diff options
279 files changed, 3072 insertions, 1340 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 97007f4f69d4..f7f37de60b12 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -7573,6 +7573,10 @@ Kernel parameters See Documentation/admin-guide/mm/transhuge.rst for more details. + tlbi= [X86-64] + Format: {ipi} + ipi: switch to IPI-based TLB flushing + topology= [S390,EARLY] Format: {off | on} Specify if the kernel should make use of the cpu @@ -8158,6 +8162,11 @@ Kernel parameters q = USB_QUIRK_FORCE_ONE_CONFIG (Device claims zero configurations, forcing to 1); + r = USB_QUIRK_WINDOWS_CONFIG_REQ_SIZE (Device + fails during initialization when asked for + 9-bytes configuration descriptor request. + Ask for 255-bytes request instead to mirror + Windows' behavior); Example: quirks=0781:5580:bk,0a5c:5834:gij usbhid.mousepoll= diff --git a/Documentation/hwmon/hwmon-kernel-api.rst b/Documentation/hwmon/hwmon-kernel-api.rst index 1d7f1397a827..9fcde32a140d 100644 --- a/Documentation/hwmon/hwmon-kernel-api.rst +++ b/Documentation/hwmon/hwmon-kernel-api.rst @@ -85,9 +85,10 @@ removal. When using ``[devm_]hwmon_device_register_with_info()`` to register the hardware monitoring device, accesses using the associated access functions are serialised by the hardware monitoring core. If a driver needs locking -for other functions such as interrupt handlers or for attributes which are -fully implemented in the driver, hwmon_lock() and hwmon_unlock() can be used -to ensure that calls to those functions are serialized. +for other functions such as interrupt handlers, attributes which are fully +implemented in the driver, or debugfs functions, hwmon_lock() and hwmon_unlock() +can be used to ensure that calls to those functions are serialized. Those +functions also support guard() and scoped_guard() variants. Using devm_hwmon_device_register_with_info() -------------------------------------------- diff --git a/Documentation/sound/alsa-configuration.rst b/Documentation/sound/alsa-configuration.rst index 4b30cd63c5a5..78fb484e8b04 100644 --- a/Documentation/sound/alsa-configuration.rst +++ b/Documentation/sound/alsa-configuration.rst @@ -2389,6 +2389,18 @@ quirk_flags from snd_usb_handle_sync_urb. Instead fall through and enqueue a packet_info containing only size-0 packets, so the OUT ring keeps moving (emits silence). Needed by Behringer Flow 8 (1397:050c). + * bit 30: ``mixer_get_cur_broken`` + Some mixers are sticky, which means that setting their current volume + is a no-op, and reading the current volume returns a constant value. + The sticky check disables these mixers to prevent confusing userspace. + However, some devices do have a tunable volume despite the reported + current volume being constant. As the sticky check can't distinguish + between the two categories, setting this flag tells that the device + should fall into the second category when GET_CUR returns a constant + value, resulting in the sticky check being non-fatal and only + disabling GET_CUR instead of the whole mixer. The current volume will + then be provided by the internal cache that stores the last set + volume This module supports multiple devices, autoprobe and hotplugging. diff --git a/MAINTAINERS b/MAINTAINERS index f74da642290a..624cfb6cf1d4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10031,6 +10031,11 @@ F: drivers/base/firmware_loader/ F: rust/kernel/firmware.rs F: include/linux/firmware.h +FIXED-LAYOUT NVMEM LAYOUT DRIVER +M: Mathieu Dubois-Briand <mathieu.dubois-briand@bootlin.com> +S: Maintained +F: drivers/nvmem/layouts/fixed-layout.c + FLEXTIMER FTM-QUADDEC DRIVER M: Patrick Havelange <patrick.havelange@essensium.com> L: linux-iio@vger.kernel.org @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 7 PATCHLEVEL = 1 -SUBLEVEL = 8 +SUBLEVEL = 9 EXTRAVERSION = NAME = Baby Opossum Posse diff --git a/arch/arm/boot/dts/broadcom/bcm-ns.dtsi b/arch/arm/boot/dts/broadcom/bcm-ns.dtsi index 392a25713669..bd52de0faa3e 100644 --- a/arch/arm/boot/dts/broadcom/bcm-ns.dtsi +++ b/arch/arm/boot/dts/broadcom/bcm-ns.dtsi @@ -141,7 +141,7 @@ /* PCIe Controller 2 */ <0x00014000 0 &gic GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>, - <0x00014000 1 &gic GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>, + <0x00014000 1 &gic GIC_SPI 139 IRQ_TYPE_LEVEL_HIGH>, <0x00014000 2 &gic GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>, <0x00014000 3 &gic GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>, <0x00014000 4 &gic GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm/mach-npcm/platsmp.c b/arch/arm/mach-npcm/platsmp.c index 41891d3aa124..4c1fc9983746 100644 --- a/arch/arm/mach-npcm/platsmp.c +++ b/arch/arm/mach-npcm/platsmp.c @@ -32,6 +32,7 @@ static int npcm7xx_smp_boot_secondary(unsigned int cpu, goto out; } gcr_base = of_iomap(gcr_np, 0); + of_node_put(gcr_np); if (!gcr_base) { pr_err("could not iomap gcr"); ret = -ENOMEM; @@ -60,6 +61,7 @@ static void __init npcm7xx_smp_prepare_cpus(unsigned int max_cpus) return; } scu_base = of_iomap(scu_np, 0); + of_node_put(scu_np); if (!scu_base) { pr_err("could not iomap scu"); return; diff --git a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi index 761c59d90ffc..09ff5e9959d3 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi @@ -678,8 +678,6 @@ <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>, <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | - IRQ_TYPE_LEVEL_LOW)>, - <GIC_PPI 12 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>; }; diff --git a/arch/arm64/boot/dts/qcom/glymur.dtsi b/arch/arm64/boot/dts/qcom/glymur.dtsi index 63df60b7e010..25df2bd06735 100644 --- a/arch/arm64/boot/dts/qcom/glymur.dtsi +++ b/arch/arm64/boot/dts/qcom/glymur.dtsi @@ -1843,7 +1843,7 @@ spi0: spi@b80000 { compatible = "qcom,geni-spi"; reg = <0x0 0x00b80000 0x0 0x4000>; - interrupts = <GIC_SPI 1052 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 92 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S0_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -1870,7 +1870,7 @@ i2c1: i2c@b84000 { compatible = "qcom,geni-i2c"; reg = <0x0 0x00b84000 0x0 0x4000>; - interrupts = <GIC_SPI 1053 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 93 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S1_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -1897,7 +1897,7 @@ spi1: spi@b84000 { compatible = "qcom,geni-spi"; reg = <0x0 0x00b84000 0x0 0x4000>; - interrupts = <GIC_SPI 1053 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 93 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S1_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -1924,7 +1924,7 @@ i2c2: i2c@b88000 { compatible = "qcom,geni-i2c"; reg = <0x0 0x00b88000 0x0 0x4000>; - interrupts = <GIC_SPI 1054 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 94 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S2_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -1951,7 +1951,7 @@ spi2: spi@b88000 { compatible = "qcom,geni-spi"; reg = <0x0 0x00b88000 0x0 0x4000>; - interrupts = <GIC_SPI 1054 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 94 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S2_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -1978,7 +1978,7 @@ uart2: serial@b88000 { compatible = "qcom,geni-uart"; reg = <0x0 0x00b88000 0x0 0x4000>; - interrupts = <GIC_SPI 1054 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 94 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S2_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -2023,7 +2023,7 @@ spi3: spi@b8c000 { compatible = "qcom,geni-spi"; reg = <0x0 0x00b8c000 0x0 0x4000>; - interrupts = <GIC_SPI 1055 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 95 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S3_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -2077,7 +2077,7 @@ spi4: spi@b90000 { compatible = "qcom,geni-spi"; reg = <0x0 0x00b90000 0x0 0x4000>; - interrupts = <GIC_SPI 1056 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 96 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S4_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -2131,7 +2131,7 @@ spi5: spi@b94000 { compatible = "qcom,geni-spi"; reg = <0x0 0x00b94000 0x0 0x4000>; - interrupts = <GIC_SPI 1057 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 97 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S5_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -2158,7 +2158,7 @@ i2c6: i2c@b98000 { compatible = "qcom,geni-i2c"; reg = <0x0 0x00b98000 0x0 0x4000>; - interrupts = <GIC_SPI 1058 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 98 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S6_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -2185,7 +2185,7 @@ spi6: spi@b98000 { compatible = "qcom,geni-spi"; reg = <0x0 0x00b98000 0x0 0x4000>; - interrupts = <GIC_SPI 1058 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 98 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S6_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -2212,7 +2212,7 @@ i2c7: i2c@b9c000 { compatible = "qcom,geni-i2c"; reg = <0x0 0x00b9c000 0x0 0x4000>; - interrupts = <GIC_SPI 1059 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 99 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S7_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -2239,7 +2239,7 @@ spi7: spi@b9c000 { compatible = "qcom,geni-spi"; reg = <0x0 0x00b9c000 0x0 0x4000>; - interrupts = <GIC_SPI 1059 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 99 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_QUPV3_WRAP0_S7_CLK>; clock-names = "se"; interconnects = <&clk_virt MASTER_QUP_CORE_0 QCOM_ICC_TAG_ALWAYS @@ -5626,9 +5626,9 @@ pcie_smmu: iommu@15480000 { compatible = "arm,smmu-v3"; reg = <0x0 0x15480000 0x0 0x20000>; - interrupts = <GIC_SPI 964 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 962 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 960 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_ESPI 4 IRQ_TYPE_LEVEL_HIGH>, + <GIC_ESPI 2 IRQ_TYPE_LEVEL_HIGH>, + <GIC_ESPI 0 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "eventq", "cmdq-sync", "gerror"; dma-coherent; #iommu-cells = <1>; diff --git a/arch/arm64/boot/dts/qcom/monaco.dtsi b/arch/arm64/boot/dts/qcom/monaco.dtsi index fa13210fc539..62e6b60087ee 100644 --- a/arch/arm64/boot/dts/qcom/monaco.dtsi +++ b/arch/arm64/boot/dts/qcom/monaco.dtsi @@ -7384,6 +7384,7 @@ interrupt-controller; #redistributor-regions = <1>; redistributor-stride = <0x0 0x20000>; + #address-cells = <0>; }; watchdog@17c10000 { diff --git a/arch/arm64/boot/dts/qcom/purwa.dtsi b/arch/arm64/boot/dts/qcom/purwa.dtsi index 9ab4f26b35f2..5b17840fb62f 100644 --- a/arch/arm64/boot/dts/qcom/purwa.dtsi +++ b/arch/arm64/boot/dts/qcom/purwa.dtsi @@ -47,6 +47,8 @@ &gpu { compatible = "qcom,adreno-43030c00", "qcom,adreno"; + iommus = <&adreno_smmu 0 0x0>; + nvmem-cells = <&gpu_speed_bin>; nvmem-cell-names = "speed_bin"; diff --git a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts index e41200839dbe..8cdaef5360d1 100644 --- a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts +++ b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts @@ -347,6 +347,10 @@ status = "okay"; }; +&cluster_sleep_0 { + arm,psci-suspend-param = <0x41008244>; +}; + &gcc { protected-clocks = <GCC_QSPI_CORE_CLK>, <GCC_QSPI_CORE_CLK_SRC>, diff --git a/arch/arm64/boot/dts/qcom/sm8650.dtsi b/arch/arm64/boot/dts/qcom/sm8650.dtsi index e2d98cf6adca..ecfa3478cbdd 100644 --- a/arch/arm64/boot/dts/qcom/sm8650.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8650.dtsi @@ -7091,8 +7091,8 @@ ranges = <0 0 0x14680000 0x2c000>; - ipa_modem_tables: modem-tables@8000 { - reg = <0x8000 0x2000>; + ipa_modem_tables: modem-tables@3000 { + reg = <0x3000 0x2000>; }; }; diff --git a/arch/arm64/include/asm/ptdump.h b/arch/arm64/include/asm/ptdump.h index baff24004459..fded5358641f 100644 --- a/arch/arm64/include/asm/ptdump.h +++ b/arch/arm64/include/asm/ptdump.h @@ -7,8 +7,6 @@ #include <linux/ptdump.h> -DECLARE_STATIC_KEY_FALSE(arm64_ptdump_lock_key); - #ifdef CONFIG_PTDUMP #include <linux/mm_types.h> diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 92fedf4db927..09fd9da4eeed 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -49,8 +49,6 @@ #define NO_CONT_MAPPINGS BIT(1) #define NO_EXEC_MAPPINGS BIT(2) /* assumes FEAT_HPDS is not used */ -DEFINE_STATIC_KEY_FALSE(arm64_ptdump_lock_key); - u64 kimage_voffset __ro_after_init; EXPORT_SYMBOL(kimage_voffset); @@ -1872,8 +1870,7 @@ int pmd_clear_huge(pmd_t *pmdp) return 1; } -static int __pmd_free_pte_page(pmd_t *pmdp, unsigned long addr, - bool acquire_mmap_lock) +int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) { pte_t *table; pmd_t pmd; @@ -1885,25 +1882,13 @@ static int __pmd_free_pte_page(pmd_t *pmdp, unsigned long addr, return 1; } - /* See comment in pud_free_pmd_page for static key logic */ table = pte_offset_kernel(pmdp, addr); pmd_clear(pmdp); __flush_tlb_kernel_pgtable(addr); - if (static_branch_unlikely(&arm64_ptdump_lock_key) && acquire_mmap_lock) { - mmap_read_lock(&init_mm); - mmap_read_unlock(&init_mm); - } - pte_free_kernel(NULL, table); return 1; } -int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) -{ - /* If ptdump is walking the pagetables, acquire init_mm.mmap_lock */ - return __pmd_free_pte_page(pmdp, addr, /* acquire_mmap_lock = */ true); -} - int pud_free_pmd_page(pud_t *pudp, unsigned long addr) { pmd_t *table; @@ -1919,36 +1904,16 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr) } table = pmd_offset(pudp, addr); - - /* - * Our objective is to prevent ptdump from reading a PMD table which has - * been freed. In this race, if pud_free_pmd_page observes the key on - * (which got flipped by ptdump) then the mmap lock sequence here will, - * as a result of the mmap write lock/unlock sequence in ptdump, give - * us the correct synchronization. If not, this means that ptdump has - * yet not started walking the pagetables - the sequence of barriers - * issued by __flush_tlb_kernel_pgtable() guarantees that ptdump will - * observe an empty PUD. - */ - pud_clear(pudp); - __flush_tlb_kernel_pgtable(addr); - if (static_branch_unlikely(&arm64_ptdump_lock_key)) { - mmap_read_lock(&init_mm); - mmap_read_unlock(&init_mm); - } - pmdp = table; next = addr; end = addr + PUD_SIZE; do { if (pmd_present(pmdp_get(pmdp))) - /* - * PMD has been isolated, so ptdump won't see it. No - * need to acquire init_mm.mmap_lock. - */ - __pmd_free_pte_page(pmdp, next, /* acquire_mmap_lock = */ false); + pmd_free_pte_page(pmdp, next); } while (pmdp++, next += PMD_SIZE, next != end); + pud_clear(pudp); + __flush_tlb_kernel_pgtable(addr); pmd_free(NULL, table); return 1; } diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c index ab9899ca1e5f..421a5de806c6 100644 --- a/arch/arm64/mm/ptdump.c +++ b/arch/arm64/mm/ptdump.c @@ -283,13 +283,6 @@ void note_page_flush(struct ptdump_state *pt_st) note_page(pt_st, 0, -1, pte_val(pte_zero)); } -static void arm64_ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm) -{ - static_branch_inc(&arm64_ptdump_lock_key); - ptdump_walk_pgd(st, mm, NULL); - static_branch_dec(&arm64_ptdump_lock_key); -} - void ptdump_walk(struct seq_file *s, struct ptdump_info *info) { unsigned long end = ~0UL; @@ -318,7 +311,7 @@ void ptdump_walk(struct seq_file *s, struct ptdump_info *info) } }; - arm64_ptdump_walk_pgd(&st.ptdump, info->mm); + ptdump_walk_pgd(&st.ptdump, info->mm, NULL); } static void __init ptdump_initialize(void) @@ -360,7 +353,7 @@ bool ptdump_check_wx(void) } }; - arm64_ptdump_walk_pgd(&st.ptdump, &init_mm); + ptdump_walk_pgd(&st.ptdump, &init_mm, NULL); if (st.wx_pages || st.uxn_pages) { pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n", diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a4268c47f2bc..558a253c92fa 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -2668,3 +2668,13 @@ void __init arch_cpu_finalize_init(void) */ mem_encrypt_init(); } + +/* Control TLB flushing methods */ +static int __init tlbi_setup(char *str) +{ + if (!strcmp(str, "ipi")) + setup_clear_cpu_cap(X86_FEATURE_INVLPGB); + + return 1; +} +__setup("tlbi=", tlbi_setup); diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index f3a793e3a6c8..1848c54bae85 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -2269,10 +2269,10 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) mca_cfg.initialized = 1; + __mcheck_cpu_setup_timer(); __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(c); __mcheck_cpu_init_prepare_banks(); - __mcheck_cpu_setup_timer(); cr4_set_bits(X86_CR4_MCE); } diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 34a312705253..0e918f35bfbe 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2415,6 +2415,9 @@ static union kvm_mmu_page_role kvm_mmu_child_role(u64 *sptep, bool direct, role.direct = direct; role.passthrough = 0; + WARN_ON_ONCE(role.invalid); + role.invalid = 0; + /* * If the guest has 4-byte PTEs then that means it's using 32-bit, * 2-level, non-PAE paging. KVM shadows such guests with PAE paging diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 996f398a577f..e1d73ccaa547 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -96,6 +96,8 @@ static u64 sev_supported_vmsa_features __ro_after_init; static u8 sev_enc_bit; static DECLARE_RWSEM(sev_deactivate_lock); static DEFINE_MUTEX(sev_bitmap_lock); +/* Protects kvm_sev_info's enc_context_owner, mirror_vms and mirror_entry. */ +static DEFINE_MUTEX(sev_mirror_lock); unsigned int max_sev_asid; static unsigned int min_sev_asid; static unsigned int max_sev_es_asid; @@ -2031,7 +2033,6 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) dst->asid = src->asid; dst->handle = src->handle; dst->pages_locked = src->pages_locked; - dst->enc_context_owner = src->enc_context_owner; dst->es_active = src->es_active; dst->vmsa_features = src->vmsa_features; @@ -2039,11 +2040,12 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) src->active = false; src->handle = 0; src->pages_locked = 0; - src->enc_context_owner = NULL; src->es_active = false; list_cut_before(&dst->regions_list, &src->regions_list, &src->regions_list); + mutex_lock(&sev_mirror_lock); + /* * If this VM has mirrors, "transfer" each mirror's refcount of the * source to the destination (this KVM). The caller holds a reference @@ -2060,12 +2062,15 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) * If this VM is a mirror, remove the old mirror from the owners list * and add the new mirror to the list. */ - if (is_mirroring_enc_context(dst_kvm)) { - struct kvm_sev_info *owner_sev_info = to_kvm_sev_info(dst->enc_context_owner); + if (is_mirroring_enc_context(src_kvm)) { + struct kvm_sev_info *owner_sev_info = to_kvm_sev_info(src->enc_context_owner); + dst->enc_context_owner = src->enc_context_owner; + src->enc_context_owner = NULL; list_del(&src->mirror_entry); list_add_tail(&dst->mirror_entry, &owner_sev_info->mirror_vms); } + mutex_unlock(&sev_mirror_lock); kvm_for_each_vcpu(i, dst_vcpu, dst_kvm) { dst_svm = to_svm(dst_vcpu); @@ -2885,11 +2890,14 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd) * disappear until we're done with it */ source_sev = to_kvm_sev_info(source_kvm); - kvm_get_kvm(source_kvm); - list_add_tail(&mirror_sev->mirror_entry, &source_sev->mirror_vms); /* Set enc_context_owner and copy its encryption context over */ + mutex_lock(&sev_mirror_lock); + kvm_get_kvm(source_kvm); + list_add_tail(&mirror_sev->mirror_entry, &source_sev->mirror_vms); mirror_sev->enc_context_owner = source_kvm; + mutex_unlock(&sev_mirror_lock); + mirror_sev->active = true; mirror_sev->asid = source_sev->asid; mirror_sev->fd = source_sev->fd; @@ -2977,11 +2985,19 @@ void sev_vm_destroy(struct kvm *kvm) * Note, mirror VMs don't support registering encrypted regions. */ if (is_mirroring_enc_context(kvm)) { - struct kvm *owner_kvm = sev->enc_context_owner; + struct kvm *owner_kvm; - mutex_lock(&owner_kvm->lock); + mutex_lock(&sev_mirror_lock); + owner_kvm = sev->enc_context_owner; list_del(&sev->mirror_entry); - mutex_unlock(&owner_kvm->lock); + sev->enc_context_owner = NULL; + + /* + * The reference to owner_kvm cannot move after sev_mirror_lock is + * released. Release it before kvm_put_kvm() so that owner_kvm is + * never destroyed inside sev_mirror_lock. + */ + mutex_unlock(&sev_mirror_lock); kvm_put_kvm(owner_kvm); return; } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 5137416be593..0632ff940eab 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -106,6 +106,7 @@ struct kvm_sev_info { u64 ap_jump_table; /* SEV-ES AP Jump Table address */ u64 vmsa_features; u16 ghcb_version; /* Highest guest GHCB protocol version allowed */ + /* The three fields below are protected by sev_mirror_lock */ struct kvm *enc_context_owner; /* Owner of copied encryption context */ struct list_head mirror_vms; /* List of VMs mirroring */ struct list_head mirror_entry; /* Use as a list entry of mirrors */ diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c index cdf113dadc4d..fff1c707d040 100644 --- a/drivers/accel/amdxdna/amdxdna_gem.c +++ b/drivers/accel/amdxdna/amdxdna_gem.c @@ -371,6 +371,23 @@ static void amdxdna_gem_dev_obj_free(struct drm_gem_object *gobj) amdxdna_gem_destroy_obj(abo); } +static void amdxdna_mark_mapp_invalid(struct amdxdna_gem_obj *abo, + struct vm_area_struct *vma) +{ + struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev); + struct amdxdna_umap *mapp; + + down_write(&xdna->notifier_lock); + abo->mem.map_invalid = true; + list_for_each_entry(mapp, &abo->mem.umap_list, node) { + if (compare_range(mapp, vma->vm_mm, vma->vm_start, vma->vm_end)) { + mapp->invalid = true; + break; + } + } + up_write(&xdna->notifier_lock); +} + static int amdxdna_insert_pages(struct amdxdna_gem_obj *abo, struct vm_area_struct *vma) { @@ -385,26 +402,17 @@ static int amdxdna_insert_pages(struct amdxdna_gem_obj *abo, XDNA_ERR(xdna, "Failed shmem mmap %d", ret); return ret; } - - /* The buffer is based on memory pages. Fix the flag. */ - vm_flags_mod(vma, VM_MIXEDMAP, VM_PFNMAP); - ret = vm_insert_pages(vma, vma->vm_start, abo->base.pages, - &num_pages); + } else { + vma->vm_private_data = NULL; + vma->vm_ops = NULL; + ret = dma_buf_mmap(abo->dma_buf, vma, 0); if (ret) { - XDNA_ERR(xdna, "Failed insert pages %d", ret); - vma->vm_ops->close(vma); + XDNA_ERR(xdna, "Failed to mmap dma buf %d", ret); return ret; } - return 0; - } - - vma->vm_private_data = NULL; - vma->vm_ops = NULL; - ret = dma_buf_mmap(abo->dma_buf, vma, 0); - if (ret) { - XDNA_ERR(xdna, "Failed to mmap dma buf %d", ret); - return ret; + /* Drop the reference drm_gem_mmap_obj() acquired.*/ + drm_gem_object_put(to_gobj(abo)); } do { @@ -413,17 +421,14 @@ static int amdxdna_insert_pages(struct amdxdna_gem_obj *abo, fault_ret = handle_mm_fault(vma, vma->vm_start + offset, FAULT_FLAG_WRITE, NULL); if (fault_ret & VM_FAULT_ERROR) { - vma->vm_ops->close(vma); XDNA_ERR(xdna, "Fault in page failed"); - return -EFAULT; + amdxdna_mark_mapp_invalid(abo, vma); + break; } offset += PAGE_SIZE; } while (--num_pages); - /* Drop the reference drm_gem_mmap_obj() acquired.*/ - drm_gem_object_put(to_gobj(abo)); - return 0; } diff --git a/drivers/android/binder/process.rs b/drivers/android/binder/process.rs index cdd1a9079726..5b8f73ec1931 100644 --- a/drivers/android/binder/process.rs +++ b/drivers/android/binder/process.rs @@ -1586,6 +1586,10 @@ impl Process { cmd: u32, reader: &mut UserSliceReader, ) -> Result { + if cmd == uapi::BINDER_FREEZE { + return ioctl_freeze(reader); + } + let thread = this.get_current_thread()?; match cmd { uapi::BINDER_SET_MAX_THREADS => this.set_max_threads(reader.read()?), @@ -1597,7 +1601,6 @@ impl Process { uapi::BINDER_ENABLE_ONEWAY_SPAM_DETECTION => { this.set_oneway_spam_detection_enabled(reader.read()?) } - uapi::BINDER_FREEZE => ioctl_freeze(reader)?, _ => return Err(EINVAL), } Ok(()) @@ -1612,15 +1615,16 @@ impl Process { cmd: u32, data: UserSlice, ) -> Result { - let thread = this.get_current_thread()?; let blocking = (file.flags() & file::flags::O_NONBLOCK) == 0; match cmd { - uapi::BINDER_WRITE_READ => thread.write_read(data, blocking)?, + uapi::BINDER_WRITE_READ => this.get_current_thread()?.write_read(data, blocking)?, uapi::BINDER_GET_NODE_DEBUG_INFO => this.get_node_debug_info(data)?, uapi::BINDER_GET_NODE_INFO_FOR_REF => this.get_node_info_from_ref(data)?, uapi::BINDER_VERSION => this.version(data)?, uapi::BINDER_GET_FROZEN_INFO => get_frozen_status(data)?, - uapi::BINDER_GET_EXTENDED_ERROR => thread.get_extended_error(data)?, + uapi::BINDER_GET_EXTENDED_ERROR => { + this.get_current_thread()?.get_extended_error(data)? + } _ => return Err(EINVAL), } Ok(()) diff --git a/drivers/ata/pata_sl82c105.c b/drivers/ata/pata_sl82c105.c index 2d24c6b3e9d9..25bce3fe2a10 100644 --- a/drivers/ata/pata_sl82c105.c +++ b/drivers/ata/pata_sl82c105.c @@ -264,6 +264,7 @@ static struct ata_port_operations sl82c105_port_ops = { static int sl82c105_bridge_revision(struct pci_dev *pdev) { struct pci_dev *bridge; + u8 revision; /* * The bridge should be part of the same device, but function 0. @@ -285,8 +286,9 @@ static int sl82c105_bridge_revision(struct pci_dev *pdev) /* * We need to find function 0's revision, not function 1 */ + revision = bridge->revision; pci_dev_put(bridge); - return bridge->revision; + return revision; } static void sl82c105_fixup(struct pci_dev *pdev) diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 03fa9409e3ee..7f54d2d2d13a 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -1343,6 +1343,19 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev) if (!btrtl_dev->ic_info) return; + switch (btrtl_dev->project_id) { + case CHIP_ID_8761B: + /* RTL8761B/BU reports HCI version 5.1 but does not support + * the LE Extended Scan commands (Opcode 0x2042), causing + * repeated -EBUSY failures when BlueZ attempts extended + * scanning while a connection is active. + */ + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_EXT_SCAN); + break; + default: + break; + } + switch (btrtl_dev->ic_info->lmp_subver) { case RTL_ROM_LMP_8703B: /* 8723CS reports two pages for local ext features, diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index a072e6f57f31..4a356f720e1f 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -832,6 +832,8 @@ static const struct usb_device_id quirks_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x2b89, 0x6275), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x37ad, 0x0600), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Additional Realtek 8821AE Bluetooth devices */ { USB_DEVICE(0x0b05, 0x17dc), .driver_info = BTUSB_REALTEK }, diff --git a/drivers/counter/microchip-tcb-capture.c b/drivers/counter/microchip-tcb-capture.c index 19d457ae4c3b..e53a8390756b 100644 --- a/drivers/counter/microchip-tcb-capture.c +++ b/drivers/counter/microchip-tcb-capture.c @@ -483,7 +483,7 @@ static int mchp_tc_probe(struct platform_device *pdev) char clk_name[7]; struct regmap *regmap; struct clk *clk[3]; - int channel; + u32 channel; int ret, i; counter = devm_counter_alloc(&pdev->dev, sizeof(*priv)); @@ -517,7 +517,7 @@ static int mchp_tc_probe(struct platform_device *pdev) priv->channel[i] = channel; - snprintf(clk_name, sizeof(clk_name), "t%d_clk", channel); + snprintf(clk_name, sizeof(clk_name), "t%u_clk", channel); clk[i] = of_clk_get_by_name(np->parent, clk_name); if (IS_ERR(clk[i])) { diff --git a/drivers/dibs/dibs_loopback.c b/drivers/dibs/dibs_loopback.c index fd5caf1e19a8..649e4e375be3 100644 --- a/drivers/dibs/dibs_loopback.c +++ b/drivers/dibs/dibs_loopback.c @@ -335,7 +335,6 @@ static int dibs_lo_dev_probe(void) return 0; err_reg: - kfree(dibs->dmb_clientid_arr); /* pairs with dibs_dev_alloc() */ put_device(&dibs->dev); kfree(ldev); diff --git a/drivers/dibs/dibs_main.c b/drivers/dibs/dibs_main.c index 14c3e2d84902..2b53a9d277dc 100644 --- a/drivers/dibs/dibs_main.c +++ b/drivers/dibs/dibs_main.c @@ -128,6 +128,7 @@ static void dibs_dev_release(struct device *dev) dibs = container_of(dev, struct dibs_dev, dev); + kfree(dibs->dmb_clientid_arr); kfree(dibs); } @@ -138,6 +139,7 @@ struct dibs_dev *dibs_dev_alloc(void) dibs = kzalloc_obj(*dibs); if (!dibs) return dibs; + spin_lock_init(&dibs->lock); dibs->dev.release = dibs_dev_release; dibs->dev.class = &dibs_class; device_initialize(&dibs->dev); @@ -186,7 +188,6 @@ int dibs_dev_add(struct dibs_dev *dibs) int i, ret; max_dmbs = dibs->ops->max_dmbs(); - spin_lock_init(&dibs->lock); dibs->dmb_clientid_arr = kzalloc(max_dmbs, GFP_KERNEL); if (!dibs->dmb_clientid_arr) return -ENOMEM; @@ -194,12 +195,13 @@ int dibs_dev_add(struct dibs_dev *dibs) ret = device_add(&dibs->dev); if (ret) - goto free_client_arr; + return ret; ret = sysfs_create_group(&dibs->dev.kobj, &dibs_dev_attr_group); if (ret) { dev_err(&dibs->dev, "sysfs_create_group failed for dibs_dev\n"); - goto err_device_del; + device_del(&dibs->dev); + return ret; } mutex_lock(&dibs_dev_list.mutex); mutex_lock(&clients_lock); @@ -214,13 +216,6 @@ int dibs_dev_add(struct dibs_dev *dibs) mutex_unlock(&dibs_dev_list.mutex); return 0; - -err_device_del: - device_del(&dibs->dev); -free_client_arr: - kfree(dibs->dmb_clientid_arr); - return ret; - } EXPORT_SYMBOL_GPL(dibs_dev_add); @@ -247,7 +242,6 @@ void dibs_dev_del(struct dibs_dev *dibs) mutex_unlock(&dibs_dev_list.mutex); device_del(&dibs->dev); - kfree(dibs->dmb_clientid_arr); } EXPORT_SYMBOL_GPL(dibs_dev_del); diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index 69c5bd9aaee7..cb282b35fb58 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -605,20 +605,28 @@ static int pca953x_read_regs(struct pca953x_chip *chip, int reg, unsigned long * return 0; } -static int pca953x_gpio_direction_input(struct gpio_chip *gc, unsigned off) +static int pca953x_gpio_direction_input_unlocked(struct gpio_chip *gc, + unsigned int off) { struct pca953x_chip *chip = gpiochip_get_data(gc); u8 dirreg = chip->recalc_addr(chip, chip->regs->direction, off); u8 bit = pca953x_get_bit_mask(chip, off); - guard(mutex)(&chip->i2c_lock); - if (PCA_CHIP_TYPE(chip->driver_data) == TCA6418_TYPE) return regmap_update_bits(chip->regmap, dirreg, bit, 0); return regmap_update_bits(chip->regmap, dirreg, bit, bit); } +static int pca953x_gpio_direction_input(struct gpio_chip *gc, unsigned int off) +{ + struct pca953x_chip *chip = gpiochip_get_data(gc); + + guard(mutex)(&chip->i2c_lock); + + return pca953x_gpio_direction_input_unlocked(gc, off); +} + static int pca953x_gpio_direction_output(struct gpio_chip *gc, unsigned off, int val) { @@ -856,9 +864,10 @@ static void pca953x_irq_bus_sync_unlock(struct irq_data *d) DECLARE_BITMAP(reg_direction, MAX_LINE); int level; + guard(mutex)(&chip->i2c_lock); + if (chip->driver_data & PCA_PCAL) { DECLARE_BITMAP(latched_inputs, MAX_LINE); - guard(mutex)(&chip->i2c_lock); /* Enable latch on edge-triggered interrupt-enabled inputs */ bitmap_or(latched_inputs, chip->irq_trig_fall, chip->irq_trig_raise, gc->ngpio); @@ -882,7 +891,7 @@ static void pca953x_irq_bus_sync_unlock(struct irq_data *d) /* Look for any newly setup interrupt */ for_each_set_bit(level, irq_mask, gc->ngpio) - pca953x_gpio_direction_input(&chip->gpio_chip, level); + pca953x_gpio_direction_input_unlocked(&chip->gpio_chip, level); mutex_unlock(&chip->irq_lock); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 3fad14824d1e..22e88644402e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4169,6 +4169,8 @@ static void amdgpu_device_unmap_mmio(struct amdgpu_device *adev) iounmap(adev->rmmio); adev->rmmio = NULL; + if (adev->mman.aper_base_kaddr) + iounmap(adev->mman.aper_base_kaddr); adev->mman.aper_base_kaddr = NULL; /* Memory manager related */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 81c8eba2b7a9..c064f8a1e5f3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -2121,23 +2121,17 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) /* Change the size here instead of the init above so only lpfn is affected */ amdgpu_ttm_set_buffer_funcs_status(adev, false); #ifdef CONFIG_64BIT - if (adev->gmc.xgmi.connected_to_cpu) { - void *kaddr = devm_memremap(adev->dev, adev->gmc.aper_base, - adev->gmc.visible_vram_size, - MEMREMAP_WB); - if (IS_ERR(kaddr)) - return PTR_ERR(kaddr); - adev->mman.aper_base_kaddr = (__force void __iomem *)kaddr; - } else if (adev->gmc.is_app_apu) { +#ifdef CONFIG_X86 + if (adev->gmc.xgmi.connected_to_cpu) + adev->mman.aper_base_kaddr = ioremap_cache(adev->gmc.aper_base, + adev->gmc.visible_vram_size); + else if (adev->gmc.is_app_apu) DRM_DEBUG_DRIVER( "No need to ioremap when real vram size is 0\n"); - } else { - adev->mman.aper_base_kaddr = devm_ioremap_wc(adev->dev, - adev->gmc.aper_base, - adev->gmc.visible_vram_size); - if (!adev->mman.aper_base_kaddr) - return -ENOMEM; - } + else +#endif + adev->mman.aper_base_kaddr = ioremap_wc(adev->gmc.aper_base, + adev->gmc.visible_vram_size); #endif amdgpu_ttm_init_vram_resv_regions(adev); @@ -2266,6 +2260,8 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) */ void amdgpu_ttm_fini(struct amdgpu_device *adev) { + int idx; + if (!adev->mman.initialized) return; @@ -2288,7 +2284,14 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev) amdgpu_ttm_unmark_vram_reserved(adev, AMDGPU_RESV_FW_VRAM_USAGE); amdgpu_ttm_unmark_vram_reserved(adev, AMDGPU_RESV_DRV_VRAM_USAGE); - adev->mman.aper_base_kaddr = NULL; + if (drm_dev_enter(adev_to_drm(adev), &idx)) { + + if (adev->mman.aper_base_kaddr) + iounmap(adev->mman.aper_base_kaddr); + adev->mman.aper_base_kaddr = NULL; + + drm_dev_exit(idx); + } if (!adev->gmc.is_app_apu) amdgpu_vram_mgr_fini(adev); 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 40d82a3eeec0..6f9d4bea3379 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -5401,11 +5401,11 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) caps = &dm->backlight_caps[aconnector->bl_idx]; if (get_brightness_range(caps, &min, &max)) { if (power_supply_is_system_supplied() > 0) - props.brightness = DIV_ROUND_CLOSEST(max * caps->ac_level, 100); + props.brightness = DIV_ROUND_CLOSEST((max - min) * caps->ac_level, 100); else - props.brightness = DIV_ROUND_CLOSEST(max * caps->dc_level, 100); + props.brightness = DIV_ROUND_CLOSEST((max - min) * caps->dc_level, 100); /* min is zero, so max needs to be adjusted */ - props.max_brightness = max; + props.max_brightness = max - min; drm_dbg(drm, "Backlight caps: min: %d, max: %d, ac %d, dc %d\n", min, max, caps->ac_level, caps->dc_level); } else diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index f0abbb7c2cb2..3b26229eff2b 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -1320,8 +1320,30 @@ void dce110_blank_stream(struct pipe_ctx *pipe_ctx) void dce110_set_avmute(struct pipe_ctx *pipe_ctx, bool enable) { - if (pipe_ctx != NULL && pipe_ctx->stream_res.stream_enc != NULL) + if (pipe_ctx == NULL || pipe_ctx->stream_res.stream_enc == NULL) + return; + + if (dc_is_hdmi_signal(pipe_ctx->stream->signal)) { pipe_ctx->stream_res.stream_enc->funcs->set_avmute(pipe_ctx->stream_res.stream_enc, enable); + + /* Wait for three frames to make sure AV mute is sent out. + * Some HDMI sinks need additional GCP packets to properly + * process the mute state, especially after link re-establishment + * with HDMI 2.0 scrambling enabled. + */ + if (enable && pipe_ctx->stream_res.tg && + pipe_ctx->stream_res.tg->funcs->is_tg_enabled && + pipe_ctx->stream_res.tg->funcs->wait_for_state && + pipe_ctx->stream_res.tg->funcs->is_tg_enabled(pipe_ctx->stream_res.tg)) { + int i; + + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + for (i = 0; i < 3; i++) { + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + } + } + } } enum audio_dto_source translate_to_dto_source(enum controller_id crtc_id) diff --git a/drivers/gpu/drm/bridge/parade-ps8640.c b/drivers/gpu/drm/bridge/parade-ps8640.c index 825777a5758f..db8e5889dc7f 100644 --- a/drivers/gpu/drm/bridge/parade-ps8640.c +++ b/drivers/gpu/drm/bridge/parade-ps8640.c @@ -257,8 +257,14 @@ static ssize_t ps8640_aux_transfer_msg(struct drm_dp_aux *aux, addr_len[PAGE0_SWAUX_LENGTH - base] = (len == 0) ? SWAUX_NO_PAYLOAD : ((len - 1) & SWAUX_LENGTH_MASK); - regmap_bulk_write(map, PAGE0_SWAUX_ADDR_7_0, addr_len, - ARRAY_SIZE(addr_len)); + ret = regmap_bulk_write(map, PAGE0_SWAUX_ADDR_7_0, addr_len, + ARRAY_SIZE(addr_len)); + if (ret) { + DRM_DEV_ERROR(dev, + "failed to write AUX address %#x, len %zu: %d\n", + msg->address, len, ret); + return ret; + } if (len && (request == DP_AUX_NATIVE_WRITE || request == DP_AUX_I2C_WRITE)) { @@ -274,13 +280,22 @@ static ssize_t ps8640_aux_transfer_msg(struct drm_dp_aux *aux, } } - regmap_write(map, PAGE0_SWAUX_CTRL, SWAUX_SEND); + ret = regmap_write(map, PAGE0_SWAUX_CTRL, SWAUX_SEND); + if (ret) { + DRM_DEV_ERROR(dev, "failed to start AUX transfer: %d\n", ret); + return ret; + } /* Zero delay loop because i2c transactions are slow already */ - regmap_read_poll_timeout(map, PAGE0_SWAUX_CTRL, data, - !(data & SWAUX_SEND), 0, 50 * 1000); + ret = regmap_read_poll_timeout(map, PAGE0_SWAUX_CTRL, data, + !(data & SWAUX_SEND), 0, 50 * 1000); + if (ret) { + DRM_DEV_ERROR(dev, "failed to complete AUX transfer: %d\n", + ret); + return ret; + } - regmap_read(map, PAGE0_SWAUX_STATUS, &data); + ret = regmap_read(map, PAGE0_SWAUX_STATUS, &data); if (ret) { DRM_DEV_ERROR(dev, "failed to read PAGE0_SWAUX_STATUS: %d\n", ret); diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index 6a3cad933439..940946390793 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -181,6 +181,12 @@ struct v3d_dev { */ struct mutex reset_lock; + /* Ordered workqueue shared by every queue's scheduler timeout work. + * V3D reset is global to all queues, so the timeout handlers must not + * run concurrently. + */ + struct workqueue_struct *reset_wq; + /* Lock taken when creating and pushing the GPU scheduler * jobs, to keep the sched-fence seqnos in order. */ diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 8a635a9ec046..bea46298b69e 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -838,6 +838,7 @@ v3d_queue_sched_init(struct v3d_dev *v3d, const struct drm_sched_backend_ops *op .num_rqs = DRM_SCHED_PRIORITY_COUNT, .credit_limit = 1, .timeout = msecs_to_jiffies(500), + .timeout_wq = v3d->reset_wq, .dev = v3d->drm.dev, }; @@ -852,9 +853,13 @@ v3d_sched_init(struct v3d_dev *v3d) { int ret; + v3d->reset_wq = alloc_ordered_workqueue("v3d_reset", 0); + if (!v3d->reset_wq) + return -ENOMEM; + ret = v3d_queue_sched_init(v3d, &v3d_bin_sched_ops, V3D_BIN, "v3d_bin"); if (ret) - return ret; + goto fail; ret = v3d_queue_sched_init(v3d, &v3d_render_sched_ops, V3D_RENDER, "v3d_render"); @@ -897,4 +902,6 @@ v3d_sched_fini(struct v3d_dev *v3d) if (v3d->queue[q].sched.ready) drm_sched_fini(&v3d->queue[q].sched); } + + destroy_workqueue(v3d->reset_wq); } diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 071b8c41df43..85778958f580 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -801,6 +801,9 @@ static int exec_queue_set_hang_replay_state(struct xe_device *xe, u64 __user *address = u64_to_user_ptr(value); void *ptr; + if (q->replay_state) + return -EINVAL; + ptr = vmemdup_user(address, size); if (XE_IOCTL_DBG(xe, IS_ERR(ptr))) return PTR_ERR(ptr); diff --git a/drivers/gpu/drm/xe/xe_uc.c b/drivers/gpu/drm/xe/xe_uc.c index 75091bde0d50..65f59f06177f 100644 --- a/drivers/gpu/drm/xe/xe_uc.c +++ b/drivers/gpu/drm/xe/xe_uc.c @@ -15,6 +15,7 @@ #include "xe_guc_pc.h" #include "xe_guc_rc.h" #include "xe_guc_engine_activity.h" +#include "xe_guc_submit.h" #include "xe_huc.h" #include "xe_sriov.h" #include "xe_wopcm.h" @@ -159,12 +160,14 @@ static int vf_uc_load_hw(struct xe_uc *uc) if (err) return err; - uc->guc.submission_state.enabled = true; - err = xe_guc_opt_in_features_enable(&uc->guc); if (err) return err; + err = xe_guc_submit_enable(&uc->guc); + if (err) + return err; + err = xe_gt_record_default_lrcs(uc_to_gt(uc)); if (err) return err; diff --git a/drivers/hwmon/ads7828.c b/drivers/hwmon/ads7828.c index 149cfcec78dc..f8f2f621dfea 100644 --- a/drivers/hwmon/ads7828.c +++ b/drivers/hwmon/ads7828.c @@ -106,12 +106,11 @@ static int ads7828_probe(struct i2c_client *client) struct ads7828_data *data; struct device *hwmon_dev; unsigned int vref_mv = ADS7828_INT_VREF_MV; - unsigned int vref_uv; + int vref_uv; bool diff_input = false; bool ext_vref = false; unsigned int regval; enum ads7828_chips chip; - struct regulator *reg; data = devm_kzalloc(dev, sizeof(struct ads7828_data), GFP_KERNEL); if (!data) @@ -125,9 +124,11 @@ static int ads7828_probe(struct i2c_client *client) } else if (dev->of_node) { diff_input = of_property_read_bool(dev->of_node, "ti,differential-input"); - reg = devm_regulator_get_optional(dev, "vref"); - if (!IS_ERR(reg)) { - vref_uv = regulator_get_voltage(reg); + vref_uv = devm_regulator_get_enable_read_voltage(dev, "vref"); + if (vref_uv < 0) { + if (vref_uv != -ENODEV) + return vref_uv; + } else { vref_mv = DIV_ROUND_CLOSEST(vref_uv, 1000); if (vref_mv < ADS7828_EXT_VREF_MV_MIN || vref_mv > ADS7828_EXT_VREF_MV_MAX) diff --git a/drivers/hwmon/corsair-psu.c b/drivers/hwmon/corsair-psu.c index ce958cdaef58..ebcaddf337d8 100644 --- a/drivers/hwmon/corsair-psu.c +++ b/drivers/hwmon/corsair-psu.c @@ -664,6 +664,8 @@ static void print_uptime(struct seq_file *seqf, u8 cmd) long val; int ret; + guard(hwmon_lock)(priv->hwmon_dev); + ret = corsairpsu_get_value(priv, cmd, 0, &val); if (ret < 0) { seq_puts(seqf, "N/A\n"); @@ -701,7 +703,7 @@ static int vendor_show(struct seq_file *seqf, void *unused) { struct corsairpsu_data *priv = seqf->private; - seq_printf(seqf, "%s\n", priv->vendor); + seq_printf(seqf, "%.*s\n", REPLY_SIZE, priv->vendor); return 0; } @@ -711,7 +713,7 @@ static int product_show(struct seq_file *seqf, void *unused) { struct corsairpsu_data *priv = seqf->private; - seq_printf(seqf, "%s\n", priv->product); + seq_printf(seqf, "%.*s\n", REPLY_SIZE, priv->product); return 0; } @@ -723,6 +725,8 @@ static int ocpmode_show(struct seq_file *seqf, void *unused) long val; int ret; + guard(hwmon_lock)(priv->hwmon_dev); + /* * The rail mode is switchable on the fly. The RAW interface can be used for this. But it * will not be included here, because I consider it somewhat dangerous for the health of the diff --git a/drivers/hwmon/ltc4282.c b/drivers/hwmon/ltc4282.c index bdbf370233d7..d7c622608144 100644 --- a/drivers/hwmon/ltc4282.c +++ b/drivers/hwmon/ltc4282.c @@ -14,6 +14,7 @@ #include <linux/hwmon.h> #include <linux/i2c.h> #include <linux/math.h> +#include <linux/math64.h> #include <linux/minmax.h> #include <linux/module.h> #include <linux/mod_devicetable.h> @@ -138,7 +139,7 @@ struct ltc4282_state { */ struct ltc4282_cache in0_1_cache[LTC4282_CHAN_VGPIO]; u32 vsense_max; - long power_max; + s64 power_max; u32 rsense; u16 vdd; u16 vfs_out; @@ -614,13 +615,12 @@ static int ltc4282_read(struct device *dev, enum hwmon_sensor_types type, } static int ltc4282_write_power_byte(const struct ltc4282_state *st, u32 reg, - long val) + s64 val) { u32 power; u64 temp; - if (val > st->power_max) - val = st->power_max; + val = clamp(val, 0, st->power_max); temp = val * int_pow(U8_MAX, 2) * st->rsense; power = DIV64_U64_ROUND_CLOSEST(temp, @@ -630,7 +630,7 @@ static int ltc4282_write_power_byte(const struct ltc4282_state *st, u32 reg, } static int ltc4282_write_power_word(const struct ltc4282_state *st, u32 reg, - long val) + u64 val) { u64 temp = int_pow(U16_MAX, 2) * st->rsense, temp_2; __be16 __raw; @@ -931,8 +931,11 @@ static int ltc4282_curr_reset_hist(struct ltc4282_state *st) static int ltc4282_write_curr(struct ltc4282_state *st, u32 attr, long val) { + s32 ulimit = min_t(u64, INT_MAX, + div_u64((u64)INT_MAX * DECA * MICRO, st->rsense)); + u64 val64 = clamp(val, 0, ulimit); /* need to pass it in millivolt */ - u32 in = DIV_ROUND_CLOSEST_ULL((u64)val * st->rsense, DECA * MICRO); + u32 in = DIV_ROUND_CLOSEST_ULL(val64 * st->rsense, DECA * MICRO); switch (attr) { case hwmon_curr_max: @@ -1223,7 +1226,8 @@ static int ltc4282_set_max_limits(struct ltc4282_state *st) return ret; /* Power is given by ISENSE * Vout. */ - st->power_max = DIV_ROUND_CLOSEST(st->vsense_max * DECA * MILLI, st->rsense) * st->vfs_out; + st->power_max = DIV_ROUND_CLOSEST_ULL((u64)st->vsense_max * DECA * MILLI, + st->rsense) * st->vfs_out; ret = ltc4282_write_power_byte(st, LTC4282_POWER_MAX, st->power_max); if (ret) return ret; @@ -1391,7 +1395,7 @@ static int ltc4282_setup(struct ltc4282_state *st, struct device *dev) if (!ret) { int reg_val; - switch (val) { + switch (st->vsense_max) { case 12500: reg_val = 0; break; diff --git a/drivers/hwmon/nzxt-smart2.c b/drivers/hwmon/nzxt-smart2.c index ff0c0bee0e83..efc78a8f58c8 100644 --- a/drivers/hwmon/nzxt-smart2.c +++ b/drivers/hwmon/nzxt-smart2.c @@ -754,7 +754,11 @@ static int nzxt_smart2_hid_probe(struct hid_device *hdev, hid_device_io_start(hdev); - init_device(drvdata, UPDATE_INTERVAL_DEFAULT_MS); + ret = init_device(drvdata, UPDATE_INTERVAL_DEFAULT_MS); + if (ret) { + dev_err(&hdev->dev, "init_device failed: %d\n", ret); + goto out_hw_close; + } drvdata->hwmon = hwmon_device_register_with_info(&hdev->dev, "nzxtsmart2", drvdata, diff --git a/drivers/hwmon/pmbus/lm25066.c b/drivers/hwmon/pmbus/lm25066.c index 0f7df7e2c9c5..cb42832cebf0 100644 --- a/drivers/hwmon/pmbus/lm25066.c +++ b/drivers/hwmon/pmbus/lm25066.c @@ -14,6 +14,7 @@ #include <linux/slab.h> #include <linux/i2c.h> #include <linux/log2.h> +#include <linux/math.h> #include <linux/of.h> #include "pmbus.h" @@ -540,8 +541,8 @@ static int lm25066_probe(struct i2c_client *client) if (of_property_read_u32(client->dev.of_node, "shunt-resistor-micro-ohms", &shunt)) shunt = 1000; - info->m[PSC_CURRENT_IN] = info->m[PSC_CURRENT_IN] * shunt / 1000; - info->m[PSC_POWER] = info->m[PSC_POWER] * shunt / 1000; + info->m[PSC_CURRENT_IN] = DIV_ROUND_CLOSEST_ULL((u64)info->m[PSC_CURRENT_IN] * shunt, 1000); + info->m[PSC_POWER] = DIV_ROUND_CLOSEST_ULL((u64)info->m[PSC_POWER] * shunt, 1000); #if IS_ENABLED(CONFIG_SENSORS_LM25066_REGULATOR) /* LM25056 doesn't support OPERATION */ diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c index 5567d37f13fe..3b219ed5386f 100644 --- a/drivers/hwmon/pmbus/pmbus_core.c +++ b/drivers/hwmon/pmbus/pmbus_core.c @@ -45,7 +45,7 @@ module_param(wp, int, 0444); struct pmbus_sensor { struct pmbus_sensor *next; char name[PMBUS_NAME_SIZE]; /* sysfs sensor name */ - struct device_attribute attribute; + struct sensor_device_attribute attribute; u8 page; /* page number */ u8 phase; /* phase number, 0xff for all phases */ u16 reg; /* register */ @@ -68,7 +68,7 @@ struct pmbus_boolean { struct pmbus_label { char name[PMBUS_NAME_SIZE]; /* sysfs label name */ - struct device_attribute attribute; + struct sensor_device_attribute attribute; char label[PMBUS_NAME_SIZE]; /* label */ }; #define to_pmbus_label(_attr) \ @@ -1241,7 +1241,8 @@ static ssize_t pmbus_show_sensor(struct device *dev, struct device_attribute *devattr, char *buf) { struct i2c_client *client = to_i2c_client(dev->parent); - struct pmbus_sensor *sensor = to_pmbus_sensor(devattr); + struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); + struct pmbus_sensor *sensor = to_pmbus_sensor(attr); struct pmbus_data *data = i2c_get_clientdata(client); s64 val; @@ -1261,7 +1262,8 @@ static ssize_t pmbus_set_sensor(struct device *dev, { struct i2c_client *client = to_i2c_client(dev->parent); struct pmbus_data *data = i2c_get_clientdata(client); - struct pmbus_sensor *sensor = to_pmbus_sensor(devattr); + struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); + struct pmbus_sensor *sensor = to_pmbus_sensor(attr); s64 val; int ret; u16 regval; @@ -1283,7 +1285,8 @@ static ssize_t pmbus_set_sensor(struct device *dev, static ssize_t pmbus_show_label(struct device *dev, struct device_attribute *da, char *buf) { - struct pmbus_label *label = to_pmbus_label(da); + struct sensor_device_attribute *attr = to_sensor_dev_attr(da); + struct pmbus_label *label = to_pmbus_label(attr); return sysfs_emit(buf, "%s\n", label->label); } @@ -1436,8 +1439,8 @@ static struct pmbus_sensor *pmbus_add_sensor(struct pmbus_data *data, bool update, bool readonly, bool writeonly, bool convert) { + struct sensor_device_attribute *a; struct pmbus_sensor *sensor; - struct device_attribute *a; sensor = devm_kzalloc(data->dev, sizeof(*sensor), GFP_KERNEL); if (!sensor) @@ -1461,12 +1464,11 @@ static struct pmbus_sensor *pmbus_add_sensor(struct pmbus_data *data, sensor->update = update; sensor->convert = convert; sensor->data = -ENODATA; - pmbus_dev_attr_init(a, sensor->name, - readonly ? 0444 : 0644, - writeonly ? pmbus_show_zero : pmbus_show_sensor, - pmbus_set_sensor); + pmbus_attr_init(a, sensor->name, readonly ? 0444 : 0644, + writeonly ? pmbus_show_zero : pmbus_show_sensor, + pmbus_set_sensor, -1); - if (pmbus_add_attribute(data, &a->attr)) + if (pmbus_add_attribute(data, &a->dev_attr.attr)) return NULL; sensor->next = data->sensors; @@ -1483,8 +1485,8 @@ static int pmbus_add_label(struct pmbus_data *data, const char *name, int seq, const char *lstring, int index, int phase) { + struct sensor_device_attribute *a; struct pmbus_label *label; - struct device_attribute *a; label = devm_kzalloc(data->dev, sizeof(*label), GFP_KERNEL); if (!label) @@ -1508,8 +1510,8 @@ static int pmbus_add_label(struct pmbus_data *data, lstring, index, phase); } - pmbus_dev_attr_init(a, label->name, 0444, pmbus_show_label, NULL); - return pmbus_add_attribute(data, &a->attr); + pmbus_attr_init(a, label->name, 0444, pmbus_show_label, NULL, -1); + return pmbus_add_attribute(data, &a->dev_attr.attr); } /* @@ -2397,7 +2399,7 @@ struct pmbus_samples_attr { struct pmbus_samples_reg { int page; struct pmbus_samples_attr *attr; - struct device_attribute dev_attr; + struct sensor_device_attribute attribute; }; static struct pmbus_samples_attr pmbus_samples_registers[] = { @@ -2419,14 +2421,15 @@ static struct pmbus_samples_attr pmbus_samples_registers[] = { } }; -#define to_samples_reg(x) container_of(x, struct pmbus_samples_reg, dev_attr) +#define to_samples_reg(x) container_of(x, struct pmbus_samples_reg, attribute) static ssize_t pmbus_show_samples(struct device *dev, struct device_attribute *devattr, char *buf) { int val; struct i2c_client *client = to_i2c_client(dev->parent); - struct pmbus_samples_reg *reg = to_samples_reg(devattr); + struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); + struct pmbus_samples_reg *reg = to_samples_reg(attr); scoped_guard(pmbus_lock, client) { val = _pmbus_read_word_data(client, reg->page, 0xff, reg->attr->reg); @@ -2444,7 +2447,8 @@ static ssize_t pmbus_set_samples(struct device *dev, int ret; long val; struct i2c_client *client = to_i2c_client(dev->parent); - struct pmbus_samples_reg *reg = to_samples_reg(devattr); + struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); + struct pmbus_samples_reg *reg = to_samples_reg(attr); if (kstrtol(buf, 0, &val) < 0) return -EINVAL; @@ -2459,6 +2463,7 @@ static ssize_t pmbus_set_samples(struct device *dev, static int pmbus_add_samples_attr(struct pmbus_data *data, int page, struct pmbus_samples_attr *attr) { + struct sensor_device_attribute *a; struct pmbus_samples_reg *reg; reg = devm_kzalloc(data->dev, sizeof(*reg), GFP_KERNEL); @@ -2468,10 +2473,12 @@ static int pmbus_add_samples_attr(struct pmbus_data *data, int page, reg->attr = attr; reg->page = page; - pmbus_dev_attr_init(®->dev_attr, attr->name, 0644, - pmbus_show_samples, pmbus_set_samples); + a = ®->attribute; + + pmbus_attr_init(a, attr->name, 0644, + pmbus_show_samples, pmbus_set_samples, -1); - return pmbus_add_attribute(data, ®->dev_attr.attr); + return pmbus_add_attribute(data, &a->dev_attr.attr); } static int pmbus_add_samples_attributes(struct i2c_client *client, @@ -2979,9 +2986,15 @@ static void pmbus_notify(struct pmbus_data *data, int page, int reg, int flags) struct device_attribute *da = to_dev_attr(data->group.attrs[i]); struct sensor_device_attribute *attr = to_sensor_dev_attr(da); int index = attr->index; - u16 smask = pb_index_to_mask(index); - u8 spage = pb_index_to_page(index); - u16 sreg = pb_index_to_reg(index); + u16 smask, sreg; + u8 spage; + + if (index == -1) + continue; + + smask = pb_index_to_mask(index); + spage = pb_index_to_page(index); + sreg = pb_index_to_reg(index); if (reg == sreg && page == spage && (smask & flags)) { dev_dbg(data->dev, "sysfs notify: %s", da->attr.name); @@ -3427,6 +3440,8 @@ static int pmbus_write_smbalert_mask(struct i2c_client *client, u8 page, u8 reg, { int ret; + guard(pmbus_lock)(client); + ret = _pmbus_write_word_data(client, page, PMBUS_SMBALERT_MASK, reg | (val << 8)); /* @@ -3662,6 +3677,8 @@ static void pmbus_init_debugfs(struct i2c_client *client, if (!entries) return; + guard(pmbus_lock)(client); + /* * Add device-specific entries. * Please note that the PMBUS standard allows all registers to be diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index c7325226cb86..3a718d600006 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -21,6 +21,7 @@ #include <linux/init.h> #include <linux/input/mt.h> #include <linux/major.h> +#include <linux/nospec.h> #include <linux/device.h> #include <linux/cdev.h> #include "input-compat.h" @@ -67,8 +68,10 @@ static size_t evdev_get_mask_cnt(unsigned int type) [EV_SND] = SND_CNT, [EV_FF] = FF_CNT, }; + unsigned long mask = array_index_mask_nospec(type, EV_CNT); - return (type < EV_CNT) ? counts[type] : 0; + /* Returns 0 for out-of-bounds types, including speculatively */ + return counts[type & mask] & mask; } /* requires the buffer lock to be held */ @@ -146,11 +149,11 @@ static void __evdev_queue_syn_dropped(struct evdev_client *client) struct timespec64 ts = ktime_to_timespec64(ev_time[client->clk_type]); struct input_event ev; + memset(&ev, 0, sizeof(ev)); ev.input_event_sec = ts.tv_sec; ev.input_event_usec = ts.tv_nsec / NSEC_PER_USEC; ev.type = EV_SYN; ev.code = SYN_DROPPED; - ev.value = 0; client->buffer[client->head++] = ev; client->head &= client->bufsize - 1; @@ -218,20 +221,20 @@ static void __pass_event(struct evdev_client *client, client->head &= client->bufsize - 1; if (unlikely(client->head == client->tail)) { + struct input_event ev; + + memset(&ev, 0, sizeof(ev)); + ev.input_event_sec = event->input_event_sec; + ev.input_event_usec = event->input_event_usec; + ev.type = EV_SYN; + ev.code = SYN_DROPPED; + /* * This effectively "drops" all unconsumed events, leaving * EV_SYN/SYN_DROPPED plus the newest event in the queue. */ client->tail = (client->head - 2) & (client->bufsize - 1); - - client->buffer[client->tail] = (struct input_event) { - .input_event_sec = event->input_event_sec, - .input_event_usec = event->input_event_usec, - .type = EV_SYN, - .code = SYN_DROPPED, - .value = 0, - }; - + client->buffer[client->tail] = ev; client->packet_head = client->tail; } @@ -253,6 +256,8 @@ static void evdev_pass_values(struct evdev_client *client, if (client->revoked) return; + memset(&event, 0, sizeof(event)); + ts = ktime_to_timespec64(ev_time[client->clk_type]); event.input_event_sec = ts.tv_sec; event.input_event_usec = ts.tv_nsec / NSEC_PER_USEC; diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index f3a49384586d..eb6c2a78d3c7 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -492,6 +492,7 @@ static void fastrpc_channel_ctx_free(struct kref *ref) cctx = container_of(ref, struct fastrpc_channel_ctx, refcount); + idr_destroy(&cctx->ctx_idr); kfree(cctx); } @@ -1305,10 +1306,12 @@ bail: } if (err == -ERESTARTSYS) { + spin_lock(&fl->lock); list_for_each_entry_safe(buf, b, &fl->mmaps, node) { list_del(&buf->node); list_add_tail(&buf->node, &fl->cctx->invoke_interrupted_mmaps); } + spin_unlock(&fl->lock); } if (err) @@ -1370,7 +1373,9 @@ static int fastrpc_init_create_static_process(struct fastrpc_user *fl, err = PTR_ERR(name); goto err; } - + inbuf.client_id = fl->client_id; + inbuf.namelen = init.namelen; + inbuf.pageslen = 0; if (!fl->cctx->remote_heap) { err = fastrpc_remote_heap_alloc(fl, fl->sctx->dev, init.memlen, &fl->cctx->remote_heap); @@ -1393,12 +1398,10 @@ static int fastrpc_init_create_static_process(struct fastrpc_user *fl, goto err_map; } scm_done = true; + inbuf.pageslen = 1; } } - inbuf.client_id = fl->client_id; - inbuf.namelen = init.namelen; - inbuf.pageslen = 0; fl->pd = USER_PD; args[0].ptr = (u64)(uintptr_t)&inbuf; @@ -1673,7 +1676,7 @@ static int fastrpc_device_open(struct inode *inode, struct file *filp) dev_err(&cctx->rpdev->dev, "No session available\n"); mutex_destroy(&fl->mutex); kfree(fl); - + fastrpc_channel_ctx_put(cctx); return -EBUSY; } @@ -1889,9 +1892,6 @@ static int fastrpc_req_munmap_impl(struct fastrpc_user *fl, struct fastrpc_buf * &args[0]); if (!err) { dev_dbg(dev, "unmmap\tpt 0x%09lx OK\n", buf->raddr); - spin_lock(&fl->lock); - list_del(&buf->node); - spin_unlock(&fl->lock); fastrpc_buf_free(buf); } else { dev_err(dev, "unmmap\tpt 0x%09lx ERROR\n", buf->raddr); @@ -1905,6 +1905,7 @@ static int fastrpc_req_munmap(struct fastrpc_user *fl, char __user *argp) struct fastrpc_buf *buf = NULL, *iter, *b; struct fastrpc_req_munmap req; struct device *dev = fl->sctx->dev; + int err; if (copy_from_user(&req, argp, sizeof(req))) return -EFAULT; @@ -1912,6 +1913,7 @@ static int fastrpc_req_munmap(struct fastrpc_user *fl, char __user *argp) spin_lock(&fl->lock); list_for_each_entry_safe(iter, b, &fl->mmaps, node) { if ((iter->raddr == req.vaddrout) && (iter->size == req.size)) { + list_del(&iter->node); buf = iter; break; } @@ -1924,7 +1926,14 @@ static int fastrpc_req_munmap(struct fastrpc_user *fl, char __user *argp) return -EINVAL; } - return fastrpc_req_munmap_impl(fl, buf); + err = fastrpc_req_munmap_impl(fl, buf); + if (err) { + spin_lock(&fl->lock); + list_add_tail(&buf->node, &fl->mmaps); + spin_unlock(&fl->lock); + } + + return err; } static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp) diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 643b0039cc72..26d2b2742d50 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -425,18 +425,24 @@ static void mei_io_tx_list_free_cl(struct list_head *head, } /** - * mei_io_list_free_fp - free cb from a list that matches file pointer + * mei_io_rd_list_free_fp - free cb from a rd_completed list that matches file pointer * - * @head: io list + * @cl: host client * @fp: file pointer (matching cb file object), may be NULL */ -static void mei_io_list_free_fp(struct list_head *head, const struct file *fp) +static void mei_io_rd_list_free_fp(struct mei_cl *cl, const struct file *fp) { struct mei_cl_cb *cb, *next; + LIST_HEAD(cmpl_list); - list_for_each_entry_safe(cb, next, head, list) + spin_lock(&cl->rd_completed_lock); + list_for_each_entry_safe(cb, next, &cl->rd_completed, list) if (!fp || fp == cb->fp) - mei_io_cb_free(cb); + list_move(&cb->list, &cmpl_list); + spin_unlock(&cl->rd_completed_lock); + + list_for_each_entry_safe(cb, next, &cmpl_list, list) + mei_io_cb_free(cb); } /** @@ -565,9 +571,7 @@ int mei_cl_flush_queues(struct mei_cl *cl, const struct file *fp) mei_io_list_flush_cl(&cl->dev->ctrl_rd_list, cl); mei_cl_free_pending(cl); } - spin_lock(&cl->rd_completed_lock); - mei_io_list_free_fp(&cl->rd_completed, fp); - spin_unlock(&cl->rd_completed_lock); + mei_io_rd_list_free_fp(cl, fp); return 0; } @@ -1401,7 +1405,7 @@ void mei_cl_add_rd_completed(struct mei_cl *cl, struct mei_cl_cb *cb) } /** - * mei_cl_del_rd_completed - free read completed callback with lock + * mei_cl_del_rd_completed - unlink read completed callback with lock and free it * * @cl: host client * @cb: callback block @@ -1410,8 +1414,9 @@ void mei_cl_add_rd_completed(struct mei_cl *cl, struct mei_cl_cb *cb) void mei_cl_del_rd_completed(struct mei_cl *cl, struct mei_cl_cb *cb) { spin_lock(&cl->rd_completed_lock); - mei_io_cb_free(cb); + list_del_init(&cb->list); spin_unlock(&cl->rd_completed_lock); + mei_io_cb_free(cb); } /** diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 2d37b07c8215..839f7482dc18 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1534,8 +1534,8 @@ void bond_alb_monitor(struct work_struct *work) struct bonding *bond = container_of(work, struct bonding, alb_work.work); struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); + struct slave *slave, *curr; struct list_head *iter; - struct slave *slave; if (!bond_has_slaves(bond)) { atomic_set(&bond_info->tx_rebalance_counter, 0); @@ -1597,9 +1597,11 @@ void bond_alb_monitor(struct work_struct *work) * because a slave was disabled then * it can now leave promiscuous mode. */ - dev_set_promiscuity(rtnl_dereference(bond->curr_active_slave)->dev, - -1); - bond_info->primary_is_promisc = 0; + curr = rtnl_dereference(bond->curr_active_slave); + if (bond_info->primary_is_promisc && curr) { + dev_set_promiscuity(curr->dev, -1); + bond_info->primary_is_promisc = 0; + } rtnl_unlock(); rcu_read_lock(); diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h index 4a6b35c84dab..2449e19321f7 100644 --- a/drivers/net/ethernet/amd/pds_core/core.h +++ b/drivers/net/ethernet/amd/pds_core/core.h @@ -171,6 +171,7 @@ struct pdsc { struct timer_list wdtimer; unsigned int wdtimer_period; struct work_struct health_work; + bool health_stopped; struct devlink_health_reporter *fw_reporter; u32 fw_recoveries; diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c index 8d94a4d70395..9a2c64198d03 100644 --- a/drivers/net/ethernet/amd/pds_core/main.c +++ b/drivers/net/ethernet/amd/pds_core/main.c @@ -470,8 +470,10 @@ static void pdsc_stop_health_thread(struct pdsc *pdsc) return; timer_shutdown_sync(&pdsc->wdtimer); - if (pdsc->health_work.func) - cancel_work_sync(&pdsc->health_work); + if (pdsc->health_work.func && !pdsc->health_stopped) { + disable_work_sync(&pdsc->health_work); + pdsc->health_stopped = true; + } } static void pdsc_restart_health_thread(struct pdsc *pdsc) @@ -479,6 +481,10 @@ static void pdsc_restart_health_thread(struct pdsc *pdsc) if (pdsc->pdev->is_virtfn) return; + if (pdsc->health_stopped) { + enable_work(&pdsc->health_work); + pdsc->health_stopped = false; + } timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0); mod_timer(&pdsc->wdtimer, jiffies + 1); } @@ -555,7 +561,11 @@ static pci_ers_result_t pdsc_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t error) { if (error == pci_channel_io_frozen) { + struct pdsc *pdsc = pci_get_drvdata(pdev); + pdsc_reset_prepare(pdev); + if (!pdev->is_virtfn) + cancel_work_sync(&pdsc->pci_reset_work); return PCI_ERS_RESULT_NEED_RESET; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index e270327e47fd..9820b9f8c210 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -336,6 +336,35 @@ out: return !!budget; } +void aq_ring_tx_deinit(struct aq_ring_s *self) +{ + if (!self) + return; + + for (; self->sw_head != self->sw_tail; + self->sw_head = aq_ring_next_dx(self, self->sw_head)) { + struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head]; + struct device *ndev = aq_nic_get_dev(self->aq_nic); + + if (buff->is_mapped) { + if (buff->is_sop) { + dma_unmap_single(ndev, buff->pa, buff->len, + DMA_TO_DEVICE); + } else { + dma_unmap_page(ndev, buff->pa, buff->len, + DMA_TO_DEVICE); + } + } + + if (buff->is_eop) { + if (buff->skb) + dev_kfree_skb_any(buff->skb); + else if (buff->xdpf) + xdp_return_frame(buff->xdpf); + } + } +} + static void aq_rx_checksum(struct aq_ring_s *self, struct aq_ring_buff_s *buff, struct sk_buff *skb) @@ -897,15 +926,29 @@ err_exit: void aq_ring_rx_deinit(struct aq_ring_s *self) { - if (!self) + unsigned int i; + + if (!self || !self->buff_ring) return; - for (; self->sw_head != self->sw_tail; - self->sw_head = aq_ring_next_dx(self, self->sw_head)) { - struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head]; + /* Release every page still owned by the ring. + * + * Walking [sw_head, sw_tail) is not enough: refill is batched + * (aq_ring_rx_fill() waits for AQ_CFG_RX_REFILL_THRES free slots), + * so slots that were cleaned but not yet reposted accumulate in the + * [sw_tail, sw_head) gap, and they keep their page for reuse. Walk + * the whole ring and release whatever is left. + */ + for (i = 0; i < self->size; i++) { + struct aq_ring_buff_s *buff = &self->buff_ring[i]; + + if (!buff->rxdata.page) + continue; aq_free_rxpage(&buff->rxdata, aq_nic_get_dev(self->aq_nic)); } + + self->sw_head = self->sw_tail; } void aq_ring_free(struct aq_ring_s *self) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h index d627ace850ff..67503c512676 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h @@ -199,6 +199,7 @@ void aq_ring_update_queue_state(struct aq_ring_s *ring); void aq_ring_queue_wake(struct aq_ring_s *ring); void aq_ring_queue_stop(struct aq_ring_s *ring); bool aq_ring_tx_clean(struct aq_ring_s *self); +void aq_ring_tx_deinit(struct aq_ring_s *self); int aq_xdp_xmit(struct net_device *dev, int num_frames, struct xdp_frame **frames, u32 flags); int aq_ring_rx_clean(struct aq_ring_s *self, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c index 2f9033ceed8c..05814fea0f5f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c @@ -275,7 +275,7 @@ void aq_vec_deinit(struct aq_vec_s *self) for (i = 0U; self->tx_rings > i; ++i) { ring = self->ring[i]; - aq_ring_tx_clean(&ring[AQ_VEC_TX_ID]); + aq_ring_tx_deinit(&ring[AQ_VEC_TX_ID]); aq_ring_rx_deinit(&ring[AQ_VEC_RX_ID]); } diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_auxr.c b/drivers/net/ethernet/broadcom/bnge/bnge_auxr.c index 67e93e17d4d9..0955b488b6fe 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_auxr.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_auxr.c @@ -141,12 +141,15 @@ static void bnge_aux_dev_release(struct device *dev) { struct bnge_auxr_priv *aux_priv = container_of(dev, struct bnge_auxr_priv, aux_dev.dev); - struct bnge_dev *bd = pci_get_drvdata(aux_priv->auxr_dev->pdev); + struct bnge_auxr_dev *auxr_dev = aux_priv->auxr_dev; + struct bnge_dev *bd = pci_get_drvdata(to_pci_dev(dev->parent)); ida_free(&bnge_aux_dev_ids, aux_priv->id); - kfree(aux_priv->auxr_dev->auxr_info); + if (auxr_dev) { + kfree(auxr_dev->auxr_info); + kfree(auxr_dev); + } bd->auxr_dev = NULL; - kfree(aux_priv->auxr_dev); kfree(aux_priv); bd->aux_priv = NULL; } diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c index 6f7ef506d4e1..ac4c93e5b634 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c @@ -2768,8 +2768,6 @@ static int bnge_init_nic(struct bnge_net *bn) err_free_ring_grps: bnge_free_ring_grps(bn); - return rc; - err_free_rx_ring_pair_bufs: bnge_free_rx_ring_pair_bufs(bn); return rc; diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_resc.c b/drivers/net/ethernet/broadcom/bnge/bnge_resc.c index 0e94f092813e..4711dd4945ff 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_resc.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_resc.c @@ -163,7 +163,8 @@ static int bnge_adjust_rings(struct bnge_dev *bd, u16 *rx, u16 tx_chunks = bnge_num_tx_to_cp(bd, *tx); if (tx_chunks != *tx) { - u16 tx_saved = tx_chunks, rc; + u16 tx_saved = tx_chunks; + int rc; rc = bnge_fix_rings_count(rx, &tx_chunks, max_nq, sh); if (rc) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index d44d3ac255aa..1cd6e88d4e81 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4611,11 +4611,14 @@ static void bnxt_init_one_rx_agg_ring_rxbd(struct bnxt *bp, type = ((u32)rxr->rx_page_size << RX_BD_LEN_SHIFT) | RX_BD_TYPE_RX_AGG_BD; - /* On P7, setting EOP will cause the chip to disable - * Relaxed Ordering (RO) for TPA data. Disable EOP for - * potentially higher performance with RO. + /* Disable EOP if TPA is enabled to prevent overlapping zero + * padding with the next segment's data. On P7_PLUS, EOP will + * automatically disable Relaxed Ordering (RO) to prevent + * potential data corruption (and may degrade performance). On + * older chips, RO will not be automatically disabled and may + * cause corruption. */ - if (BNXT_CHIP_P5_AND_MINUS(bp) || !(bp->flags & BNXT_FLAG_TPA)) + if (!(bp->flags & BNXT_FLAG_TPA)) type |= RX_BD_FLAGS_AGG_EOP; bnxt_init_rxbd_pages(ring, type); @@ -6704,22 +6707,36 @@ int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings) static void bnxt_fill_hw_rss_tbl(struct bnxt *bp, struct bnxt_vnic_info *vnic) { bool no_rss = !(vnic->flags & BNXT_VNIC_RSS_FLAG); - u16 i, j; + u16 i, j, min_j = bp->rx_nr_rings - 1; + + if (!vnic->rss_table) + goto skip_rss_tbl; /* Fill the RSS indirection table with ring group ids */ for (i = 0, j = 0; i < HW_HASH_INDEX_SIZE; i++) { if (!no_rss) j = bp->rss_indir_tbl[i]; + min_j = min(j, min_j); vnic->rss_table[i] = cpu_to_le16(vnic->fw_grp_ids[j]); } + +skip_rss_tbl: + if (vnic->rss_table && !no_rss) + vnic->default_rx_ring = min_j; + else if (vnic->flags & BNXT_VNIC_RFS_FLAG) + vnic->default_rx_ring = vnic->vnic_id - 1; + else if ((vnic->vnic_id == 1) && BNXT_CHIP_TYPE_NITRO_A0(bp)) + vnic->default_rx_ring = bp->rx_nr_rings - 1; + else + vnic->default_rx_ring = 0; } static void bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic) { + u16 tbl_size, i, min_j = bp->rx_nr_rings - 1; __le16 *ring_tbl = vnic->rss_table; struct bnxt_rx_ring_info *rxr; - u16 tbl_size, i; tbl_size = bnxt_get_rxfh_indir_size(bp->dev); @@ -6732,6 +6749,7 @@ static void bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp, j = ethtool_rxfh_context_indir(vnic->rss_ctx)[i]; else j = bp->rss_indir_tbl[i]; + min_j = min(j, min_j); rxr = &bp->rx_ring[j]; ring_id = rxr->rx_ring_struct.fw_ring_id; @@ -6739,19 +6757,15 @@ static void bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp, ring_id = bnxt_cp_ring_for_rx(bp, rxr); *ring_tbl++ = cpu_to_le16(ring_id); } + vnic->default_rx_ring = min_j; } static void __bnxt_hwrm_vnic_set_rss(struct bnxt *bp, struct hwrm_vnic_rss_cfg_input *req, struct bnxt_vnic_info *vnic) { - if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { - bnxt_fill_hw_rss_tbl_p5(bp, vnic); - if (bp->flags & BNXT_FLAG_CHIP_P7) - req->flags |= VNIC_RSS_CFG_REQ_FLAGS_IPSEC_HASH_TYPE_CFG_SUPPORT; - } else { - bnxt_fill_hw_rss_tbl(bp, vnic); - } + if (bp->flags & BNXT_FLAG_CHIP_P7) + req->flags |= VNIC_RSS_CFG_REQ_FLAGS_IPSEC_HASH_TYPE_CFG_SUPPORT; if (bp->rss_hash_delta) { req->hash_type = cpu_to_le32(bp->rss_hash_delta); @@ -6803,6 +6817,7 @@ static int bnxt_hwrm_vnic_set_rss_p5(struct bnxt *bp, if (!set_rss) return hwrm_req_send(bp, req); + bnxt_fill_hw_rss_tbl_p5(bp, vnic); __bnxt_hwrm_vnic_set_rss(bp, req, vnic); ring_tbl_map = vnic->rss_table_dma_addr; nr_ctxs = bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings); @@ -6939,8 +6954,9 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic) return rc; if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { - struct bnxt_rx_ring_info *rxr = &bp->rx_ring[0]; + struct bnxt_rx_ring_info *rxr; + rxr = &bp->rx_ring[vnic->default_rx_ring]; req->default_rx_ring_id = cpu_to_le16(rxr->rx_ring_struct.fw_ring_id); req->default_cmpl_ring_id = @@ -6973,13 +6989,7 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic) req->cos_rule = cpu_to_le16(0xffff); } - if (vnic->flags & BNXT_VNIC_RSS_FLAG) - ring = 0; - else if (vnic->flags & BNXT_VNIC_RFS_FLAG) - ring = vnic->vnic_id - 1; - else if ((vnic->vnic_id == 1) && BNXT_CHIP_TYPE_NITRO_A0(bp)) - ring = bp->rx_nr_rings - 1; - + ring = vnic->default_rx_ring; grp_idx = bp->rx_ring[ring].bnapi->index; req->dflt_ring_grp = cpu_to_le16(bp->grp_info[grp_idx].fw_grp_id); req->lb_rule = cpu_to_le16(0xffff); @@ -10866,6 +10876,7 @@ static int __bnxt_setup_vnic(struct bnxt *bp, struct bnxt_vnic_info *vnic) } skip_rss_ctx: + bnxt_fill_hw_rss_tbl(bp, vnic); /* configure default vnic, ring grp */ rc = bnxt_hwrm_vnic_cfg(bp, vnic); if (rc) { @@ -11090,6 +11101,11 @@ static int bnxt_set_vnic_mru_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic, vnic->vnic_id, rc); return rc; } + if (rxr_id == vnic->default_rx_ring) { + rc = bnxt_hwrm_vnic_cfg(bp, vnic); + if (rc) + return rc; + } } vnic->mru = mru; bnxt_hwrm_vnic_update(bp, vnic, @@ -11171,6 +11187,9 @@ static int bnxt_setup_nitroa0_vnic(struct bnxt *bp) return rc; } + /* Setup the proper default RX ring */ + bnxt_fill_hw_rss_tbl(bp, vnic); + rc = bnxt_hwrm_vnic_cfg(bp, vnic); if (rc) { netdev_err(bp->dev, "Cannot allocate special vnic for NS2 A0: %x\n", @@ -16225,6 +16244,7 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, clone->rx_next_cons = 0; clone->need_head_pool = false; clone->rx_page_size = qcfg->rx_page_size; + clone->rx_agg_bmap = NULL; rc = bnxt_alloc_rx_page_pool(bp, clone, rxr->page_pool->p.nid); if (rc) @@ -16277,6 +16297,8 @@ err_free_tpa_info: bnxt_free_one_tpa_info(bp, clone); err_free_rx_agg_ring: bnxt_free_ring(bp, &clone->rx_agg_ring_struct.ring_mem); + kfree(clone->rx_agg_bmap); + clone->rx_agg_bmap = NULL; err_free_rx_ring: bnxt_free_ring(bp, &clone->rx_ring_struct.ring_mem); err_rxq_info_unreg: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index fa13cee55779..8e04cc934c32 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1334,6 +1334,7 @@ struct bnxt_vnic_info { #define BNXT_VNIC_RSSCTX_FLAG 0x40 struct ethtool_rxfh_context *rss_ctx; u32 vnic_id; + u16 default_rx_ring; }; struct bnxt_rss_ctx { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 5d41dc1bc782..b89293dfd2d1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -495,12 +495,15 @@ static int bnxt_ptp_enable(struct ptp_clock_info *ptp_info, return rc; case PTP_CLK_REQ_PPS: /* Configure PHC PPS IN */ - rc = bnxt_ptp_cfg_pin(bp, 0, BNXT_PPS_PIN_PPS_IN); + pin_id = 0; + if (!on) + break; + rc = bnxt_ptp_cfg_pin(bp, pin_id, BNXT_PPS_PIN_PPS_IN); if (rc) return rc; rc = bnxt_ptp_cfg_event(bp, BNXT_PPS_EVENT_INTERNAL); if (!rc) - ptp->pps_info.pins[0].event = BNXT_PPS_EVENT_INTERNAL; + ptp->pps_info.pins[pin_id].event = BNXT_PPS_EVENT_INTERNAL; return rc; default: netdev_err(ptp->bp->dev, "Unrecognized PIN function\n"); diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index e7125b818087..d98f7e7ccab9 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -3011,8 +3011,9 @@ static void enic_remove(struct pci_dev *pdev) if (netdev) { struct enic *enic = netdev_priv(netdev); - cancel_work_sync(&enic->reset); - cancel_work_sync(&enic->change_mtu_work); + disable_work_sync(&enic->reset); + disable_work_sync(&enic->tx_hang_reset); + disable_work_sync(&enic->change_mtu_work); unregister_netdev(netdev); enic_dev_deinit(enic); vnic_dev_close(enic->vdev); diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c index e3e7f2270560..02282dc86faf 100644 --- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c +++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c @@ -1282,7 +1282,6 @@ static void hix5hd2_dev_remove(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct hix5hd2_priv *priv = netdev_priv(ndev); - netif_napi_del(&priv->napi); unregister_netdev(ndev); mdiobus_unregister(priv->bus); mdiobus_free(priv->bus); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 2a6e4d17452c..13c20a8ca3b0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -11926,12 +11926,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) if (ret) goto err_ptp_uninit; - if (hdev->hw.mac.media_type != HNAE3_MEDIA_TYPE_COPPER) { + if (hdev->hw.mac.media_type != HNAE3_MEDIA_TYPE_COPPER) hdev->hw.mac.req_autoneg = hdev->hw.mac.autoneg; - if (hdev->hw.mac.autoneg == AUTONEG_DISABLE && - hdev->hw.mac.speed != SPEED_UNKNOWN) - hdev->hw.mac.req_speed = hdev->hw.mac.speed; - } ret = hclge_set_autoneg_speed_dup(hdev); if (ret) { diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index c0508d261592..e606bfb211cb 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -3082,7 +3082,7 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) meta_req.tx_buffer = bi; meta_req.meta = meta; meta_req.used_desc = 0; - xsk_tx_metadata_request(meta, &igc_xsk_tx_metadata_ops, + xsk_tx_metadata_request(pool, &meta, &igc_xsk_tx_metadata_ops, &meta_req); /* xsk_tx_metadata_request() may have updated next_to_use */ @@ -7585,11 +7585,13 @@ static int __igc_resume(struct device *dev, bool rpm) err = __igc_open(netdev, true); if (!rpm) rtnl_unlock(); - if (!err) - netif_device_attach(netdev); + if (err) + return err; } - return err; + netif_device_attach(netdev); + + return 0; } static int igc_resume(struct device *dev) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 0b46ec29e64e..039fd47ebf52 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -54,10 +54,12 @@ static void otx2_get_egress_burst_cfg(struct otx2_nic *nic, u32 burst, if (burst) { *burst_exp = ilog2(burst) ? ilog2(burst) - 1 : 0; tmp = burst - rounddown_pow_of_two(burst); - if (burst < max_mantissa) + if (burst <= max_mantissa) { *burst_mantissa = tmp * 2; - else + } else { + WARN_ON(*burst_exp < 7); *burst_mantissa = tmp / (1ULL << (*burst_exp - 7)); + } } else { *burst_exp = MAX_BURST_EXPONENT; *burst_mantissa = max_mantissa; diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c index 2989a77e3b42..1ad0e62a8433 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c @@ -684,6 +684,9 @@ static int prestera_fw_hdr_parse(struct prestera_fw *fw) struct prestera_fw_header *hdr; u32 magic; + if (fw->bin->size < sizeof(*hdr)) + return -EINVAL; + hdr = (struct prestera_fw_header *)fw->bin->data; magic = be32_to_cpu(hdr->magic_number); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index adcc73e2a5b3..1493d8106c1a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -1025,13 +1025,11 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev) tracer = kvzalloc_obj(*tracer); if (!tracer) - return ERR_PTR(-ENOMEM); + return NULL; tracer->work_queue = create_singlethread_workqueue("mlx5_fw_tracer"); - if (!tracer->work_queue) { - err = -ENOMEM; + if (!tracer->work_queue) goto free_tracer; - } tracer->dev = dev; @@ -1073,7 +1071,7 @@ destroy_workqueue: destroy_workqueue(tracer->work_queue); free_tracer: kvfree(tracer); - return ERR_PTR(err); + return NULL; } static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data); @@ -1084,7 +1082,7 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) struct mlx5_core_dev *dev; int err; - if (IS_ERR_OR_NULL(tracer)) + if (!tracer) return 0; if (!tracer->str_db.loaded) @@ -1134,7 +1132,7 @@ err_cancel_work: /* Stop tracer + Cleanup HW resources */ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer) { - if (IS_ERR_OR_NULL(tracer)) + if (!tracer) return; mutex_lock(&tracer->state_lock); @@ -1163,7 +1161,7 @@ unlock: /* Free software resources (Buffers, etc ..) */ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer) { - if (IS_ERR_OR_NULL(tracer)) + if (!tracer) return; mlx5_core_dbg(tracer->dev, "FWTracer: Destroy\n"); @@ -1215,7 +1213,7 @@ int mlx5_fw_tracer_reload(struct mlx5_fw_tracer *tracer) struct mlx5_core_dev *dev; int err; - if (IS_ERR_OR_NULL(tracer)) + if (!tracer) return 0; dev = tracer->dev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 6867a5aed42c..822859c360e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -483,7 +483,7 @@ typedef int (*mlx5e_fp_xmit_xdp_frame_check)(struct mlx5e_xdpsq *); typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq *, struct mlx5e_xmit_data *, int, - struct xsk_tx_metadata *); + struct xsk_tx_metadata **); struct mlx5e_xdpsq { /* data path */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index efb34de4cb7a..692ac2f21d94 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -30,6 +30,7 @@ enum { MLX5E_TC_FLOW_FLAG_FAILED = MLX5E_TC_FLOW_BASE + 9, MLX5E_TC_FLOW_FLAG_SAMPLE = MLX5E_TC_FLOW_BASE + 10, MLX5E_TC_FLOW_FLAG_USE_ACT_STATS = MLX5E_TC_FLOW_BASE + 11, + MLX5E_TC_FLOW_FLAG_PEER = MLX5E_TC_FLOW_BASE + 12, }; struct mlx5e_tc_flow_parse_attr { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index d8c7cb8837d7..77ea51bfbaae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -452,11 +452,11 @@ INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq INDIRECT_CALLABLE_SCOPE bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, - int check_result, struct xsk_tx_metadata *meta); + int check_result, struct xsk_tx_metadata **meta); INDIRECT_CALLABLE_SCOPE bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, - int check_result, struct xsk_tx_metadata *meta) + int check_result, struct xsk_tx_metadata **meta) { struct mlx5e_tx_mpwqe *session = &sq->mpwqe; struct mlx5e_xdpsq_stats *stats = sq->stats; @@ -504,7 +504,10 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptx * and it's safe to complete it at any time. */ mlx5e_xdp_mpwqe_session_start(sq); - xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, &session->wqe->eth); + if (meta) + xsk_tx_metadata_request(sq->xsk_pool, meta, + &mlx5e_xsk_tx_metadata_ops, + &session->wqe->eth); } mlx5e_xdp_mpwqe_add_dseg(sq, p, stats); @@ -535,7 +538,7 @@ INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq) INDIRECT_CALLABLE_SCOPE bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, - int check_result, struct xsk_tx_metadata *meta) + int check_result, struct xsk_tx_metadata **meta) { struct mlx5e_xmit_data_frags *xdptxdf = container_of(xdptxd, struct mlx5e_xmit_data_frags, xd); @@ -649,7 +652,9 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, sq->pc += num_wqebbs; - xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, eseg); + if (meta) + xsk_tx_metadata_request(sq->xsk_pool, meta, + &mlx5e_xsk_tx_metadata_ops, eseg); sq->doorbell_cseg = cseg; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index 3c54f8962664..5b8f4094d553 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -114,11 +114,11 @@ extern const struct xsk_tx_metadata_ops mlx5e_xsk_tx_metadata_ops; INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, int check_result, - struct xsk_tx_metadata *meta)); + struct xsk_tx_metadata **meta)); INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, int check_result, - struct xsk_tx_metadata *meta)); + struct xsk_tx_metadata **meta)); INDIRECT_CALLABLE_DECLARE(int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq)); INDIRECT_CALLABLE_DECLARE(int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index 8aeab4b21035..3d19dad8f868 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -105,7 +105,7 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) ret = INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe, mlx5e_xmit_xdp_frame, sq, &xdptxd, - check_result, meta); + check_result, &meta); if (unlikely(!ret)) { if (sq->mpwqe.wqe) mlx5e_xdp_mpwqe_complete(sq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 7d1063c7bf64..22ae49af38cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1939,8 +1939,10 @@ err_free_txqsq: void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) { sq->txq = netdev_get_tx_queue(sq->netdev, sq->txq_ix); + /* Reset BQL only when the SQ has no bytes in flight. */ + if (sq->cc == sq->pc) + netdev_tx_reset_queue(sq->txq); set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); - netdev_tx_reset_queue(sq->txq); netif_tx_start_queue(sq->txq); netif_queue_set_napi(sq->netdev, sq->txq_ix, NETDEV_QUEUE_TYPE_TX, sq->cq.napi); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 8b5a421a22a3..f3d4586e09e3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2165,7 +2165,8 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, if (mlx5e_is_eswitch_flow(flow)) { struct mlx5_devcom_comp_dev *devcom = flow->priv->mdev->priv.eswitch->devcom; - if (!mlx5_devcom_for_each_peer_begin(devcom)) { + if (flow_flag_test(flow, PEER) || + !mlx5_devcom_for_each_peer_begin(devcom)) { mlx5e_tc_del_fdb_flow(priv, flow); return; } @@ -4605,6 +4606,7 @@ static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f, else in_mdev = priv->mdev; + flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_PEER); parse_attr = flow->attr->parse_attr; peer_flow = __mlx5e_add_fdb_flow(peer_priv, f, flow_flags, parse_attr->filter_dev, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f28367fbcaf8..84e783f87b3d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2748,8 +2748,8 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget) meta_req.set_ic = &set_ic; meta_req.tbs = tx_q->tbs; meta_req.edesc = &tx_q->dma_entx[entry]; - xsk_tx_metadata_request(meta, &stmmac_xsk_tx_metadata_ops, - &meta_req); + xsk_tx_metadata_request(pool, &meta, + &stmmac_xsk_tx_metadata_ops, &meta_req); if (set_ic) { tx_q->tx_count_frames = 0; stmmac_set_tx_ic(priv, tx_desc); @@ -4132,6 +4132,15 @@ static int __stmmac_open(struct net_device *dev, dma_conf->tx_queue[i].tbs = priv->dma_conf.tx_queue[i].tbs; memcpy(&priv->dma_conf, dma_conf, sizeof(*dma_conf)); + /* The PHY is suspended when the interface is reopened without + * disconnecting the PHY, e.g. on MTU change. IEEE 802.3 allows PHYs + * to stop their receive clock while powered down, but the DMA + * software reset in stmmac_hw_setup() requires a running receive + * clock, and phylink_start() below resumes the PHY only after the + * hardware setup. Resume a suspended PHY here first. + */ + phylink_prepare_resume(priv->phylink); + stmmac_reset_queues_param(priv); ret = stmmac_hw_setup(dev); diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index c3a6ba96fc8a..029a4a532a10 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -127,8 +127,8 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, { struct ntb_netdev_queue *q = qp_data; struct ntb_netdev *dev = q->ntdev; + struct sk_buff *skb, *new_skb; struct net_device *ndev; - struct sk_buff *skb; int rc; ndev = dev->ndev; @@ -144,6 +144,12 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, goto enqueue_again; } + new_skb = netdev_alloc_skb(ndev, ndev->mtu + ETH_HLEN); + if (!new_skb) { + ndev->stats.rx_dropped++; + goto enqueue_again; + } + skb_put(skb, len); skb->protocol = eth_type_trans(skb, ndev); skb->ip_summed = CHECKSUM_NONE; @@ -157,12 +163,7 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, ndev->stats.rx_bytes += len; } - skb = netdev_alloc_skb(ndev, ndev->mtu + ETH_HLEN); - if (!skb) { - ndev->stats.rx_errors++; - ndev->stats.rx_frame_errors++; - return; - } + skb = new_skb; enqueue_again: rc = ntb_transport_rx_enqueue(qp, skb, skb->data, ndev->mtu + ETH_HLEN); diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c index 9993c1dfe471..168cfe9b59a9 100644 --- a/drivers/net/ovpn/main.c +++ b/drivers/net/ovpn/main.c @@ -35,25 +35,11 @@ static void ovpn_priv_free(struct net_device *net) static int ovpn_mp_alloc(struct ovpn_priv *ovpn) { - struct in_device *dev_v4; int i; if (ovpn->mode != OVPN_MODE_MP) return 0; - dev_v4 = __in_dev_get_rtnl(ovpn->dev); - if (dev_v4) { - /* disable redirects as Linux gets confused by ovpn - * handling same-LAN routing. - * This happens because a multipeer interface is used as - * relay point between hosts in the same subnet, while - * in a classic LAN this would not be needed because the - * two hosts would be able to talk directly. - */ - IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false); - IPV4_DEVCONF_ALL(dev_net(ovpn->dev), SEND_REDIRECTS) = false; - } - /* the peer container is fairly large, therefore we allocate it only in * MP mode */ @@ -97,9 +83,38 @@ static void ovpn_net_uninit(struct net_device *dev) gro_cells_destroy(&ovpn->gro_cells); } +static int ovpn_net_open(struct net_device *dev) +{ + struct ovpn_priv *ovpn = netdev_priv(dev); + struct in_device *dev_v4; + + /* the IPv4 in_device (and thus its config) is recreated whenever the + * interface is moved to a new netns, so redirects must be disabled on + * every bring-up rather than once at creation time, otherwise the + * setting is silently lost after such a move + */ + if (ovpn->mode == OVPN_MODE_MP) { + dev_v4 = __in_dev_get_rtnl(dev); + if (dev_v4) { + /* disable redirects as Linux gets confused by ovpn + * handling same-LAN routing. + * This happens because a multipeer interface is used as + * relay point between hosts in the same subnet, while + * in a classic LAN this would not be needed because the + * two hosts would be able to talk directly. + */ + IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false); + IPV4_DEVCONF_ALL(dev_net(dev), SEND_REDIRECTS) = false; + } + } + + return 0; +} + static const struct net_device_ops ovpn_netdev_ops = { .ndo_init = ovpn_net_init, .ndo_uninit = ovpn_net_uninit, + .ndo_open = ovpn_net_open, .ndo_start_xmit = ovpn_net_xmit, }; @@ -183,6 +198,7 @@ static int ovpn_newlink(struct net_device *dev, struct ovpn_priv *ovpn = netdev_priv(dev); struct nlattr **data = params->data; enum ovpn_mode mode = OVPN_MODE_P2P; + int ret; if (data && data[IFLA_OVPN_MODE]) { mode = nla_get_u8(data[IFLA_OVPN_MODE]); @@ -207,7 +223,17 @@ static int ovpn_newlink(struct net_device *dev, else netif_carrier_off(dev); - return register_netdevice(dev); + ret = register_netdevice(dev); + if (ret < 0) + return ret; + + return 0; +} + +static size_t ovpn_get_size(const struct net_device *dev) +{ + /* IFLA_OVPN_MODE */ + return nla_total_size(sizeof(u8)); } static int ovpn_fill_info(struct sk_buff *skb, const struct net_device *dev) @@ -228,13 +254,17 @@ static struct rtnl_link_ops ovpn_link_ops = { .policy = ovpn_policy, .maxtype = IFLA_OVPN_MAX, .newlink = ovpn_newlink, + .get_size = ovpn_get_size, .fill_info = ovpn_fill_info, }; static int __init ovpn_init(void) { - int err = rtnl_link_register(&ovpn_link_ops); + int err; + + ovpn_tcp_init(); + err = rtnl_link_register(&ovpn_link_ops); if (err) { pr_err("ovpn: can't register rtnl link ops: %d\n", err); return err; @@ -246,8 +276,6 @@ static int __init ovpn_init(void) goto unreg_rtnl; } - ovpn_tcp_init(); - return 0; unreg_rtnl: diff --git a/drivers/net/ovpn/netlink.c b/drivers/net/ovpn/netlink.c index 4c66c1ec497e..4dad85294198 100644 --- a/drivers/net/ovpn/netlink.c +++ b/drivers/net/ovpn/netlink.c @@ -534,6 +534,12 @@ int ovpn_nl_peer_set_doit(struct sk_buff *skb, struct genl_info *info) */ if (ret > 0) ovpn_peer_hash_vpn_ip(peer); + /* if the remote endpoint was updated, the by_transp_addr hash bucket + * also needs to be refreshed, otherwise incoming packets from the new + * remote address would fail the lockless lookup + */ + if (attrs[OVPN_A_PEER_REMOTE_IPV4] || attrs[OVPN_A_PEER_REMOTE_IPV6]) + ovpn_peer_hash_transp_addr(peer); spin_unlock_bh(&ovpn->lock); ovpn_peer_put(peer); diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c index a21d02ac715e..b0519f9840d8 100644 --- a/drivers/net/ovpn/peer.c +++ b/drivers/net/ovpn/peer.c @@ -189,6 +189,9 @@ int ovpn_peer_reset_sockaddr(struct ovpn_peer *peer, &(*__tbl1)[ovpn_get_hash_slot(*__tbl1, _key, _key_len)];\ }) +static void __ovpn_peer_hash_transp_addr(struct ovpn_peer *peer, + const struct ovpn_bind *bind); + /** * ovpn_peer_endpoints_update - update remote or local endpoint for peer * @peer: peer to update the remote endpoint for @@ -196,7 +199,6 @@ int ovpn_peer_reset_sockaddr(struct ovpn_peer *peer, */ void ovpn_peer_endpoints_update(struct ovpn_peer *peer, struct sk_buff *skb) { - struct hlist_nulls_head *nhead; struct sockaddr_storage ss; struct sockaddr_in6 *sa6; bool reset_cache = false; @@ -220,9 +222,16 @@ void ovpn_peer_endpoints_update(struct ovpn_peer *peer, struct sk_buff *skb) */ local_ip = &ip_hdr(skb)->daddr; sa = (struct sockaddr_in *)&ss; - sa->sin_family = AF_INET; - sa->sin_addr.s_addr = ip_hdr(skb)->saddr; - sa->sin_port = udp_hdr(skb)->source; + /* use a designated initializer so the sin_zero padding + * is zeroed (it ends up in the by_transp_addr hash key) + * without memset-ing the whole sockaddr_storage on the + * RX fast path + */ + *sa = (struct sockaddr_in) { + .sin_family = AF_INET, + .sin_addr.s_addr = ip_hdr(skb)->saddr, + .sin_port = udp_hdr(skb)->source, + }; salen = sizeof(*sa); reset_cache = true; break; @@ -248,11 +257,19 @@ void ovpn_peer_endpoints_update(struct ovpn_peer *peer, struct sk_buff *skb) */ local_ip = &ipv6_hdr(skb)->daddr; sa6 = (struct sockaddr_in6 *)&ss; - sa6->sin6_family = AF_INET6; - sa6->sin6_addr = ipv6_hdr(skb)->saddr; - sa6->sin6_port = udp_hdr(skb)->source; - sa6->sin6_scope_id = ipv6_iface_scope_id(&ipv6_hdr(skb)->saddr, - skb->skb_iif); + /* use a designated initializer so the sin6_flowinfo + * padding is zeroed (it ends up in the by_transp_addr + * hash key) without memset-ing the whole + * sockaddr_storage on the RX fast path + */ + *sa6 = (struct sockaddr_in6) { + .sin6_family = AF_INET6, + .sin6_addr = ipv6_hdr(skb)->saddr, + .sin6_port = udp_hdr(skb)->source, + .sin6_scope_id = + ipv6_iface_scope_id(&ipv6_hdr(skb)->saddr, + skb->skb_iif), + }; salen = sizeof(*sa6); reset_cache = true; break; @@ -295,42 +312,25 @@ void ovpn_peer_endpoints_update(struct ovpn_peer *peer, struct sk_buff *skb) ovpn_nl_peer_float_notify(peer, &ss); /* rehashing is required only in MP mode as P2P has one peer - * only and thus there is no hashtable + * only and thus there is no hashtable. + * + * This function may be invoked concurrently, so re-read peer->bind + * under the proper locks and rehash against its current value. */ - if (peer->ovpn->mode == OVPN_MODE_MP) { - spin_lock_bh(&peer->ovpn->lock); - spin_lock_bh(&peer->lock); - bind = rcu_dereference_protected(peer->bind, - lockdep_is_held(&peer->lock)); - if (unlikely(!bind)) { - spin_unlock_bh(&peer->lock); - spin_unlock_bh(&peer->ovpn->lock); - return; - } - - /* This function may be invoked concurrently, therefore another - * float may have happened in parallel: perform rehashing - * using the peer->bind->remote directly as key - */ - - switch (bind->remote.in4.sin_family) { - case AF_INET: - salen = sizeof(*sa); - break; - case AF_INET6: - salen = sizeof(*sa6); - break; - } + if (peer->ovpn->mode != OVPN_MODE_MP) + return; - /* remove old hashing */ - hlist_nulls_del_init_rcu(&peer->hash_entry_transp_addr); - /* re-add with new transport address */ - nhead = ovpn_get_hash_head(peer->ovpn->peers->by_transp_addr, - &bind->remote, salen); - hlist_nulls_add_head_rcu(&peer->hash_entry_transp_addr, nhead); - spin_unlock_bh(&peer->lock); - spin_unlock_bh(&peer->ovpn->lock); - } + /* This function may be invoked concurrently, therefore another + * float may have happened in parallel: re-acquire the locks and + * rehash using the peer->bind->remote directly as key + */ + spin_lock_bh(&peer->ovpn->lock); + spin_lock_bh(&peer->lock); + bind = rcu_dereference_protected(peer->bind, + lockdep_is_held(&peer->lock)); + __ovpn_peer_hash_transp_addr(peer, bind); + spin_unlock_bh(&peer->lock); + spin_unlock_bh(&peer->ovpn->lock); return; unlock: spin_unlock_bh(&peer->lock); @@ -896,6 +896,83 @@ bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb, return match; } +/* Move @peer to the by_transp_addr bucket matching its current bind. + * + * Caller must hold both peer->ovpn->lock and peer->lock, and must have + * already dereferenced a valid (non-NULL) peer->bind, passed in as @bind. + */ +static void __ovpn_peer_hash_transp_addr(struct ovpn_peer *peer, + const struct ovpn_bind *bind) +{ + struct sockaddr_storage sa = {}; + struct hlist_nulls_head *nhead; + struct sockaddr_in6 *sa6; + struct sockaddr_in *sa4; + size_t salen; + + lockdep_assert_held(&peer->ovpn->lock); + lockdep_assert_held(&peer->lock); + + if (WARN_ON_ONCE(!bind)) + return; + + /* peer may have been concurrently removed between the caller's + * initial lookup and our acquisition of ovpn->lock; skip the + * rehash so we don't re-insert a removed peer + */ + if (unlikely(hlist_unhashed(&peer->hash_entry_id))) + return; + + /* Build the hash key from the transport identity only + * (family/address/port), matching ovpn_peer_add_mp() and the lookup + * in ovpn_peer_get_by_transp_addr(). Hashing bind->remote directly + * would fold in sin6_scope_id (set on the float path but never by the + * lookup), scattering the peer into a bucket lookups cannot reach. + */ + switch (bind->remote.in4.sin_family) { + case AF_INET: + sa4 = (struct sockaddr_in *)&sa; + sa4->sin_family = AF_INET; + sa4->sin_addr.s_addr = bind->remote.in4.sin_addr.s_addr; + sa4->sin_port = bind->remote.in4.sin_port; + salen = sizeof(*sa4); + break; + case AF_INET6: + sa6 = (struct sockaddr_in6 *)&sa; + sa6->sin6_family = AF_INET6; + sa6->sin6_addr = bind->remote.in6.sin6_addr; + sa6->sin6_port = bind->remote.in6.sin6_port; + salen = sizeof(*sa6); + break; + default: + return; + } + + /* remove old hashing (no-op if entry is not currently linked) */ + hlist_nulls_del_init_rcu(&peer->hash_entry_transp_addr); + /* re-add with current transport address */ + nhead = ovpn_get_hash_head(peer->ovpn->peers->by_transp_addr, &sa, + salen); + hlist_nulls_add_head_rcu(&peer->hash_entry_transp_addr, nhead); +} + +void ovpn_peer_hash_transp_addr(struct ovpn_peer *peer) +{ + struct ovpn_bind *bind; + + lockdep_assert_held(&peer->ovpn->lock); + + /* rehashing makes sense only in multipeer mode */ + if (peer->ovpn->mode != OVPN_MODE_MP) + return; + + spin_lock_bh(&peer->lock); + bind = rcu_dereference_protected(peer->bind, + lockdep_is_held(&peer->lock)); + __ovpn_peer_hash_transp_addr(peer, bind); + spin_unlock_bh(&peer->lock); +} + void ovpn_peer_hash_vpn_ip(struct ovpn_peer *peer) { struct hlist_nulls_head *nhead; @@ -906,6 +983,13 @@ void ovpn_peer_hash_vpn_ip(struct ovpn_peer *peer) if (peer->ovpn->mode != OVPN_MODE_MP) return; + /* peer may have been concurrently removed between the caller's + * initial lookup and our acquisition of ovpn->lock; skip the + * rehash so we don't re-insert a removed peer + */ + if (hlist_unhashed(&peer->hash_entry_id)) + return; + if (peer->vpn_addrs.ipv4.s_addr != htonl(INADDR_ANY)) { /* remove potential old hashing */ hlist_nulls_del_init_rcu(&peer->hash_entry_addr4); @@ -1165,7 +1249,7 @@ static void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, struct sock *sk, } if (sk) { - ovpn_sock = rcu_access_pointer(peer->sock); + ovpn_sock = rcu_dereference_bh(peer->sock); if (!ovpn_sock || ovpn_sock->sk != sk) { spin_unlock_bh(&ovpn->lock); return; diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h index 86c8cffada6d..dfa5c0037e02 100644 --- a/drivers/net/ovpn/peer.h +++ b/drivers/net/ovpn/peer.h @@ -150,6 +150,7 @@ struct ovpn_peer *ovpn_peer_get_by_id(struct ovpn_priv *ovpn, u32 peer_id); struct ovpn_peer *ovpn_peer_get_by_dst(struct ovpn_priv *ovpn, struct sk_buff *skb); void ovpn_peer_hash_vpn_ip(struct ovpn_peer *peer); +void ovpn_peer_hash_transp_addr(struct ovpn_peer *peer); bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb, struct ovpn_peer *peer); diff --git a/drivers/net/ovpn/socket.c b/drivers/net/ovpn/socket.c index 517caa64a4fe..6cbeb2caaeec 100644 --- a/drivers/net/ovpn/socket.c +++ b/drivers/net/ovpn/socket.c @@ -162,6 +162,15 @@ struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer) rcu_read_lock(); ovpn_sock = rcu_dereference_sk_user_data(sk); if (ovpn_sock) { + /* something else filled the sk_user_data without + * setting the encap_type. Reject the socket. + */ + if (!type) { + ovpn_sock = ERR_PTR(-EBUSY); + rcu_read_unlock(); + goto sock_release; + } + /* socket owned by another ovpn instance, we can't use it */ if (ovpn_sock->ovpn != peer->ovpn) { ovpn_sock = ERR_PTR(-EBUSY); diff --git a/drivers/net/phy/mediatek/mtk.h b/drivers/net/phy/mediatek/mtk.h index 320f76ffa81f..79e09727b81b 100644 --- a/drivers/net/phy/mediatek/mtk.h +++ b/drivers/net/phy/mediatek/mtk.h @@ -53,15 +53,15 @@ #define MTK_GPHY_LED_RX_BLINK_SET (MTK_PHY_LED_BLINK_1000RX | \ MTK_PHY_LED_BLINK_100RX | \ MTK_PHY_LED_BLINK_10RX) -#define MTK_GPHY_LED_TX_BLINK_SET (MTK_PHY_LED_BLINK_1000RX | \ - MTK_PHY_LED_BLINK_100RX | \ - MTK_PHY_LED_BLINK_10RX) +#define MTK_GPHY_LED_TX_BLINK_SET (MTK_PHY_LED_BLINK_1000TX | \ + MTK_PHY_LED_BLINK_100TX | \ + MTK_PHY_LED_BLINK_10TX) #define MTK_2P5GPHY_LED_ON_SET (MTK_PHY_LED_ON_LINK2500 | \ MTK_GPHY_LED_ON_SET) #define MTK_2P5GPHY_LED_RX_BLINK_SET (MTK_PHY_LED_BLINK_2500RX | \ MTK_GPHY_LED_RX_BLINK_SET) -#define MTK_2P5GPHY_LED_TX_BLINK_SET (MTK_PHY_LED_BLINK_2500RX | \ +#define MTK_2P5GPHY_LED_TX_BLINK_SET (MTK_PHY_LED_BLINK_2500TX | \ MTK_GPHY_LED_TX_BLINK_SET) #define MTK_PHY_LED_STATE_FORCE_ON 0 diff --git a/drivers/net/tap.c b/drivers/net/tap.c index fae115915c8e..5d2d34d24ce8 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -1074,10 +1074,21 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp) skb_reset_mac_header(skb); skb->protocol = eth_hdr(skb)->h_proto; + rcu_read_lock(); + tap = rcu_dereference(q->tap); + if (!tap) { + kfree_skb(skb); + rcu_read_unlock(); + return 0; + } + skb->dev = tap->dev; + if (vnet_hdr_len) { err = tun_vnet_hdr_to_skb(q->flags, skb, gso); - if (err) + if (err) { + rcu_read_unlock(); goto err_kfree; + } } /* Move network header to the right position for VLAN tagged packets */ @@ -1085,15 +1096,8 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp) vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); - rcu_read_lock(); - tap = rcu_dereference(q->tap); - if (tap) { - skb->dev = tap->dev; - skb_probe_transport_header(skb); - dev_queue_xmit(skb); - } else { - kfree_skb(skb); - } + skb_probe_transport_header(skb); + dev_queue_xmit(skb); rcu_read_unlock(); return 0; diff --git a/drivers/net/thunderbolt/main.c b/drivers/net/thunderbolt/main.c index ac016890646c..fb569c0abf8e 100644 --- a/drivers/net/thunderbolt/main.c +++ b/drivers/net/thunderbolt/main.c @@ -390,11 +390,16 @@ static void tbnet_tear_down(struct tbnet *net, bool send_logout) break; } - tb_ring_stop(net->rx_ring.ring); - tb_ring_stop(net->tx_ring.ring); - tbnet_free_buffers(&net->rx_ring); - tbnet_free_buffers(&net->tx_ring); - + /* Tear the paths down before stopping the rings. This mirrors + * tbnet_connected_work(), which enables the paths last so the + * Rx ring is primed before packets can arrive. Stopping a + * ring zeroes its descriptor base and tbnet_free_buffers() + * unmaps and frees the frame buffers, leaving anything still + * in flight with nowhere to drain to; + * __tb_path_deactivate_hop() then waits for the hop's + * 'pending' bit, which on some host routers never clears in + * that state. + */ ret = tb_xdomain_disable_paths(net->xd, net->local_transmit_path, net->tx_ring.ring->hop, @@ -403,6 +408,11 @@ static void tbnet_tear_down(struct tbnet *net, bool send_logout) if (ret) netdev_warn(net->dev, "failed to disable DMA paths\n"); + tb_ring_stop(net->rx_ring.ring); + tb_ring_stop(net->tx_ring.ring); + tbnet_free_buffers(&net->rx_ring); + tbnet_free_buffers(&net->tx_ring); + tb_xdomain_release_in_hopid(net->xd, net->remote_transmit_path); net->remote_transmit_path = 0; } @@ -929,12 +939,8 @@ static int tbnet_open(struct net_device *dev) netif_carrier_off(dev); - flags = RING_FLAG_FRAME; - /* Only enable full E2E if the other end supports it too */ - if (tbnet_e2e && net->svc->prtcstns & TBNET_E2E) - flags |= RING_FLAG_E2E; - - ring = tb_ring_alloc_tx(xd->tb->nhi, -1, TBNET_RING_SIZE, flags); + ring = tb_ring_alloc_tx(xd->tb->nhi, -1, TBNET_RING_SIZE, + RING_FLAG_FRAME); if (!ring) { netdev_err(dev, "failed to allocate Tx ring\n"); return -ENOMEM; @@ -953,6 +959,11 @@ static int tbnet_open(struct net_device *dev) sof_mask = BIT(TBIP_PDF_FRAME_START); eof_mask = BIT(TBIP_PDF_FRAME_END); + flags = RING_FLAG_FRAME; + /* Only enable full E2E if the other end supports it too */ + if (tbnet_e2e && net->svc->prtcstns & TBNET_E2E) + flags |= RING_FLAG_E2E; + ring = tb_ring_alloc_rx(xd->tb->nhi, -1, TBNET_RING_SIZE, flags, net->tx_ring.ring->hop, sof_mask, eof_mask, tbnet_start_poll, net); diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 98f899ea2e94..81d8412ce8e2 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1487,8 +1487,10 @@ ax88179_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags) headroom = skb_headroom(skb) - 8; - if ((dev->net->features & NETIF_F_SG) && skb_linearize(skb)) + if ((dev->net->features & NETIF_F_SG) && skb_linearize(skb)) { + dev_kfree_skb_any(skb); return NULL; + } if ((skb_header_cloned(skb) || headroom < 0) && pskb_expand_head(skb, headroom < 0 ? 8 : 0, 0, GFP_ATOMIC)) { diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index bb1364f85bd1..2b490114d232 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -490,6 +490,7 @@ static int ipheth_open(struct net_device *net) if (retval) return retval; + enable_delayed_work(&dev->carrier_work); schedule_delayed_work(&dev->carrier_work, IPHETH_CARRIER_CHECK_TIMEOUT); return retval; } @@ -499,7 +500,11 @@ static int ipheth_close(struct net_device *net) struct ipheth_device *dev = netdev_priv(net); netif_stop_queue(net); - cancel_delayed_work_sync(&dev->carrier_work); + /* A TX URB can still complete with an error after this point and + * try to re-arm the carrier work. Disable it instead of cancelling + * it, so that such a schedule_delayed_work() is a no-op. + */ + disable_delayed_work_sync(&dev->carrier_work); return 0; } @@ -629,6 +634,10 @@ static int ipheth_probe(struct usb_interface *intf, } INIT_DELAYED_WORK(&dev->carrier_work, ipheth_carrier_check_work); + /* Armed only between ipheth_open() and ipheth_close(). Start out + * disabled so the enable/disable counts balance from the first open. + */ + disable_delayed_work(&dev->carrier_work); retval = ipheth_alloc_urbs(dev); if (retval) { diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index b72ba0803392..6b5f44cbb561 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1798,7 +1798,7 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod) */ dev->hard_mtu = net->mtu + net->hard_header_len; net->min_mtu = 0; - net->max_mtu = ETH_MAX_MTU; + net->max_mtu = net->mtu; net->netdev_ops = &usbnet_netdev_ops; net->watchdog_timeo = TX_TIMEOUT_JIFFIES; @@ -1808,6 +1808,7 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod) // allow device-specific bind/init procedures // NOTE net->name still not usable ... if (info->bind) { + net->max_mtu = ETH_MAX_MTU; status = info->bind(dev, udev); if (status < 0) goto out1; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 00e34afd858e..f80f6584a6ff 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -865,18 +865,24 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, skb_reset_mac_header(skb); - /* check if bpf_xdp_adjust_tail was used */ - off = xdp->data_end - orig_data_end; - if (off != 0) - __skb_put(skb, off); /* positive on grow, negative on shrink */ - /* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers - * (e.g. bpf_xdp_adjust_tail), we need to update data_len here. + * (e.g. bpf_xdp_adjust_tail). Remove the old fragment contribution + * from skb->len before updating data_len, then add the new one back. */ - if (xdp_buff_has_frags(xdp)) + skb->len -= skb->data_len; + if (xdp_buff_has_frags(xdp)) { skb->data_len = skb_shinfo(skb)->xdp_frags_size; - else + skb->len += skb->data_len; + } else { skb->data_len = 0; + } + + /* Synchronize the skb tail with XDP's updated linear area. */ + off = xdp->data_end - orig_data_end; + if (off != 0) { + skb_set_tail_pointer(skb, xdp->data_end - xdp->data); + skb->len += off; /* positive on grow, negative on shrink */ + } skb->protocol = eth_type_trans(skb, rq->dev); diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 32613e40b3ba..608087f78d02 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -4501,7 +4501,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], if (change_igmp && vxlan_addr_multicast(&dst->remote_ip)) err = vxlan_multicast_leave(vxlan); - if (conf.age_interval != vxlan->cfg.age_interval) + if (netif_running(dev) && conf.age_interval != vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies); netdev_adjacent_change_commit(dst->remote_dev, lowerdev, dev); diff --git a/drivers/nvmem/apple-spmi-nvmem.c b/drivers/nvmem/apple-spmi-nvmem.c index 88614005d5ce..7acb0c07d6ab 100644 --- a/drivers/nvmem/apple-spmi-nvmem.c +++ b/drivers/nvmem/apple-spmi-nvmem.c @@ -18,6 +18,22 @@ static const struct regmap_config apple_spmi_regmap_config = { .max_register = 0xffff, }; +static int apple_spmi_nvmem_read(void *priv, unsigned int offset, void *val, + size_t bytes) +{ + struct regmap *map = priv; + + return regmap_bulk_read(map, offset, val, bytes); +} + +static int apple_spmi_nvmem_write(void *priv, unsigned int offset, void *val, + size_t bytes) +{ + struct regmap *map = priv; + + return regmap_bulk_write(map, offset, val, bytes); +} + static int apple_spmi_nvmem_probe(struct spmi_device *sdev) { struct regmap *regmap; @@ -28,8 +44,8 @@ static int apple_spmi_nvmem_probe(struct spmi_device *sdev) .word_size = 1, .stride = 1, .size = 0xffff, - .reg_read = (void *)regmap_bulk_read, - .reg_write = (void *)regmap_bulk_write, + .reg_read = apple_spmi_nvmem_read, + .reg_write = apple_spmi_nvmem_write, }; regmap = devm_regmap_init_spmi_ext(sdev, &apple_spmi_regmap_config); diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index e871181751f3..2f971b059704 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -786,7 +786,7 @@ static int nvmem_validate_keepouts(struct nvmem_device *nvmem) return 0; } -static int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_node *np) +int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_node *np) { struct device *dev = &nvmem->dev; const __be32 *addr; @@ -834,29 +834,13 @@ static int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_nod return 0; } +EXPORT_SYMBOL_GPL(nvmem_add_cells_from_dt); static int nvmem_add_cells_from_legacy_of(struct nvmem_device *nvmem) { return nvmem_add_cells_from_dt(nvmem, nvmem->dev.of_node); } -static int nvmem_add_cells_from_fixed_layout(struct nvmem_device *nvmem) -{ - struct device_node *layout_np; - int err = 0; - - layout_np = of_nvmem_layout_get_container(nvmem); - if (!layout_np) - return 0; - - if (of_device_is_compatible(layout_np, "fixed-layout")) - err = nvmem_add_cells_from_dt(nvmem, layout_np); - - of_node_put(layout_np); - - return err; -} - int nvmem_layout_register(struct nvmem_layout *layout) { int ret; @@ -1005,10 +989,6 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) goto err_remove_cells; } - rval = nvmem_add_cells_from_fixed_layout(nvmem); - if (rval) - goto err_remove_cells; - dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name); rval = device_add(&nvmem->dev); diff --git a/drivers/nvmem/internals.h b/drivers/nvmem/internals.h index 18fed57270e5..f6d452b6a28f 100644 --- a/drivers/nvmem/internals.h +++ b/drivers/nvmem/internals.h @@ -35,6 +35,8 @@ struct nvmem_device { bool sysfs_cells_populated; }; +int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_node *np); + #if IS_ENABLED(CONFIG_OF) int nvmem_layout_bus_register(void); void nvmem_layout_bus_unregister(void); diff --git a/drivers/nvmem/layouts.c b/drivers/nvmem/layouts.c index b90584e1b99e..07a34be9669c 100644 --- a/drivers/nvmem/layouts.c +++ b/drivers/nvmem/layouts.c @@ -125,11 +125,6 @@ static int nvmem_layout_create_device(struct nvmem_device *nvmem, return 0; } -static const struct of_device_id of_nvmem_layout_skip_table[] = { - { .compatible = "fixed-layout", }, - {} -}; - static int nvmem_layout_bus_populate(struct nvmem_device *nvmem, struct device_node *layout_dn) { @@ -142,12 +137,6 @@ static int nvmem_layout_bus_populate(struct nvmem_device *nvmem, return 0; } - /* Fixed layouts are parsed manually somewhere else for now */ - if (of_match_node(of_nvmem_layout_skip_table, layout_dn)) { - pr_debug("%s() - skipping %pOF node\n", __func__, layout_dn); - return 0; - } - if (of_node_check_flag(layout_dn, OF_POPULATED_BUS)) { pr_debug("%s() - skipping %pOF, already populated\n", __func__, layout_dn); diff --git a/drivers/nvmem/layouts/Makefile b/drivers/nvmem/layouts/Makefile index 4940c9db0665..dd6c6c70b1a9 100644 --- a/drivers/nvmem/layouts/Makefile +++ b/drivers/nvmem/layouts/Makefile @@ -3,6 +3,7 @@ # Makefile for nvmem layouts. # +obj-$(CONFIG_NVMEM_LAYOUTS) += fixed-layout.o obj-$(CONFIG_NVMEM_LAYOUT_SL28_VPD) += sl28vpd.o obj-$(CONFIG_NVMEM_LAYOUT_ONIE_TLV) += onie-tlv.o obj-$(CONFIG_NVMEM_LAYOUT_U_BOOT_ENV) += u-boot-env.o diff --git a/drivers/nvmem/layouts/fixed-layout.c b/drivers/nvmem/layouts/fixed-layout.c new file mode 100644 index 000000000000..635d448b3dd2 --- /dev/null +++ b/drivers/nvmem/layouts/fixed-layout.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2026 Bootlin + * + * Authors: Mathieu Dubois-Briand <mathieu.dubois-briand@bootlin.com> + */ + +#include <linux/nvmem-provider.h> +#include <linux/of.h> + +#include "../internals.h" + +static int fixed_layout_add_cells(struct nvmem_layout *layout) +{ + struct device_node *np; + int ret; + + np = of_nvmem_layout_get_container(layout->nvmem); + if (!np) + return -ENOENT; + + ret = nvmem_add_cells_from_dt(layout->nvmem, np); + of_node_put(np); + + return ret; +} + +static int fixed_layout_probe(struct nvmem_layout *layout) +{ + layout->add_cells = fixed_layout_add_cells; + + return nvmem_layout_register(layout); +} + +static void fixed_layout_remove(struct nvmem_layout *layout) +{ + nvmem_layout_unregister(layout); +} + +static const struct of_device_id fixed_layout_of_match_table[] = { + { .compatible = "fixed-layout", }, + {}, +}; + +static struct nvmem_layout_driver fixed_layout_layout = { + .driver = { + .name = "fixed-layout", + .of_match_table = fixed_layout_of_match_table, + }, + .probe = fixed_layout_probe, + .remove = fixed_layout_remove, +}; +module_nvmem_layout_driver(fixed_layout_layout); + +MODULE_AUTHOR("Mathieu Dubois-Briand"); +MODULE_LICENSE("GPL"); +MODULE_DEVICE_TABLE(of, fixed_layout_of_match_table); +MODULE_DESCRIPTION("NVMEM fixed-layout driver"); diff --git a/drivers/pinctrl/qcom/pinctrl-ipq8064.c b/drivers/pinctrl/qcom/pinctrl-ipq8064.c index 0a9e357e64c6..f35dbe07ab6f 100644 --- a/drivers/pinctrl/qcom/pinctrl-ipq8064.c +++ b/drivers/pinctrl/qcom/pinctrl-ipq8064.c @@ -480,7 +480,7 @@ static const char * const ps_hold_groups[] = { }; static const struct pinfunction ipq8064_functions[] = { - IPQ_PIN_FUNCTION(gpio), + IPQ_GPIO_PIN_FUNCTION(gpio), IPQ_PIN_FUNCTION(mdio), IPQ_PIN_FUNCTION(ssbi), IPQ_PIN_FUNCTION(spmi), @@ -507,19 +507,19 @@ static const struct pinfunction ipq8064_functions[] = { IPQ_PIN_FUNCTION(usb2_hsic), IPQ_PIN_FUNCTION(rgmii2), IPQ_PIN_FUNCTION(sata), - IPQ_PIN_FUNCTION(pcie1_rst), + IPQ_GPIO_PIN_FUNCTION(pcie1_rst), IPQ_PIN_FUNCTION(pcie1_prsnt), IPQ_PIN_FUNCTION(pcie1_pwren_n), IPQ_PIN_FUNCTION(pcie1_pwren), IPQ_PIN_FUNCTION(pcie1_pwrflt), IPQ_PIN_FUNCTION(pcie1_clk_req), - IPQ_PIN_FUNCTION(pcie2_rst), + IPQ_GPIO_PIN_FUNCTION(pcie2_rst), IPQ_PIN_FUNCTION(pcie2_prsnt), IPQ_PIN_FUNCTION(pcie2_pwren_n), IPQ_PIN_FUNCTION(pcie2_pwren), IPQ_PIN_FUNCTION(pcie2_pwrflt), IPQ_PIN_FUNCTION(pcie2_clk_req), - IPQ_PIN_FUNCTION(pcie3_rst), + IPQ_GPIO_PIN_FUNCTION(pcie3_rst), IPQ_PIN_FUNCTION(pcie3_prsnt), IPQ_PIN_FUNCTION(pcie3_pwren_n), IPQ_PIN_FUNCTION(pcie3_pwren), diff --git a/drivers/pinctrl/qcom/pinctrl-msm.h b/drivers/pinctrl/qcom/pinctrl-msm.h index 4fbff61de6bb..b94ba1a4177e 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.h +++ b/drivers/pinctrl/qcom/pinctrl-msm.h @@ -24,6 +24,11 @@ struct pinctrl_pin_desc; fname##_groups, \ ARRAY_SIZE(fname##_groups)) +#define IPQ_GPIO_PIN_FUNCTION(fname) \ + [IPQ_MUX_##fname] = PINCTRL_GPIO_PINFUNCTION(#fname, \ + fname##_groups, \ + ARRAY_SIZE(fname##_groups)) + #define MSM_PIN_FUNCTION(fname) \ [msm_mux_##fname] = PINCTRL_PINFUNCTION(#fname, \ fname##_groups, \ diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 735385539b9f..a93633c450b5 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -2180,9 +2180,11 @@ ptp_ocp_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, if (err) return err; + snprintf(buf, sizeof(buf), "%.*s", OCP_BOARD_ID_LEN, + (const char *)bp->board_id); err = devlink_info_version_fixed_put(req, DEVLINK_INFO_VERSION_GENERIC_BOARD_ID, - bp->board_id); + buf); if (err) return err; diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index 7d0479e4e095..369aa21b1ff7 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -148,13 +148,16 @@ static int unregister_sba(struct ism_dev *ism) if (ret && ret != ISM_ERROR) return -EIO; + return 0; +} + +static void ism_free_sba(struct ism_dev *ism) +{ dma_free_coherent(&ism->pdev->dev, PAGE_SIZE, ism->sba, ism->sba_dma_addr); ism->sba = NULL; ism->sba_dma_addr = 0; - - return 0; } static int unregister_ieq(struct ism_dev *ism) @@ -168,13 +171,16 @@ static int unregister_ieq(struct ism_dev *ism) if (ret && ret != ISM_ERROR) return -EIO; + return 0; +} + +static void ism_free_ieq(struct ism_dev *ism) +{ dma_free_coherent(&ism->pdev->dev, PAGE_SIZE, ism->ieq, ism->ieq_dma_addr); ism->ieq = NULL; ism->ieq_dma_addr = 0; - - return 0; } static int ism_read_local_gid(struct dibs_dev *dibs) @@ -573,6 +579,7 @@ static int ism_dev_init(struct ism_dev *ism) unreg_sba: unregister_sba(ism); + ism_free_sba(ism); free_irq: free_irq(pci_irq_vector(pdev, 0), ism); free_vectors: @@ -585,9 +592,13 @@ static void ism_dev_exit(struct ism_dev *ism) { struct pci_dev *pdev = ism->pdev; + /* ism will only generate new IRQs while ieq & sba are registered */ unregister_ieq(ism); unregister_sba(ism); + /* drain ongoing irpt handlers */ free_irq(pci_irq_vector(pdev, 0), ism); + ism_free_ieq(ism); + ism_free_sba(ism); pci_free_irq_vectors(pdev); } diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 615618aa11f4..87975d3d1d08 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -4318,8 +4318,8 @@ static bool comp_write_worker(struct sdeb_store_info *sip, u64 lba, u32 num, if (!res) return res; if (rest) - res = memcmp(fsp, arr + ((num - rest) * lb_size), - rest * lb_size); + res = !memcmp(fsp, arr + ((num - rest) * lb_size), + rest * lb_size); if (!res) return res; if (compare_only) diff --git a/drivers/soc/aspeed/Makefile b/drivers/soc/aspeed/Makefile index b35d74592964..b5188dcde37a 100644 --- a/drivers/soc/aspeed/Makefile +++ b/drivers/soc/aspeed/Makefile @@ -4,3 +4,4 @@ obj-$(CONFIG_ASPEED_LPC_SNOOP) += aspeed-lpc-snoop.o obj-$(CONFIG_ASPEED_UART_ROUTING) += aspeed-uart-routing.o obj-$(CONFIG_ASPEED_P2A_CTRL) += aspeed-p2a-ctrl.o obj-$(CONFIG_ASPEED_SOCINFO) += aspeed-socinfo.o +CONTEXT_ANALYSIS_aspeed-lpc-snoop.o := y diff --git a/drivers/soc/aspeed/aspeed-lpc-snoop.c b/drivers/soc/aspeed/aspeed-lpc-snoop.c index b03310c0830d..7fa1a345acac 100644 --- a/drivers/soc/aspeed/aspeed-lpc-snoop.c +++ b/drivers/soc/aspeed/aspeed-lpc-snoop.c @@ -11,6 +11,7 @@ */ #include <linux/bitops.h> +#include <linux/cleanup.h> #include <linux/clk.h> #include <linux/dev_printk.h> #include <linux/interrupt.h> @@ -74,7 +75,8 @@ struct aspeed_lpc_snoop_channel_cfg { struct aspeed_lpc_snoop_channel { const struct aspeed_lpc_snoop_channel_cfg *cfg; bool enabled; - struct kfifo fifo; + spinlock_t lock; + struct kfifo fifo __guarded_by(&lock); wait_queue_head_t wq; struct miscdevice miscdev; }; @@ -114,6 +116,7 @@ static ssize_t snoop_file_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { struct aspeed_lpc_snoop_channel *chan = snoop_file_to_chan(file); + u8 *buf __free(kfree) = NULL; unsigned int copied; int ret = 0; @@ -125,9 +128,16 @@ static ssize_t snoop_file_read(struct file *file, char __user *buffer, if (ret == -ERESTARTSYS) return -EINTR; } - ret = kfifo_to_user(&chan->fifo, buffer, count, &copied); - if (ret) - return ret; + + count = min_t(size_t, count, SNOOP_FIFO_SIZE); + + buf = kmalloc(count, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + copied = kfifo_out_spinlocked(&chan->fifo, buf, count, &chan->lock); + if (copied && copy_to_user(buffer, buf, copied)) + return -EFAULT; return copied; } @@ -151,11 +161,13 @@ static const struct file_operations snoop_fops = { /* Save a byte to a FIFO and discard the oldest byte if FIFO is full */ static void put_fifo_with_discard(struct aspeed_lpc_snoop_channel *chan, u8 val) { - if (!kfifo_initialized(&chan->fifo)) - return; - if (kfifo_is_full(&chan->fifo)) - kfifo_skip(&chan->fifo); - kfifo_put(&chan->fifo, val); + scoped_guard(spinlock, &chan->lock) { + if (!kfifo_initialized(&chan->fifo)) + return; + if (kfifo_is_full(&chan->fifo)) + kfifo_skip(&chan->fifo); + kfifo_put(&chan->fifo, val); + } wake_up_interruptible(&chan->wq); } @@ -239,9 +251,11 @@ static int aspeed_lpc_enable_snoop(struct device *dev, if (!channel->miscdev.name) return -ENOMEM; - rc = kfifo_alloc(&channel->fifo, SNOOP_FIFO_SIZE, GFP_KERNEL); - if (rc) - return rc; + scoped_guard(spinlock_init, &channel->lock) { + rc = kfifo_alloc(&channel->fifo, SNOOP_FIFO_SIZE, GFP_KERNEL); + if (rc) + return rc; + } rc = misc_register(&channel->miscdev); if (rc) diff --git a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c index 82ccdec2f365..a0dd19cb404f 100644 --- a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c +++ b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c @@ -371,6 +371,9 @@ unsigned char *rtw_get_wpa_ie(unsigned char *pie, int *wpa_ie_len, int limit) pbuf = rtw_get_ie(pbuf, WLAN_EID_VENDOR_SPECIFIC, &len, limit_new); if (pbuf) { + if (len < 6) + goto check_next_ie; + /* check if oui matches... */ if (memcmp((pbuf + 2), wpa_oui_type, sizeof(wpa_oui_type))) goto check_next_ie; diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c b/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c index e78450402d19..812edc4fe37c 100644 --- a/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c +++ b/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c @@ -897,7 +897,7 @@ unsigned int OnAuthClient(struct adapter *padapter, union recv_frame *precv_fram p = rtw_get_ie(pframe + WLAN_HDR_A3_LEN + _AUTH_IE_OFFSET_, WLAN_EID_CHALLENGE, (int *)&len, pkt_len - WLAN_HDR_A3_LEN - _AUTH_IE_OFFSET_); - if (!p) + if (!p || len != WLAN_AUTH_CHALLENGE_LEN) goto authclnt_fail; memcpy(pmlmeinfo->chg_txt, p + 2, len); diff --git a/drivers/staging/rtl8723bs/core/rtw_wlan_util.c b/drivers/staging/rtl8723bs/core/rtw_wlan_util.c index 94bbe7ac13ac..119b61baa475 100644 --- a/drivers/staging/rtl8723bs/core/rtw_wlan_util.c +++ b/drivers/staging/rtl8723bs/core/rtw_wlan_util.c @@ -693,6 +693,9 @@ int WMM_param_handler(struct adapter *padapter, struct ndis_80211_var_ie *pIE) return false; } + if (pIE->length != WLAN_WMM_LEN) + return false; + if (!memcmp(&(pmlmeinfo->WMM_param), (pIE->data + 6), sizeof(struct WMM_para_element))) return false; diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c index a0ef1e7e50a0..e65932dc6585 100644 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c +++ b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c @@ -2032,6 +2032,8 @@ static netdev_tx_t rtw_cfg80211_monitor_if_xmit_entry(struct sk_buff *skb, struc /* Skip the ratio tap header */ skb_pull(skb, rtap_len); + if (skb->len < dot11_hdr_len) + goto fail; dot11_hdr = (struct ieee80211_hdr *)skb->data; frame_control = le16_to_cpu(dot11_hdr->frame_control); @@ -2044,6 +2046,8 @@ static netdev_tx_t rtw_cfg80211_monitor_if_xmit_entry(struct sk_buff *skb, struc qos_len = 2; if ((frame_control & 0x0300) == 0x0300) dot11_hdr_len += 6; + if (skb->len < dot11_hdr_len + qos_len + snap_len) + goto fail; memcpy(dst_mac_addr, dot11_hdr->addr1, sizeof(dst_mac_addr)); memcpy(src_mac_addr, dot11_hdr->addr2, sizeof(src_mac_addr)); diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c index 223ae1571655..ec73d03a1e60 100644 --- a/drivers/thermal/thermal_hwmon.c +++ b/drivers/thermal/thermal_hwmon.c @@ -19,33 +19,30 @@ #include "thermal_hwmon.h" #include "thermal_core.h" -/* - * Needs to be large enough to hold a thermal zone type string followed by an - * underline character and a 32-bit integer in decimal representation. - */ -#define THERMAL_HWMON_NAME_LENGTH (THERMAL_NAME_LENGTH + 11) +/* hwmon sys I/F */ +/* thermal zone devices with the same type share one hwmon device */ +struct thermal_hwmon_device { + char type[THERMAL_NAME_LENGTH]; + struct device *device; + int count; + struct list_head tz_list; + struct list_head node; +}; struct thermal_hwmon_attr { struct device_attribute attr; + char name[16]; }; /* one temperature input for each thermal zone */ struct thermal_hwmon_temp { + struct list_head hwmon_node; struct thermal_zone_device *tz; struct thermal_hwmon_attr temp_input; /* hwmon sys attr */ struct thermal_hwmon_attr temp_crit; /* hwmon sys attr */ bool temp_crit_present; }; -/* hwmon sys I/F */ -/* thermal zone devices with the same type share one hwmon device */ -struct thermal_hwmon_device { - char name[THERMAL_HWMON_NAME_LENGTH]; - struct device *device; - struct list_head node; - struct thermal_hwmon_temp tz_temp; -}; - static LIST_HEAD(thermal_hwmon_list); static DEFINE_MUTEX(thermal_hwmon_list_lock); @@ -91,6 +88,45 @@ temp_crit_show(struct device *dev, struct device_attribute *attr, char *buf) return sysfs_emit(buf, "%d\n", temperature); } + +static struct thermal_hwmon_device * +thermal_hwmon_lookup_by_type(const struct thermal_zone_device *tz) +{ + struct thermal_hwmon_device *hwmon; + char type[THERMAL_NAME_LENGTH]; + + mutex_lock(&thermal_hwmon_list_lock); + list_for_each_entry(hwmon, &thermal_hwmon_list, node) { + strscpy(type, tz->type); + strreplace(type, '-', '_'); + if (!strcmp(hwmon->type, type)) { + mutex_unlock(&thermal_hwmon_list_lock); + return hwmon; + } + } + mutex_unlock(&thermal_hwmon_list_lock); + + return NULL; +} + +/* Find the temperature input matching a given thermal zone */ +static struct thermal_hwmon_temp * +thermal_hwmon_lookup_temp(const struct thermal_hwmon_device *hwmon, + const struct thermal_zone_device *tz) +{ + struct thermal_hwmon_temp *temp; + + mutex_lock(&thermal_hwmon_list_lock); + list_for_each_entry(temp, &hwmon->tz_list, hwmon_node) + if (temp->tz == tz) { + mutex_unlock(&thermal_hwmon_list_lock); + return temp; + } + mutex_unlock(&thermal_hwmon_list_lock); + + return NULL; +} + static bool thermal_zone_crit_temp_valid(struct thermal_zone_device *tz) { int temp; @@ -101,39 +137,54 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) { struct thermal_hwmon_device *hwmon; struct thermal_hwmon_temp *temp; + int new_hwmon_device = 1; int result; + hwmon = thermal_hwmon_lookup_by_type(tz); + if (hwmon) { + new_hwmon_device = 0; + goto register_sys_interface; + } + hwmon = kzalloc_obj(*hwmon); if (!hwmon) return -ENOMEM; - /* - * Append the thermal zone ID preceded by an underline character to the - * type to disambiguate the sensors command output. - */ - scnprintf(hwmon->name, THERMAL_HWMON_NAME_LENGTH, "%s_%d", tz->type, tz->id); - strreplace(hwmon->name, '-', '_'); + INIT_LIST_HEAD(&hwmon->tz_list); + strscpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH); + strreplace(hwmon->type, '-', '_'); hwmon->device = hwmon_device_register_for_thermal(&tz->device, - hwmon->name, hwmon); + hwmon->type, hwmon); if (IS_ERR(hwmon->device)) { result = PTR_ERR(hwmon->device); goto free_mem; } - temp = &hwmon->tz_temp; + register_sys_interface: + temp = kzalloc_obj(*temp); + if (!temp) { + result = -ENOMEM; + goto unregister_name; + } temp->tz = tz; + hwmon->count++; - temp->temp_input.attr.attr.name = "temp1_input"; + snprintf(temp->temp_input.name, sizeof(temp->temp_input.name), + "temp%d_input", hwmon->count); + temp->temp_input.attr.attr.name = temp->temp_input.name; temp->temp_input.attr.attr.mode = 0444; temp->temp_input.attr.show = temp_input_show; sysfs_attr_init(&temp->temp_input.attr.attr); result = device_create_file(hwmon->device, &temp->temp_input.attr); if (result) - goto unregister_name; + goto free_temp_mem; if (thermal_zone_crit_temp_valid(tz)) { - temp->temp_crit.attr.attr.name = "temp1_crit"; + snprintf(temp->temp_crit.name, + sizeof(temp->temp_crit.name), + "temp%d_crit", hwmon->count); + temp->temp_crit.attr.attr.name = temp->temp_crit.name; temp->temp_crit.attr.attr.mode = 0444; temp->temp_crit.attr.show = temp_crit_show; sysfs_attr_init(&temp->temp_crit.attr.attr); @@ -145,55 +196,62 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) temp->temp_crit_present = true; } - /* The list is needed for hwmon lookup during removal. */ mutex_lock(&thermal_hwmon_list_lock); - list_add_tail(&hwmon->node, &thermal_hwmon_list); + if (new_hwmon_device) + list_add_tail(&hwmon->node, &thermal_hwmon_list); + list_add_tail(&temp->hwmon_node, &hwmon->tz_list); mutex_unlock(&thermal_hwmon_list_lock); return 0; unregister_input: device_remove_file(hwmon->device, &temp->temp_input.attr); + free_temp_mem: + kfree(temp); unregister_name: - hwmon_device_unregister(hwmon->device); + if (new_hwmon_device) + hwmon_device_unregister(hwmon->device); free_mem: - kfree(hwmon); + if (new_hwmon_device) + kfree(hwmon); return result; } EXPORT_SYMBOL_GPL(thermal_add_hwmon_sysfs); -static struct thermal_hwmon_device * -thermal_hwmon_lookup(const struct thermal_zone_device *tz) -{ - struct thermal_hwmon_device *hwmon; - - list_for_each_entry(hwmon, &thermal_hwmon_list, node) { - if (hwmon->tz_temp.tz == tz) - return hwmon; - } - return NULL; -} - void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz) { struct thermal_hwmon_device *hwmon; struct thermal_hwmon_temp *temp; - scoped_guard(mutex, &thermal_hwmon_list_lock) { - hwmon = thermal_hwmon_lookup(tz); - if (!hwmon) - return; - - list_del(&hwmon->node); + hwmon = thermal_hwmon_lookup_by_type(tz); + if (unlikely(!hwmon)) { + /* Should never happen... */ + dev_dbg(&tz->device, "hwmon device lookup failed!\n"); + return; } - temp = &hwmon->tz_temp; + temp = thermal_hwmon_lookup_temp(hwmon, tz); + if (unlikely(!temp)) { + /* Should never happen... */ + dev_dbg(&tz->device, "temperature input lookup failed!\n"); + return; + } device_remove_file(hwmon->device, &temp->temp_input.attr); if (temp->temp_crit_present) device_remove_file(hwmon->device, &temp->temp_crit.attr); + mutex_lock(&thermal_hwmon_list_lock); + list_del(&temp->hwmon_node); + kfree(temp); + if (!list_empty(&hwmon->tz_list)) { + mutex_unlock(&thermal_hwmon_list_lock); + return; + } + list_del(&hwmon->node); + mutex_unlock(&thermal_hwmon_list_lock); + hwmon_device_unregister(hwmon->device); kfree(hwmon); } diff --git a/drivers/thunderbolt/eeprom.c b/drivers/thunderbolt/eeprom.c index 5477b9437048..e50503bb20dc 100644 --- a/drivers/thunderbolt/eeprom.c +++ b/drivers/thunderbolt/eeprom.c @@ -394,9 +394,16 @@ static int tb_drom_parse_entry_port(struct tb_switch *sw, return -EIO; } port->link_nr = entry->link_nr; - if (entry->has_dual_link_port) + if (entry->has_dual_link_port) { + if (entry->dual_link_port_nr > sw->config.max_port_number) { + tb_sw_warn(sw, + "port entry has invalid dual link port number %u\n", + entry->dual_link_port_nr); + return -EIO; + } port->dual_link_port = &port->sw->ports[entry->dual_link_port_nr]; + } } return 0; } diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index 9d95bf3ab44c..136516432f56 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -2325,7 +2325,7 @@ static int icm_usb4_switch_op(struct tb_switch *sw, u16 opcode, u32 *metadata, if (tx_data_len) { request.data_len_valid |= ICM_USB4_SWITCH_DATA_VALID; if (tx_data_len < ARRAY_SIZE(request.data)) - request.data_len_valid = + request.data_len_valid |= tx_data_len & ICM_USB4_SWITCH_DATA_LEN_MASK; memcpy(request.data, tx_data, tx_data_len * sizeof(u32)); } diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index c69c323e6952..9907966556e7 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -609,7 +609,7 @@ static int tb_consumed_dp_bandwidth(struct tb *tb, int *consumed_up, int *consumed_down) { - int group_reserved[MAX_GROUPS] = {}; + int group_reserved[MAX_GROUPS + 1] = {}; struct tb_cm *tcm = tb_priv(tb); struct tb_tunnel *tunnel; bool downstream; diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c index 3b6452e759d5..5a83e5269b41 100644 --- a/drivers/tty/serial/8250/8250_dma.c +++ b/drivers/tty/serial/8250/8250_dma.c @@ -211,11 +211,12 @@ void serial8250_rx_dma_flush(struct uart_8250_port *p) { struct uart_8250_dma *dma = p->dma; - if (dma->rx_running) { - dmaengine_pause(dma->rxchan); - __dma_rx_complete(p); - dmaengine_terminate_async(dma->rxchan); - } + if (!dma || !dma->rxchan || !dma->rx_running) + return; + + dmaengine_pause(dma->rxchan); + __dma_rx_complete(p); + dmaengine_terminate_async(dma->rxchan); } EXPORT_SYMBOL_GPL(serial8250_rx_dma_flush); @@ -324,6 +325,7 @@ void serial8250_release_dma(struct uart_8250_port *p) /* Release RX resources */ dmaengine_terminate_sync(dma->rxchan); + dma->rx_running = 0; dma_free_coherent(dma->rxchan->device->dev, dma->rx_size, dma->rx_buf, dma->rx_addr); dma_release_channel(dma->rxchan); diff --git a/drivers/tty/serial/8250/8250_of.c b/drivers/tty/serial/8250/8250_of.c index 81644d40b09a..160f4c71de06 100644 --- a/drivers/tty/serial/8250/8250_of.c +++ b/drivers/tty/serial/8250/8250_of.c @@ -81,6 +81,40 @@ static int of_platform_serial_clk_notifier_cb(struct notifier_block *nb, unsigne return NOTIFY_DONE; } +static int lpc32xx_handle_irq(struct uart_port *port) +{ + struct uart_8250_port *up = up_to_u8250p(port); + unsigned int iir; + u16 status; + + guard(serial8250_rpm)(up); + + iir = serial_port_in(port, UART_IIR); + if (iir & UART_IIR_NO_INT) + return 0; + + guard(uart_port_lock_check_sysrq_irqsave)(port); + + /* + * The LPC32xx UART can assert an RX character-timeout interrupt while + * the RX FIFO is empty: IIR reports UART_IIR_RX_TIMEOUT but LSR.DR is + * clear. The timeout is only cleared by reading RHR, but the core RX + * path skips that read when the FIFO is empty, so the level-triggered + * IRQ re-fires forever and livelocks this single-core SoC. Do one + * throwaway RHR read to clear it; a healthy UART never reports a + * timeout with DR/BI clear, so no received data is ever discarded. + */ + if ((iir & 0x3f) == UART_IIR_RX_TIMEOUT) { + status = serial_lsr_in(up); + if (!(status & (UART_LSR_DR | UART_LSR_BI))) + serial_port_in(port, UART_RX); + } + + serial8250_handle_irq_locked(port, iir); + + return 1; +} + /* * Fill a struct uart_port for a given device node */ @@ -173,6 +207,9 @@ static int of_platform_serial_setup(struct platform_device *ofdev, case PORT_NPCM: ret = npcm_setup(port); break; + case PORT_LPC3220: + port->handle_irq = lpc32xx_handle_irq; + break; default: /* Nothing to do */ ret = 0; @@ -369,6 +406,7 @@ static struct platform_driver of_platform_serial_driver = { module_platform_driver(of_platform_serial_driver); +MODULE_IMPORT_NS("SERIAL_8250"); MODULE_AUTHOR("Arnd Bergmann <arnd@arndb.de>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Serial Port driver for Open Firmware platform devices"); diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 028e37ad8d79..b863d0a328f5 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -277,6 +277,7 @@ enum pl011_rs485_tx_state { WAIT_AFTER_RTS, SEND, WAIT_AFTER_SEND, + WAIT_AFTER_SEND_DELAY, }; /* @@ -1214,7 +1215,7 @@ static void pl011_dma_shutdown(struct uart_amba_port *uap) if (uap->using_tx_dma) { /* In theory, this should already be done by pl011_dma_flush_buffer */ - dmaengine_terminate_all(uap->dmatx.chan); + dmaengine_terminate_sync(uap->dmatx.chan); if (uap->dmatx.queued) { dma_unmap_single(uap->dmatx.chan->device->dev, uap->dmatx.dma, uap->dmatx.len, @@ -1227,12 +1228,12 @@ static void pl011_dma_shutdown(struct uart_amba_port *uap) } if (uap->using_rx_dma) { - dmaengine_terminate_all(uap->dmarx.chan); + if (uap->dmarx.poll_rate) + timer_delete_sync(&uap->dmarx.timer); + dmaengine_terminate_sync(uap->dmarx.chan); /* Clean up the RX DMA */ pl011_dmabuf_free(uap->dmarx.chan, &uap->dmarx.dbuf_a, DMA_FROM_DEVICE); pl011_dmabuf_free(uap->dmarx.chan, &uap->dmarx.dbuf_b, DMA_FROM_DEVICE); - if (uap->dmarx.poll_rate) - timer_delete_sync(&uap->dmarx.timer); uap->using_rx_dma = false; } } @@ -1301,11 +1302,30 @@ static inline bool pl011_dma_rx_running(struct uart_amba_port *uap) #define pl011_dma_flush_buffer NULL #endif -static void pl011_rs485_tx_stop(struct uart_amba_port *uap) +static void pl011_rs485_tx_stop_now(struct uart_amba_port *uap) { struct uart_port *port = &uap->port; u32 cr; + cr = pl011_read(uap, REG_CR); + + if (port->rs485.flags & SER_RS485_RTS_AFTER_SEND) + cr &= ~UART011_CR_RTS; + else + cr |= UART011_CR_RTS; + + /* Disable the transmitter and reenable the transceiver */ + cr &= ~UART011_CR_TXE; + cr |= UART011_CR_RXE; + pl011_write(cr, uap, REG_CR); + + uap->rs485_tx_state = OFF; +} + +static void pl011_rs485_tx_stop(struct uart_amba_port *uap) +{ + struct uart_port *port = &uap->port; + if (uap->rs485_tx_state == SEND) uap->rs485_tx_state = WAIT_AFTER_SEND; @@ -1318,6 +1338,7 @@ static void pl011_rs485_tx_stop(struct uart_amba_port *uap) return; } if (port->rs485.delay_rts_after_send > 0) { + uap->rs485_tx_state = WAIT_AFTER_SEND_DELAY; hrtimer_start(&uap->trigger_stop_tx, ms_to_ktime(port->rs485.delay_rts_after_send), HRTIMER_MODE_REL); @@ -1328,19 +1349,7 @@ static void pl011_rs485_tx_stop(struct uart_amba_port *uap) hrtimer_try_to_cancel(&uap->trigger_start_tx); } - cr = pl011_read(uap, REG_CR); - - if (port->rs485.flags & SER_RS485_RTS_AFTER_SEND) - cr &= ~UART011_CR_RTS; - else - cr |= UART011_CR_RTS; - - /* Disable the transmitter and reenable the transceiver */ - cr &= ~UART011_CR_TXE; - cr |= UART011_CR_RXE; - pl011_write(cr, uap, REG_CR); - - uap->rs485_tx_state = OFF; + pl011_rs485_tx_stop_now(uap); } static void pl011_stop_tx(struct uart_port *port) @@ -1383,7 +1392,8 @@ static void pl011_rs485_tx_start(struct uart_amba_port *uap) uap->rs485_tx_state = SEND; return; } - if (uap->rs485_tx_state == WAIT_AFTER_SEND) { + if (uap->rs485_tx_state == WAIT_AFTER_SEND || + uap->rs485_tx_state == WAIT_AFTER_SEND_DELAY) { hrtimer_try_to_cancel(&uap->trigger_stop_tx); uap->rs485_tx_state = SEND; return; @@ -1450,7 +1460,8 @@ static enum hrtimer_restart pl011_trigger_stop_tx(struct hrtimer *t) unsigned long flags; uart_port_lock_irqsave(&uap->port, &flags); - if (uap->rs485_tx_state == WAIT_AFTER_SEND) + if (uap->rs485_tx_state == WAIT_AFTER_SEND || + uap->rs485_tx_state == WAIT_AFTER_SEND_DELAY) pl011_rs485_tx_stop(uap); uart_port_unlock_irqrestore(&uap->port, flags); @@ -2048,11 +2059,20 @@ static void pl011_shutdown(struct uart_port *port) pl011_dma_shutdown(uap); - if ((port->rs485.flags & SER_RS485_ENABLED && uap->rs485_tx_state != OFF)) - pl011_rs485_tx_stop(uap); - free_irq(uap->port.irq, uap); + /* + * free_irq() drains the UART interrupt handler, which can arm either + * timer. Cancel the timers afterwards to drain their callbacks too. + */ + hrtimer_cancel(&uap->trigger_start_tx); + hrtimer_cancel(&uap->trigger_stop_tx); + + uart_port_lock_irq(port); + if (uap->rs485_tx_state != OFF) + pl011_rs485_tx_stop_now(uap); + uart_port_unlock_irq(port); + pl011_disable_uart(uap); /* @@ -3031,6 +3051,8 @@ static void pl011_remove(struct amba_device *dev) struct uart_amba_port *uap = amba_get_drvdata(dev); uart_remove_one_port(&amba_reg, &uap->port); + hrtimer_cancel(&uap->trigger_start_tx); + hrtimer_cancel(&uap->trigger_stop_tx); pl011_unregister_port(uap); } diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 3b0f836a9822..7ae3bb207dc1 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -158,6 +158,7 @@ static const struct uart_ops qcom_geni_uart_pops; static struct uart_driver qcom_geni_console_driver; static struct uart_driver qcom_geni_uart_driver; +static void qcom_geni_serial_stop_tx_dma(struct uart_port *uport); static void __qcom_geni_serial_cancel_tx_cmd(struct uart_port *uport); static void qcom_geni_serial_cancel_tx_cmd(struct uart_port *uport); static int qcom_geni_serial_port_setup(struct uart_port *uport); @@ -636,35 +637,34 @@ static unsigned int qcom_geni_serial_tx_empty(struct uart_port *uport) return !readl(uport->membase + SE_GENI_TX_FIFO_STATUS); } +static void qcom_geni_serial_flush_buffer_dma(struct uart_port *uport) +{ + struct qcom_geni_serial_port *port = to_dev_port(uport); + + qcom_geni_serial_stop_tx_dma(uport); + port->tx_remaining = 0; + port->tx_queued = 0; +} + static void qcom_geni_serial_stop_tx_dma(struct uart_port *uport) { struct qcom_geni_serial_port *port = to_dev_port(uport); - bool done; - if (!qcom_geni_serial_main_active(uport)) - return; + if (qcom_geni_serial_main_active(uport)) + __qcom_geni_serial_cancel_tx_cmd(uport); if (port->tx_dma_addr) { + writel(1, uport->membase + SE_DMA_TX_FSM_RST); + if (!qcom_geni_serial_poll_bit(uport, SE_DMA_TX_IRQ_STAT, + TX_RESET_DONE, true)) + dev_err_ratelimited(uport->dev, "TX DMA reset failed"); + writel(TX_RESET_DONE | TX_DMA_DONE, + uport->membase + SE_DMA_TX_IRQ_CLR); + geni_se_tx_dma_unprep(&port->se, port->tx_dma_addr, port->tx_remaining); port->tx_dma_addr = 0; - port->tx_remaining = 0; } - - geni_se_cancel_m_cmd(&port->se); - - done = qcom_geni_serial_poll_bit(uport, SE_GENI_M_IRQ_STATUS, - M_CMD_CANCEL_EN, true); - if (!done) { - geni_se_abort_m_cmd(&port->se); - done = qcom_geni_serial_poll_bit(uport, SE_GENI_M_IRQ_STATUS, - M_CMD_ABORT_EN, true); - if (!done) - dev_err_ratelimited(uport->dev, "M_CMD_ABORT_EN not set"); - writel(M_CMD_ABORT_EN, uport->membase + SE_GENI_M_IRQ_CLEAR); - } - - writel(M_CMD_CANCEL_EN, uport->membase + SE_GENI_M_IRQ_CLEAR); } static void qcom_geni_serial_start_tx_dma(struct uart_port *uport) @@ -1180,7 +1180,7 @@ static void qcom_geni_serial_shutdown(struct uart_port *uport) uart_port_unlock_irq(uport); } -static void qcom_geni_serial_flush_buffer(struct uart_port *uport) +static void qcom_geni_serial_flush_buffer_fifo(struct uart_port *uport) { qcom_geni_serial_cancel_tx_cmd(uport); } @@ -1769,7 +1769,7 @@ static const struct uart_ops qcom_geni_console_pops = { .request_port = qcom_geni_serial_request_port, .config_port = qcom_geni_serial_config_port, .shutdown = qcom_geni_serial_shutdown, - .flush_buffer = qcom_geni_serial_flush_buffer, + .flush_buffer = qcom_geni_serial_flush_buffer_fifo, .type = qcom_geni_serial_get_type, .set_mctrl = qcom_geni_serial_set_mctrl, .get_mctrl = qcom_geni_serial_get_mctrl, @@ -1792,6 +1792,7 @@ static const struct uart_ops qcom_geni_uart_pops = { .request_port = qcom_geni_serial_request_port, .config_port = qcom_geni_serial_config_port, .shutdown = qcom_geni_serial_shutdown, + .flush_buffer = qcom_geni_serial_flush_buffer_dma, .type = qcom_geni_serial_get_type, .set_mctrl = qcom_geni_serial_set_mctrl, .get_mctrl = qcom_geni_serial_get_mctrl, diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index b323d1510a67..3d776cfe1113 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -828,6 +828,9 @@ static void sc16is7xx_tx_proc(struct kthread_work *ws) msleep(port->rs485.delay_rts_before_send); guard(mutex)(&one->lock); + sc16is7xx_port_update(port, SC16IS7XX_IER_REG, + SC16IS7XX_IER_THRI_BIT, + SC16IS7XX_IER_THRI_BIT); sc16is7xx_handle_tx(port); } diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c index 763a3f1b7be0..c41d850b29c6 100644 --- a/drivers/tty/vt/keyboard.c +++ b/drivers/tty/vt/keyboard.c @@ -1437,7 +1437,7 @@ static void kbd_keycode(unsigned int keycode, int down, bool hw_raw) struct keyboard_notifier_param param = { .vc = vc, .value = keycode, .down = down }; int rc; - tty = vc->port.tty; + tty = tty_port_tty_get(&vc->port); if (tty && (!tty->driver_data)) { /* No driver data? Strange. Okay we fix it then. */ @@ -1497,9 +1497,12 @@ static void kbd_keycode(unsigned int keycode, int down, bool hw_raw) * characters get aren't echoed locally. This makes key repeat * usable with slow applications and under heavy loads. */ + tty_kref_put(tty); return; } + tty_kref_put(tty); + param.shift = shift_final = (shift_state | kbd->slockstate) ^ kbd->lockstate; param.ledstate = kbd->ledflagstate; key_map = key_maps[shift_final]; diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c index 28993a3d0acb..deb3b3f93461 100644 --- a/drivers/tty/vt/vt_ioctl.c +++ b/drivers/tty/vt/vt_ioctl.c @@ -406,6 +406,8 @@ static int vt_k_ioctl(struct tty_struct *tty, unsigned int cmd, /* this could be folded into KDSKBMODE, but for compatibility reasons it is not so easy to fold KDGKBMETA into KDGKBMODE */ case KDSKBMETA: + if (!perm) + return -EPERM; return vt_do_kdskbmeta(console, arg); case KDGKBMETA: diff --git a/drivers/usb/atm/cxacru.c b/drivers/usb/atm/cxacru.c index f1900c567ba4..429ac20a8999 100644 --- a/drivers/usb/atm/cxacru.c +++ b/drivers/usb/atm/cxacru.c @@ -700,6 +700,8 @@ static int cxacru_cm(struct cxacru_data *instance, enum cxacru_cm_request cm, ret = offd; usb_dbg(instance->usbatm, "cm %#x\n", cm); fail: + if (ret < 0) + usb_kill_urb(instance->rcv_urb); mutex_unlock(&instance->cm_serialize); err: return ret; diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c index 6b3815f8a6e5..5c712bff1d2b 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.c +++ b/drivers/usb/cdns3/cdnsp-gadget.c @@ -155,9 +155,9 @@ static void cdnsp_set_apb_timeout_value(struct cdnsp_device *pdev) offset = cdnsp_find_next_ext_cap(base, offset, D_XEC_PRE_REGS_CAP); reg = base + offset + REG_CHICKEN_BITS_3_OFFSET; - val = le32_to_cpu(readl(reg)); + val = readl(reg); val = CHICKEN_APB_TIMEOUT_SET(val, cdns->override_apb_timeout); - writel(cpu_to_le32(val), reg); + writel(val, reg); } static void cdnsp_set_chicken_bits_2(struct cdnsp_device *pdev, u32 bit) diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 45e20c6d76c0..346a2faa9bb8 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -912,6 +912,18 @@ int usb_get_configuration(struct usb_device *dev) unsigned char *bigbuffer; struct usb_config_descriptor *desc; int result; + size_t usb_config_req_size; + + /* + * We usually start by grabbing the first 9-bytes descriptor so we know + * how long the whole configuration is. Some devices with quirky + * firmware will fail enumeration, so if the quirk is set, use 255 instead, + * mirroring the behavior of Windows. + */ + if (dev->quirks & USB_QUIRK_WINDOWS_CONFIG_REQ_SIZE) + usb_config_req_size = 255; + else + usb_config_req_size = USB_DT_CONFIG_SIZE; if (ncfg > USB_MAXCONFIG) { dev_notice(ddev, "too many configurations: %d, " @@ -938,15 +950,13 @@ int usb_get_configuration(struct usb_device *dev) if (!dev->rawdescriptors) return -ENOMEM; - desc = kmalloc(USB_DT_CONFIG_SIZE, GFP_KERNEL); + desc = kmalloc(usb_config_req_size, GFP_KERNEL); if (!desc) return -ENOMEM; for (cfgno = 0; cfgno < ncfg; cfgno++) { - /* We grab just the first descriptor so we know how long - * the whole configuration is */ result = usb_get_descriptor(dev, USB_DT_CONFIG, cfgno, - desc, USB_DT_CONFIG_SIZE); + desc, usb_config_req_size); if (result < 0) { dev_err(ddev, "unable to read config index %d " "descriptor/%s: %d\n", cfgno, "start", result); @@ -956,16 +966,14 @@ int usb_get_configuration(struct usb_device *dev) dev->descriptor.bNumConfigurations = cfgno; break; } else if (result < 4) { - dev_err(ddev, "config index %d descriptor too short " - "(expected %i, got %i)\n", cfgno, - USB_DT_CONFIG_SIZE, result); + dev_err(ddev, "config index %d descriptor too short (asked for %zu, got %i)\n", + cfgno, usb_config_req_size, result); result = -EINVAL; goto err; } length = max_t(int, le16_to_cpu(desc->wTotalLength), USB_DT_CONFIG_SIZE); - /* Now that we know the length, get the whole thing */ bigbuffer = kmalloc(length, GFP_KERNEL); if (!bigbuffer) { result = -ENOMEM; @@ -975,6 +983,13 @@ int usb_get_configuration(struct usb_device *dev) if (dev->quirks & USB_QUIRK_DELAY_INIT) msleep(200); + /* Skip the second read if we already got everything */ + if (result >= length) { + memcpy(bigbuffer, desc, length); + goto store_and_parse; + } + + /* Get the whole thing */ result = usb_get_descriptor(dev, USB_DT_CONFIG, cfgno, bigbuffer, length); if (result < 0) { @@ -989,6 +1004,7 @@ int usb_get_configuration(struct usb_device *dev) length = result; } +store_and_parse: dev->rawdescriptors[cfgno] = bigbuffer; result = usb_parse_configuration(dev, cfgno, diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 87ee2d938bc0..b5b577f0b931 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -142,6 +142,10 @@ static int quirks_param_set(const char *value, const struct kernel_param *kp) break; case 'q': flags |= USB_QUIRK_FORCE_ONE_CONFIG; + break; + case 'r': + flags |= USB_QUIRK_WINDOWS_CONFIG_REQ_SIZE; + break; /* Ignore unrecognized flag characters */ } } @@ -589,6 +593,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x2386, 0x350e), .driver_info = USB_QUIRK_NO_LPM }, + /* ShanWan Wireless Gamepad */ + { USB_DEVICE(0x2563, 0x0575), .driver_info = USB_QUIRK_WINDOWS_CONFIG_REQ_SIZE }, + /* UGREEN 35871 - BOS descriptor fetch hangs at SuperSpeed Plus */ { USB_DEVICE(0x2b89, 0x5871), .driver_info = USB_QUIRK_NO_BOS }, diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index 64eabda2f546..bf02545b37a2 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -1171,7 +1171,7 @@ static int ncm_unwrap_ntb(struct gether *port, unsigned char *ntb_ptr = skb->data; __le16 *tmp; unsigned index, index2; - int ndp_index; + unsigned int ndp_index; unsigned dg_len, dg_len2; unsigned ndp_len; unsigned block_len; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index d0f14fc23245..fd7420cfbf64 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -187,13 +187,13 @@ struct xhci_op_regs { /* CRCR - Command Ring Control Register - cmd_ring bitmasks */ /* bit 0 - Cycle bit indicates the ownership of the command ring */ -#define CMD_RING_CYCLE BIT(0) +#define CMD_RING_CYCLE BIT_ULL(0) /* stop ring operation after completion of the currently executing command */ -#define CMD_RING_PAUSE BIT(1) +#define CMD_RING_PAUSE BIT_ULL(1) /* stop ring immediately - abort the currently executing command */ -#define CMD_RING_ABORT BIT(2) +#define CMD_RING_ABORT BIT_ULL(2) /* true: command ring is running */ -#define CMD_RING_RUNNING BIT(3) +#define CMD_RING_RUNNING BIT_ULL(3) /* bits 63:6 - Command Ring pointer */ #define CMD_RING_PTR_MASK GENMASK_ULL(63, 6) @@ -268,7 +268,7 @@ struct xhci_intr_reg { * bit 3 - Event Handler Busy (EHB), whether the event ring is scheduled to be serviced by * a work queue (or delayed service routine)? */ -#define ERST_EHB BIT(3) +#define ERST_EHB BIT_ULL(3) /* bits 63:4 - Event Ring Dequeue Pointer */ #define ERST_PTR_MASK GENMASK_ULL(63, 4) @@ -499,7 +499,7 @@ struct xhci_ep_ctx { #define CTX_TO_MAX_ESIT_PAYLOAD(p) (((p) >> 16) & 0xffff) /* deq bitmasks */ -#define EP_CTX_CYCLE_MASK BIT(0) +#define EP_CTX_CYCLE_MASK BIT_ULL(0) /* bits 63:4 - TR Dequeue Pointer */ #define TR_DEQ_PTR_MASK GENMASK_ULL(63, 4) diff --git a/drivers/usb/misc/usbio.c b/drivers/usb/misc/usbio.c index 3c2474dca810..fe093e7760d5 100644 --- a/drivers/usb/misc/usbio.c +++ b/drivers/usb/misc/usbio.c @@ -265,7 +265,7 @@ int usbio_bulk_msg(struct auxiliary_device *adev, u8 type, u8 cmd, bool last, lockdep_assert_held(&usbio->bulk_mutex); if ((obuf_len > (usbio->txbuf_len - sizeof(*bpkt))) || - (ibuf_len > (usbio->txbuf_len - sizeof(*bpkt)))) + (ibuf_len > (usbio->rxbuf_len - sizeof(*bpkt)))) return -EMSGSIZE; if (ibuf_len) diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h index 2cedf7e2dbc4..42f2f44b383c 100644 --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h @@ -11,6 +11,8 @@ #define MLX5V_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN) +extern int mlx5_vdpa_max_iotlb_entries; + struct mlx5_vdpa_direct_mr { u64 start; u64 end; diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index 42c2705077a6..ce204ae3dfda 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -234,7 +234,8 @@ static int create_direct_keys(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr * cmds[i].out = cmd_mem->out; cmds[i].outlen = sizeof(cmd_mem->out); cmds[i].in = cmd_mem->in; - cmds[i].inlen = struct_size(cmd_mem, mtt, mttcount); + cmds[i].inlen = struct_size(cmd_mem, mtt, mttcount) - + offsetof(struct mlx5_create_mkey_mem, in); fill_create_direct_mr(mvdev, dmr, cmd_mem); @@ -777,6 +778,9 @@ static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, { int err; + if (mlx5_vdpa_max_iotlb_entries < 2) + return -EINVAL; + if (iotlb) err = create_user_mr(mvdev, mr, iotlb); else @@ -785,7 +789,7 @@ static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, if (err) return err; - mr->iotlb = vhost_iotlb_alloc(0, 0); + mr->iotlb = vhost_iotlb_alloc(mlx5_vdpa_max_iotlb_entries, 0); if (!mr->iotlb) { err = -ENOMEM; goto err_mr; diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c index aeae31d0cefa..28a4d7a35bf4 100644 --- a/drivers/vdpa/mlx5/core/resources.c +++ b/drivers/vdpa/mlx5/core/resources.c @@ -3,8 +3,14 @@ #include <linux/iova.h> #include <linux/mlx5/driver.h> +#include <linux/moduleparam.h> #include "mlx5_vdpa.h" +int mlx5_vdpa_max_iotlb_entries = 2048; +module_param_named(max_iotlb_entries, mlx5_vdpa_max_iotlb_entries, int, 0444); +MODULE_PARM_DESC(max_iotlb_entries, + "Maximum number of iotlb entries. (default: 2048)"); + static int alloc_pd(struct mlx5_vdpa_dev *dev, u32 *pdn, u16 uid) { struct mlx5_core_dev *mdev = dev->mdev; @@ -229,7 +235,10 @@ int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, u32 mkey) static int init_ctrl_vq(struct mlx5_vdpa_dev *mvdev) { - mvdev->cvq.iotlb = vhost_iotlb_alloc(0, 0); + if (mlx5_vdpa_max_iotlb_entries < 2) + return -EINVAL; + + mvdev->cvq.iotlb = vhost_iotlb_alloc(mlx5_vdpa_max_iotlb_entries, 0); if (!mvdev->cvq.iotlb) return -ENOMEM; diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 8cb1cc2ea139..4d116644851d 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -34,7 +34,7 @@ MODULE_PARM_DESC(batch_mapping, "Batched mapping 1 -Enable; 0 - Disable"); static int max_iotlb_entries = 2048; module_param(max_iotlb_entries, int, 0444); MODULE_PARM_DESC(max_iotlb_entries, - "Maximum number of iotlb entries for each address space. 0 means unlimited. (default: 2048)"); + "Maximum number of iotlb entries for each address space. (default: 2048)"); static bool use_va = true; module_param(use_va, bool, 0444); @@ -201,6 +201,8 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr, if (!dev_attr->alloc_size) return ERR_PTR(-EINVAL); + if (max_iotlb_entries < 2) + return ERR_PTR(-EINVAL); if (config->mask & BIT_ULL(VDPA_ATTR_DEV_FEATURES)) { if (config->device_features & @@ -261,8 +263,10 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr, for (i = 0; i < vdpasim->dev_attr.nas; i++) { vhost_iotlb_init(&vdpasim->iommu[i], max_iotlb_entries, 0); - vhost_iotlb_add_range(&vdpasim->iommu[i], 0, ULONG_MAX, 0, - VHOST_MAP_RW); + ret = vhost_iotlb_add_range(&vdpasim->iommu[i], 0, ULONG_MAX, + 0, VHOST_MAP_RW); + if (ret) + goto err_iommu; vdpasim->iommu_pt[i] = true; } diff --git a/drivers/vdpa/vdpa_user/iova_domain.c b/drivers/vdpa/vdpa_user/iova_domain.c index 4dc76c0d0d13..b6c958224b7c 100644 --- a/drivers/vdpa/vdpa_user/iova_domain.c +++ b/drivers/vdpa/vdpa_user/iova_domain.c @@ -12,11 +12,17 @@ #include <linux/file.h> #include <linux/anon_inodes.h> #include <linux/highmem.h> +#include <linux/moduleparam.h> #include <linux/vmalloc.h> #include <linux/vdpa.h> #include "iova_domain.h" +static int max_iotlb_entries = 2048; +module_param(max_iotlb_entries, int, 0444); +MODULE_PARM_DESC(max_iotlb_entries, + "Maximum number of iotlb entries. (default: 2048)"); + static int vduse_iotlb_add_range(struct vduse_iova_domain *domain, u64 start, u64 last, u64 addr, unsigned int perm, @@ -622,11 +628,14 @@ vduse_domain_create(unsigned long iova_limit, size_t bounce_size) if (iova_limit <= bounce_size) return NULL; + if (max_iotlb_entries <= 0) + return NULL; + domain = kzalloc_obj(*domain); if (!domain) return NULL; - domain->iotlb = vhost_iotlb_alloc(0, 0); + domain->iotlb = vhost_iotlb_alloc(max_iotlb_entries, 0); if (!domain->iotlb) goto err_iotlb; diff --git a/drivers/vhost/iotlb.c b/drivers/vhost/iotlb.c index e1414c774c34..a1d4376a5b87 100644 --- a/drivers/vhost/iotlb.c +++ b/drivers/vhost/iotlb.c @@ -20,6 +20,14 @@ INTERVAL_TREE_DEFINE(struct vhost_iotlb_map, rb, __u64, __subtree_last, START, LAST, static inline, vhost_iotlb_itree); +static void vhost_iotlb_map_unlink(struct vhost_iotlb *iotlb, + struct vhost_iotlb_map *map) +{ + vhost_iotlb_itree_remove(map, &iotlb->root); + list_del(&map->link); + iotlb->nmaps--; +} + /** * vhost_iotlb_map_free - remove a map node and free it * @iotlb: the IOTLB @@ -28,10 +36,8 @@ INTERVAL_TREE_DEFINE(struct vhost_iotlb_map, void vhost_iotlb_map_free(struct vhost_iotlb *iotlb, struct vhost_iotlb_map *map) { - vhost_iotlb_itree_remove(map, &iotlb->root); - list_del(&map->link); + vhost_iotlb_map_unlink(iotlb, map); kfree(map); - iotlb->nmaps--; } EXPORT_SYMBOL_GPL(vhost_iotlb_map_free); @@ -57,14 +63,25 @@ int vhost_iotlb_add_range_ctx(struct vhost_iotlb *iotlb, if (last < start) return -EFAULT; + if (!iotlb->limit) + return -EINVAL; + /* If the range being mapped is [0, ULONG_MAX], split it into two entries * otherwise its size would overflow u64. */ if (start == 0 && last == ULONG_MAX) { u64 mid = last / 2; - int err = vhost_iotlb_add_range_ctx(iotlb, start, mid, addr, - perm, opaque); + int err; + + if (iotlb->limit < 2) + return -ENOSPC; + if (!(iotlb->flags & VHOST_IOTLB_FLAG_RETIRE) && + iotlb->nmaps > iotlb->limit - 2) + return -ENOSPC; + + err = vhost_iotlb_add_range_ctx(iotlb, start, mid, addr, + perm, opaque); if (err) return err; @@ -72,17 +89,19 @@ int vhost_iotlb_add_range_ctx(struct vhost_iotlb *iotlb, start = mid + 1; } - if (iotlb->limit && - iotlb->nmaps == iotlb->limit && - iotlb->flags & VHOST_IOTLB_FLAG_RETIRE) { - map = list_first_entry(&iotlb->list, typeof(*map), link); - vhost_iotlb_map_free(iotlb, map); + if (iotlb->nmaps >= iotlb->limit) { + if (iotlb->flags & VHOST_IOTLB_FLAG_RETIRE) { + map = list_first_entry(&iotlb->list, typeof(*map), link); + vhost_iotlb_map_unlink(iotlb, map); + } else { + return -ENOSPC; + } + } else { + map = kmalloc_obj(*map, GFP_ATOMIC); + if (!map) + return -ENOMEM; } - map = kmalloc_obj(*map, GFP_ATOMIC); - if (!map) - return -ENOMEM; - map->start = start; map->size = last - start + 1; map->last = last; diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 9a1253b9d8c5..904bd842cdd8 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -972,6 +972,9 @@ vhost_scsi_mapal(struct vhost_scsi *vs, struct vhost_scsi_cmd *cmd, if (prot_bytes) { sgl_count = vhost_scsi_calc_sgls(prot_iter, prot_bytes, VHOST_SCSI_PREALLOC_PROT_SGLS); + if (sgl_count < 0) + return sgl_count; + cmd->prot_table.sgl = cmd->prot_sgl; ret = sg_alloc_table_chained(&cmd->prot_table, sgl_count, cmd->prot_table.sgl, @@ -1416,6 +1419,11 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) * actual data payload length. */ if (prot_bytes) { + if (prot_bytes >= exp_data_len) { + vq_err(vq, "Protection data exceeds payload length\n"); + goto err; + } + exp_data_len -= prot_bytes; prot_iter = data_iter; iov_iter_truncate(&prot_iter, prot_bytes); @@ -2219,6 +2227,7 @@ static int vhost_scsi_set_features(struct vhost_scsi *vs, u64 features) { struct vhost_virtqueue *vq; bool is_log, was_log; + u64 old_features; int i; if (features & ~VHOST_SCSI_FEATURES) @@ -2234,6 +2243,14 @@ static int vhost_scsi_set_features(struct vhost_scsi *vs, u64 features) if (!vs->dev.nvqs) goto out; + old_features = vs->vqs[0].vq.acked_features; + if (vs->vs_tpg && + ((features ^ old_features) & + ~(1ULL << VHOST_F_LOG_ALL))) { + mutex_unlock(&vs->dev.mutex); + return -EBUSY; + } + is_log = features & (1 << VHOST_F_LOG_ALL); /* * All VQs should have same feature. diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index ac55275fa0d0..c3d913bd7cac 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -34,6 +34,11 @@ enum { #define VHOST_VDPA_DEV_MAX (1U << MINORBITS) +static int max_iotlb_entries = 2048; +module_param(max_iotlb_entries, int, 0444); +MODULE_PARM_DESC(max_iotlb_entries, + "Maximum number of iotlb entries. (default: 2048)"); + #define VHOST_VDPA_IOTLB_BUCKETS 16 struct vhost_vdpa_as { @@ -109,12 +114,14 @@ static struct vhost_vdpa_as *vhost_vdpa_alloc_as(struct vhost_vdpa *v, u32 asid) if (asid >= v->vdpa->nas) return NULL; + if (max_iotlb_entries <= 0) + return NULL; as = kmalloc_obj(*as); if (!as) return NULL; - vhost_iotlb_init(&as->iotlb, 0, 0); + vhost_iotlb_init(&as->iotlb, max_iotlb_entries, 0); as->id = asid; hlist_add_head(&as->hash_link, head); @@ -1102,6 +1109,7 @@ static int vhost_vdpa_pa_map(struct vhost_vdpa *v, unsigned int gup_flags = FOLL_LONGTERM; unsigned long npages, cur_base, map_pfn, last_pfn = 0; unsigned long lock_limit, sz2pin, nchunks, i; + unsigned long page_offset; u64 start = iova; long pinned; int ret = 0; @@ -1114,7 +1122,13 @@ static int vhost_vdpa_pa_map(struct vhost_vdpa *v, if (perm & VHOST_ACCESS_WO) gup_flags |= FOLL_WRITE; - npages = PFN_UP(size + (iova & ~PAGE_MASK)); + page_offset = iova & ~PAGE_MASK; + if (size > ULONG_MAX - page_offset) { + ret = -EINVAL; + goto free; + } + + npages = PFN_UP(size + page_offset); if (!npages) { ret = -EINVAL; goto free; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index db329a6f6145..e4c44f2ea413 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1137,6 +1137,9 @@ EXPORT_SYMBOL_GPL(vhost_dev_set_owner); static struct vhost_iotlb *iotlb_alloc(void) { + if (max_iotlb_entries <= 0) + return NULL; + return vhost_iotlb_alloc(max_iotlb_entries, VHOST_IOTLB_FLAG_RETIRE); } @@ -1981,6 +1984,8 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) return -EOPNOTSUPP; if (mem.nregions > max_mem_regions) return -E2BIG; + if (max_iotlb_entries <= 0) + return -EINVAL; newmem = kvzalloc_flex(*newmem, regions, mem.nregions); if (!newmem) return -ENOMEM; @@ -2126,6 +2131,14 @@ static long vhost_vring_set_num_addr(struct vhost_dev *d, BUG(); } + /* + * The metadata cache holds the IOTLB mapping that backed the previous + * desc/avail/used addresses and vring size, both of which are being + * replaced here. iotlb_access_ok() takes a cache hit as proof that the + * region was validated, so the stale entries have to go. + */ + __vhost_vq_meta_reset(vq); + mutex_unlock(&vq->mutex); return r; @@ -2275,6 +2288,9 @@ int vhost_init_device_iotlb(struct vhost_dev *d) struct vhost_iotlb *niotlb, *oiotlb; int i; + if (max_iotlb_entries <= 0) + return -EINVAL; + niotlb = iotlb_alloc(); if (!niotlb) return -ENOMEM; diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c index 65681dcc5930..39f44258d793 100644 --- a/drivers/video/fbdev/core/bitblit.c +++ b/drivers/video/fbdev/core/bitblit.c @@ -273,9 +273,14 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, bool enable, if (!vc->vc_font.data) return; - c = scr_readw((u16 *) vc->vc_pos); + c = scr_readw((u16 *) vc->vc_pos); attribute = get_attribute(info, c); - src = vc->vc_font.data + ((c & charmask) * (w * vc->vc_font.height)); + c &= charmask; + + /* Clamp to font size, same as bit_putcs_aligned() */ + if (c >= vc->vc_font.charcount) + c = 0; + src = vc->vc_font.data + (c * (w * vc->vc_font.height)); if (par->cursor_state.image.data != (const char *)src || par->cursor_reset) { diff --git a/drivers/watchdog/at91sam9_wdt.c b/drivers/watchdog/at91sam9_wdt.c index aba66b8e9d03..80ba04df54ad 100644 --- a/drivers/watchdog/at91sam9_wdt.c +++ b/drivers/watchdog/at91sam9_wdt.c @@ -242,7 +242,7 @@ static int at91_wdt_init(struct platform_device *pdev, struct at91wdt *wdt) return 0; out_stop_timer: - timer_delete(&wdt->timer); + timer_shutdown_sync(&wdt->timer); return err; } @@ -378,7 +378,7 @@ static void at91wdt_remove(struct platform_device *pdev) watchdog_unregister_device(&wdt->wdd); pr_warn("I quit now, hardware will probably reboot!\n"); - timer_delete(&wdt->timer); + timer_shutdown_sync(&wdt->timer); } #if defined(CONFIG_OF) diff --git a/drivers/watchdog/bd96801_wdt.c b/drivers/watchdog/bd96801_wdt.c index 12b74fd2bc05..a25b7cf1488b 100644 --- a/drivers/watchdog/bd96801_wdt.c +++ b/drivers/watchdog/bd96801_wdt.c @@ -169,7 +169,6 @@ static int bd96801_set_wdt_mode(struct wdtbd96801 *w, unsigned int hw_margin, int fastng, slowng, type, ret, reg, mask; struct device *dev = w->dev; - if (hw_margin_min * 1000 > FASTNG_MAX_US) { dev_err(dev, "Unsupported fast timeout %u uS [max %u]\n", hw_margin_min * 1000, FASTNG_MAX_US); @@ -258,10 +257,10 @@ static int bd96801_set_heartbeat_from_hw(struct wdtbd96801 *w, fast = FASTNG_MIN << sel; sel = (val & BD96801_WD_RATIO_MASK) + 1; - w->wdt.max_hw_heartbeat_ms = (fast << sel) / USEC_PER_MSEC; + w->wdt.max_hw_heartbeat_ms = (fast << sel) / 10; if ((conf_reg & BD96801_WD_TYPE_MASK) == BD96801_WD_TYPE_WIN) - w->wdt.min_hw_heartbeat_ms = fast / USEC_PER_MSEC; + w->wdt.min_hw_heartbeat_ms = fast / 10; return 0; } diff --git a/fs/attr.c b/fs/attr.c index ded221defae6..fc5817c9f4e8 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -176,7 +176,7 @@ int setattr_prepare(struct mnt_idmap *idmap, struct dentry *dentry, * covered by the open-time check because sys_truncate() takes a * path, not an open file. */ - if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode)) + if (IS_VERITY(inode)) return -EPERM; error = inode_newsize_ok(inode, attr->ia_size); diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 725b48ac5873..b7075e4df46f 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -937,7 +937,8 @@ static int bm_fill_super(struct super_block *sb, struct fs_context *fc) /* last one */ {""} }; - if (WARN_ON(user_ns != current_user_ns())) + /* The fscontext fd may have been passed to another user namespace. */ + if (user_ns != current_user_ns()) return -EINVAL; /* Never exec off this instance and never let anything stack on it. */ diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index dc5148f176e7..1271be0fbfcf 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4167,10 +4167,11 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path btrfs_inode_split_flags(btrfs_inode_flags(leaf, inode_item), &inode->flags, &inode->ro_flags); + +cache_index: btrfs_update_inode_mapping_flags(inode); btrfs_set_inode_mapping_order(inode); -cache_index: /* * If we were modified in the current generation and evicted from memory * and then re-read we need to do a full sync since we don't have any @@ -10193,6 +10194,7 @@ out_cb: if (cb) cleanup_compressed_bio(cb); out: + extent_changeset_free(data_reserved); if (ret >= 0) iocb->ki_pos += encoded->len; return ret; diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index 6e4aa22853ab..2f0996692da0 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -552,17 +552,27 @@ int lzo_decompress(struct list_head *ws, const u8 *data_in, size_t max_segment_len = workspace_buf_length(fs_info); int ret; - if (unlikely(srclen < LZO_LEN || srclen > max_segment_len + LZO_LEN * 2)) + if (unlikely(srclen <= LZO_LEN * 2 || + srclen > max_segment_len + LZO_LEN * 2)) { + btrfs_err(fs_info, "invalid lzo header length, has %zu expect (%u, %zu)", + srclen, LZO_LEN * 2, max_segment_len + LZO_LEN * 2); return -EUCLEAN; + } in_len = get_unaligned_le32(data_in); - if (unlikely(in_len != srclen)) + if (unlikely(in_len != srclen)) { + btrfs_err(fs_info, "invalid lzo header length, has %zu expect %zu", + in_len, srclen); return -EUCLEAN; + } data_in += LZO_LEN; in_len = get_unaligned_le32(data_in); - if (unlikely(in_len != srclen - LZO_LEN * 2)) + if (unlikely(in_len != srclen - LZO_LEN * 2)) { + btrfs_err(fs_info, "invalid lzo segment length, has %zu expect %zu", + in_len, srclen - LZO_LEN * 2); return -EUCLEAN; + } data_in += LZO_LEN; out_len = sectorsize; diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 9915e39362db..c80b24a941ad 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -534,7 +534,7 @@ int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg) return -EFAULT; policy.version = version; - if (!inode_owner_or_capable(&nop_mnt_idmap, inode)) + if (!inode_owner_or_capable(file_mnt_idmap(filp), inode)) return -EACCES; ret = mnt_want_write_file(filp); diff --git a/fs/namespace.c b/fs/namespace.c index 341ddd353b3a..841ef2612786 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4502,6 +4502,10 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, new_mnt = vfs_create_mount(fc); if (IS_ERR(new_mnt)) return PTR_ERR(new_mnt); + if (new_mnt->mnt_sb->s_flags & SB_NOUSER) { + mntput(new_mnt); + return -EINVAL; + } new_mnt->mnt_flags = mnt_flags; new_path.dentry = dget(fc->root); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 4db27f4eb01e..6142a7daf983 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -10330,6 +10330,7 @@ static void nfs41_free_stateid_release(void *calldata) struct nfs_free_stateid_data *data = calldata; struct nfs_client *clp = data->server->nfs_client; + nfs_sb_deactive(data->server->super); nfs_put_client(clp); kfree(calldata); } @@ -10368,17 +10369,22 @@ static int nfs41_free_stateid(struct nfs_server *server, struct nfs_free_stateid_data *data; struct rpc_task *task; struct nfs_client *clp = server->nfs_client; + int ret = -EIO; if (!refcount_inc_not_zero(&clp->cl_count)) - return -EIO; + return ret; + if (!nfs_sb_active(server->super)) + goto out_put_clp; nfs4_state_protect(clp, NFS_SP4_MACH_CRED_STATEID, &task_setup.rpc_client, &msg); dprintk("NFS call free_stateid %p\n", stateid); data = kmalloc_obj(*data); - if (!data) - return -ENOMEM; + if (!data) { + ret = -ENOMEM; + goto out_put_server; + } data->server = server; nfs4_stateid_copy(&data->args.stateid, stateid); @@ -10394,6 +10400,11 @@ static int nfs41_free_stateid(struct nfs_server *server, rpc_put_task(task); stateid->type = NFS4_FREED_STATEID_TYPE; return 0; +out_put_server: + nfs_sb_deactive(server->super); +out_put_clp: + nfs_put_client(clp); + return ret; } static void diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 60f0b7ceef0a..60b808b85fc4 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1544,7 +1544,8 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) int err; err = -EIO; - if (WARN_ON(fc->user_ns != current_user_ns())) + /* The fscontext fd may have been passed to another user namespace. */ + if (fc->user_ns != current_user_ns()) goto out_err; ovl_set_d_op(sb); diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index de2012cc9cf3..7cf7dd104f7c 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -233,9 +233,9 @@ int cifs_try_adding_channels(struct cifs_ses *ses) cifs_dbg(VFS, "failed to open extra channel on iface:%pIS rc=%d\n", &iface->sockaddr, rc); - kref_put(&iface->refcount, release_iface); /* failure to add chan should increase weight */ iface->weight_fulfilled++; + kref_put(&iface->refcount, release_iface); continue; } diff --git a/fs/smb/client/smb1transport.c b/fs/smb/client/smb1transport.c index 53abb29fe71b..966f2cf83a51 100644 --- a/fs/smb/client/smb1transport.c +++ b/fs/smb/client/smb1transport.c @@ -260,9 +260,23 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, goto out; if (out_buf) { - *pbytes_returned = resp_iov.iov_len; - if (resp_iov.iov_len) - memcpy(out_buf, resp_iov.iov_base, resp_iov.iov_len); + /* Use smbCalcSize() for both single- and multi-part T2 responses, + * both here and in coalesce_t2(). + */ + unsigned int copy_len; + if (WARN_ON_ONCE(!resp_iov.iov_base)) { + rc = -EIO; + goto out; + } + copy_len = smbCalcSize(resp_iov.iov_base); + if (copy_len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) { + cifs_dbg(VFS, "response size %u exceeds buffer\n", + copy_len); + rc = -ENOBUFS; + goto out; + } + *pbytes_returned = copy_len; + memcpy(out_buf, resp_iov.iov_base, copy_len); } out: @@ -386,11 +400,13 @@ coalesce_t2(char *second_buf, struct smb_hdr *target_hdr, unsigned int *pdu_len) } put_bcc(byte_count, target_hdr); - byte_count = *pdu_len; - byte_count += total_in_src; + /* use smbCalcSize() rather than *pdu_len: the demux loop resets + * *pdu_len to each secondary's pdu_length, making it unreliable. + */ + byte_count = smbCalcSize(target_hdr); /* don't allow buffer to overflow */ if (byte_count > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) { - cifs_dbg(FYI, "coalesced BCC exceeds buffer size (%u)\n", + cifs_dbg(FYI, "coalesced size exceeds buffer size (%u)\n", byte_count); return -ENOBUFS; } diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 26b6453de30e..498d316bf5d7 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -124,7 +124,17 @@ static inline void put_ei(struct eventfs_inode *ei) static inline void free_ei(struct eventfs_inode *ei) { if (ei) { + /* The ei should have no children if it is being freed. */ + WARN_ON_ONCE(!list_empty(&ei->children)); ei->is_freed = 1; + /* + * The SRCU iteration has a smp_rmb() to make sure it + * sees a child (that may have already been freed) + * before it reads is_free. If is_free is set, it must + * not use the child it acquired from ei->children, as + * the list may be used for SRCU. + */ + smp_wmb(); put_ei(ei); } } @@ -629,6 +639,20 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx) list_for_each_entry_srcu(ei_child, &ei->children, list, srcu_read_lock_held(&eventfs_srcu)) { + /* + * If the ei is being freed, then the ei->children may be + * being used as the rcu list, which means the next element + * may be garbage. The ei->is_free is set before switching + * the ei->children over to ei->rcu. The read memory barrier + * here makes sure the ei_child is read before is_free is + * updated. + * + * Matches the smp_wmb() in free_ei() + */ + smp_rmb(); + if (ei->is_freed) + return -EINVAL; + if (c > 0) { c--; continue; @@ -824,7 +848,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry */ static void eventfs_remove_rec(struct eventfs_inode *ei, int level) { - struct eventfs_inode *ei_child; + struct eventfs_inode *ei_child, *tmp; /* * Check recursion depth. It should never be greater than 3: @@ -837,7 +861,7 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level) return; /* search for nested folders or files */ - list_for_each_entry(ei_child, &ei->children, list) + list_for_each_entry_safe(ei_child, tmp, &ei->children, list) eventfs_remove_rec(ei_child, level + 1); list_del_rcu(&ei->list); diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index a4a7f8431aff..c61481d04c8e 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -46,11 +46,11 @@ struct eventfs_attr { * @ino: The saved inode number */ struct eventfs_inode { + struct list_head list; union { - struct list_head list; + struct list_head children; struct rcu_head rcu; }; - struct list_head children; const struct eventfs_entry *entries; const char *name; struct eventfs_attr *entry_attrs; diff --git a/fs/verity/measure.c b/fs/verity/measure.c index 6a35623ebdf0..465ec3733a8a 100644 --- a/fs/verity/measure.c +++ b/fs/verity/measure.c @@ -122,11 +122,11 @@ __bpf_kfunc int bpf_get_fsverity_digest(struct file *file, struct bpf_dynptr *di { struct bpf_dynptr_kern *digest_ptr = (struct bpf_dynptr_kern *)digest_p; const struct inode *inode = file_inode(file); - u32 dynptr_sz = __bpf_dynptr_size(digest_ptr); + u64 dynptr_sz = __bpf_dynptr_size(digest_ptr); struct fsverity_digest *arg; const struct fsverity_info *vi; const struct fsverity_hash_alg *hash_alg; - int out_digest_sz; + u64 out_digest_sz; if (dynptr_sz < sizeof(struct fsverity_digest)) return -EINVAL; @@ -144,17 +144,20 @@ __bpf_kfunc int bpf_get_fsverity_digest(struct file *file, struct bpf_dynptr *di hash_alg = vi->tree_params.hash_alg; + out_digest_sz = dynptr_sz - sizeof(struct fsverity_digest); + if (out_digest_sz < hash_alg->digest_size) + return -EOVERFLOW; + arg->digest_algorithm = hash_alg - fsverity_hash_algs; arg->digest_size = hash_alg->digest_size; - out_digest_sz = dynptr_sz - sizeof(struct fsverity_digest); - /* copy digest */ - memcpy(arg->digest, vi->file_digest, min_t(int, hash_alg->digest_size, out_digest_sz)); + memcpy(arg->digest, vi->file_digest, hash_alg->digest_size); /* fill the extra buffer with zeros */ if (out_digest_sz > hash_alg->digest_size) - memset(arg->digest + arg->digest_size, 0, out_digest_sz - hash_alg->digest_size); + memset(arg->digest + hash_alg->digest_size, 0, + out_digest_sz - hash_alg->digest_size); return 0; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 0cea458f1353..23bd81fbc278 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -114,7 +114,7 @@ xfs_buf_free( vfree(bp->b_addr); else if (bp->b_flags & _XBF_KMEM) kfree(bp->b_addr); - else + else if (bp->b_addr) folio_put(virt_to_folio(bp->b_addr)); call_rcu(&bp->b_rcu, xfs_buf_free_callback); diff --git a/include/linux/dibs.h b/include/linux/dibs.h index c75607f8a5cf..d3e0777f25ae 100644 --- a/include/linux/dibs.h +++ b/include/linux/dibs.h @@ -439,7 +439,7 @@ static inline void *dibs_get_priv(struct dibs_dev *dev, /** * dibs_dev_alloc() - allocate and reference device structure * - * The following fields will be valid upon successful return: dev + * The following fields will be valid upon successful return: dev, lock * NOTE: Use put_device(dibs_get_dev(@dibs)) to give up your reference instead * of freeing @dibs @dev directly once you have successfully called this * function. diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 301a83afbd66..f5330e7ae247 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -13,6 +13,7 @@ #define _HWMON_H_ #include <linux/bitops.h> +#include <linux/cleanup.h> struct device; struct attribute_group; @@ -495,6 +496,8 @@ char *devm_hwmon_sanitize_name(struct device *dev, const char *name); void hwmon_lock(struct device *dev); void hwmon_unlock(struct device *dev); +DEFINE_GUARD(hwmon_lock, struct device *, hwmon_lock(_T), hwmon_unlock(_T)) + /** * hwmon_is_bad_char - Is the char invalid in a hwmon name * @ch: the char to be considered diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 04b8f61ece5d..6b5c2390cc30 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -621,6 +621,7 @@ static inline void mmap_read_unlock(struct mm_struct *mm) DEFINE_GUARD(mmap_read_lock, struct mm_struct *, mmap_read_lock(_T), mmap_read_unlock(_T)) +DEFINE_GUARD_COND(mmap_read_lock, _try, mmap_read_trylock(_T)) static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4a0e83709f29..7bd4d989d2eb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -300,9 +300,11 @@ struct hh_cache { * We could use other alignment values, but we must maintain the * relationship HH alignment <= LL alignment. */ -#define LL_RESERVED_SPACE(dev) \ - ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \ +#define LL_RESERVED_SPACE_EX(dev, hlen) \ + ((((hlen) + READ_ONCE((dev)->needed_headroom)) \ & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) +#define LL_RESERVED_SPACE(dev) \ + LL_RESERVED_SPACE_EX(dev, (dev)->hard_header_len) #define LL_RESERVED_SPACE_EXTRA(dev,extra) \ ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \ & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) @@ -3507,11 +3509,6 @@ static inline bool dev_validate_header(const struct net_device *dev, if (len < dev->min_header_len) return false; - if (capable(CAP_SYS_RAWIO)) { - memset(ll_header + len, 0, dev->hard_header_len - len); - return true; - } - if (dev->header_ops && dev->header_ops->validate) return dev->header_ops->validate(ll_header, len); diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index b98331572ad2..cadae9b2578f 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -273,7 +273,7 @@ struct ip_set { /* Number of elements (vs timeout) */ u32 elements; /* Size of the dynamic extensions (vs timeout) */ - size_t ext_size; + atomic64_t ext_size; /* Element data size */ size_t dsize; /* Offsets to extensions in elements */ diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index f3b13da78aac..6063fe5b7784 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -214,6 +214,12 @@ static inline int nvmem_layout_register(struct nvmem_layout *layout) static inline void nvmem_layout_unregister(struct nvmem_layout *layout) {} +static inline int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, + struct device_node *np) +{ + return -EOPNOTSUPP; +} + #endif /* CONFIG_NVMEM */ #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) diff --git a/include/linux/psi.h b/include/linux/psi.h index e0745873e3f2..7966e3ac03b9 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -25,7 +25,9 @@ void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, enum psi_res res, struct file *file, - struct kernfs_open_file *of); + struct kernfs_open_file *of, + bool *need_rtpoll_worker); +int psi_trigger_create_rtpoll_worker(struct psi_group *group); void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 2129e18ada58..31c810a3b808 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -235,11 +235,11 @@ struct sched_ext_entity { * to %SCHED_EXT with -%EACCES. * * Can be set from ops.init_task() while the BPF scheduler is being - * loaded (!scx_init_task_args->fork). If set and the task's policy is - * already %SCHED_EXT, the task's policy is rejected and forcefully - * reverted to %SCHED_NORMAL. The number of such events are reported - * through /sys/kernel/debug/sched_ext::nr_rejected. Setting this flag - * during fork is not allowed. + * loaded. If set and the task's policy is already %SCHED_EXT, the + * task's policy is rejected and forcefully reverted to %SCHED_NORMAL. + * The number of such events are reported through + * /sys/kernel/sched_ext/nr_rejected. Setting this flag from any other + * ops.init_task() invocation, such as during fork, fails the scheduler. */ bool disallow; /* reject switching into SCX */ diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index b3cc7beab4a3..a4043b33c2c2 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -81,4 +81,7 @@ /* Device claims zero configurations, forcing to 1 */ #define USB_QUIRK_FORCE_ONE_CONFIG BIT(18) +/* Use a 255 bytes config descriptor request mirroring windows behavior */ +#define USB_QUIRK_WINDOWS_CONFIG_REQ_SIZE BIT(19) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/net/act_api.h b/include/net/act_api.h index fd2967ee08f7..ee29d25d8df2 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -270,6 +270,25 @@ int tcf_action_check_ctrlact(int action, struct tcf_proto *tp, struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action, struct tcf_chain *newchain); +/* Range check for a control action supplied by user space. + * + * This is the same test tcf_action_check_ctrlact() applies to the primary + * control action, factored out for the *fallback* control actions + * (act_gact's TCA_GACT_PROB.paction and act_police's TCA_POLICE_RESULT), + * which must not reach tcf_action_check_ctrlact() because they have no + * goto_chain to allocate. Without it, user space can store kernel-internal + * verdicts such as TC_ACT_CONSUMED, which is TC_ACT_VALUE_MAX + 1 and is + * deliberately not part of the UAPI value range. + */ +static inline bool tcf_action_valid(int action) +{ + int opcode = TC_ACT_EXT_OPCODE(action); + + if (!opcode) + return action <= TC_ACT_VALUE_MAX; + return opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC; +} + #ifdef CONFIG_INET DECLARE_STATIC_KEY_FALSE(tcf_frag_xmit_count); #endif diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 8ced27a8229b..e6764245995f 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -405,8 +405,8 @@ static inline struct inet6_dev *in6_dev_get(const struct net_device *dev) rcu_read_lock(); idev = rcu_dereference(dev->ip6_ptr); - if (idev) - refcount_inc(&idev->refcnt); + if (idev && !refcount_inc_not_zero(&idev->refcnt)) + idev = NULL; rcu_read_unlock(); return idev; } diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 8d98f7e0a9fb..7f7fa4484492 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -25,9 +25,7 @@ #include <linux/netfilter.h> /* for union nf_inet_addr */ #include <linux/ip.h> #include <linux/ipv6.h> /* for struct ipv6hdr */ -#include <net/route.h> #include <net/ipv6.h> -#include <net/ip6_fib.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #endif @@ -38,6 +36,12 @@ #define IP_VS_HDR_INVERSE 1 #define IP_VS_HDR_ICMP 2 +/* Destination Server Flags */ +#define IP_VS_DEST_F_OVERLOAD 0x0002 /* server is overloaded */ + +/* Destination Server Config Flags */ +#define IP_VS_DEST_CF_AVAILABLE 0x0001 /* server is available */ + /* conn_tab limits (as per Kconfig) */ #define IP_VS_CONN_TAB_MIN_BITS 8 #if BITS_PER_LONG > 32 @@ -970,6 +974,7 @@ struct ip_vs_dest { volatile unsigned int flags; /* dest status flags */ atomic_t conn_flags; /* flags to copy to conn */ atomic_t weight; /* server weight */ + unsigned long cflags; /* config flags */ atomic_t last_weight; /* server latest weight */ __u16 tun_type; /* tunnel type */ __be16 tun_port; /* tunnel port */ @@ -981,10 +986,11 @@ struct ip_vs_dest { /* connection counters and thresholds */ atomic_t activeconns; /* active connections */ - atomic_t inactconns; /* inactive connections */ + atomic_t totalconns; /* total connections */ atomic_t persistconns; /* persistent connections */ __u32 u_threshold; /* upper threshold */ __u32 l_threshold; /* lower threshold */ + __u32 l_threshold_val;/* used lower threshold */ /* for destination cache */ spinlock_t dst_lock; /* lock of dst_cache */ @@ -1887,6 +1893,8 @@ static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest) kfree(dest); } +void ip_vs_dest_update_overload(struct ip_vs_dest *dest, int mode); + /* IPVS sync daemon data and function prototypes * (from ip_vs_sync.c) */ @@ -2040,7 +2048,7 @@ static inline bool ip_vs_conn_use_hash2(struct ip_vs_conn *cp) void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int dir, unsigned int toff, - bool has_ports); + bool has_ports, struct ip_vs_iphdr *ciph); #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, @@ -2073,30 +2081,23 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum) return csum_partial(diff, sizeof(diff), oldsum); } -static inline bool ip_vs_checksum_needed(struct sk_buff *skb, int af) +static inline bool ip_vs_checksum_needed(struct sk_buff *skb) { /* Checksum unnecessary or already validated? */ if (skb_csum_unnecessary(skb)) return false; - /* LOCAL_OUT ? */ - if (!skb->dev || skb->dev->flags & IFF_LOOPBACK) + /* Locally generated ? */ + if (!skb->dev) return false; - /* !LOCAL_IN (FORWARD) ? */ - if (af == AF_INET6) { - if (!(dst_rt6_info(skb_dst(skb))->rt6i_flags & RTF_LOCAL)) - return false; - } else { - if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) - return false; - } return true; } static inline bool ip_vs_checksum_common_check(struct sk_buff *skb, int offset, int proto, int af) { - if (!ip_vs_checksum_needed(skb, af)) + if (!ip_vs_checksum_needed(skb)) return true; + /* Validate csum even for FORWARD */ return !nf_checksum(skb, NF_INET_LOCAL_IN, offset, proto, af); } @@ -2207,14 +2208,21 @@ void ip_vs_unregister_hooks(struct netns_ipvs *ipvs, unsigned int af); static inline int ip_vs_dest_conn_overhead(struct ip_vs_dest *dest) { - /* We think the overhead of processing active connections is 256 + /* We think the overhead of processing active connections is 257 * times higher than that of inactive connections in average. (This - * 256 times might not be accurate, we will change it later) We + * 257 times might not be accurate, we will change it later) We * use the following formula to estimate the overhead now: - * dest->activeconns*256 + dest->inactconns + * dest->activeconns*256 + dest->totalconns */ return (atomic_read(&dest->activeconns) << 8) + - atomic_read(&dest->inactconns); + atomic_read(&dest->totalconns); +} + +static inline int +ip_vs_dest_inactconns(const struct ip_vs_dest *dest) +{ + return max(atomic_read(&dest->totalconns) - + atomic_read(&dest->activeconns), 0); } #ifdef CONFIG_IP_VS_PROTO_TCP diff --git a/include/net/libeth/xsk.h b/include/net/libeth/xsk.h index 82b5d21aae87..5dcc0d7f65b7 100644 --- a/include/net/libeth/xsk.h +++ b/include/net/libeth/xsk.h @@ -205,7 +205,7 @@ __libeth_xsk_xmit_fill_buf_md(const struct xdp_desc *xdesc, BUILD_BUG_ON(!__builtin_constant_p(tmo == libeth_xsktmo)); tmo = tmo == libeth_xsktmo ? &__libeth_xsktmo : tmo; - xsk_tx_metadata_request(ctx.meta, tmo, &desc); + xsk_tx_metadata_request(sq->pool, &ctx.meta, tmo, &desc); return desc; } diff --git a/include/net/route.h b/include/net/route.h index f90106f383c5..45290177a33c 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -276,6 +276,8 @@ int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fib_info *fi, int *fa_index, int fa_start, unsigned int flags); +void fnhe_update_pmtu(struct fib_nh_exception *fnhe, u32 new, u32 orig); + static inline void ip_rt_put(struct rtable *rt) { /* dst_release() accepts a NULL parameter. diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 195e22a83566..ca51b2c3b042 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -99,6 +99,7 @@ struct Qdisc { struct hlist_node hash; u32 handle; u32 parent; + int depth; struct netdev_queue *dev_queue; diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 8b51876efbed..6e70b320b399 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -141,45 +141,16 @@ INDIRECT_CALLABLE_DECLARE(void xsk_destruct_skb(struct sk_buff *)); static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta, struct xsk_tx_metadata_compl *compl) { - if (!meta) - return; + compl->tx_timestamp = NULL; - if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP) - compl->tx_timestamp = &meta->completion.tx_timestamp; - else - compl->tx_timestamp = NULL; -} - -/** - * xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission - * and call appropriate xsk_tx_metadata_ops operation. - * @meta: pointer to AF_XDP metadata area - * @ops: pointer to struct xsk_tx_metadata_ops - * @priv: pointer to driver-private aread - * - * This function should be called by the networking device when - * it prepares AF_XDP egress packet. - */ -static inline void xsk_tx_metadata_request(const struct xsk_tx_metadata *meta, - const struct xsk_tx_metadata_ops *ops, - void *priv) -{ if (!meta) return; - if (ops->tmo_request_launch_time) - if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME) - ops->tmo_request_launch_time(meta->request.launch_time, - priv); - - if (ops->tmo_request_timestamp) - if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP) - ops->tmo_request_timestamp(priv); + /* we can only arrive here if the completion timestamp has been + * requested via XDP_TXMD_FLAGS_TIMESTAMP, see xsk_tx_metadata_request + */ - if (ops->tmo_request_checksum) - if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) - ops->tmo_request_checksum(meta->request.csum_start, - meta->request.csum_offset, priv); + compl->tx_timestamp = &meta->completion.tx_timestamp; } /** @@ -231,12 +202,6 @@ static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta, { } -static inline void xsk_tx_metadata_request(struct xsk_tx_metadata *meta, - const struct xsk_tx_metadata_ops *ops, - void *priv) -{ -} - static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl, const struct xsk_tx_metadata_ops *ops, void *priv) diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 46797645a0c2..b344789f5df8 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -245,7 +245,7 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr) * details. * * Return: new &xdp_desc_ctx struct containing desc's DMA address and metadata - * pointer, if it is present and valid (initialized to %NULL otherwise). + * pointer, if it is present (initialized to %NULL otherwise). */ static inline struct xdp_desc_ctx xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr) @@ -260,24 +260,70 @@ xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr) 0) static inline bool -xsk_buff_valid_tx_metadata(const struct xsk_tx_metadata *meta) +xsk_buff_valid_tx_metadata(const struct xsk_buff_pool *pool, + const struct xsk_tx_metadata *meta, u64 *flags) { - return !(meta->flags & ~XDP_TXMD_FLAGS_VALID); + *flags = READ_ONCE(meta->flags); + if (*flags & XDP_TXMD_FLAGS_LAUNCH_TIME) + if (pool->tx_metadata_len < + offsetofend(struct xsk_tx_metadata, request.launch_time)) + return false; + return !(*flags & ~XDP_TXMD_FLAGS_VALID); +} + +/** + * xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission + * and call appropriate xsk_tx_metadata_ops operation. + * @pool: pointer to AF_XDP buffer pool, used to validate the metadata + * @pmeta: pointer to pointer to AF_XDP metadata area + * @ops: pointer to struct xsk_tx_metadata_ops + * @priv: pointer to driver-private area + * + * This function should be called by the networking device when + * it prepares AF_XDP egress packet. + */ +static inline void +xsk_tx_metadata_request(const struct xsk_buff_pool *pool, + struct xsk_tx_metadata **pmeta, + const struct xsk_tx_metadata_ops *ops, void *priv) +{ + const struct xsk_tx_metadata *meta = *pmeta; + u64 flags; + + if (!meta) + return; + + if (unlikely(!xsk_buff_valid_tx_metadata(pool, meta, &flags))) { + *pmeta = NULL; + return; /* no way to signal the error to the user */ + } + + if (ops->tmo_request_launch_time) + if (flags & XDP_TXMD_FLAGS_LAUNCH_TIME) + ops->tmo_request_launch_time( + READ_ONCE(meta->request.launch_time), priv); + + if (ops->tmo_request_timestamp) + if (flags & XDP_TXMD_FLAGS_TIMESTAMP) + ops->tmo_request_timestamp(priv); + + if (ops->tmo_request_checksum) + if (flags & XDP_TXMD_FLAGS_CHECKSUM) + ops->tmo_request_checksum( + READ_ONCE(meta->request.csum_start), + READ_ONCE(meta->request.csum_offset), priv); + + if (!(flags & XDP_TXMD_FLAGS_TIMESTAMP)) + *pmeta = NULL; } static inline struct xsk_tx_metadata * __xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data) { - struct xsk_tx_metadata *meta; - if (!pool->tx_metadata_len) return NULL; - meta = data - pool->tx_metadata_len; - if (unlikely(!xsk_buff_valid_tx_metadata(meta))) - return NULL; /* no way to signal the error to the user */ - - return meta; + return data - pool->tx_metadata_len; } static inline struct xsk_tx_metadata * @@ -469,11 +515,20 @@ xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr) return (struct xdp_desc_ctx){ }; } -static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta) +static inline bool +xsk_buff_valid_tx_metadata(const struct xsk_buff_pool *pool, + const struct xsk_tx_metadata *meta, u64 *flags) { return false; } +static inline void +xsk_tx_metadata_request(const struct xsk_buff_pool *pool, + struct xsk_tx_metadata **pmeta, + const struct xsk_tx_metadata_ops *ops, void *priv) +{ +} + static inline struct xsk_tx_metadata * __xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data) { diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h index 1ed234e7f251..2c37c6ac7525 100644 --- a/include/uapi/linux/ip_vs.h +++ b/include/uapi/linux/ip_vs.h @@ -29,12 +29,6 @@ #define IP_VS_SVC_F_SCHED_SH_PORT IP_VS_SVC_F_SCHED2 /* SH use port */ /* - * Destination Server Flags - */ -#define IP_VS_DEST_F_AVAILABLE 0x0001 /* server is available */ -#define IP_VS_DEST_F_OVERLOAD 0x0002 /* server is overloaded */ - -/* * IPVS sync daemon states */ #define IP_VS_STATE_NONE 0x0000 /* daemon is stopped */ diff --git a/kernel/bpf/rqspinlock.c b/kernel/bpf/rqspinlock.c index e4e338cdb437..2129defc4a9a 100644 --- a/kernel/bpf/rqspinlock.c +++ b/kernel/bpf/rqspinlock.c @@ -572,9 +572,10 @@ queue: /* Disable queue destruction when we detect deadlocks. */ if (ret == -EDEADLK) { - if (!next) + if (!try_cmpxchg_tail(lock, tail, 0)) { next = smp_cond_load_relaxed(&node->next, (VAL)); - arch_mcs_spin_unlock_contended(&next->locked); + arch_mcs_spin_unlock_contended(&next->locked); + } goto err_release_node; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 523f00e609e2..5bad71f003dc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -13801,13 +13801,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return -EACCES; } - /* - * Accesses to untrusted PTR_TO_MEM are done through probe - * instructions, hence no need to track offsets. - */ - if (base_type(ptr_reg->type) == PTR_TO_MEM && (ptr_reg->type & PTR_UNTRUSTED)) - return 0; - switch (base_type(ptr_reg->type)) { case PTR_TO_CTX: case PTR_TO_MAP_VALUE: @@ -13837,11 +13830,19 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return -EACCES; } - /* In case of 'scalar += pointer', dst_reg inherits pointer type and id. - * The id may be overwritten later if we create a new variable offset. + /* For 'scalar += pointer', dst_reg inherits the complete pointer + * register state. Individual fields may be adjusted later by pointer + * arithmetic. Callers guarantee that below does not overwrite off_reg. */ - dst_reg->type = ptr_reg->type; - dst_reg->id = ptr_reg->id; + if (dst_reg != ptr_reg) + *dst_reg = *ptr_reg; + + /* + * Accesses to untrusted PTR_TO_MEM are done through probe + * instructions, hence no need to track offsets. + */ + if (base_type(ptr_reg->type) == PTR_TO_MEM && (ptr_reg->type & PTR_UNTRUSTED)) + return 0; if (!check_reg_sane_offset_scalar(env, off_reg, ptr_reg->type) || !check_reg_sane_offset_ptr(env, ptr_reg, ptr_reg->type)) @@ -13893,7 +13894,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } break; case BPF_SUB: - if (dst_reg == off_reg) { + if (dst_reg != ptr_reg) { /* scalar -= pointer. Creates an unknown scalar */ verbose(env, "R%d tried to subtract pointer from scalar\n", dst); @@ -15137,8 +15138,8 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, err = mark_chain_precision(env, insn->dst_reg); if (err) return err; - return adjust_ptr_min_max_vals(env, insn, - src_reg, dst_reg); + off_reg = *dst_reg; + return adjust_ptr_min_max_vals(env, insn, src_reg, &off_reg); } } else if (ptr_reg) { /* pointer += scalar */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 6152add0c5eb..25e2367b3e0b 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3961,6 +3961,7 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, struct psi_trigger *new; struct cgroup *cgrp; struct psi_group *psi; + bool need_rtpoll_worker; ssize_t ret = 0; cgrp = cgroup_kn_lock_live(of->kn, false); @@ -3980,12 +3981,32 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, } psi = cgroup_psi(cgrp); - new = psi_trigger_create(psi, buf, res, of->file, of); + new = psi_trigger_create(psi, buf, res, of->file, of, + &need_rtpoll_worker); if (IS_ERR(new)) { ret = PTR_ERR(new); goto out_unlock; } + /* + * The worker fork must run with neither cgroup_mutex nor the file's + * kernfs active reference held. The latter is broken since + * cgroup_kn_lock_live(). @of->priv may be released while unlocked, so + * recheck before publishing @new. + */ + if (need_rtpoll_worker) { + cgroup_unlock(); + ret = psi_trigger_create_rtpoll_worker(psi); + cgroup_lock(); + + if (!ret && !of->priv) + ret = -ENODEV; + if (ret) { + psi_trigger_destroy(new); + goto out_unlock; + } + } + smp_store_release(&ctx->psi.trigger, new); out_unlock: diff --git a/kernel/events/core.c b/kernel/events/core.c index 240684f4b18c..3b4c43203210 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2342,6 +2342,34 @@ static inline struct list_head *get_event_list(struct perf_event *event) &event->pmu_ctx->flexible_active; } +/* @sibling must already be unlinked from its old leader's sibling_list. */ +static void perf_promote_sibling_to_leader(struct perf_event *sibling, + struct perf_event_context *ctx, + int group_caps) +{ + /* + * Events that have PERF_EV_CAP_SIBLING require being part of + * a group and cannot exist on their own, schedule them out + * and move them into the ERROR state. Also see + * _perf_event_enable(), it will not be able to recover this + * ERROR state. + */ + if (sibling->event_caps & PERF_EV_CAP_SIBLING) + __event_disable(sibling, ctx, PERF_EVENT_STATE_ERROR); + + sibling->group_leader = sibling; + sibling->group_caps = group_caps; + + if (sibling->attach_state & PERF_ATTACH_CONTEXT) { + add_event_to_groups(sibling, ctx); + + if (sibling->state == PERF_EVENT_STATE_ACTIVE) + list_add_tail(&sibling->active_list, get_event_list(sibling)); + } + + perf_event__header_size(sibling); +} + static void perf_group_detach(struct perf_event *event) { struct perf_event *leader = event->group_leader; @@ -2365,8 +2393,9 @@ static void perf_group_detach(struct perf_event *event) */ if (leader != event) { list_del_init(&event->sibling_list); - event->group_leader->nr_siblings--; - event->group_leader->group_generation++; + leader->nr_siblings--; + leader->group_generation++; + perf_promote_sibling_to_leader(event, ctx, event->event_caps); goto out; } @@ -2376,32 +2405,14 @@ static void perf_group_detach(struct perf_event *event) * to whatever list we are on. */ list_for_each_entry_safe(sibling, tmp, &event->sibling_list, sibling_list) { - - /* - * Events that have PERF_EV_CAP_SIBLING require being part of - * a group and cannot exist on their own, schedule them out - * and move them into the ERROR state. Also see - * _perf_event_enable(), it will not be able to recover this - * ERROR state. - */ - if (sibling->event_caps & PERF_EV_CAP_SIBLING) - __event_disable(sibling, ctx, PERF_EVENT_STATE_ERROR); - - sibling->group_leader = sibling; list_del_init(&sibling->sibling_list); /* Inherit group flags from the previous leader */ - sibling->group_caps = event->group_caps; - - if (sibling->attach_state & PERF_ATTACH_CONTEXT) { - add_event_to_groups(sibling, event->ctx); - - if (sibling->state == PERF_EVENT_STATE_ACTIVE) - list_add_tail(&sibling->active_list, get_event_list(sibling)); - } + perf_promote_sibling_to_leader(sibling, ctx, event->group_caps); WARN_ON_ONCE(sibling->ctx != event->ctx); } + event->nr_siblings = 0; out: for_each_sibling_event(tmp, leader) @@ -2591,12 +2602,7 @@ __perf_remove_from_context(struct perf_event *event, if (flags & DETACH_DEAD) state = PERF_EVENT_STATE_DEAD; - event_sched_out(event, ctx); - - if (event->state > PERF_EVENT_STATE_OFF) - perf_cgroup_event_disable(event, ctx); - - perf_event_set_state(event, min(event->state, state)); + __event_disable(event, ctx, state); if (flags & DETACH_GROUP) perf_group_detach(event); @@ -2665,8 +2671,9 @@ static void __event_disable(struct perf_event *event, enum perf_event_state state) { event_sched_out(event, ctx); - perf_cgroup_event_disable(event, ctx); - perf_event_set_state(event, state); + if (event->state > PERF_EVENT_STATE_OFF) + perf_cgroup_event_disable(event, ctx); + perf_event_set_state(event, min(event->state, state)); } /* diff --git a/kernel/futex/core.c b/kernel/futex/core.c index ff2a4fb2993f..6b3121c734bb 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -1027,8 +1027,11 @@ retry: return -1; /* - * Special case for regular (non PI) futexes. The unlock path in - * user space has two race scenarios: + * Special case for regular (non PI) futexes. Ordinarily, we do + * not perform any processing here unless the current thread was + * the owner of the futex (by the TID check below). + * + * However, the unlock path has three race scenarios: * * 1. The unlock path releases the user space futex value and * before it can execute the futex() syscall to wake up @@ -1037,42 +1040,70 @@ retry: * 2. A woken up waiter is killed before it can acquire the * futex in user space. * - * In the second case, the wake up notification could be generated - * by the unlock path in user space after setting the futex value - * to zero or by the kernel after setting the OWNER_DIED bit below. + * 3. A woken up waiter is killed in user space after another + * thread has acquired the futex, but before it can set + * FUTEX_WAITERS. + * + * Note that, if userspace uses the FUTEX_ROBUST_UNLOCK flag, we + * will not see case 1 here. + * + * In the second and third case, the wake up notification could + * be generated from any of: + * + * i. An ordinary futex wakeup after unlock (with or + * without FUTEX_ROBUST_UNLOCK) + * ii. A robust wakeup from another thread's death + * iii. A previous round through this special case + * + * As a result, the futex world will be in one of four states: + * + * A. The futex word is 0 (unlocked) + * B. The futex word is owned by another thread + * (FUTEX_WAITERS is not set) + * C. The futex word is owned by another thread + * (FUTEX_WAITERS set) + * D. The futex's owner died and OWNER_DIED is set + * (the owner part of the word is 0) * - * In both cases the TID validation below prevents a wakeup of - * potential waiters which can cause these waiters to block - * forever. + * The key issue is that the kernel usually (at least from + * sources ii. and iii. or when so requested by userspace from + * source i.) only ever wakes *one* waiter at a time. If this + * waiter dies before acquiring the futex (or setting the + * FUTEX_WAITERS bit), the kernel *must* still wake the next + * waiter down the line to uphold the futex invariants and + * avoid lost wakeups. Note we do not need to handle state C, + * as it does not matter to us whether *we* successfully set + * the bit or a third thread did so in the meantime. * - * In both cases the following conditions are met: + * Therefore, in these cases we must issue an additional + * futex_wake(). Note however that we *must not* set OWNER_DIED + * here. Our thread is *not* the owner of the futex. * - * 1) task->robust_list->list_op_pending != NULL - * @pending_op == true - * 2) The owner part of user space futex value == 0 + * Thus to summarize, the conditions for needing the additional + * futex_wake() are: + * + * 1) @pending_op == true (the thread has not finished the + * mutex operation) + * 2) The futex word is in one of the states A, B or D * 3) Regular futex: @pi == false * - * If these conditions are met, it is safe to attempt waking up a - * potential waiter without touching the user space futex value and - * trying to set the OWNER_DIED bit. If the futex value is zero, - * the rest of the user space mutex state is consistent, so a woken - * waiter will just take over the uncontended futex. Setting the - * OWNER_DIED bit would create inconsistent state and malfunction - * of the user space owner died handling. Otherwise, the OWNER_DIED - * bit is already set, and the woken waiter is expected to deal with - * this. + * Note in particular that in all of the states A-D the owner + * portion of the futex word differs from our thread's TID + * (unless the actual owner has the same TID in another PID + * namespace, but we cannot currently distinguish that + * scenario), so this can be a special-case wakeup in the bail + * path of the ordinary TID check. */ owner = uval & FUTEX_TID_MASK; - if (pending_op && !pi && !owner) { - futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, - FUTEX_BITSET_MATCH_ANY); + if (owner != task_pid_vnr(curr)) { + if (pending_op && !pi && (!owner || !(uval & FUTEX_WAITERS))) { + futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, + FUTEX_BITSET_MATCH_ANY); + } return 0; } - if (owner != task_pid_vnr(curr)) - return 0; - /* * Ok, this dying thread is truly holding a futex * of interest. Set the OWNER_DIED bit atomically diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 5c780756e362..d46662365a69 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -3581,6 +3581,9 @@ static int __scx_init_task(struct scx_sched *sch, struct task_struct *p, bool fo } else if (unlikely(fork)) { scx_error(sch, "ops.init_task() set task->scx.disallow for %s[%d] during fork", p->comm, p->pid); + } else if (unlikely(scx_enable_state() != SCX_ENABLING)) { + scx_error(sch, "ops.init_task() set task->scx.disallow for %s[%d] outside the enable path", + p->comm, p->pid); } else { struct rq *rq; struct rq_flags rf; @@ -4512,20 +4515,25 @@ static struct cgroup *root_cgroup(void) return &cgrp_dfl_root.cgrp; } +/* + * cgroup_lock() must nest outside the rwsem write side: a writer waiting + * for cgroup_mutex deadlocks with cgroup teardown, which holds it while + * draining a set_* file write blocked on the rwsem behind the writer. + */ static void scx_cgroup_lock(void) { + cgroup_lock(); #ifdef CONFIG_EXT_GROUP_SCHED percpu_down_write(&scx_cgroup_ops_rwsem); #endif - cgroup_lock(); } static void scx_cgroup_unlock(void) { - cgroup_unlock(); #ifdef CONFIG_EXT_GROUP_SCHED percpu_up_write(&scx_cgroup_ops_rwsem); #endif + cgroup_unlock(); } #else /* CONFIG_EXT_GROUP_SCHED || CONFIG_EXT_SUB_SCHED */ static struct cgroup *root_cgroup(void) { return NULL; } @@ -5795,6 +5803,15 @@ static void scx_sub_disable(struct scx_sched *sch) percpu_down_write(&scx_fork_rwsem); scx_cgroup_lock(); + /* + * An enable that failed before scx_link_sched() never owned a cgroup or + * task and won't be waited on by an ancestor's drain_descendants(). + * Nothing to reparent and walking the tasks can misbehave as the task + * ownership invariant (either owned by self or parent) does not hold. + */ + if (list_empty(&sch->sibling)) + goto dump; + set_cgroup_sched(sch_cgroup(sch), parent); scx_task_iter_start(&sti, sch->cgrp); @@ -5807,8 +5824,8 @@ static void scx_sub_disable(struct scx_sched *sch) continue; /* - * By the time control reaches here, all descendant schedulers - * should already have been disabled. + * By the time control reaches here, all linked descendant + * schedulers should have been disabled. */ WARN_ON_ONCE(!scx_task_on_sched(sch, p)); @@ -5862,15 +5879,22 @@ static void scx_sub_disable(struct scx_sched *sch) /* * $p is initialized for $parent and still attached to * @sch. Disable and exit for @sch, switch over to - * $parent, override the state to READY to account for - * $p having already been initialized, and then enable. + * $parent and override the state to READY to account + * for $p having already been initialized. */ scx_disable_and_exit_task(sch, p); scx_set_task_state(p, SCX_TASK_INIT_BEGIN); scx_set_task_state(p, SCX_TASK_INIT); scx_set_task_sched(p, parent); scx_set_task_state(p, SCX_TASK_READY); - scx_enable_task(parent, p); + + /* + * A task on a non-ext class, possible under an + * %SCX_OPS_SWITCH_PARTIAL root, stays READY and is + * enabled by switching_to_scx() if it switches over. + */ + if (p->sched_class == &ext_sched_class) + scx_enable_task(parent, p); } task_rq_unlock(rq, p, &rf); @@ -5878,6 +5902,7 @@ static void scx_sub_disable(struct scx_sched *sch) } scx_task_iter_stop(&sti); +dump: scx_disable_dump(sch); scx_cgroup_unlock(); @@ -7364,10 +7389,14 @@ static void scx_sub_enable_workfn(struct kthread_work *work) /* * $p is now only initialized for @sch and READY, which - * is what we want. Assign it to @sch and enable. + * is what we want. Assign it to @sch and, if it's on + * the ext class, enable. A non-ext task, possible under + * an %SCX_OPS_SWITCH_PARTIAL root, stays READY and is + * enabled by switching_to_scx() if it switches over. */ scx_set_task_sched(p, sch); - scx_enable_task(sch, p); + if (p->sched_class == &ext_sched_class) + scx_enable_task(sch, p); p->scx.flags &= ~SCX_TASK_SUB_INIT; } diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index d9c9d9480a45..e2e825dcd088 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1134,6 +1134,12 @@ void psi_cgroup_free(struct cgroup *cgroup) return; cancel_delayed_work_sync(&cgroup->psi->avgs_work); + /* + * A psi_schedule_rtpoll_work() call racing the last trigger's + * destruction may have re-armed the timer after psi_trigger_destroy() + * deleted it. Spurious firing while the group is alive is harmless. + */ + timer_shutdown_sync(&cgroup->psi->rtpoll_timer); free_percpu(cgroup->psi->pcpu); /* All triggers must be removed by now */ WARN_ONCE(cgroup->psi->rtpoll_states, "psi: trigger leak\n"); @@ -1292,9 +1298,44 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) return 0; } +/* + * Create @group's rtpoll worker after psi_trigger_create() reported the need + * for one. kthread creation depends on the whole fork path and we don't want + * all of that nested inside cgroup_mutex, so the caller must drop it and any + * other lock that forks can wait behind. If two callers race, the loser stops + * its never-woken kthread. + */ +int psi_trigger_create_rtpoll_worker(struct psi_group *group) +{ + struct task_struct *task; + + task = kthread_create(psi_rtpoll_worker, group, "psimon"); + if (IS_ERR(task)) + return PTR_ERR(task); + + scoped_guard(mutex, &group->rtpoll_trigger_lock) { + if (!rcu_access_pointer(group->rtpoll_task)) { + atomic_set(&group->rtpoll_wakeup, 0); + wake_up_process(task); + rcu_assign_pointer(group->rtpoll_task, task); + + /* + * Poll once to catch up on scheduling attempts dropped + * while there was no rtpoll worker. + */ + psi_schedule_rtpoll_work(group, 1, true); + return 0; + } + } + + kthread_stop(task); + return 0; +} + struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, enum psi_res res, struct file *file, - struct kernfs_open_file *of) + struct kernfs_open_file *of, + bool *need_rtpoll_worker) { struct psi_trigger *t; enum psi_states state; @@ -1302,6 +1343,8 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, bool privileged; u32 window_us; + *need_rtpoll_worker = false; + if (static_branch_likely(&psi_disabled)) return ERR_PTR(-EOPNOTSUPP); @@ -1362,26 +1405,14 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, if (privileged) { mutex_lock(&group->rtpoll_trigger_lock); - if (!rcu_access_pointer(group->rtpoll_task)) { - struct task_struct *task; - - task = kthread_create(psi_rtpoll_worker, group, "psimon"); - if (IS_ERR(task)) { - kfree(t); - mutex_unlock(&group->rtpoll_trigger_lock); - return ERR_CAST(task); - } - atomic_set(&group->rtpoll_wakeup, 0); - wake_up_process(task); - rcu_assign_pointer(group->rtpoll_task, task); - } - list_add(&t->node, &group->rtpoll_triggers); group->rtpoll_min_period = min(group->rtpoll_min_period, div_u64(t->win.size, UPDATES_PER_WINDOW)); group->rtpoll_nr_triggers[t->state]++; group->rtpoll_states |= (1 << t->state); + *need_rtpoll_worker = !rcu_access_pointer(group->rtpoll_task); + mutex_unlock(&group->rtpoll_trigger_lock); } else { mutex_lock(&group->avgs_lock); @@ -1541,6 +1572,8 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, size_t buf_size; struct seq_file *seq; struct psi_trigger *new; + bool need_rtpoll_worker; + int ret; if (static_branch_likely(&psi_disabled)) return -EOPNOTSUPP; @@ -1565,12 +1598,22 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, return -EBUSY; } - new = psi_trigger_create(&psi_system, buf, res, file, NULL); + new = psi_trigger_create(&psi_system, buf, res, file, NULL, + &need_rtpoll_worker); if (IS_ERR(new)) { mutex_unlock(&seq->lock); return PTR_ERR(new); } + if (need_rtpoll_worker) { + ret = psi_trigger_create_rtpoll_worker(&psi_system); + if (ret) { + psi_trigger_destroy(new); + mutex_unlock(&seq->lock); + return ret; + } + } + smp_store_release(&seq->private, new); mutex_unlock(&seq->lock); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index d2e2cf18bfdb..ae48017c45dd 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2400,6 +2400,7 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) bpage = alloc_cpu_page(cpu); if (!bpage) return NULL; + bpage->order = cpu_buffer->buffer->subbuf_order; rb_check_bpage(cpu_buffer, bpage); @@ -2418,6 +2419,8 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) if (cpu_buffer->ring_meta->head_buffer) rb_meta_buffer_update(cpu_buffer, bpage); bpage->range = 1; + + atomic_inc(&cpu_buffer->resize_disabled); } else if (buffer->remote) { struct ring_buffer_desc *desc = ring_buffer_desc(buffer->remote->desc, cpu); @@ -6680,7 +6683,7 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a, { struct ring_buffer_per_cpu *cpu_buffer_a; struct ring_buffer_per_cpu *cpu_buffer_b; - int ret = -EINVAL; + int ret = -EBUSY; if (!cpumask_test_cpu(cpu, buffer_a->cpumask) || !cpumask_test_cpu(cpu, buffer_b->cpumask)) @@ -6721,10 +6724,10 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a, atomic_inc(&cpu_buffer_a->record_disabled); atomic_inc(&cpu_buffer_b->record_disabled); - ret = -EBUSY; - if (local_read(&cpu_buffer_a->committing)) + /* Do not swap if either buffer is in the process of writing */ + if (cpu_buffer_a->current_context) goto out_dec; - if (local_read(&cpu_buffer_b->committing)) + if (cpu_buffer_b->current_context) goto out_dec; /* @@ -7168,7 +7171,7 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) cpu_buffer = buffer->buffers[cpu]; - if (cpu_buffer->mapped) { + if (atomic_read(&cpu_buffer->resize_disabled)) { err = -EBUSY; goto error; } @@ -8024,7 +8027,7 @@ static __init int test_ringbuffer(void) out_free: for_each_online_cpu(cpu) { - if (!rb_threads[cpu]) + if (IS_ERR_OR_NULL(rb_threads[cpu])) break; kthread_stop(rb_threads[cpu]); } diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index c01b10b99f67..3650d84d4f16 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -945,7 +945,7 @@ static int remove_cache_mod(struct trace_array *tr, const char *mod, if (strcmp(event_mod->module, mod) != 0) continue; - if (match && strcmp(event_mod->match, match) != 0) + if (match && (!event_mod->match || strcmp(event_mod->match, match) != 0)) continue; if (system && @@ -3566,6 +3566,7 @@ void trace_event_update_all(struct trace_eval_map **map, int len) int last_i; int i; + mutex_lock(&event_mutex); down_write(&trace_event_sem); list_for_each_entry_safe(call, p, &ftrace_events, list) { /* events are usually grouped together with systems */ @@ -3604,6 +3605,7 @@ void trace_event_update_all(struct trace_eval_map **map, int len) cond_resched(); } up_write(&trace_event_sem); + mutex_unlock(&event_mutex); } static bool event_in_systems(struct trace_event_call *call, diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c index 8cfe7bd3dc1d..c61c3d3a5ffd 100644 --- a/mm/damon/lru_sort.c +++ b/mm/damon/lru_sort.c @@ -234,6 +234,8 @@ static int damon_lru_sort_add_quota_goals(struct damos *hot_scheme, if (!active_mem_bp) return 0; + if (10000 < active_mem_bp) + return -EINVAL; goal = damos_new_quota_goal(DAMOS_QUOTA_ACTIVE_MEM_BP, active_mem_bp); if (!goal) return -ENOMEM; diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c index 4752d6118eb9..cca7014ab5f1 100644 --- a/mm/damon/ops-common.c +++ b/mm/damon/ops-common.c @@ -374,6 +374,8 @@ keep: while (!list_empty(folio_list)) { folio = lru_to_folio(folio_list); list_del(&folio->lru); + node_stat_sub_folio(folio, NR_ISOLATED_ANON + + folio_is_file_lru(folio)); folio_putback_lru(folio); } @@ -391,8 +393,17 @@ unsigned long damon_migrate_pages(struct list_head *folio_list, int target_nid) return nr_migrated; if (target_nid < 0 || target_nid >= MAX_NUMNODES || - !node_state(target_nid, N_MEMORY)) + !node_state(target_nid, N_MEMORY)) { + while (!list_empty(folio_list)) { + struct folio *folio = lru_to_folio(folio_list); + + list_del(&folio->lru); + node_stat_sub_folio(folio, NR_ISOLATED_ANON + + folio_is_file_lru(folio)); + folio_putback_lru(folio); + } return nr_migrated; + } noreclaim_flag = memalloc_noreclaim_save(); diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index 5cdcc5037cbc..e701ffa8506b 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -277,6 +277,8 @@ static unsigned long damon_pa_migrate(struct damon_region *r, if (!folio_isolate_lru(folio)) goto put_folio; + node_stat_add_folio(folio, NR_ISOLATED_ANON + + folio_is_file_lru(folio)); list_add(&folio->lru, &folio_list); put_folio: addr += folio_size(folio); diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index b069dbc7e3d2..9845ceeedc0b 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -627,7 +627,8 @@ static void damos_va_migrate_dests_add(struct folio *folio, isolate: if (!folio_isolate_lru(folio)) return; - + node_stat_add_folio(folio, NR_ISOLATED_ANON + + folio_is_file_lru(folio)); list_add(&folio->lru, &migration_lists[i]); } diff --git a/mm/filemap.c b/mm/filemap.c index b72f8c23c322..bbd400d893aa 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -932,6 +932,12 @@ unlock: if (!xas_nomem(&xas, gfp)) break; + + /* + * Lock has been dropped: start again with the original index + * and order (but now with the memory reserved by xas_nomem()). + */ + xas_set_order(&xas, index, forder); } if (xas_error(&xas)) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 7a44c428d187..6916def3ce57 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -40,6 +40,7 @@ #include <linux/pgalloc.h> #include <linux/pgalloc_tag.h> #include <linux/pagewalk.h> +#include <linux/cleanup.h> #include <asm/tlb.h> #include "internal.h" @@ -75,6 +76,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, static bool split_underused_thp = true; static atomic_t huge_zero_refcount; +static DEFINE_SPINLOCK(huge_zero_lock); struct folio *huge_zero_folio __read_mostly; unsigned long huge_zero_pfn __read_mostly = ~0UL; unsigned long huge_anon_orders_always __read_mostly; @@ -221,7 +223,8 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, static bool get_huge_zero_folio(void) { struct folio *zero_folio; -retry: + + /* Paired with atomic_set_release(). */ if (likely(atomic_inc_not_zero(&huge_zero_refcount))) return true; @@ -234,17 +237,22 @@ retry: } /* Ensure zero folio won't have large_rmappable flag set. */ folio_clear_large_rmappable(zero_folio); - preempt_disable(); - if (cmpxchg(&huge_zero_folio, NULL, zero_folio)) { - preempt_enable(); + + /* Paired with critical section in shrink_huge_zero_folio_scan(). */ + spin_lock(&huge_zero_lock); + if (huge_zero_folio) { + /* Somebody else already installed it. */ + atomic_inc(&huge_zero_refcount); + spin_unlock(&huge_zero_lock); folio_put(zero_folio); - goto retry; + return true; } + WRITE_ONCE(huge_zero_folio, zero_folio); WRITE_ONCE(huge_zero_pfn, folio_pfn(zero_folio)); + /* Paired with atomic_inc_not_zero(). +1 for shrinker pin. */ + atomic_set_release(&huge_zero_refcount, 2); + spin_unlock(&huge_zero_lock); - /* We take additional reference here. It will be put back by shrinker */ - atomic_set(&huge_zero_refcount, 2); - preempt_enable(); count_vm_event(THP_ZERO_PAGE_ALLOC); return true; } @@ -294,15 +302,22 @@ static unsigned long shrink_huge_zero_folio_count(struct shrinker *shrink, static unsigned long shrink_huge_zero_folio_scan(struct shrinker *shrink, struct shrink_control *sc) { - if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { - struct folio *zero_folio = xchg(&huge_zero_folio, NULL); - BUG_ON(zero_folio == NULL); + struct folio *zero_folio; + + /* Paired with critical section in get_huge_zero_folio(). */ + scoped_guard(spinlock, &huge_zero_lock) { + /* Paired with atomic_inc_not_zero() in get_huge_zero_folio(). */ + if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) != 1) + return 0; + + zero_folio = huge_zero_folio; + VM_WARN_ON_ONCE(!zero_folio); + WRITE_ONCE(huge_zero_folio, NULL); WRITE_ONCE(huge_zero_pfn, ~0UL); - folio_put(zero_folio); - return HPAGE_PMD_NR; } - return 0; + folio_put(zero_folio); + return HPAGE_PMD_NR; } static struct shrinker *huge_zero_folio_shrinker; @@ -4108,7 +4123,7 @@ static int __folio_split(struct folio *folio, unsigned int new_order, gfp_t gfp; mapping = folio->mapping; - min_order = mapping_min_folio_order(folio->mapping); + min_order = mapping_min_folio_order(mapping); if (new_order < min_order) { ret = -EINVAL; goto out; @@ -4122,6 +4137,8 @@ static int __folio_split(struct folio *folio, unsigned int new_order, goto out; } + mapping_set_update(&xas, mapping); + if (split_type == SPLIT_TYPE_UNIFORM) { xas_set_order(&xas, folio->index, new_order); xas_split_alloc(&xas, folio, old_order, gfp); diff --git a/mm/memory.c b/mm/memory.c index 86a973119bd4..13b70861c8a3 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1981,7 +1981,7 @@ retry: if (can_reclaim_pt) { if (direct_reclaim || zap_pte_table_if_empty(mm, pmd, start, &pmdval)) { - pte_free_tlb(tlb, pmd_pgtable(pmdval), addr); + pte_free_tlb(tlb, pmd_pgtable(pmdval), start); mm_dec_nr_ptes(mm); } } diff --git a/mm/page_table_check.c b/mm/page_table_check.c index 53a8997ec043..2403f5a11410 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -151,18 +151,29 @@ void __page_table_check_pte_clear(struct mm_struct *mm, unsigned long addr, if (&init_mm == mm) return; - if (pte_user_accessible_page(mm, addr, pte)) + if (pte_user_accessible_page(mm, addr, pte) && !pte_special(pte)) page_table_check_clear(pte_pfn(pte), PAGE_SIZE >> PAGE_SHIFT); } EXPORT_SYMBOL(__page_table_check_pte_clear); +static inline bool page_table_check_huge_zero_pmd(pmd_t pmd) +{ + unsigned long pfn = pmd_pfn(pmd); + + if (!pfn_valid(pfn)) + return false; + + return is_huge_zero_folio(page_folio(pfn_to_page(pfn))); +} + void __page_table_check_pmd_clear(struct mm_struct *mm, unsigned long addr, pmd_t pmd) { if (&init_mm == mm) return; - if (pmd_user_accessible_page(mm, addr, pmd)) + if (pmd_user_accessible_page(mm, addr, pmd) && + !page_table_check_huge_zero_pmd(pmd)) page_table_check_clear(pmd_pfn(pmd), PMD_SIZE >> PAGE_SHIFT); } EXPORT_SYMBOL(__page_table_check_pmd_clear); @@ -208,7 +219,7 @@ void __page_table_check_ptes_set(struct mm_struct *mm, unsigned long addr, for (i = 0; i < nr; i++) __page_table_check_pte_clear(mm, addr + PAGE_SIZE * i, ptep_get(ptep + i)); - if (pte_user_accessible_page(mm, addr, pte)) + if (pte_user_accessible_page(mm, addr, pte) && !pte_special(pte)) page_table_check_set(pte_pfn(pte), nr, pte_write(pte)); } EXPORT_SYMBOL(__page_table_check_ptes_set); @@ -238,7 +249,8 @@ void __page_table_check_pmds_set(struct mm_struct *mm, unsigned long addr, for (i = 0; i < nr; i++) __page_table_check_pmd_clear(mm, addr + PMD_SIZE * i, *(pmdp + i)); - if (pmd_user_accessible_page(mm, addr, pmd)) + if (pmd_user_accessible_page(mm, addr, pmd) && + !page_table_check_huge_zero_pmd(pmd)) page_table_check_set(pmd_pfn(pmd), stride * nr, pmd_write(pmd)); } EXPORT_SYMBOL(__page_table_check_pmds_set); diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 3ae2586ff45b..5d87c632a255 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -678,6 +678,8 @@ int walk_kernel_page_table_range_lockless(unsigned long start, unsigned long end * will also not lock the PTEs for the pte_entry() callback. * * This is for debugging purposes ONLY. + * + * The mmap write lock must be held. */ int walk_page_range_debug(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, @@ -691,24 +693,28 @@ int walk_page_range_debug(struct mm_struct *mm, unsigned long start, .no_vma = true }; - /* For convenience, we allow traversal of kernel mappings. */ - if (mm == &init_mm) - return walk_kernel_page_table_range(start, end, ops, - pgd, private); - if (start >= end || !walk.mm) - return -EINVAL; - if (!check_ops_safe(ops)) - return -EINVAL; - /* - * The mmap lock protects the page walker from changes to the page - * tables during the walk. However a read lock is insufficient to - * protect those areas which don't have a VMA as munmap() detaches - * the VMAs before downgrading to a read lock and actually tearing - * down PTEs/page tables. In which case, the mmap write lock should - * be held. + * When walking userland page tables, an mmap write lock must be held to + * account for munmap() downgrading to an mmap read lock when tearing + * down page tables. + * + * When walking kernel page tables, an mmap write lock must also be held + * to account for page table freeing on vmap huge page mapping. */ mmap_assert_write_locked(mm); + /* + * x86, arm64 ptdump allow walks of efi mm's and x86 ptdump allows walks + * of arbitrary mm's. + * + * However, they both must also hold the init_mm lock to account for + * concurrent kernel page table freeing. + */ + mmap_assert_write_locked(&init_mm); + + if (start >= end) + return -EINVAL; + if (!check_ops_safe(ops)) + return -EINVAL; return walk_pgd_range(start, end, &walk); } diff --git a/mm/ptdump.c b/mm/ptdump.c index 973020000096..5851096e6f65 100644 --- a/mm/ptdump.c +++ b/mm/ptdump.c @@ -178,11 +178,18 @@ void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd) get_online_mems(); mmap_write_lock(mm); + /* To stabilise kernel page tables we must hold the init_mm lock too. */ + if (mm != &init_mm) + mmap_write_lock_nested(&init_mm, SINGLE_DEPTH_NESTING); + while (range->start != range->end) { walk_page_range_debug(mm, range->start, range->end, &ptdump_ops, pgd, st); range++; } + + if (mm != &init_mm) + mmap_write_unlock(&init_mm); mmap_write_unlock(mm); put_online_mems(); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index bb6ae08d18f5..a22358f8cc2f 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -43,6 +43,7 @@ #include <asm/tlbflush.h> #include <asm/shmparam.h> #include <linux/page_owner.h> +#include <linux/cleanup.h> #define CREATE_TRACE_POINTS #include <trace/events/vmalloc.h> @@ -158,10 +159,21 @@ static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end, if (!IS_ALIGNED(phys_addr, PMD_SIZE)) return 0; - if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr)) - return 0; + if (!pmd_present(*pmd)) + return pmd_set_huge(pmd, phys_addr, prot); - return pmd_set_huge(pmd, phys_addr, prot); + /* + * Acquire the mmap read lock to exclude ptdump, which walks + * kernel page tables it does not own under the mmap write lock. + * + * Concurrent read lock holders are safe: each exclusively owns + * the range it operates on and cannot reach this page table. + */ + scoped_cond_guard(mmap_read_lock_try, return 0, &init_mm) { + if (!pmd_free_pte_page(pmd, addr)) + return 0; + return pmd_set_huge(pmd, phys_addr, prot); + } } static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, @@ -210,10 +222,15 @@ static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end, if (!IS_ALIGNED(phys_addr, PUD_SIZE)) return 0; - if (pud_present(*pud) && !pud_free_pmd_page(pud, addr)) - return 0; + if (!pud_present(*pud)) + return pud_set_huge(pud, phys_addr, prot); - return pud_set_huge(pud, phys_addr, prot); + /* See comment in vmap_try_huge_pmd(). */ + scoped_cond_guard(mmap_read_lock_try, return 0, &init_mm) { + if (!pud_free_pmd_page(pud, addr)) + return 0; + return pud_set_huge(pud, phys_addr, prot); + } } static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, @@ -262,10 +279,15 @@ static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end, if (!IS_ALIGNED(phys_addr, P4D_SIZE)) return 0; - if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr)) - return 0; + if (!p4d_present(*p4d)) + return p4d_set_huge(p4d, phys_addr, prot); - return p4d_set_huge(p4d, phys_addr, prot); + /* See comment in vmap_try_huge_pmd(). */ + scoped_cond_guard(mmap_read_lock_try, return 0, &init_mm) { + if (!p4d_free_pud_page(p4d, addr)) + return 0; + return p4d_set_huge(p4d, phys_addr, prot); + } } static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, diff --git a/net/atm/common.c b/net/atm/common.c index 6eb78c34c284..c3fbbb63c5d8 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -760,7 +760,7 @@ int vcc_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct atm_vcc *vcc; - unsigned long value; + int value; int error; if (__SO_LEVEL_MATCH(optname, level) && optlen != __SO_SIZE(optname)) @@ -772,8 +772,10 @@ int vcc_setsockopt(struct socket *sock, int level, int optname, { struct atm_qos qos; - if (copy_from_sockptr(&qos, optval, sizeof(qos))) - return -EFAULT; + error = copy_safe_from_sockptr(&qos, sizeof(qos), optval, + optlen); + if (error) + return error; error = check_qos(&qos); if (error) return error; @@ -786,8 +788,10 @@ int vcc_setsockopt(struct socket *sock, int level, int optname, return 0; } case SO_SETCLP: - if (copy_from_sockptr(&value, optval, sizeof(value))) - return -EFAULT; + error = copy_safe_from_sockptr(&value, sizeof(value), optval, + optlen); + if (error) + return error; if (value) vcc->atm_options |= ATM_ATMOPT_CLP; else diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index 460be392af47..31160bc09ee7 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -224,11 +224,9 @@ static struct sk_buff *br_mrp_alloc_test_skb(struct br_mrp *mrp, sub_opt = skb_put(skb, sizeof(*sub_opt)); memset(sub_opt, 0x0, sizeof(*sub_opt)); - sub_tlv = skb_put(skb, sizeof(*sub_tlv)); - sub_tlv->type = BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR; - /* 32 bit alligment shall be ensured therefore add 2 bytes */ - skb_put(skb, MRP_OPT_PADDING); + sub_tlv = skb_put_zero(skb, sizeof(*sub_tlv) + MRP_OPT_PADDING); + sub_tlv->type = BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR; } br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_END, 0x0); diff --git a/net/bridge/netfilter/ebt_nflog.c b/net/bridge/netfilter/ebt_nflog.c index 61bf8f4465ab..426f8adc912c 100644 --- a/net/bridge/netfilter/ebt_nflog.c +++ b/net/bridge/netfilter/ebt_nflog.c @@ -41,11 +41,25 @@ ebt_nflog_tg(struct sk_buff *skb, const struct xt_action_param *par) static int ebt_nflog_tg_check(const struct xt_tgchk_param *par) { struct ebt_nflog_info *info = par->targinfo; + int ret; if (info->flags & ~EBT_NFLOG_MASK) return -EINVAL; info->prefix[EBT_NFLOG_PREFIX_SIZE - 1] = '\0'; - return 0; + + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + if (ret != 0 && !par->nft_compat) { + request_module("%s", "nfnetlink_log"); + + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + } + + return ret; +} + +static void ebt_nflog_tg_destroy(const struct xt_tgdtor_param *par) +{ + nf_logger_put(par->family, NF_LOG_TYPE_ULOG); } static struct xt_target ebt_nflog_tg_reg __read_mostly = { @@ -54,6 +68,7 @@ static struct xt_target ebt_nflog_tg_reg __read_mostly = { .family = NFPROTO_BRIDGE, .target = ebt_nflog_tg, .checkentry = ebt_nflog_tg_check, + .destroy = ebt_nflog_tg_destroy, .targetsize = sizeof(struct ebt_nflog_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 58a33d0380b0..7ecb8a26bfa3 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -280,6 +280,7 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb, ret = nf_ct_br_defrag6(skb, &bridge_state); break; default: + nf_reset_ct(skb); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); return NF_ACCEPT; } diff --git a/net/core/datagram.c b/net/core/datagram.c index c285c6465923..173b5d97bd40 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -712,6 +712,9 @@ zerocopy_fill_skb_from_devmem(struct sk_buff *skb, struct iov_iter *from, size_t virt_addr, size, off; struct net_iov *niov; + if (i && skb_frags_readable(skb)) + return -EFAULT; + /* Devmem filling works by taking an IOVEC from the user where the * iov_addrs are interpreted as an offset in bytes into the dma-buf to * send from. We do not support other iter types. diff --git a/net/core/dev.c b/net/core/dev.c index 31741169cb0b..58ec448e8357 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5515,12 +5515,16 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, } /* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers - * (e.g. bpf_xdp_adjust_tail), we need to update data_len here. + * (e.g. bpf_xdp_adjust_tail). Remove the old fragment contribution + * from skb->len before updating data_len, then add the new one back. */ - if (xdp_buff_has_frags(xdp)) + skb->len -= skb->data_len; + if (xdp_buff_has_frags(xdp)) { skb->data_len = skb_shinfo(skb)->xdp_frags_size; - else + skb->len += skb->data_len; + } else { skb->data_len = 0; + } /* check if XDP changed eth hdr such SKB needs update */ eth = (struct ethhdr *)xdp->data; diff --git a/net/core/filter.c b/net/core/filter.c index 66837e93d3f2..233adfdc1c34 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7645,7 +7645,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len return -EINVAL; /* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */ - if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) + if (sk->sk_state != TCP_LISTEN || sk->sk_protocol != IPPROTO_TCP) return -EINVAL; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) @@ -7718,7 +7718,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, if (unlikely(!sk || th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; - if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) + if (sk->sk_state != TCP_LISTEN || sk->sk_protocol != IPPROTO_TCP) return -EINVAL; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) diff --git a/net/core/sock.c b/net/core/sock.c index 5714436b0871..aaa3bb214eff 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -779,7 +779,6 @@ bool sk_mc_loop(const struct sock *sk) return inet6_test_bit(MC6_LOOP, sk); #endif } - WARN_ON_ONCE(1); return true; } EXPORT_SYMBOL(sk_mc_loop); diff --git a/net/core/xdp.c b/net/core/xdp.c index 9890a30584ba..0194e69da339 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -871,7 +871,7 @@ struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf) headroom = xdpf->headroom + sizeof(*xdpf); totalsize = headroom + xdpf->len; - if (unlikely(totalsize > PAGE_SIZE)) + if (unlikely(totalsize > SKB_WITH_OVERHEAD(PAGE_SIZE))) return NULL; page = dev_alloc_page(); if (!page) diff --git a/net/devlink/dev.c b/net/devlink/dev.c index 57b2b8f03543..fd5633fa88ec 100644 --- a/net/devlink/dev.c +++ b/net/devlink/dev.c @@ -578,6 +578,7 @@ int devlink_nl_reload_doit(struct sk_buff *skb, struct genl_info *info) action != DEVLINK_RELOAD_ACTION_DRIVER_REINIT) { NL_SET_ERR_MSG_MOD(info->extack, "Changing namespace is only supported for reinit action"); + put_net(dest_net); return -EOPNOTSUPP; } } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 3e8fadc28798..49ffb8db2350 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -491,6 +491,34 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev) return -1; } +static size_t fib_nexthop_nlmsg_size(const struct fib_nh_common *nhc, + bool skip_oif) +{ + size_t nhsize = 0; + + switch (nhc->nhc_gw_family) { + case AF_INET: + nhsize += nla_total_size(4); /* RTA_GATEWAY */ + break; + case AF_INET6: + nhsize += nla_total_size(sizeof(struct rtvia) + + sizeof(struct in6_addr)); + break; + } + + if (!skip_oif && nhc->nhc_dev) + nhsize += nla_total_size(4); /* RTA_OIF */ + + if (nhc->nhc_lwtstate) { + /* RTA_ENCAP */ + nhsize += lwtunnel_get_encap_size(nhc->nhc_lwtstate); + /* RTA_ENCAP_TYPE */ + nhsize += nla_total_size(2); + } + + return nhsize; +} + size_t fib_nlmsg_size(struct fib_info *fi) { size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg)) @@ -508,32 +536,35 @@ size_t fib_nlmsg_size(struct fib_info *fi) payload += nla_total_size(4); /* RTA_NH_ID */ if (nhs) { - size_t nh_encapsize = 0; - /* Also handles the special case nhs == 1 */ - - /* each nexthop is packed in an attribute */ - size_t nhsize = nla_total_size(sizeof(struct rtnexthop)); + size_t mpsize = 0; unsigned int i; - /* may contain flow and gateway attribute */ - nhsize += 2 * nla_total_size(4); - - /* grab encap info */ for (i = 0; i < fib_info_num_path(fi); i++) { struct fib_nh_common *nhc = fib_info_nhc(fi, i); + size_t nhsize; + + nhsize = fib_nexthop_nlmsg_size(nhc, nhs != 1); + + if (nhs != 1) + nhsize += NLA_ALIGN(sizeof(struct rtnexthop)); + +#ifdef CONFIG_IP_ROUTE_CLASSID + if (nhc->nhc_family == AF_INET) { + struct fib_nh *nh; - if (nhc->nhc_lwtstate) { - /* RTA_ENCAP_TYPE */ - nh_encapsize += lwtunnel_get_encap_size( - nhc->nhc_lwtstate); - /* RTA_ENCAP */ - nh_encapsize += nla_total_size(2); + nh = container_of(nhc, struct fib_nh, nh_common); + if (nh->nh_tclassid) + nhsize += nla_total_size(4); } +#endif + if (nhs == 1) + payload += nhsize; + else + mpsize += nhsize; } - /* all nexthops are packed in a nested attribute */ - payload += nla_total_size((nhs * nhsize) + nh_encapsize); - + if (nhs != 1) + payload += nla_total_size(mpsize); } return payload; @@ -1868,42 +1899,30 @@ static int call_fib_nh_notifiers(struct fib_nh *nh, return NOTIFY_DONE; } -/* Update the PMTU of exceptions when: - * - the new MTU of the first hop becomes smaller than the PMTU - * - the old MTU was the same as the PMTU, and it limited discovery of - * larger MTUs on the path. With that limit raised, we can now - * discover larger MTUs - * A special case is locked exceptions, for which the PMTU is smaller - * than the minimal accepted PMTU: - * - if the new MTU is greater than the PMTU, don't make any change - * - otherwise, unlock and set PMTU +/* Walk the exceptions of a nexthop after its first hop MTU changed. The + * chain is RCU protected here, while fnhe_update_pmtu() takes fnhe_lock + * for the update of each entry. */ void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig) { struct fnhe_hash_bucket *bucket; int i; - bucket = rcu_dereference_protected(nhc->nhc_exceptions, 1); + rcu_read_lock(); + bucket = rcu_dereference(nhc->nhc_exceptions); if (!bucket) - return; + goto out; for (i = 0; i < FNHE_HASH_SIZE; i++) { struct fib_nh_exception *fnhe; - for (fnhe = rcu_dereference_protected(bucket[i].chain, 1); + for (fnhe = rcu_dereference(bucket[i].chain); fnhe; - fnhe = rcu_dereference_protected(fnhe->fnhe_next, 1)) { - if (fnhe->fnhe_mtu_locked) { - if (new <= fnhe->fnhe_pmtu) { - fnhe->fnhe_pmtu = new; - fnhe->fnhe_mtu_locked = false; - } - } else if (new < fnhe->fnhe_pmtu || - orig == fnhe->fnhe_pmtu) { - fnhe->fnhe_pmtu = new; - } - } + fnhe = rcu_dereference(fnhe->fnhe_next)) + fnhe_update_pmtu(fnhe, new, orig); } +out: + rcu_read_unlock(); } void fib_sync_mtu(struct net_device *dev, u32 orig_mtu) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 690f7fb3f029..935b46db6154 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -946,11 +946,23 @@ static struct request_sock *inet_reqsk_clone(struct request_sock *req, nreq->rsk_listener = sk; - /* We need not acquire fastopenq->lock - * because the child socket is locked in inet_csk_listen_stop(). - */ - if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(nreq)->tfo_listener) + if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(nreq)->tfo_listener) { + struct fastopen_queue *fastopenq; + + /* reqsk_fastopen_remove() will uncharge nreq->rsk_listener, + * that is @sk, so charge it here. Unlike the listener + * being closed, @sk is live and needs its lock. + */ + fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq; + spin_lock_bh(&fastopenq->lock); + fastopenq->qlen++; + spin_unlock_bh(&fastopenq->lock); + + /* We need not acquire fastopenq->lock + * because the child socket is locked in inet_csk_listen_stop(). + */ rcu_assign_pointer(tcp_sk(nreq->sk)->fastopen_rsk, nreq); + } return nreq; } diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 1127519b8416..8fdd19310efd 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -395,8 +395,8 @@ static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir, *prev = ERR_PTR(-ENOMEM); return NULL; } - mod_timer(&q->timer, jiffies + fqdir->timeout); + spin_lock_bh(&q->lock); *prev = rhashtable_lookup_get_insert_key(&fqdir->rhashtable, &q->key, &q->node, f->rhash_params); if (*prev) { @@ -404,13 +404,13 @@ static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir, * we need to cancel what inet_frag_alloc() * anticipated. */ - int refs = 1; - q->flags |= INET_FRAG_COMPLETE; - inet_frag_kill(q, &refs); - inet_frag_putn(q, refs); + spin_unlock_bh(&q->lock); + inet_frag_putn(q, 2); return NULL; } + mod_timer(&q->timer, jiffies + fqdir->timeout); + spin_unlock_bh(&q->lock); return q; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 7cc9a7336c30..5c6d7e6995b2 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -741,6 +741,35 @@ out_unlock: spin_unlock_bh(&fnhe_lock); } +/* Update the PMTU of an exception when: + * - the new MTU of the first hop becomes smaller than the PMTU + * - the old MTU was the same as the PMTU, and it limited discovery of + * larger MTUs on the path. With that limit raised, we can now + * discover larger MTUs + * A special case is locked exceptions, for which the PMTU is smaller + * than the minimal accepted PMTU: + * - if the new MTU is greater than the PMTU, don't make any change + * - otherwise, unlock and set PMTU + * + * fnhe_lock keeps fnhe_pmtu and fnhe_mtu_locked consistent against + * update_or_create_fnhe(), which sets both under the same lock. + */ +void fnhe_update_pmtu(struct fib_nh_exception *fnhe, u32 new, u32 orig) +{ + spin_lock_bh(&fnhe_lock); + + if (fnhe->fnhe_mtu_locked) { + if (new <= fnhe->fnhe_pmtu) { + fnhe->fnhe_pmtu = new; + fnhe->fnhe_mtu_locked = false; + } + } else if (new < fnhe->fnhe_pmtu || orig == fnhe->fnhe_pmtu) { + fnhe->fnhe_pmtu = new; + } + + spin_unlock_bh(&fnhe_lock); +} + static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4, bool kill_route) { diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index b9f036633365..18b45950d1ac 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -454,6 +454,7 @@ more_data: case __SK_REDIRECT: redir_ingress = psock->redir_ingress; sk_redir = psock->sk_redir; + sock_hold(sk_redir); sk_msg_apply_bytes(psock, tosend); if (!psock->apply_bytes) { /* Clean up before releasing the sock lock. */ @@ -474,6 +475,7 @@ more_data: if (eval == __SK_REDIRECT) sock_put(sk_redir); + sock_put(sk_redir); lock_sock(sk); sk_mem_uncharge(sk, sent); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index eed808c2adbb..e2c022f02c64 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -252,7 +252,7 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); val = tcp_win_from_space(sk, sk->sk_rcvbuf); - tcp_set_window_clamp(sk, val); + WRITE_ONCE(tp->window_clamp, val); if (tp->window_clamp < tp->rcvq_space.space) tp->rcvq_space.space = tp->window_clamp; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ce572025eeeb..4b59d258c266 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3079,24 +3079,24 @@ static unsigned int bpf_iter_tcp_established_batch(struct seq_file *seq, { struct bpf_tcp_iter_state *iter = seq->private; struct hlist_nulls_node *node; - unsigned int expected = 1; - struct sock *sk; - - sock_hold(*start_sk); - iter->batch[iter->end_sk++].sk = *start_sk; + struct sock *sk = *start_sk; + unsigned int expected = 0; - sk = sk_nulls_next(*start_sk); *start_sk = NULL; sk_nulls_for_each_from(sk, node) { - if (seq_sk_match(seq, sk)) { - if (iter->end_sk < iter->max_sk) { - sock_hold(sk); - iter->batch[iter->end_sk++].sk = sk; - } else if (!*start_sk) { - /* Remember where we left off. */ - *start_sk = sk; - } - expected++; + if (!seq_sk_match(seq, sk)) + continue; + expected++; + if (iter->end_sk < iter->max_sk) { + /* reqsk_queue_hash_req() inserts with sk_refcnt == 0 + * and refcount_set()s it after the bucket lock drops. + */ + if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) + continue; + iter->batch[iter->end_sk++].sk = sk; + } else if (!*start_sk) { + /* Remember where we left off. */ + *start_sk = sk; } } @@ -3134,12 +3134,13 @@ static struct sock *bpf_iter_tcp_batch(struct seq_file *seq) struct sock *sk; int err; +again: sk = bpf_iter_tcp_resume(seq); if (!sk) return NULL; /* Done */ expected = bpf_iter_fill_batch(seq, &sk); - if (likely(iter->end_sk == expected)) + if (likely(!sk)) goto done; /* Batch size was too small. */ @@ -3158,7 +3159,7 @@ static struct sock *bpf_iter_tcp_batch(struct seq_file *seq) return NULL; /* Done */ expected = bpf_iter_fill_batch(seq, &sk); - if (likely(iter->end_sk == expected)) + if (likely(!sk)) goto done; /* Batch size was still too small. Hold onto the lock while we try @@ -3171,10 +3172,14 @@ static struct sock *bpf_iter_tcp_batch(struct seq_file *seq) return ERR_PTR(err); } - expected = bpf_iter_fill_batch(seq, &sk); - WARN_ON_ONCE(iter->end_sk != expected); + bpf_iter_fill_batch(seq, &sk); + WARN_ON_ONCE(sk); done: bpf_iter_tcp_unlock_bucket(seq); + if (unlikely(!iter->end_sk)) { + ++iter->state.bucket; + goto again; + } return iter->batch[0].sk; } diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 29651b1a0bc7..abcd3cc2d9a3 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -178,17 +178,19 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); bool remcsum, need_csum, offload_csum, gso_partial; struct sk_buff *segs = ERR_PTR(-EINVAL); - struct udphdr *uh = udp_hdr(skb); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int udp_offset, outer_hlen; + struct udphdr *uh; __wsum partial; bool need_ipsec; if (unlikely(!pskb_may_pull(skb, tnl_hlen))) goto out; + uh = udp_hdr(skb); + /* Adjust partial header checksum to negate old length. * We cannot rely on the value contained in uh->len as it is * possible that the actual value exceeds the boundaries of the diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 95da1f087294..49f719ab55a9 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -684,6 +684,9 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!skb2) return 0; + /* Remove debris left by outer IPv6 stack. */ + memset(IP6CB(skb2), 0, sizeof(*IP6CB(skb2))); + skb_dst_drop(skb2); skb_pull(skb2, offset); skb_reset_network_header(skb2); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d4edc133c045..f2cc5476553f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -987,13 +987,13 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, } else if (rinfo->prefix_len > 128) { return -EINVAL; } else if (rinfo->prefix_len > 64) { - if (rinfo->length < 2) { + /* RFC 4191: Length MUST be 3 when Prefix Length > 64 */ + if (rinfo->length < 3) return -EINVAL; - } } else if (rinfo->prefix_len > 0) { - if (rinfo->length < 1) { + /* RFC 4191: Length MUST be 2 or 3 when Prefix Length > 0 */ + if (rinfo->length < 2) return -EINVAL; - } } pref = rinfo->route_pref; diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c index 65089826ff59..005338f89b75 100644 --- a/net/mac802154/scan.c +++ b/net/mac802154/scan.c @@ -415,6 +415,7 @@ void mac802154_beacon_worker(struct work_struct *work) container_of(work, struct ieee802154_local, beacon_work.work); struct cfg802154_beacon_request *beacon_req; struct ieee802154_sub_if_data *sdata; + netdevice_tracker dev_tracker; struct wpan_dev *wpan_dev; u8 interval; int ret; @@ -427,12 +428,14 @@ void mac802154_beacon_worker(struct work_struct *work) } sdata = IEEE802154_WPAN_DEV_TO_SUB_IF(beacon_req->wpan_dev); + netdev_hold(sdata->dev, &dev_tracker, GFP_ATOMIC); /* Wait an arbitrary amount of time in case we cannot use the device */ if (local->suspended || !ieee802154_sdata_running(sdata)) { rcu_read_unlock(); queue_delayed_work(local->mac_wq, &local->beacon_work, msecs_to_jiffies(1000)); + netdev_put(sdata->dev, &dev_tracker); return; } @@ -450,6 +453,7 @@ void mac802154_beacon_worker(struct work_struct *work) if (interval < IEEE802154_ACTIVE_SCAN_DURATION) queue_delayed_work(local->mac_wq, &local->beacon_work, local->beacon_interval); + netdev_put(sdata->dev, &dev_tracker); } int mac802154_stop_beacons_locked(struct ieee802154_local *local, diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index 2f872d064396..8cc538358f6a 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -461,6 +461,10 @@ static int ncsi_send_cmd_nl(struct sk_buff *msg, struct genl_info *info) nca.req_flags = NCSI_REQ_FLAG_NETLINK_DRIVEN; nca.info = info; nca.payload = ntohs(hdr->length); + if (nca.payload > len - sizeof(*hdr)) { + ret = -EINVAL; + goto out_netlink; + } nca.data = data + sizeof(*hdr); ret = ncsi_xmit_cmd(&nca); diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index bb9b5bed10e1..226fdf17b683 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -77,7 +77,7 @@ mtype_flush(struct ip_set *set) mtype_ext_cleanup(set); bitmap_zero(map->members, map->elements); set->elements = 0; - set->ext_size = 0; + atomic64_set(&set->ext_size, 0); } /* Calculate the actual memory size of the set data */ @@ -93,7 +93,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) { const struct mtype *map = set->data; struct nlattr *nested; - size_t memsize = mtype_memsize(map, set->dsize) + set->ext_size; + size_t memsize = mtype_memsize(map, set->dsize) + atomic64_read(&set->ext_size); nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 6cfad152d7d1..822a53a7f502 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -350,7 +350,7 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, size_t len = ext->comment ? strlen(ext->comment) : 0; if (unlikely(c)) { - set->ext_size -= sizeof(*c) + strlen(c->str) + 1; + atomic64_sub(sizeof(*c) + strlen(c->str) + 1, &set->ext_size); rcu_assign_pointer(comment->c, NULL); kfree_rcu(c, rcu); } @@ -362,7 +362,7 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, if (unlikely(!c)) return; strscpy(c->str, ext->comment, len + 1); - set->ext_size += sizeof(*c) + strlen(c->str) + 1; + atomic64_add(sizeof(*c) + strlen(c->str) + 1, &set->ext_size); rcu_assign_pointer(comment->c, c); } EXPORT_SYMBOL_GPL(ip_set_init_comment); @@ -392,7 +392,7 @@ ip_set_comment_free(struct ip_set *set, void *ptr) c = rcu_dereference_protected(comment->c, 1); if (unlikely(!c)) return; - set->ext_size -= sizeof(*c) + strlen(c->str) + 1; + atomic64_sub(sizeof(*c) + strlen(c->str) + 1, &set->ext_size); rcu_assign_pointer(comment->c, NULL); kfree_rcu(c, rcu); } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index a3ed683cc47e..3072b4e28853 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -1288,7 +1288,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); mtype_ext_size(set, &elements, &ext_size); - memsize = mtype_ahash_memsize(h, t) + ext_size + set->ext_size; + memsize = mtype_ahash_memsize(h, t) + ext_size + atomic64_read(&set->ext_size); htable_bits = t->htable_bits; rcu_read_unlock_bh(); diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 1cef84f15e8c..ca3ef9479e83 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -421,7 +421,7 @@ list_set_flush(struct ip_set *set) list_for_each_entry_safe(e, n, &map->members, list) list_set_del(set, e); set->elements = 0; - set->ext_size = 0; + atomic64_set(&set->ext_size, 0); } static void @@ -455,7 +455,7 @@ list_set_head(struct ip_set *set, struct sk_buff *skb) { const struct list_set *map = set->data; struct nlattr *nested; - size_t memsize = list_set_memsize(map, set->dsize) + set->ext_size; + size_t memsize = list_set_memsize(map, set->dsize) + atomic64_read(&set->ext_size); nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index fc1dd4c463b1..e4ca8fd4b658 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1081,12 +1081,6 @@ static inline void ip_vs_bind_xmit_v6(struct ip_vs_conn *cp) #endif -static inline int ip_vs_dest_totalconns(struct ip_vs_dest *dest) -{ - return atomic_read(&dest->activeconns) - + atomic_read(&dest->inactconns); -} - /* * Bind a connection entry with a virtual service destination * Called just after a new connection entry is created. @@ -1147,23 +1141,22 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) /* Update the connection counters */ if (!(flags & IP_VS_CONN_F_TEMPLATE)) { + int tc; + /* It is a normal connection, so modify the counters * according to the flags, later the protocol can * update them on state change */ if (!(flags & IP_VS_CONN_F_INACTIVE)) atomic_inc(&dest->activeconns); - else - atomic_inc(&dest->inactconns); + tc = atomic_inc_return(&dest->totalconns); + if (tc == READ_ONCE(dest->u_threshold)) + ip_vs_dest_update_overload(dest, 1); } else { /* It is a persistent connection/template, so increase the persistent connection counter */ atomic_inc(&dest->persistconns); } - - if (dest->u_threshold != 0 && - ip_vs_dest_totalconns(dest) >= dest->u_threshold) - dest->flags |= IP_VS_DEST_F_OVERLOAD; } @@ -1244,30 +1237,20 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp) /* Update the connection counters */ if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) { - /* It is a normal connection, so decrease the inactconns - or activeconns counter */ - if (cp->flags & IP_VS_CONN_F_INACTIVE) { - atomic_dec(&dest->inactconns); - } else { + int tc; + + /* It is a normal connection, so decrease the counters */ + if (!(cp->flags & IP_VS_CONN_F_INACTIVE)) atomic_dec(&dest->activeconns); - } + tc = atomic_fetch_dec(&dest->totalconns); + if (tc == READ_ONCE(dest->l_threshold_val)) + ip_vs_dest_update_overload(dest, -1); } else { /* It is a persistent connection/template, so decrease the persistent connection counter */ atomic_dec(&dest->persistconns); } - if (dest->l_threshold != 0) { - if (ip_vs_dest_totalconns(dest) < dest->l_threshold) - dest->flags &= ~IP_VS_DEST_F_OVERLOAD; - } else if (dest->u_threshold != 0) { - if (ip_vs_dest_totalconns(dest) * 4 < dest->u_threshold * 3) - dest->flags &= ~IP_VS_DEST_F_OVERLOAD; - } else { - if (dest->flags & IP_VS_DEST_F_OVERLOAD) - dest->flags &= ~IP_VS_DEST_F_OVERLOAD; - } - ip_vs_dest_put(dest); } @@ -1296,7 +1279,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct, struct ip_vs_dest *cdest) * Checking the dest server status. */ if ((dest == NULL) || - !(dest->flags & IP_VS_DEST_F_AVAILABLE) || + !(dest->cflags & IP_VS_DEST_CF_AVAILABLE) || expire_quiescent_template(ipvs, dest) || (cdest && (dest != cdest))) { IP_VS_DBG_BUF(9, "check_template: dest not available for " @@ -2029,7 +2012,7 @@ repeat: cp = ip_vs_hn0_to_conn(hn); resched_score++; dest = cp->dest; - if (!dest || (dest->flags & IP_VS_DEST_F_AVAILABLE)) + if (!dest || (dest->cflags & IP_VS_DEST_CF_AVAILABLE)) continue; if (atomic_read(&cp->n_control)) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 6b79e0c4d9e2..a46e7acdd8e1 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -302,7 +302,7 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) struct ip_vs_dest *dest = cp->dest; struct netns_ipvs *ipvs = cp->ipvs; - if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { + if (dest && (dest->cflags & IP_VS_DEST_CF_AVAILABLE)) { struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; @@ -338,7 +338,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) struct ip_vs_dest *dest = cp->dest; struct netns_ipvs *ipvs = cp->ipvs; - if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { + if (dest && (dest->cflags & IP_VS_DEST_CF_AVAILABLE)) { struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; @@ -925,28 +925,27 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, */ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout, unsigned int toff, - bool has_ports) + bool has_ports, struct ip_vs_iphdr *ciph) { struct iphdr *iph = ip_hdr(skb); struct icmphdr *icmph = (struct icmphdr *)(skb->data + toff); - struct iphdr *ciph = (struct iphdr *)(icmph + 1); - unsigned int coff __maybe_unused = toff + sizeof(struct icmphdr); + struct iphdr *cih = (struct iphdr *)(icmph + 1); if (inout) { iph->saddr = cp->vaddr.ip; ip_send_check(iph); - ciph->daddr = cp->vaddr.ip; - ip_send_check(ciph); + cih->daddr = cp->vaddr.ip; + ip_send_check(cih); } else { iph->daddr = cp->daddr.ip; ip_send_check(iph); - ciph->saddr = cp->daddr.ip; - ip_send_check(ciph); + cih->saddr = cp->daddr.ip; + ip_send_check(cih); } /* the TCP/UDP/SCTP port */ if (has_ports) { - __be16 *ports = (void *)ciph + ciph->ihl*4; + __be16 *ports = (void *)(skb->data + ciph->len); if (inout) ports[1] = cp->vport; @@ -960,10 +959,10 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, skb->ip_summed = CHECKSUM_UNNECESSARY; if (inout) - IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff, + IP_VS_DBG_PKT(11, AF_INET, pp, skb, ciph->off, "Forwarding altered outgoing ICMP"); else - IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff, + IP_VS_DBG_PKT(11, AF_INET, pp, skb, ciph->off, "Forwarding altered incoming ICMP"); } @@ -1056,7 +1055,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb, ip_vs_nat_icmp_v6(skb, pp, cp, 1, toff, has_ports, ciph); else #endif - ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports); + ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports, ciph); if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; @@ -1092,7 +1091,7 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; - unsigned int offset, ihl; + unsigned int offset; union nf_inet_addr snet; *related = 1; @@ -1105,7 +1104,6 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; } - ihl = ipvsh->len; offset = ipvsh->len; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) @@ -1131,11 +1129,15 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, /* Now find the contained IP header */ offset += sizeof(_icmph); + if (!ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph)) + return NF_ACCEPT; /* The packet looks wrong, ignore */ + cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (!(cih && cih->version == 4 && cih->ihl >= 5)) + if (!(cih && cih->version == 4 && + ciph.len - ciph.off >= sizeof(struct iphdr))) return NF_ACCEPT; /* The packet looks wrong, ignore */ - pp = ip_vs_proto_get(cih->protocol); + pp = ip_vs_proto_get(ciph.protocol); if (!pp) return NF_ACCEPT; @@ -1146,8 +1148,6 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking outgoing ICMP for"); - ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph); - /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET, skb, &ciph); @@ -1155,8 +1155,8 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; snet.ip = ipvsh->saddr.ip; - return handle_response_icmp(AF_INET, skb, &snet, cp, pp, &ciph, ihl, - hooknum); + return handle_response_icmp(AF_INET, skb, &snet, cp, pp, &ciph, + ipvsh->len, hooknum); } #ifdef CONFIG_IP_VS_IPV6 @@ -1803,10 +1803,12 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (!(cih && cih->version == 4 && cih->ihl >= 5)) + if (!cih) return NF_ACCEPT; /* The packet looks wrong, ignore */ - raddr = (union nf_inet_addr *)&cih->daddr; hlen_ipip = cih->ihl * 4; + if (!(cih->version == 4 && hlen_ipip >= sizeof(struct iphdr))) + return NF_ACCEPT; /* The packet looks wrong, ignore */ + raddr = (union nf_inet_addr *)&cih->daddr; /* Special case for errors for IPIP/UDP/GRE tunnel packets */ tunnel = false; @@ -1823,9 +1825,6 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP) return NF_ACCEPT; offset += hlen_ipip; - cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (!(cih && cih->version == 4 && cih->ihl >= 5)) - return NF_ACCEPT; /* The packet looks wrong, ignore */ tunnel = true; } else if ((cih->protocol == IPPROTO_UDP || /* Can be UDP encap */ cih->protocol == IPPROTO_GRE) && /* Can be GRE encap */ @@ -1850,21 +1849,25 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Skip IP and UDP/GRE tunnel headers */ offset = offset2 + ulen; /* Now we should be at the original IP header */ - cih = skb_header_pointer(skb, offset, sizeof(_ciph), - &_ciph); - if (cih && cih->version == 4 && cih->ihl >= 5 && - iproto == IPPROTO_IPIP) + if (iproto == IPPROTO_IPIP) tunnel = true; else return NF_ACCEPT; } } - pd = ip_vs_proto_data_get(ipvs, cih->protocol); + if (!ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph)) + return NF_ACCEPT; + pd = ip_vs_proto_data_get(ipvs, ciph.protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; + cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); + if (!(cih && cih->version == 4 && + ciph.len - ciph.off >= sizeof(struct iphdr))) + return NF_ACCEPT; /* The packet looks wrong, ignore */ + /* Is the embedded protocol header present? */ if (unlikely(cih->frag_off & htons(IP_OFFSET) && !pp->dont_defrag)) return NF_ACCEPT; @@ -1872,9 +1875,6 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking incoming ICMP for"); - offset2 = offset; - ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph); - /* The embedded headers contain source and dest in reverse order. * For IPIP/UDP/GRE tunnel this is error for request, not for reply. */ @@ -1904,11 +1904,12 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, } if (tunnel) { - unsigned int hlen_orig = cih->ihl * 4; + unsigned int hlen_orig = ciph.len - ciph.off; __be32 info = ic->un.gateway; __u8 type = ic->type; __u8 code = ic->code; + offset2 = offset; /* Update the MTU */ if (ic->type == ICMP_DEST_UNREACH && ic->code == ICMP_FRAG_NEEDED) { @@ -1949,6 +1950,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (pskb_pull(skb, offset2) == NULL) goto ignore_tunnel; skb_reset_network_header(skb); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); /* Ensure the IP header is present in headroom */ if (!pskb_may_pull(skb, hlen_orig)) goto ignore_tunnel; @@ -2209,7 +2211,7 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state } /* Check the server status */ - if (cp && cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { + if (cp && cp->dest && !(cp->dest->cflags & IP_VS_DEST_CF_AVAILABLE)) { /* the destination server is not available */ if (sysctl_expire_nodest_conn(ipvs)) { bool old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 16daba8cac83..ad3583d8174b 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1304,6 +1304,40 @@ void ip_vs_stats_free(struct ip_vs_stats *stats) } } +/* Update overload flag based on number of dest conns and lower/upper + * connection thresholds: + * - conns reach u_threshold and exceed it: set the flag + * - conns go below l_threshold (or 75% of u_threshold): clear the flag + */ +static void __ip_vs_dest_update_overload(struct ip_vs_dest *dest, int mode) +{ + int conns; + u32 l, u; + + lockdep_assert_held(&dest->dst_lock); + u = READ_ONCE(dest->u_threshold); + if (!u) + goto unset; + l = READ_ONCE(dest->l_threshold_val); + conns = atomic_read(&dest->totalconns); + if (conns >= (mode > 0 ? l : u)) { + dest->flags |= IP_VS_DEST_F_OVERLOAD; + return; + } + if (conns >= (mode < 0 ? u : l)) + return; + +unset: + dest->flags &= ~IP_VS_DEST_F_OVERLOAD; +} + +void ip_vs_dest_update_overload(struct ip_vs_dest *dest, int mode) +{ + spin_lock_bh(&dest->dst_lock); + __ip_vs_dest_update_overload(dest, mode); + spin_unlock_bh(&dest->dst_lock); +} + /* * Update a destination in the given service */ @@ -1368,12 +1402,21 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, } /* set the dest status flags */ - dest->flags |= IP_VS_DEST_F_AVAILABLE; + dest->cflags |= IP_VS_DEST_CF_AVAILABLE; - if (udest->u_threshold == 0 || udest->u_threshold > dest->u_threshold) - dest->flags &= ~IP_VS_DEST_F_OVERLOAD; - dest->u_threshold = udest->u_threshold; - dest->l_threshold = udest->l_threshold; + if (READ_ONCE(dest->u_threshold) != udest->u_threshold || + READ_ONCE(dest->l_threshold) != udest->l_threshold) { + spin_lock_bh(&dest->dst_lock); + WRITE_ONCE(dest->u_threshold, udest->u_threshold); + WRITE_ONCE(dest->l_threshold, udest->l_threshold); + /* Low threshold defaults to 75% of upper threshold */ + WRITE_ONCE(dest->l_threshold_val, + udest->l_threshold ? : + (udest->u_threshold - + (udest->u_threshold >> 2))); + __ip_vs_dest_update_overload(dest, 0); + spin_unlock_bh(&dest->dst_lock); + } dest->af = udest->af; @@ -1445,7 +1488,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) dest->port = udest->port; atomic_set(&dest->activeconns, 0); - atomic_set(&dest->inactconns, 0); + atomic_set(&dest->totalconns, 0); atomic_set(&dest->persistconns, 0); refcount_set(&dest->refcnt, 1); @@ -1486,6 +1529,9 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) return -ERANGE; } + if (udest->u_threshold > INT_MAX) + return -EINVAL; + if (udest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { if (udest->tun_port == 0) { pr_err("%s(): tunnel port is zero\n", __func__); @@ -1559,6 +1605,9 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) return -ERANGE; } + if (udest->u_threshold > INT_MAX) + return -EINVAL; + if (udest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { if (udest->tun_port == 0) { pr_err("%s(): tunnel port is zero\n", __func__); @@ -1613,7 +1662,7 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, int svcupd) { - dest->flags &= ~IP_VS_DEST_F_AVAILABLE; + dest->cflags &= ~IP_VS_DEST_CF_AVAILABLE; spin_lock_bh(&dest->dst_lock); __ip_vs_dst_cache_reset(dest); @@ -2986,7 +3035,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) ip_vs_fwd_name(atomic_read(&dest->conn_flags)), atomic_read(&dest->weight), atomic_read(&dest->activeconns), - atomic_read(&dest->inactconns)); + ip_vs_dest_inactconns(dest)); else #endif seq_printf(seq, @@ -2997,7 +3046,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) ip_vs_fwd_name(atomic_read(&dest->conn_flags)), atomic_read(&dest->weight), atomic_read(&dest->activeconns), - atomic_read(&dest->inactconns)); + ip_vs_dest_inactconns(dest)); } } @@ -3622,10 +3671,10 @@ __ip_vs_get_dest_entries(struct netns_ipvs *ipvs, const struct ip_vs_get_dests * entry.port = dest->port; entry.conn_flags = atomic_read(&dest->conn_flags); entry.weight = atomic_read(&dest->weight); - entry.u_threshold = dest->u_threshold; - entry.l_threshold = dest->l_threshold; + entry.u_threshold = READ_ONCE(dest->u_threshold); + entry.l_threshold = READ_ONCE(dest->l_threshold); entry.activeconns = atomic_read(&dest->activeconns); - entry.inactconns = atomic_read(&dest->inactconns); + entry.inactconns = ip_vs_dest_inactconns(dest); entry.persistconns = atomic_read(&dest->persistconns); ip_vs_copy_stats(&kstats, &dest->stats); ip_vs_export_stats_user(&entry.stats, &kstats); @@ -4232,12 +4281,14 @@ static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest) dest->tun_port) || nla_put_u16(skb, IPVS_DEST_ATTR_TUN_FLAGS, dest->tun_flags) || - nla_put_u32(skb, IPVS_DEST_ATTR_U_THRESH, dest->u_threshold) || - nla_put_u32(skb, IPVS_DEST_ATTR_L_THRESH, dest->l_threshold) || + nla_put_u32(skb, IPVS_DEST_ATTR_U_THRESH, + READ_ONCE(dest->u_threshold)) || + nla_put_u32(skb, IPVS_DEST_ATTR_L_THRESH, + READ_ONCE(dest->l_threshold)) || nla_put_u32(skb, IPVS_DEST_ATTR_ACTIVE_CONNS, atomic_read(&dest->activeconns)) || nla_put_u32(skb, IPVS_DEST_ATTR_INACT_CONNS, - atomic_read(&dest->inactconns)) || + ip_vs_dest_inactconns(dest)) || nla_put_u32(skb, IPVS_DEST_ATTR_PERSIST_CONNS, atomic_read(&dest->persistconns)) || nla_put_u16(skb, IPVS_DEST_ATTR_ADDR_FAMILY, dest->af)) diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c index e1f62f6b25e2..43abed7a26a6 100644 --- a/net/netfilter/ipvs/ip_vs_dh.c +++ b/net/netfilter/ipvs/ip_vs_dh.c @@ -219,8 +219,8 @@ ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, s = (struct ip_vs_dh_state *) svc->sched_data; dest = ip_vs_dh_get(svc->af, s, &iph->daddr); - if (!dest - || !(dest->flags & IP_VS_DEST_F_AVAILABLE) + if (!dest || + !(dest->cflags & IP_VS_DEST_CF_AVAILABLE) || atomic_read(&dest->weight) <= 0 || is_overloaded(dest)) { ip_vs_scheduler_err(svc, "no destination available"); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index ab09f5182951..05a216a47b45 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -191,8 +191,11 @@ static int ip_vs_estimation_kthread(void *data) } /* kthread 0 will handle the calc phase */ - if (ipvs->est_calc_phase) + if (ipvs->est_calc_phase) { ip_vs_est_calc_phase(ipvs); + if (kthread_should_stop() || !READ_ONCE(ipvs->enable)) + return 0; + } } while (1) { @@ -270,6 +273,7 @@ int ip_vs_est_kthread_start(struct netns_ipvs *ipvs, kd->task = NULL; goto out; } + get_task_struct(kd->task); set_user_nice(kd->task, sysctl_est_nice(ipvs)); if (sysctl_est_preferred_cpulist(ipvs)) @@ -286,7 +290,7 @@ void ip_vs_est_kthread_stop(struct ip_vs_est_kt_data *kd) { if (kd->task) { pr_info("stopping estimator thread %d...\n", kd->id); - kthread_stop(kd->task); + kthread_stop_put(kd->task); kd->task = NULL; } } @@ -526,7 +530,7 @@ static void ip_vs_est_kthread_destroy(struct ip_vs_est_kt_data *kd) if (kd) { if (kd->task) { pr_info("stop unused estimator thread %d...\n", kd->id); - kthread_stop(kd->task); + kthread_stop_put(kd->task); } ip_vs_stats_free(kd->calc_stats); kfree(kd); diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 15ccb2b2fa1f..693bcc82ccb7 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -502,7 +502,7 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, */ dest = en->dest; - if ((dest->flags & IP_VS_DEST_F_AVAILABLE) && + if ((dest->cflags & IP_VS_DEST_CF_AVAILABLE) && atomic_read(&dest->weight) > 0 && !is_overloaded(dest, svc)) goto out; } diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index c90ea897c3f7..f53f05ceea36 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -169,8 +169,8 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) if (least->flags & IP_VS_DEST_F_OVERLOAD) continue; - if ((atomic_read(&least->weight) > 0) - && (least->flags & IP_VS_DEST_F_AVAILABLE)) { + if ((atomic_read(&least->weight) > 0) && + (least->cflags & IP_VS_DEST_CF_AVAILABLE)) { loh = ip_vs_dest_conn_overhead(least); goto nextstage; } @@ -186,8 +186,8 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) doh = ip_vs_dest_conn_overhead(dest); if (((__s64)loh * atomic_read(&dest->weight) > - (__s64)doh * atomic_read(&least->weight)) - && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { + (__s64)doh * atomic_read(&least->weight)) && + (dest->cflags & IP_VS_DEST_CF_AVAILABLE)) { least = dest; loh = doh; } diff --git a/net/netfilter/ipvs/ip_vs_lc.c b/net/netfilter/ipvs/ip_vs_lc.c index 38cc38c5d8bb..18b976a7c4d2 100644 --- a/net/netfilter/ipvs/ip_vs_lc.c +++ b/net/netfilter/ipvs/ip_vs_lc.c @@ -30,7 +30,7 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, /* * Simply select the server with the least number of - * (activeconns<<5) + inactconns + * (activeconns*256) + totalconns * Except whose weight is equal to zero. * If the weight is equal to zero, it means that the server is * quiesced, the existing connections to the server still get @@ -56,7 +56,7 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), - atomic_read(&least->inactconns)); + ip_vs_dest_inactconns(least)); return least; } diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 3dbd3096e163..fb8af6b15a39 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -193,7 +193,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, struct sctphdr *sh; __le32 cmp, val; - if (!ip_vs_checksum_needed(skb, af)) + if (!ip_vs_checksum_needed(skb)) return 1; sh = (struct sctphdr *)(skb->data + sctphoff); cmp = sh->checksum; @@ -446,12 +446,10 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && (next_state != IP_VS_SCTP_S_ESTABLISHED)) { atomic_dec(&dest->activeconns); - atomic_inc(&dest->inactconns); cp->flags |= IP_VS_CONN_F_INACTIVE; } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) && (next_state == IP_VS_SCTP_S_ESTABLISHED)) { atomic_inc(&dest->activeconns); - atomic_dec(&dest->inactconns); cp->flags &= ~IP_VS_CONN_F_INACTIVE; } } diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 99a286fdc90c..fec0e8b47b71 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -526,12 +526,10 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && !tcp_state_active(new_state)) { atomic_dec(&dest->activeconns); - atomic_inc(&dest->inactconns); cp->flags |= IP_VS_CONN_F_INACTIVE; } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) && tcp_state_active(new_state)) { atomic_inc(&dest->activeconns); - atomic_dec(&dest->inactconns); cp->flags &= ~IP_VS_CONN_F_INACTIVE; } } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 93038abbf5e0..ea5fdd4f4ce7 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -878,13 +878,10 @@ static void ip_vs_proc_conn(struct netns_ipvs *ipvs, struct ip_vs_conn_param *pa spin_lock_bh(&cp->lock); if ((cp->flags ^ flags) & IP_VS_CONN_F_INACTIVE && !(flags & IP_VS_CONN_F_TEMPLATE) && dest) { - if (flags & IP_VS_CONN_F_INACTIVE) { + if (flags & IP_VS_CONN_F_INACTIVE) atomic_dec(&dest->activeconns); - atomic_inc(&dest->inactconns); - } else { + else atomic_inc(&dest->activeconns); - atomic_dec(&dest->inactconns); - } } flags &= IP_VS_CONN_F_BACKUP_UPD_MASK; flags |= cp->flags & ~IP_VS_CONN_F_BACKUP_UPD_MASK; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 0b0c5304993a..fc7403186394 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -351,7 +351,7 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, * stored in dest_trash. */ if (!rt_dev_is_down(dst_dev_rcu(&rt->dst)) && - dest->flags & IP_VS_DEST_F_AVAILABLE) + dest->cflags & IP_VS_DEST_CF_AVAILABLE) __ip_vs_dst_set(dest, dest_dst, &rt->dst, 0); else noref = 0; @@ -530,7 +530,7 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, * stored in dest_trash. */ if (!rt_dev_is_down(dst_dev_rcu(&rt->dst)) && - dest->flags & IP_VS_DEST_F_AVAILABLE) + dest->cflags & IP_VS_DEST_CF_AVAILABLE) __ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie); else noref = 0; @@ -1580,7 +1580,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error; - ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports); + ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports, ciph); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index f98d1d4b42c3..c2df7c948281 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -122,42 +122,54 @@ __bpf_nf_ct_alloc_entry(struct net *net, struct bpf_sock_tuple *bpf_tuple, struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_zone ct_zone; struct nf_conn *ct; + u8 ct_zone_dir = 0; + u16 ct_zone_id; + s32 netns_id; + u8 l4proto; int err; if (!(opts_len == NF_BPF_CT_OPTS_SZ || opts_len == 12)) return ERR_PTR(-EINVAL); + + netns_id = READ_ONCE(opts->netns_id); + l4proto = READ_ONCE(opts->l4proto); + ct_zone_id = READ_ONCE(opts->ct_zone_id); if (opts_len == NF_BPF_CT_OPTS_SZ) { - if (opts->reserved[0] || opts->reserved[1] || opts->reserved[2]) + ct_zone_dir = READ_ONCE(opts->ct_zone_dir); + if (READ_ONCE(opts->reserved[0]) || + READ_ONCE(opts->reserved[1]) || + READ_ONCE(opts->reserved[2])) return ERR_PTR(-EINVAL); } else { - if (opts->ct_zone_id) + if (ct_zone_id) return ERR_PTR(-EINVAL); } - if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS)) + if (unlikely(netns_id < BPF_F_CURRENT_NETNS)) return ERR_PTR(-EINVAL); - err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, opts->l4proto, + err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, l4proto, IP_CT_DIR_ORIGINAL, &otuple); if (err < 0) return ERR_PTR(err); - err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, opts->l4proto, + err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, l4proto, IP_CT_DIR_REPLY, &rtuple); if (err < 0) return ERR_PTR(err); - if (opts->netns_id >= 0) { - net = get_net_ns_by_id(net, opts->netns_id); + if (netns_id >= 0) { + net = get_net_ns_by_id(net, netns_id); if (unlikely(!net)) return ERR_PTR(-ENONET); } if (opts_len == NF_BPF_CT_OPTS_SZ) { - if (opts->ct_zone_dir == 0) - opts->ct_zone_dir = NF_CT_DEFAULT_ZONE_DIR; - nf_ct_zone_init(&ct_zone, - opts->ct_zone_id, opts->ct_zone_dir, 0); + if (ct_zone_dir == 0) { + ct_zone_dir = NF_CT_DEFAULT_ZONE_DIR; + opts->ct_zone_dir = ct_zone_dir; + } + nf_ct_zone_init(&ct_zone, ct_zone_id, ct_zone_dir, 0); } else { ct_zone = nf_ct_zone_dflt; } @@ -171,7 +183,7 @@ __bpf_nf_ct_alloc_entry(struct net *net, struct bpf_sock_tuple *bpf_tuple, __nf_ct_set_timeout(ct, timeout * HZ); out: - if (opts->netns_id >= 0) + if (netns_id >= 0) put_net(net); return ct; @@ -186,46 +198,58 @@ static struct nf_conn *__bpf_nf_ct_lookup(struct net *net, struct nf_conntrack_tuple tuple; struct nf_conntrack_zone ct_zone; struct nf_conn *ct; + u8 ct_zone_dir = 0; + u16 ct_zone_id; + s32 netns_id; + u8 l4proto; int err; if (!opts || !bpf_tuple) return ERR_PTR(-EINVAL); if (!(opts_len == NF_BPF_CT_OPTS_SZ || opts_len == 12)) return ERR_PTR(-EINVAL); + + netns_id = READ_ONCE(opts->netns_id); + l4proto = READ_ONCE(opts->l4proto); + ct_zone_id = READ_ONCE(opts->ct_zone_id); if (opts_len == NF_BPF_CT_OPTS_SZ) { - if (opts->reserved[0] || opts->reserved[1] || opts->reserved[2]) + ct_zone_dir = READ_ONCE(opts->ct_zone_dir); + if (READ_ONCE(opts->reserved[0]) || + READ_ONCE(opts->reserved[1]) || + READ_ONCE(opts->reserved[2])) return ERR_PTR(-EINVAL); } else { - if (opts->ct_zone_id) + if (ct_zone_id) return ERR_PTR(-EINVAL); } - if (unlikely(opts->l4proto != IPPROTO_TCP && opts->l4proto != IPPROTO_UDP)) + if (unlikely(l4proto != IPPROTO_TCP && l4proto != IPPROTO_UDP)) return ERR_PTR(-EPROTO); - if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS)) + if (unlikely(netns_id < BPF_F_CURRENT_NETNS)) return ERR_PTR(-EINVAL); - err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, opts->l4proto, + err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, l4proto, IP_CT_DIR_ORIGINAL, &tuple); if (err < 0) return ERR_PTR(err); - if (opts->netns_id >= 0) { - net = get_net_ns_by_id(net, opts->netns_id); + if (netns_id >= 0) { + net = get_net_ns_by_id(net, netns_id); if (unlikely(!net)) return ERR_PTR(-ENONET); } if (opts_len == NF_BPF_CT_OPTS_SZ) { - if (opts->ct_zone_dir == 0) - opts->ct_zone_dir = NF_CT_DEFAULT_ZONE_DIR; - nf_ct_zone_init(&ct_zone, - opts->ct_zone_id, opts->ct_zone_dir, 0); + if (ct_zone_dir == 0) { + ct_zone_dir = NF_CT_DEFAULT_ZONE_DIR; + opts->ct_zone_dir = ct_zone_dir; + } + nf_ct_zone_init(&ct_zone, ct_zone_id, ct_zone_dir, 0); } else { ct_zone = nf_ct_zone_dflt; } hash = nf_conntrack_find_get(net, &ct_zone, &tuple); - if (opts->netns_id >= 0) + if (netns_id >= 0) put_net(net); if (!hash) return ERR_PTR(-ENOENT); diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 50ddd3d613e1..e00957719351 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -79,6 +79,12 @@ void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, struct net *net; va_list args; + /* nfnetlink_log may re-enter conntrack attribute dumping and try to + * take ct->lock again via helpers such as tcp_to_nlattr(), so invalid + * conntrack logs must only be emitted after dropping ct->lock. + */ + lockdep_assert_not_held(&ct->lock); + net = nf_ct_net(ct); if (likely(net->ct.sysctl_log_invalid == 0)) return; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 7e10fa65cbdd..71cc920f6856 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -336,10 +336,12 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, struct sctphdr _sctph; const struct sctp_chunkhdr *sch; struct sctp_chunkhdr _sch; + bool log_invalid = false; u_int32_t offset, count; unsigned int *timeouts; unsigned long map[256 / sizeof(unsigned long)] = { 0 }; bool ignore = false; + u8 invalid_type = 0; if (sctp_error(skb, dataoff, state)) return -NF_ACCEPT; @@ -451,10 +453,8 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, /* Invalid */ if (new_state == SCTP_CONNTRACK_MAX) { - nf_ct_l4proto_log_invalid(skb, ct, state, - "Invalid, old_state %d, dir %d, type %d", - old_state, dir, sch->type); - + log_invalid = true; + invalid_type = sch->type; goto out_unlock; } @@ -529,6 +529,10 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, out_unlock: spin_unlock_bh(&ct->lock); + if (log_invalid) + nf_ct_l4proto_log_invalid(skb, ct, state, + "Invalid, old_state %d, dir %d, type %d", + old_state, dir, invalid_type); out: return -NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index e99ab1e88e9f..c289bec0c7c7 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -480,37 +480,81 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender, } } -__printf(6, 7) -static enum nf_ct_tcp_action nf_tcp_log_invalid(const struct sk_buff *skb, - const struct nf_conn *ct, - const struct nf_hook_state *state, - const struct ip_ct_tcp_state *sender, - enum nf_ct_tcp_action ret, - const char *fmt, ...) +enum nf_tcp_invalid_log_type { + NF_TCP_LOG_NONE, + NF_TCP_LOG_OVERSHOT, + NF_TCP_LOG_SEQ_OVER, + NF_TCP_LOG_ACK_OVER, + NF_TCP_LOG_SEQ_UNDER, + NF_TCP_LOG_ACK_UNDER, +}; + +struct nf_tcp_invalid_log { + enum nf_tcp_invalid_log_type type; + u32 value; +}; + +static enum nf_ct_tcp_action +nf_tcp_store_invalid(const struct nf_conn *ct, + const struct ip_ct_tcp_state *sender, + struct nf_tcp_invalid_log *log, + enum nf_ct_tcp_action ret, + enum nf_tcp_invalid_log_type type, + u32 value) { const struct nf_tcp_net *tn = nf_tcp_pernet(nf_ct_net(ct)); - struct va_format vaf; - va_list args; bool be_liberal; be_liberal = sender->flags & IP_CT_TCP_FLAG_BE_LIBERAL || tn->tcp_be_liberal; if (be_liberal) return NFCT_TCP_ACCEPT; - va_start(args, fmt); - vaf.fmt = fmt; - vaf.va = &args; - nf_ct_l4proto_log_invalid(skb, ct, state, "%pV", &vaf); - va_end(args); - + log->type = type; + log->value = value; return ret; } +static void nf_tcp_log_invalid(const struct sk_buff *skb, + const struct nf_conn *ct, + const struct nf_hook_state *state, + const struct nf_tcp_invalid_log *log) +{ + switch (log->type) { + case NF_TCP_LOG_OVERSHOT: + nf_ct_l4proto_log_invalid(skb, ct, state, + "%u bytes more than expected", + log->value); + break; + case NF_TCP_LOG_SEQ_OVER: + nf_ct_l4proto_log_invalid(skb, ct, state, + "SEQ is over upper bound %u (over the window of the receiver)", + log->value); + break; + case NF_TCP_LOG_ACK_OVER: + nf_ct_l4proto_log_invalid(skb, ct, state, + "ACK is over upper bound %u (ACKed data not seen yet)", + log->value); + break; + case NF_TCP_LOG_SEQ_UNDER: + nf_ct_l4proto_log_invalid(skb, ct, state, + "SEQ is under lower bound %u (already ACKed data retransmitted)", + log->value); + break; + case NF_TCP_LOG_ACK_UNDER: + nf_ct_l4proto_log_invalid(skb, ct, state, + "ignored ACK under lower bound %u (possible overly delayed)", + log->value); + break; + case NF_TCP_LOG_NONE: + break; + } +} + static enum nf_ct_tcp_action tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, unsigned int index, const struct sk_buff *skb, unsigned int dataoff, const struct tcphdr *tcph, - const struct nf_hook_state *hook_state) + struct nf_tcp_invalid_log *log) { struct ip_ct_tcp *state = &ct->proto.tcp; struct ip_ct_tcp_state *sender = &state->seen[dir]; @@ -640,31 +684,29 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, sender->td_end = end; sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED; - return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_IGNORE, - "%u bytes more than expected", overshot); + return nf_tcp_store_invalid(ct, sender, log, NFCT_TCP_IGNORE, + NF_TCP_LOG_OVERSHOT, overshot); } - return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_INVALID, - "SEQ is over upper bound %u (over the window of the receiver)", - sender->td_maxend + 1); + return nf_tcp_store_invalid(ct, sender, log, NFCT_TCP_INVALID, + NF_TCP_LOG_SEQ_OVER, sender->td_maxend + 1); } if (!before(sack, receiver->td_end + 1)) - return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_INVALID, - "ACK is over upper bound %u (ACKed data not seen yet)", - receiver->td_end + 1); + return nf_tcp_store_invalid(ct, sender, log, NFCT_TCP_INVALID, + NF_TCP_LOG_ACK_OVER, receiver->td_end + 1); /* Is the ending sequence in the receive window (if available)? */ in_recv_win = !receiver->td_maxwin || after(end, sender->td_end - receiver->td_maxwin - 1); if (!in_recv_win) - return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_IGNORE, - "SEQ is under lower bound %u (already ACKed data retransmitted)", - sender->td_end - receiver->td_maxwin - 1); + return nf_tcp_store_invalid(ct, sender, log, NFCT_TCP_IGNORE, + NF_TCP_LOG_SEQ_UNDER, + sender->td_end - receiver->td_maxwin - 1); if (!after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)) - return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_IGNORE, - "ignored ACK under lower bound %u (possible overly delayed)", - receiver->td_end - MAXACKWINDOW(sender) - 1); + return nf_tcp_store_invalid(ct, sender, log, NFCT_TCP_IGNORE, + NF_TCP_LOG_ACK_UNDER, + receiver->td_end - MAXACKWINDOW(sender) - 1); /* Take into account window scaling (RFC 1323). */ if (!tcph->syn) @@ -719,11 +761,8 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, return NFCT_TCP_ACCEPT; } -static void __cold nf_tcp_handle_invalid(struct nf_conn *ct, - enum ip_conntrack_dir dir, - int index, - const struct sk_buff *skb, - const struct nf_hook_state *hook_state) +static bool __cold +nf_tcp_handle_invalid(struct nf_conn *ct, enum ip_conntrack_dir dir, int index) { const unsigned int *timeouts; const struct nf_tcp_net *tn; @@ -732,7 +771,7 @@ static void __cold nf_tcp_handle_invalid(struct nf_conn *ct, if (!test_bit(IPS_ASSURED_BIT, &ct->status) || test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status)) - return; + return false; /* We don't want to have connections hanging around in ESTABLISHED * state for long time 'just because' conntrack deemed a FIN/RST @@ -747,7 +786,7 @@ static void __cold nf_tcp_handle_invalid(struct nf_conn *ct, case TCP_FIN_SET: break; default: - return; + return false; } if (ct->proto.tcp.last_dir != dir && @@ -755,7 +794,7 @@ static void __cold nf_tcp_handle_invalid(struct nf_conn *ct, ct->proto.tcp.last_index == TCP_RST_SET)) { expires = nf_ct_expires(ct); if (expires < 120 * HZ) - return; + return false; tn = nf_tcp_pernet(nf_ct_net(ct)); timeouts = nf_ct_timeout_lookup(ct); @@ -764,16 +803,15 @@ static void __cold nf_tcp_handle_invalid(struct nf_conn *ct, timeout = READ_ONCE(timeouts[TCP_CONNTRACK_UNACK]); if (expires > timeout) { - nf_ct_l4proto_log_invalid(skb, ct, hook_state, - "packet (index %d, dir %d) response for index %d lower timeout to %u", - index, dir, ct->proto.tcp.last_index, timeout); - WRITE_ONCE(ct->timeout, timeout + nfct_time_stamp); + return true; } } else { ct->proto.tcp.last_index = index; ct->proto.tcp.last_dir = dir; } + + return false; } /* table of valid flag combinations - PUSH, ECE and CWR are always valid */ @@ -969,7 +1007,9 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, struct net *net = nf_ct_net(ct); struct nf_tcp_net *tn = nf_tcp_pernet(net); enum tcp_conntrack new_state, old_state; + struct nf_tcp_invalid_log log = {}; unsigned int index, *timeouts; + bool lowered_timeout = false; enum nf_ct_tcp_action res; enum ip_conntrack_dir dir; const struct tcphdr *th; @@ -1252,14 +1292,18 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, } res = tcp_in_window(ct, dir, index, - skb, dataoff, th, state); + skb, dataoff, th, &log); switch (res) { case NFCT_TCP_IGNORE: spin_unlock_bh(&ct->lock); + nf_tcp_log_invalid(skb, ct, state, &log); return NF_ACCEPT; case NFCT_TCP_INVALID: - nf_tcp_handle_invalid(ct, dir, index, skb, state); + lowered_timeout = nf_tcp_handle_invalid(ct, dir, index); spin_unlock_bh(&ct->lock); + nf_tcp_log_invalid(skb, ct, state, &log); + if (lowered_timeout) + nf_ct_l4proto_log_invalid(skb, ct, state, "lowered timeout to UNACK"); return -NF_ACCEPT; case NFCT_TCP_ACCEPT: break; diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 0b78decce8a9..c9e332fafcb5 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -310,6 +310,7 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, struct dst_entry *dst) { skb_orphan(skb); + skb_dst_drop(skb); skb_dst_set_noref(skb, dst); dst_output(state->net, state->sk, skb); return NF_STOLEN; @@ -861,6 +862,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, return NF_DROP; } xmit.dest = neigh->ha; + skb_dst_drop(skb); skb_dst_set_noref(skb, &rt->dst); break; case FLOW_OFFLOAD_XMIT_DIRECT: @@ -1178,6 +1180,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, return NF_DROP; } xmit.dest = neigh->ha; + skb_dst_drop(skb); skb_dst_set_noref(skb, &rt->dst); break; case FLOW_OFFLOAD_XMIT_DIRECT: diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index eaf332b156d7..ae69b2cabab9 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1113,9 +1113,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) error = -EEXIST; goto err_unlock_ovs; } - /* The flow identifier has to be the same for flow updates. - * Look for any overlapping flow. - */ + + /* Look for any overlapping flow. */ if (unlikely(!ovs_flow_cmp(flow, &match))) { if (ovs_identifier_is_key(&flow->id)) flow = ovs_flow_tbl_lookup_exact(&dp->table, @@ -1127,6 +1126,30 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) goto err_unlock_ovs; } } + + if (unlikely(reply)) { + size_t cur, req; + + cur = ovs_flow_cmd_msg_size(acts, &new_flow->id, + ufid_flags); + req = ovs_flow_cmd_msg_size(acts, &flow->id, + ufid_flags); + if (cur < req) { + struct sk_buff *resized; + + resized = ovs_flow_cmd_alloc_info(acts, + &flow->id, + info, false, + ufid_flags); + if (IS_ERR(resized)) { + error = PTR_ERR(resized); + goto err_unlock_ovs; + } + kfree_skb(reply); + reply = resized; + } + } + /* Update actions. */ old_acts = ovsl_dereference(flow->sf_acts); rcu_assign_pointer(flow->sf_acts, acts); diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 66366982f604..46c1d66aad8c 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -889,8 +889,6 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) * Ethernet header * @key: output flow key * - * The caller must ensure that skb->len >= ETH_HLEN. - * * Initializes @skb header fields as follows: * * - skb->mac_header: the L2 header. @@ -910,8 +908,6 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) */ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) { - struct ethhdr *eth; - /* Flags are always used as part of stats */ key->tp.flags = 0; @@ -926,6 +922,13 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) skb_reset_network_header(skb); key->eth.type = skb->protocol; } else { + struct ethhdr *eth; + int err; + + err = check_header(skb, ETH_HLEN); + if (unlikely(err)) + return err; + eth = eth_hdr(skb); ether_addr_copy(key->eth.src, eth->h_source); ether_addr_copy(key->eth.dst, eth->h_dest); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e75d2932475a..435756877aba 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1315,13 +1315,25 @@ static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) return ret; } -static void packet_rcv_try_clear_pressure(struct packet_sock *po) +static void __packet_rcv_try_clear_pressure(struct packet_sock *po) { if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, false); } +static void packet_rcv_try_clear_pressure(struct packet_sock *po) +{ + struct sock *sk = &po->sk; + + if (!packet_sock_flag(po, PACKET_SOCK_PRESSURE)) + return; + + spin_lock_bh(&sk->sk_receive_queue.lock); + __packet_rcv_try_clear_pressure(po); + spin_unlock_bh(&sk->sk_receive_queue.lock); +} + static void packet_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_error_queue); @@ -1924,11 +1936,12 @@ static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) { int depth; + /* On TX skb->data is the L2 header; anchor it for all socket types. */ + skb_reset_mac_header(skb); + if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) && - sock->type == SOCK_RAW) { - skb_reset_mac_header(skb); + sock->type == SOCK_RAW) skb->protocol = dev_parse_header_protocol(skb); - } /* Move network header to the right position for VLAN tagged packets */ if (likely(skb->dev->type == ARPHRD_ETHER) && @@ -1953,8 +1966,9 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, struct net_device *dev; struct sockcm_cookie sockc; __be16 proto = 0; - int err; + int hard_header_len; int extra_len = 0; + int err; /* * Get and verify the address. @@ -1997,14 +2011,18 @@ retry: extra_len = 4; /* We're doing our own CRC */ } + /* Keep the allocation-time header length across retry. */ + if (!skb) + hard_header_len = READ_ONCE(dev->hard_header_len); + err = -EMSGSIZE; - if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN + extra_len) + if (len > dev->mtu + hard_header_len + VLAN_HLEN + extra_len) goto out_unlock; if (!skb) { - size_t reserved = LL_RESERVED_SPACE(dev); + size_t reserved = LL_RESERVED_SPACE_EX(dev, hard_header_len); int tlen = dev->needed_tailroom; - unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0; + unsigned int hhlen = dev->header_ops ? hard_header_len : 0; rcu_read_unlock(); skb = sock_wmalloc(sk, len + reserved + tlen, 0, GFP_KERNEL); @@ -2034,7 +2052,7 @@ retry: err = -EINVAL; goto out_unlock; } - if (len > (dev->mtu + dev->hard_header_len + extra_len) && + if (len > (dev->mtu + hard_header_len + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_unlock; @@ -2569,6 +2587,7 @@ static int packet_snd_vnet_parse(struct msghdr *msg, size_t *len, static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, void *data, int tp_len, __be16 proto, unsigned char *addr, int hlen, int copylen, + int hard_header_len, const struct sockcm_cookie *sockc) { union tpacket_uhdr ph; @@ -2600,8 +2619,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, } else if (copylen) { int hdrlen = min_t(int, copylen, tp_len); - skb_push(skb, dev->hard_header_len); - skb_put(skb, copylen - dev->hard_header_len); + skb_push(skb, hard_header_len); + skb_put(skb, copylen - hard_header_len); err = skb_store_bits(skb, 0, data, hdrlen); if (unlikely(err)) return err; @@ -2732,7 +2751,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) void *data; int len_sum = 0; int status = TP_STATUS_AVAILABLE; - int hlen, tlen, copylen = 0; + int hard_header_len, hlen, tlen, copylen = 0; long timeo; mutex_lock(&po->pg_vec_lock); @@ -2779,8 +2798,9 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto out_put; } + hard_header_len = READ_ONCE(dev->hard_header_len); if (po->sk.sk_socket->type == SOCK_RAW) - reserve = dev->hard_header_len; + reserve = hard_header_len; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); @@ -2817,7 +2837,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto tpacket_error; status = TP_STATUS_SEND_REQUEST; - hlen = LL_RESERVED_SPACE(dev); + hlen = LL_RESERVED_SPACE_EX(dev, hard_header_len); tlen = dev->needed_tailroom; if (vnet_hdr_sz) { data += vnet_hdr_sz; @@ -2835,10 +2855,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) vnet_hdr.hdr_len); has_vnet_hdr = true; } - copylen = max_t(int, copylen, dev->hard_header_len); + copylen = max_t(int, copylen, hard_header_len); skb = sock_alloc_send_skb(&po->sk, hlen + tlen + sizeof(struct sockaddr_ll) + - (copylen - dev->hard_header_len), + (copylen - hard_header_len), !need_wait, &err); if (unlikely(skb == NULL)) { @@ -2848,7 +2868,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto out_status; } tp_len = tpacket_fill_skb(po, skb, ph, dev, data, tp_len, proto, - addr, hlen, copylen, &sockc); + addr, hlen, copylen, hard_header_len, + &sockc); if (likely(tp_len >= 0) && tp_len > dev->mtu + reserve && !vnet_hdr_sz && @@ -2956,7 +2977,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) int offset = 0; struct packet_sock *po = pkt_sk(sk); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); - int hlen, tlen, linear; + int hard_header_len, hlen, tlen, linear; int extra_len = 0; /* @@ -2996,8 +3017,9 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_unlock; } + hard_header_len = READ_ONCE(dev->hard_header_len); if (sock->type == SOCK_RAW) - reserve = dev->hard_header_len; + reserve = hard_header_len; if (vnet_hdr_sz) { err = packet_snd_vnet_parse(msg, &len, &vnet_hdr, vnet_hdr_sz); if (err) @@ -3018,10 +3040,10 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_unlock; err = -ENOBUFS; - hlen = LL_RESERVED_SPACE(dev); + hlen = LL_RESERVED_SPACE_EX(dev, hard_header_len); tlen = dev->needed_tailroom; linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len); - linear = max(linear, min_t(int, len, dev->hard_header_len)); + linear = max(linear, min_t(int, len, hard_header_len)); skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear, msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) @@ -3037,7 +3059,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) } else if (reserve) { skb_reserve(skb, -reserve); if (len < reserve + sizeof(struct ipv6hdr) && - dev->min_header_len != dev->hard_header_len) + dev->min_header_len != hard_header_len) skb_reset_network_header(skb); } @@ -4304,7 +4326,7 @@ static __poll_t packet_poll(struct file *file, struct socket *sock, TP_STATUS_KERNEL)) mask |= EPOLLIN | EPOLLRDNORM; } - packet_rcv_try_clear_pressure(po); + __packet_rcv_try_clear_pressure(po); spin_unlock_bh(&sk->sk_receive_queue.lock); spin_lock_bh(&sk->sk_write_queue.lock); if (po->tx_ring.pg_vec) { @@ -4544,14 +4566,14 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, rb->frame_max = (req->tp_frame_nr - 1); rb->head = 0; rb->frame_size = req->tp_frame_size; + po->prot_hook.func = (po->rx_ring.pg_vec) ? + tpacket_rcv : packet_rcv; spin_unlock_bh(&rb_queue->lock); swap(rb->pg_vec_order, order); swap(rb->pg_vec_len, req->tp_block_nr); rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE; - po->prot_hook.func = (po->rx_ring.pg_vec) ? - tpacket_rcv : packet_rcv; skb_queue_purge(rb_queue); if (atomic_long_read(&po->mapped)) pr_err("packet_mmap: vma is busy: %ld\n", diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index e5b2adb161d9..c5e7e01db249 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -78,7 +78,7 @@ struct qrtr_node { */ #define QRTR_NS_MAX_NODES 512 #define QRTR_NS_MAX_SERVERS 256 -#define QRTR_NS_MAX_LOOKUPS 64 +#define QRTR_NS_MAX_LOOKUPS 128 static u16 node_count; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index be535a261fa0..e250969c84ac 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -840,8 +840,15 @@ static int tcf_ct_ipv6_is_fragment(struct sk_buff *skb, bool *frag) return 0; } +/* On error, tells the caller whether it still owns @skb and must free it + * itself. @skb is ours only when the header checks below reject the packet + * before it is handed to the defragmentation engine; once nf_ct_handle_ + * fragments() has been called the skb is either queued (-EINPROGRESS) or has + * already been freed by it. + */ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, - u8 family, u16 zone, bool *defrag) + u8 family, u16 zone, bool *defrag, + bool *skb_is_ours) { enum ip_conntrack_info ctinfo; struct tc_skb_cb cb; @@ -859,8 +866,12 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, err = tcf_ct_ipv4_is_fragment(skb, &frag); else err = tcf_ct_ipv6_is_fragment(skb, &frag); - if (err || !frag) + if (err) { + *skb_is_ours = true; return err; + } + if (!frag) + return 0; cb = *tc_skb_cb(skb); err = nf_ct_handle_fragments(net, skb, zone, family, &proto, &cb.mru); @@ -977,6 +988,7 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, int nh_ofs, err, retval; struct tcf_ct_params *p; bool add_helper = false; + bool skb_is_ours = false; bool skip_add = false; bool defrag = false; struct nf_conn *ct; @@ -1012,9 +1024,18 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, */ nh_ofs = skb_network_offset(skb); skb_pull_rcsum(skb, nh_ofs); - err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag); - if (err) + err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag, + &skb_is_ours); + if (err) { + /* The skb is still ours only when the header checks rejected + * it; returning TC_ACT_CONSUMED for such a packet would leak + * it, since no caller frees an skb it was told it no longer + * owns. + */ + if (skb_is_ours) + goto drop; goto out_frag; + } err = nf_ct_skb_network_trim(skb, family); if (err) diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index e949280eb800..565860cccba6 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -89,6 +89,11 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, p_parm = nla_data(tb[TCA_GACT_PROB]); if (p_parm->ptype >= MAX_RAND) return -EINVAL; + if (!tcf_action_valid(p_parm->paction)) { + NL_SET_ERR_MSG(extack, + "invalid fallback control action"); + return -EINVAL; + } if (TC_ACT_EXT_CMP(p_parm->paction, TC_ACT_GOTO_CHAIN)) { NL_SET_ERR_MSG(extack, "goto chain not allowed on fallback"); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 12ea9e5a6005..837dc42457a6 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -128,6 +128,12 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, if (tb[TCA_POLICE_RESULT]) { tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); + if (!tcf_action_valid(tcfp_result)) { + NL_SET_ERR_MSG(extack, + "invalid fallback control action"); + err = -EINVAL; + goto failure; + } if (TC_ACT_EXT_CMP(tcfp_result, TC_ACT_GOTO_CHAIN)) { NL_SET_ERR_MSG(extack, "goto chain not allowed on fallback"); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index fee4524adc98..4e6a2812a4f3 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -443,7 +443,22 @@ static void tcf_chain_put(struct tcf_chain *chain); static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held, bool sig_destroy, struct netlink_ext_ack *extack) { - tp->ops->destroy(tp, rtnl_held, extack); + /* A locked classifier's destroy callback (e.g. u32_destroy) uses + * rtnl_dereference() and mutates shared structures (e.g. the + * tc_u_common hash list) that are only safe under rtnl_lock. When an + * unlocked classifier's request (e.g. flower on ingress) loses the + * tcf_chain_tp_insert_unique() race and ends up dropping the last + * reference on a locked classifier's proto, destroy() would run + * without rtnl held. Take it here in that case. + */ + bool not_lockless = !rtnl_held && + !(tp->ops->flags & TCF_PROTO_OPS_DOIT_UNLOCKED); + + if (not_lockless) + rtnl_lock(); + tp->ops->destroy(tp, rtnl_held || not_lockless, extack); + if (not_lockless) + rtnl_unlock(); tcf_proto_count_usesw(tp, false); if (sig_destroy) tcf_proto_signal_destroyed(tp->chain, tp); diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index bd6f945bd388..eded7aacd3f7 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -52,6 +52,7 @@ struct route4_filter { struct tcf_result res; struct tcf_exts exts; u32 handle; + bool dying; struct route4_bucket *bkt; struct tcf_proto *tp; struct rcu_work rwork; @@ -66,9 +67,11 @@ static inline int route4_fastmap_hash(u32 id, int iif) static DEFINE_SPINLOCK(fastmap_lock); static void -route4_reset_fastmap(struct route4_head *head) +route4_reset_fastmap(struct route4_head *head, struct route4_filter *f) { spin_lock_bh(&fastmap_lock); + if (f) + f->dying = true; memset(head->fastmap, 0, sizeof(head->fastmap)); spin_unlock_bh(&fastmap_lock); } @@ -81,9 +84,11 @@ route4_set_fastmap(struct route4_head *head, u32 id, int iif, /* fastmap updates must look atomic to aling id, iff, filter */ spin_lock_bh(&fastmap_lock); - head->fastmap[h].id = id; - head->fastmap[h].iif = iif; - head->fastmap[h].filter = f; + if (f == ROUTE4_FAILURE || !f->dying) { + head->fastmap[h].id = id; + head->fastmap[h].iif = iif; + head->fastmap[h].filter = f; + } spin_unlock_bh(&fastmap_lock); } @@ -297,6 +302,13 @@ static void route4_destroy(struct tcf_proto *tp, bool rtnl_held, next = rtnl_dereference(f->next); RCU_INIT_POINTER(b->ht[h2], next); tcf_unbind_filter(tp, &f->res); + /* Mark the filter dying under fastmap_lock so + * any in-flight reader that still holds it + * will skip the republish in route4_set_fastmap(). + */ + spin_lock_bh(&fastmap_lock); + f->dying = true; + spin_unlock_bh(&fastmap_lock); if (tcf_exts_get_net(&f->exts)) route4_queue_work(f); else @@ -307,6 +319,11 @@ static void route4_destroy(struct tcf_proto *tp, bool rtnl_held, kfree_rcu(b, rcu); } } + + /* All filters are unlinked and marked dying, so no in-flight + * reader can republish a stale entry after this reset. + */ + route4_reset_fastmap(head, NULL); kfree_rcu(head, rcu); } @@ -334,11 +351,11 @@ static int route4_delete(struct tcf_proto *tp, void *arg, bool *last, /* unlink it */ RCU_INIT_POINTER(*fp, rtnl_dereference(f->next)); - /* Remove any fastmap lookups that might ref filter - * notice we unlink'd the filter so we can't get it - * back in the fastmap. + /* Clear any fastmap entries that may ref this filter and + * mark it dying so in-flight readers can't republish it + * after the reset. */ - route4_reset_fastmap(head); + route4_reset_fastmap(head, f); /* Delete it */ tcf_unbind_filter(tp, &f->res); @@ -558,7 +575,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, } } - route4_reset_fastmap(head); + route4_reset_fastmap(head, fold); *arg = f; if (fold) { tcf_unbind_filter(tp, &fold->res); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 487cbfdc5655..d90f41817b11 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1110,6 +1110,9 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, unsigned int i, num_q, ingress; struct netdev_queue *dev_queue; + if (new) + new->depth = 0; + ingress = 0; num_q = dev->num_tx_queues; if ((q && q->flags & TCQ_F_INGRESS) || @@ -1207,9 +1210,15 @@ skip: NL_SET_ERR_MSG(extack, "STAB not supported on a non root"); return -EINVAL; } + if (new && parent->depth >= 7) { + NL_SET_ERR_MSG(extack, "Qdisc hierarchy is too deep"); + return -E2BIG; + } err = cops->graft(parent, cl, new, &old, extack); if (err) return err; + if (new) + new->depth = parent->depth + 1; notify_and_destroy(net, skb, n, classid, old, new, extack); } return 0; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 8965fe252471..755c42c32bcf 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1287,7 +1287,6 @@ static struct sk_buff *cake_ack_filter(struct cake_sched_data *q, seglen = ipv6_payload_len(skb, ipv6h_check); } else { - WARN_ON(1); /* shouldn't happen */ continue; } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index b6ac0966420a..5be0bed2685e 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -543,6 +543,9 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc, asoc->addip_last_asconf->transport == peer) asoc->addip_last_asconf->transport = NULL; + if (asoc->new_transport == peer) + asoc->new_transport = NULL; + /* If we have something on the transmitted list, we have to * save it off. The best place is the active path. */ @@ -573,6 +576,10 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc, if (ch->transport == peer) ch->transport = NULL; + list_for_each_entry(ch, &asoc->outqueue.control_chunk_list, list) + if (ch->transport == peer) + ch->transport = NULL; + asoc->peer.transport_count--; sctp_ulpevent_notify_peer_addr_change(peer, SCTP_ADDR_REMOVED, 0); @@ -1709,6 +1716,8 @@ void sctp_asconf_queue_teardown(struct sctp_association *asoc) sctp_assoc_free_asconf_queue(asoc); /* Free any cached ASCONF chunk. */ - if (asoc->addip_last_asconf) + if (asoc->addip_last_asconf) { sctp_chunk_free(asoc->addip_last_asconf); + asoc->addip_last_asconf = NULL; + } } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index f6b8c13dafa4..e92fb9da4647 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -650,6 +650,7 @@ static int __sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, if (chunk->tsn_gap_acked) { list_move_tail(&chunk->transmitted_list, &transport->transmitted); + chunk->transport = transport; continue; } diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 0ae30c3c8913..e25612e9d082 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3336,12 +3336,11 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, goto done; } done: - asoc->peer.addip_serial++; - /* If we are sending a new ASCONF_ACK hold a reference to it in assoc * after freeing the reference to old asconf ack if any. */ if (asconf_ack) { + asoc->peer.addip_serial++; sctp_chunk_hold(asconf_ack); list_add_tail(&asconf_ack->transmitted_list, &asoc->asconf_ack_list); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 708fa07d5fff..3a8e16b29660 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -6145,8 +6145,12 @@ enum sctp_disposition sctp_sf_t4_timer_expire( struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = asoc->addip_last_asconf; - struct sctp_transport *transport = chunk->transport; + struct sctp_transport *transport; + + if (!chunk) + return SCTP_DISPOSITION_CONSUME; + transport = chunk->transport; SCTP_INC_STATS(net, SCTP_MIB_T4_RTO_EXPIREDS); /* ADDIP 4.1 B1) Increment the error counters and perform path failure diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index b5db69073e20..00403175b740 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1931,11 +1931,12 @@ static void smc_listen_out(struct smc_sock *new_smc) atomic_dec(&lsmc->queued_smc_hs); release_sock(newsmcsk); /* lock in smc_listen_work() */ + lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); if (lsmc->sk.sk_state == SMC_LISTEN) { - lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); smc_accept_enqueue(&lsmc->sk, newsmcsk); release_sock(&lsmc->sk); } else { /* no longer listening */ + release_sock(&lsmc->sk); smc_close_non_accepted(newsmcsk); } diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 954b2ff1815c..aa6d83af55ed 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -1927,7 +1927,8 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) return; case SMC_LLC_CONFIRM_LINK: case SMC_LLC_ADD_LINK_CONT: - if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { + if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE && + !lgr->llc_flow_lcl.qentry) { /* a flow is waiting for this message */ smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, qentry); wake_up(&lgr->llc_msg_waiter); diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index c1d9b923938d..5c9e4d8b57de 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -150,7 +150,12 @@ static const struct pipe_buf_operations smc_pipe_ops = { static void smc_rx_spd_release(struct splice_pipe_desc *spd, unsigned int i) { + struct smc_spd_priv *priv = (struct smc_spd_priv *)spd->partial[i].private; + struct sock *sk = &priv->smc->sk; + + kfree(priv); put_page(spd->pages[i]); + sock_put(sk); } static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len, @@ -209,6 +214,10 @@ static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len, offset = 0; } } + for (i = 0; i < nr_pages; i++) { + get_page(pages[i]); + sock_hold(&smc->sk); + } spd.nr_pages_max = nr_pages; spd.nr_pages = nr_pages; spd.pages = pages; @@ -217,16 +226,8 @@ static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len, spd.spd_release = smc_rx_spd_release; bytes = splice_to_pipe(pipe, &spd); - if (bytes > 0) { - sock_hold(&smc->sk); - if (!lgr->is_smcd && smc->conn.rmb_desc->is_vm) { - for (i = 0; i < PAGE_ALIGN(bytes + offset) / PAGE_SIZE; i++) - get_page(pages[i]); - } else { - get_page(smc->conn.rmb_desc->pages); - } + if (bytes > 0) atomic_add(bytes, &smc->conn.splice_pending); - } kfree(priv); kfree(partial); kfree(pages); diff --git a/net/tipc/node.c b/net/tipc/node.c index 8e4ef2630ae4..683a136e53ef 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1061,18 +1061,23 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id, static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete) { - struct tipc_link_entry *le = &n->links[bearer_id]; struct tipc_media_addr *maddr = NULL; - struct tipc_link *l = le->link; int old_bearer_id = bearer_id; + struct tipc_link_entry *le; struct sk_buff_head xmitq; - - if (!l) - return; + struct tipc_link *l; __skb_queue_head_init(&xmitq); + /* Synchronize the link lookup with bearer teardown. */ tipc_node_write_lock(n); + le = &n->links[bearer_id]; + l = le->link; + if (!l) { + tipc_node_write_unlock_fast(n); + return; + } + if (!tipc_link_is_establishing(l)) { __tipc_node_link_down(n, &bearer_id, &xmitq, &maddr); } else { diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index ba95f9d927a3..e9aea371331b 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -458,7 +458,7 @@ int tls_tx_records(struct sock *sk, int flags) } tx_err: - if (rc < 0 && rc != -EAGAIN) + if (rc < 0 && rc != -EAGAIN && rc != -EINTR && rc != -ERESTARTSYS) tls_err_abort(sk, rc); return rc; @@ -1116,6 +1116,14 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg, if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; + /* open record may be full if we couldn't push it in the last sendmsg call */ + if (sk_msg_full(msg_pl)) { + full_record = true; + sk_msg_trim(sk, msg_en, + msg_pl->sg.size + prot->overhead_size); + goto copied; + } + alloc_encrypted: ret = tls_alloc_encrypted_msg(sk, required_size); if (ret) { @@ -1216,6 +1224,12 @@ fallback_to_reg_send: msg_pl, try_to_copy); if (ret < 0) goto trim_sgl; + + if (sk_msg_full(msg_pl)) { + full_record = true; + sk_msg_trim(sk, msg_en, + msg_pl->sg.size + prot->overhead_size); + } } /* Open records defined only if successfully copied, otherwise @@ -1731,6 +1745,8 @@ tls_decrypt_sw(struct sock *sk, struct tls_context *tls_ctx, /* If opportunistic TLS 1.3 ZC failed retry without ZC */ if (unlikely(darg->zc && prot->version == TLS_1_3_VERSION && darg->tail != TLS_RECORD_TYPE_DATA)) { + iov_iter_revert(&msg->msg_iter, strp_msg(darg->skb)->full_len - + prot->overhead_size); darg->zc = false; if (!darg->tail) TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXNOPADVIOL); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 57f2d6ec3ffc..96c9fe8d357c 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -346,12 +346,13 @@ static void virtio_transport_tx_work(struct work_struct *work) struct virtqueue *vq; bool added = false; - vq = vsock->vqs[VSOCK_VQ_TX]; mutex_lock(&vsock->tx_lock); if (!vsock->tx_run) goto out; + vq = vsock->vqs[VSOCK_VQ_TX]; + do { struct sk_buff *skb; unsigned int len; @@ -451,13 +452,13 @@ static void virtio_transport_event_work(struct work_struct *work) container_of(work, struct virtio_vsock, event_work); struct virtqueue *vq; - vq = vsock->vqs[VSOCK_VQ_EVENT]; - mutex_lock(&vsock->event_lock); if (!vsock->event_run) goto out; + vq = vsock->vqs[VSOCK_VQ_EVENT]; + do { struct virtio_vsock_event *event; unsigned int len; @@ -634,12 +635,12 @@ static void virtio_transport_rx_work(struct work_struct *work) container_of(work, struct virtio_vsock, rx_work); struct virtqueue *vq; - vq = vsock->vqs[VSOCK_VQ_RX]; - mutex_lock(&vsock->rx_lock); if (!vsock->rx_run) - goto out; + goto out_nofill; + + vq = vsock->vqs[VSOCK_VQ_RX]; do { virtqueue_disable_cb(vq); @@ -691,6 +692,7 @@ static void virtio_transport_rx_work(struct work_struct *work) out: if (vsock->rx_buf_nr < vsock->rx_buf_max_nr / 2) virtio_vsock_rx_fill(vsock); +out_nofill: mutex_unlock(&vsock->rx_lock); } diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index f9758c140ba4..e8c4f51035f6 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -362,6 +362,7 @@ static void x25_destroy_timer(struct timer_list *t) struct sock *sk = timer_container_of(sk, t, sk_timer); x25_destroy_socket_from_timer(sk); + sock_put(sk); } /* @@ -397,9 +398,8 @@ static void __x25_destroy_socket(struct sock *sk) if (sk_has_allocations(sk)) { /* Defer: outstanding buffers */ - sk->sk_timer.expires = jiffies + 10 * HZ; sk->sk_timer.function = x25_destroy_timer; - add_timer(&sk->sk_timer); + sk_reset_timer(sk, &sk->sk_timer, jiffies + 10 * HZ); } else { /* drop last reference so sock_put will free */ __sock_put(sk); diff --git a/net/x25/x25_timer.c b/net/x25/x25_timer.c index 2ec63a1f4c6d..7896cd43f1cc 100644 --- a/net/x25/x25_timer.c +++ b/net/x25/x25_timer.c @@ -36,45 +36,45 @@ void x25_init_timers(struct sock *sk) void x25_start_heartbeat(struct sock *sk) { - mod_timer(&sk->sk_timer, jiffies + 5 * HZ); + sk_reset_timer(sk, &sk->sk_timer, jiffies + 5 * HZ); } void x25_stop_heartbeat(struct sock *sk) { - timer_delete(&sk->sk_timer); + sk_stop_timer(sk, &sk->sk_timer); } void x25_start_t2timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); - mod_timer(&x25->timer, jiffies + x25->t2); + sk_reset_timer(sk, &x25->timer, jiffies + x25->t2); } void x25_start_t21timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); - mod_timer(&x25->timer, jiffies + x25->t21); + sk_reset_timer(sk, &x25->timer, jiffies + x25->t21); } void x25_start_t22timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); - mod_timer(&x25->timer, jiffies + x25->t22); + sk_reset_timer(sk, &x25->timer, jiffies + x25->t22); } void x25_start_t23timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); - mod_timer(&x25->timer, jiffies + x25->t23); + sk_reset_timer(sk, &x25->timer, jiffies + x25->t23); } void x25_stop_timer(struct sock *sk) { - timer_delete(&x25_sk(sk)->timer); + sk_stop_timer(sk, &x25_sk(sk)->timer); } unsigned long x25_display_timer(struct sock *sk) @@ -108,7 +108,7 @@ static void x25_heartbeat_expiry(struct timer_list *t) sock_flag(sk, SOCK_DEAD))) { bh_unlock_sock(sk); x25_destroy_socket_from_timer(sk); - return; + goto out; } break; @@ -120,8 +120,14 @@ static void x25_heartbeat_expiry(struct timer_list *t) break; } restart_heartbeat: - x25_start_heartbeat(sk); + /* Do not rearm once __x25_destroy_socket() has unlinked the socket: + * it is past its cancel point and owns the teardown from there on. + */ + if (sk_hashed(sk)) + x25_start_heartbeat(sk); bh_unlock_sock(sk); +out: + sock_put(sk); } /* @@ -166,4 +172,5 @@ static void x25_timer_expiry(struct timer_list *t) } else x25_do_timer_expiry(sk); bh_unlock_sock(sk); + sock_put(sk); } diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 58da2f4f4397..cd8643360eb3 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -210,6 +210,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (mr->flags & XDP_UMEM_TX_METADATA_LEN) { if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8) return -EINVAL; + if (mr->tx_metadata_len < 16) + return -EINVAL; umem->tx_metadata_len = mr->tx_metadata_len; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 855fe92358ba..95a9ff3d0bdb 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -966,15 +966,16 @@ static int xsk_skb_metadata(struct sk_buff *skb, void *buffer, { struct xsk_tx_metadata *meta = NULL; u16 csum_start, csum_offset; + u64 flags; if (unlikely(pool->tx_metadata_len == 0)) return -EINVAL; meta = buffer - pool->tx_metadata_len; - if (unlikely(!xsk_buff_valid_tx_metadata(meta))) + if (unlikely(!xsk_buff_valid_tx_metadata(pool, meta, &flags))) return -EINVAL; - if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) { + if (flags & XDP_TXMD_FLAGS_CHECKSUM) { csum_start = READ_ONCE(meta->request.csum_start); csum_offset = READ_ONCE(meta->request.csum_offset); @@ -995,8 +996,10 @@ static int xsk_skb_metadata(struct sk_buff *skb, void *buffer, } } - if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME) - skb->skb_mstamp_ns = meta->request.launch_time; + if (flags & XDP_TXMD_FLAGS_LAUNCH_TIME) + skb->skb_mstamp_ns = READ_ONCE(meta->request.launch_time); + if (!(flags & XDP_TXMD_FLAGS_TIMESTAMP)) + meta = NULL; xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta); return 0; diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 4538223f4408..f72042260777 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -765,11 +765,11 @@ EXPORT_SYMBOL(xp_raw_get_dma); * @addr: desc address (from userspace) * * Helper for getting desc's DMA address and metadata pointer, if present. - * Saves one call on hotpath, double calculation of the actual address, - * and inline checks for metadata presence and sanity. + * Saves one call on hotpath and double calculation of the actual address. + * Metadata is validated later by xsk_tx_metadata_request(). * * Return: new &xdp_desc_ctx struct containing desc's DMA address and metadata - * pointer, if it is present and valid (initialized to %NULL otherwise). + * pointer, if it is present (initialized to %NULL otherwise). */ struct xdp_desc_ctx xp_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr) { diff --git a/samples/damon/mtier.c b/samples/damon/mtier.c index 7f84367ad3e5..a26cdfa73f1d 100644 --- a/samples/damon/mtier.c +++ b/samples/damon/mtier.c @@ -154,6 +154,9 @@ static struct damon_ctx *damon_sample_mtier_build_ctx(bool promote) if (!scheme) goto free_out; damon_set_schemes(ctx, &scheme, 1); + /* zero target value causes division by zero in damos_quota_store() */ + if (!node0_mem_used_bp || !node0_mem_free_bp) + goto free_out; quota_goal = damos_new_quota_goal( promote ? DAMOS_QUOTA_NODE_MEM_USED_BP : DAMOS_QUOTA_NODE_MEM_FREE_BP, diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 2dd231567710..c509abd75fbe 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -269,8 +269,13 @@ static int xattr_verify(enum ima_hooks func, struct ima_iint_cache *iint, } else { set_bit(IMA_DIGSIG, &iint->atomic_flags); } - if (xattr_len - sizeof(xattr_value->type) - hash_start >= - iint->ima_hash->length) + /* + * Use addition, not subtraction: sizeof() forces unsigned + * math and a short xattr_len would wrap around, bypassing + * this bounds check. + */ + if (xattr_len >= (int)sizeof(xattr_value->type) + hash_start + + (int)iint->ima_hash->length) /* * xattr length may be longer. md5 hash in previous * version occupied 20 bytes in xattr, instead of 16 diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 5cea53fc36df..ff52becc3031 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -687,6 +687,43 @@ static int ima_file_check(struct file *file, int mask) MAY_APPEND), FILE_CHECK, 0, false); } +/* + * ima_reset_action_flags - invalidate action flags after a content change + * @inode: inode of the file whose content is about to be truncated + * + * Clear IMA_DONE_MASK so the file is re-collected, re-measured, + * re-audited, and re-appraised on next access. + */ +static void ima_reset_action_flags(struct inode *inode) +{ + struct ima_iint_cache *iint; + + if (!ima_policy_flag || !S_ISREG(inode->i_mode)) + return; + + iint = ima_iint_find(inode); + if (!iint) + return; + + mutex_lock(&iint->mutex); + iint->flags &= ~IMA_DONE_MASK; + iint->measured_pcrs = 0; + mutex_unlock(&iint->mutex); + return; +} + +static int ima_path_truncate(const struct path *path) +{ + ima_reset_action_flags(path->dentry->d_inode); + return 0; +} + +static int ima_file_truncate(struct file *file) +{ + ima_reset_action_flags(file_inode(file)); + return 0; +} + static int __ima_inode_hash(struct inode *inode, struct file *file, char *buf, size_t buf_size) { @@ -1300,11 +1337,13 @@ static struct security_hook_list ima_hooks[] __ro_after_init = { LSM_HOOK_INIT(file_release, ima_file_free), LSM_HOOK_INIT(mmap_file, ima_file_mmap), LSM_HOOK_INIT(file_mprotect, ima_file_mprotect), + LSM_HOOK_INIT(file_truncate, ima_file_truncate), LSM_HOOK_INIT(kernel_load_data, ima_load_data), LSM_HOOK_INIT(kernel_post_load_data, ima_post_load_data), LSM_HOOK_INIT(kernel_read_file, ima_read_file), LSM_HOOK_INIT(kernel_post_read_file, ima_post_read_file), LSM_HOOK_INIT(path_post_mknod, ima_post_path_mknod), + LSM_HOOK_INIT(path_truncate, ima_path_truncate), #ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS LSM_HOOK_INIT(key_post_create_or_update, ima_post_key_create_or_update), #endif diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_spi.c b/sound/hda/codecs/side-codecs/tas2781_hda_spi.c index d243baff95a7..5b38e4e9f228 100644 --- a/sound/hda/codecs/side-codecs/tas2781_hda_spi.c +++ b/sound/hda/codecs/side-codecs/tas2781_hda_spi.c @@ -344,6 +344,8 @@ static int tas2781_read_acpi(struct tas2781_hda *tas_hda, strscpy(p->dev_name, hid, sizeof(p->dev_name)); physdev = get_device(acpi_get_first_physical_node(adev)); acpi_dev_put(adev); + if (!physdev) + return -ENODEV; property = "ti,dev-index"; ret = device_property_count_u32(physdev, property); @@ -386,7 +388,6 @@ static int tas2781_read_acpi(struct tas2781_hda *tas_hda, err: dev_err(p->dev, "read acpi error, ret: %d\n", ret); put_device(physdev); - acpi_dev_put(adev); return ret; } diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index dca06ba1c67e..a1d449f2a342 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -385,13 +385,15 @@ static int prepare_inbound_urb(struct snd_usb_endpoint *ep, case SND_USB_ENDPOINT_TYPE_DATA: offs = 0; for (i = 0; i < urb_ctx->packets; i++) { + if (offs + ep->curpacksize > urb_ctx->buffer_size) + break; urb->iso_frame_desc[i].offset = offs; urb->iso_frame_desc[i].length = ep->curpacksize; offs += ep->curpacksize; } urb->transfer_buffer_length = offs; - urb->number_of_packets = urb_ctx->packets; + urb->number_of_packets = i; break; case SND_USB_ENDPOINT_TYPE_SYNC: @@ -1243,10 +1245,10 @@ static int data_ep_set_params(struct snd_usb_endpoint *ep) u->index = i; u->ep = ep; u->packets = urb_packs; - u->buffer_size = maxsize * u->packets; if (fmt->fmt_type == UAC_FORMAT_TYPE_II) u->packets++; /* for transfer delimiter */ + u->buffer_size = maxsize * u->packets; u->urb = usb_alloc_urb(u->packets, GFP_KERNEL); if (!u->urb) goto out_of_memory; diff --git a/sound/usb/fcp.c b/sound/usb/fcp.c index c45dbe4d4532..ec1ddfa4d0ce 100644 --- a/sound/usb/fcp.c +++ b/sound/usb/fcp.c @@ -129,6 +129,10 @@ struct fcp_data { #define FCP_SEGMENT_APP_GOLD 0 +#define FCP_MAX_METER_MAP_SIZE \ + (sizeof_field(struct snd_ctl_elem_value, value.integer.value) / \ + sizeof(long)) + /* Forward declarations */ static int fcp_init(struct usb_mixer_interface *mixer, void *step0_resp, void *step2_resp); @@ -410,6 +414,9 @@ static int fcp_meter_ctl_get(struct snd_kcontrol *kctl, if (err < 0) return err; + if (WARN_ON_ONCE(elem->channels > FCP_MAX_METER_MAP_SIZE)) + return -EINVAL; + /* copy & translate from resp[] using meter_level_map[] */ for (i = 0; i < elem->channels; i++) { int idx = private->meter_level_map[i]; @@ -636,7 +643,8 @@ static int fcp_ioctl_set_meter_map(struct usb_mixer_interface *mixer, } /* Validate the map size */ - if (map.map_size < 1 || map.map_size > 255 || + if (map.map_size < 1 || + map.map_size > FCP_MAX_METER_MAP_SIZE || map.meter_slots < 1 || map.meter_slots > 255) return -EINVAL; diff --git a/sound/usb/midi2.c b/sound/usb/midi2.c index 83980fb83ac8..1dc78f536ef9 100644 --- a/sound/usb/midi2.c +++ b/sound/usb/midi2.c @@ -677,6 +677,14 @@ static int parse_midi_2_0_endpoints(struct snd_usb_midi2_interface *umidi) return 0; } +static void free_ump_private_data(struct snd_ump_endpoint *ump) +{ + struct snd_usb_midi2_ump *rmidi = ump->private_data; + + if (rmidi) + rmidi->ump = NULL; +} + static void free_all_midi2_umps(struct snd_usb_midi2_interface *umidi) { struct snd_usb_midi2_ump *rmidi; @@ -727,6 +735,7 @@ static int create_midi2_ump(struct snd_usb_midi2_interface *umidi, ump->private_data = rmidi; ump->ops = &snd_usb_midi_v2_ump_ops; + ump->private_free = free_ump_private_data; rmidi->eps[STR_IN] = ep_in; rmidi->eps[STR_OUT] = ep_out; diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index dbcefcaf7c36..142f5ca7a72d 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -434,6 +434,11 @@ int snd_usb_get_cur_mix_value(struct usb_mixer_elem_info *cval, *value = cval->cache_val[index]; return 0; } + + /* The current value is always provided by the cache after initialization. */ + if (cval->get_cur_broken) + return -ENXIO; + err = get_cur_mix_raw(cval, channel, value); if (err < 0) { if (!cval->head.mixer->ignore_ctl_error) @@ -1234,7 +1239,7 @@ static void init_cur_mix_raw(struct usb_mixer_elem_info *cval, int ch, int idx) err = snd_usb_get_cur_mix_value(cval, ch, idx, &val); if (!err) return; - if (!cval->head.mixer->ignore_ctl_error) + if (!cval->head.mixer->ignore_ctl_error && !cval->get_cur_broken) usb_audio_warn(cval->head.mixer->chip, "%d:%d: failed to get current value for ch %d (%d)\n", cval->head.id, mixer_ctrl_intf(cval->head.mixer), @@ -1248,8 +1253,16 @@ static void init_cur_mix_raw(struct usb_mixer_elem_info *cval, int ch, int idx) * Some devices' volume control mixers are sticky, which accept SET_CUR but * do absolutely nothing. * - * Prevent sticky mixers from being registered, otherwise they confuses - * userspace and results in ineffective volume control. + * Check the return values of GET_CUR with different SET_CUR values. Consider + * the mixer as sticky if GET_CUR always returns a constant value. + * + * Some devices have effective SET_CUR despite GET_CUR being constant. Do not + * consider the mixer as sticky if a quirk flag indicates that. + * + * Gate the registration of sticky mixers to prevent confusing userspace, so + * that they won't cause ineffective volume control. However, for mixers with + * effective SET_CUR but broken GET_CUR, the registration can continue normally + * but further GET_CUR requests will be gated. */ static int check_sticky_volume_control(struct usb_mixer_elem_info *cval, int channel, int saved) @@ -1269,10 +1282,22 @@ static int check_sticky_volume_control(struct usb_mixer_elem_info *cval, return 0; } + if (cval->head.mixer->chip->quirk_flags & QUIRK_FLAG_MIXER_GET_CUR_BROKEN) { + usb_audio_info(cval->head.mixer->chip, + "%d:%d: broken mixer GET_CUR (%d/%d/%d => %d)\n", + cval->head.id, mixer_ctrl_intf(cval->head.mixer), + cval->min, cval->max, cval->res, saved); + + cval->get_cur_broken = 1; + return -ENXIO; + } + usb_audio_err(cval->head.mixer->chip, "%d:%d: sticky mixer values (%d/%d/%d => %d), disabling\n", cval->head.id, mixer_ctrl_intf(cval->head.mixer), cval->min, cval->max, cval->res, saved); + usb_audio_info(cval->head.mixer->chip, + "check MIXER_GET_CUR_BROKEN if you believe the mixer is non-sticky"); return -ENODEV; } @@ -1315,7 +1340,7 @@ static void check_volume_control_res(struct usb_mixer_elem_info *cval, static int get_min_max_with_quirks(struct usb_mixer_elem_info *cval, int default_min, struct snd_kcontrol *kctl) { - int i, idx, ret; + int i, idx, ret = 0; /* for failsafe */ cval->min = default_min; @@ -1371,8 +1396,10 @@ static int get_min_max_with_quirks(struct usb_mixer_elem_info *cval, goto no_checks; ret = check_sticky_volume_control(cval, minchn, saved); - if (ret < 0) + if (ret == -ENODEV) goto sticky; + if (ret) + goto no_checks; if (cval->min + cval->res < cval->max) check_volume_control_res(cval, minchn, saved); @@ -1381,6 +1408,16 @@ static int get_min_max_with_quirks(struct usb_mixer_elem_info *cval, } no_checks: + /* + * Got a non-fatal failure during sanity checks. + * + * Do not propagate mixer values written by sanity checks. + * Instead, rely on init_cur_mix_raw() to initialize the mixer + * properly. + */ + if (ret) + cval->cached = 0; + cval->initialized = 1; } @@ -3538,7 +3575,8 @@ void snd_usb_mixer_notify_id(struct usb_mixer_interface *mixer, int unitid) continue; info = mixer_elem_list_to_info(list); /* invalidate cache, so the value is read from the device */ - info->cached = 0; + if (!info->get_cur_broken) + info->cached = 0; snd_ctl_notify(mixer->chip->card, SNDRV_CTL_EVENT_MASK_VALUE, &list->kctl->id); } @@ -3635,10 +3673,12 @@ static void snd_usb_mixer_interrupt_v2(struct usb_mixer_interface *mixer, switch (attribute) { case UAC2_CS_CUR: /* invalidate cache, so the value is read from the device */ - if (channel) - info->cached &= ~BIT(channel); - else /* master channel */ - info->cached = 0; + if (!info->get_cur_broken) { + if (channel) + info->cached &= ~BIT(channel); + else /* master channel */ + info->cached = 0; + } snd_ctl_notify(mixer->chip->card, SNDRV_CTL_EVENT_MASK_VALUE, &info->head.kctl->id); diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h index afbb3dd9f177..3fa1bd96f858 100644 --- a/sound/usb/mixer.h +++ b/sound/usb/mixer.h @@ -94,6 +94,7 @@ struct usb_mixer_elem_info { int cache_val[MAX_CHANNELS]; u8 initialized; u8 min_mute; + u8 get_cur_broken; void *private_data; }; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 33eb8be48af8..354866a80605 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2249,6 +2249,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { DEVICE_FLG(0x046d, 0x0a8f, /* Logitech H390 headset */ QUIRK_FLAG_CTL_MSG_DELAY_1M | QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE), + DEVICE_FLG(0x046d, 0x0af7, /* Logitech PRO X 2 LIGHTSPEED */ + QUIRK_FLAG_MIXER_GET_CUR_BROKEN), DEVICE_FLG(0x0499, 0x1506, /* Yamaha THR5 */ QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x0499, 0x1509, /* Steinberg UR22 */ @@ -2318,6 +2320,10 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x0763, 0x2031, /* M-Audio Fast Track C600 */ QUIRK_FLAG_GENERIC_IMPLICIT_FB), + DEVICE_FLG(0x0763, 0x2080, /* M-Audio Fast Track Ultra */ + QUIRK_FLAG_MIXER_GET_CUR_BROKEN | QUIRK_FLAG_GENERIC_IMPLICIT_FB), + DEVICE_FLG(0x0763, 0x2081, /* M-Audio Fast Track Ultra */ + QUIRK_FLAG_MIXER_GET_CUR_BROKEN | QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x07fd, 0x000b, /* MOTU M Series 2nd hardware revision */ QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x08bb, 0x2702, /* LineX FM Transmitter */ @@ -2611,6 +2617,7 @@ static const char *const snd_usb_audio_quirk_flag_names[] = { QUIRK_STRING_ENTRY(MIXER_PLAYBACK_LINEAR_VOL), QUIRK_STRING_ENTRY(MIXER_CAPTURE_LINEAR_VOL), QUIRK_STRING_ENTRY(IFB_SILENCE_ON_EMPTY), + QUIRK_STRING_ENTRY(MIXER_GET_CUR_BROKEN), NULL }; diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h index 9afcad8f143a..e472aef6eb87 100644 --- a/sound/usb/usbaudio.h +++ b/sound/usb/usbaudio.h @@ -242,6 +242,17 @@ extern bool snd_usb_skip_validation; * from snd_usb_handle_sync_urb. Instead fall through and enqueue a * packet_info containing only size-0 packets, so the OUT ring keeps * moving (emits silence). Needed by Behringer Flow 8 (1397:050c). + * QUIRK_FLAG_MIXER_GET_CUR_BROKEN + * Some mixers are sticky, which means that setting their current volume is a + * no-op, and reading the current volume returns a constant value. The sticky + * check disables these mixers to prevent confusing userspace. However, some + * devices do have a tunable volume despite the reported current volume being + * constant. As the sticky check can't distinguish between the two categories, + * setting this flag tells that the device should fall into the second + * category when GET_CUR returns a constant value, resulting in the sticky + * check being non-fatal and only disabling GET_CUR instead of the whole mixer. + * The current volume will then be provided by the internal cache that stores + * the last set volume */ enum { @@ -275,6 +286,7 @@ enum { QUIRK_TYPE_MIXER_PLAYBACK_LINEAR_VOL = 27, QUIRK_TYPE_MIXER_CAPTURE_LINEAR_VOL = 28, QUIRK_TYPE_IFB_SILENCE_ON_EMPTY = 29, + QUIRK_TYPE_MIXER_GET_CUR_BROKEN = 30, /* Please also edit snd_usb_audio_quirk_flag_names */ }; @@ -310,5 +322,6 @@ enum { #define QUIRK_FLAG_MIXER_PLAYBACK_LINEAR_VOL QUIRK_FLAG(MIXER_PLAYBACK_LINEAR_VOL) #define QUIRK_FLAG_MIXER_CAPTURE_LINEAR_VOL QUIRK_FLAG(MIXER_CAPTURE_LINEAR_VOL) #define QUIRK_FLAG_IFB_SILENCE_ON_EMPTY QUIRK_FLAG(IFB_SILENCE_ON_EMPTY) +#define QUIRK_FLAG_MIXER_GET_CUR_BROKEN QUIRK_FLAG(MIXER_GET_CUR_BROKEN) #endif /* __USBAUDIO_H */ diff --git a/sound/usb/usx2y/us144mkii_capture.c b/sound/usb/usx2y/us144mkii_capture.c index fa01da98151a..d7cdf9e0f685 100644 --- a/sound/usb/usx2y/us144mkii_capture.c +++ b/sound/usb/usx2y/us144mkii_capture.c @@ -302,6 +302,7 @@ void capture_urb_complete(struct urb *urb) } usb_get_urb(urb); + usb_anchor_urb(urb, &tascam->capture_anchor); ret = usb_submit_urb(urb, GFP_ATOMIC); if (ret < 0) { dev_err_ratelimited(tascam->card->dev, diff --git a/sound/usb/usx2y/usX2Yhwdep.c b/sound/usb/usx2y/usX2Yhwdep.c index 4d7925184826..7f153a2fcdd8 100644 --- a/sound/usb/usx2y/usX2Yhwdep.c +++ b/sound/usb/usx2y/usX2Yhwdep.c @@ -25,6 +25,8 @@ static vm_fault_t snd_us428ctls_vm_fault(struct vm_fault *vmf) void *vaddr; offset = vmf->pgoff << PAGE_SHIFT; + if (offset >= US428_SHAREDMEM_PAGES) + return VM_FAULT_SIGBUS; vaddr = (char *)((struct usx2ydev *)vmf->vma->vm_private_data)->us428ctls_sharedmem + offset; page = virt_to_page(vaddr); get_page(page); diff --git a/sound/usb/usx2y/usx2yhwdeppcm.c b/sound/usb/usx2y/usx2yhwdeppcm.c index 7c90214485d9..f1d5b4b797ad 100644 --- a/sound/usb/usx2y/usx2yhwdeppcm.c +++ b/sound/usb/usx2y/usx2yhwdeppcm.c @@ -672,6 +672,8 @@ static vm_fault_t snd_usx2y_hwdep_pcm_vm_fault(struct vm_fault *vmf) void *vaddr; offset = vmf->pgoff << PAGE_SHIFT; + if (offset >= USX2Y_HWDEP_PCM_PAGES) + return VM_FAULT_SIGBUS; vaddr = (char *)((struct usx2ydev *)vmf->vma->vm_private_data)->hwdep_pcm_shm + offset; vmf->page = virt_to_page(vaddr); get_page(vmf->page); diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index d2846579285f..b4019d1a5575 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -807,7 +807,7 @@ static void test_sockmap_many_socket(void) return; } - udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0); + udp = socket_loopback(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK); if (udp < 0) { close(dgram); close(tcp); @@ -876,7 +876,7 @@ static void test_sockmap_many_maps(void) return; } - udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0); + udp = socket_loopback(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK); if (udp < 0) { close(dgram); close(tcp); @@ -947,7 +947,7 @@ static void test_sockmap_same_sock(void) return; } - udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0); + udp = socket_loopback(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK); if (udp < 0) { close(dgram); close(tcp); diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index cc0c68bab907..1c96a3cf4b97 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -53,8 +53,8 @@ static void test_insert_opened(struct test_sockmap_listen *skel __always_unused, int family, int sotype, int mapfd) { u32 key = 0; - u64 value; int err, s; + u64 value; s = xsocket(family, sotype, 0); if (s == -1) @@ -63,11 +63,8 @@ static void test_insert_opened(struct test_sockmap_listen *skel __always_unused, errno = 0; value = s; err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); - if (sotype == SOCK_STREAM) { - if (!err || errno != EOPNOTSUPP) - FAIL_ERRNO("map_update: expected EOPNOTSUPP"); - } else if (err) - FAIL_ERRNO("map_update: expected success"); + ASSERT_ERR(err, "map_update"); + ASSERT_EQ(errno, EOPNOTSUPP, "errno"); xclose(s); } @@ -77,8 +74,8 @@ static void test_insert_bound(struct test_sockmap_listen *skel __always_unused, struct sockaddr_storage addr; socklen_t len = 0; u32 key = 0; - u64 value; int err, s; + u64 value; init_addr_loopback(family, &addr, &len); @@ -93,8 +90,12 @@ static void test_insert_bound(struct test_sockmap_listen *skel __always_unused, errno = 0; value = s; err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); - if (!err || errno != EOPNOTSUPP) - FAIL_ERRNO("map_update: expected EOPNOTSUPP"); + if (sotype == SOCK_STREAM) { + ASSERT_ERR(err, "map_update"); + ASSERT_EQ(errno, EOPNOTSUPP, "errno"); + } else { + ASSERT_OK(err, "map_update"); + } close: xclose(s); } @@ -1289,7 +1290,7 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map, /* insert */ TEST(test_insert_invalid), TEST(test_insert_opened), - TEST(test_insert_bound, SOCK_STREAM), + TEST(test_insert_bound), TEST(test_insert), /* delete */ TEST(test_delete_after_insert), diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.c b/tools/testing/selftests/bpf/prog_tests/test_xsk.c index 7950c504ed28..31bf8a3fcd66 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_xsk.c +++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.c @@ -414,14 +414,14 @@ static u32 pkt_nb_frags(u32 frame_size, struct pkt_stream *pkt_stream, struct pk } /* Search for the end of the packet in verbatim mode */ - if (!pkt_continues(pkt->options) || !pkt->valid) + if (!pkt_continues(pkt->options)) return nb_frags; next_frag = pkt_stream->current_pkt_nb; pkt++; while (next_frag++ < pkt_stream->nb_pkts) { nb_frags++; - if (!pkt_continues(pkt->options) || !pkt->valid) + if (!pkt_continues(pkt->options)) break; pkt++; } @@ -652,11 +652,11 @@ static struct pkt_stream *__pkt_stream_generate_custom(struct ifobject *ifobj, s if (!frame->valid || !pkt_continues(frame->options)) payload++; } else { - if (frame->valid) + if (frame->valid) { len += frame->len; - if (frame->valid && pkt_continues(frame->options)) - continue; - + if (pkt_continues(frame->options)) + continue; + } pkt->pkt_nb = pkt_nb; pkt->len = len; pkt->valid = frame->valid; @@ -1236,10 +1236,9 @@ static int __send_pkts(struct ifobject *ifobject, struct xsk_socket_info *xsk, b } } - if (pkt && pkt->valid) { + if (pkt && pkt->valid) valid_pkts++; - valid_frags += nb_frags; - } + valid_frags += nb_frags; } pthread_mutex_lock(&pacing_mutex); @@ -2075,13 +2074,16 @@ int testapp_invalid_desc_mb(struct test_spec *test) {0, 0, 0, false, 0}, /* Invalid address in the second frame */ {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - {umem_size, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {umem_size * 2, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {0, MIN_PKT_SIZE, 0, false, 0}, /* Invalid len in the middle */ {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, {0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {0, MIN_PKT_SIZE, 0, false, 0}, /* Invalid options in the middle */ {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XSK_DESC__INVALID_OPTION}, + {0, MIN_PKT_SIZE, 0, false, 0}, /* Transmit 2 frags, receive 3 */ {0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, XDP_PKT_CONTD}, {0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, 0}, @@ -2093,8 +2095,8 @@ int testapp_invalid_desc_mb(struct test_spec *test) if (umem->unaligned_mode) { /* Crossing a chunk boundary allowed */ - pkts[12].valid = true; - pkts[13].valid = true; + pkts[15].valid = true; + pkts[16].valid = true; } test->mtu = MAX_ETH_JUMBO_SIZE; @@ -2229,7 +2231,7 @@ int testapp_too_many_frags(struct test_spec *test) max_frags += 1; } - pkts = calloc(2 * max_frags + 2, sizeof(struct pkt)); + pkts = calloc(2 * max_frags + 3, sizeof(struct pkt)); if (!pkts) return TEST_FAILURE; @@ -2247,24 +2249,30 @@ int testapp_too_many_frags(struct test_spec *test) } pkts[max_frags].options = 0; - /* An invalid packet with the max amount of frags but signals packet - * continues on the last frag - */ - for (i = max_frags + 1; i < 2 * max_frags + 1; i++) { + /* An invalid packet with the max + 1 amount of frags */ + for (i = max_frags + 1; i < 2 * max_frags + 2; i++) { pkts[i].len = MIN_PKT_SIZE; pkts[i].options = XDP_PKT_CONTD; - pkts[i].valid = false; + pkts[i].valid = true; } + pkts[2 * max_frags + 1].options = 0; /* Valid packet for synch */ - pkts[2 * max_frags + 1].len = MIN_PKT_SIZE; - pkts[2 * max_frags + 1].valid = true; + pkts[2 * max_frags + 2].len = MIN_PKT_SIZE; + pkts[2 * max_frags + 2].valid = true; - if (pkt_stream_generate_custom(test, pkts, 2 * max_frags + 2)) { + if (pkt_stream_generate_custom(test, pkts, 2 * max_frags + 3)) { free(pkts); return TEST_FAILURE; } + /* The generated Tx stream must keep the too-big packet valid so that + * __send_pkts() accounts its descriptors in outstanding_tx. The Rx + * stream, however, must not expect this packet on the wire. + */ + test->ifobj_rx->xsk->pkt_stream->pkts[2].valid = false; + test->ifobj_rx->xsk->pkt_stream->nb_valid_entries--; + ret = testapp_validate_traffic(test); free(pkts); return ret; diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index ccc5acd55ff9..d194b44ff8be 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -748,16 +748,15 @@ static void test_sockmap(unsigned int tasks, void *data) goto out_sockmap; } - /* Test update with unsupported UDP socket */ + /* Test update with unsupported unbound UDP socket */ udp = socket(AF_INET, SOCK_DGRAM, 0); - i = 0; - err = bpf_map_update_elem(fd, &i, &udp, BPF_ANY); - if (err) { - printf("Failed socket update SOCK_DGRAM '%i:%i'\n", - i, udp); + CHECK(udp < 0, "socket(AF_INET, SOCK_DGRAM)", "errno:%d\n", errno); + err = bpf_map_update_elem(fd, &(int){0}, &udp, BPF_ANY); + close(udp); + if (!err) { + printf("Unexpectedly succeeded unbound UDP update '0:%i'\n", udp); goto out_sockmap; } - close(udp); /* Test update without programs */ for (i = 0; i < 6; i++) { diff --git a/tools/testing/selftests/bpf/verifier/sleepable.c b/tools/testing/selftests/bpf/verifier/sleepable.c index c2b7f5ebf168..6dabc5522945 100644 --- a/tools/testing/selftests/bpf/verifier/sleepable.c +++ b/tools/testing/selftests/bpf/verifier/sleepable.c @@ -76,7 +76,20 @@ .runs = -1, }, { - "sleepable raw tracepoint reject", + "sleepable raw tracepoint accept", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACING, + .expected_attach_type = BPF_TRACE_RAW_TP, + .kfunc = "sys_enter", + .result = ACCEPT, + .flags = BPF_F_SLEEPABLE, + .runs = -1, +}, +{ + "sleepable raw tracepoint reject non-faultable", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), @@ -85,7 +98,7 @@ .expected_attach_type = BPF_TRACE_RAW_TP, .kfunc = "sched_switch", .result = REJECT, - .errstr = "Only fentry/fexit/fsession/fmod_ret, lsm, iter, uprobe, and struct_ops programs can be sleepable", + .errstr = "Sleepable program cannot attach to non-faultable tracepoint", .flags = BPF_F_SLEEPABLE, .runs = -1, }, diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc index c300eb020262..e2322693d0c3 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc @@ -1,16 +1,16 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: Generic dynamic event - add/remove eprobe events -# requires: dynamic_events events/syscalls/sys_enter_openat "<attached-group>.<attached-event> [<args>]":README +# requires: dynamic_events events/syscalls/sys_enter_chdir "<attached-group>.<attached-event> [<args>]":README echo 0 > events/enable clear_dynamic_events SYSTEM="syscalls" -EVENT="sys_enter_openat" +EVENT="sys_enter_chdir" FIELD="filename" -EPROBE="eprobe_open" +EPROBE="eprobe_chdir" OPTIONS="file=+0(\$filename):ustring" echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events @@ -18,20 +18,14 @@ grep -q "$EPROBE" dynamic_events test -d events/eprobes/$EPROBE echo 1 > events/eprobes/$EPROBE/enable -ls +cd /sys/kernel/tracing echo 0 > events/eprobes/$EPROBE/enable -content=`grep '^ *ls-' trace | grep 'file='` -nocontent=`grep '^ *ls-' trace | grep 'file=' | grep -v -e '"/' -e '"."' -e '(fault)' ` || true - +content=`grep -e 'file="/sys/kernel/tracing"\|(fault)' trace` if [ -z "$content" ]; then exit_fail fi -if [ ! -z "$nocontent" ]; then - exit_fail -fi - echo "-:$EPROBE" >> dynamic_events ! grep -q "$EPROBE" dynamic_events diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index d805a7dfbdd5..d7741ef944bb 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -1802,6 +1802,63 @@ TEST_F(tls, recv_efault) } #define TLS_RECORD_TYPE_HANDSHAKE 0x16 + +TEST_F(tls_basic, recvmsg_nopad_retry_iov) +{ + char payload[32]; + char first_iov[sizeof(payload)]; + char later_iov[sizeof(payload) * 2]; + char expected_later_iov[sizeof(later_iov)]; + char cbuf[CMSG_SPACE(sizeof(char))]; + struct tls_crypto_info_keys tls13; + struct iovec iov[] = { + { .iov_base = first_iov, .iov_len = sizeof(first_iov) }, + { .iov_base = later_iov, .iov_len = sizeof(later_iov) }, + }; + struct msghdr msg = { + .msg_iov = iov, + .msg_iovlen = ARRAY_SIZE(iov), + .msg_control = cbuf, + .msg_controllen = sizeof(cbuf), + }; + int one = 1; + int ret; + int i; + + if (self->notls) + SKIP(return, "no TLS support"); + + tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128, + &tls13, 0); + + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls13, tls13.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls13, tls13.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX_EXPECT_NO_PAD, + &one, sizeof(one)); + ASSERT_EQ(ret, 0); + + for (i = 0; i < sizeof(payload); i++) + payload[i] = 0x40 + i; + memset(first_iov, 0xa5, sizeof(first_iov)); + memset(later_iov, 0x5a, sizeof(later_iov)); + memset(expected_later_iov, 0x5a, sizeof(expected_later_iov)); + + /* A control record forces optimistic TLS 1.3 RX to retry. */ + ret = tls_send_cmsg(self->fd, TLS_RECORD_TYPE_HANDSHAKE, + payload, sizeof(payload), 0); + ASSERT_EQ(ret, sizeof(payload)); + + ret = recvmsg(self->cfd, &msg, 0); + ASSERT_EQ(ret, sizeof(payload)); + EXPECT_EQ(memcmp(first_iov, payload, sizeof(payload)), 0); + EXPECT_EQ(memcmp(later_iov, expected_later_iov, + sizeof(later_iov)), 0); +} + /* key_update, length 1, update_not_requested */ static const char key_update_msg[] = "\x18\x00\x00\x01\x00"; static void tls_send_keyupdate(struct __test_metadata *_metadata, int fd) diff --git a/tools/testing/selftests/sched_ext/numa.bpf.c b/tools/testing/selftests/sched_ext/numa.bpf.c index 78cc49a7f9a6..6b4515c28aa0 100644 --- a/tools/testing/selftests/sched_ext/numa.bpf.c +++ b/tools/testing/selftests/sched_ext/numa.bpf.c @@ -34,7 +34,8 @@ static bool is_cpu_idle(s32 cpu, int node) s32 BPF_STRUCT_OPS(numa_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) { - int node = __COMPAT_scx_bpf_cpu_node(scx_bpf_task_cpu(p)); + s32 task_cpu = scx_bpf_task_cpu(p); + int node = __COMPAT_scx_bpf_cpu_node(task_cpu); s32 cpu; /* @@ -48,6 +49,16 @@ s32 BPF_STRUCT_OPS(numa_select_cpu, cpu = __COMPAT_scx_bpf_pick_any_cpu_node(p->cpus_ptr, node, __COMPAT_SCX_PICK_IDLE_IN_NODE); + /* + * @task_cpu may be outside of p->cpus_ptr if @p's affinity + * changed while it was sleeping. This means it's possible for + * p->cpus_ptr to not include any CPUs from @node. + * If we failed to find a cpu in @node, check if @task_cpu + * is outside of p->cpus_ptr and just return @prev_cpu if it is. + */ + if (cpu < 0 && !bpf_cpumask_test_cpu(task_cpu, p->cpus_ptr)) + return prev_cpu; + if (is_cpu_idle(cpu, node)) scx_bpf_error("CPU %d should be marked as busy", cpu); |