diff options
156 files changed, 2028 insertions, 820 deletions
diff --git a/Documentation/devicetree/bindings/net/airoha,en7581-npu.yaml b/Documentation/devicetree/bindings/net/airoha,en7581-npu.yaml index 76dd97c3fb40..c7644e6586d3 100644 --- a/Documentation/devicetree/bindings/net/airoha,en7581-npu.yaml +++ b/Documentation/devicetree/bindings/net/airoha,en7581-npu.yaml @@ -41,9 +41,21 @@ properties: - description: wlan irq line5 memory-region: - maxItems: 1 - description: - Memory used to store NPU firmware binary. + oneOf: + - items: + - description: NPU firmware binary region + - items: + - description: NPU firmware binary region + - description: NPU wlan offload RX buffers region + - description: NPU wlan offload TX buffers region + - description: NPU wlan offload TX packet identifiers region + + memory-region-names: + items: + - const: firmware + - const: pkt + - const: tx-pkt + - const: tx-bufid required: - compatible @@ -79,6 +91,8 @@ examples: <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>; - memory-region = <&npu_binary>; + memory-region = <&npu_firmware>, <&npu_pkt>, <&npu_txpkt>, + <&npu_txbufid>; + memory-region-names = "firmware", "pkt", "tx-pkt", "tx-bufid"; }; }; diff --git a/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml b/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml index 5f49bd9ac5e6..783a85b84893 100644 --- a/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml +++ b/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml @@ -56,7 +56,6 @@ properties: Regulator for supply voltage to VIN pin ti,rx-gain-reduction-db: - $ref: /schemas/types.yaml#/definitions/uint32 description: | Specify an RX gain reduction to reduce antenna sensitivity with 5dB per increment, with a maximum of 15dB. Supported values: [0, 5, 10, 15]. 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/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 1bc1bd7d33c2..7a7594713f1f 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -205,6 +205,9 @@ definitions: - name: gtp-teid - + name: ip6-fl + doc: IPv6 Flow Label + - name: discard value: 31 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 39d5e4e09273..4dcce7a5894b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11439,6 +11439,7 @@ 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 @@ -12584,10 +12585,9 @@ 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 @@ -12725,9 +12725,8 @@ 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 @@ -13687,7 +13686,6 @@ 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 @@ -15675,7 +15673,6 @@ 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 @@ -17452,6 +17449,7 @@ 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/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/airoha/airoha_npu.c b/drivers/net/ethernet/airoha/airoha_npu.c index a802f95df99d..1a6b191ae0b0 100644 --- a/drivers/net/ethernet/airoha/airoha_npu.c +++ b/drivers/net/ethernet/airoha/airoha_npu.c @@ -11,9 +11,9 @@ #include <linux/of_platform.h> #include <linux/of_reserved_mem.h> #include <linux/regmap.h> +#include <linux/soc/airoha/airoha_offload.h> #include "airoha_eth.h" -#include "airoha_npu.h" #define NPU_EN7581_FIRMWARE_DATA "airoha/en7581_npu_data.bin" #define NPU_EN7581_FIRMWARE_RV32 "airoha/en7581_npu_rv32.bin" @@ -42,6 +42,22 @@ #define REG_CR_MBQ8_CTRL(_n) (NPU_MBOX_BASE_ADDR + 0x0b0 + ((_n) << 2)) #define REG_CR_NPU_MIB(_n) (NPU_MBOX_BASE_ADDR + 0x140 + ((_n) << 2)) +#define NPU_WLAN_BASE_ADDR 0x30d000 + +#define REG_IRQ_STATUS (NPU_WLAN_BASE_ADDR + 0x030) +#define REG_IRQ_RXDONE(_n) (NPU_WLAN_BASE_ADDR + ((_n) << 2) + 0x034) +#define NPU_IRQ_RX_MASK(_n) ((_n) == 1 ? BIT(17) : BIT(16)) + +#define REG_TX_BASE(_n) (NPU_WLAN_BASE_ADDR + ((_n) << 4) + 0x080) +#define REG_TX_DSCP_NUM(_n) (NPU_WLAN_BASE_ADDR + ((_n) << 4) + 0x084) +#define REG_TX_CPU_IDX(_n) (NPU_WLAN_BASE_ADDR + ((_n) << 4) + 0x088) +#define REG_TX_DMA_IDX(_n) (NPU_WLAN_BASE_ADDR + ((_n) << 4) + 0x08c) + +#define REG_RX_BASE(_n) (NPU_WLAN_BASE_ADDR + ((_n) << 4) + 0x180) +#define REG_RX_DSCP_NUM(_n) (NPU_WLAN_BASE_ADDR + ((_n) << 4) + 0x184) +#define REG_RX_CPU_IDX(_n) (NPU_WLAN_BASE_ADDR + ((_n) << 4) + 0x188) +#define REG_RX_DMA_IDX(_n) (NPU_WLAN_BASE_ADDR + ((_n) << 4) + 0x18c) + #define NPU_TIMER_BASE_ADDR 0x310100 #define REG_WDT_TIMER_CTRL(_n) (NPU_TIMER_BASE_ADDR + ((_n) * 0x100)) #define WDT_EN_MASK BIT(25) @@ -124,6 +140,13 @@ struct ppe_mbox_data { }; }; +struct wlan_mbox_data { + u32 ifindex:4; + u32 func_type:4; + u32 func_id; + DECLARE_FLEX_ARRAY(u8, d); +}; + static int airoha_npu_send_msg(struct airoha_npu *npu, int func_id, void *p, int size) { @@ -390,6 +413,136 @@ out: return err; } +static int airoha_npu_wlan_msg_send(struct airoha_npu *npu, int ifindex, + enum airoha_npu_wlan_set_cmd func_id, + void *data, int data_len, gfp_t gfp) +{ + struct wlan_mbox_data *wlan_data; + int err, len; + + len = sizeof(*wlan_data) + data_len; + wlan_data = kzalloc(len, gfp); + if (!wlan_data) + return -ENOMEM; + + wlan_data->ifindex = ifindex; + wlan_data->func_type = NPU_OP_SET; + wlan_data->func_id = func_id; + memcpy(wlan_data->d, data, data_len); + + err = airoha_npu_send_msg(npu, NPU_FUNC_WIFI, wlan_data, len); + kfree(wlan_data); + + return err; +} + +static int airoha_npu_wlan_msg_get(struct airoha_npu *npu, int ifindex, + enum airoha_npu_wlan_get_cmd func_id, + void *data, int data_len, gfp_t gfp) +{ + struct wlan_mbox_data *wlan_data; + int err, len; + + len = sizeof(*wlan_data) + data_len; + wlan_data = kzalloc(len, gfp); + if (!wlan_data) + return -ENOMEM; + + wlan_data->ifindex = ifindex; + wlan_data->func_type = NPU_OP_GET; + wlan_data->func_id = func_id; + + err = airoha_npu_send_msg(npu, NPU_FUNC_WIFI, wlan_data, len); + if (!err) + memcpy(data, wlan_data->d, data_len); + kfree(wlan_data); + + return err; +} + +static int +airoha_npu_wlan_set_reserved_memory(struct airoha_npu *npu, + int ifindex, const char *name, + enum airoha_npu_wlan_set_cmd func_id) +{ + struct device *dev = npu->dev; + struct resource res; + int err; + u32 val; + + err = of_reserved_mem_region_to_resource_byname(dev->of_node, name, + &res); + if (err) + return err; + + val = res.start; + return airoha_npu_wlan_msg_send(npu, ifindex, func_id, &val, + sizeof(val), GFP_KERNEL); +} + +static int airoha_npu_wlan_init_memory(struct airoha_npu *npu) +{ + enum airoha_npu_wlan_set_cmd cmd = WLAN_FUNC_SET_WAIT_NPU_BAND0_ONCPU; + u32 val = 0; + int err; + + err = airoha_npu_wlan_msg_send(npu, 1, cmd, &val, sizeof(val), + GFP_KERNEL); + if (err) + return err; + + cmd = WLAN_FUNC_SET_WAIT_TX_BUF_CHECK_ADDR; + err = airoha_npu_wlan_set_reserved_memory(npu, 0, "tx-bufid", cmd); + if (err) + return err; + + cmd = WLAN_FUNC_SET_WAIT_PKT_BUF_ADDR; + err = airoha_npu_wlan_set_reserved_memory(npu, 0, "pkt", cmd); + if (err) + return err; + + cmd = WLAN_FUNC_SET_WAIT_TX_PKT_BUF_ADDR; + err = airoha_npu_wlan_set_reserved_memory(npu, 0, "tx-pkt", cmd); + if (err) + return err; + + cmd = WLAN_FUNC_SET_WAIT_IS_FORCE_TO_CPU; + return airoha_npu_wlan_msg_send(npu, 0, cmd, &val, sizeof(val), + GFP_KERNEL); +} + +static u32 airoha_npu_wlan_queue_addr_get(struct airoha_npu *npu, int qid, + bool xmit) +{ + if (xmit) + return REG_TX_BASE(qid + 2); + + return REG_RX_BASE(qid); +} + +static void airoha_npu_wlan_irq_status_set(struct airoha_npu *npu, u32 val) +{ + regmap_write(npu->regmap, REG_IRQ_STATUS, val); +} + +static u32 airoha_npu_wlan_irq_status_get(struct airoha_npu *npu, int q) +{ + u32 val; + + regmap_read(npu->regmap, REG_IRQ_STATUS, &val); + return val; +} + +static void airoha_npu_wlan_irq_enable(struct airoha_npu *npu, int q) +{ + regmap_set_bits(npu->regmap, REG_IRQ_RXDONE(q), NPU_IRQ_RX_MASK(q)); +} + +static void airoha_npu_wlan_irq_disable(struct airoha_npu *npu, int q) +{ + regmap_clear_bits(npu->regmap, REG_IRQ_RXDONE(q), NPU_IRQ_RX_MASK(q)); +} + struct airoha_npu *airoha_npu_get(struct device *dev, dma_addr_t *stats_addr) { struct platform_device *pdev; @@ -493,6 +646,14 @@ static int airoha_npu_probe(struct platform_device *pdev) npu->ops.ppe_deinit = airoha_npu_ppe_deinit; npu->ops.ppe_flush_sram_entries = airoha_npu_ppe_flush_sram_entries; npu->ops.ppe_foe_commit_entry = airoha_npu_foe_commit_entry; + npu->ops.wlan_init_reserved_memory = airoha_npu_wlan_init_memory; + npu->ops.wlan_send_msg = airoha_npu_wlan_msg_send; + npu->ops.wlan_get_msg = airoha_npu_wlan_msg_get; + npu->ops.wlan_get_queue_addr = airoha_npu_wlan_queue_addr_get; + npu->ops.wlan_set_irq_status = airoha_npu_wlan_irq_status_set; + npu->ops.wlan_get_irq_status = airoha_npu_wlan_irq_status_get; + npu->ops.wlan_enable_irq = airoha_npu_wlan_irq_enable; + npu->ops.wlan_disable_irq = airoha_npu_wlan_irq_disable; npu->regmap = devm_regmap_init_mmio(dev, base, ®map_config); if (IS_ERR(npu->regmap)) @@ -529,6 +690,15 @@ static int airoha_npu_probe(struct platform_device *pdev) INIT_WORK(&core->wdt_work, airoha_npu_wdt_work); } + /* wlan IRQ lines */ + for (i = 0; i < ARRAY_SIZE(npu->irqs); i++) { + irq = platform_get_irq(pdev, i + ARRAY_SIZE(npu->cores) + 1); + if (irq < 0) + return irq; + + npu->irqs[i] = irq; + } + err = dma_set_coherent_mask(dev, DMA_BIT_MASK(32)); if (err) return err; @@ -550,8 +720,7 @@ static int airoha_npu_probe(struct platform_device *pdev) usleep_range(1000, 2000); /* enable NPU cores */ - /* do not start core3 since it is used for WiFi offloading */ - regmap_write(npu->regmap, REG_CR_BOOT_CONFIG, 0xf7); + regmap_write(npu->regmap, REG_CR_BOOT_CONFIG, 0xff); regmap_write(npu->regmap, REG_CR_BOOT_TRIGGER, 0x1); msleep(100); diff --git a/drivers/net/ethernet/airoha/airoha_npu.h b/drivers/net/ethernet/airoha/airoha_npu.h deleted file mode 100644 index 98ec3be74ce4..000000000000 --- a/drivers/net/ethernet/airoha/airoha_npu.h +++ /dev/null @@ -1,36 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (c) 2025 AIROHA Inc - * Author: Lorenzo Bianconi <lorenzo@kernel.org> - */ - -#define NPU_NUM_CORES 8 - -struct airoha_npu { - struct device *dev; - struct regmap *regmap; - - struct airoha_npu_core { - struct airoha_npu *npu; - /* protect concurrent npu memory accesses */ - spinlock_t lock; - struct work_struct wdt_work; - } cores[NPU_NUM_CORES]; - - struct airoha_foe_stats __iomem *stats; - - struct { - int (*ppe_init)(struct airoha_npu *npu); - int (*ppe_deinit)(struct airoha_npu *npu); - int (*ppe_flush_sram_entries)(struct airoha_npu *npu, - dma_addr_t foe_addr, - int sram_num_entries); - int (*ppe_foe_commit_entry)(struct airoha_npu *npu, - dma_addr_t foe_addr, - u32 entry_size, u32 hash, - bool ppe2); - } ops; -}; - -struct airoha_npu *airoha_npu_get(struct device *dev, dma_addr_t *stats_addr); -void airoha_npu_put(struct airoha_npu *npu); diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index 47411d2cbd28..82163392332c 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -7,10 +7,10 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/rhashtable.h> +#include <linux/soc/airoha/airoha_offload.h> #include <net/ipv6.h> #include <net/pkt_cls.h> -#include "airoha_npu.h" #include "airoha_regs.h" #include "airoha_eth.h" diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 5578ddcb465d..2d4fdf5a0dc5 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) @@ -6957,6 +6969,8 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp) bp->rss_cap |= BNXT_RSS_CAP_ESP_V4_RSS_CAP; if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV6_CAP) bp->rss_cap |= BNXT_RSS_CAP_ESP_V6_RSS_CAP; + if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_IPV6_FLOW_LABEL_CAP) + bp->rss_cap |= BNXT_RSS_CAP_IPV6_FLOW_LABEL_RSS_CAP; if (flags & VNIC_QCAPS_RESP_FLAGS_RE_FLUSH_CAP) bp->fw_cap |= BNXT_FW_CAP_VNIC_RE_FLUSH; } @@ -16031,6 +16045,7 @@ 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/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index fda0d3cc6227..40ae34923511 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2407,6 +2407,7 @@ struct bnxt { #define BNXT_RSS_CAP_ESP_V4_RSS_CAP BIT(6) #define BNXT_RSS_CAP_ESP_V6_RSS_CAP BIT(7) #define BNXT_RSS_CAP_MULTI_RSS_CTX BIT(8) +#define BNXT_RSS_CAP_IPV6_FLOW_LABEL_RSS_CAP BIT(9) u8 rss_hash_key[HW_HASH_KEY_SIZE]; u8 rss_hash_key_valid:1; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 1b37612b1c01..68a4ee9f69b1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -1584,6 +1584,8 @@ static u64 get_ethtool_ipv6_rss(struct bnxt *bp) { if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6) return RXH_IP_SRC | RXH_IP_DST; + if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL) + return RXH_IP_SRC | RXH_IP_DST | RXH_IP6_FL; return 0; } @@ -1662,13 +1664,18 @@ static int bnxt_set_rxfh_fields(struct net_device *dev, if (cmd->data == RXH_4TUPLE) tuple = 4; - else if (cmd->data == RXH_2TUPLE) + else if (cmd->data == RXH_2TUPLE || + cmd->data == (RXH_2TUPLE | RXH_IP6_FL)) tuple = 2; else if (!cmd->data) tuple = 0; else return -EINVAL; + if (cmd->data & RXH_IP6_FL && + !(bp->rss_cap & BNXT_RSS_CAP_IPV6_FLOW_LABEL_RSS_CAP)) + return -EINVAL; + if (cmd->flow_type == TCP_V4_FLOW) { rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4; if (tuple == 4) @@ -1732,10 +1739,15 @@ static int bnxt_set_rxfh_fields(struct net_device *dev, case AH_V6_FLOW: case ESP_V6_FLOW: case IPV6_FLOW: - if (tuple == 2) + rss_hash_cfg &= ~(VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 | + VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL); + if (!tuple) + break; + if (cmd->data & RXH_IP6_FL) + rss_hash_cfg |= + VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL; + else if (tuple == 2) rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6; - else if (!tuple) - rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6; break; } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index ce95fad8cedd..ce55a1f59b50 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -4822,36 +4822,45 @@ static unsigned long fu540_macb_tx_recalc_rate(struct clk_hw *hw, return mgmt->rate; } -static long fu540_macb_tx_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *parent_rate) -{ - if (WARN_ON(rate < 2500000)) - return 2500000; - else if (rate == 2500000) - return 2500000; - else if (WARN_ON(rate < 13750000)) - return 2500000; - else if (WARN_ON(rate < 25000000)) - return 25000000; - else if (rate == 25000000) - return 25000000; - else if (WARN_ON(rate < 75000000)) - return 25000000; - else if (WARN_ON(rate < 125000000)) - return 125000000; - else if (rate == 125000000) - return 125000000; - - WARN_ON(rate > 125000000); - - return 125000000; +static int fu540_macb_tx_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) +{ + if (WARN_ON(req->rate < 2500000)) + req->rate = 2500000; + else if (req->rate == 2500000) + req->rate = 2500000; + else if (WARN_ON(req->rate < 13750000)) + req->rate = 2500000; + else if (WARN_ON(req->rate < 25000000)) + req->rate = 25000000; + else if (req->rate == 25000000) + req->rate = 25000000; + else if (WARN_ON(req->rate < 75000000)) + req->rate = 25000000; + else if (WARN_ON(req->rate < 125000000)) + req->rate = 125000000; + else if (req->rate == 125000000) + req->rate = 125000000; + else if (WARN_ON(req->rate > 125000000)) + req->rate = 125000000; + else + req->rate = 125000000; + + return 0; } static int fu540_macb_tx_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { - rate = fu540_macb_tx_round_rate(hw, rate, &parent_rate); - if (rate != 125000000) + struct clk_rate_request req; + int ret; + + clk_hw_init_rate_request(hw, &req, rate); + ret = fu540_macb_tx_determine_rate(hw, &req); + if (ret != 0) + return ret; + + if (req.rate != 125000000) iowrite32(1, mgmt->reg); else iowrite32(0, mgmt->reg); @@ -4862,7 +4871,7 @@ static int fu540_macb_tx_set_rate(struct clk_hw *hw, unsigned long rate, static const struct clk_ops fu540_c000_ops = { .recalc_rate = fu540_macb_tx_recalc_rate, - .round_rate = fu540_macb_tx_round_rate, + .determine_rate = fu540_macb_tx_determine_rate, .set_rate = fu540_macb_tx_set_rate, }; diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c index b3dc1afeefd1..38fb81db48c2 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c @@ -1016,8 +1016,7 @@ static int enetc4_pf_probe(struct pci_dev *pdev, err = devm_add_action_or_reset(dev, enetc4_pci_remove, pdev); if (err) - return dev_err_probe(dev, err, - "Add enetc4_pci_remove() action failed\n"); + return err; /* si is the private data. */ si = pci_get_drvdata(pdev); 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/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 8e0b06c1e02b..93c6e64ed940 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -9117,7 +9117,7 @@ static int ice_create_q_channels(struct ice_vsi *vsi) list_add_tail(&ch->list, &vsi->ch_list); vsi->tc_map_vsi[i] = ch->ch_vsi; dev_dbg(ice_pf_to_dev(pf), - "successfully created channel: VSI %pK\n", ch->ch_vsi); + "successfully created channel: VSI %p\n", ch->ch_vsi); } return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_trace.h b/drivers/net/ethernet/intel/ice/ice_trace.h index 07aab6e130cd..4f35ef8d6b29 100644 --- a/drivers/net/ethernet/intel/ice/ice_trace.h +++ b/drivers/net/ethernet/intel/ice/ice_trace.h @@ -130,7 +130,7 @@ DECLARE_EVENT_CLASS(ice_tx_template, __entry->buf = buf; __assign_str(devname);), - TP_printk("netdev: %s ring: %pK desc: %pK buf %pK", __get_str(devname), + TP_printk("netdev: %s ring: %p desc: %p buf %p", __get_str(devname), __entry->ring, __entry->desc, __entry->buf) ); @@ -158,7 +158,7 @@ DECLARE_EVENT_CLASS(ice_rx_template, __entry->desc = desc; __assign_str(devname);), - TP_printk("netdev: %s ring: %pK desc: %pK", __get_str(devname), + TP_printk("netdev: %s ring: %p desc: %p", __get_str(devname), __entry->ring, __entry->desc) ); DEFINE_EVENT(ice_rx_template, ice_clean_rx_irq, @@ -182,7 +182,7 @@ DECLARE_EVENT_CLASS(ice_rx_indicate_template, __entry->skb = skb; __assign_str(devname);), - TP_printk("netdev: %s ring: %pK desc: %pK skb %pK", __get_str(devname), + TP_printk("netdev: %s ring: %p desc: %p skb %p", __get_str(devname), __entry->ring, __entry->desc, __entry->skb) ); @@ -205,7 +205,7 @@ DECLARE_EVENT_CLASS(ice_xmit_template, __entry->skb = skb; __assign_str(devname);), - TP_printk("netdev: %s skb: %pK ring: %pK", __get_str(devname), + TP_printk("netdev: %s skb: %p ring: %p", __get_str(devname), __entry->skb, __entry->ring) ); @@ -228,7 +228,7 @@ DECLARE_EVENT_CLASS(ice_tx_tstamp_template, TP_fast_assign(__entry->skb = skb; __entry->idx = idx;), - TP_printk("skb %pK idx %d", + TP_printk("skb %p idx %d", __entry->skb, __entry->idx) ); #define DEFINE_TX_TSTAMP_OP_EVENT(name) \ 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/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 0a80d8f8cff7..3dbb113b792c 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -59,7 +59,9 @@ struct mtk_wed_flow_block_priv { static const struct mtk_wed_soc_data mt7622_data = { .regmap = { .tx_bm_tkid = 0x088, - .wpdma_rx_ring0 = 0x770, + .wpdma_rx_ring = { + 0x770, + }, .reset_idx_tx_mask = GENMASK(3, 0), .reset_idx_rx_mask = GENMASK(17, 16), }, @@ -70,7 +72,9 @@ static const struct mtk_wed_soc_data mt7622_data = { static const struct mtk_wed_soc_data mt7986_data = { .regmap = { .tx_bm_tkid = 0x0c8, - .wpdma_rx_ring0 = 0x770, + .wpdma_rx_ring = { + 0x770, + }, .reset_idx_tx_mask = GENMASK(1, 0), .reset_idx_rx_mask = GENMASK(7, 6), }, @@ -81,7 +85,10 @@ static const struct mtk_wed_soc_data mt7986_data = { static const struct mtk_wed_soc_data mt7988_data = { .regmap = { .tx_bm_tkid = 0x0c8, - .wpdma_rx_ring0 = 0x7d0, + .wpdma_rx_ring = { + 0x7d0, + 0x7d8, + }, .reset_idx_tx_mask = GENMASK(1, 0), .reset_idx_rx_mask = GENMASK(7, 6), }, @@ -621,8 +628,8 @@ mtk_wed_amsdu_init(struct mtk_wed_device *dev) return ret; } - /* eagle E1 PCIE1 tx ring 22 flow control issue */ - if (dev->wlan.id == 0x7991) + /* Kite and Eagle E1 PCIE1 tx ring 22 flow control issue */ + if (dev->wlan.id == 0x7991 || dev->wlan.id == 0x7992) wed_clr(dev, MTK_WED_AMSDU_FIFO, MTK_WED_AMSDU_IS_PRIOR0_RING); wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_TX_AMSDU_EN); @@ -1239,7 +1246,11 @@ mtk_wed_set_wpdma(struct mtk_wed_device *dev) return; wed_w32(dev, MTK_WED_WPDMA_RX_GLO_CFG, dev->wlan.wpdma_rx_glo); - wed_w32(dev, dev->hw->soc->regmap.wpdma_rx_ring0, dev->wlan.wpdma_rx); + wed_w32(dev, dev->hw->soc->regmap.wpdma_rx_ring[0], + dev->wlan.wpdma_rx[0]); + if (mtk_wed_is_v3_or_greater(dev->hw)) + wed_w32(dev, dev->hw->soc->regmap.wpdma_rx_ring[1], + dev->wlan.wpdma_rx[1]); if (!dev->wlan.hw_rro) return; @@ -2323,6 +2334,16 @@ mtk_wed_start(struct mtk_wed_device *dev, u32 irq_mask) if (!dev->rx_wdma[i].desc) mtk_wed_wdma_rx_ring_setup(dev, i, 16, false); + if (dev->wlan.hw_rro) { + for (i = 0; i < MTK_WED_RX_PAGE_QUEUES; i++) { + u32 addr = MTK_WED_RRO_MSDU_PG_CTRL0(i) + + MTK_WED_RING_OFS_COUNT; + + if (!wed_r32(dev, addr)) + wed_w32(dev, addr, 1); + } + } + mtk_wed_hw_init(dev); mtk_wed_configure_irq(dev, irq_mask); diff --git a/drivers/net/ethernet/mediatek/mtk_wed.h b/drivers/net/ethernet/mediatek/mtk_wed.h index c1f0479d7a71..b49aee9a8b65 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.h +++ b/drivers/net/ethernet/mediatek/mtk_wed.h @@ -17,7 +17,7 @@ struct mtk_wed_wo; struct mtk_wed_soc_data { struct { u32 tx_bm_tkid; - u32 wpdma_rx_ring0; + u32 wpdma_rx_ring[MTK_WED_RX_QUEUES]; u32 reset_idx_tx_mask; u32 reset_idx_rx_mask; } regmap; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h index 0537de86f981..9b0f44253f33 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h @@ -28,7 +28,7 @@ DECLARE_EVENT_CLASS(mlx5_sf_dev_template, __entry->hw_fn_id = sfdev->fn_id; __entry->sfnum = sfdev->sfnum; ), - TP_printk("(%s) sfdev=%pK aux_id=%d hw_id=0x%x sfnum=%u\n", + TP_printk("(%s) sfdev=%p aux_id=%d hw_id=0x%x sfnum=%u\n", __get_str(devname), __entry->sfdev, __entry->aux_id, __entry->hw_fn_id, __entry->sfnum) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c index dc7ba8d5fc43..461c8661eb93 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c @@ -1310,7 +1310,7 @@ fbnic_get_rss_hash_opts(struct net_device *netdev, #define FBNIC_L2_HASH_OPTIONS \ (RXH_L2DA | RXH_DISCARD) #define FBNIC_L3_HASH_OPTIONS \ - (FBNIC_L2_HASH_OPTIONS | RXH_IP_SRC | RXH_IP_DST) + (FBNIC_L2_HASH_OPTIONS | RXH_IP_SRC | RXH_IP_DST | RXH_IP6_FL) #define FBNIC_L4_HASH_OPTIONS \ (FBNIC_L3_HASH_OPTIONS | RXH_L4_B_0_1 | RXH_L4_B_2_3) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c index 8ff07b5562e3..a4dc1024c0c2 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c @@ -71,6 +71,8 @@ u16 fbnic_flow_hash_2_rss_en_mask(struct fbnic_net *fbn, int flow_type) rss_en_mask |= FBNIC_FH_2_RSSEM_BIT(IP_DST, IP_DST, flow_hash); rss_en_mask |= FBNIC_FH_2_RSSEM_BIT(L4_B_0_1, L4_SRC, flow_hash); rss_en_mask |= FBNIC_FH_2_RSSEM_BIT(L4_B_2_3, L4_DST, flow_hash); + rss_en_mask |= FBNIC_FH_2_RSSEM_BIT(IP6_FL, OV6_FL_LBL, flow_hash); + rss_en_mask |= FBNIC_FH_2_RSSEM_BIT(IP6_FL, IV6_FL_LBL, flow_hash); return rss_en_mask; } 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-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c index 889e2bb6f7f5..c2d9e89f0063 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c @@ -49,7 +49,7 @@ struct imx_dwmac_ops { u32 flags; bool mac_rgmii_txclk_auto_adj; - int (*fix_soc_reset)(void *priv, void __iomem *ioaddr); + int (*fix_soc_reset)(struct stmmac_priv *priv, void __iomem *ioaddr); int (*set_intf_mode)(struct plat_stmmacenet_data *plat_dat); void (*fix_mac_speed)(void *priv, int speed, unsigned int mode); }; @@ -265,9 +265,9 @@ static void imx93_dwmac_fix_speed(void *priv, int speed, unsigned int mode) writel(old_ctrl, dwmac->base_addr + MAC_CTRL_REG); } -static int imx_dwmac_mx93_reset(void *priv, void __iomem *ioaddr) +static int imx_dwmac_mx93_reset(struct stmmac_priv *priv, void __iomem *ioaddr) { - struct plat_stmmacenet_data *plat_dat = priv; + struct plat_stmmacenet_data *plat_dat = priv->plat; u32 value = readl(ioaddr + DMA_BUS_MODE); /* DMA SW reset */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index ea33ae39be6b..3fac3945cbfa 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -1231,6 +1231,37 @@ static int stmmac_config_multi_msi(struct pci_dev *pdev, return 0; } +static int intel_eth_pci_suspend(struct device *dev, void *bsp_priv) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret; + + ret = pci_save_state(pdev); + if (ret) + return ret; + + pci_wake_from_d3(pdev, true); + pci_set_power_state(pdev, PCI_D3hot); + return 0; +} + +static int intel_eth_pci_resume(struct device *dev, void *bsp_priv) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret; + + pci_restore_state(pdev); + pci_set_power_state(pdev, PCI_D0); + + ret = pcim_enable_device(pdev); + if (ret) + return ret; + + pci_set_master(pdev); + + return 0; +} + /** * intel_eth_pci_probe * @@ -1292,6 +1323,9 @@ static int intel_eth_pci_probe(struct pci_dev *pdev, pci_set_master(pdev); plat->bsp_priv = intel_priv; + plat->suspend = intel_eth_pci_suspend; + plat->resume = intel_eth_pci_resume; + intel_priv->mdio_adhoc_addr = INTEL_MGBE_ADHOC_ADDR; intel_priv->crossts_adj = 1; @@ -1355,44 +1389,6 @@ static void intel_eth_pci_remove(struct pci_dev *pdev) clk_unregister_fixed_rate(priv->plat->stmmac_clk); } -static int __maybe_unused intel_eth_pci_suspend(struct device *dev) -{ - struct pci_dev *pdev = to_pci_dev(dev); - int ret; - - ret = stmmac_suspend(dev); - if (ret) - return ret; - - ret = pci_save_state(pdev); - if (ret) - return ret; - - pci_wake_from_d3(pdev, true); - pci_set_power_state(pdev, PCI_D3hot); - return 0; -} - -static int __maybe_unused intel_eth_pci_resume(struct device *dev) -{ - struct pci_dev *pdev = to_pci_dev(dev); - int ret; - - pci_restore_state(pdev); - pci_set_power_state(pdev, PCI_D0); - - ret = pcim_enable_device(pdev); - if (ret) - return ret; - - pci_set_master(pdev); - - return stmmac_resume(dev); -} - -static SIMPLE_DEV_PM_OPS(intel_eth_pm_ops, intel_eth_pci_suspend, - intel_eth_pci_resume); - #define PCI_DEVICE_ID_INTEL_QUARK 0x0937 #define PCI_DEVICE_ID_INTEL_EHL_RGMII1G 0x4b30 #define PCI_DEVICE_ID_INTEL_EHL_SGMII1G 0x4b31 @@ -1442,7 +1438,7 @@ static struct pci_driver intel_eth_pci_driver = { .probe = intel_eth_pci_probe, .remove = intel_eth_pci_remove, .driver = { - .pm = &intel_eth_pm_ops, + .pm = &stmmac_simple_pm_ops, }, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index e1591e6217d4..6fca0fca4892 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -509,10 +509,15 @@ static int loongson_dwmac_acpi_config(struct pci_dev *pdev, } /* Loongson's DWMAC device may take nearly two seconds to complete DMA reset */ -static int loongson_dwmac_fix_reset(void *priv, void __iomem *ioaddr) +static int loongson_dwmac_fix_reset(struct stmmac_priv *priv, void __iomem *ioaddr) { u32 value = readl(ioaddr + DMA_BUS_MODE); + if (value & DMA_BUS_MODE_SFT_RESET) { + netdev_err(priv->dev, "the PHY clock is missing\n"); + return -EINVAL; + } + value |= DMA_BUS_MODE_SFT_RESET; writel(value, ioaddr + DMA_BUS_MODE); @@ -521,6 +526,37 @@ static int loongson_dwmac_fix_reset(void *priv, void __iomem *ioaddr) 10000, 2000000); } +static int loongson_dwmac_suspend(struct device *dev, void *bsp_priv) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret; + + ret = pci_save_state(pdev); + if (ret) + return ret; + + pci_disable_device(pdev); + pci_wake_from_d3(pdev, true); + return 0; +} + +static int loongson_dwmac_resume(struct device *dev, void *bsp_priv) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret; + + pci_restore_state(pdev); + pci_set_power_state(pdev, PCI_D0); + + ret = pci_enable_device(pdev); + if (ret) + return ret; + + pci_set_master(pdev); + + return 0; +} + static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct plat_stmmacenet_data *plat; @@ -565,6 +601,8 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id plat->bsp_priv = ld; plat->setup = loongson_dwmac_setup; plat->fix_soc_reset = loongson_dwmac_fix_reset; + plat->suspend = loongson_dwmac_suspend; + plat->resume = loongson_dwmac_resume; ld->dev = &pdev->dev; ld->loongson_id = readl(res.addr + GMAC_VERSION) & 0xff; @@ -621,44 +659,6 @@ static void loongson_dwmac_remove(struct pci_dev *pdev) pci_disable_device(pdev); } -static int __maybe_unused loongson_dwmac_suspend(struct device *dev) -{ - struct pci_dev *pdev = to_pci_dev(dev); - int ret; - - ret = stmmac_suspend(dev); - if (ret) - return ret; - - ret = pci_save_state(pdev); - if (ret) - return ret; - - pci_disable_device(pdev); - pci_wake_from_d3(pdev, true); - return 0; -} - -static int __maybe_unused loongson_dwmac_resume(struct device *dev) -{ - struct pci_dev *pdev = to_pci_dev(dev); - int ret; - - pci_restore_state(pdev); - pci_set_power_state(pdev, PCI_D0); - - ret = pci_enable_device(pdev); - if (ret) - return ret; - - pci_set_master(pdev); - - return stmmac_resume(dev); -} - -static SIMPLE_DEV_PM_OPS(loongson_dwmac_pm_ops, loongson_dwmac_suspend, - loongson_dwmac_resume); - static const struct pci_device_id loongson_dwmac_id_table[] = { { PCI_DEVICE_DATA(LOONGSON, GMAC1, &loongson_gmac_pci_info) }, { PCI_DEVICE_DATA(LOONGSON, GMAC2, &loongson_gmac_pci_info) }, @@ -673,7 +673,7 @@ static struct pci_driver loongson_dwmac_driver = { .probe = loongson_dwmac_probe, .remove = loongson_dwmac_remove, .driver = { - .pm = &loongson_dwmac_pm_ops, + .pm = &stmmac_simple_pm_ops, }, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c index 39421d6a34e4..f1b36f0a401d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c @@ -523,7 +523,7 @@ static int mediatek_dwmac_clk_init(struct mediatek_dwmac_plat_data *plat) return ret; } -static int mediatek_dwmac_init(struct platform_device *pdev, void *priv) +static int mediatek_dwmac_init(struct device *dev, void *priv) { struct mediatek_dwmac_plat_data *plat = priv; const struct mediatek_dwmac_variant *variant = plat->variant; @@ -532,7 +532,7 @@ static int mediatek_dwmac_init(struct platform_device *pdev, void *priv) if (variant->dwmac_set_phy_interface) { ret = variant->dwmac_set_phy_interface(plat); if (ret) { - dev_err(plat->dev, "failed to set phy interface, err = %d\n", ret); + dev_err(dev, "failed to set phy interface, err = %d\n", ret); return ret; } } @@ -540,7 +540,7 @@ static int mediatek_dwmac_init(struct platform_device *pdev, void *priv) if (variant->dwmac_set_delay) { ret = variant->dwmac_set_delay(plat); if (ret) { - dev_err(plat->dev, "failed to set delay value, err = %d\n", ret); + dev_err(dev, "failed to set delay value, err = %d\n", ret); return ret; } } @@ -589,7 +589,7 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev, plat->maxmtu = ETH_DATA_LEN; plat->host_dma_width = priv_plat->variant->dma_bit_mask; plat->bsp_priv = priv_plat; - plat->init = mediatek_dwmac_init; + plat->resume = mediatek_dwmac_init; plat->clks_config = mediatek_dwmac_clks_config; plat->safety_feat_cfg = devm_kzalloc(&pdev->dev, @@ -654,7 +654,7 @@ static int mediatek_dwmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); mediatek_dwmac_common_data(pdev, plat_dat, priv_plat); - mediatek_dwmac_init(pdev, priv_plat); + mediatek_dwmac_init(&pdev->dev, priv_plat); ret = mediatek_dwmac_clks_config(priv_plat, true); if (ret) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 79b92130a03f..7c898768d544 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -71,7 +71,6 @@ struct rk_priv_data { phy_interface_t phy_iface; int id; struct regulator *regulator; - bool suspended; const struct rk_gmac_ops *ops; bool clk_enabled; @@ -1706,6 +1705,28 @@ static int rk_set_clk_tx_rate(void *bsp_priv_, struct clk *clk_tx_i, return -EINVAL; } +static int rk_gmac_suspend(struct device *dev, void *bsp_priv_) +{ + struct rk_priv_data *bsp_priv = bsp_priv_; + + /* Keep the PHY up if we use Wake-on-Lan. */ + if (!device_may_wakeup(dev)) + rk_gmac_powerdown(bsp_priv); + + return 0; +} + +static int rk_gmac_resume(struct device *dev, void *bsp_priv_) +{ + struct rk_priv_data *bsp_priv = bsp_priv_; + + /* The PHY was up for Wake-on-Lan. */ + if (!device_may_wakeup(dev)) + rk_gmac_powerup(bsp_priv); + + return 0; +} + static int rk_gmac_probe(struct platform_device *pdev) { struct plat_stmmacenet_data *plat_dat; @@ -1738,6 +1759,8 @@ static int rk_gmac_probe(struct platform_device *pdev) plat_dat->get_interfaces = rk_get_interfaces; plat_dat->set_clk_tx_rate = rk_set_clk_tx_rate; + plat_dat->suspend = rk_gmac_suspend; + plat_dat->resume = rk_gmac_resume; plat_dat->bsp_priv = rk_gmac_setup(pdev, plat_dat, data); if (IS_ERR(plat_dat->bsp_priv)) @@ -1765,44 +1788,17 @@ 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); -} - -#ifdef CONFIG_PM_SLEEP -static int rk_gmac_suspend(struct device *dev) -{ - struct rk_priv_data *bsp_priv = get_stmmac_bsp_priv(dev); - int ret = stmmac_suspend(dev); - /* Keep the PHY up if we use Wake-on-Lan. */ - if (!device_may_wakeup(dev)) { - rk_gmac_powerdown(bsp_priv); - bsp_priv->suspended = true; - } - - return ret; + if (priv->plat->phy_node && bsp_priv->integrated_phy) + clk_put(bsp_priv->clk_phy); } -static int rk_gmac_resume(struct device *dev) -{ - struct rk_priv_data *bsp_priv = get_stmmac_bsp_priv(dev); - - /* The PHY was up for Wake-on-Lan. */ - if (bsp_priv->suspended) { - rk_gmac_powerup(bsp_priv); - bsp_priv->suspended = false; - } - - return stmmac_resume(dev); -} -#endif /* CONFIG_PM_SLEEP */ - -static SIMPLE_DEV_PM_OPS(rk_gmac_pm_ops, rk_gmac_suspend, rk_gmac_resume); - static const struct of_device_id rk_gmac_dwmac_match[] = { { .compatible = "rockchip,px30-gmac", .data = &px30_ops }, { .compatible = "rockchip,rk3128-gmac", .data = &rk3128_ops }, @@ -1828,7 +1824,7 @@ static struct platform_driver rk_gmac_dwmac_driver = { .remove = rk_gmac_remove, .driver = { .name = "rk_gmac-dwmac", - .pm = &rk_gmac_pm_ops, + .pm = &stmmac_simple_pm_ops, .of_match_table = rk_gmac_dwmac_match, }, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c index 1eb16eec9c0d..77a04c4579c9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c @@ -498,6 +498,26 @@ static int stm32mp1_parse_data(struct stm32_dwmac *dwmac, return err; } +static int stm32_dwmac_suspend(struct device *dev, void *bsp_priv) +{ + struct stm32_dwmac *dwmac = bsp_priv; + + stm32_dwmac_clk_disable(dwmac); + + return dwmac->ops->suspend ? dwmac->ops->suspend(dwmac) : 0; +} + +static int stm32_dwmac_resume(struct device *dev, void *bsp_priv) +{ + struct stmmac_priv *priv = netdev_priv(dev_get_drvdata(dev)); + struct stm32_dwmac *dwmac = bsp_priv; + + if (dwmac->ops->resume) + dwmac->ops->resume(dwmac); + + return stm32_dwmac_init(priv->plat); +} + static int stm32_dwmac_probe(struct platform_device *pdev) { struct plat_stmmacenet_data *plat_dat; @@ -535,6 +555,8 @@ static int stm32_dwmac_probe(struct platform_device *pdev) plat_dat->flags |= STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP; plat_dat->bsp_priv = dwmac; + plat_dat->suspend = stm32_dwmac_suspend; + plat_dat->resume = stm32_dwmac_resume; ret = stm32_dwmac_init(plat_dat); if (ret) @@ -600,50 +622,6 @@ static void stm32mp1_resume(struct stm32_dwmac *dwmac) clk_disable_unprepare(dwmac->clk_ethstp); } -#ifdef CONFIG_PM_SLEEP -static int stm32_dwmac_suspend(struct device *dev) -{ - struct net_device *ndev = dev_get_drvdata(dev); - struct stmmac_priv *priv = netdev_priv(ndev); - struct stm32_dwmac *dwmac = priv->plat->bsp_priv; - - int ret; - - ret = stmmac_suspend(dev); - if (ret) - return ret; - - stm32_dwmac_clk_disable(dwmac); - - if (dwmac->ops->suspend) - ret = dwmac->ops->suspend(dwmac); - - return ret; -} - -static int stm32_dwmac_resume(struct device *dev) -{ - struct net_device *ndev = dev_get_drvdata(dev); - struct stmmac_priv *priv = netdev_priv(ndev); - struct stm32_dwmac *dwmac = priv->plat->bsp_priv; - int ret; - - if (dwmac->ops->resume) - dwmac->ops->resume(dwmac); - - ret = stm32_dwmac_init(priv->plat); - if (ret) - return ret; - - ret = stmmac_resume(dev); - - return ret; -} -#endif /* CONFIG_PM_SLEEP */ - -static SIMPLE_DEV_PM_OPS(stm32_dwmac_pm_ops, - stm32_dwmac_suspend, stm32_dwmac_resume); - static struct stm32_ops stm32mcu_dwmac_data = { .set_mode = stm32mcu_set_mode }; @@ -691,7 +669,7 @@ static struct platform_driver stm32_dwmac_driver = { .remove = stm32_dwmac_remove, .driver = { .name = "stm32-dwmac", - .pm = &stm32_dwmac_pm_ops, + .pm = &stmmac_simple_pm_ops, .of_match_table = stm32_dwmac_match, }, }; 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/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index 4846bf49c576..467f1a05747e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -251,7 +251,7 @@ void dwmac_dma_flush_tx_fifo(void __iomem *ioaddr) void stmmac_set_mac_addr(void __iomem *ioaddr, const u8 addr[6], unsigned int high, unsigned int low) { - unsigned long data; + u32 data; data = (addr[5] << 8) | addr[4]; /* For MAC Addr registers we have to set the Address Enable (AE) diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c index 99635b37044a..3f7c765dcb79 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.c +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c @@ -100,7 +100,7 @@ int stmmac_reset(struct stmmac_priv *priv, void __iomem *ioaddr) return -EINVAL; if (plat && plat->fix_soc_reset) - return plat->fix_soc_reset(plat, ioaddr); + return plat->fix_soc_reset(priv, ioaddr); return stmmac_do_callback(priv, dma, reset, ioaddr); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index cda09cf5dcca..bf95f03dd33f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -374,6 +374,8 @@ enum stmmac_state { STMMAC_SERVICE_SCHED, }; +extern const struct dev_pm_ops stmmac_simple_pm_ops; + int stmmac_mdio_unregister(struct net_device *ndev); int stmmac_mdio_register(struct net_device *ndev); int stmmac_mdio_reset(struct mii_bus *mii); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f1abf4242cd2..9a77390b7f9d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -7879,6 +7879,9 @@ int stmmac_suspend(struct device *dev) if (stmmac_fpe_supported(priv)) ethtool_mmsv_stop(&priv->fpe_cfg.mmsv); + if (priv->plat->suspend) + return priv->plat->suspend(dev, priv->plat->bsp_priv); + return 0; } EXPORT_SYMBOL_GPL(stmmac_suspend); @@ -7931,6 +7934,12 @@ int stmmac_resume(struct device *dev) struct stmmac_priv *priv = netdev_priv(ndev); int ret; + if (priv->plat->resume) { + ret = priv->plat->resume(dev, priv->plat->bsp_priv); + if (ret) + return ret; + } + if (!netif_running(ndev)) return 0; @@ -7975,7 +7984,14 @@ int stmmac_resume(struct device *dev) stmmac_free_tx_skbufs(priv); stmmac_clear_descriptors(priv, &priv->dma_conf); - stmmac_hw_setup(ndev, false); + ret = stmmac_hw_setup(ndev, false); + if (ret < 0) { + netdev_err(priv->dev, "%s: Hw setup failed\n", __func__); + mutex_unlock(&priv->lock); + rtnl_unlock(); + return ret; + } + stmmac_init_coalesce(priv); phylink_rx_clk_stop_block(priv->phylink); stmmac_set_rx_mode(ndev); @@ -8004,6 +8020,9 @@ int stmmac_resume(struct device *dev) } EXPORT_SYMBOL_GPL(stmmac_resume); +EXPORT_GPL_SIMPLE_DEV_PM_OPS(stmmac_simple_pm_ops, stmmac_suspend, + stmmac_resume); + #ifndef MODULE static int __init stmmac_cmdline_opt(char *str) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 9c1b54b701f7..e6a7d0ddac2a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -138,6 +138,37 @@ static const struct stmmac_pci_info snps_gmac5_pci_info = { .setup = snps_gmac5_default_data, }; +static int stmmac_pci_suspend(struct device *dev, void *bsp_priv) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret; + + ret = pci_save_state(pdev); + if (ret) + return ret; + + pci_disable_device(pdev); + pci_wake_from_d3(pdev, true); + return 0; +} + +static int stmmac_pci_resume(struct device *dev, void *bsp_priv) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret; + + pci_restore_state(pdev); + pci_set_power_state(pdev, PCI_D0); + + ret = pci_enable_device(pdev); + if (ret) + return ret; + + pci_set_master(pdev); + + return 0; +} + /** * stmmac_pci_probe * @@ -217,6 +248,9 @@ static int stmmac_pci_probe(struct pci_dev *pdev, plat->safety_feat_cfg->prtyen = 1; plat->safety_feat_cfg->tmouten = 1; + plat->suspend = stmmac_pci_suspend; + plat->resume = stmmac_pci_resume; + return stmmac_dvr_probe(&pdev->dev, plat, &res); } @@ -231,43 +265,6 @@ static void stmmac_pci_remove(struct pci_dev *pdev) stmmac_dvr_remove(&pdev->dev); } -static int __maybe_unused stmmac_pci_suspend(struct device *dev) -{ - struct pci_dev *pdev = to_pci_dev(dev); - int ret; - - ret = stmmac_suspend(dev); - if (ret) - return ret; - - ret = pci_save_state(pdev); - if (ret) - return ret; - - pci_disable_device(pdev); - pci_wake_from_d3(pdev, true); - return 0; -} - -static int __maybe_unused stmmac_pci_resume(struct device *dev) -{ - struct pci_dev *pdev = to_pci_dev(dev); - int ret; - - pci_restore_state(pdev); - pci_set_power_state(pdev, PCI_D0); - - ret = pci_enable_device(pdev); - if (ret) - return ret; - - pci_set_master(pdev); - - return stmmac_resume(dev); -} - -static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_pci_suspend, stmmac_pci_resume); - /* synthetic ID, no official vendor */ #define PCI_VENDOR_ID_STMMAC 0x0700 @@ -289,7 +286,7 @@ static struct pci_driver stmmac_pci_driver = { .probe = stmmac_pci_probe, .remove = stmmac_pci_remove, .driver = { - .pm = &stmmac_pm_ops, + .pm = &stmmac_simple_pm_ops, }, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 030fcf1b5993..c849676d98e8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -811,6 +811,22 @@ static void stmmac_pltfr_exit(struct platform_device *pdev, plat->exit(pdev, plat->bsp_priv); } +static int stmmac_plat_suspend(struct device *dev, void *bsp_priv) +{ + struct stmmac_priv *priv = netdev_priv(dev_get_drvdata(dev)); + + stmmac_pltfr_exit(to_platform_device(dev), priv->plat); + + return 0; +} + +static int stmmac_plat_resume(struct device *dev, void *bsp_priv) +{ + struct stmmac_priv *priv = netdev_priv(dev_get_drvdata(dev)); + + return stmmac_pltfr_init(to_platform_device(dev), priv->plat); +} + /** * stmmac_pltfr_probe * @pdev: platform device pointer @@ -825,6 +841,11 @@ int stmmac_pltfr_probe(struct platform_device *pdev, { int ret; + if (!plat->suspend && plat->exit) + plat->suspend = stmmac_plat_suspend; + if (!plat->resume && plat->init) + plat->resume = stmmac_plat_resume; + ret = stmmac_pltfr_init(pdev, plat); if (ret) return ret; @@ -886,47 +907,6 @@ void stmmac_pltfr_remove(struct platform_device *pdev) } EXPORT_SYMBOL_GPL(stmmac_pltfr_remove); -/** - * stmmac_pltfr_suspend - * @dev: device pointer - * Description: this function is invoked when suspend the driver and it direcly - * call the main suspend function and then, if required, on some platform, it - * can call an exit helper. - */ -static int __maybe_unused stmmac_pltfr_suspend(struct device *dev) -{ - int ret; - struct net_device *ndev = dev_get_drvdata(dev); - struct stmmac_priv *priv = netdev_priv(ndev); - struct platform_device *pdev = to_platform_device(dev); - - ret = stmmac_suspend(dev); - stmmac_pltfr_exit(pdev, priv->plat); - - return ret; -} - -/** - * stmmac_pltfr_resume - * @dev: device pointer - * Description: this function is invoked when resume the driver before calling - * the main resume function, on some platforms, it can call own init helper - * if required. - */ -static int __maybe_unused stmmac_pltfr_resume(struct device *dev) -{ - struct net_device *ndev = dev_get_drvdata(dev); - struct stmmac_priv *priv = netdev_priv(ndev); - struct platform_device *pdev = to_platform_device(dev); - int ret; - - ret = stmmac_pltfr_init(pdev, priv->plat); - if (ret) - return ret; - - return stmmac_resume(dev); -} - static int __maybe_unused stmmac_runtime_suspend(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); @@ -994,7 +974,7 @@ static int __maybe_unused stmmac_pltfr_noirq_resume(struct device *dev) } const struct dev_pm_ops stmmac_pltfr_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_suspend, stmmac_pltfr_resume) + SET_SYSTEM_SLEEP_PM_OPS(stmmac_suspend, stmmac_resume) SET_RUNTIME_PM_OPS(stmmac_runtime_suspend, stmmac_runtime_resume, NULL) SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_noirq_suspend, stmmac_pltfr_noirq_resume) }; 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/ethernet/wangxun/libwx/wx_vf.h b/drivers/net/ethernet/wangxun/libwx/wx_vf.h index fec1126703e3..3f16de0fa427 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_vf.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_vf.h @@ -4,6 +4,7 @@ #ifndef _WX_VF_H_ #define _WX_VF_H_ +/* Control registers */ #define WX_VF_MAX_RING_NUMS 8 #define WX_VX_PF_BME 0x4B8 #define WX_VF_BME_ENABLE BIT(0) @@ -12,16 +13,32 @@ #define WX_VXCTRL_RST BIT(0) #define WX_VXMRQC 0x78 +#define WX_VXMRQC_PSR_L4HDR BIT(0) +#define WX_VXMRQC_PSR_L3HDR BIT(1) +#define WX_VXMRQC_PSR_L2HDR BIT(2) +#define WX_VXMRQC_PSR_TUNHDR BIT(3) +#define WX_VXMRQC_PSR_TUNMAC BIT(4) +#define WX_VXMRQC_PSR_MASK GENMASK(5, 1) +#define WX_VXMRQC_PSR(f) FIELD_PREP(GENMASK(5, 1), f) +#define WX_VXMRQC_RSS_HASH(f) FIELD_PREP(GENMASK(15, 13), f) +#define WX_VXMRQC_RSS_MASK GENMASK(31, 16) +#define WX_VXMRQC_RSS(f) FIELD_PREP(GENMASK(31, 16), f) +#define WX_VXMRQC_RSS_ALG_IPV4_TCP BIT(0) +#define WX_VXMRQC_RSS_ALG_IPV4 BIT(1) +#define WX_VXMRQC_RSS_ALG_IPV6 BIT(4) +#define WX_VXMRQC_RSS_ALG_IPV6_TCP BIT(5) +#define WX_VXMRQC_RSS_EN BIT(8) + +#define WX_VXRSSRK(i) (0x80 + ((i) * 4)) /* i=[0,9] */ +#define WX_VXRETA(i) (0xC0 + ((i) * 4)) /* i=[0,15] */ + +/* Interrupt registers */ #define WX_VXICR 0x100 #define WX_VXIMS 0x108 #define WX_VXIMC 0x10C #define WX_VF_IRQ_CLEAR_MASK 7 #define WX_VF_MAX_TX_QUEUES 4 #define WX_VF_MAX_RX_QUEUES 4 -#define WX_VXTXDCTL(r) (0x3010 + (0x40 * (r))) -#define WX_VXRXDCTL(r) (0x1010 + (0x40 * (r))) -#define WX_VXRXDCTL_ENABLE BIT(0) -#define WX_VXTXDCTL_FLUSH BIT(26) #define WX_VXITR(i) (0x200 + (4 * (i))) /* i=[0,1] */ #define WX_VXITR_MASK GENMASK(8, 0) @@ -29,16 +46,6 @@ #define WX_VXIVAR_MISC 0x260 #define WX_VXIVAR(i) (0x240 + (4 * (i))) /* i=[0,3] */ -#define WX_VXRXDCTL_RSCMAX(f) FIELD_PREP(GENMASK(24, 23), f) -#define WX_VXRXDCTL_BUFLEN(f) FIELD_PREP(GENMASK(6, 1), f) -#define WX_VXRXDCTL_BUFSZ(f) FIELD_PREP(GENMASK(11, 8), f) -#define WX_VXRXDCTL_HDRSZ(f) FIELD_PREP(GENMASK(15, 12), f) - -#define WX_VXRXDCTL_RSCMAX_MASK GENMASK(24, 23) -#define WX_VXRXDCTL_BUFLEN_MASK GENMASK(6, 1) -#define WX_VXRXDCTL_BUFSZ_MASK GENMASK(11, 8) -#define WX_VXRXDCTL_HDRSZ_MASK GENMASK(15, 12) - #define wx_conf_size(v, mwidth, uwidth) ({ \ typeof(v) _v = (v); \ (_v == 2 << (mwidth) ? 0 : _v >> (uwidth)); \ @@ -59,44 +66,35 @@ #define WX_VXRDBAH(r) (0x1004 + (0x40 * (r))) #define WX_VXRDT(r) (0x1008 + (0x40 * (r))) #define WX_VXRDH(r) (0x100C + (0x40 * (r))) - +#define WX_VXRXDCTL(r) (0x1010 + (0x40 * (r))) +#define WX_VXRXDCTL_ENABLE BIT(0) +#define WX_VXRXDCTL_BUFLEN_MASK GENMASK(6, 1) +#define WX_VXRXDCTL_BUFLEN(f) FIELD_PREP(GENMASK(6, 1), f) +#define WX_VXRXDCTL_BUFSZ_MASK GENMASK(11, 8) +#define WX_VXRXDCTL_BUFSZ(f) FIELD_PREP(GENMASK(11, 8), f) +#define WX_VXRXDCTL_HDRSZ_MASK GENMASK(15, 12) +#define WX_VXRXDCTL_HDRSZ(f) FIELD_PREP(GENMASK(15, 12), f) +#define WX_VXRXDCTL_RSCMAX_MASK GENMASK(24, 23) +#define WX_VXRXDCTL_RSCMAX(f) FIELD_PREP(GENMASK(24, 23), f) #define WX_VXRXDCTL_RSCEN BIT(29) #define WX_VXRXDCTL_DROP BIT(30) #define WX_VXRXDCTL_VLAN BIT(31) +/* Transimit Path */ #define WX_VXTDBAL(r) (0x3000 + (0x40 * (r))) #define WX_VXTDBAH(r) (0x3004 + (0x40 * (r))) #define WX_VXTDT(r) (0x3008 + (0x40 * (r))) #define WX_VXTDH(r) (0x300C + (0x40 * (r))) - +#define WX_VXTXDCTL(r) (0x3010 + (0x40 * (r))) #define WX_VXTXDCTL_ENABLE BIT(0) #define WX_VXTXDCTL_BUFLEN(f) FIELD_PREP(GENMASK(6, 1), f) #define WX_VXTXDCTL_PTHRESH(f) FIELD_PREP(GENMASK(11, 8), f) #define WX_VXTXDCTL_WTHRESH(f) FIELD_PREP(GENMASK(22, 16), f) - -#define WX_VXMRQC_PSR(f) FIELD_PREP(GENMASK(5, 1), f) -#define WX_VXMRQC_PSR_MASK GENMASK(5, 1) -#define WX_VXMRQC_PSR_L4HDR BIT(0) -#define WX_VXMRQC_PSR_L3HDR BIT(1) -#define WX_VXMRQC_PSR_L2HDR BIT(2) -#define WX_VXMRQC_PSR_TUNHDR BIT(3) -#define WX_VXMRQC_PSR_TUNMAC BIT(4) - -#define WX_VXRSSRK(i) (0x80 + ((i) * 4)) /* i=[0,9] */ -#define WX_VXRETA(i) (0xC0 + ((i) * 4)) /* i=[0,15] */ - -#define WX_VXMRQC_RSS(f) FIELD_PREP(GENMASK(31, 16), f) -#define WX_VXMRQC_RSS_MASK GENMASK(31, 16) -#define WX_VXMRQC_RSS_ALG_IPV4_TCP BIT(0) -#define WX_VXMRQC_RSS_ALG_IPV4 BIT(1) -#define WX_VXMRQC_RSS_ALG_IPV6 BIT(4) -#define WX_VXMRQC_RSS_ALG_IPV6_TCP BIT(5) -#define WX_VXMRQC_RSS_EN BIT(8) -#define WX_VXMRQC_RSS_HASH(f) FIELD_PREP(GENMASK(15, 13), f) +#define WX_VXTXDCTL_FLUSH BIT(26) #define WX_PFLINK_STATUS(g) FIELD_GET(BIT(0), g) #define WX_PFLINK_SPEED(g) FIELD_GET(GENMASK(31, 1), g) -#define WX_VXSTATUS_SPEED(g) FIELD_GET(GENMASK(4, 1), g) +#define WX_VXSTATUS_SPEED(g) FIELD_GET(GENMASK(4, 1), g) struct wx_link_reg_fields { u32 mac_type; 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/mdio/mdio-bcm-unimac.c b/drivers/net/mdio/mdio-bcm-unimac.c index 7baab230008a..37e35f282d9a 100644 --- a/drivers/net/mdio/mdio-bcm-unimac.c +++ b/drivers/net/mdio/mdio-bcm-unimac.c @@ -215,7 +215,9 @@ static int unimac_mdio_clk_set(struct unimac_mdio_priv *priv) div = (rate / (2 * priv->clk_freq)) - 1; if (div & ~MDIO_CLK_DIV_MASK) { - pr_warn("Incorrect MDIO clock frequency, ignoring\n"); + dev_warn(priv->mii_bus->parent, + "Ignoring MDIO clock frequency request: %d vs. rate: %ld\n", + priv->clk_freq, rate); ret = 0; goto out; } diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index e3722de08ea9..194570443493 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -300,6 +300,33 @@ static void netconsole_print_banner(struct netpoll *np) np_info(np, "remote ethernet address %pM\n", np->remote_mac); } +/* Parse the string and populate the `inet_addr` union. Return 0 if IPv4 is + * populated, 1 if IPv6 is populated, and -1 upon failure. + */ +static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr) +{ + const char *end = NULL; + int len; + + len = strlen(str); + if (!len) + return -1; + + if (str[len - 1] == '\n') + len -= 1; + + if (in4_pton(str, len, (void *)addr, -1, &end) > 0 && + (!end || *end == 0 || *end == '\n')) + return 0; + + if (IS_ENABLED(CONFIG_IPV6) && + in6_pton(str, len, (void *)addr, -1, &end) > 0 && + (!end || *end == 0 || *end == '\n')) + return 1; + + return -1; +} + #ifdef CONFIG_NETCONSOLE_DYNAMIC /* @@ -730,6 +757,7 @@ static ssize_t local_ip_store(struct config_item *item, const char *buf, { struct netconsole_target *nt = to_target(item); ssize_t ret = -EINVAL; + int ipv6; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { @@ -738,23 +766,10 @@ static ssize_t local_ip_store(struct config_item *item, const char *buf, goto out_unlock; } - if (strnchr(buf, count, ':')) { - const char *end; - - if (in6_pton(buf, count, nt->np.local_ip.in6.s6_addr, -1, &end) > 0) { - if (*end && *end != '\n') { - pr_err("invalid IPv6 address at: <%c>\n", *end); - goto out_unlock; - } - nt->np.ipv6 = true; - } else - goto out_unlock; - } else { - if (!nt->np.ipv6) - nt->np.local_ip.ip = in_aton(buf); - else - goto out_unlock; - } + ipv6 = netpoll_parse_ip_addr(buf, &nt->np.local_ip); + if (ipv6 == -1) + goto out_unlock; + nt->np.ipv6 = !!ipv6; ret = strnlen(buf, count); out_unlock: @@ -767,6 +782,7 @@ static ssize_t remote_ip_store(struct config_item *item, const char *buf, { struct netconsole_target *nt = to_target(item); ssize_t ret = -EINVAL; + int ipv6; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { @@ -775,23 +791,10 @@ static ssize_t remote_ip_store(struct config_item *item, const char *buf, goto out_unlock; } - if (strnchr(buf, count, ':')) { - const char *end; - - if (in6_pton(buf, count, nt->np.remote_ip.in6.s6_addr, -1, &end) > 0) { - if (*end && *end != '\n') { - pr_err("invalid IPv6 address at: <%c>\n", *end); - goto out_unlock; - } - nt->np.ipv6 = true; - } else - goto out_unlock; - } else { - if (!nt->np.ipv6) - nt->np.remote_ip.ip = in_aton(buf); - else - goto out_unlock; - } + ipv6 = netpoll_parse_ip_addr(buf, &nt->np.remote_ip); + if (ipv6 == -1) + goto out_unlock; + nt->np.ipv6 = !!ipv6; ret = strnlen(buf, count); out_unlock: @@ -1742,26 +1745,6 @@ static void write_msg(struct console *con, const char *msg, unsigned int len) spin_unlock_irqrestore(&target_list_lock, flags); } -static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr) -{ - const char *end; - - if (!strchr(str, ':') && - in4_pton(str, -1, (void *)addr, -1, &end) > 0) { - if (!*end) - return 0; - } - if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) { -#if IS_ENABLED(CONFIG_IPV6) - if (!*end) - return 1; -#else - return -1; -#endif - } - return -1; -} - static int netconsole_parser_cmdline(struct netpoll *np, char *opt) { bool ipversion_set = false; 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/tun.c b/drivers/net/tun.c index cc6c50180663..86a9e927d0ff 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2823,13 +2823,13 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (netif_running(tun->dev)) netif_tx_wake_all_queues(tun->dev); - strcpy(ifr->ifr_name, tun->dev->name); + strscpy(ifr->ifr_name, tun->dev->name); return 0; } static void tun_get_iff(struct tun_struct *tun, struct ifreq *ifr) { - strcpy(ifr->ifr_name, tun->dev->name); + strscpy(ifr->ifr_name, tun->dev->name); ifr->ifr_flags = tun_flags(tun); 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/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c index 4a82f8e4c118..36488aa6cc20 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c @@ -664,8 +664,8 @@ int mt7915_mmio_wed_init(struct mt7915_dev *dev, void *pdev_ptr, MT_RXQ_WED_RING_BASE; wed->wlan.wpdma_rx_glo = pci_resource_start(pci_dev, 0) + MT_WPDMA_GLO_CFG; - wed->wlan.wpdma_rx = pci_resource_start(pci_dev, 0) + - MT_RXQ_WED_DATA_RING_BASE; + wed->wlan.wpdma_rx[0] = pci_resource_start(pci_dev, 0) + + MT_RXQ_WED_DATA_RING_BASE; } else { struct platform_device *plat_dev = pdev_ptr; struct resource *res; @@ -687,7 +687,7 @@ int mt7915_mmio_wed_init(struct mt7915_dev *dev, void *pdev_ptr, wed->wlan.wpdma_tx = res->start + MT_TXQ_WED_RING_BASE; wed->wlan.wpdma_txfree = res->start + MT_RXQ_WED_RING_BASE; wed->wlan.wpdma_rx_glo = res->start + MT_WPDMA_GLO_CFG; - wed->wlan.wpdma_rx = res->start + MT_RXQ_WED_DATA_RING_BASE; + wed->wlan.wpdma_rx[0] = res->start + MT_RXQ_WED_DATA_RING_BASE; } wed->wlan.nbuf = MT7915_HW_TOKEN_SIZE; wed->wlan.tx_tbit[0] = is_mt7915(&dev->mt76) ? 4 : 30; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c index 30b40f4a91be..fb2428a9b877 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c @@ -503,9 +503,9 @@ int mt7996_mmio_wed_init(struct mt7996_dev *dev, void *pdev_ptr, } wed->wlan.wpdma_rx_glo = wed->wlan.phy_base + hif1_ofs + MT_WFDMA0_GLO_CFG; - wed->wlan.wpdma_rx = wed->wlan.phy_base + hif1_ofs + - MT_RXQ_RING_BASE(MT7996_RXQ_BAND0) + - MT7996_RXQ_BAND0 * MT_RING_SIZE; + wed->wlan.wpdma_rx[0] = wed->wlan.phy_base + hif1_ofs + + MT_RXQ_RING_BASE(MT7996_RXQ_BAND0) + + MT7996_RXQ_BAND0 * MT_RING_SIZE; wed->wlan.id = MT7996_DEVICE_ID_2; wed->wlan.tx_tbit[0] = ffs(MT_INT_TX_DONE_BAND2) - 1; @@ -518,9 +518,9 @@ int mt7996_mmio_wed_init(struct mt7996_dev *dev, void *pdev_ptr, wed->wlan.wpdma_rx_glo = wed->wlan.phy_base + MT_WFDMA0_GLO_CFG; - wed->wlan.wpdma_rx = wed->wlan.phy_base + - MT_RXQ_RING_BASE(MT7996_RXQ_BAND0) + - MT7996_RXQ_BAND0 * MT_RING_SIZE; + wed->wlan.wpdma_rx[0] = wed->wlan.phy_base + + MT_RXQ_RING_BASE(MT7996_RXQ_BAND0) + + MT7996_RXQ_BAND0 * MT_RING_SIZE; wed->wlan.wpdma_rx_rro[0] = wed->wlan.phy_base + MT_RXQ_RING_BASE(MT7996_RXQ_RRO_BAND0) + 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/erofs/Kconfig b/fs/erofs/Kconfig index 7b26efc271ee..d81f3318417d 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -3,8 +3,18 @@ config EROFS_FS tristate "EROFS filesystem support" depends on BLOCK + select CACHEFILES if EROFS_FS_ONDEMAND select CRC32 + select CRYPTO if EROFS_FS_ZIP_ACCEL + select CRYPTO_DEFLATE if EROFS_FS_ZIP_ACCEL select FS_IOMAP + select LZ4_DECOMPRESS if EROFS_FS_ZIP + select NETFS_SUPPORT if EROFS_FS_ONDEMAND + select XXHASH if EROFS_FS_XATTR + select XZ_DEC if EROFS_FS_ZIP_LZMA + select XZ_DEC_MICROLZMA if EROFS_FS_ZIP_LZMA + select ZLIB_INFLATE if EROFS_FS_ZIP_DEFLATE + select ZSTD_DECOMPRESS if EROFS_FS_ZIP_ZSTD help EROFS (Enhanced Read-Only File System) is a lightweight read-only file system with modern designs (e.g. no buffer heads, inline @@ -38,7 +48,6 @@ config EROFS_FS_DEBUG config EROFS_FS_XATTR bool "EROFS extended attributes" depends on EROFS_FS - select XXHASH default y help Extended attributes are name:value pairs associated with inodes by @@ -94,7 +103,6 @@ config EROFS_FS_BACKED_BY_FILE config EROFS_FS_ZIP bool "EROFS Data Compression Support" depends on EROFS_FS - select LZ4_DECOMPRESS default y help Enable transparent compression support for EROFS file systems. @@ -104,8 +112,6 @@ config EROFS_FS_ZIP config EROFS_FS_ZIP_LZMA bool "EROFS LZMA compressed data support" depends on EROFS_FS_ZIP - select XZ_DEC - select XZ_DEC_MICROLZMA help Saying Y here includes support for reading EROFS file systems containing LZMA compressed data, specifically called microLZMA. It @@ -117,7 +123,6 @@ config EROFS_FS_ZIP_LZMA config EROFS_FS_ZIP_DEFLATE bool "EROFS DEFLATE compressed data support" depends on EROFS_FS_ZIP - select ZLIB_INFLATE help Saying Y here includes support for reading EROFS file systems containing DEFLATE compressed data. It gives better compression @@ -132,7 +137,6 @@ config EROFS_FS_ZIP_DEFLATE config EROFS_FS_ZIP_ZSTD bool "EROFS Zstandard compressed data support" depends on EROFS_FS_ZIP - select ZSTD_DECOMPRESS help Saying Y here includes support for reading EROFS file systems containing Zstandard compressed data. It gives better compression @@ -147,8 +151,6 @@ config EROFS_FS_ZIP_ZSTD config EROFS_FS_ZIP_ACCEL bool "EROFS hardware decompression support" depends on EROFS_FS_ZIP - select CRYPTO - select CRYPTO_DEFLATE help Saying Y here includes hardware accelerator support for reading EROFS file systems containing compressed data. It gives better @@ -163,9 +165,7 @@ config EROFS_FS_ZIP_ACCEL config EROFS_FS_ONDEMAND bool "EROFS fscache-based on-demand read support (deprecated)" depends on EROFS_FS - select NETFS_SUPPORT select FSCACHE - select CACHEFILES select CACHEFILES_ONDEMAND help This permits EROFS to use fscache-backed data blobs with on-demand diff --git a/fs/erofs/super.c b/fs/erofs/super.c index e1020aa60771..1b529ace4db0 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -174,6 +174,11 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, if (!erofs_is_fileio_mode(sbi)) { dif->dax_dev = fs_dax_get_by_bdev(file_bdev(file), &dif->dax_part_off, NULL, NULL); + if (!dif->dax_dev && test_opt(&sbi->opt, DAX_ALWAYS)) { + erofs_info(sb, "DAX unsupported by %s. Turning off DAX.", + dif->path); + clear_opt(&sbi->opt, DAX_ALWAYS); + } } else if (!S_ISREG(file_inode(file)->i_mode)) { fput(file); return -EINVAL; @@ -210,8 +215,13 @@ static int erofs_scan_devices(struct super_block *sb, ondisk_extradevs, sbi->devs->extra_devices); return -EINVAL; } - if (!ondisk_extradevs) + if (!ondisk_extradevs) { + if (test_opt(&sbi->opt, DAX_ALWAYS) && !sbi->dif0.dax_dev) { + erofs_info(sb, "DAX unsupported by block device. Turning off DAX."); + clear_opt(&sbi->opt, DAX_ALWAYS); + } return 0; + } if (!sbi->devs->extra_devices && !erofs_is_fscache_mode(sb)) sbi->devs->flatdev = true; @@ -313,8 +323,8 @@ static int erofs_read_superblock(struct super_block *sb) sbi->islotbits = ilog2(sizeof(struct erofs_inode_compact)); if (erofs_sb_has_48bit(sbi) && dsb->rootnid_8b) { sbi->root_nid = le64_to_cpu(dsb->rootnid_8b); - sbi->dif0.blocks = (sbi->dif0.blocks << 32) | - le16_to_cpu(dsb->rb.blocks_hi); + sbi->dif0.blocks = sbi->dif0.blocks | + ((u64)le16_to_cpu(dsb->rb.blocks_hi) << 32); } else { sbi->root_nid = le16_to_cpu(dsb->rb.rootnid_2b); } @@ -338,7 +348,6 @@ static int erofs_read_superblock(struct super_block *sb) if (ret < 0) goto out; - /* handle multiple devices */ ret = erofs_scan_devices(sb, dsb); if (erofs_sb_has_48bit(sbi)) @@ -671,14 +680,9 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) return invalfc(fc, "cannot use fsoffset in fscache mode"); } - if (test_opt(&sbi->opt, DAX_ALWAYS)) { - if (!sbi->dif0.dax_dev) { - errorfc(fc, "DAX unsupported by block device. Turning off DAX."); - clear_opt(&sbi->opt, DAX_ALWAYS); - } else if (sbi->blkszbits != PAGE_SHIFT) { - errorfc(fc, "unsupported blocksize for DAX"); - clear_opt(&sbi->opt, DAX_ALWAYS); - } + if (test_opt(&sbi->opt, DAX_ALWAYS) && sbi->blkszbits != PAGE_SHIFT) { + erofs_info(sb, "unsupported blocksize for DAX"); + clear_opt(&sbi->opt, DAX_ALWAYS); } sb->s_time_gran = 1; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 792f20888a8f..2d73297003d2 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1432,6 +1432,16 @@ static void z_erofs_decompressqueue_kthread_work(struct kthread_work *work) } #endif +/* Use (kthread_)work in atomic contexts to minimize scheduling overhead */ +static inline bool z_erofs_in_atomic(void) +{ + if (IS_ENABLED(CONFIG_PREEMPTION) && rcu_preempt_depth()) + return true; + if (!IS_ENABLED(CONFIG_PREEMPT_COUNT)) + return true; + return !preemptible(); +} + static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, int bios) { @@ -1446,8 +1456,7 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, if (atomic_add_return(bios, &io->pending_bios)) return; - /* Use (kthread_)work and sync decompression for atomic contexts only */ - if (!in_task() || irqs_disabled() || rcu_read_lock_any_held()) { + if (z_erofs_in_atomic()) { #ifdef CONFIG_EROFS_FS_PCPU_KTHREAD struct kthread_worker *worker; 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/linux/soc/airoha/airoha_offload.h b/include/linux/soc/airoha/airoha_offload.h new file mode 100644 index 000000000000..117c63c2448d --- /dev/null +++ b/include/linux/soc/airoha/airoha_offload.h @@ -0,0 +1,260 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 AIROHA Inc + * Author: Lorenzo Bianconi <lorenzo@kernel.org> + */ +#ifndef AIROHA_OFFLOAD_H +#define AIROHA_OFFLOAD_H + +#include <linux/spinlock.h> +#include <linux/workqueue.h> + +#define NPU_NUM_CORES 8 +#define NPU_NUM_IRQ 6 +#define NPU_RX0_DESC_NUM 512 +#define NPU_RX1_DESC_NUM 512 + +/* CTRL */ +#define NPU_RX_DMA_DESC_LAST_MASK BIT(29) +#define NPU_RX_DMA_DESC_LEN_MASK GENMASK(28, 15) +#define NPU_RX_DMA_DESC_CUR_LEN_MASK GENMASK(14, 1) +#define NPU_RX_DMA_DESC_DONE_MASK BIT(0) +/* INFO */ +#define NPU_RX_DMA_PKT_COUNT_MASK GENMASK(31, 28) +#define NPU_RX_DMA_PKT_ID_MASK GENMASK(28, 26) +#define NPU_RX_DMA_SRC_PORT_MASK GENMASK(25, 21) +#define NPU_RX_DMA_CRSN_MASK GENMASK(20, 16) +#define NPU_RX_DMA_FOE_ID_MASK GENMASK(15, 0) +/* DATA */ +#define NPU_RX_DMA_SID_MASK GENMASK(31, 16) +#define NPU_RX_DMA_FRAG_TYPE_MASK GENMASK(15, 14) +#define NPU_RX_DMA_PRIORITY_MASK GENMASK(13, 10) +#define NPU_RX_DMA_RADIO_ID_MASK GENMASK(9, 6) +#define NPU_RX_DMA_VAP_ID_MASK GENMASK(5, 2) +#define NPU_RX_DMA_FRAME_TYPE_MASK GENMASK(1, 0) + +struct airoha_npu_rx_dma_desc { + u32 ctrl; + u32 info; + u32 data; + u32 addr; + u64 rsv; +} __packed; + +/* CTRL */ +#define NPU_TX_DMA_DESC_SCHED_MASK BIT(31) +#define NPU_TX_DMA_DESC_LEN_MASK GENMASK(30, 18) +#define NPU_TX_DMA_DESC_VEND_LEN_MASK GENMASK(17, 1) +#define NPU_TX_DMA_DESC_DONE_MASK BIT(0) + +#define NPU_TXWI_LEN 192 + +struct airoha_npu_tx_dma_desc { + u32 ctrl; + u32 addr; + u64 rsv; + u8 txwi[NPU_TXWI_LEN]; +} __packed; + +enum airoha_npu_wlan_set_cmd { + WLAN_FUNC_SET_WAIT_PCIE_ADDR, + WLAN_FUNC_SET_WAIT_DESC, + WLAN_FUNC_SET_WAIT_NPU_INIT_DONE, + WLAN_FUNC_SET_WAIT_TRAN_TO_CPU, + WLAN_FUNC_SET_WAIT_BA_WIN_SIZE, + WLAN_FUNC_SET_WAIT_DRIVER_MODEL, + WLAN_FUNC_SET_WAIT_DEL_STA, + WLAN_FUNC_SET_WAIT_DRAM_BA_NODE_ADDR, + WLAN_FUNC_SET_WAIT_PKT_BUF_ADDR, + WLAN_FUNC_SET_WAIT_IS_TEST_NOBA, + WLAN_FUNC_SET_WAIT_FLUSHONE_TIMEOUT, + WLAN_FUNC_SET_WAIT_FLUSHALL_TIMEOUT, + WLAN_FUNC_SET_WAIT_IS_FORCE_TO_CPU, + WLAN_FUNC_SET_WAIT_PCIE_STATE, + WLAN_FUNC_SET_WAIT_PCIE_PORT_TYPE, + WLAN_FUNC_SET_WAIT_ERROR_RETRY_TIMES, + WLAN_FUNC_SET_WAIT_BAR_INFO, + WLAN_FUNC_SET_WAIT_FAST_FLAG, + WLAN_FUNC_SET_WAIT_NPU_BAND0_ONCPU, + WLAN_FUNC_SET_WAIT_TX_RING_PCIE_ADDR, + WLAN_FUNC_SET_WAIT_TX_DESC_HW_BASE, + WLAN_FUNC_SET_WAIT_TX_BUF_SPACE_HW_BASE, + WLAN_FUNC_SET_WAIT_RX_RING_FOR_TXDONE_HW_BASE, + WLAN_FUNC_SET_WAIT_TX_PKT_BUF_ADDR, + WLAN_FUNC_SET_WAIT_INODE_TXRX_REG_ADDR, + WLAN_FUNC_SET_WAIT_INODE_DEBUG_FLAG, + WLAN_FUNC_SET_WAIT_INODE_HW_CFG_INFO, + WLAN_FUNC_SET_WAIT_INODE_STOP_ACTION, + WLAN_FUNC_SET_WAIT_INODE_PCIE_SWAP, + WLAN_FUNC_SET_WAIT_RATELIMIT_CTRL, + WLAN_FUNC_SET_WAIT_HWNAT_INIT, + WLAN_FUNC_SET_WAIT_ARHT_CHIP_INFO, + WLAN_FUNC_SET_WAIT_TX_BUF_CHECK_ADDR, + WLAN_FUNC_SET_WAIT_TOKEN_ID_SIZE, +}; + +enum airoha_npu_wlan_get_cmd { + WLAN_FUNC_GET_WAIT_NPU_INFO, + WLAN_FUNC_GET_WAIT_LAST_RATE, + WLAN_FUNC_GET_WAIT_COUNTER, + WLAN_FUNC_GET_WAIT_DBG_COUNTER, + WLAN_FUNC_GET_WAIT_RXDESC_BASE, + WLAN_FUNC_GET_WAIT_WCID_DBG_COUNTER, + WLAN_FUNC_GET_WAIT_DMA_ADDR, + WLAN_FUNC_GET_WAIT_RING_SIZE, + WLAN_FUNC_GET_WAIT_NPU_SUPPORT_MAP, + WLAN_FUNC_GET_WAIT_MDC_LOCK_ADDRESS, + WLAN_FUNC_GET_WAIT_NPU_VERSION, +}; + +struct airoha_npu { +#if (IS_BUILTIN(CONFIG_NET_AIROHA_NPU) || IS_MODULE(CONFIG_NET_AIROHA_NPU)) + struct device *dev; + struct regmap *regmap; + + struct airoha_npu_core { + struct airoha_npu *npu; + /* protect concurrent npu memory accesses */ + spinlock_t lock; + struct work_struct wdt_work; + } cores[NPU_NUM_CORES]; + + int irqs[NPU_NUM_IRQ]; + + struct airoha_foe_stats __iomem *stats; + + struct { + int (*ppe_init)(struct airoha_npu *npu); + int (*ppe_deinit)(struct airoha_npu *npu); + int (*ppe_flush_sram_entries)(struct airoha_npu *npu, + dma_addr_t foe_addr, + int sram_num_entries); + int (*ppe_foe_commit_entry)(struct airoha_npu *npu, + dma_addr_t foe_addr, + u32 entry_size, u32 hash, + bool ppe2); + int (*wlan_init_reserved_memory)(struct airoha_npu *npu); + int (*wlan_send_msg)(struct airoha_npu *npu, int ifindex, + enum airoha_npu_wlan_set_cmd func_id, + void *data, int data_len, gfp_t gfp); + int (*wlan_get_msg)(struct airoha_npu *npu, int ifindex, + enum airoha_npu_wlan_get_cmd func_id, + void *data, int data_len, gfp_t gfp); + u32 (*wlan_get_queue_addr)(struct airoha_npu *npu, int qid, + bool xmit); + void (*wlan_set_irq_status)(struct airoha_npu *npu, u32 val); + u32 (*wlan_get_irq_status)(struct airoha_npu *npu, int q); + void (*wlan_enable_irq)(struct airoha_npu *npu, int q); + void (*wlan_disable_irq)(struct airoha_npu *npu, int q); + } ops; +#endif +}; + +#if (IS_BUILTIN(CONFIG_NET_AIROHA_NPU) || IS_MODULE(CONFIG_NET_AIROHA_NPU)) +struct airoha_npu *airoha_npu_get(struct device *dev, dma_addr_t *stats_addr); +void airoha_npu_put(struct airoha_npu *npu); + +static inline int airoha_npu_wlan_init_reserved_memory(struct airoha_npu *npu) +{ + return npu->ops.wlan_init_reserved_memory(npu); +} + +static inline int airoha_npu_wlan_send_msg(struct airoha_npu *npu, + int ifindex, + enum airoha_npu_wlan_set_cmd cmd, + void *data, int data_len, gfp_t gfp) +{ + return npu->ops.wlan_send_msg(npu, ifindex, cmd, data, data_len, gfp); +} + +static inline int airoha_npu_wlan_get_msg(struct airoha_npu *npu, int ifindex, + enum airoha_npu_wlan_get_cmd cmd, + void *data, int data_len, gfp_t gfp) +{ + return npu->ops.wlan_get_msg(npu, ifindex, cmd, data, data_len, gfp); +} + +static inline u32 airoha_npu_wlan_get_queue_addr(struct airoha_npu *npu, + int qid, bool xmit) +{ + return npu->ops.wlan_get_queue_addr(npu, qid, xmit); +} + +static inline void airoha_npu_wlan_set_irq_status(struct airoha_npu *npu, + u32 val) +{ + npu->ops.wlan_set_irq_status(npu, val); +} + +static inline u32 airoha_npu_wlan_get_irq_status(struct airoha_npu *npu, int q) +{ + return npu->ops.wlan_get_irq_status(npu, q); +} + +static inline void airoha_npu_wlan_enable_irq(struct airoha_npu *npu, int q) +{ + npu->ops.wlan_enable_irq(npu, q); +} + +static inline void airoha_npu_wlan_disable_irq(struct airoha_npu *npu, int q) +{ + npu->ops.wlan_disable_irq(npu, q); +} +#else +static inline struct airoha_npu *airoha_npu_get(struct device *dev, + dma_addr_t *foe_stats_addr) +{ + return NULL; +} + +static inline void airoha_npu_put(struct airoha_npu *npu) +{ +} + +static inline int airoha_npu_wlan_init_reserved_memory(struct airoha_npu *npu) +{ + return -EOPNOTSUPP; +} + +static inline int airoha_npu_wlan_send_msg(struct airoha_npu *npu, + int ifindex, + enum airoha_npu_wlan_set_cmd cmd, + void *data, int data_len, gfp_t gfp) +{ + return -EOPNOTSUPP; +} + +static inline int airoha_npu_wlan_get_msg(struct airoha_npu *npu, int ifindex, + enum airoha_npu_wlan_get_cmd cmd, + void *data, int data_len, gfp_t gfp) +{ + return -EOPNOTSUPP; +} + +static inline u32 airoha_npu_wlan_get_queue_addr(struct airoha_npu *npu, + int qid, bool xmit) +{ + return 0; +} + +static inline void airoha_npu_wlan_set_irq_status(struct airoha_npu *npu, + u32 val) +{ +} + +static inline u32 airoha_npu_wlan_get_irq_status(struct airoha_npu *npu, + int q) +{ + return 0; +} + +static inline void airoha_npu_wlan_enable_irq(struct airoha_npu *npu, int q) +{ +} + +static inline void airoha_npu_wlan_disable_irq(struct airoha_npu *npu, int q) +{ +} +#endif + +#endif /* AIROHA_OFFLOAD_H */ diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index d8949a4ed0dc..c4ff6bab176d 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -147,7 +147,7 @@ struct mtk_wed_device { u32 wpdma_tx; u32 wpdma_txfree; u32 wpdma_rx_glo; - u32 wpdma_rx; + u32 wpdma_rx[MTK_WED_RX_QUEUES]; u32 wpdma_rx_rro[MTK_WED_RX_QUEUES]; u32 wpdma_rx_pg; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 26ddf95d23f9..e284f04964bf 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -238,7 +238,7 @@ struct plat_stmmacenet_data { int (*set_clk_tx_rate)(void *priv, struct clk *clk_tx_i, phy_interface_t interface, int speed); void (*fix_mac_speed)(void *priv, int speed, unsigned int mode); - int (*fix_soc_reset)(void *priv, void __iomem *ioaddr); + int (*fix_soc_reset)(struct stmmac_priv *priv, void __iomem *ioaddr); int (*serdes_powerup)(struct net_device *ndev, void *priv); void (*serdes_powerdown)(struct net_device *ndev, void *priv); int (*mac_finish)(struct net_device *ndev, @@ -248,6 +248,8 @@ struct plat_stmmacenet_data { void (*ptp_clk_freq_config)(struct stmmac_priv *priv); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); + int (*suspend)(struct device *dev, void *priv); + int (*resume)(struct device *dev, void *priv); struct mac_device_info *(*setup)(void *priv); int (*clks_config)(void *priv, bool enabled); int (*crosststamp)(ktime_t *device, struct system_counterval_t *system, 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/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 9e9afdd1238a..8bd5ea5469d9 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2380,6 +2380,7 @@ enum { #define RXH_L4_B_0_1 (1 << 6) /* src port in case of TCP/UDP/SCTP */ #define RXH_L4_B_2_3 (1 << 7) /* dst port in case of TCP/UDP/SCTP */ #define RXH_GTP_TEID (1 << 8) /* teid in case of GTP */ +#define RXH_IP6_FL (1 << 9) /* IPv6 flow label */ #define RXH_DISCARD (1 << 31) #define RX_CLS_FLOW_DISC 0xffffffffffffffffULL 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/caif/cfctrl.c b/net/caif/cfctrl.c index 06b604cf9d58..2aa1e7d46eb2 100644 --- a/net/caif/cfctrl.c +++ b/net/caif/cfctrl.c @@ -257,9 +257,7 @@ int cfctrl_linkup_request(struct cflayer *layer, cfpkt_add_body(pkt, &tmp16, 2); tmp16 = cpu_to_le16(param->u.utility.fifosize_bufs); cfpkt_add_body(pkt, &tmp16, 2); - memset(utility_name, 0, sizeof(utility_name)); - strscpy(utility_name, param->u.utility.name, - UTILITY_NAME_LENGTH); + strscpy_pad(utility_name, param->u.utility.name); cfpkt_add_body(pkt, utility_name, UTILITY_NAME_LENGTH); tmp8 = param->u.utility.paramlen; cfpkt_add_body(pkt, &tmp8, 1); 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/ethtool/ioctl.c b/net/ethtool/ioctl.c index 43a7854e784e..0b2a4d0573b3 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1014,6 +1014,28 @@ static bool flow_type_hashable(u32 flow_type) return false; } +static bool flow_type_v6(u32 flow_type) +{ + switch (flow_type) { + case TCP_V6_FLOW: + case UDP_V6_FLOW: + case SCTP_V6_FLOW: + case AH_ESP_V6_FLOW: + case AH_V6_FLOW: + case ESP_V6_FLOW: + case IPV6_FLOW: + case GTPU_V6_FLOW: + case GTPC_V6_FLOW: + case GTPC_TEID_V6_FLOW: + case GTPU_EH_V6_FLOW: + case GTPU_UL_V6_FLOW: + case GTPU_DL_V6_FLOW: + return true; + } + + return false; +} + /* When adding a new type, update the assert and, if it's hashable, add it to * the flow_type_hashable switch case. */ @@ -1077,6 +1099,9 @@ ethtool_set_rxfh_fields(struct net_device *dev, u32 cmd, void __user *useraddr) if (rc) return rc; + if (info.data & RXH_IP6_FL && !flow_type_v6(info.flow_type)) + return -EINVAL; + if (info.flow_type & FLOW_RSS && info.rss_context && !ops->rxfh_per_ctx_fields) return -EINVAL; diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 992e98abe9dd..202d95e8bf3e 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -536,35 +536,36 @@ void ethtool_rss_notify(struct net_device *dev, u32 type, u32 rss_context) #define RFH_MASK (RXH_L2DA | RXH_VLAN | RXH_IP_SRC | RXH_IP_DST | \ RXH_L3_PROTO | RXH_L4_B_0_1 | RXH_L4_B_2_3 | \ RXH_GTP_TEID | RXH_DISCARD) +#define RFH_MASKv6 (RFH_MASK | RXH_IP6_FL) static const struct nla_policy ethnl_rss_flows_policy[] = { [ETHTOOL_A_FLOW_ETHER] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), [ETHTOOL_A_FLOW_IP4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), - [ETHTOOL_A_FLOW_IP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_IP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASKv6), [ETHTOOL_A_FLOW_TCP4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), [ETHTOOL_A_FLOW_UDP4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), [ETHTOOL_A_FLOW_SCTP4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), [ETHTOOL_A_FLOW_AH_ESP4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), - [ETHTOOL_A_FLOW_TCP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), - [ETHTOOL_A_FLOW_UDP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), - [ETHTOOL_A_FLOW_SCTP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), - [ETHTOOL_A_FLOW_AH_ESP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_TCP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASKv6), + [ETHTOOL_A_FLOW_UDP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASKv6), + [ETHTOOL_A_FLOW_SCTP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASKv6), + [ETHTOOL_A_FLOW_AH_ESP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASKv6), [ETHTOOL_A_FLOW_AH4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), [ETHTOOL_A_FLOW_ESP4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), - [ETHTOOL_A_FLOW_AH6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), - [ETHTOOL_A_FLOW_ESP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_AH6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASKv6), + [ETHTOOL_A_FLOW_ESP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASKv6), [ETHTOOL_A_FLOW_GTPU4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), - [ETHTOOL_A_FLOW_GTPU6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPU6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASKv6), [ETHTOOL_A_FLOW_GTPC4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), - [ETHTOOL_A_FLOW_GTPC6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPC6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASKv6), [ETHTOOL_A_FLOW_GTPC_TEID4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), - [ETHTOOL_A_FLOW_GTPC_TEID6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPC_TEID6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASKv6), [ETHTOOL_A_FLOW_GTPU_EH4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), - [ETHTOOL_A_FLOW_GTPU_EH6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPU_EH6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASKv6), [ETHTOOL_A_FLOW_GTPU_UL4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), - [ETHTOOL_A_FLOW_GTPU_UL6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPU_UL6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASKv6), [ETHTOOL_A_FLOW_GTPU_DL4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), - [ETHTOOL_A_FLOW_GTPU_DL6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPU_DL6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASKv6), }; const struct nla_policy ethnl_rss_set_policy[ETHTOOL_A_RSS_FLOW_HASH + 1] = { 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/tcp_cdg.c b/net/ipv4/tcp_cdg.c index ba4d98e510e0..fbad6c35dee9 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -379,7 +379,7 @@ static void tcp_cdg_init(struct sock *sk) /* We silently fall back to window = 1 if allocation fails. */ if (window > 1) ca->gradients = kcalloc(window, sizeof(ca->gradients[0]), - GFP_NOWAIT | __GFP_NOWARN); + GFP_NOWAIT); ca->rtt_seq = tp->snd_nxt; ca->shadow_wnd = tcp_snd_cwnd(tp); } 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/phonet/af_phonet.c b/net/phonet/af_phonet.c index a27efa4faa4e..238a9638d2b0 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -22,7 +22,7 @@ #include <net/phonet/pn_dev.h> /* Transport protocol registration */ -static const struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly; +static const struct phonet_protocol __rcu *proto_tab[PHONET_NPROTO] __read_mostly; static const struct phonet_protocol *phonet_proto_get(unsigned int protocol) { @@ -482,7 +482,7 @@ void phonet_proto_unregister(unsigned int protocol, const struct phonet_protocol *pp) { mutex_lock(&proto_tab_lock); - BUG_ON(proto_tab[protocol] != pp); + BUG_ON(rcu_access_pointer(proto_tab[protocol]) != pp); RCU_INIT_POINTER(proto_tab[protocol], NULL); mutex_unlock(&proto_tab_lock); synchronize_rcu(); diff --git a/net/phonet/socket.c b/net/phonet/socket.c index ea4d5e6533db..2b61a40b568e 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -602,7 +602,7 @@ const struct seq_operations pn_sock_seq_ops = { #endif static struct { - struct sock *sk[256]; + struct sock __rcu *sk[256]; } pnres; /* @@ -654,7 +654,7 @@ int pn_sock_unbind_res(struct sock *sk, u8 res) return -EPERM; mutex_lock(&resource_mutex); - if (pnres.sk[res] == sk) { + if (rcu_access_pointer(pnres.sk[res]) == sk) { RCU_INIT_POINTER(pnres.sk[res], NULL); ret = 0; } @@ -673,7 +673,7 @@ void pn_sock_unbind_all_res(struct sock *sk) mutex_lock(&resource_mutex); for (res = 0; res < 256; res++) { - if (pnres.sk[res] == sk) { + if (rcu_access_pointer(pnres.sk[res]) == sk) { RCU_INIT_POINTER(pnres.sk[res], NULL); match++; } @@ -688,7 +688,7 @@ void pn_sock_unbind_all_res(struct sock *sk) } #ifdef CONFIG_PROC_FS -static struct sock **pn_res_get_idx(struct seq_file *seq, loff_t pos) +static struct sock __rcu **pn_res_get_idx(struct seq_file *seq, loff_t pos) { struct net *net = seq_file_net(seq); unsigned int i; @@ -697,7 +697,7 @@ static struct sock **pn_res_get_idx(struct seq_file *seq, loff_t pos) return NULL; for (i = 0; i < 256; i++) { - if (pnres.sk[i] == NULL) + if (rcu_access_pointer(pnres.sk[i]) == NULL) continue; if (!pos) return pnres.sk + i; @@ -706,7 +706,7 @@ static struct sock **pn_res_get_idx(struct seq_file *seq, loff_t pos) return NULL; } -static struct sock **pn_res_get_next(struct seq_file *seq, struct sock **sk) +static struct sock __rcu **pn_res_get_next(struct seq_file *seq, struct sock __rcu **sk) { struct net *net = seq_file_net(seq); unsigned int i; @@ -728,7 +728,7 @@ static void *pn_res_seq_start(struct seq_file *seq, loff_t *pos) static void *pn_res_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct sock **sk; + struct sock __rcu **sk; if (v == SEQ_START_TOKEN) sk = pn_res_get_idx(seq, 0); @@ -747,11 +747,12 @@ static void pn_res_seq_stop(struct seq_file *seq, void *v) static int pn_res_seq_show(struct seq_file *seq, void *v) { seq_setwidth(seq, 63); - if (v == SEQ_START_TOKEN) + if (v == SEQ_START_TOKEN) { seq_puts(seq, "rs uid inode"); - else { - struct sock **psk = v; - struct sock *sk = *psk; + } else { + struct sock __rcu **psk = v; + struct sock *sk = rcu_dereference_protected(*psk, + lockdep_is_held(&resource_mutex)); seq_printf(seq, "%02X %5u %lu", (int) (psk - pnres.sk), diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index e53b7f266bd7..4248dfa816eb 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -1034,7 +1034,7 @@ void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic, rds_ib_stats_inc(s_ib_rx_ring_empty); if (rds_ib_ring_low(&ic->i_recv_ring)) { - rds_ib_recv_refill(conn, 0, GFP_NOWAIT | __GFP_NOWARN); + rds_ib_recv_refill(conn, 0, GFP_NOWAIT); rds_ib_stats_inc(s_ib_rx_refill_from_cq); } } diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index f3abe0545989..8e69a919b4fe 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -72,7 +72,6 @@ static int reset_policy(struct tc_action *a, const struct nlattr *defdata, d = to_defact(a); spin_lock_bh(&d->tcf_lock); goto_ch = tcf_action_set_ctrlact(a, p->action, goto_ch); - memset(d->tcfd_defdata, 0, SIMP_MAX_DATA); nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA); spin_unlock_bh(&d->tcf_lock); if (goto_ch) 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..0538948d5fd9 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++; @@ -1028,12 +1029,7 @@ static int vsock_getname(struct socket *sock, vm_addr = &vsk->local_addr; } - /* sys_getsockname() and sys_getpeername() pass us a - * MAX_SOCK_ADDR-sized buffer and don't set addr_len. Unfortunately - * that macro is defined in socket.c instead of .h, so we hardcode its - * value here. - */ - BUILD_BUG_ON(sizeof(*vm_addr) > 128); + BUILD_BUG_ON(sizeof(*vm_addr) > sizeof(struct sockaddr_storage)); memcpy(addr, vm_addr, sizeof(*vm_addr)); err = sizeof(*vm_addr); 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/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index fdc97355588c..5159fd34cb33 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -18,6 +18,7 @@ TEST_PROGS = \ pp_alloc_fail.py \ rss_api.py \ rss_ctx.py \ + rss_flow_label.py \ rss_input_xfrm.py \ tso.py \ xsk_reconfig.py \ diff --git a/tools/testing/selftests/drivers/net/hw/config b/tools/testing/selftests/drivers/net/hw/config index 88ae719e6f8f..e8a06aa1471c 100644 --- a/tools/testing/selftests/drivers/net/hw/config +++ b/tools/testing/selftests/drivers/net/hw/config @@ -1,5 +1,7 @@ +CONFIG_IO_URING=y CONFIG_IPV6=y CONFIG_IPV6_GRE=y CONFIG_NET_IPGRE=y CONFIG_NET_IPGRE_DEMUX=y +CONFIG_UDMABUF=y CONFIG_VXLAN=y diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py index baa2f24240ba..45c2d49d55b6 100755 --- a/tools/testing/selftests/drivers/net/hw/devmem.py +++ b/tools/testing/selftests/drivers/net/hw/devmem.py @@ -24,7 +24,7 @@ def check_rx(cfg) -> None: require_devmem(cfg) port = rand_port() - socat = f"socat -u - TCP{cfg.addr_ipver}:{cfg.addr}:{port},bind={cfg.remote_addr}:{port}" + socat = f"socat -u - TCP{cfg.addr_ipver}:{cfg.baddr}:{port},bind={cfg.remote_baddr}:{port}" listen_cmd = f"{cfg.bin_local} -l -f {cfg.ifname} -s {cfg.addr} -p {port} -c {cfg.remote_addr} -v 7" with bkg(listen_cmd, exit_wait=True) as ncdevmem: @@ -42,9 +42,9 @@ def check_tx(cfg) -> None: port = rand_port() listen_cmd = f"socat -U - TCP{cfg.addr_ipver}-LISTEN:{port}" - with bkg(listen_cmd) as socat: - wait_port_listen(port) - cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_remote} -f {cfg.ifname} -s {cfg.addr} -p {port}", host=cfg.remote, shell=True) + with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as socat: + wait_port_listen(port, host=cfg.remote) + cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_local} -f {cfg.ifname} -s {cfg.remote_addr} -p {port}", shell=True) ksft_eq(socat.stdout.strip(), "hello\nworld") @@ -56,9 +56,9 @@ def check_tx_chunks(cfg) -> None: port = rand_port() listen_cmd = f"socat -U - TCP{cfg.addr_ipver}-LISTEN:{port}" - with bkg(listen_cmd, exit_wait=True) as socat: - wait_port_listen(port) - cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_remote} -f {cfg.ifname} -s {cfg.addr} -p {port} -z 3", host=cfg.remote, shell=True) + with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as socat: + wait_port_listen(port, host=cfg.remote) + cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_local} -f {cfg.ifname} -s {cfg.remote_addr} -p {port} -z 3", shell=True) ksft_eq(socat.stdout.strip(), "hello\nworld") diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c index 72f828021f83..be937542b4c0 100644 --- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c +++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c @@ -287,10 +287,10 @@ static int reset_flow_steering(void) * the exit status. */ - run_command("sudo ethtool -K %s ntuple off >&2", ifname); - run_command("sudo ethtool -K %s ntuple on >&2", ifname); + run_command("ethtool -K %s ntuple off >&2", ifname); + run_command("ethtool -K %s ntuple on >&2", ifname); run_command( - "sudo ethtool -n %s | grep 'Filter:' | awk '{print $2}' | xargs -n1 ethtool -N %s delete >&2", + "ethtool -n %s | grep 'Filter:' | awk '{print $2}' | xargs -n1 ethtool -N %s delete >&2", ifname, ifname); return 0; } @@ -351,12 +351,12 @@ static int configure_headersplit(bool on) static int configure_rss(void) { - return run_command("sudo ethtool -X %s equal %d >&2", ifname, start_queue); + return run_command("ethtool -X %s equal %d >&2", ifname, start_queue); } static int configure_channels(unsigned int rx, unsigned int tx) { - return run_command("sudo ethtool -L %s rx %u tx %u", ifname, rx, tx); + return run_command("ethtool -L %s rx %u tx %u", ifname, rx, tx); } static int configure_flow_steering(struct sockaddr_in6 *server_sin) @@ -374,7 +374,7 @@ static int configure_flow_steering(struct sockaddr_in6 *server_sin) } /* Try configure 5-tuple */ - if (run_command("sudo ethtool -N %s flow-type %s %s %s dst-ip %s %s %s dst-port %s queue %d >&2", + if (run_command("ethtool -N %s flow-type %s %s %s dst-ip %s %s %s dst-port %s queue %d >&2", ifname, type, client_ip ? "src-ip" : "", @@ -384,7 +384,7 @@ static int configure_flow_steering(struct sockaddr_in6 *server_sin) client_ip ? port : "", port, start_queue)) /* If that fails, try configure 3-tuple */ - if (run_command("sudo ethtool -N %s flow-type %s dst-ip %s dst-port %s queue %d >&2", + if (run_command("ethtool -N %s flow-type %s dst-ip %s dst-port %s queue %d >&2", ifname, type, server_addr, diff --git a/tools/testing/selftests/drivers/net/hw/rss_flow_label.py b/tools/testing/selftests/drivers/net/hw/rss_flow_label.py new file mode 100755 index 000000000000..6fa95fe27c47 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/rss_flow_label.py @@ -0,0 +1,167 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +Tests for RSS hashing on IPv6 Flow Label. +""" + +import glob +import os +import socket +from lib.py import CmdExitFailure +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge, ksft_in, \ + ksft_not_in, ksft_raises, KsftSkipEx +from lib.py import bkg, cmd, defer, fd_read_timeout, rand_port +from lib.py import NetDrvEpEnv + + +def _check_system(cfg): + if not hasattr(socket, "SO_INCOMING_CPU"): + raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11") + + qcnt = len(glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*")) + if qcnt < 2: + raise KsftSkipEx(f"Local has only {qcnt} queues") + + for f in [f"/sys/class/net/{cfg.ifname}/queues/rx-0/rps_flow_cnt", + f"/sys/class/net/{cfg.ifname}/queues/rx-0/rps_cpus"]: + try: + with open(f, 'r') as fp: + setting = fp.read().strip() + # CPU mask will be zeros and commas + if setting.replace("0", "").replace(",", ""): + raise KsftSkipEx(f"RPS/RFS is configured: {f}: {setting}") + except FileNotFoundError: + pass + + # 1 is the default, if someone changed it we probably shouldn"t mess with it + af = cmd("cat /proc/sys/net/ipv6/auto_flowlabels", host=cfg.remote).stdout + if af.strip() != "1": + raise KsftSkipEx("Remote does not have auto_flowlabels enabled") + + +def _ethtool_get_cfg(cfg, fl_type): + descr = cmd(f"ethtool -n {cfg.ifname} rx-flow-hash {fl_type}").stdout + + converter = { + "IP SA": "s", + "IP DA": "d", + "L3 proto": "t", + "L4 bytes 0 & 1 [TCP/UDP src port]": "f", + "L4 bytes 2 & 3 [TCP/UDP dst port]": "n", + "IPv6 Flow Label": "l", + } + + ret = "" + for line in descr.split("\n")[1:-2]: + # if this raises we probably need to add more keys to converter above + ret += converter[line] + return ret + + +def _traffic(cfg, one_sock, one_cpu): + local_port = rand_port(socket.SOCK_DGRAM) + remote_port = rand_port(socket.SOCK_DGRAM) + + sock = socket.socket(socket.AF_INET6, socket.SOCK_DGRAM) + sock.bind(("", local_port)) + sock.connect((cfg.remote_addr_v["6"], 0)) + if one_sock: + send = f"exec 5<>/dev/udp/{cfg.addr_v['6']}/{local_port}; " \ + "for i in `seq 20`; do echo a >&5; sleep 0.02; done; exec 5>&-" + else: + send = "for i in `seq 20`; do echo a | socat -t0.02 - UDP6:" \ + f"[{cfg.addr_v['6']}]:{local_port},sourceport={remote_port}; done" + + cpus = set() + with bkg(send, shell=True, host=cfg.remote, exit_wait=True): + for _ in range(20): + fd_read_timeout(sock.fileno(), 1) + cpu = sock.getsockopt(socket.SOL_SOCKET, socket.SO_INCOMING_CPU) + cpus.add(cpu) + + if one_cpu: + ksft_eq(len(cpus), 1, + f"{one_sock=} - expected one CPU, got traffic on: {cpus=}") + else: + ksft_ge(len(cpus), 2, + f"{one_sock=} - expected many CPUs, got traffic on: {cpus=}") + + +def test_rss_flow_label(cfg): + """ + Test hashing on IPv6 flow label. Send traffic over a single socket + and over multiple sockets. Depend on the remote having auto-label + enabled so that it randomizes the label per socket. + """ + + cfg.require_ipver("6") + cfg.require_cmd("socat", remote=True) + _check_system(cfg) + + # Enable flow label hashing for UDP6 + initial = _ethtool_get_cfg(cfg, "udp6") + no_lbl = initial.replace("l", "") + if "l" not in initial: + try: + cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 l{no_lbl}") + except CmdExitFailure as exc: + raise KsftSkipEx("Device doesn't support Flow Label for UDP6") from exc + + defer(cmd, f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {initial}") + + _traffic(cfg, one_sock=True, one_cpu=True) + _traffic(cfg, one_sock=False, one_cpu=False) + + # Disable it, we should see no hashing (reset was already defer()ed) + cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {no_lbl}") + + _traffic(cfg, one_sock=False, one_cpu=True) + + +def _check_v4_flow_types(cfg): + for fl_type in ["tcp4", "udp4", "ah4", "esp4", "sctp4"]: + try: + cur = cmd(f"ethtool -n {cfg.ifname} rx-flow-hash {fl_type}").stdout + ksft_not_in("Flow Label", cur, + comment=f"{fl_type=} has Flow Label:" + cur) + except CmdExitFailure: + # Probably does not support this flow type + pass + + +def test_rss_flow_label_6only(cfg): + """ + Test interactions with IPv4 flow types. It should not be possible to set + IPv6 Flow Label hashing for an IPv4 flow type. The Flow Label should also + not appear in the IPv4 "current config". + """ + + with ksft_raises(CmdExitFailure) as cm: + cmd(f"ethtool -N {cfg.ifname} rx-flow-hash tcp4 sdfnl") + ksft_in("Invalid argument", cm.exception.cmd.stderr) + + _check_v4_flow_types(cfg) + + # Try to enable Flow Labels and check again, in case it leaks thru + initial = _ethtool_get_cfg(cfg, "udp6") + changed = initial.replace("l", "") if "l" in initial else initial + "l" + + cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {changed}") + restore = defer(cmd, f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {initial}") + + _check_v4_flow_types(cfg) + restore.exec() + _check_v4_flow_types(cfg) + + +def main() -> None: + with NetDrvEpEnv(__file__, nsim_test=False) as cfg: + ksft_run([test_rss_flow_label, + test_rss_flow_label_6only], + args=(cfg, )) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh index b6071e80ebbb..8e1085e89647 100644 --- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh +++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh @@ -148,12 +148,20 @@ function create_dynamic_target() { # Generate the command line argument for netconsole following: # netconsole=[+][src-port]@[src-ip]/[<dev>],[tgt-port]@<tgt-ip>/[tgt-macaddr] function create_cmdline_str() { + local BINDMODE=${1:-"ifname"} + if [ "${BINDMODE}" == "ifname" ] + then + SRCDEV=${SRCIF} + else + SRCDEV=$(mac_get "${SRCIF}") + fi + DSTMAC=$(ip netns exec "${NAMESPACE}" \ ip link show "${DSTIF}" | awk '/ether/ {print $2}') SRCPORT="1514" TGTPORT="6666" - echo "netconsole=\"+${SRCPORT}@${SRCIP}/${SRCIF},${TGTPORT}@${DSTIP}/${DSTMAC}\"" + echo "netconsole=\"+${SRCPORT}@${SRCIP}/${SRCDEV},${TGTPORT}@${DSTIP}/${DSTMAC}\"" } # Do not append the release to the header of the message 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/drivers/net/netcons_cmdline.sh b/tools/testing/selftests/drivers/net/netcons_cmdline.sh index ad2fb8b1c463..d1d23dc67f99 100755 --- a/tools/testing/selftests/drivers/net/netcons_cmdline.sh +++ b/tools/testing/selftests/drivers/net/netcons_cmdline.sh @@ -19,9 +19,6 @@ check_netconsole_module modprobe netdevsim 2> /dev/null || true rmmod netconsole 2> /dev/null || true -# The content of kmsg will be save to the following file -OUTPUT_FILE="/tmp/${TARGET}" - # Check for basic system dependency and exit if not found # check_for_dependencies # Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5) @@ -30,23 +27,39 @@ echo "6 5" > /proc/sys/kernel/printk trap do_cleanup EXIT # Create one namespace and two interfaces set_network -# Create the command line for netconsole, with the configuration from the -# function above -CMDLINE="$(create_cmdline_str)" - -# Load the module, with the cmdline set -modprobe netconsole "${CMDLINE}" - -# Listed for netconsole port inside the namespace and destination interface -listen_port_and_save_to "${OUTPUT_FILE}" & -# Wait for socat to start and listen to the port. -wait_local_port_listen "${NAMESPACE}" "${PORT}" udp -# Send the message -echo "${MSG}: ${TARGET}" > /dev/kmsg -# Wait until socat saves the file to disk -busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" -# Make sure the message was received in the dst part -# and exit -validate_msg "${OUTPUT_FILE}" + +# Run the test twice, with different cmdline parameters +for BINDMODE in "ifname" "mac" +do + echo "Running with bind mode: ${BINDMODE}" >&2 + # Create the command line for netconsole, with the configuration from + # the function above + CMDLINE=$(create_cmdline_str "${BINDMODE}") + + # The content of kmsg will be save to the following file + OUTPUT_FILE="/tmp/${TARGET}-${BINDMODE}" + + # Load the module, with the cmdline set + modprobe netconsole "${CMDLINE}" + + # Listed for netconsole port inside the namespace and destination + # interface + listen_port_and_save_to "${OUTPUT_FILE}" & + # Wait for socat to start and listen to the port. + wait_local_port_listen "${NAMESPACE}" "${PORT}" udp + # Send the message + echo "${MSG}: ${TARGET}" > /dev/kmsg + # Wait until socat saves the file to disk + busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" + # Make sure the message was received in the dst part + # and exit + validate_msg "${OUTPUT_FILE}" + + # kill socat in case it is still running + pkill_socat + # Unload the module + rmmod netconsole + echo "${BINDMODE} : Test passed" >&2 +done exit "${ksft_pass}" diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index a4b61c6d0290..0a20c98bbcfd 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,4 +1,4 @@ -CFLAGS += $(KHDR_INCLUDES) +CFLAGS += $(KHDR_INCLUDES) -Wall -Wflex-array-member-not-at-end TEST_GEN_PROGS := diag_uid msg_oob scm_inq scm_pidfd scm_rights unix_connect include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/scm_inq.c b/tools/testing/selftests/net/af_unix/scm_inq.c index 9d22561e7b8f..fc467714387e 100644 --- a/tools/testing/selftests/net/af_unix/scm_inq.c +++ b/tools/testing/selftests/net/af_unix/scm_inq.c @@ -11,11 +11,6 @@ #define NR_CHUNKS 100 #define MSG_LEN 256 -struct scm_inq { - struct cmsghdr cmsghdr; - int inq; -}; - FIXTURE(scm_inq) { int fd[2]; @@ -70,35 +65,38 @@ static void send_chunks(struct __test_metadata *_metadata, static void recv_chunks(struct __test_metadata *_metadata, FIXTURE_DATA(scm_inq) *self) { + char cmsg_buf[CMSG_SPACE(sizeof(int))]; struct msghdr msg = {}; struct iovec iov = {}; - struct scm_inq cmsg; + struct cmsghdr *cmsg; char buf[MSG_LEN]; int i, ret; int inq; msg.msg_iov = &iov; msg.msg_iovlen = 1; - msg.msg_control = &cmsg; - msg.msg_controllen = CMSG_SPACE(sizeof(cmsg.inq)); + msg.msg_control = cmsg_buf; + msg.msg_controllen = sizeof(cmsg_buf); iov.iov_base = buf; iov.iov_len = sizeof(buf); for (i = 0; i < NR_CHUNKS; i++) { memset(buf, 0, sizeof(buf)); - memset(&cmsg, 0, sizeof(cmsg)); + memset(cmsg_buf, 0, sizeof(cmsg_buf)); ret = recvmsg(self->fd[1], &msg, 0); ASSERT_EQ(MSG_LEN, ret); - ASSERT_NE(NULL, CMSG_FIRSTHDR(&msg)); - ASSERT_EQ(CMSG_LEN(sizeof(cmsg.inq)), cmsg.cmsghdr.cmsg_len); - ASSERT_EQ(SOL_SOCKET, cmsg.cmsghdr.cmsg_level); - ASSERT_EQ(SCM_INQ, cmsg.cmsghdr.cmsg_type); + + cmsg = CMSG_FIRSTHDR(&msg); + ASSERT_NE(NULL, cmsg); + ASSERT_EQ(CMSG_LEN(sizeof(int)), cmsg->cmsg_len); + ASSERT_EQ(SOL_SOCKET, cmsg->cmsg_level); + ASSERT_EQ(SCM_INQ, cmsg->cmsg_type); ret = ioctl(self->fd[1], SIOCINQ, &inq); ASSERT_EQ(0, ret); - ASSERT_EQ(cmsg.inq, inq); + ASSERT_EQ(*(int *)CMSG_DATA(cmsg), inq); } } diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c index 37e034874034..ef2921988e5f 100644 --- a/tools/testing/selftests/net/af_unix/scm_pidfd.c +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -137,7 +137,6 @@ struct cmsg_data { static int parse_cmsg(struct msghdr *msg, struct cmsg_data *res) { struct cmsghdr *cmsg; - int data = 0; if (msg->msg_flags & (MSG_TRUNC | MSG_CTRUNC)) { log_err("recvmsg: truncated"); @@ -243,7 +242,6 @@ static int cmsg_check_dead(int fd, int expected_pid) int data = 0; char control[CMSG_SPACE(sizeof(struct ucred)) + CMSG_SPACE(sizeof(int))] = { 0 }; - pid_t client_pid; struct pidfd_info info = { .mask = PIDFD_INFO_EXIT, }; diff --git a/tools/testing/selftests/net/af_unix/scm_rights.c b/tools/testing/selftests/net/af_unix/scm_rights.c index 8b015f16c03d..914f99d153ce 100644 --- a/tools/testing/selftests/net/af_unix/scm_rights.c +++ b/tools/testing/selftests/net/af_unix/scm_rights.c @@ -271,20 +271,11 @@ void __send_fd(struct __test_metadata *_metadata, { #define MSG "x" #define MSGLEN 1 - struct { - struct cmsghdr cmsghdr; - int fd[2]; - } cmsg = { - .cmsghdr = { - .cmsg_len = CMSG_LEN(sizeof(cmsg.fd)), - .cmsg_level = SOL_SOCKET, - .cmsg_type = SCM_RIGHTS, - }, - .fd = { - self->fd[inflight * 2], - self->fd[inflight * 2], - }, + int fds[2] = { + self->fd[inflight * 2], + self->fd[inflight * 2], }; + char cmsg_buf[CMSG_SPACE(sizeof(fds))]; struct iovec iov = { .iov_base = MSG, .iov_len = MSGLEN, @@ -294,11 +285,18 @@ void __send_fd(struct __test_metadata *_metadata, .msg_namelen = 0, .msg_iov = &iov, .msg_iovlen = 1, - .msg_control = &cmsg, - .msg_controllen = CMSG_SPACE(sizeof(cmsg.fd)), + .msg_control = cmsg_buf, + .msg_controllen = sizeof(cmsg_buf), }; + struct cmsghdr *cmsg; int ret; + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_RIGHTS; + cmsg->cmsg_len = CMSG_LEN(sizeof(fds)); + memcpy(CMSG_DATA(cmsg), fds, sizeof(fds)); + ret = sendmsg(self->fd[receiver * 2 + 1], &msg, variant->flags); if (variant->disabled) { diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index d7bb2e80e88c..0a0d4c2a85f7 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -1,6 +1,8 @@ # SPDX-License-Identifier: GPL-2.0+ OR MIT -TEST_PROGS = bridge_fdb_learning_limit.sh \ +TEST_PROGS = \ + bridge_activity_notify.sh \ + bridge_fdb_learning_limit.sh \ bridge_igmp.sh \ bridge_locked_port.sh \ bridge_mdb.sh \ diff --git a/tools/testing/selftests/net/forwarding/bridge_activity_notify.sh b/tools/testing/selftests/net/forwarding/bridge_activity_notify.sh new file mode 100755 index 000000000000..a20ef4bd310b --- /dev/null +++ b/tools/testing/selftests/net/forwarding/bridge_activity_notify.sh @@ -0,0 +1,173 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +-----------------------+ +------------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | 192.0.2.1/28 | | 192.0.2.2/28 | +# | + $h1 | | + $h2 | +# +----|------------------+ +----|-------------------+ +# | | +# +----|--------------------------------------------------|-------------------+ +# | SW | | | +# | +--|--------------------------------------------------|-----------------+ | +# | | + $swp1 BR1 (802.1d) + $swp2 | | +# | | | | +# | +-----------------------------------------------------------------------+ | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + new_inactive_test + existing_active_test + norefresh_test +" + +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init "$h1" 192.0.2.1/28 + defer simple_if_fini "$h1" 192.0.2.1/28 +} + +h2_create() +{ + simple_if_init "$h2" 192.0.2.2/28 + defer simple_if_fini "$h2" 192.0.2.2/28 +} + +switch_create() +{ + ip_link_add br1 type bridge vlan_filtering 0 mcast_snooping 0 \ + ageing_time "$LOW_AGEING_TIME" + ip_link_set_up br1 + + ip_link_set_master "$swp1" br1 + ip_link_set_up "$swp1" + + ip_link_set_master "$swp2" br1 + ip_link_set_up "$swp2" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + defer vrf_cleanup + + h1_create + h2_create + switch_create +} + +fdb_active_wait() +{ + local mac=$1; shift + + bridge -d fdb get "$mac" br br1 | grep -q -v "inactive" +} + +fdb_inactive_wait() +{ + local mac=$1; shift + + bridge -d fdb get "$mac" br br1 | grep -q "inactive" +} + +new_inactive_test() +{ + local mac="00:11:22:33:44:55" + + # Add a new FDB entry as static and inactive and check that it + # becomes active upon traffic. + RET=0 + + bridge fdb add "$mac" dev "$swp1" master static activity_notify inactive + bridge -d fdb get "$mac" br br1 | grep -q "inactive" + check_err $? "FDB entry not present as \"inactive\" when should" + + $MZ "$h1" -c 1 -p 64 -a "$mac" -b bcast -t ip -q + + busywait "$BUSYWAIT_TIMEOUT" fdb_active_wait "$mac" + check_err $? "FDB entry present as \"inactive\" when should not" + + log_test "Transition from inactive to active" + + bridge fdb del "$mac" dev "$swp1" master +} + +existing_active_test() +{ + local mac="00:11:22:33:44:55" + local ageing_time + + # Enable activity notifications on an existing dynamic FDB entry and + # check that it becomes inactive after the ageing time passed. + RET=0 + + bridge fdb add "$mac" dev "$swp1" master dynamic + bridge fdb replace "$mac" dev "$swp1" master static activity_notify norefresh + + bridge -d fdb get "$mac" br br1 | grep -q "activity_notify" + check_err $? "FDB entry not present as \"activity_notify\" when should" + + bridge -d fdb get "$mac" br br1 | grep -q "inactive" + check_fail $? "FDB entry present as \"inactive\" when should not" + + ageing_time=$(bridge_ageing_time_get br1) + slowwait $((ageing_time * 2)) fdb_inactive_wait "$mac" + check_err $? "FDB entry not present as \"inactive\" when should" + + log_test "Transition from active to inactive" + + bridge fdb del "$mac" dev "$swp1" master +} + +norefresh_test() +{ + local mac="00:11:22:33:44:55" + local updated_time + + # Check that the "updated" time is reset when replacing an FDB entry + # without the "norefresh" keyword and that it is not reset when + # replacing with the "norefresh" keyword. + RET=0 + + bridge fdb add "$mac" dev "$swp1" master static + sleep 1 + + bridge fdb replace "$mac" dev "$swp1" master static activity_notify + updated_time=$(bridge -d -s -j fdb get "$mac" br br1 | jq '.[]["updated"]') + if [[ $updated_time -ne 0 ]]; then + check_err 1 "\"updated\" time was not reset when should" + fi + + sleep 1 + bridge fdb replace "$mac" dev "$swp1" master static norefresh + updated_time=$(bridge -d -s -j fdb get "$mac" br br1 | jq '.[]["updated"]') + if [[ $updated_time -eq 0 ]]; then + check_err 1 "\"updated\" time was reset when should not" + fi + + log_test "Resetting of \"updated\" time" + + bridge fdb del "$mac" dev "$swp1" master +} + +if ! bridge fdb help 2>&1 | grep -q "activity_notify"; then + echo "SKIP: iproute2 too old, missing bridge FDB activity notification control" + exit "$ksft_skip" +fi + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit "$EXIT_STATUS" 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/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py index f395c90fb0f1..4ac9249c85ab 100644 --- a/tools/testing/selftests/net/lib/py/utils.py +++ b/tools/testing/selftests/net/lib/py/utils.py @@ -117,6 +117,7 @@ class bkg(cmd): shell=shell, fail=fail, ns=ns, host=host, ksft_wait=ksft_wait) self.terminate = not exit_wait and not ksft_wait + self._exit_wait = exit_wait self.check_fail = fail if shell and self.terminate: @@ -127,7 +128,9 @@ class bkg(cmd): return self def __exit__(self, ex_type, ex_value, ex_tb): - return self.process(terminate=self.terminate, fail=self.check_fail) + # Force termination on exception + terminate = self.terminate or (self._exit_wait and ex_type) + return self.process(terminate=terminate, fail=self.check_fail) global_defer_queue = [] diff --git a/tools/testing/selftests/net/psock_tpacket.c b/tools/testing/selftests/net/psock_tpacket.c index 221270cee3ea..2938045c5cf9 100644 --- a/tools/testing/selftests/net/psock_tpacket.c +++ b/tools/testing/selftests/net/psock_tpacket.c @@ -22,6 +22,7 @@ * - TPACKET_V3: RX_RING */ +#undef NDEBUG #include <stdio.h> #include <stdlib.h> #include <sys/types.h> @@ -33,7 +34,6 @@ #include <ctype.h> #include <fcntl.h> #include <unistd.h> -#include <bits/wordsize.h> #include <net/ethernet.h> #include <netinet/ip.h> #include <arpa/inet.h> @@ -785,7 +785,7 @@ static int test_kernel_bit_width(void) static int test_user_bit_width(void) { - return __WORDSIZE; + return sizeof(long) * 8; } static const char *tpacket_str[] = { 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) |