diff options
202 files changed, 2003 insertions, 1221 deletions
@@ -27,6 +27,7 @@ Alan Cox <alan@lxorguk.ukuu.org.uk> Alan Cox <root@hraefn.swansea.linux.org.uk> Aleksandar Markovic <aleksandar.markovic@mips.com> <aleksandar.markovic@imgtec.com> Aleksey Gorelov <aleksey_gorelov@phoenix.com> +Alex Williamson <alex@shazbot.org> <alex.williamson@redhat.com> Alexander Lobakin <alobakin@pm.me> <alobakin@dlink.ru> Alexander Lobakin <alobakin@pm.me> <alobakin@marvell.com> Alexander Lobakin <alobakin@pm.me> <bloodyreaper@yandex.ru> diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml index a58370a6a5d3..fba7b2549dde 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml @@ -24,6 +24,10 @@ properties: - enum: - qcom,qcs8300-qmp-ufs-phy - const: qcom,sa8775p-qmp-ufs-phy + - items: + - enum: + - qcom,kaanapali-qmp-ufs-phy + - const: qcom,sm8750-qmp-ufs-phy - enum: - qcom,msm8996-qmp-ufs-phy - qcom,msm8998-qmp-ufs-phy diff --git a/Documentation/devicetree/bindings/spi/spi-cadence.yaml b/Documentation/devicetree/bindings/spi/spi-cadence.yaml index 8de96abe9da1..27414b78d61d 100644 --- a/Documentation/devicetree/bindings/spi/spi-cadence.yaml +++ b/Documentation/devicetree/bindings/spi/spi-cadence.yaml @@ -14,9 +14,14 @@ allOf: properties: compatible: - enum: - - cdns,spi-r1p6 - - xlnx,zynq-spi-r1p6 + oneOf: + - enum: + - xlnx,zynq-spi-r1p6 + - items: + - enum: + - xlnx,zynqmp-spi-r1p6 + - xlnx,versal-net-spi-r1p6 + - const: cdns,spi-r1p6 reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/spi/spi-rockchip.yaml b/Documentation/devicetree/bindings/spi/spi-rockchip.yaml index 748faf7f7081..ce6762c92fda 100644 --- a/Documentation/devicetree/bindings/spi/spi-rockchip.yaml +++ b/Documentation/devicetree/bindings/spi/spi-rockchip.yaml @@ -34,6 +34,7 @@ properties: - rockchip,rk3328-spi - rockchip,rk3368-spi - rockchip,rk3399-spi + - rockchip,rk3506-spi - rockchip,rk3528-spi - rockchip,rk3562-spi - rockchip,rk3568-spi diff --git a/Documentation/devicetree/bindings/ufs/qcom,sm8650-ufshc.yaml b/Documentation/devicetree/bindings/ufs/qcom,sm8650-ufshc.yaml index aaa0bbb5bfe1..cea84ab2204f 100644 --- a/Documentation/devicetree/bindings/ufs/qcom,sm8650-ufshc.yaml +++ b/Documentation/devicetree/bindings/ufs/qcom,sm8650-ufshc.yaml @@ -15,6 +15,7 @@ select: compatible: contains: enum: + - qcom,kaanapali-ufshc - qcom,sm8650-ufshc - qcom,sm8750-ufshc required: @@ -24,6 +25,7 @@ properties: compatible: items: - enum: + - qcom,kaanapali-ufshc - qcom,sm8650-ufshc - qcom,sm8750-ufshc - const: qcom,ufshc diff --git a/Documentation/networking/ax25.rst b/Documentation/networking/ax25.rst index 605e72c6c877..89c79dd6c6f9 100644 --- a/Documentation/networking/ax25.rst +++ b/Documentation/networking/ax25.rst @@ -11,6 +11,7 @@ found on https://linux-ax25.in-berlin.de. There is a mailing list for discussing Linux amateur radio matters called linux-hams@vger.kernel.org. To subscribe to it, send a message to -majordomo@vger.kernel.org with the words "subscribe linux-hams" in the body -of the message, the subject field is ignored. You don't need to be -subscribed to post but of course that means you might miss an answer. +linux-hams+subscribe@vger.kernel.org or use the web interface at +https://vger.kernel.org. The subject and body of the message are +ignored. You don't need to be subscribed to post but of course that +means you might miss an answer. diff --git a/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst b/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst index 289c146a8291..6877a3260582 100644 --- a/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst +++ b/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst @@ -137,16 +137,20 @@ d. Checksum offload header v5 Checksum offload header fields are in big endian format. +Packet format:: + Bit 0 - 6 7 8-15 16-31 Function Header Type Next Header Checksum Valid Reserved Header Type is to indicate the type of header, this usually is set to CHECKSUM Header types -= ========================================== + += =============== 0 Reserved 1 Reserved 2 checksum header += =============== Checksum Valid is to indicate whether the header checksum is valid. Value of 1 implies that checksum is calculated on this packet and is valid, value of 0 @@ -183,9 +187,11 @@ rmnet in a single linear skb. rmnet will process the individual packets and either ACK the MAP command or deliver the IP packet to the network stack as needed -MAP header|IP Packet|Optional padding|MAP header|IP Packet|Optional padding.... +Packet format:: + + MAP header|IP Packet|Optional padding|MAP header|IP Packet|Optional padding.... -MAP header|IP Packet|Optional padding|MAP header|Command Packet|Optional pad... + MAP header|IP Packet|Optional padding|MAP header|Command Packet|Optional pad... 3. Userspace configuration ========================== diff --git a/Documentation/networking/net_failover.rst b/Documentation/networking/net_failover.rst index f4e1b4e07adc..2f776e90d318 100644 --- a/Documentation/networking/net_failover.rst +++ b/Documentation/networking/net_failover.rst @@ -96,9 +96,8 @@ needed to these network configuration daemons to make sure that an IP is received only on the 'failover' device. Below is the patch snippet used with 'cloud-ifupdown-helper' script found on -Debian cloud images: +Debian cloud images:: -:: @@ -27,6 +27,8 @@ do_setup() { local working="$cfgdir/.$INTERFACE" local final="$cfgdir/$INTERFACE" @@ -172,9 +171,8 @@ appropriate FDB entry is added. The following script is executed on the destination hypervisor once migration completes, and it reattaches the VF to the VM and brings down the virtio-net -interface. +interface:: -:: # reattach-vf.sh #!/bin/bash diff --git a/MAINTAINERS b/MAINTAINERS index 545a4776795e..3da2c26a796b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1997,6 +1997,10 @@ F: include/uapi/linux/if_arcnet.h ARM AND ARM64 SoC SUB-ARCHITECTURES (COMMON PARTS) M: Arnd Bergmann <arnd@arndb.de> +M: Krzysztof Kozlowski <krzk@kernel.org> +M: Alexandre Belloni <alexandre.belloni@bootlin.com> +M: Linus Walleij <linus.walleij@linaro.org> +R: Drew Fustini <fustini@kernel.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: soc@lists.linux.dev S: Maintained @@ -3841,6 +3845,7 @@ F: drivers/hwmon/asus-ec-sensors.c ASUS NOTEBOOKS AND EEEPC ACPI/WMI EXTRAS DRIVERS M: Corentin Chary <corentin.chary@gmail.com> M: Luke D. Jones <luke@ljones.dev> +M: Denis Benato <benato.denis96@gmail.com> L: platform-driver-x86@vger.kernel.org S: Maintained W: https://asus-linux.org/ @@ -13111,6 +13116,15 @@ F: include/uapi/linux/io_uring.h F: include/uapi/linux/io_uring/ F: io_uring/ +IO_URING ZCRX +M: Pavel Begunkov <asml.silence@gmail.com> +L: io-uring@vger.kernel.org +L: netdev@vger.kernel.org +T: git https://github.com/isilence/linux.git zcrx/for-next +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux.git +S: Maintained +F: io_uring/zcrx.* + IPMI SUBSYSTEM M: Corey Minyard <corey@minyard.net> L: openipmi-developer@lists.sourceforge.net (moderated for non-subscribers) @@ -14394,6 +14408,7 @@ F: tools/memory-model/ LINUX-NEXT TREE M: Stephen Rothwell <sfr@canb.auug.org.au> +M: Mark Brown <broonie@kernel.org> L: linux-next@vger.kernel.org S: Supported B: mailto:linux-next@vger.kernel.org and the appropriate development tree @@ -26885,7 +26900,7 @@ S: Maintained F: drivers/vfio/cdx/* VFIO DRIVER -M: Alex Williamson <alex.williamson@redhat.com> +M: Alex Williamson <alex@shazbot.org> L: kvm@vger.kernel.org S: Maintained T: git https://github.com/awilliam/linux-vfio.git @@ -27048,7 +27063,7 @@ T: git git://linuxtv.org/media.git F: drivers/media/test-drivers/vimc/* VIRT LIB -M: Alex Williamson <alex.williamson@redhat.com> +M: Alex Williamson <alex@shazbot.org> M: Paolo Bonzini <pbonzini@redhat.com> L: kvm@vger.kernel.org S: Supported diff --git a/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi b/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi index c78ed064d166..1eb6406449d1 100644 --- a/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi +++ b/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi @@ -77,6 +77,14 @@ /delete-property/ pinctrl-0; }; +&pm { + clocks = <&firmware_clocks 5>, + <&clocks BCM2835_CLOCK_PERI_IMAGE>, + <&clocks BCM2835_CLOCK_H264>, + <&clocks BCM2835_CLOCK_ISP>; + clock-names = "v3d", "peri_image", "h264", "isp"; +}; + &rmem { /* * RPi4's co-processor will copy the board's bootloader configuration diff --git a/arch/arm/boot/dts/broadcom/bcm2835-rpi-common.dtsi b/arch/arm/boot/dts/broadcom/bcm2835-rpi-common.dtsi index 8b3c21d9f333..fa9d784c88b6 100644 --- a/arch/arm/boot/dts/broadcom/bcm2835-rpi-common.dtsi +++ b/arch/arm/boot/dts/broadcom/bcm2835-rpi-common.dtsi @@ -13,7 +13,16 @@ clock-names = "pixel", "hdmi"; }; +&pm { + clocks = <&firmware_clocks 5>, + <&clocks BCM2835_CLOCK_PERI_IMAGE>, + <&clocks BCM2835_CLOCK_H264>, + <&clocks BCM2835_CLOCK_ISP>; + clock-names = "v3d", "peri_image", "h264", "isp"; +}; + &v3d { + clocks = <&firmware_clocks 5>; power-domains = <&power RPI_POWER_DOMAIN_V3D>; }; diff --git a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi index e77a66adc22a..205b87f557d6 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi @@ -326,6 +326,8 @@ <0x7fffe000 0x2000>; interrupt-controller; #address-cells = <0>; + interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(4) | + IRQ_TYPE_LEVEL_HIGH)>; #interrupt-cells = <3>; }; diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index aa89c2e67ebc..0944e296dd4a 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -293,7 +293,8 @@ static inline pmd_t set_pmd_bit(pmd_t pmd, pgprot_t prot) static inline pte_t pte_mkwrite_novma(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_WRITE)); - pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); + if (pte_sw_dirty(pte)) + pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c index a86c897017df..cd5912ba617b 100644 --- a/arch/arm64/mm/copypage.c +++ b/arch/arm64/mm/copypage.c @@ -35,7 +35,7 @@ void copy_highpage(struct page *to, struct page *from) from != folio_page(src, 0)) return; - WARN_ON_ONCE(!folio_try_hugetlb_mte_tagging(dst)); + folio_try_hugetlb_mte_tagging(dst); /* * Populate tags for all subpages. @@ -51,8 +51,13 @@ void copy_highpage(struct page *to, struct page *from) } folio_set_hugetlb_mte_tagged(dst); } else if (page_mte_tagged(from)) { - /* It's a new page, shouldn't have been tagged yet */ - WARN_ON_ONCE(!try_page_mte_tagging(to)); + /* + * Most of the time it's a new page that shouldn't have been + * tagged yet. However, folio migration can end up reusing the + * same page without untagging it. Ignore the warning if the + * page is already tagged. + */ + try_page_mte_tagging(to); mte_copy_page_tags(kto, kfrom); set_page_mte_tagged(to); diff --git a/arch/csky/abiv2/cacheflush.c b/arch/csky/abiv2/cacheflush.c index 876028b1083f..064b0f0f95ca 100644 --- a/arch/csky/abiv2/cacheflush.c +++ b/arch/csky/abiv2/cacheflush.c @@ -21,7 +21,7 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, folio = page_folio(pfn_to_page(pfn)); - if (test_and_set_bit(PG_dcache_clean, &folio->flags)) + if (test_and_set_bit(PG_dcache_clean, &folio->flags.f)) return; icache_inv_range(address, address + nr*PAGE_SIZE); diff --git a/arch/csky/abiv2/inc/abi/cacheflush.h b/arch/csky/abiv2/inc/abi/cacheflush.h index 6513ac5d2578..da51a0f02391 100644 --- a/arch/csky/abiv2/inc/abi/cacheflush.h +++ b/arch/csky/abiv2/inc/abi/cacheflush.h @@ -20,8 +20,8 @@ static inline void flush_dcache_folio(struct folio *folio) { - if (test_bit(PG_dcache_clean, &folio->flags)) - clear_bit(PG_dcache_clean, &folio->flags); + if (test_bit(PG_dcache_clean, &folio->flags.f)) + clear_bit(PG_dcache_clean, &folio->flags.f); } #define flush_dcache_folio flush_dcache_folio diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c index 3a2836e9d856..816570514c37 100644 --- a/arch/mips/mti-malta/malta-setup.c +++ b/arch/mips/mti-malta/malta-setup.c @@ -47,7 +47,7 @@ static struct resource standard_io_resources[] = { .name = "keyboard", .start = 0x60, .end = 0x6f, - .flags = IORESOURCE_IO | IORESOURCE_BUSY + .flags = IORESOURCE_IO }, { .name = "dma page reg", @@ -213,7 +213,7 @@ void __init plat_mem_setup(void) /* Request I/O space for devices used on the Malta board. */ for (i = 0; i < ARRAY_SIZE(standard_io_resources); i++) - request_resource(&ioport_resource, standard_io_resources+i); + insert_resource(&ioport_resource, standard_io_resources + i); /* * Enable DMA channel 4 (cascade channel) in the PIIX4 south bridge. diff --git a/arch/mips/pci/pci-malta.c b/arch/mips/pci/pci-malta.c index 6aefdf20ca05..2e35aeba45bc 100644 --- a/arch/mips/pci/pci-malta.c +++ b/arch/mips/pci/pci-malta.c @@ -230,8 +230,7 @@ void __init mips_pcibios_init(void) } /* PIIX4 ACPI starts at 0x1000 */ - if (controller->io_resource->start < 0x00001000UL) - controller->io_resource->start = 0x00001000UL; + PCIBIOS_MIN_IO = 0x1000; iomem_resource.end &= 0xfffffffffULL; /* 64 GB */ ioport_resource.end = controller->io_resource->end; diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h index 8bd2a11382a3..ac28066bb564 100644 --- a/arch/riscv/include/asm/asm.h +++ b/arch/riscv/include/asm/asm.h @@ -84,15 +84,9 @@ .endm #ifdef CONFIG_SMP -#ifdef CONFIG_32BIT -#define PER_CPU_OFFSET_SHIFT 2 -#else -#define PER_CPU_OFFSET_SHIFT 3 -#endif - .macro asm_per_cpu dst sym tmp lw \tmp, TASK_TI_CPU_NUM(tp) - slli \tmp, \tmp, PER_CPU_OFFSET_SHIFT + slli \tmp, \tmp, RISCV_LGPTR la \dst, __per_cpu_offset add \dst, \dst, \tmp REG_L \tmp, 0(\dst) diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index fbd0e4306c93..62837fa981e8 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -31,6 +31,8 @@ struct riscv_isainfo { DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); +extern const struct seq_operations cpuinfo_op; + /* Per-cpu ISA extensions. */ extern struct riscv_isainfo hart_isa[NR_CPUS]; diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h index 948d2b34e94e..58f8dda73259 100644 --- a/arch/riscv/include/asm/hwprobe.h +++ b/arch/riscv/include/asm/hwprobe.h @@ -42,4 +42,11 @@ static inline bool riscv_hwprobe_pair_cmp(struct riscv_hwprobe *pair, return pair->value == other_pair->value; } +#ifdef CONFIG_MMU +void riscv_hwprobe_register_async_probe(void); +void riscv_hwprobe_complete_async_probe(void); +#else +static inline void riscv_hwprobe_register_async_probe(void) {} +static inline void riscv_hwprobe_complete_async_probe(void) {} +#endif #endif diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index 1018d2216901..6e789fa58514 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -69,6 +69,8 @@ typedef struct { #define PTRS_PER_PMD (PAGE_SIZE / sizeof(pmd_t)) +#define MAX_POSSIBLE_PHYSMEM_BITS 56 + /* * rv64 PTE format: * | 63 | 62 61 | 60 54 | 53 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 29e994a9afb6..5a08eb5fe99f 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -654,6 +654,8 @@ static inline pgprot_t pgprot_writecombine(pgprot_t _prot) return __pgprot(prot); } +#define pgprot_dmacoherent pgprot_writecombine + /* * Both Svade and Svadu control the hardware behavior when the PTE A/D bits need to be set. By * default the M-mode firmware enables the hardware updating scheme when only Svadu is present in diff --git a/arch/riscv/include/asm/vdso/arch_data.h b/arch/riscv/include/asm/vdso/arch_data.h index da57a3786f7a..88b37af55175 100644 --- a/arch/riscv/include/asm/vdso/arch_data.h +++ b/arch/riscv/include/asm/vdso/arch_data.h @@ -12,6 +12,12 @@ struct vdso_arch_data { /* Boolean indicating all CPUs have the same static hwprobe values. */ __u8 homogeneous_cpus; + + /* + * A gate to check and see if the hwprobe data is actually ready, as + * probing is deferred to avoid boot slowdowns. + */ + __u8 ready; }; #endif /* __RISCV_ASM_VDSO_ARCH_DATA_H */ diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index f6b13e9f5e6c..3dbc8cc557dd 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -62,10 +62,8 @@ int __init riscv_early_of_processor_hartid(struct device_node *node, unsigned lo return -ENODEV; } - if (!of_device_is_available(node)) { - pr_info("CPU with hartid=%lu is not available\n", *hart); + if (!of_device_is_available(node)) return -ENODEV; - } if (of_property_read_string(node, "riscv,isa-base", &isa)) goto old_interface; diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 67b59699357d..72ca768f4e91 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -932,9 +932,9 @@ static int has_thead_homogeneous_vlenb(void) { int cpu; u32 prev_vlenb = 0; - u32 vlenb; + u32 vlenb = 0; - /* Ignore thead,vlenb property if xtheavector is not enabled in the kernel */ + /* Ignore thead,vlenb property if xtheadvector is not enabled in the kernel */ if (!IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) return 0; diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index e650dec44817..5ed5095320e6 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -40,6 +40,17 @@ enum ipi_message_type { IPI_MAX }; +static const char * const ipi_names[] = { + [IPI_RESCHEDULE] = "Rescheduling interrupts", + [IPI_CALL_FUNC] = "Function call interrupts", + [IPI_CPU_STOP] = "CPU stop interrupts", + [IPI_CPU_CRASH_STOP] = "CPU stop (for crash dump) interrupts", + [IPI_IRQ_WORK] = "IRQ work interrupts", + [IPI_TIMER] = "Timer broadcast interrupts", + [IPI_CPU_BACKTRACE] = "CPU backtrace interrupts", + [IPI_KGDB_ROUNDUP] = "KGDB roundup interrupts", +}; + unsigned long __cpuid_to_hartid_map[NR_CPUS] __ro_after_init = { [0 ... NR_CPUS-1] = INVALID_HARTID }; @@ -199,7 +210,7 @@ void riscv_ipi_set_virq_range(int virq, int nr) /* Request IPIs */ for (i = 0; i < nr_ipi; i++) { err = request_percpu_irq(ipi_virq_base + i, handle_IPI, - "IPI", &ipi_dummy_dev); + ipi_names[i], &ipi_dummy_dev); WARN_ON(err); ipi_desc[i] = irq_to_desc(ipi_virq_base + i); @@ -210,17 +221,6 @@ void riscv_ipi_set_virq_range(int virq, int nr) riscv_ipi_enable(); } -static const char * const ipi_names[] = { - [IPI_RESCHEDULE] = "Rescheduling interrupts", - [IPI_CALL_FUNC] = "Function call interrupts", - [IPI_CPU_STOP] = "CPU stop interrupts", - [IPI_CPU_CRASH_STOP] = "CPU stop (for crash dump) interrupts", - [IPI_IRQ_WORK] = "IRQ work interrupts", - [IPI_TIMER] = "Timer broadcast interrupts", - [IPI_CPU_BACKTRACE] = "CPU backtrace interrupts", - [IPI_KGDB_ROUNDUP] = "KGDB roundup interrupts", -}; - void show_ipi_stats(struct seq_file *p, int prec) { unsigned int cpu, i; diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c index 000f4451a9d8..199d13f86f31 100644 --- a/arch/riscv/kernel/sys_hwprobe.c +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -5,6 +5,9 @@ * more details. */ #include <linux/syscalls.h> +#include <linux/completion.h> +#include <linux/atomic.h> +#include <linux/once.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/hwprobe.h> @@ -28,6 +31,11 @@ static void hwprobe_arch_id(struct riscv_hwprobe *pair, bool first = true; int cpu; + if (pair->key != RISCV_HWPROBE_KEY_MVENDORID && + pair->key != RISCV_HWPROBE_KEY_MIMPID && + pair->key != RISCV_HWPROBE_KEY_MARCHID) + goto out; + for_each_cpu(cpu, cpus) { u64 cpu_id; @@ -58,6 +66,7 @@ static void hwprobe_arch_id(struct riscv_hwprobe *pair, } } +out: pair->value = id; } @@ -454,28 +463,32 @@ static int hwprobe_get_cpus(struct riscv_hwprobe __user *pairs, return 0; } -static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs, - size_t pair_count, size_t cpusetsize, - unsigned long __user *cpus_user, - unsigned int flags) -{ - if (flags & RISCV_HWPROBE_WHICH_CPUS) - return hwprobe_get_cpus(pairs, pair_count, cpusetsize, - cpus_user, flags); +#ifdef CONFIG_MMU - return hwprobe_get_values(pairs, pair_count, cpusetsize, - cpus_user, flags); +static DECLARE_COMPLETION(boot_probes_done); +static atomic_t pending_boot_probes = ATOMIC_INIT(1); + +void riscv_hwprobe_register_async_probe(void) +{ + atomic_inc(&pending_boot_probes); } -#ifdef CONFIG_MMU +void riscv_hwprobe_complete_async_probe(void) +{ + if (atomic_dec_and_test(&pending_boot_probes)) + complete(&boot_probes_done); +} -static int __init init_hwprobe_vdso_data(void) +static int complete_hwprobe_vdso_data(void) { struct vdso_arch_data *avd = vdso_k_arch_data; u64 id_bitsmash = 0; struct riscv_hwprobe pair; int key; + if (unlikely(!atomic_dec_and_test(&pending_boot_probes))) + wait_for_completion(&boot_probes_done); + /* * Initialize vDSO data with the answers for the "all CPUs" case, to * save a syscall in the common case. @@ -503,13 +516,52 @@ static int __init init_hwprobe_vdso_data(void) * vDSO should defer to the kernel for exotic cpu masks. */ avd->homogeneous_cpus = id_bitsmash != 0 && id_bitsmash != -1; + + /* + * Make sure all the VDSO values are visible before we look at them. + * This pairs with the implicit "no speculativly visible accesses" + * barrier in the VDSO hwprobe code. + */ + smp_wmb(); + avd->ready = true; + return 0; +} + +static int __init init_hwprobe_vdso_data(void) +{ + struct vdso_arch_data *avd = vdso_k_arch_data; + + /* + * Prevent the vDSO cached values from being used, as they're not ready + * yet. + */ + avd->ready = false; return 0; } arch_initcall_sync(init_hwprobe_vdso_data); +#else + +static int complete_hwprobe_vdso_data(void) { return 0; } + #endif /* CONFIG_MMU */ +static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs, + size_t pair_count, size_t cpusetsize, + unsigned long __user *cpus_user, + unsigned int flags) +{ + DO_ONCE_SLEEPABLE(complete_hwprobe_vdso_data); + + if (flags & RISCV_HWPROBE_WHICH_CPUS) + return hwprobe_get_cpus(pairs, pair_count, cpusetsize, + cpus_user, flags); + + return hwprobe_get_values(pairs, pair_count, cpusetsize, + cpus_user, flags); +} + SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs, size_t, pair_count, size_t, cpusetsize, unsigned long __user *, cpus, unsigned int, flags) diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c index ae2068425fbc..70b5e6927620 100644 --- a/arch/riscv/kernel/unaligned_access_speed.c +++ b/arch/riscv/kernel/unaligned_access_speed.c @@ -379,6 +379,7 @@ free: static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused) { schedule_on_each_cpu(check_vector_unaligned_access); + riscv_hwprobe_complete_async_probe(); return 0; } @@ -473,8 +474,12 @@ static int __init check_unaligned_access_all_cpus(void) per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param; } else if (!check_vector_unaligned_access_emulated_all_cpus() && IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) { - kthread_run(vec_check_unaligned_access_speed_all_cpus, - NULL, "vec_check_unaligned_access_speed_all_cpus"); + riscv_hwprobe_register_async_probe(); + if (IS_ERR(kthread_run(vec_check_unaligned_access_speed_all_cpus, + NULL, "vec_check_unaligned_access_speed_all_cpus"))) { + pr_warn("Failed to create vec_unalign_check kthread\n"); + riscv_hwprobe_complete_async_probe(); + } } /* diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c index 2ddeba6c68dd..8f45500d0a6e 100644 --- a/arch/riscv/kernel/vdso/hwprobe.c +++ b/arch/riscv/kernel/vdso/hwprobe.c @@ -27,7 +27,7 @@ static int riscv_vdso_get_values(struct riscv_hwprobe *pairs, size_t pair_count, * homogeneous, then this function can handle requests for arbitrary * masks. */ - if ((flags != 0) || (!all_cpus && !avd->homogeneous_cpus)) + if (flags != 0 || (!all_cpus && !avd->homogeneous_cpus) || unlikely(!avd->ready)) return riscv_hwprobe(pairs, pair_count, cpusetsize, cpus, flags); /* This is something we can handle, fill out the pairs. */ diff --git a/block/blk-settings.c b/block/blk-settings.c index 54cffaae4df4..d74b13ec8e54 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -184,6 +184,16 @@ static int blk_validate_integrity_limits(struct queue_limits *lim) if (!bi->interval_exp) bi->interval_exp = ilog2(lim->logical_block_size); + /* + * The PI generation / validation helpers do not expect intervals to + * straddle multiple bio_vecs. Enforce alignment so that those are + * never generated, and that each buffer is aligned as expected. + */ + if (bi->csum_type) { + lim->dma_alignment = max(lim->dma_alignment, + (1U << bi->interval_exp) - 1); + } + return 0; } diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c index 049f6c2f1e32..e5631027f7f1 100644 --- a/drivers/acpi/acpica/tbprint.c +++ b/drivers/acpi/acpica/tbprint.c @@ -95,6 +95,11 @@ acpi_tb_print_table_header(acpi_physical_address address, { struct acpi_table_header local_header; +#pragma GCC diagnostic push +#if defined(__GNUC__) && __GNUC__ >= 11 +#pragma GCC diagnostic ignored "-Wstringop-overread" +#endif + if (ACPI_COMPARE_NAMESEG(header->signature, ACPI_SIG_FACS)) { /* FACS only has signature and length fields */ @@ -143,4 +148,5 @@ acpi_tb_print_table_header(acpi_physical_address address, local_header.asl_compiler_id, local_header.asl_compiler_revision)); } +#pragma GCC diagnostic pop } diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 1b997a5497e7..43d5e457814e 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -1107,7 +1107,7 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, size_t num_args, struct fwnode_reference_args *args) { - return acpi_fwnode_get_reference_args(fwnode, propname, NULL, index, num_args, args); + return acpi_fwnode_get_reference_args(fwnode, propname, NULL, num_args, index, args); } EXPORT_SYMBOL_GPL(__acpi_node_get_property_reference); diff --git a/drivers/acpi/riscv/rimt.c b/drivers/acpi/riscv/rimt.c index 683fcfe35c31..7f423405e5ef 100644 --- a/drivers/acpi/riscv/rimt.c +++ b/drivers/acpi/riscv/rimt.c @@ -61,30 +61,6 @@ static int rimt_set_fwnode(struct acpi_rimt_node *rimt_node, return 0; } -/** - * rimt_get_fwnode() - Retrieve fwnode associated with an RIMT node - * - * @node: RIMT table node to be looked-up - * - * Returns: fwnode_handle pointer on success, NULL on failure - */ -static struct fwnode_handle *rimt_get_fwnode(struct acpi_rimt_node *node) -{ - struct fwnode_handle *fwnode = NULL; - struct rimt_fwnode *curr; - - spin_lock(&rimt_fwnode_lock); - list_for_each_entry(curr, &rimt_fwnode_list, list) { - if (curr->rimt_node == node) { - fwnode = curr->fwnode; - break; - } - } - spin_unlock(&rimt_fwnode_lock); - - return fwnode; -} - static acpi_status rimt_match_node_callback(struct acpi_rimt_node *node, void *context) { @@ -202,6 +178,67 @@ static struct acpi_rimt_node *rimt_scan_node(enum acpi_rimt_node_type type, return NULL; } +/* + * RISC-V supports IOMMU as a PCI device or a platform device. + * When it is a platform device, there should be a namespace device as + * well along with RIMT. To create the link between RIMT information and + * the platform device, the IOMMU driver should register itself with the + * RIMT module. This is true for PCI based IOMMU as well. + */ +int rimt_iommu_register(struct device *dev) +{ + struct fwnode_handle *rimt_fwnode; + struct acpi_rimt_node *node; + + node = rimt_scan_node(ACPI_RIMT_NODE_TYPE_IOMMU, dev); + if (!node) { + pr_err("Could not find IOMMU node in RIMT\n"); + return -ENODEV; + } + + if (dev_is_pci(dev)) { + rimt_fwnode = acpi_alloc_fwnode_static(); + if (!rimt_fwnode) + return -ENOMEM; + + rimt_fwnode->dev = dev; + if (!dev->fwnode) + dev->fwnode = rimt_fwnode; + + rimt_set_fwnode(node, rimt_fwnode); + } else { + rimt_set_fwnode(node, dev->fwnode); + } + + return 0; +} + +#ifdef CONFIG_IOMMU_API + +/** + * rimt_get_fwnode() - Retrieve fwnode associated with an RIMT node + * + * @node: RIMT table node to be looked-up + * + * Returns: fwnode_handle pointer on success, NULL on failure + */ +static struct fwnode_handle *rimt_get_fwnode(struct acpi_rimt_node *node) +{ + struct fwnode_handle *fwnode = NULL; + struct rimt_fwnode *curr; + + spin_lock(&rimt_fwnode_lock); + list_for_each_entry(curr, &rimt_fwnode_list, list) { + if (curr->rimt_node == node) { + fwnode = curr->fwnode; + break; + } + } + spin_unlock(&rimt_fwnode_lock); + + return fwnode; +} + static bool rimt_pcie_rc_supports_ats(struct acpi_rimt_node *node) { struct acpi_rimt_pcie_rc *pci_rc; @@ -290,43 +327,6 @@ static struct acpi_rimt_node *rimt_node_get_id(struct acpi_rimt_node *node, return NULL; } -/* - * RISC-V supports IOMMU as a PCI device or a platform device. - * When it is a platform device, there should be a namespace device as - * well along with RIMT. To create the link between RIMT information and - * the platform device, the IOMMU driver should register itself with the - * RIMT module. This is true for PCI based IOMMU as well. - */ -int rimt_iommu_register(struct device *dev) -{ - struct fwnode_handle *rimt_fwnode; - struct acpi_rimt_node *node; - - node = rimt_scan_node(ACPI_RIMT_NODE_TYPE_IOMMU, dev); - if (!node) { - pr_err("Could not find IOMMU node in RIMT\n"); - return -ENODEV; - } - - if (dev_is_pci(dev)) { - rimt_fwnode = acpi_alloc_fwnode_static(); - if (!rimt_fwnode) - return -ENOMEM; - - rimt_fwnode->dev = dev; - if (!dev->fwnode) - dev->fwnode = rimt_fwnode; - - rimt_set_fwnode(node, rimt_fwnode); - } else { - rimt_set_fwnode(node, dev->fwnode); - } - - return 0; -} - -#ifdef CONFIG_IOMMU_API - static struct acpi_rimt_node *rimt_node_map_id(struct acpi_rimt_node *node, u32 id_in, u32 *id_out, u8 type_mask) diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 1037169abb45..e1eff05bea4a 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -292,7 +292,7 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu) * frequency (by keeping the initial capacity_freq_ref value). */ cpu_clk = of_clk_get(cpu_node, 0); - if (!PTR_ERR_OR_ZERO(cpu_clk)) { + if (!IS_ERR_OR_NULL(cpu_clk)) { per_cpu(capacity_freq_ref, cpu) = clk_get_rate(cpu_clk) / HZ_PER_KHZ; clk_put(cpu_clk); diff --git a/drivers/base/core.c b/drivers/base/core.c index 3c533dab8fa5..f69dc9c85954 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1784,7 +1784,7 @@ static int fw_devlink_dev_sync_state(struct device *dev, void *data) return 0; if (fw_devlink_sync_state == FW_DEVLINK_SYNC_STATE_STRICT) { - dev_warn(sup, "sync_state() pending due to %s\n", + dev_info(sup, "sync_state() pending due to %s\n", dev_name(link->consumer)); return 0; } diff --git a/drivers/base/devcoredump.c b/drivers/base/devcoredump.c index 37faf6156d7c..55bdc7f5e59d 100644 --- a/drivers/base/devcoredump.c +++ b/drivers/base/devcoredump.c @@ -23,50 +23,46 @@ struct devcd_entry { void *data; size_t datalen; /* - * Here, mutex is required to serialize the calls to del_wk work between - * user/kernel space which happens when devcd is added with device_add() - * and that sends uevent to user space. User space reads the uevents, - * and calls to devcd_data_write() which try to modify the work which is - * not even initialized/queued from devcoredump. + * There are 2 races for which mutex is required. * + * The first race is between device creation and userspace writing to + * schedule immediately destruction. * + * This race is handled by arming the timer before device creation, but + * when device creation fails the timer still exists. * - * cpu0(X) cpu1(Y) + * To solve this, hold the mutex during device_add(), and set + * init_completed on success before releasing the mutex. * - * dev_coredump() uevent sent to user space - * device_add() ======================> user space process Y reads the - * uevents writes to devcd fd - * which results into writes to + * That way the timer will never fire until device_add() is called, + * it will do nothing if init_completed is not set. The timer is also + * cancelled in that case. * - * devcd_data_write() - * mod_delayed_work() - * try_to_grab_pending() - * timer_delete() - * debug_assert_init() - * INIT_DELAYED_WORK() - * schedule_delayed_work() - * - * - * Also, mutex alone would not be enough to avoid scheduling of - * del_wk work after it get flush from a call to devcd_free() - * mentioned as below. - * - * disabled_store() - * devcd_free() - * mutex_lock() devcd_data_write() - * flush_delayed_work() - * mutex_unlock() - * mutex_lock() - * mod_delayed_work() - * mutex_unlock() - * So, delete_work flag is required. + * The second race involves multiple parallel invocations of devcd_free(), + * add a deleted flag so only 1 can call the destructor. */ struct mutex mutex; - bool delete_work; + bool init_completed, deleted; struct module *owner; ssize_t (*read)(char *buffer, loff_t offset, size_t count, void *data, size_t datalen); void (*free)(void *data); + /* + * If nothing interferes and device_add() was returns success, + * del_wk will destroy the device after the timer fires. + * + * Multiple userspace processes can interfere in the working of the timer: + * - Writing to the coredump will reschedule the timer to run immediately, + * if still armed. + * + * This is handled by using "if (cancel_delayed_work()) { + * schedule_delayed_work() }", to prevent re-arming after having + * been previously fired. + * - Writing to /sys/class/devcoredump/disabled will destroy the + * coredump synchronously. + * This is handled by using disable_delayed_work_sync(), and then + * checking if deleted flag is set with &devcd->mutex held. + */ struct delayed_work del_wk; struct device *failing_dev; }; @@ -95,14 +91,27 @@ static void devcd_dev_release(struct device *dev) kfree(devcd); } +static void __devcd_del(struct devcd_entry *devcd) +{ + devcd->deleted = true; + device_del(&devcd->devcd_dev); + put_device(&devcd->devcd_dev); +} + static void devcd_del(struct work_struct *wk) { struct devcd_entry *devcd; + bool init_completed; devcd = container_of(wk, struct devcd_entry, del_wk.work); - device_del(&devcd->devcd_dev); - put_device(&devcd->devcd_dev); + /* devcd->mutex serializes against dev_coredumpm_timeout */ + mutex_lock(&devcd->mutex); + init_completed = devcd->init_completed; + mutex_unlock(&devcd->mutex); + + if (init_completed) + __devcd_del(devcd); } static ssize_t devcd_data_read(struct file *filp, struct kobject *kobj, @@ -122,12 +131,12 @@ static ssize_t devcd_data_write(struct file *filp, struct kobject *kobj, struct device *dev = kobj_to_dev(kobj); struct devcd_entry *devcd = dev_to_devcd(dev); - mutex_lock(&devcd->mutex); - if (!devcd->delete_work) { - devcd->delete_work = true; - mod_delayed_work(system_wq, &devcd->del_wk, 0); - } - mutex_unlock(&devcd->mutex); + /* + * Although it's tempting to use mod_delayed work here, + * that will cause a reschedule if the timer already fired. + */ + if (cancel_delayed_work(&devcd->del_wk)) + schedule_delayed_work(&devcd->del_wk, 0); return count; } @@ -151,11 +160,21 @@ static int devcd_free(struct device *dev, void *data) { struct devcd_entry *devcd = dev_to_devcd(dev); + /* + * To prevent a race with devcd_data_write(), disable work and + * complete manually instead. + * + * We cannot rely on the return value of + * disable_delayed_work_sync() here, because it might be in the + * middle of a cancel_delayed_work + schedule_delayed_work pair. + * + * devcd->mutex here guards against multiple parallel invocations + * of devcd_free(). + */ + disable_delayed_work_sync(&devcd->del_wk); mutex_lock(&devcd->mutex); - if (!devcd->delete_work) - devcd->delete_work = true; - - flush_delayed_work(&devcd->del_wk); + if (!devcd->deleted) + __devcd_del(devcd); mutex_unlock(&devcd->mutex); return 0; } @@ -179,12 +198,10 @@ static ssize_t disabled_show(const struct class *class, const struct class_attri * put_device() <- last reference * error = fn(dev, data) devcd_dev_release() * devcd_free(dev, data) kfree(devcd) - * mutex_lock(&devcd->mutex); * * * In the above diagram, it looks like disabled_store() would be racing with parallelly - * running devcd_del() and result in memory abort while acquiring devcd->mutex which - * is called after kfree of devcd memory after dropping its last reference with + * running devcd_del() and result in memory abort after dropping its last reference with * put_device(). However, this will not happens as fn(dev, data) runs * with its own reference to device via klist_node so it is not its last reference. * so, above situation would not occur. @@ -374,7 +391,7 @@ void dev_coredumpm_timeout(struct device *dev, struct module *owner, devcd->read = read; devcd->free = free; devcd->failing_dev = get_device(dev); - devcd->delete_work = false; + devcd->deleted = false; mutex_init(&devcd->mutex); device_initialize(&devcd->devcd_dev); @@ -383,8 +400,14 @@ void dev_coredumpm_timeout(struct device *dev, struct module *owner, atomic_inc_return(&devcd_count)); devcd->devcd_dev.class = &devcd_class; - mutex_lock(&devcd->mutex); dev_set_uevent_suppress(&devcd->devcd_dev, true); + + /* devcd->mutex prevents devcd_del() completing until init finishes */ + mutex_lock(&devcd->mutex); + devcd->init_completed = false; + INIT_DELAYED_WORK(&devcd->del_wk, devcd_del); + schedule_delayed_work(&devcd->del_wk, timeout); + if (device_add(&devcd->devcd_dev)) goto put_device; @@ -401,13 +424,20 @@ void dev_coredumpm_timeout(struct device *dev, struct module *owner, dev_set_uevent_suppress(&devcd->devcd_dev, false); kobject_uevent(&devcd->devcd_dev.kobj, KOBJ_ADD); - INIT_DELAYED_WORK(&devcd->del_wk, devcd_del); - schedule_delayed_work(&devcd->del_wk, timeout); + + /* + * Safe to run devcd_del() now that we are done with devcd_dev. + * Alternatively we could have taken a ref on devcd_dev before + * dropping the lock. + */ + devcd->init_completed = true; mutex_unlock(&devcd->mutex); return; put_device: - put_device(&devcd->devcd_dev); mutex_unlock(&devcd->mutex); + cancel_delayed_work_sync(&devcd->del_wk); + put_device(&devcd->devcd_dev); + put_module: module_put(owner); free: diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 1188f32a5e5e..a853c65ac65d 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -52,6 +52,7 @@ static DEFINE_IDR(nbd_index_idr); static DEFINE_MUTEX(nbd_index_mutex); static struct workqueue_struct *nbd_del_wq; +static struct cred *nbd_cred; static int nbd_total_devices = 0; struct nbd_sock { @@ -554,6 +555,7 @@ static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send, int result; struct msghdr msg = {} ; unsigned int noreclaim_flag; + const struct cred *old_cred; if (unlikely(!sock)) { dev_err_ratelimited(disk_to_dev(nbd->disk), @@ -562,6 +564,8 @@ static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send, return -EINVAL; } + old_cred = override_creds(nbd_cred); + msg.msg_iter = *iter; noreclaim_flag = memalloc_noreclaim_save(); @@ -586,6 +590,8 @@ static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send, memalloc_noreclaim_restore(noreclaim_flag); + revert_creds(old_cred); + return result; } @@ -2677,7 +2683,15 @@ static int __init nbd_init(void) return -ENOMEM; } + nbd_cred = prepare_kernel_cred(&init_task); + if (!nbd_cred) { + destroy_workqueue(nbd_del_wq); + unregister_blkdev(NBD_MAJOR, "nbd"); + return -ENOMEM; + } + if (genl_register_family(&nbd_genl_family)) { + put_cred(nbd_cred); destroy_workqueue(nbd_del_wq); unregister_blkdev(NBD_MAJOR, "nbd"); return -EINVAL; @@ -2732,6 +2746,7 @@ static void __exit nbd_cleanup(void) /* Also wait for nbd_dev_remove_work() completes */ destroy_workqueue(nbd_del_wq); + put_cred(nbd_cred); idr_destroy(&nbd_index_idr); unregister_blkdev(NBD_MAJOR, "nbd"); } diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 298e92d8cc03..b44f0f7a5ba1 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -1614,7 +1614,11 @@ static int amd_pstate_cpu_offline(struct cpufreq_policy *policy) * min_perf value across kexec reboots. If this CPU is just onlined normally after this, the * limits, epp and desired perf will get reset to the cached values in cpudata struct */ - return amd_pstate_update_perf(policy, perf.bios_min_perf, 0U, 0U, 0U, false); + return amd_pstate_update_perf(policy, perf.bios_min_perf, + FIELD_GET(AMD_CPPC_DES_PERF_MASK, cpudata->cppc_req_cached), + FIELD_GET(AMD_CPPC_MAX_PERF_MASK, cpudata->cppc_req_cached), + FIELD_GET(AMD_CPPC_EPP_PERF_MASK, cpudata->cppc_req_cached), + false); } static int amd_pstate_suspend(struct cpufreq_policy *policy) diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 4d9aa5ce31f0..7d21fb5a72f4 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -188,20 +188,17 @@ again: * * This can deal with workloads that have long pauses interspersed * with sporadic activity with a bunch of short pauses. + * + * However, if the number of remaining samples is too small to exclude + * any more outliers, allow the deepest available idle state to be + * selected because there are systems where the time spent by CPUs in + * deep idle states is correlated to the maximum frequency the CPUs + * can get to. On those systems, shallow idle states should be avoided + * unless there is a clear indication that the given CPU is most likley + * going to be woken up shortly. */ - if (divisor * 4 <= INTERVALS * 3) { - /* - * If there are sufficiently many data points still under - * consideration after the outliers have been eliminated, - * returning without a prediction would be a mistake because it - * is likely that the next interval will not exceed the current - * maximum, so return the latter in that case. - */ - if (divisor >= INTERVALS / 2) - return max; - + if (divisor * 4 <= INTERVALS * 3) return UINT_MAX; - } /* Update the thresholds for the next round. */ if (avg - min > max - avg) diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c index dd3656a0c1ff..c65f491c54d0 100644 --- a/drivers/firewire/core-transaction.c +++ b/drivers/firewire/core-transaction.c @@ -269,7 +269,7 @@ static void fw_fill_request(struct fw_packet *packet, int tcode, int tlabel, } static int allocate_tlabel(struct fw_card *card) -__must_hold(&card->transactions_lock) +__must_hold(&card->transactions.lock) { int tlabel; diff --git a/drivers/firewire/init_ohci1394_dma.c b/drivers/firewire/init_ohci1394_dma.c index 48b879e9e831..121f0c2f6401 100644 --- a/drivers/firewire/init_ohci1394_dma.c +++ b/drivers/firewire/init_ohci1394_dma.c @@ -167,6 +167,7 @@ static inline void __init init_ohci1394_initialize(struct ohci *ohci) /** * init_ohci1394_wait_for_busresets - wait until bus resets are completed + * @ohci: Pointer to the OHCI-1394 controller structure * * OHCI1394 initialization itself and any device going on- or offline * and any cable issue cause a IEEE1394 bus reset. The OHCI1394 spec @@ -189,6 +190,8 @@ static inline void __init init_ohci1394_wait_for_busresets(struct ohci *ohci) /** * init_ohci1394_enable_physical_dma - Enable physical DMA for remote debugging + * @ohci: Pointer to the OHCI-1394 controller structure + * * This enables remote DMA access over IEEE1394 from every host for the low * 4GB of address space. DMA accesses above 4GB are not available currently. */ @@ -201,6 +204,8 @@ static inline void __init init_ohci1394_enable_physical_dma(struct ohci *ohci) /** * init_ohci1394_reset_and_init_dma - init controller and enable DMA + * @ohci: Pointer to the OHCI-1394 controller structure + * * This initializes the given controller and enables physical DMA engine in it. */ static inline void __init init_ohci1394_reset_and_init_dma(struct ohci *ohci) @@ -230,6 +235,10 @@ static inline void __init init_ohci1394_reset_and_init_dma(struct ohci *ohci) /** * init_ohci1394_controller - Map the registers of the controller and init DMA + * @num: PCI bus number + * @slot: PCI device number + * @func: PCI function number + * * This maps the registers of the specified controller and initializes it */ static inline void __init init_ohci1394_controller(int num, int slot, int func) @@ -284,6 +293,7 @@ void __init init_ohci1394_dma_on_all_controllers(void) /** * setup_ohci1394_dma - enables early OHCI1394 DMA initialization + * @opt: Kernel command line parameter string */ static int __init setup_ohci1394_dma(char *opt) { diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index 65bf1685350a..c72ee4756585 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -649,6 +649,26 @@ static u16 ffa_memory_attributes_get(u32 func_id) return FFA_MEM_NORMAL | FFA_MEM_WRITE_BACK | FFA_MEM_INNER_SHAREABLE; } +static void ffa_emad_impdef_value_init(u32 version, void *dst, void *src) +{ + struct ffa_mem_region_attributes *ep_mem_access; + + if (FFA_EMAD_HAS_IMPDEF_FIELD(version)) + memcpy(dst, src, sizeof(ep_mem_access->impdef_val)); +} + +static void +ffa_mem_region_additional_setup(u32 version, struct ffa_mem_region *mem_region) +{ + if (!FFA_MEM_REGION_HAS_EP_MEM_OFFSET(version)) { + mem_region->ep_mem_size = 0; + } else { + mem_region->ep_mem_size = ffa_emad_size_get(version); + mem_region->ep_mem_offset = sizeof(*mem_region); + memset(mem_region->reserved, 0, 12); + } +} + static int ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, struct ffa_mem_ops_args *args) @@ -667,27 +687,24 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, mem_region->flags = args->flags; mem_region->sender_id = drv_info->vm_id; mem_region->attributes = ffa_memory_attributes_get(func_id); - ep_mem_access = buffer + - ffa_mem_desc_offset(buffer, 0, drv_info->version); composite_offset = ffa_mem_desc_offset(buffer, args->nattrs, drv_info->version); - for (idx = 0; idx < args->nattrs; idx++, ep_mem_access++) { + for (idx = 0; idx < args->nattrs; idx++) { + ep_mem_access = buffer + + ffa_mem_desc_offset(buffer, idx, drv_info->version); ep_mem_access->receiver = args->attrs[idx].receiver; ep_mem_access->attrs = args->attrs[idx].attrs; ep_mem_access->composite_off = composite_offset; ep_mem_access->flag = 0; ep_mem_access->reserved = 0; + ffa_emad_impdef_value_init(drv_info->version, + ep_mem_access->impdef_val, + args->attrs[idx].impdef_val); } mem_region->handle = 0; mem_region->ep_count = args->nattrs; - if (drv_info->version <= FFA_VERSION_1_0) { - mem_region->ep_mem_size = 0; - } else { - mem_region->ep_mem_size = sizeof(*ep_mem_access); - mem_region->ep_mem_offset = sizeof(*mem_region); - memset(mem_region->reserved, 0, 12); - } + ffa_mem_region_additional_setup(drv_info->version, mem_region); composite = buffer + composite_offset; composite->total_pg_cnt = ffa_get_num_pages_sg(args->sg); diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h index 07b9e629276d..7c35c95fddba 100644 --- a/drivers/firmware/arm_scmi/common.h +++ b/drivers/firmware/arm_scmi/common.h @@ -309,16 +309,36 @@ enum debug_counters { SCMI_DEBUG_COUNTERS_LAST }; -static inline void scmi_inc_count(atomic_t *arr, int stat) +/** + * struct scmi_debug_info - Debug common info + * @top_dentry: A reference to the top debugfs dentry + * @name: Name of this SCMI instance + * @type: Type of this SCMI instance + * @is_atomic: Flag to state if the transport of this instance is atomic + * @counters: An array of atomic_c's used for tracking statistics (if enabled) + */ +struct scmi_debug_info { + struct dentry *top_dentry; + const char *name; + const char *type; + bool is_atomic; + atomic_t counters[SCMI_DEBUG_COUNTERS_LAST]; +}; + +static inline void scmi_inc_count(struct scmi_debug_info *dbg, int stat) { - if (IS_ENABLED(CONFIG_ARM_SCMI_DEBUG_COUNTERS)) - atomic_inc(&arr[stat]); + if (IS_ENABLED(CONFIG_ARM_SCMI_DEBUG_COUNTERS)) { + if (dbg) + atomic_inc(&dbg->counters[stat]); + } } -static inline void scmi_dec_count(atomic_t *arr, int stat) +static inline void scmi_dec_count(struct scmi_debug_info *dbg, int stat) { - if (IS_ENABLED(CONFIG_ARM_SCMI_DEBUG_COUNTERS)) - atomic_dec(&arr[stat]); + if (IS_ENABLED(CONFIG_ARM_SCMI_DEBUG_COUNTERS)) { + if (dbg) + atomic_dec(&dbg->counters[stat]); + } } enum scmi_bad_msg { diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index bd56a877fdfc..5caa9191a8d1 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -116,22 +116,6 @@ struct scmi_protocol_instance { #define ph_to_pi(h) container_of(h, struct scmi_protocol_instance, ph) /** - * struct scmi_debug_info - Debug common info - * @top_dentry: A reference to the top debugfs dentry - * @name: Name of this SCMI instance - * @type: Type of this SCMI instance - * @is_atomic: Flag to state if the transport of this instance is atomic - * @counters: An array of atomic_c's used for tracking statistics (if enabled) - */ -struct scmi_debug_info { - struct dentry *top_dentry; - const char *name; - const char *type; - bool is_atomic; - atomic_t counters[SCMI_DEBUG_COUNTERS_LAST]; -}; - -/** * struct scmi_info - Structure representing a SCMI instance * * @id: A sequence number starting from zero identifying this instance @@ -610,7 +594,7 @@ scmi_xfer_inflight_register_unlocked(struct scmi_xfer *xfer, /* Set in-flight */ set_bit(xfer->hdr.seq, minfo->xfer_alloc_table); hash_add(minfo->pending_xfers, &xfer->node, xfer->hdr.seq); - scmi_inc_count(info->dbg->counters, XFERS_INFLIGHT); + scmi_inc_count(info->dbg, XFERS_INFLIGHT); xfer->pending = true; } @@ -819,8 +803,9 @@ __scmi_xfer_put(struct scmi_xfers_info *minfo, struct scmi_xfer *xfer) hash_del(&xfer->node); xfer->pending = false; - scmi_dec_count(info->dbg->counters, XFERS_INFLIGHT); + scmi_dec_count(info->dbg, XFERS_INFLIGHT); } + xfer->flags = 0; hlist_add_head(&xfer->node, &minfo->free_xfers); } spin_unlock_irqrestore(&minfo->xfer_lock, flags); @@ -839,8 +824,6 @@ void scmi_xfer_raw_put(const struct scmi_handle *handle, struct scmi_xfer *xfer) { struct scmi_info *info = handle_to_scmi_info(handle); - xfer->flags &= ~SCMI_XFER_FLAG_IS_RAW; - xfer->flags &= ~SCMI_XFER_FLAG_CHAN_SET; return __scmi_xfer_put(&info->tx_minfo, xfer); } @@ -1034,7 +1017,7 @@ scmi_xfer_command_acquire(struct scmi_chan_info *cinfo, u32 msg_hdr) spin_unlock_irqrestore(&minfo->xfer_lock, flags); scmi_bad_message_trace(cinfo, msg_hdr, MSG_UNEXPECTED); - scmi_inc_count(info->dbg->counters, ERR_MSG_UNEXPECTED); + scmi_inc_count(info->dbg, ERR_MSG_UNEXPECTED); return xfer; } @@ -1062,7 +1045,7 @@ scmi_xfer_command_acquire(struct scmi_chan_info *cinfo, u32 msg_hdr) msg_type, xfer_id, msg_hdr, xfer->state); scmi_bad_message_trace(cinfo, msg_hdr, MSG_INVALID); - scmi_inc_count(info->dbg->counters, ERR_MSG_INVALID); + scmi_inc_count(info->dbg, ERR_MSG_INVALID); /* On error the refcount incremented above has to be dropped */ __scmi_xfer_put(minfo, xfer); @@ -1107,7 +1090,7 @@ static void scmi_handle_notification(struct scmi_chan_info *cinfo, PTR_ERR(xfer)); scmi_bad_message_trace(cinfo, msg_hdr, MSG_NOMEM); - scmi_inc_count(info->dbg->counters, ERR_MSG_NOMEM); + scmi_inc_count(info->dbg, ERR_MSG_NOMEM); scmi_clear_channel(info, cinfo); return; @@ -1123,7 +1106,7 @@ static void scmi_handle_notification(struct scmi_chan_info *cinfo, trace_scmi_msg_dump(info->id, cinfo->id, xfer->hdr.protocol_id, xfer->hdr.id, "NOTI", xfer->hdr.seq, xfer->hdr.status, xfer->rx.buf, xfer->rx.len); - scmi_inc_count(info->dbg->counters, NOTIFICATION_OK); + scmi_inc_count(info->dbg, NOTIFICATION_OK); scmi_notify(cinfo->handle, xfer->hdr.protocol_id, xfer->hdr.id, xfer->rx.buf, xfer->rx.len, ts); @@ -1183,10 +1166,10 @@ static void scmi_handle_response(struct scmi_chan_info *cinfo, if (xfer->hdr.type == MSG_TYPE_DELAYED_RESP) { scmi_clear_channel(info, cinfo); complete(xfer->async_done); - scmi_inc_count(info->dbg->counters, DELAYED_RESPONSE_OK); + scmi_inc_count(info->dbg, DELAYED_RESPONSE_OK); } else { complete(&xfer->done); - scmi_inc_count(info->dbg->counters, RESPONSE_OK); + scmi_inc_count(info->dbg, RESPONSE_OK); } if (IS_ENABLED(CONFIG_ARM_SCMI_RAW_MODE_SUPPORT)) { @@ -1296,7 +1279,7 @@ static int scmi_wait_for_reply(struct device *dev, const struct scmi_desc *desc, "timed out in resp(caller: %pS) - polling\n", (void *)_RET_IP_); ret = -ETIMEDOUT; - scmi_inc_count(info->dbg->counters, XFERS_RESPONSE_POLLED_TIMEOUT); + scmi_inc_count(info->dbg, XFERS_RESPONSE_POLLED_TIMEOUT); } } @@ -1321,7 +1304,7 @@ static int scmi_wait_for_reply(struct device *dev, const struct scmi_desc *desc, "RESP" : "resp", xfer->hdr.seq, xfer->hdr.status, xfer->rx.buf, xfer->rx.len); - scmi_inc_count(info->dbg->counters, RESPONSE_POLLED_OK); + scmi_inc_count(info->dbg, RESPONSE_POLLED_OK); if (IS_ENABLED(CONFIG_ARM_SCMI_RAW_MODE_SUPPORT)) { scmi_raw_message_report(info->raw, xfer, @@ -1336,7 +1319,7 @@ static int scmi_wait_for_reply(struct device *dev, const struct scmi_desc *desc, dev_err(dev, "timed out in resp(caller: %pS)\n", (void *)_RET_IP_); ret = -ETIMEDOUT; - scmi_inc_count(info->dbg->counters, XFERS_RESPONSE_TIMEOUT); + scmi_inc_count(info->dbg, XFERS_RESPONSE_TIMEOUT); } } @@ -1420,13 +1403,13 @@ static int do_xfer(const struct scmi_protocol_handle *ph, !is_transport_polling_capable(info->desc)) { dev_warn_once(dev, "Polling mode is not supported by transport.\n"); - scmi_inc_count(info->dbg->counters, SENT_FAIL_POLLING_UNSUPPORTED); + scmi_inc_count(info->dbg, SENT_FAIL_POLLING_UNSUPPORTED); return -EINVAL; } cinfo = idr_find(&info->tx_idr, pi->proto->id); if (unlikely(!cinfo)) { - scmi_inc_count(info->dbg->counters, SENT_FAIL_CHANNEL_NOT_FOUND); + scmi_inc_count(info->dbg, SENT_FAIL_CHANNEL_NOT_FOUND); return -EINVAL; } /* True ONLY if also supported by transport. */ @@ -1461,19 +1444,19 @@ static int do_xfer(const struct scmi_protocol_handle *ph, ret = info->desc->ops->send_message(cinfo, xfer); if (ret < 0) { dev_dbg(dev, "Failed to send message %d\n", ret); - scmi_inc_count(info->dbg->counters, SENT_FAIL); + scmi_inc_count(info->dbg, SENT_FAIL); return ret; } trace_scmi_msg_dump(info->id, cinfo->id, xfer->hdr.protocol_id, xfer->hdr.id, "CMND", xfer->hdr.seq, xfer->hdr.status, xfer->tx.buf, xfer->tx.len); - scmi_inc_count(info->dbg->counters, SENT_OK); + scmi_inc_count(info->dbg, SENT_OK); ret = scmi_wait_for_message_response(cinfo, xfer); if (!ret && xfer->hdr.status) { ret = scmi_to_linux_errno(xfer->hdr.status); - scmi_inc_count(info->dbg->counters, ERR_PROTOCOL); + scmi_inc_count(info->dbg, ERR_PROTOCOL); } if (info->desc->ops->mark_txdone) @@ -3044,9 +3027,6 @@ static int scmi_debugfs_raw_mode_setup(struct scmi_info *info) u8 channels[SCMI_MAX_CHANNELS] = {}; DECLARE_BITMAP(protos, SCMI_MAX_CHANNELS) = {}; - if (!info->dbg) - return -EINVAL; - /* Enumerate all channels to collect their ids */ idr_for_each_entry(&info->tx_idr, cinfo, id) { /* @@ -3218,7 +3198,7 @@ static int scmi_probe(struct platform_device *pdev) if (!info->dbg) dev_warn(dev, "Failed to setup SCMI debugfs.\n"); - if (IS_ENABLED(CONFIG_ARM_SCMI_RAW_MODE_SUPPORT)) { + if (info->dbg && IS_ENABLED(CONFIG_ARM_SCMI_RAW_MODE_SUPPORT)) { ret = scmi_debugfs_raw_mode_setup(info); if (!coex) { if (ret) @@ -3423,6 +3403,9 @@ int scmi_inflight_count(const struct scmi_handle *handle) if (IS_ENABLED(CONFIG_ARM_SCMI_DEBUG_COUNTERS)) { struct scmi_info *info = handle_to_scmi_info(handle); + if (!info->dbg) + return 0; + return atomic_read(&info->dbg->counters[XFERS_INFLIGHT]); } else { return 0; diff --git a/drivers/gpio/gpio-104-idio-16.c b/drivers/gpio/gpio-104-idio-16.c index ffe7e1cb6b23..fe5c10cd5c32 100644 --- a/drivers/gpio/gpio-104-idio-16.c +++ b/drivers/gpio/gpio-104-idio-16.c @@ -59,6 +59,7 @@ static const struct regmap_config idio_16_regmap_config = { .reg_stride = 1, .val_bits = 8, .io_port = true, + .max_register = 0x5, .wr_table = &idio_16_wr_table, .rd_table = &idio_16_rd_table, .volatile_table = &idio_16_rd_table, diff --git a/drivers/gpio/gpio-idio-16.c b/drivers/gpio/gpio-idio-16.c index 0103be977c66..4fbae6f6a497 100644 --- a/drivers/gpio/gpio-idio-16.c +++ b/drivers/gpio/gpio-idio-16.c @@ -6,6 +6,7 @@ #define DEFAULT_SYMBOL_NAMESPACE "GPIO_IDIO_16" +#include <linux/bitmap.h> #include <linux/bits.h> #include <linux/device.h> #include <linux/err.h> @@ -107,6 +108,7 @@ int devm_idio_16_regmap_register(struct device *const dev, struct idio_16_data *data; struct regmap_irq_chip *chip; struct regmap_irq_chip_data *chip_data; + DECLARE_BITMAP(fixed_direction_output, IDIO_16_NGPIO); if (!config->parent) return -EINVAL; @@ -164,6 +166,9 @@ int devm_idio_16_regmap_register(struct device *const dev, gpio_config.irq_domain = regmap_irq_get_domain(chip_data); gpio_config.reg_mask_xlate = idio_16_reg_mask_xlate; + bitmap_from_u64(fixed_direction_output, GENMASK_U64(15, 0)); + gpio_config.fixed_direction_output = fixed_direction_output; + return PTR_ERR_OR_ZERO(devm_gpio_regmap_register(dev, &gpio_config)); } EXPORT_SYMBOL_GPL(devm_idio_16_regmap_register); diff --git a/drivers/gpio/gpio-ljca.c b/drivers/gpio/gpio-ljca.c index 3b4f8830c741..f32d1d237795 100644 --- a/drivers/gpio/gpio-ljca.c +++ b/drivers/gpio/gpio-ljca.c @@ -286,22 +286,14 @@ static void ljca_gpio_event_cb(void *context, u8 cmd, const void *evt_data, { const struct ljca_gpio_packet *packet = evt_data; struct ljca_gpio_dev *ljca_gpio = context; - int i, irq; + int i; if (cmd != LJCA_GPIO_INT_EVENT) return; for (i = 0; i < packet->num; i++) { - irq = irq_find_mapping(ljca_gpio->gc.irq.domain, - packet->item[i].index); - if (!irq) { - dev_err(ljca_gpio->gc.parent, - "gpio_id %u does not mapped to IRQ yet\n", - packet->item[i].index); - return; - } - - generic_handle_domain_irq(ljca_gpio->gc.irq.domain, irq); + generic_handle_domain_irq(ljca_gpio->gc.irq.domain, + packet->item[i].index); set_bit(packet->item[i].index, ljca_gpio->reenable_irqs); } diff --git a/drivers/gpio/gpio-pci-idio-16.c b/drivers/gpio/gpio-pci-idio-16.c index 476cea1b5ed7..9d28ca8e1d6f 100644 --- a/drivers/gpio/gpio-pci-idio-16.c +++ b/drivers/gpio/gpio-pci-idio-16.c @@ -41,6 +41,7 @@ static const struct regmap_config idio_16_regmap_config = { .reg_stride = 1, .val_bits = 8, .io_port = true, + .max_register = 0x7, .wr_table = &idio_16_wr_table, .rd_table = &idio_16_rd_table, .volatile_table = &idio_16_rd_table, diff --git a/drivers/gpio/gpio-regmap.c b/drivers/gpio/gpio-regmap.c index ab9e4077fa60..f4267af00027 100644 --- a/drivers/gpio/gpio-regmap.c +++ b/drivers/gpio/gpio-regmap.c @@ -31,6 +31,7 @@ struct gpio_regmap { unsigned int reg_clr_base; unsigned int reg_dir_in_base; unsigned int reg_dir_out_base; + unsigned long *fixed_direction_output; #ifdef CONFIG_REGMAP_IRQ int regmap_irq_line; @@ -134,6 +135,13 @@ static int gpio_regmap_get_direction(struct gpio_chip *chip, unsigned int base, val, reg, mask; int invert, ret; + if (gpio->fixed_direction_output) { + if (test_bit(offset, gpio->fixed_direction_output)) + return GPIO_LINE_DIRECTION_OUT; + else + return GPIO_LINE_DIRECTION_IN; + } + if (gpio->reg_dat_base && !gpio->reg_set_base) return GPIO_LINE_DIRECTION_IN; if (gpio->reg_set_base && !gpio->reg_dat_base) @@ -284,6 +292,17 @@ struct gpio_regmap *gpio_regmap_register(const struct gpio_regmap_config *config goto err_free_gpio; } + if (config->fixed_direction_output) { + gpio->fixed_direction_output = bitmap_alloc(chip->ngpio, + GFP_KERNEL); + if (!gpio->fixed_direction_output) { + ret = -ENOMEM; + goto err_free_gpio; + } + bitmap_copy(gpio->fixed_direction_output, + config->fixed_direction_output, chip->ngpio); + } + /* if not set, assume there is only one register */ gpio->ngpio_per_reg = config->ngpio_per_reg; if (!gpio->ngpio_per_reg) @@ -300,7 +319,7 @@ struct gpio_regmap *gpio_regmap_register(const struct gpio_regmap_config *config ret = gpiochip_add_data(chip, gpio); if (ret < 0) - goto err_free_gpio; + goto err_free_bitmap; #ifdef CONFIG_REGMAP_IRQ if (config->regmap_irq_chip) { @@ -309,7 +328,7 @@ struct gpio_regmap *gpio_regmap_register(const struct gpio_regmap_config *config config->regmap_irq_line, config->regmap_irq_flags, 0, config->regmap_irq_chip, &gpio->irq_chip_data); if (ret) - goto err_free_gpio; + goto err_free_bitmap; irq_domain = regmap_irq_get_domain(gpio->irq_chip_data); } else @@ -326,6 +345,8 @@ struct gpio_regmap *gpio_regmap_register(const struct gpio_regmap_config *config err_remove_gpiochip: gpiochip_remove(chip); +err_free_bitmap: + bitmap_free(gpio->fixed_direction_output); err_free_gpio: kfree(gpio); return ERR_PTR(ret); @@ -344,6 +365,7 @@ void gpio_regmap_unregister(struct gpio_regmap *gpio) #endif gpiochip_remove(&gpio->gpio_chip); + bitmap_free(gpio->fixed_direction_output); kfree(gpio); } EXPORT_SYMBOL_GPL(gpio_regmap_unregister); diff --git a/drivers/gpio/gpiolib-acpi-core.c b/drivers/gpio/gpiolib-acpi-core.c index 284e762d92c4..d441c1236d8c 100644 --- a/drivers/gpio/gpiolib-acpi-core.c +++ b/drivers/gpio/gpiolib-acpi-core.c @@ -291,6 +291,19 @@ acpi_gpio_to_gpiod_flags(const struct acpi_resource_gpio *agpio, int polarity) return GPIOD_ASIS; } +static void acpi_gpio_set_debounce_timeout(struct gpio_desc *desc, + unsigned int acpi_debounce) +{ + int ret; + + /* ACPI uses hundredths of milliseconds units */ + acpi_debounce *= 10; + ret = gpio_set_debounce_timeout(desc, acpi_debounce); + if (ret) + gpiod_warn(desc, "Failed to set debounce-timeout %u: %d\n", + acpi_debounce, ret); +} + static struct gpio_desc *acpi_request_own_gpiod(struct gpio_chip *chip, struct acpi_resource_gpio *agpio, unsigned int index, @@ -300,18 +313,12 @@ static struct gpio_desc *acpi_request_own_gpiod(struct gpio_chip *chip, enum gpiod_flags flags = acpi_gpio_to_gpiod_flags(agpio, polarity); unsigned int pin = agpio->pin_table[index]; struct gpio_desc *desc; - int ret; desc = gpiochip_request_own_desc(chip, pin, label, polarity, flags); if (IS_ERR(desc)) return desc; - /* ACPI uses hundredths of milliseconds units */ - ret = gpio_set_debounce_timeout(desc, agpio->debounce_timeout * 10); - if (ret) - dev_warn(chip->parent, - "Failed to set debounce-timeout for pin 0x%04X, err %d\n", - pin, ret); + acpi_gpio_set_debounce_timeout(desc, agpio->debounce_timeout); return desc; } @@ -375,8 +382,8 @@ static acpi_status acpi_gpiochip_alloc_event(struct acpi_resource *ares, desc = acpi_request_own_gpiod(chip, agpio, 0, "ACPI:Event"); if (IS_ERR(desc)) { dev_err(chip->parent, - "Failed to request GPIO for pin 0x%04X, err %ld\n", - pin, PTR_ERR(desc)); + "Failed to request GPIO for pin 0x%04X, err %pe\n", + pin, desc); return AE_OK; } @@ -944,7 +951,6 @@ struct gpio_desc *acpi_find_gpio(struct fwnode_handle *fwnode, bool can_fallback = acpi_can_fallback_to_crs(adev, con_id); struct acpi_gpio_info info = {}; struct gpio_desc *desc; - int ret; desc = __acpi_find_gpio(fwnode, con_id, idx, can_fallback, &info); if (IS_ERR(desc)) @@ -959,10 +965,7 @@ struct gpio_desc *acpi_find_gpio(struct fwnode_handle *fwnode, acpi_gpio_update_gpiod_flags(dflags, &info); acpi_gpio_update_gpiod_lookup_flags(lookupflags, &info); - /* ACPI uses hundredths of milliseconds units */ - ret = gpio_set_debounce_timeout(desc, info.debounce * 10); - if (ret) - return ERR_PTR(ret); + acpi_gpio_set_debounce_timeout(desc, info.debounce); return desc; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 6597475e245d..bfa3199591b6 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -551,13 +551,13 @@ static void schedule_dc_vmin_vmax(struct amdgpu_device *adev, struct dc_stream_state *stream, struct dc_crtc_timing_adjust *adjust) { - struct vupdate_offload_work *offload_work = kzalloc(sizeof(*offload_work), GFP_KERNEL); + struct vupdate_offload_work *offload_work = kzalloc(sizeof(*offload_work), GFP_NOWAIT); if (!offload_work) { drm_dbg_driver(adev_to_drm(adev), "Failed to allocate vupdate_offload_work\n"); return; } - struct dc_crtc_timing_adjust *adjust_copy = kzalloc(sizeof(*adjust_copy), GFP_KERNEL); + struct dc_crtc_timing_adjust *adjust_copy = kzalloc(sizeof(*adjust_copy), GFP_NOWAIT); if (!adjust_copy) { drm_dbg_driver(adev_to_drm(adev), "Failed to allocate adjust_copy\n"); kfree(offload_work); 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 7c276c319086..ce3d0b45fb4c 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 @@ -200,6 +200,9 @@ void dcn401_init_hw(struct dc *dc) */ struct dc_link *link = dc->links[i]; + if (link->ep_type != DISPLAY_ENDPOINT_PHY) + continue; + link->link_enc->funcs->hw_init(link->link_enc); /* Check for enabled DIG to identify enabled display */ diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h index 41c76ba9ba56..62a39204fe0b 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h @@ -44,7 +44,13 @@ */ #define MAX_PIPES 6 #define MAX_PHANTOM_PIPES (MAX_PIPES / 2) -#define MAX_LINKS (MAX_PIPES * 2 +2) + +#define MAX_DPIA 6 +#define MAX_CONNECTOR 6 +#define MAX_VIRTUAL_LINKS 4 + +#define MAX_LINKS (MAX_DPIA + MAX_CONNECTOR + MAX_VIRTUAL_LINKS) + #define MAX_DIG_LINK_ENCODERS 7 #define MAX_DWB_PIPES 1 #define MAX_HPO_DP2_ENCODERS 4 diff --git a/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c b/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c index 9e33bf937a69..2676ae9f6fe8 100644 --- a/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c +++ b/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c @@ -78,6 +78,7 @@ static void dp_retrain_link_dp_test(struct dc_link *link, struct audio_output audio_output[MAX_PIPES]; struct dc_stream_state *streams_on_link[MAX_PIPES]; int num_streams_on_link = 0; + struct dc *dc = (struct dc *)link->dc; needs_divider_update = (link->dc->link_srv->dp_get_encoding_format(link_setting) != link->dc->link_srv->dp_get_encoding_format((const struct dc_link_settings *) &link->cur_link_settings)); @@ -150,7 +151,7 @@ static void dp_retrain_link_dp_test(struct dc_link *link, if (streams_on_link[i] && streams_on_link[i]->link && streams_on_link[i]->link == link) { stream_update.stream = streams_on_link[i]; stream_update.dpms_off = &dpms_off; - dc_update_planes_and_stream(state->clk_mgr->ctx->dc, NULL, 0, streams_on_link[i], &stream_update); + dc_update_planes_and_stream(dc, NULL, 0, streams_on_link[i], &stream_update); } } } diff --git a/drivers/gpu/drm/drm_panic.c b/drivers/gpu/drm/drm_panic.c index 1d6312fa1429..d4b6ea42db0f 100644 --- a/drivers/gpu/drm/drm_panic.c +++ b/drivers/gpu/drm/drm_panic.c @@ -174,6 +174,33 @@ static void drm_panic_write_pixel24(void *vaddr, unsigned int offset, u32 color) *p = color & 0xff; } +/* + * Special case if the pixel crosses page boundaries + */ +static void drm_panic_write_pixel24_xpage(void *vaddr, struct page *next_page, + unsigned int offset, u32 color) +{ + u8 *vaddr2; + u8 *p = vaddr + offset; + + vaddr2 = kmap_local_page_try_from_panic(next_page); + + *p++ = color & 0xff; + color >>= 8; + + if (offset == PAGE_SIZE - 1) + p = vaddr2; + + *p++ = color & 0xff; + color >>= 8; + + if (offset == PAGE_SIZE - 2) + p = vaddr2; + + *p = color & 0xff; + kunmap_local(vaddr2); +} + static void drm_panic_write_pixel32(void *vaddr, unsigned int offset, u32 color) { u32 *p = vaddr + offset; @@ -231,7 +258,14 @@ static void drm_panic_blit_page(struct page **pages, unsigned int dpitch, page = new_page; vaddr = kmap_local_page_try_from_panic(pages[page]); } - if (vaddr) + if (!vaddr) + continue; + + // Special case for 24bit, as a pixel might cross page boundaries + if (cpp == 3 && offset + 3 > PAGE_SIZE) + drm_panic_write_pixel24_xpage(vaddr, pages[page + 1], + offset, fg32); + else drm_panic_write_pixel(vaddr, offset, fg32, cpp); } } @@ -321,7 +355,15 @@ static void drm_panic_fill_page(struct page **pages, unsigned int dpitch, page = new_page; vaddr = kmap_local_page_try_from_panic(pages[page]); } - drm_panic_write_pixel(vaddr, offset, color, cpp); + if (!vaddr) + continue; + + // Special case for 24bit, as a pixel might cross page boundaries + if (cpp == 3 && offset + 3 > PAGE_SIZE) + drm_panic_write_pixel24_xpage(vaddr, pages[page + 1], + offset, color); + else + drm_panic_write_pixel(vaddr, offset, color, cpp); } } if (vaddr) @@ -429,6 +471,9 @@ static void drm_panic_logo_rect(struct drm_rect *rect, const struct font_desc *f static void drm_panic_logo_draw(struct drm_scanout_buffer *sb, struct drm_rect *rect, const struct font_desc *font, u32 fg_color) { + if (rect->x2 > sb->width || rect->y2 > sb->height) + return; + if (logo_mono) drm_panic_blit(sb, rect, logo_mono->data, DIV_ROUND_UP(drm_rect_width(rect), 8), 1, fg_color); @@ -477,7 +522,7 @@ static int draw_line_with_wrap(struct drm_scanout_buffer *sb, const struct font_ struct drm_panic_line *line, int yoffset, u32 fg_color) { int chars_per_row = sb->width / font->width; - struct drm_rect r_txt = DRM_RECT_INIT(0, yoffset, sb->width, sb->height); + struct drm_rect r_txt = DRM_RECT_INIT(0, yoffset, sb->width, font->height); struct drm_panic_line line_wrap; if (line->len > chars_per_row) { @@ -520,7 +565,7 @@ static void draw_panic_static_kmsg(struct drm_scanout_buffer *sb) struct drm_panic_line line; int yoffset; - if (!font) + if (!font || font->width > sb->width) return; yoffset = sb->height - font->height - (sb->height % font->height) / 2; @@ -733,7 +778,10 @@ static int _draw_panic_static_qr_code(struct drm_scanout_buffer *sb) pr_debug("QR width %d and scale %d\n", qr_width, scale); r_qr_canvas = DRM_RECT_INIT(0, 0, qr_canvas_width * scale, qr_canvas_width * scale); - v_margin = (sb->height - drm_rect_height(&r_qr_canvas) - drm_rect_height(&r_msg)) / 5; + v_margin = sb->height - drm_rect_height(&r_qr_canvas) - drm_rect_height(&r_msg); + if (v_margin < 0) + return -ENOSPC; + v_margin /= 5; drm_rect_translate(&r_qr_canvas, (sb->width - r_qr_canvas.x2) / 2, 2 * v_margin); r_qr = DRM_RECT_INIT(r_qr_canvas.x1 + QR_MARGIN * scale, r_qr_canvas.y1 + QR_MARGIN * scale, @@ -746,7 +794,7 @@ static int _draw_panic_static_qr_code(struct drm_scanout_buffer *sb) /* Fill with the background color, and draw text on top */ drm_panic_fill(sb, &r_screen, bg_color); - if (!drm_rect_overlap(&r_logo, &r_msg) && !drm_rect_overlap(&r_logo, &r_qr)) + if (!drm_rect_overlap(&r_logo, &r_msg) && !drm_rect_overlap(&r_logo, &r_qr_canvas)) drm_panic_logo_draw(sb, &r_logo, font, fg_color); draw_txt_rectangle(sb, font, panic_msg, panic_msg_lines, true, &r_msg, fg_color); diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c index b817ff44c043..c48384e58ea1 100644 --- a/drivers/gpu/drm/i915/display/intel_fb.c +++ b/drivers/gpu/drm/i915/display/intel_fb.c @@ -2117,6 +2117,7 @@ static void intel_user_framebuffer_destroy(struct drm_framebuffer *fb) intel_frontbuffer_put(intel_fb->frontbuffer); + kfree(intel_fb->panic); kfree(intel_fb); } @@ -2215,16 +2216,22 @@ int intel_framebuffer_init(struct intel_framebuffer *intel_fb, struct intel_display *display = to_intel_display(obj->dev); struct drm_framebuffer *fb = &intel_fb->base; u32 max_stride; - int ret = -EINVAL; + int ret; int i; + intel_fb->panic = intel_panic_alloc(); + if (!intel_fb->panic) + return -ENOMEM; + /* * intel_frontbuffer_get() must be done before * intel_fb_bo_framebuffer_init() to avoid set_tiling vs. addfb race. */ intel_fb->frontbuffer = intel_frontbuffer_get(obj); - if (!intel_fb->frontbuffer) - return -ENOMEM; + if (!intel_fb->frontbuffer) { + ret = -ENOMEM; + goto err_free_panic; + } ret = intel_fb_bo_framebuffer_init(fb, obj, mode_cmd); if (ret) @@ -2323,6 +2330,9 @@ err_bo_framebuffer_fini: intel_fb_bo_framebuffer_fini(obj); err_frontbuffer_put: intel_frontbuffer_put(intel_fb->frontbuffer); +err_free_panic: + kfree(intel_fb->panic); + return ret; } @@ -2349,20 +2359,11 @@ intel_user_framebuffer_create(struct drm_device *dev, struct intel_framebuffer *intel_framebuffer_alloc(void) { struct intel_framebuffer *intel_fb; - struct intel_panic *panic; intel_fb = kzalloc(sizeof(*intel_fb), GFP_KERNEL); if (!intel_fb) return NULL; - panic = intel_panic_alloc(); - if (!panic) { - kfree(intel_fb); - return NULL; - } - - intel_fb->panic = panic; - return intel_fb; } diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c index 6dec4354e378..7870e7dbaa5d 100644 --- a/drivers/gpu/drm/panthor/panthor_mmu.c +++ b/drivers/gpu/drm/panthor/panthor_mmu.c @@ -1175,10 +1175,14 @@ panthor_vm_op_ctx_prealloc_vmas(struct panthor_vm_op_ctx *op_ctx) break; case DRM_PANTHOR_VM_BIND_OP_TYPE_UNMAP: - /* Partial unmaps might trigger a remap with either a prev or a next VA, - * but not both. + /* Two VMAs can be needed for an unmap, as an unmap can happen + * in the middle of a drm_gpuva, requiring a remap with both + * prev & next VA. Or an unmap can span more than one drm_gpuva + * where the first and last ones are covered partially, requring + * a remap for the first with a prev VA and remap for the last + * with a next VA. */ - vma_count = 1; + vma_count = 2; break; default: diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c index 7b613997bb50..727cdf768161 100644 --- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c +++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c @@ -361,7 +361,7 @@ static void dw_hdmi_rk3228_setup_hpd(struct dw_hdmi *dw_hdmi, void *data) regmap_write(hdmi->regmap, RK3228_GRF_SOC_CON2, FIELD_PREP_WM16(RK3228_HDMI_SDAIN_MSK, 1) | - FIELD_PREP_WM16(RK3328_HDMI_SCLIN_MSK, 1)); + FIELD_PREP_WM16(RK3228_HDMI_SCLIN_MSK, 1)); } static enum drm_connector_status diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c index 7fdd0a97a628..5edc0cad47e2 100644 --- a/drivers/gpu/drm/xe/xe_ggtt.c +++ b/drivers/gpu/drm/xe/xe_ggtt.c @@ -292,6 +292,9 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt) ggtt->pt_ops = &xelp_pt_ops; ggtt->wq = alloc_workqueue("xe-ggtt-wq", 0, WQ_MEM_RECLAIM); + if (!ggtt->wq) + return -ENOMEM; + __xe_ggtt_init_early(ggtt, xe_wopcm_size(xe)); err = drmm_add_action_or_reset(&xe->drm, ggtt_fini_early, ggtt); diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index a1c88f9a6c76..07f96bda638a 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -2022,7 +2022,7 @@ static int op_prepare(struct xe_vm *vm, case DRM_GPUVA_OP_MAP: if ((!op->map.immediate && xe_vm_in_fault_mode(vm) && !op->map.invalidate_on_bind) || - op->map.is_cpu_addr_mirror) + (op->map.vma_flags & XE_VMA_SYSTEM_ALLOCATOR)) break; err = bind_op_prepare(vm, tile, pt_update_ops, op->map.vma, @@ -2252,7 +2252,7 @@ static void op_commit(struct xe_vm *vm, switch (op->base.op) { case DRM_GPUVA_OP_MAP: if ((!op->map.immediate && xe_vm_in_fault_mode(vm)) || - op->map.is_cpu_addr_mirror) + (op->map.vma_flags & XE_VMA_SYSTEM_ALLOCATOR)) break; bind_op_commit(vm, tile, pt_update_ops, op->map.vma, fence, diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c index da2a412f80c0..129e7818565c 100644 --- a/drivers/gpu/drm/xe/xe_svm.c +++ b/drivers/gpu/drm/xe/xe_svm.c @@ -302,6 +302,11 @@ static int xe_svm_range_set_default_attr(struct xe_vm *vm, u64 range_start, u64 if (!vma) return -EINVAL; + if (!(vma->gpuva.flags & XE_VMA_MADV_AUTORESET)) { + drm_dbg(&vm->xe->drm, "Skipping madvise reset for vma.\n"); + return 0; + } + if (xe_vma_has_default_mem_attrs(vma)) return 0; diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index f602b874e054..63c65e3d207b 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -616,6 +616,13 @@ static void xe_vma_ops_incr_pt_update_ops(struct xe_vma_ops *vops, u8 tile_mask, vops->pt_update_ops[i].num_ops += inc_val; } +#define XE_VMA_CREATE_MASK ( \ + XE_VMA_READ_ONLY | \ + XE_VMA_DUMPABLE | \ + XE_VMA_SYSTEM_ALLOCATOR | \ + DRM_GPUVA_SPARSE | \ + XE_VMA_MADV_AUTORESET) + static void xe_vm_populate_rebind(struct xe_vma_op *op, struct xe_vma *vma, u8 tile_mask) { @@ -628,8 +635,7 @@ static void xe_vm_populate_rebind(struct xe_vma_op *op, struct xe_vma *vma, op->base.map.gem.offset = vma->gpuva.gem.offset; op->map.vma = vma; op->map.immediate = true; - op->map.dumpable = vma->gpuva.flags & XE_VMA_DUMPABLE; - op->map.is_null = xe_vma_is_null(vma); + op->map.vma_flags = vma->gpuva.flags & XE_VMA_CREATE_MASK; } static int xe_vm_ops_add_rebind(struct xe_vma_ops *vops, struct xe_vma *vma, @@ -932,11 +938,6 @@ static void xe_vma_free(struct xe_vma *vma) kfree(vma); } -#define VMA_CREATE_FLAG_READ_ONLY BIT(0) -#define VMA_CREATE_FLAG_IS_NULL BIT(1) -#define VMA_CREATE_FLAG_DUMPABLE BIT(2) -#define VMA_CREATE_FLAG_IS_SYSTEM_ALLOCATOR BIT(3) - static struct xe_vma *xe_vma_create(struct xe_vm *vm, struct xe_bo *bo, u64 bo_offset_or_userptr, @@ -947,11 +948,8 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm, struct xe_vma *vma; struct xe_tile *tile; u8 id; - bool read_only = (flags & VMA_CREATE_FLAG_READ_ONLY); - bool is_null = (flags & VMA_CREATE_FLAG_IS_NULL); - bool dumpable = (flags & VMA_CREATE_FLAG_DUMPABLE); - bool is_cpu_addr_mirror = - (flags & VMA_CREATE_FLAG_IS_SYSTEM_ALLOCATOR); + bool is_null = (flags & DRM_GPUVA_SPARSE); + bool is_cpu_addr_mirror = (flags & XE_VMA_SYSTEM_ALLOCATOR); xe_assert(vm->xe, start < end); xe_assert(vm->xe, end < vm->size); @@ -972,10 +970,6 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm, if (!vma) return ERR_PTR(-ENOMEM); - if (is_cpu_addr_mirror) - vma->gpuva.flags |= XE_VMA_SYSTEM_ALLOCATOR; - if (is_null) - vma->gpuva.flags |= DRM_GPUVA_SPARSE; if (bo) vma->gpuva.gem.obj = &bo->ttm.base; } @@ -986,10 +980,7 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm, vma->gpuva.vm = &vm->gpuvm; vma->gpuva.va.addr = start; vma->gpuva.va.range = end - start + 1; - if (read_only) - vma->gpuva.flags |= XE_VMA_READ_ONLY; - if (dumpable) - vma->gpuva.flags |= XE_VMA_DUMPABLE; + vma->gpuva.flags = flags; for_each_tile(tile, vm->xe, id) vma->tile_mask |= 0x1 << id; @@ -2272,12 +2263,16 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_vma_ops *vops, if (__op->op == DRM_GPUVA_OP_MAP) { op->map.immediate = flags & DRM_XE_VM_BIND_FLAG_IMMEDIATE; - op->map.read_only = - flags & DRM_XE_VM_BIND_FLAG_READONLY; - op->map.is_null = flags & DRM_XE_VM_BIND_FLAG_NULL; - op->map.is_cpu_addr_mirror = flags & - DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR; - op->map.dumpable = flags & DRM_XE_VM_BIND_FLAG_DUMPABLE; + if (flags & DRM_XE_VM_BIND_FLAG_READONLY) + op->map.vma_flags |= XE_VMA_READ_ONLY; + if (flags & DRM_XE_VM_BIND_FLAG_NULL) + op->map.vma_flags |= DRM_GPUVA_SPARSE; + if (flags & DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR) + op->map.vma_flags |= XE_VMA_SYSTEM_ALLOCATOR; + if (flags & DRM_XE_VM_BIND_FLAG_DUMPABLE) + op->map.vma_flags |= XE_VMA_DUMPABLE; + if (flags & DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET) + op->map.vma_flags |= XE_VMA_MADV_AUTORESET; op->map.pat_index = pat_index; op->map.invalidate_on_bind = __xe_vm_needs_clear_scratch_pages(vm, flags); @@ -2590,14 +2585,7 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops, .pat_index = op->map.pat_index, }; - flags |= op->map.read_only ? - VMA_CREATE_FLAG_READ_ONLY : 0; - flags |= op->map.is_null ? - VMA_CREATE_FLAG_IS_NULL : 0; - flags |= op->map.dumpable ? - VMA_CREATE_FLAG_DUMPABLE : 0; - flags |= op->map.is_cpu_addr_mirror ? - VMA_CREATE_FLAG_IS_SYSTEM_ALLOCATOR : 0; + flags |= op->map.vma_flags & XE_VMA_CREATE_MASK; vma = new_vma(vm, &op->base.map, &default_attr, flags); @@ -2606,7 +2594,7 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops, op->map.vma = vma; if (((op->map.immediate || !xe_vm_in_fault_mode(vm)) && - !op->map.is_cpu_addr_mirror) || + !(op->map.vma_flags & XE_VMA_SYSTEM_ALLOCATOR)) || op->map.invalidate_on_bind) xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask, 1); @@ -2637,18 +2625,7 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops, op->remap.start = xe_vma_start(old); op->remap.range = xe_vma_size(old); - flags |= op->base.remap.unmap->va->flags & - XE_VMA_READ_ONLY ? - VMA_CREATE_FLAG_READ_ONLY : 0; - flags |= op->base.remap.unmap->va->flags & - DRM_GPUVA_SPARSE ? - VMA_CREATE_FLAG_IS_NULL : 0; - flags |= op->base.remap.unmap->va->flags & - XE_VMA_DUMPABLE ? - VMA_CREATE_FLAG_DUMPABLE : 0; - flags |= xe_vma_is_cpu_addr_mirror(old) ? - VMA_CREATE_FLAG_IS_SYSTEM_ALLOCATOR : 0; - + flags |= op->base.remap.unmap->va->flags & XE_VMA_CREATE_MASK; if (op->base.remap.prev) { vma = new_vma(vm, op->base.remap.prev, &old->attr, flags); @@ -3279,7 +3256,8 @@ ALLOW_ERROR_INJECTION(vm_bind_ioctl_ops_execute, ERRNO); DRM_XE_VM_BIND_FLAG_NULL | \ DRM_XE_VM_BIND_FLAG_DUMPABLE | \ DRM_XE_VM_BIND_FLAG_CHECK_PXP | \ - DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR) + DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR | \ + DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET) #ifdef TEST_VM_OPS_ERROR #define SUPPORTED_FLAGS (SUPPORTED_FLAGS_STUB | FORCE_OP_ERROR) @@ -3394,7 +3372,9 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, struct xe_vm *vm, XE_IOCTL_DBG(xe, (prefetch_region != DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC && !(BIT(prefetch_region) & xe->info.mem_region_mask))) || XE_IOCTL_DBG(xe, obj && - op == DRM_XE_VM_BIND_OP_UNMAP)) { + op == DRM_XE_VM_BIND_OP_UNMAP) || + XE_IOCTL_DBG(xe, (flags & DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET) && + (!is_cpu_addr_mirror || op != DRM_XE_VM_BIND_OP_MAP))) { err = -EINVAL; goto free_bind_ops; } @@ -4212,7 +4192,7 @@ static int xe_vm_alloc_vma(struct xe_vm *vm, struct xe_vma_ops vops; struct drm_gpuva_ops *ops = NULL; struct drm_gpuva_op *__op; - bool is_cpu_addr_mirror = false; + unsigned int vma_flags = 0; bool remap_op = false; struct xe_vma_mem_attr tmp_attr; u16 default_pat; @@ -4242,15 +4222,17 @@ static int xe_vm_alloc_vma(struct xe_vm *vm, vma = gpuva_to_vma(op->base.unmap.va); XE_WARN_ON(!xe_vma_has_default_mem_attrs(vma)); default_pat = vma->attr.default_pat_index; + vma_flags = vma->gpuva.flags; } if (__op->op == DRM_GPUVA_OP_REMAP) { vma = gpuva_to_vma(op->base.remap.unmap->va); default_pat = vma->attr.default_pat_index; + vma_flags = vma->gpuva.flags; } if (__op->op == DRM_GPUVA_OP_MAP) { - op->map.is_cpu_addr_mirror = true; + op->map.vma_flags |= vma_flags & XE_VMA_CREATE_MASK; op->map.pat_index = default_pat; } } else { @@ -4259,11 +4241,7 @@ static int xe_vm_alloc_vma(struct xe_vm *vm, xe_assert(vm->xe, !remap_op); xe_assert(vm->xe, xe_vma_has_no_bo(vma)); remap_op = true; - - if (xe_vma_is_cpu_addr_mirror(vma)) - is_cpu_addr_mirror = true; - else - is_cpu_addr_mirror = false; + vma_flags = vma->gpuva.flags; } if (__op->op == DRM_GPUVA_OP_MAP) { @@ -4272,10 +4250,10 @@ static int xe_vm_alloc_vma(struct xe_vm *vm, /* * In case of madvise ops DRM_GPUVA_OP_MAP is * always after DRM_GPUVA_OP_REMAP, so ensure - * we assign op->map.is_cpu_addr_mirror true - * if REMAP is for xe_vma_is_cpu_addr_mirror vma + * to propagate the flags from the vma we're + * unmapping. */ - op->map.is_cpu_addr_mirror = is_cpu_addr_mirror; + op->map.vma_flags |= vma_flags & XE_VMA_CREATE_MASK; } } print_op(vm->xe, __op); diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index 413353e1c225..d6e2a0fdd4b3 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -46,6 +46,7 @@ struct xe_vm_pgtable_update_op; #define XE_VMA_PTE_COMPACT (DRM_GPUVA_USERBITS << 7) #define XE_VMA_DUMPABLE (DRM_GPUVA_USERBITS << 8) #define XE_VMA_SYSTEM_ALLOCATOR (DRM_GPUVA_USERBITS << 9) +#define XE_VMA_MADV_AUTORESET (DRM_GPUVA_USERBITS << 10) /** * struct xe_vma_mem_attr - memory attributes associated with vma @@ -345,17 +346,10 @@ struct xe_vm { struct xe_vma_op_map { /** @vma: VMA to map */ struct xe_vma *vma; + unsigned int vma_flags; /** @immediate: Immediate bind */ bool immediate; /** @read_only: Read only */ - bool read_only; - /** @is_null: is NULL binding */ - bool is_null; - /** @is_cpu_addr_mirror: is CPU address mirror binding */ - bool is_cpu_addr_mirror; - /** @dumpable: whether BO is dumped on GPU hang */ - bool dumpable; - /** @invalidate: invalidate the VMA before bind */ bool invalidate_on_bind; /** @pat_index: The pat index to use for this operation. */ u16 pat_index; diff --git a/drivers/hwmon/cgbc-hwmon.c b/drivers/hwmon/cgbc-hwmon.c index 772f44d56ccf..3aff4e092132 100644 --- a/drivers/hwmon/cgbc-hwmon.c +++ b/drivers/hwmon/cgbc-hwmon.c @@ -107,6 +107,9 @@ static int cgbc_hwmon_probe_sensors(struct device *dev, struct cgbc_hwmon_data * nb_sensors = data[0]; hwmon->sensors = devm_kzalloc(dev, sizeof(*hwmon->sensors) * nb_sensors, GFP_KERNEL); + if (!hwmon->sensors) + return -ENOMEM; + sensor = hwmon->sensors; for (i = 0; i < nb_sensors; i++) { diff --git a/drivers/hwmon/gpd-fan.c b/drivers/hwmon/gpd-fan.c index 644dc3ca9df7..321794807e8d 100644 --- a/drivers/hwmon/gpd-fan.c +++ b/drivers/hwmon/gpd-fan.c @@ -615,14 +615,14 @@ static int gpd_fan_probe(struct platform_device *pdev) const struct device *hwdev; res = platform_get_resource(pdev, IORESOURCE_IO, 0); - if (IS_ERR(res)) - return dev_err_probe(dev, PTR_ERR(res), + if (!res) + return dev_err_probe(dev, -EINVAL, "Failed to get platform resource\n"); region = devm_request_region(dev, res->start, resource_size(res), DRIVER_NAME); - if (IS_ERR(region)) - return dev_err_probe(dev, PTR_ERR(region), + if (!region) + return dev_err_probe(dev, -EBUSY, "Failed to request region\n"); hwdev = devm_hwmon_device_register_with_info(dev, @@ -631,7 +631,7 @@ static int gpd_fan_probe(struct platform_device *pdev) &gpd_fan_chip_info, NULL); if (IS_ERR(hwdev)) - return dev_err_probe(dev, PTR_ERR(region), + return dev_err_probe(dev, PTR_ERR(hwdev), "Failed to register hwmon device\n"); return 0; diff --git a/drivers/hwmon/pmbus/isl68137.c b/drivers/hwmon/pmbus/isl68137.c index 52cf62e45a86..6bba9b50c51b 100644 --- a/drivers/hwmon/pmbus/isl68137.c +++ b/drivers/hwmon/pmbus/isl68137.c @@ -336,10 +336,9 @@ static int isl68137_probe_from_dt(struct device *dev, struct isl68137_data *data) { const struct device_node *np = dev->of_node; - struct device_node *child; int err; - for_each_child_of_node(np, child) { + for_each_child_of_node_scoped(np, child) { if (strcmp(child->name, "channel")) continue; diff --git a/drivers/hwmon/pmbus/max34440.c b/drivers/hwmon/pmbus/max34440.c index 56834d26f8ef..ef981ed97da8 100644 --- a/drivers/hwmon/pmbus/max34440.c +++ b/drivers/hwmon/pmbus/max34440.c @@ -336,18 +336,18 @@ static struct pmbus_driver_info max34440_info[] = { .format[PSC_CURRENT_IN] = direct, .format[PSC_CURRENT_OUT] = direct, .format[PSC_TEMPERATURE] = direct, - .m[PSC_VOLTAGE_IN] = 1, + .m[PSC_VOLTAGE_IN] = 125, .b[PSC_VOLTAGE_IN] = 0, .R[PSC_VOLTAGE_IN] = 0, - .m[PSC_VOLTAGE_OUT] = 1, + .m[PSC_VOLTAGE_OUT] = 125, .b[PSC_VOLTAGE_OUT] = 0, .R[PSC_VOLTAGE_OUT] = 0, - .m[PSC_CURRENT_IN] = 1, + .m[PSC_CURRENT_IN] = 250, .b[PSC_CURRENT_IN] = 0, - .R[PSC_CURRENT_IN] = 2, - .m[PSC_CURRENT_OUT] = 1, + .R[PSC_CURRENT_IN] = -1, + .m[PSC_CURRENT_OUT] = 250, .b[PSC_CURRENT_OUT] = 0, - .R[PSC_CURRENT_OUT] = 2, + .R[PSC_CURRENT_OUT] = -1, .m[PSC_TEMPERATURE] = 1, .b[PSC_TEMPERATURE] = 0, .R[PSC_TEMPERATURE] = 2, diff --git a/drivers/hwmon/sht3x.c b/drivers/hwmon/sht3x.c index 557ad3e7752a..f36c0229328f 100644 --- a/drivers/hwmon/sht3x.c +++ b/drivers/hwmon/sht3x.c @@ -291,24 +291,26 @@ out: return data; } -static int temp1_input_read(struct device *dev) +static int temp1_input_read(struct device *dev, long *temp) { struct sht3x_data *data = sht3x_update_client(dev); if (IS_ERR(data)) return PTR_ERR(data); - return data->temperature; + *temp = data->temperature; + return 0; } -static int humidity1_input_read(struct device *dev) +static int humidity1_input_read(struct device *dev, long *humidity) { struct sht3x_data *data = sht3x_update_client(dev); if (IS_ERR(data)) return PTR_ERR(data); - return data->humidity; + *humidity = data->humidity; + return 0; } /* @@ -706,6 +708,7 @@ static int sht3x_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *val) { enum sht3x_limits index; + int ret; switch (type) { case hwmon_chip: @@ -720,10 +723,12 @@ static int sht3x_read(struct device *dev, enum hwmon_sensor_types type, case hwmon_temp: switch (attr) { case hwmon_temp_input: - *val = temp1_input_read(dev); - break; + return temp1_input_read(dev, val); case hwmon_temp_alarm: - *val = temp1_alarm_read(dev); + ret = temp1_alarm_read(dev); + if (ret < 0) + return ret; + *val = ret; break; case hwmon_temp_max: index = limit_max; @@ -748,10 +753,12 @@ static int sht3x_read(struct device *dev, enum hwmon_sensor_types type, case hwmon_humidity: switch (attr) { case hwmon_humidity_input: - *val = humidity1_input_read(dev); - break; + return humidity1_input_read(dev, val); case hwmon_humidity_alarm: - *val = humidity1_alarm_read(dev); + ret = humidity1_alarm_read(dev); + if (ret < 0) + return ret; + *val = ret; break; case hwmon_humidity_max: index = limit_max; diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c index 6df51ee8db62..cc1d18b3df5c 100644 --- a/drivers/misc/vmw_balloon.c +++ b/drivers/misc/vmw_balloon.c @@ -1737,7 +1737,7 @@ static int vmballoon_migratepage(struct balloon_dev_info *b_dev_info, { unsigned long status, flags; struct vmballoon *b; - int ret; + int ret = 0; b = container_of(b_dev_info, struct vmballoon, b_dev_info); @@ -1796,17 +1796,15 @@ static int vmballoon_migratepage(struct balloon_dev_info *b_dev_info, * A failure happened. While we can deflate the page we just * inflated, this deflation can also encounter an error. Instead * we will decrease the size of the balloon to reflect the - * change and report failure. + * change. */ atomic64_dec(&b->size); - ret = -EBUSY; } else { /* * Success. Take a reference for the page, and we will add it to * the list after acquiring the lock. */ get_page(newpage); - ret = 0; } /* Update the balloon list under the @pages_lock */ @@ -1817,7 +1815,7 @@ static int vmballoon_migratepage(struct balloon_dev_info *b_dev_info, * If we succeed just insert it to the list and update the statistics * under the lock. */ - if (!ret) { + if (status == VMW_BALLOON_SUCCESS) { balloon_page_insert(&b->b_dev_info, newpage); __count_vm_event(BALLOON_MIGRATE); } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 4da619210c1f..e95e593cd12d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2287,7 +2287,9 @@ skip_mac_set: unblock_netpoll_tx(); } - if (bond_mode_can_use_xmit_hash(bond)) + /* broadcast mode uses the all_slaves to loop through slaves. */ + if (bond_mode_can_use_xmit_hash(bond) || + BOND_MODE(bond) == BOND_MODE_BROADCAST) bond_update_slave_arr(bond, NULL); if (!slave_dev->netdev_ops->ndo_bpf || @@ -2463,7 +2465,8 @@ static int __bond_release_one(struct net_device *bond_dev, bond_upper_dev_unlink(bond, slave); - if (bond_mode_can_use_xmit_hash(bond)) + if (bond_mode_can_use_xmit_hash(bond) || + BOND_MODE(bond) == BOND_MODE_BROADCAST) bond_update_slave_arr(bond, slave); slave_info(bond_dev, slave_dev, "Releasing %s interface\n", @@ -2871,7 +2874,7 @@ static void bond_mii_monitor(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, mii_work.work); - bool should_notify_peers = false; + bool should_notify_peers; bool commit; unsigned long delay; struct slave *slave; @@ -2883,30 +2886,33 @@ static void bond_mii_monitor(struct work_struct *work) goto re_arm; rcu_read_lock(); + should_notify_peers = bond_should_notify_peers(bond); commit = !!bond_miimon_inspect(bond); - if (bond->send_peer_notif) { - rcu_read_unlock(); - if (rtnl_trylock()) { - bond->send_peer_notif--; - rtnl_unlock(); - } - } else { - rcu_read_unlock(); - } - if (commit) { + rcu_read_unlock(); + + if (commit || bond->send_peer_notif) { /* Race avoidance with bond_close cancel of workqueue */ if (!rtnl_trylock()) { delay = 1; - should_notify_peers = false; goto re_arm; } - bond_for_each_slave(bond, slave, iter) { - bond_commit_link_state(slave, BOND_SLAVE_NOTIFY_LATER); + if (commit) { + bond_for_each_slave(bond, slave, iter) { + bond_commit_link_state(slave, + BOND_SLAVE_NOTIFY_LATER); + } + bond_miimon_commit(bond); + } + + if (bond->send_peer_notif) { + bond->send_peer_notif--; + if (should_notify_peers) + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, + bond->dev); } - bond_miimon_commit(bond); rtnl_unlock(); /* might sleep, hold no other locks */ } @@ -2914,13 +2920,6 @@ static void bond_mii_monitor(struct work_struct *work) re_arm: if (bond->params.miimon) queue_delayed_work(bond->wq, &bond->mii_work, delay); - - if (should_notify_peers) { - if (!rtnl_trylock()) - return; - call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); - rtnl_unlock(); - } } static int bond_upper_dev_walk(struct net_device *upper, diff --git a/drivers/net/can/bxcan.c b/drivers/net/can/bxcan.c index bfc60eb33dc3..333ad42ea73b 100644 --- a/drivers/net/can/bxcan.c +++ b/drivers/net/can/bxcan.c @@ -842,7 +842,7 @@ static netdev_tx_t bxcan_start_xmit(struct sk_buff *skb, u32 id; int i, j; - if (can_dropped_invalid_skb(ndev, skb)) + if (can_dev_dropped_skb(ndev, skb)) return NETDEV_TX_OK; if (bxcan_tx_busy(priv)) diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 0591406b6f32..6f83b87d54fc 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -452,7 +452,9 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], } if (data[IFLA_CAN_RESTART_MS]) { - if (!priv->do_set_mode) { + unsigned int restart_ms = nla_get_u32(data[IFLA_CAN_RESTART_MS]); + + if (restart_ms != 0 && !priv->do_set_mode) { NL_SET_ERR_MSG(extack, "Device doesn't support restart from Bus Off"); return -EOPNOTSUPP; @@ -461,7 +463,7 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], /* Do not allow changing restart delay while running */ if (dev->flags & IFF_UP) return -EBUSY; - priv->restart_ms = nla_get_u32(data[IFLA_CAN_RESTART_MS]); + priv->restart_ms = restart_ms; } if (data[IFLA_CAN_RESTART]) { diff --git a/drivers/net/can/esd/esdacc.c b/drivers/net/can/esd/esdacc.c index c80032bc1a52..73e66f9a3781 100644 --- a/drivers/net/can/esd/esdacc.c +++ b/drivers/net/can/esd/esdacc.c @@ -254,7 +254,7 @@ netdev_tx_t acc_start_xmit(struct sk_buff *skb, struct net_device *netdev) u32 acc_id; u32 acc_dlc; - if (can_dropped_invalid_skb(netdev, skb)) + if (can_dev_dropped_skb(netdev, skb)) return NETDEV_TX_OK; /* Access core->tx_fifo_tail only once because it may be changed diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c index 865a15e033a9..12200dcfd338 100644 --- a/drivers/net/can/rockchip/rockchip_canfd-tx.c +++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c @@ -72,7 +72,7 @@ netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev) int err; u8 i; - if (can_dropped_invalid_skb(ndev, skb)) + if (can_dev_dropped_skb(ndev, skb)) return NETDEV_TX_OK; if (!netif_subqueue_maybe_stop(priv->ndev, 0, diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index 7077d705e471..6e4f17142519 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -733,7 +733,7 @@ start_xmit (struct sk_buff *skb, struct net_device *dev) u64 tfc_vlan_tag = 0; if (np->link_status == 0) { /* Link Down */ - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } entry = np->cur_tx % TX_RING_SIZE; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index c96d1d6ba8fe..18d86badd6ea 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -1077,8 +1077,7 @@ static int dpaa2_eth_build_single_fd(struct dpaa2_eth_priv *priv, dma_addr_t addr; buffer_start = skb->data - dpaa2_eth_needed_headroom(skb); - aligned_start = PTR_ALIGN(buffer_start - DPAA2_ETH_TX_BUF_ALIGN, - DPAA2_ETH_TX_BUF_ALIGN); + aligned_start = PTR_ALIGN(buffer_start, DPAA2_ETH_TX_BUF_ALIGN); if (aligned_start >= skb->head) buffer_start = aligned_start; else diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index aae462a0cf5a..0535e92404e3 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1595,6 +1595,8 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, /* next descriptor to process */ i = rx_ring->next_to_clean; + enetc_lock_mdio(); + while (likely(rx_frm_cnt < work_limit)) { union enetc_rx_bd *rxbd; struct sk_buff *skb; @@ -1630,7 +1632,9 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, rx_byte_cnt += skb->len + ETH_HLEN; rx_frm_cnt++; + enetc_unlock_mdio(); napi_gro_receive(napi, skb); + enetc_lock_mdio(); } rx_ring->next_to_clean = i; @@ -1638,6 +1642,8 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, rx_ring->stats.packets += rx_frm_cnt; rx_ring->stats.bytes += rx_byte_cnt; + enetc_unlock_mdio(); + return rx_frm_cnt; } @@ -1947,6 +1953,8 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, /* next descriptor to process */ i = rx_ring->next_to_clean; + enetc_lock_mdio(); + while (likely(rx_frm_cnt < work_limit)) { union enetc_rx_bd *rxbd, *orig_rxbd; struct xdp_buff xdp_buff; @@ -2010,7 +2018,9 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, */ enetc_bulk_flip_buff(rx_ring, orig_i, i); + enetc_unlock_mdio(); napi_gro_receive(napi, skb); + enetc_lock_mdio(); break; case XDP_TX: tx_ring = priv->xdp_tx_ring[rx_ring->index]; @@ -2045,7 +2055,9 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, } break; case XDP_REDIRECT: + enetc_unlock_mdio(); err = xdp_do_redirect(rx_ring->ndev, &xdp_buff, prog); + enetc_lock_mdio(); if (unlikely(err)) { enetc_xdp_drop(rx_ring, orig_i, i); rx_ring->stats.xdp_redirect_failures++; @@ -2065,8 +2077,11 @@ out: rx_ring->stats.packets += rx_frm_cnt; rx_ring->stats.bytes += rx_byte_cnt; - if (xdp_redirect_frm_cnt) + if (xdp_redirect_frm_cnt) { + enetc_unlock_mdio(); xdp_do_flush(); + enetc_lock_mdio(); + } if (xdp_tx_frm_cnt) enetc_update_tx_ring_tail(tx_ring); @@ -2075,6 +2090,8 @@ out: enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring) - rx_ring->xdp.xdp_tx_in_flight); + enetc_unlock_mdio(); + return rx_frm_cnt; } @@ -2093,6 +2110,7 @@ static int enetc_poll(struct napi_struct *napi, int budget) for (i = 0; i < v->count_tx_rings; i++) if (!enetc_clean_tx_ring(&v->tx_ring[i], budget)) complete = false; + enetc_unlock_mdio(); prog = rx_ring->xdp.prog; if (prog) @@ -2104,10 +2122,8 @@ static int enetc_poll(struct napi_struct *napi, int budget) if (work_done) v->rx_napi_work = true; - if (!complete) { - enetc_unlock_mdio(); + if (!complete) return budget; - } napi_complete_done(napi, work_done); @@ -2116,6 +2132,7 @@ static int enetc_poll(struct napi_struct *napi, int budget) v->rx_napi_work = false; + enetc_lock_mdio(); /* enable interrupts */ enetc_wr_reg_hot(v->rbier, ENETC_RBIER_RXTIE); diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index 0ec010a7d640..f279fa597991 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -76,7 +76,7 @@ struct enetc_lso_t { #define ENETC_LSO_MAX_DATA_LEN SZ_256K #define ENETC_RX_MAXFRM_SIZE ENETC_MAC_MAXFRM_SIZE -#define ENETC_RXB_TRUESIZE 2048 /* PAGE_SIZE >> 1 */ +#define ENETC_RXB_TRUESIZE (PAGE_SIZE >> 1) #define ENETC_RXB_PAD NET_SKB_PAD /* add extra space if needed */ #define ENETC_RXB_DMA_SIZE \ (SKB_WITH_OVERHEAD(ENETC_RXB_TRUESIZE) - ENETC_RXB_PAD) diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 65302c41bfb1..38875c196cb6 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -148,6 +148,7 @@ config HIBMCGE tristate "Hisilicon BMC Gigabit Ethernet Device Support" depends on PCI && PCI_MSI select PHYLIB + select FIXED_PHY select MOTORCOMM_PHY select REALTEK_PHY help diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 3692298e10f2..c9bdee9a8b30 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -100,7 +100,7 @@ u8 mlx5e_mpwrq_umr_entry_size(enum mlx5e_mpwrq_umr_mode mode) return sizeof(struct mlx5_ksm) * 4; } WARN_ONCE(1, "MPWRQ UMR mode %d is not known\n", mode); - return 0; + return 1; } u8 mlx5e_mpwrq_log_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index 5d7c15abfcaf..f8eaaf37963b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -342,6 +342,7 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry, void mlx5e_ipsec_handle_mpv_event(int event, struct mlx5e_priv *slave_priv, struct mlx5e_priv *master_priv); void mlx5e_ipsec_send_event(struct mlx5e_priv *priv, int event); +void mlx5e_ipsec_disable_events(struct mlx5e_priv *priv); static inline struct mlx5_core_dev * mlx5e_ipsec_sa2dev(struct mlx5e_ipsec_sa_entry *sa_entry) @@ -387,6 +388,10 @@ static inline void mlx5e_ipsec_handle_mpv_event(int event, struct mlx5e_priv *sl static inline void mlx5e_ipsec_send_event(struct mlx5e_priv *priv, int event) { } + +static inline void mlx5e_ipsec_disable_events(struct mlx5e_priv *priv) +{ +} #endif #endif /* __MLX5E_IPSEC_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index bf1d2769d4f1..feef86fff4bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -2893,9 +2893,30 @@ void mlx5e_ipsec_handle_mpv_event(int event, struct mlx5e_priv *slave_priv, void mlx5e_ipsec_send_event(struct mlx5e_priv *priv, int event) { - if (!priv->ipsec) - return; /* IPsec not supported */ + if (!priv->ipsec || mlx5_devcom_comp_get_size(priv->devcom) < 2) + return; /* IPsec not supported or no peers */ mlx5_devcom_send_event(priv->devcom, event, event, priv); wait_for_completion(&priv->ipsec->comp); } + +void mlx5e_ipsec_disable_events(struct mlx5e_priv *priv) +{ + struct mlx5_devcom_comp_dev *tmp = NULL; + struct mlx5e_priv *peer_priv; + + if (!priv->devcom) + return; + + if (!mlx5_devcom_for_each_peer_begin(priv->devcom)) + goto out; + + peer_priv = mlx5_devcom_get_next_peer_data(priv->devcom, &tmp); + if (peer_priv) + complete_all(&peer_priv->ipsec->comp); + + mlx5_devcom_for_each_peer_end(priv->devcom); +out: + mlx5_devcom_unregister_component(priv->devcom); + priv->devcom = NULL; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index a56825921c23..9c46511e7b43 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -242,8 +242,8 @@ static int mlx5e_devcom_init_mpv(struct mlx5e_priv *priv, u64 *data) &attr, mlx5e_devcom_event_mpv, priv); - if (IS_ERR(priv->devcom)) - return PTR_ERR(priv->devcom); + if (!priv->devcom) + return -EINVAL; if (mlx5_core_is_mp_master(priv->mdev)) { mlx5_devcom_send_event(priv->devcom, MPV_DEVCOM_MASTER_UP, @@ -256,7 +256,7 @@ static int mlx5e_devcom_init_mpv(struct mlx5e_priv *priv, u64 *data) static void mlx5e_devcom_cleanup_mpv(struct mlx5e_priv *priv) { - if (IS_ERR_OR_NULL(priv->devcom)) + if (!priv->devcom) return; if (mlx5_core_is_mp_master(priv->mdev)) { @@ -266,6 +266,7 @@ static void mlx5e_devcom_cleanup_mpv(struct mlx5e_priv *priv) } mlx5_devcom_unregister_component(priv->devcom); + priv->devcom = NULL; } static int blocking_event(struct notifier_block *nb, unsigned long event, void *data) @@ -6120,6 +6121,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) if (mlx5e_monitor_counter_supported(priv)) mlx5e_monitor_counter_cleanup(priv); + mlx5e_ipsec_disable_events(priv); mlx5e_disable_blocking_events(priv); mlx5e_disable_async_events(priv); mlx5_lag_remove_netdev(mdev, priv->netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 263d5628ee44..1c79adc51a04 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1794,14 +1794,27 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi } prog = rcu_dereference(rq->xdp_prog); - if (prog && mlx5e_xdp_handle(rq, prog, mxbuf)) { - if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { - struct mlx5e_wqe_frag_info *pwi; + if (prog) { + u8 nr_frags_free, old_nr_frags = sinfo->nr_frags; + + if (mlx5e_xdp_handle(rq, prog, mxbuf)) { + if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, + rq->flags)) { + struct mlx5e_wqe_frag_info *pwi; + + wi -= old_nr_frags - sinfo->nr_frags; + + for (pwi = head_wi; pwi < wi; pwi++) + pwi->frag_page->frags++; + } + return NULL; /* page/packet was consumed by XDP */ + } - for (pwi = head_wi; pwi < wi; pwi++) - pwi->frag_page->frags++; + nr_frags_free = old_nr_frags - sinfo->nr_frags; + if (unlikely(nr_frags_free)) { + wi -= nr_frags_free; + truesize -= nr_frags_free * frag_info->frag_stride; } - return NULL; /* page/packet was consumed by XDP */ } skb = mlx5e_build_linear_skb( @@ -2027,6 +2040,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w u32 byte_cnt = cqe_bcnt; struct skb_shared_info *sinfo; unsigned int truesize = 0; + u32 pg_consumed_bytes; struct bpf_prog *prog; struct sk_buff *skb; u32 linear_frame_sz; @@ -2080,7 +2094,8 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w while (byte_cnt) { /* Non-linear mode, hence non-XSK, which always uses PAGE_SIZE. */ - u32 pg_consumed_bytes = min_t(u32, PAGE_SIZE - frag_offset, byte_cnt); + pg_consumed_bytes = + min_t(u32, PAGE_SIZE - frag_offset, byte_cnt); if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) truesize += pg_consumed_bytes; @@ -2096,10 +2111,15 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w } if (prog) { + u8 nr_frags_free, old_nr_frags = sinfo->nr_frags; + u32 len; + if (mlx5e_xdp_handle(rq, prog, mxbuf)) { if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { struct mlx5e_frag_page *pfp; + frag_page -= old_nr_frags - sinfo->nr_frags; + for (pfp = head_page; pfp < frag_page; pfp++) pfp->frags++; @@ -2110,9 +2130,19 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w return NULL; /* page/packet was consumed by XDP */ } + nr_frags_free = old_nr_frags - sinfo->nr_frags; + if (unlikely(nr_frags_free)) { + frag_page -= nr_frags_free; + truesize -= (nr_frags_free - 1) * PAGE_SIZE + + ALIGN(pg_consumed_bytes, + BIT(rq->mpwqe.log_stride_sz)); + } + + len = mxbuf->xdp.data_end - mxbuf->xdp.data; + skb = mlx5e_build_linear_skb( rq, mxbuf->xdp.data_hard_start, linear_frame_sz, - mxbuf->xdp.data - mxbuf->xdp.data_hard_start, 0, + mxbuf->xdp.data - mxbuf->xdp.data_hard_start, len, mxbuf->xdp.data - mxbuf->xdp.data_meta); if (unlikely(!skb)) { mlx5e_page_release_fragmented(rq->page_pool, @@ -2137,8 +2167,11 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w do pagep->frags++; while (++pagep < frag_page); + + headlen = min_t(u16, MLX5E_RX_MAX_HEAD - len, + skb->data_len); + __pskb_pull_tail(skb, headlen); } - __pskb_pull_tail(skb, headlen); } else { dma_addr_t addr; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 7c029a7d0fd7..a2802cfc9b98 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -1614,7 +1614,9 @@ void mlx5e_stats_fec_get(struct mlx5e_priv *priv, fec_set_corrected_bits_total(priv, fec_stats); fec_set_block_stats(priv, mode, fec_stats); - fec_set_histograms_stats(priv, mode, hist); + + if (MLX5_CAP_PCAM_REG(priv->mdev, pphcr)) + fec_set_histograms_stats(priv, mode, hist); } #define PPORT_ETH_EXT_OFF(c) \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index b7227afcb51d..2702b3885f06 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -256,7 +256,7 @@ mlx5e_tx_wqe_inline_mode(struct mlx5e_txqsq *sq, struct sk_buff *skb, u8 mode; #ifdef CONFIG_MLX5_EN_TLS - if (accel && accel->tls.tls_tisn) + if (accel->tls.tls_tisn) return MLX5_INLINE_MODE_TCP_UDP; #endif @@ -982,6 +982,7 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5e_tx_attr attr; struct mlx5i_tx_wqe *wqe; + struct mlx5e_accel_tx_state accel = {}; struct mlx5_wqe_datagram_seg *datagram; struct mlx5_wqe_ctrl_seg *cseg; struct mlx5_wqe_eth_seg *eseg; @@ -992,7 +993,7 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, int num_dma; u16 pi; - mlx5e_sq_xmit_prepare(sq, skb, NULL, &attr); + mlx5e_sq_xmit_prepare(sq, skb, &accel, &attr); mlx5i_sq_calc_wqe_attr(skb, &attr, &wqe_attr); pi = mlx5e_txqsq_get_next_pi(sq, wqe_attr.num_wqebbs); @@ -1009,7 +1010,7 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, mlx5i_txwqe_build_datagram(av, dqpn, dqkey, datagram); - mlx5e_txwqe_build_eseg_csum(sq, skb, NULL, eseg); + mlx5e_txwqe_build_eseg_csum(sq, skb, &accel, eseg); eseg->mss = attr.mss; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 4cf995be127d..34749814f19b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -3129,7 +3129,7 @@ void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw, attr, mlx5_esw_offloads_devcom_event, esw); - if (IS_ERR(esw->devcom)) + if (!esw->devcom) return; mlx5_devcom_send_event(esw->devcom, @@ -3140,7 +3140,7 @@ void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw, void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) { - if (IS_ERR_OR_NULL(esw->devcom)) + if (!esw->devcom) return; mlx5_devcom_send_event(esw->devcom, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 59c00c911275..3db0387bf6dc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -1430,11 +1430,10 @@ static int mlx5_lag_register_hca_devcom_comp(struct mlx5_core_dev *dev) mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_HCA_PORTS, &attr, NULL, dev); - if (IS_ERR(dev->priv.hca_devcom_comp)) { + if (!dev->priv.hca_devcom_comp) { mlx5_core_err(dev, - "Failed to register devcom HCA component, err: %ld\n", - PTR_ERR(dev->priv.hca_devcom_comp)); - return PTR_ERR(dev->priv.hca_devcom_comp); + "Failed to register devcom HCA component."); + return -EINVAL; } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index d0ba83d77cd1..29e7fa09c32c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -1444,7 +1444,7 @@ static void mlx5_shared_clock_register(struct mlx5_core_dev *mdev, u64 key) compd = mlx5_devcom_register_component(mdev->priv.devc, MLX5_DEVCOM_SHARED_CLOCK, &attr, NULL, mdev); - if (IS_ERR(compd)) + if (!compd) return; mdev->clock_state->compdev = compd; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c index faa2833602c8..e749618229bc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c @@ -76,20 +76,18 @@ mlx5_devcom_dev_alloc(struct mlx5_core_dev *dev) struct mlx5_devcom_dev * mlx5_devcom_register_device(struct mlx5_core_dev *dev) { - struct mlx5_devcom_dev *devc; + struct mlx5_devcom_dev *devc = NULL; mutex_lock(&dev_list_lock); if (devcom_dev_exists(dev)) { - devc = ERR_PTR(-EEXIST); + mlx5_core_err(dev, "devcom device already exists"); goto out; } devc = mlx5_devcom_dev_alloc(dev); - if (!devc) { - devc = ERR_PTR(-ENOMEM); + if (!devc) goto out; - } list_add_tail(&devc->list, &devcom_dev_list); out: @@ -110,8 +108,10 @@ mlx5_devcom_dev_release(struct kref *ref) void mlx5_devcom_unregister_device(struct mlx5_devcom_dev *devc) { - if (!IS_ERR_OR_NULL(devc)) - kref_put(&devc->ref, mlx5_devcom_dev_release); + if (!devc) + return; + + kref_put(&devc->ref, mlx5_devcom_dev_release); } static struct mlx5_devcom_comp * @@ -122,7 +122,7 @@ mlx5_devcom_comp_alloc(u64 id, const struct mlx5_devcom_match_attr *attr, comp = kzalloc(sizeof(*comp), GFP_KERNEL); if (!comp) - return ERR_PTR(-ENOMEM); + return NULL; comp->id = id; comp->key.key = attr->key; @@ -160,7 +160,7 @@ devcom_alloc_comp_dev(struct mlx5_devcom_dev *devc, devcom = kzalloc(sizeof(*devcom), GFP_KERNEL); if (!devcom) - return ERR_PTR(-ENOMEM); + return NULL; kref_get(&devc->ref); devcom->devc = devc; @@ -240,31 +240,28 @@ mlx5_devcom_register_component(struct mlx5_devcom_dev *devc, mlx5_devcom_event_handler_t handler, void *data) { - struct mlx5_devcom_comp_dev *devcom; + struct mlx5_devcom_comp_dev *devcom = NULL; struct mlx5_devcom_comp *comp; - if (IS_ERR_OR_NULL(devc)) - return ERR_PTR(-EINVAL); + if (!devc) + return NULL; mutex_lock(&comp_list_lock); comp = devcom_component_get(devc, id, attr, handler); - if (IS_ERR(comp)) { - devcom = ERR_PTR(-EINVAL); + if (IS_ERR(comp)) goto out_unlock; - } if (!comp) { comp = mlx5_devcom_comp_alloc(id, attr, handler); - if (IS_ERR(comp)) { - devcom = ERR_CAST(comp); + if (!comp) goto out_unlock; - } + list_add_tail(&comp->comp_list, &devcom_comp_list); } mutex_unlock(&comp_list_lock); devcom = devcom_alloc_comp_dev(devc, comp, data); - if (IS_ERR(devcom)) + if (!devcom) kref_put(&comp->ref, mlx5_devcom_comp_release); return devcom; @@ -276,8 +273,10 @@ out_unlock: void mlx5_devcom_unregister_component(struct mlx5_devcom_comp_dev *devcom) { - if (!IS_ERR_OR_NULL(devcom)) - devcom_free_comp_dev(devcom); + if (!devcom) + return; + + devcom_free_comp_dev(devcom); } int mlx5_devcom_comp_get_size(struct mlx5_devcom_comp_dev *devcom) @@ -296,7 +295,7 @@ int mlx5_devcom_send_event(struct mlx5_devcom_comp_dev *devcom, int err = 0; void *data; - if (IS_ERR_OR_NULL(devcom)) + if (!devcom) return -ENODEV; comp = devcom->comp; @@ -338,7 +337,7 @@ void mlx5_devcom_comp_set_ready(struct mlx5_devcom_comp_dev *devcom, bool ready) bool mlx5_devcom_comp_is_ready(struct mlx5_devcom_comp_dev *devcom) { - if (IS_ERR_OR_NULL(devcom)) + if (!devcom) return false; return READ_ONCE(devcom->comp->ready); @@ -348,7 +347,7 @@ bool mlx5_devcom_for_each_peer_begin(struct mlx5_devcom_comp_dev *devcom) { struct mlx5_devcom_comp *comp; - if (IS_ERR_OR_NULL(devcom)) + if (!devcom) return false; comp = devcom->comp; @@ -421,21 +420,21 @@ void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom_comp_dev *devcom, void mlx5_devcom_comp_lock(struct mlx5_devcom_comp_dev *devcom) { - if (IS_ERR_OR_NULL(devcom)) + if (!devcom) return; down_write(&devcom->comp->sem); } void mlx5_devcom_comp_unlock(struct mlx5_devcom_comp_dev *devcom) { - if (IS_ERR_OR_NULL(devcom)) + if (!devcom) return; up_write(&devcom->comp->sem); } int mlx5_devcom_comp_trylock(struct mlx5_devcom_comp_dev *devcom) { - if (IS_ERR_OR_NULL(devcom)) + if (!devcom) return 0; return down_write_trylock(&devcom->comp->sem); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c index f5c2701f6e87..8e17daae48af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -221,8 +221,8 @@ static int sd_register(struct mlx5_core_dev *dev) attr.net = mlx5_core_net(dev); devcom = mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_SD_GROUP, &attr, NULL, dev); - if (IS_ERR(devcom)) - return PTR_ERR(devcom); + if (!devcom) + return -EINVAL; sd->devcom = devcom; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index df93625c9dfa..70c156591b0b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -978,9 +978,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) int err; dev->priv.devc = mlx5_devcom_register_device(dev); - if (IS_ERR(dev->priv.devc)) - mlx5_core_warn(dev, "failed to register devcom device %pe\n", - dev->priv.devc); + if (!dev->priv.devc) + mlx5_core_warn(dev, "failed to register devcom device\n"); err = mlx5_query_board_id(dev); if (err) { diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 9d3bd65b85ff..e2d7ce1a85e8 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -2211,15 +2211,35 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) skb_tx_timestamp(skb); } - /* Descriptor type must be set after all the above writes */ - dma_wmb(); + if (num_tx_desc > 1) { desc->die_dt = DT_FEND; desc--; + /* When using multi-descriptors, DT_FEND needs to get written + * before DT_FSTART, but the compiler may reorder the memory + * writes in an attempt to optimize the code. + * Use a dma_wmb() barrier to make sure DT_FEND and DT_FSTART + * are written exactly in the order shown in the code. + * This is particularly important for cases where the DMA engine + * is already running when we are running this code. If the DMA + * sees DT_FSTART without the corresponding DT_FEND it will enter + * an error condition. + */ + dma_wmb(); desc->die_dt = DT_FSTART; } else { + /* Descriptor type must be set after all the above writes */ + dma_wmb(); desc->die_dt = DT_FSINGLE; } + + /* Before ringing the doorbell we need to make sure that the latest + * writes have been committed to memory, otherwise it could delay + * things until the doorbell is rang again. + * This is in replacement of the read operation mentioned in the HW + * manuals. + */ + dma_wmb(); ravb_modify(ndev, TCCR, TCCR_TSRQ0 << q, TCCR_TSRQ0 << q); priv->cur_tx[q] += num_tx_desc; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 51ea0caf16c1..0786816e05f0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -1446,14 +1446,15 @@ static int gmac_clk_enable(struct rk_priv_data *bsp_priv, bool enable) } } else { if (bsp_priv->clk_enabled) { + if (bsp_priv->ops && bsp_priv->ops->set_clock_selection) { + bsp_priv->ops->set_clock_selection(bsp_priv, + bsp_priv->clock_input, false); + } + clk_bulk_disable_unprepare(bsp_priv->num_clks, bsp_priv->clks); clk_disable_unprepare(bsp_priv->clk_phy); - if (bsp_priv->ops && bsp_priv->ops->set_clock_selection) - bsp_priv->ops->set_clock_selection(bsp_priv, - bsp_priv->clock_input, false); - bsp_priv->clk_enabled = false; } } diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index 59d6ab989c55..8ffbfaa3ab18 100644 --- a/drivers/net/ethernet/ti/am65-cpts.c +++ b/drivers/net/ethernet/ti/am65-cpts.c @@ -163,7 +163,9 @@ struct am65_cpts { struct device_node *clk_mux_np; struct clk *refclk; u32 refclk_freq; - struct list_head events; + /* separate lists to handle TX and RX timestamp independently */ + struct list_head events_tx; + struct list_head events_rx; struct list_head pool; struct am65_cpts_event pool_data[AM65_CPTS_MAX_EVENTS]; spinlock_t lock; /* protects events lists*/ @@ -227,6 +229,24 @@ static void am65_cpts_disable(struct am65_cpts *cpts) am65_cpts_write32(cpts, 0, int_enable); } +static int am65_cpts_purge_event_list(struct am65_cpts *cpts, + struct list_head *events) +{ + struct list_head *this, *next; + struct am65_cpts_event *event; + int removed = 0; + + list_for_each_safe(this, next, events) { + event = list_entry(this, struct am65_cpts_event, list); + if (time_after(jiffies, event->tmo)) { + list_del_init(&event->list); + list_add(&event->list, &cpts->pool); + ++removed; + } + } + return removed; +} + static int am65_cpts_event_get_port(struct am65_cpts_event *event) { return (event->event1 & AM65_CPTS_EVENT_1_PORT_NUMBER_MASK) >> @@ -239,20 +259,12 @@ static int am65_cpts_event_get_type(struct am65_cpts_event *event) AM65_CPTS_EVENT_1_EVENT_TYPE_SHIFT; } -static int am65_cpts_cpts_purge_events(struct am65_cpts *cpts) +static int am65_cpts_purge_events(struct am65_cpts *cpts) { - struct list_head *this, *next; - struct am65_cpts_event *event; int removed = 0; - list_for_each_safe(this, next, &cpts->events) { - event = list_entry(this, struct am65_cpts_event, list); - if (time_after(jiffies, event->tmo)) { - list_del_init(&event->list); - list_add(&event->list, &cpts->pool); - ++removed; - } - } + removed += am65_cpts_purge_event_list(cpts, &cpts->events_tx); + removed += am65_cpts_purge_event_list(cpts, &cpts->events_rx); if (removed) dev_dbg(cpts->dev, "event pool cleaned up %d\n", removed); @@ -287,7 +299,7 @@ static int __am65_cpts_fifo_read(struct am65_cpts *cpts) struct am65_cpts_event, list); if (!event) { - if (am65_cpts_cpts_purge_events(cpts)) { + if (am65_cpts_purge_events(cpts)) { dev_err(cpts->dev, "cpts: event pool empty\n"); ret = -1; goto out; @@ -306,11 +318,21 @@ static int __am65_cpts_fifo_read(struct am65_cpts *cpts) cpts->timestamp); break; case AM65_CPTS_EV_RX: + event->tmo = jiffies + + msecs_to_jiffies(AM65_CPTS_EVENT_RX_TX_TIMEOUT); + + list_move_tail(&event->list, &cpts->events_rx); + + dev_dbg(cpts->dev, + "AM65_CPTS_EV_RX e1:%08x e2:%08x t:%lld\n", + event->event1, event->event2, + event->timestamp); + break; case AM65_CPTS_EV_TX: event->tmo = jiffies + msecs_to_jiffies(AM65_CPTS_EVENT_RX_TX_TIMEOUT); - list_move_tail(&event->list, &cpts->events); + list_move_tail(&event->list, &cpts->events_tx); dev_dbg(cpts->dev, "AM65_CPTS_EV_TX e1:%08x e2:%08x t:%lld\n", @@ -828,7 +850,7 @@ static bool am65_cpts_match_tx_ts(struct am65_cpts *cpts, return found; } -static void am65_cpts_find_ts(struct am65_cpts *cpts) +static void am65_cpts_find_tx_ts(struct am65_cpts *cpts) { struct am65_cpts_event *event; struct list_head *this, *next; @@ -837,7 +859,7 @@ static void am65_cpts_find_ts(struct am65_cpts *cpts) LIST_HEAD(events); spin_lock_irqsave(&cpts->lock, flags); - list_splice_init(&cpts->events, &events); + list_splice_init(&cpts->events_tx, &events); spin_unlock_irqrestore(&cpts->lock, flags); list_for_each_safe(this, next, &events) { @@ -850,7 +872,7 @@ static void am65_cpts_find_ts(struct am65_cpts *cpts) } spin_lock_irqsave(&cpts->lock, flags); - list_splice_tail(&events, &cpts->events); + list_splice_tail(&events, &cpts->events_tx); list_splice_tail(&events_free, &cpts->pool); spin_unlock_irqrestore(&cpts->lock, flags); } @@ -861,7 +883,7 @@ static long am65_cpts_ts_work(struct ptp_clock_info *ptp) unsigned long flags; long delay = -1; - am65_cpts_find_ts(cpts); + am65_cpts_find_tx_ts(cpts); spin_lock_irqsave(&cpts->txq.lock, flags); if (!skb_queue_empty(&cpts->txq)) @@ -905,7 +927,7 @@ static u64 am65_cpts_find_rx_ts(struct am65_cpts *cpts, u32 skb_mtype_seqid) spin_lock_irqsave(&cpts->lock, flags); __am65_cpts_fifo_read(cpts); - list_for_each_safe(this, next, &cpts->events) { + list_for_each_safe(this, next, &cpts->events_rx) { event = list_entry(this, struct am65_cpts_event, list); if (time_after(jiffies, event->tmo)) { list_move(&event->list, &cpts->pool); @@ -1155,7 +1177,8 @@ struct am65_cpts *am65_cpts_create(struct device *dev, void __iomem *regs, return ERR_PTR(ret); mutex_init(&cpts->ptp_clk_lock); - INIT_LIST_HEAD(&cpts->events); + INIT_LIST_HEAD(&cpts->events_tx); + INIT_LIST_HEAD(&cpts->events_rx); INIT_LIST_HEAD(&cpts->pool); spin_lock_init(&cpts->lock); skb_queue_head_init(&cpts->txq); diff --git a/drivers/net/ovpn/tcp.c b/drivers/net/ovpn/tcp.c index 289f62c5d2c7..0d7f30360d87 100644 --- a/drivers/net/ovpn/tcp.c +++ b/drivers/net/ovpn/tcp.c @@ -560,16 +560,34 @@ static void ovpn_tcp_close(struct sock *sk, long timeout) static __poll_t ovpn_tcp_poll(struct file *file, struct socket *sock, poll_table *wait) { - __poll_t mask = datagram_poll(file, sock, wait); + struct sk_buff_head *queue = &sock->sk->sk_receive_queue; struct ovpn_socket *ovpn_sock; + struct ovpn_peer *peer = NULL; + __poll_t mask; rcu_read_lock(); ovpn_sock = rcu_dereference_sk_user_data(sock->sk); - if (ovpn_sock && ovpn_sock->peer && - !skb_queue_empty(&ovpn_sock->peer->tcp.user_queue)) - mask |= EPOLLIN | EPOLLRDNORM; + /* if we landed in this callback, we expect to have a + * meaningful state. The ovpn_socket lifecycle would + * prevent it otherwise. + */ + if (WARN(!ovpn_sock || !ovpn_sock->peer, + "ovpn: null state in ovpn_tcp_poll!")) { + rcu_read_unlock(); + return 0; + } + + if (ovpn_peer_hold(ovpn_sock->peer)) { + peer = ovpn_sock->peer; + queue = &peer->tcp.user_queue; + } rcu_read_unlock(); + mask = datagram_poll_queue(file, sock, wait, queue); + + if (peer) + ovpn_peer_put(peer); + return mask; } diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 79ce3eb6752b..604b5de0c158 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -4262,6 +4262,8 @@ static int __lan8814_ptp_probe_once(struct phy_device *phydev, char *pin_name, { struct lan8814_shared_priv *shared = phy_package_get_priv(phydev); + shared->phydev = phydev; + /* Initialise shared lock for clock*/ mutex_init(&shared->shared_lock); @@ -4317,8 +4319,6 @@ static int __lan8814_ptp_probe_once(struct phy_device *phydev, char *pin_name, phydev_dbg(phydev, "successfully registered ptp clock\n"); - shared->phydev = phydev; - /* The EP.4 is shared between all the PHYs in the package and also it * can be accessed by any of the PHYs */ diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c index a724b21b4fe7..16a347084293 100644 --- a/drivers/net/phy/realtek/realtek_main.c +++ b/drivers/net/phy/realtek/realtek_main.c @@ -154,7 +154,7 @@ #define RTL_8211FVD_PHYID 0x001cc878 #define RTL_8221B 0x001cc840 #define RTL_8221B_VB_CG 0x001cc849 -#define RTL_8221B_VN_CG 0x001cc84a +#define RTL_8221B_VM_CG 0x001cc84a #define RTL_8251B 0x001cc862 #define RTL_8261C 0x001cc890 @@ -1523,16 +1523,16 @@ static int rtl8221b_vb_cg_c45_match_phy_device(struct phy_device *phydev, return rtlgen_is_c45_match(phydev, RTL_8221B_VB_CG, true); } -static int rtl8221b_vn_cg_c22_match_phy_device(struct phy_device *phydev, +static int rtl8221b_vm_cg_c22_match_phy_device(struct phy_device *phydev, const struct phy_driver *phydrv) { - return rtlgen_is_c45_match(phydev, RTL_8221B_VN_CG, false); + return rtlgen_is_c45_match(phydev, RTL_8221B_VM_CG, false); } -static int rtl8221b_vn_cg_c45_match_phy_device(struct phy_device *phydev, +static int rtl8221b_vm_cg_c45_match_phy_device(struct phy_device *phydev, const struct phy_driver *phydrv) { - return rtlgen_is_c45_match(phydev, RTL_8221B_VN_CG, true); + return rtlgen_is_c45_match(phydev, RTL_8221B_VM_CG, true); } static int rtl_internal_nbaset_match_phy_device(struct phy_device *phydev, @@ -1879,7 +1879,7 @@ static struct phy_driver realtek_drvs[] = { .suspend = genphy_c45_pma_suspend, .resume = rtlgen_c45_resume, }, { - .match_phy_device = rtl8221b_vn_cg_c22_match_phy_device, + .match_phy_device = rtl8221b_vm_cg_c22_match_phy_device, .name = "RTL8221B-VM-CG 2.5Gbps PHY (C22)", .probe = rtl822x_probe, .get_features = rtl822x_get_features, @@ -1892,8 +1892,8 @@ static struct phy_driver realtek_drvs[] = { .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, }, { - .match_phy_device = rtl8221b_vn_cg_c45_match_phy_device, - .name = "RTL8221B-VN-CG 2.5Gbps PHY (C45)", + .match_phy_device = rtl8221b_vm_cg_c45_match_phy_device, + .name = "RTL8221B-VM-CG 2.5Gbps PHY (C45)", .probe = rtl822x_probe, .config_init = rtl822xb_config_init, .get_rate_matching = rtl822xb_get_rate_matching, diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 92add3daadbb..278e6cb6f4d9 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -685,9 +685,16 @@ static netdev_tx_t rtl8150_start_xmit(struct sk_buff *skb, rtl8150_t *dev = netdev_priv(netdev); int count, res; + /* pad the frame and ensure terminating USB packet, datasheet 9.2.3 */ + count = max(skb->len, ETH_ZLEN); + if (count % 64 == 0) + count++; + if (skb_padto(skb, count)) { + netdev->stats.tx_dropped++; + return NETDEV_TX_OK; + } + netif_stop_queue(netdev); - count = (skb->len < 60) ? 60 : skb->len; - count = (count & 0x3f) ? count : count + 1; dev->tx_skb = skb; usb_fill_bulk_urb(dev->tx_urb, dev->udev, usb_sndbulkpipe(dev->udev, 2), skb->data, count, write_bulk_callback, dev); diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 65c3c23255b7..1cd93549d093 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -671,6 +671,36 @@ err: } } +static int of_check_msi_parent(struct device_node *dev_node, struct device_node **msi_node) +{ + struct of_phandle_args msi_spec; + int ret; + + /* + * An msi-parent phandle with a missing or == 0 #msi-cells + * property identifies a 1:1 ID translation mapping. + * + * Set the msi controller node if the firmware matches this + * condition. + */ + ret = of_parse_phandle_with_optional_args(dev_node, "msi-parent", "#msi-cells", + 0, &msi_spec); + if (ret) + return ret; + + if ((*msi_node && *msi_node != msi_spec.np) || msi_spec.args_count != 0) + ret = -EINVAL; + + if (!ret) { + /* Return with a node reference held */ + *msi_node = msi_spec.np; + return 0; + } + of_node_put(msi_spec.np); + + return ret; +} + /** * of_msi_xlate - map a MSI ID and find relevant MSI controller node * @dev: device for which the mapping is to be done. @@ -678,7 +708,7 @@ err: * @id_in: Device ID. * * Walk up the device hierarchy looking for devices with a "msi-map" - * property. If found, apply the mapping to @id_in. + * or "msi-parent" property. If found, apply the mapping to @id_in. * If @msi_np points to a non-NULL device node pointer, only entries targeting * that node will be matched; if it points to a NULL value, it will receive the * device node of the first matching target phandle, with a reference held. @@ -692,14 +722,18 @@ u32 of_msi_xlate(struct device *dev, struct device_node **msi_np, u32 id_in) /* * Walk up the device parent links looking for one with a - * "msi-map" property. + * "msi-map" or an "msi-parent" property. */ - for (parent_dev = dev; parent_dev; parent_dev = parent_dev->parent) + for (parent_dev = dev; parent_dev; parent_dev = parent_dev->parent) { if (!of_map_id(parent_dev->of_node, id_in, "msi-map", "msi-map-mask", msi_np, &id_out)) break; + if (!of_check_msi_parent(parent_dev->of_node, msi_np)) + break; + } return id_out; } +EXPORT_SYMBOL_GPL(of_msi_xlate); /** * of_msi_map_get_device_domain - Use msi-map to find the relevant MSI domain @@ -741,8 +775,10 @@ struct irq_domain *of_msi_get_domain(struct device *dev, of_for_each_phandle(&it, err, np, "msi-parent", "#msi-cells", 0) { d = irq_find_matching_host(it.node, token); - if (d) + if (d) { + of_node_put(it.node); return d; + } } return NULL; diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index 20c9333bcb1c..e92513c5bda5 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -23,6 +23,7 @@ #include "pcie-designware.h" static struct pci_ops dw_pcie_ops; +static struct pci_ops dw_pcie_ecam_ops; static struct pci_ops dw_child_pcie_ops; #define DW_PCIE_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ @@ -471,9 +472,6 @@ static int dw_pcie_create_ecam_window(struct dw_pcie_rp *pp, struct resource *re if (IS_ERR(pp->cfg)) return PTR_ERR(pp->cfg); - pci->dbi_base = pp->cfg->win; - pci->dbi_phys_addr = res->start; - return 0; } @@ -529,7 +527,7 @@ static int dw_pcie_host_get_resources(struct dw_pcie_rp *pp) if (ret) return ret; - pp->bridge->ops = (struct pci_ops *)&pci_generic_ecam_ops.pci_ops; + pp->bridge->ops = &dw_pcie_ecam_ops; pp->bridge->sysdata = pp->cfg; pp->cfg->priv = pp; } else { @@ -842,12 +840,34 @@ void __iomem *dw_pcie_own_conf_map_bus(struct pci_bus *bus, unsigned int devfn, } EXPORT_SYMBOL_GPL(dw_pcie_own_conf_map_bus); +static void __iomem *dw_pcie_ecam_conf_map_bus(struct pci_bus *bus, unsigned int devfn, int where) +{ + struct pci_config_window *cfg = bus->sysdata; + struct dw_pcie_rp *pp = cfg->priv; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + unsigned int busn = bus->number; + + if (busn > 0) + return pci_ecam_map_bus(bus, devfn, where); + + if (PCI_SLOT(devfn) > 0) + return NULL; + + return pci->dbi_base + where; +} + static struct pci_ops dw_pcie_ops = { .map_bus = dw_pcie_own_conf_map_bus, .read = pci_generic_config_read, .write = pci_generic_config_write, }; +static struct pci_ops dw_pcie_ecam_ops = { + .map_bus = dw_pcie_ecam_conf_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + static int dw_pcie_iatu_setup(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 805edbbfe7eb..6948824642dc 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -55,7 +55,6 @@ #define PARF_AXI_MSTR_WR_ADDR_HALT_V2 0x1a8 #define PARF_Q2A_FLUSH 0x1ac #define PARF_LTSSM 0x1b0 -#define PARF_SLV_DBI_ELBI 0x1b4 #define PARF_INT_ALL_STATUS 0x224 #define PARF_INT_ALL_CLEAR 0x228 #define PARF_INT_ALL_MASK 0x22c @@ -65,16 +64,6 @@ #define PARF_DBI_BASE_ADDR_V2_HI 0x354 #define PARF_SLV_ADDR_SPACE_SIZE_V2 0x358 #define PARF_SLV_ADDR_SPACE_SIZE_V2_HI 0x35c -#define PARF_BLOCK_SLV_AXI_WR_BASE 0x360 -#define PARF_BLOCK_SLV_AXI_WR_BASE_HI 0x364 -#define PARF_BLOCK_SLV_AXI_WR_LIMIT 0x368 -#define PARF_BLOCK_SLV_AXI_WR_LIMIT_HI 0x36c -#define PARF_BLOCK_SLV_AXI_RD_BASE 0x370 -#define PARF_BLOCK_SLV_AXI_RD_BASE_HI 0x374 -#define PARF_BLOCK_SLV_AXI_RD_LIMIT 0x378 -#define PARF_BLOCK_SLV_AXI_RD_LIMIT_HI 0x37c -#define PARF_ECAM_BASE 0x380 -#define PARF_ECAM_BASE_HI 0x384 #define PARF_NO_SNOOP_OVERRIDE 0x3d4 #define PARF_ATU_BASE_ADDR 0x634 #define PARF_ATU_BASE_ADDR_HI 0x638 @@ -98,7 +87,6 @@ /* PARF_SYS_CTRL register fields */ #define MAC_PHY_POWERDOWN_IN_P2_D_MUX_EN BIT(29) -#define PCIE_ECAM_BLOCKER_EN BIT(26) #define MST_WAKEUP_EN BIT(13) #define SLV_WAKEUP_EN BIT(12) #define MSTR_ACLK_CGC_DIS BIT(10) @@ -146,9 +134,6 @@ /* PARF_LTSSM register fields */ #define LTSSM_EN BIT(8) -/* PARF_SLV_DBI_ELBI */ -#define SLV_DBI_ELBI_ADDR_BASE GENMASK(11, 0) - /* PARF_INT_ALL_{STATUS/CLEAR/MASK} register fields */ #define PARF_INT_ALL_LINK_UP BIT(13) #define PARF_INT_MSI_DEV_0_7 GENMASK(30, 23) @@ -326,47 +311,6 @@ static void qcom_ep_reset_deassert(struct qcom_pcie *pcie) qcom_perst_assert(pcie, false); } -static void qcom_pci_config_ecam(struct dw_pcie_rp *pp) -{ - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct qcom_pcie *pcie = to_qcom_pcie(pci); - u64 addr, addr_end; - u32 val; - - writel_relaxed(lower_32_bits(pci->dbi_phys_addr), pcie->parf + PARF_ECAM_BASE); - writel_relaxed(upper_32_bits(pci->dbi_phys_addr), pcie->parf + PARF_ECAM_BASE_HI); - - /* - * The only device on the root bus is a single Root Port. If we try to - * access any devices other than Device/Function 00.0 on Bus 0, the TLP - * will go outside of the controller to the PCI bus. But with CFG Shift - * Feature (ECAM) enabled in iATU, there is no guarantee that the - * response is going to be all F's. Hence, to make sure that the - * requester gets all F's response for accesses other than the Root - * Port, configure iATU to block the transactions starting from - * function 1 of the root bus to the end of the root bus (i.e., from - * dbi_base + 4KB to dbi_base + 1MB). - */ - addr = pci->dbi_phys_addr + SZ_4K; - writel_relaxed(lower_32_bits(addr), pcie->parf + PARF_BLOCK_SLV_AXI_WR_BASE); - writel_relaxed(upper_32_bits(addr), pcie->parf + PARF_BLOCK_SLV_AXI_WR_BASE_HI); - - writel_relaxed(lower_32_bits(addr), pcie->parf + PARF_BLOCK_SLV_AXI_RD_BASE); - writel_relaxed(upper_32_bits(addr), pcie->parf + PARF_BLOCK_SLV_AXI_RD_BASE_HI); - - addr_end = pci->dbi_phys_addr + SZ_1M - 1; - - writel_relaxed(lower_32_bits(addr_end), pcie->parf + PARF_BLOCK_SLV_AXI_WR_LIMIT); - writel_relaxed(upper_32_bits(addr_end), pcie->parf + PARF_BLOCK_SLV_AXI_WR_LIMIT_HI); - - writel_relaxed(lower_32_bits(addr_end), pcie->parf + PARF_BLOCK_SLV_AXI_RD_LIMIT); - writel_relaxed(upper_32_bits(addr_end), pcie->parf + PARF_BLOCK_SLV_AXI_RD_LIMIT_HI); - - val = readl_relaxed(pcie->parf + PARF_SYS_CTRL); - val |= PCIE_ECAM_BLOCKER_EN; - writel_relaxed(val, pcie->parf + PARF_SYS_CTRL); -} - static int qcom_pcie_start_link(struct dw_pcie *pci) { struct qcom_pcie *pcie = to_qcom_pcie(pci); @@ -1320,7 +1264,6 @@ static int qcom_pcie_host_init(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct qcom_pcie *pcie = to_qcom_pcie(pci); - u16 offset; int ret; qcom_ep_reset_assert(pcie); @@ -1329,17 +1272,6 @@ static int qcom_pcie_host_init(struct dw_pcie_rp *pp) if (ret) return ret; - if (pp->ecam_enabled) { - /* - * Override ELBI when ECAM is enabled, as when ECAM is enabled, - * ELBI moves under the 'config' space. - */ - offset = FIELD_GET(SLV_DBI_ELBI_ADDR_BASE, readl(pcie->parf + PARF_SLV_DBI_ELBI)); - pci->elbi_base = pci->dbi_base + offset; - - qcom_pci_config_ecam(pp); - } - ret = qcom_pcie_phy_power_on(pcie); if (ret) goto err_deinit; diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 7cc8281e7011..79b965158473 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -243,8 +243,7 @@ struct pcie_link_state { /* Clock PM state */ u32 clkpm_capable:1; /* Clock PM capable? */ u32 clkpm_enabled:1; /* Current Clock PM state */ - u32 clkpm_default:1; /* Default Clock PM state by BIOS or - override */ + u32 clkpm_default:1; /* Default Clock PM state by BIOS */ u32 clkpm_disable:1; /* Clock PM disabled */ }; @@ -376,18 +375,6 @@ static void pcie_set_clkpm(struct pcie_link_state *link, int enable) pcie_set_clkpm_nocheck(link, enable); } -static void pcie_clkpm_override_default_link_state(struct pcie_link_state *link, - int enabled) -{ - struct pci_dev *pdev = link->downstream; - - /* For devicetree platforms, enable ClockPM by default */ - if (of_have_populated_dt() && !enabled) { - link->clkpm_default = 1; - pci_info(pdev, "ASPM: DT platform, enabling ClockPM\n"); - } -} - static void pcie_clkpm_cap_init(struct pcie_link_state *link, int blacklist) { int capable = 1, enabled = 1; @@ -410,7 +397,6 @@ static void pcie_clkpm_cap_init(struct pcie_link_state *link, int blacklist) } link->clkpm_enabled = enabled; link->clkpm_default = enabled; - pcie_clkpm_override_default_link_state(link, enabled); link->clkpm_capable = capable; link->clkpm_disable = blacklist ? 1 : 0; } @@ -811,19 +797,17 @@ static void pcie_aspm_override_default_link_state(struct pcie_link_state *link) struct pci_dev *pdev = link->downstream; u32 override; - /* For devicetree platforms, enable all ASPM states by default */ + /* For devicetree platforms, enable L0s and L1 by default */ if (of_have_populated_dt()) { - link->aspm_default = PCIE_LINK_STATE_ASPM_ALL; + if (link->aspm_support & PCIE_LINK_STATE_L0S) + link->aspm_default |= PCIE_LINK_STATE_L0S; + if (link->aspm_support & PCIE_LINK_STATE_L1) + link->aspm_default |= PCIE_LINK_STATE_L1; override = link->aspm_default & ~link->aspm_enabled; if (override) - pci_info(pdev, "ASPM: DT platform, enabling%s%s%s%s%s%s%s\n", - FLAG(override, L0S_UP, " L0s-up"), - FLAG(override, L0S_DW, " L0s-dw"), - FLAG(override, L1, " L1"), - FLAG(override, L1_1, " ASPM-L1.1"), - FLAG(override, L1_2, " ASPM-L1.2"), - FLAG(override, L1_1_PCIPM, " PCI-PM-L1.1"), - FLAG(override, L1_2_PCIPM, " PCI-PM-L1.2")); + pci_info(pdev, "ASPM: default states%s%s\n", + FLAG(override, L0S, " L0s"), + FLAG(override, L1, " L1")); } } diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c index 4776013e0764..16a2fd9fdd9b 100644 --- a/drivers/platform/mellanox/mlxbf-pmc.c +++ b/drivers/platform/mellanox/mlxbf-pmc.c @@ -2015,6 +2015,7 @@ static int mlxbf_pmc_init_perftype_counter(struct device *dev, unsigned int blk_ if (pmc->block[blk_num].type == MLXBF_PMC_TYPE_CRSPACE) { /* Program crspace counters to count clock cycles using "count_clock" sysfs */ attr = &pmc->block[blk_num].attr_count_clock; + sysfs_attr_init(&attr->dev_attr.attr); attr->dev_attr.attr.mode = 0644; attr->dev_attr.show = mlxbf_pmc_count_clock_show; attr->dev_attr.store = mlxbf_pmc_count_clock_store; diff --git a/drivers/platform/x86/dell/alienware-wmi-wmax.c b/drivers/platform/x86/dell/alienware-wmi-wmax.c index 31f9643a6a3b..f417dcc9af35 100644 --- a/drivers/platform/x86/dell/alienware-wmi-wmax.c +++ b/drivers/platform/x86/dell/alienware-wmi-wmax.c @@ -210,6 +210,14 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = { .driver_data = &g_series_quirks, }, { + .ident = "Dell Inc. G15 5530", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell G15 5530"), + }, + .driver_data = &g_series_quirks, + }, + { .ident = "Dell Inc. G16 7630", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), @@ -1639,7 +1647,7 @@ static int wmax_wmi_probe(struct wmi_device *wdev, const void *context) static int wmax_wmi_suspend(struct device *dev) { - if (awcc->hwmon) + if (awcc && awcc->hwmon) awcc_hwmon_suspend(dev); return 0; @@ -1647,7 +1655,7 @@ static int wmax_wmi_suspend(struct device *dev) static int wmax_wmi_resume(struct device *dev) { - if (awcc->hwmon) + if (awcc && awcc->hwmon) awcc_hwmon_resume(dev); return 0; diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 794ec6e71990..a5c363252986 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -2548,7 +2548,7 @@ ptp_ocp_sma_fb_init(struct ptp_ocp *bp) for (i = 0; i < OCP_SMA_NUM; i++) { bp->sma[i].fixed_fcn = true; bp->sma[i].fixed_dir = true; - bp->sma[1].dpll_prop.capabilities &= + bp->sma[i].dpll_prop.capabilities &= ~DPLL_PIN_CAPABILITIES_DIRECTION_CAN_CHANGE; } return; diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c index 16d0f02af1e4..31d08c115521 100644 --- a/drivers/scsi/libfc/fc_fcp.c +++ b/drivers/scsi/libfc/fc_fcp.c @@ -503,7 +503,7 @@ static void fc_fcp_recv_data(struct fc_fcp_pkt *fsp, struct fc_frame *fp) host_bcode = FC_ERROR; goto err; } - if (offset + len > fsp->data_len) { + if (size_add(offset, len) > fsp->data_len) { /* this should never happen */ if ((fr_flags(fp) & FCPHF_CRC_UNCHECKED) && fc_frame_crc_check(fp)) diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index a761c0aa5127..83ff66f954e6 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -4104,7 +4104,7 @@ void qla4xxx_srb_compl(struct kref *ref) * The mid-level driver tries to ensure that queuecommand never gets * invoked concurrently with itself or the interrupt handler (although * the interrupt handler may call this routine as part of request- - * completion handling). Unfortunely, it sometimes calls the scheduler + * completion handling). Unfortunately, it sometimes calls the scheduler * in interrupt context which is a big NO! NO!. **/ static int qla4xxx_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd) @@ -4647,7 +4647,7 @@ static int qla4xxx_cmd_wait(struct scsi_qla_host *ha) cmd = scsi_host_find_tag(ha->host, index); /* * We cannot just check if the index is valid, - * becase if we are run from the scsi eh, then + * because if we are run from the scsi eh, then * the scsi/block layer is going to prevent * the tag from being released. */ @@ -4952,7 +4952,7 @@ recover_ha_init_adapter: /* Upon successful firmware/chip reset, re-initialize the adapter */ if (status == QLA_SUCCESS) { /* For ISP-4xxx, force function 1 to always initialize - * before function 3 to prevent both funcions from + * before function 3 to prevent both functions from * stepping on top of the other */ if (is_qla40XX(ha) && (ha->mac_index == 3)) ssleep(6); @@ -6914,7 +6914,7 @@ static int qla4xxx_sess_conn_setup(struct scsi_qla_host *ha, struct ddb_entry *ddb_entry = NULL; /* Create session object, with INVALID_ENTRY, - * the targer_id would get set when we issue the login + * the target_id would get set when we issue the login */ cls_sess = iscsi_session_setup(&qla4xxx_iscsi_transport, ha->host, cmds_max, sizeof(struct ddb_entry), diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 567f9cd29102..6e4112143c76 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1406,14 +1406,19 @@ static struct vmbus_channel *get_og_chn(struct storvsc_device *stor_device, } /* - * Our channel array is sparsley populated and we + * Our channel array could be sparsley populated and we * initiated I/O on a processor/hw-q that does not * currently have a designated channel. Fix this. * The strategy is simple: - * I. Ensure NUMA locality - * II. Distribute evenly (best effort) + * I. Prefer the channel associated with the current CPU + * II. Ensure NUMA locality + * III. Distribute evenly (best effort) */ + /* Prefer the channel on the I/O issuing processor/hw-q */ + if (cpumask_test_cpu(q_num, &stor_device->alloced_cpus)) + return stor_device->stor_chns[q_num]; + node_mask = cpumask_of_node(cpu_to_node(q_num)); num_channels = 0; @@ -1469,59 +1474,48 @@ static int storvsc_do_io(struct hv_device *device, /* See storvsc_change_target_cpu(). */ outgoing_channel = READ_ONCE(stor_device->stor_chns[q_num]); if (outgoing_channel != NULL) { - if (outgoing_channel->target_cpu == q_num) { - /* - * Ideally, we want to pick a different channel if - * available on the same NUMA node. - */ - node_mask = cpumask_of_node(cpu_to_node(q_num)); - for_each_cpu_wrap(tgt_cpu, - &stor_device->alloced_cpus, q_num + 1) { - if (!cpumask_test_cpu(tgt_cpu, node_mask)) - continue; - if (tgt_cpu == q_num) - continue; - channel = READ_ONCE( - stor_device->stor_chns[tgt_cpu]); - if (channel == NULL) - continue; - if (hv_get_avail_to_write_percent( - &channel->outbound) - > ring_avail_percent_lowater) { - outgoing_channel = channel; - goto found_channel; - } - } + if (hv_get_avail_to_write_percent(&outgoing_channel->outbound) + > ring_avail_percent_lowater) + goto found_channel; - /* - * All the other channels on the same NUMA node are - * busy. Try to use the channel on the current CPU - */ - if (hv_get_avail_to_write_percent( - &outgoing_channel->outbound) - > ring_avail_percent_lowater) + /* + * Channel is busy, try to find a channel on the same NUMA node + */ + node_mask = cpumask_of_node(cpu_to_node(q_num)); + for_each_cpu_wrap(tgt_cpu, &stor_device->alloced_cpus, + q_num + 1) { + if (!cpumask_test_cpu(tgt_cpu, node_mask)) + continue; + channel = READ_ONCE(stor_device->stor_chns[tgt_cpu]); + if (!channel) + continue; + if (hv_get_avail_to_write_percent(&channel->outbound) + > ring_avail_percent_lowater) { + outgoing_channel = channel; goto found_channel; + } + } - /* - * If we reach here, all the channels on the current - * NUMA node are busy. Try to find a channel in - * other NUMA nodes - */ - for_each_cpu(tgt_cpu, &stor_device->alloced_cpus) { - if (cpumask_test_cpu(tgt_cpu, node_mask)) - continue; - channel = READ_ONCE( - stor_device->stor_chns[tgt_cpu]); - if (channel == NULL) - continue; - if (hv_get_avail_to_write_percent( - &channel->outbound) - > ring_avail_percent_lowater) { - outgoing_channel = channel; - goto found_channel; - } + /* + * If we reach here, all the channels on the current + * NUMA node are busy. Try to find a channel in + * all NUMA nodes + */ + for_each_cpu_wrap(tgt_cpu, &stor_device->alloced_cpus, + q_num + 1) { + channel = READ_ONCE(stor_device->stor_chns[tgt_cpu]); + if (!channel) + continue; + if (hv_get_avail_to_write_percent(&channel->outbound) + > ring_avail_percent_lowater) { + outgoing_channel = channel; + goto found_channel; } } + /* + * If we reach here, all the channels are busy. Use the + * original channel found. + */ } else { spin_lock_irqsave(&stor_device->lock, flags); outgoing_channel = stor_device->stor_chns[q_num]; diff --git a/drivers/spi/spi-airoha-snfi.c b/drivers/spi/spi-airoha-snfi.c index dbe640986825..b78163eaed61 100644 --- a/drivers/spi/spi-airoha-snfi.c +++ b/drivers/spi/spi-airoha-snfi.c @@ -192,6 +192,14 @@ #define SPI_NAND_OP_RESET 0xff #define SPI_NAND_OP_DIE_SELECT 0xc2 +/* SNAND FIFO commands */ +#define SNAND_FIFO_TX_BUSWIDTH_SINGLE 0x08 +#define SNAND_FIFO_TX_BUSWIDTH_DUAL 0x09 +#define SNAND_FIFO_TX_BUSWIDTH_QUAD 0x0a +#define SNAND_FIFO_RX_BUSWIDTH_SINGLE 0x0c +#define SNAND_FIFO_RX_BUSWIDTH_DUAL 0x0e +#define SNAND_FIFO_RX_BUSWIDTH_QUAD 0x0f + #define SPI_NAND_CACHE_SIZE (SZ_4K + SZ_256) #define SPI_MAX_TRANSFER_SIZE 511 @@ -387,10 +395,26 @@ static int airoha_snand_set_mode(struct airoha_snand_ctrl *as_ctrl, return regmap_write(as_ctrl->regmap_ctrl, REG_SPI_CTRL_DUMMY, 0); } -static int airoha_snand_write_data(struct airoha_snand_ctrl *as_ctrl, u8 cmd, - const u8 *data, int len) +static int airoha_snand_write_data(struct airoha_snand_ctrl *as_ctrl, + const u8 *data, int len, int buswidth) { int i, data_len; + u8 cmd; + + switch (buswidth) { + case 0: + case 1: + cmd = SNAND_FIFO_TX_BUSWIDTH_SINGLE; + break; + case 2: + cmd = SNAND_FIFO_TX_BUSWIDTH_DUAL; + break; + case 4: + cmd = SNAND_FIFO_TX_BUSWIDTH_QUAD; + break; + default: + return -EINVAL; + } for (i = 0; i < len; i += data_len) { int err; @@ -409,16 +433,32 @@ static int airoha_snand_write_data(struct airoha_snand_ctrl *as_ctrl, u8 cmd, return 0; } -static int airoha_snand_read_data(struct airoha_snand_ctrl *as_ctrl, u8 *data, - int len) +static int airoha_snand_read_data(struct airoha_snand_ctrl *as_ctrl, + u8 *data, int len, int buswidth) { int i, data_len; + u8 cmd; + + switch (buswidth) { + case 0: + case 1: + cmd = SNAND_FIFO_RX_BUSWIDTH_SINGLE; + break; + case 2: + cmd = SNAND_FIFO_RX_BUSWIDTH_DUAL; + break; + case 4: + cmd = SNAND_FIFO_RX_BUSWIDTH_QUAD; + break; + default: + return -EINVAL; + } for (i = 0; i < len; i += data_len) { int err; data_len = min(len - i, SPI_MAX_TRANSFER_SIZE); - err = airoha_snand_set_fifo_op(as_ctrl, 0xc, data_len); + err = airoha_snand_set_fifo_op(as_ctrl, cmd, data_len); if (err) return err; @@ -618,6 +658,10 @@ static int airoha_snand_dirmap_create(struct spi_mem_dirmap_desc *desc) if (desc->info.offset + desc->info.length > U32_MAX) return -EINVAL; + /* continuous reading is not supported */ + if (desc->info.length > SPI_NAND_CACHE_SIZE) + return -E2BIG; + if (!airoha_snand_supports_op(desc->mem, &desc->info.op_tmpl)) return -EOPNOTSUPP; @@ -654,13 +698,13 @@ static ssize_t airoha_snand_dirmap_read(struct spi_mem_dirmap_desc *desc, err = airoha_snand_nfi_config(as_ctrl); if (err) - return err; + goto error_dma_mode_off; dma_addr = dma_map_single(as_ctrl->dev, txrx_buf, SPI_NAND_CACHE_SIZE, DMA_FROM_DEVICE); err = dma_mapping_error(as_ctrl->dev, dma_addr); if (err) - return err; + goto error_dma_mode_off; /* set dma addr */ err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_STRADDR, @@ -689,8 +733,9 @@ static ssize_t airoha_snand_dirmap_read(struct spi_mem_dirmap_desc *desc, if (err) goto error_dma_unmap; - /* set read addr */ - err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_RD_CTL3, 0x0); + /* set read addr: zero page offset + descriptor read offset */ + err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_RD_CTL3, + desc->info.offset); if (err) goto error_dma_unmap; @@ -760,6 +805,8 @@ static ssize_t airoha_snand_dirmap_read(struct spi_mem_dirmap_desc *desc, error_dma_unmap: dma_unmap_single(as_ctrl->dev, dma_addr, SPI_NAND_CACHE_SIZE, DMA_FROM_DEVICE); +error_dma_mode_off: + airoha_snand_set_mode(as_ctrl, SPI_MODE_MANUAL); return err; } @@ -824,7 +871,9 @@ static ssize_t airoha_snand_dirmap_write(struct spi_mem_dirmap_desc *desc, if (err) goto error_dma_unmap; - err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_PG_CTL2, 0x0); + /* set write addr: zero page offset + descriptor write offset */ + err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_PG_CTL2, + desc->info.offset); if (err) goto error_dma_unmap; @@ -892,18 +941,35 @@ static ssize_t airoha_snand_dirmap_write(struct spi_mem_dirmap_desc *desc, error_dma_unmap: dma_unmap_single(as_ctrl->dev, dma_addr, SPI_NAND_CACHE_SIZE, DMA_TO_DEVICE); + airoha_snand_set_mode(as_ctrl, SPI_MODE_MANUAL); return err; } static int airoha_snand_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) { - u8 data[8], cmd, opcode = op->cmd.opcode; struct airoha_snand_ctrl *as_ctrl; + int op_len, addr_len, dummy_len; + u8 buf[20], *data; int i, err; as_ctrl = spi_controller_get_devdata(mem->spi->controller); + op_len = op->cmd.nbytes; + addr_len = op->addr.nbytes; + dummy_len = op->dummy.nbytes; + + if (op_len + dummy_len + addr_len > sizeof(buf)) + return -EIO; + + data = buf; + for (i = 0; i < op_len; i++) + *data++ = op->cmd.opcode >> (8 * (op_len - i - 1)); + for (i = 0; i < addr_len; i++) + *data++ = op->addr.val >> (8 * (addr_len - i - 1)); + for (i = 0; i < dummy_len; i++) + *data++ = 0xff; + /* switch to manual mode */ err = airoha_snand_set_mode(as_ctrl, SPI_MODE_MANUAL); if (err < 0) @@ -914,40 +980,40 @@ static int airoha_snand_exec_op(struct spi_mem *mem, return err; /* opcode */ - err = airoha_snand_write_data(as_ctrl, 0x8, &opcode, sizeof(opcode)); + data = buf; + err = airoha_snand_write_data(as_ctrl, data, op_len, + op->cmd.buswidth); if (err) return err; /* addr part */ - cmd = opcode == SPI_NAND_OP_GET_FEATURE ? 0x11 : 0x8; - put_unaligned_be64(op->addr.val, data); - - for (i = ARRAY_SIZE(data) - op->addr.nbytes; - i < ARRAY_SIZE(data); i++) { - err = airoha_snand_write_data(as_ctrl, cmd, &data[i], - sizeof(data[0])); + data += op_len; + if (addr_len) { + err = airoha_snand_write_data(as_ctrl, data, addr_len, + op->addr.buswidth); if (err) return err; } /* dummy */ - data[0] = 0xff; - for (i = 0; i < op->dummy.nbytes; i++) { - err = airoha_snand_write_data(as_ctrl, 0x8, &data[0], - sizeof(data[0])); + data += addr_len; + if (dummy_len) { + err = airoha_snand_write_data(as_ctrl, data, dummy_len, + op->dummy.buswidth); if (err) return err; } /* data */ - if (op->data.dir == SPI_MEM_DATA_IN) { - err = airoha_snand_read_data(as_ctrl, op->data.buf.in, - op->data.nbytes); - if (err) - return err; - } else { - err = airoha_snand_write_data(as_ctrl, 0x8, op->data.buf.out, - op->data.nbytes); + if (op->data.nbytes) { + if (op->data.dir == SPI_MEM_DATA_IN) + err = airoha_snand_read_data(as_ctrl, op->data.buf.in, + op->data.nbytes, + op->data.buswidth); + else + err = airoha_snand_write_data(as_ctrl, op->data.buf.out, + op->data.nbytes, + op->data.buswidth); if (err) return err; } diff --git a/drivers/spi/spi-amlogic-spifc-a4.c b/drivers/spi/spi-amlogic-spifc-a4.c index 4338d00e56a6..35a7c4965e11 100644 --- a/drivers/spi/spi-amlogic-spifc-a4.c +++ b/drivers/spi/spi-amlogic-spifc-a4.c @@ -286,7 +286,7 @@ static int aml_sfc_set_bus_width(struct aml_sfc *sfc, u8 buswidth, u32 mask) for (i = 0; i <= LANE_MAX; i++) { if (buswidth == 1 << i) { - conf = i << __bf_shf(mask); + conf = i << __ffs(mask); return regmap_update_bits(sfc->regmap_base, SFC_SPI_CFG, mask, conf); } @@ -566,7 +566,7 @@ static int aml_sfc_raw_io_op(struct aml_sfc *sfc, const struct spi_mem_op *op) if (!op->data.nbytes) goto end_xfer; - conf = (op->data.nbytes >> RAW_SIZE_BW) << __bf_shf(RAW_EXT_SIZE); + conf = (op->data.nbytes >> RAW_SIZE_BW) << __ffs(RAW_EXT_SIZE); ret = regmap_update_bits(sfc->regmap_base, SFC_SPI_CFG, RAW_EXT_SIZE, conf); if (ret) goto err_out; diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 8fb13df8ff87..81017402bc56 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -1995,7 +1995,7 @@ static int cqspi_probe(struct platform_device *pdev) if (cqspi->use_direct_mode) { ret = cqspi_request_mmap_dma(cqspi); if (ret == -EPROBE_DEFER) - goto probe_setup_failed; + goto probe_dma_failed; } if (!(ddata && (ddata->quirks & CQSPI_DISABLE_RUNTIME_PM))) { @@ -2019,9 +2019,10 @@ static int cqspi_probe(struct platform_device *pdev) return 0; probe_setup_failed: - cqspi_controller_enable(cqspi, 0); if (!(ddata && (ddata->quirks & CQSPI_DISABLE_RUNTIME_PM))) pm_runtime_disable(dev); +probe_dma_failed: + cqspi_controller_enable(cqspi, 0); probe_reset_failed: if (cqspi->is_jh7110) cqspi_jh7110_disable_clk(pdev, cqspi); diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c index f0f576fac77a..7a5197586919 100644 --- a/drivers/spi/spi-dw-mmio.c +++ b/drivers/spi/spi-dw-mmio.c @@ -358,7 +358,9 @@ static int dw_spi_mmio_probe(struct platform_device *pdev) if (IS_ERR(dwsmmio->rstc)) return PTR_ERR(dwsmmio->rstc); - reset_control_deassert(dwsmmio->rstc); + ret = reset_control_deassert(dwsmmio->rstc); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to deassert resets\n"); dws->bus_num = pdev->id; diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c index 4b63cb98df9c..7765fb27c37c 100644 --- a/drivers/spi/spi-intel-pci.c +++ b/drivers/spi/spi-intel-pci.c @@ -75,10 +75,12 @@ static const struct pci_device_id intel_spi_pci_ids[] = { { PCI_VDEVICE(INTEL, 0x38a4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0x43a4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x4b24), (unsigned long)&bxt_info }, + { PCI_VDEVICE(INTEL, 0x4d23), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x4da4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0x51a4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x54a4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x5794), (unsigned long)&cnl_info }, + { PCI_VDEVICE(INTEL, 0x7723), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7a24), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7aa4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7e23), (unsigned long)&cnl_info }, diff --git a/drivers/spi/spi-intel.c b/drivers/spi/spi-intel.c index 13bbb2133507..1775ad39e633 100644 --- a/drivers/spi/spi-intel.c +++ b/drivers/spi/spi-intel.c @@ -132,6 +132,7 @@ #define FLCOMP_C0DEN_16M 0x05 #define FLCOMP_C0DEN_32M 0x06 #define FLCOMP_C0DEN_64M 0x07 +#define FLCOMP_C0DEN_128M 0x08 #define INTEL_SPI_TIMEOUT 5000 /* ms */ #define INTEL_SPI_FIFO_SZ 64 @@ -1347,7 +1348,12 @@ static int intel_spi_read_desc(struct intel_spi *ispi) case FLCOMP_C0DEN_64M: ispi->chip0_size = SZ_64M; break; + case FLCOMP_C0DEN_128M: + ispi->chip0_size = SZ_128M; + break; default: + dev_warn(ispi->dev, "unsupported C0DEN: %#lx\n", + flcomp & FLCOMP_C0DEN_MASK); return -EINVAL; } diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c index f9371f98a65b..b6c79e50d842 100644 --- a/drivers/spi/spi-nxp-fspi.c +++ b/drivers/spi/spi-nxp-fspi.c @@ -404,6 +404,10 @@ struct nxp_fspi { #define FSPI_NEED_INIT BIT(0) #define FSPI_DTR_MODE BIT(1) int flags; + /* save the previous operation clock rate */ + unsigned long pre_op_rate; + /* the max clock rate fspi output to device */ + unsigned long max_rate; }; static inline int needs_ip_only(struct nxp_fspi *f) @@ -685,10 +689,13 @@ static void nxp_fspi_select_rx_sample_clk_source(struct nxp_fspi *f, * change the mode back to mode 0. */ reg = fspi_readl(f, f->iobase + FSPI_MCR0); - if (op_is_dtr) + if (op_is_dtr) { reg |= FSPI_MCR0_RXCLKSRC(3); - else /*select mode 0 */ + f->max_rate = 166000000; + } else { /*select mode 0 */ reg &= ~FSPI_MCR0_RXCLKSRC(3); + f->max_rate = 66000000; + } fspi_writel(f, reg, f->iobase + FSPI_MCR0); } @@ -719,6 +726,12 @@ static void nxp_fspi_dll_calibration(struct nxp_fspi *f) 0, POLL_TOUT, true); if (ret) dev_warn(f->dev, "DLL lock failed, please fix it!\n"); + + /* + * For ERR050272, DLL lock status bit is not accurate, + * wait for 4us more as a workaround. + */ + udelay(4); } /* @@ -780,11 +793,17 @@ static void nxp_fspi_select_mem(struct nxp_fspi *f, struct spi_device *spi, uint64_t size_kb; /* - * Return, if previously selected target device is same as current - * requested target device. Also the DTR or STR mode do not change. + * Return when following condition all meet, + * 1, if previously selected target device is same as current + * requested target device. + * 2, the DTR or STR mode do not change. + * 3, previous operation max rate equals current one. + * + * For other case, need to re-config. */ if ((f->selected == spi_get_chipselect(spi, 0)) && - (!!(f->flags & FSPI_DTR_MODE) == op_is_dtr)) + (!!(f->flags & FSPI_DTR_MODE) == op_is_dtr) && + (f->pre_op_rate == op->max_freq)) return; /* Reset FLSHxxCR0 registers */ @@ -802,6 +821,7 @@ static void nxp_fspi_select_mem(struct nxp_fspi *f, struct spi_device *spi, dev_dbg(f->dev, "Target device [CS:%x] selected\n", spi_get_chipselect(spi, 0)); nxp_fspi_select_rx_sample_clk_source(f, op_is_dtr); + rate = min(f->max_rate, op->max_freq); if (op_is_dtr) { f->flags |= FSPI_DTR_MODE; @@ -832,6 +852,8 @@ static void nxp_fspi_select_mem(struct nxp_fspi *f, struct spi_device *spi, else nxp_fspi_dll_override(f); + f->pre_op_rate = op->max_freq; + f->selected = spi_get_chipselect(spi, 0); } diff --git a/drivers/spi/spi-rockchip-sfc.c b/drivers/spi/spi-rockchip-sfc.c index 9eba5c0a60f2..b3c2b03b1153 100644 --- a/drivers/spi/spi-rockchip-sfc.c +++ b/drivers/spi/spi-rockchip-sfc.c @@ -704,7 +704,12 @@ static int rockchip_sfc_probe(struct platform_device *pdev) ret = -ENOMEM; goto err_dma; } - sfc->dma_buffer = virt_to_phys(sfc->buffer); + sfc->dma_buffer = dma_map_single(dev, sfc->buffer, + sfc->max_iosize, DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev, sfc->dma_buffer)) { + ret = -ENOMEM; + goto err_dma_map; + } } ret = devm_spi_register_controller(dev, host); @@ -715,6 +720,9 @@ static int rockchip_sfc_probe(struct platform_device *pdev) return 0; err_register: + dma_unmap_single(dev, sfc->dma_buffer, sfc->max_iosize, + DMA_BIDIRECTIONAL); +err_dma_map: free_pages((unsigned long)sfc->buffer, get_order(sfc->max_iosize)); err_dma: pm_runtime_get_sync(dev); @@ -736,6 +744,8 @@ static void rockchip_sfc_remove(struct platform_device *pdev) struct spi_controller *host = sfc->host; spi_unregister_controller(host); + dma_unmap_single(&pdev->dev, sfc->dma_buffer, sfc->max_iosize, + DMA_BIDIRECTIONAL); free_pages((unsigned long)sfc->buffer, get_order(sfc->max_iosize)); clk_disable_unprepare(sfc->clk); diff --git a/drivers/tee/qcomtee/Kconfig b/drivers/tee/qcomtee/Kconfig index 927686abceb1..9f19dee08db4 100644 --- a/drivers/tee/qcomtee/Kconfig +++ b/drivers/tee/qcomtee/Kconfig @@ -2,6 +2,7 @@ # Qualcomm Trusted Execution Environment Configuration config QCOMTEE tristate "Qualcomm TEE Support" + depends on ARCH_QCOM || COMPILE_TEST depends on !CPU_BIG_ENDIAN select QCOM_SCM select QCOM_TZMEM_MODE_SHMBRIDGE diff --git a/drivers/tee/qcomtee/call.c b/drivers/tee/qcomtee/call.c index cc17a48d0ab7..ac134452cc9c 100644 --- a/drivers/tee/qcomtee/call.c +++ b/drivers/tee/qcomtee/call.c @@ -308,7 +308,7 @@ out_failed: } /* Release any IO and OO objects not processed. */ - for (; u[i].type && i < num_params; i++) { + for (; i < num_params && u[i].type; i++) { if (u[i].type == QCOMTEE_ARG_TYPE_OO || u[i].type == QCOMTEE_ARG_TYPE_IO) qcomtee_object_put(u[i].o); diff --git a/drivers/tee/qcomtee/core.c b/drivers/tee/qcomtee/core.c index 783acc59cfa9..b6715ada7700 100644 --- a/drivers/tee/qcomtee/core.c +++ b/drivers/tee/qcomtee/core.c @@ -424,7 +424,7 @@ static int qcomtee_prepare_msg(struct qcomtee_object_invoke_ctx *oic, if (!(u[i].flags & QCOMTEE_ARG_FLAGS_UADDR)) memcpy(msgptr, u[i].b.addr, u[i].b.size); else if (copy_from_user(msgptr, u[i].b.uaddr, u[i].b.size)) - return -EINVAL; + return -EFAULT; offset += qcomtee_msg_offset_align(u[i].b.size); ib++; diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index f3248a3e5402..c1acbc98465d 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -66,7 +66,6 @@ static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) struct p9_fid *fid; struct inode *inode; struct v9fs_inode *v9inode; - unsigned int cached; if (flags & LOOKUP_RCU) return -ECHILD; @@ -76,11 +75,7 @@ static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) goto out_valid; v9inode = V9FS_I(inode); - struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode); - - cached = v9ses->cache & (CACHE_META | CACHE_LOOSE); - - if (!cached || v9inode->cache_validity & V9FS_INO_INVALID_ATTR) { + if (v9inode->cache_validity & V9FS_INO_INVALID_ATTR) { int retval; struct v9fs_session_info *v9ses; @@ -114,6 +109,7 @@ static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) p9_debug(P9_DEBUG_VFS, "refresh inode: dentry = %pd (%p), got error %pe\n", dentry, dentry, ERR_PTR(retval)); + if (retval < 0) return retval; } } @@ -150,8 +146,6 @@ const struct dentry_operations v9fs_cached_dentry_operations = { }; const struct dentry_operations v9fs_dentry_operations = { - .d_revalidate = v9fs_lookup_revalidate, - .d_weak_revalidate = __v9fs_lookup_revalidate, .d_release = v9fs_dentry_release, .d_unalias_trylock = v9fs_dentry_unalias_trylock, .d_unalias_unlock = v9fs_dentry_unalias_unlock, diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 69f378a83775..d0c77ec31b1d 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -1339,14 +1339,8 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode) * Don't update inode if the file type is different */ umode = p9mode2unixmode(v9ses, st, &rdev); - if (inode_wrong_type(inode, umode)) { - /* - * Do this as a way of letting the caller know the inode should not - * be reused - */ - v9fs_invalidate_inode_attr(inode); + if (inode_wrong_type(inode, umode)) goto out; - } /* * We don't want to refresh inode->i_size, diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 0b404e8484d2..be297e335468 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -897,14 +897,8 @@ int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode) /* * Don't update inode if the file type is different */ - if (inode_wrong_type(inode, st->st_mode)) { - /* - * Do this as a way of letting the caller know the inode should not - * be reused - */ - v9fs_invalidate_inode_attr(inode); + if (inode_wrong_type(inode, st->st_mode)) goto out; - } /* * We don't want to refresh inode->i_size, diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 41e37f7f67cc..3df7b9d7fbe8 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -2110,9 +2110,9 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root) for (int i = 0; i < count; i++) { __btrfs_kill_delayed_node(delayed_nodes[i]); + btrfs_delayed_node_ref_tracker_dir_print(delayed_nodes[i]); btrfs_release_delayed_node(delayed_nodes[i], &delayed_node_trackers[i]); - btrfs_delayed_node_ref_tracker_dir_print(delayed_nodes[i]); } } } diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index 0d949edc0caf..b09d4ec8c77d 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -219,6 +219,13 @@ static inline void btrfs_delayed_node_ref_tracker_dir_print(struct btrfs_delayed if (!btrfs_test_opt(node->root->fs_info, REF_TRACKER)) return; + /* + * Only print if there are leaked references. The caller is + * holding one reference, so if refs == 1 there is no leak. + */ + if (refcount_read(&node->refs) == 1) + return; + ref_tracker_dir_print(&node->ref_dir.dir, BTRFS_DELAYED_NODE_REF_TRACKER_DISPLAY_LIMIT); } diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index de4cb0f3fbd0..e9224145d754 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -982,7 +982,7 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info) extent_root = btrfs_extent_root(fs_info, 0); /* If the extent tree is damaged we cannot ignore it (IGNOREBADROOTS). */ - if (IS_ERR(extent_root)) { + if (!extent_root) { btrfs_warn(fs_info, "ref-verify: extent tree not available, disabling"); btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); return 0; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 6144e66661f5..96a030d28e09 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -4102,6 +4102,48 @@ out: return ret; } +static int rbtree_check_dir_ref_comp(const void *k, const struct rb_node *node) +{ + const struct recorded_ref *data = k; + const struct recorded_ref *ref = rb_entry(node, struct recorded_ref, node); + + if (data->dir > ref->dir) + return 1; + if (data->dir < ref->dir) + return -1; + if (data->dir_gen > ref->dir_gen) + return 1; + if (data->dir_gen < ref->dir_gen) + return -1; + return 0; +} + +static bool rbtree_check_dir_ref_less(struct rb_node *node, const struct rb_node *parent) +{ + const struct recorded_ref *entry = rb_entry(node, struct recorded_ref, node); + + return rbtree_check_dir_ref_comp(entry, parent) < 0; +} + +static int record_check_dir_ref_in_tree(struct rb_root *root, + struct recorded_ref *ref, struct list_head *list) +{ + struct recorded_ref *tmp_ref; + int ret; + + if (rb_find(ref, root, rbtree_check_dir_ref_comp)) + return 0; + + ret = dup_ref(ref, list); + if (ret < 0) + return ret; + + tmp_ref = list_last_entry(list, struct recorded_ref, list); + rb_add(&tmp_ref->node, root, rbtree_check_dir_ref_less); + tmp_ref->root = root; + return 0; +} + static int rename_current_inode(struct send_ctx *sctx, struct fs_path *current_path, struct fs_path *new_path) @@ -4129,11 +4171,11 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) struct recorded_ref *cur; struct recorded_ref *cur2; LIST_HEAD(check_dirs); + struct rb_root rbtree_check_dirs = RB_ROOT; struct fs_path *valid_path = NULL; u64 ow_inode = 0; u64 ow_gen; u64 ow_mode; - u64 last_dir_ino_rm = 0; bool did_overwrite = false; bool is_orphan = false; bool can_rename = true; @@ -4437,7 +4479,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) goto out; } } - ret = dup_ref(cur, &check_dirs); + ret = record_check_dir_ref_in_tree(&rbtree_check_dirs, cur, &check_dirs); if (ret < 0) goto out; } @@ -4465,7 +4507,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) } list_for_each_entry(cur, &sctx->deleted_refs, list) { - ret = dup_ref(cur, &check_dirs); + ret = record_check_dir_ref_in_tree(&rbtree_check_dirs, cur, &check_dirs); if (ret < 0) goto out; } @@ -4475,7 +4517,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) * We have a moved dir. Add the old parent to check_dirs */ cur = list_first_entry(&sctx->deleted_refs, struct recorded_ref, list); - ret = dup_ref(cur, &check_dirs); + ret = record_check_dir_ref_in_tree(&rbtree_check_dirs, cur, &check_dirs); if (ret < 0) goto out; } else if (!S_ISDIR(sctx->cur_inode_mode)) { @@ -4509,7 +4551,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) if (is_current_inode_path(sctx, cur->full_path)) fs_path_reset(&sctx->cur_inode_path); } - ret = dup_ref(cur, &check_dirs); + ret = record_check_dir_ref_in_tree(&rbtree_check_dirs, cur, &check_dirs); if (ret < 0) goto out; } @@ -4552,8 +4594,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) ret = cache_dir_utimes(sctx, cur->dir, cur->dir_gen); if (ret < 0) goto out; - } else if (ret == inode_state_did_delete && - cur->dir != last_dir_ino_rm) { + } else if (ret == inode_state_did_delete) { ret = can_rmdir(sctx, cur->dir, cur->dir_gen); if (ret < 0) goto out; @@ -4565,7 +4606,6 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) ret = send_rmdir(sctx, valid_path); if (ret < 0) goto out; - last_dir_ino_rm = cur->dir; } } } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index aadc02374b2a..430e7419349c 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2068,7 +2068,13 @@ static int btrfs_get_tree_subvol(struct fs_context *fc) fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL); fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL); if (!fs_info->super_copy || !fs_info->super_for_commit) { - btrfs_free_fs_info(fs_info); + /* + * Dont call btrfs_free_fs_info() to free it as it's still + * initialized partially. + */ + kfree(fs_info->super_copy); + kfree(fs_info->super_for_commit); + kvfree(fs_info); return -ENOMEM; } btrfs_init_fs_info(fs_info); diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index e5581dbeb4c2..c8d8e129eb4b 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -55,10 +55,6 @@ static int z_erofs_load_full_lcluster(struct z_erofs_maprecorder *m, } else { m->partialref = !!(advise & Z_EROFS_LI_PARTIAL_REF); m->clusterofs = le16_to_cpu(di->di_clusterofs); - if (m->clusterofs >= 1 << vi->z_lclusterbits) { - DBG_BUGON(1); - return -EFSCORRUPTED; - } m->pblk = le32_to_cpu(di->di_u.blkaddr); } return 0; @@ -240,21 +236,29 @@ static int z_erofs_load_compact_lcluster(struct z_erofs_maprecorder *m, static int z_erofs_load_lcluster_from_disk(struct z_erofs_maprecorder *m, unsigned int lcn, bool lookahead) { + struct erofs_inode *vi = EROFS_I(m->inode); + int err; + + if (vi->datalayout == EROFS_INODE_COMPRESSED_COMPACT) { + err = z_erofs_load_compact_lcluster(m, lcn, lookahead); + } else { + DBG_BUGON(vi->datalayout != EROFS_INODE_COMPRESSED_FULL); + err = z_erofs_load_full_lcluster(m, lcn); + } + if (err) + return err; + if (m->type >= Z_EROFS_LCLUSTER_TYPE_MAX) { erofs_err(m->inode->i_sb, "unknown type %u @ lcn %u of nid %llu", - m->type, lcn, EROFS_I(m->inode)->nid); + m->type, lcn, EROFS_I(m->inode)->nid); DBG_BUGON(1); return -EOPNOTSUPP; + } else if (m->type != Z_EROFS_LCLUSTER_TYPE_NONHEAD && + m->clusterofs >= (1 << vi->z_lclusterbits)) { + DBG_BUGON(1); + return -EFSCORRUPTED; } - - switch (EROFS_I(m->inode)->datalayout) { - case EROFS_INODE_COMPRESSED_FULL: - return z_erofs_load_full_lcluster(m, lcn); - case EROFS_INODE_COMPRESSED_COMPACT: - return z_erofs_load_compact_lcluster(m, lcn, lookahead); - default: - return -EINVAL; - } + return 0; } static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, @@ -268,20 +272,19 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, unsigned long lcn = m->lcn - lookback_distance; int err; + if (!lookback_distance) + break; + err = z_erofs_load_lcluster_from_disk(m, lcn, false); if (err) return err; - if (m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) { lookback_distance = m->delta[0]; - if (!lookback_distance) - break; continue; - } else { - m->headtype = m->type; - m->map->m_la = (lcn << lclusterbits) | m->clusterofs; - return 0; } + m->headtype = m->type; + m->map->m_la = (lcn << lclusterbits) | m->clusterofs; + return 0; } erofs_err(sb, "bogus lookback distance %u @ lcn %lu of nid %llu", lookback_distance, m->lcn, vi->nid); @@ -431,13 +434,6 @@ static int z_erofs_map_blocks_fo(struct inode *inode, end = inode->i_size; } else { if (m.type != Z_EROFS_LCLUSTER_TYPE_NONHEAD) { - /* m.lcn should be >= 1 if endoff < m.clusterofs */ - if (!m.lcn) { - erofs_err(sb, "invalid logical cluster 0 at nid %llu", - vi->nid); - err = -EFSCORRUPTED; - goto unmap_out; - } end = (m.lcn << lclusterbits) | m.clusterofs; map->m_flags |= EROFS_MAP_FULL_MAPPED; m.delta[0] = 1; @@ -596,7 +592,7 @@ static int z_erofs_map_blocks_ext(struct inode *inode, vi->z_fragmentoff = map->m_plen; if (recsz > offsetof(struct z_erofs_extent, pstart_lo)) vi->z_fragmentoff |= map->m_pa << 32; - } else if (map->m_plen) { + } else if (map->m_plen & Z_EROFS_EXTENT_PLEN_MASK) { map->m_flags |= EROFS_MAP_MAPPED | EROFS_MAP_FULL_MAPPED | EROFS_MAP_ENCODED; fmt = map->m_plen >> Z_EROFS_EXTENT_PLEN_FMT_BIT; @@ -715,6 +711,7 @@ static int z_erofs_map_sanity_check(struct inode *inode, struct erofs_map_blocks *map) { struct erofs_sb_info *sbi = EROFS_I_SB(inode); + u64 pend; if (!(map->m_flags & EROFS_MAP_ENCODED)) return 0; @@ -732,6 +729,10 @@ static int z_erofs_map_sanity_check(struct inode *inode, if (unlikely(map->m_plen > Z_EROFS_PCLUSTER_MAX_SIZE || map->m_llen > Z_EROFS_PCLUSTER_MAX_DSIZE)) return -EOPNOTSUPP; + /* Filesystems beyond 48-bit physical block addresses are invalid */ + if (unlikely(check_add_overflow(map->m_pa, map->m_plen, &pend) || + (pend >> sbi->blkszbits) >= BIT_ULL(48))) + return -EFSCORRUPTED; return 0; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 9c94ed8c3ab0..f42548ee9083 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -478,14 +478,6 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end, if (!hugetlb_vma_trylock_write(vma)) continue; - /* - * Skip VMAs without shareable locks. Per the design in commit - * 40549ba8f8e0, these will be handled by remove_inode_hugepages() - * called after this function with proper locking. - */ - if (!__vma_shareable_lock(vma)) - goto skip; - v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); @@ -496,7 +488,6 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end, * vmas. Therefore, lock is not held when calling * unmap_hugepage_range for private vmas. */ -skip: hugetlb_vma_unlock_write(vma); } } diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index 1161eabf11ee..9cc7eb863643 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -17,6 +17,7 @@ #include "fanotify/fanotify.h" #include "fdinfo.h" #include "fsnotify.h" +#include "../internal.h" #if defined(CONFIG_PROC_FS) @@ -46,7 +47,12 @@ static void show_mark_fhandle(struct seq_file *m, struct inode *inode) size = f->handle_bytes >> 2; + if (!super_trylock_shared(inode->i_sb)) + return; + ret = exportfs_encode_fid(inode, (struct fid *)f->f_handle, &size); + up_read(&inode->i_sb->s_umount); + if ((ret == FILEID_INVALID) || (ret < 0)) return; diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 86f2631e6360..10923bf7c8b8 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -867,6 +867,11 @@ static int __ocfs2_move_extents_range(struct buffer_head *di_bh, mlog_errno(ret); goto out; } + /* + * Invalidate extent cache after moving/defragging to prevent + * stale cached data with outdated extent flags. + */ + ocfs2_extent_map_trunc(inode, cpos); context->clusters_moved += alloc_size; next: diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 16a00a61fd2c..203e2aaa3c25 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -534,8 +534,6 @@ struct smb_version_operations { void (*new_lease_key)(struct cifs_fid *); int (*generate_signingkey)(struct cifs_ses *ses, struct TCP_Server_Info *server); - int (*calc_signature)(struct smb_rqst *, struct TCP_Server_Info *, - bool allocate_crypto); int (*set_integrity)(const unsigned int, struct cifs_tcon *tcon, struct cifsFileInfo *src_file); int (*enum_snapshots)(const unsigned int xid, struct cifs_tcon *tcon, @@ -732,7 +730,7 @@ struct TCP_Server_Info { bool nosharesock; bool tcp_nodelay; bool terminate; - unsigned int credits; /* send no more requests at once */ + int credits; /* send no more requests at once */ unsigned int max_credits; /* can override large 32000 default at mnt */ unsigned int in_flight; /* number of requests on the wire to server */ unsigned int max_in_flight; /* max number of requests that were on wire */ diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 4976be2c47c1..fb1813cbe0eb 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -9,6 +9,7 @@ #define _CIFSPROTO_H #include <linux/nls.h> #include <linux/ctype.h> +#include "cifsglob.h" #include "trace.h" #ifdef CONFIG_CIFS_DFS_UPCALL #include "dfs_cache.h" diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 2881efcbe09a..7da194f29fef 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1311,6 +1311,8 @@ cifs_readv_callback(struct mid_q_entry *mid) .rreq_debug_id = rdata->rreq->debug_id, .rreq_debug_index = rdata->subreq.debug_index, }; + unsigned int rreq_debug_id = rdata->rreq->debug_id; + unsigned int subreq_debug_index = rdata->subreq.debug_index; cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu\n", __func__, mid->mid, mid->mid_state, rdata->result, @@ -1374,6 +1376,9 @@ do_retry: __set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags); } + trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value, + server->credits, server->in_flight, + 0, cifs_trace_rw_credits_read_response_clear); rdata->credits.value = 0; rdata->subreq.error = rdata->result; rdata->subreq.transferred += rdata->got_bytes; @@ -1381,6 +1386,9 @@ do_retry: netfs_read_subreq_terminated(&rdata->subreq); release_mid(mid); add_credits(server, &credits, 0); + trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0, + server->credits, server->in_flight, + credits.value, cifs_trace_rw_credits_read_response_add); } /* cifs_async_readv - send an async write, and set up mid to handle result */ diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 098a79b7a959..cac355364e43 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -2484,11 +2484,8 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ do_rename_exit: - if (rc == 0) { + if (rc == 0) d_move(from_dentry, to_dentry); - /* Force a new lookup */ - d_drop(from_dentry); - } cifs_put_tlink(tlink); return rc; } diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 95cd484cfbba..0f9130ef2e7d 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -5446,7 +5446,6 @@ struct smb_version_operations smb20_operations = { .get_lease_key = smb2_get_lease_key, .set_lease_key = smb2_set_lease_key, .new_lease_key = smb2_new_lease_key, - .calc_signature = smb2_calc_signature, .is_read_op = smb2_is_read_op, .set_oplock_level = smb2_set_oplock_level, .create_lease_buf = smb2_create_lease_buf, @@ -5550,7 +5549,6 @@ struct smb_version_operations smb21_operations = { .get_lease_key = smb2_get_lease_key, .set_lease_key = smb2_set_lease_key, .new_lease_key = smb2_new_lease_key, - .calc_signature = smb2_calc_signature, .is_read_op = smb21_is_read_op, .set_oplock_level = smb21_set_oplock_level, .create_lease_buf = smb2_create_lease_buf, @@ -5660,7 +5658,6 @@ struct smb_version_operations smb30_operations = { .set_lease_key = smb2_set_lease_key, .new_lease_key = smb2_new_lease_key, .generate_signingkey = generate_smb30signingkey, - .calc_signature = smb3_calc_signature, .set_integrity = smb3_set_integrity, .is_read_op = smb21_is_read_op, .set_oplock_level = smb3_set_oplock_level, @@ -5777,7 +5774,6 @@ struct smb_version_operations smb311_operations = { .set_lease_key = smb2_set_lease_key, .new_lease_key = smb2_new_lease_key, .generate_signingkey = generate_smb311signingkey, - .calc_signature = smb3_calc_signature, .set_integrity = smb3_set_integrity, .is_read_op = smb21_is_read_op, .set_oplock_level = smb3_set_oplock_level, diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index 6eb86d134abc..5241daaae543 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -39,12 +39,6 @@ extern struct mid_q_entry *smb2_setup_async_request( struct TCP_Server_Info *server, struct smb_rqst *rqst); extern struct cifs_tcon *smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid); -extern int smb2_calc_signature(struct smb_rqst *rqst, - struct TCP_Server_Info *server, - bool allocate_crypto); -extern int smb3_calc_signature(struct smb_rqst *rqst, - struct TCP_Server_Info *server, - bool allocate_crypto); extern void smb2_echo_request(struct work_struct *work); extern __le32 smb2_get_lease_state(struct cifsInodeInfo *cinode); extern bool smb2_is_valid_oplock_break(char *buffer, diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index ad6068e17a2a..6a9b80385b86 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -209,9 +209,9 @@ smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid) return tcon; } -int +static int smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server, - bool allocate_crypto) + bool allocate_crypto) { int rc; unsigned char smb2_signature[SMB2_HMACSHA256_SIZE]; @@ -465,9 +465,9 @@ generate_smb311signingkey(struct cifs_ses *ses, return generate_smb3signingkey(ses, server, &triplet); } -int +static int smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server, - bool allocate_crypto) + bool allocate_crypto) { int rc; unsigned char smb3_signature[SMB2_CMACAES_SIZE]; @@ -477,6 +477,9 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server, struct smb_rqst drqst; u8 key[SMB3_SIGN_KEY_SIZE]; + if (server->vals->protocol_id <= SMB21_PROT_ID) + return smb2_calc_signature(rqst, server, allocate_crypto); + rc = smb3_get_sign_key(le64_to_cpu(shdr->SessionId), server, key); if (unlikely(rc)) { cifs_server_dbg(FYI, "%s: Could not get signing key\n", __func__); @@ -547,7 +550,6 @@ out: static int smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server) { - int rc = 0; struct smb2_hdr *shdr; struct smb2_sess_setup_req *ssr; bool is_binding; @@ -574,9 +576,7 @@ smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server) return 0; } - rc = server->ops->calc_signature(rqst, server, false); - - return rc; + return smb3_calc_signature(rqst, server, false); } int @@ -612,7 +612,7 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) memset(shdr->Signature, 0, SMB2_SIGNATURE_SIZE); - rc = server->ops->calc_signature(rqst, server, true); + rc = smb3_calc_signature(rqst, server, true); if (rc) return rc; diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index f2da694336ee..85a4c55b61b8 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -1784,6 +1784,7 @@ static struct smbd_connection *_smbd_get_connection( struct smbdirect_socket *sc; struct smbdirect_socket_parameters *sp; struct rdma_conn_param conn_param; + struct ib_qp_cap qp_cap; struct ib_qp_init_attr qp_attr; struct sockaddr_in *addr_in = (struct sockaddr_in *) dstaddr; struct ib_port_immutable port_immutable; @@ -1855,6 +1856,25 @@ static struct smbd_connection *_smbd_get_connection( goto config_failed; } + sp->responder_resources = + min_t(u8, sp->responder_resources, + sc->ib.dev->attrs.max_qp_rd_atom); + log_rdma_mr(INFO, "responder_resources=%d\n", + sp->responder_resources); + + /* + * We use allocate sp->responder_resources * 2 MRs + * and each MR needs WRs for REG and INV, so + * we use '* 4'. + * + * +1 for ib_drain_qp() + */ + memset(&qp_cap, 0, sizeof(qp_cap)); + qp_cap.max_send_wr = sp->send_credit_target + sp->responder_resources * 4 + 1; + qp_cap.max_recv_wr = sp->recv_credit_max + 1; + qp_cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; + qp_cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; + sc->ib.pd = ib_alloc_pd(sc->ib.dev, 0); if (IS_ERR(sc->ib.pd)) { rc = PTR_ERR(sc->ib.pd); @@ -1865,7 +1885,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.send_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->send_credit_target, IB_POLL_SOFTIRQ); + qp_cap.max_send_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.send_cq)) { sc->ib.send_cq = NULL; goto alloc_cq_failed; @@ -1873,7 +1893,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.recv_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->recv_credit_max, IB_POLL_SOFTIRQ); + qp_cap.max_recv_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.recv_cq)) { sc->ib.recv_cq = NULL; goto alloc_cq_failed; @@ -1882,11 +1902,7 @@ static struct smbd_connection *_smbd_get_connection( memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.event_handler = smbd_qp_async_error_upcall; qp_attr.qp_context = sc; - qp_attr.cap.max_send_wr = sp->send_credit_target; - qp_attr.cap.max_recv_wr = sp->recv_credit_max; - qp_attr.cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; - qp_attr.cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; - qp_attr.cap.max_inline_data = 0; + qp_attr.cap = qp_cap; qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR; qp_attr.qp_type = IB_QPT_RC; qp_attr.send_cq = sc->ib.send_cq; @@ -1900,12 +1916,6 @@ static struct smbd_connection *_smbd_get_connection( } sc->ib.qp = sc->rdma.cm_id->qp; - sp->responder_resources = - min_t(u8, sp->responder_resources, - sc->ib.dev->attrs.max_qp_rd_atom); - log_rdma_mr(INFO, "responder_resources=%d\n", - sp->responder_resources); - memset(&conn_param, 0, sizeof(conn_param)); conn_param.initiator_depth = sp->initiator_depth; conn_param.responder_resources = sp->responder_resources; diff --git a/fs/smb/client/trace.c b/fs/smb/client/trace.c index 465483787193..16b0e719731f 100644 --- a/fs/smb/client/trace.c +++ b/fs/smb/client/trace.c @@ -4,5 +4,6 @@ * * Author(s): Steve French <stfrench@microsoft.com> */ +#include "cifsglob.h" #define CREATE_TRACE_POINTS #include "trace.h" diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index 2d78e94072a0..e142bac4f9f8 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -498,17 +498,26 @@ int compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj, } EXPORT_SYMBOL_GPL(compat_only_sysfs_link_entry_to_kobj); -static int sysfs_group_attrs_change_owner(struct kernfs_node *grp_kn, +static int sysfs_group_attrs_change_owner(struct kobject *kobj, + struct kernfs_node *grp_kn, const struct attribute_group *grp, struct iattr *newattrs) { struct kernfs_node *kn; - int error; + int error, i; + umode_t mode; if (grp->attrs) { struct attribute *const *attr; - for (attr = grp->attrs; *attr; attr++) { + for (i = 0, attr = grp->attrs; *attr; i++, attr++) { + if (grp->is_visible) { + mode = grp->is_visible(kobj, *attr, i); + if (mode & SYSFS_GROUP_INVISIBLE) + break; + if (!mode) + continue; + } kn = kernfs_find_and_get(grp_kn, (*attr)->name); if (!kn) return -ENOENT; @@ -523,7 +532,14 @@ static int sysfs_group_attrs_change_owner(struct kernfs_node *grp_kn, if (grp->bin_attrs) { const struct bin_attribute *const *bin_attr; - for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) { + for (i = 0, bin_attr = grp->bin_attrs; *bin_attr; i++, bin_attr++) { + if (grp->is_bin_visible) { + mode = grp->is_bin_visible(kobj, *bin_attr, i); + if (mode & SYSFS_GROUP_INVISIBLE) + break; + if (!mode) + continue; + } kn = kernfs_find_and_get(grp_kn, (*bin_attr)->attr.name); if (!kn) return -ENOENT; @@ -573,7 +589,7 @@ int sysfs_group_change_owner(struct kobject *kobj, error = kernfs_setattr(grp_kn, &newattrs); if (!error) - error = sysfs_group_attrs_change_owner(grp_kn, grp, &newattrs); + error = sysfs_group_attrs_change_owner(kobj, grp_kn, grp, &newattrs); kernfs_put(grp_kn); diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index 8930d5254e1d..b99da294e9a3 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -119,6 +119,15 @@ config XFS_RT See the xfs man page in section 5 for additional information. + This option is mandatory to support zoned block devices. For these + devices, the realtime subvolume must be backed by a zoned block + device and a regular block device used as the main device (for + metadata). If the zoned block device is a host-managed SMR hard-disk + containing conventional zones at the beginning of its address space, + XFS will use the disk conventional zones as the main device and the + remaining sequential write required zones as the backing storage for + the realtime subvolume. + If unsure, say N. config XFS_DRAIN_INTENTS @@ -156,7 +165,7 @@ config XFS_ONLINE_SCRUB_STATS bool "XFS online metadata check usage data collection" default y depends on XFS_ONLINE_SCRUB - select DEBUG_FS + depends on DEBUG_FS help If you say Y here, the kernel will gather usage data about the online metadata check subsystem. This includes the number diff --git a/fs/xfs/scrub/nlinks.c b/fs/xfs/scrub/nlinks.c index 26721fab5cab..091c79e432e5 100644 --- a/fs/xfs/scrub/nlinks.c +++ b/fs/xfs/scrub/nlinks.c @@ -376,6 +376,36 @@ out_incomplete: return error; } +static uint +xchk_nlinks_ilock_dir( + struct xfs_inode *ip) +{ + uint lock_mode = XFS_ILOCK_SHARED; + + /* + * We're going to scan the directory entries, so we must be ready to + * pull the data fork mappings into memory if they aren't already. + */ + if (xfs_need_iread_extents(&ip->i_df)) + lock_mode = XFS_ILOCK_EXCL; + + /* + * We're going to scan the parent pointers, so we must be ready to + * pull the attr fork mappings into memory if they aren't already. + */ + if (xfs_has_parent(ip->i_mount) && xfs_inode_has_attr_fork(ip) && + xfs_need_iread_extents(&ip->i_af)) + lock_mode = XFS_ILOCK_EXCL; + + /* + * Take the IOLOCK so that other threads cannot start a directory + * update while we're scanning. + */ + lock_mode |= XFS_IOLOCK_SHARED; + xfs_ilock(ip, lock_mode); + return lock_mode; +} + /* Walk a directory to bump the observed link counts of the children. */ STATIC int xchk_nlinks_collect_dir( @@ -394,8 +424,7 @@ xchk_nlinks_collect_dir( return 0; /* Prevent anyone from changing this directory while we walk it. */ - xfs_ilock(dp, XFS_IOLOCK_SHARED); - lock_mode = xfs_ilock_data_map_shared(dp); + lock_mode = xchk_nlinks_ilock_dir(dp); /* * The dotdot entry of an unlinked directory still points to the last @@ -452,7 +481,6 @@ out_abort: xchk_iscan_abort(&xnc->collect_iscan); out_unlock: xfs_iunlock(dp, lock_mode); - xfs_iunlock(dp, XFS_IOLOCK_SHARED); return error; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 773d959965dc..47edf3041631 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1751,7 +1751,7 @@ xfs_init_buftarg( const char *descr) { /* The maximum size of the buftarg is only known once the sb is read. */ - btp->bt_nr_sectors = (xfs_daddr_t)-1; + btp->bt_nr_sectors = XFS_BUF_DADDR_MAX; /* Set up device logical sector size mask */ btp->bt_logical_sectorsize = logical_sectorsize; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 8fa7bdf59c91..e25cd2a160f3 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -22,6 +22,7 @@ extern struct kmem_cache *xfs_buf_cache; */ struct xfs_buf; +#define XFS_BUF_DADDR_MAX ((xfs_daddr_t) S64_MAX) #define XFS_BUF_DADDR_NULL ((xfs_daddr_t) (-1LL)) #define XBF_READ (1u << 0) /* buffer intended for reading from device */ diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index f046d1215b04..b871dfde372b 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -236,7 +236,6 @@ typedef struct xfs_mount { bool m_update_sb; /* sb needs update in mount */ unsigned int m_max_open_zones; unsigned int m_zonegc_low_space; - struct xfs_mru_cache *m_zone_cache; /* Inode to open zone cache */ /* max_atomic_write mount option value */ unsigned long long m_awu_max_bytes; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index e85a156dc17d..1067ebb3b001 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -102,7 +102,7 @@ static const struct constant_table dax_param_enums[] = { * Table driven mount option parser. */ enum { - Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev, + Op_deprecated, Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev, Opt_wsync, Opt_noalign, Opt_swalloc, Opt_sunit, Opt_swidth, Opt_nouuid, Opt_grpid, Opt_nogrpid, Opt_bsdgroups, Opt_sysvgroups, Opt_allocsize, Opt_norecovery, Opt_inode64, Opt_inode32, @@ -114,7 +114,21 @@ enum { Opt_lifetime, Opt_nolifetime, Opt_max_atomic_write, }; +#define fsparam_dead(NAME) \ + __fsparam(NULL, (NAME), Op_deprecated, fs_param_deprecated, NULL) + static const struct fs_parameter_spec xfs_fs_parameters[] = { + /* + * These mount options were supposed to be deprecated in September 2025 + * but the deprecation warning was buggy, so not all users were + * notified. The deprecation is now obnoxiously loud and postponed to + * September 2030. + */ + fsparam_dead("attr2"), + fsparam_dead("noattr2"), + fsparam_dead("ikeep"), + fsparam_dead("noikeep"), + fsparam_u32("logbufs", Opt_logbufs), fsparam_string("logbsize", Opt_logbsize), fsparam_string("logdev", Opt_logdev), @@ -786,6 +800,12 @@ xfs_fs_evict_inode( truncate_inode_pages_final(&inode->i_data); clear_inode(inode); + + if (IS_ENABLED(CONFIG_XFS_RT) && + S_ISREG(inode->i_mode) && inode->i_private) { + xfs_open_zone_put(inode->i_private); + inode->i_private = NULL; + } } static void @@ -1373,16 +1393,25 @@ suffix_kstrtoull( static inline void xfs_fs_warn_deprecated( struct fs_context *fc, - struct fs_parameter *param, - uint64_t flag, - bool value) + struct fs_parameter *param) { - /* Don't print the warning if reconfiguring and current mount point - * already had the flag set + /* + * Always warn about someone passing in a deprecated mount option. + * Previously we wouldn't print the warning if we were reconfiguring + * and current mount point already had the flag set, but that was not + * the right thing to do. + * + * Many distributions mount the root filesystem with no options in the + * initramfs and rely on mount -a to remount the root fs with the + * options in fstab. However, the old behavior meant that there would + * never be a warning about deprecated mount options for the root fs in + * /etc/fstab. On a single-fs system, that means no warning at all. + * + * Compounding this problem are distribution scripts that copy + * /proc/mounts to fstab, which means that we can't remove mount + * options unless we're 100% sure they have only ever been advertised + * in /proc/mounts in response to explicitly provided mount options. */ - if ((fc->purpose & FS_CONTEXT_FOR_RECONFIGURE) && - !!(XFS_M(fc->root->d_sb)->m_features & flag) == value) - return; xfs_warn(fc->s_fs_info, "%s mount option is deprecated.", param->key); } @@ -1408,6 +1437,9 @@ xfs_fs_parse_param( return opt; switch (opt) { + case Op_deprecated: + xfs_fs_warn_deprecated(fc, param); + return 0; case Opt_logbufs: parsing_mp->m_logbufs = result.uint_32; return 0; @@ -1528,7 +1560,6 @@ xfs_fs_parse_param( xfs_mount_set_dax_mode(parsing_mp, result.uint_32); return 0; #endif - /* Following mount options will be removed in September 2025 */ case Opt_max_open_zones: parsing_mp->m_max_open_zones = result.uint_32; return 0; @@ -2221,7 +2252,7 @@ xfs_init_fs_context( struct xfs_mount *mp; int i; - mp = kzalloc(sizeof(struct xfs_mount), GFP_KERNEL | __GFP_NOFAIL); + mp = kzalloc(sizeof(struct xfs_mount), GFP_KERNEL); if (!mp) return -ENOMEM; diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index 1147bacb2da8..23cdab4515bb 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -26,14 +26,22 @@ #include "xfs_trace.h" #include "xfs_mru_cache.h" +static void +xfs_open_zone_free_rcu( + struct callback_head *cb) +{ + struct xfs_open_zone *oz = container_of(cb, typeof(*oz), oz_rcu); + + xfs_rtgroup_rele(oz->oz_rtg); + kfree(oz); +} + void xfs_open_zone_put( struct xfs_open_zone *oz) { - if (atomic_dec_and_test(&oz->oz_ref)) { - xfs_rtgroup_rele(oz->oz_rtg); - kfree(oz); - } + if (atomic_dec_and_test(&oz->oz_ref)) + call_rcu(&oz->oz_rcu, xfs_open_zone_free_rcu); } static inline uint32_t @@ -614,14 +622,25 @@ static inline enum rw_hint xfs_inode_write_hint(struct xfs_inode *ip) } /* - * Try to pack inodes that are written back after they were closed tight instead - * of trying to open new zones for them or spread them to the least recently - * used zone. This optimizes the data layout for workloads that untar or copy - * a lot of small files. Right now this does not separate multiple such + * Try to tightly pack small files that are written back after they were closed + * instead of trying to open new zones for them or spread them to the least + * recently used zone. This optimizes the data layout for workloads that untar + * or copy a lot of small files. Right now this does not separate multiple such * streams. */ static inline bool xfs_zoned_pack_tight(struct xfs_inode *ip) { + struct xfs_mount *mp = ip->i_mount; + size_t zone_capacity = + XFS_FSB_TO_B(mp, mp->m_groups[XG_TYPE_RTG].blocks); + + /* + * Do not pack write files that are already using a full zone to avoid + * fragmentation. + */ + if (i_size_read(VFS_I(ip)) >= zone_capacity) + return false; + return !inode_is_open_for_write(VFS_I(ip)) && !(ip->i_diflags & XFS_DIFLAG_APPEND); } @@ -746,97 +765,54 @@ xfs_mark_rtg_boundary( } /* - * Cache the last zone written to for an inode so that it is considered first - * for subsequent writes. - */ -struct xfs_zone_cache_item { - struct xfs_mru_cache_elem mru; - struct xfs_open_zone *oz; -}; - -static inline struct xfs_zone_cache_item * -xfs_zone_cache_item(struct xfs_mru_cache_elem *mru) -{ - return container_of(mru, struct xfs_zone_cache_item, mru); -} - -static void -xfs_zone_cache_free_func( - void *data, - struct xfs_mru_cache_elem *mru) -{ - struct xfs_zone_cache_item *item = xfs_zone_cache_item(mru); - - xfs_open_zone_put(item->oz); - kfree(item); -} - -/* * Check if we have a cached last open zone available for the inode and * if yes return a reference to it. */ static struct xfs_open_zone * -xfs_cached_zone( - struct xfs_mount *mp, - struct xfs_inode *ip) +xfs_get_cached_zone( + struct xfs_inode *ip) { - struct xfs_mru_cache_elem *mru; - struct xfs_open_zone *oz; + struct xfs_open_zone *oz; - mru = xfs_mru_cache_lookup(mp->m_zone_cache, ip->i_ino); - if (!mru) - return NULL; - oz = xfs_zone_cache_item(mru)->oz; + rcu_read_lock(); + oz = VFS_I(ip)->i_private; if (oz) { /* * GC only steals open zones at mount time, so no GC zones * should end up in the cache. */ ASSERT(!oz->oz_is_gc); - ASSERT(atomic_read(&oz->oz_ref) > 0); - atomic_inc(&oz->oz_ref); + if (!atomic_inc_not_zero(&oz->oz_ref)) + oz = NULL; } - xfs_mru_cache_done(mp->m_zone_cache); + rcu_read_unlock(); + return oz; } /* - * Update the last used zone cache for a given inode. + * Stash our zone in the inode so that is is reused for future allocations. * - * The caller must have a reference on the open zone. + * The open_zone structure will be pinned until either the inode is freed or + * until the cached open zone is replaced with a different one because the + * current one was full when we tried to use it. This means we keep any + * open zone around forever as long as any inode that used it for the last + * write is cached, which slightly increases the memory use of cached inodes + * that were every written to, but significantly simplifies the cached zone + * lookup. Because the open_zone is clearly marked as full when all data + * in the underlying RTG was written, the caching is always safe. */ static void -xfs_zone_cache_create_association( - struct xfs_inode *ip, - struct xfs_open_zone *oz) +xfs_set_cached_zone( + struct xfs_inode *ip, + struct xfs_open_zone *oz) { - struct xfs_mount *mp = ip->i_mount; - struct xfs_zone_cache_item *item = NULL; - struct xfs_mru_cache_elem *mru; + struct xfs_open_zone *old_oz; - ASSERT(atomic_read(&oz->oz_ref) > 0); atomic_inc(&oz->oz_ref); - - mru = xfs_mru_cache_lookup(mp->m_zone_cache, ip->i_ino); - if (mru) { - /* - * If we have an association already, update it to point to the - * new zone. - */ - item = xfs_zone_cache_item(mru); - xfs_open_zone_put(item->oz); - item->oz = oz; - xfs_mru_cache_done(mp->m_zone_cache); - return; - } - - item = kmalloc(sizeof(*item), GFP_KERNEL); - if (!item) { - xfs_open_zone_put(oz); - return; - } - item->oz = oz; - xfs_mru_cache_insert(mp->m_zone_cache, ip->i_ino, &item->mru); + old_oz = xchg(&VFS_I(ip)->i_private, oz); + if (old_oz) + xfs_open_zone_put(old_oz); } static void @@ -880,15 +856,14 @@ xfs_zone_alloc_and_submit( * the inode is still associated with a zone and use that if so. */ if (!*oz) - *oz = xfs_cached_zone(mp, ip); + *oz = xfs_get_cached_zone(ip); if (!*oz) { select_zone: *oz = xfs_select_zone(mp, write_hint, pack_tight); if (!*oz) goto out_error; - - xfs_zone_cache_create_association(ip, *oz); + xfs_set_cached_zone(ip, *oz); } alloc_len = xfs_zone_alloc_blocks(*oz, XFS_B_TO_FSB(mp, ioend->io_size), @@ -966,6 +941,12 @@ xfs_free_open_zones( xfs_open_zone_put(oz); } spin_unlock(&zi->zi_open_zones_lock); + + /* + * Wait for all open zones to be freed so that they drop the group + * references: + */ + rcu_barrier(); } struct xfs_init_zones { @@ -1279,14 +1260,6 @@ xfs_mount_zones( error = xfs_zone_gc_mount(mp); if (error) goto out_free_zone_info; - - /* - * Set up a mru cache to track inode to open zone for data placement - * purposes. The magic values for group count and life time is the - * same as the defaults for file streams, which seems sane enough. - */ - xfs_mru_cache_create(&mp->m_zone_cache, mp, - 5000, 10, xfs_zone_cache_free_func); return 0; out_free_zone_info: @@ -1300,5 +1273,4 @@ xfs_unmount_zones( { xfs_zone_gc_unmount(mp); xfs_free_zone_info(mp->m_zone_info); - xfs_mru_cache_destroy(mp->m_zone_cache); } diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c index 064cd1a857a0..109877d9a6bf 100644 --- a/fs/xfs/xfs_zone_gc.c +++ b/fs/xfs/xfs_zone_gc.c @@ -491,21 +491,6 @@ xfs_zone_gc_select_victim( struct xfs_rtgroup *victim_rtg = NULL; unsigned int bucket; - if (xfs_is_shutdown(mp)) - return false; - - if (iter->victim_rtg) - return true; - - /* - * Don't start new work if we are asked to stop or park. - */ - if (kthread_should_stop() || kthread_should_park()) - return false; - - if (!xfs_zoned_need_gc(mp)) - return false; - spin_lock(&zi->zi_used_buckets_lock); for (bucket = 0; bucket < XFS_ZONE_USED_BUCKETS; bucket++) { victim_rtg = xfs_zone_gc_pick_victim_from(mp, bucket); @@ -975,6 +960,27 @@ xfs_zone_gc_reset_zones( } while (next); } +static bool +xfs_zone_gc_should_start_new_work( + struct xfs_zone_gc_data *data) +{ + if (xfs_is_shutdown(data->mp)) + return false; + if (!xfs_zone_gc_space_available(data)) + return false; + + if (!data->iter.victim_rtg) { + if (kthread_should_stop() || kthread_should_park()) + return false; + if (!xfs_zoned_need_gc(data->mp)) + return false; + if (!xfs_zone_gc_select_victim(data)) + return false; + } + + return true; +} + /* * Handle the work to read and write data for GC and to reset the zones, * including handling all completions. @@ -982,7 +988,7 @@ xfs_zone_gc_reset_zones( * Note that the order of the chunks is preserved so that we don't undo the * optimal order established by xfs_zone_gc_query(). */ -static bool +static void xfs_zone_gc_handle_work( struct xfs_zone_gc_data *data) { @@ -996,30 +1002,22 @@ xfs_zone_gc_handle_work( zi->zi_reset_list = NULL; spin_unlock(&zi->zi_reset_list_lock); - if (!xfs_zone_gc_select_victim(data) || - !xfs_zone_gc_space_available(data)) { - if (list_empty(&data->reading) && - list_empty(&data->writing) && - list_empty(&data->resetting) && - !reset_list) - return false; - } - - __set_current_state(TASK_RUNNING); - try_to_freeze(); - - if (reset_list) + if (reset_list) { + set_current_state(TASK_RUNNING); xfs_zone_gc_reset_zones(data, reset_list); + } list_for_each_entry_safe(chunk, next, &data->resetting, entry) { if (READ_ONCE(chunk->state) != XFS_GC_BIO_DONE) break; + set_current_state(TASK_RUNNING); xfs_zone_gc_finish_reset(chunk); } list_for_each_entry_safe(chunk, next, &data->writing, entry) { if (READ_ONCE(chunk->state) != XFS_GC_BIO_DONE) break; + set_current_state(TASK_RUNNING); xfs_zone_gc_finish_chunk(chunk); } @@ -1027,15 +1025,18 @@ xfs_zone_gc_handle_work( list_for_each_entry_safe(chunk, next, &data->reading, entry) { if (READ_ONCE(chunk->state) != XFS_GC_BIO_DONE) break; + set_current_state(TASK_RUNNING); xfs_zone_gc_write_chunk(chunk); } blk_finish_plug(&plug); - blk_start_plug(&plug); - while (xfs_zone_gc_start_chunk(data)) - ; - blk_finish_plug(&plug); - return true; + if (xfs_zone_gc_should_start_new_work(data)) { + set_current_state(TASK_RUNNING); + blk_start_plug(&plug); + while (xfs_zone_gc_start_chunk(data)) + ; + blk_finish_plug(&plug); + } } /* @@ -1059,8 +1060,18 @@ xfs_zoned_gcd( for (;;) { set_current_state(TASK_INTERRUPTIBLE | TASK_FREEZABLE); xfs_set_zonegc_running(mp); - if (xfs_zone_gc_handle_work(data)) + + xfs_zone_gc_handle_work(data); + + /* + * Only sleep if nothing set the state to running. Else check for + * work again as someone might have queued up more work and woken + * us in the meantime. + */ + if (get_current_state() == TASK_RUNNING) { + try_to_freeze(); continue; + } if (list_empty(&data->reading) && list_empty(&data->writing) && diff --git a/fs/xfs/xfs_zone_priv.h b/fs/xfs/xfs_zone_priv.h index 35e6de3d25ed..4322e26dd99a 100644 --- a/fs/xfs/xfs_zone_priv.h +++ b/fs/xfs/xfs_zone_priv.h @@ -44,6 +44,8 @@ struct xfs_open_zone { * the life time of an open zone. */ struct xfs_rtgroup *oz_rtg; + + struct rcu_head oz_rcu; }; /* diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index cd7ee4df9045..81e603839c4a 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -338,6 +338,7 @@ struct ffa_mem_region_attributes { * an `struct ffa_mem_region_addr_range`. */ u32 composite_off; + u8 impdef_val[16]; u64 reserved; }; @@ -417,15 +418,31 @@ struct ffa_mem_region { #define CONSTITUENTS_OFFSET(x) \ (offsetof(struct ffa_composite_mem_region, constituents[x])) +#define FFA_EMAD_HAS_IMPDEF_FIELD(version) ((version) >= FFA_VERSION_1_2) +#define FFA_MEM_REGION_HAS_EP_MEM_OFFSET(version) ((version) > FFA_VERSION_1_0) + +static inline u32 ffa_emad_size_get(u32 ffa_version) +{ + u32 sz; + struct ffa_mem_region_attributes *ep_mem_access; + + if (FFA_EMAD_HAS_IMPDEF_FIELD(ffa_version)) + sz = sizeof(*ep_mem_access); + else + sz = sizeof(*ep_mem_access) - sizeof(ep_mem_access->impdef_val); + + return sz; +} + static inline u32 ffa_mem_desc_offset(struct ffa_mem_region *buf, int count, u32 ffa_version) { - u32 offset = count * sizeof(struct ffa_mem_region_attributes); + u32 offset = count * ffa_emad_size_get(ffa_version); /* * Earlier to v1.1, the endpoint memory descriptor array started at * offset 32(i.e. offset of ep_mem_offset in the current structure) */ - if (ffa_version <= FFA_VERSION_1_0) + if (!FFA_MEM_REGION_HAS_EP_MEM_OFFSET(ffa_version)) offset += offsetof(struct ffa_mem_region, ep_mem_offset); else offset += sizeof(struct ffa_mem_region); diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 93318fce31f3..b760a3c470a5 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -452,7 +452,7 @@ struct cgroup_freezer_state { int nr_frozen_tasks; /* Freeze time data consistency protection */ - seqcount_t freeze_seq; + seqcount_spinlock_t freeze_seq; /* * Most recent time the cgroup was requested to freeze. diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index d0cf10d5e0f7..f0cf2714ec52 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -320,9 +320,6 @@ static inline bool exportfs_can_decode_fh(const struct export_operations *nop) static inline bool exportfs_can_encode_fh(const struct export_operations *nop, int fh_flags) { - if (!nop) - return false; - /* * If a non-decodeable file handle was requested, we only need to make * sure that filesystem did not opt-out of encoding fid. @@ -330,6 +327,10 @@ static inline bool exportfs_can_encode_fh(const struct export_operations *nop, if (fh_flags & EXPORT_FH_FID) return exportfs_can_encode_fid(nop); + /* Normal file handles cannot be created without export ops */ + if (!nop) + return false; + /* * If a connectable file handle was requested, we need to make sure that * filesystem can also decode connected file handles. diff --git a/include/linux/gpio/regmap.h b/include/linux/gpio/regmap.h index 622a2939ebe0..87983a5f3681 100644 --- a/include/linux/gpio/regmap.h +++ b/include/linux/gpio/regmap.h @@ -38,6 +38,10 @@ struct regmap; * offset to a register/bitmask pair. If not * given the default gpio_regmap_simple_xlate() * is used. + * @fixed_direction_output: + * (Optional) Bitmap representing the fixed direction of + * the GPIO lines. Useful when there are GPIO lines with a + * fixed direction mixed together in the same register. * @drvdata: (Optional) Pointer to driver specific data which is * not used by gpio-remap but is provided "as is" to the * driver callback(s). @@ -85,6 +89,7 @@ struct gpio_regmap_config { int reg_stride; int ngpio_per_reg; struct irq_domain *irq_domain; + unsigned long *fixed_direction_output; #ifdef CONFIG_REGMAP_IRQ struct regmap_irq_chip *regmap_irq_chip; diff --git a/include/linux/hung_task.h b/include/linux/hung_task.h index 34e615c76ca5..c4403eeb7144 100644 --- a/include/linux/hung_task.h +++ b/include/linux/hung_task.h @@ -20,6 +20,10 @@ * always zero. So we can use these bits to encode the specific blocking * type. * + * Note that on architectures where this is not guaranteed, or for any + * unaligned lock, this tracking mechanism is silently skipped for that + * lock. + * * Type encoding: * 00 - Blocked on mutex (BLOCKER_TYPE_MUTEX) * 01 - Blocked on semaphore (BLOCKER_TYPE_SEM) @@ -45,7 +49,7 @@ static inline void hung_task_set_blocker(void *lock, unsigned long type) * If the lock pointer matches the BLOCKER_TYPE_MASK, return * without writing anything. */ - if (WARN_ON_ONCE(lock_ptr & BLOCKER_TYPE_MASK)) + if (lock_ptr & BLOCKER_TYPE_MASK) return; WRITE_ONCE(current->blocker, lock_ptr | type); @@ -53,8 +57,6 @@ static inline void hung_task_set_blocker(void *lock, unsigned long type) static inline void hung_task_clear_blocker(void) { - WARN_ON_ONCE(!READ_ONCE(current->blocker)); - WRITE_ONCE(current->blocker, 0UL); } diff --git a/include/linux/misc_cgroup.h b/include/linux/misc_cgroup.h index 71cf5bfc6349..0cb36a3ffc47 100644 --- a/include/linux/misc_cgroup.h +++ b/include/linux/misc_cgroup.h @@ -19,7 +19,7 @@ enum misc_res_type { MISC_CG_RES_SEV_ES, #endif #ifdef CONFIG_INTEL_TDX_HOST - /* Intel TDX HKIDs resource */ + /** @MISC_CG_RES_TDX: Intel TDX HKIDs resource */ MISC_CG_RES_TDX, #endif /** @MISC_CG_RES_TYPES: count of enum misc_res_type constants */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 07614cd95bed..1b0b36aa2a76 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10833,7 +10833,9 @@ struct mlx5_ifc_pcam_regs_5000_to_507f_bits { u8 port_access_reg_cap_mask_127_to_96[0x20]; u8 port_access_reg_cap_mask_95_to_64[0x20]; - u8 port_access_reg_cap_mask_63_to_36[0x1c]; + u8 port_access_reg_cap_mask_63[0x1]; + u8 pphcr[0x1]; + u8 port_access_reg_cap_mask_61_to_36[0x1a]; u8 pplm[0x1]; u8 port_access_reg_cap_mask_34_to_32[0x3]; diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index a3f44f6c2da1..0b436e15f4cd 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -629,13 +629,13 @@ DEFINE_GUARD(pm_runtime_active_auto, struct device *, * device. */ DEFINE_GUARD_COND(pm_runtime_active, _try, - pm_runtime_get_active(_T, RPM_TRANSPARENT)) + pm_runtime_get_active(_T, RPM_TRANSPARENT), _RET == 0) DEFINE_GUARD_COND(pm_runtime_active, _try_enabled, - pm_runtime_resume_and_get(_T)) + pm_runtime_resume_and_get(_T), _RET == 0) DEFINE_GUARD_COND(pm_runtime_active_auto, _try, - pm_runtime_get_active(_T, RPM_TRANSPARENT)) + pm_runtime_get_active(_T, RPM_TRANSPARENT), _RET == 0) DEFINE_GUARD_COND(pm_runtime_active_auto, _try_enabled, - pm_runtime_resume_and_get(_T)) + pm_runtime_resume_and_get(_T), _RET == 0) /** * pm_runtime_put_sync - Drop device usage counter and run "idle check" if 0. diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fb3fec9affaa..a7cc3d1f4fd1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4204,6 +4204,9 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, unsigned int flags, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err); +__poll_t datagram_poll_queue(struct file *file, struct socket *sock, + struct poll_table_struct *wait, + struct sk_buff_head *rcv_queue); __poll_t datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 20e0584db1dd..4d1780848d0e 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -401,6 +401,10 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, if (!tnl_hdr_negotiated) return -EINVAL; + vhdr->hash_hdr.hash_value = 0; + vhdr->hash_hdr.hash_report = 0; + vhdr->hash_hdr.padding = 0; + /* Let the basic parsing deal with plain GSO features. */ skb_shinfo(skb)->gso_type &= ~tnl_gso_type; ret = virtio_net_hdr_from_skb(skb, hdr, true, false, vlan_hlen); diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 40ff19f52a8d..517489a7ec60 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -1013,6 +1013,20 @@ struct drm_xe_vm_destroy { * valid on VMs with DRM_XE_VM_CREATE_FLAG_FAULT_MODE set. The CPU address * mirror flag are only valid for DRM_XE_VM_BIND_OP_MAP operations, the BO * handle MBZ, and the BO offset MBZ. + * - %DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET - Can be used in combination with + * %DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR to reset madvises when the underlying + * CPU address space range is unmapped (typically with munmap(2) or brk(2)). + * The madvise values set with &DRM_IOCTL_XE_MADVISE are reset to the values + * that were present immediately after the &DRM_IOCTL_XE_VM_BIND. + * The reset GPU virtual address range is the intersection of the range bound + * using &DRM_IOCTL_XE_VM_BIND and the virtual CPU address space range + * unmapped. + * This functionality is present to mimic the behaviour of CPU address space + * madvises set using madvise(2), which are typically reset on unmap. + * Note: free(3) may or may not call munmap(2) and/or brk(2), and may thus + * not invoke autoreset. Neither will stack variables going out of scope. + * Therefore it's recommended to always explicitly reset the madvises when + * freeing the memory backing a region used in a &DRM_IOCTL_XE_MADVISE call. * * The @prefetch_mem_region_instance for %DRM_XE_VM_BIND_OP_PREFETCH can also be: * - %DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC, which ensures prefetching occurs in @@ -1119,6 +1133,7 @@ struct drm_xe_vm_bind_op { #define DRM_XE_VM_BIND_FLAG_DUMPABLE (1 << 3) #define DRM_XE_VM_BIND_FLAG_CHECK_PXP (1 << 4) #define DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR (1 << 5) +#define DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET (1 << 6) /** @flags: Bind flags */ __u32 flags; diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index ff3364531c77..294c75a8a3bd 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -59,7 +59,6 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) { struct io_overflow_cqe *ocqe; struct io_rings *r = ctx->rings; - struct rusage sq_usage; unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1; unsigned int sq_head = READ_ONCE(r->sq.head); unsigned int sq_tail = READ_ONCE(r->sq.tail); @@ -152,14 +151,15 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) * thread termination. */ if (tsk) { + u64 usec; + get_task_struct(tsk); rcu_read_unlock(); - getrusage(tsk, RUSAGE_SELF, &sq_usage); + usec = io_sq_cpu_usec(tsk); put_task_struct(tsk); sq_pid = sq->task_pid; sq_cpu = sq->sq_cpu; - sq_total_time = (sq_usage.ru_stime.tv_sec * 1000000 - + sq_usage.ru_stime.tv_usec); + sq_total_time = usec; sq_work_time = sq->work_time; } else { rcu_read_unlock(); diff --git a/io_uring/filetable.c b/io_uring/filetable.c index a21660e3145a..794ef95df293 100644 --- a/io_uring/filetable.c +++ b/io_uring/filetable.c @@ -57,7 +57,7 @@ void io_free_file_tables(struct io_ring_ctx *ctx, struct io_file_table *table) static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, u32 slot_index) - __must_hold(&req->ctx->uring_lock) + __must_hold(&ctx->uring_lock) { struct io_rsrc_node *node; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 820ef0527666..296667ba712c 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -879,7 +879,7 @@ static inline struct io_cqe io_init_cqe(u64 user_data, s32 res, u32 cflags) } static __cold void io_cqe_overflow(struct io_ring_ctx *ctx, struct io_cqe *cqe, - struct io_big_cqe *big_cqe) + struct io_big_cqe *big_cqe) { struct io_overflow_cqe *ocqe; diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index aad655e38672..a727e020fe03 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -155,6 +155,27 @@ static int io_provided_buffers_select(struct io_kiocb *req, size_t *len, return 1; } +static bool io_should_commit(struct io_kiocb *req, unsigned int issue_flags) +{ + /* + * If we came in unlocked, we have no choice but to consume the + * buffer here, otherwise nothing ensures that the buffer won't + * get used by others. This does mean it'll be pinned until the + * IO completes, coming in unlocked means we're being called from + * io-wq context and there may be further retries in async hybrid + * mode. For the locked case, the caller must call commit when + * the transfer completes (or if we get -EAGAIN and must poll of + * retry). + */ + if (issue_flags & IO_URING_F_UNLOCKED) + return true; + + /* uring_cmd commits kbuf upfront, no need to auto-commit */ + if (!io_file_can_poll(req) && req->opcode != IORING_OP_URING_CMD) + return true; + return false; +} + static struct io_br_sel io_ring_buffer_select(struct io_kiocb *req, size_t *len, struct io_buffer_list *bl, unsigned int issue_flags) @@ -181,17 +202,7 @@ static struct io_br_sel io_ring_buffer_select(struct io_kiocb *req, size_t *len, sel.buf_list = bl; sel.addr = u64_to_user_ptr(buf->addr); - if (issue_flags & IO_URING_F_UNLOCKED || !io_file_can_poll(req)) { - /* - * If we came in unlocked, we have no choice but to consume the - * buffer here, otherwise nothing ensures that the buffer won't - * get used by others. This does mean it'll be pinned until the - * IO completes, coming in unlocked means we're being called from - * io-wq context and there may be further retries in async hybrid - * mode. For the locked case, the caller must call commit when - * the transfer completes (or if we get -EAGAIN and must poll of - * retry). - */ + if (io_should_commit(req, issue_flags)) { io_kbuf_commit(req, sel.buf_list, *len, 1); sel.buf_list = NULL; } diff --git a/io_uring/net.c b/io_uring/net.c index f99b90c762fc..a95cc9ca2a4d 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -383,7 +383,7 @@ static int io_send_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; if (sr->flags & IORING_SEND_VECTORIZED) - return io_net_import_vec(req, kmsg, sr->buf, sr->len, ITER_SOURCE); + return io_net_import_vec(req, kmsg, sr->buf, sr->len, ITER_SOURCE); return import_ubuf(ITER_SOURCE, sr->buf, sr->len, &kmsg->msg.msg_iter); } diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index a3f11349ce06..e22f072c7d5f 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -11,6 +11,7 @@ #include <linux/audit.h> #include <linux/security.h> #include <linux/cpuset.h> +#include <linux/sched/cputime.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> @@ -169,7 +170,38 @@ static inline bool io_sqd_events_pending(struct io_sq_data *sqd) return READ_ONCE(sqd->state); } -static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) +struct io_sq_time { + bool started; + u64 usec; +}; + +u64 io_sq_cpu_usec(struct task_struct *tsk) +{ + u64 utime, stime; + + task_cputime_adjusted(tsk, &utime, &stime); + do_div(stime, 1000); + return stime; +} + +static void io_sq_update_worktime(struct io_sq_data *sqd, struct io_sq_time *ist) +{ + if (!ist->started) + return; + ist->started = false; + sqd->work_time += io_sq_cpu_usec(current) - ist->usec; +} + +static void io_sq_start_worktime(struct io_sq_time *ist) +{ + if (ist->started) + return; + ist->started = true; + ist->usec = io_sq_cpu_usec(current); +} + +static int __io_sq_thread(struct io_ring_ctx *ctx, struct io_sq_data *sqd, + bool cap_entries, struct io_sq_time *ist) { unsigned int to_submit; int ret = 0; @@ -182,6 +214,8 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) if (to_submit || !wq_list_empty(&ctx->iopoll_list)) { const struct cred *creds = NULL; + io_sq_start_worktime(ist); + if (ctx->sq_creds != current_cred()) creds = override_creds(ctx->sq_creds); @@ -255,23 +289,11 @@ static bool io_sq_tw_pending(struct llist_node *retry_list) return retry_list || !llist_empty(&tctx->task_list); } -static void io_sq_update_worktime(struct io_sq_data *sqd, struct rusage *start) -{ - struct rusage end; - - getrusage(current, RUSAGE_SELF, &end); - end.ru_stime.tv_sec -= start->ru_stime.tv_sec; - end.ru_stime.tv_usec -= start->ru_stime.tv_usec; - - sqd->work_time += end.ru_stime.tv_usec + end.ru_stime.tv_sec * 1000000; -} - static int io_sq_thread(void *data) { struct llist_node *retry_list = NULL; struct io_sq_data *sqd = data; struct io_ring_ctx *ctx; - struct rusage start; unsigned long timeout = 0; char buf[TASK_COMM_LEN] = {}; DEFINE_WAIT(wait); @@ -309,6 +331,7 @@ static int io_sq_thread(void *data) mutex_lock(&sqd->lock); while (1) { bool cap_entries, sqt_spin = false; + struct io_sq_time ist = { }; if (io_sqd_events_pending(sqd) || signal_pending(current)) { if (io_sqd_handle_event(sqd)) @@ -317,9 +340,8 @@ static int io_sq_thread(void *data) } cap_entries = !list_is_singular(&sqd->ctx_list); - getrusage(current, RUSAGE_SELF, &start); list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { - int ret = __io_sq_thread(ctx, cap_entries); + int ret = __io_sq_thread(ctx, sqd, cap_entries, &ist); if (!sqt_spin && (ret > 0 || !wq_list_empty(&ctx->iopoll_list))) sqt_spin = true; @@ -327,15 +349,18 @@ static int io_sq_thread(void *data) if (io_sq_tw(&retry_list, IORING_TW_CAP_ENTRIES_VALUE)) sqt_spin = true; - list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) - if (io_napi(ctx)) + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { + if (io_napi(ctx)) { + io_sq_start_worktime(&ist); io_napi_sqpoll_busy_poll(ctx); + } + } + + io_sq_update_worktime(sqd, &ist); if (sqt_spin || !time_after(jiffies, timeout)) { - if (sqt_spin) { - io_sq_update_worktime(sqd, &start); + if (sqt_spin) timeout = jiffies + sqd->sq_thread_idle; - } if (unlikely(need_resched())) { mutex_unlock(&sqd->lock); cond_resched(); diff --git a/io_uring/sqpoll.h b/io_uring/sqpoll.h index b83dcdec9765..fd2f6f29b516 100644 --- a/io_uring/sqpoll.h +++ b/io_uring/sqpoll.h @@ -29,6 +29,7 @@ void io_sq_thread_unpark(struct io_sq_data *sqd); void io_put_sq_data(struct io_sq_data *sqd); void io_sqpoll_wait_sq(struct io_ring_ctx *ctx); int io_sqpoll_wq_cpu_affinity(struct io_ring_ctx *ctx, cpumask_var_t mask); +u64 io_sq_cpu_usec(struct task_struct *tsk); static inline struct task_struct *sqpoll_task_locked(struct io_sq_data *sqd) { diff --git a/io_uring/waitid.c b/io_uring/waitid.c index f25110fb1b12..53532ae6256c 100644 --- a/io_uring/waitid.c +++ b/io_uring/waitid.c @@ -250,7 +250,7 @@ int io_waitid_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EINVAL; iwa = io_uring_alloc_async_data(NULL, req); - if (!unlikely(iwa)) + if (unlikely(!iwa)) return -ENOMEM; iwa->req = req; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 6ae5f48cf64e..fdee387f0d6b 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5892,7 +5892,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name, * if the parent has to be frozen, the child has too. */ cgrp->freezer.e_freeze = parent->freezer.e_freeze; - seqcount_init(&cgrp->freezer.freeze_seq); + seqcount_spinlock_init(&cgrp->freezer.freeze_seq, &css_set_lock); if (cgrp->freezer.e_freeze) { /* * Set the CGRP_FREEZE flag, so when a process will be diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 1e5c64cb6a42..138ede653de4 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -23,6 +23,7 @@ #include <linux/ctype.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/swiotlb.h> #include <asm/sections.h> #include "debug.h" @@ -594,7 +595,9 @@ static void add_dma_entry(struct dma_debug_entry *entry, unsigned long attrs) if (rc == -ENOMEM) { pr_err_once("cacheline tracking ENOMEM, dma-debug disabled\n"); global_disable = true; - } else if (rc == -EEXIST && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) { + } else if (rc == -EEXIST && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) && + !(IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && + is_swiotlb_active(entry->dev))) { err_printk(entry->dev, entry, "cacheline tracking EEXIST, overlapping mappings aren't supported\n"); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 1f5d07067f60..361f9101cef9 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -3740,11 +3740,9 @@ static inline int mm_cid_get(struct rq *rq, struct task_struct *t, struct mm_struct *mm) { struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid; - struct cpumask *cpumask; int cid; lockdep_assert_rq_held(rq); - cpumask = mm_cidmask(mm); cid = __this_cpu_read(pcpu_cid->cid); if (mm_cid_is_valid(cid)) { mm_cid_snapshot_time(rq, mm); diff --git a/kernel/trace/rv/monitors/pagefault/Kconfig b/kernel/trace/rv/monitors/pagefault/Kconfig index 5e16625f1653..0e013f00c33b 100644 --- a/kernel/trace/rv/monitors/pagefault/Kconfig +++ b/kernel/trace/rv/monitors/pagefault/Kconfig @@ -5,6 +5,7 @@ config RV_MON_PAGEFAULT select RV_LTL_MONITOR depends on RV_MON_RTAPP depends on X86 || RISCV + depends on MMU default y select LTL_MON_EVENTS_ID bool "pagefault monitor" diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index 48338520376f..43e9ea473cda 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -501,7 +501,7 @@ static void *enabled_monitors_next(struct seq_file *m, void *p, loff_t *pos) list_for_each_entry_continue(mon, &rv_monitors_list, list) { if (mon->enabled) - return mon; + return &mon->list; } return NULL; @@ -509,7 +509,7 @@ static void *enabled_monitors_next(struct seq_file *m, void *p, loff_t *pos) static void *enabled_monitors_start(struct seq_file *m, loff_t *pos) { - struct rv_monitor *mon; + struct list_head *head; loff_t l; mutex_lock(&rv_interface_lock); @@ -517,15 +517,15 @@ static void *enabled_monitors_start(struct seq_file *m, loff_t *pos) if (list_empty(&rv_monitors_list)) return NULL; - mon = list_entry(&rv_monitors_list, struct rv_monitor, list); + head = &rv_monitors_list; for (l = 0; l <= *pos; ) { - mon = enabled_monitors_next(m, mon, &l); - if (!mon) + head = enabled_monitors_next(m, head, &l); + if (!head) break; } - return mon; + return head; } /* diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig index eea17e36a22b..8886055e938f 100644 --- a/lib/crypto/Kconfig +++ b/lib/crypto/Kconfig @@ -97,7 +97,7 @@ config CRYPTO_LIB_POLY1305 config CRYPTO_LIB_POLY1305_ARCH bool - depends on CRYPTO_LIB_POLY1305 && !UML + depends on CRYPTO_LIB_POLY1305 && !UML && !KMSAN default y if ARM default y if ARM64 && KERNEL_MODE_NEON default y if MIPS diff --git a/mm/damon/core.c b/mm/damon/core.c index 93848b4c6944..109b050c795a 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -452,6 +452,9 @@ void damon_destroy_scheme(struct damos *s) damos_for_each_filter_safe(f, next, s) damos_destroy_filter(f); + damos_for_each_ops_filter_safe(f, next, s) + damos_destroy_filter(f); + kfree(s->migrate_dests.node_id_arr); kfree(s->migrate_dests.weight_arr); damon_del_scheme(s); @@ -832,7 +835,7 @@ int damos_commit_quota_goals(struct damos_quota *dst, struct damos_quota *src) src_goal->metric, src_goal->target_value); if (!new_goal) return -ENOMEM; - damos_commit_quota_goal_union(new_goal, src_goal); + damos_commit_quota_goal(new_goal, src_goal); damos_add_quota_goal(dst, new_goal); } return 0; @@ -1450,7 +1453,7 @@ int damon_call(struct damon_ctx *ctx, struct damon_call_control *control) INIT_LIST_HEAD(&control->list); mutex_lock(&ctx->call_controls_lock); - list_add_tail(&ctx->call_controls, &control->list); + list_add_tail(&control->list, &ctx->call_controls); mutex_unlock(&ctx->call_controls_lock); if (!damon_is_running(ctx)) return -EINVAL; diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index 2fc722f998f8..cd6815ecc04e 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -1473,13 +1473,14 @@ static int damon_sysfs_commit_input(void *data) if (IS_ERR(param_ctx)) return PTR_ERR(param_ctx); test_ctx = damon_new_ctx(); + if (!test_ctx) + return -ENOMEM; err = damon_commit_ctx(test_ctx, param_ctx); - if (err) { - damon_destroy_ctx(test_ctx); + if (err) goto out; - } err = damon_commit_ctx(kdamond->damon_ctx, param_ctx); out: + damon_destroy_ctx(test_ctx); damon_destroy_ctx(param_ctx); return err; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1b81680b4225..1d1b74950332 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -4109,6 +4109,9 @@ static bool thp_underused(struct folio *folio) if (khugepaged_max_ptes_none == HPAGE_PMD_NR - 1) return false; + if (folio_contain_hwpoisoned_page(folio)) + return false; + for (i = 0; i < folio_nr_pages(folio); i++) { if (pages_identical(folio_page(folio, i), ZERO_PAGE(0))) { if (++num_zero_pages > khugepaged_max_ptes_none) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 795ee393eac0..0455119716ec 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7614,13 +7614,12 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); - i_mmap_assert_write_locked(vma->vm_file->f_mapping); - hugetlb_vma_assert_locked(vma); if (sz != PMD_SIZE) return 0; if (!ptdesc_pmd_is_shared(virt_to_ptdesc(ptep))) return 0; - + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + hugetlb_vma_assert_locked(vma); pud_clear(pud); /* * Once our caller drops the rmap lock, some other process might be diff --git a/mm/migrate.c b/mm/migrate.c index e3065c9edb55..c0e9f15be2a2 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -301,8 +301,9 @@ static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw, struct page *page = folio_page(folio, idx); pte_t newpte; - if (PageCompound(page)) + if (PageCompound(page) || PageHWPoison(page)) return false; + VM_BUG_ON_PAGE(!PageAnon(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(pte_present(old_pte), page); diff --git a/mm/mremap.c b/mm/mremap.c index 35de0a7b910e..bd7314898ec5 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1237,10 +1237,10 @@ static int copy_vma_and_data(struct vma_remap_struct *vrm, } /* - * Perform final tasks for MADV_DONTUNMAP operation, clearing mlock() and - * account flags on remaining VMA by convention (it cannot be mlock()'d any - * longer, as pages in range are no longer mapped), and removing anon_vma_chain - * links from it (if the entire VMA was copied over). + * Perform final tasks for MADV_DONTUNMAP operation, clearing mlock() flag on + * remaining VMA by convention (it cannot be mlock()'d any longer, as pages in + * range are no longer mapped), and removing anon_vma_chain links from it if the + * entire VMA was copied over. */ static void dontunmap_complete(struct vma_remap_struct *vrm, struct vm_area_struct *new_vma) @@ -1250,11 +1250,8 @@ static void dontunmap_complete(struct vma_remap_struct *vrm, unsigned long old_start = vrm->vma->vm_start; unsigned long old_end = vrm->vma->vm_end; - /* - * We always clear VM_LOCKED[ONFAULT] | VM_ACCOUNT on the old - * vma. - */ - vm_flags_clear(vrm->vma, VM_LOCKED_MASK | VM_ACCOUNT); + /* We always clear VM_LOCKED[ONFAULT] on the old VMA. */ + vm_flags_clear(vrm->vma, VM_LOCKED_MASK); /* * anon_vma links of the old vma is no longer needed after its page diff --git a/mm/page_owner.c b/mm/page_owner.c index c3ca21132c2c..589ec37c94aa 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -168,6 +168,9 @@ static void add_stack_record_to_list(struct stack_record *stack_record, unsigned long flags; struct stack *stack; + if (!gfpflags_allow_spinning(gfp_mask)) + return; + set_current_in_page_owner(); stack = kmalloc(sizeof(*stack), gfp_nested_mask(gfp_mask)); if (!stack) { diff --git a/mm/slub.c b/mm/slub.c index a8fcc7e6f25a..d4367f25b20d 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2052,9 +2052,9 @@ static inline void mark_objexts_empty(struct slabobj_ext *obj_exts) } } -static inline void mark_failed_objexts_alloc(struct slab *slab) +static inline bool mark_failed_objexts_alloc(struct slab *slab) { - slab->obj_exts = OBJEXTS_ALLOC_FAIL; + return cmpxchg(&slab->obj_exts, 0, OBJEXTS_ALLOC_FAIL) == 0; } static inline void handle_failed_objexts_alloc(unsigned long obj_exts, @@ -2076,7 +2076,7 @@ static inline void handle_failed_objexts_alloc(unsigned long obj_exts, #else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ static inline void mark_objexts_empty(struct slabobj_ext *obj_exts) {} -static inline void mark_failed_objexts_alloc(struct slab *slab) {} +static inline bool mark_failed_objexts_alloc(struct slab *slab) { return false; } static inline void handle_failed_objexts_alloc(unsigned long obj_exts, struct slabobj_ext *vec, unsigned int objects) {} @@ -2124,8 +2124,14 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, slab_nid(slab)); } if (!vec) { - /* Mark vectors which failed to allocate */ - mark_failed_objexts_alloc(slab); + /* + * Try to mark vectors which failed to allocate. + * If this operation fails, there may be a racing process + * that has already completed the allocation. + */ + if (!mark_failed_objexts_alloc(slab) && + slab_obj_exts(slab)) + return 0; return -ENOMEM; } @@ -2136,6 +2142,7 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, #ifdef CONFIG_MEMCG new_exts |= MEMCG_DATA_OBJEXTS; #endif +retry: old_exts = READ_ONCE(slab->obj_exts); handle_failed_objexts_alloc(old_exts, vec, objects); if (new_slab) { @@ -2145,8 +2152,7 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, * be simply assigned. */ slab->obj_exts = new_exts; - } else if ((old_exts & ~OBJEXTS_FLAGS_MASK) || - cmpxchg(&slab->obj_exts, old_exts, new_exts) != old_exts) { + } else if (old_exts & ~OBJEXTS_FLAGS_MASK) { /* * If the slab is already in use, somebody can allocate and * assign slabobj_exts in parallel. In this case the existing @@ -2158,6 +2164,9 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, else kfree(vec); return 0; + } else if (cmpxchg(&slab->obj_exts, old_exts, new_exts) != old_exts) { + /* Retry if a racing thread changed slab->obj_exts from under us. */ + goto retry; } if (allow_spin) @@ -3419,7 +3428,6 @@ static void *alloc_single_from_new_slab(struct kmem_cache *s, struct slab *slab, if (!allow_spin && !spin_trylock_irqsave(&n->list_lock, flags)) { /* Unlucky, discard newly allocated slab */ - slab->frozen = 1; defer_deactivate_slab(slab, NULL); return NULL; } @@ -6468,9 +6476,12 @@ static void free_deferred_objects(struct irq_work *work) struct slab *slab = container_of(pos, struct slab, llnode); #ifdef CONFIG_SLUB_TINY - discard_slab(slab->slab_cache, slab); + free_slab(slab->slab_cache, slab); #else - deactivate_slab(slab->slab_cache, slab, slab->flush_freelist); + if (slab->frozen) + deactivate_slab(slab->slab_cache, slab, slab->flush_freelist); + else + free_slab(slab->slab_cache, slab); #endif } } diff --git a/net/core/datagram.c b/net/core/datagram.c index cb4b9ef2e4e3..c285c6465923 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -920,21 +920,22 @@ fault: EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg); /** - * datagram_poll - generic datagram poll + * datagram_poll_queue - same as datagram_poll, but on a specific receive + * queue * @file: file struct * @sock: socket * @wait: poll table + * @rcv_queue: receive queue to poll * - * Datagram poll: Again totally generic. This also handles - * sequenced packet sockets providing the socket receive queue - * is only ever holding data ready to receive. + * Performs polling on the given receive queue, handling shutdown, error, + * and connection state. This is useful for protocols that deliver + * userspace-bound packets through a custom queue instead of + * sk->sk_receive_queue. * - * Note: when you *don't* use this routine for this protocol, - * and you use a different write policy from sock_writeable() - * then please supply your own write_space callback. + * Return: poll bitmask indicating the socket's current state */ -__poll_t datagram_poll(struct file *file, struct socket *sock, - poll_table *wait) +__poll_t datagram_poll_queue(struct file *file, struct socket *sock, + poll_table *wait, struct sk_buff_head *rcv_queue) { struct sock *sk = sock->sk; __poll_t mask; @@ -956,7 +957,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, mask |= EPOLLHUP; /* readable? */ - if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(rcv_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ @@ -978,4 +979,27 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, return mask; } +EXPORT_SYMBOL(datagram_poll_queue); + +/** + * datagram_poll - generic datagram poll + * @file: file struct + * @sock: socket + * @wait: poll table + * + * Datagram poll: Again totally generic. This also handles + * sequenced packet sockets providing the socket receive queue + * is only ever holding data ready to receive. + * + * Note: when you *don't* use this routine for this protocol, + * and you use a different write policy from sock_writeable() + * then please supply your own write_space callback. + * + * Return: poll bitmask indicating the socket's current state + */ +__poll_t datagram_poll(struct file *file, struct socket *sock, poll_table *wait) +{ + return datagram_poll_queue(file, sock, wait, + &sock->sk->sk_receive_queue); +} EXPORT_SYMBOL(datagram_poll); diff --git a/net/core/gro.c b/net/core/gro.c index 5ba4504cfd28..76f9c3712422 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -639,6 +639,8 @@ EXPORT_SYMBOL(gro_receive_skb); static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) { + struct skb_shared_info *shinfo; + if (unlikely(skb->pfmemalloc)) { consume_skb(skb); return; @@ -655,8 +657,12 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->encapsulation = 0; skb->ip_summed = CHECKSUM_NONE; - skb_shinfo(skb)->gso_type = 0; - skb_shinfo(skb)->gso_size = 0; + + shinfo = skb_shinfo(skb); + shinfo->gso_type = 0; + shinfo->gso_size = 0; + shinfo->hwtstamps.hwtstamp = 0; + if (unlikely(skb->slow_gro)) { skb_orphan(skb); skb_ext_reset(skb); diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index b43911562f4d..fd57b845de33 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -43,12 +43,11 @@ drop: if (skb_queue_len(&cell->napi_skbs) == 1) napi_schedule(&cell->napi); - if (have_bh_lock) - local_unlock_nested_bh(&gcells->cells->bh_lock); - res = NET_RX_SUCCESS; unlock: + if (have_bh_lock) + local_unlock_nested_bh(&gcells->cells->bh_lock); rcu_read_unlock(); return res; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 8040ff7c356e..576d5ec3bb36 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4715,9 +4715,6 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, int err; u16 vid; - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - if (!del_bulk) { err = nlmsg_parse_deprecated(nlh, sizeof(*ndm), tb, NDA_MAX, NULL, extack); diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index b120470246cc..c96b63adf96f 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -34,12 +34,18 @@ static int hsr_newlink(struct net_device *dev, struct netlink_ext_ack *extack) { struct net *link_net = rtnl_newlink_link_net(params); + struct net_device *link[2], *interlink = NULL; struct nlattr **data = params->data; enum hsr_version proto_version; unsigned char multicast_spec; u8 proto = HSR_PROTOCOL_HSR; - struct net_device *link[2], *interlink = NULL; + if (!net_eq(link_net, dev_net(dev))) { + NL_SET_ERR_MSG_MOD(extack, + "HSR slaves/interlink must be on the same net namespace than HSR link"); + return -EINVAL; + } + if (!data) { NL_SET_ERR_MSG_MOD(extack, "No slave devices specified"); return -EINVAL; diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index e0f44dc232aa..2ae95476dba3 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -370,6 +370,10 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) } subflow: + /* No need to try establishing subflows to remote id0 if not allowed */ + if (mptcp_pm_add_addr_c_flag_case(msk)) + goto exit; + /* check if should create a new subflow */ while (msk->pm.local_addr_used < endp_subflow_max && msk->pm.extra_subflows < limit_extra_subflows) { @@ -401,6 +405,8 @@ subflow: __mptcp_subflow_connect(sk, &local, &addrs[i]); spin_lock_bh(&msk->pm.lock); } + +exit: mptcp_pm_nl_check_work_pending(msk); } diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 5c1652181805..f5a7d5a38755 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -169,13 +169,14 @@ next_chunk: chunk->head_skb = chunk->skb; /* skbs with "cover letter" */ - if (chunk->head_skb && chunk->skb->data_len == chunk->skb->len) + if (chunk->head_skb && chunk->skb->data_len == chunk->skb->len) { + if (WARN_ON(!skb_shinfo(chunk->skb)->frag_list)) { + __SCTP_INC_STATS(dev_net(chunk->skb->dev), + SCTP_MIB_IN_PKT_DISCARDS); + sctp_chunk_free(chunk); + goto next_chunk; + } chunk->skb = skb_shinfo(chunk->skb)->frag_list; - - if (WARN_ON(!chunk->skb)) { - __SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS); - sctp_chunk_free(chunk); - goto next_chunk; } } diff --git a/net/smc/smc_inet.c b/net/smc/smc_inet.c index a944e7dcb8b9..a94084b4a498 100644 --- a/net/smc/smc_inet.c +++ b/net/smc/smc_inet.c @@ -56,7 +56,6 @@ static struct inet_protosw smc_inet_protosw = { .protocol = IPPROTO_SMC, .prot = &smc_inet_prot, .ops = &smc_inet_stream_ops, - .flags = INET_PROTOSW_ICSK, }; #if IS_ENABLED(CONFIG_IPV6) @@ -104,27 +103,15 @@ static struct inet_protosw smc_inet6_protosw = { .protocol = IPPROTO_SMC, .prot = &smc_inet6_prot, .ops = &smc_inet6_stream_ops, - .flags = INET_PROTOSW_ICSK, }; #endif /* CONFIG_IPV6 */ -static unsigned int smc_sync_mss(struct sock *sk, u32 pmtu) -{ - /* No need pass it through to clcsock, mss can always be set by - * sock_create_kern or smc_setsockopt. - */ - return 0; -} - static int smc_inet_init_sock(struct sock *sk) { struct net *net = sock_net(sk); /* init common smc sock */ smc_sk_init(net, sk, IPPROTO_SMC); - - inet_csk(sk)->icsk_sync_mss = smc_sync_mss; - /* create clcsock */ return smc_create_clcsk(net, sk, sk->sk_family); } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 4c2db6cca557..76763247a377 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -487,12 +487,26 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) goto err; } - if (vsk->transport) { - if (vsk->transport == new_transport) { - ret = 0; - goto err; - } + if (vsk->transport && vsk->transport == new_transport) { + ret = 0; + goto err; + } + /* We increase the module refcnt to prevent the transport unloading + * while there are open sockets assigned to it. + */ + if (!new_transport || !try_module_get(new_transport->module)) { + ret = -ENODEV; + goto err; + } + + /* It's safe to release the mutex after a successful try_module_get(). + * Whichever transport `new_transport` points at, it won't go away until + * the last module_put() below or in vsock_deassign_transport(). + */ + mutex_unlock(&vsock_register_mutex); + + if (vsk->transport) { /* transport->release() must be called with sock lock acquired. * This path can only be taken during vsock_connect(), where we * have already held the sock lock. In the other cases, this @@ -512,20 +526,6 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) vsk->peer_shutdown = 0; } - /* We increase the module refcnt to prevent the transport unloading - * while there are open sockets assigned to it. - */ - if (!new_transport || !try_module_get(new_transport->module)) { - ret = -ENODEV; - goto err; - } - - /* It's safe to release the mutex after a successful try_module_get(). - * Whichever transport `new_transport` points at, it won't go away until - * the last module_put() below or in vsock_deassign_transport(). - */ - mutex_unlock(&vsock_register_mutex); - if (sk->sk_type == SOCK_SEQPACKET) { if (!new_transport->seqpacket_allow || !new_transport->seqpacket_allow(remote_cid)) { diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index fc7a603b04f1..bf744ac9d5a7 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -555,14 +555,10 @@ static void espintcp_close(struct sock *sk, long timeout) static __poll_t espintcp_poll(struct file *file, struct socket *sock, poll_table *wait) { - __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; struct espintcp_ctx *ctx = espintcp_getctx(sk); - if (!skb_queue_empty(&ctx->ike_queue)) - mask |= EPOLLIN | EPOLLRDNORM; - - return mask; + return datagram_poll_queue(file, sock, wait, &ctx->ike_queue); } static void build_protos(struct proto *espintcp_prot, diff --git a/rust/kernel/auxiliary.rs b/rust/kernel/auxiliary.rs index e11848bbf206..7a3b0b9c418e 100644 --- a/rust/kernel/auxiliary.rs +++ b/rust/kernel/auxiliary.rs @@ -217,13 +217,7 @@ impl<Ctx: device::DeviceContext> Device<Ctx> { /// Returns a reference to the parent [`device::Device`], if any. pub fn parent(&self) -> Option<&device::Device> { - let ptr: *const Self = self; - // CAST: `Device<Ctx: DeviceContext>` types are transparent to each other. - let ptr: *const Device = ptr.cast(); - // SAFETY: `ptr` was derived from `&self`. - let this = unsafe { &*ptr }; - - this.as_ref().parent() + self.as_ref().parent() } } diff --git a/rust/kernel/device.rs b/rust/kernel/device.rs index 1321e6f0b53c..a849b7dde2fd 100644 --- a/rust/kernel/device.rs +++ b/rust/kernel/device.rs @@ -251,7 +251,7 @@ impl<Ctx: DeviceContext> Device<Ctx> { /// Returns a reference to the parent device, if any. #[cfg_attr(not(CONFIG_AUXILIARY_BUS), expect(dead_code))] - pub(crate) fn parent(&self) -> Option<&Self> { + pub(crate) fn parent(&self) -> Option<&Device> { // SAFETY: // - By the type invariant `self.as_raw()` is always valid. // - The parent device is only ever set at device creation. @@ -264,7 +264,7 @@ impl<Ctx: DeviceContext> Device<Ctx> { // - Since `parent` is not NULL, it must be a valid pointer to a `struct device`. // - `parent` is valid for the lifetime of `self`, since a `struct device` holds a // reference count of its parent. - Some(unsafe { Self::from_raw(parent) }) + Some(unsafe { Device::from_raw(parent) }) } } diff --git a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h index 9dc90a1b386d..7ab2824ed7b5 100644 --- a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h +++ b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h @@ -25,6 +25,26 @@ static inline int values_close(long a, long b, int err) return labs(a - b) <= (a + b) / 100 * err; } +/* + * Checks if two given values differ by less than err% of their sum and assert + * with detailed debug info if not. + */ +static inline int values_close_report(long a, long b, int err) +{ + long diff = labs(a - b); + long limit = (a + b) / 100 * err; + double actual_err = (a + b) ? (100.0 * diff / (a + b)) : 0.0; + int close = diff <= limit; + + if (!close) + fprintf(stderr, + "[FAIL] actual=%ld expected=%ld | diff=%ld | limit=%ld | " + "tolerance=%d%% | actual_error=%.2f%%\n", + a, b, diff, limit, err, actual_err); + + return close; +} + extern ssize_t read_text(const char *path, char *buf, size_t max_len); extern ssize_t write_text(const char *path, char *buf, ssize_t len); diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c index 2a60e6c41940..d54e2317efff 100644 --- a/tools/testing/selftests/cgroup/test_cpu.c +++ b/tools/testing/selftests/cgroup/test_cpu.c @@ -219,7 +219,7 @@ static int test_cpucg_stats(const char *root) if (user_usec <= 0) goto cleanup; - if (!values_close(usage_usec, expected_usage_usec, 1)) + if (!values_close_report(usage_usec, expected_usage_usec, 1)) goto cleanup; ret = KSFT_PASS; @@ -291,7 +291,7 @@ static int test_cpucg_nice(const char *root) user_usec = cg_read_key_long(cpucg, "cpu.stat", "user_usec"); nice_usec = cg_read_key_long(cpucg, "cpu.stat", "nice_usec"); - if (!values_close(nice_usec, expected_nice_usec, 1)) + if (!values_close_report(nice_usec, expected_nice_usec, 1)) goto cleanup; ret = KSFT_PASS; @@ -404,7 +404,7 @@ overprovision_validate(const struct cpu_hogger *children, int num_children) goto cleanup; delta = children[i + 1].usage - children[i].usage; - if (!values_close(delta, children[0].usage, 35)) + if (!values_close_report(delta, children[0].usage, 35)) goto cleanup; } @@ -444,7 +444,7 @@ underprovision_validate(const struct cpu_hogger *children, int num_children) int ret = KSFT_FAIL, i; for (i = 0; i < num_children - 1; i++) { - if (!values_close(children[i + 1].usage, children[0].usage, 15)) + if (!values_close_report(children[i + 1].usage, children[0].usage, 15)) goto cleanup; } @@ -573,16 +573,16 @@ run_cpucg_nested_weight_test(const char *root, bool overprovisioned) nested_leaf_usage = leaf[1].usage + leaf[2].usage; if (overprovisioned) { - if (!values_close(leaf[0].usage, nested_leaf_usage, 15)) + if (!values_close_report(leaf[0].usage, nested_leaf_usage, 15)) goto cleanup; - } else if (!values_close(leaf[0].usage * 2, nested_leaf_usage, 15)) + } else if (!values_close_report(leaf[0].usage * 2, nested_leaf_usage, 15)) goto cleanup; child_usage = cg_read_key_long(child, "cpu.stat", "usage_usec"); if (child_usage <= 0) goto cleanup; - if (!values_close(child_usage, nested_leaf_usage, 1)) + if (!values_close_report(child_usage, nested_leaf_usage, 1)) goto cleanup; ret = KSFT_PASS; @@ -691,7 +691,7 @@ static int test_cpucg_max(const char *root) expected_usage_usec = n_periods * quota_usec + MIN(remainder_usec, quota_usec); - if (!values_close(usage_usec, expected_usage_usec, 10)) + if (!values_close_report(usage_usec, expected_usage_usec, 10)) goto cleanup; ret = KSFT_PASS; @@ -762,7 +762,7 @@ static int test_cpucg_max_nested(const char *root) expected_usage_usec = n_periods * quota_usec + MIN(remainder_usec, quota_usec); - if (!values_close(usage_usec, expected_usage_usec, 10)) + if (!values_close_report(usage_usec, expected_usage_usec, 10)) goto cleanup; ret = KSFT_PASS; diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index c90d8e8b95cb..78a1aa4ecff2 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -2324,7 +2324,7 @@ laminar_endp_tests() { # no laminar endpoints: routing rules are used if reset_with_tcp_filter "without a laminar endpoint" ns1 10.0.2.2 REJECT && - mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then + continue_if mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal @@ -2336,7 +2336,7 @@ laminar_endp_tests() # laminar endpoints: this endpoint is used if reset_with_tcp_filter "with a laminar endpoint" ns1 10.0.2.2 REJECT && - mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then + continue_if mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal @@ -2348,7 +2348,7 @@ laminar_endp_tests() # laminar endpoints: these endpoints are used if reset_with_tcp_filter "with multiple laminar endpoints" ns1 10.0.2.2 REJECT && - mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then + continue_if mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal @@ -2363,7 +2363,7 @@ laminar_endp_tests() # laminar endpoints: only one endpoint is used if reset_with_tcp_filter "single laminar endpoint" ns1 10.0.2.2 REJECT && - mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then + continue_if mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal @@ -2376,7 +2376,7 @@ laminar_endp_tests() # laminar endpoints: subflow and laminar flags if reset_with_tcp_filter "sublow + laminar endpoints" ns1 10.0.2.2 REJECT && - mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then + continue_if mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then pm_nl_set_limits $ns1 0 4 pm_nl_set_limits $ns2 2 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal @@ -3939,7 +3939,7 @@ endpoint_tests() # subflow_rebuild_header is needed to support the implicit flag # userspace pm type prevents add_addr if reset "implicit EP" && - mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 2 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal @@ -3964,7 +3964,7 @@ endpoint_tests() fi if reset_with_tcp_filter "delete and re-add" ns2 10.0.3.2 REJECT OUTPUT && - mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then start_events pm_nl_set_limits $ns1 0 3 pm_nl_set_limits $ns2 0 3 @@ -4040,7 +4040,7 @@ endpoint_tests() # remove and re-add if reset_with_events "delete re-add signal" && - mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=0 pm_nl_set_limits $ns1 0 3 pm_nl_set_limits $ns2 3 3 @@ -4115,7 +4115,7 @@ endpoint_tests() # flush and re-add if reset_with_tcp_filter "flush re-add" ns2 10.0.3.2 REJECT OUTPUT && - mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 1 2 # broadcast IP: no packet for this address will be received on ns1 diff --git a/tools/testing/selftests/net/sctp_hello.c b/tools/testing/selftests/net/sctp_hello.c index f02f1f95d227..a04dac0b8027 100644 --- a/tools/testing/selftests/net/sctp_hello.c +++ b/tools/testing/selftests/net/sctp_hello.c @@ -29,7 +29,6 @@ static void set_addr(struct sockaddr_storage *ss, char *ip, char *port, int *len static int do_client(int argc, char *argv[]) { struct sockaddr_storage ss; - char buf[] = "hello"; int csk, ret, len; if (argc < 5) { @@ -56,16 +55,10 @@ static int do_client(int argc, char *argv[]) set_addr(&ss, argv[3], argv[4], &len); ret = connect(csk, (struct sockaddr *)&ss, len); - if (ret < 0) { - printf("failed to connect to peer\n"); + if (ret < 0) return -1; - } - ret = send(csk, buf, strlen(buf) + 1, 0); - if (ret < 0) { - printf("failed to send msg %d\n", ret); - return -1; - } + recv(csk, NULL, 0, 0); close(csk); return 0; @@ -75,7 +68,6 @@ int main(int argc, char *argv[]) { struct sockaddr_storage ss; int lsk, csk, ret, len; - char buf[20]; if (argc < 2 || (strcmp(argv[1], "server") && strcmp(argv[1], "client"))) { printf("%s server|client ...\n", argv[0]); @@ -125,11 +117,6 @@ int main(int argc, char *argv[]) return -1; } - ret = recv(csk, buf, sizeof(buf), 0); - if (ret <= 0) { - printf("failed to recv msg %d\n", ret); - return -1; - } close(csk); close(lsk); diff --git a/tools/testing/selftests/net/sctp_vrf.sh b/tools/testing/selftests/net/sctp_vrf.sh index c854034b6aa1..667b211aa8a1 100755 --- a/tools/testing/selftests/net/sctp_vrf.sh +++ b/tools/testing/selftests/net/sctp_vrf.sh @@ -20,9 +20,9 @@ setup() { modprobe sctp_diag setup_ns CLIENT_NS1 CLIENT_NS2 SERVER_NS - ip net exec $CLIENT_NS1 sysctl -w net.ipv6.conf.default.accept_dad=0 2>&1 >/dev/null - ip net exec $CLIENT_NS2 sysctl -w net.ipv6.conf.default.accept_dad=0 2>&1 >/dev/null - ip net exec $SERVER_NS sysctl -w net.ipv6.conf.default.accept_dad=0 2>&1 >/dev/null + ip net exec $CLIENT_NS1 sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip net exec $CLIENT_NS2 sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip net exec $SERVER_NS sysctl -wq net.ipv6.conf.default.accept_dad=0 ip -n $SERVER_NS link add veth1 type veth peer name veth1 netns $CLIENT_NS1 ip -n $SERVER_NS link add veth2 type veth peer name veth1 netns $CLIENT_NS2 @@ -62,17 +62,40 @@ setup() { } cleanup() { - ip netns exec $SERVER_NS pkill sctp_hello 2>&1 >/dev/null + wait_client $CLIENT_NS1 + wait_client $CLIENT_NS2 + stop_server cleanup_ns $CLIENT_NS1 $CLIENT_NS2 $SERVER_NS } -wait_server() { +start_server() { local IFACE=$1 local CNT=0 - until ip netns exec $SERVER_NS ss -lS src $SERVER_IP:$SERVER_PORT | \ - grep LISTEN | grep "$IFACE" 2>&1 >/dev/null; do - [ $((CNT++)) = "20" ] && { RET=3; return $RET; } + ip netns exec $SERVER_NS ./sctp_hello server $AF $SERVER_IP $SERVER_PORT $IFACE & + disown + until ip netns exec $SERVER_NS ss -SlH | grep -q "$IFACE"; do + [ $((CNT++)) -eq 30 ] && { RET=3; return $RET; } + sleep 0.1 + done +} + +stop_server() { + local CNT=0 + + ip netns exec $SERVER_NS pkill sctp_hello + while ip netns exec $SERVER_NS ss -SaH | grep -q .; do + [ $((CNT++)) -eq 30 ] && break + sleep 0.1 + done +} + +wait_client() { + local CLIENT_NS=$1 + local CNT=0 + + while ip netns exec $CLIENT_NS ss -SaH | grep -q .; do + [ $((CNT++)) -eq 30 ] && break sleep 0.1 done } @@ -81,14 +104,12 @@ do_test() { local CLIENT_NS=$1 local IFACE=$2 - ip netns exec $SERVER_NS pkill sctp_hello 2>&1 >/dev/null - ip netns exec $SERVER_NS ./sctp_hello server $AF $SERVER_IP \ - $SERVER_PORT $IFACE 2>&1 >/dev/null & - disown - wait_server $IFACE || return $RET + start_server $IFACE || return $RET timeout 3 ip netns exec $CLIENT_NS ./sctp_hello client $AF \ - $SERVER_IP $SERVER_PORT $CLIENT_IP $CLIENT_PORT 2>&1 >/dev/null + $SERVER_IP $SERVER_PORT $CLIENT_IP $CLIENT_PORT RET=$? + wait_client $CLIENT_NS + stop_server return $RET } @@ -96,25 +117,21 @@ do_testx() { local IFACE1=$1 local IFACE2=$2 - ip netns exec $SERVER_NS pkill sctp_hello 2>&1 >/dev/null - ip netns exec $SERVER_NS ./sctp_hello server $AF $SERVER_IP \ - $SERVER_PORT $IFACE1 2>&1 >/dev/null & - disown - wait_server $IFACE1 || return $RET - ip netns exec $SERVER_NS ./sctp_hello server $AF $SERVER_IP \ - $SERVER_PORT $IFACE2 2>&1 >/dev/null & - disown - wait_server $IFACE2 || return $RET + start_server $IFACE1 || return $RET + start_server $IFACE2 || return $RET timeout 3 ip netns exec $CLIENT_NS1 ./sctp_hello client $AF \ - $SERVER_IP $SERVER_PORT $CLIENT_IP $CLIENT_PORT 2>&1 >/dev/null && \ + $SERVER_IP $SERVER_PORT $CLIENT_IP $CLIENT_PORT && \ timeout 3 ip netns exec $CLIENT_NS2 ./sctp_hello client $AF \ - $SERVER_IP $SERVER_PORT $CLIENT_IP $CLIENT_PORT 2>&1 >/dev/null + $SERVER_IP $SERVER_PORT $CLIENT_IP $CLIENT_PORT RET=$? + wait_client $CLIENT_NS1 + wait_client $CLIENT_NS2 + stop_server return $RET } testup() { - ip netns exec $SERVER_NS sysctl -w net.sctp.l3mdev_accept=1 2>&1 >/dev/null + ip netns exec $SERVER_NS sysctl -wq net.sctp.l3mdev_accept=1 echo -n "TEST 01: nobind, connect from client 1, l3mdev_accept=1, Y " do_test $CLIENT_NS1 || { echo "[FAIL]"; return $RET; } echo "[PASS]" @@ -123,7 +140,7 @@ testup() { do_test $CLIENT_NS2 && { echo "[FAIL]"; return $RET; } echo "[PASS]" - ip netns exec $SERVER_NS sysctl -w net.sctp.l3mdev_accept=0 2>&1 >/dev/null + ip netns exec $SERVER_NS sysctl -wq net.sctp.l3mdev_accept=0 echo -n "TEST 03: nobind, connect from client 1, l3mdev_accept=0, N " do_test $CLIENT_NS1 && { echo "[FAIL]"; return $RET; } echo "[PASS]" @@ -160,7 +177,7 @@ testup() { do_testx vrf-1 vrf-2 || { echo "[FAIL]"; return $RET; } echo "[PASS]" - echo -n "TEST 12: bind vrf-2 & 1 in server, connect from client 1 & 2, N " + echo -n "TEST 12: bind vrf-2 & 1 in server, connect from client 1 & 2, Y " do_testx vrf-2 vrf-1 || { echo "[FAIL]"; return $RET; } echo "[PASS]" } |