diff options
97 files changed, 680 insertions, 251 deletions
diff --git a/Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml b/Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml index 6d9de3303762..b3492a9aa4ef 100644 --- a/Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml +++ b/Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml @@ -62,11 +62,13 @@ properties: items: - description: GMAC main clock - description: Peripheral registers interface clock + - description: APB glue registers interface clock clock-names: items: - const: stmmaceth - const: pclk + - const: apb interrupts: items: @@ -88,8 +90,8 @@ examples: compatible = "thead,th1520-gmac", "snps,dwmac-3.70a"; reg = <0xe7070000 0x2000>, <0xec003000 0x1000>; reg-names = "dwmac", "apb"; - clocks = <&clk 1>, <&clk 2>; - clock-names = "stmmaceth", "pclk"; + clocks = <&clk 1>, <&clk 2>, <&clk 3>; + clock-names = "stmmaceth", "pclk", "apb"; interrupts = <66>; interrupt-names = "macirq"; phy-mode = "rgmii-id"; diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index bb620f554598..9756d16e3df1 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1420,7 +1420,7 @@ udp_hash_entries - INTEGER A negative value means the networking namespace does not own its hash buckets and shares the initial networking namespace's one. -udp_child_ehash_entries - INTEGER +udp_child_hash_entries - INTEGER Control the number of hash buckets for UDP sockets in the child networking namespace, which must be set before clone() or unshare(). diff --git a/MAINTAINERS b/MAINTAINERS index fe168477caa4..daf520a13bdf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11438,6 +11438,7 @@ F: drivers/tty/hvc/ HUNG TASK DETECTOR M: Andrew Morton <akpm@linux-foundation.org> R: Lance Yang <lance.yang@linux.dev> +R: Masami Hiramatsu <mhiramat@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained F: include/linux/hung_task.h @@ -12583,10 +12584,9 @@ S: Supported F: drivers/cpufreq/intel_pstate.c INTEL PTP DFL ToD DRIVER -M: Tianfei Zhang <tianfei.zhang@intel.com> L: linux-fpga@vger.kernel.org L: netdev@vger.kernel.org -S: Maintained +S: Orphan F: drivers/ptp/ptp_dfl_tod.c INTEL QUADRATURE ENCODER PERIPHERAL DRIVER @@ -12724,9 +12724,8 @@ S: Maintained F: drivers/platform/x86/intel/wmi/thunderbolt.c INTEL WWAN IOSM DRIVER -M: M Chetan Kumar <m.chetan.kumar@intel.com> L: netdev@vger.kernel.org -S: Maintained +S: Orphan F: drivers/net/wwan/iosm/ INTEL(R) FLEXIBLE RETURN AND EVENT DELIVERY @@ -13686,7 +13685,6 @@ F: scripts/Makefile.kmsan KPROBES M: Naveen N Rao <naveen@kernel.org> -M: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> M: "David S. Miller" <davem@davemloft.net> M: Masami Hiramatsu <mhiramat@kernel.org> L: linux-kernel@vger.kernel.org @@ -15674,7 +15672,6 @@ MEDIATEK T7XX 5G WWAN MODEM DRIVER M: Chandrashekar Devegowda <chandrashekar.devegowda@intel.com> R: Chiranjeevi Rapolu <chiranjeevi.rapolu@linux.intel.com> R: Liu Haijun <haijun.liu@mediatek.com> -R: M Chetan Kumar <m.chetan.kumar@linux.intel.com> R: Ricardo Martinez <ricardo.martinez@linux.intel.com> L: netdev@vger.kernel.org S: Supported @@ -17451,6 +17448,7 @@ F: drivers/net/ethernet/neterion/ NETFILTER M: Pablo Neira Ayuso <pablo@netfilter.org> M: Jozsef Kadlecsik <kadlec@netfilter.org> +M: Florian Westphal <fw@strlen.de> L: netfilter-devel@vger.kernel.org L: coreteam@netfilter.org S: Maintained diff --git a/arch/riscv/boot/dts/thead/th1520.dtsi b/arch/riscv/boot/dts/thead/th1520.dtsi index 42724bf7e90e..03f1d7319049 100644 --- a/arch/riscv/boot/dts/thead/th1520.dtsi +++ b/arch/riscv/boot/dts/thead/th1520.dtsi @@ -297,8 +297,9 @@ reg-names = "dwmac", "apb"; interrupts = <67 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq"; - clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC1>; - clock-names = "stmmaceth", "pclk"; + clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC1>, + <&clk CLK_PERISYS_APB4_HCLK>; + clock-names = "stmmaceth", "pclk", "apb"; snps,pbl = <32>; snps,fixed-burst; snps,multicast-filter-bins = <64>; @@ -319,8 +320,9 @@ reg-names = "dwmac", "apb"; interrupts = <66 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq"; - clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC0>; - clock-names = "stmmaceth", "pclk"; + clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC0>, + <&clk CLK_PERISYS_APB4_HCLK>; + clock-names = "stmmaceth", "pclk", "apb"; snps,pbl = <32>; snps,fixed-burst; snps,multicast-filter-bins = <64>; diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c index 916bac09b464..63e037e94e4c 100644 --- a/arch/x86/boot/cpuflags.c +++ b/arch/x86/boot/cpuflags.c @@ -106,5 +106,18 @@ void get_cpuflags(void) cpuid(0x80000001, &ignored, &ignored, &cpu.flags[6], &cpu.flags[1]); } + + if (max_amd_level >= 0x8000001f) { + u32 ebx; + + /* + * The X86_FEATURE_COHERENCY_SFW_NO feature bit is in + * the virtualization flags entry (word 8) and set by + * scattered.c, so the bit needs to be explicitly set. + */ + cpuid(0x8000001f, &ignored, &ebx, &ignored, &ignored); + if (ebx & BIT(31)) + set_bit(X86_FEATURE_COHERENCY_SFW_NO, cpu.flags); + } } } diff --git a/arch/x86/boot/startup/sev-shared.c b/arch/x86/boot/startup/sev-shared.c index 7a706db87b93..ac7dfd21ddd4 100644 --- a/arch/x86/boot/startup/sev-shared.c +++ b/arch/x86/boot/startup/sev-shared.c @@ -810,6 +810,13 @@ static void __head pvalidate_4k_page(unsigned long vaddr, unsigned long paddr, if (ret) sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); } + + /* + * If validating memory (making it private) and affected by the + * cache-coherency vulnerability, perform the cache eviction mitigation. + */ + if (validate && !has_cpuflag(X86_FEATURE_COHERENCY_SFW_NO)) + sev_evict_cache((void *)vaddr, 1); } /* diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c index fc59ce78c477..400a6ab75d45 100644 --- a/arch/x86/coco/sev/core.c +++ b/arch/x86/coco/sev/core.c @@ -358,10 +358,31 @@ static void svsm_pval_pages(struct snp_psc_desc *desc) static void pvalidate_pages(struct snp_psc_desc *desc) { + struct psc_entry *e; + unsigned int i; + if (snp_vmpl) svsm_pval_pages(desc); else pval_pages(desc); + + /* + * If not affected by the cache-coherency vulnerability there is no need + * to perform the cache eviction mitigation. + */ + if (cpu_feature_enabled(X86_FEATURE_COHERENCY_SFW_NO)) + return; + + for (i = 0; i <= desc->hdr.end_entry; i++) { + e = &desc->entries[i]; + + /* + * If validating memory (making it private) perform the cache + * eviction mitigation. + */ + if (e->operation == SNP_PAGE_STATE_PRIVATE) + sev_evict_cache(pfn_to_kaddr(e->gfn), e->pagesize ? 512 : 1); + } } static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 602957dd2609..06fc0479a23f 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -218,6 +218,7 @@ #define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* "flexpriority" Intel FlexPriority */ #define X86_FEATURE_EPT ( 8*32+ 2) /* "ept" Intel Extended Page Table */ #define X86_FEATURE_VPID ( 8*32+ 3) /* "vpid" Intel Virtual Processor ID */ +#define X86_FEATURE_COHERENCY_SFW_NO ( 8*32+ 4) /* SNP cache coherency software work around not needed */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* Xen paravirtual guest */ diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 89075ff19afa..02236962fdb1 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -619,6 +619,24 @@ int rmp_make_shared(u64 pfn, enum pg_level level); void snp_leak_pages(u64 pfn, unsigned int npages); void kdump_sev_callback(void); void snp_fixup_e820_tables(void); + +static inline void sev_evict_cache(void *va, int npages) +{ + volatile u8 val __always_unused; + u8 *bytes = va; + int page_idx; + + /* + * For SEV guests, a read from the first/last cache-lines of a 4K page + * using the guest key is sufficient to cause a flush of all cache-lines + * associated with that 4K page without incurring all the overhead of a + * full CLFLUSH sequence. + */ + for (page_idx = 0; page_idx < npages; page_idx++) { + val = bytes[page_idx * PAGE_SIZE]; + val = bytes[page_idx * PAGE_SIZE + PAGE_SIZE - 1]; + } +} #else static inline bool snp_probe_rmptable_info(void) { return false; } static inline int snp_rmptable_init(void) { return -ENOSYS; } @@ -634,6 +652,7 @@ static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV static inline void snp_leak_pages(u64 pfn, unsigned int npages) {} static inline void kdump_sev_callback(void) { } static inline void snp_fixup_e820_tables(void) {} +static inline void sev_evict_cache(void *va, int npages) {} #endif #endif diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index b4a1f6732a3a..6b868afb26c3 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -48,6 +48,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, { X86_FEATURE_AMD_FAST_CPPC, CPUID_EDX, 15, 0x80000007, 0 }, { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, + { X86_FEATURE_COHERENCY_SFW_NO, CPUID_EBX, 31, 0x8000001f, 0 }, { X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 }, { X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 }, { X86_FEATURE_TSA_SQ_NO, CPUID_ECX, 1, 0x80000021, 0 }, diff --git a/drivers/accel/habanalabs/common/memory.c b/drivers/accel/habanalabs/common/memory.c index 601fdbe70179..61472a381904 100644 --- a/drivers/accel/habanalabs/common/memory.c +++ b/drivers/accel/habanalabs/common/memory.c @@ -1829,9 +1829,6 @@ static void hl_release_dmabuf(struct dma_buf *dmabuf) struct hl_dmabuf_priv *hl_dmabuf = dmabuf->priv; struct hl_ctx *ctx; - if (!hl_dmabuf) - return; - ctx = hl_dmabuf->ctx; if (hl_dmabuf->memhash_hnode) @@ -1859,7 +1856,12 @@ static int export_dmabuf(struct hl_ctx *ctx, { DEFINE_DMA_BUF_EXPORT_INFO(exp_info); struct hl_device *hdev = ctx->hdev; - int rc, fd; + CLASS(get_unused_fd, fd)(flags); + + if (fd < 0) { + dev_err(hdev->dev, "failed to get a file descriptor for a dma-buf, %d\n", fd); + return fd; + } exp_info.ops = &habanalabs_dmabuf_ops; exp_info.size = total_size; @@ -1872,13 +1874,6 @@ static int export_dmabuf(struct hl_ctx *ctx, return PTR_ERR(hl_dmabuf->dmabuf); } - fd = dma_buf_fd(hl_dmabuf->dmabuf, flags); - if (fd < 0) { - dev_err(hdev->dev, "failed to get a file descriptor for a dma-buf, %d\n", fd); - rc = fd; - goto err_dma_buf_put; - } - hl_dmabuf->ctx = ctx; hl_ctx_get(hl_dmabuf->ctx); atomic_inc(&ctx->hdev->dmabuf_export_cnt); @@ -1890,13 +1885,9 @@ static int export_dmabuf(struct hl_ctx *ctx, get_file(ctx->hpriv->file_priv->filp); *dmabuf_fd = fd; + fd_install(take_fd(fd), hl_dmabuf->dmabuf->file); return 0; - -err_dma_buf_put: - hl_dmabuf->dmabuf->priv = NULL; - dma_buf_put(hl_dmabuf->dmabuf); - return rc; } static int validate_export_params_common(struct hl_device *hdev, u64 addr, u64 size, u64 offset) diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 75c7db8b156a..7855bbf752b1 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -2033,7 +2033,7 @@ void __init acpi_ec_ecdt_probe(void) goto out; } - if (!strstarts(ecdt_ptr->id, "\\")) { + if (!strlen(ecdt_ptr->id)) { /* * The ECDT table on some MSI notebooks contains invalid data, together * with an empty ID string (""). @@ -2042,9 +2042,13 @@ void __init acpi_ec_ecdt_probe(void) * a "fully qualified reference to the (...) embedded controller device", * so this string always has to start with a backslash. * - * By verifying this we can avoid such faulty ECDT tables in a safe way. + * However some ThinkBook machines have a ECDT table with a valid EC + * description but an invalid ID string ("_SB.PC00.LPCB.EC0"). + * + * Because of this we only check if the ID string is empty in order to + * avoid the obvious cases. */ - pr_err(FW_BUG "Ignoring ECDT due to invalid ID string \"%s\"\n", ecdt_ptr->id); + pr_err(FW_BUG "Ignoring ECDT due to empty ID string\n"); goto out; } diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index 755003bf3a45..8972446b7162 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -180,7 +180,7 @@ void acpi_processor_ppc_init(struct cpufreq_policy *policy) struct acpi_processor *pr = per_cpu(processors, cpu); int ret; - if (!pr || !pr->performance) + if (!pr) continue; /* @@ -197,6 +197,9 @@ void acpi_processor_ppc_init(struct cpufreq_policy *policy) pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu, ret); + if (!pr->performance) + continue; + ret = acpi_processor_get_platform_limit(pr); if (ret) pr_err("Failed to update freq constraint for CPU%d (%d)\n", diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 06a1c7dd081f..f366d35c5840 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2793,6 +2793,7 @@ static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = { X86_MATCH(INTEL_GRANITERAPIDS_X, core_funcs), X86_MATCH(INTEL_ATOM_CRESTMONT, core_funcs), X86_MATCH(INTEL_ATOM_CRESTMONT_X, core_funcs), + X86_MATCH(INTEL_ATOM_DARKMONT_X, core_funcs), {} }; #endif diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 52d5d26fc7c6..81306612a5c6 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -97,6 +97,14 @@ static inline int which_bucket(u64 duration_ns) static DEFINE_PER_CPU(struct menu_device, menu_devices); +static void menu_update_intervals(struct menu_device *data, unsigned int interval_us) +{ + /* Update the repeating-pattern data. */ + data->intervals[data->interval_ptr++] = interval_us; + if (data->interval_ptr >= INTERVALS) + data->interval_ptr = 0; +} + static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev); /* @@ -222,6 +230,14 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, if (data->needs_update) { menu_update(drv, dev); data->needs_update = 0; + } else if (!dev->last_residency_ns) { + /* + * This happens when the driver rejects the previously selected + * idle state and returns an error, so update the recent + * intervals table to prevent invalid information from being + * used going forward. + */ + menu_update_intervals(data, UINT_MAX); } /* Find the shortest expected idle interval. */ @@ -482,10 +498,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) data->correction_factor[data->bucket] = new_factor; - /* update the repeating-pattern data */ - data->intervals[data->interval_ptr++] = ktime_to_us(measured_ns); - if (data->interval_ptr >= INTERVALS) - data->interval_ptr = 0; + menu_update_intervals(data, ktime_to_us(measured_ns)); } /** diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 73747d20df85..91a7b7e7c0c8 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1679,7 +1679,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = { }; static const struct x86_cpu_id intel_mwait_ids[] __initconst = { - X86_MATCH_VENDOR_FAM_FEATURE(INTEL, 6, X86_FEATURE_MWAIT, NULL), + X86_MATCH_VENDOR_FAM_FEATURE(INTEL, X86_FAMILY_ANY, X86_FEATURE_MWAIT, NULL), {} }; diff --git a/drivers/net/dsa/microchip/ksz8.c b/drivers/net/dsa/microchip/ksz8.c index 76e490070e9c..c354abdafc1b 100644 --- a/drivers/net/dsa/microchip/ksz8.c +++ b/drivers/net/dsa/microchip/ksz8.c @@ -36,15 +36,14 @@ static void ksz_cfg(struct ksz_device *dev, u32 addr, u8 bits, bool set) { - regmap_update_bits(ksz_regmap_8(dev), addr, bits, set ? bits : 0); + ksz_rmw8(dev, addr, bits, set ? bits : 0); } static void ksz_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits, bool set) { - regmap_update_bits(ksz_regmap_8(dev), - dev->dev_ops->get_port_addr(port, offset), - bits, set ? bits : 0); + ksz_rmw8(dev, dev->dev_ops->get_port_addr(port, offset), bits, + set ? bits : 0); } /** @@ -1955,16 +1954,19 @@ int ksz8_setup(struct dsa_switch *ds) ksz_cfg(dev, S_LINK_AGING_CTRL, SW_LINK_AUTO_AGING, true); /* Enable aggressive back off algorithm in half duplex mode. */ - regmap_update_bits(ksz_regmap_8(dev), REG_SW_CTRL_1, - SW_AGGR_BACKOFF, SW_AGGR_BACKOFF); + ret = ksz_rmw8(dev, REG_SW_CTRL_1, SW_AGGR_BACKOFF, SW_AGGR_BACKOFF); + if (ret) + return ret; /* * Make sure unicast VLAN boundary is set as default and * enable no excessive collision drop. */ - regmap_update_bits(ksz_regmap_8(dev), REG_SW_CTRL_2, - UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP, - UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP); + ret = ksz_rmw8(dev, REG_SW_CTRL_2, + UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP, + UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP); + if (ret) + return ret; ksz_cfg(dev, S_REPLACE_VID_CTRL, SW_REPLACE_VID, false); diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 7292bfe2f7ca..4cb14288ff0f 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -1447,6 +1447,7 @@ static const struct regmap_range ksz8873_valid_regs[] = { regmap_reg_range(0x3f, 0x3f), /* advanced control registers */ + regmap_reg_range(0x43, 0x43), regmap_reg_range(0x60, 0x6f), regmap_reg_range(0x70, 0x75), regmap_reg_range(0x76, 0x78), diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 5578ddcb465d..2800a90fba1f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -926,15 +926,21 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping, static netmem_ref __bnxt_alloc_rx_netmem(struct bnxt *bp, dma_addr_t *mapping, struct bnxt_rx_ring_info *rxr, + unsigned int *offset, gfp_t gfp) { netmem_ref netmem; - netmem = page_pool_alloc_netmems(rxr->page_pool, gfp); + if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) { + netmem = page_pool_alloc_frag_netmem(rxr->page_pool, offset, BNXT_RX_PAGE_SIZE, gfp); + } else { + netmem = page_pool_alloc_netmems(rxr->page_pool, gfp); + *offset = 0; + } if (!netmem) return 0; - *mapping = page_pool_get_dma_addr_netmem(netmem); + *mapping = page_pool_get_dma_addr_netmem(netmem) + *offset; return netmem; } @@ -1029,7 +1035,7 @@ static int bnxt_alloc_rx_netmem(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, dma_addr_t mapping; netmem_ref netmem; - netmem = __bnxt_alloc_rx_netmem(bp, &mapping, rxr, gfp); + netmem = __bnxt_alloc_rx_netmem(bp, &mapping, rxr, &offset, gfp); if (!netmem) return -ENOMEM; @@ -3819,7 +3825,6 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp, if (BNXT_RX_PAGE_MODE(bp)) pp.pool_size += bp->rx_ring_size / rx_size_fac; pp.nid = numa_node; - pp.napi = &rxr->bnapi->napi; pp.netdev = bp->dev; pp.dev = &bp->pdev->dev; pp.dma_dir = bp->rx_dir; @@ -3851,6 +3856,12 @@ err_destroy_pp: return PTR_ERR(pool); } +static void bnxt_enable_rx_page_pool(struct bnxt_rx_ring_info *rxr) +{ + page_pool_enable_direct_recycling(rxr->head_pool, &rxr->bnapi->napi); + page_pool_enable_direct_recycling(rxr->page_pool, &rxr->bnapi->napi); +} + static int bnxt_alloc_rx_agg_bmap(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) { u16 mem_size; @@ -3889,6 +3900,7 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp) rc = bnxt_alloc_rx_page_pool(bp, rxr, cpu_node); if (rc) return rc; + bnxt_enable_rx_page_pool(rxr); rc = xdp_rxq_info_reg(&rxr->xdp_rxq, bp->dev, i, 0); if (rc < 0) @@ -16031,6 +16043,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) goto err_reset; } + bnxt_enable_rx_page_pool(rxr); napi_enable_locked(&bnapi->napi); bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons); diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c index 503cfbfb4a8a..83cf75bf7a17 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c @@ -53,9 +53,11 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type) { int ret; - ASSERT_RTNL(); + if (test_and_set_bit(HBG_NIC_STATE_RESETTING, &priv->state)) + return -EBUSY; if (netif_running(priv->netdev)) { + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state); dev_warn(&priv->pdev->dev, "failed to reset because port is up\n"); return -EBUSY; @@ -64,7 +66,6 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type) netif_device_detach(priv->netdev); priv->reset_type = type; - set_bit(HBG_NIC_STATE_RESETTING, &priv->state); clear_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state); ret = hbg_hw_event_notify(priv, HBG_HW_EVENT_RESET); if (ret) { @@ -84,29 +85,26 @@ static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type) type != priv->reset_type) return 0; - ASSERT_RTNL(); - - clear_bit(HBG_NIC_STATE_RESETTING, &priv->state); ret = hbg_rebuild(priv); if (ret) { priv->stats.reset_fail_cnt++; set_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state); + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state); dev_err(&priv->pdev->dev, "failed to rebuild after reset\n"); return ret; } netif_device_attach(priv->netdev); + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state); dev_info(&priv->pdev->dev, "reset done\n"); return ret; } -/* must be protected by rtnl lock */ int hbg_reset(struct hbg_priv *priv) { int ret; - ASSERT_RTNL(); ret = hbg_reset_prepare(priv, HBG_RESET_TYPE_FUNCTION); if (ret) return ret; @@ -171,7 +169,6 @@ static void hbg_pci_err_reset_prepare(struct pci_dev *pdev) struct net_device *netdev = pci_get_drvdata(pdev); struct hbg_priv *priv = netdev_priv(netdev); - rtnl_lock(); hbg_reset_prepare(priv, HBG_RESET_TYPE_FLR); } @@ -181,7 +178,6 @@ static void hbg_pci_err_reset_done(struct pci_dev *pdev) struct hbg_priv *priv = netdev_priv(netdev); hbg_reset_done(priv, HBG_RESET_TYPE_FLR); - rtnl_unlock(); } static const struct pci_error_handlers hbg_pci_err_handler = { diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c index 8cca8316ba40..d0aa0661ecd4 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c @@ -12,6 +12,8 @@ #define HBG_HW_EVENT_WAIT_TIMEOUT_US (2 * 1000 * 1000) #define HBG_HW_EVENT_WAIT_INTERVAL_US (10 * 1000) +#define HBG_MAC_LINK_WAIT_TIMEOUT_US (500 * 1000) +#define HBG_MAC_LINK_WAIT_INTERVAL_US (5 * 1000) /* little endian or big endian. * ctrl means packet description, data means skb packet data */ @@ -228,6 +230,9 @@ void hbg_hw_fill_buffer(struct hbg_priv *priv, u32 buffer_dma_addr) void hbg_hw_adjust_link(struct hbg_priv *priv, u32 speed, u32 duplex) { + u32 link_status; + int ret; + hbg_hw_mac_enable(priv, HBG_STATUS_DISABLE); hbg_reg_write_field(priv, HBG_REG_PORT_MODE_ADDR, @@ -239,8 +244,14 @@ void hbg_hw_adjust_link(struct hbg_priv *priv, u32 speed, u32 duplex) hbg_hw_mac_enable(priv, HBG_STATUS_ENABLE); - if (!hbg_reg_read_field(priv, HBG_REG_AN_NEG_STATE_ADDR, - HBG_REG_AN_NEG_STATE_NP_LINK_OK_B)) + /* wait MAC link up */ + ret = readl_poll_timeout(priv->io_base + HBG_REG_AN_NEG_STATE_ADDR, + link_status, + FIELD_GET(HBG_REG_AN_NEG_STATE_NP_LINK_OK_B, + link_status), + HBG_MAC_LINK_WAIT_INTERVAL_US, + HBG_MAC_LINK_WAIT_TIMEOUT_US); + if (ret) hbg_np_link_fail_task_schedule(priv); } diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h index 2883a5899ae2..8b6110599e10 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h @@ -29,7 +29,12 @@ static inline bool hbg_fifo_is_full(struct hbg_priv *priv, enum hbg_dir dir) static inline u32 hbg_get_queue_used_num(struct hbg_ring *ring) { - return (ring->ntu + ring->len - ring->ntc) % ring->len; + u32 len = READ_ONCE(ring->len); + + if (!len) + return 0; + + return (READ_ONCE(ring->ntu) + len - READ_ONCE(ring->ntc)) % len; } netdev_tx_t hbg_net_start_xmit(struct sk_buff *skb, struct net_device *netdev); diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c index 54f1b83dfe42..d227f4d2a2d1 100644 --- a/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c @@ -543,6 +543,7 @@ int ixgbe_devlink_register_port(struct ixgbe_adapter *adapter) attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; attrs.phys.port_number = adapter->hw.bus.func; + attrs.no_phys_port_name = 1; ixgbe_devlink_set_switch_id(adapter, &attrs.switch_id); devlink_port_attrs_set(devlink_port, &attrs); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index 09ae16e026eb..6c363f9b0ce2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -330,15 +330,11 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev) if (IS_ERR(plat_dat)) return PTR_ERR(plat_dat); - ret = devm_clk_bulk_get_all(&pdev->dev, &plat_dat->clks); + ret = devm_clk_bulk_get_all_enabled(&pdev->dev, &plat_dat->clks); if (ret < 0) - return dev_err_probe(&pdev->dev, ret, "Failed to retrieve all required clocks\n"); + return dev_err_probe(&pdev->dev, ret, "Failed to retrieve and enable all required clocks\n"); plat_dat->num_clks = ret; - ret = clk_bulk_prepare_enable(plat_dat->num_clks, plat_dat->clks); - if (ret) - return dev_err_probe(&pdev->dev, ret, "Failed to enable clocks\n"); - plat_dat->stmmac_clk = stmmac_pltfr_find_clk(plat_dat, data->stmmac_clk_name); @@ -346,7 +342,6 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev) ret = data->probe(pdev, plat_dat, &stmmac_res); if (ret < 0) { dev_err_probe(&pdev->dev, ret, "failed to probe subdriver\n"); - clk_bulk_disable_unprepare(plat_dat->num_clks, plat_dat->clks); return ret; } @@ -370,15 +365,11 @@ remove: static void dwc_eth_dwmac_remove(struct platform_device *pdev) { const struct dwc_eth_dwmac_data *data = device_get_match_data(&pdev->dev); - struct plat_stmmacenet_data *plat_dat = dev_get_platdata(&pdev->dev); stmmac_dvr_remove(&pdev->dev); if (data->remove) data->remove(pdev); - - if (plat_dat) - clk_bulk_disable_unprepare(plat_dat->num_clks, plat_dat->clks); } static const struct of_device_id dwc_eth_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 79b92130a03f..f6687c2f30f6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -1765,11 +1765,15 @@ err_gmac_powerdown: static void rk_gmac_remove(struct platform_device *pdev) { - struct rk_priv_data *bsp_priv = get_stmmac_bsp_priv(&pdev->dev); + struct stmmac_priv *priv = netdev_priv(platform_get_drvdata(pdev)); + struct rk_priv_data *bsp_priv = priv->plat->bsp_priv; stmmac_dvr_remove(&pdev->dev); rk_gmac_powerdown(bsp_priv); + + if (priv->plat->phy_node && bsp_priv->integrated_phy) + clk_put(bsp_priv->clk_phy); } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c index c72ee759aae5..f2946bea0bc2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c @@ -211,6 +211,7 @@ static int thead_dwmac_probe(struct platform_device *pdev) struct stmmac_resources stmmac_res; struct plat_stmmacenet_data *plat; struct thead_dwmac *dwmac; + struct clk *apb_clk; void __iomem *apb; int ret; @@ -224,6 +225,19 @@ static int thead_dwmac_probe(struct platform_device *pdev) return dev_err_probe(&pdev->dev, PTR_ERR(plat), "dt configuration failed\n"); + /* + * The APB clock is essential for accessing glue registers. However, + * old devicetrees don't describe it correctly. We continue to probe + * and emit a warning if it isn't present. + */ + apb_clk = devm_clk_get_enabled(&pdev->dev, "apb"); + if (PTR_ERR(apb_clk) == -ENOENT) + dev_warn(&pdev->dev, + "cannot get apb clock, link may break after speed changes\n"); + else if (IS_ERR(apb_clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(apb_clk), + "failed to get apb clock\n"); + dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); if (!dwmac) return -ENOMEM; diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c index 50bfbc2779e4..d8c9fe1d98c4 100644 --- a/drivers/net/ethernet/ti/icssg/icss_iep.c +++ b/drivers/net/ethernet/ti/icssg/icss_iep.c @@ -621,7 +621,8 @@ exit: static int icss_iep_extts_enable(struct icss_iep *iep, u32 index, int on) { - u32 val, cap, ret = 0; + u32 val, cap; + int ret = 0; mutex_lock(&iep->ptp_clk_mutex); diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 2b973d6e2341..6c7d776ae4ee 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -50,6 +50,8 @@ /* CTRLMMR_ICSSG_RGMII_CTRL register bits */ #define ICSSG_CTRL_RGMII_ID_MODE BIT(24) +static void emac_adjust_link(struct net_device *ndev); + static int emac_get_tx_ts(struct prueth_emac *emac, struct emac_tx_ts_response *rsp) { @@ -229,6 +231,10 @@ static int prueth_emac_common_start(struct prueth *prueth) ret = icssg_config(prueth, emac, slice); if (ret) goto disable_class; + + mutex_lock(&emac->ndev->phydev->lock); + emac_adjust_link(emac->ndev); + mutex_unlock(&emac->ndev->phydev->lock); } ret = prueth_emac_start(prueth); diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index 0e0fe32d2da4..045c5177262e 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -138,7 +138,7 @@ static inline struct net_device *bpq_get_ax25_dev(struct net_device *dev) static inline int dev_is_ethdev(struct net_device *dev) { - return dev->type == ARPHRD_ETHER && strncmp(dev->name, "dummy", 5); + return dev->type == ARPHRD_ETHER && !netdev_need_ops_lock(dev); } /* ------------------------------------------------------------------------ */ diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index cb6f5482d203..7397c693f984 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -1061,6 +1061,7 @@ struct net_device_context { struct net_device __rcu *vf_netdev; struct netvsc_vf_pcpu_stats __percpu *vf_stats; struct delayed_work vf_takeover; + struct delayed_work vfns_work; /* 1: allocated, serial number is valid. 0: not allocated */ u32 vf_alloc; @@ -1075,6 +1076,8 @@ struct net_device_context { struct netvsc_device_info *saved_netvsc_dev_info; }; +void netvsc_vfns_work(struct work_struct *w); + /* Azure hosts don't support non-TCP port numbers in hashing for fragmented * packets. We can use ethtool to change UDP hash level when necessary. */ diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index f44753756358..39c892e46cb0 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2522,6 +2522,7 @@ static int netvsc_probe(struct hv_device *dev, spin_lock_init(&net_device_ctx->lock); INIT_LIST_HEAD(&net_device_ctx->reconfig_events); INIT_DELAYED_WORK(&net_device_ctx->vf_takeover, netvsc_vf_setup); + INIT_DELAYED_WORK(&net_device_ctx->vfns_work, netvsc_vfns_work); net_device_ctx->vf_stats = netdev_alloc_pcpu_stats(struct netvsc_vf_pcpu_stats); @@ -2666,6 +2667,8 @@ static void netvsc_remove(struct hv_device *dev) cancel_delayed_work_sync(&ndev_ctx->dwork); rtnl_lock(); + cancel_delayed_work_sync(&ndev_ctx->vfns_work); + nvdev = rtnl_dereference(ndev_ctx->nvdev); if (nvdev) { cancel_work_sync(&nvdev->subchan_work); @@ -2707,6 +2710,7 @@ static int netvsc_suspend(struct hv_device *dev) cancel_delayed_work_sync(&ndev_ctx->dwork); rtnl_lock(); + cancel_delayed_work_sync(&ndev_ctx->vfns_work); nvdev = rtnl_dereference(ndev_ctx->nvdev); if (nvdev == NULL) { @@ -2800,6 +2804,27 @@ static void netvsc_event_set_vf_ns(struct net_device *ndev) } } +void netvsc_vfns_work(struct work_struct *w) +{ + struct net_device_context *ndev_ctx = + container_of(w, struct net_device_context, vfns_work.work); + struct net_device *ndev; + + if (!rtnl_trylock()) { + schedule_delayed_work(&ndev_ctx->vfns_work, 1); + return; + } + + ndev = hv_get_drvdata(ndev_ctx->device_ctx); + if (!ndev) + goto out; + + netvsc_event_set_vf_ns(ndev); + +out: + rtnl_unlock(); +} + /* * On Hyper-V, every VF interface is matched with a corresponding * synthetic interface. The synthetic interface is presented first @@ -2810,10 +2835,12 @@ static int netvsc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); + struct net_device_context *ndev_ctx; int ret = 0; if (event_dev->netdev_ops == &device_ops && event == NETDEV_REGISTER) { - netvsc_event_set_vf_ns(event_dev); + ndev_ctx = netdev_priv(event_dev); + schedule_delayed_work(&ndev_ctx->vfns_work, 0); return NOTIFY_DONE; } diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 39fe28af48b9..0178219f0db5 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -710,9 +710,13 @@ static struct nsim_rq *nsim_queue_alloc(void) static void nsim_queue_free(struct net_device *dev, struct nsim_rq *rq) { hrtimer_cancel(&rq->napi_timer); - local_bh_disable(); - dev_dstats_rx_dropped_add(dev, rq->skb_queue.qlen); - local_bh_enable(); + + if (rq->skb_queue.qlen) { + local_bh_disable(); + dev_dstats_rx_dropped_add(dev, rq->skb_queue.qlen); + local_bh_enable(); + } + skb_queue_purge_reason(&rq->skb_queue, SKB_DROP_REASON_QUEUE_PURGE); kfree(rq); } diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index fda2e27c1810..cad6ed3aa10b 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -91,6 +91,7 @@ int mdiobus_unregister_device(struct mdio_device *mdiodev) if (mdiodev->bus->mdio_map[mdiodev->addr] != mdiodev) return -EINVAL; + gpiod_put(mdiodev->reset_gpio); reset_control_put(mdiodev->reset_ctrl); mdiodev->bus->mdio_map[mdiodev->addr] = NULL; diff --git a/drivers/net/phy/mdio_bus_provider.c b/drivers/net/phy/mdio_bus_provider.c index 48dc4bf85125..f43973e73ea3 100644 --- a/drivers/net/phy/mdio_bus_provider.c +++ b/drivers/net/phy/mdio_bus_provider.c @@ -443,9 +443,6 @@ void mdiobus_unregister(struct mii_bus *bus) if (!mdiodev) continue; - if (mdiodev->reset_gpio) - gpiod_put(mdiodev->reset_gpio); - mdiodev->device_remove(mdiodev); mdiodev->device_free(mdiodev); } diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index 4c6d905f0a9f..87adb6508017 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -1965,24 +1965,27 @@ static int nxp_c45_macsec_ability(struct phy_device *phydev) return macsec_ability; } +static bool tja11xx_phy_id_compare(struct phy_device *phydev, + const struct phy_driver *phydrv) +{ + u32 id = phydev->is_c45 ? phydev->c45_ids.device_ids[MDIO_MMD_PMAPMD] : + phydev->phy_id; + + return phy_id_compare(id, phydrv->phy_id, phydrv->phy_id_mask); +} + static int tja11xx_no_macsec_match_phy_device(struct phy_device *phydev, const struct phy_driver *phydrv) { - if (!phy_id_compare(phydev->phy_id, phydrv->phy_id, - phydrv->phy_id_mask)) - return 0; - - return !nxp_c45_macsec_ability(phydev); + return tja11xx_phy_id_compare(phydev, phydrv) && + !nxp_c45_macsec_ability(phydev); } static int tja11xx_macsec_match_phy_device(struct phy_device *phydev, const struct phy_driver *phydrv) { - if (!phy_id_compare(phydev->phy_id, phydrv->phy_id, - phydrv->phy_id_mask)) - return 0; - - return nxp_c45_macsec_ability(phydev); + return tja11xx_phy_id_compare(phydev, phydrv) && + nxp_c45_macsec_ability(phydev); } static const struct nxp_c45_regmap tja1120_regmap = { diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 9b0318fb50b5..d9f5942ccc44 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -676,6 +676,7 @@ static int ax88772_init_mdio(struct usbnet *dev) priv->mdio->read = &asix_mdio_bus_read; priv->mdio->write = &asix_mdio_bus_write; priv->mdio->name = "Asix MDIO Bus"; + priv->mdio->phy_mask = ~(BIT(priv->phy_addr) | BIT(AX_EMBD_PHY_ADDR)); /* mii bus name is usb-<usb bus number>-<usb device number> */ snprintf(priv->mdio->id, MII_BUS_ID_SIZE, "usb-%03d:%03d", dev->udev->bus->busnum, dev->udev->devnum); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index f5647ee0adde..e56901bb6ebc 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1361,6 +1361,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x1bc7, 0x1057, 2)}, /* Telit FN980 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)}, /* Telit LN920 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)}, /* Telit FN990A */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1077, 2)}, /* Telit FN990A w/audio */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1080, 2)}, /* Telit FE990A */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a0, 0)}, /* Telit FN920C04 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a4, 0)}, /* Telit FN920C04 */ diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index 995a7207bdf8..f357a7ac70ac 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -81,7 +81,7 @@ static struct lapbethdev *lapbeth_get_x25_dev(struct net_device *dev) static __inline__ int dev_is_ethdev(struct net_device *dev) { - return dev->type == ARPHRD_ETHER && strncmp(dev->name, "dummy", 5); + return dev->type == ARPHRD_ETHER && !netdev_need_ops_lock(dev); } /* ------------------------------------------------------------------------ */ diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index a6aad743c282..b352df4cd3f9 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -24,6 +24,11 @@ #define PTP_DEFAULT_MAX_VCLOCKS 20 #define PTP_MAX_CHANNELS 2048 +enum { + PTP_LOCK_PHYSICAL = 0, + PTP_LOCK_VIRTUAL, +}; + struct timestamp_event_queue { struct ptp_extts_event buf[PTP_MAX_TIMESTAMPS]; int head; diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c index 2fdeedd60e21..64c950456517 100644 --- a/drivers/ptp/ptp_vclock.c +++ b/drivers/ptp/ptp_vclock.c @@ -154,6 +154,11 @@ static long ptp_vclock_refresh(struct ptp_clock_info *ptp) return PTP_VCLOCK_REFRESH_INTERVAL; } +static void ptp_vclock_set_subclass(struct ptp_clock *ptp) +{ + lockdep_set_subclass(&ptp->clock.rwsem, PTP_LOCK_VIRTUAL); +} + static const struct ptp_clock_info ptp_vclock_info = { .owner = THIS_MODULE, .name = "ptp virtual clock", @@ -213,6 +218,8 @@ struct ptp_vclock *ptp_vclock_register(struct ptp_clock *pclock) return NULL; } + ptp_vclock_set_subclass(vclock->clock); + timecounter_init(&vclock->tc, &vclock->cc, 0); ptp_schedule_worker(vclock->clock, PTP_VCLOCK_REFRESH_INTERVAL); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 835b0deef9bb..f23d75986947 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4331,15 +4331,18 @@ static int try_release_subpage_extent_buffer(struct folio *folio) unsigned long end = index + (PAGE_SIZE >> fs_info->nodesize_bits) - 1; int ret; - xa_lock_irq(&fs_info->buffer_tree); + rcu_read_lock(); xa_for_each_range(&fs_info->buffer_tree, index, eb, start, end) { /* * The same as try_release_extent_buffer(), to ensure the eb * won't disappear out from under us. */ spin_lock(&eb->refs_lock); + rcu_read_unlock(); + if (refcount_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) { spin_unlock(&eb->refs_lock); + rcu_read_lock(); continue; } @@ -4358,11 +4361,10 @@ static int try_release_subpage_extent_buffer(struct folio *folio) * check the folio private at the end. And * release_extent_buffer() will release the refs_lock. */ - xa_unlock_irq(&fs_info->buffer_tree); release_extent_buffer(eb); - xa_lock_irq(&fs_info->buffer_tree); + rcu_read_lock(); } - xa_unlock_irq(&fs_info->buffer_tree); + rcu_read_unlock(); /* * Finally to check if we have cleared folio private, as if we have @@ -4375,7 +4377,6 @@ static int try_release_subpage_extent_buffer(struct folio *folio) ret = 0; spin_unlock(&folio->mapping->i_private_lock); return ret; - } int try_release_extent_buffer(struct folio *folio) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b77dd22b8cdb..d740910e071a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -401,10 +401,12 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode, while (index <= end_index) { folio = filemap_get_folio(inode->vfs_inode.i_mapping, index); - index++; - if (IS_ERR(folio)) + if (IS_ERR(folio)) { + index++; continue; + } + index = folio_end(folio) >> PAGE_SHIFT; /* * Here we just clear all Ordered bits for every page in the * range, then btrfs_mark_ordered_io_finished() will handle @@ -2013,7 +2015,7 @@ static int nocow_one_range(struct btrfs_inode *inode, struct folio *locked_folio * cleaered by the caller. */ if (ret < 0) - btrfs_cleanup_ordered_extents(inode, file_pos, end); + btrfs_cleanup_ordered_extents(inode, file_pos, len); return ret; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 1a5972178b3a..ccaa9a3cf1ce 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1453,7 +1453,6 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root, struct btrfs_qgroup *src, int sign) { struct btrfs_qgroup *qgroup; - struct btrfs_qgroup *cur; LIST_HEAD(qgroup_list); u64 num_bytes = src->excl; int ret = 0; @@ -1463,7 +1462,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root, goto out; qgroup_iterator_add(&qgroup_list, qgroup); - list_for_each_entry(cur, &qgroup_list, iterator) { + list_for_each_entry(qgroup, &qgroup_list, iterator) { struct btrfs_qgroup_list *glist; qgroup->rfer += sign * num_bytes; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index e58151933844..7256f6748c8f 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -602,6 +602,25 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans, if (btrfs_root_id(root) == objectid) { u64 commit_root_gen; + /* + * Relocation will wait for cleaner thread, and any half-dropped + * subvolume will be fully cleaned up at mount time. + * So here we shouldn't hit a subvolume with non-zero drop_progress. + * + * If this isn't the case, error out since it can make us attempt to + * drop references for extents that were already dropped before. + */ + if (unlikely(btrfs_disk_key_objectid(&root->root_item.drop_progress))) { + struct btrfs_key cpu_key; + + btrfs_disk_key_to_cpu(&cpu_key, &root->root_item.drop_progress); + btrfs_err(fs_info, + "cannot relocate partially dropped subvolume %llu, drop progress key (%llu %u %llu)", + objectid, cpu_key.objectid, cpu_key.type, cpu_key.offset); + ret = -EUCLEAN; + goto fail; + } + /* called by btrfs_init_reloc_root */ ret = btrfs_copy_root(trans, root, root->commit_root, &eb, BTRFS_TREE_RELOC_OBJECTID); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 2186e87fb61b..69e11557fd13 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2605,14 +2605,14 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, /* * Correctly adjust the reserved bytes occupied by a log tree extent buffer */ -static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start) +static int unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start) { struct btrfs_block_group *cache; cache = btrfs_lookup_block_group(fs_info, start); if (!cache) { btrfs_err(fs_info, "unable to find block group for %llu", start); - return; + return -ENOENT; } spin_lock(&cache->space_info->lock); @@ -2623,27 +2623,22 @@ static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start) spin_unlock(&cache->space_info->lock); btrfs_put_block_group(cache); + + return 0; } static int clean_log_buffer(struct btrfs_trans_handle *trans, struct extent_buffer *eb) { - int ret; - btrfs_tree_lock(eb); btrfs_clear_buffer_dirty(trans, eb); wait_on_extent_buffer_writeback(eb); btrfs_tree_unlock(eb); - if (trans) { - ret = btrfs_pin_reserved_extent(trans, eb); - if (ret) - return ret; - } else { - unaccount_log_buffer(eb->fs_info, eb->start); - } + if (trans) + return btrfs_pin_reserved_extent(trans, eb); - return 0; + return unaccount_log_buffer(eb->fs_info, eb->start); } static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 245e813ecd78..db11b5b5f0e6 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -2650,7 +2650,7 @@ int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info) spin_lock(&block_group->lock); if (block_group->reserved || block_group->alloc_offset == 0 || - (block_group->flags & BTRFS_BLOCK_GROUP_SYSTEM) || + !(block_group->flags & BTRFS_BLOCK_GROUP_DATA) || test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags)) { spin_unlock(&block_group->lock); continue; diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c index 4f6468eb2adf..cb237f1b902a 100644 --- a/fs/nfsd/localio.c +++ b/fs/nfsd/localio.c @@ -103,10 +103,11 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom, if (nfsd_file_get(new) == NULL) goto again; /* - * Drop the ref we were going to install and the - * one we were going to return. + * Drop the ref we were going to install (both file and + * net) and the one we were going to return (only file). */ nfsd_file_put(localio); + nfsd_net_put(net); nfsd_file_put(localio); localio = new; } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 98ab55ba3ced..edf050766e57 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -470,7 +470,15 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) if (!iap->ia_valid) return 0; - iap->ia_valid |= ATTR_CTIME; + /* + * If ATTR_DELEG is set, then this is an update from a client that + * holds a delegation. If this is an update for only the atime, the + * ctime should not be changed. If the update contains the mtime + * too, then ATTR_CTIME should already be set. + */ + if (!(iap->ia_valid & ATTR_DELEG)) + iap->ia_valid |= ATTR_CTIME; + return notify_change(&nop_mnt_idmap, dentry, iap, NULL); } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 3d6d8a9f13fc..29cca0e6d0ff 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -340,8 +340,8 @@ static int proc_maps_open(struct inode *inode, struct file *file, priv->inode = inode; priv->mm = proc_mem_open(inode, PTRACE_MODE_READ); - if (IS_ERR_OR_NULL(priv->mm)) { - int err = priv->mm ? PTR_ERR(priv->mm) : -ESRCH; + if (IS_ERR(priv->mm)) { + int err = PTR_ERR(priv->mm); seq_release_private(inode, file); return err; @@ -1148,10 +1148,13 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; - pte_t ptent = huge_ptep_get(walk->mm, addr, pte); struct folio *folio = NULL; bool present = false; + spinlock_t *ptl; + pte_t ptent; + ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte); + ptent = huge_ptep_get(walk->mm, addr, pte); if (pte_present(ptent)) { folio = page_folio(pte_page(ptent)); present = true; @@ -1170,6 +1173,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, else mss->private_hugetlb += huge_page_size(hstate_vma(vma)); } + spin_unlock(ptl); return 0; } #else @@ -2017,12 +2021,14 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, struct pagemapread *pm = walk->private; struct vm_area_struct *vma = walk->vma; u64 flags = 0, frame = 0; + spinlock_t *ptl; int err = 0; pte_t pte; if (vma->vm_flags & VM_SOFTDIRTY) flags |= PM_SOFT_DIRTY; + ptl = huge_pte_lock(hstate_vma(vma), walk->mm, ptep); pte = huge_ptep_get(walk->mm, addr, ptep); if (pte_present(pte)) { struct folio *folio = page_folio(pte_page(pte)); @@ -2050,11 +2056,12 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, err = add_to_pagemap(&pme, pm); if (err) - return err; + break; if (pm->show_pfn && (flags & PM_PRESENT)) frame++; } + spin_unlock(ptl); cond_resched(); return err; @@ -3128,17 +3135,22 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { - pte_t huge_pte = huge_ptep_get(walk->mm, addr, pte); + pte_t huge_pte; struct numa_maps *md; struct page *page; + spinlock_t *ptl; + ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); + huge_pte = huge_ptep_get(walk->mm, addr, pte); if (!pte_present(huge_pte)) - return 0; + goto out; page = pte_page(huge_pte); md = walk->private; gather_stats(page, md, pte_dirty(huge_pte), 1); +out: + spin_unlock(ptl); return 0; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5e5de4b0a433..f3a3b761abfb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2071,6 +2071,8 @@ enum netdev_reg_state { * @max_pacing_offload_horizon: max EDT offload horizon in nsec. * @napi_config: An array of napi_config structures containing per-NAPI * settings. + * @num_napi_configs: number of allocated NAPI config structs, + * always >= max(num_rx_queues, num_tx_queues). * @gro_flush_timeout: timeout for GRO layer in NAPI * @napi_defer_hard_irqs: If not zero, provides a counter that would * allow to avoid NIC hard IRQ, on busy queues. @@ -2482,8 +2484,9 @@ struct net_device { u64 max_pacing_offload_horizon; struct napi_config *napi_config; - unsigned long gro_flush_timeout; + u32 num_napi_configs; u32 napi_defer_hard_irqs; + unsigned long gro_flush_timeout; /** * @up: copy of @state's IFF_UP, but safe to read with just @lock. diff --git a/include/net/devlink.h b/include/net/devlink.h index 93640a29427c..b32c9ceeb81d 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -78,6 +78,9 @@ struct devlink_port_pci_sf_attrs { * @flavour: flavour of the port * @split: indicates if this is split port * @splittable: indicates if the port can be split. + * @no_phys_port_name: skip automatic phys_port_name generation; for + * compatibility only, newly added driver/port instance + * should never set this. * @lanes: maximum number of lanes the port supports. 0 value is not passed to netlink. * @switch_id: if the port is part of switch, this is buffer with ID, otherwise this is NULL * @phys: physical port attributes @@ -87,7 +90,8 @@ struct devlink_port_pci_sf_attrs { */ struct devlink_port_attrs { u8 split:1, - splittable:1; + splittable:1, + no_phys_port_name:1; u32 lanes; enum devlink_port_flavour flavour; struct netdev_phys_item_id switch_id; diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index ff406ef4fd4a..29a36709e7f3 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1163,6 +1163,14 @@ static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs) return housekeeping_cpumask(HK_TYPE_KTHREAD); } +static inline const struct cpumask *sysctl_est_preferred_cpulist(struct netns_ipvs *ipvs) +{ + if (ipvs->est_cpulist_valid) + return ipvs->sysctl_est_cpulist; + else + return NULL; +} + static inline int sysctl_est_nice(struct netns_ipvs *ipvs) { return ipvs->sysctl_est_nice; @@ -1270,6 +1278,11 @@ static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs) return housekeeping_cpumask(HK_TYPE_KTHREAD); } +static inline const struct cpumask *sysctl_est_preferred_cpulist(struct netns_ipvs *ipvs) +{ + return NULL; +} + static inline int sysctl_est_nice(struct netns_ipvs *ipvs) { return IPVS_EST_NICE; diff --git a/include/net/kcm.h b/include/net/kcm.h index 441e993be634..d9c35e71ecea 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -71,7 +71,6 @@ struct kcm_sock { struct list_head wait_psock_list; struct sk_buff *seq_skb; struct mutex tx_mutex; - u32 tx_stopped : 1; /* Don't use bit fields here, these are set under different locks */ bool tx_wait; diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 431b593de709..1509a536cb85 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -265,6 +265,8 @@ struct page_pool *page_pool_create_percpu(const struct page_pool_params *params, struct xdp_mem_info; #ifdef CONFIG_PAGE_POOL +void page_pool_enable_direct_recycling(struct page_pool *pool, + struct napi_struct *napi); void page_pool_disable_direct_recycling(struct page_pool *pool); void page_pool_destroy(struct page_pool *pool); void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), diff --git a/kernel/kthread.c b/kernel/kthread.c index 0e98b228a8ef..31b072e8d427 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -893,6 +893,7 @@ out: return ret; } +EXPORT_SYMBOL_GPL(kthread_affine_preferred); /* * Re-affine kthreads according to their preferences diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 174ee243b349..8eff357b0436 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4262,6 +4262,8 @@ int rcutree_prepare_cpu(unsigned int cpu) rdp->rcu_iw_gp_seq = rdp->gp_seq - 1; trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl")); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + + rcu_preempt_deferred_qs_init(rdp); rcu_spawn_rnp_kthreads(rnp); rcu_spawn_cpu_nocb_kthread(cpu); ASSERT_EXCLUSIVE_WRITER(rcu_state.n_online_cpus); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index de6ca13a7b5f..b8bbe7960cda 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -488,6 +488,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp); static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); static void rcu_flavor_sched_clock_irq(int user); static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck); +static void rcu_preempt_deferred_qs_init(struct rcu_data *rdp); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); static bool rcu_is_callbacks_kthread(struct rcu_data *rdp); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index fc14adf15cbb..4cd170b2d655 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -763,8 +763,6 @@ static void rcu_read_unlock_special(struct task_struct *t) cpu_online(rdp->cpu)) { // Get scheduler to re-evaluate and call hooks. // If !IRQ_WORK, FQS scan will eventually IPI. - rdp->defer_qs_iw = - IRQ_WORK_INIT_HARD(rcu_preempt_deferred_qs_handler); rdp->defer_qs_iw_pending = DEFER_QS_PENDING; irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu); } @@ -904,6 +902,10 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) } } +static void rcu_preempt_deferred_qs_init(struct rcu_data *rdp) +{ + rdp->defer_qs_iw = IRQ_WORK_INIT_HARD(rcu_preempt_deferred_qs_handler); +} #else /* #ifdef CONFIG_PREEMPT_RCU */ /* @@ -1103,6 +1105,8 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks)); } +static void rcu_preempt_deferred_qs_init(struct rcu_data *rdp) { } + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c index a9e6ffcff04b..cce12287708e 100644 --- a/lib/ref_tracker.c +++ b/lib/ref_tracker.c @@ -434,7 +434,7 @@ void ref_tracker_dir_debugfs(struct ref_tracker_dir *dir) if (dentry && !xa_is_err(dentry)) return; - ret = snprintf(name, sizeof(name), "%s@%px", dir->class, dir); + ret = snprintf(name, sizeof(name), "%s@%p", dir->class, dir); name[sizeof(name) - 1] = '\0'; if (ret < sizeof(name)) { diff --git a/mm/kasan/kasan_test_c.c b/mm/kasan/kasan_test_c.c index 2aa12dfa427a..e0968acc03aa 100644 --- a/mm/kasan/kasan_test_c.c +++ b/mm/kasan/kasan_test_c.c @@ -47,7 +47,7 @@ static struct { * Some tests use these global variables to store return values from function * calls that could otherwise be eliminated by the compiler as dead code. */ -static volatile void *kasan_ptr_result; +static void *volatile kasan_ptr_result; static volatile int kasan_int_result; /* Probe for console output: obtains test_status lines of interest. */ diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 374a6a5193a7..6b40bdfd224c 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1172,11 +1172,11 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, if (result != SCAN_SUCCEED) goto out_up_write; /* check if the pmd is still valid */ + vma_start_write(vma); result = check_pmd_still_valid(mm, address, pmd); if (result != SCAN_SUCCEED) goto out_up_write; - vma_start_write(vma); anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address, diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 8d588e685311..84265983f239 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -470,6 +470,7 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp) { unsigned long flags; struct kmemleak_object *object; + bool warn = false; /* try the slab allocator first */ if (object_cache) { @@ -488,8 +489,10 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp) else if (mem_pool_free_count) object = &mem_pool[--mem_pool_free_count]; else - pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n"); + warn = true; raw_spin_unlock_irqrestore(&kmemleak_lock, flags); + if (warn) + pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n"); return object; } @@ -2181,6 +2184,7 @@ static const struct file_operations kmemleak_fops = { static void __kmemleak_do_cleanup(void) { struct kmemleak_object *object, *tmp; + unsigned int cnt = 0; /* * Kmemleak has already been disabled, no need for RCU list traversal @@ -2189,6 +2193,10 @@ static void __kmemleak_do_cleanup(void) list_for_each_entry_safe(object, tmp, &object_list, object_list) { __remove_object(object); __delete_object(object); + + /* Call cond_resched() once per 64 iterations to avoid soft lockup */ + if (!(++cnt & 0x3f)) + cond_resched(); } } diff --git a/mm/mprotect.c b/mm/mprotect.c index 78bded7acf79..113b48985834 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -120,9 +120,8 @@ static int mprotect_folio_pte_batch(struct folio *folio, pte_t *ptep, static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr, pte_t oldpte, pte_t *pte, int target_node, - struct folio **foliop) + struct folio *folio) { - struct folio *folio = NULL; bool ret = true; bool toptier; int nid; @@ -131,7 +130,6 @@ static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr, if (pte_protnone(oldpte)) goto skip; - folio = vm_normal_folio(vma, addr, oldpte); if (!folio) goto skip; @@ -173,7 +171,6 @@ static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr, folio_xchg_access_time(folio, jiffies_to_msecs(jiffies)); skip: - *foliop = folio; return ret; } @@ -231,10 +228,9 @@ static int page_anon_exclusive_sub_batch(int start_idx, int max_len, * retrieve sub-batches. */ static void commit_anon_folio_batch(struct vm_area_struct *vma, - struct folio *folio, unsigned long addr, pte_t *ptep, + struct folio *folio, struct page *first_page, unsigned long addr, pte_t *ptep, pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb) { - struct page *first_page = folio_page(folio, 0); bool expected_anon_exclusive; int sub_batch_idx = 0; int len; @@ -251,7 +247,7 @@ static void commit_anon_folio_batch(struct vm_area_struct *vma, } static void set_write_prot_commit_flush_ptes(struct vm_area_struct *vma, - struct folio *folio, unsigned long addr, pte_t *ptep, + struct folio *folio, struct page *page, unsigned long addr, pte_t *ptep, pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb) { bool set_write; @@ -270,7 +266,7 @@ static void set_write_prot_commit_flush_ptes(struct vm_area_struct *vma, /* idx = */ 0, set_write, tlb); return; } - commit_anon_folio_batch(vma, folio, addr, ptep, oldpte, ptent, nr_ptes, tlb); + commit_anon_folio_batch(vma, folio, page, addr, ptep, oldpte, ptent, nr_ptes, tlb); } static long change_pte_range(struct mmu_gather *tlb, @@ -305,15 +301,19 @@ static long change_pte_range(struct mmu_gather *tlb, const fpb_t flags = FPB_RESPECT_SOFT_DIRTY | FPB_RESPECT_WRITE; int max_nr_ptes = (end - addr) >> PAGE_SHIFT; struct folio *folio = NULL; + struct page *page; pte_t ptent; + page = vm_normal_page(vma, addr, oldpte); + if (page) + folio = page_folio(page); /* * Avoid trapping faults against the zero or KSM * pages. See similar comment in change_huge_pmd. */ if (prot_numa) { int ret = prot_numa_skip(vma, addr, oldpte, pte, - target_node, &folio); + target_node, folio); if (ret) { /* determine batch to skip */ @@ -323,9 +323,6 @@ static long change_pte_range(struct mmu_gather *tlb, } } - if (!folio) - folio = vm_normal_folio(vma, addr, oldpte); - nr_ptes = mprotect_folio_pte_batch(folio, pte, oldpte, max_nr_ptes, flags); oldpte = modify_prot_start_ptes(vma, addr, pte, nr_ptes); @@ -351,7 +348,7 @@ static long change_pte_range(struct mmu_gather *tlb, */ if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) && !pte_write(ptent)) - set_write_prot_commit_flush_ptes(vma, folio, + set_write_prot_commit_flush_ptes(vma, folio, page, addr, pte, oldpte, ptent, nr_ptes, tlb); else prot_commit_flush_ptes(vma, addr, pte, oldpte, ptent, diff --git a/mm/mremap.c b/mm/mremap.c index 677a4d744df9..9afa8cd524f5 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -179,6 +179,10 @@ static int mremap_folio_pte_batch(struct vm_area_struct *vma, unsigned long addr if (max_nr == 1) return 1; + /* Avoid expensive folio lookup if we stand no chance of benefit. */ + if (pte_batch_hint(ptep, pte) == 1) + return 1; + folio = vm_normal_folio(vma, addr, pte); if (!folio || !folio_test_large(folio)) return 1; diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index cbed91b09640..45e6290e2e8b 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1821,13 +1821,16 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start, /* Check if we can move the pmd without splitting it. */ if (move_splits_huge_pmd(dst_addr, src_addr, src_start + len) || !pmd_none(dst_pmdval)) { - struct folio *folio = pmd_folio(*src_pmd); - - if (!folio || (!is_huge_zero_folio(folio) && - !PageAnonExclusive(&folio->page))) { - spin_unlock(ptl); - err = -EBUSY; - break; + /* Can be a migration entry */ + if (pmd_present(*src_pmd)) { + struct folio *folio = pmd_folio(*src_pmd); + + if (!is_huge_zero_folio(folio) && + !PageAnonExclusive(&folio->page)) { + spin_unlock(ptl); + err = -EBUSY; + break; + } } spin_unlock(ptl); diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index 60f28e4fb5c0..4fd5a6ea26b4 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -43,6 +43,7 @@ config NF_CONNTRACK_BRIDGE config BRIDGE_NF_EBTABLES_LEGACY tristate "Legacy EBTABLES support" depends on BRIDGE && NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES default n help Legacy ebtables packet/frame classifier. diff --git a/net/core/dev.c b/net/core/dev.c index 68dc47d7e700..5a3c0f40a93f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6999,7 +6999,7 @@ int netif_set_threaded(struct net_device *dev, enum netdev_napi_threaded threaded) { struct napi_struct *napi; - int err = 0; + int i, err = 0; netdev_assert_locked_or_invisible(dev); @@ -7021,6 +7021,10 @@ int netif_set_threaded(struct net_device *dev, list_for_each_entry(napi, &dev->napi_list, dev_list) WARN_ON_ONCE(napi_set_threaded(napi, threaded)); + /* Override the config for all NAPIs even if currently not listed */ + for (i = 0; i < dev->num_napi_configs; i++) + dev->napi_config[i].threaded = threaded; + return err; } @@ -7353,8 +7357,9 @@ void netif_napi_add_weight_locked(struct net_device *dev, * Clear dev->threaded if kthread creation failed so that * threaded mode will not be enabled in napi_enable(). */ - if (dev->threaded && napi_kthread_create(napi)) - dev->threaded = NETDEV_NAPI_THREADED_DISABLED; + if (napi_get_threaded_config(dev, napi)) + if (napi_kthread_create(napi)) + dev->threaded = NETDEV_NAPI_THREADED_DISABLED; netif_napi_set_irq_locked(napi, -1); } EXPORT_SYMBOL(netif_napi_add_weight_locked); @@ -11873,6 +11878,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, goto free_all; dev->cfg_pending = dev->cfg; + dev->num_napi_configs = maxqs; napi_config_sz = array_size(maxqs, sizeof(*dev->napi_config)); dev->napi_config = kvzalloc(napi_config_sz, GFP_KERNEL_ACCOUNT); if (!dev->napi_config) diff --git a/net/core/dev.h b/net/core/dev.h index ab69edc0c3e3..d6b08d435479 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -323,6 +323,14 @@ static inline enum netdev_napi_threaded napi_get_threaded(struct napi_struct *n) return NETDEV_NAPI_THREADED_DISABLED; } +static inline enum netdev_napi_threaded +napi_get_threaded_config(struct net_device *dev, struct napi_struct *n) +{ + if (n->config) + return n->config->threaded; + return dev->threaded; +} + int napi_set_threaded(struct napi_struct *n, enum netdev_napi_threaded threaded); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 05e2e22a8f7c..343a6cac21e3 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -1201,6 +1201,35 @@ void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), pool->xdp_mem_id = mem->id; } +/** + * page_pool_enable_direct_recycling() - mark page pool as owned by NAPI + * @pool: page pool to modify + * @napi: NAPI instance to associate the page pool with + * + * Associate a page pool with a NAPI instance for lockless page recycling. + * This is useful when a new page pool has to be added to a NAPI instance + * without disabling that NAPI instance, to mark the point at which control + * path "hands over" the page pool to the NAPI instance. In most cases driver + * can simply set the @napi field in struct page_pool_params, and does not + * have to call this helper. + * + * The function is idempotent, but does not implement any refcounting. + * Single page_pool_disable_direct_recycling() will disable recycling, + * no matter how many times enable was called. + */ +void page_pool_enable_direct_recycling(struct page_pool *pool, + struct napi_struct *napi) +{ + if (READ_ONCE(pool->p.napi) == napi) + return; + WARN_ON(!napi || pool->p.napi); + + mutex_lock(&page_pools_lock); + WRITE_ONCE(pool->p.napi, napi); + mutex_unlock(&page_pools_lock); +} +EXPORT_SYMBOL(page_pool_enable_direct_recycling); + void page_pool_disable_direct_recycling(struct page_pool *pool) { /* Disable direct recycling based on pool->cpuid. diff --git a/net/devlink/port.c b/net/devlink/port.c index 939081a0e615..cb8d4df61619 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -1519,7 +1519,7 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, struct devlink_port_attrs *attrs = &devlink_port->attrs; int n = 0; - if (!devlink_port->attrs_set) + if (!devlink_port->attrs_set || devlink_port->attrs.no_phys_port_name) return -EOPNOTSUPP; switch (attrs->flavour) { diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 2c438b140e88..7dc9772fe2d8 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -14,6 +14,7 @@ config NF_DEFRAG_IPV4 config IP_NF_IPTABLES_LEGACY tristate "Legacy IP tables support" depends on NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES default m if NETFILTER_XTABLES_LEGACY help iptables is a legacy packet classifier. @@ -326,6 +327,7 @@ endif # IP_NF_IPTABLES config IP_NF_ARPTABLES tristate "Legacy ARPTABLES support" depends on NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES default n help arptables is a legacy packet classifier. @@ -343,6 +345,7 @@ config IP_NF_ARPFILTER select IP_NF_ARPTABLES select NETFILTER_FAMILY_ARP depends on NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES help ARP packet filtering defines a table `filter', which has a series of rules for simple ARP packet filtering at local input and diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 5128e2a5b00a..b1f3fd302e9d 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -217,7 +217,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM); skb->remcsum_offload = remcsum; - need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); + need_ipsec = (skb_dst(skb) && dst_xfrm(skb_dst(skb))) || skb_sec_path(skb); /* Try to offload checksum if possible */ offload_csum = !!(need_csum && !need_ipsec && diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 276860f65baa..81daf82ddc2d 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -10,6 +10,7 @@ menu "IPv6: Netfilter Configuration" config IP6_NF_IPTABLES_LEGACY tristate "Legacy IP6 tables support" depends on INET && IPV6 && NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES default m if NETFILTER_XTABLES_LEGACY help ip6tables is a legacy packet classifier. diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 5120a763da0d..0a0eeaed0591 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -334,7 +334,7 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); + xfrm_state_flush(net, 0, false); xfrm_flush_gc(); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index a4971e6fa943..b4f01cb07561 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -430,7 +430,7 @@ static void psock_write_space(struct sock *sk) /* Check if the socket is reserved so someone is waiting for sending. */ kcm = psock->tx_kcm; - if (kcm && !unlikely(kcm->tx_stopped)) + if (kcm) queue_work(kcm_wq, &kcm->tx_work); spin_unlock_bh(&mux->lock); @@ -1693,12 +1693,6 @@ static int kcm_release(struct socket *sock) */ __skb_queue_purge(&sk->sk_write_queue); - /* Set tx_stopped. This is checked when psock is bound to a kcm and we - * get a writespace callback. This prevents further work being queued - * from the callback (unbinding the psock occurs after canceling work. - */ - kcm->tx_stopped = 1; - release_sock(sk); spin_lock_bh(&mux->lock); @@ -1714,7 +1708,7 @@ static int kcm_release(struct socket *sock) /* Cancel work. After this point there should be no outside references * to the kcm socket. */ - cancel_work_sync(&kcm->tx_work); + disable_work_sync(&kcm->tx_work); lock_sock(sk); psock = kcm->tx_psock; diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index fb6b46a952cb..69a3ccfc6310 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -1586,7 +1586,6 @@ static void mctp_test_bind_lookup(struct kunit *test) cleanup: kfree_skb(skb_sock); - kfree_skb(skb_pkt); /* Drop all binds */ for (size_t i = 0; i < ARRAY_SIZE(lookup_binds); i++) diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index f821ad2e19b3..15049b826732 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -265,7 +265,8 @@ int ip_vs_est_kthread_start(struct netns_ipvs *ipvs, } set_user_nice(kd->task, sysctl_est_nice(ipvs)); - set_cpus_allowed_ptr(kd->task, sysctl_est_cpulist(ipvs)); + if (sysctl_est_preferred_cpulist(ipvs)) + kthread_affine_preferred(kd->task, sysctl_est_preferred_cpulist(ipvs)); pr_info("starting estimator thread %d...\n", kd->id); wake_up_process(kd->task); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 486d52b45fe5..50fd6809380f 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -884,8 +884,6 @@ errout: static int ctnetlink_done(struct netlink_callback *cb) { - if (cb->args[1]) - nf_ct_put((struct nf_conn *)cb->args[1]); kfree(cb->data); return 0; } @@ -1208,19 +1206,26 @@ ignore_entry: return 0; } +static unsigned long ctnetlink_get_id(const struct nf_conn *ct) +{ + unsigned long id = nf_ct_get_id(ct); + + return id ? id : 1; +} + static int ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { unsigned int flags = cb->data ? NLM_F_DUMP_FILTERED : 0; struct net *net = sock_net(skb->sk); - struct nf_conn *ct, *last; + unsigned long last_id = cb->args[1]; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; struct nf_conn *nf_ct_evict[8]; + struct nf_conn *ct; int res, i; spinlock_t *lockp; - last = (struct nf_conn *)cb->args[1]; i = 0; local_bh_disable(); @@ -1257,7 +1262,7 @@ restart: continue; if (cb->args[1]) { - if (ct != last) + if (ctnetlink_get_id(ct) != last_id) continue; cb->args[1] = 0; } @@ -1270,8 +1275,7 @@ restart: NFNL_MSG_TYPE(cb->nlh->nlmsg_type), ct, true, flags); if (res < 0) { - nf_conntrack_get(&ct->ct_general); - cb->args[1] = (unsigned long)ct; + cb->args[1] = ctnetlink_get_id(ct); spin_unlock(lockp); goto out; } @@ -1284,12 +1288,10 @@ restart: } out: local_bh_enable(); - if (last) { + if (last_id) { /* nf ct hash resize happened, now clear the leftover. */ - if ((struct nf_conn *)cb->args[1] == last) + if (cb->args[1] == last_id) cb->args[1] = 0; - - nf_ct_put(last); } while (i) { @@ -3168,23 +3170,27 @@ errout: return 0; } #endif -static int ctnetlink_exp_done(struct netlink_callback *cb) + +static unsigned long ctnetlink_exp_id(const struct nf_conntrack_expect *exp) { - if (cb->args[1]) - nf_ct_expect_put((struct nf_conntrack_expect *)cb->args[1]); - return 0; + unsigned long id = (unsigned long)exp; + + id += nf_ct_get_id(exp->master); + id += exp->class; + + return id ? id : 1; } static int ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; + unsigned long last_id = cb->args[1]; + struct nf_conntrack_expect *exp; rcu_read_lock(); - last = (struct nf_conntrack_expect *)cb->args[1]; for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) { restart: hlist_for_each_entry_rcu(exp, &nf_ct_expect_hash[cb->args[0]], @@ -3196,7 +3202,7 @@ restart: continue; if (cb->args[1]) { - if (exp != last) + if (ctnetlink_exp_id(exp) != last_id) continue; cb->args[1] = 0; } @@ -3205,9 +3211,7 @@ restart: cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { - if (!refcount_inc_not_zero(&exp->use)) - continue; - cb->args[1] = (unsigned long)exp; + cb->args[1] = ctnetlink_exp_id(exp); goto out; } } @@ -3218,32 +3222,30 @@ restart: } out: rcu_read_unlock(); - if (last) - nf_ct_expect_put(last); - return skb->len; } static int ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { - struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct nf_conn *ct = cb->data; struct nf_conn_help *help = nfct_help(ct); u_int8_t l3proto = nfmsg->nfgen_family; + unsigned long last_id = cb->args[1]; + struct nf_conntrack_expect *exp; if (cb->args[0]) return 0; rcu_read_lock(); - last = (struct nf_conntrack_expect *)cb->args[1]; + restart: hlist_for_each_entry_rcu(exp, &help->expectations, lnode) { if (l3proto && exp->tuple.src.l3num != l3proto) continue; if (cb->args[1]) { - if (exp != last) + if (ctnetlink_exp_id(exp) != last_id) continue; cb->args[1] = 0; } @@ -3251,9 +3253,7 @@ restart: cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { - if (!refcount_inc_not_zero(&exp->use)) - continue; - cb->args[1] = (unsigned long)exp; + cb->args[1] = ctnetlink_exp_id(exp); goto out; } } @@ -3264,9 +3264,6 @@ restart: cb->args[0] = 1; out: rcu_read_unlock(); - if (last) - nf_ct_expect_put(last); - return skb->len; } @@ -3285,7 +3282,6 @@ static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl, struct nf_conntrack_zone zone; struct netlink_dump_control c = { .dump = ctnetlink_exp_ct_dump_table, - .done = ctnetlink_exp_done, }; err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, @@ -3335,7 +3331,6 @@ static int ctnetlink_get_expect(struct sk_buff *skb, else { struct netlink_dump_control c = { .dump = ctnetlink_exp_dump_table, - .done = ctnetlink_exp_done, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 9b8b10a85233..1f14ef0436c6 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -567,16 +567,16 @@ nf_conntrack_log_invalid_sysctl(const struct ctl_table *table, int write, return ret; if (*(u8 *)table->data == 0) - return ret; + return 0; /* Load nf_log_syslog only if no logger is currently registered */ for (i = 0; i < NFPROTO_NUMPROTO; i++) { if (nf_log_is_registered(i)) - return ret; + return 0; } request_module("%s", "nf_log_syslog"); - return ret; + return 0; } static struct ctl_table_header *nf_ct_netfilter_header; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 13d0ed9d1895..58c5425d61c2 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2803,6 +2803,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, struct nft_chain *chain = ctx->chain; struct nft_chain_hook hook = {}; struct nft_stats __percpu *stats = NULL; + struct nftables_pernet *nft_net; struct nft_hook *h, *next; struct nf_hook_ops *ops; struct nft_trans *trans; @@ -2845,6 +2846,20 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, if (nft_hook_list_find(&basechain->hook_list, h)) { list_del(&h->list); nft_netdev_hook_free(h); + continue; + } + + nft_net = nft_pernet(ctx->net); + list_for_each_entry(trans, &nft_net->commit_list, list) { + if (trans->msg_type != NFT_MSG_NEWCHAIN || + trans->table != ctx->table || + !nft_trans_chain_update(trans)) + continue; + + if (nft_hook_list_find(&nft_trans_chain_hooks(trans), h)) { + nft_chain_release_hook(&hook); + return -EEXIST; + } } } } else { @@ -9060,6 +9075,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, { const struct nlattr * const *nla = ctx->nla; struct nft_flowtable_hook flowtable_hook; + struct nftables_pernet *nft_net; struct nft_hook *hook, *next; struct nf_hook_ops *ops; struct nft_trans *trans; @@ -9076,6 +9092,20 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, if (nft_hook_list_find(&flowtable->hook_list, hook)) { list_del(&hook->list); nft_netdev_hook_free(hook); + continue; + } + + nft_net = nft_pernet(ctx->net); + list_for_each_entry(trans, &nft_net->commit_list, list) { + if (trans->msg_type != NFT_MSG_NEWFLOWTABLE || + trans->table != ctx->table || + !nft_trans_flowtable_update(trans)) + continue; + + if (nft_hook_list_find(&nft_trans_flowtable_hooks(trans), hook)) { + err = -EEXIST; + goto err_flowtable_update_hook; + } } } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 1a19649c2851..9a10251228fd 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -426,10 +426,9 @@ static struct nft_pipapo_elem *pipapo_get(const struct nft_pipapo_match *m, local_bh_disable(); - if (unlikely(!raw_cpu_ptr(m->scratch))) - goto out; - scratch = *raw_cpu_ptr(m->scratch); + if (unlikely(!scratch)) + goto out; map_index = scratch->map_index; diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index db5d367e43c4..2f090e253caf 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -1150,12 +1150,12 @@ nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, const u32 *key) { struct nft_pipapo *priv = nft_set_priv(set); + const struct nft_set_ext *ext = NULL; struct nft_pipapo_scratch *scratch; u8 genmask = nft_genmask_cur(net); const struct nft_pipapo_match *m; const struct nft_pipapo_field *f; const u8 *rp = (const u8 *)key; - const struct nft_set_ext *ext; unsigned long *res, *fill; bool map_index; int i; @@ -1246,13 +1246,13 @@ next_match: goto out; if (last) { - ext = &f->mt[ret].e->ext; - if (unlikely(nft_set_elem_expired(ext) || - !nft_set_elem_active(ext, genmask))) { - ext = NULL; + const struct nft_set_ext *e = &f->mt[ret].e->ext; + + if (unlikely(nft_set_elem_expired(e) || + !nft_set_elem_active(e, genmask))) goto next_match; - } + ext = e; goto out; } diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 35d0409b0095..36affbb697c2 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -217,7 +217,7 @@ static int nft_socket_init(const struct nft_ctx *ctx, level += err; /* Implies a giant cgroup tree */ - if (WARN_ON_ONCE(level > 255)) + if (level > 255) return -EOPNOTSUPP; priv->level = level; diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 037f764822b9..82635dd2cfa5 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -651,6 +651,12 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); + for (i = nbands; i < oldbands; i++) { + if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) + list_del_init(&q->classes[i].alist); + qdisc_purge_queue(q->classes[i].qdisc); + } + WRITE_ONCE(q->nbands, nbands); for (i = nstrict; i < q->nstrict; i++) { if (q->classes[i].qdisc->q.qlen) { @@ -658,11 +664,6 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, q->classes[i].deficit = quanta[i]; } } - for (i = q->nbands; i < oldbands; i++) { - if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) - list_del_init(&q->classes[i].alist); - qdisc_purge_queue(q->classes[i].qdisc); - } WRITE_ONCE(q->nstrict, nstrict); memcpy(q->prio2band, priomap, sizeof(priomap)); diff --git a/net/sctp/input.c b/net/sctp/input.c index 2dc2666988fb..7e99894778d4 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -117,7 +117,7 @@ int sctp_rcv(struct sk_buff *skb) * it's better to just linearize it otherwise crc computing * takes longer. */ - if ((!is_gso && skb_linearize(skb)) || + if (((!is_gso || skb_cloned(skb)) && skb_linearize(skb)) || !pskb_may_pull(skb, sizeof(struct sctphdr))) goto discard_it; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 46c156b121db..e2c5e0e626f9 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -257,20 +257,47 @@ svc_tcp_sock_process_cmsg(struct socket *sock, struct msghdr *msg, } static int -svc_tcp_sock_recv_cmsg(struct svc_sock *svsk, struct msghdr *msg) +svc_tcp_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags) { union { struct cmsghdr cmsg; u8 buf[CMSG_SPACE(sizeof(u8))]; } u; - struct socket *sock = svsk->sk_sock; + u8 alert[2]; + struct kvec alert_kvec = { + .iov_base = alert, + .iov_len = sizeof(alert), + }; + struct msghdr msg = { + .msg_flags = *msg_flags, + .msg_control = &u, + .msg_controllen = sizeof(u), + }; + int ret; + + iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1, + alert_kvec.iov_len); + ret = sock_recvmsg(sock, &msg, MSG_DONTWAIT); + if (ret > 0 && + tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) { + iov_iter_revert(&msg.msg_iter, ret); + ret = svc_tcp_sock_process_cmsg(sock, &msg, &u.cmsg, -EAGAIN); + } + return ret; +} + +static int +svc_tcp_sock_recvmsg(struct svc_sock *svsk, struct msghdr *msg) +{ int ret; + struct socket *sock = svsk->sk_sock; - msg->msg_control = &u; - msg->msg_controllen = sizeof(u); ret = sock_recvmsg(sock, msg, MSG_DONTWAIT); - if (unlikely(msg->msg_controllen != sizeof(u))) - ret = svc_tcp_sock_process_cmsg(sock, msg, &u.cmsg, ret); + if (msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~(MSG_CTRUNC | MSG_EOR); + if (ret == 0 || ret == -EIO) + ret = svc_tcp_sock_recv_cmsg(sock, &msg->msg_flags); + } return ret; } @@ -321,7 +348,7 @@ static ssize_t svc_tcp_read_msg(struct svc_rqst *rqstp, size_t buflen, iov_iter_advance(&msg.msg_iter, seek); buflen -= seek; } - len = svc_tcp_sock_recv_cmsg(svsk, &msg); + len = svc_tcp_sock_recvmsg(svsk, &msg); if (len > 0) svc_flush_bvec(bvec, len, seek); @@ -1018,7 +1045,7 @@ static ssize_t svc_tcp_read_marker(struct svc_sock *svsk, iov.iov_base = ((char *)&svsk->sk_marker) + svsk->sk_tcplen; iov.iov_len = want; iov_iter_kvec(&msg.msg_iter, ITER_DEST, &iov, 1, want); - len = svc_tcp_sock_recv_cmsg(svsk, &msg); + len = svc_tcp_sock_recvmsg(svsk, &msg); if (len < 0) return len; svsk->sk_tcplen += len; diff --git a/net/tls/tls.h b/net/tls/tls.h index 774859b63f0d..4e077068e6d9 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -196,7 +196,7 @@ void tls_strp_msg_done(struct tls_strparser *strp); int tls_rx_msg_size(struct tls_strparser *strp, struct sk_buff *skb); void tls_rx_msg_ready(struct tls_strparser *strp); -void tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh); +bool tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh); int tls_strp_msg_cow(struct tls_sw_context_rx *ctx); struct sk_buff *tls_strp_msg_detach(struct tls_sw_context_rx *ctx); int tls_strp_msg_hold(struct tls_strparser *strp, struct sk_buff_head *dst); diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 095cf31bae0b..d71643b494a1 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -475,7 +475,7 @@ static void tls_strp_load_anchor_with_queue(struct tls_strparser *strp, int len) strp->stm.offset = offset; } -void tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh) +bool tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh) { struct strp_msg *rxm; struct tls_msg *tlm; @@ -484,8 +484,11 @@ void tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh) DEBUG_NET_WARN_ON_ONCE(!strp->stm.full_len); if (!strp->copy_mode && force_refresh) { - if (WARN_ON(tcp_inq(strp->sk) < strp->stm.full_len)) - return; + if (unlikely(tcp_inq(strp->sk) < strp->stm.full_len)) { + WRITE_ONCE(strp->msg_ready, 0); + memset(&strp->stm, 0, sizeof(strp->stm)); + return false; + } tls_strp_load_anchor_with_queue(strp, strp->stm.full_len); } @@ -495,6 +498,8 @@ void tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh) rxm->offset = strp->stm.offset; tlm = tls_msg(strp->anchor); tlm->control = strp->mark; + + return true; } /* Called with lock held on lower socket */ diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 549d1ea01a72..51c98a007dda 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1384,7 +1384,8 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, return sock_intr_errno(timeo); } - tls_strp_msg_load(&ctx->strp, released); + if (unlikely(!tls_strp_msg_load(&ctx->strp, released))) + return tls_rx_rec_wait(sk, psock, nonblock, false); return 1; } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index ead6a3c14b87..bebb355f3ffe 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -689,7 +689,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk, unsigned int i; for (i = 0; i < MAX_PORT_RETRIES; i++) { - if (port <= LAST_RESERVED_PORT) + if (port == VMADDR_PORT_ANY || + port <= LAST_RESERVED_PORT) port = LAST_RESERVED_PORT + 1; new_addr.svm_port = port++; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index d2819baea414..c7a1f080d2de 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -155,7 +155,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } - if (skb_is_gso(skb) && unlikely(xmit_xfrm_check_overflow(skb))) { + if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) || + unlikely(xmit_xfrm_check_overflow(skb)))) { struct sk_buff *segs; /* Packet got rerouted, fixup features and segment it. */ @@ -415,10 +416,12 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) struct net_device *dev = x->xso.dev; bool check_tunnel_size; - if (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED) + if (!x->type_offload || + (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED && x->encap)) return false; - if ((dev == xfrm_dst_path(dst)->dev) && !xdst->child->xfrm) { + if ((!dev || dev == xfrm_dst_path(dst)->dev) && + !xdst->child->xfrm) { mtu = xfrm_state_mtu(x, xdst->child_mtu_cached); if (skb->len <= mtu) goto ok; @@ -430,6 +433,9 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) return false; ok: + if (!dev) + return true; + check_tunnel_size = x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->props.mode == XFRM_MODE_TUNNEL; switch (x->props.family) { diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 77db3b5fe4ac..78fcbb89cf32 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -3297,7 +3297,7 @@ void xfrm_state_fini(struct net *net) unsigned int sz; flush_work(&net->xfrm.state_hash_work); - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); + xfrm_state_flush(net, 0, false); flush_work(&xfrm_state_gc_work); WARN_ON(!list_empty(&net->xfrm.state_all)); diff --git a/tools/testing/selftests/drivers/net/napi_threaded.py b/tools/testing/selftests/drivers/net/napi_threaded.py index b2698db39817..9699a100a87d 100755 --- a/tools/testing/selftests/drivers/net/napi_threaded.py +++ b/tools/testing/selftests/drivers/net/napi_threaded.py @@ -35,6 +35,8 @@ def _setup_deferred_cleanup(cfg) -> None: threaded = cmd(f"cat /sys/class/net/{cfg.ifname}/threaded").stdout defer(_set_threaded_state, cfg, threaded) + return combined + def enable_dev_threaded_disable_napi_threaded(cfg, nl) -> None: """ @@ -49,7 +51,7 @@ def enable_dev_threaded_disable_napi_threaded(cfg, nl) -> None: napi0_id = napis[0]['id'] napi1_id = napis[1]['id'] - _setup_deferred_cleanup(cfg) + qcnt = _setup_deferred_cleanup(cfg) # set threaded _set_threaded_state(cfg, 1) @@ -62,7 +64,7 @@ def enable_dev_threaded_disable_napi_threaded(cfg, nl) -> None: nl.napi_set({'id': napi1_id, 'threaded': 'disabled'}) cmd(f"ethtool -L {cfg.ifname} combined 1") - cmd(f"ethtool -L {cfg.ifname} combined 2") + cmd(f"ethtool -L {cfg.ifname} combined {qcnt}") _assert_napi_threaded_enabled(nl, napi0_id) _assert_napi_threaded_disabled(nl, napi1_id) @@ -80,7 +82,7 @@ def change_num_queues(cfg, nl) -> None: napi0_id = napis[0]['id'] napi1_id = napis[1]['id'] - _setup_deferred_cleanup(cfg) + qcnt = _setup_deferred_cleanup(cfg) # set threaded _set_threaded_state(cfg, 1) @@ -90,7 +92,7 @@ def change_num_queues(cfg, nl) -> None: _assert_napi_threaded_enabled(nl, napi1_id) cmd(f"ethtool -L {cfg.ifname} combined 1") - cmd(f"ethtool -L {cfg.ifname} combined 2") + cmd(f"ethtool -L {cfg.ifname} combined {qcnt}") # check napi threaded is set for both napis _assert_napi_threaded_enabled(nl, napi0_id) diff --git a/tools/testing/selftests/net/forwarding/sch_ets.sh b/tools/testing/selftests/net/forwarding/sch_ets.sh index 1f6f53e284b5..6269d5e23487 100755 --- a/tools/testing/selftests/net/forwarding/sch_ets.sh +++ b/tools/testing/selftests/net/forwarding/sch_ets.sh @@ -11,6 +11,7 @@ ALL_TESTS=" ets_test_strict ets_test_mixed ets_test_dwrr + ets_test_plug classifier_mode ets_test_strict ets_test_mixed diff --git a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh index 08240d3e3c87..79d837a2868a 100644 --- a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh +++ b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh @@ -224,3 +224,11 @@ ets_test_dwrr() ets_set_dwrr_two_bands xfail_on_slow ets_dwrr_test_01 } + +ets_test_plug() +{ + ets_change_qdisc $put 2 "3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3" "1514 1514" + tc qdisc add dev $put handle 20: parent 10:4 plug + start_traffic_pktsize 100 $h1.10 192.0.2.1 192.0.2.2 00:c1:a0:c1:a0:00 "-c 1" + ets_qdisc_setup $put 2 +} diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 5ded3b3a7538..d8cfcf9bb825 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -2708,6 +2708,69 @@ TEST(prequeue) { close(cfd); } +TEST(data_steal) { + struct tls_crypto_info_keys tls; + char buf[20000], buf2[20000]; + struct sockaddr_in addr; + int sfd, cfd, ret, fd; + int pid, status; + socklen_t len; + + len = sizeof(addr); + memrnd(buf, sizeof(buf)); + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_256, &tls, 0); + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + fd = socket(AF_INET, SOCK_STREAM, 0); + sfd = socket(AF_INET, SOCK_STREAM, 0); + + ASSERT_EQ(bind(sfd, &addr, sizeof(addr)), 0); + ASSERT_EQ(listen(sfd, 10), 0); + ASSERT_EQ(getsockname(sfd, &addr, &len), 0); + ASSERT_EQ(connect(fd, &addr, sizeof(addr)), 0); + ASSERT_GE(cfd = accept(sfd, &addr, &len), 0); + close(sfd); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (ret) { + ASSERT_EQ(errno, ENOENT); + SKIP(return, "no TLS support"); + } + ASSERT_EQ(setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")), 0); + + /* Spawn a child and get it into the read wait path of the underlying + * TCP socket. + */ + pid = fork(); + ASSERT_GE(pid, 0); + if (!pid) { + EXPECT_EQ(recv(cfd, buf, sizeof(buf), MSG_WAITALL), + sizeof(buf)); + exit(!__test_passed(_metadata)); + } + + usleep(2000); + ASSERT_EQ(setsockopt(fd, SOL_TLS, TLS_TX, &tls, tls.len), 0); + ASSERT_EQ(setsockopt(cfd, SOL_TLS, TLS_RX, &tls, tls.len), 0); + + EXPECT_EQ(send(fd, buf, sizeof(buf), 0), sizeof(buf)); + usleep(2000); + EXPECT_EQ(recv(cfd, buf2, sizeof(buf2), MSG_DONTWAIT), -1); + /* Don't check errno, the error will be different depending + * on what random bytes TLS interpreted as the record length. + */ + + close(fd); + close(cfd); + + EXPECT_EQ(wait(&status), pid); + EXPECT_EQ(status, 0); +} + static void __attribute__((constructor)) fips_check(void) { int res; FILE *f; diff --git a/tools/testing/selftests/proc/proc-maps-race.c b/tools/testing/selftests/proc/proc-maps-race.c index 66773685a047..94bba4553130 100644 --- a/tools/testing/selftests/proc/proc-maps-race.c +++ b/tools/testing/selftests/proc/proc-maps-race.c @@ -202,11 +202,11 @@ static void print_first_lines(char *text, int nr) int offs = end - text; text[offs] = '\0'; - printf(text); + printf("%s", text); text[offs] = '\n'; printf("\n"); } else { - printf(text); + printf("%s", text); } } @@ -221,7 +221,7 @@ static void print_last_lines(char *text, int nr) nr--; start--; } - printf(start); + printf("%s", start); } static void print_boundaries(const char *title, FIXTURE_DATA(proc_maps_race) *self) |