ_ONCE(txq->xmit_lock_owner) == smp_processor_id()) + if (netif_tx_owned(txq, smp_processor_id())) return 1; } diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 9a3965680451..6a6f2cda5aae 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -20,7 +20,6 @@ #include static siphash_aligned_key_t net_secret; -static siphash_aligned_key_t ts_secret; #define EPHEMERAL_PORT_SHUFFLE_PERIOD (10 * HZ) @@ -28,11 +27,6 @@ static __always_inline void net_secret_init(void) { net_get_random_once(&net_secret, sizeof(net_secret)); } - -static __always_inline void ts_secret_init(void) -{ - net_get_random_once(&ts_secret, sizeof(ts_secret)); -} #endif #ifdef CONFIG_INET @@ -53,28 +47,9 @@ static u32 seq_scale(u32 seq) #endif #if IS_ENABLED(CONFIG_IPV6) -u32 secure_tcpv6_ts_off(const struct net *net, - const __be32 *saddr, const __be32 *daddr) -{ - const struct { - struct in6_addr saddr; - struct in6_addr daddr; - } __aligned(SIPHASH_ALIGNMENT) combined = { - .saddr = *(struct in6_addr *)saddr, - .daddr = *(struct in6_addr *)daddr, - }; - - if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) - return 0; - - ts_secret_init(); - return siphash(&combined, offsetofend(typeof(combined), daddr), - &ts_secret); -} -EXPORT_IPV6_MOD(secure_tcpv6_ts_off); - -u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, - __be16 sport, __be16 dport) +union tcp_seq_and_ts_off +secure_tcpv6_seq_and_ts_off(const struct net *net, const __be32 *saddr, + const __be32 *daddr, __be16 sport, __be16 dport) { const struct { struct in6_addr saddr; @@ -87,14 +62,20 @@ u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, .sport = sport, .dport = dport }; - u32 hash; + union tcp_seq_and_ts_off st; net_secret_init(); - hash = siphash(&combined, offsetofend(typeof(combined), dport), - &net_secret); - return seq_scale(hash); + + st.hash64 = siphash(&combined, offsetofend(typeof(combined), dport), + &net_secret); + + if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) + st.ts_off = 0; + + st.seq = seq_scale(st.seq); + return st; } -EXPORT_SYMBOL(secure_tcpv6_seq); +EXPORT_SYMBOL(secure_tcpv6_seq_and_ts_off); u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport) @@ -118,33 +99,30 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET -u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr) -{ - if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) - return 0; - - ts_secret_init(); - return siphash_2u32((__force u32)saddr, (__force u32)daddr, - &ts_secret); -} - /* secure_tcp_seq_and_tsoff(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d), * but fortunately, `sport' cannot be 0 in any circumstances. If this changes, * it would be easy enough to have the former function use siphash_4u32, passing * the arguments as separate u32. */ -u32 secure_tcp_seq(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport) +union tcp_seq_and_ts_off +secure_tcp_seq_and_ts_off(const struct net *net, __be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) { - u32 hash; + u32 ports = (__force u32)sport << 16 | (__force u32)dport; + union tcp_seq_and_ts_off st; net_secret_init(); - hash = siphash_3u32((__force u32)saddr, (__force u32)daddr, - (__force u32)sport << 16 | (__force u32)dport, - &net_secret); - return seq_scale(hash); + + st.hash64 = siphash_3u32((__force u32)saddr, (__force u32)daddr, + ports, &net_secret); + + if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) + st.ts_off = 0; + + st.seq = seq_scale(st.seq); + return st; } -EXPORT_SYMBOL_GPL(secure_tcp_seq); +EXPORT_SYMBOL_GPL(secure_tcp_seq_and_ts_off); u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 2e26174c9919..3261793abe83 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1205,8 +1205,8 @@ void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) return; psock->saved_data_ready = sk->sk_data_ready; - sk->sk_data_ready = sk_psock_strp_data_ready; - sk->sk_write_space = sk_psock_write_space; + WRITE_ONCE(sk->sk_data_ready, sk_psock_strp_data_ready); + WRITE_ONCE(sk->sk_write_space, sk_psock_write_space); } void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) @@ -1216,8 +1216,8 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) if (!psock->saved_data_ready) return; - sk->sk_data_ready = psock->saved_data_ready; - psock->saved_data_ready = NULL; + WRITE_ONCE(sk->sk_data_ready, psock->saved_data_ready); + WRITE_ONCE(psock->saved_data_ready, NULL); strp_stop(&psock->strp); } @@ -1296,8 +1296,8 @@ void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) return; psock->saved_data_ready = sk->sk_data_ready; - sk->sk_data_ready = sk_psock_verdict_data_ready; - sk->sk_write_space = sk_psock_write_space; + WRITE_ONCE(sk->sk_data_ready, sk_psock_verdict_data_ready); + WRITE_ONCE(sk->sk_write_space, sk_psock_write_space); } void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) @@ -1308,6 +1308,6 @@ void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) if (!psock->saved_data_ready) return; - sk->sk_data_ready = psock->saved_data_ready; + WRITE_ONCE(sk->sk_data_ready, psock->saved_data_ready); psock->saved_data_ready = NULL; } diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index b71c22475c51..df922f9f5289 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -748,6 +748,7 @@ config TCP_SIGPOOL config TCP_AO bool "TCP: Authentication Option (RFC5925)" select CRYPTO + select CRYPTO_LIB_UTILS select TCP_SIGPOOL depends on 64BIT && IPV6 != m # seq-number extension needs WRITE_ONCE(u64) help @@ -761,6 +762,7 @@ config TCP_AO config TCP_MD5SIG bool "TCP: MD5 Signature Option support (RFC2385)" select CRYPTO_LIB_MD5 + select CRYPTO_LIB_UTILS help RFC2385 specifies a method of giving MD5 protection to TCP sessions. Its main (only?) use is to protect BGP sessions between core routers diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index fca980772c81..9bfccc283fa6 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -200,7 +200,7 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2, void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, struct inet_bind2_bucket *tb2, unsigned short port) { - inet_sk(sk)->inet_num = port; + WRITE_ONCE(inet_sk(sk)->inet_num, port); inet_csk(sk)->icsk_bind_hash = tb; inet_csk(sk)->icsk_bind2_hash = tb2; sk_add_bind_node(sk, &tb2->owners); @@ -224,7 +224,7 @@ static void __inet_put_port(struct sock *sk) spin_lock(&head->lock); tb = inet_csk(sk)->icsk_bind_hash; inet_csk(sk)->icsk_bind_hash = NULL; - inet_sk(sk)->inet_num = 0; + WRITE_ONCE(inet_sk(sk)->inet_num, 0); sk->sk_userlocks &= ~SOCK_CONNECT_BIND; spin_lock(&head2->lock); @@ -352,7 +352,7 @@ static inline int compute_score(struct sock *sk, const struct net *net, { int score = -1; - if (net_eq(sock_net(sk), net) && sk->sk_num == hnum && + if (net_eq(sock_net(sk), net) && READ_ONCE(sk->sk_num) == hnum && !ipv6_only_sock(sk)) { if (sk->sk_rcv_saddr != daddr) return -1; @@ -1206,7 +1206,7 @@ error: sk->sk_hash = 0; inet_sk(sk)->inet_sport = 0; - inet_sk(sk)->inet_num = 0; + WRITE_ONCE(inet_sk(sk)->inet_num, 0); if (tw) inet_twsk_bind_unhash(tw, hinfo); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 061751aabc8e..fc3affd9c801 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -378,9 +378,14 @@ static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk, tcp_parse_options(net, skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { - tsoff = secure_tcp_ts_off(net, - ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr); + union tcp_seq_and_ts_off st; + + st = secure_tcp_seq_and_ts_off(net, + ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); + tsoff = st.ts_off; tcp_opt.rcv_tsecr -= tsoff; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 643763bc2142..5654cc9c8a0b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -486,7 +486,8 @@ static void proc_fib_multipath_hash_set_seed(struct net *net, u32 user_seed) proc_fib_multipath_hash_rand_seed), }; - WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed, new); + WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.user_seed, new.user_seed); + WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.mp_seed, new.mp_seed); } static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int write, @@ -500,7 +501,7 @@ static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int write int ret; mphs = &net->ipv4.sysctl_fib_multipath_hash_seed; - user_seed = mphs->user_seed; + user_seed = READ_ONCE(mphs->user_seed); tmp = *table; tmp.data = &user_seed; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f84d9a45cc9d..202a4e57a218 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -244,6 +244,7 @@ #define pr_fmt(fmt) "TCP: " fmt #include +#include #include #include #include @@ -1446,7 +1447,7 @@ out_err: err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { - sk->sk_write_space(sk); + READ_ONCE(sk->sk_write_space)(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } if (binding) @@ -4181,7 +4182,7 @@ ao_parse: break; case TCP_NOTSENT_LOWAT: WRITE_ONCE(tp->notsent_lowat, val); - sk->sk_write_space(sk); + READ_ONCE(sk->sk_write_space)(sk); break; case TCP_INQ: if (val > 1 || val < 0) @@ -4970,7 +4971,7 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, tcp_v4_md5_hash_skb(newhash, key, NULL, skb); else tp->af_specific->calc_md5_hash(newhash, key, NULL, skb); - if (memcmp(hash_location, newhash, 16) != 0) { + if (crypto_memneq(hash_location, newhash, 16)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); trace_tcp_hash_md5_mismatch(sk, skb); return SKB_DROP_REASON_TCP_MD5FAILURE; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 4980caddb0fc..a97cdf3e6af4 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -10,6 +10,7 @@ #define pr_fmt(fmt) "TCP: " fmt #include +#include #include #include @@ -922,7 +923,7 @@ tcp_ao_verify_hash(const struct sock *sk, const struct sk_buff *skb, /* XXX: make it per-AF callback? */ tcp_ao_hash_skb(family, hash_buf, key, sk, skb, traffic_key, (phash - (u8 *)th), sne); - if (memcmp(phash, hash_buf, maclen)) { + if (crypto_memneq(phash, hash_buf, maclen)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); atomic64_inc(&info->counters.pkt_bad); atomic64_inc(&key->pkt_bad); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index c449a044895e..813d2e498c93 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -725,7 +725,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) WRITE_ONCE(sk->sk_prot->unhash, psock->saved_unhash); tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space); } else { - sk->sk_write_space = psock->saved_write_space; + WRITE_ONCE(sk->sk_write_space, psock->saved_write_space); /* Pairs with lockless read in sk_clone_lock() */ sock_replace_proto(sk, psock->sk_proto); } diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index d83efd91f461..7935702e394b 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -509,7 +509,7 @@ next_chunk: if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) goto next_normal; - if (r->id.idiag_sport != htons(sk->sk_num) && + if (r->id.idiag_sport != htons(READ_ONCE(sk->sk_num)) && r->id.idiag_sport) goto next_normal; if (r->id.idiag_dport != sk->sk_dport && diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 41c57efd125c..cba89733d121 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5374,25 +5374,11 @@ static void tcp_ofo_queue(struct sock *sk) static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb); static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb); -/* Check if this incoming skb can be added to socket receive queues - * while satisfying sk->sk_rcvbuf limit. - * - * In theory we should use skb->truesize, but this can cause problems - * when applications use too small SO_RCVBUF values. - * When LRO / hw gro is used, the socket might have a high tp->scaling_ratio, - * allowing RWIN to be close to available space. - * Whenever the receive queue gets full, we can receive a small packet - * filling RWIN, but with a high skb->truesize, because most NIC use 4K page - * plus sk_buff metadata even when receiving less than 1500 bytes of payload. - * - * Note that we use skb->len to decide to accept or drop this packet, - * but sk->sk_rmem_alloc is the sum of all skb->truesize. - */ static bool tcp_can_ingest(const struct sock *sk, const struct sk_buff *skb) { unsigned int rmem = atomic_read(&sk->sk_rmem_alloc); - return rmem + skb->len <= sk->sk_rcvbuf; + return rmem <= sk->sk_rcvbuf; } static int tcp_try_rmem_schedule(struct sock *sk, const struct sk_buff *skb, @@ -5425,7 +5411,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP); - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); tcp_drop_reason(sk, skb, SKB_DROP_REASON_PROTO_MEM); return; } @@ -5635,7 +5621,7 @@ err: void tcp_data_ready(struct sock *sk) { if (tcp_epollin_ready(sk, sk->sk_rcvlowat) || sock_flag(sk, SOCK_DONE)) - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); } static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) @@ -5691,7 +5677,7 @@ queue_and_out: inet_csk(sk)->icsk_ack.pending |= (ICSK_ACK_NOMEM | ICSK_ACK_NOW); inet_csk_schedule_ack(sk); - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); if (skb_queue_len(&sk->sk_receive_queue) && skb->len) { reason = SKB_DROP_REASON_PROTO_MEM; @@ -6114,7 +6100,9 @@ static void tcp_new_space(struct sock *sk) tp->snd_cwnd_stamp = tcp_jiffies32; } - INDIRECT_CALL_1(sk->sk_write_space, sk_stream_write_space, sk); + INDIRECT_CALL_1(READ_ONCE(sk->sk_write_space), + sk_stream_write_space, + sk); } /* Caller made space either from: @@ -6325,7 +6313,7 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t BUG(); WRITE_ONCE(tp->urg_data, TCP_URG_VALID | tmp); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); } } } @@ -7658,6 +7646,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct sock *fastopen_sk = NULL; + union tcp_seq_and_ts_off st; struct request_sock *req; bool want_cookie = false; struct dst_entry *dst; @@ -7727,9 +7716,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (!dst) goto drop_and_free; + if (tmp_opt.tstamp_ok || (!want_cookie && !isn)) + st = af_ops->init_seq_and_ts_off(net, skb); + if (tmp_opt.tstamp_ok) { tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst); - tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb); + tcp_rsk(req)->ts_off = st.ts_off; } if (!want_cookie && !isn) { int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog); @@ -7751,7 +7743,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop_and_release; } - isn = af_ops->init_seq(skb); + isn = st.seq; } tcp_ecn_create_request(req, skb, sk, dst); @@ -7792,7 +7784,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, sock_put(fastopen_sk); goto drop_and_free; } - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); bh_unlock_sock(fastopen_sk); sock_put(fastopen_sk); } else { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d53d39be291a..c7b2463c2e25 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -88,6 +88,7 @@ #include #include +#include #include @@ -104,17 +105,14 @@ static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = { static DEFINE_MUTEX(tcp_exit_batch_mutex); -static u32 tcp_v4_init_seq(const struct sk_buff *skb) +static union tcp_seq_and_ts_off +tcp_v4_init_seq_and_ts_off(const struct net *net, const struct sk_buff *skb) { - return secure_tcp_seq(ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr, - tcp_hdr(skb)->dest, - tcp_hdr(skb)->source); -} - -static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) -{ - return secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); + return secure_tcp_seq_and_ts_off(net, + ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); } int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) @@ -326,15 +324,16 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len rt = NULL; if (likely(!tp->repair)) { + union tcp_seq_and_ts_off st; + + st = secure_tcp_seq_and_ts_off(net, + inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + usin->sin_port); if (!tp->write_seq) - WRITE_ONCE(tp->write_seq, - secure_tcp_seq(inet->inet_saddr, - inet->inet_daddr, - inet->inet_sport, - usin->sin_port)); - WRITE_ONCE(tp->tsoffset, - secure_tcp_ts_off(net, inet->inet_saddr, - inet->inet_daddr)); + WRITE_ONCE(tp->write_seq, st.seq); + WRITE_ONCE(tp->tsoffset, st.ts_off); } atomic_set(&inet->inet_id, get_random_u16()); @@ -839,7 +838,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, goto out; tcp_v4_md5_hash_skb(newhash, key, NULL, skb); - if (memcmp(md5_hash_location, newhash, 16) != 0) + if (crypto_memneq(md5_hash_location, newhash, 16)) goto out; } @@ -1676,8 +1675,7 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .cookie_init_seq = cookie_v4_init_sequence, #endif .route_req = tcp_v4_route_req, - .init_seq = tcp_v4_init_seq, - .init_ts_off = tcp_v4_init_ts_off, + .init_seq_and_ts_off = tcp_v4_init_seq_and_ts_off, .send_synack = tcp_v4_send_synack, }; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index d9c5a43bd281..dafb63b923d0 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -1004,7 +1004,7 @@ enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child, reason = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ if (state == TCP_SYN_RECV && child->sk_state != state) - parent->sk_data_ready(parent); + READ_ONCE(parent->sk_data_ready)(parent); } else { /* Alas, it is possible again, because we do lookup * in main socket hash table and lock on listening diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 6c6b68a66dcd..b60fad393e18 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1787,7 +1787,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) * using prepare_to_wait_exclusive(). */ while (nb) { - INDIRECT_CALL_1(sk->sk_data_ready, + INDIRECT_CALL_1(READ_ONCE(sk->sk_data_ready), sock_def_readable, sk); nb--; } @@ -2287,7 +2287,6 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4) udp_sk(sk)->udp_port_hash); hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); nhslot2 = udp_hashslot2(udptable, newhash); - udp_sk(sk)->udp_portaddr_hash = newhash; if (hslot2 != nhslot2 || rcu_access_pointer(sk->sk_reuseport_cb)) { @@ -2321,19 +2320,25 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4) if (udp_hashed4(sk)) { spin_lock_bh(&hslot->lock); - udp_rehash4(udptable, sk, newhash4); - if (hslot2 != nhslot2) { - spin_lock(&hslot2->lock); - udp_hash4_dec(hslot2); - spin_unlock(&hslot2->lock); + if (inet_rcv_saddr_any(sk)) { + udp_unhash4(udptable, sk); + } else { + udp_rehash4(udptable, sk, newhash4); + if (hslot2 != nhslot2) { + spin_lock(&hslot2->lock); + udp_hash4_dec(hslot2); + spin_unlock(&hslot2->lock); - spin_lock(&nhslot2->lock); - udp_hash4_inc(nhslot2); - spin_unlock(&nhslot2->lock); + spin_lock(&nhslot2->lock); + udp_hash4_inc(nhslot2); + spin_unlock(&nhslot2->lock); + } } spin_unlock_bh(&hslot->lock); } + + udp_sk(sk)->udp_portaddr_hash = newhash; } } EXPORT_IPV6_MOD(udp_lib_rehash); diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index 91233e37cd97..779a3a03762f 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -158,7 +158,7 @@ int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6; if (restore) { - sk->sk_write_space = psock->saved_write_space; + WRITE_ONCE(sk->sk_write_space, psock->saved_write_space); sock_replace_proto(sk, psock->sk_proto); return 0; } diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 5e1da088d8e1..182d38e6d6d8 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -95,7 +95,8 @@ static inline int compute_score(struct sock *sk, const struct net *net, { int score = -1; - if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum && + if (net_eq(sock_net(sk), net) && + READ_ONCE(inet_sk(sk)->inet_num) == hnum && sk->sk_family == PF_INET6) { if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return -1; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 85df25c36409..08cd86f49bf9 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1063,7 +1063,8 @@ static struct net_device *ip6_rt_get_dev_rcu(const struct fib6_result *res) */ if (netif_is_l3_slave(dev) && !rt6_need_strict(&res->f6i->fib6_dst.addr)) - dev = l3mdev_master_dev_rcu(dev); + dev = l3mdev_master_dev_rcu(dev) ? : + dev_net(dev)->loopback_dev; else if (!netif_is_l3_master(dev)) dev = dev_net(dev)->loopback_dev; /* last case is netif_is_l3_master(dev) is true in which @@ -3582,7 +3583,6 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, netdevice_tracker *dev_tracker = &fib6_nh->fib_nh_dev_tracker; struct net_device *dev = NULL; struct inet6_dev *idev = NULL; - int addr_type; int err; fib6_nh->fib_nh_family = AF_INET6; @@ -3624,11 +3624,10 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, fib6_nh->fib_nh_weight = 1; - /* We cannot add true routes via loopback here, - * they would result in kernel looping; promote them to reject routes + /* Reset the nexthop device to the loopback device in case of reject + * routes. */ - addr_type = ipv6_addr_type(&cfg->fc_dst); - if (fib6_is_reject(cfg->fc_flags, dev, addr_type)) { + if (cfg->fc_flags & RTF_REJECT) { /* hold loopback dev/idev if we haven't done so. */ if (dev != net->loopback_dev) { if (dev) { diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 7e007f013ec8..4f6f0d751d6c 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -151,9 +151,14 @@ static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk, tcp_parse_options(net, skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { - tsoff = secure_tcpv6_ts_off(net, - ipv6_hdr(skb)->daddr.s6_addr32, - ipv6_hdr(skb)->saddr.s6_addr32); + union tcp_seq_and_ts_off st; + + st = secure_tcpv6_seq_and_ts_off(net, + ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); + tsoff = st.ts_off; tcp_opt.rcv_tsecr -= tsoff; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index e46a0efae012..bb09d5ccf599 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -68,6 +68,7 @@ #include #include +#include #include @@ -104,18 +105,14 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) } } -static u32 tcp_v6_init_seq(const struct sk_buff *skb) +static union tcp_seq_and_ts_off +tcp_v6_init_seq_and_ts_off(const struct net *net, const struct sk_buff *skb) { - return secure_tcpv6_seq(ipv6_hdr(skb)->daddr.s6_addr32, - ipv6_hdr(skb)->saddr.s6_addr32, - tcp_hdr(skb)->dest, - tcp_hdr(skb)->source); -} - -static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb) -{ - return secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32, - ipv6_hdr(skb)->saddr.s6_addr32); + return secure_tcpv6_seq_and_ts_off(net, + ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); } static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, @@ -319,14 +316,16 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr_unsized *uaddr, sk_set_txhash(sk); if (likely(!tp->repair)) { + union tcp_seq_and_ts_off st; + + st = secure_tcpv6_seq_and_ts_off(net, + np->saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, + inet->inet_sport, + inet->inet_dport); if (!tp->write_seq) - WRITE_ONCE(tp->write_seq, - secure_tcpv6_seq(np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32, - inet->inet_sport, - inet->inet_dport)); - tp->tsoffset = secure_tcpv6_ts_off(net, np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32); + WRITE_ONCE(tp->write_seq, st.seq); + tp->tsoffset = st.ts_off; } if (tcp_fastopen_defer_connect(sk, &err)) @@ -816,8 +815,7 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .cookie_init_seq = cookie_v6_init_sequence, #endif .route_req = tcp_v6_route_req, - .init_seq = tcp_v6_init_seq, - .init_ts_off = tcp_v6_init_ts_off, + .init_seq_and_ts_off = tcp_v6_init_seq_and_ts_off, .send_synack = tcp_v6_send_synack, }; @@ -1048,7 +1046,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb, key.type = TCP_KEY_MD5; tcp_v6_md5_hash_skb(newhash, key.md5_key, NULL, skb); - if (memcmp(md5_hash_location, newhash, 16) != 0) + if (crypto_memneq(md5_hash_location, newhash, 16)) goto out; } #endif diff --git a/net/mac80211/eht.c b/net/mac80211/eht.c index 75096b2195d2..078e1e23d8d1 100644 --- a/net/mac80211/eht.c +++ b/net/mac80211/eht.c @@ -154,6 +154,7 @@ void ieee80211_rx_eml_op_mode_notif(struct ieee80211_sub_if_data *sdata, u8 *ptr = mgmt->u.action.u.eml_omn.variable; struct ieee80211_eml_params eml_params = { .link_id = status->link_id, + .control = control, }; struct sta_info *sta; int opt_len = 0; diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 7298836469b3..57a456690406 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -212,9 +212,24 @@ void mptcp_pm_send_ack(struct mptcp_sock *msk, spin_lock_bh(&msk->pm.lock); } -void mptcp_pm_addr_send_ack(struct mptcp_sock *msk) +static bool subflow_in_rm_list(const struct mptcp_subflow_context *subflow, + const struct mptcp_rm_list *rm_list) { - struct mptcp_subflow_context *subflow, *alt = NULL; + u8 i, id = subflow_get_local_id(subflow); + + for (i = 0; i < rm_list->nr; i++) { + if (rm_list->ids[i] == id) + return true; + } + + return false; +} + +static void +mptcp_pm_addr_send_ack_avoid_list(struct mptcp_sock *msk, + const struct mptcp_rm_list *rm_list) +{ + struct mptcp_subflow_context *subflow, *stale = NULL, *same_id = NULL; msk_owned_by_me(msk); lockdep_assert_held(&msk->pm.lock); @@ -224,19 +239,35 @@ void mptcp_pm_addr_send_ack(struct mptcp_sock *msk) return; mptcp_for_each_subflow(msk, subflow) { - if (__mptcp_subflow_active(subflow)) { - if (!subflow->stale) { - mptcp_pm_send_ack(msk, subflow, false, false); - return; - } + if (!__mptcp_subflow_active(subflow)) + continue; - if (!alt) - alt = subflow; + if (unlikely(subflow->stale)) { + if (!stale) + stale = subflow; + } else if (unlikely(rm_list && + subflow_in_rm_list(subflow, rm_list))) { + if (!same_id) + same_id = subflow; + } else { + goto send_ack; } } - if (alt) - mptcp_pm_send_ack(msk, alt, false, false); + if (same_id) + subflow = same_id; + else if (stale) + subflow = stale; + else + return; + +send_ack: + mptcp_pm_send_ack(msk, subflow, false, false); +} + +void mptcp_pm_addr_send_ack(struct mptcp_sock *msk) +{ + mptcp_pm_addr_send_ack_avoid_list(msk, NULL); } int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk, @@ -470,7 +501,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_ msk->pm.rm_list_tx = *rm_list; rm_addr |= BIT(MPTCP_RM_ADDR_SIGNAL); WRITE_ONCE(msk->pm.addr_signal, rm_addr); - mptcp_pm_addr_send_ack(msk); + mptcp_pm_addr_send_ack_avoid_list(msk, rm_list); return 0; } diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index b5316a6c7d1b..b2b9df43960e 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -418,6 +418,15 @@ subflow: } exit: + /* If an endpoint has both the signal and subflow flags, but it is not + * possible to create subflows -- the 'while' loop body above never + * executed -- then still mark the endp as used, which is somehow the + * case. This avoids issues later when removing the endpoint and calling + * __mark_subflow_endp_available(), which expects the increment here. + */ + if (signal_and_subflow && local.addr.id != msk->mpc_endpoint_id) + msk->pm.local_addr_used++; + mptcp_pm_nl_check_work_pending(msk); } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fd7f7e4e2a43..1862bd7fe804 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -833,6 +833,11 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, } } +/* Use NFT_ITER_UPDATE iterator even if this may be called from the preparation + * phase, the set clone might already exist from a previous command, or it might + * be a set that is going away and does not require a clone. The netns and + * netlink release paths also need to work on the live set. + */ static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter iter = { @@ -7170,6 +7175,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, struct nft_data_desc desc; enum nft_registers dreg; struct nft_trans *trans; + bool set_full = false; u64 expiration; u64 timeout; int err, i; @@ -7461,10 +7467,18 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) goto err_elem_free; + if (!(flags & NFT_SET_ELEM_CATCHALL)) { + unsigned int max = nft_set_maxsize(set), nelems; + + nelems = atomic_inc_return(&set->nelems); + if (nelems > max) + set_full = true; + } + trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set); if (trans == NULL) { err = -ENOMEM; - goto err_elem_free; + goto err_set_size; } ext->genmask = nft_genmask_cur(ctx->net); @@ -7516,7 +7530,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, ue->priv = elem_priv; nft_trans_commit_list_add_elem(ctx->net, trans); - goto err_elem_free; + goto err_set_size; } } } @@ -7534,23 +7548,16 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, goto err_element_clash; } - if (!(flags & NFT_SET_ELEM_CATCHALL)) { - unsigned int max = nft_set_maxsize(set); - - if (!atomic_add_unless(&set->nelems, 1, max)) { - err = -ENFILE; - goto err_set_full; - } - } - nft_trans_container_elem(trans)->elems[0].priv = elem.priv; nft_trans_commit_list_add_elem(ctx->net, trans); - return 0; -err_set_full: - nft_setelem_remove(ctx->net, set, elem.priv); + return set_full ? -ENFILE : 0; + err_element_clash: kfree(trans); +err_set_size: + if (!(flags & NFT_SET_ELEM_CATCHALL)) + atomic_dec(&set->nelems); err_elem_free: nf_tables_set_elem_destroy(ctx, set, elem.priv); err_parse_data: @@ -7901,9 +7908,12 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, static int nft_set_flush(struct nft_ctx *ctx, struct nft_set *set, u8 genmask) { + /* The set backend might need to clone the set, do it now from the + * preparation phase, use NFT_ITER_UPDATE_CLONE iterator type. + */ struct nft_set_iter iter = { .genmask = genmask, - .type = NFT_ITER_UPDATE, + .type = NFT_ITER_UPDATE_CLONE, .fn = nft_setelem_flush, }; @@ -10483,11 +10493,6 @@ static void nft_trans_gc_queue_work(struct nft_trans_gc *trans) 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) { diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 739b992bde59..b0e571c8e3f3 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -374,6 +374,7 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, { switch (iter->type) { case NFT_ITER_UPDATE: + case NFT_ITER_UPDATE_CLONE: /* only relevant for netlink dumps which use READ type */ WARN_ON_ONCE(iter->skip != 0); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 7ef4b44471d3..a34632ae6048 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1680,11 +1680,11 @@ static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set, } /** - * pipapo_gc() - Drop expired entries from set, destroy start and end elements + * pipapo_gc_scan() - Drop expired entries from set and link them to gc list * @set: nftables API set representation * @m: Matching data */ -static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) +static void pipapo_gc_scan(struct nft_set *set, struct nft_pipapo_match *m) { struct nft_pipapo *priv = nft_set_priv(set); struct net *net = read_pnet(&set->net); @@ -1697,6 +1697,8 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) if (!gc) return; + list_add(&gc->list, &priv->gc_head); + while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; const struct nft_pipapo_field *f; @@ -1724,9 +1726,13 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) * NFT_SET_ELEM_DEAD_BIT. */ if (__nft_set_elem_expired(&e->ext, tstamp)) { - gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); - if (!gc) - return; + if (!nft_trans_gc_space(gc)) { + gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); + if (!gc) + return; + + list_add(&gc->list, &priv->gc_head); + } nft_pipapo_gc_deactivate(net, set, e); pipapo_drop(m, rulemap); @@ -1740,10 +1746,30 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) } } - gc = nft_trans_gc_catchall_sync(gc); + priv->last_gc = jiffies; +} + +/** + * pipapo_gc_queue() - Free expired elements + * @set: nftables API set representation + */ +static void pipapo_gc_queue(struct nft_set *set) +{ + struct nft_pipapo *priv = nft_set_priv(set); + struct nft_trans_gc *gc, *next; + + /* always do a catchall cycle: */ + gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); if (gc) { + gc = nft_trans_gc_catchall_sync(gc); + if (gc) + nft_trans_gc_queue_sync_done(gc); + } + + /* always purge queued gc elements. */ + list_for_each_entry_safe(gc, next, &priv->gc_head, list) { + list_del(&gc->list); nft_trans_gc_queue_sync_done(gc); - priv->last_gc = jiffies; } } @@ -1797,6 +1823,10 @@ static void pipapo_reclaim_match(struct rcu_head *rcu) * * We also need to create a new working copy for subsequent insertions and * deletions. + * + * After the live copy has been replaced by the clone, we can safely queue + * expired elements that have been collected by pipapo_gc_scan() for + * memory reclaim. */ static void nft_pipapo_commit(struct nft_set *set) { @@ -1807,7 +1837,7 @@ static void nft_pipapo_commit(struct nft_set *set) return; if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set))) - pipapo_gc(set, priv->clone); + pipapo_gc_scan(set, priv->clone); old = rcu_replace_pointer(priv->match, priv->clone, nft_pipapo_transaction_mutex_held(set)); @@ -1815,6 +1845,8 @@ static void nft_pipapo_commit(struct nft_set *set) if (old) call_rcu(&old->rcu, pipapo_reclaim_match); + + pipapo_gc_queue(set); } static void nft_pipapo_abort(const struct nft_set *set) @@ -2144,13 +2176,20 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_pipapo_match *m; switch (iter->type) { - case NFT_ITER_UPDATE: + case NFT_ITER_UPDATE_CLONE: m = pipapo_maybe_clone(set); if (!m) { iter->err = -ENOMEM; return; } - + nft_pipapo_do_walk(ctx, set, m, iter); + break; + case NFT_ITER_UPDATE: + if (priv->clone) + m = priv->clone; + else + m = rcu_dereference_protected(priv->match, + nft_pipapo_transaction_mutex_held(set)); nft_pipapo_do_walk(ctx, set, m, iter); break; case NFT_ITER_READ: @@ -2272,6 +2311,7 @@ static int nft_pipapo_init(const struct nft_set *set, f->mt = NULL; } + INIT_LIST_HEAD(&priv->gc_head); rcu_assign_pointer(priv->match, m); return 0; @@ -2321,6 +2361,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m; + WARN_ON_ONCE(!list_empty(&priv->gc_head)); + m = rcu_dereference_protected(priv->match, true); if (priv->clone) { diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index eaab422aa56a..9aee9a9eaeb7 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -156,12 +156,14 @@ struct nft_pipapo_match { * @clone: Copy where pending insertions and deletions are kept * @width: Total bytes to be matched for one packet, including padding * @last_gc: Timestamp of last garbage collection run, jiffies + * @gc_head: list of nft_trans_gc to queue up for mem reclaim */ struct nft_pipapo { struct nft_pipapo_match __rcu *match; struct nft_pipapo_match *clone; int width; unsigned long last_gc; + struct list_head gc_head; }; struct nft_pipapo_elem; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 3f02e4478216..ee3d4f5b9ff7 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -861,13 +861,15 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, struct nft_rbtree *priv = nft_set_priv(set); switch (iter->type) { - case NFT_ITER_UPDATE: - lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex); - + case NFT_ITER_UPDATE_CLONE: if (nft_array_may_resize(set) < 0) { iter->err = -ENOMEM; break; } + fallthrough; + case NFT_ITER_UPDATE: + lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex); + nft_rbtree_do_walk(ctx, set, iter); break; case NFT_ITER_READ: diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index 3670bb33732e..7cb1e6aaae90 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -707,8 +707,10 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target, int rc; data_exch = kzalloc_obj(*data_exch); - if (!data_exch) + if (!data_exch) { + kfree_skb(skb); return -ENOMEM; + } data_exch->cb = cb; data_exch->cb_context = cb_context; @@ -731,8 +733,10 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target, data_exch); exit: - if (rc) + if (rc) { + kfree_skb(skb); kfree(data_exch); + } return rc; } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 6e9b76e2cc56..43d871525dbc 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -567,6 +567,10 @@ static int nci_close_device(struct nci_dev *ndev) flush_workqueue(ndev->cmd_wq); timer_delete_sync(&ndev->cmd_timer); timer_delete_sync(&ndev->data_timer); + if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags)) + nci_data_exchange_complete(ndev, NULL, + ndev->cur_conn_id, + -ENODEV); mutex_unlock(&ndev->req_lock); return 0; } @@ -598,6 +602,11 @@ static int nci_close_device(struct nci_dev *ndev) flush_workqueue(ndev->cmd_wq); timer_delete_sync(&ndev->cmd_timer); + timer_delete_sync(&ndev->data_timer); + + if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags)) + nci_data_exchange_complete(ndev, NULL, ndev->cur_conn_id, + -ENODEV); /* Clear flags except NCI_UNREG */ ndev->flags &= BIT(NCI_UNREG); @@ -1035,18 +1044,23 @@ static int nci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target, struct nci_conn_info *conn_info; conn_info = ndev->rf_conn_info; - if (!conn_info) + if (!conn_info) { + kfree_skb(skb); return -EPROTO; + } pr_debug("target_idx %d, len %d\n", target->idx, skb->len); if (!ndev->target_active_prot) { pr_err("unable to exchange data, no active target\n"); + kfree_skb(skb); return -EINVAL; } - if (test_and_set_bit(NCI_DATA_EXCHANGE, &ndev->flags)) + if (test_and_set_bit(NCI_DATA_EXCHANGE, &ndev->flags)) { + kfree_skb(skb); return -EBUSY; + } /* store cb and context to be used on receiving data */ conn_info->data_exchange_cb = cb; @@ -1482,10 +1496,20 @@ static bool nci_valid_size(struct sk_buff *skb) unsigned int hdr_size = NCI_CTRL_HDR_SIZE; if (skb->len < hdr_size || - !nci_plen(skb->data) || skb->len < hdr_size + nci_plen(skb->data)) { return false; } + + if (!nci_plen(skb->data)) { + /* Allow zero length in proprietary notifications (0x20 - 0x3F). */ + if (nci_opcode_oid(nci_opcode(skb->data)) >= 0x20 && + nci_mt(skb->data) == NCI_MT_NTF_PKT) + return true; + + /* Disallow zero length otherwise. */ + return false; + } + return true; } diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index 78f4131af3cf..5f98c73db5af 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -33,7 +33,8 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id); if (!conn_info) { kfree_skb(skb); - goto exit; + clear_bit(NCI_DATA_EXCHANGE, &ndev->flags); + return; } cb = conn_info->data_exchange_cb; @@ -45,6 +46,12 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, timer_delete_sync(&ndev->data_timer); clear_bit(NCI_DATA_EXCHANGE_TO, &ndev->flags); + /* Mark the exchange as done before calling the callback. + * The callback (e.g. rawsock_data_exchange_complete) may + * want to immediately queue another data exchange. + */ + clear_bit(NCI_DATA_EXCHANGE, &ndev->flags); + if (cb) { /* forward skb to nfc core */ cb(cb_context, skb, err); @@ -54,9 +61,6 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, /* no waiting callback, free skb */ kfree_skb(skb); } - -exit: - clear_bit(NCI_DATA_EXCHANGE, &ndev->flags); } /* ----------------- NCI TX Data ----------------- */ diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index b049022399ae..f7d7a599fade 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -67,6 +67,17 @@ static int rawsock_release(struct socket *sock) if (sock->type == SOCK_RAW) nfc_sock_unlink(&raw_sk_list, sk); + if (sk->sk_state == TCP_ESTABLISHED) { + /* Prevent rawsock_tx_work from starting new transmits and + * wait for any in-progress work to finish. This must happen + * before the socket is orphaned to avoid a race where + * rawsock_tx_work runs after the NCI device has been freed. + */ + sk->sk_shutdown |= SEND_SHUTDOWN; + cancel_work_sync(&nfc_rawsock(sk)->tx_work); + rawsock_write_queue_purge(sk); + } + sock_orphan(sk); sock_put(sk); diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 04f310255692..654e23d13e3d 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -490,18 +490,24 @@ bool rds_tcp_tune(struct socket *sock) struct rds_tcp_net *rtn; tcp_sock_set_nodelay(sock->sk); - lock_sock(sk); /* TCP timer functions might access net namespace even after * a process which created this net namespace terminated. */ if (!sk->sk_net_refcnt) { - if (!maybe_get_net(net)) { - release_sock(sk); + if (!maybe_get_net(net)) return false; - } + /* + * sk_net_refcnt_upgrade() must be called before lock_sock() + * because it does a GFP_KERNEL allocation, which can trigger + * fs_reclaim and create a circular lock dependency with the + * socket lock. The fields it modifies (sk_net_refcnt, + * ns_tracker) are not accessed by any concurrent code path + * at this point. + */ sk_net_refcnt_upgrade(sk); put_net(net); } + lock_sock(sk); rtn = net_generic(net, rds_tcp_netid); if (rtn->sndbuf_size > 0) { sk->sk_sndbuf = rtn->sndbuf_size; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index bd51522c7953..7d5e50c921a0 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1360,6 +1360,12 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, return -EINVAL; } + if (bind && !(flags & TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT)) { + NL_SET_ERR_MSG_MOD(extack, + "Attaching ct to a non ingress/clsact qdisc is unsupported"); + return -EOPNOTSUPP; + } + err = nla_parse_nested(tb, TCA_CT_MAX, nla, ct_policy, extack); if (err < 0) return err; diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index 686eaed81b81..fdbfcaa3e2ab 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -32,9 +32,12 @@ static ktime_t gate_get_time(struct tcf_gate *gact) return KTIME_MAX; } -static void gate_get_start_time(struct tcf_gate *gact, ktime_t *start) +static void tcf_gate_params_free_rcu(struct rcu_head *head); + +static void gate_get_start_time(struct tcf_gate *gact, + const struct tcf_gate_params *param, + ktime_t *start) { - struct tcf_gate_params *param = &gact->param; ktime_t now, base, cycle; u64 n; @@ -69,12 +72,14 @@ static enum hrtimer_restart gate_timer_func(struct hrtimer *timer) { struct tcf_gate *gact = container_of(timer, struct tcf_gate, hitimer); - struct tcf_gate_params *p = &gact->param; struct tcfg_gate_entry *next; + struct tcf_gate_params *p; ktime_t close_time, now; spin_lock(&gact->tcf_lock); + p = rcu_dereference_protected(gact->param, + lockdep_is_held(&gact->tcf_lock)); next = gact->next_entry; /* cycle start, clear pending bit, clear total octets */ @@ -225,6 +230,35 @@ static void release_entry_list(struct list_head *entries) } } +static int tcf_gate_copy_entries(struct tcf_gate_params *dst, + const struct tcf_gate_params *src, + struct netlink_ext_ack *extack) +{ + struct tcfg_gate_entry *entry; + int i = 0; + + list_for_each_entry(entry, &src->entries, list) { + struct tcfg_gate_entry *new; + + new = kzalloc(sizeof(*new), GFP_ATOMIC); + if (!new) { + NL_SET_ERR_MSG(extack, "Not enough memory for entry"); + return -ENOMEM; + } + + new->index = entry->index; + new->gate_state = entry->gate_state; + new->interval = entry->interval; + new->ipv = entry->ipv; + new->maxoctets = entry->maxoctets; + list_add_tail(&new->list, &dst->entries); + i++; + } + + dst->num_entries = i; + return 0; +} + static int parse_gate_list(struct nlattr *list_attr, struct tcf_gate_params *sched, struct netlink_ext_ack *extack) @@ -270,24 +304,44 @@ release_list: return err; } -static void gate_setup_timer(struct tcf_gate *gact, u64 basetime, - enum tk_offsets tko, s32 clockid, - bool do_init) +static bool gate_timer_needs_cancel(u64 basetime, u64 old_basetime, + enum tk_offsets tko, + enum tk_offsets old_tko, + s32 clockid, s32 old_clockid) { - if (!do_init) { - if (basetime == gact->param.tcfg_basetime && - tko == gact->tk_offset && - clockid == gact->param.tcfg_clockid) - return; + return basetime != old_basetime || + clockid != old_clockid || + tko != old_tko; +} - spin_unlock_bh(&gact->tcf_lock); - hrtimer_cancel(&gact->hitimer); - spin_lock_bh(&gact->tcf_lock); +static int gate_clock_resolve(s32 clockid, enum tk_offsets *tko, + struct netlink_ext_ack *extack) +{ + switch (clockid) { + case CLOCK_REALTIME: + *tko = TK_OFFS_REAL; + return 0; + case CLOCK_MONOTONIC: + *tko = TK_OFFS_MAX; + return 0; + case CLOCK_BOOTTIME: + *tko = TK_OFFS_BOOT; + return 0; + case CLOCK_TAI: + *tko = TK_OFFS_TAI; + return 0; + default: + NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); + return -EINVAL; } - gact->param.tcfg_basetime = basetime; - gact->param.tcfg_clockid = clockid; - gact->tk_offset = tko; - hrtimer_setup(&gact->hitimer, gate_timer_func, clockid, HRTIMER_MODE_ABS_SOFT); +} + +static void gate_setup_timer(struct tcf_gate *gact, s32 clockid, + enum tk_offsets tko) +{ + WRITE_ONCE(gact->tk_offset, tko); + hrtimer_setup(&gact->hitimer, gate_timer_func, clockid, + HRTIMER_MODE_ABS_SOFT); } static int tcf_gate_init(struct net *net, struct nlattr *nla, @@ -296,15 +350,22 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_gate_ops.net_id); - enum tk_offsets tk_offset = TK_OFFS_TAI; + u64 cycletime = 0, basetime = 0, cycletime_ext = 0; + struct tcf_gate_params *p = NULL, *old_p = NULL; + enum tk_offsets old_tk_offset = TK_OFFS_TAI; + const struct tcf_gate_params *cur_p = NULL; bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_GATE_MAX + 1]; + enum tk_offsets tko = TK_OFFS_TAI; struct tcf_chain *goto_ch = NULL; - u64 cycletime = 0, basetime = 0; - struct tcf_gate_params *p; + s32 timer_clockid = CLOCK_TAI; + bool use_old_entries = false; + s32 old_clockid = CLOCK_TAI; + bool need_cancel = false; s32 clockid = CLOCK_TAI; struct tcf_gate *gact; struct tc_gate *parm; + u64 old_basetime = 0; int ret = 0, err; u32 gflags = 0; s32 prio = -1; @@ -321,26 +382,8 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (!tb[TCA_GATE_PARMS]) return -EINVAL; - if (tb[TCA_GATE_CLOCKID]) { + if (tb[TCA_GATE_CLOCKID]) clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]); - switch (clockid) { - case CLOCK_REALTIME: - tk_offset = TK_OFFS_REAL; - break; - case CLOCK_MONOTONIC: - tk_offset = TK_OFFS_MAX; - break; - case CLOCK_BOOTTIME: - tk_offset = TK_OFFS_BOOT; - break; - case CLOCK_TAI: - tk_offset = TK_OFFS_TAI; - break; - default: - NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); - return -EINVAL; - } - } parm = nla_data(tb[TCA_GATE_PARMS]); index = parm->index; @@ -366,6 +409,60 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, return -EEXIST; } + gact = to_gate(*a); + + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) { + err = -ENOMEM; + goto chain_put; + } + INIT_LIST_HEAD(&p->entries); + + use_old_entries = !tb[TCA_GATE_ENTRY_LIST]; + if (!use_old_entries) { + err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack); + if (err < 0) + goto err_free; + use_old_entries = !err; + } + + if (ret == ACT_P_CREATED && use_old_entries) { + NL_SET_ERR_MSG(extack, "The entry list is empty"); + err = -EINVAL; + goto err_free; + } + + if (ret != ACT_P_CREATED) { + rcu_read_lock(); + cur_p = rcu_dereference(gact->param); + + old_basetime = cur_p->tcfg_basetime; + old_clockid = cur_p->tcfg_clockid; + old_tk_offset = READ_ONCE(gact->tk_offset); + + basetime = old_basetime; + cycletime_ext = cur_p->tcfg_cycletime_ext; + prio = cur_p->tcfg_priority; + gflags = cur_p->tcfg_flags; + + if (!tb[TCA_GATE_CLOCKID]) + clockid = old_clockid; + + err = 0; + if (use_old_entries) { + err = tcf_gate_copy_entries(p, cur_p, extack); + if (!err && !tb[TCA_GATE_CYCLE_TIME]) + cycletime = cur_p->tcfg_cycletime; + } + rcu_read_unlock(); + if (err) + goto err_free; + } + if (tb[TCA_GATE_PRIORITY]) prio = nla_get_s32(tb[TCA_GATE_PRIORITY]); @@ -375,25 +472,26 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (tb[TCA_GATE_FLAGS]) gflags = nla_get_u32(tb[TCA_GATE_FLAGS]); - gact = to_gate(*a); - if (ret == ACT_P_CREATED) - INIT_LIST_HEAD(&gact->param.entries); - - err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); - if (err < 0) - goto release_idr; - - spin_lock_bh(&gact->tcf_lock); - p = &gact->param; - if (tb[TCA_GATE_CYCLE_TIME]) cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]); - if (tb[TCA_GATE_ENTRY_LIST]) { - err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack); - if (err < 0) - goto chain_put; - } + if (tb[TCA_GATE_CYCLE_TIME_EXT]) + cycletime_ext = nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]); + + err = gate_clock_resolve(clockid, &tko, extack); + if (err) + goto err_free; + timer_clockid = clockid; + + need_cancel = ret != ACT_P_CREATED && + gate_timer_needs_cancel(basetime, old_basetime, + tko, old_tk_offset, + timer_clockid, old_clockid); + + if (need_cancel) + hrtimer_cancel(&gact->hitimer); + + spin_lock_bh(&gact->tcf_lock); if (!cycletime) { struct tcfg_gate_entry *entry; @@ -402,22 +500,20 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, list_for_each_entry(entry, &p->entries, list) cycle = ktime_add_ns(cycle, entry->interval); cycletime = cycle; - if (!cycletime) { - err = -EINVAL; - goto chain_put; - } } p->tcfg_cycletime = cycletime; + p->tcfg_cycletime_ext = cycletime_ext; - if (tb[TCA_GATE_CYCLE_TIME_EXT]) - p->tcfg_cycletime_ext = - nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]); - - gate_setup_timer(gact, basetime, tk_offset, clockid, - ret == ACT_P_CREATED); + if (need_cancel || ret == ACT_P_CREATED) + gate_setup_timer(gact, timer_clockid, tko); p->tcfg_priority = prio; p->tcfg_flags = gflags; - gate_get_start_time(gact, &start); + p->tcfg_basetime = basetime; + p->tcfg_clockid = timer_clockid; + gate_get_start_time(gact, p, &start); + + old_p = rcu_replace_pointer(gact->param, p, + lockdep_is_held(&gact->tcf_lock)); gact->current_close_time = start; gact->current_gate_status = GATE_ACT_GATE_OPEN | GATE_ACT_PENDING; @@ -434,11 +530,15 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); + if (old_p) + call_rcu(&old_p->rcu, tcf_gate_params_free_rcu); + return ret; +err_free: + release_entry_list(&p->entries); + kfree(p); chain_put: - spin_unlock_bh(&gact->tcf_lock); - if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: @@ -446,21 +546,29 @@ release_idr: * without taking tcf_lock. */ if (ret == ACT_P_CREATED) - gate_setup_timer(gact, gact->param.tcfg_basetime, - gact->tk_offset, gact->param.tcfg_clockid, - true); + gate_setup_timer(gact, timer_clockid, tko); + tcf_idr_release(*a, bind); return err; } +static void tcf_gate_params_free_rcu(struct rcu_head *head) +{ + struct tcf_gate_params *p = container_of(head, struct tcf_gate_params, rcu); + + release_entry_list(&p->entries); + kfree(p); +} + static void tcf_gate_cleanup(struct tc_action *a) { struct tcf_gate *gact = to_gate(a); struct tcf_gate_params *p; - p = &gact->param; hrtimer_cancel(&gact->hitimer); - release_entry_list(&p->entries); + p = rcu_dereference_protected(gact->param, 1); + if (p) + call_rcu(&p->rcu, tcf_gate_params_free_rcu); } static int dumping_entry(struct sk_buff *skb, @@ -509,10 +617,9 @@ static int tcf_gate_dump(struct sk_buff *skb, struct tc_action *a, struct nlattr *entry_list; struct tcf_t t; - spin_lock_bh(&gact->tcf_lock); - opt.action = gact->tcf_action; - - p = &gact->param; + rcu_read_lock(); + opt.action = READ_ONCE(gact->tcf_action); + p = rcu_dereference(gact->param); if (nla_put(skb, TCA_GATE_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -552,12 +659,12 @@ static int tcf_gate_dump(struct sk_buff *skb, struct tc_action *a, tcf_tm_dump(&t, &gact->tcf_tm); if (nla_put_64bit(skb, TCA_GATE_TM, sizeof(t), &t, TCA_GATE_PAD)) goto nla_put_failure; - spin_unlock_bh(&gact->tcf_lock); + rcu_read_unlock(); return skb->len; nla_put_failure: - spin_unlock_bh(&gact->tcf_lock); + rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 79df81d12894..d5e8a91bb4eb 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -293,8 +293,8 @@ static int load_metaops_and_vet(u32 metaid, void *val, int len, bool rtnl_held) /* called when adding new meta information */ static int __add_metainfo(const struct tcf_meta_ops *ops, - struct tcf_ife_info *ife, u32 metaid, void *metaval, - int len, bool atomic, bool exists) + struct tcf_ife_params *p, u32 metaid, void *metaval, + int len, bool atomic) { struct tcf_meta_info *mi = NULL; int ret = 0; @@ -313,45 +313,40 @@ static int __add_metainfo(const struct tcf_meta_ops *ops, } } - if (exists) - spin_lock_bh(&ife->tcf_lock); - list_add_tail(&mi->metalist, &ife->metalist); - if (exists) - spin_unlock_bh(&ife->tcf_lock); + list_add_tail(&mi->metalist, &p->metalist); return ret; } static int add_metainfo_and_get_ops(const struct tcf_meta_ops *ops, - struct tcf_ife_info *ife, u32 metaid, - bool exists) + struct tcf_ife_params *p, u32 metaid) { int ret; if (!try_module_get(ops->owner)) return -ENOENT; - ret = __add_metainfo(ops, ife, metaid, NULL, 0, true, exists); + ret = __add_metainfo(ops, p, metaid, NULL, 0, true); if (ret) module_put(ops->owner); return ret; } -static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, - int len, bool exists) +static int add_metainfo(struct tcf_ife_params *p, u32 metaid, void *metaval, + int len) { const struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret; if (!ops) return -ENOENT; - ret = __add_metainfo(ops, ife, metaid, metaval, len, false, exists); + ret = __add_metainfo(ops, p, metaid, metaval, len, false); if (ret) /*put back what find_ife_oplist took */ module_put(ops->owner); return ret; } -static int use_all_metadata(struct tcf_ife_info *ife, bool exists) +static int use_all_metadata(struct tcf_ife_params *p) { struct tcf_meta_ops *o; int rc = 0; @@ -359,7 +354,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists) read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { - rc = add_metainfo_and_get_ops(o, ife, o->metaid, exists); + rc = add_metainfo_and_get_ops(o, p, o->metaid); if (rc == 0) installed += 1; } @@ -371,7 +366,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists) return -EINVAL; } -static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife) +static int dump_metalist(struct sk_buff *skb, struct tcf_ife_params *p) { struct tcf_meta_info *e; struct nlattr *nest; @@ -379,14 +374,14 @@ static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife) int total_encoded = 0; /*can only happen on decode */ - if (list_empty(&ife->metalist)) + if (list_empty(&p->metalist)) return 0; nest = nla_nest_start_noflag(skb, TCA_IFE_METALST); if (!nest) goto out_nlmsg_trim; - list_for_each_entry(e, &ife->metalist, metalist) { + list_for_each_entry(e, &p->metalist, metalist) { if (!e->ops->get(skb, e)) total_encoded += 1; } @@ -403,13 +398,11 @@ out_nlmsg_trim: return -1; } -/* under ife->tcf_lock */ -static void _tcf_ife_cleanup(struct tc_action *a) +static void __tcf_ife_cleanup(struct tcf_ife_params *p) { - struct tcf_ife_info *ife = to_ife(a); struct tcf_meta_info *e, *n; - list_for_each_entry_safe(e, n, &ife->metalist, metalist) { + list_for_each_entry_safe(e, n, &p->metalist, metalist) { list_del(&e->metalist); if (e->metaval) { if (e->ops->release) @@ -422,18 +415,23 @@ static void _tcf_ife_cleanup(struct tc_action *a) } } +static void tcf_ife_cleanup_params(struct rcu_head *head) +{ + struct tcf_ife_params *p = container_of(head, struct tcf_ife_params, + rcu); + + __tcf_ife_cleanup(p); + kfree(p); +} + static void tcf_ife_cleanup(struct tc_action *a) { struct tcf_ife_info *ife = to_ife(a); struct tcf_ife_params *p; - spin_lock_bh(&ife->tcf_lock); - _tcf_ife_cleanup(a); - spin_unlock_bh(&ife->tcf_lock); - p = rcu_dereference_protected(ife->params, 1); if (p) - kfree_rcu(p, rcu); + call_rcu(&p->rcu, tcf_ife_cleanup_params); } static int load_metalist(struct nlattr **tb, bool rtnl_held) @@ -455,8 +453,7 @@ static int load_metalist(struct nlattr **tb, bool rtnl_held) return 0; } -static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, - bool exists, bool rtnl_held) +static int populate_metalist(struct tcf_ife_params *p, struct nlattr **tb) { int len = 0; int rc = 0; @@ -468,7 +465,7 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, val = nla_data(tb[i]); len = nla_len(tb[i]); - rc = add_metainfo(ife, i, val, len, exists); + rc = add_metainfo(p, i, val, len); if (rc) return rc; } @@ -523,6 +520,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, p = kzalloc_obj(*p); if (!p) return -ENOMEM; + INIT_LIST_HEAD(&p->metalist); if (tb[TCA_IFE_METALST]) { err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, @@ -567,8 +565,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } ife = to_ife(*a); - if (ret == ACT_P_CREATED) - INIT_LIST_HEAD(&ife->metalist); err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) @@ -600,8 +596,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } if (tb[TCA_IFE_METALST]) { - err = populate_metalist(ife, tb2, exists, - !(flags & TCA_ACT_FLAGS_NO_RTNL)); + err = populate_metalist(p, tb2); if (err) goto metadata_parse_err; } else { @@ -610,7 +605,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, * as we can. You better have at least one else we are * going to bail out */ - err = use_all_metadata(ife, exists); + err = use_all_metadata(p); if (err) goto metadata_parse_err; } @@ -626,13 +621,14 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); if (p) - kfree_rcu(p, rcu); + call_rcu(&p->rcu, tcf_ife_cleanup_params); return ret; metadata_parse_err: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: + __tcf_ife_cleanup(p); kfree(p); tcf_idr_release(*a, bind); return err; @@ -679,7 +675,7 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, if (nla_put(skb, TCA_IFE_TYPE, 2, &p->eth_type)) goto nla_put_failure; - if (dump_metalist(skb, ife)) { + if (dump_metalist(skb, p)) { /*ignore failure to dump metalist */ pr_info("Failed to dump metalist\n"); } @@ -693,13 +689,13 @@ nla_put_failure: return -1; } -static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, +static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_params *p, u16 metaid, u16 mlen, void *mdata) { struct tcf_meta_info *e; /* XXX: use hash to speed up */ - list_for_each_entry(e, &ife->metalist, metalist) { + list_for_each_entry_rcu(e, &p->metalist, metalist) { if (metaid == e->metaid) { if (e->ops) { /* We check for decode presence already */ @@ -716,10 +712,13 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, { struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; + struct tcf_ife_params *p; u8 *ifehdr_end; u8 *tlv_data; u16 metalen; + p = rcu_dereference_bh(ife->params); + bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); @@ -745,7 +744,7 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, return TC_ACT_SHOT; } - if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) { + if (find_decode_metaid(skb, p, mtype, dlen, curr_data)) { /* abuse overlimits to count when we receive metadata * but dont have an ops for it */ @@ -769,12 +768,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, /*XXX: check if we can do this at install time instead of current * send data path **/ -static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife) +static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_params *p) { - struct tcf_meta_info *e, *n; + struct tcf_meta_info *e; int tot_run_sz = 0, run_sz = 0; - list_for_each_entry_safe(e, n, &ife->metalist, metalist) { + list_for_each_entry_rcu(e, &p->metalist, metalist) { if (e->ops->check_presence) { run_sz = e->ops->check_presence(skb, e); tot_run_sz += run_sz; @@ -795,7 +794,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA where ORIGDATA = original ethernet header ... */ - u16 metalen = ife_get_sz(skb, ife); + u16 metalen = ife_get_sz(skb, p); int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN; unsigned int skboff = 0; int new_len = skb->len + hdrm; @@ -833,25 +832,21 @@ drop: if (!ife_meta) goto drop; - spin_lock(&ife->tcf_lock); - /* XXX: we dont have a clever way of telling encode to * not repeat some of the computations that are done by * ops->presence_check... */ - list_for_each_entry(e, &ife->metalist, metalist) { + list_for_each_entry_rcu(e, &p->metalist, metalist) { if (e->ops->encode) { err = e->ops->encode(skb, (void *)(ife_meta + skboff), e); } if (err < 0) { /* too corrupt to keep around if overwritten */ - spin_unlock(&ife->tcf_lock); goto drop; } skboff += err; } - spin_unlock(&ife->tcf_lock); oethh = (struct ethhdr *)skb->data; if (!is_zero_ether_addr(p->eth_src)) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 343309e9009b..4829c27446e3 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2228,6 +2228,11 @@ static bool is_qdisc_ingress(__u32 classid) return (TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS)); } +static bool is_ingress_or_clsact(struct tcf_block *block, struct Qdisc *q) +{ + return tcf_block_shared(block) || (q && !!(q->flags & TCQ_F_INGRESS)); +} + static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { @@ -2420,6 +2425,8 @@ replay: flags |= TCA_ACT_FLAGS_NO_RTNL; if (is_qdisc_ingress(parent)) flags |= TCA_ACT_FLAGS_AT_INGRESS; + if (is_ingress_or_clsact(block, q)) + flags |= TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT; err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, flags, extack); if (err == 0) { diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index a01f14b1c216..9efe23f8371b 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -391,8 +391,8 @@ static const u32 inv_sqrt_cache[REC_INV_SQRT_CACHE] = { 1239850263, 1191209601, 1147878294, 1108955788 }; -static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, - u64 target_ns, u64 rtt_est_ns); +static void cake_configure_rates(struct Qdisc *sch, u64 rate, bool rate_adjust); + /* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2) * @@ -2013,7 +2013,8 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch) u64 delay; u32 len; - if (q->config->is_shared && now - q->last_checked_active >= q->config->sync_time) { + if (q->config->is_shared && q->rate_ns && + now - q->last_checked_active >= q->config->sync_time) { struct net_device *dev = qdisc_dev(sch); struct cake_sched_data *other_priv; u64 new_rate = q->config->rate_bps; @@ -2039,12 +2040,9 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch) if (num_active_qs > 1) new_rate = div64_u64(q->config->rate_bps, num_active_qs); - /* mtu = 0 is used to only update the rate and not mess with cobalt params */ - cake_set_rate(b, new_rate, 0, 0, 0); + cake_configure_rates(sch, new_rate, true); q->last_checked_active = now; q->active_queues = num_active_qs; - q->rate_ns = b->tin_rate_ns; - q->rate_shft = b->tin_rate_shft; } begin: @@ -2361,12 +2359,10 @@ static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, b->cparams.p_dec = 1 << 20; /* 1/4096 */ } -static int cake_config_besteffort(struct Qdisc *sch) +static int cake_config_besteffort(struct Qdisc *sch, u64 rate, u32 mtu) { struct cake_sched_data *q = qdisc_priv(sch); struct cake_tin_data *b = &q->tins[0]; - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; q->tin_cnt = 1; @@ -2380,12 +2376,10 @@ static int cake_config_besteffort(struct Qdisc *sch) return 0; } -static int cake_config_precedence(struct Qdisc *sch) +static int cake_config_precedence(struct Qdisc *sch, u64 rate, u32 mtu) { /* convert high-level (user visible) parameters into internal format */ struct cake_sched_data *q = qdisc_priv(sch); - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; u32 quantum = 256; u32 i; @@ -2456,7 +2450,7 @@ static int cake_config_precedence(struct Qdisc *sch) * Total 12 traffic classes. */ -static int cake_config_diffserv8(struct Qdisc *sch) +static int cake_config_diffserv8(struct Qdisc *sch, u64 rate, u32 mtu) { /* Pruned list of traffic classes for typical applications: * @@ -2473,8 +2467,6 @@ static int cake_config_diffserv8(struct Qdisc *sch) */ struct cake_sched_data *q = qdisc_priv(sch); - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; u32 quantum = 256; u32 i; @@ -2504,7 +2496,7 @@ static int cake_config_diffserv8(struct Qdisc *sch) return 0; } -static int cake_config_diffserv4(struct Qdisc *sch) +static int cake_config_diffserv4(struct Qdisc *sch, u64 rate, u32 mtu) { /* Further pruned list of traffic classes for four-class system: * @@ -2517,8 +2509,6 @@ static int cake_config_diffserv4(struct Qdisc *sch) */ struct cake_sched_data *q = qdisc_priv(sch); - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; u32 quantum = 1024; q->tin_cnt = 4; @@ -2546,7 +2536,7 @@ static int cake_config_diffserv4(struct Qdisc *sch) return 0; } -static int cake_config_diffserv3(struct Qdisc *sch) +static int cake_config_diffserv3(struct Qdisc *sch, u64 rate, u32 mtu) { /* Simplified Diffserv structure with 3 tins. * Latency Sensitive (CS7, CS6, EF, VA, TOS4) @@ -2554,8 +2544,6 @@ static int cake_config_diffserv3(struct Qdisc *sch) * Low Priority (LE, CS1) */ struct cake_sched_data *q = qdisc_priv(sch); - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; u32 quantum = 1024; q->tin_cnt = 3; @@ -2580,32 +2568,33 @@ static int cake_config_diffserv3(struct Qdisc *sch) return 0; } -static void cake_reconfigure(struct Qdisc *sch) +static void cake_configure_rates(struct Qdisc *sch, u64 rate, bool rate_adjust) { + u32 mtu = likely(rate_adjust) ? 0 : psched_mtu(qdisc_dev(sch)); struct cake_sched_data *qd = qdisc_priv(sch); struct cake_sched_config *q = qd->config; int c, ft; switch (q->tin_mode) { case CAKE_DIFFSERV_BESTEFFORT: - ft = cake_config_besteffort(sch); + ft = cake_config_besteffort(sch, rate, mtu); break; case CAKE_DIFFSERV_PRECEDENCE: - ft = cake_config_precedence(sch); + ft = cake_config_precedence(sch, rate, mtu); break; case CAKE_DIFFSERV_DIFFSERV8: - ft = cake_config_diffserv8(sch); + ft = cake_config_diffserv8(sch, rate, mtu); break; case CAKE_DIFFSERV_DIFFSERV4: - ft = cake_config_diffserv4(sch); + ft = cake_config_diffserv4(sch, rate, mtu); break; case CAKE_DIFFSERV_DIFFSERV3: default: - ft = cake_config_diffserv3(sch); + ft = cake_config_diffserv3(sch, rate, mtu); break; } @@ -2616,6 +2605,14 @@ static void cake_reconfigure(struct Qdisc *sch) qd->rate_ns = qd->tins[ft].tin_rate_ns; qd->rate_shft = qd->tins[ft].tin_rate_shft; +} + +static void cake_reconfigure(struct Qdisc *sch) +{ + struct cake_sched_data *qd = qdisc_priv(sch); + struct cake_sched_config *q = qd->config; + + cake_configure_rates(sch, qd->config->rate_bps, false); if (q->buffer_config_limit) { qd->buffer_limit = q->buffer_config_limit; diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 306e046276d4..a4b07b661b77 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -115,12 +115,12 @@ static void ets_offload_change(struct Qdisc *sch) struct ets_sched *q = qdisc_priv(sch); struct tc_ets_qopt_offload qopt; unsigned int w_psum_prev = 0; - unsigned int q_psum = 0; - unsigned int q_sum = 0; unsigned int quantum; unsigned int w_psum; unsigned int weight; unsigned int i; + u64 q_psum = 0; + u64 q_sum = 0; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return; @@ -138,8 +138,12 @@ static void ets_offload_change(struct Qdisc *sch) for (i = 0; i < q->nbands; i++) { quantum = q->classes[i].quantum; - q_psum += quantum; - w_psum = quantum ? q_psum * 100 / q_sum : 0; + if (quantum) { + q_psum += quantum; + w_psum = div64_u64(q_psum * 100, q_sum); + } else { + w_psum = 0; + } weight = w_psum - w_psum_prev; w_psum_prev = w_psum; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 80235e85f844..05084c9af48e 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -827,6 +827,7 @@ static void fq_reset(struct Qdisc *sch) for (idx = 0; idx < FQ_BANDS; idx++) { q->band_flows[idx].new_flows.first = NULL; q->band_flows[idx].old_flows.first = NULL; + q->band_pkt_count[idx] = 0; } q->delayed = RB_ROOT; q->flows = 0; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3756a93dc63a..7eaa5b187fef 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1785,7 +1785,7 @@ restart: __skb_queue_tail(&other->sk_receive_queue, skb); spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); - other->sk_data_ready(other); + READ_ONCE(other->sk_data_ready)(other); sock_put(other); return 0; @@ -2278,7 +2278,7 @@ restart_locked: scm_stat_add(other, skb); skb_queue_tail(&other->sk_receive_queue, skb); unix_state_unlock(other); - other->sk_data_ready(other); + READ_ONCE(other->sk_data_ready)(other); sock_put(other); scm_destroy(&scm); return len; @@ -2351,7 +2351,7 @@ static int queue_oob(struct sock *sk, struct msghdr *msg, struct sock *other, sk_send_sigurg(other); unix_state_unlock(other); - other->sk_data_ready(other); + READ_ONCE(other->sk_data_ready)(other); return 0; out_unlock: @@ -2477,7 +2477,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); - other->sk_data_ready(other); + READ_ONCE(other->sk_data_ready)(other); sent += size; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 3b46bc635c43..6149f6a79897 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -167,26 +167,32 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) struct xdp_buff_xsk *pos, *tmp; struct list_head *xskb_list; u32 contd = 0; + u32 num_desc; int err; - if (frags) - contd = XDP_PKT_CONTD; - - err = __xsk_rcv_zc(xs, xskb, len, contd); - if (err) - goto err; - if (likely(!frags)) + if (likely(!frags)) { + err = __xsk_rcv_zc(xs, xskb, len, contd); + if (err) + goto err; return 0; + } + contd = XDP_PKT_CONTD; + num_desc = xdp_get_shared_info_from_buff(xdp)->nr_frags + 1; + if (xskq_prod_nb_free(xs->rx, num_desc) < num_desc) { + xs->rx_queue_full++; + err = -ENOBUFS; + goto err; + } + + __xsk_rcv_zc(xs, xskb, len, contd); xskb_list = &xskb->pool->xskb_list; list_for_each_entry_safe(pos, tmp, xskb_list, list_node) { if (list_is_singular(xskb_list)) contd = 0; len = pos->xdp.data_end - pos->xdp.data; - err = __xsk_rcv_zc(xs, pos, len, contd); - if (err) - goto err; - list_del(&pos->list_node); + __xsk_rcv_zc(xs, pos, len, contd); + list_del_init(&pos->list_node); } return 0; diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs index f93f24a60bdd..a1edf7491579 100644 --- a/rust/kernel/kunit.rs +++ b/rust/kernel/kunit.rs @@ -14,6 +14,10 @@ use crate::prelude::*; /// Public but hidden since it should only be used from KUnit generated code. #[doc(hidden)] pub fn err(args: fmt::Arguments<'_>) { + // `args` is unused if `CONFIG_PRINTK` is not set - this avoids a build-time warning. + #[cfg(not(CONFIG_PRINTK))] + let _ = args; + // SAFETY: The format string is null-terminated and the `%pA` specifier matches the argument we // are passing. #[cfg(CONFIG_PRINTK)] @@ -30,6 +34,10 @@ pub fn err(args: fmt::Arguments<'_>) { /// Public but hidden since it should only be used from KUnit generated code. #[doc(hidden)] pub fn info(args: fmt::Arguments<'_>) { + // `args` is unused if `CONFIG_PRINTK` is not set - this avoids a build-time warning. + #[cfg(not(CONFIG_PRINTK))] + let _ = args; + // SAFETY: The format string is null-terminated and the `%pA` specifier matches the argument we // are passing. #[cfg(CONFIG_PRINTK)] diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index efdcf07c4eb6..cabcd146f3aa 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -325,8 +325,8 @@ direct_declarator: { $$ = $4; } | direct_declarator BRACKET_PHRASE { $$ = $2; } - | '(' declarator ')' - { $$ = $3; } + | '(' attribute_opt declarator ')' + { $$ = $4; } ; /* Nested declarators differ from regular declarators in that they do diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build index 2576cf7902db..f12e1ffe409e 100755 --- a/scripts/package/install-extmod-build +++ b/scripts/package/install-extmod-build @@ -32,6 +32,10 @@ mkdir -p "${destdir}" echo tools/objtool/objtool fi + if is_enabled CONFIG_DEBUG_INFO_BTF_MODULES; then + echo tools/bpf/resolve_btfids/resolve_btfids + fi + echo Module.symvers echo "arch/${SRCARCH}/include/generated" echo include/config/auto.conf diff --git a/sound/firewire/dice/dice.c b/sound/firewire/dice/dice.c index 85d265c7d544..f7a50bae4b55 100644 --- a/sound/firewire/dice/dice.c +++ b/sound/firewire/dice/dice.c @@ -122,7 +122,7 @@ static void dice_card_strings(struct snd_dice *dice) fw_csr_string(dev->config_rom + 5, CSR_VENDOR, vendor, sizeof(vendor)); strscpy(model, "?"); fw_csr_string(dice->unit->directory, CSR_MODEL, model, sizeof(model)); - snprintf(card->longname, sizeof(card->longname), + scnprintf(card->longname, sizeof(card->longname), "%s %s (serial %u) at %s, S%d", vendor, model, dev->config_rom[4] & 0x3fffff, dev_name(&dice->unit->device), 100 << dev->max_speed); diff --git a/sound/hda/codecs/ca0132.c b/sound/hda/codecs/ca0132.c index bf342a76807c..a0677d7da8e2 100644 --- a/sound/hda/codecs/ca0132.c +++ b/sound/hda/codecs/ca0132.c @@ -9816,6 +9816,15 @@ static void ca0132_config(struct hda_codec *codec) spec->dig_in = 0x09; break; } + + /* Default HP/Speaker auto-detect from headphone pin verb: enable if the + * pin config indicates presence detect (not AC_DEFCFG_MISC_NO_PRESENCE). + */ + if (spec->unsol_tag_hp && + (snd_hda_query_pin_caps(codec, spec->unsol_tag_hp) & AC_PINCAP_PRES_DETECT) && + !(get_defcfg_misc(snd_hda_codec_get_pincfg(codec, spec->unsol_tag_hp)) & + AC_DEFCFG_MISC_NO_PRESENCE)) + spec->vnode_lswitch[VNID_HP_ASEL - VNODE_START_NID] = 1; } static int ca0132_prepare_verbs(struct hda_codec *codec) diff --git a/sound/hda/codecs/hdmi/tegrahdmi.c b/sound/hda/codecs/hdmi/tegrahdmi.c index 5f6fe31aa202..ebb6410a4831 100644 --- a/sound/hda/codecs/hdmi/tegrahdmi.c +++ b/sound/hda/codecs/hdmi/tegrahdmi.c @@ -299,6 +299,7 @@ static const struct hda_device_id snd_hda_id_tegrahdmi[] = { HDA_CODEC_ID_MODEL(0x10de002f, "Tegra194 HDMI/DP2", MODEL_TEGRA), HDA_CODEC_ID_MODEL(0x10de0030, "Tegra194 HDMI/DP3", MODEL_TEGRA), HDA_CODEC_ID_MODEL(0x10de0031, "Tegra234 HDMI/DP", MODEL_TEGRA234), + HDA_CODEC_ID_MODEL(0x10de0032, "Tegra238 HDMI/DP", MODEL_TEGRA234), HDA_CODEC_ID_MODEL(0x10de0033, "SoC 33 HDMI/DP", MODEL_TEGRA234), HDA_CODEC_ID_MODEL(0x10de0034, "Tegra264 HDMI/DP", MODEL_TEGRA234), HDA_CODEC_ID_MODEL(0x10de0035, "SoC 35 HDMI/DP", MODEL_TEGRA234), diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 86bb22d19629..4c49f1195e1b 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -6904,6 +6904,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x103c, 0x88b3, "HP ENVY x360 Convertible 15-es0xxx", ALC245_FIXUP_HP_ENVY_X360_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x88d1, "HP Pavilion 15-eh1xxx (mainboard 88D1)", ALC245_FIXUP_HP_MUTE_LED_V1_COEFBIT), SND_PCI_QUIRK(0x103c, 0x88dd, "HP Pavilion 15z-ec200", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x88eb, "HP Victus 16-e0xxx", ALC245_FIXUP_HP_MUTE_LED_V2_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8902, "HP OMEN 16", ALC285_FIXUP_HP_MUTE_LED), diff --git a/sound/hda/codecs/senarytech.c b/sound/hda/codecs/senarytech.c index 3a50d4b3a064..6239a25bb8f3 100644 --- a/sound/hda/codecs/senarytech.c +++ b/sound/hda/codecs/senarytech.c @@ -19,15 +19,13 @@ #include "hda_jack.h" #include "generic.h" -/* GPIO node ID */ -#define SENARY_GPIO_NODE 0x01 - struct senary_spec { struct hda_gen_spec gen; /* extra EAPD pins */ unsigned int num_eapds; hda_nid_t eapds[4]; + bool dynamic_eapd; hda_nid_t mute_led_eapd; unsigned int parse_flags; /* flag for snd_hda_parse_pin_defcfg() */ @@ -123,19 +121,23 @@ static void senary_init_gpio_led(struct hda_codec *codec) unsigned int mask = spec->gpio_mute_led_mask | spec->gpio_mic_led_mask; if (mask) { - snd_hda_codec_write(codec, SENARY_GPIO_NODE, 0, AC_VERB_SET_GPIO_MASK, + snd_hda_codec_write(codec, codec->core.afg, 0, AC_VERB_SET_GPIO_MASK, mask); - snd_hda_codec_write(codec, SENARY_GPIO_NODE, 0, AC_VERB_SET_GPIO_DIRECTION, + snd_hda_codec_write(codec, codec->core.afg, 0, AC_VERB_SET_GPIO_DIRECTION, mask); - snd_hda_codec_write(codec, SENARY_GPIO_NODE, 0, AC_VERB_SET_GPIO_DATA, + snd_hda_codec_write(codec, codec->core.afg, 0, AC_VERB_SET_GPIO_DATA, spec->gpio_led); } } static int senary_init(struct hda_codec *codec) { + struct senary_spec *spec = codec->spec; + snd_hda_gen_init(codec); senary_init_gpio_led(codec); + if (!spec->dynamic_eapd) + senary_auto_turn_eapd(codec, spec->num_eapds, spec->eapds, true); snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_INIT); return 0; diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c index 74c3cf1e45e1..67240ce184e1 100644 --- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c +++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c @@ -60,7 +60,6 @@ struct tas2781_hda_i2c_priv { int (*save_calibration)(struct tas2781_hda *h); int hda_chip_id; - bool skip_calibration; }; static int tas2781_get_i2c_res(struct acpi_resource *ares, void *data) @@ -479,8 +478,7 @@ static void tasdevice_dspfw_init(void *context) /* If calibrated data occurs error, dsp will still works with default * calibrated data inside algo. */ - if (!hda_priv->skip_calibration) - hda_priv->save_calibration(tas_hda); + hda_priv->save_calibration(tas_hda); } static void tasdev_fw_ready(const struct firmware *fmw, void *context) @@ -535,7 +533,6 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, void *master_data) { struct tas2781_hda *tas_hda = dev_get_drvdata(dev); - struct tas2781_hda_i2c_priv *hda_priv = tas_hda->hda_priv; struct hda_component_parent *parent = master_data; struct hda_component *comp; struct hda_codec *codec; @@ -564,14 +561,6 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, break; } - /* - * Using ASUS ROG Xbox Ally X (RC73XA) UEFI calibration data - * causes audio dropouts during playback, use fallback data - * from DSP firmware as a workaround. - */ - if (codec->core.subsystem_id == 0x10431384) - hda_priv->skip_calibration = true; - guard(pm_runtime_active_auto)(dev); comp->dev = dev; @@ -643,6 +632,7 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt) */ device_name = "TIAS2781"; hda_priv->hda_chip_id = HDA_TAS2781; + tas_hda->priv->chip_id = TAS2781; hda_priv->save_calibration = tas2781_save_calibration; tas_hda->priv->global_addr = TAS2781_GLOBAL_ADDR; } else if (strstarts(dev_name(&clt->dev), "i2c-TXNW2770")) { @@ -656,6 +646,7 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt) "i2c-TXNW2781:00-tas2781-hda.0")) { device_name = "TXNW2781"; hda_priv->hda_chip_id = HDA_TAS2781; + tas_hda->priv->chip_id = TAS2781; hda_priv->save_calibration = tas2781_save_calibration; tas_hda->priv->global_addr = TAS2781_GLOBAL_ADDR; } else if (strstr(dev_name(&clt->dev), "INT8866")) { diff --git a/sound/soc/amd/acp/amd-acp63-acpi-match.c b/sound/soc/amd/acp/amd-acp63-acpi-match.c index 9b6a49c051cd..1dbbaba3c75b 100644 --- a/sound/soc/amd/acp/amd-acp63-acpi-match.c +++ b/sound/soc/amd/acp/amd-acp63-acpi-match.c @@ -30,6 +30,20 @@ static const struct snd_soc_acpi_endpoint spk_r_endpoint = { .group_id = 1 }; +static const struct snd_soc_acpi_endpoint spk_2_endpoint = { + .num = 0, + .aggregated = 1, + .group_position = 2, + .group_id = 1 +}; + +static const struct snd_soc_acpi_endpoint spk_3_endpoint = { + .num = 0, + .aggregated = 1, + .group_position = 3, + .group_id = 1 +}; + static const struct snd_soc_acpi_adr_device rt711_rt1316_group_adr[] = { { .adr = 0x000030025D071101ull, @@ -103,6 +117,345 @@ static const struct snd_soc_acpi_adr_device rt722_0_single_adr[] = { } }; +static const struct snd_soc_acpi_endpoint cs42l43_endpoints[] = { + { /* Jack Playback Endpoint */ + .num = 0, + .aggregated = 0, + .group_position = 0, + .group_id = 0, + }, + { /* DMIC Capture Endpoint */ + .num = 1, + .aggregated = 0, + .group_position = 0, + .group_id = 0, + }, + { /* Jack Capture Endpoint */ + .num = 2, + .aggregated = 0, + .group_position = 0, + .group_id = 0, + }, + { /* Speaker Playback Endpoint */ + .num = 3, + .aggregated = 0, + .group_position = 0, + .group_id = 0, + }, +}; + +static const struct snd_soc_acpi_adr_device cs35l56x4_l1u3210_adr[] = { + { + .adr = 0x00013301FA355601ull, + .num_endpoints = 1, + .endpoints = &spk_l_endpoint, + .name_prefix = "AMP1" + }, + { + .adr = 0x00013201FA355601ull, + .num_endpoints = 1, + .endpoints = &spk_r_endpoint, + .name_prefix = "AMP2" + }, + { + .adr = 0x00013101FA355601ull, + .num_endpoints = 1, + .endpoints = &spk_2_endpoint, + .name_prefix = "AMP3" + }, + { + .adr = 0x00013001FA355601ull, + .num_endpoints = 1, + .endpoints = &spk_3_endpoint, + .name_prefix = "AMP4" + }, +}; + +static const struct snd_soc_acpi_adr_device cs35l63x2_l0u01_adr[] = { + { + .adr = 0x00003001FA356301ull, + .num_endpoints = 1, + .endpoints = &spk_l_endpoint, + .name_prefix = "AMP1" + }, + { + .adr = 0x00003101FA356301ull, + .num_endpoints = 1, + .endpoints = &spk_r_endpoint, + .name_prefix = "AMP2" + }, +}; + +static const struct snd_soc_acpi_adr_device cs35l63x2_l1u01_adr[] = { + { + .adr = 0x00013001FA356301ull, + .num_endpoints = 1, + .endpoints = &spk_l_endpoint, + .name_prefix = "AMP1" + }, + { + .adr = 0x00013101FA356301ull, + .num_endpoints = 1, + .endpoints = &spk_r_endpoint, + .name_prefix = "AMP2" + }, +}; + +static const struct snd_soc_acpi_adr_device cs35l63x2_l1u13_adr[] = { + { + .adr = 0x00013101FA356301ull, + .num_endpoints = 1, + .endpoints = &spk_l_endpoint, + .name_prefix = "AMP1" + }, + { + .adr = 0x00013301FA356301ull, + .num_endpoints = 1, + .endpoints = &spk_r_endpoint, + .name_prefix = "AMP2" + }, +}; + +static const struct snd_soc_acpi_adr_device cs35l63x4_l0u0246_adr[] = { + { + .adr = 0x00003001FA356301ull, + .num_endpoints = 1, + .endpoints = &spk_l_endpoint, + .name_prefix = "AMP1" + }, + { + .adr = 0x00003201FA356301ull, + .num_endpoints = 1, + .endpoints = &spk_r_endpoint, + .name_prefix = "AMP2" + }, + { + .adr = 0x00003401FA356301ull, + .num_endpoints = 1, + .endpoints = &spk_2_endpoint, + .name_prefix = "AMP3" + }, + { + .adr = 0x00003601FA356301ull, + .num_endpoints = 1, + .endpoints = &spk_3_endpoint, + .name_prefix = "AMP4" + }, +}; + +static const struct snd_soc_acpi_adr_device cs42l43_l0u0_adr[] = { + { + .adr = 0x00003001FA424301ull, + .num_endpoints = ARRAY_SIZE(cs42l43_endpoints), + .endpoints = cs42l43_endpoints, + .name_prefix = "cs42l43" + } +}; + +static const struct snd_soc_acpi_adr_device cs42l43_l0u1_adr[] = { + { + .adr = 0x00003101FA424301ull, + .num_endpoints = ARRAY_SIZE(cs42l43_endpoints), + .endpoints = cs42l43_endpoints, + .name_prefix = "cs42l43" + } +}; + +static const struct snd_soc_acpi_adr_device cs42l43b_l0u1_adr[] = { + { + .adr = 0x00003101FA2A3B01ull, + .num_endpoints = ARRAY_SIZE(cs42l43_endpoints), + .endpoints = cs42l43_endpoints, + .name_prefix = "cs42l43" + } +}; + +static const struct snd_soc_acpi_adr_device cs42l43_l1u0_cs35l56x4_l1u0123_adr[] = { + { + .adr = 0x00013001FA424301ull, + .num_endpoints = ARRAY_SIZE(cs42l43_endpoints), + .endpoints = cs42l43_endpoints, + .name_prefix = "cs42l43" + }, + { + .adr = 0x00013001FA355601ull, + .num_endpoints = 1, + .endpoints = &spk_l_endpoint, + .name_prefix = "AMP1" + }, + { + .adr = 0x00013101FA355601ull, + .num_endpoints = 1, + .endpoints = &spk_r_endpoint, + .name_prefix = "AMP2" + }, + { + .adr = 0x00013201FA355601ull, + .num_endpoints = 1, + .endpoints = &spk_2_endpoint, + .name_prefix = "AMP3" + }, + { + .adr = 0x00013301FA355601ull, + .num_endpoints = 1, + .endpoints = &spk_3_endpoint, + .name_prefix = "AMP4" + }, +}; + +static const struct snd_soc_acpi_adr_device cs42l45_l0u0_adr[] = { + { + .adr = 0x00003001FA424501ull, + /* Re-use endpoints, but cs42l45 has no speaker */ + .num_endpoints = ARRAY_SIZE(cs42l43_endpoints) - 1, + .endpoints = cs42l43_endpoints, + .name_prefix = "cs42l45" + } +}; + +static const struct snd_soc_acpi_adr_device cs42l45_l1u0_adr[] = { + { + .adr = 0x00013001FA424501ull, + /* Re-use endpoints, but cs42l45 has no speaker */ + .num_endpoints = ARRAY_SIZE(cs42l43_endpoints) - 1, + .endpoints = cs42l43_endpoints, + .name_prefix = "cs42l45" + } +}; + +static const struct snd_soc_acpi_link_adr acp63_cs35l56x4_l1u3210[] = { + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(cs35l56x4_l1u3210_adr), + .adr_d = cs35l56x4_l1u3210_adr, + }, + {} +}; + +static const struct snd_soc_acpi_link_adr acp63_cs35l63x4_l0u0246[] = { + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(cs35l63x4_l0u0246_adr), + .adr_d = cs35l63x4_l0u0246_adr, + }, + {} +}; + +static const struct snd_soc_acpi_link_adr acp63_cs42l43_l0u1[] = { + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(cs42l43_l0u1_adr), + .adr_d = cs42l43_l0u1_adr, + }, + {} +}; + +static const struct snd_soc_acpi_link_adr acp63_cs42l43b_l0u1[] = { + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(cs42l43b_l0u1_adr), + .adr_d = cs42l43b_l0u1_adr, + }, + {} +}; + +static const struct snd_soc_acpi_link_adr acp63_cs42l43_l0u0_cs35l56x4_l1u3210[] = { + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(cs42l43_l0u0_adr), + .adr_d = cs42l43_l0u0_adr, + }, + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(cs35l56x4_l1u3210_adr), + .adr_d = cs35l56x4_l1u3210_adr, + }, + {} +}; + +static const struct snd_soc_acpi_link_adr acp63_cs42l43_l1u0_cs35l56x4_l1u0123[] = { + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(cs42l43_l1u0_cs35l56x4_l1u0123_adr), + .adr_d = cs42l43_l1u0_cs35l56x4_l1u0123_adr, + }, + {} +}; + +static const struct snd_soc_acpi_link_adr acp63_cs42l45_l0u0[] = { + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(cs42l45_l0u0_adr), + .adr_d = cs42l45_l0u0_adr, + }, + {} +}; + +static const struct snd_soc_acpi_link_adr acp63_cs42l45_l0u0_cs35l63x2_l1u01[] = { + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(cs42l45_l0u0_adr), + .adr_d = cs42l45_l0u0_adr, + }, + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(cs35l63x2_l1u01_adr), + .adr_d = cs35l63x2_l1u01_adr, + }, + {} +}; + +static const struct snd_soc_acpi_link_adr acp63_cs42l45_l0u0_cs35l63x2_l1u13[] = { + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(cs42l45_l0u0_adr), + .adr_d = cs42l45_l0u0_adr, + }, + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(cs35l63x2_l1u13_adr), + .adr_d = cs35l63x2_l1u13_adr, + }, + {} +}; + +static const struct snd_soc_acpi_link_adr acp63_cs42l45_l1u0[] = { + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(cs42l45_l1u0_adr), + .adr_d = cs42l45_l1u0_adr, + }, + {} +}; + +static const struct snd_soc_acpi_link_adr acp63_cs42l45_l1u0_cs35l63x2_l0u01[] = { + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(cs42l45_l1u0_adr), + .adr_d = cs42l45_l1u0_adr, + }, + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(cs35l63x2_l0u01_adr), + .adr_d = cs35l63x2_l0u01_adr, + }, + {} +}; + +static const struct snd_soc_acpi_link_adr acp63_cs42l45_l1u0_cs35l63x4_l0u0246[] = { + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(cs42l45_l1u0_adr), + .adr_d = cs42l45_l1u0_adr, + }, + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(cs35l63x4_l0u0246_adr), + .adr_d = cs35l63x4_l0u0246_adr, + }, + {} +}; + static const struct snd_soc_acpi_link_adr acp63_rt722_only[] = { { .mask = BIT(0), @@ -135,6 +488,66 @@ struct snd_soc_acpi_mach snd_soc_acpi_amd_acp63_sdw_machines[] = { .links = acp63_4_in_1_sdca, .drv_name = "amd_sdw", }, + { + .link_mask = BIT(0) | BIT(1), + .links = acp63_cs42l43_l0u0_cs35l56x4_l1u3210, + .drv_name = "amd_sdw", + }, + { + .link_mask = BIT(0) | BIT(1), + .links = acp63_cs42l45_l1u0_cs35l63x4_l0u0246, + .drv_name = "amd_sdw", + }, + { + .link_mask = BIT(0) | BIT(1), + .links = acp63_cs42l45_l0u0_cs35l63x2_l1u01, + .drv_name = "amd_sdw", + }, + { + .link_mask = BIT(0) | BIT(1), + .links = acp63_cs42l45_l0u0_cs35l63x2_l1u13, + .drv_name = "amd_sdw", + }, + { + .link_mask = BIT(0) | BIT(1), + .links = acp63_cs42l45_l1u0_cs35l63x2_l0u01, + .drv_name = "amd_sdw", + }, + { + .link_mask = BIT(1), + .links = acp63_cs42l43_l1u0_cs35l56x4_l1u0123, + .drv_name = "amd_sdw", + }, + { + .link_mask = BIT(1), + .links = acp63_cs35l56x4_l1u3210, + .drv_name = "amd_sdw", + }, + { + .link_mask = BIT(0), + .links = acp63_cs35l63x4_l0u0246, + .drv_name = "amd_sdw", + }, + { + .link_mask = BIT(0), + .links = acp63_cs42l43_l0u1, + .drv_name = "amd_sdw", + }, + { + .link_mask = BIT(0), + .links = acp63_cs42l43b_l0u1, + .drv_name = "amd_sdw", + }, + { + .link_mask = BIT(0), + .links = acp63_cs42l45_l0u0, + .drv_name = "amd_sdw", + }, + { + .link_mask = BIT(1), + .links = acp63_cs42l45_l1u0, + .drv_name = "amd_sdw", + }, {}, }; EXPORT_SYMBOL(snd_soc_acpi_amd_acp63_sdw_machines); diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 7af4daeb4c6f..1324543b42d7 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -710,6 +710,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "ASUS EXPERTBOOK BM1503CDA"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "PM1503CDA"), + } + }, {} }; diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c index 4707f28bfca2..af87ebae98cb 100644 --- a/sound/soc/codecs/cs35l56-shared.c +++ b/sound/soc/codecs/cs35l56-shared.c @@ -26,7 +26,7 @@ #include "cs35l56.h" -static const struct reg_sequence cs35l56_patch[] = { +static const struct reg_sequence cs35l56_asp_patch[] = { /* * Firmware can change these to non-defaults to satisfy SDCA. * Ensure that they are at known defaults. @@ -43,6 +43,20 @@ static const struct reg_sequence cs35l56_patch[] = { { CS35L56_ASP1TX2_INPUT, 0x00000000 }, { CS35L56_ASP1TX3_INPUT, 0x00000000 }, { CS35L56_ASP1TX4_INPUT, 0x00000000 }, +}; + +int cs35l56_set_asp_patch(struct cs35l56_base *cs35l56_base) +{ + return regmap_register_patch(cs35l56_base->regmap, cs35l56_asp_patch, + ARRAY_SIZE(cs35l56_asp_patch)); +} +EXPORT_SYMBOL_NS_GPL(cs35l56_set_asp_patch, "SND_SOC_CS35L56_SHARED"); + +static const struct reg_sequence cs35l56_patch[] = { + /* + * Firmware can change these to non-defaults to satisfy SDCA. + * Ensure that they are at known defaults. + */ { CS35L56_SWIRE_DP3_CH1_INPUT, 0x00000018 }, { CS35L56_SWIRE_DP3_CH2_INPUT, 0x00000019 }, { CS35L56_SWIRE_DP3_CH3_INPUT, 0x00000029 }, diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index 2ff8b172b76e..37909a319f88 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -348,6 +348,13 @@ static int cs35l56_dsp_event(struct snd_soc_dapm_widget *w, return wm_adsp_event(w, kcontrol, event); } +static int cs35l56_asp_dai_probe(struct snd_soc_dai *codec_dai) +{ + struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(codec_dai->component); + + return cs35l56_set_asp_patch(&cs35l56->base); +} + static int cs35l56_asp_dai_set_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) { struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(codec_dai->component); @@ -552,6 +559,7 @@ static int cs35l56_asp_dai_set_sysclk(struct snd_soc_dai *dai, } static const struct snd_soc_dai_ops cs35l56_ops = { + .probe = cs35l56_asp_dai_probe, .set_fmt = cs35l56_asp_dai_set_fmt, .set_tdm_slot = cs35l56_asp_dai_set_tdm_slot, .hw_params = cs35l56_asp_dai_hw_params, @@ -1617,9 +1625,9 @@ static int cs35l56_process_xu_onchip_speaker_id(struct cs35l56_private *cs35l56, if (num_pulls < 0) return num_pulls; - if (num_pulls != num_gpios) { + if (num_pulls && (num_pulls != num_gpios)) { dev_warn(cs35l56->base.dev, "%s count(%d) != %s count(%d)\n", - pull_name, num_pulls, gpio_name, num_gpios); + pull_name, num_pulls, gpio_name, num_gpios); } ret = cs35l56_check_and_save_onchip_spkid_gpios(&cs35l56->base, diff --git a/sound/soc/codecs/rt1320-sdw.c b/sound/soc/codecs/rt1320-sdw.c index 50f65662e143..8bb7e8497c72 100644 --- a/sound/soc/codecs/rt1320-sdw.c +++ b/sound/soc/codecs/rt1320-sdw.c @@ -2629,7 +2629,7 @@ static int rt1320_sdw_hw_params(struct snd_pcm_substream *substream, struct sdw_port_config port_config; struct sdw_port_config dmic_port_config[2]; struct sdw_stream_runtime *sdw_stream; - int retval; + int retval, num_channels; unsigned int sampling_rate; dev_dbg(dai->dev, "%s %s", __func__, dai->name); @@ -2661,7 +2661,8 @@ static int rt1320_sdw_hw_params(struct snd_pcm_substream *substream, dmic_port_config[1].num = 10; break; case RT1321_DEV_ID: - dmic_port_config[0].ch_mask = BIT(0) | BIT(1); + num_channels = params_channels(params); + dmic_port_config[0].ch_mask = GENMASK(num_channels - 1, 0); dmic_port_config[0].num = 8; break; default: diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c index c969eb38704e..5798d518d94c 100644 --- a/sound/soc/codecs/tas2781-fmwlib.c +++ b/sound/soc/codecs/tas2781-fmwlib.c @@ -32,6 +32,10 @@ #define TAS2781_YRAM1_PAGE 42 #define TAS2781_YRAM1_START_REG 88 +#define TAS2781_PG_REG TASDEVICE_REG(0x00, 0x00, 0x7c) +#define TAS2781_PG_1_0 0xA0 +#define TAS2781_PG_2_0 0xA8 + #define TAS2781_YRAM2_START_PAGE 43 #define TAS2781_YRAM2_END_PAGE 49 #define TAS2781_YRAM2_START_REG 8 @@ -98,6 +102,12 @@ struct blktyp_devidx_map { unsigned char dev_idx; }; +struct tas2781_cali_specific { + unsigned char sin_gni[4]; + int sin_gni_reg; + bool is_sin_gn_flush; +}; + static const char deviceNumber[TASDEVICE_DSP_TAS_MAX_DEVICE] = { 1, 2, 1, 2, 1, 1, 0, 2, 4, 3, 1, 2, 3, 4, 1, 2 }; @@ -2454,6 +2464,84 @@ static int tasdevice_load_data(struct tasdevice_priv *tas_priv, return ret; } +static int tas2781_cali_preproc(struct tasdevice_priv *priv, int i) +{ + struct tas2781_cali_specific *spec = priv->tasdevice[i].cali_specific; + struct calidata *cali_data = &priv->cali_data; + struct cali_reg *p = &cali_data->cali_reg_array; + unsigned char *data = cali_data->data; + int rc; + + /* + * On TAS2781, if the Speaker calibrated impedance is lower than + * default value hard-coded inside the TAS2781, it will cuase vol + * lower than normal. In order to fix this issue, the parameter of + * SineGainI need updating. + */ + if (spec == NULL) { + int k = i * (cali_data->cali_dat_sz_per_dev + 1); + int re_org, re_cal, corrected_sin_gn, pg_id; + unsigned char r0_deflt[4]; + + spec = devm_kzalloc(priv->dev, sizeof(*spec), GFP_KERNEL); + if (spec == NULL) + return -ENOMEM; + priv->tasdevice[i].cali_specific = spec; + rc = tasdevice_dev_bulk_read(priv, i, p->r0_reg, r0_deflt, 4); + if (rc < 0) { + dev_err(priv->dev, "invalid RE from %d = %d\n", i, rc); + return rc; + } + /* + * SineGainI need to be re-calculated, calculate the high 16 + * bits. + */ + re_org = r0_deflt[0] << 8 | r0_deflt[1]; + re_cal = data[k + 1] << 8 | data[k + 2]; + if (re_org > re_cal) { + rc = tasdevice_dev_read(priv, i, TAS2781_PG_REG, + &pg_id); + if (rc < 0) { + dev_err(priv->dev, "invalid PG id %d = %d\n", + i, rc); + return rc; + } + + spec->sin_gni_reg = (pg_id == TAS2781_PG_1_0) ? + TASDEVICE_REG(0, 0x1b, 0x34) : + TASDEVICE_REG(0, 0x18, 0x1c); + + rc = tasdevice_dev_bulk_read(priv, i, + spec->sin_gni_reg, + spec->sin_gni, 4); + if (rc < 0) { + dev_err(priv->dev, "wrong sinegaini %d = %d\n", + i, rc); + return rc; + } + corrected_sin_gn = re_org * ((spec->sin_gni[0] << 8) + + spec->sin_gni[1]); + corrected_sin_gn /= re_cal; + spec->sin_gni[0] = corrected_sin_gn >> 8; + spec->sin_gni[1] = corrected_sin_gn & 0xff; + + spec->is_sin_gn_flush = true; + } + } + + if (spec->is_sin_gn_flush) { + rc = tasdevice_dev_bulk_write(priv, i, spec->sin_gni_reg, + spec->sin_gni, 4); + if (rc < 0) { + dev_err(priv->dev, "update failed %d = %d\n", + i, rc); + return rc; + } + } + + return 0; +} + static void tasdev_load_calibrated_data(struct tasdevice_priv *priv, int i) { struct calidata *cali_data = &priv->cali_data; @@ -2469,6 +2557,12 @@ static void tasdev_load_calibrated_data(struct tasdevice_priv *priv, int i) } k++; + if (priv->chip_id == TAS2781) { + rc = tas2781_cali_preproc(priv, i); + if (rc < 0) + return; + } + rc = tasdevice_dev_bulk_write(priv, i, p->r0_reg, &(data[k]), 4); if (rc < 0) { dev_err(priv->dev, "chn %d r0_reg bulk_wr err = %d\n", i, rc); diff --git a/sound/soc/fsl/fsl_easrc.c b/sound/soc/fsl/fsl_easrc.c index e64a0d97afd0..6c56134c60cc 100644 --- a/sound/soc/fsl/fsl_easrc.c +++ b/sound/soc/fsl/fsl_easrc.c @@ -52,10 +52,13 @@ static int fsl_easrc_iec958_put_bits(struct snd_kcontrol *kcontrol, struct soc_mreg_control *mc = (struct soc_mreg_control *)kcontrol->private_value; unsigned int regval = ucontrol->value.integer.value[0]; + int ret; + + ret = (easrc_priv->bps_iec958[mc->regbase] != regval); easrc_priv->bps_iec958[mc->regbase] = regval; - return 0; + return ret; } static int fsl_easrc_iec958_get_bits(struct snd_kcontrol *kcontrol, @@ -93,14 +96,17 @@ static int fsl_easrc_set_reg(struct snd_kcontrol *kcontrol, struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); struct soc_mreg_control *mc = (struct soc_mreg_control *)kcontrol->private_value; + struct fsl_asrc *easrc = snd_soc_component_get_drvdata(component); unsigned int regval = ucontrol->value.integer.value[0]; + bool changed; int ret; - ret = snd_soc_component_write(component, mc->regbase, regval); - if (ret < 0) + ret = regmap_update_bits_check(easrc->regmap, mc->regbase, + GENMASK(31, 0), regval, &changed); + if (ret != 0) return ret; - return 0; + return changed; } #define SOC_SINGLE_REG_RW(xname, xreg) \ diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index f230991f5f8e..c18ec607e029 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -763,6 +763,14 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { }, .driver_data = (void *)(SOC_SDW_CODEC_SPKR), }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0CCD") + }, + .driver_data = (void *)(SOC_SDW_CODEC_SPKR), + }, /* Pantherlake devices*/ { .callback = sof_sdw_quirk_cb, diff --git a/sound/soc/sdca/sdca_functions.c b/sound/soc/sdca/sdca_functions.c index 95b67bb904c3..e0ed593697ba 100644 --- a/sound/soc/sdca/sdca_functions.c +++ b/sound/soc/sdca/sdca_functions.c @@ -1156,9 +1156,12 @@ static int find_sdca_entity_iot(struct device *dev, if (!terminal->is_dataport) { const char *type_name = sdca_find_terminal_name(terminal->type); - if (type_name) + if (type_name) { entity->label = devm_kasprintf(dev, GFP_KERNEL, "%s %s", entity->label, type_name); + if (!entity->label) + return -ENOMEM; + } } ret = fwnode_property_read_u32(entity_node, diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index c6a78efbcaa3..d54a1a44a69b 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2219,6 +2219,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_ALIGN_TRANSFER), DEVICE_FLG(0x05e1, 0x0480, /* Hauppauge Woodbury */ QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER), + DEVICE_FLG(0x0624, 0x3d3f, /* AB13X USB Audio */ + QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY), DEVICE_FLG(0x0644, 0x8043, /* TEAC UD-501/UD-501V2/UD-503/NT-503 */ QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY | QUIRK_FLAG_IFACE_DELAY), diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c index 011ea96e9779..f00b53346abd 100644 --- a/sound/usb/usx2y/us122l.c +++ b/sound/usb/usx2y/us122l.c @@ -520,8 +520,6 @@ static int us122l_usb_probe(struct usb_interface *intf, return err; } - usb_get_intf(usb_ifnum_to_if(device, 0)); - usb_get_dev(device); *cardp = card; return 0; } @@ -542,11 +540,9 @@ static int snd_us122l_probe(struct usb_interface *intf, if (intf->cur_altsetting->desc.bInterfaceNumber != 1) return 0; - err = us122l_usb_probe(usb_get_intf(intf), id, &card); - if (err < 0) { - usb_put_intf(intf); + err = us122l_usb_probe(intf, id, &card); + if (err < 0) return err; - } usb_set_intfdata(intf, card); return 0; @@ -574,10 +570,6 @@ static void snd_us122l_disconnect(struct usb_interface *intf) snd_usbmidi_disconnect(p); } - usb_put_intf(usb_ifnum_to_if(us122l->dev, 0)); - usb_put_intf(usb_ifnum_to_if(us122l->dev, 1)); - usb_put_dev(us122l->dev); - snd_card_free_when_closed(card); } diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index ef083602b73a..7672208f65e4 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -23,6 +23,7 @@ RM ?= rm HOSTCC ?= gcc HOSTLD ?= ld HOSTAR ?= ar +HOSTPKG_CONFIG ?= pkg-config CROSS_COMPILE = OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/ @@ -63,10 +64,14 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OU $(abspath $@) install_headers LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null) + +ifneq ($(filter -static,$(EXTRA_LDFLAGS)),) +LIBELF_LIBS := $(shell $(HOSTPKG_CONFIG) libelf --libs --static 2>/dev/null || echo -lelf -lzstd) +else LIBELF_LIBS := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf) +endif ZLIB_LIBS := $(shell $(HOSTPKG_CONFIG) zlib --libs 2>/dev/null || echo -lz) -ZSTD_LIBS := $(shell $(HOSTPKG_CONFIG) libzstd --libs 2>/dev/null || echo -lzstd) HOSTCFLAGS_resolve_btfids += -g \ -I$(srctree)/tools/include \ @@ -76,7 +81,7 @@ HOSTCFLAGS_resolve_btfids += -g \ $(LIBELF_FLAGS) \ -Wall -Werror -LIBS = $(LIBELF_LIBS) $(ZLIB_LIBS) $(ZSTD_LIBS) +LIBS = $(LIBELF_LIBS) $(ZLIB_LIBS) export srctree OUTPUT HOSTCFLAGS_resolve_btfids Q HOSTCC HOSTLD HOSTAR include $(srctree)/tools/build/Makefile.include diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index 6964175abdfd..76bcd4e85de3 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -142,13 +142,15 @@ $(LIBSUBCMD)-clean: $(Q)$(RM) -r -- $(LIBSUBCMD_OUTPUT) clean: $(LIBSUBCMD)-clean - $(call QUIET_CLEAN, objtool) $(RM) $(OBJTOOL) - $(Q)find $(OUTPUT) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete + $(Q)find $(OUTPUT) \( -name '*.o' -o -name '\.*.cmd' -o -name '\.*.d' \) -type f -print | xargs $(RM) $(Q)$(RM) $(OUTPUT)arch/x86/lib/cpu-feature-names.c $(OUTPUT)fixdep $(Q)$(RM) $(OUTPUT)arch/x86/lib/inat-tables.c $(OUTPUT)fixdep $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.objtool $(Q)$(RM) -r -- $(OUTPUT)feature +mrproper: clean + $(call QUIET_CLEAN, objtool) $(RM) $(OBJTOOL) + FORCE: -.PHONY: clean FORCE +.PHONY: clean mrproper FORCE diff --git a/tools/sched_ext/Kconfig b/tools/sched_ext/Kconfig new file mode 100644 index 000000000000..275bd97ae62b --- /dev/null +++ b/tools/sched_ext/Kconfig @@ -0,0 +1,61 @@ +# sched-ext mandatory options +# +CONFIG_BPF=y +CONFIG_BPF_SYSCALL=y +CONFIG_BPF_JIT=y +CONFIG_DEBUG_INFO_BTF=y +CONFIG_BPF_JIT_ALWAYS_ON=y +CONFIG_BPF_JIT_DEFAULT_ON=y +CONFIG_SCHED_CLASS_EXT=y + +# Required by some rust schedulers (e.g. scx_p2dq) +# +CONFIG_KALLSYMS_ALL=y + +# Required on arm64 +# +# CONFIG_DEBUG_INFO_REDUCED is not set + +# LAVD tracks futex to give an additional time slice for futex holder +# (i.e., avoiding lock holder preemption) for better system-wide progress. +# LAVD first tries to use ftrace to trace futex function calls. +# If that is not available, it tries to use a tracepoint. +CONFIG_FUNCTION_TRACER=y + +# Enable scheduling debugging +# +CONFIG_SCHED_DEBUG=y + +# Enable extra scheduling features (for a better code coverage while testing +# the schedulers) +# +CONFIG_SCHED_AUTOGROUP=y +CONFIG_SCHED_CORE=y +CONFIG_SCHED_MC=y + +# Enable fully preemptible kernel for a better test coverage of the schedulers +# +# CONFIG_PREEMPT_NONE is not set +# CONFIG_PREEMPT_VOLUNTARY is not set +CONFIG_PREEMPT=y +CONFIG_PREEMPT_DYNAMIC=y + +# Additional debugging information (useful to catch potential locking issues) +CONFIG_DEBUG_LOCKDEP=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_PROVE_LOCKING=y + +# Bpftrace headers (for additional debug info) +CONFIG_BPF_EVENTS=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_DYNAMIC_FTRACE=y +CONFIG_KPROBES=y +CONFIG_KPROBE_EVENTS=y +CONFIG_UPROBES=y +CONFIG_UPROBE_EVENTS=y +CONFIG_DEBUG_FS=y + +# Enable access to kernel configuration and headers at runtime +CONFIG_IKHEADERS=y +CONFIG_IKCONFIG_PROC=y +CONFIG_IKCONFIG=y diff --git a/tools/sched_ext/Makefile b/tools/sched_ext/Makefile index 47ad7444677e..21554f089692 100644 --- a/tools/sched_ext/Makefile +++ b/tools/sched_ext/Makefile @@ -122,6 +122,8 @@ BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) \ -I../../include \ $(call get_sys_includes,$(CLANG)) \ -Wall -Wno-compare-distinct-pointer-types \ + -Wno-microsoft-anon-tag \ + -fms-extensions \ -O2 -mcpu=v3 # sort removes libbpf duplicates when not cross-building diff --git a/tools/sched_ext/README.md b/tools/sched_ext/README.md index 56a9d1557ac4..6e282bce453c 100644 --- a/tools/sched_ext/README.md +++ b/tools/sched_ext/README.md @@ -58,14 +58,8 @@ CONFIG_SCHED_CLASS_EXT=y CONFIG_BPF_SYSCALL=y CONFIG_BPF_JIT=y CONFIG_DEBUG_INFO_BTF=y -``` - -It's also recommended that you also include the following Kconfig options: - -``` CONFIG_BPF_JIT_ALWAYS_ON=y CONFIG_BPF_JIT_DEFAULT_ON=y -CONFIG_PAHOLE_HAS_BTF_TAG=y ``` There is a `Kconfig` file in this directory whose contents you can append to diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h index 8b4897fc8b99..edccc99c7294 100644 --- a/tools/sched_ext/include/scx/compat.h +++ b/tools/sched_ext/include/scx/compat.h @@ -125,6 +125,7 @@ static inline long scx_hotplug_seq(void) { int fd; char buf[32]; + char *endptr; ssize_t len; long val; @@ -137,8 +138,10 @@ static inline long scx_hotplug_seq(void) buf[len] = 0; close(fd); - val = strtoul(buf, NULL, 10); - SCX_BUG_ON(val < 0, "invalid num hotplug events: %lu", val); + errno = 0; + val = strtoul(buf, &endptr, 10); + SCX_BUG_ON(errno == ERANGE || endptr == buf || + (*endptr != '\n' && *endptr != '\0'), "invalid num hotplug events: %ld", val); return val; } diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c index 2a805f1d6c8f..710fa03376e2 100644 --- a/tools/sched_ext/scx_central.c +++ b/tools/sched_ext/scx_central.c @@ -66,7 +66,7 @@ restart: assert(skel->rodata->nr_cpu_ids > 0); assert(skel->rodata->nr_cpu_ids <= INT32_MAX); - while ((opt = getopt(argc, argv, "s:c:pvh")) != -1) { + while ((opt = getopt(argc, argv, "s:c:vh")) != -1) { switch (opt) { case 's': skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000; diff --git a/tools/sched_ext/scx_sdt.c b/tools/sched_ext/scx_sdt.c index d8ca9aa316a5..a36405d8df30 100644 --- a/tools/sched_ext/scx_sdt.c +++ b/tools/sched_ext/scx_sdt.c @@ -54,7 +54,7 @@ restart: optind = 1; skel = SCX_OPS_OPEN(sdt_ops, scx_sdt); - while ((opt = getopt(argc, argv, "fvh")) != -1) { + while ((opt = getopt(argc, argv, "vh")) != -1) { switch (opt) { case 'v': verbose = true; diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 260d8d9aa1db..2998e1bc088b 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -346,8 +346,10 @@ class LinuxSourceTree: return self.validate_config(build_dir) def run_kernel(self, args: Optional[List[str]]=None, build_dir: str='', filter_glob: str='', filter: str='', filter_action: Optional[str]=None, timeout: Optional[int]=None) -> Iterator[str]: - if not args: - args = [] + # Copy to avoid mutating the caller-supplied list. exec_tests() reuses + # the same args across repeated run_kernel() calls (e.g. --run_isolated), + # so appending to the original would accumulate stale flags on each call. + args = list(args) if args else [] if filter_glob: args.append('kunit.filter_glob=' + filter_glob) if filter: diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index b67408147c1f..f6383884c599 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -503,6 +503,32 @@ class LinuxSourceTreeTest(unittest.TestCase): with open(kunit_kernel.get_outfile_path(build_dir), 'rt') as outfile: self.assertEqual(outfile.read(), 'hi\nbye\n', msg='Missing some output') + def test_run_kernel_args_not_mutated(self): + """Verify run_kernel() copies args so callers can reuse them.""" + start_calls = [] + + def fake_start(start_args, unused_build_dir): + start_calls.append(list(start_args)) + return subprocess.Popen(['printf', 'KTAP version 1\n'], + text=True, stdout=subprocess.PIPE) + + with tempfile.TemporaryDirectory('') as build_dir: + tree = kunit_kernel.LinuxSourceTree(build_dir, + kunitconfig_paths=[os.devnull]) + with mock.patch.object(tree._ops, 'start', side_effect=fake_start), \ + mock.patch.object(kunit_kernel.subprocess, 'call'): + kernel_args = ['mem=1G'] + for _ in tree.run_kernel(args=kernel_args, build_dir=build_dir, + filter_glob='suite.test1'): + pass + for _ in tree.run_kernel(args=kernel_args, build_dir=build_dir, + filter_glob='suite.test2'): + pass + self.assertEqual(kernel_args, ['mem=1G'], + 'run_kernel() should not modify caller args') + self.assertIn('kunit.filter_glob=suite.test1', start_calls[0]) + self.assertIn('kunit.filter_glob=suite.test2', start_calls[1]) + def test_build_reconfig_no_config(self): with tempfile.TemporaryDirectory('') as build_dir: with open(kunit_kernel.get_kunitconfig_path(build_dir), 'w') as f: diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index 9d2df1f3e6bb..c2661a312fc9 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -475,8 +475,8 @@ static void sve2_sigill(void) static void sve2p1_sigill(void) { - /* BFADD Z0.H, Z0.H, Z0.H */ - asm volatile(".inst 0x65000000" : : : "z0"); + /* LD1Q {Z0.Q}, P0/Z, [Z0.D, X0] */ + asm volatile(".inst 0xC400A000" : : : "z0"); } static void sve2p2_sigill(void) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 72a9ba41f95e..d5acbeba0383 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -409,6 +409,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids \ CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" \ LIBBPF_INCLUDE=$(HOST_INCLUDE_DIR) \ EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)' \ + HOSTPKG_CONFIG=$(PKG_CONFIG) \ OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ) # Get Clang's default includes on this system, as opposed to those seen by diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c index 0322f817d07b..cb8dd2f63296 100644 --- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c +++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c @@ -422,15 +422,69 @@ static bool is_valid_range(enum num_t t, struct range x) } } -static struct range range_improve(enum num_t t, struct range old, struct range new) +static struct range range_intersection(enum num_t t, struct range old, struct range new) { return range(t, max_t(t, old.a, new.a), min_t(t, old.b, new.b)); } +/* + * Result is precise when 'x' and 'y' overlap or form a continuous range, + * result is an over-approximation if 'x' and 'y' do not overlap. + */ +static struct range range_union(enum num_t t, struct range x, struct range y) +{ + if (!is_valid_range(t, x)) + return y; + if (!is_valid_range(t, y)) + return x; + return range(t, min_t(t, x.a, y.a), max_t(t, x.b, y.b)); +} + +/* + * This function attempts to improve x range intersecting it with y. + * range_cast(... to_t ...) looses precision for ranges that pass to_t + * min/max boundaries. To avoid such precision loses this function + * splits both x and y into halves corresponding to non-overflowing + * sub-ranges: [0, smin] and [smax, -1]. + * Final result is computed as follows: + * + * ((x ∩ [0, smax]) ∩ (y ∩ [0, smax])) ∪ + * ((x ∩ [smin,-1]) ∩ (y ∩ [smin,-1])) + * + * Precision might still be lost if final union is not a continuous range. + */ +static struct range range_refine_in_halves(enum num_t x_t, struct range x, + enum num_t y_t, struct range y) +{ + struct range x_pos, x_neg, y_pos, y_neg, r_pos, r_neg; + u64 smax, smin, neg_one; + + if (t_is_32(x_t)) { + smax = (u64)(u32)S32_MAX; + smin = (u64)(u32)S32_MIN; + neg_one = (u64)(u32)(s32)(-1); + } else { + smax = (u64)S64_MAX; + smin = (u64)S64_MIN; + neg_one = U64_MAX; + } + x_pos = range_intersection(x_t, x, range(x_t, 0, smax)); + x_neg = range_intersection(x_t, x, range(x_t, smin, neg_one)); + y_pos = range_intersection(y_t, y, range(x_t, 0, smax)); + y_neg = range_intersection(y_t, y, range(y_t, smin, neg_one)); + r_pos = range_intersection(x_t, x_pos, range_cast(y_t, x_t, y_pos)); + r_neg = range_intersection(x_t, x_neg, range_cast(y_t, x_t, y_neg)); + return range_union(x_t, r_pos, r_neg); + +} + static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t, struct range y) { struct range y_cast; + if (t_is_32(x_t) == t_is_32(y_t)) + x = range_refine_in_halves(x_t, x, y_t, y); + y_cast = range_cast(y_t, x_t, y); /* If we know that @@ -444,7 +498,7 @@ static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t, */ if (x_t == S64 && y_t == S32 && y_cast.a <= S32_MAX && y_cast.b <= S32_MAX && (s64)x.a >= S32_MIN && (s64)x.b <= S32_MAX) - return range_improve(x_t, x, y_cast); + return range_intersection(x_t, x, y_cast); /* the case when new range knowledge, *y*, is a 32-bit subregister * range, while previous range knowledge, *x*, is a full register @@ -462,25 +516,11 @@ static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t, x_swap = range(x_t, swap_low32(x.a, y_cast.a), swap_low32(x.b, y_cast.b)); if (!is_valid_range(x_t, x_swap)) return x; - return range_improve(x_t, x, x_swap); - } - - if (!t_is_32(x_t) && !t_is_32(y_t) && x_t != y_t) { - if (x_t == S64 && x.a > x.b) { - if (x.b < y.a && x.a <= y.b) - return range(x_t, x.a, y.b); - if (x.a > y.b && x.b >= y.a) - return range(x_t, y.a, x.b); - } else if (x_t == U64 && y.a > y.b) { - if (y.b < x.a && y.a <= x.b) - return range(x_t, y.a, x.b); - if (y.a > x.b && y.b >= x.a) - return range(x_t, x.a, y.b); - } + return range_intersection(x_t, x, x_swap); } /* otherwise, plain range cast and intersection works */ - return range_improve(x_t, x, y_cast); + return range_intersection(x_t, x, y_cast); } /* ======================= diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c index fb952703653e..e8ea26464349 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c @@ -610,6 +610,61 @@ out: system("ip link del bond"); } +/* + * Test that changing xmit_hash_policy to vlan+srcmac is rejected when a + * native XDP program is loaded on a bond in 802.3ad or balance-xor mode. + * These modes support XDP only when xmit_hash_policy != vlan+srcmac; freely + * changing the policy creates an inconsistency that triggers a WARNING in + * dev_xdp_uninstall() during device teardown. + */ +static void test_xdp_bonding_xmit_policy_compat(struct skeletons *skeletons) +{ + struct nstoken *nstoken = NULL; + int bond_ifindex = -1; + int xdp_fd, err; + + SYS(out, "ip netns add ns_xmit_policy"); + nstoken = open_netns("ns_xmit_policy"); + if (!ASSERT_OK_PTR(nstoken, "open ns_xmit_policy")) + goto out; + + /* 802.3ad with layer2+3 policy: native XDP is supported */ + SYS(out, "ip link add bond0 type bond mode 802.3ad xmit_hash_policy layer2+3"); + SYS(out, "ip link add veth0 type veth peer name veth0p"); + SYS(out, "ip link set veth0 master bond0"); + SYS(out, "ip link set bond0 up"); + + bond_ifindex = if_nametoindex("bond0"); + if (!ASSERT_GT(bond_ifindex, 0, "bond0 ifindex")) + goto out; + + xdp_fd = bpf_program__fd(skeletons->xdp_dummy->progs.xdp_dummy_prog); + if (!ASSERT_GE(xdp_fd, 0, "xdp_dummy fd")) + goto out; + + err = bpf_xdp_attach(bond_ifindex, xdp_fd, XDP_FLAGS_DRV_MODE, NULL); + if (!ASSERT_OK(err, "attach XDP to bond0")) + goto out; + + /* With XDP loaded, switching to vlan+srcmac must be rejected */ + err = system("ip link set bond0 type bond xmit_hash_policy vlan+srcmac 2>/dev/null"); + ASSERT_NEQ(err, 0, "vlan+srcmac change with XDP loaded should fail"); + + /* Detach XDP first, then the same change must succeed */ + ASSERT_OK(bpf_xdp_detach(bond_ifindex, XDP_FLAGS_DRV_MODE, NULL), + "detach XDP from bond0"); + + bond_ifindex = -1; + err = system("ip link set bond0 type bond xmit_hash_policy vlan+srcmac 2>/dev/null"); + ASSERT_OK(err, "vlan+srcmac change without XDP should succeed"); + +out: + if (bond_ifindex > 0) + bpf_xdp_detach(bond_ifindex, XDP_FLAGS_DRV_MODE, NULL); + close_netns(nstoken); + SYS_NOFAIL("ip netns del ns_xmit_policy"); +} + static int libbpf_debug_print(enum libbpf_print_level level, const char *format, va_list args) { @@ -677,6 +732,9 @@ void serial_test_xdp_bonding(void) test_case->xmit_policy); } + if (test__start_subtest("xdp_bonding_xmit_policy_compat")) + test_xdp_bonding_xmit_policy_compat(&skeletons); + if (test__start_subtest("xdp_bonding_redirect_multi")) test_xdp_bonding_redirect_multi(&skeletons); diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c index a01c2736890f..858af5988a38 100644 --- a/tools/testing/selftests/bpf/progs/exceptions_assert.c +++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c @@ -18,43 +18,43 @@ return *(u64 *)num; \ } -__msg(": R0=0xffffffff80000000") +__msg("R{{.}}=0xffffffff80000000") check_assert(s64, ==, eq_int_min, INT_MIN); -__msg(": R0=0x7fffffff") +__msg("R{{.}}=0x7fffffff") check_assert(s64, ==, eq_int_max, INT_MAX); -__msg(": R0=0") +__msg("R{{.}}=0") check_assert(s64, ==, eq_zero, 0); -__msg(": R0=0x8000000000000000 R1=0x8000000000000000") +__msg("R{{.}}=0x8000000000000000") check_assert(s64, ==, eq_llong_min, LLONG_MIN); -__msg(": R0=0x7fffffffffffffff R1=0x7fffffffffffffff") +__msg("R{{.}}=0x7fffffffffffffff") check_assert(s64, ==, eq_llong_max, LLONG_MAX); -__msg(": R0=scalar(id=1,smax=0x7ffffffe)") +__msg("R{{.}}=scalar(id=1,smax=0x7ffffffe)") check_assert(s64, <, lt_pos, INT_MAX); -__msg(": R0=scalar(id=1,smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))") +__msg("R{{.}}=scalar(id=1,smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))") check_assert(s64, <, lt_zero, 0); -__msg(": R0=scalar(id=1,smax=0xffffffff7fffffff") +__msg("R{{.}}=scalar(id=1,smax=0xffffffff7fffffff") check_assert(s64, <, lt_neg, INT_MIN); -__msg(": R0=scalar(id=1,smax=0x7fffffff)") +__msg("R{{.}}=scalar(id=1,smax=0x7fffffff)") check_assert(s64, <=, le_pos, INT_MAX); -__msg(": R0=scalar(id=1,smax=0)") +__msg("R{{.}}=scalar(id=1,smax=0)") check_assert(s64, <=, le_zero, 0); -__msg(": R0=scalar(id=1,smax=0xffffffff80000000") +__msg("R{{.}}=scalar(id=1,smax=0xffffffff80000000") check_assert(s64, <=, le_neg, INT_MIN); -__msg(": R0=scalar(id=1,smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") +__msg("R{{.}}=scalar(id=1,smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, >, gt_pos, INT_MAX); -__msg(": R0=scalar(id=1,smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") +__msg("R{{.}}=scalar(id=1,smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, >, gt_zero, 0); -__msg(": R0=scalar(id=1,smin=0xffffffff80000001") +__msg("R{{.}}=scalar(id=1,smin=0xffffffff80000001") check_assert(s64, >, gt_neg, INT_MIN); -__msg(": R0=scalar(id=1,smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") +__msg("R{{.}}=scalar(id=1,smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, >=, ge_pos, INT_MAX); -__msg(": R0=scalar(id=1,smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") +__msg("R{{.}}=scalar(id=1,smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, >=, ge_zero, 0); -__msg(": R0=scalar(id=1,smin=0xffffffff80000000") +__msg("R{{.}}=scalar(id=1,smin=0xffffffff80000000") check_assert(s64, >=, ge_neg, INT_MIN); SEC("?tc") diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c index 97065a26cf70..e526315c718a 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bounds.c +++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c @@ -1148,7 +1148,7 @@ l0_%=: r0 = 0; \ SEC("xdp") __description("bound check with JMP32_JSLT for crossing 32-bit signed boundary") __success __retval(0) -__flag(!BPF_F_TEST_REG_INVARIANTS) /* known invariants violation */ +__flag(BPF_F_TEST_REG_INVARIANTS) __naked void crossing_32_bit_signed_boundary_2(void) { asm volatile (" \ @@ -2000,4 +2000,41 @@ __naked void bounds_refinement_multiple_overlaps(void *ctx) : __clobber_all); } +SEC("socket") +__success +__flag(BPF_F_TEST_REG_INVARIANTS) +__naked void signed_unsigned_intersection32_case1(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + w0 &= 0xffffffff; \ + if w0 < 0x3 goto 1f; /* on fall-through u32 range [3..U32_MAX] */ \ + if w0 s> 0x1 goto 1f; /* on fall-through s32 range [S32_MIN..1] */ \ + if w0 s< 0x0 goto 1f; /* range can be narrowed to [S32_MIN..-1] */ \ + r10 = 0; /* thus predicting the jump. */ \ +1: exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__success +__flag(BPF_F_TEST_REG_INVARIANTS) +__naked void signed_unsigned_intersection32_case2(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + w0 &= 0xffffffff; \ + if w0 > 0x80000003 goto 1f; /* on fall-through u32 range [0..S32_MIN+3] */ \ + if w0 s< -3 goto 1f; /* on fall-through s32 range [-3..S32_MAX] */ \ + if w0 s> 5 goto 1f; /* on fall-through s32 range [-3..5] */ \ + if w0 <= 5 goto 1f; /* range can be narrowed to [0..5] */ \ + r10 = 0; /* thus predicting the jump */ \ +1: exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c index 2ef346c827c2..7bf7dbfd237d 100644 --- a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c +++ b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c @@ -363,4 +363,68 @@ void alu32_negative_offset(void) __sink(path[0]); } +void dummy_calls(void) +{ + bpf_iter_num_new(0, 0, 0); + bpf_iter_num_next(0); + bpf_iter_num_destroy(0); +} + +SEC("socket") +__success +__flag(BPF_F_TEST_STATE_FREQ) +int spurious_precision_marks(void *ctx) +{ + struct bpf_iter_num iter; + + asm volatile( + "r1 = %[iter];" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "1:" + "r1 = %[iter];" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto 4f;" + "r7 = *(u32 *)(r0 + 0);" + "r8 = *(u32 *)(r0 + 0);" + /* This jump can't be predicted and does not change r7 or r8 state. */ + "if r7 > r8 goto 2f;" + /* Branch explored first ties r2 and r7 as having the same id. */ + "r2 = r7;" + "goto 3f;" + "2:" + /* Branch explored second does not tie r2 and r7 but has a function call. */ + "call %[bpf_get_prandom_u32];" + "3:" + /* + * A checkpoint. + * When first branch is explored, this would inject linked registers + * r2 and r7 into the jump history. + * When second branch is explored, this would be a cache hit point, + * triggering propagate_precision(). + */ + "if r7 <= 42 goto +0;" + /* + * Mark r7 as precise using an if condition that is always true. + * When reached via the second branch, this triggered a bug in the backtrack_insn() + * because r2 (tied to r7) was propagated as precise to a call. + */ + "if r7 <= 0xffffFFFF goto +0;" + "goto 1b;" + "4:" + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + : + : __imm_ptr(iter), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy), + __imm(bpf_get_prandom_u32) + : __clobber_common, "r7", "r8" + ); + + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c index 3072fee9a448..58c7704d61cd 100644 --- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c +++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c @@ -40,6 +40,9 @@ __naked void linked_regs_bpf_k(void) */ "r3 = r10;" "r3 += r0;" + /* Mark r1 and r2 as alive. */ + "r1 = r1;" + "r2 = r2;" "r0 = 0;" "exit;" : @@ -73,6 +76,9 @@ __naked void linked_regs_bpf_x_src(void) */ "r4 = r10;" "r4 += r0;" + /* Mark r1 and r2 as alive. */ + "r1 = r1;" + "r2 = r2;" "r0 = 0;" "exit;" : @@ -106,6 +112,10 @@ __naked void linked_regs_bpf_x_dst(void) */ "r4 = r10;" "r4 += r3;" + /* Mark r1 and r2 as alive. */ + "r0 = r0;" + "r1 = r1;" + "r2 = r2;" "r0 = 0;" "exit;" : @@ -143,6 +153,9 @@ __naked void linked_regs_broken_link(void) */ "r3 = r10;" "r3 += r0;" + /* Mark r1 and r2 as alive. */ + "r1 = r1;" + "r2 = r2;" "r0 = 0;" "exit;" : @@ -156,16 +169,16 @@ __naked void linked_regs_broken_link(void) */ SEC("socket") __success __log_level(2) -__msg("12: (0f) r2 += r1") +__msg("17: (0f) r2 += r1") /* Current state */ -__msg("frame2: last_idx 12 first_idx 11 subseq_idx -1 ") -__msg("frame2: regs=r1 stack= before 11: (bf) r2 = r10") +__msg("frame2: last_idx 17 first_idx 14 subseq_idx -1 ") +__msg("frame2: regs=r1 stack= before 16: (bf) r2 = r10") __msg("frame2: parent state regs=r1 stack=") __msg("frame1: parent state regs= stack=") __msg("frame0: parent state regs= stack=") /* Parent state */ -__msg("frame2: last_idx 10 first_idx 10 subseq_idx 11 ") -__msg("frame2: regs=r1 stack= before 10: (25) if r1 > 0x7 goto pc+0") +__msg("frame2: last_idx 13 first_idx 13 subseq_idx 14 ") +__msg("frame2: regs=r1 stack= before 13: (25) if r1 > 0x7 goto pc+0") __msg("frame2: parent state regs=r1 stack=") /* frame1.r{6,7} are marked because mark_precise_scalar_ids() * looks for all registers with frame2.r1.id in the current state @@ -173,20 +186,20 @@ __msg("frame2: parent state regs=r1 stack=") __msg("frame1: parent state regs=r6,r7 stack=") __msg("frame0: parent state regs=r6 stack=") /* Parent state */ -__msg("frame2: last_idx 8 first_idx 8 subseq_idx 10") -__msg("frame2: regs=r1 stack= before 8: (85) call pc+1") +__msg("frame2: last_idx 9 first_idx 9 subseq_idx 13") +__msg("frame2: regs=r1 stack= before 9: (85) call pc+3") /* frame1.r1 is marked because of backtracking of call instruction */ __msg("frame1: parent state regs=r1,r6,r7 stack=") __msg("frame0: parent state regs=r6 stack=") /* Parent state */ -__msg("frame1: last_idx 7 first_idx 6 subseq_idx 8") -__msg("frame1: regs=r1,r6,r7 stack= before 7: (bf) r7 = r1") -__msg("frame1: regs=r1,r6 stack= before 6: (bf) r6 = r1") +__msg("frame1: last_idx 8 first_idx 7 subseq_idx 9") +__msg("frame1: regs=r1,r6,r7 stack= before 8: (bf) r7 = r1") +__msg("frame1: regs=r1,r6 stack= before 7: (bf) r6 = r1") __msg("frame1: parent state regs=r1 stack=") __msg("frame0: parent state regs=r6 stack=") /* Parent state */ -__msg("frame1: last_idx 4 first_idx 4 subseq_idx 6") -__msg("frame1: regs=r1 stack= before 4: (85) call pc+1") +__msg("frame1: last_idx 4 first_idx 4 subseq_idx 7") +__msg("frame1: regs=r1 stack= before 4: (85) call pc+2") __msg("frame0: parent state regs=r1,r6 stack=") /* Parent state */ __msg("frame0: last_idx 3 first_idx 1 subseq_idx 4") @@ -204,6 +217,7 @@ __naked void precision_many_frames(void) "r1 = r0;" "r6 = r0;" "call precision_many_frames__foo;" + "r6 = r6;" /* mark r6 as live */ "exit;" : : __imm(bpf_ktime_get_ns) @@ -220,6 +234,8 @@ void precision_many_frames__foo(void) "r6 = r1;" "r7 = r1;" "call precision_many_frames__bar;" + "r6 = r6;" /* mark r6 as live */ + "r7 = r7;" /* mark r7 as live */ "exit" ::: __clobber_all); } @@ -229,6 +245,8 @@ void precision_many_frames__bar(void) { asm volatile ( "if r1 > 7 goto +0;" + "r6 = 0;" /* mark r6 as live */ + "r7 = 0;" /* mark r7 as live */ /* force r1 to be precise, this eventually marks: * - bar frame r1 * - foo frame r{1,6,7} @@ -340,6 +358,8 @@ __naked void precision_two_ids(void) "r3 += r7;" /* force r9 to be precise, this also marks r8 */ "r3 += r9;" + "r6 = r6;" /* mark r6 as live */ + "r8 = r8;" /* mark r8 as live */ "exit;" : : __imm(bpf_ktime_get_ns) @@ -353,7 +373,7 @@ __flag(BPF_F_TEST_STATE_FREQ) * collect_linked_regs() can't tie more than 6 registers for a single insn. */ __msg("8: (25) if r0 > 0x7 goto pc+0 ; R0=scalar(id=1") -__msg("9: (bf) r6 = r6 ; R6=scalar(id=2") +__msg("14: (bf) r6 = r6 ; R6=scalar(id=2") /* check that r{0-5} are marked precise after 'if' */ __msg("frame0: regs=r0 stack= before 8: (25) if r0 > 0x7 goto pc+0") __msg("frame0: parent state regs=r0,r1,r2,r3,r4,r5 stack=:") @@ -372,6 +392,12 @@ __naked void linked_regs_too_many_regs(void) "r6 = r0;" /* propagate range for r{0-6} */ "if r0 > 7 goto +0;" + /* keep r{1-5} live */ + "r1 = r1;" + "r2 = r2;" + "r3 = r3;" + "r4 = r4;" + "r5 = r5;" /* make r6 appear in the log */ "r6 = r6;" /* force r0 to be precise, @@ -517,7 +543,7 @@ __naked void check_ids_in_regsafe_2(void) "*(u64*)(r10 - 8) = r1;" /* r9 = pointer to stack */ "r9 = r10;" - "r9 += -8;" + "r9 += -16;" /* r8 = ktime_get_ns() */ "call %[bpf_ktime_get_ns];" "r8 = r0;" @@ -538,6 +564,8 @@ __naked void check_ids_in_regsafe_2(void) "if r7 > 4 goto l2_%=;" /* Access memory at r9[r6] */ "r9 += r6;" + "r9 += r7;" + "r9 += r8;" "r0 = *(u8*)(r9 + 0);" "l2_%=:" "r0 = 0;" diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c index 061d98f6e9bb..a9242103dc47 100644 --- a/tools/testing/selftests/bpf/verifier/precise.c +++ b/tools/testing/selftests/bpf/verifier/precise.c @@ -44,9 +44,9 @@ mark_precise: frame0: regs=r2 stack= before 23\ mark_precise: frame0: regs=r2 stack= before 22\ mark_precise: frame0: regs=r2 stack= before 20\ - mark_precise: frame0: parent state regs=r2,r9 stack=:\ + mark_precise: frame0: parent state regs=r2 stack=:\ mark_precise: frame0: last_idx 19 first_idx 10\ - mark_precise: frame0: regs=r2,r9 stack= before 19\ + mark_precise: frame0: regs=r2 stack= before 19\ mark_precise: frame0: regs=r9 stack= before 18\ mark_precise: frame0: regs=r8,r9 stack= before 17\ mark_precise: frame0: regs=r0,r9 stack= before 15\ @@ -107,9 +107,9 @@ mark_precise: frame0: parent state regs=r2 stack=:\ mark_precise: frame0: last_idx 20 first_idx 20\ mark_precise: frame0: regs=r2 stack= before 20\ - mark_precise: frame0: parent state regs=r2,r9 stack=:\ + mark_precise: frame0: parent state regs=r2 stack=:\ mark_precise: frame0: last_idx 19 first_idx 17\ - mark_precise: frame0: regs=r2,r9 stack= before 19\ + mark_precise: frame0: regs=r2 stack= before 19\ mark_precise: frame0: regs=r9 stack= before 18\ mark_precise: frame0: regs=r8,r9 stack= before 17\ mark_precise: frame0: parent state regs= stack=:", diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index 5dff3ad53867..a56f4153c64d 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -196,7 +196,6 @@ test_add_proc() # P = set cpus.partition (0:member, 1:root, 2:isolated) # C = add cpu-list to cpuset.cpus # X = add cpu-list to cpuset.cpus.exclusive -# S

= use prefix in subtree_control # T = put a task into cgroup # CX = add cpu-list to both cpuset.cpus and cpuset.cpus.exclusive # O= = Write to CPU online file of @@ -209,44 +208,46 @@ test_add_proc() # sched-debug matching which includes offline CPUs and single-CPU partitions # while the second one is for matching cpuset.cpus.isolated. # -SETUP_A123_PARTITIONS="C1-3:P1:S+ C2-3:P1:S+ C3:P1" +SETUP_A123_PARTITIONS="C1-3:P1 C2-3:P1 C3:P1" TEST_MATRIX=( # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- - " C0-1 . . C2-3 S+ C4-5 . . 0 A2:0-1" + " C0-1 . . C2-3 . C4-5 . . 0 A2:0-1" " C0-1 . . C2-3 P1 . . . 0 " - " C0-1 . . C2-3 P1:S+ C0-1:P1 . . 0 " - " C0-1 . . C2-3 P1:S+ C1:P1 . . 0 " - " C0-1:S+ . . C2-3 . . . P1 0 " - " C0-1:P1 . . C2-3 S+ C1 . . 0 " - " C0-1:P1 . . C2-3 S+ C1:P1 . . 0 " - " C0-1:P1 . . C2-3 S+ C1:P1 . P1 0 " + " C0-1 . . C2-3 P1 C0-1:P1 . . 0 " + " C0-1 . . C2-3 P1 C1:P1 . . 0 " + " C0-1 . . C2-3 . . . P1 0 " + " C0-1:P1 . . C2-3 . C1 . . 0 " + " C0-1:P1 . . C2-3 . C1:P1 . . 0 " + " C0-1:P1 . . C2-3 . C1:P1 . P1 0 " " C0-1:P1 . . C2-3 C4-5 . . . 0 A1:4-5" - " C0-1:P1 . . C2-3 S+:C4-5 . . . 0 A1:4-5" " C0-1 . . C2-3:P1 . . . C2 0 " " C0-1 . . C2-3:P1 . . . C4-5 0 B1:4-5" - "C0-3:P1:S+ C2-3:P1 . . . . . . 0 A1:0-1|A2:2-3|XA2:2-3" - "C0-3:P1:S+ C2-3:P1 . . C1-3 . . . 0 A1:1|A2:2-3|XA2:2-3" - "C2-3:P1:S+ C3:P1 . . C3 . . . 0 A1:|A2:3|XA2:3 A1:P1|A2:P1" - "C2-3:P1:S+ C3:P1 . . C3 P0 . . 0 A1:3|A2:3 A1:P1|A2:P0" - "C2-3:P1:S+ C2:P1 . . C2-4 . . . 0 A1:3-4|A2:2" - "C2-3:P1:S+ C3:P1 . . C3 . . C0-2 0 A1:|B1:0-2 A1:P1|A2:P1" + " C0-3:P1 C2-3:P1 . . . . . . 0 A1:0-1|A2:2-3|XA2:2-3" + " C0-3:P1 C2-3:P1 . . C1-3 . . . 0 A1:1|A2:2-3|XA2:2-3" + " C2-3:P1 C3:P1 . . C3 . . . 0 A1:|A2:3|XA2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . C3 P0 . . 0 A1:3|A2:3 A1:P1|A2:P0" + " C2-3:P1 C2:P1 . . C2-4 . . . 0 A1:3-4|A2:2" + " C2-3:P1 C3:P1 . . C3 . . C0-2 0 A1:|B1:0-2 A1:P1|A2:P1" "$SETUP_A123_PARTITIONS . C2-3 . . . 0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1" # CPU offlining cases: - " C0-1 . . C2-3 S+ C4-5 . O2=0 0 A1:0-1|B1:3" - "C0-3:P1:S+ C2-3:P1 . . O2=0 . . . 0 A1:0-1|A2:3" - "C0-3:P1:S+ C2-3:P1 . . O2=0 O2=1 . . 0 A1:0-1|A2:2-3" - "C0-3:P1:S+ C2-3:P1 . . O1=0 . . . 0 A1:0|A2:2-3" - "C0-3:P1:S+ C2-3:P1 . . O1=0 O1=1 . . 0 A1:0-1|A2:2-3" - "C2-3:P1:S+ C3:P1 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P1" - "C2-3:P1:S+ C3:P2 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P2" - "C2-3:P1:S+ C3:P1 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P1" - "C2-3:P1:S+ C3:P2 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P2" - "C2-3:P1:S+ C3:P1 . . O2=0 . . . 0 A1:|A2:3 A1:P1|A2:P1" - "C2-3:P1:S+ C3:P1 . . O3=0 . . . 0 A1:2|A2: A1:P1|A2:P1" - "C2-3:P1:S+ C3:P1 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-1" - "C2-3:P1:S+ C3:P1 . . . T:O3=0 . . 0 A1:2|A2:2 A1:P1|A2:P-1" + " C0-1 . . C2-3 . C4-5 . O2=0 0 A1:0-1|B1:3" + " C0-3:P1 C2-3:P1 . . O2=0 . . . 0 A1:0-1|A2:3" + " C0-3:P1 C2-3:P1 . . O2=0 O2=1 . . 0 A1:0-1|A2:2-3" + " C0-3:P1 C2-3:P1 . . O1=0 . . . 0 A1:0|A2:2-3" + " C0-3:P1 C2-3:P1 . . O1=0 O1=1 . . 0 A1:0-1|A2:2-3" + " C2-3:P1 C3:P1 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P2 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P2" + " C2-3:P1 C3:P1 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P2 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P2" + " C2-3:P1 C3:P1 . . O2=0 . . . 0 A1:|A2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . O3=0 . . . 0 A1:2|A2: A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-1" + " C2-3:P1 C3:P1 . . . T:O3=0 . . 0 A1:2|A2:2 A1:P1|A2:P-1" + " C2-3:P1 C3:P2 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-2" + " C1-3:P1 C3:P2 . . . T:O3=0 . . 0 A1:1-2|A2:1-2 A1:P1|A2:P-2 3|" + " C1-3:P1 C3:P2 . . . T:O3=0 O3=1 . 0 A1:1-2|A2:3 A1:P1|A2:P2 3" "$SETUP_A123_PARTITIONS . O1=0 . . . 0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1" "$SETUP_A123_PARTITIONS . O2=0 . . . 0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1" "$SETUP_A123_PARTITIONS . O3=0 . . . 0 A1:1|A2:2|A3: A1:P1|A2:P1|A3:P1" @@ -264,88 +265,87 @@ TEST_MATRIX=( # # Remote partition and cpuset.cpus.exclusive tests # - " C0-3:S+ C1-3:S+ C2-3 . X2-3 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3:P2 . . 0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X3:P2 . . 0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 C2-3 . . . P2 0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2" - " C0-3:S+ C1-3:S+ C2-3 C4-5 . . . P2 0 B1:4-5 B1:P2 4-5" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2:C1-3 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" - " C0-3:S+ C1-3:S+ C2-3 C4 X1-3 X1-3:P2 P2 . 0 A2:1|A3:2-3 A2:P2|A3:P2 1-3" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5" - " C4:X0-3:S+ X1-3:S+ X2-3 . . P2 . . 0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3" - " C4:X0-3:S+ X1-3:S+ X2-3 . . . P2 . 0 A1:4|A2:4|A3:2-3 A3:P2 2-3" + " C0-3 C1-3 C2-3 . X2-3 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3" + " C0-3 C1-3 C2-3 . X2-3 X2-3:P2 . . 0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3" + " C0-3 C1-3 C2-3 . X2-3 X3:P2 . . 0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3" + " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" + " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" + " C0-3 C1-3 C2-3 C2-3 . . . P2 0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2" + " C0-3 C1-3 C2-3 C4-5 . . . P2 0 B1:4-5 B1:P2 4-5" + " C0-3 C1-3 C2-3 C4 X2-3 X2-3 X2-3:P2 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" + " C0-3 C1-3 C2-3 C4 X2-3 X2-3 X2-3:P2:C1-3 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" + " C0-3 C1-3 C2-3 C4 X1-3 X1-3:P2 P2 . 0 A2:1|A3:2-3 A2:P2|A3:P2 1-3" + " C0-3 C1-3 C2-3 C4 X2-3 X2-3 X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5" + " C4:X0-3 X1-3 X2-3 . . P2 . . 0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3" + " C4:X0-3 X1-3 X2-3 . . . P2 . 0 A1:4|A2:4|A3:2-3 A3:P2 2-3" # Nested remote/local partition tests - " C0-3:S+ C1-3:S+ C2-3 C4-5 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4-5 \ + " C0-3 C1-3 C2-3 C4-5 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4-5 \ A1:P0|A2:P1|A3:P2|B1:P1 2-3" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4 \ + " C0-3 C1-3 C2-3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4 \ A1:P0|A2:P1|A3:P2|B1:P1 2-4|2-3" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 . P1 0 A1:0-1|A2:2-3|A3:2-3|B1:4 \ + " C0-3 C1-3 C2-3 C4 X2-3 X2-3:P1 . P1 0 A1:0-1|A2:2-3|A3:2-3|B1:4 \ A1:P0|A2:P1|A3:P0|B1:P1" - " C0-3:S+ C1-3:S+ C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:2|A3:3|B1:4 \ + " C0-3 C1-3 C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:2|A3:3|B1:4 \ A1:P0|A2:P1|A3:P2|B1:P1 2-4|3" - " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1|A2:2-3|A3:4 \ + " C0-4 C1-4 C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1|A2:2-3|A3:4 \ A1:P0|A2:P2|A3:P1 2-4|2-3" - " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1|A2:2|A3:3-4 \ + " C0-4 C1-4 C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1|A2:2|A3:3-4 \ A1:P0|A2:P2|A3:P1 2" - " C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \ + " C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \ . . X5 . . 0 A1:0-4|A2:1-4|A3:2-4 \ A1:P0|A2:P-2|A3:P-1 ." - " C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \ + " C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \ . . . X1 . 0 A1:0-1|A2:2-4|A3:2-4 \ A1:P0|A2:P2|A3:P-1 2-4" # Remote partition offline tests - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 . 0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 P2:O3=0 . 0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3" - " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 T:P2:O3=0 . 0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|" + " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2:O2=0 . 0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3" + " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" + " C0-3 C1-3 C3 . X2-3 X2-3 P2:O3=0 . 0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3" + " C0-3 C1-3 C3 . X2-3 X2-3 T:P2:O3=0 . 0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|" # An invalidated remote partition cannot self-recover from hotplug - " C0-3:S+ C1-3:S+ C2 . X2-3 X2-3 T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ." + " C0-3 C1-3 C2 . X2-3 X2-3 T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ." # cpus.exclusive.effective clearing test - " C0-3:S+ C1-3:S+ C2 . X2-3:X . . . 0 A1:0-3|A2:1-3|A3:2|XA1:" + " C0-3 C1-3 C2 . X2-3:X . . . 0 A1:0-3|A2:1-3|A3:2|XA1:" # Invalid to valid remote partition transition test - " C0-3:S+ C1-3 . . . X3:P2 . . 0 A1:0-3|A2:1-3|XA2: A2:P-2 ." - " C0-3:S+ C1-3:X3:P2 - . . X2-3 P2 . . 0 A1:0-2|A2:3|XA2:3 A2:P2 3" + " C0-3 C1-3 . . . X3:P2 . . 0 A1:0-3|A2:1-3|XA2: A2:P-2 ." + " C0-3 C1-3:X3:P2 . . X2-3 P2 . . 0 A1:0-2|A2:3|XA2:3 A2:P2 3" # Invalid to valid local partition direct transition tests - " C1-3:S+:P2 X4:P2 . . . . . . 0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3" - " C1-3:S+:P2 X4:P2 . . . X3:P2 . . 0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3" - " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4|B1:5-6 A1:P2|B1:P0" - " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3" + " C1-3:P2 X4:P2 . . . . . . 0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3" + " C1-3:P2 X4:P2 . . . X3:P2 . . 0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3" + " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4|B1:5-6 A1:P2|B1:P0" + " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3" # Local partition invalidation tests - " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \ + " C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \ . . . . . 0 A1:1|A2:2|A3:3 A1:P2|A2:P2|A3:P2 1-3" - " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \ + " C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \ . . X4 . . 0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3" - " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \ + " C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \ . . C4:X . . 0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3" # Local partition CPU change tests - " C0-5:S+:P2 C4-5:S+:P1 . . . C3-5 . . 0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2" - " C0-5:S+:P2 C4-5:S+:P1 . . C1-5 . . . 0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3" + " C0-5:P2 C4-5:P1 . . . C3-5 . . 0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2" + " C0-5:P2 C4-5:P1 . . C1-5 . . . 0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3" # cpus_allowed/exclusive_cpus update tests - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \ . X:C4 . P2 . 0 A1:4|A2:4|XA2:|XA3:|A3:4 \ A1:P0|A3:P-2 ." - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \ . X1 . P2 . 0 A1:0-3|A2:1-3|XA1:1|XA2:|XA3:|A3:2-3 \ A1:P0|A3:P-2 ." - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \ . . X3 P2 . 0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3 \ A1:P0|A3:P2 3" - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \ . . X3 . . 0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3|XA3:3 \ A1:P0|A3:P2 3" - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \ . X4 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:4|XA2:|XA3 \ A1:P0|A3:P-2" @@ -356,37 +356,37 @@ TEST_MATRIX=( # # Adding CPUs to partition root that are not in parent's # cpuset.cpus is allowed, but those extra CPUs are ignored. - "C2-3:P1:S+ C3:P1 . . . C2-4 . . 0 A1:|A2:2-3 A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . . C2-4 . . 0 A1:|A2:2-3 A1:P1|A2:P1" # Taking away all CPUs from parent or itself if there are tasks # will make the partition invalid. - "C2-3:P1:S+ C3:P1 . . T C2-3 . . 0 A1:2-3|A2:2-3 A1:P1|A2:P-1" - " C3:P1:S+ C3 . . T P1 . . 0 A1:3|A2:3 A1:P1|A2:P-1" + " C2-3:P1 C3:P1 . . T C2-3 . . 0 A1:2-3|A2:2-3 A1:P1|A2:P-1" + " C3:P1 C3 . . T P1 . . 0 A1:3|A2:3 A1:P1|A2:P-1" "$SETUP_A123_PARTITIONS . T:C2-3 . . . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1" "$SETUP_A123_PARTITIONS . T:C2-3:C1-3 . . . 0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1" # Changing a partition root to member makes child partitions invalid - "C2-3:P1:S+ C3:P1 . . P0 . . . 0 A1:2-3|A2:3 A1:P0|A2:P-1" + " C2-3:P1 C3:P1 . . P0 . . . 0 A1:2-3|A2:3 A1:P0|A2:P-1" "$SETUP_A123_PARTITIONS . C2-3 P0 . . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P0|A3:P-1" # cpuset.cpus can contains cpus not in parent's cpuset.cpus as long # as they overlap. - "C2-3:P1:S+ . . . . C3-4:P1 . . 0 A1:2|A2:3 A1:P1|A2:P1" + " C2-3:P1 . . . . C3-4:P1 . . 0 A1:2|A2:3 A1:P1|A2:P1" # Deletion of CPUs distributed to child cgroup is allowed. - "C0-1:P1:S+ C1 . C2-3 C4-5 . . . 0 A1:4-5|A2:4-5" + " C0-1:P1 C1 . C2-3 C4-5 . . . 0 A1:4-5|A2:4-5" # To become a valid partition root, cpuset.cpus must overlap parent's # cpuset.cpus. - " C0-1:P1 . . C2-3 S+ C4-5:P1 . . 0 A1:0-1|A2:0-1 A1:P1|A2:P-1" + " C0-1:P1 . . C2-3 . C4-5:P1 . . 0 A1:0-1|A2:0-1 A1:P1|A2:P-1" # Enabling partition with child cpusets is allowed - " C0-1:S+ C1 . C2-3 P1 . . . 0 A1:0-1|A2:1 A1:P1" + " C0-1 C1 . C2-3 P1 . . . 0 A1:0-1|A2:1 A1:P1" # A partition root with non-partition root parent is invalid| but it # can be made valid if its parent becomes a partition root too. - " C0-1:S+ C1 . C2-3 . P2 . . 0 A1:0-1|A2:1 A1:P0|A2:P-2" - " C0-1:S+ C1:P2 . C2-3 P1 . . . 0 A1:0|A2:1 A1:P1|A2:P2 0-1|1" + " C0-1 C1 . C2-3 . P2 . . 0 A1:0-1|A2:1 A1:P0|A2:P-2" + " C0-1 C1:P2 . C2-3 P1 . . . 0 A1:0|A2:1 A1:P1|A2:P2 0-1|1" # A non-exclusive cpuset.cpus change will not invalidate its siblings partition. " C0-1:P1 . . C2-3 C0-2 . . . 0 A1:0-2|B1:3 A1:P1|B1:P0" @@ -398,23 +398,23 @@ TEST_MATRIX=( # Child partition root that try to take all CPUs from parent partition # with tasks will remain invalid. - " C1-4:P1:S+ P1 . . . . . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1" - " C1-4:P1:S+ P1 . . . C1-4 . . 0 A1|A2:1-4 A1:P1|A2:P1" - " C1-4:P1:S+ P1 . . T C1-4 . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1" + " C1-4:P1 P1 . . . . . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1" + " C1-4:P1 P1 . . . C1-4 . . 0 A1|A2:1-4 A1:P1|A2:P1" + " C1-4:P1 P1 . . T C1-4 . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1" # Clearing of cpuset.cpus with a preset cpuset.cpus.exclusive shouldn't # affect cpuset.cpus.exclusive.effective. - " C1-4:X3:S+ C1:X3 . . . C . . 0 A2:1-4|XA2:3" + " C1-4:X3 C1:X3 . . . C . . 0 A2:1-4|XA2:3" # cpuset.cpus can contain CPUs that overlap a sibling cpuset with cpus.exclusive # but creating a local partition out of it is not allowed. Similarly and change # in cpuset.cpus of a local partition that overlaps sibling exclusive CPUs will # invalidate it. - " CX1-4:S+ CX2-4:P2 . C5-6 . . . P1 0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \ + " CX1-4 CX2-4:P2 . C5-6 . . . P1 0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \ A1:P0|A2:P2:B1:P1 2-4" - " CX1-4:S+ CX2-4:P2 . C3-6 . . . P1 0 A1:1|A2:2-4|B1:5-6 \ + " CX1-4 CX2-4:P2 . C3-6 . . . P1 0 A1:1|A2:2-4|B1:5-6 \ A1:P0|A2:P2:B1:P-1 2-4" - " CX1-4:S+ CX2-4:P2 . C5-6 . . . P1:C3-6 0 A1:1|A2:2-4|B1:5-6 \ + " CX1-4 CX2-4:P2 . C5-6 . . . P1:C3-6 0 A1:1|A2:2-4|B1:5-6 \ A1:P0|A2:P2:B1:P-1 2-4" # When multiple partitions with conflicting cpuset.cpus are created, the @@ -426,14 +426,14 @@ TEST_MATRIX=( " C1-3:X1-3 . . C4-5 . . . C1-2 0 A1:1-3|B1:1-2" # cpuset.cpus can become empty with task in it as it inherits parent's effective CPUs - " C1-3:S+ C2 . . . T:C . . 0 A1:1-3|A2:1-3" + " C1-3 C2 . . . T:C . . 0 A1:1-3|A2:1-3" # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- # Failure cases: # A task cannot be added to a partition with no cpu - "C2-3:P1:S+ C3:P1 . . O2=0:T . . . 1 A1:|A2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . O2=0:T . . . 1 A1:|A2:3 A1:P1|A2:P1" # Changes to cpuset.cpus.exclusive that violate exclusivity rule is rejected " C0-3 . . C4-5 X0-3 . . X3-5 1 A1:0-3|B1:4-5" @@ -465,31 +465,31 @@ REMOTE_TEST_MATRIX=( # old-p1 old-p2 old-c11 old-c12 old-c21 old-c22 # new-p1 new-p2 new-c11 new-c12 new-c21 new-c22 ECPUs Pstate ISOLCPUS # ------ ------ ------- ------- ------- ------- ----- ------ -------- - " X1-3:S+ X4-6:S+ X1-2 X3 X4-5 X6 \ + " X1-3 X4-6 X1-2 X3 X4-5 X6 \ . . P2 P2 P2 P2 c11:1-2|c12:3|c21:4-5|c22:6 \ c11:P2|c12:P2|c21:P2|c22:P2 1-6" - " CX1-4:S+ . X1-2:P2 C3 . . \ + " CX1-4 . X1-2:P2 C3 . . \ . . . C3-4 . . p1:3-4|c11:1-2|c12:3-4 \ p1:P0|c11:P2|c12:P0 1-2" - " CX1-4:S+ . X1-2:P2 . . . \ + " CX1-4 . X1-2:P2 . . . \ X2-4 . . . . . p1:1,3-4|c11:2 \ p1:P0|c11:P2 2" - " CX1-5:S+ . X1-2:P2 X3-5:P1 . . \ + " CX1-5 . X1-2:P2 X3-5:P1 . . \ X2-4 . . . . . p1:1,5|c11:2|c12:3-4 \ p1:P0|c11:P2|c12:P1 2" - " CX1-4:S+ . X1-2:P2 X3-4:P1 . . \ + " CX1-4 . X1-2:P2 X3-4:P1 . . \ . . X2 . . . p1:1|c11:2|c12:3-4 \ p1:P0|c11:P2|c12:P1 2" # p1 as member, will get its effective CPUs from its parent rtest - " CX1-4:S+ . X1-2:P2 X3-4:P1 . . \ + " CX1-4 . X1-2:P2 X3-4:P1 . . \ . . X1 CX2-4 . . p1:5-7|c11:1|c12:2-4 \ p1:P0|c11:P2|c12:P1 1" - " CX1-4:S+ X5-6:P1:S+ . . . . \ - . . X1-2:P2 X4-5:P1 . X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \ + " CX1-4 X5-6:P1 . . . . \ + . . X1-2:P2 X4-5:P1 . X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \ p1:P0|p2:P1|c11:P2|c12:P1|c22:P2 \ 1-2,4-6|1-2,5-6" # c12 whose cpuset.cpus CPUs are all granted to c11 will become invalid partition - " C1-5:P1:S+ . C1-4:P1 C2-3 . . \ + " C1-5:P1 . C1-4:P1 C2-3 . . \ . . . P1 . . p1:5|c11:1-4|c12:5 \ p1:P1|c11:P1|c12:P-1" ) @@ -530,7 +530,6 @@ set_ctrl_state() CGRP=$1 STATE=$2 SHOWERR=${3} - CTRL=${CTRL:=$CONTROLLER} HASERR=0 REDIRECT="2> $TMPMSG" [[ -z "$STATE" || "$STATE" = '.' ]] && return 0 @@ -540,15 +539,16 @@ set_ctrl_state() for CMD in $(echo $STATE | sed -e "s/:/ /g") do TFILE=$CGRP/cgroup.procs - SFILE=$CGRP/cgroup.subtree_control PFILE=$CGRP/cpuset.cpus.partition CFILE=$CGRP/cpuset.cpus XFILE=$CGRP/cpuset.cpus.exclusive - case $CMD in - S*) PREFIX=${CMD#?} - COMM="echo ${PREFIX}${CTRL} > $SFILE" + + # Enable cpuset controller if not enabled yet + [[ -f $CFILE ]] || { + COMM="echo +cpuset > $CGRP/../cgroup.subtree_control" eval $COMM $REDIRECT - ;; + } + case $CMD in X*) CPUS=${CMD#?} COMM="echo $CPUS > $XFILE" @@ -764,7 +764,7 @@ check_cgroup_states() # only CPUs in isolated partitions as well as those that are isolated at # boot time. # -# $1 - expected isolated cpu list(s) {,} +# $1 - expected isolated cpu list(s) {|} # - expected sched/domains value # - cpuset.cpus.isolated value = if not defined # @@ -773,6 +773,7 @@ check_isolcpus() EXPECTED_ISOLCPUS=$1 ISCPUS=${CGROUP2}/cpuset.cpus.isolated ISOLCPUS=$(cat $ISCPUS) + HKICPUS=$(cat /sys/devices/system/cpu/isolated) LASTISOLCPU= SCHED_DOMAINS=/sys/kernel/debug/sched/domains if [[ $EXPECTED_ISOLCPUS = . ]] @@ -810,6 +811,11 @@ check_isolcpus() ISOLCPUS= EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN + # + # The inverse of HK_TYPE_DOMAIN cpumask in $HKICPUS should match $ISOLCPUS + # + [[ "$ISOLCPUS" != "$HKICPUS" ]] && return 1 + # # Use the sched domain in debugfs to check isolated CPUs, if available # @@ -947,7 +953,6 @@ check_test_results() run_state_test() { TEST=$1 - CONTROLLER=cpuset CGROUP_LIST=". A1 A1/A2 A1/A2/A3 B1" RESET_LIST="A1/A2/A3 A1/A2 A1 B1" I=0 @@ -1003,7 +1008,6 @@ run_state_test() run_remote_state_test() { TEST=$1 - CONTROLLER=cpuset [[ -d rtest ]] || mkdir rtest cd rtest echo +cpuset > cgroup.subtree_control diff --git a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c index 61e55dfbf121..e19ff8168baf 100644 --- a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c +++ b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c @@ -37,17 +37,20 @@ FIXTURE(iterate_mount_namespaces) { __u64 mnt_ns_id[MNT_NS_COUNT]; }; +static inline bool mntns_in_list(__u64 *mnt_ns_id, struct mnt_ns_info *info) +{ + for (int i = 0; i < MNT_NS_COUNT; i++) { + if (mnt_ns_id[i] == info->mnt_ns_id) + return true; + } + return false; +} + FIXTURE_SETUP(iterate_mount_namespaces) { for (int i = 0; i < MNT_NS_COUNT; i++) self->fd_mnt_ns[i] = -EBADF; - /* - * Creating a new user namespace let's us guarantee that we only see - * mount namespaces that we did actually create. - */ - ASSERT_EQ(unshare(CLONE_NEWUSER), 0); - for (int i = 0; i < MNT_NS_COUNT; i++) { struct mnt_ns_info info = {}; @@ -75,13 +78,15 @@ TEST_F(iterate_mount_namespaces, iterate_all_forward) fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[0], F_DUPFD_CLOEXEC); ASSERT_GE(fd_mnt_ns_cur, 0); - for (;; count++) { + for (;;) { struct mnt_ns_info info = {}; int fd_mnt_ns_next; fd_mnt_ns_next = ioctl(fd_mnt_ns_cur, NS_MNT_GET_NEXT, &info); if (fd_mnt_ns_next < 0 && errno == ENOENT) break; + if (mntns_in_list(self->mnt_ns_id, &info)) + count++; ASSERT_GE(fd_mnt_ns_next, 0); ASSERT_EQ(close(fd_mnt_ns_cur), 0); fd_mnt_ns_cur = fd_mnt_ns_next; @@ -96,13 +101,15 @@ TEST_F(iterate_mount_namespaces, iterate_all_backwards) fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[MNT_NS_LAST_INDEX], F_DUPFD_CLOEXEC); ASSERT_GE(fd_mnt_ns_cur, 0); - for (;; count++) { + for (;;) { struct mnt_ns_info info = {}; int fd_mnt_ns_prev; fd_mnt_ns_prev = ioctl(fd_mnt_ns_cur, NS_MNT_GET_PREV, &info); if (fd_mnt_ns_prev < 0 && errno == ENOENT) break; + if (mntns_in_list(self->mnt_ns_id, &info)) + count++; ASSERT_GE(fd_mnt_ns_prev, 0); ASSERT_EQ(close(fd_mnt_ns_cur), 0); fd_mnt_ns_cur = fd_mnt_ns_prev; @@ -125,7 +132,6 @@ TEST_F(iterate_mount_namespaces, iterate_forward) ASSERT_GE(fd_mnt_ns_next, 0); ASSERT_EQ(close(fd_mnt_ns_cur), 0); fd_mnt_ns_cur = fd_mnt_ns_next; - ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]); } } @@ -144,7 +150,6 @@ TEST_F(iterate_mount_namespaces, iterate_backward) ASSERT_GE(fd_mnt_ns_prev, 0); ASSERT_EQ(close(fd_mnt_ns_cur), 0); fd_mnt_ns_cur = fd_mnt_ns_prev; - ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]); } } diff --git a/tools/testing/selftests/hid/tests/test_wacom_generic.py b/tools/testing/selftests/hid/tests/test_wacom_generic.py index 2d6d04f0ff80..3903f479b15b 100644 --- a/tools/testing/selftests/hid/tests/test_wacom_generic.py +++ b/tools/testing/selftests/hid/tests/test_wacom_generic.py @@ -598,18 +598,6 @@ class BaseTest: if unit_set: assert required[usage].contains(field) - def test_prop_direct(self): - """ - Todo: Verify that INPUT_PROP_DIRECT is set on display devices. - """ - pass - - def test_prop_pointer(self): - """ - Todo: Verify that INPUT_PROP_POINTER is set on opaque devices. - """ - pass - class PenTabletTest(BaseTest.TestTablet): def assertName(self, uhdev): @@ -677,6 +665,15 @@ class TestOpaqueTablet(PenTabletTest): uhdev.event(130, 240, pressure=0), [], auto_syn=False, strict=True ) + def test_prop_pointer(self): + """ + Verify that INPUT_PROP_POINTER is set and INPUT_PROP_DIRECT + is not set on opaque devices. + """ + evdev = self.uhdev.get_evdev() + assert libevdev.INPUT_PROP_POINTER in evdev.properties + assert libevdev.INPUT_PROP_DIRECT not in evdev.properties + class TestOpaqueCTLTablet(TestOpaqueTablet): def create_device(self): @@ -862,7 +859,18 @@ class TestPTHX60_Pen(TestOpaqueCTLTablet): ) -class TestDTH2452Tablet(test_multitouch.BaseTest.TestMultitouch, TouchTabletTest): +class DirectTabletTest(): + def test_prop_direct(self): + """ + Verify that INPUT_PROP_DIRECT is set and INPUT_PROP_POINTER + is not set on display devices. + """ + evdev = self.uhdev.get_evdev() + assert libevdev.INPUT_PROP_DIRECT in evdev.properties + assert libevdev.INPUT_PROP_POINTER not in evdev.properties + + +class TestDTH2452Tablet(test_multitouch.BaseTest.TestMultitouch, TouchTabletTest, DirectTabletTest): ContactIds = namedtuple("ContactIds", "contact_id, tracking_id, slot_num") def create_device(self): diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 16a119a4656c..4afaef01c22e 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -76,6 +76,9 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) memset(s, c, n); } +#define KSELFTEST_PRIO_TEST_F 20000 +#define KSELFTEST_PRIO_XFAIL 20001 + #define TEST_TIMEOUT_DEFAULT 30 /* Utilities exposed to the test definitions */ @@ -465,7 +468,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) fixture_name##_teardown(_metadata, self, variant); \ } \ static struct __test_metadata *_##fixture_name##_##test_name##_object; \ - static void __attribute__((constructor)) \ + static void __attribute__((constructor(KSELFTEST_PRIO_TEST_F))) \ _register_##fixture_name##_##test_name(void) \ { \ struct __test_metadata *object = mmap(NULL, sizeof(*object), \ @@ -880,7 +883,7 @@ struct __test_xfail { .fixture = &_##fixture_name##_fixture_object, \ .variant = &_##fixture_name##_##variant_name##_object, \ }; \ - static void __attribute__((constructor)) \ + static void __attribute__((constructor(KSELFTEST_PRIO_XFAIL))) \ _register_##fixture_name##_##variant_name##_##test_name##_xfail(void) \ { \ _##fixture_name##_##variant_name##_##test_name##_xfail.test = \ diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index afdea6d95bde..605c54c0e8a3 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -15,6 +15,7 @@ TEST_PROGS := \ big_tcp.sh \ bind_bhash.sh \ bpf_offload.py \ + bridge_vlan_dump.sh \ broadcast_ether_dst.sh \ broadcast_pmtu.sh \ busy_poll_test.sh \ diff --git a/tools/testing/selftests/net/bridge_vlan_dump.sh b/tools/testing/selftests/net/bridge_vlan_dump.sh new file mode 100755 index 000000000000..ad66731d2a6f --- /dev/null +++ b/tools/testing/selftests/net/bridge_vlan_dump.sh @@ -0,0 +1,204 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test bridge VLAN range grouping. VLANs are collapsed into a range entry in +# the dump if they have the same per-VLAN options. These tests verify that +# VLANs with different per-VLAN option values are not grouped together. + +# shellcheck disable=SC1091,SC2034,SC2154,SC2317 +source lib.sh + +ALL_TESTS=" + vlan_range_neigh_suppress + vlan_range_mcast_max_groups + vlan_range_mcast_n_groups + vlan_range_mcast_enabled +" + +setup_prepare() +{ + setup_ns NS + defer cleanup_all_ns + + ip -n "$NS" link add name br0 type bridge vlan_filtering 1 \ + vlan_default_pvid 0 mcast_snooping 1 mcast_vlan_snooping 1 + ip -n "$NS" link set dev br0 up + + ip -n "$NS" link add name dummy0 type dummy + ip -n "$NS" link set dev dummy0 master br0 + ip -n "$NS" link set dev dummy0 up +} + +vlan_range_neigh_suppress() +{ + RET=0 + + # Add two new consecutive VLANs for range grouping test + bridge -n "$NS" vlan add vid 10 dev dummy0 + defer bridge -n "$NS" vlan del vid 10 dev dummy0 + + bridge -n "$NS" vlan add vid 11 dev dummy0 + defer bridge -n "$NS" vlan del vid 11 dev dummy0 + + # Configure different neigh_suppress values and verify no range grouping + bridge -n "$NS" vlan set vid 10 dev dummy0 neigh_suppress on + check_err $? "Failed to set neigh_suppress for VLAN 10" + + bridge -n "$NS" vlan set vid 11 dev dummy0 neigh_suppress off + check_err $? "Failed to set neigh_suppress for VLAN 11" + + # Verify VLANs are not shown as a range, but individual entries exist + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_fail $? "VLANs with different neigh_suppress incorrectly grouped" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$" + check_err $? "VLAN 10 individual entry not found" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$" + check_err $? "VLAN 11 individual entry not found" + + # Configure same neigh_suppress value and verify range grouping + bridge -n "$NS" vlan set vid 11 dev dummy0 neigh_suppress on + check_err $? "Failed to set neigh_suppress for VLAN 11" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_err $? "VLANs with same neigh_suppress not grouped" + + log_test "VLAN range grouping with neigh_suppress" +} + +vlan_range_mcast_max_groups() +{ + RET=0 + + # Add two new consecutive VLANs for range grouping test + bridge -n "$NS" vlan add vid 10 dev dummy0 + defer bridge -n "$NS" vlan del vid 10 dev dummy0 + + bridge -n "$NS" vlan add vid 11 dev dummy0 + defer bridge -n "$NS" vlan del vid 11 dev dummy0 + + # Configure different mcast_max_groups values and verify no range grouping + bridge -n "$NS" vlan set vid 10 dev dummy0 mcast_max_groups 100 + check_err $? "Failed to set mcast_max_groups for VLAN 10" + + bridge -n "$NS" vlan set vid 11 dev dummy0 mcast_max_groups 200 + check_err $? "Failed to set mcast_max_groups for VLAN 11" + + # Verify VLANs are not shown as a range, but individual entries exist + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_fail $? "VLANs with different mcast_max_groups incorrectly grouped" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$" + check_err $? "VLAN 10 individual entry not found" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$" + check_err $? "VLAN 11 individual entry not found" + + # Configure same mcast_max_groups value and verify range grouping + bridge -n "$NS" vlan set vid 11 dev dummy0 mcast_max_groups 100 + check_err $? "Failed to set mcast_max_groups for VLAN 11" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_err $? "VLANs with same mcast_max_groups not grouped" + + log_test "VLAN range grouping with mcast_max_groups" +} + +vlan_range_mcast_n_groups() +{ + RET=0 + + # Add two new consecutive VLANs for range grouping test + bridge -n "$NS" vlan add vid 10 dev dummy0 + defer bridge -n "$NS" vlan del vid 10 dev dummy0 + + bridge -n "$NS" vlan add vid 11 dev dummy0 + defer bridge -n "$NS" vlan del vid 11 dev dummy0 + + # Add different numbers of multicast groups to each VLAN + bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.1 vid 10 + check_err $? "Failed to add mdb entry to VLAN 10" + defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.1 vid 10 + + bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.2 vid 10 + check_err $? "Failed to add second mdb entry to VLAN 10" + defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.2 vid 10 + + bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.1 vid 11 + check_err $? "Failed to add mdb entry to VLAN 11" + defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.1 vid 11 + + # Verify VLANs are not shown as a range due to different mcast_n_groups + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_fail $? "VLANs with different mcast_n_groups incorrectly grouped" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$" + check_err $? "VLAN 10 individual entry not found" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$" + check_err $? "VLAN 11 individual entry not found" + + # Add another group to VLAN 11 to match VLAN 10's count + bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.2 vid 11 + check_err $? "Failed to add second mdb entry to VLAN 11" + defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.2 vid 11 + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_err $? "VLANs with same mcast_n_groups not grouped" + + log_test "VLAN range grouping with mcast_n_groups" +} + +vlan_range_mcast_enabled() +{ + RET=0 + + # Add two new consecutive VLANs for range grouping test + bridge -n "$NS" vlan add vid 10 dev br0 self + defer bridge -n "$NS" vlan del vid 10 dev br0 self + + bridge -n "$NS" vlan add vid 11 dev br0 self + defer bridge -n "$NS" vlan del vid 11 dev br0 self + + bridge -n "$NS" vlan add vid 10 dev dummy0 + defer bridge -n "$NS" vlan del vid 10 dev dummy0 + + bridge -n "$NS" vlan add vid 11 dev dummy0 + defer bridge -n "$NS" vlan del vid 11 dev dummy0 + + # Configure different mcast_snooping for bridge VLANs + # Port VLANs inherit BR_VLFLAG_MCAST_ENABLED from bridge VLANs + bridge -n "$NS" vlan global set dev br0 vid 10 mcast_snooping 1 + bridge -n "$NS" vlan global set dev br0 vid 11 mcast_snooping 0 + + # Verify port VLANs are not grouped due to different mcast_enabled + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_fail $? "VLANs with different mcast_enabled incorrectly grouped" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$" + check_err $? "VLAN 10 individual entry not found" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$" + check_err $? "VLAN 11 individual entry not found" + + # Configure same mcast_snooping and verify range grouping + bridge -n "$NS" vlan global set dev br0 vid 11 mcast_snooping 1 + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_err $? "VLANs with same mcast_enabled not grouped" + + log_test "VLAN range grouping with mcast_enabled" +} + +# Verify the newest tested option is supported +if ! bridge vlan help 2>&1 | grep -q "neigh_suppress"; then + echo "SKIP: iproute2 too old, missing per-VLAN neighbor suppression support" + exit "$ksft_skip" +fi + +trap defer_scopes_cleanup EXIT +setup_prepare +tests_run + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 21026b667667..6eb7f95e70e1 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1672,6 +1672,17 @@ ipv4_withv6_fcnal() run_cmd "$IP ro replace 172.16.101.1/32 via inet6 2001:db8:50::1 dev veth1" log_test $? 2 "IPv4 route with invalid IPv6 gateway" + + # Test IPv4 route with loopback IPv6 nexthop + # Regression test: loopback IPv6 nexthop was misclassified as reject + # route, skipping nhc_pcpu_rth_output allocation, causing panic when + # an IPv4 route references it and triggers __mkroute_output(). + run_cmd "$IP -6 nexthop add id 20 dev lo" + run_cmd "$IP ro add 172.20.20.0/24 nhid 20" + run_cmd "ip netns exec $me ping -c1 -W1 172.20.20.1" + log_test $? 1 "IPv4 route with loopback IPv6 nexthop (no crash)" + run_cmd "$IP ro del 172.20.20.0/24" + run_cmd "$IP nexthop del id 20" } ipv4_fcnal_runtime() diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index dc1f200aaa81..a3144d7298a5 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -104,6 +104,24 @@ CBPF_MPTCP_SUBOPTION_ADD_ADDR="14, 6 0 0 65535, 6 0 0 0" +# IPv4: TCP hdr of 48B, a first suboption of 12B (DACK8), the RM_ADDR suboption +# generated using "nfbpf_compile '(ip[32] & 0xf0) == 0xc0 && ip[53] == 0x0c && +# (ip[66] & 0xf0) == 0x40'" +CBPF_MPTCP_SUBOPTION_RM_ADDR="13, + 48 0 0 0, + 84 0 0 240, + 21 0 9 64, + 48 0 0 32, + 84 0 0 240, + 21 0 6 192, + 48 0 0 53, + 21 0 4 12, + 48 0 0 66, + 84 0 0 240, + 21 0 1 64, + 6 0 0 65535, + 6 0 0 0" + init_partial() { capout=$(mktemp) @@ -2608,6 +2626,19 @@ remove_tests() chk_rst_nr 0 0 fi + # signal+subflow with limits, remove + if reset "remove signal+subflow with limits"; then + pm_nl_set_limits $ns1 0 0 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,subflow + pm_nl_set_limits $ns2 0 0 + addr_nr_ns1=-1 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + chk_add_nr 1 1 + chk_rm_nr 1 0 invert + chk_rst_nr 0 0 + fi + # addresses remove if reset "remove addresses"; then pm_nl_set_limits $ns1 3 3 @@ -4217,6 +4248,14 @@ endpoint_tests() chk_subflow_nr "after no reject" 3 chk_mptcp_info subflows 2 subflows 2 + # To make sure RM_ADDR are sent over a different subflow, but + # allow the rest to quickly and cleanly close the subflow + local ipt=1 + ip netns exec "${ns2}" ${iptables} -I OUTPUT -s "10.0.1.2" \ + -p tcp -m tcp --tcp-option 30 \ + -m bpf --bytecode \ + "$CBPF_MPTCP_SUBOPTION_RM_ADDR" \ + -j DROP || ipt=0 local i for i in $(seq 3); do pm_nl_del_endpoint $ns2 1 10.0.1.2 @@ -4229,6 +4268,7 @@ endpoint_tests() chk_subflow_nr "after re-add id 0 ($i)" 3 chk_mptcp_info subflows 3 subflows 3 done + [ ${ipt} = 1 ] && ip netns exec "${ns2}" ${iptables} -D OUTPUT 1 mptcp_lib_kill_group_wait $tests_pid @@ -4288,11 +4328,20 @@ endpoint_tests() chk_mptcp_info subflows 2 subflows 2 chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 + # To make sure RM_ADDR are sent over a different subflow, but + # allow the rest to quickly and cleanly close the subflow + local ipt=1 + ip netns exec "${ns1}" ${iptables} -I OUTPUT -s "10.0.1.1" \ + -p tcp -m tcp --tcp-option 30 \ + -m bpf --bytecode \ + "$CBPF_MPTCP_SUBOPTION_RM_ADDR" \ + -j DROP || ipt=0 pm_nl_del_endpoint $ns1 42 10.0.1.1 sleep 0.5 chk_subflow_nr "after delete ID 0" 2 chk_mptcp_info subflows 2 subflows 2 chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 + [ ${ipt} = 1 ] && ip netns exec "${ns1}" ${iptables} -D OUTPUT 1 pm_nl_add_endpoint $ns1 10.0.1.1 id 99 flags signal wait_mpj 4 diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 806aaa7d2d61..d11a8b949aab 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -237,10 +237,13 @@ run_test() for dev in ns2eth1 ns2eth2; do tc -n $ns2 qdisc del dev $dev root >/dev/null 2>&1 done - tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1 - tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2 - tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 - tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 + + # keep the queued pkts number low, or the RTT estimator will see + # increasing latency over time. + tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1 limit 50 + tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2 limit 50 + tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 limit 50 + tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 limit 50 # time is measured in ms, account for transfer size, aggregated link speed # and header overhead (10%) diff --git a/tools/testing/selftests/net/netfilter/nf_queue.c b/tools/testing/selftests/net/netfilter/nf_queue.c index 9e56b9d47037..116c0ca0eabb 100644 --- a/tools/testing/selftests/net/netfilter/nf_queue.c +++ b/tools/testing/selftests/net/netfilter/nf_queue.c @@ -18,6 +18,7 @@ struct options { bool count_packets; bool gso_enabled; + bool failopen; int verbose; unsigned int queue_num; unsigned int timeout; @@ -30,7 +31,7 @@ static struct options opts; static void help(const char *p) { - printf("Usage: %s [-c|-v [-vv] ] [-t timeout] [-q queue_num] [-Qdst_queue ] [ -d ms_delay ] [-G]\n", p); + printf("Usage: %s [-c|-v [-vv] ] [-o] [-t timeout] [-q queue_num] [-Qdst_queue ] [ -d ms_delay ] [-G]\n", p); } static int parse_attr_cb(const struct nlattr *attr, void *data) @@ -236,6 +237,8 @@ struct mnl_socket *open_queue(void) flags = opts.gso_enabled ? NFQA_CFG_F_GSO : 0; flags |= NFQA_CFG_F_UID_GID; + if (opts.failopen) + flags |= NFQA_CFG_F_FAIL_OPEN; mnl_attr_put_u32(nlh, NFQA_CFG_FLAGS, htonl(flags)); mnl_attr_put_u32(nlh, NFQA_CFG_MASK, htonl(flags)); @@ -329,7 +332,7 @@ static void parse_opts(int argc, char **argv) { int c; - while ((c = getopt(argc, argv, "chvt:q:Q:d:G")) != -1) { + while ((c = getopt(argc, argv, "chvot:q:Q:d:G")) != -1) { switch (c) { case 'c': opts.count_packets = true; @@ -366,6 +369,9 @@ static void parse_opts(int argc, char **argv) case 'G': opts.gso_enabled = false; break; + case 'o': + opts.failopen = true; + break; case 'v': opts.verbose++; break; diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh index 139bc1211878..ea766bdc5d04 100755 --- a/tools/testing/selftests/net/netfilter/nft_queue.sh +++ b/tools/testing/selftests/net/netfilter/nft_queue.sh @@ -591,6 +591,7 @@ EOF test_udp_gro_ct() { local errprefix="FAIL: test_udp_gro_ct:" + local timeout=5 ip netns exec "$nsrouter" conntrack -F 2>/dev/null @@ -630,10 +631,10 @@ table inet udpq { } } EOF - timeout 10 ip netns exec "$ns2" socat UDP-LISTEN:12346,fork,pf=ipv4 OPEN:"$TMPFILE1",trunc & + timeout "$timeout" ip netns exec "$ns2" socat UDP-LISTEN:12346,fork,pf=ipv4 OPEN:"$TMPFILE1",trunc & local rpid=$! - ip netns exec "$nsrouter" ./nf_queue -G -c -q 1 -t 2 > "$TMPFILE2" & + ip netns exec "$nsrouter" nice -n -19 ./nf_queue -G -c -q 1 -o -t 2 > "$TMPFILE2" & local nfqpid=$! ip netns exec "$nsrouter" ethtool -K "veth0" rx-udp-gro-forwarding on rx-gro-list on generic-receive-offload on @@ -643,8 +644,12 @@ EOF local bs=512 local count=$(((32 * 1024 * 1024) / bs)) - dd if=/dev/zero bs="$bs" count="$count" 2>/dev/null | for i in $(seq 1 16); do - timeout 5 ip netns exec "$ns1" \ + + local nprocs=$(nproc) + [ $nprocs -gt 1 ] && nprocs=$((nprocs - 1)) + + dd if=/dev/zero bs="$bs" count="$count" 2>/dev/null | for i in $(seq 1 $nprocs); do + timeout "$timeout" nice -n 19 ip netns exec "$ns1" \ socat -u -b 512 STDIN UDP-DATAGRAM:10.0.2.99:12346,reuseport,bind=0.0.0.0:55221 & done diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt index 3848b419e68c..6c0f32c40f19 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt @@ -38,7 +38,7 @@ // If queue is empty, accept a packet even if its end_seq is above wup + rcv_wnd +0 < P. 4001:54001(50000) ack 1 win 257 - +0 > . 1:1(0) ack 54001 win 0 + * > . 1:1(0) ack 54001 win 0 // Check LINUX_MIB_BEYOND_WINDOW has been incremented 3 times. +0 `nstat | grep TcpExtBeyondWindow | grep -q " 3 "` diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt deleted file mode 100644 index f575c0ff89da..000000000000 --- a/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt +++ /dev/null @@ -1,33 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - ---mss=1000 - -`./defaults.sh` - - 0 `nstat -n` - -// Establish a connection. - +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 - +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 - +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 4) = 0 - +0 bind(3, ..., ...) = 0 - +0 listen(3, 1) = 0 - - +0 < S 0:0(0) win 32792 - +0 > S. 0:0(0) ack 1 win 18980 - +.1 < . 1:1(0) ack 1 win 257 - - +0 accept(3, ..., ...) = 4 - - +0 < P. 1:20001(20000) ack 1 win 257 - +.04 > . 1:1(0) ack 20001 win 18000 - - +0 setsockopt(4, SOL_SOCKET, SO_RCVBUF, [12000], 4) = 0 - +0 < P. 20001:80001(60000) ack 1 win 257 - +0 > . 1:1(0) ack 20001 win 18000 - - +0 read(4, ..., 20000) = 20000 -// A too big packet is accepted if the receive queue is empty - +0 < P. 20001:80001(60000) ack 1 win 257 - +0 > . 1:1(0) ack 80001 win 0 - diff --git a/tools/testing/selftests/net/tun.c b/tools/testing/selftests/net/tun.c index 8a5cd5cb5472..cf106a49b55e 100644 --- a/tools/testing/selftests/net/tun.c +++ b/tools/testing/selftests/net/tun.c @@ -944,8 +944,8 @@ TEST_F(tun_vnet_udptnl, send_gso_packet) ASSERT_EQ(ret, off); ret = receive_gso_packet_from_tunnel(self, variant, &r_num_mss); - ASSERT_EQ(ret, variant->data_size); - ASSERT_EQ(r_num_mss, variant->r_num_mss); + EXPECT_EQ(ret, variant->data_size); + EXPECT_EQ(r_num_mss, variant->r_num_mss); } TEST_F(tun_vnet_udptnl, recv_gso_packet) @@ -955,18 +955,18 @@ TEST_F(tun_vnet_udptnl, recv_gso_packet) int ret, gso_type = VIRTIO_NET_HDR_GSO_UDP_L4; ret = send_gso_packet_into_tunnel(self, variant); - ASSERT_EQ(ret, variant->data_size); + EXPECT_EQ(ret, variant->data_size); memset(&vnet_hdr, 0, sizeof(vnet_hdr)); ret = receive_gso_packet_from_tun(self, variant, &vnet_hdr); - ASSERT_EQ(ret, variant->data_size); + EXPECT_EQ(ret, variant->data_size); if (!variant->no_gso) { - ASSERT_EQ(vh->gso_size, variant->gso_size); + EXPECT_EQ(vh->gso_size, variant->gso_size); gso_type |= (variant->tunnel_type & UDP_TUNNEL_OUTER_IPV4) ? (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4) : (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6); - ASSERT_EQ(vh->gso_type, gso_type); + EXPECT_EQ(vh->gso_type, gso_type); } } diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N index 07f5e0a70ae7..f943cdfb0a74 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N @@ -2,7 +2,9 @@ CONFIG_RCU_TRACE=n CONFIG_SMP=y CONFIG_NR_CPUS=4 CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_DYNAMIC=n +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n #CHECK#CONFIG_RCU_EXPERT=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T index c70cf0405f24..06e4d1030279 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T @@ -1,5 +1,6 @@ CONFIG_SMP=n -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U index bc9eeabaa1b1..71da6e3e9488 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U @@ -1,5 +1,6 @@ CONFIG_SMP=n -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n @@ -7,4 +8,3 @@ CONFIG_PREEMPT_DYNAMIC=n CONFIG_RCU_TRACE=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n -CONFIG_PREEMPT_COUNT=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 index 2f9fcffff5ae..dd2bd4e08da4 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 @@ -1,5 +1,6 @@ CONFIG_SMP=n -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY01 b/tools/testing/selftests/rcutorture/configs/rcu/TINY01 index 0953c52fcfd7..2be53bf60d65 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TINY01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY01 @@ -1,5 +1,6 @@ CONFIG_SMP=n -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n @@ -11,4 +12,3 @@ CONFIG_RCU_TRACE=n #CHECK#CONFIG_RCU_STALL_COMMON=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n -CONFIG_PREEMPT_COUNT=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 index 30439f6fc20e..be8860342ef7 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 @@ -1,5 +1,6 @@ CONFIG_SMP=n -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 index 18efab346381..8fb124c28f28 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 @@ -1,7 +1,8 @@ CONFIG_SMP=y CONFIG_NR_CPUS=5 CONFIG_HOTPLUG_CPU=y -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 index 67caf4276bb0..ac857d5bcb22 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 @@ -1,10 +1,12 @@ CONFIG_SMP=y CONFIG_NR_CPUS=8 +CONFIG_PREEMPT_LAZY=y CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=y +CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n #CHECK#CONFIG_TREE_RCU=y +#CHECK#CONFIG_PREEMPT_RCU=n CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 index 9f48c73709ec..61d15b1b54d1 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 @@ -1,6 +1,8 @@ CONFIG_SMP=y CONFIG_NR_CPUS=8 -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_DYNAMIC=n +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n #CHECK#CONFIG_TREE_RCU=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 index db27651de04b..0e090bb68a0f 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 @@ -1,9 +1,12 @@ CONFIG_SMP=y CONFIG_NR_CPUS=8 -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_DYNAMIC=n +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n #CHECK#CONFIG_TREE_RCU=y +#CHECK#CONFIG_PREEMPT_RCU=n CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE10 b/tools/testing/selftests/rcutorture/configs/rcu/TREE10 index 420632b030dc..b2ce37861e71 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE10 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE10 @@ -6,6 +6,7 @@ CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n #CHECK#CONFIG_TREE_RCU=y +CONFIG_PREEMPT_RCU=n CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL b/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL index 5d546efa68e8..696fba9968c6 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL +++ b/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL @@ -1,6 +1,8 @@ CONFIG_SMP=y CONFIG_NR_CPUS=8 -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_DYNAMIC=n +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_HZ_PERIODIC=n diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TINY b/tools/testing/selftests/rcutorture/configs/rcuscale/TINY index 0fa2dc086e10..c1a7d38823fb 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuscale/TINY +++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TINY @@ -1,5 +1,6 @@ CONFIG_SMP=n -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 index 0059592c7408..f3f1368b8386 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 +++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 @@ -1,5 +1,6 @@ CONFIG_SMP=y -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT index 67f9d2998afd..1f215e17cbae 100644 --- a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT +++ b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT @@ -1,5 +1,6 @@ CONFIG_SMP=y -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/rcutorture/configs/refscale/TINY b/tools/testing/selftests/rcutorture/configs/refscale/TINY index 759343980b80..9a11b578ff34 100644 --- a/tools/testing/selftests/rcutorture/configs/refscale/TINY +++ b/tools/testing/selftests/rcutorture/configs/refscale/TINY @@ -1,5 +1,6 @@ CONFIG_SMP=n -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT index 6133f54ce2a7..f9621e2770a4 100644 --- a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT +++ b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT @@ -1,5 +1,6 @@ CONFIG_SMP=y -CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_LAZY=y +CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n CONFIG_PREEMPT_DYNAMIC=n diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index 2c601a7eaff5..006300ac6dff 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -93,6 +93,8 @@ BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) \ $(CLANG_SYS_INCLUDES) \ -Wall -Wno-compare-distinct-pointer-types \ -Wno-incompatible-function-pointer-types \ + -Wno-microsoft-anon-tag \ + -fms-extensions \ -O2 -mcpu=v3 # sort removes libbpf duplicates when not cross-building diff --git a/tools/testing/selftests/sched_ext/init_enable_count.c b/tools/testing/selftests/sched_ext/init_enable_count.c index 82c71653977b..44577e30e764 100644 --- a/tools/testing/selftests/sched_ext/init_enable_count.c +++ b/tools/testing/selftests/sched_ext/init_enable_count.c @@ -57,7 +57,8 @@ static enum scx_test_status run_test(bool global) char buf; close(pipe_fds[1]); - read(pipe_fds[0], &buf, 1); + if (read(pipe_fds[0], &buf, 1) < 0) + exit(1); close(pipe_fds[0]); exit(0); } diff --git a/tools/testing/selftests/sched_ext/peek_dsq.bpf.c b/tools/testing/selftests/sched_ext/peek_dsq.bpf.c index a3faf5bb49d6..784f2f6c1af9 100644 --- a/tools/testing/selftests/sched_ext/peek_dsq.bpf.c +++ b/tools/testing/selftests/sched_ext/peek_dsq.bpf.c @@ -58,14 +58,14 @@ static void record_peek_result(long pid) { u32 slot_key; long *slot_pid_ptr; - int ix; + u32 ix; if (pid <= 0) return; /* Find an empty slot or one with the same PID */ bpf_for(ix, 0, 10) { - slot_key = (pid + ix) % MAX_SAMPLES; + slot_key = ((u64)pid + ix) % MAX_SAMPLES; slot_pid_ptr = bpf_map_lookup_elem(&peek_results, &slot_key); if (!slot_pid_ptr) continue; diff --git a/tools/testing/selftests/sched_ext/rt_stall.c b/tools/testing/selftests/sched_ext/rt_stall.c index ab772e336f86..81ea9b4883e5 100644 --- a/tools/testing/selftests/sched_ext/rt_stall.c +++ b/tools/testing/selftests/sched_ext/rt_stall.c @@ -15,7 +15,6 @@ #include #include #include -#include #include "rt_stall.bpf.skel.h" #include "scx_test.h" #include "../kselftest.h" diff --git a/tools/testing/selftests/sched_ext/runner.c b/tools/testing/selftests/sched_ext/runner.c index 5748d2c69903..761c21f96404 100644 --- a/tools/testing/selftests/sched_ext/runner.c +++ b/tools/testing/selftests/sched_ext/runner.c @@ -166,6 +166,9 @@ int main(int argc, char **argv) enum scx_test_status status; struct scx_test *test = &__scx_tests[i]; + if (exit_req) + break; + if (list) { printf("%s\n", test->name); if (i == (__scx_num_tests - 1)) diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json index 7d07c55bb668..33bb8f3ff8ed 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json @@ -505,5 +505,164 @@ "teardown": [ "$TC qdisc del dev $DEV1 ingress" ] + }, + { + "id": "8883", + "name": "Try to attach act_ct to an ets qdisc", + "category": [ + "actions", + "ct" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ct", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 root handle 1: ets bands 2" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: prio 1 protocol ip matchall action ct index 42", + "expExitCode": "2", + "verifyCmd": "$TC -j filter ls dev $DEV1 parent 1: prio 1 protocol ip", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DEV1 root" + ] + }, + { + "id": "3b10", + "name": "Attach act_ct to an ingress qdisc", + "category": [ + "actions", + "ct" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ct", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 ingress prio 1 protocol ip matchall action ct index 42", + "expExitCode": "0", + "verifyCmd": "$TC -j filter ls dev $DEV1 ingress prio 1 protocol ip", + "matchJSON": [ + { + "kind": "matchall" + }, + { + "options": { + "actions": [ + { + "order": 1, + "kind": "ct", + "index": 42, + "ref": 1, + "bind": 1 + } + ] + } + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "0337", + "name": "Attach act_ct to a clsact/egress qdisc", + "category": [ + "actions", + "ct" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ct", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 clsact" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 egress prio 1 protocol ip matchall action ct index 42", + "expExitCode": "0", + "verifyCmd": "$TC -j filter ls dev $DEV1 egress prio 1 protocol ip", + "matchJSON": [ + { + "kind": "matchall" + }, + { + "options": { + "actions": [ + { + "order": 1, + "kind": "ct", + "index": 42, + "ref": 1, + "bind": 1 + } + ] + } + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 clsact" + ] + }, + { + "id": "4f60", + "name": "Attach act_ct to a shared block", + "category": [ + "actions", + "ct" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ct", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 ingress_block 21 clsact" + ], + "cmdUnderTest": "$TC filter add block 21 prio 1 protocol ip matchall action ct index 42", + "expExitCode": "0", + "verifyCmd": "$TC -j filter ls block 21 prio 1 protocol ip", + "matchJSON": [ + { + "kind": "matchall" + }, + { + "options": { + "actions": [ + { + "order": 1, + "kind": "ct", + "index": 42, + "ref": 1, + "bind": 1 + } + ] + } + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 ingress_block 21 clsact" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json index f587a32e44c4..808aef4afe22 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json @@ -1279,5 +1279,104 @@ "teardown": [ "$TC actions flush action ife" ] + }, + { + "id": "f2a0", + "name": "Update decode ife action with encode metadata", + "category": [ + "actions", + "ife" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife decode index 10" + ], + "cmdUnderTest": "$TC actions replace action ife encode use tcindex 1 index 10", + "expExitCode": "0", + "verifyCmd": "$TC -j actions get action ife index 10", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "ife", + "mode": "encode", + "control_action": { + "type": "pipe" + }, + "type": "0xed3e", + "tcindex": 1, + "index": 10, + "ref": 1, + "bind": 0, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "d352", + "name": "Update decode ife action into encode with multiple metadata", + "category": [ + "actions", + "ife" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife decode index 10" + ], + "cmdUnderTest": "$TC actions replace action ife encode use tcindex 1 use mark 22 index 10", + "expExitCode": "0", + "verifyCmd": "$TC -j actions get action ife index 10", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "ife", + "mode": "encode", + "control_action": { + "type": "pipe" + }, + "type": "0xed3e", + "tcindex": 1, + "mark": 22, + "index": 10, + "ref": 1, + "bind": 0, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC actions flush action ife" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tdc_helper.py b/tools/testing/selftests/tc-testing/tdc_helper.py index 0440d252c4c5..bc447ca57333 100644 --- a/tools/testing/selftests/tc-testing/tdc_helper.py +++ b/tools/testing/selftests/tc-testing/tdc_helper.py @@ -38,10 +38,14 @@ def list_test_cases(testlist): def list_categories(testlist): - """ Show all categories that are present in a test case file. """ - categories = set(map(lambda x: x['category'], testlist)) + """Show all unique categories present in the test cases.""" + categories = set() + for t in testlist: + if 'category' in t: + categories.update(t['category']) + print("Available categories:") - print(", ".join(str(s) for s in categories)) + print(", ".join(sorted(categories))) print("")