diff options
186 files changed, 3612 insertions, 2013 deletions
diff --git a/Documentation/devicetree/bindings/mfd/brcm,cru.yaml b/Documentation/devicetree/bindings/mfd/brcm,cru.yaml index fc1317ab3226..28ac60acf4ac 100644 --- a/Documentation/devicetree/bindings/mfd/brcm,cru.yaml +++ b/Documentation/devicetree/bindings/mfd/brcm,cru.yaml @@ -32,13 +32,13 @@ properties: "#size-cells": const: 1 - pinctrl: - $ref: ../pinctrl/brcm,ns-pinmux.yaml - patternProperties: '^clock-controller@[a-f0-9]+$': $ref: ../clock/brcm,iproc-clocks.yaml + '^pin-controller@[a-f0-9]+$': + $ref: ../pinctrl/brcm,ns-pinmux.yaml + '^thermal@[a-f0-9]+$': $ref: ../thermal/brcm,ns-thermal.yaml @@ -73,9 +73,10 @@ examples: "iprocfast", "sata1", "sata2"; }; - pinctrl { + pin-controller@1c0 { compatible = "brcm,bcm4708-pinmux"; - offset = <0x1c0>; + reg = <0x1c0 0x24>; + reg-names = "cru_gpio_control"; }; thermal@2c0 { diff --git a/Documentation/devicetree/bindings/net/lantiq,xrx200-net.yaml b/Documentation/devicetree/bindings/net/lantiq,xrx200-net.yaml index 16d831f22063..7bc074a42369 100644 --- a/Documentation/devicetree/bindings/net/lantiq,xrx200-net.yaml +++ b/Documentation/devicetree/bindings/net/lantiq,xrx200-net.yaml @@ -29,18 +29,6 @@ properties: - const: tx - const: rx - lantiq,tx-burst-length: - $ref: /schemas/types.yaml#/definitions/uint32 - description: | - TX programmable burst length. - enum: [2, 4, 8] - - lantiq,rx-burst-length: - $ref: /schemas/types.yaml#/definitions/uint32 - description: | - RX programmable burst length. - enum: [2, 4, 8] - '#address-cells': const: 1 @@ -53,8 +41,6 @@ required: - interrupt-parent - interrupts - interrupt-names - - lantiq,tx-burst-length - - lantiq,rx-burst-length - "#address-cells" - "#size-cells" @@ -70,6 +56,4 @@ examples: interrupt-parent = <&icu0>; interrupts = <73>, <72>; interrupt-names = "tx", "rx"; - lantiq,tx-burst-length = <8>; - lantiq,rx-burst-length = <8>; }; diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,ns-pinmux.yaml b/Documentation/devicetree/bindings/pinctrl/brcm,ns-pinmux.yaml index 470aff599c27..fc39e3e9f71c 100644 --- a/Documentation/devicetree/bindings/pinctrl/brcm,ns-pinmux.yaml +++ b/Documentation/devicetree/bindings/pinctrl/brcm,ns-pinmux.yaml @@ -17,9 +17,6 @@ description: A list of pins varies across chipsets so few bindings are available. - Node of the pinmux must be nested in the CRU (Central Resource Unit) "syscon" - node. - properties: compatible: enum: @@ -27,10 +24,11 @@ properties: - brcm,bcm4709-pinmux - brcm,bcm53012-pinmux - offset: - description: offset of pin registers in the CRU block + reg: maxItems: 1 - $ref: /schemas/types.yaml#/definitions/uint32-array + + reg-names: + const: cru_gpio_control patternProperties: '-pins$': @@ -72,23 +70,20 @@ allOf: uart1_grp ] required: - - offset + - reg + - reg-names additionalProperties: false examples: - | - cru@1800c100 { - compatible = "syscon", "simple-mfd"; - reg = <0x1800c100 0x1a4>; - - pinctrl { - compatible = "brcm,bcm4708-pinmux"; - offset = <0xc0>; - - spi-pins { - function = "spi"; - groups = "spi_grp"; - }; + pin-controller@1800c1c0 { + compatible = "brcm,bcm4708-pinmux"; + reg = <0x1800c1c0 0x24>; + reg-names = "cru_gpio_control"; + + spi-pins { + function = "spi"; + groups = "spi_grp"; }; }; diff --git a/Documentation/networking/devlink/bnxt.rst b/Documentation/networking/devlink/bnxt.rst index 3dfd84ccb1c7..a4fb27663cd6 100644 --- a/Documentation/networking/devlink/bnxt.rst +++ b/Documentation/networking/devlink/bnxt.rst @@ -22,6 +22,8 @@ Parameters - Permanent * - ``msix_vec_per_pf_min`` - Permanent + * - ``enable_remote_dev_reset`` + - Runtime The ``bnxt`` driver also implements the following driver-specific parameters. diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 2e8134059c87..6655d929a351 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -104,6 +104,7 @@ Code Seq# Include File Comments '8' all SNP8023 advanced NIC card <mailto:[email protected]> ';' 64-7F linux/vfio.h +'=' 00-3f uapi/linux/ptp_clock.h <mailto:[email protected]> '@' 00-0F linux/radeonfb.h conflict! '@' 00-0F drivers/video/aty/aty128fb.c conflict! 'A' 00-1F linux/apm_bios.h conflict! diff --git a/MAINTAINERS b/MAINTAINERS index 975086c5345d..3b85f039fbf9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5464,6 +5464,19 @@ F: include/net/devlink.h F: include/uapi/linux/devlink.h F: net/core/devlink.c +DH ELECTRONICS IMX6 DHCOM BOARD SUPPORT +M: Christoph Niedermaier <[email protected]> +S: Maintained +F: arch/arm/boot/dts/imx6*-dhcom-* + +DH ELECTRONICS STM32MP1 DHCOM/DHCOR BOARD SUPPORT +M: Marek Vasut <[email protected]> +S: Maintained +F: arch/arm/boot/dts/stm32mp1*-dhcom-* +F: arch/arm/boot/dts/stm32mp1*-dhcor-* + DIALOG SEMICONDUCTOR DRIVERS M: Support Opensource <[email protected]> S: Supported @@ -11284,7 +11297,6 @@ F: Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst F: drivers/net/ethernet/marvell/octeontx2/af/ MARVELL PRESTERA ETHERNET SWITCH DRIVER -M: Vadym Kochan <[email protected]> M: Taras Chornyi <[email protected]> S: Supported W: https://github.com/Marvell-switching/switchdev-prestera @@ -20352,6 +20364,7 @@ X86 ARCHITECTURE (32-BIT AND 64-BIT) M: Thomas Gleixner <[email protected]> M: Ingo Molnar <[email protected]> M: Borislav Petkov <[email protected]> +M: Dave Hansen <[email protected]> R: "H. Peter Anvin" <[email protected]> @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 15 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Opossums on Parade # *DOCUMENTATION* diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 59baf6c132a7..dcf2df6da98f 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -92,6 +92,7 @@ config ARM select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG select HAVE_FUNCTION_TRACER if !XIP_KERNEL + select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_GCC_PLUGINS select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7) select HAVE_IRQ_TIME_ACCOUNTING diff --git a/arch/arm/boot/compressed/decompress.c b/arch/arm/boot/compressed/decompress.c index aa075d8372ea..74255e819831 100644 --- a/arch/arm/boot/compressed/decompress.c +++ b/arch/arm/boot/compressed/decompress.c @@ -47,7 +47,10 @@ extern char * strchrnul(const char *, int); #endif #ifdef CONFIG_KERNEL_XZ +/* Prevent KASAN override of string helpers in decompressor */ +#undef memmove #define memmove memmove +#undef memcpy #define memcpy memcpy #include "../../../../lib/decompress_unxz.c" #endif diff --git a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts index 8077f1716fbc..ecb91fb899ff 100644 --- a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts +++ b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts @@ -112,7 +112,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 084d1c07c2d0..36fbc3329252 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -176,6 +176,7 @@ extern int __get_user_64t_4(void *); register unsigned long __l asm("r1") = __limit; \ register int __e asm("r0"); \ unsigned int __ua_flags = uaccess_save_and_enable(); \ + int __tmp_e; \ switch (sizeof(*(__p))) { \ case 1: \ if (sizeof((x)) >= 8) \ @@ -203,9 +204,10 @@ extern int __get_user_64t_4(void *); break; \ default: __e = __get_user_bad(); break; \ } \ + __tmp_e = __e; \ uaccess_restore(__ua_flags); \ x = (typeof(*(p))) __r2; \ - __e; \ + __tmp_e; \ }) #define get_user(x, p) \ diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 29070eb8df7d..3fc7f9750ce4 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -253,7 +253,7 @@ __create_page_tables: add r0, r4, #KERNEL_OFFSET >> (SECTION_SHIFT - PMD_ORDER) ldr r6, =(_end - 1) adr_l r5, kernel_sec_start @ _pa(kernel_sec_start) -#ifdef CONFIG_CPU_ENDIAN_BE8 +#if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32 str r8, [r5, #4] @ Save physical start of kernel (BE) #else str r8, [r5] @ Save physical start of kernel (LE) @@ -266,7 +266,7 @@ __create_page_tables: bls 1b eor r3, r3, r7 @ Remove the MMU flags adr_l r5, kernel_sec_end @ _pa(kernel_sec_end) -#ifdef CONFIG_CPU_ENDIAN_BE8 +#if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32 str r3, [r5, #4] @ Save physical end of kernel (BE) #else str r3, [r5] @ Save physical end of kernel (LE) diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 4a7edc6e848f..195dff58bafc 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -136,7 +136,7 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom, for (p = first, i = 0; i < 8 && p < top; i++, p += 4) { if (p >= bottom && p < top) { unsigned long val; - if (get_kernel_nofault(val, (unsigned long *)p)) + if (!get_kernel_nofault(val, (unsigned long *)p)) sprintf(str + i * 9, " %08lx", val); else sprintf(str + i * 9, " ????????"); diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S index 50136828f5b5..f14c2360ea0b 100644 --- a/arch/arm/kernel/vmlinux-xip.lds.S +++ b/arch/arm/kernel/vmlinux-xip.lds.S @@ -40,6 +40,10 @@ SECTIONS ARM_DISCARD *(.alt.smp.init) *(.pv_table) +#ifndef CONFIG_ARM_UNWIND + *(.ARM.exidx) *(.ARM.exidx.*) + *(.ARM.extab) *(.ARM.extab.*) +#endif } . = XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR); @@ -172,7 +176,7 @@ ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined") ASSERT((_end - __bss_start) >= 12288, ".bss too small for CONFIG_XIP_DEFLATED_DATA") #endif -#ifdef CONFIG_ARM_MPU +#if defined(CONFIG_ARM_MPU) && !defined(CONFIG_COMPILE_TEST) /* * Due to PMSAv7 restriction on base address and size we have to * enforce minimal alignment restrictions. It was seen that weaker diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index e2c743aa2eb2..d9f7dfe2a7ed 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -340,6 +340,7 @@ ENTRY(\name\()_cache_fns) .macro define_tlb_functions name:req, flags_up:req, flags_smp .type \name\()_tlb_fns, #object + .align 2 ENTRY(\name\()_tlb_fns) .long \name\()_flush_user_tlb_range .long \name\()_flush_kern_tlb_range diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c index 27e0af78e88b..9d8634e2f12f 100644 --- a/arch/arm/probes/kprobes/core.c +++ b/arch/arm/probes/kprobes/core.c @@ -439,7 +439,7 @@ static struct undef_hook kprobes_arm_break_hook = { #endif /* !CONFIG_THUMB2_KERNEL */ -int __init arch_init_kprobes() +int __init arch_init_kprobes(void) { arm_probes_decode_init(); #ifdef CONFIG_THUMB2_KERNEL diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts index 02f8e72f0cad..05486cccee1c 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts @@ -75,7 +75,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts index d17abb515835..e99e7644ff39 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts @@ -70,7 +70,9 @@ regulator-name = "rst-usb-eth2"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usb_eth2>; - gpio = <&gpio3 2 GPIO_ACTIVE_LOW>; + gpio = <&gpio3 2 GPIO_ACTIVE_HIGH>; + enable-active-high; + regulator-always-on; }; reg_vdd_5v: regulator-5v { @@ -95,7 +97,7 @@ clocks = <&osc_can>; interrupt-parent = <&gpio4>; interrupts = <28 IRQ_TYPE_EDGE_FALLING>; - spi-max-frequency = <100000>; + spi-max-frequency = <10000000>; vdd-supply = <®_vdd_3v3>; xceiver-supply = <®_vdd_5v>; }; @@ -111,7 +113,7 @@ &fec1 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-connection-type = "rgmii"; + phy-connection-type = "rgmii-rxid"; phy-handle = <ðphy>; status = "okay"; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi index 9db9b90bf2bc..42bbbb3f532b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi @@ -91,10 +91,12 @@ reg_vdd_soc: BUCK1 { regulator-name = "buck1"; regulator-min-microvolt = <800000>; - regulator-max-microvolt = <900000>; + regulator-max-microvolt = <850000>; regulator-boot-on; regulator-always-on; regulator-ramp-delay = <3125>; + nxp,dvs-run-voltage = <850000>; + nxp,dvs-standby-voltage = <800000>; }; reg_vdd_arm: BUCK2 { @@ -111,7 +113,7 @@ reg_vdd_dram: BUCK3 { regulator-name = "buck3"; regulator-min-microvolt = <850000>; - regulator-max-microvolt = <900000>; + regulator-max-microvolt = <950000>; regulator-boot-on; regulator-always-on; }; @@ -150,7 +152,7 @@ reg_vdd_snvs: LDO2 { regulator-name = "ldo2"; - regulator-min-microvolt = <850000>; + regulator-min-microvolt = <800000>; regulator-max-microvolt = <900000>; regulator-boot-on; regulator-always-on; diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index 8c15d9fed08f..d12e4cbfc852 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -2590,9 +2590,10 @@ power-domains = <&dispcc MDSS_GDSC>; clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>, + <&gcc GCC_DISP_HF_AXI_CLK>, <&gcc GCC_DISP_SF_AXI_CLK>, <&dispcc DISP_CC_MDSS_MDP_CLK>; - clock-names = "iface", "nrt_bus", "core"; + clock-names = "iface", "bus", "nrt_bus", "core"; assigned-clocks = <&dispcc DISP_CC_MDSS_MDP_CLK>; assigned-clock-rates = <460000000>; diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 41c23f474ea6..803e7773fa86 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1136,6 +1136,11 @@ out: return prog; } +u64 bpf_jit_alloc_exec_limit(void) +{ + return BPF_JIT_REGION_SIZE; +} + void *bpf_jit_alloc_exec(unsigned long size) { return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START, diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c index 0e23e3a8df6b..d55b73b18149 100644 --- a/arch/nds32/kernel/ftrace.c +++ b/arch/nds32/kernel/ftrace.c @@ -6,7 +6,7 @@ #ifndef CONFIG_DYNAMIC_FTRACE extern void (*ftrace_trace_function)(unsigned long, unsigned long, - struct ftrace_ops*, struct pt_regs*); + struct ftrace_ops*, struct ftrace_regs*); extern void ftrace_graph_caller(void); noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip, diff --git a/arch/nios2/platform/Kconfig.platform b/arch/nios2/platform/Kconfig.platform index 9e32fb7f3d4c..e849daff6fd1 100644 --- a/arch/nios2/platform/Kconfig.platform +++ b/arch/nios2/platform/Kconfig.platform @@ -37,6 +37,7 @@ config NIOS2_DTB_PHYS_ADDR config NIOS2_DTB_SOURCE_BOOL bool "Compile and link device tree into kernel image" + depends on !COMPILE_TEST help This allows you to specify a dts (device tree source) file which will be compiled and linked into the kernel image. diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index fed86f42dfbe..753d85bdfad0 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -125,7 +125,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) if (i == NR_JIT_ITERATIONS) { pr_err("bpf-jit: image did not converge in <%d passes!\n", i); - bpf_jit_binary_free(jit_data->header); + if (jit_data->header) + bpf_jit_binary_free(jit_data->header); prog = orig_prog; goto out_offset; } @@ -166,6 +167,11 @@ out: return prog; } +u64 bpf_jit_alloc_exec_limit(void) +{ + return BPF_JIT_REGION_SIZE; +} + void *bpf_jit_alloc_exec(unsigned long size) { return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START, diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f8f48a7ec577..5a0298aa56ba 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -702,7 +702,8 @@ struct kvm_vcpu_arch { struct kvm_pio_request pio; void *pio_data; - void *guest_ins_data; + void *sev_pio_data; + unsigned sev_pio_count; u8 event_exit_inst_len; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 1a64ba5b9437..0cc58901bf7a 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4596,10 +4596,10 @@ static void update_pkru_bitmask(struct kvm_mmu *mmu) unsigned bit; bool wp; - if (!is_cr4_pke(mmu)) { - mmu->pkru_mask = 0; + mmu->pkru_mask = 0; + + if (!is_cr4_pke(mmu)) return; - } wp = is_cr0_wp(mmu); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 0d21d59936e5..2e4916be290e 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1484,6 +1484,13 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) goto e_free_trans; } + /* + * Flush (on non-coherent CPUs) before RECEIVE_UPDATE_DATA, the PSP + * encrypts the written data with the guest's key, and the cache may + * contain dirty, unencrypted data. + */ + sev_clflush_pages(guest_page, n); + /* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */ data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset; data.guest_address |= sev_me_mask; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 7fb2a3a1ca46..7d595effb66f 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6305,18 +6305,13 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) /* * If we are running L2 and L1 has a new pending interrupt - * which can be injected, we should re-evaluate - * what should be done with this new L1 interrupt. - * If L1 intercepts external-interrupts, we should - * exit from L2 to L1. Otherwise, interrupt should be - * delivered directly to L2. + * which can be injected, this may cause a vmexit or it may + * be injected into L2. Either way, this interrupt will be + * processed via KVM_REQ_EVENT, not RVI, because we do not use + * virtual interrupt delivery to inject L1 interrupts into L2. */ - if (is_guest_mode(vcpu) && max_irr_updated) { - if (nested_exit_on_intr(vcpu)) - kvm_vcpu_exiting_guest_mode(vcpu); - else - kvm_make_request(KVM_REQ_EVENT, vcpu); - } + if (is_guest_mode(vcpu) && max_irr_updated) + kvm_make_request(KVM_REQ_EVENT, vcpu); } else { max_irr = kvm_lapic_find_highest_irr(vcpu); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0c8b5129effd..b26647a5ea22 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6906,7 +6906,7 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) } static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, - unsigned short port, void *val, + unsigned short port, unsigned int count, bool in) { vcpu->arch.pio.port = port; @@ -6914,10 +6914,8 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, vcpu->arch.pio.count = count; vcpu->arch.pio.size = size; - if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { - vcpu->arch.pio.count = 0; + if (!kernel_pio(vcpu, vcpu->arch.pio_data)) return 1; - } vcpu->run->exit_reason = KVM_EXIT_IO; vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; @@ -6929,26 +6927,39 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, return 0; } -static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, - unsigned short port, void *val, unsigned int count) +static int __emulator_pio_in(struct kvm_vcpu *vcpu, int size, + unsigned short port, unsigned int count) { - int ret; + WARN_ON(vcpu->arch.pio.count); + memset(vcpu->arch.pio_data, 0, size * count); + return emulator_pio_in_out(vcpu, size, port, count, true); +} - if (vcpu->arch.pio.count) - goto data_avail; +static void complete_emulator_pio_in(struct kvm_vcpu *vcpu, void *val) +{ + int size = vcpu->arch.pio.size; + unsigned count = vcpu->arch.pio.count; + memcpy(val, vcpu->arch.pio_data, size * count); + trace_kvm_pio(KVM_PIO_IN, vcpu->arch.pio.port, size, count, vcpu->arch.pio_data); + vcpu->arch.pio.count = 0; +} - memset(vcpu->arch.pio_data, 0, size * count); +static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, + unsigned short port, void *val, unsigned int count) +{ + if (vcpu->arch.pio.count) { + /* Complete previous iteration. */ + } else { + int r = __emulator_pio_in(vcpu, size, port, count); + if (!r) + return r; - ret = emulator_pio_in_out(vcpu, size, port, val, count, true); - if (ret) { -data_avail: - memcpy(val, vcpu->arch.pio_data, size * count); - trace_kvm_pio(KVM_PIO_IN, port, size, count, vcpu->arch.pio_data); - vcpu->arch.pio.count = 0; - return 1; + /* Results already available, fall through. */ } - return 0; + WARN_ON(count != vcpu->arch.pio.count); + complete_emulator_pio_in(vcpu, val); + return 1; } static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, @@ -6963,9 +6974,15 @@ static int emulator_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port, const void *val, unsigned int count) { + int ret; + memcpy(vcpu->arch.pio_data, val, size * count); trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data); - return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false); + ret = emulator_pio_in_out(vcpu, size, port, count, false); + if (ret) + vcpu->arch.pio.count = 0; + + return ret; } static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, @@ -9643,14 +9660,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) break; - if (unlikely(kvm_vcpu_exit_request(vcpu))) { + if (vcpu->arch.apicv_active) + static_call(kvm_x86_sync_pir_to_irr)(vcpu); + + if (unlikely(kvm_vcpu_exit_request(vcpu))) { exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED; break; } - - if (vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); - } + } /* * Do this here before restoring debug registers on the host. And @@ -12368,44 +12385,81 @@ int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes, } EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_read); -static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu) +static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size, + unsigned int port); + +static int complete_sev_es_emulated_outs(struct kvm_vcpu *vcpu) { - memcpy(vcpu->arch.guest_ins_data, vcpu->arch.pio_data, - vcpu->arch.pio.count * vcpu->arch.pio.size); - vcpu->arch.pio.count = 0; + int size = vcpu->arch.pio.size; + int port = vcpu->arch.pio.port; + vcpu->arch.pio.count = 0; + if (vcpu->arch.sev_pio_count) + return kvm_sev_es_outs(vcpu, size, port); return 1; } static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size, - unsigned int port, void *data, unsigned int count) + unsigned int port) { - int ret; - - ret = emulator_pio_out_emulated(vcpu->arch.emulate_ctxt, size, port, - data, count); - if (ret) - return ret; + for (;;) { + unsigned int count = + min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count); + int ret = emulator_pio_out(vcpu, size, port, vcpu->arch.sev_pio_data, count); + + /* memcpy done already by emulator_pio_out. */ + vcpu->arch.sev_pio_count -= count; + vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size; + if (!ret) + break; - vcpu->arch.pio.count = 0; + /* Emulation done by the kernel. */ + if (!vcpu->arch.sev_pio_count) + return 1; + } + vcpu->arch.complete_userspace_io = complete_sev_es_emulated_outs; return 0; } static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size, - unsigned int port, void *data, unsigned int count) + unsigned int port); + +static void advance_sev_es_emulated_ins(struct kvm_vcpu *vcpu) { - int ret; + unsigned count = vcpu->arch.pio.count; + complete_emulator_pio_in(vcpu, vcpu->arch.sev_pio_data); + vcpu->arch.sev_pio_count -= count; + vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size; +} - ret = emulator_pio_in_emulated(vcpu->arch.emulate_ctxt, size, port, - data, count); - if (ret) { - vcpu->arch.pio.count = 0; - } else { - vcpu->arch.guest_ins_data = data; - vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins; +static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu) +{ + int size = vcpu->arch.pio.size; + int port = vcpu->arch.pio.port; + + advance_sev_es_emulated_ins(vcpu); + if (vcpu->arch.sev_pio_count) + return kvm_sev_es_ins(vcpu, size, port); + return 1; +} + +static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size, + unsigned int port) +{ + for (;;) { + unsigned int count = + min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count); + if (!__emulator_pio_in(vcpu, size, port, count)) + break; + + /* Emulation done by the kernel. */ + advance_sev_es_emulated_ins(vcpu); + if (!vcpu->arch.sev_pio_count) + return 1; } + vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins; return 0; } @@ -12413,8 +12467,10 @@ int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port, void *data, unsigned int count, int in) { - return in ? kvm_sev_es_ins(vcpu, size, port, data, count) - : kvm_sev_es_outs(vcpu, size, port, data, count); + vcpu->arch.sev_pio_data = data; + vcpu->arch.sev_pio_count = count; + return in ? kvm_sev_es_ins(vcpu, size, port) + : kvm_sev_es_outs(vcpu, size, port); } EXPORT_SYMBOL_GPL(kvm_sev_es_string_io); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 38b9f7684952..9a1c5839dd46 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1897,10 +1897,11 @@ void blk_cgroup_bio_start(struct bio *bio) { int rwd = blk_cgroup_io_type(bio), cpu; struct blkg_iostat_set *bis; + unsigned long flags; cpu = get_cpu(); bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu); - u64_stats_update_begin(&bis->sync); + flags = u64_stats_update_begin_irqsave(&bis->sync); /* * If the bio is flagged with BIO_CGROUP_ACCT it means this is a split @@ -1912,7 +1913,7 @@ void blk_cgroup_bio_start(struct bio *bio) } bis->cur.ios[rwd]++; - u64_stats_update_end(&bis->sync); + u64_stats_update_end_irqrestore(&bis->sync, flags); if (cgroup_subsys_on_dfl(io_cgrp_subsys)) cgroup_rstat_updated(bio->bi_blkg->blkcg->css.cgroup, cpu); put_cpu(); diff --git a/block/partitions/core.c b/block/partitions/core.c index 58c4c362c94f..7bea19dd9458 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -423,6 +423,7 @@ out_del: device_del(pdev); out_put: put_device(pdev); + return ERR_PTR(err); out_put_disk: put_disk(disk); return ERR_PTR(err); diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index b9863e22b952..f0ed4414edb1 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -1035,13 +1035,8 @@ void acpi_turn_off_unused_power_resources(void) list_for_each_entry_reverse(resource, &acpi_power_resource_list, list_node) { mutex_lock(&resource->resource_lock); - /* - * Turn off power resources in an unknown state too, because the - * platform firmware on some system expects the OS to turn off - * power resources without any users unconditionally. - */ if (!resource->ref_count && - resource->state != ACPI_POWER_RESOURCE_STATE_OFF) { + resource->state == ACPI_POWER_RESOURCE_STATE_ON) { acpi_handle_debug(resource->device.handle, "Turning OFF\n"); __acpi_power_off(resource); } diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index 9d86203e1e7a..c53633d47bfb 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -3896,8 +3896,8 @@ static int mv_chip_id(struct ata_host *host, unsigned int board_idx) break; default: - dev_err(host->dev, "BUG: invalid board index %u\n", board_idx); - return 1; + dev_alert(host->dev, "BUG: invalid board index %u\n", board_idx); + return -EINVAL; } hpriv->hp_flags = hp_flags; diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c index cfa29dc89bbf..fabf87058d80 100644 --- a/drivers/base/regmap/regcache-rbtree.c +++ b/drivers/base/regmap/regcache-rbtree.c @@ -281,14 +281,14 @@ static int regcache_rbtree_insert_to_block(struct regmap *map, if (!blk) return -ENOMEM; + rbnode->block = blk; + if (BITS_TO_LONGS(blklen) > BITS_TO_LONGS(rbnode->blklen)) { present = krealloc(rbnode->cache_present, BITS_TO_LONGS(blklen) * sizeof(*present), GFP_KERNEL); - if (!present) { - kfree(blk); + if (!present) return -ENOMEM; - } memset(present + BITS_TO_LONGS(rbnode->blklen), 0, (BITS_TO_LONGS(blklen) - BITS_TO_LONGS(rbnode->blklen)) @@ -305,7 +305,6 @@ static int regcache_rbtree_insert_to_block(struct regmap *map, } /* update the rbnode block, its size and the base register */ - rbnode->block = blk; rbnode->blklen = blklen; rbnode->base_reg = base_reg; rbnode->cache_present = present; diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 42f3d9d123a1..d030577ad6a2 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -13,6 +13,7 @@ #define _HYPERV_VMBUS_H #include <linux/list.h> +#include <linux/bitops.h> #include <asm/sync_bitops.h> #include <asm/hyperv-tlfs.h> #include <linux/atomic.h> diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index a20b8108e160..c00f8e28aab7 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -706,8 +706,9 @@ static void ib_nl_set_path_rec_attrs(struct sk_buff *skb, /* Construct the family header first */ header = skb_put(skb, NLMSG_ALIGN(sizeof(*header))); - memcpy(header->device_name, dev_name(&query->port->agent->device->dev), - LS_DEVICE_NAME_MAX); + strscpy_pad(header->device_name, + dev_name(&query->port->agent->device->dev), + LS_DEVICE_NAME_MAX); header->port_num = query->port->port_num; if ((comp_mask & IB_SA_PATH_REC_REVERSIBLE) && diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index 489b436f19bb..3d42bd2b36bd 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -878,6 +878,7 @@ void sc_disable(struct send_context *sc) { u64 reg; struct pio_buf *pbuf; + LIST_HEAD(wake_list); if (!sc) return; @@ -912,19 +913,21 @@ void sc_disable(struct send_context *sc) spin_unlock(&sc->release_lock); write_seqlock(&sc->waitlock); - while (!list_empty(&sc->piowait)) { + if (!list_empty(&sc->piowait)) + list_move(&sc->piowait, &wake_list); + write_sequnlock(&sc->waitlock); + while (!list_empty(&wake_list)) { struct iowait *wait; struct rvt_qp *qp; struct hfi1_qp_priv *priv; - wait = list_first_entry(&sc->piowait, struct iowait, list); + wait = list_first_entry(&wake_list, struct iowait, list); qp = iowait_to_qp(wait); priv = qp->priv; list_del_init(&priv->s_iowait.list); priv->s_iowait.lock = NULL; hfi1_qp_wakeup(qp, RVT_S_WAIT_PIO | HFI1_S_WAIT_PIO_DRAIN); } - write_sequnlock(&sc->waitlock); spin_unlock_irq(&sc->alloc_lock); } diff --git a/drivers/infiniband/hw/irdma/uk.c b/drivers/infiniband/hw/irdma/uk.c index 5fb92de1f015..9b544a3b1288 100644 --- a/drivers/infiniband/hw/irdma/uk.c +++ b/drivers/infiniband/hw/irdma/uk.c @@ -1092,12 +1092,12 @@ irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq, struct irdma_cq_poll_info *info) if (cq->avoid_mem_cflct) { ext_cqe = (__le64 *)((u8 *)cqe + 32); get_64bit_val(ext_cqe, 24, &qword7); - polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword3); + polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword7); } else { peek_head = (cq->cq_ring.head + 1) % cq->cq_ring.size; ext_cqe = cq->cq_base[peek_head].buf; get_64bit_val(ext_cqe, 24, &qword7); - polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword3); + polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword7); if (!peek_head) polarity ^= 1; } diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 7110ebf834f9..102dc9342f2a 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -3399,9 +3399,13 @@ static void irdma_process_cqe(struct ib_wc *entry, } if (cq_poll_info->ud_vlan_valid) { - entry->vlan_id = cq_poll_info->ud_vlan & VLAN_VID_MASK; - entry->wc_flags |= IB_WC_WITH_VLAN; + u16 vlan = cq_poll_info->ud_vlan & VLAN_VID_MASK; + entry->sl = cq_poll_info->ud_vlan >> VLAN_PRIO_SHIFT; + if (vlan) { + entry->vlan_id = vlan; + entry->wc_flags |= IB_WC_WITH_VLAN; + } } else { entry->sl = 0; } diff --git a/drivers/infiniband/hw/irdma/ws.c b/drivers/infiniband/hw/irdma/ws.c index b68c575eb78e..b0d6ee0739f5 100644 --- a/drivers/infiniband/hw/irdma/ws.c +++ b/drivers/infiniband/hw/irdma/ws.c @@ -330,8 +330,10 @@ enum irdma_status_code irdma_ws_add(struct irdma_sc_vsi *vsi, u8 user_pri) tc_node->enable = true; ret = irdma_ws_cqp_cmd(vsi, tc_node, IRDMA_OP_WS_MODIFY_NODE); - if (ret) + if (ret) { + vsi->unregister_qset(vsi, tc_node); goto reg_err; + } } ibdev_dbg(to_ibdev(vsi->dev), "WS: Using node %d which represents VSI %d TC %d\n", @@ -350,6 +352,10 @@ enum irdma_status_code irdma_ws_add(struct irdma_sc_vsi *vsi, u8 user_pri) } goto exit; +reg_err: + irdma_ws_cqp_cmd(vsi, tc_node, IRDMA_OP_WS_DELETE_NODE); + list_del(&tc_node->siblings); + irdma_free_node(vsi, tc_node); leaf_add_err: if (list_empty(&vsi_node->child_list_head)) { if (irdma_ws_cqp_cmd(vsi, vsi_node, IRDMA_OP_WS_DELETE_NODE)) @@ -369,11 +375,6 @@ vsi_add_err: exit: mutex_unlock(&vsi->dev->ws_mutex); return ret; - -reg_err: - mutex_unlock(&vsi->dev->ws_mutex); - irdma_ws_remove(vsi, user_pri); - return ret; } /** diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 14c5564428ab..d2044df30394 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1342,7 +1342,6 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, struct ib_umem *umem, goto err_2; } mr->mmkey.type = MLX5_MKEY_MR; - mr->desc_size = sizeof(struct mlx5_mtt); mr->umem = umem; set_mr_fields(dev, mr, umem->length, access_flags, iova); kvfree(in); @@ -1536,6 +1535,7 @@ static struct ib_mr *create_user_odp_mr(struct ib_pd *pd, u64 start, u64 length, ib_umem_release(&odp->umem); return ERR_CAST(mr); } + xa_init(&mr->implicit_children); odp->private = mr; err = mlx5r_store_odp_mkey(dev, &mr->mmkey); diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index b2fca110346c..e5abbcfc1d57 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -4458,6 +4458,8 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr, MLX5_SET(dctc, dctc, mtu, attr->path_mtu); MLX5_SET(dctc, dctc, my_addr_index, attr->ah_attr.grh.sgid_index); MLX5_SET(dctc, dctc, hop_limit, attr->ah_attr.grh.hop_limit); + if (attr->ah_attr.type == RDMA_AH_ATTR_TYPE_ROCE) + MLX5_SET(dctc, dctc, eth_prio, attr->ah_attr.sl & 0x7); err = mlx5_core_create_dct(dev, &qp->dct.mdct, qp->dct.in, MLX5_ST_SZ_BYTES(create_dct_in), out, diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h index 3cb4febaad0f..8def88cfa300 100644 --- a/drivers/infiniband/hw/qedr/qedr.h +++ b/drivers/infiniband/hw/qedr/qedr.h @@ -455,6 +455,7 @@ struct qedr_qp { /* synchronization objects used with iwarp ep */ struct kref refcnt; struct completion iwarp_cm_comp; + struct completion qp_rel_comp; unsigned long iwarp_cm_flags; /* enum iwarp_cm_flags */ }; diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c index 1715fbe0719d..a51fc6854984 100644 --- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c @@ -83,7 +83,7 @@ static void qedr_iw_free_qp(struct kref *ref) { struct qedr_qp *qp = container_of(ref, struct qedr_qp, refcnt); - kfree(qp); + complete(&qp->qp_rel_comp); } static void diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 3fbf172dbbef..dcb3653db72d 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -1357,6 +1357,7 @@ static void qedr_set_common_qp_params(struct qedr_dev *dev, if (rdma_protocol_iwarp(&dev->ibdev, 1)) { kref_init(&qp->refcnt); init_completion(&qp->iwarp_cm_comp); + init_completion(&qp->qp_rel_comp); } qp->pd = pd; @@ -2857,8 +2858,10 @@ int qedr_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) qedr_free_qp_resources(dev, qp, udata); - if (rdma_protocol_iwarp(&dev->ibdev, 1)) + if (rdma_protocol_iwarp(&dev->ibdev, 1)) { qedr_iw_qp_rem_ref(&qp->ibqp); + wait_for_completion(&qp->qp_rel_comp); + } return 0; } diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c index a67599b5a550..ac11943a5ddb 100644 --- a/drivers/infiniband/hw/qib/qib_user_sdma.c +++ b/drivers/infiniband/hw/qib/qib_user_sdma.c @@ -602,7 +602,7 @@ done: /* * How many pages in this iovec element? */ -static int qib_user_sdma_num_pages(const struct iovec *iov) +static size_t qib_user_sdma_num_pages(const struct iovec *iov) { const unsigned long addr = (unsigned long) iov->iov_base; const unsigned long len = iov->iov_len; @@ -658,7 +658,7 @@ static void qib_user_sdma_free_pkt_frag(struct device *dev, static int qib_user_sdma_pin_pages(const struct qib_devdata *dd, struct qib_user_sdma_queue *pq, struct qib_user_sdma_pkt *pkt, - unsigned long addr, int tlen, int npages) + unsigned long addr, int tlen, size_t npages) { struct page *pages[8]; int i, j; @@ -722,7 +722,7 @@ static int qib_user_sdma_pin_pkt(const struct qib_devdata *dd, unsigned long idx; for (idx = 0; idx < niov; idx++) { - const int npages = qib_user_sdma_num_pages(iov + idx); + const size_t npages = qib_user_sdma_num_pages(iov + idx); const unsigned long addr = (unsigned long) iov[idx].iov_base; ret = qib_user_sdma_pin_pages(dd, pq, pkt, addr, @@ -824,8 +824,8 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd, unsigned pktnw; unsigned pktnwc; int nfrags = 0; - int npages = 0; - int bytes_togo = 0; + size_t npages = 0; + size_t bytes_togo = 0; int tiddma = 0; int cfur; @@ -885,7 +885,11 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd, npages += qib_user_sdma_num_pages(&iov[idx]); - bytes_togo += slen; + if (check_add_overflow(bytes_togo, slen, &bytes_togo) || + bytes_togo > type_max(typeof(pkt->bytes_togo))) { + ret = -EINVAL; + goto free_pbc; + } pktnwc += slen >> 2; idx++; nfrags++; @@ -904,8 +908,7 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd, } if (frag_size) { - int tidsmsize, n; - size_t pktsize; + size_t tidsmsize, n, pktsize, sz, addrlimit; n = npages*((2*PAGE_SIZE/frag_size)+1); pktsize = struct_size(pkt, addr, n); @@ -923,14 +926,24 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd, else tidsmsize = 0; - pkt = kmalloc(pktsize+tidsmsize, GFP_KERNEL); + if (check_add_overflow(pktsize, tidsmsize, &sz)) { + ret = -EINVAL; + goto free_pbc; + } + pkt = kmalloc(sz, GFP_KERNEL); if (!pkt) { ret = -ENOMEM; goto free_pbc; } pkt->largepkt = 1; pkt->frag_size = frag_size; - pkt->addrlimit = n + ARRAY_SIZE(pkt->addr); + if (check_add_overflow(n, ARRAY_SIZE(pkt->addr), + &addrlimit) || + addrlimit > type_max(typeof(pkt->addrlimit))) { + ret = -EINVAL; + goto free_pbc; + } + pkt->addrlimit = addrlimit; if (tiddma) { char *tidsm = (char *)pkt + pktsize; diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 49bdd78ac664..3305f2744bfa 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -1223,7 +1223,7 @@ int rvt_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *init_attr, spin_lock(&rdi->n_qps_lock); if (rdi->n_qps_allocated == rdi->dparms.props.max_qp) { spin_unlock(&rdi->n_qps_lock); - ret = ENOMEM; + ret = -ENOMEM; goto bail_ip; } diff --git a/drivers/net/ethernet/broadcom/bnxt/Makefile b/drivers/net/ethernet/broadcom/bnxt/Makefile index c6ef7ec2c115..2bc2b707d6ee 100644 --- a/drivers/net/ethernet/broadcom/bnxt/Makefile +++ b/drivers/net/ethernet/broadcom/bnxt/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_BNXT) += bnxt_en.o -bnxt_en-y := bnxt.o bnxt_hwrm.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_ptp.o bnxt_vfr.o bnxt_devlink.o bnxt_dim.o +bnxt_en-y := bnxt.o bnxt_hwrm.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_ptp.o bnxt_vfr.o bnxt_devlink.o bnxt_dim.o bnxt_coredump.o bnxt_en-$(CONFIG_BNXT_FLOWER_OFFLOAD) += bnxt_tc.o bnxt_en-$(CONFIG_DEBUG_FS) += bnxt_debugfs.o diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 66263aa0d96b..c04ea83188e2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -49,8 +49,6 @@ #include <linux/log2.h> #include <linux/aer.h> #include <linux/bitmap.h> -#include <linux/ptp_clock_kernel.h> -#include <linux/timecounter.h> #include <linux/cpu_rmap.h> #include <linux/cpumask.h> #include <net/pkt_cls.h> @@ -85,55 +83,7 @@ MODULE_DESCRIPTION("Broadcom BCM573xx network driver"); #define BNXT_TX_PUSH_THRESH 164 -enum board_idx { - BCM57301, - BCM57302, - BCM57304, - BCM57417_NPAR, - BCM58700, - BCM57311, - BCM57312, - BCM57402, - BCM57404, - BCM57406, - BCM57402_NPAR, - BCM57407, - BCM57412, - BCM57414, - BCM57416, - BCM57417, - BCM57412_NPAR, - BCM57314, - BCM57417_SFP, - BCM57416_SFP, - BCM57404_NPAR, - BCM57406_NPAR, - BCM57407_SFP, - BCM57407_NPAR, - BCM57414_NPAR, - BCM57416_NPAR, - BCM57452, - BCM57454, - BCM5745x_NPAR, - BCM57508, - BCM57504, - BCM57502, - BCM57508_NPAR, - BCM57504_NPAR, - BCM57502_NPAR, - BCM58802, - BCM58804, - BCM58808, - NETXTREME_E_VF, - NETXTREME_C_VF, - NETXTREME_S_VF, - NETXTREME_C_VF_HV, - NETXTREME_E_VF_HV, - NETXTREME_E_P5_VF, - NETXTREME_E_P5_VF_HV, -}; - -/* indexed by enum above */ +/* indexed by enum board_idx */ static const struct { char *name; } board_info[] = { @@ -2172,7 +2122,7 @@ static int bnxt_async_event_process(struct bnxt *bp, set_bit(BNXT_RESET_TASK_SILENT_SP_EVENT, &bp->sp_event); break; case ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY: { - char *fatal_str = "non-fatal"; + char *type_str = "Solicited"; if (!bp->fw_health) goto async_event_process_exit; @@ -2184,13 +2134,21 @@ static int bnxt_async_event_process(struct bnxt *bp, bp->fw_reset_max_dsecs = le16_to_cpu(cmpl->timestamp_hi); if (!bp->fw_reset_max_dsecs) bp->fw_reset_max_dsecs = BNXT_DFLT_FW_RST_MAX_DSECS; - if (EVENT_DATA1_RESET_NOTIFY_FATAL(data1)) { - fatal_str = "fatal"; + if (EVENT_DATA1_RESET_NOTIFY_FW_ACTIVATION(data1)) { + set_bit(BNXT_STATE_FW_ACTIVATE_RESET, &bp->state); + } else if (EVENT_DATA1_RESET_NOTIFY_FATAL(data1)) { + type_str = "Fatal"; + bp->fw_health->fatalities++; set_bit(BNXT_STATE_FW_FATAL_COND, &bp->state); + } else if (data2 && BNXT_FW_STATUS_HEALTHY != + EVENT_DATA2_RESET_NOTIFY_FW_STATUS_CODE(data2)) { + type_str = "Non-fatal"; + bp->fw_health->survivals++; + set_bit(BNXT_STATE_FW_NON_FATAL_COND, &bp->state); } netif_warn(bp, hw, bp->dev, - "Firmware %s reset event, data1: 0x%x, data2: 0x%x, min wait %u ms, max wait %u ms\n", - fatal_str, data1, data2, + "%s firmware reset event, data1: 0x%x, data2: 0x%x, min wait %u ms, max wait %u ms\n", + type_str, data1, data2, bp->fw_reset_min_dsecs * 100, bp->fw_reset_max_dsecs * 100); set_bit(BNXT_FW_RESET_NOTIFY_SP_EVENT, &bp->sp_event); @@ -2198,17 +2156,18 @@ static int bnxt_async_event_process(struct bnxt *bp, } case ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY: { struct bnxt_fw_health *fw_health = bp->fw_health; + char *status_desc = "healthy"; + u32 status; if (!fw_health) goto async_event_process_exit; if (!EVENT_DATA1_RECOVERY_ENABLED(data1)) { fw_health->enabled = false; - netif_info(bp, drv, bp->dev, - "Error recovery info: error recovery[0]\n"); + netif_info(bp, drv, bp->dev, "Driver recovery watchdog is disabled\n"); break; } - fw_health->master = EVENT_DATA1_RECOVERY_MASTER_FUNC(data1); + fw_health->primary = EVENT_DATA1_RECOVERY_MASTER_FUNC(data1); fw_health->tmr_multiplier = DIV_ROUND_UP(fw_health->polling_dsecs * HZ, bp->current_interval * 10); @@ -2218,10 +2177,13 @@ static int bnxt_async_event_process(struct bnxt *bp, bnxt_fw_health_readl(bp, BNXT_FW_HEARTBEAT_REG); fw_health->last_fw_reset_cnt = bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG); + status = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG); + if (status != BNXT_FW_STATUS_HEALTHY) + status_desc = "unhealthy"; netif_info(bp, drv, bp->dev, - "Error recovery info: error recovery[1], master[%d], reset count[%u], health status: 0x%x\n", - fw_health->master, fw_health->last_fw_reset_cnt, - bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG)); + "Driver recovery watchdog, role: %s, firmware status: 0x%x (%s), resets: %u\n", + fw_health->primary ? "primary" : "backup", status, + status_desc, fw_health->last_fw_reset_cnt); if (!fw_health->enabled) { /* Make sure tmr_counter is set and visible to * bnxt_health_check() before setting enabled to true. @@ -4651,7 +4613,7 @@ int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size, return rc; } -static int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp) +int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp) { struct hwrm_func_drv_unrgtr_input *req; int rc; @@ -7192,7 +7154,7 @@ static void bnxt_free_ctx_pg_tbls(struct bnxt *bp, ctx_pg->nr_pages = 0; } -static void bnxt_free_ctx_mem(struct bnxt *bp) +void bnxt_free_ctx_mem(struct bnxt *bp) { struct bnxt_ctx_mem_info *ctx = bp->ctx; int i; @@ -7518,12 +7480,18 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp) bp->fw_cap |= BNXT_FW_CAP_ERR_RECOVER_RELOAD; if (!(flags & FUNC_QCAPS_RESP_FLAGS_VLAN_ACCELERATION_TX_DISABLED)) bp->fw_cap |= BNXT_FW_CAP_VLAN_TX_INSERT; + if (flags & FUNC_QCAPS_RESP_FLAGS_DBG_QCAPS_CMD_SUPPORTED) + bp->fw_cap |= BNXT_FW_CAP_DBG_QCAPS; flags_ext = le32_to_cpu(resp->flags_ext); if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_EXT_HW_STATS_SUPPORTED) bp->fw_cap |= BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED; if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_PTP_PPS_SUPPORTED)) bp->fw_cap |= BNXT_FW_CAP_PTP_PPS; + if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_HOT_RESET_IF_SUPPORT)) + bp->fw_cap |= BNXT_FW_CAP_HOT_RESET_IF; + if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_FW_LIVEPATCH_SUPPORTED)) + bp->fw_cap |= BNXT_FW_CAP_LIVEPATCH; bp->tx_push_thresh = 0; if ((flags & FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED) && @@ -7579,6 +7547,32 @@ hwrm_func_qcaps_exit: return rc; } +static void bnxt_hwrm_dbg_qcaps(struct bnxt *bp) +{ + struct hwrm_dbg_qcaps_output *resp; + struct hwrm_dbg_qcaps_input *req; + int rc; + + bp->fw_dbg_cap = 0; + if (!(bp->fw_cap & BNXT_FW_CAP_DBG_QCAPS)) + return; + + rc = hwrm_req_init(bp, req, HWRM_DBG_QCAPS); + if (rc) + return; + + req->fid = cpu_to_le16(0xffff); + resp = hwrm_req_hold(bp, req); + rc = hwrm_req_send(bp, req); + if (rc) + goto hwrm_dbg_qcaps_exit; + + bp->fw_dbg_cap = le32_to_cpu(resp->flags); + +hwrm_dbg_qcaps_exit: + hwrm_req_drop(bp, req); +} + static int bnxt_hwrm_queue_qportcfg(struct bnxt *bp); static int bnxt_hwrm_func_qcaps(struct bnxt *bp) @@ -7588,6 +7582,9 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp) rc = __bnxt_hwrm_func_qcaps(bp); if (rc) return rc; + + bnxt_hwrm_dbg_qcaps(bp); + rc = bnxt_hwrm_queue_qportcfg(bp); if (rc) { netdev_err(bp->dev, "hwrm query qportcfg failure rc: %d\n", rc); @@ -7642,6 +7639,7 @@ static int __bnxt_alloc_fw_health(struct bnxt *bp) if (!bp->fw_health) return -ENOMEM; + mutex_init(&bp->fw_health->lock); return 0; } @@ -7688,12 +7686,16 @@ static void bnxt_inv_fw_health_reg(struct bnxt *bp) struct bnxt_fw_health *fw_health = bp->fw_health; u32 reg_type; - if (!fw_health || !fw_health->status_reliable) + if (!fw_health) return; reg_type = BNXT_FW_HEALTH_REG_TYPE(fw_health->regs[BNXT_FW_HEALTH_REG]); if (reg_type == BNXT_FW_HEALTH_REG_TYPE_GRC) fw_health->status_reliable = false; + + reg_type = BNXT_FW_HEALTH_REG_TYPE(fw_health->regs[BNXT_FW_RESET_CNT_REG]); + if (reg_type == BNXT_FW_HEALTH_REG_TYPE_GRC) + fw_health->resets_reliable = false; } static void bnxt_try_map_fw_health_reg(struct bnxt *bp) @@ -7750,6 +7752,7 @@ static int bnxt_map_fw_health_regs(struct bnxt *bp) int i; bp->fw_health->status_reliable = false; + bp->fw_health->resets_reliable = false; /* Only pre-map the monitoring GRC registers using window 3 */ for (i = 0; i < 4; i++) { u32 reg = fw_health->regs[i]; @@ -7763,6 +7766,7 @@ static int bnxt_map_fw_health_regs(struct bnxt *bp) fw_health->mapped_regs[i] = BNXT_FW_HEALTH_WIN_OFF(reg); } bp->fw_health->status_reliable = true; + bp->fw_health->resets_reliable = true; if (reg_base == 0xffffffff) return 0; @@ -8208,6 +8212,10 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp, u8 flags) if (!rc) { bp->fw_rx_stats_ext_size = le16_to_cpu(resp_qs->rx_stat_size) / 8; + if (BNXT_FW_MAJ(bp) < 220 && + bp->fw_rx_stats_ext_size > BNXT_RX_STATS_EXT_NUM_LEGACY) + bp->fw_rx_stats_ext_size = BNXT_RX_STATS_EXT_NUM_LEGACY; + bp->fw_tx_stats_ext_size = tx_stat_size ? le16_to_cpu(resp_qs->tx_stat_size) / 8 : 0; } else { @@ -9246,7 +9254,7 @@ static char *bnxt_report_fec(struct bnxt_link_info *link_info) } } -static void bnxt_report_link(struct bnxt *bp) +void bnxt_report_link(struct bnxt *bp) { if (bp->link_info.link_up) { const char *signal = ""; @@ -9691,8 +9699,6 @@ static int bnxt_hwrm_shutdown_link(struct bnxt *bp) return hwrm_req_send(bp, req); } -static int bnxt_fw_init_one(struct bnxt *bp); - static int bnxt_fw_reset_via_optee(struct bnxt *bp) { #ifdef CONFIG_TEE_BNXT_FW @@ -9739,6 +9745,33 @@ static int bnxt_try_recover_fw(struct bnxt *bp) return -ENODEV; } +int bnxt_cancel_reservations(struct bnxt *bp, bool fw_reset) +{ + struct bnxt_hw_resc *hw_resc = &bp->hw_resc; + int rc; + + if (!BNXT_NEW_RM(bp)) + return 0; /* no resource reservations required */ + + rc = bnxt_hwrm_func_resc_qcaps(bp, true); + if (rc) + netdev_err(bp->dev, "resc_qcaps failed\n"); + + hw_resc->resv_cp_rings = 0; + hw_resc->resv_stat_ctxs = 0; + hw_resc->resv_irqs = 0; + hw_resc->resv_tx_rings = 0; + hw_resc->resv_rx_rings = 0; + hw_resc->resv_hw_ring_grps = 0; + hw_resc->resv_vnics = 0; + if (!fw_reset) { + bp->tx_nr_rings = 0; + bp->rx_nr_rings = 0; + } + + return rc; +} + static int bnxt_hwrm_if_change(struct bnxt *bp, bool up) { struct hwrm_func_drv_if_change_output *resp; @@ -9822,25 +9855,7 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up) return rc; } } - if (BNXT_NEW_RM(bp)) { - struct bnxt_hw_resc *hw_resc = &bp->hw_resc; - - rc = bnxt_hwrm_func_resc_qcaps(bp, true); - if (rc) - netdev_err(bp->dev, "resc_qcaps failed\n"); - - hw_resc->resv_cp_rings = 0; - hw_resc->resv_stat_ctxs = 0; - hw_resc->resv_irqs = 0; - hw_resc->resv_tx_rings = 0; - hw_resc->resv_rx_rings = 0; - hw_resc->resv_hw_ring_grps = 0; - hw_resc->resv_vnics = 0; - if (!fw_reset) { - bp->tx_nr_rings = 0; - bp->rx_nr_rings = 0; - } - } + rc = bnxt_cancel_reservations(bp, fw_reset); } return rc; } @@ -10318,7 +10333,7 @@ void bnxt_half_close_nic(struct bnxt *bp) bnxt_free_mem(bp, false); } -static void bnxt_reenable_sriov(struct bnxt *bp) +void bnxt_reenable_sriov(struct bnxt *bp) { if (BNXT_PF(bp)) { struct bnxt_pf_info *pf = &bp->pf; @@ -11295,14 +11310,18 @@ static void bnxt_fw_health_check(struct bnxt *bp) } val = bnxt_fw_health_readl(bp, BNXT_FW_HEARTBEAT_REG); - if (val == fw_health->last_fw_heartbeat) + if (val == fw_health->last_fw_heartbeat) { + fw_health->arrests++; goto fw_reset; + } fw_health->last_fw_heartbeat = val; val = bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG); - if (val != fw_health->last_fw_reset_cnt) + if (val != fw_health->last_fw_reset_cnt) { + fw_health->discoveries++; goto fw_reset; + } fw_health->tmr_counter = fw_health->tmr_multiplier; return; @@ -11508,7 +11527,7 @@ static void bnxt_force_fw_reset(struct bnxt *bp) } bnxt_fw_reset_close(bp); wait_dsecs = fw_health->master_func_wait_dsecs; - if (fw_health->master) { + if (fw_health->primary) { if (fw_health->flags & ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU) wait_dsecs = 0; bp->fw_reset_state = BNXT_FW_RESET_STATE_RESET_FW; @@ -11772,13 +11791,17 @@ static void bnxt_sp_task(struct work_struct *work) if (test_and_clear_bit(BNXT_RST_RING_SP_EVENT, &bp->sp_event)) bnxt_rx_ring_reset(bp); - if (test_and_clear_bit(BNXT_FW_RESET_NOTIFY_SP_EVENT, &bp->sp_event)) - bnxt_devlink_health_report(bp, BNXT_FW_RESET_NOTIFY_SP_EVENT); + if (test_and_clear_bit(BNXT_FW_RESET_NOTIFY_SP_EVENT, &bp->sp_event)) { + if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state) || + test_bit(BNXT_STATE_FW_NON_FATAL_COND, &bp->state)) + bnxt_devlink_health_fw_report(bp); + else + bnxt_fw_reset(bp); + } if (test_and_clear_bit(BNXT_FW_EXCEPTION_SP_EVENT, &bp->sp_event)) { if (!is_bnxt_fw_ok(bp)) - bnxt_devlink_health_report(bp, - BNXT_FW_EXCEPTION_SP_EVENT); + bnxt_devlink_health_fw_report(bp); } smp_mb__before_atomic(); @@ -11989,7 +12012,7 @@ static void bnxt_fw_init_one_p3(struct bnxt *bp) static int bnxt_probe_phy(struct bnxt *bp, bool fw_dflt); -static int bnxt_fw_init_one(struct bnxt *bp) +int bnxt_fw_init_one(struct bnxt *bp) { int rc; @@ -12051,6 +12074,27 @@ static void bnxt_fw_reset_writel(struct bnxt *bp, int reg_idx) } } +bool bnxt_hwrm_reset_permitted(struct bnxt *bp) +{ + struct hwrm_func_qcfg_output *resp; + struct hwrm_func_qcfg_input *req; + bool result = true; /* firmware will enforce if unknown */ + + if (~bp->fw_cap & BNXT_FW_CAP_HOT_RESET_IF) + return result; + + if (hwrm_req_init(bp, req, HWRM_FUNC_QCFG)) + return result; + + req->fid = cpu_to_le16(0xffff); + resp = hwrm_req_hold(bp, req); + if (!hwrm_req_send(bp, req)) + result = !!(le16_to_cpu(resp->flags) & + FUNC_QCFG_RESP_FLAGS_HOT_RESET_ALLOWED); + hwrm_req_drop(bp, req); + return result; +} + static void bnxt_reset_all(struct bnxt *bp) { struct bnxt_fw_health *fw_health = bp->fw_health; @@ -12093,7 +12137,7 @@ static void bnxt_fw_reset_abort(struct bnxt *bp, int rc) clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF) { bnxt_ulp_start(bp, rc); - bnxt_dl_health_status_update(bp, false); + bnxt_dl_health_fw_status_update(bp, false); } bp->fw_reset_state = 0; dev_close(bp->dev); @@ -12159,7 +12203,7 @@ static void bnxt_fw_reset_task(struct work_struct *work) return; } - if (!bp->fw_health->master) { + if (!bp->fw_health->primary) { u32 wait_dsecs = bp->fw_health->normal_func_wait_dsecs; bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV; @@ -12192,6 +12236,10 @@ static void bnxt_fw_reset_task(struct work_struct *work) } } clear_bit(BNXT_STATE_FW_FATAL_COND, &bp->state); + clear_bit(BNXT_STATE_FW_NON_FATAL_COND, &bp->state); + if (test_and_clear_bit(BNXT_STATE_FW_ACTIVATE_RESET, &bp->state) && + !test_bit(BNXT_STATE_FW_ACTIVATE, &bp->state)) + bnxt_dl_remote_reload(bp); if (pci_enable_device(bp->pdev)) { netdev_err(bp->dev, "Cannot re-enable PCI device\n"); rc = -ENODEV; @@ -12241,8 +12289,11 @@ static void bnxt_fw_reset_task(struct work_struct *work) bnxt_vf_reps_alloc(bp); bnxt_vf_reps_open(bp); bnxt_ptp_reapply_pps(bp); - bnxt_dl_health_recovery_done(bp); - bnxt_dl_health_status_update(bp, true); + clear_bit(BNXT_STATE_FW_ACTIVATE, &bp->state); + if (test_and_clear_bit(BNXT_STATE_RECOVER, &bp->state)) { + bnxt_dl_health_fw_recovery_done(bp); + bnxt_dl_health_fw_status_update(bp, true); + } rtnl_unlock(); break; } @@ -13186,6 +13237,15 @@ static int bnxt_map_db_bar(struct bnxt *bp) return 0; } +void bnxt_print_device_info(struct bnxt *bp) +{ + netdev_info(bp->dev, "%s found at mem %lx, node addr %pM\n", + board_info[bp->board_idx].name, + (long)pci_resource_start(bp->pdev, 0), bp->dev->dev_addr); + + pcie_print_link_status(bp->pdev); +} + static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { struct net_device *dev; @@ -13209,10 +13269,11 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return -ENOMEM; bp = netdev_priv(dev); + bp->board_idx = ent->driver_data; bp->msg_enable = BNXT_DEF_MSG_ENABLE; bnxt_set_max_func_irqs(bp, max_irqs); - if (bnxt_vf_pciid(ent->driver_data)) + if (bnxt_vf_pciid(bp->board_idx)) bp->flags |= BNXT_FLAG_VF; if (pdev->msix_cap) @@ -13382,10 +13443,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) devlink_port_type_eth_set(&bp->dl_port, bp->dev); bnxt_dl_fw_reporters_create(bp); - netdev_info(dev, "%s found at mem %lx, node addr %pM\n", - board_info[ent->driver_data].name, - (long)pci_resource_start(pdev, 0), dev->dev_addr); - pcie_print_link_status(pdev); + bnxt_print_device_info(bp); pci_save_state(pdev); return 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 19fe6478e9b4..d0d5da9b78f8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -489,6 +489,15 @@ struct rx_tpa_end_cmp_ext { ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MASK) ==\ ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_FATAL) +#define EVENT_DATA1_RESET_NOTIFY_FW_ACTIVATION(data1) \ + (((data1) & \ + ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MASK) ==\ + ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_ACTIVATION) + +#define EVENT_DATA2_RESET_NOTIFY_FW_STATUS_CODE(data2) \ + ((data2) & \ + ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA2_FW_STATUS_CODE_MASK) + #define EVENT_DATA1_RECOVERY_MASTER_FUNC(data1) \ !!((data1) & \ ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASTER_FUNC) @@ -1514,6 +1523,21 @@ struct bnxt_ctx_mem_info { struct bnxt_mem_init mem_init[BNXT_CTX_MEM_INIT_MAX]; }; +enum bnxt_health_severity { + SEVERITY_NORMAL = 0, + SEVERITY_WARNING, + SEVERITY_RECOVERABLE, + SEVERITY_FATAL, +}; + +enum bnxt_health_remedy { + REMEDY_DEVLINK_RECOVER, + REMEDY_POWER_CYCLE_DEVICE, + REMEDY_POWER_CYCLE_HOST, + REMEDY_FW_UPDATE, + REMEDY_HW_REPLACE, +}; + struct bnxt_fw_health { u32 flags; u32 polling_dsecs; @@ -1531,9 +1555,9 @@ struct bnxt_fw_health { u32 last_fw_heartbeat; u32 last_fw_reset_cnt; u8 enabled:1; - u8 master:1; - u8 fatal:1; + u8 primary:1; u8 status_reliable:1; + u8 resets_reliable:1; u8 tmr_multiplier; u8 tmr_counter; u8 fw_reset_seq_cnt; @@ -1543,12 +1567,15 @@ struct bnxt_fw_health { u32 echo_req_data1; u32 echo_req_data2; struct devlink_health_reporter *fw_reporter; - struct devlink_health_reporter *fw_reset_reporter; - struct devlink_health_reporter *fw_fatal_reporter; -}; - -struct bnxt_fw_reporter_ctx { - unsigned long sp_event; + /* Protects severity and remedy */ + struct mutex lock; + enum bnxt_health_severity severity; + enum bnxt_health_remedy remedy; + u32 arrests; + u32 discoveries; + u32 survivals; + u32 fatalities; + u32 diagnoses; }; #define BNXT_FW_HEALTH_REG_TYPE_MASK 3 @@ -1586,6 +1613,54 @@ struct bnxt_fw_reporter_ctx { #define BNXT_FW_RETRY 5 #define BNXT_FW_IF_RETRY 10 +enum board_idx { + BCM57301, + BCM57302, + BCM57304, + BCM57417_NPAR, + BCM58700, + BCM57311, + BCM57312, + BCM57402, + BCM57404, + BCM57406, + BCM57402_NPAR, + BCM57407, + BCM57412, + BCM57414, + BCM57416, + BCM57417, + BCM57412_NPAR, + BCM57314, + BCM57417_SFP, + BCM57416_SFP, + BCM57404_NPAR, + BCM57406_NPAR, + BCM57407_SFP, + BCM57407_NPAR, + BCM57414_NPAR, + BCM57416_NPAR, + BCM57452, + BCM57454, + BCM5745x_NPAR, + BCM57508, + BCM57504, + BCM57502, + BCM57508_NPAR, + BCM57504_NPAR, + BCM57502_NPAR, + BCM58802, + BCM58804, + BCM58808, + NETXTREME_E_VF, + NETXTREME_C_VF, + NETXTREME_S_VF, + NETXTREME_C_VF_HV, + NETXTREME_E_VF_HV, + NETXTREME_E_P5_VF, + NETXTREME_E_P5_VF_HV, +}; + struct bnxt { void __iomem *bar0; void __iomem *bar1; @@ -1840,6 +1915,10 @@ struct bnxt { #define BNXT_STATE_DRV_REGISTERED 7 #define BNXT_STATE_PCI_CHANNEL_IO_FROZEN 8 #define BNXT_STATE_NAPI_DISABLED 9 +#define BNXT_STATE_FW_ACTIVATE 11 +#define BNXT_STATE_RECOVER 12 +#define BNXT_STATE_FW_NON_FATAL_COND 13 +#define BNXT_STATE_FW_ACTIVATE_RESET 14 #define BNXT_NO_FW_ACCESS(bp) \ (test_bit(BNXT_STATE_FW_FATAL_COND, &(bp)->state) || \ @@ -1879,8 +1958,13 @@ struct bnxt { #define BNXT_FW_CAP_VLAN_RX_STRIP 0x01000000 #define BNXT_FW_CAP_VLAN_TX_INSERT 0x02000000 #define BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED 0x04000000 + #define BNXT_FW_CAP_LIVEPATCH 0x08000000 #define BNXT_FW_CAP_PTP_PPS 0x10000000 + #define BNXT_FW_CAP_HOT_RESET_IF 0x20000000 #define BNXT_FW_CAP_RING_MONITOR 0x40000000 + #define BNXT_FW_CAP_DBG_QCAPS 0x80000000 + + u32 fw_dbg_cap; #define BNXT_NEW_RM(bp) ((bp)->fw_cap & BNXT_FW_CAP_NEW_RM) u32 hwrm_spec_code; @@ -2049,6 +2133,7 @@ struct bnxt { struct list_head tc_indr_block_list; struct dentry *debugfs_pdev; struct device *hwmon_dev; + enum board_idx board_idx; }; #define BNXT_NUM_RX_RING_STATS 8 @@ -2090,6 +2175,9 @@ struct bnxt { #define BNXT_RX_STATS_EXT_OFFSET(counter) \ (offsetof(struct rx_port_stats_ext, counter) / 8) +#define BNXT_RX_STATS_EXT_NUM_LEGACY \ + BNXT_RX_STATS_EXT_OFFSET(rx_fec_corrected_blocks) + #define BNXT_TX_STATS_EXT_OFFSET(counter) \ (offsetof(struct tx_port_stats_ext, counter) / 8) @@ -2181,11 +2269,13 @@ void bnxt_set_ring_params(struct bnxt *); int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode); int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size, bool async_only); +int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp); int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings); int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id); int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings); int bnxt_nq_rings_in_use(struct bnxt *bp); int bnxt_hwrm_set_coal(struct bnxt *); +void bnxt_free_ctx_mem(struct bnxt *bp); unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp); unsigned int bnxt_get_avail_stat_ctxs_for_en(struct bnxt *bp); unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp); @@ -2194,9 +2284,11 @@ int bnxt_get_avail_msix(struct bnxt *bp, int num); int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init); void bnxt_tx_disable(struct bnxt *bp); void bnxt_tx_enable(struct bnxt *bp); +void bnxt_report_link(struct bnxt *bp); int bnxt_update_link(struct bnxt *bp, bool chng_link_state); int bnxt_hwrm_set_pause(struct bnxt *); int bnxt_hwrm_set_link_setting(struct bnxt *, bool, bool); +int bnxt_cancel_reservations(struct bnxt *bp, bool fw_reset); int bnxt_hwrm_alloc_wol_fltr(struct bnxt *bp); int bnxt_hwrm_free_wol_fltr(struct bnxt *bp); int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all); @@ -2205,6 +2297,7 @@ int bnxt_hwrm_fw_set_time(struct bnxt *); int bnxt_open_nic(struct bnxt *, bool, bool); int bnxt_half_open_nic(struct bnxt *bp); void bnxt_half_close_nic(struct bnxt *bp); +void bnxt_reenable_sriov(struct bnxt *bp); int bnxt_close_nic(struct bnxt *, bool, bool); int bnxt_dbg_hwrm_rd_reg(struct bnxt *bp, u32 reg_off, u16 num_words, u32 *reg_buf); @@ -2212,6 +2305,8 @@ void bnxt_fw_exception(struct bnxt *bp); void bnxt_fw_reset(struct bnxt *bp); int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs, int tx_xdp); +int bnxt_fw_init_one(struct bnxt *bp); +bool bnxt_hwrm_reset_permitted(struct bnxt *bp); int bnxt_setup_mq_tc(struct net_device *dev, u8 tc); int bnxt_get_max_rings(struct bnxt *, int *, int *, bool); int bnxt_restore_pf_fw_resources(struct bnxt *bp); @@ -2219,5 +2314,5 @@ int bnxt_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid); void bnxt_dim_work(struct work_struct *work); int bnxt_hwrm_set_ring_coal(struct bnxt *bp, struct bnxt_napi *bnapi); - +void bnxt_print_device_info(struct bnxt *bp); #endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c new file mode 100644 index 000000000000..d3cb2f21946d --- /dev/null +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c @@ -0,0 +1,444 @@ +/* Broadcom NetXtreme-C/E network driver. + * + * Copyright (c) 2021 Broadcom Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + */ + +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/pci.h> +#include "bnxt_hsi.h" +#include "bnxt.h" +#include "bnxt_hwrm.h" +#include "bnxt_coredump.h" + +static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg, + struct bnxt_hwrm_dbg_dma_info *info) +{ + struct hwrm_dbg_cmn_input *cmn_req = msg; + __le16 *seq_ptr = msg + info->seq_off; + struct hwrm_dbg_cmn_output *cmn_resp; + u16 seq = 0, len, segs_off; + dma_addr_t dma_handle; + void *dma_buf, *resp; + int rc, off = 0; + + dma_buf = hwrm_req_dma_slice(bp, msg, info->dma_len, &dma_handle); + if (!dma_buf) { + hwrm_req_drop(bp, msg); + return -ENOMEM; + } + + hwrm_req_timeout(bp, msg, HWRM_COREDUMP_TIMEOUT); + cmn_resp = hwrm_req_hold(bp, msg); + resp = cmn_resp; + + segs_off = offsetof(struct hwrm_dbg_coredump_list_output, + total_segments); + cmn_req->host_dest_addr = cpu_to_le64(dma_handle); + cmn_req->host_buf_len = cpu_to_le32(info->dma_len); + while (1) { + *seq_ptr = cpu_to_le16(seq); + rc = hwrm_req_send(bp, msg); + if (rc) + break; + + len = le16_to_cpu(*((__le16 *)(resp + info->data_len_off))); + if (!seq && + cmn_req->req_type == cpu_to_le16(HWRM_DBG_COREDUMP_LIST)) { + info->segs = le16_to_cpu(*((__le16 *)(resp + + segs_off))); + if (!info->segs) { + rc = -EIO; + break; + } + + info->dest_buf_size = info->segs * + sizeof(struct coredump_segment_record); + info->dest_buf = kmalloc(info->dest_buf_size, + GFP_KERNEL); + if (!info->dest_buf) { + rc = -ENOMEM; + break; + } + } + + if (info->dest_buf) { + if ((info->seg_start + off + len) <= + BNXT_COREDUMP_BUF_LEN(info->buf_len)) { + memcpy(info->dest_buf + off, dma_buf, len); + } else { + rc = -ENOBUFS; + break; + } + } + + if (cmn_req->req_type == + cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE)) + info->dest_buf_size += len; + + if (!(cmn_resp->flags & HWRM_DBG_CMN_FLAGS_MORE)) + break; + + seq++; + off += len; + } + hwrm_req_drop(bp, msg); + return rc; +} + +static int bnxt_hwrm_dbg_coredump_list(struct bnxt *bp, + struct bnxt_coredump *coredump) +{ + struct bnxt_hwrm_dbg_dma_info info = {NULL}; + struct hwrm_dbg_coredump_list_input *req; + int rc; + + rc = hwrm_req_init(bp, req, HWRM_DBG_COREDUMP_LIST); + if (rc) + return rc; + + info.dma_len = COREDUMP_LIST_BUF_LEN; + info.seq_off = offsetof(struct hwrm_dbg_coredump_list_input, seq_no); + info.data_len_off = offsetof(struct hwrm_dbg_coredump_list_output, + data_len); + + rc = bnxt_hwrm_dbg_dma_data(bp, req, &info); + if (!rc) { + coredump->data = info.dest_buf; + coredump->data_size = info.dest_buf_size; + coredump->total_segs = info.segs; + } + return rc; +} + +static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id, + u16 segment_id) +{ + struct hwrm_dbg_coredump_initiate_input *req; + int rc; + + rc = hwrm_req_init(bp, req, HWRM_DBG_COREDUMP_INITIATE); + if (rc) + return rc; + + hwrm_req_timeout(bp, req, HWRM_COREDUMP_TIMEOUT); + req->component_id = cpu_to_le16(component_id); + req->segment_id = cpu_to_le16(segment_id); + + return hwrm_req_send(bp, req); +} + +static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id, + u16 segment_id, u32 *seg_len, + void *buf, u32 buf_len, u32 offset) +{ + struct hwrm_dbg_coredump_retrieve_input *req; + struct bnxt_hwrm_dbg_dma_info info = {NULL}; + int rc; + + rc = hwrm_req_init(bp, req, HWRM_DBG_COREDUMP_RETRIEVE); + if (rc) + return rc; + + req->component_id = cpu_to_le16(component_id); + req->segment_id = cpu_to_le16(segment_id); + + info.dma_len = COREDUMP_RETRIEVE_BUF_LEN; + info.seq_off = offsetof(struct hwrm_dbg_coredump_retrieve_input, + seq_no); + info.data_len_off = offsetof(struct hwrm_dbg_coredump_retrieve_output, + data_len); + if (buf) { + info.dest_buf = buf + offset; + info.buf_len = buf_len; + info.seg_start = offset; + } + + rc = bnxt_hwrm_dbg_dma_data(bp, req, &info); + if (!rc) + *seg_len = info.dest_buf_size; + + return rc; +} + +static void +bnxt_fill_coredump_seg_hdr(struct bnxt *bp, + struct bnxt_coredump_segment_hdr *seg_hdr, + struct coredump_segment_record *seg_rec, u32 seg_len, + int status, u32 duration, u32 instance) +{ + memset(seg_hdr, 0, sizeof(*seg_hdr)); + memcpy(seg_hdr->signature, "sEgM", 4); + if (seg_rec) { + seg_hdr->component_id = (__force __le32)seg_rec->component_id; + seg_hdr->segment_id = (__force __le32)seg_rec->segment_id; + seg_hdr->low_version = seg_rec->version_low; + seg_hdr->high_version = seg_rec->version_hi; + seg_hdr->flags = cpu_to_le32(seg_rec->compress_flags); + } else { + /* For hwrm_ver_get response Component id = 2 + * and Segment id = 0 + */ + seg_hdr->component_id = cpu_to_le32(2); + seg_hdr->segment_id = 0; + } + seg_hdr->function_id = cpu_to_le16(bp->pdev->devfn); + seg_hdr->length = cpu_to_le32(seg_len); + seg_hdr->status = cpu_to_le32(status); + seg_hdr->duration = cpu_to_le32(duration); + seg_hdr->data_offset = cpu_to_le32(sizeof(*seg_hdr)); + seg_hdr->instance = cpu_to_le32(instance); +} + +static void bnxt_fill_cmdline(struct bnxt_coredump_record *record) +{ + struct mm_struct *mm = current->mm; + int i, len, last = 0; + + if (mm) { + len = min_t(int, mm->arg_end - mm->arg_start, + sizeof(record->commandline) - 1); + if (len && !copy_from_user(record->commandline, + (char __user *)mm->arg_start, len)) { + for (i = 0; i < len; i++) { + if (record->commandline[i]) + last = i; + else + record->commandline[i] = ' '; + } + record->commandline[last + 1] = 0; + return; + } + } + + strscpy(record->commandline, current->comm, TASK_COMM_LEN); +} + +static void +bnxt_fill_coredump_record(struct bnxt *bp, struct bnxt_coredump_record *record, + time64_t start, s16 start_utc, u16 total_segs, + int status) +{ + time64_t end = ktime_get_real_seconds(); + u32 os_ver_major = 0, os_ver_minor = 0; + struct tm tm; + + time64_to_tm(start, 0, &tm); + memset(record, 0, sizeof(*record)); + memcpy(record->signature, "cOrE", 4); + record->flags = 0; + record->low_version = 0; + record->high_version = 1; + record->asic_state = 0; + strscpy(record->system_name, utsname()->nodename, + sizeof(record->system_name)); + record->year = cpu_to_le16(tm.tm_year + 1900); + record->month = cpu_to_le16(tm.tm_mon + 1); + record->day = cpu_to_le16(tm.tm_mday); + record->hour = cpu_to_le16(tm.tm_hour); + record->minute = cpu_to_le16(tm.tm_min); + record->second = cpu_to_le16(tm.tm_sec); + record->utc_bias = cpu_to_le16(start_utc); + bnxt_fill_cmdline(record); + record->total_segments = cpu_to_le32(total_segs); + + if (sscanf(utsname()->release, "%u.%u", &os_ver_major, &os_ver_minor) != 2) + netdev_warn(bp->dev, "Unknown OS release in coredump\n"); + record->os_ver_major = cpu_to_le32(os_ver_major); + record->os_ver_minor = cpu_to_le32(os_ver_minor); + + strscpy(record->os_name, utsname()->sysname, sizeof(record->os_name)); + time64_to_tm(end, 0, &tm); + record->end_year = cpu_to_le16(tm.tm_year + 1900); + record->end_month = cpu_to_le16(tm.tm_mon + 1); + record->end_day = cpu_to_le16(tm.tm_mday); + record->end_hour = cpu_to_le16(tm.tm_hour); + record->end_minute = cpu_to_le16(tm.tm_min); + record->end_second = cpu_to_le16(tm.tm_sec); + record->end_utc_bias = cpu_to_le16(sys_tz.tz_minuteswest * 60); + record->asic_id1 = cpu_to_le32(bp->chip_num << 16 | + bp->ver_resp.chip_rev << 8 | + bp->ver_resp.chip_metal); + record->asic_id2 = 0; + record->coredump_status = cpu_to_le32(status); + record->ioctl_low_version = 0; + record->ioctl_high_version = 0; +} + +static int __bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len) +{ + u32 ver_get_resp_len = sizeof(struct hwrm_ver_get_output); + u32 offset = 0, seg_hdr_len, seg_record_len, buf_len = 0; + struct coredump_segment_record *seg_record = NULL; + struct bnxt_coredump_segment_hdr seg_hdr; + struct bnxt_coredump coredump = {NULL}; + time64_t start_time; + u16 start_utc; + int rc = 0, i; + + if (buf) + buf_len = *dump_len; + + start_time = ktime_get_real_seconds(); + start_utc = sys_tz.tz_minuteswest * 60; + seg_hdr_len = sizeof(seg_hdr); + + /* First segment should be hwrm_ver_get response */ + *dump_len = seg_hdr_len + ver_get_resp_len; + if (buf) { + bnxt_fill_coredump_seg_hdr(bp, &seg_hdr, NULL, ver_get_resp_len, + 0, 0, 0); + memcpy(buf + offset, &seg_hdr, seg_hdr_len); + offset += seg_hdr_len; + memcpy(buf + offset, &bp->ver_resp, ver_get_resp_len); + offset += ver_get_resp_len; + } + + rc = bnxt_hwrm_dbg_coredump_list(bp, &coredump); + if (rc) { + netdev_err(bp->dev, "Failed to get coredump segment list\n"); + goto err; + } + + *dump_len += seg_hdr_len * coredump.total_segs; + + seg_record = (struct coredump_segment_record *)coredump.data; + seg_record_len = sizeof(*seg_record); + + for (i = 0; i < coredump.total_segs; i++) { + u16 comp_id = le16_to_cpu(seg_record->component_id); + u16 seg_id = le16_to_cpu(seg_record->segment_id); + u32 duration = 0, seg_len = 0; + unsigned long start, end; + + if (buf && ((offset + seg_hdr_len) > + BNXT_COREDUMP_BUF_LEN(buf_len))) { + rc = -ENOBUFS; + goto err; + } + + start = jiffies; + + rc = bnxt_hwrm_dbg_coredump_initiate(bp, comp_id, seg_id); + if (rc) { + netdev_err(bp->dev, + "Failed to initiate coredump for seg = %d\n", + seg_record->segment_id); + goto next_seg; + } + + /* Write segment data into the buffer */ + rc = bnxt_hwrm_dbg_coredump_retrieve(bp, comp_id, seg_id, + &seg_len, buf, buf_len, + offset + seg_hdr_len); + if (rc && rc == -ENOBUFS) + goto err; + else if (rc) + netdev_err(bp->dev, + "Failed to retrieve coredump for seg = %d\n", + seg_record->segment_id); + +next_seg: + end = jiffies; + duration = jiffies_to_msecs(end - start); + bnxt_fill_coredump_seg_hdr(bp, &seg_hdr, seg_record, seg_len, + rc, duration, 0); + + if (buf) { + /* Write segment header into the buffer */ + memcpy(buf + offset, &seg_hdr, seg_hdr_len); + offset += seg_hdr_len + seg_len; + } + + *dump_len += seg_len; + seg_record = + (struct coredump_segment_record *)((u8 *)seg_record + + seg_record_len); + } + +err: + if (buf) + bnxt_fill_coredump_record(bp, buf + offset, start_time, + start_utc, coredump.total_segs + 1, + rc); + kfree(coredump.data); + *dump_len += sizeof(struct bnxt_coredump_record); + if (rc == -ENOBUFS) + netdev_err(bp->dev, "Firmware returned large coredump buffer\n"); + return rc; +} + +int bnxt_get_coredump(struct bnxt *bp, u16 dump_type, void *buf, u32 *dump_len) +{ + if (dump_type == BNXT_DUMP_CRASH) { +#ifdef CONFIG_TEE_BNXT_FW + return tee_bnxt_copy_coredump(buf, 0, *dump_len); +#else + return -EOPNOTSUPP; +#endif + } else { + return __bnxt_get_coredump(bp, buf, dump_len); + } +} + +static int bnxt_hwrm_get_dump_len(struct bnxt *bp, u16 dump_type, u32 *dump_len) +{ + struct hwrm_dbg_qcfg_output *resp; + struct hwrm_dbg_qcfg_input *req; + int rc, hdr_len = 0; + + if (!(bp->fw_cap & BNXT_FW_CAP_DBG_QCAPS)) + return -EOPNOTSUPP; + + if (dump_type == BNXT_DUMP_CRASH && + !(bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR)) + return -EOPNOTSUPP; + + rc = hwrm_req_init(bp, req, HWRM_DBG_QCFG); + if (rc) + return rc; + + req->fid = cpu_to_le16(0xffff); + if (dump_type == BNXT_DUMP_CRASH) + req->flags = cpu_to_le16(DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_SOC_DDR); + + resp = hwrm_req_hold(bp, req); + rc = hwrm_req_send(bp, req); + if (rc) + goto get_dump_len_exit; + + if (dump_type == BNXT_DUMP_CRASH) { + *dump_len = le32_to_cpu(resp->crashdump_size); + } else { + /* Driver adds coredump header and "HWRM_VER_GET response" + * segment additionally to coredump. + */ + hdr_len = sizeof(struct bnxt_coredump_segment_hdr) + + sizeof(struct hwrm_ver_get_output) + + sizeof(struct bnxt_coredump_record); + *dump_len = le32_to_cpu(resp->coredump_size) + hdr_len; + } + if (*dump_len <= hdr_len) + rc = -EINVAL; + +get_dump_len_exit: + hwrm_req_drop(bp, req); + return rc; +} + +u32 bnxt_get_coredump_length(struct bnxt *bp, u16 dump_type) +{ + u32 len = 0; + + if (bnxt_hwrm_get_dump_len(bp, dump_type, &len)) { + if (dump_type == BNXT_DUMP_CRASH) + len = BNXT_CRASH_DUMP_LEN; + else + __bnxt_get_coredump(bp, NULL, &len); + } + return len; +} diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h index 09c22f8fe399..b1a1b2fffb19 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h @@ -10,6 +10,10 @@ #ifndef BNXT_COREDUMP_H #define BNXT_COREDUMP_H +#include <linux/utsname.h> +#include <linux/time.h> +#include <linux/rtc.h> + struct bnxt_coredump_segment_hdr { __u8 signature[4]; __le32 component_id; @@ -63,4 +67,51 @@ struct bnxt_coredump_record { __u8 ioctl_high_version; __le16 rsvd3[313]; }; + +#define BNXT_CRASH_DUMP_LEN (8 << 20) + +#define COREDUMP_LIST_BUF_LEN 2048 +#define COREDUMP_RETRIEVE_BUF_LEN 4096 + +struct bnxt_coredump { + void *data; + int data_size; + u16 total_segs; +}; + +#define BNXT_COREDUMP_BUF_LEN(len) ((len) - sizeof(struct bnxt_coredump_record)) + +struct bnxt_hwrm_dbg_dma_info { + void *dest_buf; + int dest_buf_size; + u16 dma_len; + u16 seq_off; + u16 data_len_off; + u16 segs; + u32 seg_start; + u32 buf_len; +}; + +struct hwrm_dbg_cmn_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le64 host_dest_addr; + __le32 host_buf_len; +}; + +struct hwrm_dbg_cmn_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 flags; + #define HWRM_DBG_CMN_FLAGS_MORE 1 +}; + +int bnxt_get_coredump(struct bnxt *bp, u16 dump_type, void *buf, u32 *dump_len); +u32 bnxt_get_coredump_length(struct bnxt *bp, u16 dump_type); + #endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 951c0c00cc95..ce790e9b45c3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -16,6 +16,18 @@ #include "bnxt_vfr.h" #include "bnxt_devlink.h" #include "bnxt_ethtool.h" +#include "bnxt_ulp.h" +#include "bnxt_ptp.h" +#include "bnxt_coredump.h" + +static void __bnxt_fw_recover(struct bnxt *bp) +{ + if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state) || + test_bit(BNXT_STATE_FW_NON_FATAL_COND, &bp->state)) + bnxt_fw_reset(bp); + else + bnxt_fw_exception(bp); +} static int bnxt_dl_flash_update(struct devlink *dl, @@ -40,146 +52,208 @@ bnxt_dl_flash_update(struct devlink *dl, return rc; } -static int bnxt_fw_reporter_diagnose(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg, - struct netlink_ext_ack *extack) +static int bnxt_hwrm_remote_dev_reset_set(struct bnxt *bp, bool remote_reset) +{ + struct hwrm_func_cfg_input *req; + int rc; + + if (~bp->fw_cap & BNXT_FW_CAP_HOT_RESET_IF) + return -EOPNOTSUPP; + + rc = hwrm_req_init(bp, req, HWRM_FUNC_CFG); + if (rc) + return rc; + + req->fid = cpu_to_le16(0xffff); + req->enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_HOT_RESET_IF_SUPPORT); + if (remote_reset) + req->flags = cpu_to_le32(FUNC_CFG_REQ_FLAGS_HOT_RESET_IF_EN_DIS); + + return hwrm_req_send(bp, req); +} + +static char *bnxt_health_severity_str(enum bnxt_health_severity severity) +{ + switch (severity) { + case SEVERITY_NORMAL: return "normal"; + case SEVERITY_WARNING: return "warning"; + case SEVERITY_RECOVERABLE: return "recoverable"; + case SEVERITY_FATAL: return "fatal"; + default: return "unknown"; + } +} + +static char *bnxt_health_remedy_str(enum bnxt_health_remedy remedy) +{ + switch (remedy) { + case REMEDY_DEVLINK_RECOVER: return "devlink recover"; + case REMEDY_POWER_CYCLE_DEVICE: return "device power cycle"; + case REMEDY_POWER_CYCLE_HOST: return "host power cycle"; + case REMEDY_FW_UPDATE: return "update firmware"; + case REMEDY_HW_REPLACE: return "replace hardware"; + default: return "unknown"; + } +} + +static int bnxt_fw_diagnose(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) { struct bnxt *bp = devlink_health_reporter_priv(reporter); - u32 val; + struct bnxt_fw_health *h = bp->fw_health; + u32 fw_status, fw_resets; int rc; if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) - return 0; + return devlink_fmsg_string_pair_put(fmsg, "Status", "recovering"); - val = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG); + if (!h->status_reliable) + return devlink_fmsg_string_pair_put(fmsg, "Status", "unknown"); - if (BNXT_FW_IS_BOOTING(val)) { - rc = devlink_fmsg_string_pair_put(fmsg, "Description", - "Not yet completed initialization"); + mutex_lock(&h->lock); + fw_status = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG); + if (BNXT_FW_IS_BOOTING(fw_status)) { + rc = devlink_fmsg_string_pair_put(fmsg, "Status", "initializing"); if (rc) - return rc; - } else if (BNXT_FW_IS_ERR(val)) { - rc = devlink_fmsg_string_pair_put(fmsg, "Description", - "Encountered fatal error and cannot recover"); + goto unlock; + } else if (h->severity || fw_status != BNXT_FW_STATUS_HEALTHY) { + if (!h->severity) { + h->severity = SEVERITY_FATAL; + h->remedy = REMEDY_POWER_CYCLE_DEVICE; + h->diagnoses++; + devlink_health_report(h->fw_reporter, + "FW error diagnosed", h); + } + rc = devlink_fmsg_string_pair_put(fmsg, "Status", "error"); if (rc) - return rc; + goto unlock; + rc = devlink_fmsg_u32_pair_put(fmsg, "Syndrome", fw_status); + if (rc) + goto unlock; + } else { + rc = devlink_fmsg_string_pair_put(fmsg, "Status", "healthy"); + if (rc) + goto unlock; } - if (val >> 16) { - rc = devlink_fmsg_u32_pair_put(fmsg, "Error code", val >> 16); + rc = devlink_fmsg_string_pair_put(fmsg, "Severity", + bnxt_health_severity_str(h->severity)); + if (rc) + goto unlock; + + if (h->severity) { + rc = devlink_fmsg_string_pair_put(fmsg, "Remedy", + bnxt_health_remedy_str(h->remedy)); if (rc) - return rc; + goto unlock; + if (h->remedy == REMEDY_DEVLINK_RECOVER) { + rc = devlink_fmsg_string_pair_put(fmsg, "Impact", + "traffic+ntuple_cfg"); + if (rc) + goto unlock; + } } - val = bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG); - rc = devlink_fmsg_u32_pair_put(fmsg, "Reset count", val); - if (rc) +unlock: + mutex_unlock(&h->lock); + if (rc || !h->resets_reliable) return rc; - return 0; + fw_resets = bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG); + rc = devlink_fmsg_u32_pair_put(fmsg, "Resets", fw_resets); + if (rc) + return rc; + rc = devlink_fmsg_u32_pair_put(fmsg, "Arrests", h->arrests); + if (rc) + return rc; + rc = devlink_fmsg_u32_pair_put(fmsg, "Survivals", h->survivals); + if (rc) + return rc; + rc = devlink_fmsg_u32_pair_put(fmsg, "Discoveries", h->discoveries); + if (rc) + return rc; + rc = devlink_fmsg_u32_pair_put(fmsg, "Fatalities", h->fatalities); + if (rc) + return rc; + return devlink_fmsg_u32_pair_put(fmsg, "Diagnoses", h->diagnoses); } -static const struct devlink_health_reporter_ops bnxt_dl_fw_reporter_ops = { - .name = "fw", - .diagnose = bnxt_fw_reporter_diagnose, -}; - -static int bnxt_fw_reset_recover(struct devlink_health_reporter *reporter, - void *priv_ctx, - struct netlink_ext_ack *extack) +static int bnxt_fw_dump(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) { struct bnxt *bp = devlink_health_reporter_priv(reporter); + u32 dump_len; + void *data; + int rc; - if (!priv_ctx) + /* TODO: no firmware dump support in devlink_health_report() context */ + if (priv_ctx) return -EOPNOTSUPP; - bnxt_fw_reset(bp); - return -EINPROGRESS; -} + dump_len = bnxt_get_coredump_length(bp, BNXT_DUMP_LIVE); + if (!dump_len) + return -EIO; -static const -struct devlink_health_reporter_ops bnxt_dl_fw_reset_reporter_ops = { - .name = "fw_reset", - .recover = bnxt_fw_reset_recover, -}; + data = vmalloc(dump_len); + if (!data) + return -ENOMEM; -static int bnxt_fw_fatal_recover(struct devlink_health_reporter *reporter, - void *priv_ctx, - struct netlink_ext_ack *extack) + rc = bnxt_get_coredump(bp, BNXT_DUMP_LIVE, data, &dump_len); + if (!rc) { + rc = devlink_fmsg_pair_nest_start(fmsg, "core"); + if (rc) + goto exit; + rc = devlink_fmsg_binary_pair_put(fmsg, "data", data, dump_len); + if (rc) + goto exit; + rc = devlink_fmsg_u32_pair_put(fmsg, "size", dump_len); + if (rc) + goto exit; + rc = devlink_fmsg_pair_nest_end(fmsg); + } + +exit: + vfree(data); + return rc; +} + +static int bnxt_fw_recover(struct devlink_health_reporter *reporter, + void *priv_ctx, + struct netlink_ext_ack *extack) { struct bnxt *bp = devlink_health_reporter_priv(reporter); - struct bnxt_fw_reporter_ctx *fw_reporter_ctx = priv_ctx; - unsigned long event; - if (!priv_ctx) - return -EOPNOTSUPP; + if (bp->fw_health->severity == SEVERITY_FATAL) + return -ENODEV; - bp->fw_health->fatal = true; - event = fw_reporter_ctx->sp_event; - if (event == BNXT_FW_RESET_NOTIFY_SP_EVENT) - bnxt_fw_reset(bp); - else if (event == BNXT_FW_EXCEPTION_SP_EVENT) - bnxt_fw_exception(bp); + set_bit(BNXT_STATE_RECOVER, &bp->state); + __bnxt_fw_recover(bp); return -EINPROGRESS; } -static const -struct devlink_health_reporter_ops bnxt_dl_fw_fatal_reporter_ops = { - .name = "fw_fatal", - .recover = bnxt_fw_fatal_recover, +static const struct devlink_health_reporter_ops bnxt_dl_fw_reporter_ops = { + .name = "fw", + .diagnose = bnxt_fw_diagnose, + .dump = bnxt_fw_dump, + .recover = bnxt_fw_recover, }; void bnxt_dl_fw_reporters_create(struct bnxt *bp) { struct bnxt_fw_health *health = bp->fw_health; - if (!health) + if (!health || health->fw_reporter) return; - if (!(bp->fw_cap & BNXT_FW_CAP_HOT_RESET) || health->fw_reset_reporter) - goto err_recovery; - - health->fw_reset_reporter = - devlink_health_reporter_create(bp->dl, - &bnxt_dl_fw_reset_reporter_ops, + health->fw_reporter = + devlink_health_reporter_create(bp->dl, &bnxt_dl_fw_reporter_ops, 0, bp); - if (IS_ERR(health->fw_reset_reporter)) { - netdev_warn(bp->dev, "Failed to create FW fatal health reporter, rc = %ld\n", - PTR_ERR(health->fw_reset_reporter)); - health->fw_reset_reporter = NULL; - bp->fw_cap &= ~BNXT_FW_CAP_HOT_RESET; - } - -err_recovery: - if (!(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)) - return; - - if (!health->fw_reporter) { - health->fw_reporter = - devlink_health_reporter_create(bp->dl, - &bnxt_dl_fw_reporter_ops, - 0, bp); - if (IS_ERR(health->fw_reporter)) { - netdev_warn(bp->dev, "Failed to create FW health reporter, rc = %ld\n", - PTR_ERR(health->fw_reporter)); - health->fw_reporter = NULL; - bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY; - return; - } - } - - if (health->fw_fatal_reporter) - return; - - health->fw_fatal_reporter = - devlink_health_reporter_create(bp->dl, - &bnxt_dl_fw_fatal_reporter_ops, - 0, bp); - if (IS_ERR(health->fw_fatal_reporter)) { - netdev_warn(bp->dev, "Failed to create FW fatal health reporter, rc = %ld\n", - PTR_ERR(health->fw_fatal_reporter)); - health->fw_fatal_reporter = NULL; + if (IS_ERR(health->fw_reporter)) { + netdev_warn(bp->dev, "Failed to create FW health reporter, rc = %ld\n", + PTR_ERR(health->fw_reporter)); + health->fw_reporter = NULL; bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY; } } @@ -191,12 +265,6 @@ void bnxt_dl_fw_reporters_destroy(struct bnxt *bp, bool all) if (!health) return; - if ((all || !(bp->fw_cap & BNXT_FW_CAP_HOT_RESET)) && - health->fw_reset_reporter) { - devlink_health_reporter_destroy(health->fw_reset_reporter); - health->fw_reset_reporter = NULL; - } - if ((bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) && !all) return; @@ -204,82 +272,319 @@ void bnxt_dl_fw_reporters_destroy(struct bnxt *bp, bool all) devlink_health_reporter_destroy(health->fw_reporter); health->fw_reporter = NULL; } - - if (health->fw_fatal_reporter) { - devlink_health_reporter_destroy(health->fw_fatal_reporter); - health->fw_fatal_reporter = NULL; - } } -void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event) +void bnxt_devlink_health_fw_report(struct bnxt *bp) { struct bnxt_fw_health *fw_health = bp->fw_health; - struct bnxt_fw_reporter_ctx fw_reporter_ctx; - - fw_reporter_ctx.sp_event = event; - switch (event) { - case BNXT_FW_RESET_NOTIFY_SP_EVENT: - if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) { - if (!fw_health->fw_fatal_reporter) - return; - - devlink_health_report(fw_health->fw_fatal_reporter, - "FW fatal async event received", - &fw_reporter_ctx); - return; - } - if (!fw_health->fw_reset_reporter) - return; + int rc; - devlink_health_report(fw_health->fw_reset_reporter, - "FW non-fatal reset event received", - &fw_reporter_ctx); + if (!fw_health) return; - case BNXT_FW_EXCEPTION_SP_EVENT: - if (!fw_health->fw_fatal_reporter) - return; - - devlink_health_report(fw_health->fw_fatal_reporter, - "FW fatal error reported", - &fw_reporter_ctx); + if (!fw_health->fw_reporter) { + __bnxt_fw_recover(bp); return; } + + mutex_lock(&fw_health->lock); + fw_health->severity = SEVERITY_RECOVERABLE; + fw_health->remedy = REMEDY_DEVLINK_RECOVER; + mutex_unlock(&fw_health->lock); + rc = devlink_health_report(fw_health->fw_reporter, "FW error reported", + fw_health); + if (rc == -ECANCELED) + __bnxt_fw_recover(bp); } -void bnxt_dl_health_status_update(struct bnxt *bp, bool healthy) +void bnxt_dl_health_fw_status_update(struct bnxt *bp, bool healthy) { - struct bnxt_fw_health *health = bp->fw_health; + struct bnxt_fw_health *fw_health = bp->fw_health; u8 state; - if (healthy) + mutex_lock(&fw_health->lock); + if (healthy) { + fw_health->severity = SEVERITY_NORMAL; state = DEVLINK_HEALTH_REPORTER_STATE_HEALTHY; - else + } else { + fw_health->severity = SEVERITY_FATAL; + fw_health->remedy = REMEDY_POWER_CYCLE_DEVICE; state = DEVLINK_HEALTH_REPORTER_STATE_ERROR; - - if (health->fatal) - devlink_health_reporter_state_update(health->fw_fatal_reporter, - state); - else - devlink_health_reporter_state_update(health->fw_reset_reporter, - state); - - health->fatal = false; + } + mutex_unlock(&fw_health->lock); + devlink_health_reporter_state_update(fw_health->fw_reporter, state); } -void bnxt_dl_health_recovery_done(struct bnxt *bp) +void bnxt_dl_health_fw_recovery_done(struct bnxt *bp) { - struct bnxt_fw_health *hlth = bp->fw_health; + struct bnxt_dl *dl = devlink_priv(bp->dl); - if (hlth->fatal) - devlink_health_reporter_recovery_done(hlth->fw_fatal_reporter); - else - devlink_health_reporter_recovery_done(hlth->fw_reset_reporter); + devlink_health_reporter_recovery_done(bp->fw_health->fw_reporter); + bnxt_hwrm_remote_dev_reset_set(bp, dl->remote_reset); } static int bnxt_dl_info_get(struct devlink *dl, struct devlink_info_req *req, struct netlink_ext_ack *extack); +static void +bnxt_dl_livepatch_report_err(struct bnxt *bp, struct netlink_ext_ack *extack, + struct hwrm_fw_livepatch_output *resp) +{ + int err = ((struct hwrm_err_output *)resp)->cmd_err; + + switch (err) { + case FW_LIVEPATCH_CMD_ERR_CODE_INVALID_OPCODE: + netdev_err(bp->dev, "Illegal live patch opcode"); + NL_SET_ERR_MSG_MOD(extack, "Invalid opcode"); + break; + case FW_LIVEPATCH_CMD_ERR_CODE_NOT_SUPPORTED: + NL_SET_ERR_MSG_MOD(extack, "Live patch operation not supported"); + break; + case FW_LIVEPATCH_CMD_ERR_CODE_NOT_INSTALLED: + NL_SET_ERR_MSG_MOD(extack, "Live patch not found"); + break; + case FW_LIVEPATCH_CMD_ERR_CODE_NOT_PATCHED: + NL_SET_ERR_MSG_MOD(extack, + "Live patch deactivation failed. Firmware not patched."); + break; + case FW_LIVEPATCH_CMD_ERR_CODE_AUTH_FAIL: + NL_SET_ERR_MSG_MOD(extack, "Live patch not authenticated"); + break; + case FW_LIVEPATCH_CMD_ERR_CODE_INVALID_HEADER: + NL_SET_ERR_MSG_MOD(extack, "Incompatible live patch"); + break; + case FW_LIVEPATCH_CMD_ERR_CODE_INVALID_SIZE: + NL_SET_ERR_MSG_MOD(extack, "Live patch has invalid size"); + break; + case FW_LIVEPATCH_CMD_ERR_CODE_ALREADY_PATCHED: + NL_SET_ERR_MSG_MOD(extack, "Live patch already applied"); + break; + default: + netdev_err(bp->dev, "Unexpected live patch error: %hhd\n", err); + NL_SET_ERR_MSG_MOD(extack, "Failed to activate live patch"); + break; + } +} + +static int +bnxt_dl_livepatch_activate(struct bnxt *bp, struct netlink_ext_ack *extack) +{ + struct hwrm_fw_livepatch_query_output *query_resp; + struct hwrm_fw_livepatch_query_input *query_req; + struct hwrm_fw_livepatch_output *patch_resp; + struct hwrm_fw_livepatch_input *patch_req; + u32 installed = 0; + u16 flags; + u8 target; + int rc; + + if (~bp->fw_cap & BNXT_FW_CAP_LIVEPATCH) { + NL_SET_ERR_MSG_MOD(extack, "Device does not support live patch"); + return -EOPNOTSUPP; + } + + rc = hwrm_req_init(bp, query_req, HWRM_FW_LIVEPATCH_QUERY); + if (rc) + return rc; + query_resp = hwrm_req_hold(bp, query_req); + + rc = hwrm_req_init(bp, patch_req, HWRM_FW_LIVEPATCH); + if (rc) { + hwrm_req_drop(bp, query_req); + return rc; + } + patch_req->opcode = FW_LIVEPATCH_REQ_OPCODE_ACTIVATE; + patch_req->loadtype = FW_LIVEPATCH_REQ_LOADTYPE_NVM_INSTALL; + patch_resp = hwrm_req_hold(bp, patch_req); + + for (target = 1; target <= FW_LIVEPATCH_REQ_FW_TARGET_LAST; target++) { + query_req->fw_target = target; + rc = hwrm_req_send(bp, query_req); + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "Failed to query packages"); + break; + } + + flags = le16_to_cpu(query_resp->status_flags); + if (~flags & FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_INSTALL) + continue; + if ((flags & FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_ACTIVE) && + !strncmp(query_resp->active_ver, query_resp->install_ver, + sizeof(query_resp->active_ver))) + continue; + + patch_req->fw_target = target; + rc = hwrm_req_send(bp, patch_req); + if (rc) { + bnxt_dl_livepatch_report_err(bp, extack, patch_resp); + break; + } + installed++; + } + + if (!rc && !installed) { + NL_SET_ERR_MSG_MOD(extack, "No live patches found"); + rc = -ENOENT; + } + hwrm_req_drop(bp, query_req); + hwrm_req_drop(bp, patch_req); + return rc; +} + +static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + struct netlink_ext_ack *extack) +{ + struct bnxt *bp = bnxt_get_bp_from_dl(dl); + int rc = 0; + + switch (action) { + case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: { + if (BNXT_PF(bp) && bp->pf.active_vfs) { + NL_SET_ERR_MSG_MOD(extack, + "reload is unsupported when VFs are allocated\n"); + return -EOPNOTSUPP; + } + rtnl_lock(); + if (bp->dev->reg_state == NETREG_UNREGISTERED) { + rtnl_unlock(); + return -ENODEV; + } + bnxt_ulp_stop(bp); + if (netif_running(bp->dev)) { + rc = bnxt_close_nic(bp, true, true); + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "Failed to close"); + dev_close(bp->dev); + rtnl_unlock(); + break; + } + } + bnxt_vf_reps_free(bp); + rc = bnxt_hwrm_func_drv_unrgtr(bp); + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "Failed to deregister"); + if (netif_running(bp->dev)) + dev_close(bp->dev); + rtnl_unlock(); + break; + } + bnxt_cancel_reservations(bp, false); + bnxt_free_ctx_mem(bp); + kfree(bp->ctx); + bp->ctx = NULL; + break; + } + case DEVLINK_RELOAD_ACTION_FW_ACTIVATE: { + if (limit == DEVLINK_RELOAD_LIMIT_NO_RESET) + return bnxt_dl_livepatch_activate(bp, extack); + if (~bp->fw_cap & BNXT_FW_CAP_HOT_RESET) { + NL_SET_ERR_MSG_MOD(extack, "Device not capable, requires reboot"); + return -EOPNOTSUPP; + } + if (!bnxt_hwrm_reset_permitted(bp)) { + NL_SET_ERR_MSG_MOD(extack, + "Reset denied by firmware, it may be inhibited by remote driver"); + return -EPERM; + } + rtnl_lock(); + if (bp->dev->reg_state == NETREG_UNREGISTERED) { + rtnl_unlock(); + return -ENODEV; + } + if (netif_running(bp->dev)) + set_bit(BNXT_STATE_FW_ACTIVATE, &bp->state); + rc = bnxt_hwrm_firmware_reset(bp->dev, + FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP, + FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP, + FW_RESET_REQ_FLAGS_RESET_GRACEFUL | + FW_RESET_REQ_FLAGS_FW_ACTIVATION); + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "Failed to activate firmware"); + clear_bit(BNXT_STATE_FW_ACTIVATE, &bp->state); + rtnl_unlock(); + } + break; + } + default: + rc = -EOPNOTSUPP; + } + + return rc; +} + +static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action action, + enum devlink_reload_limit limit, u32 *actions_performed, + struct netlink_ext_ack *extack) +{ + struct bnxt *bp = bnxt_get_bp_from_dl(dl); + int rc = 0; + + *actions_performed = 0; + switch (action) { + case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: { + bnxt_fw_init_one(bp); + bnxt_vf_reps_alloc(bp); + if (netif_running(bp->dev)) + rc = bnxt_open_nic(bp, true, true); + bnxt_ulp_start(bp, rc); + if (!rc) { + bnxt_reenable_sriov(bp); + bnxt_ptp_reapply_pps(bp); + } + break; + } + case DEVLINK_RELOAD_ACTION_FW_ACTIVATE: { + unsigned long start = jiffies; + unsigned long timeout = start + BNXT_DFLT_FW_RST_MAX_DSECS * HZ / 10; + + if (limit == DEVLINK_RELOAD_LIMIT_NO_RESET) + break; + if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) + timeout = start + bp->fw_health->normal_func_wait_dsecs * HZ / 10; + if (!netif_running(bp->dev)) + NL_SET_ERR_MSG_MOD(extack, + "Device is closed, not waiting for reset notice that will never come"); + rtnl_unlock(); + while (test_bit(BNXT_STATE_FW_ACTIVATE, &bp->state)) { + if (time_after(jiffies, timeout)) { + NL_SET_ERR_MSG_MOD(extack, "Activation incomplete"); + rc = -ETIMEDOUT; + break; + } + if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) { + NL_SET_ERR_MSG_MOD(extack, "Activation aborted"); + rc = -ENODEV; + break; + } + msleep(50); + } + rtnl_lock(); + if (!rc) + *actions_performed |= BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT); + clear_bit(BNXT_STATE_FW_ACTIVATE, &bp->state); + break; + } + default: + return -EOPNOTSUPP; + } + + if (!rc) { + bnxt_print_device_info(bp); + if (netif_running(bp->dev)) { + mutex_lock(&bp->link_lock); + bnxt_report_link(bp); + mutex_unlock(&bp->link_lock); + } + *actions_performed |= BIT(action); + } else if (netif_running(bp->dev)) { + dev_close(bp->dev); + } + rtnl_unlock(); + return rc; +} + static const struct devlink_ops bnxt_dl_ops = { #ifdef CONFIG_BNXT_SRIOV .eswitch_mode_set = bnxt_dl_eswitch_mode_set, @@ -287,6 +592,11 @@ static const struct devlink_ops bnxt_dl_ops = { #endif /* CONFIG_BNXT_SRIOV */ .info_get = bnxt_dl_info_get, .flash_update = bnxt_dl_flash_update, + .reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) | + BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE), + .reload_limits = BIT(DEVLINK_RELOAD_LIMIT_NO_RESET), + .reload_down = bnxt_dl_reload_down, + .reload_up = bnxt_dl_reload_up, }; static const struct devlink_ops bnxt_vf_dl_ops; @@ -430,6 +740,57 @@ static int bnxt_dl_info_put(struct bnxt *bp, struct devlink_info_req *req, return 0; } +#define BNXT_FW_SRT_PATCH "fw.srt.patch" +#define BNXT_FW_CRT_PATCH "fw.crt.patch" + +static int bnxt_dl_livepatch_info_put(struct bnxt *bp, + struct devlink_info_req *req, + const char *key) +{ + struct hwrm_fw_livepatch_query_input *query; + struct hwrm_fw_livepatch_query_output *resp; + u16 flags; + int rc; + + if (~bp->fw_cap & BNXT_FW_CAP_LIVEPATCH) + return 0; + + rc = hwrm_req_init(bp, query, HWRM_FW_LIVEPATCH_QUERY); + if (rc) + return rc; + + if (!strcmp(key, BNXT_FW_SRT_PATCH)) + query->fw_target = FW_LIVEPATCH_QUERY_REQ_FW_TARGET_SECURE_FW; + else if (!strcmp(key, BNXT_FW_CRT_PATCH)) + query->fw_target = FW_LIVEPATCH_QUERY_REQ_FW_TARGET_COMMON_FW; + else + goto exit; + + resp = hwrm_req_hold(bp, query); + rc = hwrm_req_send(bp, query); + if (rc) + goto exit; + + flags = le16_to_cpu(resp->status_flags); + if (flags & FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_ACTIVE) { + resp->active_ver[sizeof(resp->active_ver) - 1] = '\0'; + rc = devlink_info_version_running_put(req, key, resp->active_ver); + if (rc) + goto exit; + } + + if (flags & FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_INSTALL) { + resp->install_ver[sizeof(resp->install_ver) - 1] = '\0'; + rc = devlink_info_version_stored_put(req, key, resp->install_ver); + if (rc) + goto exit; + } + +exit: + hwrm_req_drop(bp, query); + return rc; +} + #define HWRM_FW_VER_STR_LEN 16 static int bnxt_dl_info_get(struct devlink *dl, struct devlink_info_req *req, @@ -554,8 +915,13 @@ static int bnxt_dl_info_get(struct devlink *dl, struct devlink_info_req *req, rc = bnxt_hwrm_nvm_get_dev_info(bp, &nvm_dev_info); if (rc || - !(nvm_dev_info.flags & NVM_GET_DEV_INFO_RESP_FLAGS_FW_VER_VALID)) + !(nvm_dev_info.flags & NVM_GET_DEV_INFO_RESP_FLAGS_FW_VER_VALID)) { + if (!bnxt_get_pkginfo(bp->dev, buf, sizeof(buf))) + return bnxt_dl_info_put(bp, req, BNXT_VERSION_STORED, + DEVLINK_INFO_VERSION_GENERIC_FW, + buf); return 0; + } buf[0] = 0; strncat(buf, nvm_dev_info.pkg_name, HWRM_FW_VER_STR_LEN); @@ -583,8 +949,16 @@ static int bnxt_dl_info_get(struct devlink *dl, struct devlink_info_req *req, snprintf(roce_ver, FW_VER_STR_LEN, "%d.%d.%d.%d", nvm_dev_info.roce_fw_major, nvm_dev_info.roce_fw_minor, nvm_dev_info.roce_fw_build, nvm_dev_info.roce_fw_patch); - return bnxt_dl_info_put(bp, req, BNXT_VERSION_STORED, - DEVLINK_INFO_VERSION_GENERIC_FW_ROCE, roce_ver); + rc = bnxt_dl_info_put(bp, req, BNXT_VERSION_STORED, + DEVLINK_INFO_VERSION_GENERIC_FW_ROCE, roce_ver); + if (rc) + return rc; + + rc = bnxt_dl_livepatch_info_put(bp, req, BNXT_FW_SRT_PATCH); + if (rc) + return rc; + return bnxt_dl_livepatch_info_put(bp, req, BNXT_FW_CRT_PATCH); + } static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, @@ -712,6 +1086,32 @@ static int bnxt_dl_msix_validate(struct devlink *dl, u32 id, return 0; } +static int bnxt_remote_dev_reset_get(struct devlink *dl, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct bnxt *bp = bnxt_get_bp_from_dl(dl); + + if (~bp->fw_cap & BNXT_FW_CAP_HOT_RESET_IF) + return -EOPNOTSUPP; + + ctx->val.vbool = bnxt_dl_get_remote_reset(dl); + return 0; +} + +static int bnxt_remote_dev_reset_set(struct devlink *dl, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct bnxt *bp = bnxt_get_bp_from_dl(dl); + int rc; + + rc = bnxt_hwrm_remote_dev_reset_set(bp, ctx->val.vbool); + if (rc) + return rc; + + bnxt_dl_set_remote_reset(dl, ctx->val.vbool); + return rc; +} + static const struct devlink_param bnxt_dl_params[] = { DEVLINK_PARAM_GENERIC(ENABLE_SRIOV, BIT(DEVLINK_PARAM_CMODE_PERMANENT), @@ -734,17 +1134,25 @@ static const struct devlink_param bnxt_dl_params[] = { BIT(DEVLINK_PARAM_CMODE_PERMANENT), bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set, NULL), + /* keep REMOTE_DEV_RESET last, it is excluded based on caps */ + DEVLINK_PARAM_GENERIC(ENABLE_REMOTE_DEV_RESET, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + bnxt_remote_dev_reset_get, + bnxt_remote_dev_reset_set, NULL), }; static int bnxt_dl_params_register(struct bnxt *bp) { + int num_params = ARRAY_SIZE(bnxt_dl_params); int rc; if (bp->hwrm_spec_code < 0x10600) return 0; - rc = devlink_params_register(bp->dl, bnxt_dl_params, - ARRAY_SIZE(bnxt_dl_params)); + if (~bp->fw_cap & BNXT_FW_CAP_HOT_RESET_IF) + num_params--; + + rc = devlink_params_register(bp->dl, bnxt_dl_params, num_params); if (rc) netdev_warn(bp->dev, "devlink_params_register failed. rc=%d\n", rc); @@ -753,11 +1161,15 @@ static int bnxt_dl_params_register(struct bnxt *bp) static void bnxt_dl_params_unregister(struct bnxt *bp) { + int num_params = ARRAY_SIZE(bnxt_dl_params); + if (bp->hwrm_spec_code < 0x10600) return; - devlink_params_unregister(bp->dl, bnxt_dl_params, - ARRAY_SIZE(bnxt_dl_params)); + if (~bp->fw_cap & BNXT_FW_CAP_HOT_RESET_IF) + num_params--; + + devlink_params_unregister(bp->dl, bnxt_dl_params, num_params); } int bnxt_dl_register(struct bnxt *bp) @@ -782,6 +1194,7 @@ int bnxt_dl_register(struct bnxt *bp) bp->dl = dl; bp_dl = devlink_priv(dl); bp_dl->bp = bp; + bnxt_dl_set_remote_reset(dl, true); /* Add switchdev eswitch mode setting, if SRIOV supported */ if (pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV) && diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h index 406dc655a5fc..a715458abc30 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h @@ -13,6 +13,7 @@ /* Struct to hold housekeeping info needed by devlink interface */ struct bnxt_dl { struct bnxt *bp; /* back ptr to the controlling dev */ + bool remote_reset; }; static inline struct bnxt *bnxt_get_bp_from_dl(struct devlink *dl) @@ -20,6 +21,23 @@ static inline struct bnxt *bnxt_get_bp_from_dl(struct devlink *dl) return ((struct bnxt_dl *)devlink_priv(dl))->bp; } +static inline void bnxt_dl_remote_reload(struct bnxt *bp) +{ + devlink_remote_reload_actions_performed(bp->dl, 0, + BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) | + BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE)); +} + +static inline bool bnxt_dl_get_remote_reset(struct devlink *dl) +{ + return ((struct bnxt_dl *)devlink_priv(dl))->remote_reset; +} + +static inline void bnxt_dl_set_remote_reset(struct devlink *dl, bool value) +{ + ((struct bnxt_dl *)devlink_priv(dl))->remote_reset = value; +} + #define NVM_OFF_MSIX_VEC_PER_PF_MAX 108 #define NVM_OFF_MSIX_VEC_PER_PF_MIN 114 #define NVM_OFF_IGNORE_ARI 164 @@ -53,9 +71,9 @@ enum bnxt_dl_version_type { BNXT_VERSION_STORED, }; -void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event); -void bnxt_dl_health_status_update(struct bnxt *bp, bool healthy); -void bnxt_dl_health_recovery_done(struct bnxt *bp); +void bnxt_devlink_health_fw_report(struct bnxt *bp); +void bnxt_dl_health_fw_status_update(struct bnxt *bp, bool healthy); +void bnxt_dl_health_fw_recovery_done(struct bnxt *bp); void bnxt_dl_fw_reporters_create(struct bnxt *bp); void bnxt_dl_fw_reporters_destroy(struct bnxt *bp, bool all); int bnxt_dl_register(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index fbb56b1f70fd..8188d55722e4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -427,6 +427,8 @@ static const struct { BNXT_RX_STATS_EXT_ENTRY(rx_pcs_symbol_err), BNXT_RX_STATS_EXT_ENTRY(rx_corrected_bits), BNXT_RX_STATS_EXT_DISCARD_COS_ENTRIES, + BNXT_RX_STATS_EXT_ENTRY(rx_fec_corrected_blocks), + BNXT_RX_STATS_EXT_ENTRY(rx_fec_uncorrectable_blocks), }; static const struct { @@ -2180,13 +2182,18 @@ static int bnxt_flash_nvram(struct net_device *dev, u16 dir_type, return rc; } -static int bnxt_hwrm_firmware_reset(struct net_device *dev, u8 proc_type, - u8 self_reset, u8 flags) +int bnxt_hwrm_firmware_reset(struct net_device *dev, u8 proc_type, + u8 self_reset, u8 flags) { struct bnxt *bp = netdev_priv(dev); struct hwrm_fw_reset_input *req; int rc; + if (!bnxt_hwrm_reset_permitted(bp)) { + netdev_warn(bp->dev, "Reset denied by firmware, it may be inhibited by remote driver"); + return -EPERM; + } + rc = hwrm_req_init(bp, req, HWRM_FW_RESET); if (rc) return rc; @@ -2825,39 +2832,56 @@ static char *bnxt_parse_pkglog(int desired_field, u8 *data, size_t datalen) return retval; } -static void bnxt_get_pkgver(struct net_device *dev) +int bnxt_get_pkginfo(struct net_device *dev, char *ver, int size) { struct bnxt *bp = netdev_priv(dev); u16 index = 0; char *pkgver; u32 pkglen; u8 *pkgbuf; - int len; + int rc; - if (bnxt_find_nvram_item(dev, BNX_DIR_TYPE_PKG_LOG, - BNX_DIR_ORDINAL_FIRST, BNX_DIR_EXT_NONE, - &index, NULL, &pkglen) != 0) - return; + rc = bnxt_find_nvram_item(dev, BNX_DIR_TYPE_PKG_LOG, + BNX_DIR_ORDINAL_FIRST, BNX_DIR_EXT_NONE, + &index, NULL, &pkglen); + if (rc) + return rc; pkgbuf = kzalloc(pkglen, GFP_KERNEL); if (!pkgbuf) { dev_err(&bp->pdev->dev, "Unable to allocate memory for pkg version, length = %u\n", pkglen); - return; + return -ENOMEM; } - if (bnxt_get_nvram_item(dev, index, 0, pkglen, pkgbuf)) + rc = bnxt_get_nvram_item(dev, index, 0, pkglen, pkgbuf); + if (rc) goto err; pkgver = bnxt_parse_pkglog(BNX_PKG_LOG_FIELD_IDX_PKG_VERSION, pkgbuf, pkglen); - if (pkgver && *pkgver != 0 && isdigit(*pkgver)) { + if (pkgver && *pkgver != 0 && isdigit(*pkgver)) + strscpy(ver, pkgver, size); + else + rc = -ENOENT; + +err: + kfree(pkgbuf); + + return rc; +} + +static void bnxt_get_pkgver(struct net_device *dev) +{ + struct bnxt *bp = netdev_priv(dev); + char buf[FW_VER_STR_LEN]; + int len; + + if (!bnxt_get_pkginfo(dev, buf, sizeof(buf))) { len = strlen(bp->fw_ver_str); snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len - 1, - "/pkg %s", pkgver); + "/pkg %s", buf); } -err: - kfree(pkgbuf); } static int bnxt_get_eeprom(struct net_device *dev, @@ -3609,337 +3633,6 @@ static int bnxt_reset(struct net_device *dev, u32 *flags) return 0; } -static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg, - struct bnxt_hwrm_dbg_dma_info *info) -{ - struct hwrm_dbg_cmn_input *cmn_req = msg; - __le16 *seq_ptr = msg + info->seq_off; - struct hwrm_dbg_cmn_output *cmn_resp; - u16 seq = 0, len, segs_off; - dma_addr_t dma_handle; - void *dma_buf, *resp; - int rc, off = 0; - - dma_buf = hwrm_req_dma_slice(bp, msg, info->dma_len, &dma_handle); - if (!dma_buf) { - hwrm_req_drop(bp, msg); - return -ENOMEM; - } - - hwrm_req_timeout(bp, msg, HWRM_COREDUMP_TIMEOUT); - cmn_resp = hwrm_req_hold(bp, msg); - resp = cmn_resp; - - segs_off = offsetof(struct hwrm_dbg_coredump_list_output, - total_segments); - cmn_req->host_dest_addr = cpu_to_le64(dma_handle); - cmn_req->host_buf_len = cpu_to_le32(info->dma_len); - while (1) { - *seq_ptr = cpu_to_le16(seq); - rc = hwrm_req_send(bp, msg); - if (rc) - break; - - len = le16_to_cpu(*((__le16 *)(resp + info->data_len_off))); - if (!seq && - cmn_req->req_type == cpu_to_le16(HWRM_DBG_COREDUMP_LIST)) { - info->segs = le16_to_cpu(*((__le16 *)(resp + - segs_off))); - if (!info->segs) { - rc = -EIO; - break; - } - - info->dest_buf_size = info->segs * - sizeof(struct coredump_segment_record); - info->dest_buf = kmalloc(info->dest_buf_size, - GFP_KERNEL); - if (!info->dest_buf) { - rc = -ENOMEM; - break; - } - } - - if (info->dest_buf) { - if ((info->seg_start + off + len) <= - BNXT_COREDUMP_BUF_LEN(info->buf_len)) { - memcpy(info->dest_buf + off, dma_buf, len); - } else { - rc = -ENOBUFS; - break; - } - } - - if (cmn_req->req_type == - cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE)) - info->dest_buf_size += len; - - if (!(cmn_resp->flags & HWRM_DBG_CMN_FLAGS_MORE)) - break; - - seq++; - off += len; - } - hwrm_req_drop(bp, msg); - return rc; -} - -static int bnxt_hwrm_dbg_coredump_list(struct bnxt *bp, - struct bnxt_coredump *coredump) -{ - struct bnxt_hwrm_dbg_dma_info info = {NULL}; - struct hwrm_dbg_coredump_list_input *req; - int rc; - - rc = hwrm_req_init(bp, req, HWRM_DBG_COREDUMP_LIST); - if (rc) - return rc; - - info.dma_len = COREDUMP_LIST_BUF_LEN; - info.seq_off = offsetof(struct hwrm_dbg_coredump_list_input, seq_no); - info.data_len_off = offsetof(struct hwrm_dbg_coredump_list_output, - data_len); - - rc = bnxt_hwrm_dbg_dma_data(bp, req, &info); - if (!rc) { - coredump->data = info.dest_buf; - coredump->data_size = info.dest_buf_size; - coredump->total_segs = info.segs; - } - return rc; -} - -static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id, - u16 segment_id) -{ - struct hwrm_dbg_coredump_initiate_input *req; - int rc; - - rc = hwrm_req_init(bp, req, HWRM_DBG_COREDUMP_INITIATE); - if (rc) - return rc; - - hwrm_req_timeout(bp, req, HWRM_COREDUMP_TIMEOUT); - req->component_id = cpu_to_le16(component_id); - req->segment_id = cpu_to_le16(segment_id); - - return hwrm_req_send(bp, req); -} - -static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id, - u16 segment_id, u32 *seg_len, - void *buf, u32 buf_len, u32 offset) -{ - struct hwrm_dbg_coredump_retrieve_input *req; - struct bnxt_hwrm_dbg_dma_info info = {NULL}; - int rc; - - rc = hwrm_req_init(bp, req, HWRM_DBG_COREDUMP_RETRIEVE); - if (rc) - return rc; - - req->component_id = cpu_to_le16(component_id); - req->segment_id = cpu_to_le16(segment_id); - - info.dma_len = COREDUMP_RETRIEVE_BUF_LEN; - info.seq_off = offsetof(struct hwrm_dbg_coredump_retrieve_input, - seq_no); - info.data_len_off = offsetof(struct hwrm_dbg_coredump_retrieve_output, - data_len); - if (buf) { - info.dest_buf = buf + offset; - info.buf_len = buf_len; - info.seg_start = offset; - } - - rc = bnxt_hwrm_dbg_dma_data(bp, req, &info); - if (!rc) - *seg_len = info.dest_buf_size; - - return rc; -} - -static void -bnxt_fill_coredump_seg_hdr(struct bnxt *bp, - struct bnxt_coredump_segment_hdr *seg_hdr, - struct coredump_segment_record *seg_rec, u32 seg_len, - int status, u32 duration, u32 instance) -{ - memset(seg_hdr, 0, sizeof(*seg_hdr)); - memcpy(seg_hdr->signature, "sEgM", 4); - if (seg_rec) { - seg_hdr->component_id = (__force __le32)seg_rec->component_id; - seg_hdr->segment_id = (__force __le32)seg_rec->segment_id; - seg_hdr->low_version = seg_rec->version_low; - seg_hdr->high_version = seg_rec->version_hi; - } else { - /* For hwrm_ver_get response Component id = 2 - * and Segment id = 0 - */ - seg_hdr->component_id = cpu_to_le32(2); - seg_hdr->segment_id = 0; - } - seg_hdr->function_id = cpu_to_le16(bp->pdev->devfn); - seg_hdr->length = cpu_to_le32(seg_len); - seg_hdr->status = cpu_to_le32(status); - seg_hdr->duration = cpu_to_le32(duration); - seg_hdr->data_offset = cpu_to_le32(sizeof(*seg_hdr)); - seg_hdr->instance = cpu_to_le32(instance); -} - -static void -bnxt_fill_coredump_record(struct bnxt *bp, struct bnxt_coredump_record *record, - time64_t start, s16 start_utc, u16 total_segs, - int status) -{ - time64_t end = ktime_get_real_seconds(); - u32 os_ver_major = 0, os_ver_minor = 0; - struct tm tm; - - time64_to_tm(start, 0, &tm); - memset(record, 0, sizeof(*record)); - memcpy(record->signature, "cOrE", 4); - record->flags = 0; - record->low_version = 0; - record->high_version = 1; - record->asic_state = 0; - strlcpy(record->system_name, utsname()->nodename, - sizeof(record->system_name)); - record->year = cpu_to_le16(tm.tm_year + 1900); - record->month = cpu_to_le16(tm.tm_mon + 1); - record->day = cpu_to_le16(tm.tm_mday); - record->hour = cpu_to_le16(tm.tm_hour); - record->minute = cpu_to_le16(tm.tm_min); - record->second = cpu_to_le16(tm.tm_sec); - record->utc_bias = cpu_to_le16(start_utc); - strcpy(record->commandline, "ethtool -w"); - record->total_segments = cpu_to_le32(total_segs); - - sscanf(utsname()->release, "%u.%u", &os_ver_major, &os_ver_minor); - record->os_ver_major = cpu_to_le32(os_ver_major); - record->os_ver_minor = cpu_to_le32(os_ver_minor); - - strlcpy(record->os_name, utsname()->sysname, 32); - time64_to_tm(end, 0, &tm); - record->end_year = cpu_to_le16(tm.tm_year + 1900); - record->end_month = cpu_to_le16(tm.tm_mon + 1); - record->end_day = cpu_to_le16(tm.tm_mday); - record->end_hour = cpu_to_le16(tm.tm_hour); - record->end_minute = cpu_to_le16(tm.tm_min); - record->end_second = cpu_to_le16(tm.tm_sec); - record->end_utc_bias = cpu_to_le16(sys_tz.tz_minuteswest * 60); - record->asic_id1 = cpu_to_le32(bp->chip_num << 16 | - bp->ver_resp.chip_rev << 8 | - bp->ver_resp.chip_metal); - record->asic_id2 = 0; - record->coredump_status = cpu_to_le32(status); - record->ioctl_low_version = 0; - record->ioctl_high_version = 0; -} - -static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len) -{ - u32 ver_get_resp_len = sizeof(struct hwrm_ver_get_output); - u32 offset = 0, seg_hdr_len, seg_record_len, buf_len = 0; - struct coredump_segment_record *seg_record = NULL; - struct bnxt_coredump_segment_hdr seg_hdr; - struct bnxt_coredump coredump = {NULL}; - time64_t start_time; - u16 start_utc; - int rc = 0, i; - - if (buf) - buf_len = *dump_len; - - start_time = ktime_get_real_seconds(); - start_utc = sys_tz.tz_minuteswest * 60; - seg_hdr_len = sizeof(seg_hdr); - - /* First segment should be hwrm_ver_get response */ - *dump_len = seg_hdr_len + ver_get_resp_len; - if (buf) { - bnxt_fill_coredump_seg_hdr(bp, &seg_hdr, NULL, ver_get_resp_len, - 0, 0, 0); - memcpy(buf + offset, &seg_hdr, seg_hdr_len); - offset += seg_hdr_len; - memcpy(buf + offset, &bp->ver_resp, ver_get_resp_len); - offset += ver_get_resp_len; - } - - rc = bnxt_hwrm_dbg_coredump_list(bp, &coredump); - if (rc) { - netdev_err(bp->dev, "Failed to get coredump segment list\n"); - goto err; - } - - *dump_len += seg_hdr_len * coredump.total_segs; - - seg_record = (struct coredump_segment_record *)coredump.data; - seg_record_len = sizeof(*seg_record); - - for (i = 0; i < coredump.total_segs; i++) { - u16 comp_id = le16_to_cpu(seg_record->component_id); - u16 seg_id = le16_to_cpu(seg_record->segment_id); - u32 duration = 0, seg_len = 0; - unsigned long start, end; - - if (buf && ((offset + seg_hdr_len) > - BNXT_COREDUMP_BUF_LEN(buf_len))) { - rc = -ENOBUFS; - goto err; - } - - start = jiffies; - - rc = bnxt_hwrm_dbg_coredump_initiate(bp, comp_id, seg_id); - if (rc) { - netdev_err(bp->dev, - "Failed to initiate coredump for seg = %d\n", - seg_record->segment_id); - goto next_seg; - } - - /* Write segment data into the buffer */ - rc = bnxt_hwrm_dbg_coredump_retrieve(bp, comp_id, seg_id, - &seg_len, buf, buf_len, - offset + seg_hdr_len); - if (rc && rc == -ENOBUFS) - goto err; - else if (rc) - netdev_err(bp->dev, - "Failed to retrieve coredump for seg = %d\n", - seg_record->segment_id); - -next_seg: - end = jiffies; - duration = jiffies_to_msecs(end - start); - bnxt_fill_coredump_seg_hdr(bp, &seg_hdr, seg_record, seg_len, - rc, duration, 0); - - if (buf) { - /* Write segment header into the buffer */ - memcpy(buf + offset, &seg_hdr, seg_hdr_len); - offset += seg_hdr_len + seg_len; - } - - *dump_len += seg_len; - seg_record = - (struct coredump_segment_record *)((u8 *)seg_record + - seg_record_len); - } - -err: - if (buf) - bnxt_fill_coredump_record(bp, buf + offset, start_time, - start_utc, coredump.total_segs + 1, - rc); - kfree(coredump.data); - *dump_len += sizeof(struct bnxt_coredump_record); - if (rc == -ENOBUFS) - netdev_err(bp->dev, "Firmware returned large coredump buffer\n"); - return rc; -} - static int bnxt_set_dump(struct net_device *dev, struct ethtool_dump *dump) { struct bnxt *bp = netdev_priv(dev); @@ -3971,10 +3664,7 @@ static int bnxt_get_dump_flag(struct net_device *dev, struct ethtool_dump *dump) bp->ver_resp.hwrm_fw_rsvd_8b; dump->flag = bp->dump_flag; - if (bp->dump_flag == BNXT_DUMP_CRASH) - dump->len = BNXT_CRASH_DUMP_LEN; - else - bnxt_get_coredump(bp, NULL, &dump->len); + dump->len = bnxt_get_coredump_length(bp, bp->dump_flag); return 0; } @@ -3989,15 +3679,7 @@ static int bnxt_get_dump_data(struct net_device *dev, struct ethtool_dump *dump, memset(buf, 0, dump->len); dump->flag = bp->dump_flag; - if (dump->flag == BNXT_DUMP_CRASH) { -#ifdef CONFIG_TEE_BNXT_FW - return tee_bnxt_copy_coredump(buf, 0, dump->len); -#endif - } else { - return bnxt_get_coredump(bp, buf, &dump->len); - } - - return 0; + return bnxt_get_coredump(bp, dump->flag, buf, &dump->len); } static int bnxt_get_ts_info(struct net_device *dev, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h index 0a57cb6a4a4b..6aa44840f13a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h @@ -22,49 +22,6 @@ struct bnxt_led_cfg { u8 rsvd; }; -#define COREDUMP_LIST_BUF_LEN 2048 -#define COREDUMP_RETRIEVE_BUF_LEN 4096 - -struct bnxt_coredump { - void *data; - int data_size; - u16 total_segs; -}; - -#define BNXT_COREDUMP_BUF_LEN(len) ((len) - sizeof(struct bnxt_coredump_record)) - -struct bnxt_hwrm_dbg_dma_info { - void *dest_buf; - int dest_buf_size; - u16 dma_len; - u16 seq_off; - u16 data_len_off; - u16 segs; - u32 seg_start; - u32 buf_len; -}; - -struct hwrm_dbg_cmn_input { - __le16 req_type; - __le16 cmpl_ring; - __le16 seq_id; - __le16 target_id; - __le64 resp_addr; - __le64 host_dest_addr; - __le32 host_buf_len; -}; - -struct hwrm_dbg_cmn_output { - __le16 error_code; - __le16 req_type; - __le16 seq_id; - __le16 resp_len; - u8 flags; - #define HWRM_DBG_CMN_FLAGS_MORE 1 -}; - -#define BNXT_CRASH_DUMP_LEN (8 << 20) - #define BNXT_LED_DFLT_ENA \ (PORT_LED_CFG_REQ_ENABLES_LED0_ID | \ PORT_LED_CFG_REQ_ENABLES_LED0_STATE | \ @@ -94,8 +51,11 @@ u32 bnxt_fw_to_ethtool_speed(u16); u16 bnxt_get_fw_auto_link_speeds(u32); int bnxt_hwrm_nvm_get_dev_info(struct bnxt *bp, struct hwrm_nvm_get_dev_info_output *nvm_dev_info); +int bnxt_hwrm_firmware_reset(struct net_device *dev, u8 proc_type, + u8 self_reset, u8 flags); int bnxt_flash_package_from_fw_obj(struct net_device *dev, const struct firmware *fw, u32 install_type); +int bnxt_get_pkginfo(struct net_device *dev, char *ver, int size); void bnxt_ethtool_init(struct bnxt *bp); void bnxt_ethtool_free(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index 94d07a9f7034..ea86c54247c7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -532,8 +532,8 @@ struct hwrm_err_output { #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 10 #define HWRM_VERSION_UPDATE 2 -#define HWRM_VERSION_RSVD 52 -#define HWRM_VERSION_STR "1.10.2.52" +#define HWRM_VERSION_RSVD 63 +#define HWRM_VERSION_STR "1.10.2.63" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -1587,6 +1587,8 @@ struct hwrm_func_qcaps_output { #define FUNC_QCAPS_RESP_FLAGS_EXT_DFLT_VLAN_TPID_PCP_SUPPORTED 0x200000UL #define FUNC_QCAPS_RESP_FLAGS_EXT_KTLS_SUPPORTED 0x400000UL #define FUNC_QCAPS_RESP_FLAGS_EXT_EP_RATE_CONTROL 0x800000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_MIN_BW_SUPPORTED 0x1000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_TX_COAL_CMPL_CAP 0x2000000UL u8 max_schqs; u8 mpc_chnls_cap; #define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TCE 0x1UL @@ -1956,6 +1958,18 @@ struct hwrm_func_cfg_output { u8 valid; }; +/* hwrm_func_cfg_cmd_err (size:64b/8B) */ +struct hwrm_func_cfg_cmd_err { + u8 code; + #define FUNC_CFG_CMD_ERR_CODE_UNKNOWN 0x0UL + #define FUNC_CFG_CMD_ERR_CODE_PARTITION_MIN_BW_RANGE 0x1UL + #define FUNC_CFG_CMD_ERR_CODE_PARTITION_MIN_MORE_THAN_MAX 0x2UL + #define FUNC_CFG_CMD_ERR_CODE_PARTITION_MIN_BW_UNSUPPORTED 0x3UL + #define FUNC_CFG_CMD_ERR_CODE_PARTITION_BW_PERCENT 0x4UL + #define FUNC_CFG_CMD_ERR_CODE_LAST FUNC_CFG_CMD_ERR_CODE_PARTITION_BW_PERCENT + u8 unused_0[7]; +}; + /* hwrm_func_qstats_input (size:192b/24B) */ struct hwrm_func_qstats_input { __le16 req_type; @@ -3601,7 +3615,15 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASESR4 0x1dUL #define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASELR4 0x1eUL #define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER4 0x1fUL - #define PORT_PHY_QCFG_RESP_PHY_TYPE_LAST PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER4 + #define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASECR 0x20UL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASESR 0x21UL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASELR 0x22UL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASEER 0x23UL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR2 0x24UL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR2 0x25UL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR2 0x26UL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER2 0x27UL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_LAST PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER2 u8 media_type; #define PORT_PHY_QCFG_RESP_MEDIA_TYPE_UNKNOWN 0x0UL #define PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP 0x1UL @@ -4040,7 +4062,7 @@ struct tx_port_stats_ext { __le64 pfc_pri7_tx_transitions; }; -/* rx_port_stats_ext (size:3648b/456B) */ +/* rx_port_stats_ext (size:3776b/472B) */ struct rx_port_stats_ext { __le64 link_down_events; __le64 continuous_pause_events; @@ -4099,6 +4121,8 @@ struct rx_port_stats_ext { __le64 rx_discard_packets_cos5; __le64 rx_discard_packets_cos6; __le64 rx_discard_packets_cos7; + __le64 rx_fec_corrected_blocks; + __le64 rx_fec_uncorrectable_blocks; }; /* hwrm_port_qstats_ext_input (size:320b/40B) */ @@ -4372,7 +4396,10 @@ struct hwrm_port_phy_qcaps_output { #define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_50G 0x1UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_100G 0x2UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_200G 0x4UL - u8 unused_0[3]; + __le16 flags2; + #define PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED 0x1UL + #define PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED 0x2UL + u8 unused_0[1]; u8 valid; }; @@ -6076,6 +6103,11 @@ struct hwrm_vnic_qcaps_output { #define VNIC_QCAPS_RESP_FLAGS_VIRTIO_NET_VNIC_ALLOC_CAP 0x800UL #define VNIC_QCAPS_RESP_FLAGS_METADATA_FORMAT_CAP 0x1000UL #define VNIC_QCAPS_RESP_FLAGS_RSS_STRICT_HASH_TYPE_CAP 0x2000UL + #define VNIC_QCAPS_RESP_FLAGS_RSS_HASH_TYPE_DELTA_CAP 0x4000UL + #define VNIC_QCAPS_RESP_FLAGS_RSS_HASH_FUNCTION_TOEPLITZ_CAP 0x8000UL + #define VNIC_QCAPS_RESP_FLAGS_RSS_HASH_FUNCTION_XOR_CAP 0x10000UL + #define VNIC_QCAPS_RESP_FLAGS_RSS_HASH_FUNCTION_CHKSM_CAP 0x20000UL + #define VNIC_QCAPS_RESP_FLAGS_RSS_IPV6_FLOW_LABEL_CAP 0x40000UL __le16 max_aggs_supported; u8 unused_1[5]; u8 valid; @@ -6206,7 +6238,15 @@ struct hwrm_vnic_rss_cfg_input { __le64 ring_grp_tbl_addr; __le64 hash_key_tbl_addr; __le16 rss_ctx_idx; - u8 unused_1[6]; + u8 flags; + #define VNIC_RSS_CFG_REQ_FLAGS_HASH_TYPE_INCLUDE 0x1UL + #define VNIC_RSS_CFG_REQ_FLAGS_HASH_TYPE_EXCLUDE 0x2UL + u8 rss_hash_function; + #define VNIC_RSS_CFG_REQ_RSS_HASH_FUNCTION_TOEPLITZ 0x0UL + #define VNIC_RSS_CFG_REQ_RSS_HASH_FUNCTION_XOR 0x1UL + #define VNIC_RSS_CFG_REQ_RSS_HASH_FUNCTION_CHECKSUM 0x2UL + #define VNIC_RSS_CFG_REQ_RSS_HASH_FUNCTION_LAST VNIC_RSS_CFG_REQ_RSS_HASH_FUNCTION_CHECKSUM + u8 unused_1[4]; }; /* hwrm_vnic_rss_cfg_output (size:128b/16B) */ @@ -6331,7 +6371,24 @@ struct hwrm_ring_alloc_input { #define RING_ALLOC_REQ_RING_TYPE_RX_AGG 0x4UL #define RING_ALLOC_REQ_RING_TYPE_NQ 0x5UL #define RING_ALLOC_REQ_RING_TYPE_LAST RING_ALLOC_REQ_RING_TYPE_NQ - u8 unused_0; + u8 cmpl_coal_cnt; + #define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_OFF 0x0UL + #define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_4 0x1UL + #define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_8 0x2UL + #define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_12 0x3UL + #define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_16 0x4UL + #define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_24 0x5UL + #define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_32 0x6UL + #define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_48 0x7UL + #define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_64 0x8UL + #define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_96 0x9UL + #define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_128 0xaUL + #define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_192 0xbUL + #define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_256 0xcUL + #define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_320 0xdUL + #define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_384 0xeUL + #define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_MAX 0xfUL + #define RING_ALLOC_REQ_CMPL_COAL_CNT_LAST RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_MAX __le16 flags; #define RING_ALLOC_REQ_FLAGS_RX_SOP_PAD 0x1UL __le64 page_tbl_addr; @@ -7099,6 +7156,7 @@ struct hwrm_cfa_ntuple_filter_alloc_input { #define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_FID 0x8UL #define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_ARP_REPLY 0x10UL #define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_RFS_RING_IDX 0x20UL + #define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_NO_L2_CONTEXT 0x40UL __le32 enables; #define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_L2_FILTER_ID 0x1UL #define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE 0x2UL @@ -7234,6 +7292,7 @@ struct hwrm_cfa_ntuple_filter_cfg_input { __le32 flags; #define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_DEST_FID 0x1UL #define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_DEST_RFS_RING_IDX 0x2UL + #define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_NO_L2_CONTEXT 0x4UL __le64 ntuple_filter_id; __le32 new_dst_id; __le32 new_mirror_vnic_id; @@ -7834,11 +7893,11 @@ struct hwrm_cfa_adv_flow_mgnt_qcaps_output { #define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_TRUFLOW_CAPABLE 0x8000UL #define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_L2_FILTER_TRAFFIC_TYPE_L2_ROCE_SUPPORTED 0x10000UL #define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_LAG_SUPPORTED 0x20000UL + #define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_NO_L2CTX_SUPPORTED 0x40000UL u8 unused_0[3]; u8 valid; }; -/* hwrm_tunnel_dst_port_query_input (size:192b/24B) */ struct hwrm_tunnel_dst_port_query_input { __le16 req_type; __le16 cmpl_ring; @@ -8414,6 +8473,86 @@ struct hwrm_fw_get_structured_data_cmd_err { u8 unused_0[7]; }; +/* hwrm_fw_livepatch_query_input (size:192b/24B) */ +struct hwrm_fw_livepatch_query_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + u8 fw_target; + #define FW_LIVEPATCH_QUERY_REQ_FW_TARGET_COMMON_FW 0x1UL + #define FW_LIVEPATCH_QUERY_REQ_FW_TARGET_SECURE_FW 0x2UL + #define FW_LIVEPATCH_QUERY_REQ_FW_TARGET_LAST FW_LIVEPATCH_QUERY_REQ_FW_TARGET_SECURE_FW + u8 unused_0[7]; +}; + +/* hwrm_fw_livepatch_query_output (size:640b/80B) */ +struct hwrm_fw_livepatch_query_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + char install_ver[32]; + char active_ver[32]; + __le16 status_flags; + #define FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_INSTALL 0x1UL + #define FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_ACTIVE 0x2UL + u8 unused_0[5]; + u8 valid; +}; + +/* hwrm_fw_livepatch_input (size:256b/32B) */ +struct hwrm_fw_livepatch_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + u8 opcode; + #define FW_LIVEPATCH_REQ_OPCODE_ACTIVATE 0x1UL + #define FW_LIVEPATCH_REQ_OPCODE_DEACTIVATE 0x2UL + #define FW_LIVEPATCH_REQ_OPCODE_LAST FW_LIVEPATCH_REQ_OPCODE_DEACTIVATE + u8 fw_target; + #define FW_LIVEPATCH_REQ_FW_TARGET_COMMON_FW 0x1UL + #define FW_LIVEPATCH_REQ_FW_TARGET_SECURE_FW 0x2UL + #define FW_LIVEPATCH_REQ_FW_TARGET_LAST FW_LIVEPATCH_REQ_FW_TARGET_SECURE_FW + u8 loadtype; + #define FW_LIVEPATCH_REQ_LOADTYPE_NVM_INSTALL 0x1UL + #define FW_LIVEPATCH_REQ_LOADTYPE_MEMORY_DIRECT 0x2UL + #define FW_LIVEPATCH_REQ_LOADTYPE_LAST FW_LIVEPATCH_REQ_LOADTYPE_MEMORY_DIRECT + u8 flags; + __le32 patch_len; + __le64 host_addr; +}; + +/* hwrm_fw_livepatch_output (size:128b/16B) */ +struct hwrm_fw_livepatch_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 unused_0[7]; + u8 valid; +}; + +/* hwrm_fw_livepatch_cmd_err (size:64b/8B) */ +struct hwrm_fw_livepatch_cmd_err { + u8 code; + #define FW_LIVEPATCH_CMD_ERR_CODE_UNKNOWN 0x0UL + #define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_OPCODE 0x1UL + #define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_TARGET 0x2UL + #define FW_LIVEPATCH_CMD_ERR_CODE_NOT_SUPPORTED 0x3UL + #define FW_LIVEPATCH_CMD_ERR_CODE_NOT_INSTALLED 0x4UL + #define FW_LIVEPATCH_CMD_ERR_CODE_NOT_PATCHED 0x5UL + #define FW_LIVEPATCH_CMD_ERR_CODE_AUTH_FAIL 0x6UL + #define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_HEADER 0x7UL + #define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_SIZE 0x8UL + #define FW_LIVEPATCH_CMD_ERR_CODE_ALREADY_PATCHED 0x9UL + #define FW_LIVEPATCH_CMD_ERR_CODE_LAST FW_LIVEPATCH_CMD_ERR_CODE_ALREADY_PATCHED + u8 unused_0[7]; +}; + /* hwrm_exec_fwd_resp_input (size:1024b/128B) */ struct hwrm_exec_fwd_resp_input { __le16 req_type; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index f0aa480799ca..8388be119f9a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -11,9 +11,7 @@ #include <linux/pci.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> -#include <linux/ptp_clock_kernel.h> #include <linux/net_tstamp.h> -#include <linux/timecounter.h> #include <linux/timekeeping.h> #include <linux/ptp_classify.h> #include "bnxt_hsi.h" diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h index fa5f05708e6d..7c528e1f8713 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h @@ -10,6 +10,9 @@ #ifndef BNXT_PTP_H #define BNXT_PTP_H +#include <linux/ptp_clock_kernel.h> +#include <linux/timecounter.h> + #define BNXT_PTP_GRC_WIN 6 #define BNXT_PTP_GRC_WIN_BASE 0x6000 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 1a1bebd453d3..67364ab63a1f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -137,7 +137,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = { .name = "uc", .cmd = HNAE3_DBG_CMD_MAC_UC, .dentry = HNS3_DBG_DENTRY_MAC, - .buf_len = HNS3_DBG_READ_LEN, + .buf_len = HNS3_DBG_READ_LEN_128KB, .init = hns3_dbg_common_file_init, }, { @@ -256,7 +256,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = { .name = "tqp", .cmd = HNAE3_DBG_CMD_REG_TQP, .dentry = HNS3_DBG_DENTRY_REG, - .buf_len = HNS3_DBG_READ_LEN, + .buf_len = HNS3_DBG_READ_LEN_128KB, .init = hns3_dbg_common_file_init, }, { @@ -298,7 +298,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = { .name = "fd_tcam", .cmd = HNAE3_DBG_CMD_FD_TCAM, .dentry = HNS3_DBG_DENTRY_FD, - .buf_len = HNS3_DBG_READ_LEN, + .buf_len = HNS3_DBG_READ_LEN_1MB, .init = hns3_dbg_common_file_init, }, { @@ -584,7 +584,7 @@ static const struct hns3_dbg_item rx_queue_info_items[] = { { "TAIL", 2 }, { "HEAD", 2 }, { "FBDNUM", 2 }, - { "PKTNUM", 2 }, + { "PKTNUM", 5 }, { "COPYBREAK", 2 }, { "RING_EN", 2 }, { "RX_RING_EN", 2 }, @@ -687,7 +687,7 @@ static const struct hns3_dbg_item tx_queue_info_items[] = { { "HEAD", 2 }, { "FBDNUM", 2 }, { "OFFSET", 2 }, - { "PKTNUM", 2 }, + { "PKTNUM", 5 }, { "RING_EN", 2 }, { "TX_RING_EN", 2 }, { "BASE_ADDR", 10 }, @@ -912,13 +912,13 @@ static int hns3_dbg_rx_bd_info(struct hns3_dbg_data *d, char *buf, int len) } static const struct hns3_dbg_item tx_bd_info_items[] = { - { "BD_IDX", 5 }, - { "ADDRESS", 2 }, + { "BD_IDX", 2 }, + { "ADDRESS", 13 }, { "VLAN_TAG", 2 }, { "SIZE", 2 }, { "T_CS_VLAN_TSO", 2 }, { "OT_VLAN_TAG", 3 }, - { "TV", 2 }, + { "TV", 5 }, { "OLT_VLAN_LEN", 2 }, { "PAYLEN_OL4CS", 2 }, { "BD_FE_SC_VLD", 2 }, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index f0aa4fbd2200..4e0a8c2f7c05 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -391,7 +391,7 @@ static int hclge_dbg_dump_mac(struct hclge_dev *hdev, char *buf, int len) static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len, int *pos) { - struct hclge_dbg_bitmap_cmd *bitmap; + struct hclge_dbg_bitmap_cmd req; struct hclge_desc desc; u16 qset_id, qset_num; int ret; @@ -408,12 +408,12 @@ static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len, if (ret) return ret; - bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1]; + req.bitmap = (u8)le32_to_cpu(desc.data[1]); *pos += scnprintf(buf + *pos, len - *pos, "%04u %#x %#x %#x %#x\n", - qset_id, bitmap->bit0, bitmap->bit1, - bitmap->bit2, bitmap->bit3); + qset_id, req.bit0, req.bit1, req.bit2, + req.bit3); } return 0; @@ -422,7 +422,7 @@ static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len, static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len, int *pos) { - struct hclge_dbg_bitmap_cmd *bitmap; + struct hclge_dbg_bitmap_cmd req; struct hclge_desc desc; u8 pri_id, pri_num; int ret; @@ -439,12 +439,11 @@ static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len, if (ret) return ret; - bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1]; + req.bitmap = (u8)le32_to_cpu(desc.data[1]); *pos += scnprintf(buf + *pos, len - *pos, "%03u %#x %#x %#x\n", - pri_id, bitmap->bit0, bitmap->bit1, - bitmap->bit2); + pri_id, req.bit0, req.bit1, req.bit2); } return 0; @@ -453,7 +452,7 @@ static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len, static int hclge_dbg_dump_dcb_pg(struct hclge_dev *hdev, char *buf, int len, int *pos) { - struct hclge_dbg_bitmap_cmd *bitmap; + struct hclge_dbg_bitmap_cmd req; struct hclge_desc desc; u8 pg_id; int ret; @@ -466,12 +465,11 @@ static int hclge_dbg_dump_dcb_pg(struct hclge_dev *hdev, char *buf, int len, if (ret) return ret; - bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1]; + req.bitmap = (u8)le32_to_cpu(desc.data[1]); *pos += scnprintf(buf + *pos, len - *pos, "%03u %#x %#x %#x\n", - pg_id, bitmap->bit0, bitmap->bit1, - bitmap->bit2); + pg_id, req.bit0, req.bit1, req.bit2); } return 0; @@ -511,7 +509,7 @@ static int hclge_dbg_dump_dcb_queue(struct hclge_dev *hdev, char *buf, int len, static int hclge_dbg_dump_dcb_port(struct hclge_dev *hdev, char *buf, int len, int *pos) { - struct hclge_dbg_bitmap_cmd *bitmap; + struct hclge_dbg_bitmap_cmd req; struct hclge_desc desc; u8 port_id = 0; int ret; @@ -521,12 +519,12 @@ static int hclge_dbg_dump_dcb_port(struct hclge_dev *hdev, char *buf, int len, if (ret) return ret; - bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1]; + req.bitmap = (u8)le32_to_cpu(desc.data[1]); *pos += scnprintf(buf + *pos, len - *pos, "port_mask: %#x\n", - bitmap->bit0); + req.bit0); *pos += scnprintf(buf + *pos, len - *pos, "port_shaping_pass: %#x\n", - bitmap->bit1); + req.bit1); return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index f1db6699f81f..2e41aa2d1df8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2930,33 +2930,29 @@ static void hclge_mbx_task_schedule(struct hclge_dev *hdev) { if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) && !test_and_set_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state)) - mod_delayed_work_on(cpumask_first(&hdev->affinity_mask), - hclge_wq, &hdev->service_task, 0); + mod_delayed_work(hclge_wq, &hdev->service_task, 0); } static void hclge_reset_task_schedule(struct hclge_dev *hdev) { if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) && + test_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state) && !test_and_set_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state)) - mod_delayed_work_on(cpumask_first(&hdev->affinity_mask), - hclge_wq, &hdev->service_task, 0); + mod_delayed_work(hclge_wq, &hdev->service_task, 0); } static void hclge_errhand_task_schedule(struct hclge_dev *hdev) { if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) && !test_and_set_bit(HCLGE_STATE_ERR_SERVICE_SCHED, &hdev->state)) - mod_delayed_work_on(cpumask_first(&hdev->affinity_mask), - hclge_wq, &hdev->service_task, 0); + mod_delayed_work(hclge_wq, &hdev->service_task, 0); } void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time) { if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) && !test_bit(HCLGE_STATE_RST_FAIL, &hdev->state)) - mod_delayed_work_on(cpumask_first(&hdev->affinity_mask), - hclge_wq, &hdev->service_task, - delay_time); + mod_delayed_work(hclge_wq, &hdev->service_task, delay_time); } static int hclge_get_mac_link_status(struct hclge_dev *hdev, int *link_status) @@ -3650,33 +3646,14 @@ static void hclge_get_misc_vector(struct hclge_dev *hdev) hdev->num_msi_used += 1; } -static void hclge_irq_affinity_notify(struct irq_affinity_notify *notify, - const cpumask_t *mask) -{ - struct hclge_dev *hdev = container_of(notify, struct hclge_dev, - affinity_notify); - - cpumask_copy(&hdev->affinity_mask, mask); -} - -static void hclge_irq_affinity_release(struct kref *ref) -{ -} - static void hclge_misc_affinity_setup(struct hclge_dev *hdev) { irq_set_affinity_hint(hdev->misc_vector.vector_irq, &hdev->affinity_mask); - - hdev->affinity_notify.notify = hclge_irq_affinity_notify; - hdev->affinity_notify.release = hclge_irq_affinity_release; - irq_set_affinity_notifier(hdev->misc_vector.vector_irq, - &hdev->affinity_notify); } static void hclge_misc_affinity_teardown(struct hclge_dev *hdev) { - irq_set_affinity_notifier(hdev->misc_vector.vector_irq, NULL); irq_set_affinity_hint(hdev->misc_vector.vector_irq, NULL); } @@ -13233,7 +13210,7 @@ static int hclge_init(void) { pr_info("%s is initializing\n", HCLGE_NAME); - hclge_wq = alloc_workqueue("%s", 0, 0, HCLGE_NAME); + hclge_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, HCLGE_NAME); if (!hclge_wq) { pr_err("%s: failed to create workqueue\n", HCLGE_NAME); return -ENOMEM; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 4f8403af84be..9e1eede599ec 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -974,7 +974,6 @@ struct hclge_dev { /* affinity mask and notify for misc interrupt */ cpumask_t affinity_mask; - struct irq_affinity_notify affinity_notify; struct hclge_ptp *ptp; struct devlink *devlink; }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 3306050ad72c..645b2c0011e6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -2232,6 +2232,7 @@ static void hclgevf_get_misc_vector(struct hclgevf_dev *hdev) void hclgevf_reset_task_schedule(struct hclgevf_dev *hdev) { if (!test_bit(HCLGEVF_STATE_REMOVING, &hdev->state) && + test_bit(HCLGEVF_STATE_SERVICE_INITED, &hdev->state) && !test_and_set_bit(HCLGEVF_STATE_RST_SERVICE_SCHED, &hdev->state)) mod_delayed_work(hclgevf_wq, &hdev->service_task, 0); @@ -3449,6 +3450,8 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) hclgevf_init_rxd_adv_layout(hdev); + set_bit(HCLGEVF_STATE_SERVICE_INITED, &hdev->state); + hdev->last_reset_time = jiffies; dev_info(&hdev->pdev->dev, "finished initializing %s driver\n", HCLGEVF_DRIVER_NAME); @@ -3899,7 +3902,7 @@ static int hclgevf_init(void) { pr_info("%s is initializing\n", HCLGEVF_NAME); - hclgevf_wq = alloc_workqueue("%s", 0, 0, HCLGEVF_NAME); + hclgevf_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, HCLGEVF_NAME); if (!hclgevf_wq) { pr_err("%s: failed to create workqueue\n", HCLGEVF_NAME); return -ENOMEM; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 883130a9b48f..28288d7e3303 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -146,6 +146,7 @@ enum hclgevf_states { HCLGEVF_STATE_REMOVING, HCLGEVF_STATE_NIC_REGISTERED, HCLGEVF_STATE_ROCE_REGISTERED, + HCLGEVF_STATE_SERVICE_INITED, /* task states */ HCLGEVF_STATE_RST_SERVICE_SCHED, HCLGEVF_STATE_RST_HANDLING, diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index 37c18c66b5c7..e375ac849aec 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -100,9 +100,9 @@ static void ice_display_lag_info(struct ice_lag *lag) */ static void ice_lag_info_event(struct ice_lag *lag, void *ptr) { - struct net_device *event_netdev, *netdev_tmp; struct netdev_notifier_bonding_info *info; struct netdev_bonding_info *bonding_info; + struct net_device *event_netdev; const char *lag_netdev_name; event_netdev = netdev_notifier_info_to_dev(ptr); @@ -123,19 +123,6 @@ static void ice_lag_info_event(struct ice_lag *lag, void *ptr) goto lag_out; } - rcu_read_lock(); - for_each_netdev_in_bond_rcu(lag->upper_netdev, netdev_tmp) { - if (!netif_is_ice(netdev_tmp)) - continue; - - if (netdev_tmp && netdev_tmp != lag->netdev && - lag->peer_netdev != netdev_tmp) { - dev_hold(netdev_tmp); - lag->peer_netdev = netdev_tmp; - } - } - rcu_read_unlock(); - if (bonding_info->slave.state) ice_lag_set_backup(lag); else @@ -319,6 +306,9 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event, case NETDEV_BONDING_INFO: ice_lag_info_event(lag, ptr); break; + case NETDEV_UNREGISTER: + ice_lag_unlink(lag, ptr); + break; default: break; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index a1be0d04a2d0..bf7247c6f58e 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -1929,6 +1929,9 @@ err_kworker: */ void ice_ptp_release(struct ice_pf *pf) { + if (!test_bit(ICE_FLAG_PTP, pf->flags)) + return; + /* Disable timestamping for both Tx and Rx */ ice_ptp_cfg_timestamp(pf, false); diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index ecf1e11d9b91..0da09ea81980 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -25,6 +25,7 @@ #define XRX200_DMA_DATA_LEN (SZ_64K - 1) #define XRX200_DMA_RX 0 #define XRX200_DMA_TX 1 +#define XRX200_DMA_BURST_LEN 8 /* cpu port mac */ #define PMAC_RX_IPG 0x0024 @@ -73,9 +74,6 @@ struct xrx200_priv { struct net_device *net_dev; struct device *dev; - int tx_burst_len; - int rx_burst_len; - __iomem void *pmac_reg; }; @@ -323,7 +321,7 @@ static netdev_tx_t xrx200_start_xmit(struct sk_buff *skb, goto err_drop; /* dma needs to start on a burst length value aligned address */ - byte_offset = mapping % (priv->tx_burst_len * 4); + byte_offset = mapping % (XRX200_DMA_BURST_LEN * 4); desc->addr = mapping - byte_offset; /* Make sure the address is written before we give it to HW */ @@ -422,7 +420,8 @@ static int xrx200_dma_init(struct xrx200_priv *priv) int ret = 0; int i; - ltq_dma_init_port(DMA_PORT_ETOP, priv->tx_burst_len, rx_burst_len); + ltq_dma_init_port(DMA_PORT_ETOP, XRX200_DMA_BURST_LEN, + XRX200_DMA_BURST_LEN); ch_rx->dma.nr = XRX200_DMA_RX; ch_rx->dma.dev = priv->dev; @@ -531,18 +530,6 @@ static int xrx200_probe(struct platform_device *pdev) if (err) eth_hw_addr_random(net_dev); - err = device_property_read_u32(dev, "lantiq,tx-burst-length", &priv->tx_burst_len); - if (err < 0) { - dev_err(dev, "unable to read tx-burst-length property\n"); - return err; - } - - err = device_property_read_u32(dev, "lantiq,rx-burst-length", &priv->rx_burst_len); - if (err < 0) { - dev_err(dev, "unable to read rx-burst-length property\n"); - return err; - } - /* bring up the dma engine and IP core */ err = xrx200_dma_init(priv); if (err) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 94d479010410..c7fd466a0efd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -316,18 +316,85 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp, RVU_DEBUG_FOPS(lmtst_map_table, lmtst_map_table_display, NULL); +static void get_lf_str_list(struct rvu_block block, int pcifunc, + char *lfs) +{ + int lf = 0, seq = 0, len = 0, prev_lf = block.lf.max; + + for_each_set_bit(lf, block.lf.bmap, block.lf.max) { + if (lf >= block.lf.max) + break; + + if (block.fn_map[lf] != pcifunc) + continue; + + if (lf == prev_lf + 1) { + prev_lf = lf; + seq = 1; + continue; + } + + if (seq) + len += sprintf(lfs + len, "-%d,%d", prev_lf, lf); + else + len += (len ? sprintf(lfs + len, ",%d", lf) : + sprintf(lfs + len, "%d", lf)); + + prev_lf = lf; + seq = 0; + } + + if (seq) + len += sprintf(lfs + len, "-%d", prev_lf); + + lfs[len] = '\0'; +} + +static int get_max_column_width(struct rvu *rvu) +{ + int index, pf, vf, lf_str_size = 12, buf_size = 256; + struct rvu_block block; + u16 pcifunc; + char *buf; + + buf = kzalloc(buf_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + for (pf = 0; pf < rvu->hw->total_pfs; pf++) { + for (vf = 0; vf <= rvu->hw->total_vfs; vf++) { + pcifunc = pf << 10 | vf; + if (!pcifunc) + continue; + + for (index = 0; index < BLK_COUNT; index++) { + block = rvu->hw->block[index]; + if (!strlen(block.name)) + continue; + + get_lf_str_list(block, pcifunc, buf); + if (lf_str_size <= strlen(buf)) + lf_str_size = strlen(buf) + 1; + } + } + } + + kfree(buf); + return lf_str_size; +} + /* Dumps current provisioning status of all RVU block LFs */ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { - int index, off = 0, flag = 0, go_back = 0, len = 0; + int index, off = 0, flag = 0, len = 0, i = 0; struct rvu *rvu = filp->private_data; - int lf, pf, vf, pcifunc; + int bytes_not_copied = 0; struct rvu_block block; - int bytes_not_copied; - int lf_str_size = 12; + int pf, vf, pcifunc; int buf_size = 2048; + int lf_str_size; char *lfs; char *buf; @@ -339,6 +406,9 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, if (!buf) return -ENOSPC; + /* Get the maximum width of a column */ + lf_str_size = get_max_column_width(rvu); + lfs = kzalloc(lf_str_size, GFP_KERNEL); if (!lfs) { kfree(buf); @@ -352,65 +422,69 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, "%-*s", lf_str_size, rvu->hw->block[index].name); } + off += scnprintf(&buf[off], buf_size - 1 - off, "\n"); + bytes_not_copied = copy_to_user(buffer + (i * off), buf, off); + if (bytes_not_copied) + goto out; + + i++; + *ppos += off; for (pf = 0; pf < rvu->hw->total_pfs; pf++) { for (vf = 0; vf <= rvu->hw->total_vfs; vf++) { + off = 0; + flag = 0; pcifunc = pf << 10 | vf; if (!pcifunc) continue; if (vf) { sprintf(lfs, "PF%d:VF%d", pf, vf - 1); - go_back = scnprintf(&buf[off], - buf_size - 1 - off, - "%-*s", lf_str_size, lfs); + off = scnprintf(&buf[off], + buf_size - 1 - off, + "%-*s", lf_str_size, lfs); } else { sprintf(lfs, "PF%d", pf); - go_back = scnprintf(&buf[off], - buf_size - 1 - off, - "%-*s", lf_str_size, lfs); + off = scnprintf(&buf[off], + buf_size - 1 - off, + "%-*s", lf_str_size, lfs); } - off += go_back; - for (index = 0; index < BLKTYPE_MAX; index++) { + for (index = 0; index < BLK_COUNT; index++) { block = rvu->hw->block[index]; if (!strlen(block.name)) continue; len = 0; lfs[len] = '\0'; - for (lf = 0; lf < block.lf.max; lf++) { - if (block.fn_map[lf] != pcifunc) - continue; + get_lf_str_list(block, pcifunc, lfs); + if (strlen(lfs)) flag = 1; - len += sprintf(&lfs[len], "%d,", lf); - } - if (flag) - len--; - lfs[len] = '\0'; off += scnprintf(&buf[off], buf_size - 1 - off, "%-*s", lf_str_size, lfs); - if (!strlen(lfs)) - go_back += lf_str_size; } - if (!flag) - off -= go_back; - else - flag = 0; - off--; - off += scnprintf(&buf[off], buf_size - 1 - off, "\n"); + if (flag) { + off += scnprintf(&buf[off], + buf_size - 1 - off, "\n"); + bytes_not_copied = copy_to_user(buffer + + (i * off), + buf, off); + if (bytes_not_copied) + goto out; + + i++; + *ppos += off; + } } } - bytes_not_copied = copy_to_user(buffer, buf, off); +out: kfree(lfs); kfree(buf); - if (bytes_not_copied) return -EFAULT; - *ppos = off; - return off; + return *ppos; } RVU_DEBUG_FOPS(rsrc_status, rsrc_attach_status, NULL); @@ -594,7 +668,7 @@ static ssize_t rvu_dbg_qsize_write(struct file *filp, if (cmd_buf) ret = -EINVAL; - if (!strncmp(subtoken, "help", 4) || ret < 0) { + if (ret < 0 || !strncmp(subtoken, "help", 4)) { dev_info(rvu->dev, "Use echo <%s-lf > qsize\n", blk_string); goto qsize_write_done; } @@ -1809,6 +1883,10 @@ static int rvu_dbg_nix_band_prof_ctx_display(struct seq_file *m, void *unused) u16 pcifunc; char *str; + /* Ingress policers do not exist on all platforms */ + if (!nix_hw->ipolicer) + return 0; + for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) { if (layer == BAND_PROF_INVAL_LAYER) continue; @@ -1858,6 +1936,10 @@ static int rvu_dbg_nix_band_prof_rsrc_display(struct seq_file *m, void *unused) int layer; char *str; + /* Ingress policers do not exist on all platforms */ + if (!nix_hw->ipolicer) + return 0; + seq_puts(m, "\nBandwidth profile resource free count\n"); seq_puts(m, "=====================================\n"); for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 7761dcf17b91..d8b1948aaa0a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -2583,6 +2583,9 @@ static void nix_free_tx_vtag_entries(struct rvu *rvu, u16 pcifunc) return; nix_hw = get_nix_hw(rvu->hw, blkaddr); + if (!nix_hw) + return; + vlan = &nix_hw->txvlan; mutex_lock(&vlan->rsrc_lock); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 13b0259f7ea6..fcace73eae40 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -353,13 +353,10 @@ static int mlxsw_pci_rdq_skb_alloc(struct mlxsw_pci *mlxsw_pci, struct sk_buff *skb; int err; - elem_info->u.rdq.skb = NULL; skb = netdev_alloc_skb_ip_align(NULL, buf_len); if (!skb) return -ENOMEM; - /* Assume that wqe was previously zeroed. */ - err = mlxsw_pci_wqe_frag_map(mlxsw_pci, wqe, 0, skb->data, buf_len, DMA_FROM_DEVICE); if (err) @@ -597,21 +594,26 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, struct pci_dev *pdev = mlxsw_pci->pdev; struct mlxsw_pci_queue_elem_info *elem_info; struct mlxsw_rx_info rx_info = {}; - char *wqe; + char wqe[MLXSW_PCI_WQE_SIZE]; struct sk_buff *skb; u16 byte_count; int err; elem_info = mlxsw_pci_queue_elem_info_consumer_get(q); - skb = elem_info->u.sdq.skb; - if (!skb) - return; - wqe = elem_info->elem; - mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE); + skb = elem_info->u.rdq.skb; + memcpy(wqe, elem_info->elem, MLXSW_PCI_WQE_SIZE); if (q->consumer_counter++ != consumer_counter_limit) dev_dbg_ratelimited(&pdev->dev, "Consumer counter does not match limit in RDQ\n"); + err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info); + if (err) { + dev_err_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n"); + goto out; + } + + mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE); + if (mlxsw_pci_cqe_lag_get(cqe_v, cqe)) { rx_info.is_lag = true; rx_info.u.lag_id = mlxsw_pci_cqe_lag_id_get(cqe_v, cqe); @@ -647,10 +649,7 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, skb_put(skb, byte_count); mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info); - memset(wqe, 0, q->elem_size); - err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info); - if (err) - dev_dbg_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n"); +out: /* Everything is set up, ring doorbell to pass elem to HW */ q->producer_counter++; mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c index ddb5ad88b350..4243d3b883ff 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c @@ -271,6 +271,7 @@ mlxsw_sp_qdisc_destroy(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc_tree_validate { bool forbid_ets; + bool forbid_root_tbf; bool forbid_tbf; bool forbid_red; }; @@ -310,18 +311,26 @@ __mlxsw_sp_qdisc_tree_validate(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, if (validate.forbid_red) return -EINVAL; validate.forbid_red = true; + validate.forbid_root_tbf = true; validate.forbid_ets = true; break; case MLXSW_SP_QDISC_TBF: - if (validate.forbid_tbf) - return -EINVAL; - validate.forbid_tbf = true; - validate.forbid_ets = true; + if (validate.forbid_root_tbf) { + if (validate.forbid_tbf) + return -EINVAL; + /* This is a TC TBF. */ + validate.forbid_tbf = true; + validate.forbid_ets = true; + } else { + /* This is root TBF. */ + validate.forbid_root_tbf = true; + } break; case MLXSW_SP_QDISC_PRIO: case MLXSW_SP_QDISC_ETS: if (validate.forbid_ets) return -EINVAL; + validate.forbid_root_tbf = true; validate.forbid_ets = true; break; default: @@ -905,16 +914,34 @@ mlxsw_sp_setup_tc_qdisc_leaf_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_qdisc->stats_base.backlog = 0; } +static enum mlxsw_reg_qeec_hr +mlxsw_sp_qdisc_tbf_hr(struct mlxsw_sp_port *mlxsw_sp_port, + struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) +{ + if (mlxsw_sp_qdisc == &mlxsw_sp_port->qdisc->root_qdisc) + return MLXSW_REG_QEEC_HR_PORT; + + /* Configure subgroup shaper, so that both UC and MC traffic is subject + * to shaping. That is unlike RED, however UC queue lengths are going to + * be different than MC ones due to different pool and quota + * configurations, so the configuration is not applicable. For shaper on + * the other hand, subjecting the overall stream to the configured + * shaper makes sense. Also note that that is what we do for + * ieee_setmaxrate(). + */ + return MLXSW_REG_QEEC_HR_SUBGROUP; +} + static int mlxsw_sp_qdisc_tbf_destroy(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) { + enum mlxsw_reg_qeec_hr hr = mlxsw_sp_qdisc_tbf_hr(mlxsw_sp_port, + mlxsw_sp_qdisc); int tclass_num = mlxsw_sp_qdisc_get_tclass_num(mlxsw_sp_port, mlxsw_sp_qdisc); - return mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port, - MLXSW_REG_QEEC_HR_SUBGROUP, - tclass_num, 0, + return mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port, hr, tclass_num, 0, MLXSW_REG_QEEC_MAS_DIS, 0); } @@ -996,6 +1023,8 @@ mlxsw_sp_qdisc_tbf_replace(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, void *params) { + enum mlxsw_reg_qeec_hr hr = mlxsw_sp_qdisc_tbf_hr(mlxsw_sp_port, + mlxsw_sp_qdisc); struct tc_tbf_qopt_offload_replace_params *p = params; u64 rate_kbps = mlxsw_sp_qdisc_tbf_rate_kbps(p); int tclass_num; @@ -1016,17 +1045,7 @@ mlxsw_sp_qdisc_tbf_replace(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, /* check_params above was supposed to reject this value. */ return -EINVAL; - /* Configure subgroup shaper, so that both UC and MC traffic is subject - * to shaping. That is unlike RED, however UC queue lengths are going to - * be different than MC ones due to different pool and quota - * configurations, so the configuration is not applicable. For shaper on - * the other hand, subjecting the overall stream to the configured - * shaper makes sense. Also note that that is what we do for - * ieee_setmaxrate(). - */ - return mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port, - MLXSW_REG_QEEC_HR_SUBGROUP, - tclass_num, 0, + return mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port, hr, tclass_num, 0, rate_kbps, burst_size); } diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 03d02403c19e..4fc97823bc84 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -1743,6 +1743,16 @@ static int lan743x_tx_ring_init(struct lan743x_tx *tx) ret = -EINVAL; goto cleanup; } + if (dma_set_mask_and_coherent(&tx->adapter->pdev->dev, + DMA_BIT_MASK(64))) { + if (dma_set_mask_and_coherent(&tx->adapter->pdev->dev, + DMA_BIT_MASK(32))) { + dev_warn(&tx->adapter->pdev->dev, + "lan743x_: No suitable DMA available\n"); + ret = -ENOMEM; + goto cleanup; + } + } ring_allocation_size = ALIGN(tx->ring_size * sizeof(struct lan743x_tx_descriptor), PAGE_SIZE); @@ -1934,7 +1944,8 @@ static void lan743x_rx_update_tail(struct lan743x_rx *rx, int index) index); } -static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index) +static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index, + gfp_t gfp) { struct net_device *netdev = rx->adapter->netdev; struct device *dev = &rx->adapter->pdev->dev; @@ -1948,7 +1959,7 @@ static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index) descriptor = &rx->ring_cpu_ptr[index]; buffer_info = &rx->buffer_info[index]; - skb = __netdev_alloc_skb(netdev, buffer_length, GFP_ATOMIC | GFP_DMA); + skb = __netdev_alloc_skb(netdev, buffer_length, gfp); if (!skb) return -ENOMEM; dma_ptr = dma_map_single(dev, skb->data, buffer_length, DMA_FROM_DEVICE); @@ -2110,7 +2121,8 @@ static int lan743x_rx_process_buffer(struct lan743x_rx *rx) /* save existing skb, allocate new skb and map to dma */ skb = buffer_info->skb; - if (lan743x_rx_init_ring_element(rx, rx->last_head)) { + if (lan743x_rx_init_ring_element(rx, rx->last_head, + GFP_ATOMIC | GFP_DMA)) { /* failed to allocate next skb. * Memory is very low. * Drop this packet and reuse buffer. @@ -2276,6 +2288,16 @@ static int lan743x_rx_ring_init(struct lan743x_rx *rx) ret = -EINVAL; goto cleanup; } + if (dma_set_mask_and_coherent(&rx->adapter->pdev->dev, + DMA_BIT_MASK(64))) { + if (dma_set_mask_and_coherent(&rx->adapter->pdev->dev, + DMA_BIT_MASK(32))) { + dev_warn(&rx->adapter->pdev->dev, + "lan743x_: No suitable DMA available\n"); + ret = -ENOMEM; + goto cleanup; + } + } ring_allocation_size = ALIGN(rx->ring_size * sizeof(struct lan743x_rx_descriptor), PAGE_SIZE); @@ -2315,13 +2337,16 @@ static int lan743x_rx_ring_init(struct lan743x_rx *rx) rx->last_head = 0; for (index = 0; index < rx->ring_size; index++) { - ret = lan743x_rx_init_ring_element(rx, index); + ret = lan743x_rx_init_ring_element(rx, index, GFP_KERNEL); if (ret) goto cleanup; } return 0; cleanup: + netif_warn(rx->adapter, ifup, rx->adapter->netdev, + "Error allocating memory for LAN743x\n"); + lan743x_rx_ring_cleanup(rx); return ret; } @@ -3019,6 +3044,8 @@ static int lan743x_pm_resume(struct device *dev) if (ret) { netif_err(adapter, probe, adapter->netdev, "lan743x_hardware_init returned %d\n", ret); + lan743x_pci_cleanup(adapter); + return ret; } /* open netdev when netdev is at running state while resume. diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index 11c83a99b014..f469950c7265 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -182,15 +182,21 @@ static int nfp_bpf_check_mtu(struct nfp_app *app, struct net_device *netdev, int new_mtu) { struct nfp_net *nn = netdev_priv(netdev); - unsigned int max_mtu; + struct nfp_bpf_vnic *bv; + struct bpf_prog *prog; if (~nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) return 0; - max_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32; - if (new_mtu > max_mtu) { - nn_info(nn, "BPF offload active, MTU over %u not supported\n", - max_mtu); + if (nn->xdp_hw.prog) { + prog = nn->xdp_hw.prog; + } else { + bv = nn->app_priv; + prog = bv->tc_prog; + } + + if (nfp_bpf_offload_check_mtu(nn, prog, new_mtu)) { + nn_info(nn, "BPF offload active, potential packet access beyond hardware packet boundary"); return -EBUSY; } return 0; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index d0e17eebddd9..16841bb750b7 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -560,6 +560,8 @@ bool nfp_is_subprog_start(struct nfp_insn_meta *meta); void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog); int nfp_bpf_jit(struct nfp_prog *prog); bool nfp_bpf_supported_opcode(u8 code); +bool nfp_bpf_offload_check_mtu(struct nfp_net *nn, struct bpf_prog *prog, + unsigned int mtu); int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 53851853562c..9d97cd281f18 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -481,19 +481,28 @@ int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data, return 0; } +bool nfp_bpf_offload_check_mtu(struct nfp_net *nn, struct bpf_prog *prog, + unsigned int mtu) +{ + unsigned int fw_mtu, pkt_off; + + fw_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32; + pkt_off = min(prog->aux->max_pkt_offset, mtu); + + return fw_mtu < pkt_off; +} + static int nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog, struct netlink_ext_ack *extack) { struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv; - unsigned int fw_mtu, pkt_off, max_stack, max_prog_len; + unsigned int max_stack, max_prog_len; dma_addr_t dma_addr; void *img; int err; - fw_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32; - pkt_off = min(prog->aux->max_pkt_offset, nn->dp.netdev->mtu); - if (fw_mtu < pkt_off) { + if (nfp_bpf_offload_check_mtu(nn, prog, nn->dp.netdev->mtu)) { NL_SET_ERR_MSG_MOD(extack, "BPF offload not supported with potential packet access beyond HW packet split boundary"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index a63cc295b979..bc39558fe82b 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -1015,9 +1015,6 @@ static int lpc_eth_close(struct net_device *ndev) napi_disable(&pldat->napi); netif_stop_queue(ndev); - if (ndev->phydev) - phy_stop(ndev->phydev); - spin_lock_irqsave(&pldat->lock, flags); __lpc_eth_reset(pldat); netif_carrier_off(ndev); @@ -1025,6 +1022,8 @@ static int lpc_eth_close(struct net_device *ndev) writel(0, LPC_ENET_MAC2(pldat->net_base)); spin_unlock_irqrestore(&pldat->lock, flags); + if (ndev->phydev) + phy_stop(ndev->phydev); clk_disable_unprepare(pldat->clk); return 0; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index ee6c9c842012..bbe21db20417 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -156,6 +156,7 @@ static const struct pci_device_id rtl8169_pci_tbl[] = { { PCI_VDEVICE(REALTEK, 0x8129) }, { PCI_VDEVICE(REALTEK, 0x8136), RTL_CFG_NO_GBIT }, { PCI_VDEVICE(REALTEK, 0x8161) }, + { PCI_VDEVICE(REALTEK, 0x8162) }, { PCI_VDEVICE(REALTEK, 0x8167) }, { PCI_VDEVICE(REALTEK, 0x8168) }, { PCI_VDEVICE(NCUBE, 0x8168) }, diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index f124a8a58bd4..a3bfb156c83d 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -243,62 +243,10 @@ static void phy_sanitize_settings(struct phy_device *phydev) } } -int phy_ethtool_ksettings_set(struct phy_device *phydev, - const struct ethtool_link_ksettings *cmd) -{ - __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); - u8 autoneg = cmd->base.autoneg; - u8 duplex = cmd->base.duplex; - u32 speed = cmd->base.speed; - - if (cmd->base.phy_address != phydev->mdio.addr) - return -EINVAL; - - linkmode_copy(advertising, cmd->link_modes.advertising); - - /* We make sure that we don't pass unsupported values in to the PHY */ - linkmode_and(advertising, advertising, phydev->supported); - - /* Verify the settings we care about. */ - if (autoneg != AUTONEG_ENABLE && autoneg != AUTONEG_DISABLE) - return -EINVAL; - - if (autoneg == AUTONEG_ENABLE && linkmode_empty(advertising)) - return -EINVAL; - - if (autoneg == AUTONEG_DISABLE && - ((speed != SPEED_1000 && - speed != SPEED_100 && - speed != SPEED_10) || - (duplex != DUPLEX_HALF && - duplex != DUPLEX_FULL))) - return -EINVAL; - - phydev->autoneg = autoneg; - - if (autoneg == AUTONEG_DISABLE) { - phydev->speed = speed; - phydev->duplex = duplex; - } - - linkmode_copy(phydev->advertising, advertising); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, - phydev->advertising, autoneg == AUTONEG_ENABLE); - - phydev->master_slave_set = cmd->base.master_slave_cfg; - phydev->mdix_ctrl = cmd->base.eth_tp_mdix_ctrl; - - /* Restart the PHY */ - phy_start_aneg(phydev); - - return 0; -} -EXPORT_SYMBOL(phy_ethtool_ksettings_set); - void phy_ethtool_ksettings_get(struct phy_device *phydev, struct ethtool_link_ksettings *cmd) { + mutex_lock(&phydev->lock); linkmode_copy(cmd->link_modes.supported, phydev->supported); linkmode_copy(cmd->link_modes.advertising, phydev->advertising); linkmode_copy(cmd->link_modes.lp_advertising, phydev->lp_advertising); @@ -317,6 +265,7 @@ void phy_ethtool_ksettings_get(struct phy_device *phydev, cmd->base.autoneg = phydev->autoneg; cmd->base.eth_tp_mdix_ctrl = phydev->mdix_ctrl; cmd->base.eth_tp_mdix = phydev->mdix; + mutex_unlock(&phydev->lock); } EXPORT_SYMBOL(phy_ethtool_ksettings_get); @@ -751,7 +700,7 @@ static int phy_check_link_status(struct phy_device *phydev) } /** - * phy_start_aneg - start auto-negotiation for this PHY device + * _phy_start_aneg - start auto-negotiation for this PHY device * @phydev: the phy_device struct * * Description: Sanitizes the settings (if we're not autonegotiating @@ -759,25 +708,43 @@ static int phy_check_link_status(struct phy_device *phydev) * If the PHYCONTROL Layer is operating, we change the state to * reflect the beginning of Auto-negotiation or forcing. */ -int phy_start_aneg(struct phy_device *phydev) +static int _phy_start_aneg(struct phy_device *phydev) { int err; + lockdep_assert_held(&phydev->lock); + if (!phydev->drv) return -EIO; - mutex_lock(&phydev->lock); - if (AUTONEG_DISABLE == phydev->autoneg) phy_sanitize_settings(phydev); err = phy_config_aneg(phydev); if (err < 0) - goto out_unlock; + return err; if (phy_is_started(phydev)) err = phy_check_link_status(phydev); -out_unlock: + + return err; +} + +/** + * phy_start_aneg - start auto-negotiation for this PHY device + * @phydev: the phy_device struct + * + * Description: Sanitizes the settings (if we're not autonegotiating + * them), and then calls the driver's config_aneg function. + * If the PHYCONTROL Layer is operating, we change the state to + * reflect the beginning of Auto-negotiation or forcing. + */ +int phy_start_aneg(struct phy_device *phydev) +{ + int err; + + mutex_lock(&phydev->lock); + err = _phy_start_aneg(phydev); mutex_unlock(&phydev->lock); return err; @@ -800,6 +767,61 @@ static int phy_poll_aneg_done(struct phy_device *phydev) return ret < 0 ? ret : 0; } +int phy_ethtool_ksettings_set(struct phy_device *phydev, + const struct ethtool_link_ksettings *cmd) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); + u8 autoneg = cmd->base.autoneg; + u8 duplex = cmd->base.duplex; + u32 speed = cmd->base.speed; + + if (cmd->base.phy_address != phydev->mdio.addr) + return -EINVAL; + + linkmode_copy(advertising, cmd->link_modes.advertising); + + /* We make sure that we don't pass unsupported values in to the PHY */ + linkmode_and(advertising, advertising, phydev->supported); + + /* Verify the settings we care about. */ + if (autoneg != AUTONEG_ENABLE && autoneg != AUTONEG_DISABLE) + return -EINVAL; + + if (autoneg == AUTONEG_ENABLE && linkmode_empty(advertising)) + return -EINVAL; + + if (autoneg == AUTONEG_DISABLE && + ((speed != SPEED_1000 && + speed != SPEED_100 && + speed != SPEED_10) || + (duplex != DUPLEX_HALF && + duplex != DUPLEX_FULL))) + return -EINVAL; + + mutex_lock(&phydev->lock); + phydev->autoneg = autoneg; + + if (autoneg == AUTONEG_DISABLE) { + phydev->speed = speed; + phydev->duplex = duplex; + } + + linkmode_copy(phydev->advertising, advertising); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + phydev->advertising, autoneg == AUTONEG_ENABLE); + + phydev->master_slave_set = cmd->base.master_slave_cfg; + phydev->mdix_ctrl = cmd->base.eth_tp_mdix_ctrl; + + /* Restart the PHY */ + _phy_start_aneg(phydev); + + mutex_unlock(&phydev->lock); + return 0; +} +EXPORT_SYMBOL(phy_ethtool_ksettings_set); + /** * phy_speed_down - set speed to lowest speed supported by both link partners * @phydev: the phy_device struct diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 03319fdb5235..f20376c1ef3f 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -4122,6 +4122,12 @@ static int lan78xx_probe(struct usb_interface *intf, dev->maxpacket = usb_maxpacket(dev->udev, dev->pipe_out, 1); + /* Reject broken descriptors. */ + if (dev->maxpacket == 0) { + ret = -ENODEV; + goto out4; + } + /* driver requires remote-wakeup capability during autosuspend. */ intf->needs_remote_wakeup = 1; diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 350bae673ed4..9a6450f796dc 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1792,6 +1792,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) dev->maxpacket = usb_maxpacket (dev->udev, dev->out, 1); if (dev->maxpacket == 0) { /* that is a broken device */ + status = -ENODEV; goto out4; } diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 3e1b7746cce4..14fae317bc70 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -3833,7 +3833,6 @@ vmxnet3_suspend(struct device *device) vmxnet3_free_intr_resources(adapter); netif_device_detach(netdev); - netif_tx_stop_all_queues(netdev); /* Create wake-up filters. */ pmConf = adapter->pm_conf; diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 57437e4b8a94..911f43986a8c 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1730,6 +1730,10 @@ static int netfront_resume(struct xenbus_device *dev) dev_dbg(&dev->dev, "%s\n", dev->nodename); + netif_tx_lock_bh(info->netdev); + netif_device_detach(info->netdev); + netif_tx_unlock_bh(info->netdev); + xennet_disconnect_backend(info); return 0; } @@ -2351,6 +2355,10 @@ static int xennet_connect(struct net_device *dev) * domain a kick because we've probably just requeued some * packets. */ + netif_tx_lock_bh(np->netdev); + netif_device_attach(np->netdev); + netif_tx_unlock_bh(np->netdev); + netif_carrier_on(np->netdev); for (j = 0; j < num_queues; ++j) { queue = &np->queues[j]; diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c index 517376c43b86..16ceb763594f 100644 --- a/drivers/nfc/port100.c +++ b/drivers/nfc/port100.c @@ -1006,11 +1006,11 @@ static u64 port100_get_command_type_mask(struct port100 *dev) skb = port100_alloc_skb(dev, 0); if (!skb) - return -ENOMEM; + return 0; resp = port100_send_cmd_sync(dev, PORT100_CMD_GET_COMMAND_TYPE, skb); if (IS_ERR(resp)) - return PTR_ERR(resp); + return 0; if (resp->len < 8) mask = 0; diff --git a/drivers/pinctrl/bcm/pinctrl-ns.c b/drivers/pinctrl/bcm/pinctrl-ns.c index e79690bd8b85..d7f8175d2c1c 100644 --- a/drivers/pinctrl/bcm/pinctrl-ns.c +++ b/drivers/pinctrl/bcm/pinctrl-ns.c @@ -5,7 +5,6 @@ #include <linux/err.h> #include <linux/io.h> -#include <linux/mfd/syscon.h> #include <linux/module.h> #include <linux/of.h> #include <linux/of_device.h> @@ -13,7 +12,6 @@ #include <linux/pinctrl/pinctrl.h> #include <linux/pinctrl/pinmux.h> #include <linux/platform_device.h> -#include <linux/regmap.h> #include <linux/slab.h> #define FLAG_BCM4708 BIT(1) @@ -24,8 +22,7 @@ struct ns_pinctrl { struct device *dev; unsigned int chipset_flag; struct pinctrl_dev *pctldev; - struct regmap *regmap; - u32 offset; + void __iomem *base; struct pinctrl_desc pctldesc; struct ns_pinctrl_group *groups; @@ -232,9 +229,9 @@ static int ns_pinctrl_set_mux(struct pinctrl_dev *pctrl_dev, unset |= BIT(pin_number); } - regmap_read(ns_pinctrl->regmap, ns_pinctrl->offset, &tmp); + tmp = readl(ns_pinctrl->base); tmp &= ~unset; - regmap_write(ns_pinctrl->regmap, ns_pinctrl->offset, tmp); + writel(tmp, ns_pinctrl->base); return 0; } @@ -266,13 +263,13 @@ static const struct of_device_id ns_pinctrl_of_match_table[] = { static int ns_pinctrl_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct device_node *np = dev->of_node; const struct of_device_id *of_id; struct ns_pinctrl *ns_pinctrl; struct pinctrl_desc *pctldesc; struct pinctrl_pin_desc *pin; struct ns_pinctrl_group *group; struct ns_pinctrl_function *function; + struct resource *res; int i; ns_pinctrl = devm_kzalloc(dev, sizeof(*ns_pinctrl), GFP_KERNEL); @@ -290,18 +287,12 @@ static int ns_pinctrl_probe(struct platform_device *pdev) return -EINVAL; ns_pinctrl->chipset_flag = (uintptr_t)of_id->data; - ns_pinctrl->regmap = syscon_node_to_regmap(of_get_parent(np)); - if (IS_ERR(ns_pinctrl->regmap)) { - int err = PTR_ERR(ns_pinctrl->regmap); - - dev_err(dev, "Failed to map pinctrl regs: %d\n", err); - - return err; - } - - if (of_property_read_u32(np, "offset", &ns_pinctrl->offset)) { - dev_err(dev, "Failed to get register offset\n"); - return -ENOENT; + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "cru_gpio_control"); + ns_pinctrl->base = devm_ioremap_resource(dev, res); + if (IS_ERR(ns_pinctrl->base)) { + dev_err(dev, "Failed to map pinctrl regs\n"); + return PTR_ERR(ns_pinctrl->base); } memcpy(pctldesc, &ns_pinctrl_desc, sizeof(*pctldesc)); diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 8d0f88e9ca88..bae9d429b813 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -840,6 +840,34 @@ static const struct pinconf_ops amd_pinconf_ops = { .pin_config_group_set = amd_pinconf_group_set, }; +static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) +{ + struct pinctrl_desc *desc = gpio_dev->pctrl->desc; + unsigned long flags; + u32 pin_reg, mask; + int i; + + mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3) | + BIT(INTERRUPT_MASK_OFF) | BIT(INTERRUPT_ENABLE_OFF) | + BIT(WAKE_CNTRL_OFF_S4); + + for (i = 0; i < desc->npins; i++) { + int pin = desc->pins[i].number; + const struct pin_desc *pd = pin_desc_get(gpio_dev->pctrl, pin); + + if (!pd) + continue; + + raw_spin_lock_irqsave(&gpio_dev->lock, flags); + + pin_reg = readl(gpio_dev->base + i * 4); + pin_reg &= ~mask; + writel(pin_reg, gpio_dev->base + i * 4); + + raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); + } +} + #ifdef CONFIG_PM_SLEEP static bool amd_gpio_should_save(struct amd_gpio *gpio_dev, unsigned int pin) { @@ -976,6 +1004,9 @@ static int amd_gpio_probe(struct platform_device *pdev) return PTR_ERR(gpio_dev->pctrl); } + /* Disable and mask interrupts */ + amd_gpio_irq_init(gpio_dev); + girq = &gpio_dev->gc.irq; girq->chip = &amd_gpio_irqchip; /* This will let us handle the parent IRQ in the driver */ diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c index 68b3886f9f0f..dfd8888a222a 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32.c @@ -1644,8 +1644,8 @@ int __maybe_unused stm32_pinctrl_resume(struct device *dev) struct stm32_pinctrl_group *g = pctl->groups; int i; - for (i = g->pin; i < g->pin + pctl->ngroups; i++) - stm32_pinctrl_restore_gpio_regs(pctl, i); + for (i = 0; i < pctl->ngroups; i++, g++) + stm32_pinctrl_restore_gpio_regs(pctl, g->pin); return 0; } diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig index be799a5abf8a..b0056ae5d463 100644 --- a/drivers/reset/Kconfig +++ b/drivers/reset/Kconfig @@ -147,8 +147,8 @@ config RESET_OXNAS bool config RESET_PISTACHIO - bool "Pistachio Reset Driver" if COMPILE_TEST - default MACH_PISTACHIO + bool "Pistachio Reset Driver" + depends on MIPS || COMPILE_TEST help This enables the reset driver for ImgTec Pistachio SoCs. diff --git a/drivers/reset/reset-brcmstb-rescal.c b/drivers/reset/reset-brcmstb-rescal.c index b6f074d6a65f..433fa0c40e47 100644 --- a/drivers/reset/reset-brcmstb-rescal.c +++ b/drivers/reset/reset-brcmstb-rescal.c @@ -38,7 +38,7 @@ static int brcm_rescal_reset_set(struct reset_controller_dev *rcdev, } ret = readl_poll_timeout(base + BRCM_RESCAL_STATUS, reg, - !(reg & BRCM_RESCAL_STATUS_BIT), 100, 1000); + (reg & BRCM_RESCAL_STATUS_BIT), 100, 1000); if (ret) { dev_err(data->dev, "time out on SATA/PCIe rescal\n"); return ret; diff --git a/drivers/reset/reset-socfpga.c b/drivers/reset/reset-socfpga.c index 2a72f861f798..8c6492e5693c 100644 --- a/drivers/reset/reset-socfpga.c +++ b/drivers/reset/reset-socfpga.c @@ -92,3 +92,29 @@ void __init socfpga_reset_init(void) for_each_matching_node(np, socfpga_early_reset_dt_ids) a10_reset_init(np); } + +/* + * The early driver is problematic, because it doesn't register + * itself as a driver. This causes certain device links to prevent + * consumer devices from probing. The hacky solution is to register + * an empty driver, whose only job is to attach itself to the reset + * manager and call probe. + */ +static const struct of_device_id socfpga_reset_dt_ids[] = { + { .compatible = "altr,rst-mgr", }, + { /* sentinel */ }, +}; + +static int reset_simple_probe(struct platform_device *pdev) +{ + return 0; +} + +static struct platform_driver reset_socfpga_driver = { + .probe = reset_simple_probe, + .driver = { + .name = "socfpga-reset", + .of_match_table = socfpga_reset_dt_ids, + }, +}; +builtin_platform_driver(reset_socfpga_driver); diff --git a/drivers/reset/tegra/reset-bpmp.c b/drivers/reset/tegra/reset-bpmp.c index 24d3395964cc..4c5bba52b105 100644 --- a/drivers/reset/tegra/reset-bpmp.c +++ b/drivers/reset/tegra/reset-bpmp.c @@ -20,6 +20,7 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc, struct tegra_bpmp *bpmp = to_tegra_bpmp(rstc); struct mrq_reset_request request; struct tegra_bpmp_message msg; + int err; memset(&request, 0, sizeof(request)); request.cmd = command; @@ -30,7 +31,13 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc, msg.tx.data = &request; msg.tx.size = sizeof(request); - return tegra_bpmp_transfer(bpmp, &msg); + err = tegra_bpmp_transfer(bpmp, &msg); + if (err) + return err; + if (msg.rx.ret) + return -EINVAL; + + return 0; } static int tegra_bpmp_reset_module(struct reset_controller_dev *rstc, diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 3f6f14f0cafb..24b72ee4246f 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -220,7 +220,8 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev, goto fail; } - shost->cmd_per_lun = min_t(short, shost->cmd_per_lun, + /* Use min_t(int, ...) in case shost->can_queue exceeds SHRT_MAX */ + shost->cmd_per_lun = min_t(int, shost->cmd_per_lun, shost->can_queue); error = scsi_init_sense_cache(shost); diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c index 2197988333fe..3cae8803383b 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_os.c +++ b/drivers/scsi/mpi3mr/mpi3mr_os.c @@ -3736,7 +3736,7 @@ mpi3mr_probe(struct pci_dev *pdev, const struct pci_device_id *id) shost->max_lun = -1; shost->unique_id = mrioc->id; - shost->max_channel = 1; + shost->max_channel = 0; shost->max_id = 0xFFFFFFFF; if (prot_mask >= 0) diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c index 4b5d28d89d69..655cf5de604b 100644 --- a/drivers/scsi/qla2xxx/qla_bsg.c +++ b/drivers/scsi/qla2xxx/qla_bsg.c @@ -431,7 +431,7 @@ done_unmap_sg: goto done_free_fcport; done_free_fcport: - if (bsg_request->msgcode == FC_BSG_RPT_ELS) + if (bsg_request->msgcode != FC_BSG_RPT_ELS) qla2x00_free_fcport(fcport); done: return rval; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index d2e40aaba734..836fedcea241 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -4157,7 +4157,7 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len, ql_dbg_pci(ql_dbg_init, ha->pdev, 0xe0ee, "%s: failed alloc dsd\n", __func__); - return 1; + return -ENOMEM; } ha->dif_bundle_kallocs++; diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index b3478ed9b12e..7d8242c120fc 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -3319,8 +3319,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type, "RESET-RSP online/active/old-count/new-count = %d/%d/%d/%d.\n", vha->flags.online, qla2x00_reset_active(vha), cmd->reset_count, qpair->chip_reset); - spin_unlock_irqrestore(qpair->qp_lock_ptr, flags); - return 0; + goto out_unmap_unlock; } /* Does F/W have an IOCBs for this request */ @@ -3445,10 +3444,6 @@ int qlt_rdy_to_xfer(struct qla_tgt_cmd *cmd) prm.sg = NULL; prm.req_cnt = 1; - /* Calculate number of entries and segments required */ - if (qlt_pci_map_calc_cnt(&prm) != 0) - return -EAGAIN; - if (!qpair->fw_started || (cmd->reset_count != qpair->chip_reset) || (cmd->sess && cmd->sess->deleted)) { /* @@ -3466,6 +3461,10 @@ int qlt_rdy_to_xfer(struct qla_tgt_cmd *cmd) return 0; } + /* Calculate number of entries and segments required */ + if (qlt_pci_map_calc_cnt(&prm) != 0) + return -EAGAIN; + spin_lock_irqsave(qpair->qp_lock_ptr, flags); /* Does F/W have an IOCBs for this request */ res = qlt_check_reserve_free_req(qpair, prm.req_cnt); @@ -3870,9 +3869,6 @@ void qlt_free_cmd(struct qla_tgt_cmd *cmd) BUG_ON(cmd->cmd_in_wq); - if (cmd->sg_mapped) - qlt_unmap_sg(cmd->vha, cmd); - if (!cmd->q_full) qlt_decr_num_pend_cmds(cmd->vha); diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index b241f9e3885c..291ecc33b1fe 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -553,8 +553,10 @@ EXPORT_SYMBOL(scsi_device_get); */ void scsi_device_put(struct scsi_device *sdev) { - module_put(sdev->host->hostt->module); + struct module *mod = sdev->host->hostt->module; + put_device(&sdev->sdev_gendev); + module_put(mod); } EXPORT_SYMBOL(scsi_device_put); diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 86793259e541..a35841b34bfd 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -449,9 +449,12 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work) struct scsi_vpd *vpd_pg80 = NULL, *vpd_pg83 = NULL; struct scsi_vpd *vpd_pg0 = NULL, *vpd_pg89 = NULL; unsigned long flags; + struct module *mod; sdev = container_of(work, struct scsi_device, ew.work); + mod = sdev->host->hostt->module; + scsi_dh_release_device(sdev); parent = sdev->sdev_gendev.parent; @@ -502,11 +505,17 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work) if (parent) put_device(parent); + module_put(mod); } static void scsi_device_dev_release(struct device *dev) { struct scsi_device *sdp = to_scsi_device(dev); + + /* Set module pointer as NULL in case of module unloading */ + if (!try_module_get(sdp->host->hostt->module)) + sdp->host->hostt->module = NULL; + execute_in_process_context(scsi_device_dev_release_usercontext, &sdp->ew); } diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 922e4c7bd88e..78343d3f9385 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -2930,8 +2930,6 @@ iscsi_set_param(struct iscsi_transport *transport, struct iscsi_uevent *ev) session->recovery_tmo = value; break; default: - err = transport->set_param(conn, ev->u.set_param.param, - data, ev->u.set_param.len); if ((conn->state == ISCSI_CONN_BOUND) || (conn->state == ISCSI_CONN_UP)) { err = transport->set_param(conn, ev->u.set_param.param, diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 523bf2fdc253..fce63335084e 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3683,7 +3683,12 @@ static int sd_resume(struct device *dev) static int sd_resume_runtime(struct device *dev) { struct scsi_disk *sdkp = dev_get_drvdata(dev); - struct scsi_device *sdp = sdkp->device; + struct scsi_device *sdp; + + if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ + return 0; + + sdp = sdkp->device; if (sdp->ignore_media_change) { /* clear the device's sense data */ diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index ebbbc1299c62..9eb1b88a29dd 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1285,11 +1285,15 @@ static void storvsc_on_channel_callback(void *context) foreach_vmbus_pkt(desc, channel) { struct vstor_packet *packet = hv_pkt_data(desc); struct storvsc_cmd_request *request = NULL; + u32 pktlen = hv_pkt_datalen(desc); u64 rqst_id = desc->trans_id; + u32 minlen = rqst_id ? sizeof(struct vstor_packet) - + stor_device->vmscsi_size_delta : sizeof(enum vstor_packet_operation); - if (hv_pkt_datalen(desc) < sizeof(struct vstor_packet) - - stor_device->vmscsi_size_delta) { - dev_err(&device->device, "Invalid packet len\n"); + if (pktlen < minlen) { + dev_err(&device->device, + "Invalid pkt: id=%llu, len=%u, minlen=%u\n", + rqst_id, pktlen, minlen); continue; } @@ -1302,13 +1306,23 @@ static void storvsc_on_channel_callback(void *context) if (rqst_id == 0) { /* * storvsc_on_receive() looks at the vstor_packet in the message - * from the ring buffer. If the operation in the vstor_packet is - * COMPLETE_IO, then we call storvsc_on_io_completion(), and - * dereference the guest memory address. Make sure we don't call - * storvsc_on_io_completion() with a guest memory address that is - * zero if Hyper-V were to construct and send such a bogus packet. + * from the ring buffer. + * + * - If the operation in the vstor_packet is COMPLETE_IO, then + * we call storvsc_on_io_completion(), and dereference the + * guest memory address. Make sure we don't call + * storvsc_on_io_completion() with a guest memory address + * that is zero if Hyper-V were to construct and send such + * a bogus packet. + * + * - If the operation in the vstor_packet is FCHBA_DATA, then + * we call cache_wwn(), and access the data payload area of + * the packet (wwn_packet); however, there is no guarantee + * that the packet is big enough to contain such area. + * Future-proof the code by rejecting such a bogus packet. */ - if (packet->operation == VSTOR_OPERATION_COMPLETE_IO) { + if (packet->operation == VSTOR_OPERATION_COMPLETE_IO || + packet->operation == VSTOR_OPERATION_FCHBA_DATA) { dev_err(&device->device, "Invalid packet with ID of 0\n"); continue; } diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c index 149c1aa09103..51424557810d 100644 --- a/drivers/scsi/ufs/ufshcd-pci.c +++ b/drivers/scsi/ufs/ufshcd-pci.c @@ -370,20 +370,6 @@ static void ufs_intel_common_exit(struct ufs_hba *hba) static int ufs_intel_resume(struct ufs_hba *hba, enum ufs_pm_op op) { - /* - * To support S4 (suspend-to-disk) with spm_lvl other than 5, the base - * address registers must be restored because the restore kernel can - * have used different addresses. - */ - ufshcd_writel(hba, lower_32_bits(hba->utrdl_dma_addr), - REG_UTP_TRANSFER_REQ_LIST_BASE_L); - ufshcd_writel(hba, upper_32_bits(hba->utrdl_dma_addr), - REG_UTP_TRANSFER_REQ_LIST_BASE_H); - ufshcd_writel(hba, lower_32_bits(hba->utmrdl_dma_addr), - REG_UTP_TASK_REQ_LIST_BASE_L); - ufshcd_writel(hba, upper_32_bits(hba->utmrdl_dma_addr), - REG_UTP_TASK_REQ_LIST_BASE_H); - if (ufshcd_is_link_hibern8(hba)) { int ret = ufshcd_uic_hibern8_exit(hba); @@ -463,6 +449,18 @@ static struct ufs_hba_variant_ops ufs_intel_lkf_hba_vops = { .device_reset = ufs_intel_device_reset, }; +#ifdef CONFIG_PM_SLEEP +static int ufshcd_pci_restore(struct device *dev) +{ + struct ufs_hba *hba = dev_get_drvdata(dev); + + /* Force a full reset and restore */ + ufshcd_set_link_off(hba); + + return ufshcd_system_resume(dev); +} +#endif + /** * ufshcd_pci_shutdown - main function to put the controller in reset state * @pdev: pointer to PCI device handle @@ -546,9 +544,14 @@ ufshcd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) } static const struct dev_pm_ops ufshcd_pci_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(ufshcd_system_suspend, ufshcd_system_resume) SET_RUNTIME_PM_OPS(ufshcd_runtime_suspend, ufshcd_runtime_resume, NULL) #ifdef CONFIG_PM_SLEEP + .suspend = ufshcd_system_suspend, + .resume = ufshcd_system_resume, + .freeze = ufshcd_system_suspend, + .thaw = ufshcd_system_resume, + .poweroff = ufshcd_system_suspend, + .restore = ufshcd_pci_restore, .prepare = ufshcd_suspend_prepare, .complete = ufshcd_resume_complete, #endif diff --git a/drivers/spi/spi-altera-dfl.c b/drivers/spi/spi-altera-dfl.c index 44fc9ee13fc7..ca40923258af 100644 --- a/drivers/spi/spi-altera-dfl.c +++ b/drivers/spi/spi-altera-dfl.c @@ -134,7 +134,7 @@ static int dfl_spi_altera_probe(struct dfl_device *dfl_dev) if (!master) return -ENOMEM; - master->bus_num = dfl_dev->id; + master->bus_num = -1; hw = spi_master_get_devdata(master); diff --git a/drivers/spi/spi-altera-platform.c b/drivers/spi/spi-altera-platform.c index f7a7c14e3679..65147aae82a1 100644 --- a/drivers/spi/spi-altera-platform.c +++ b/drivers/spi/spi-altera-platform.c @@ -48,7 +48,7 @@ static int altera_spi_probe(struct platform_device *pdev) return err; /* setup the master state. */ - master->bus_num = pdev->id; + master->bus_num = -1; if (pdata) { if (pdata->num_chipselect > ALTERA_SPI_MAX_CS) { diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c index feebda66f56e..e4484ace584e 100644 --- a/drivers/spi/spi-pl022.c +++ b/drivers/spi/spi-pl022.c @@ -1716,12 +1716,13 @@ static int verify_controller_parameters(struct pl022 *pl022, return -EINVAL; } } else { - if (chip_info->duplex != SSP_MICROWIRE_CHANNEL_FULL_DUPLEX) + if (chip_info->duplex != SSP_MICROWIRE_CHANNEL_FULL_DUPLEX) { dev_err(&pl022->adev->dev, "Microwire half duplex mode requested," " but this is only available in the" " ST version of PL022\n"); - return -EINVAL; + return -EINVAL; + } } } return 0; diff --git a/drivers/spi/spi-tegra20-slink.c b/drivers/spi/spi-tegra20-slink.c index 713292b0c71e..3226c4e1c7c0 100644 --- a/drivers/spi/spi-tegra20-slink.c +++ b/drivers/spi/spi-tegra20-slink.c @@ -1194,7 +1194,7 @@ static int __maybe_unused tegra_slink_runtime_suspend(struct device *dev) return 0; } -static int tegra_slink_runtime_resume(struct device *dev) +static int __maybe_unused tegra_slink_runtime_resume(struct device *dev) { struct spi_master *master = dev_get_drvdata(dev); struct tegra_slink_data *tspi = spi_master_get_devdata(master); diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 26e3d90d1e7c..841667a896dd 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -80,6 +80,7 @@ struct vduse_dev { struct vdpa_callback config_cb; struct work_struct inject; spinlock_t irq_lock; + struct rw_semaphore rwsem; int minor; bool broken; bool connected; @@ -410,6 +411,8 @@ static void vduse_dev_reset(struct vduse_dev *dev) if (domain->bounce_map) vduse_domain_reset_bounce_map(domain); + down_write(&dev->rwsem); + dev->status = 0; dev->driver_features = 0; dev->generation++; @@ -443,6 +446,8 @@ static void vduse_dev_reset(struct vduse_dev *dev) flush_work(&vq->inject); flush_work(&vq->kick); } + + up_write(&dev->rwsem); } static int vduse_vdpa_set_vq_address(struct vdpa_device *vdpa, u16 idx, @@ -885,6 +890,23 @@ static void vduse_vq_irq_inject(struct work_struct *work) spin_unlock_irq(&vq->irq_lock); } +static int vduse_dev_queue_irq_work(struct vduse_dev *dev, + struct work_struct *irq_work) +{ + int ret = -EINVAL; + + down_read(&dev->rwsem); + if (!(dev->status & VIRTIO_CONFIG_S_DRIVER_OK)) + goto unlock; + + ret = 0; + queue_work(vduse_irq_wq, irq_work); +unlock: + up_read(&dev->rwsem); + + return ret; +} + static long vduse_dev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -966,8 +988,7 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, break; } case VDUSE_DEV_INJECT_CONFIG_IRQ: - ret = 0; - queue_work(vduse_irq_wq, &dev->inject); + ret = vduse_dev_queue_irq_work(dev, &dev->inject); break; case VDUSE_VQ_SETUP: { struct vduse_vq_config config; @@ -1053,9 +1074,8 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, if (index >= dev->vq_num) break; - ret = 0; index = array_index_nospec(index, dev->vq_num); - queue_work(vduse_irq_wq, &dev->vqs[index].inject); + ret = vduse_dev_queue_irq_work(dev, &dev->vqs[index].inject); break; } default: @@ -1136,6 +1156,7 @@ static struct vduse_dev *vduse_dev_create(void) INIT_LIST_HEAD(&dev->send_list); INIT_LIST_HEAD(&dev->recv_list); spin_lock_init(&dev->irq_lock); + init_rwsem(&dev->rwsem); INIT_WORK(&dev->inject, vduse_dev_irq_inject); init_waitqueue_head(&dev->waitq); diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index dd95dfd85e98..3035bb6f5458 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -576,7 +576,7 @@ static inline int virtqueue_add_split(struct virtqueue *_vq, /* Last one doesn't continue. */ desc[prev].flags &= cpu_to_virtio16(_vq->vdev, ~VRING_DESC_F_NEXT); if (!indirect && vq->use_dma_api) - vq->split.desc_extra[prev & (vq->split.vring.num - 1)].flags = + vq->split.desc_extra[prev & (vq->split.vring.num - 1)].flags &= ~VRING_DESC_F_NEXT; if (indirect) { diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c index 643c6c2d0b72..ced2fc0deb8c 100644 --- a/drivers/watchdog/iTCO_wdt.c +++ b/drivers/watchdog/iTCO_wdt.c @@ -71,8 +71,6 @@ #define TCOBASE(p) ((p)->tco_res->start) /* SMI Control and Enable Register */ #define SMI_EN(p) ((p)->smi_res->start) -#define TCO_EN (1 << 13) -#define GBL_SMI_EN (1 << 0) #define TCO_RLD(p) (TCOBASE(p) + 0x00) /* TCO Timer Reload/Curr. Value */ #define TCOv1_TMR(p) (TCOBASE(p) + 0x01) /* TCOv1 Timer Initial Value*/ @@ -357,12 +355,8 @@ static int iTCO_wdt_set_timeout(struct watchdog_device *wd_dev, unsigned int t) tmrval = seconds_to_ticks(p, t); - /* - * If TCO SMIs are off, the timer counts down twice before rebooting. - * Otherwise, the BIOS generally reboots when the SMI triggers. - */ - if (p->smi_res && - (inl(SMI_EN(p)) & (TCO_EN | GBL_SMI_EN)) != (TCO_EN | GBL_SMI_EN)) + /* For TCO v1 the timer counts down twice before rebooting */ + if (p->iTCO_version == 1) tmrval /= 2; /* from the specs: */ @@ -527,7 +521,7 @@ static int iTCO_wdt_probe(struct platform_device *pdev) * Disables TCO logic generating an SMI# */ val32 = inl(SMI_EN(p)); - val32 &= ~TCO_EN; /* Turn off SMI clearing watchdog */ + val32 &= 0xffffdfff; /* Turn off SMI clearing watchdog */ outl(val32, SMI_EN(p)); } diff --git a/drivers/watchdog/ixp4xx_wdt.c b/drivers/watchdog/ixp4xx_wdt.c index 2693ffb24ac7..31b03fa71341 100644 --- a/drivers/watchdog/ixp4xx_wdt.c +++ b/drivers/watchdog/ixp4xx_wdt.c @@ -119,7 +119,7 @@ static int ixp4xx_wdt_probe(struct platform_device *pdev) iwdt = devm_kzalloc(dev, sizeof(*iwdt), GFP_KERNEL); if (!iwdt) return -ENOMEM; - iwdt->base = dev->platform_data; + iwdt->base = (void __iomem *)dev->platform_data; /* * Retrieve rate from a fixed clock from the device tree if diff --git a/drivers/watchdog/omap_wdt.c b/drivers/watchdog/omap_wdt.c index 1616f93dfad7..74d785b2b478 100644 --- a/drivers/watchdog/omap_wdt.c +++ b/drivers/watchdog/omap_wdt.c @@ -268,8 +268,12 @@ static int omap_wdt_probe(struct platform_device *pdev) wdev->wdog.bootstatus = WDIOF_CARDRESET; } - if (!early_enable) + if (early_enable) { + omap_wdt_start(&wdev->wdog); + set_bit(WDOG_HW_RUNNING, &wdev->wdog.status); + } else { omap_wdt_disable(wdev); + } ret = watchdog_register_device(&wdev->wdog); if (ret) { diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c index ee9ff38929eb..9791c74aebd4 100644 --- a/drivers/watchdog/sbsa_gwdt.c +++ b/drivers/watchdog/sbsa_gwdt.c @@ -130,7 +130,7 @@ static u64 sbsa_gwdt_reg_read(struct sbsa_gwdt *gwdt) if (gwdt->version == 0) return readl(gwdt->control_base + SBSA_GWDT_WOR); else - return readq(gwdt->control_base + SBSA_GWDT_WOR); + return lo_hi_readq(gwdt->control_base + SBSA_GWDT_WOR); } static void sbsa_gwdt_reg_write(u64 val, struct sbsa_gwdt *gwdt) @@ -138,7 +138,7 @@ static void sbsa_gwdt_reg_write(u64 val, struct sbsa_gwdt *gwdt) if (gwdt->version == 0) writel((u32)val, gwdt->control_base + SBSA_GWDT_WOR); else - writeq(val, gwdt->control_base + SBSA_GWDT_WOR); + lo_hi_writeq(val, gwdt->control_base + SBSA_GWDT_WOR); } /* @@ -411,4 +411,3 @@ MODULE_AUTHOR("Suravee Suthikulpanit <[email protected]>"); MODULE_AUTHOR("Al Stone <[email protected]>"); MODULE_AUTHOR("Timur Tabi <[email protected]>"); MODULE_LICENSE("GPL v2"); -MODULE_ALIAS("platform:" DRV_NAME); diff --git a/fs/autofs/waitq.c b/fs/autofs/waitq.c index 16b5fca0626e..54c1f8b8b075 100644 --- a/fs/autofs/waitq.c +++ b/fs/autofs/waitq.c @@ -358,7 +358,7 @@ int autofs_wait(struct autofs_sb_info *sbi, qstr.len = strlen(p); offset = p - name; } - qstr.hash = full_name_hash(dentry, name, qstr.len); + qstr.hash = full_name_hash(dentry, qstr.name, qstr.len); if (mutex_lock_interruptible(&sbi->wq_mutex)) { kfree(name); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 319596df5dc6..f55f9f94b1a4 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -1121,6 +1121,9 @@ int fuse_init_fs_context_submount(struct fs_context *fsc); */ void fuse_conn_destroy(struct fuse_mount *fm); +/* Drop the connection and free the fuse mount */ +void fuse_mount_destroy(struct fuse_mount *fm); + /** * Add connection to control filesystem */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 36cd03114b6d..12d49a1914e8 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -457,14 +457,6 @@ static void fuse_send_destroy(struct fuse_mount *fm) } } -static void fuse_put_super(struct super_block *sb) -{ - struct fuse_mount *fm = get_fuse_mount_super(sb); - - fuse_conn_put(fm->fc); - kfree(fm); -} - static void convert_fuse_statfs(struct kstatfs *stbuf, struct fuse_kstatfs *attr) { stbuf->f_type = FUSE_SUPER_MAGIC; @@ -1003,7 +995,6 @@ static const struct super_operations fuse_super_operations = { .evict_inode = fuse_evict_inode, .write_inode = fuse_write_inode, .drop_inode = generic_delete_inode, - .put_super = fuse_put_super, .umount_begin = fuse_umount_begin, .statfs = fuse_statfs, .sync_fs = fuse_sync_fs, @@ -1424,20 +1415,17 @@ static int fuse_get_tree_submount(struct fs_context *fsc) if (!fm) return -ENOMEM; + fm->fc = fuse_conn_get(fc); fsc->s_fs_info = fm; sb = sget_fc(fsc, NULL, set_anon_super_fc); - if (IS_ERR(sb)) { - kfree(fm); + if (fsc->s_fs_info) + fuse_mount_destroy(fm); + if (IS_ERR(sb)) return PTR_ERR(sb); - } - fm->fc = fuse_conn_get(fc); /* Initialize superblock, making @mp_fi its root */ err = fuse_fill_super_submount(sb, mp_fi); if (err) { - fuse_conn_put(fc); - kfree(fm); - sb->s_fs_info = NULL; deactivate_locked_super(sb); return err; } @@ -1569,8 +1557,6 @@ static int fuse_fill_super(struct super_block *sb, struct fs_context *fsc) { struct fuse_fs_context *ctx = fsc->fs_private; int err; - struct fuse_conn *fc; - struct fuse_mount *fm; if (!ctx->file || !ctx->rootmode_present || !ctx->user_id_present || !ctx->group_id_present) @@ -1580,42 +1566,18 @@ static int fuse_fill_super(struct super_block *sb, struct fs_context *fsc) * Require mount to happen from the same user namespace which * opened /dev/fuse to prevent potential attacks. */ - err = -EINVAL; if ((ctx->file->f_op != &fuse_dev_operations) || (ctx->file->f_cred->user_ns != sb->s_user_ns)) - goto err; + return -EINVAL; ctx->fudptr = &ctx->file->private_data; - fc = kmalloc(sizeof(*fc), GFP_KERNEL); - err = -ENOMEM; - if (!fc) - goto err; - - fm = kzalloc(sizeof(*fm), GFP_KERNEL); - if (!fm) { - kfree(fc); - goto err; - } - - fuse_conn_init(fc, fm, sb->s_user_ns, &fuse_dev_fiq_ops, NULL); - fc->release = fuse_free_conn; - - sb->s_fs_info = fm; - err = fuse_fill_super_common(sb, ctx); if (err) - goto err_put_conn; + return err; /* file->private_data shall be visible on all CPUs after this */ smp_mb(); fuse_send_init(get_fuse_mount_super(sb)); return 0; - - err_put_conn: - fuse_conn_put(fc); - kfree(fm); - sb->s_fs_info = NULL; - err: - return err; } /* @@ -1637,22 +1599,40 @@ static int fuse_get_tree(struct fs_context *fsc) { struct fuse_fs_context *ctx = fsc->fs_private; struct fuse_dev *fud; + struct fuse_conn *fc; + struct fuse_mount *fm; struct super_block *sb; int err; + fc = kmalloc(sizeof(*fc), GFP_KERNEL); + if (!fc) + return -ENOMEM; + + fm = kzalloc(sizeof(*fm), GFP_KERNEL); + if (!fm) { + kfree(fc); + return -ENOMEM; + } + + fuse_conn_init(fc, fm, fsc->user_ns, &fuse_dev_fiq_ops, NULL); + fc->release = fuse_free_conn; + + fsc->s_fs_info = fm; + if (ctx->fd_present) ctx->file = fget(ctx->fd); if (IS_ENABLED(CONFIG_BLOCK) && ctx->is_bdev) { err = get_tree_bdev(fsc, fuse_fill_super); - goto out_fput; + goto out; } /* * While block dev mount can be initialized with a dummy device fd * (found by device name), normal fuse mounts can't */ + err = -EINVAL; if (!ctx->file) - return -EINVAL; + goto out; /* * Allow creating a fuse mount with an already initialized fuse @@ -1668,7 +1648,9 @@ static int fuse_get_tree(struct fs_context *fsc) } else { err = get_tree_nodev(fsc, fuse_fill_super); } -out_fput: +out: + if (fsc->s_fs_info) + fuse_mount_destroy(fm); if (ctx->file) fput(ctx->file); return err; @@ -1747,17 +1729,25 @@ static void fuse_sb_destroy(struct super_block *sb) struct fuse_mount *fm = get_fuse_mount_super(sb); bool last; - if (fm) { + if (sb->s_root) { last = fuse_mount_remove(fm); if (last) fuse_conn_destroy(fm); } } +void fuse_mount_destroy(struct fuse_mount *fm) +{ + fuse_conn_put(fm->fc); + kfree(fm); +} +EXPORT_SYMBOL(fuse_mount_destroy); + static void fuse_kill_sb_anon(struct super_block *sb) { fuse_sb_destroy(sb); kill_anon_super(sb); + fuse_mount_destroy(get_fuse_mount_super(sb)); } static struct file_system_type fuse_fs_type = { @@ -1775,6 +1765,7 @@ static void fuse_kill_sb_blk(struct super_block *sb) { fuse_sb_destroy(sb); kill_block_super(sb); + fuse_mount_destroy(get_fuse_mount_super(sb)); } static struct file_system_type fuseblk_fs_type = { diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 0ad89c6629d7..94fc874f5de7 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -1394,12 +1394,13 @@ static void virtio_kill_sb(struct super_block *sb) bool last; /* If mount failed, we can still be called without any fc */ - if (fm) { + if (sb->s_root) { last = fuse_mount_remove(fm); if (last) virtio_fs_conn_destroy(fm); } kill_anon_super(sb); + fuse_mount_destroy(fm); } static int virtio_fs_test_super(struct super_block *sb, @@ -1455,19 +1456,14 @@ static int virtio_fs_get_tree(struct fs_context *fsc) fsc->s_fs_info = fm; sb = sget_fc(fsc, virtio_fs_test_super, set_anon_super_fc); - if (fsc->s_fs_info) { - fuse_conn_put(fc); - kfree(fm); - } + if (fsc->s_fs_info) + fuse_mount_destroy(fm); if (IS_ERR(sb)) return PTR_ERR(sb); if (!sb->s_root) { err = virtio_fs_fill_super(sb, fsc); if (err) { - fuse_conn_put(fc); - kfree(fm); - sb->s_fs_info = NULL; deactivate_locked_super(sb); return err; } diff --git a/fs/io-wq.c b/fs/io-wq.c index 5bf8aa81715e..422a7ed6a9bd 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -253,7 +253,7 @@ static bool io_wqe_create_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) pr_warn_once("io-wq is not configured for unbound workers"); raw_spin_lock(&wqe->lock); - if (acct->nr_workers == acct->max_workers) { + if (acct->nr_workers >= acct->max_workers) { raw_spin_unlock(&wqe->lock); return true; } @@ -1291,15 +1291,18 @@ int io_wq_max_workers(struct io_wq *wq, int *new_count) rcu_read_lock(); for_each_node(node) { + struct io_wqe *wqe = wq->wqes[node]; struct io_wqe_acct *acct; + raw_spin_lock(&wqe->lock); for (i = 0; i < IO_WQ_ACCT_NR; i++) { - acct = &wq->wqes[node]->acct[i]; + acct = &wqe->acct[i]; prev = max_t(int, acct->max_workers, prev); if (new_count[i]) acct->max_workers = new_count[i]; new_count[i] = prev; } + raw_spin_unlock(&wqe->lock); } rcu_read_unlock(); return 0; diff --git a/fs/io_uring.c b/fs/io_uring.c index e68d27829bb2..bc18af5e0a93 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -456,6 +456,8 @@ struct io_ring_ctx { struct work_struct exit_work; struct list_head tctx_list; struct completion ref_comp; + u32 iowq_limits[2]; + bool iowq_limits_set; }; }; @@ -1368,11 +1370,6 @@ static void io_req_track_inflight(struct io_kiocb *req) } } -static inline void io_unprep_linked_timeout(struct io_kiocb *req) -{ - req->flags &= ~REQ_F_LINK_TIMEOUT; -} - static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req) { if (WARN_ON_ONCE(!req->link)) @@ -6983,7 +6980,7 @@ issue_sqe: switch (io_arm_poll_handler(req)) { case IO_APOLL_READY: if (linked_timeout) - io_unprep_linked_timeout(req); + io_queue_linked_timeout(linked_timeout); goto issue_sqe; case IO_APOLL_ABORTED: /* @@ -9638,7 +9635,16 @@ static int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) ret = io_uring_alloc_task_context(current, ctx); if (unlikely(ret)) return ret; + tctx = current->io_uring; + if (ctx->iowq_limits_set) { + unsigned int limits[2] = { ctx->iowq_limits[0], + ctx->iowq_limits[1], }; + + ret = io_wq_max_workers(tctx->io_wq, limits); + if (ret) + return ret; + } } if (!xa_load(&tctx->xa, (unsigned long)ctx)) { node = kmalloc(sizeof(*node), GFP_KERNEL); @@ -10643,7 +10649,9 @@ static int io_unregister_iowq_aff(struct io_ring_ctx *ctx) static int io_register_iowq_max_workers(struct io_ring_ctx *ctx, void __user *arg) + __must_hold(&ctx->uring_lock) { + struct io_tctx_node *node; struct io_uring_task *tctx = NULL; struct io_sq_data *sqd = NULL; __u32 new_count[2]; @@ -10674,13 +10682,19 @@ static int io_register_iowq_max_workers(struct io_ring_ctx *ctx, tctx = current->io_uring; } - ret = -EINVAL; - if (!tctx || !tctx->io_wq) - goto err; + BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits)); - ret = io_wq_max_workers(tctx->io_wq, new_count); - if (ret) - goto err; + memcpy(ctx->iowq_limits, new_count, sizeof(new_count)); + ctx->iowq_limits_set = true; + + ret = -EINVAL; + if (tctx && tctx->io_wq) { + ret = io_wq_max_workers(tctx->io_wq, new_count); + if (ret) + goto err; + } else { + memset(new_count, 0, sizeof(new_count)); + } if (sqd) { mutex_unlock(&sqd->lock); @@ -10690,6 +10704,22 @@ static int io_register_iowq_max_workers(struct io_ring_ctx *ctx, if (copy_to_user(arg, new_count, sizeof(new_count))) return -EFAULT; + /* that's it for SQPOLL, only the SQPOLL task creates requests */ + if (sqd) + return 0; + + /* now propagate the restriction to all registered users */ + list_for_each_entry(node, &ctx->tctx_list, ctx_node) { + struct io_uring_task *tctx = node->task->io_uring; + + if (WARN_ON_ONCE(!tctx->io_wq)) + continue; + + for (i = 0; i < ARRAY_SIZE(new_count); i++) + new_count[i] = ctx->iowq_limits[i]; + /* ignore errors, it always returns zero anyway */ + (void)io_wq_max_workers(tctx->io_wq, new_count); + } return 0; err: if (sqd) { diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c index 71c989f1568d..30a92ddc1817 100644 --- a/fs/ksmbd/auth.c +++ b/fs/ksmbd/auth.c @@ -298,8 +298,8 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, int blob_len, struct ksmbd_session *sess) { char *domain_name; - unsigned int lm_off, nt_off; - unsigned short nt_len; + unsigned int nt_off, dn_off; + unsigned short nt_len, dn_len; int ret; if (blob_len < sizeof(struct authenticate_message)) { @@ -314,15 +314,17 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, return -EINVAL; } - lm_off = le32_to_cpu(authblob->LmChallengeResponse.BufferOffset); nt_off = le32_to_cpu(authblob->NtChallengeResponse.BufferOffset); nt_len = le16_to_cpu(authblob->NtChallengeResponse.Length); + dn_off = le32_to_cpu(authblob->DomainName.BufferOffset); + dn_len = le16_to_cpu(authblob->DomainName.Length); + + if (blob_len < (u64)dn_off + dn_len || blob_len < (u64)nt_off + nt_len) + return -EINVAL; /* TODO : use domain name that imported from configuration file */ - domain_name = smb_strndup_from_utf16((const char *)authblob + - le32_to_cpu(authblob->DomainName.BufferOffset), - le16_to_cpu(authblob->DomainName.Length), true, - sess->conn->local_nls); + domain_name = smb_strndup_from_utf16((const char *)authblob + dn_off, + dn_len, true, sess->conn->local_nls); if (IS_ERR(domain_name)) return PTR_ERR(domain_name); diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index 48b18b4ec117..b57a0d8a392f 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -61,6 +61,8 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) conn->local_nls = load_nls_default(); atomic_set(&conn->req_running, 0); atomic_set(&conn->r_count, 0); + conn->total_credits = 1; + init_waitqueue_head(&conn->req_running_q); INIT_LIST_HEAD(&conn->conns_list); INIT_LIST_HEAD(&conn->sessions); diff --git a/fs/ksmbd/ksmbd_netlink.h b/fs/ksmbd/ksmbd_netlink.h index 2fbe2bc1e093..c6718a05d347 100644 --- a/fs/ksmbd/ksmbd_netlink.h +++ b/fs/ksmbd/ksmbd_netlink.h @@ -211,6 +211,7 @@ struct ksmbd_tree_disconnect_request { */ struct ksmbd_logout_request { __s8 account[KSMBD_REQ_MAX_ACCOUNT_NAME_SZ]; /* user account name */ + __u32 account_flags; }; /* @@ -317,6 +318,7 @@ enum KSMBD_TREE_CONN_STATUS { #define KSMBD_USER_FLAG_BAD_UID BIT(2) #define KSMBD_USER_FLAG_BAD_USER BIT(3) #define KSMBD_USER_FLAG_GUEST_ACCOUNT BIT(4) +#define KSMBD_USER_FLAG_DELAY_SESSION BIT(5) /* * Share config flags. diff --git a/fs/ksmbd/mgmt/user_config.c b/fs/ksmbd/mgmt/user_config.c index d21629ae5c89..1019d3677d55 100644 --- a/fs/ksmbd/mgmt/user_config.c +++ b/fs/ksmbd/mgmt/user_config.c @@ -55,7 +55,7 @@ struct ksmbd_user *ksmbd_alloc_user(struct ksmbd_login_response *resp) void ksmbd_free_user(struct ksmbd_user *user) { - ksmbd_ipc_logout_request(user->name); + ksmbd_ipc_logout_request(user->name, user->flags); kfree(user->name); kfree(user->passkey); kfree(user); diff --git a/fs/ksmbd/mgmt/user_config.h b/fs/ksmbd/mgmt/user_config.h index b2bb074a0150..aff80b029579 100644 --- a/fs/ksmbd/mgmt/user_config.h +++ b/fs/ksmbd/mgmt/user_config.h @@ -18,6 +18,7 @@ struct ksmbd_user { size_t passkey_sz; char *passkey; + unsigned int failed_login_count; }; static inline bool user_guest(struct ksmbd_user *user) diff --git a/fs/ksmbd/smb2misc.c b/fs/ksmbd/smb2misc.c index 9edd9c161b27..030ca57c3784 100644 --- a/fs/ksmbd/smb2misc.c +++ b/fs/ksmbd/smb2misc.c @@ -284,11 +284,13 @@ static inline int smb2_ioctl_resp_len(struct smb2_ioctl_req *h) le32_to_cpu(h->MaxOutputResponse); } -static int smb2_validate_credit_charge(struct smb2_hdr *hdr) +static int smb2_validate_credit_charge(struct ksmbd_conn *conn, + struct smb2_hdr *hdr) { - int req_len = 0, expect_resp_len = 0, calc_credit_num, max_len; - int credit_charge = le16_to_cpu(hdr->CreditCharge); + unsigned int req_len = 0, expect_resp_len = 0, calc_credit_num, max_len; + unsigned short credit_charge = le16_to_cpu(hdr->CreditCharge); void *__hdr = hdr; + int ret; switch (hdr->Command) { case SMB2_QUERY_INFO: @@ -310,21 +312,37 @@ static int smb2_validate_credit_charge(struct smb2_hdr *hdr) req_len = smb2_ioctl_req_len(__hdr); expect_resp_len = smb2_ioctl_resp_len(__hdr); break; - default: + case SMB2_CANCEL: return 0; + default: + req_len = 1; + break; } - credit_charge = max(1, credit_charge); - max_len = max(req_len, expect_resp_len); + credit_charge = max_t(unsigned short, credit_charge, 1); + max_len = max_t(unsigned int, req_len, expect_resp_len); calc_credit_num = DIV_ROUND_UP(max_len, SMB2_MAX_BUFFER_SIZE); if (credit_charge < calc_credit_num) { - pr_err("Insufficient credit charge, given: %d, needed: %d\n", - credit_charge, calc_credit_num); + ksmbd_debug(SMB, "Insufficient credit charge, given: %d, needed: %d\n", + credit_charge, calc_credit_num); + return 1; + } else if (credit_charge > conn->max_credits) { + ksmbd_debug(SMB, "Too large credit charge: %d\n", credit_charge); return 1; } - return 0; + spin_lock(&conn->credits_lock); + if (credit_charge <= conn->total_credits) { + conn->total_credits -= credit_charge; + ret = 0; + } else { + ksmbd_debug(SMB, "Insufficient credits granted, given: %u, granted: %u\n", + credit_charge, conn->total_credits); + ret = 1; + } + spin_unlock(&conn->credits_lock); + return ret; } int ksmbd_smb2_check_message(struct ksmbd_work *work) @@ -382,26 +400,20 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) } } - if ((work->conn->vals->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU) && - smb2_validate_credit_charge(hdr)) { - work->conn->ops->set_rsp_status(work, STATUS_INVALID_PARAMETER); - return 1; - } - if (smb2_calc_size(hdr, &clc_len)) return 1; if (len != clc_len) { /* client can return one byte more due to implied bcc[0] */ if (clc_len == len + 1) - return 0; + goto validate_credit; /* * Some windows servers (win2016) will pad also the final * PDU in a compound to 8 bytes. */ if (ALIGN(clc_len, 8) == len) - return 0; + goto validate_credit; /* * windows client also pad up to 8 bytes when compounding. @@ -414,7 +426,7 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) "cli req padded more than expected. Length %d not %d for cmd:%d mid:%llu\n", len, clc_len, command, le64_to_cpu(hdr->MessageId)); - return 0; + goto validate_credit; } ksmbd_debug(SMB, @@ -425,6 +437,13 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) return 1; } +validate_credit: + if ((work->conn->vals->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU) && + smb2_validate_credit_charge(work->conn, hdr)) { + work->conn->ops->set_rsp_status(work, STATUS_INVALID_PARAMETER); + return 1; + } + return 0; } diff --git a/fs/ksmbd/smb2ops.c b/fs/ksmbd/smb2ops.c index b06456eb587b..fb6a65d23139 100644 --- a/fs/ksmbd/smb2ops.c +++ b/fs/ksmbd/smb2ops.c @@ -284,6 +284,7 @@ int init_smb3_11_server(struct ksmbd_conn *conn) void init_smb2_max_read_size(unsigned int sz) { + sz = clamp_val(sz, SMB3_MIN_IOSIZE, SMB3_MAX_IOSIZE); smb21_server_values.max_read_size = sz; smb30_server_values.max_read_size = sz; smb302_server_values.max_read_size = sz; @@ -292,6 +293,7 @@ void init_smb2_max_read_size(unsigned int sz) void init_smb2_max_write_size(unsigned int sz) { + sz = clamp_val(sz, SMB3_MIN_IOSIZE, SMB3_MAX_IOSIZE); smb21_server_values.max_write_size = sz; smb30_server_values.max_write_size = sz; smb302_server_values.max_write_size = sz; @@ -300,6 +302,7 @@ void init_smb2_max_write_size(unsigned int sz) void init_smb2_max_trans_size(unsigned int sz) { + sz = clamp_val(sz, SMB3_MIN_IOSIZE, SMB3_MAX_IOSIZE); smb21_server_values.max_trans_size = sz; smb30_server_values.max_trans_size = sz; smb302_server_values.max_trans_size = sz; diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 005aa93a49d6..7e448df3f847 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -292,22 +292,6 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) return 0; } -static int smb2_consume_credit_charge(struct ksmbd_work *work, - unsigned short credit_charge) -{ - struct ksmbd_conn *conn = work->conn; - unsigned int rsp_credits = 1; - - if (!conn->total_credits) - return 0; - - if (credit_charge > 0) - rsp_credits = credit_charge; - - conn->total_credits -= rsp_credits; - return rsp_credits; -} - /** * smb2_set_rsp_credits() - set number of credits in response buffer * @work: smb work containing smb response buffer @@ -317,49 +301,43 @@ int smb2_set_rsp_credits(struct ksmbd_work *work) struct smb2_hdr *req_hdr = ksmbd_req_buf_next(work); struct smb2_hdr *hdr = ksmbd_resp_buf_next(work); struct ksmbd_conn *conn = work->conn; - unsigned short credits_requested = le16_to_cpu(req_hdr->CreditRequest); - unsigned short credit_charge = 1, credits_granted = 0; - unsigned short aux_max, aux_credits, min_credits; - int rsp_credit_charge; + unsigned short credits_requested; + unsigned short credit_charge, credits_granted = 0; + unsigned short aux_max, aux_credits; - if (hdr->Command == SMB2_CANCEL) - goto out; + if (work->send_no_response) + return 0; - /* get default minimum credits by shifting maximum credits by 4 */ - min_credits = conn->max_credits >> 4; + hdr->CreditCharge = req_hdr->CreditCharge; - if (conn->total_credits >= conn->max_credits) { + if (conn->total_credits > conn->max_credits) { + hdr->CreditRequest = 0; pr_err("Total credits overflow: %d\n", conn->total_credits); - conn->total_credits = min_credits; - } - - rsp_credit_charge = - smb2_consume_credit_charge(work, le16_to_cpu(req_hdr->CreditCharge)); - if (rsp_credit_charge < 0) return -EINVAL; + } - hdr->CreditCharge = cpu_to_le16(rsp_credit_charge); + credit_charge = max_t(unsigned short, + le16_to_cpu(req_hdr->CreditCharge), 1); + credits_requested = max_t(unsigned short, + le16_to_cpu(req_hdr->CreditRequest), 1); - if (credits_requested > 0) { - aux_credits = credits_requested - 1; - aux_max = 32; - if (hdr->Command == SMB2_NEGOTIATE) - aux_max = 0; - aux_credits = (aux_credits < aux_max) ? aux_credits : aux_max; - credits_granted = aux_credits + credit_charge; + /* according to smb2.credits smbtorture, Windows server + * 2016 or later grant up to 8192 credits at once. + * + * TODO: Need to adjuct CreditRequest value according to + * current cpu load + */ + aux_credits = credits_requested - 1; + if (hdr->Command == SMB2_NEGOTIATE) + aux_max = 0; + else + aux_max = conn->max_credits - credit_charge; + aux_credits = min_t(unsigned short, aux_credits, aux_max); + credits_granted = credit_charge + aux_credits; - /* if credits granted per client is getting bigger than default - * minimum credits then we should wrap it up within the limits. - */ - if ((conn->total_credits + credits_granted) > min_credits) - credits_granted = min_credits - conn->total_credits; - /* - * TODO: Need to adjuct CreditRequest value according to - * current cpu load - */ - } else if (conn->total_credits == 0) { - credits_granted = 1; - } + if (conn->max_credits - conn->total_credits < credits_granted) + credits_granted = conn->max_credits - + conn->total_credits; conn->total_credits += credits_granted; work->credits_granted += credits_granted; @@ -368,7 +346,6 @@ int smb2_set_rsp_credits(struct ksmbd_work *work) /* Update CreditRequest in last request */ hdr->CreditRequest = cpu_to_le16(work->credits_granted); } -out: ksmbd_debug(SMB, "credits: requested[%d] granted[%d] total_granted[%d]\n", credits_requested, credits_granted, @@ -472,6 +449,12 @@ bool is_chained_smb2_message(struct ksmbd_work *work) return false; } + if ((u64)get_rfc1002_len(work->response_buf) + MAX_CIFS_SMALL_BUFFER_SIZE > + work->response_sz) { + pr_err("next response offset exceeds response buffer size\n"); + return false; + } + ksmbd_debug(SMB, "got SMB2 chained command\n"); init_chained_smb2_rsp(work); return true; @@ -541,7 +524,7 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) { struct smb2_hdr *hdr = work->request_buf; size_t small_sz = MAX_CIFS_SMALL_BUFFER_SIZE; - size_t large_sz = work->conn->vals->max_trans_size + MAX_SMB2_HDR_SIZE; + size_t large_sz = small_sz + work->conn->vals->max_trans_size; size_t sz = small_sz; int cmd = le16_to_cpu(hdr->Command); @@ -1274,19 +1257,13 @@ static int generate_preauth_hash(struct ksmbd_work *work) return 0; } -static int decode_negotiation_token(struct ksmbd_work *work, - struct negotiate_message *negblob) +static int decode_negotiation_token(struct ksmbd_conn *conn, + struct negotiate_message *negblob, + size_t sz) { - struct ksmbd_conn *conn = work->conn; - struct smb2_sess_setup_req *req; - int sz; - if (!conn->use_spnego) return -EINVAL; - req = work->request_buf; - sz = le16_to_cpu(req->SecurityBufferLength); - if (ksmbd_decode_negTokenInit((char *)negblob, sz, conn)) { if (ksmbd_decode_negTokenTarg((char *)negblob, sz, conn)) { conn->auth_mechs |= KSMBD_AUTH_NTLMSSP; @@ -1298,9 +1275,9 @@ static int decode_negotiation_token(struct ksmbd_work *work, } static int ntlm_negotiate(struct ksmbd_work *work, - struct negotiate_message *negblob) + struct negotiate_message *negblob, + size_t negblob_len) { - struct smb2_sess_setup_req *req = work->request_buf; struct smb2_sess_setup_rsp *rsp = work->response_buf; struct challenge_message *chgblob; unsigned char *spnego_blob = NULL; @@ -1309,8 +1286,7 @@ static int ntlm_negotiate(struct ksmbd_work *work, int sz, rc; ksmbd_debug(SMB, "negotiate phase\n"); - sz = le16_to_cpu(req->SecurityBufferLength); - rc = ksmbd_decode_ntlmssp_neg_blob(negblob, sz, work->sess); + rc = ksmbd_decode_ntlmssp_neg_blob(negblob, negblob_len, work->sess); if (rc) return rc; @@ -1378,12 +1354,23 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn, struct authenticate_message *authblob; struct ksmbd_user *user; char *name; - int sz; + unsigned int auth_msg_len, name_off, name_len, secbuf_len; + secbuf_len = le16_to_cpu(req->SecurityBufferLength); + if (secbuf_len < sizeof(struct authenticate_message)) { + ksmbd_debug(SMB, "blob len %d too small\n", secbuf_len); + return NULL; + } authblob = user_authblob(conn, req); - sz = le32_to_cpu(authblob->UserName.BufferOffset); - name = smb_strndup_from_utf16((const char *)authblob + sz, - le16_to_cpu(authblob->UserName.Length), + name_off = le32_to_cpu(authblob->UserName.BufferOffset); + name_len = le16_to_cpu(authblob->UserName.Length); + auth_msg_len = le16_to_cpu(req->SecurityBufferOffset) + secbuf_len; + + if (auth_msg_len < (u64)name_off + name_len) + return NULL; + + name = smb_strndup_from_utf16((const char *)authblob + name_off, + name_len, true, conn->local_nls); if (IS_ERR(name)) { @@ -1629,6 +1616,7 @@ int smb2_sess_setup(struct ksmbd_work *work) struct smb2_sess_setup_rsp *rsp = work->response_buf; struct ksmbd_session *sess; struct negotiate_message *negblob; + unsigned int negblob_len, negblob_off; int rc = 0; ksmbd_debug(SMB, "Received request for session setup\n"); @@ -1709,10 +1697,16 @@ int smb2_sess_setup(struct ksmbd_work *work) if (sess->state == SMB2_SESSION_EXPIRED) sess->state = SMB2_SESSION_IN_PROGRESS; + negblob_off = le16_to_cpu(req->SecurityBufferOffset); + negblob_len = le16_to_cpu(req->SecurityBufferLength); + if (negblob_off < (offsetof(struct smb2_sess_setup_req, Buffer) - 4) || + negblob_len < offsetof(struct negotiate_message, NegotiateFlags)) + return -EINVAL; + negblob = (struct negotiate_message *)((char *)&req->hdr.ProtocolId + - le16_to_cpu(req->SecurityBufferOffset)); + negblob_off); - if (decode_negotiation_token(work, negblob) == 0) { + if (decode_negotiation_token(conn, negblob, negblob_len) == 0) { if (conn->mechToken) negblob = (struct negotiate_message *)conn->mechToken; } @@ -1736,7 +1730,7 @@ int smb2_sess_setup(struct ksmbd_work *work) sess->Preauth_HashValue = NULL; } else if (conn->preferred_auth_mech == KSMBD_AUTH_NTLMSSP) { if (negblob->MessageType == NtLmNegotiate) { - rc = ntlm_negotiate(work, negblob); + rc = ntlm_negotiate(work, negblob, negblob_len); if (rc) goto out_err; rsp->hdr.Status = @@ -1796,9 +1790,30 @@ out_err: conn->mechToken = NULL; } - if (rc < 0 && sess) { - ksmbd_session_destroy(sess); - work->sess = NULL; + if (rc < 0) { + /* + * SecurityBufferOffset should be set to zero + * in session setup error response. + */ + rsp->SecurityBufferOffset = 0; + + if (sess) { + bool try_delay = false; + + /* + * To avoid dictionary attacks (repeated session setups rapidly sent) to + * connect to server, ksmbd make a delay of a 5 seconds on session setup + * failure to make it harder to send enough random connection requests + * to break into a server. + */ + if (sess->user && sess->user->flags & KSMBD_USER_FLAG_DELAY_SESSION) + try_delay = true; + + ksmbd_session_destroy(sess); + work->sess = NULL; + if (try_delay) + ssleep(5); + } } return rc; @@ -3779,6 +3794,24 @@ static int verify_info_level(int info_level) return 0; } +static int smb2_calc_max_out_buf_len(struct ksmbd_work *work, + unsigned short hdr2_len, + unsigned int out_buf_len) +{ + int free_len; + + if (out_buf_len > work->conn->vals->max_trans_size) + return -EINVAL; + + free_len = (int)(work->response_sz - + (get_rfc1002_len(work->response_buf) + 4)) - + hdr2_len; + if (free_len < 0) + return -EINVAL; + + return min_t(int, out_buf_len, free_len); +} + int smb2_query_dir(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; @@ -3855,9 +3888,13 @@ int smb2_query_dir(struct ksmbd_work *work) memset(&d_info, 0, sizeof(struct ksmbd_dir_info)); d_info.wptr = (char *)rsp->Buffer; d_info.rptr = (char *)rsp->Buffer; - d_info.out_buf_len = (work->response_sz - (get_rfc1002_len(rsp_org) + 4)); - d_info.out_buf_len = min_t(int, d_info.out_buf_len, le32_to_cpu(req->OutputBufferLength)) - - sizeof(struct smb2_query_directory_rsp); + d_info.out_buf_len = + smb2_calc_max_out_buf_len(work, 8, + le32_to_cpu(req->OutputBufferLength)); + if (d_info.out_buf_len < 0) { + rc = -EINVAL; + goto err_out; + } d_info.flags = srch_flag; /* @@ -4091,12 +4128,11 @@ static int smb2_get_ea(struct ksmbd_work *work, struct ksmbd_file *fp, le32_to_cpu(req->Flags)); } - buf_free_len = work->response_sz - - (get_rfc1002_len(rsp_org) + 4) - - sizeof(struct smb2_query_info_rsp); - - if (le32_to_cpu(req->OutputBufferLength) < buf_free_len) - buf_free_len = le32_to_cpu(req->OutputBufferLength); + buf_free_len = + smb2_calc_max_out_buf_len(work, 8, + le32_to_cpu(req->OutputBufferLength)); + if (buf_free_len < 0) + return -EINVAL; rc = ksmbd_vfs_listxattr(path->dentry, &xattr_list); if (rc < 0) { @@ -4407,6 +4443,8 @@ static void get_file_stream_info(struct ksmbd_work *work, struct path *path = &fp->filp->f_path; ssize_t xattr_list_len; int nbytes = 0, streamlen, stream_name_len, next, idx = 0; + int buf_free_len; + struct smb2_query_info_req *req = ksmbd_req_buf_next(work); generic_fillattr(file_mnt_user_ns(fp->filp), file_inode(fp->filp), &stat); @@ -4420,6 +4458,12 @@ static void get_file_stream_info(struct ksmbd_work *work, goto out; } + buf_free_len = + smb2_calc_max_out_buf_len(work, 8, + le32_to_cpu(req->OutputBufferLength)); + if (buf_free_len < 0) + goto out; + while (idx < xattr_list_len) { stream_name = xattr_list + idx; streamlen = strlen(stream_name); @@ -4444,6 +4488,10 @@ static void get_file_stream_info(struct ksmbd_work *work, streamlen = snprintf(stream_buf, streamlen + 1, ":%s", &stream_name[XATTR_NAME_STREAM_LEN]); + next = sizeof(struct smb2_file_stream_info) + streamlen * 2; + if (next > buf_free_len) + break; + file_info = (struct smb2_file_stream_info *)&rsp->Buffer[nbytes]; streamlen = smbConvertToUTF16((__le16 *)file_info->StreamName, stream_buf, streamlen, @@ -4454,12 +4502,13 @@ static void get_file_stream_info(struct ksmbd_work *work, file_info->StreamSize = cpu_to_le64(stream_name_len); file_info->StreamAllocationSize = cpu_to_le64(stream_name_len); - next = sizeof(struct smb2_file_stream_info) + streamlen; nbytes += next; + buf_free_len -= next; file_info->NextEntryOffset = cpu_to_le32(next); } - if (!S_ISDIR(stat.mode)) { + if (!S_ISDIR(stat.mode) && + buf_free_len >= sizeof(struct smb2_file_stream_info) + 7 * 2) { file_info = (struct smb2_file_stream_info *) &rsp->Buffer[nbytes]; streamlen = smbConvertToUTF16((__le16 *)file_info->StreamName, @@ -6220,8 +6269,7 @@ static noinline int smb2_write_pipe(struct ksmbd_work *work) (offsetof(struct smb2_write_req, Buffer) - 4)) { data_buf = (char *)&req->Buffer[0]; } else { - if ((le16_to_cpu(req->DataOffset) > get_rfc1002_len(req)) || - (le16_to_cpu(req->DataOffset) + length > get_rfc1002_len(req))) { + if ((u64)le16_to_cpu(req->DataOffset) + length > get_rfc1002_len(req)) { pr_err("invalid write data offset %u, smb_len %u\n", le16_to_cpu(req->DataOffset), get_rfc1002_len(req)); @@ -6379,8 +6427,7 @@ int smb2_write(struct ksmbd_work *work) (offsetof(struct smb2_write_req, Buffer) - 4)) { data_buf = (char *)&req->Buffer[0]; } else { - if ((le16_to_cpu(req->DataOffset) > get_rfc1002_len(req)) || - (le16_to_cpu(req->DataOffset) + length > get_rfc1002_len(req))) { + if ((u64)le16_to_cpu(req->DataOffset) + length > get_rfc1002_len(req)) { pr_err("invalid write data offset %u, smb_len %u\n", le16_to_cpu(req->DataOffset), get_rfc1002_len(req)); @@ -7023,24 +7070,26 @@ out2: return err; } -static int fsctl_copychunk(struct ksmbd_work *work, struct smb2_ioctl_req *req, +static int fsctl_copychunk(struct ksmbd_work *work, + struct copychunk_ioctl_req *ci_req, + unsigned int cnt_code, + unsigned int input_count, + unsigned long long volatile_id, + unsigned long long persistent_id, struct smb2_ioctl_rsp *rsp) { - struct copychunk_ioctl_req *ci_req; struct copychunk_ioctl_rsp *ci_rsp; struct ksmbd_file *src_fp = NULL, *dst_fp = NULL; struct srv_copychunk *chunks; unsigned int i, chunk_count, chunk_count_written = 0; unsigned int chunk_size_written = 0; loff_t total_size_written = 0; - int ret, cnt_code; + int ret = 0; - cnt_code = le32_to_cpu(req->CntCode); - ci_req = (struct copychunk_ioctl_req *)&req->Buffer[0]; ci_rsp = (struct copychunk_ioctl_rsp *)&rsp->Buffer[0]; - rsp->VolatileFileId = req->VolatileFileId; - rsp->PersistentFileId = req->PersistentFileId; + rsp->VolatileFileId = cpu_to_le64(volatile_id); + rsp->PersistentFileId = cpu_to_le64(persistent_id); ci_rsp->ChunksWritten = cpu_to_le32(ksmbd_server_side_copy_max_chunk_count()); ci_rsp->ChunkBytesWritten = @@ -7050,12 +7099,13 @@ static int fsctl_copychunk(struct ksmbd_work *work, struct smb2_ioctl_req *req, chunks = (struct srv_copychunk *)&ci_req->Chunks[0]; chunk_count = le32_to_cpu(ci_req->ChunkCount); + if (chunk_count == 0) + goto out; total_size_written = 0; /* verify the SRV_COPYCHUNK_COPY packet */ if (chunk_count > ksmbd_server_side_copy_max_chunk_count() || - le32_to_cpu(req->InputCount) < - offsetof(struct copychunk_ioctl_req, Chunks) + + input_count < offsetof(struct copychunk_ioctl_req, Chunks) + chunk_count * sizeof(struct srv_copychunk)) { rsp->hdr.Status = STATUS_INVALID_PARAMETER; return -EINVAL; @@ -7076,9 +7126,7 @@ static int fsctl_copychunk(struct ksmbd_work *work, struct smb2_ioctl_req *req, src_fp = ksmbd_lookup_foreign_fd(work, le64_to_cpu(ci_req->ResumeKey[0])); - dst_fp = ksmbd_lookup_fd_slow(work, - le64_to_cpu(req->VolatileFileId), - le64_to_cpu(req->PersistentFileId)); + dst_fp = ksmbd_lookup_fd_slow(work, volatile_id, persistent_id); ret = -EINVAL; if (!src_fp || src_fp->persistent_id != le64_to_cpu(ci_req->ResumeKey[1])) { @@ -7153,8 +7201,8 @@ static __be32 idev_ipv4_address(struct in_device *idev) } static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn, - struct smb2_ioctl_req *req, - struct smb2_ioctl_rsp *rsp) + struct smb2_ioctl_rsp *rsp, + unsigned int out_buf_len) { struct network_interface_info_ioctl_rsp *nii_rsp = NULL; int nbytes = 0; @@ -7166,6 +7214,12 @@ static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn, rtnl_lock(); for_each_netdev(&init_net, netdev) { + if (out_buf_len < + nbytes + sizeof(struct network_interface_info_ioctl_rsp)) { + rtnl_unlock(); + return -ENOSPC; + } + if (netdev->type == ARPHRD_LOOPBACK) continue; @@ -7245,11 +7299,6 @@ static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn, if (nii_rsp) nii_rsp->Next = 0; - if (!nbytes) { - rsp->hdr.Status = STATUS_BUFFER_TOO_SMALL; - return -EINVAL; - } - rsp->PersistentFileId = cpu_to_le64(SMB2_NO_FID); rsp->VolatileFileId = cpu_to_le64(SMB2_NO_FID); return nbytes; @@ -7257,11 +7306,16 @@ static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn, static int fsctl_validate_negotiate_info(struct ksmbd_conn *conn, struct validate_negotiate_info_req *neg_req, - struct validate_negotiate_info_rsp *neg_rsp) + struct validate_negotiate_info_rsp *neg_rsp, + unsigned int in_buf_len) { int ret = 0; int dialect; + if (in_buf_len < sizeof(struct validate_negotiate_info_req) + + le16_to_cpu(neg_req->DialectCount) * sizeof(__le16)) + return -EINVAL; + dialect = ksmbd_lookup_dialect_by_id(neg_req->Dialects, neg_req->DialectCount); if (dialect == BAD_PROT_ID || dialect != conn->dialect) { @@ -7295,7 +7349,7 @@ err_out: static int fsctl_query_allocated_ranges(struct ksmbd_work *work, u64 id, struct file_allocated_range_buffer *qar_req, struct file_allocated_range_buffer *qar_rsp, - int in_count, int *out_count) + unsigned int in_count, unsigned int *out_count) { struct ksmbd_file *fp; loff_t start, length; @@ -7322,7 +7376,8 @@ static int fsctl_query_allocated_ranges(struct ksmbd_work *work, u64 id, } static int fsctl_pipe_transceive(struct ksmbd_work *work, u64 id, - int out_buf_len, struct smb2_ioctl_req *req, + unsigned int out_buf_len, + struct smb2_ioctl_req *req, struct smb2_ioctl_rsp *rsp) { struct ksmbd_rpc_command *rpc_resp; @@ -7436,8 +7491,7 @@ int smb2_ioctl(struct ksmbd_work *work) { struct smb2_ioctl_req *req; struct smb2_ioctl_rsp *rsp, *rsp_org; - int cnt_code, nbytes = 0; - int out_buf_len; + unsigned int cnt_code, nbytes = 0, out_buf_len, in_buf_len; u64 id = KSMBD_NO_FID; struct ksmbd_conn *conn = work->conn; int ret = 0; @@ -7465,8 +7519,14 @@ int smb2_ioctl(struct ksmbd_work *work) } cnt_code = le32_to_cpu(req->CntCode); - out_buf_len = le32_to_cpu(req->MaxOutputResponse); - out_buf_len = min(KSMBD_IPC_MAX_PAYLOAD, out_buf_len); + ret = smb2_calc_max_out_buf_len(work, 48, + le32_to_cpu(req->MaxOutputResponse)); + if (ret < 0) { + rsp->hdr.Status = STATUS_INVALID_PARAMETER; + goto out; + } + out_buf_len = (unsigned int)ret; + in_buf_len = le32_to_cpu(req->InputCount); switch (cnt_code) { case FSCTL_DFS_GET_REFERRALS: @@ -7494,6 +7554,7 @@ int smb2_ioctl(struct ksmbd_work *work) break; } case FSCTL_PIPE_TRANSCEIVE: + out_buf_len = min_t(u32, KSMBD_IPC_MAX_PAYLOAD, out_buf_len); nbytes = fsctl_pipe_transceive(work, id, out_buf_len, req, rsp); break; case FSCTL_VALIDATE_NEGOTIATE_INFO: @@ -7502,9 +7563,16 @@ int smb2_ioctl(struct ksmbd_work *work) goto out; } + if (in_buf_len < sizeof(struct validate_negotiate_info_req)) + return -EINVAL; + + if (out_buf_len < sizeof(struct validate_negotiate_info_rsp)) + return -EINVAL; + ret = fsctl_validate_negotiate_info(conn, (struct validate_negotiate_info_req *)&req->Buffer[0], - (struct validate_negotiate_info_rsp *)&rsp->Buffer[0]); + (struct validate_negotiate_info_rsp *)&rsp->Buffer[0], + in_buf_len); if (ret < 0) goto out; @@ -7513,9 +7581,10 @@ int smb2_ioctl(struct ksmbd_work *work) rsp->VolatileFileId = cpu_to_le64(SMB2_NO_FID); break; case FSCTL_QUERY_NETWORK_INTERFACE_INFO: - nbytes = fsctl_query_iface_info_ioctl(conn, req, rsp); - if (nbytes < 0) + ret = fsctl_query_iface_info_ioctl(conn, rsp, out_buf_len); + if (ret < 0) goto out; + nbytes = ret; break; case FSCTL_REQUEST_RESUME_KEY: if (out_buf_len < sizeof(struct resume_key_ioctl_rsp)) { @@ -7540,15 +7609,33 @@ int smb2_ioctl(struct ksmbd_work *work) goto out; } + if (in_buf_len < sizeof(struct copychunk_ioctl_req)) { + ret = -EINVAL; + goto out; + } + if (out_buf_len < sizeof(struct copychunk_ioctl_rsp)) { ret = -EINVAL; goto out; } nbytes = sizeof(struct copychunk_ioctl_rsp); - fsctl_copychunk(work, req, rsp); + rsp->VolatileFileId = req->VolatileFileId; + rsp->PersistentFileId = req->PersistentFileId; + fsctl_copychunk(work, + (struct copychunk_ioctl_req *)&req->Buffer[0], + le32_to_cpu(req->CntCode), + le32_to_cpu(req->InputCount), + le64_to_cpu(req->VolatileFileId), + le64_to_cpu(req->PersistentFileId), + rsp); break; case FSCTL_SET_SPARSE: + if (in_buf_len < sizeof(struct file_sparse)) { + ret = -EINVAL; + goto out; + } + ret = fsctl_set_sparse(work, id, (struct file_sparse *)&req->Buffer[0]); if (ret < 0) @@ -7567,6 +7654,11 @@ int smb2_ioctl(struct ksmbd_work *work) goto out; } + if (in_buf_len < sizeof(struct file_zero_data_information)) { + ret = -EINVAL; + goto out; + } + zero_data = (struct file_zero_data_information *)&req->Buffer[0]; @@ -7586,6 +7678,11 @@ int smb2_ioctl(struct ksmbd_work *work) break; } case FSCTL_QUERY_ALLOCATED_RANGES: + if (in_buf_len < sizeof(struct file_allocated_range_buffer)) { + ret = -EINVAL; + goto out; + } + ret = fsctl_query_allocated_ranges(work, id, (struct file_allocated_range_buffer *)&req->Buffer[0], (struct file_allocated_range_buffer *)&rsp->Buffer[0], @@ -7626,6 +7723,11 @@ int smb2_ioctl(struct ksmbd_work *work) struct duplicate_extents_to_file *dup_ext; loff_t src_off, dst_off, length, cloned; + if (in_buf_len < sizeof(struct duplicate_extents_to_file)) { + ret = -EINVAL; + goto out; + } + dup_ext = (struct duplicate_extents_to_file *)&req->Buffer[0]; fp_in = ksmbd_lookup_fd_slow(work, dup_ext->VolatileFileHandle, @@ -7696,6 +7798,8 @@ out: rsp->hdr.Status = STATUS_OBJECT_NAME_NOT_FOUND; else if (ret == -EOPNOTSUPP) rsp->hdr.Status = STATUS_NOT_SUPPORTED; + else if (ret == -ENOSPC) + rsp->hdr.Status = STATUS_BUFFER_TOO_SMALL; else if (ret < 0 || rsp->hdr.Status == 0) rsp->hdr.Status = STATUS_INVALID_PARAMETER; smb2_set_err_rsp(work); diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index a6dec5ec6a54..ff5a2f01d34a 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -113,6 +113,8 @@ #define SMB21_DEFAULT_IOSIZE (1024 * 1024) #define SMB3_DEFAULT_IOSIZE (4 * 1024 * 1024) #define SMB3_DEFAULT_TRANS_SIZE (1024 * 1024) +#define SMB3_MIN_IOSIZE (64 * 1024) +#define SMB3_MAX_IOSIZE (8 * 1024 * 1024) /* * SMB2 Header Definition diff --git a/fs/ksmbd/transport_ipc.c b/fs/ksmbd/transport_ipc.c index 44aea33a67fa..1acf1892a466 100644 --- a/fs/ksmbd/transport_ipc.c +++ b/fs/ksmbd/transport_ipc.c @@ -601,7 +601,7 @@ int ksmbd_ipc_tree_disconnect_request(unsigned long long session_id, return ret; } -int ksmbd_ipc_logout_request(const char *account) +int ksmbd_ipc_logout_request(const char *account, int flags) { struct ksmbd_ipc_msg *msg; struct ksmbd_logout_request *req; @@ -616,6 +616,7 @@ int ksmbd_ipc_logout_request(const char *account) msg->type = KSMBD_EVENT_LOGOUT_REQUEST; req = (struct ksmbd_logout_request *)msg->payload; + req->account_flags = flags; strscpy(req->account, account, KSMBD_REQ_MAX_ACCOUNT_NAME_SZ); ret = ipc_msg_send(msg); diff --git a/fs/ksmbd/transport_ipc.h b/fs/ksmbd/transport_ipc.h index 9eacc895ffdb..5e5b90a0c187 100644 --- a/fs/ksmbd/transport_ipc.h +++ b/fs/ksmbd/transport_ipc.h @@ -25,7 +25,7 @@ ksmbd_ipc_tree_connect_request(struct ksmbd_session *sess, struct sockaddr *peer_addr); int ksmbd_ipc_tree_disconnect_request(unsigned long long session_id, unsigned long long connect_id); -int ksmbd_ipc_logout_request(const char *account); +int ksmbd_ipc_logout_request(const char *account, int flags); struct ksmbd_share_config_response * ksmbd_ipc_share_config_request(const char *name); struct ksmbd_spnego_authen_response * diff --git a/fs/ksmbd/transport_rdma.c b/fs/ksmbd/transport_rdma.c index 3a7fa23ba850..a2fd5a4d4cd5 100644 --- a/fs/ksmbd/transport_rdma.c +++ b/fs/ksmbd/transport_rdma.c @@ -549,6 +549,10 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) switch (recvmsg->type) { case SMB_DIRECT_MSG_NEGOTIATE_REQ: + if (wc->byte_len < sizeof(struct smb_direct_negotiate_req)) { + put_empty_recvmsg(t, recvmsg); + return; + } t->negotiation_requested = true; t->full_packet_received = true; wake_up_interruptible(&t->wait_status); @@ -556,10 +560,23 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) case SMB_DIRECT_MSG_DATA_TRANSFER: { struct smb_direct_data_transfer *data_transfer = (struct smb_direct_data_transfer *)recvmsg->packet; - int data_length = le32_to_cpu(data_transfer->data_length); + unsigned int data_length; int avail_recvmsg_count, receive_credits; + if (wc->byte_len < + offsetof(struct smb_direct_data_transfer, padding)) { + put_empty_recvmsg(t, recvmsg); + return; + } + + data_length = le32_to_cpu(data_transfer->data_length); if (data_length) { + if (wc->byte_len < sizeof(struct smb_direct_data_transfer) + + (u64)data_length) { + put_empty_recvmsg(t, recvmsg); + return; + } + if (t->full_packet_received) recvmsg->first_segment = true; @@ -568,7 +585,7 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) else t->full_packet_received = true; - enqueue_reassembly(t, recvmsg, data_length); + enqueue_reassembly(t, recvmsg, (int)data_length); wake_up_interruptible(&t->wait_reassembly_queue); spin_lock(&t->receive_credit_lock); diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c index b41954294d38..835b384b0895 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/ksmbd/vfs.c @@ -1023,7 +1023,7 @@ int ksmbd_vfs_zero_data(struct ksmbd_work *work, struct ksmbd_file *fp, int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length, struct file_allocated_range_buffer *ranges, - int in_count, int *out_count) + unsigned int in_count, unsigned int *out_count) { struct file *f = fp->filp; struct inode *inode = file_inode(fp->filp); diff --git a/fs/ksmbd/vfs.h b/fs/ksmbd/vfs.h index 7b1dcaa3fbdc..b0d5b8feb4a3 100644 --- a/fs/ksmbd/vfs.h +++ b/fs/ksmbd/vfs.h @@ -166,7 +166,7 @@ int ksmbd_vfs_zero_data(struct ksmbd_work *work, struct ksmbd_file *fp, struct file_allocated_range_buffer; int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length, struct file_allocated_range_buffer *ranges, - int in_count, int *out_count); + unsigned int in_count, unsigned int *out_count); int ksmbd_vfs_unlink(struct user_namespace *user_ns, struct dentry *dir, struct dentry *dentry); void *ksmbd_vfs_init_kstat(char **p, struct ksmbd_kstat *ksmbd_kstat); diff --git a/include/acpi/platform/acgcc.h b/include/acpi/platform/acgcc.h index fb172a03a753..20ecb004f5a4 100644 --- a/include/acpi/platform/acgcc.h +++ b/include/acpi/platform/acgcc.h @@ -22,9 +22,14 @@ typedef __builtin_va_list va_list; #define va_arg(v, l) __builtin_va_arg(v, l) #define va_copy(d, s) __builtin_va_copy(d, s) #else +#ifdef __KERNEL__ #include <linux/stdarg.h> -#endif -#endif +#else +/* Used to build acpi tools */ +#include <stdarg.h> +#endif /* __KERNEL__ */ +#endif /* ACPI_USE_BUILTIN_STDARG */ +#endif /* ! va_arg */ #define ACPI_INLINE __inline__ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1c7fd7c4c6d3..e6f5579f9356 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -931,8 +931,11 @@ struct bpf_array_aux { * stored in the map to make sure that all callers and callees have * the same prog type and JITed flag. */ - enum bpf_prog_type type; - bool jited; + struct { + spinlock_t lock; + enum bpf_prog_type type; + bool jited; + } owner; /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; struct bpf_map *map; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 9c81724e4b98..bbe1eefa4c8a 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -101,14 +101,14 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_trace_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) -#ifdef CONFIG_NET -BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) -BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops) -BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops) #ifdef CONFIG_BPF_LSM BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_TASK_STORAGE, task_storage_map_ops) +#ifdef CONFIG_NET +BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) #if defined(CONFIG_XDP_SOCKETS) BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) diff --git a/include/linux/filter.h b/include/linux/filter.h index 47f80adbe744..8231a6a257f6 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1050,6 +1050,7 @@ extern int bpf_jit_enable; extern int bpf_jit_harden; extern int bpf_jit_kallsyms; extern long bpf_jit_limit; +extern long bpf_jit_limit_max; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 14ab0c0bc924..1ce9a9eb223b 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -128,6 +128,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); +bool sk_msg_is_readable(struct sock *sk); static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes) { diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7c9d5db4f0e6..423f97b982ff 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5442,7 +5442,6 @@ static inline void wiphy_unlock(struct wiphy *wiphy) * netdev and may otherwise be used by driver read-only, will be update * by cfg80211 on change_interface * @mgmt_registrations: list of registrations for management frames - * @mgmt_registrations_lock: lock for the list * @mgmt_registrations_need_update: mgmt registrations were updated, * need to propagate the update to the driver * @mtx: mutex used to lock data in this struct, may be used by drivers @@ -5489,7 +5488,6 @@ struct wireless_dev { u32 identifier; struct list_head mgmt_registrations; - spinlock_t mgmt_registrations_lock; u8 mgmt_registrations_need_update:1; struct mutex mtx; diff --git a/include/net/mptcp.h b/include/net/mptcp.h index f83fa48408b3..a925349b4b89 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -71,6 +71,10 @@ struct mptcp_out_options { struct { u64 sndr_key; u64 rcvr_key; + u64 data_seq; + u32 subflow_seq; + u16 data_len; + __sum16 csum; }; struct { struct mptcp_addr_info addr; diff --git a/include/net/sock.h b/include/net/sock.h index fb70d8553fae..620de053002d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1213,7 +1213,7 @@ struct proto { int (*forward_alloc_get)(const struct sock *sk); bool (*stream_memory_free)(const struct sock *sk, int wake); - bool (*stream_memory_read)(const struct sock *sk); + bool (*sock_is_readable)(struct sock *sk); /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); void (*leave_memory_pressure)(struct sock *sk); @@ -2854,4 +2854,10 @@ int sock_get_timeout(long timeo, void *optval, bool old_timeval); int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, sockptr_t optval, int optlen, bool old_timeval); +static inline bool sk_is_readable(struct sock *sk) +{ + if (sk->sk_prot->sock_is_readable) + return sk->sk_prot->sock_is_readable(sk); + return false; +} #endif /* _SOCK_H */ diff --git a/include/net/tls.h b/include/net/tls.h index adab19a8aed7..526cb2c3b724 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -361,6 +361,7 @@ int tls_sk_query(struct sock *sk, int optname, char __user *optval, int __user *optlen); int tls_sk_attach(struct sock *sk, int optname, char __user *optval, unsigned int optlen); +void tls_err_abort(struct sock *sk, int err); int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx); void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); @@ -378,7 +379,7 @@ void tls_sw_release_resources_rx(struct sock *sk); void tls_sw_free_ctx_rx(struct tls_context *tls_ctx); int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); -bool tls_sw_stream_read(const struct sock *sk); +bool tls_sw_sock_is_readable(struct sock *sk); ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); @@ -469,12 +470,6 @@ static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk) #endif } -static inline void tls_err_abort(struct sock *sk, int err) -{ - sk->sk_err = err; - sk_error_report(sk); -} - static inline bool tls_bigint_increment(unsigned char *seq, int len) { int i; @@ -515,7 +510,7 @@ static inline void tls_advance_record_sn(struct sock *sk, struct cipher_context *ctx) { if (tls_bigint_increment(ctx->rec_seq, prot->rec_seq_size)) - tls_err_abort(sk, EBADMSG); + tls_err_abort(sk, -EBADMSG); if (prot->version != TLS_1_3_VERSION && prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305) diff --git a/include/net/udp.h b/include/net/udp.h index 360df454356c..909ecf447e0f 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -494,8 +494,9 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk, * CHECKSUM_NONE in __udp_gso_segment. UDP GRO indeed builds partial * packets in udp_gro_complete_segment. As does UDP GSO, verified by * udp_send_skb. But when those packets are looped in dev_loopback_xmit - * their ip_summed is set to CHECKSUM_UNNECESSARY. Reset in this - * specific case, where PARTIAL is both correct and required. + * their ip_summed CHECKSUM_NONE is changed to CHECKSUM_UNNECESSARY. + * Reset in this specific case, where PARTIAL is both correct and + * required. */ if (skb->pkt_type == PACKET_LOOPBACK) skb->ip_summed = CHECKSUM_PARTIAL; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 5e1ccfae916b..c7a5be3bf8be 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -1071,6 +1071,7 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr) INIT_WORK(&aux->work, prog_array_map_clear_deferred); INIT_LIST_HEAD(&aux->poke_progs); mutex_init(&aux->poke_mutex); + spin_lock_init(&aux->owner.lock); map = array_map_alloc(attr); if (IS_ERR(map)) { diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ea8a468dbded..ded9163185d1 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -524,6 +524,7 @@ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_harden __read_mostly; long bpf_jit_limit __read_mostly; +long bpf_jit_limit_max __read_mostly; static void bpf_prog_ksym_set_addr(struct bpf_prog *prog) @@ -817,7 +818,8 @@ u64 __weak bpf_jit_alloc_exec_limit(void) static int __init bpf_jit_charge_init(void) { /* Only used as heuristic here to derive limit. */ - bpf_jit_limit = min_t(u64, round_up(bpf_jit_alloc_exec_limit() >> 2, + bpf_jit_limit_max = bpf_jit_alloc_exec_limit(); + bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 2, PAGE_SIZE), LONG_MAX); return 0; } @@ -1821,20 +1823,26 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx, bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp) { + bool ret; + if (fp->kprobe_override) return false; - if (!array->aux->type) { + spin_lock(&array->aux->owner.lock); + + if (!array->aux->owner.type) { /* There's no owner yet where we could check for * compatibility. */ - array->aux->type = fp->type; - array->aux->jited = fp->jited; - return true; + array->aux->owner.type = fp->type; + array->aux->owner.jited = fp->jited; + ret = true; + } else { + ret = array->aux->owner.type == fp->type && + array->aux->owner.jited == fp->jited; } - - return array->aux->type == fp->type && - array->aux->jited == fp->jited; + spin_unlock(&array->aux->owner.lock); + return ret; } static int bpf_check_tail_call(const struct bpf_prog *fp) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4e50c0bfdb7d..1cad6979a0d0 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -543,8 +543,10 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) { array = container_of(map, struct bpf_array, map); - type = array->aux->type; - jited = array->aux->jited; + spin_lock(&array->aux->owner.lock); + type = array->aux->owner.type; + jited = array->aux->owner.jited; + spin_unlock(&array->aux->owner.lock); } seq_printf(m, @@ -1337,12 +1339,11 @@ int generic_map_update_batch(struct bpf_map *map, void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); u32 value_size, cp, max_count; - int ufd = attr->map_fd; + int ufd = attr->batch.map_fd; void *key, *value; struct fd f; int err = 0; - f = fdget(ufd); if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; @@ -1367,6 +1368,7 @@ int generic_map_update_batch(struct bpf_map *map, return -ENOMEM; } + f = fdget(ufd); /* bpf_map_do_batch() guarantees ufd is valid */ for (cp = 0; cp < max_count; cp++) { err = -EFAULT; if (copy_from_user(key, keys + cp * map->key_size, @@ -1386,6 +1388,7 @@ int generic_map_update_batch(struct bpf_map *map, kvfree(value); kvfree(key); + fdput(f); return err; } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 570b0c97392a..ea08f01d0111 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2187,8 +2187,10 @@ static void cgroup_kill_sb(struct super_block *sb) * And don't kill the default root. */ if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root && - !percpu_ref_is_dying(&root->cgrp.self.refcnt)) + !percpu_ref_is_dying(&root->cgrp.self.refcnt)) { + cgroup_bpf_offline(&root->cgrp); percpu_ref_kill(&root->cgrp.self.refcnt); + } cgroup_put(&root->cgrp); kernfs_kill_sb(sb); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1bba4128a3e6..f21714ea3db8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8795,6 +8795,7 @@ void idle_task_exit(void) finish_arch_post_lock_switch(); } + scs_task_reset(current); /* finish_cpu(), as ran on the BP, will clean up the active_mm state */ } diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index c4a15aef36af..5c5f208c15d3 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -904,8 +904,8 @@ static int __trace_eprobe_create(int argc, const char *argv[]) if (IS_ERR(ep)) { ret = PTR_ERR(ep); - /* This must return -ENOMEM, else there is a bug */ - WARN_ON_ONCE(ret != -ENOMEM); + /* This must return -ENOMEM or misssing event, else there is a bug */ + WARN_ON_ONCE(ret != -ENOMEM && ret != -ENODEV); ep = NULL; goto error; } diff --git a/mm/secretmem.c b/mm/secretmem.c index 1fea68b8d5a6..c2dda408bb36 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -18,7 +18,6 @@ #include <linux/secretmem.h> #include <linux/set_memory.h> #include <linux/sched/signal.h> -#include <linux/refcount.h> #include <uapi/linux/magic.h> @@ -41,11 +40,11 @@ module_param_named(enable, secretmem_enable, bool, 0400); MODULE_PARM_DESC(secretmem_enable, "Enable secretmem and memfd_secret(2) system call"); -static refcount_t secretmem_users; +static atomic_t secretmem_users; bool secretmem_active(void) { - return !!refcount_read(&secretmem_users); + return !!atomic_read(&secretmem_users); } static vm_fault_t secretmem_fault(struct vm_fault *vmf) @@ -104,7 +103,7 @@ static const struct vm_operations_struct secretmem_vm_ops = { static int secretmem_release(struct inode *inode, struct file *file) { - refcount_dec(&secretmem_users); + atomic_dec(&secretmem_users); return 0; } @@ -204,6 +203,8 @@ SYSCALL_DEFINE1(memfd_secret, unsigned int, flags) if (flags & ~(SECRETMEM_FLAGS_MASK | O_CLOEXEC)) return -EINVAL; + if (atomic_read(&secretmem_users) < 0) + return -ENFILE; fd = get_unused_fd_flags(flags & O_CLOEXEC); if (fd < 0) @@ -218,7 +219,7 @@ SYSCALL_DEFINE1(memfd_secret, unsigned int, flags) file->f_flags |= O_LARGEFILE; fd_install(fd, file); - refcount_inc(&secretmem_users); + atomic_inc(&secretmem_users); return fd; err_put_fd: diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 7242b32fff80..2ed9496fc41f 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1560,10 +1560,14 @@ int batadv_bla_init(struct batadv_priv *bat_priv) return 0; bat_priv->bla.claim_hash = batadv_hash_new(128); - bat_priv->bla.backbone_hash = batadv_hash_new(32); + if (!bat_priv->bla.claim_hash) + return -ENOMEM; - if (!bat_priv->bla.claim_hash || !bat_priv->bla.backbone_hash) + bat_priv->bla.backbone_hash = batadv_hash_new(32); + if (!bat_priv->bla.backbone_hash) { + batadv_hash_destroy(bat_priv->bla.claim_hash); return -ENOMEM; + } batadv_hash_set_lock_class(bat_priv->bla.claim_hash, &batadv_claim_hash_lock_class_key); diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 3ddd66e4c29e..5207cd8d6ad8 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -190,29 +190,41 @@ int batadv_mesh_init(struct net_device *soft_iface) bat_priv->gw.generation = 0; - ret = batadv_v_mesh_init(bat_priv); - if (ret < 0) - goto err; - ret = batadv_originator_init(bat_priv); - if (ret < 0) - goto err; + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_orig; + } ret = batadv_tt_init(bat_priv); - if (ret < 0) - goto err; + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_tt; + } + + ret = batadv_v_mesh_init(bat_priv); + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_v; + } ret = batadv_bla_init(bat_priv); - if (ret < 0) - goto err; + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_bla; + } ret = batadv_dat_init(bat_priv); - if (ret < 0) - goto err; + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_dat; + } ret = batadv_nc_mesh_init(bat_priv); - if (ret < 0) - goto err; + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_nc; + } batadv_gw_init(bat_priv); batadv_mcast_init(bat_priv); @@ -222,8 +234,20 @@ int batadv_mesh_init(struct net_device *soft_iface) return 0; -err: - batadv_mesh_free(soft_iface); +err_nc: + batadv_dat_free(bat_priv); +err_dat: + batadv_bla_free(bat_priv); +err_bla: + batadv_v_mesh_free(bat_priv); +err_v: + batadv_tt_free(bat_priv); +err_tt: + batadv_originator_free(bat_priv); +err_orig: + batadv_purge_outstanding_packets(bat_priv, NULL); + atomic_set(&bat_priv->mesh_state, BATADV_MESH_INACTIVE); + return ret; } diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 9f06132e007d..0a7f1d36a6a8 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -152,8 +152,10 @@ int batadv_nc_mesh_init(struct batadv_priv *bat_priv) &batadv_nc_coding_hash_lock_class_key); bat_priv->nc.decoding_hash = batadv_hash_new(128); - if (!bat_priv->nc.decoding_hash) + if (!bat_priv->nc.decoding_hash) { + batadv_hash_destroy(bat_priv->nc.coding_hash); goto err; + } batadv_hash_set_lock_class(bat_priv->nc.decoding_hash, &batadv_nc_decoding_hash_lock_class_key); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index e0b3dace2020..4b7ad6684bc4 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -4162,8 +4162,10 @@ int batadv_tt_init(struct batadv_priv *bat_priv) return ret; ret = batadv_tt_global_init(bat_priv); - if (ret < 0) + if (ret < 0) { + batadv_tt_local_table_free(bat_priv); return ret; + } batadv_tvlv_handler_register(bat_priv, batadv_tt_tvlv_ogm_handler_v1, batadv_tt_tvlv_unicast_handler_v1, diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 61ccf46fcc21..4556d913955b 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -552,252 +552,16 @@ out: return nlmsg_size; } -struct br_mdb_complete_info { - struct net_bridge_port *port; - struct br_ip ip; -}; - -static void br_mdb_complete(struct net_device *dev, int err, void *priv) -{ - struct br_mdb_complete_info *data = priv; - struct net_bridge_port_group __rcu **pp; - struct net_bridge_port_group *p; - struct net_bridge_mdb_entry *mp; - struct net_bridge_port *port = data->port; - struct net_bridge *br = port->br; - - if (err) - goto err; - - spin_lock_bh(&br->multicast_lock); - mp = br_mdb_ip_get(br, &data->ip); - if (!mp) - goto out; - for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; - pp = &p->next) { - if (p->key.port != port) - continue; - p->flags |= MDB_PG_FLAGS_OFFLOAD; - } -out: - spin_unlock_bh(&br->multicast_lock); -err: - kfree(priv); -} - -static void br_switchdev_mdb_populate(struct switchdev_obj_port_mdb *mdb, - const struct net_bridge_mdb_entry *mp) -{ - if (mp->addr.proto == htons(ETH_P_IP)) - ip_eth_mc_map(mp->addr.dst.ip4, mdb->addr); -#if IS_ENABLED(CONFIG_IPV6) - else if (mp->addr.proto == htons(ETH_P_IPV6)) - ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb->addr); -#endif - else - ether_addr_copy(mdb->addr, mp->addr.dst.mac_addr); - - mdb->vid = mp->addr.vid; -} - -static int br_mdb_replay_one(struct notifier_block *nb, struct net_device *dev, - const struct switchdev_obj_port_mdb *mdb, - unsigned long action, const void *ctx, - struct netlink_ext_ack *extack) -{ - struct switchdev_notifier_port_obj_info obj_info = { - .info = { - .dev = dev, - .extack = extack, - .ctx = ctx, - }, - .obj = &mdb->obj, - }; - int err; - - err = nb->notifier_call(nb, action, &obj_info); - return notifier_to_errno(err); -} - -static int br_mdb_queue_one(struct list_head *mdb_list, - enum switchdev_obj_id id, - const struct net_bridge_mdb_entry *mp, - struct net_device *orig_dev) -{ - struct switchdev_obj_port_mdb *mdb; - - mdb = kzalloc(sizeof(*mdb), GFP_ATOMIC); - if (!mdb) - return -ENOMEM; - - mdb->obj.id = id; - mdb->obj.orig_dev = orig_dev; - br_switchdev_mdb_populate(mdb, mp); - list_add_tail(&mdb->obj.list, mdb_list); - - return 0; -} - -int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, - const void *ctx, bool adding, struct notifier_block *nb, - struct netlink_ext_ack *extack) -{ - const struct net_bridge_mdb_entry *mp; - struct switchdev_obj *obj, *tmp; - struct net_bridge *br; - unsigned long action; - LIST_HEAD(mdb_list); - int err = 0; - - ASSERT_RTNL(); - - if (!nb) - return 0; - - if (!netif_is_bridge_master(br_dev) || !netif_is_bridge_port(dev)) - return -EINVAL; - - br = netdev_priv(br_dev); - - if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) - return 0; - - /* We cannot walk over br->mdb_list protected just by the rtnl_mutex, - * because the write-side protection is br->multicast_lock. But we - * need to emulate the [ blocking ] calling context of a regular - * switchdev event, so since both br->multicast_lock and RCU read side - * critical sections are atomic, we have no choice but to pick the RCU - * read side lock, queue up all our events, leave the critical section - * and notify switchdev from blocking context. - */ - rcu_read_lock(); - - hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) { - struct net_bridge_port_group __rcu * const *pp; - const struct net_bridge_port_group *p; - - if (mp->host_joined) { - err = br_mdb_queue_one(&mdb_list, - SWITCHDEV_OBJ_ID_HOST_MDB, - mp, br_dev); - if (err) { - rcu_read_unlock(); - goto out_free_mdb; - } - } - - for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL; - pp = &p->next) { - if (p->key.port->dev != dev) - continue; - - err = br_mdb_queue_one(&mdb_list, - SWITCHDEV_OBJ_ID_PORT_MDB, - mp, dev); - if (err) { - rcu_read_unlock(); - goto out_free_mdb; - } - } - } - - rcu_read_unlock(); - - if (adding) - action = SWITCHDEV_PORT_OBJ_ADD; - else - action = SWITCHDEV_PORT_OBJ_DEL; - - list_for_each_entry(obj, &mdb_list, list) { - err = br_mdb_replay_one(nb, dev, SWITCHDEV_OBJ_PORT_MDB(obj), - action, ctx, extack); - if (err) - goto out_free_mdb; - } - -out_free_mdb: - list_for_each_entry_safe(obj, tmp, &mdb_list, list) { - list_del(&obj->list); - kfree(SWITCHDEV_OBJ_PORT_MDB(obj)); - } - - return err; -} - -static void br_mdb_switchdev_host_port(struct net_device *dev, - struct net_device *lower_dev, - struct net_bridge_mdb_entry *mp, - int type) -{ - struct switchdev_obj_port_mdb mdb = { - .obj = { - .id = SWITCHDEV_OBJ_ID_HOST_MDB, - .flags = SWITCHDEV_F_DEFER, - .orig_dev = dev, - }, - }; - - br_switchdev_mdb_populate(&mdb, mp); - - switch (type) { - case RTM_NEWMDB: - switchdev_port_obj_add(lower_dev, &mdb.obj, NULL); - break; - case RTM_DELMDB: - switchdev_port_obj_del(lower_dev, &mdb.obj); - break; - } -} - -static void br_mdb_switchdev_host(struct net_device *dev, - struct net_bridge_mdb_entry *mp, int type) -{ - struct net_device *lower_dev; - struct list_head *iter; - - netdev_for_each_lower_dev(dev, lower_dev, iter) - br_mdb_switchdev_host_port(dev, lower_dev, mp, type); -} - void br_mdb_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *pg, int type) { - struct br_mdb_complete_info *complete_info; - struct switchdev_obj_port_mdb mdb = { - .obj = { - .id = SWITCHDEV_OBJ_ID_PORT_MDB, - .flags = SWITCHDEV_F_DEFER, - }, - }; struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; - if (pg) { - br_switchdev_mdb_populate(&mdb, mp); - - mdb.obj.orig_dev = pg->key.port->dev; - switch (type) { - case RTM_NEWMDB: - complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC); - if (!complete_info) - break; - complete_info->port = pg->key.port; - complete_info->ip = mp->addr; - mdb.obj.complete_priv = complete_info; - mdb.obj.complete = br_mdb_complete; - if (switchdev_port_obj_add(pg->key.port->dev, &mdb.obj, NULL)) - kfree(complete_info); - break; - case RTM_DELMDB: - switchdev_port_obj_del(pg->key.port->dev, &mdb.obj); - break; - } - } else { - br_mdb_switchdev_host(dev, mp, type); - } + br_switchdev_mdb_notify(dev, mp, pg, type); skb = nlmsg_new(rtnl_mdb_nlmsg_size(pg), GFP_ATOMIC); if (!skb) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 3c9327628060..5552c00ed9c4 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -956,9 +956,11 @@ int br_multicast_toggle_vlan_snooping(struct net_bridge *br, bool on, struct netlink_ext_ack *extack); bool br_multicast_toggle_global_vlan(struct net_bridge_vlan *vlan, bool on); -int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, - const void *ctx, bool adding, struct notifier_block *nb, - struct netlink_ext_ack *extack); +void br_switchdev_mdb_notify(struct net_device *dev, + struct net_bridge_mdb_entry *mp, + struct net_bridge_port_group *pg, + int type); + int br_rports_fill_info(struct sk_buff *skb, const struct net_bridge_mcast *brmctx); int br_multicast_dump_querier_state(struct sk_buff *skb, @@ -1394,12 +1396,11 @@ static inline bool br_multicast_toggle_global_vlan(struct net_bridge_vlan *vlan, return false; } -static inline int br_mdb_replay(struct net_device *br_dev, - struct net_device *dev, const void *ctx, - bool adding, struct notifier_block *nb, - struct netlink_ext_ack *extack) +static inline void br_switchdev_mdb_notify(struct net_device *dev, + struct net_bridge_mdb_entry *mp, + struct net_bridge_port_group *pg, + int type) { - return -EOPNOTSUPP; } static inline bool @@ -1459,9 +1460,6 @@ void br_vlan_notify(const struct net_bridge *br, const struct net_bridge_port *p, u16 vid, u16 vid_range, int cmd); -int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, - const void *ctx, bool adding, struct notifier_block *nb, - struct netlink_ext_ack *extack); bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end); @@ -1708,13 +1706,11 @@ static inline bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, return true; } -static inline int br_vlan_replay(struct net_device *br_dev, - struct net_device *dev, const void *ctx, - bool adding, struct notifier_block *nb, - struct netlink_ext_ack *extack) +static inline u16 br_vlan_flags(const struct net_bridge_vlan *v, u16 pvid) { - return -EOPNOTSUPP; + return 0; } + #endif /* br_vlan_options.c */ diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 2fbe881cdfe2..f8fbaaa7c501 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -4,6 +4,7 @@ #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> +#include <net/ip.h> #include <net/switchdev.h> #include "br_private.h" @@ -280,9 +281,10 @@ static void nbp_switchdev_del(struct net_bridge_port *p) } } -static int br_fdb_replay_one(struct net_bridge *br, struct notifier_block *nb, - const struct net_bridge_fdb_entry *fdb, - unsigned long action, const void *ctx) +static int +br_switchdev_fdb_replay_one(struct net_bridge *br, struct notifier_block *nb, + const struct net_bridge_fdb_entry *fdb, + unsigned long action, const void *ctx) { struct switchdev_notifier_fdb_info item; int err; @@ -293,8 +295,9 @@ static int br_fdb_replay_one(struct net_bridge *br, struct notifier_block *nb, return notifier_to_errno(err); } -static int br_fdb_replay(const struct net_device *br_dev, const void *ctx, - bool adding, struct notifier_block *nb) +static int +br_switchdev_fdb_replay(const struct net_device *br_dev, const void *ctx, + bool adding, struct notifier_block *nb) { struct net_bridge_fdb_entry *fdb; struct net_bridge *br; @@ -317,7 +320,7 @@ static int br_fdb_replay(const struct net_device *br_dev, const void *ctx, rcu_read_lock(); hlist_for_each_entry_rcu(fdb, &br->fdb_list, fdb_node) { - err = br_fdb_replay_one(br, nb, fdb, action, ctx); + err = br_switchdev_fdb_replay_one(br, nb, fdb, action, ctx); if (err) break; } @@ -327,6 +330,348 @@ static int br_fdb_replay(const struct net_device *br_dev, const void *ctx, return err; } +static int +br_switchdev_vlan_replay_one(struct notifier_block *nb, + struct net_device *dev, + struct switchdev_obj_port_vlan *vlan, + const void *ctx, unsigned long action, + struct netlink_ext_ack *extack) +{ + struct switchdev_notifier_port_obj_info obj_info = { + .info = { + .dev = dev, + .extack = extack, + .ctx = ctx, + }, + .obj = &vlan->obj, + }; + int err; + + err = nb->notifier_call(nb, action, &obj_info); + return notifier_to_errno(err); +} + +static int br_switchdev_vlan_replay(struct net_device *br_dev, + struct net_device *dev, + const void *ctx, bool adding, + struct notifier_block *nb, + struct netlink_ext_ack *extack) +{ + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *v; + struct net_bridge_port *p; + struct net_bridge *br; + unsigned long action; + int err = 0; + u16 pvid; + + ASSERT_RTNL(); + + if (!nb) + return 0; + + if (!netif_is_bridge_master(br_dev)) + return -EINVAL; + + if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) + return -EINVAL; + + if (netif_is_bridge_master(dev)) { + br = netdev_priv(dev); + vg = br_vlan_group(br); + p = NULL; + } else { + p = br_port_get_rtnl(dev); + if (WARN_ON(!p)) + return -EINVAL; + vg = nbp_vlan_group(p); + br = p->br; + } + + if (!vg) + return 0; + + if (adding) + action = SWITCHDEV_PORT_OBJ_ADD; + else + action = SWITCHDEV_PORT_OBJ_DEL; + + pvid = br_get_pvid(vg); + + list_for_each_entry(v, &vg->vlan_list, vlist) { + struct switchdev_obj_port_vlan vlan = { + .obj.orig_dev = dev, + .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, + .flags = br_vlan_flags(v, pvid), + .vid = v->vid, + }; + + if (!br_vlan_should_use(v)) + continue; + + err = br_switchdev_vlan_replay_one(nb, dev, &vlan, ctx, + action, extack); + if (err) + return err; + } + + return err; +} + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING +struct br_switchdev_mdb_complete_info { + struct net_bridge_port *port; + struct br_ip ip; +}; + +static void br_switchdev_mdb_complete(struct net_device *dev, int err, void *priv) +{ + struct br_switchdev_mdb_complete_info *data = priv; + struct net_bridge_port_group __rcu **pp; + struct net_bridge_port_group *p; + struct net_bridge_mdb_entry *mp; + struct net_bridge_port *port = data->port; + struct net_bridge *br = port->br; + + if (err) + goto err; + + spin_lock_bh(&br->multicast_lock); + mp = br_mdb_ip_get(br, &data->ip); + if (!mp) + goto out; + for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (p->key.port != port) + continue; + p->flags |= MDB_PG_FLAGS_OFFLOAD; + } +out: + spin_unlock_bh(&br->multicast_lock); +err: + kfree(priv); +} + +static void br_switchdev_mdb_populate(struct switchdev_obj_port_mdb *mdb, + const struct net_bridge_mdb_entry *mp) +{ + if (mp->addr.proto == htons(ETH_P_IP)) + ip_eth_mc_map(mp->addr.dst.ip4, mdb->addr); +#if IS_ENABLED(CONFIG_IPV6) + else if (mp->addr.proto == htons(ETH_P_IPV6)) + ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb->addr); +#endif + else + ether_addr_copy(mdb->addr, mp->addr.dst.mac_addr); + + mdb->vid = mp->addr.vid; +} + +static void br_switchdev_host_mdb_one(struct net_device *dev, + struct net_device *lower_dev, + struct net_bridge_mdb_entry *mp, + int type) +{ + struct switchdev_obj_port_mdb mdb = { + .obj = { + .id = SWITCHDEV_OBJ_ID_HOST_MDB, + .flags = SWITCHDEV_F_DEFER, + .orig_dev = dev, + }, + }; + + br_switchdev_mdb_populate(&mdb, mp); + + switch (type) { + case RTM_NEWMDB: + switchdev_port_obj_add(lower_dev, &mdb.obj, NULL); + break; + case RTM_DELMDB: + switchdev_port_obj_del(lower_dev, &mdb.obj); + break; + } +} + +static void br_switchdev_host_mdb(struct net_device *dev, + struct net_bridge_mdb_entry *mp, int type) +{ + struct net_device *lower_dev; + struct list_head *iter; + + netdev_for_each_lower_dev(dev, lower_dev, iter) + br_switchdev_host_mdb_one(dev, lower_dev, mp, type); +} + +static int +br_switchdev_mdb_replay_one(struct notifier_block *nb, struct net_device *dev, + const struct switchdev_obj_port_mdb *mdb, + unsigned long action, const void *ctx, + struct netlink_ext_ack *extack) +{ + struct switchdev_notifier_port_obj_info obj_info = { + .info = { + .dev = dev, + .extack = extack, + .ctx = ctx, + }, + .obj = &mdb->obj, + }; + int err; + + err = nb->notifier_call(nb, action, &obj_info); + return notifier_to_errno(err); +} + +static int br_switchdev_mdb_queue_one(struct list_head *mdb_list, + enum switchdev_obj_id id, + const struct net_bridge_mdb_entry *mp, + struct net_device *orig_dev) +{ + struct switchdev_obj_port_mdb *mdb; + + mdb = kzalloc(sizeof(*mdb), GFP_ATOMIC); + if (!mdb) + return -ENOMEM; + + mdb->obj.id = id; + mdb->obj.orig_dev = orig_dev; + br_switchdev_mdb_populate(mdb, mp); + list_add_tail(&mdb->obj.list, mdb_list); + + return 0; +} + +void br_switchdev_mdb_notify(struct net_device *dev, + struct net_bridge_mdb_entry *mp, + struct net_bridge_port_group *pg, + int type) +{ + struct br_switchdev_mdb_complete_info *complete_info; + struct switchdev_obj_port_mdb mdb = { + .obj = { + .id = SWITCHDEV_OBJ_ID_PORT_MDB, + .flags = SWITCHDEV_F_DEFER, + }, + }; + + if (!pg) + return br_switchdev_host_mdb(dev, mp, type); + + br_switchdev_mdb_populate(&mdb, mp); + + mdb.obj.orig_dev = pg->key.port->dev; + switch (type) { + case RTM_NEWMDB: + complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC); + if (!complete_info) + break; + complete_info->port = pg->key.port; + complete_info->ip = mp->addr; + mdb.obj.complete_priv = complete_info; + mdb.obj.complete = br_switchdev_mdb_complete; + if (switchdev_port_obj_add(pg->key.port->dev, &mdb.obj, NULL)) + kfree(complete_info); + break; + case RTM_DELMDB: + switchdev_port_obj_del(pg->key.port->dev, &mdb.obj); + break; + } +} +#endif + +static int +br_switchdev_mdb_replay(struct net_device *br_dev, struct net_device *dev, + const void *ctx, bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack) +{ +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + const struct net_bridge_mdb_entry *mp; + struct switchdev_obj *obj, *tmp; + struct net_bridge *br; + unsigned long action; + LIST_HEAD(mdb_list); + int err = 0; + + ASSERT_RTNL(); + + if (!nb) + return 0; + + if (!netif_is_bridge_master(br_dev) || !netif_is_bridge_port(dev)) + return -EINVAL; + + br = netdev_priv(br_dev); + + if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) + return 0; + + /* We cannot walk over br->mdb_list protected just by the rtnl_mutex, + * because the write-side protection is br->multicast_lock. But we + * need to emulate the [ blocking ] calling context of a regular + * switchdev event, so since both br->multicast_lock and RCU read side + * critical sections are atomic, we have no choice but to pick the RCU + * read side lock, queue up all our events, leave the critical section + * and notify switchdev from blocking context. + */ + rcu_read_lock(); + + hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) { + struct net_bridge_port_group __rcu * const *pp; + const struct net_bridge_port_group *p; + + if (mp->host_joined) { + err = br_switchdev_mdb_queue_one(&mdb_list, + SWITCHDEV_OBJ_ID_HOST_MDB, + mp, br_dev); + if (err) { + rcu_read_unlock(); + goto out_free_mdb; + } + } + + for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL; + pp = &p->next) { + if (p->key.port->dev != dev) + continue; + + err = br_switchdev_mdb_queue_one(&mdb_list, + SWITCHDEV_OBJ_ID_PORT_MDB, + mp, dev); + if (err) { + rcu_read_unlock(); + goto out_free_mdb; + } + } + } + + rcu_read_unlock(); + + if (adding) + action = SWITCHDEV_PORT_OBJ_ADD; + else + action = SWITCHDEV_PORT_OBJ_DEL; + + list_for_each_entry(obj, &mdb_list, list) { + err = br_switchdev_mdb_replay_one(nb, dev, + SWITCHDEV_OBJ_PORT_MDB(obj), + action, ctx, extack); + if (err) + goto out_free_mdb; + } + +out_free_mdb: + list_for_each_entry_safe(obj, tmp, &mdb_list, list) { + list_del(&obj->list); + kfree(SWITCHDEV_OBJ_PORT_MDB(obj)); + } + + if (err) + return err; +#endif + + return 0; +} + static int nbp_switchdev_sync_objs(struct net_bridge_port *p, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb, @@ -336,15 +681,17 @@ static int nbp_switchdev_sync_objs(struct net_bridge_port *p, const void *ctx, struct net_device *dev = p->dev; int err; - err = br_vlan_replay(br_dev, dev, ctx, true, blocking_nb, extack); + err = br_switchdev_vlan_replay(br_dev, dev, ctx, true, blocking_nb, + extack); if (err && err != -EOPNOTSUPP) return err; - err = br_mdb_replay(br_dev, dev, ctx, true, blocking_nb, extack); + err = br_switchdev_mdb_replay(br_dev, dev, ctx, true, blocking_nb, + extack); if (err && err != -EOPNOTSUPP) return err; - err = br_fdb_replay(br_dev, ctx, true, atomic_nb); + err = br_switchdev_fdb_replay(br_dev, ctx, true, atomic_nb); if (err && err != -EOPNOTSUPP) return err; @@ -359,11 +706,11 @@ static void nbp_switchdev_unsync_objs(struct net_bridge_port *p, struct net_device *br_dev = p->br->dev; struct net_device *dev = p->dev; - br_vlan_replay(br_dev, dev, ctx, false, blocking_nb, NULL); + br_switchdev_vlan_replay(br_dev, dev, ctx, false, blocking_nb, NULL); - br_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL); + br_switchdev_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL); - br_fdb_replay(br_dev, ctx, false, atomic_nb); + br_switchdev_fdb_replay(br_dev, ctx, false, atomic_nb); } /* Let the bridge know that this port is offloaded, so that it can assign a diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 57bd6ee72a07..49e105e0a447 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1860,90 +1860,6 @@ out_kfree: kfree_skb(skb); } -static int br_vlan_replay_one(struct notifier_block *nb, - struct net_device *dev, - struct switchdev_obj_port_vlan *vlan, - const void *ctx, unsigned long action, - struct netlink_ext_ack *extack) -{ - struct switchdev_notifier_port_obj_info obj_info = { - .info = { - .dev = dev, - .extack = extack, - .ctx = ctx, - }, - .obj = &vlan->obj, - }; - int err; - - err = nb->notifier_call(nb, action, &obj_info); - return notifier_to_errno(err); -} - -int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, - const void *ctx, bool adding, struct notifier_block *nb, - struct netlink_ext_ack *extack) -{ - struct net_bridge_vlan_group *vg; - struct net_bridge_vlan *v; - struct net_bridge_port *p; - struct net_bridge *br; - unsigned long action; - int err = 0; - u16 pvid; - - ASSERT_RTNL(); - - if (!nb) - return 0; - - if (!netif_is_bridge_master(br_dev)) - return -EINVAL; - - if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) - return -EINVAL; - - if (netif_is_bridge_master(dev)) { - br = netdev_priv(dev); - vg = br_vlan_group(br); - p = NULL; - } else { - p = br_port_get_rtnl(dev); - if (WARN_ON(!p)) - return -EINVAL; - vg = nbp_vlan_group(p); - br = p->br; - } - - if (!vg) - return 0; - - if (adding) - action = SWITCHDEV_PORT_OBJ_ADD; - else - action = SWITCHDEV_PORT_OBJ_DEL; - - pvid = br_get_pvid(vg); - - list_for_each_entry(v, &vg->vlan_list, vlist) { - struct switchdev_obj_port_vlan vlan = { - .obj.orig_dev = dev, - .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, - .flags = br_vlan_flags(v, pvid), - .vid = v->vid, - }; - - if (!br_vlan_should_use(v)) - continue; - - err = br_vlan_replay_one(nb, dev, &vlan, ctx, action, extack); - if (err) - return err; - } - - return err; -} - /* check if v_curr can enter a range ending in range_end */ bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end) diff --git a/net/core/dev.c b/net/core/dev.c index e8754560e641..edeb811c454e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3171,6 +3171,12 @@ static u16 skb_tx_hash(const struct net_device *dev, qoffset = sb_dev->tc_to_txq[tc].offset; qcount = sb_dev->tc_to_txq[tc].count; + if (unlikely(!qcount)) { + net_warn_ratelimited("%s: invalid qcount, qoffset %u for tc %u\n", + sb_dev->name, qoffset, tc); + qoffset = 0; + qcount = dev->real_num_tx_queues; + } } if (skb_rx_queue_recorded(skb)) { @@ -3914,7 +3920,8 @@ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) skb_reset_mac_header(skb); __skb_pull(skb, skb_network_offset(skb)); skb->pkt_type = PACKET_LOOPBACK; - skb->ip_summed = CHECKSUM_UNNECESSARY; + if (skb->ip_summed == CHECKSUM_NONE) + skb->ip_summed = CHECKSUM_UNNECESSARY; WARN_ON(!skb_dst(skb)); skb_dst_force(skb); netif_rx_ni(skb); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index d6e4e0b43beb..9c01c642cf9e 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -2028,9 +2028,9 @@ int netdev_register_kobject(struct net_device *ndev) int netdev_change_owner(struct net_device *ndev, const struct net *net_old, const struct net *net_new) { + kuid_t old_uid = GLOBAL_ROOT_UID, new_uid = GLOBAL_ROOT_UID; + kgid_t old_gid = GLOBAL_ROOT_GID, new_gid = GLOBAL_ROOT_GID; struct device *dev = &ndev->dev; - kuid_t old_uid, new_uid; - kgid_t old_gid, new_gid; int error; net_ns_get_ownership(net_old, &old_uid, &old_gid); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 74601bbc56ac..09b8cf8ab234 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -80,6 +80,7 @@ #include <linux/indirect_call_wrapper.h> #include "datagram.h" +#include "sock_destructor.h" struct kmem_cache *skbuff_head_cache __ro_after_init; static struct kmem_cache *skbuff_fclone_cache __ro_after_init; @@ -1803,30 +1804,39 @@ EXPORT_SYMBOL(skb_realloc_headroom); struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom) { int delta = headroom - skb_headroom(skb); + int osize = skb_end_offset(skb); + struct sock *sk = skb->sk; if (WARN_ONCE(delta <= 0, "%s is expecting an increase in the headroom", __func__)) return skb; - /* pskb_expand_head() might crash, if skb is shared */ - if (skb_shared(skb)) { + delta = SKB_DATA_ALIGN(delta); + /* pskb_expand_head() might crash, if skb is shared. */ + if (skb_shared(skb) || !is_skb_wmem(skb)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); - if (likely(nskb)) { - if (skb->sk) - skb_set_owner_w(nskb, skb->sk); - consume_skb(skb); - } else { - kfree_skb(skb); - } + if (unlikely(!nskb)) + goto fail; + + if (sk) + skb_set_owner_w(nskb, sk); + consume_skb(skb); skb = nskb; } - if (skb && - pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { - kfree_skb(skb); - skb = NULL; + if (pskb_expand_head(skb, delta, 0, GFP_ATOMIC)) + goto fail; + + if (sk && is_skb_wmem(skb)) { + delta = skb_end_offset(skb) - osize; + refcount_add(delta, &sk->sk_wmem_alloc); + skb->truesize += delta; } return skb; + +fail: + kfree_skb(skb); + return NULL; } EXPORT_SYMBOL(skb_expand_head); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 2d6249b28928..a86ef7e844f8 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -474,6 +474,20 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, } EXPORT_SYMBOL_GPL(sk_msg_recvmsg); +bool sk_msg_is_readable(struct sock *sk) +{ + struct sk_psock *psock; + bool empty = true; + + rcu_read_lock(); + psock = sk_psock(sk); + if (likely(psock)) + empty = list_empty(&psock->ingress_msg); + rcu_read_unlock(); + return !empty; +} +EXPORT_SYMBOL_GPL(sk_msg_is_readable); + static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk, struct sk_buff *skb) { diff --git a/net/core/sock_destructor.h b/net/core/sock_destructor.h new file mode 100644 index 000000000000..2f396e6bfba5 --- /dev/null +++ b/net/core/sock_destructor.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _NET_CORE_SOCK_DESTRUCTOR_H +#define _NET_CORE_SOCK_DESTRUCTOR_H +#include <net/tcp.h> + +static inline bool is_skb_wmem(const struct sk_buff *skb) +{ + return skb->destructor == sock_wfree || + skb->destructor == __sock_wfree || + (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree); +} +#endif diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index c8496c1142c9..5f88526ad61c 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -419,7 +419,7 @@ static struct ctl_table net_core_table[] = { .mode = 0600, .proc_handler = proc_dolongvec_minmax_bpf_restricted, .extra1 = &long_one, - .extra2 = &long_max, + .extra2 = &bpf_jit_limit_max, }, #endif { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7a7b9aa8f19a..a7b1138d619c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -481,10 +481,7 @@ static bool tcp_stream_is_readable(struct sock *sk, int target) { if (tcp_epollin_ready(sk, target)) return true; - - if (sk->sk_prot->stream_memory_read) - return sk->sk_prot->stream_memory_read(sk); - return false; + return sk_is_readable(sk); } /* diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index d3e9386b493e..5f4d6f45d87f 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -150,19 +150,6 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir); #ifdef CONFIG_BPF_SYSCALL -static bool tcp_bpf_stream_read(const struct sock *sk) -{ - struct sk_psock *psock; - bool empty = true; - - rcu_read_lock(); - psock = sk_psock(sk); - if (likely(psock)) - empty = list_empty(&psock->ingress_msg); - rcu_read_unlock(); - return !empty; -} - static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock, long timeo) { @@ -232,6 +219,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, bool cork = false, enospc = sk_msg_full(msg); struct sock *sk_redir; u32 tosend, delta = 0; + u32 eval = __SK_NONE; int ret; more_data: @@ -275,13 +263,24 @@ more_data: case __SK_REDIRECT: sk_redir = psock->sk_redir; sk_msg_apply_bytes(psock, tosend); + if (!psock->apply_bytes) { + /* Clean up before releasing the sock lock. */ + eval = psock->eval; + psock->eval = __SK_NONE; + psock->sk_redir = NULL; + } if (psock->cork) { cork = true; psock->cork = NULL; } sk_msg_return(sk, msg, tosend); release_sock(sk); + ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags); + + if (eval == __SK_REDIRECT) + sock_put(sk_redir); + lock_sock(sk); if (unlikely(ret < 0)) { int free = sk_msg_free_nocharge(sk, msg); @@ -479,7 +478,7 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS], prot[TCP_BPF_BASE].unhash = sock_map_unhash; prot[TCP_BPF_BASE].close = sock_map_close; prot[TCP_BPF_BASE].recvmsg = tcp_bpf_recvmsg; - prot[TCP_BPF_BASE].stream_memory_read = tcp_bpf_stream_read; + prot[TCP_BPF_BASE].sock_is_readable = sk_msg_is_readable; prot[TCP_BPF_TX] = prot[TCP_BPF_BASE]; prot[TCP_BPF_TX].sendmsg = tcp_bpf_sendmsg; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8536b2a7210b..2fffcf2b54f3 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2867,6 +2867,9 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait) !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1) mask &= ~(EPOLLIN | EPOLLRDNORM); + /* psock ingress_msg queue should not contain any bad checksum frames */ + if (sk_is_readable(sk)) + mask |= EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index 7a1d5f473878..bbe6569c9ad3 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -114,6 +114,7 @@ static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base) *prot = *base; prot->close = sock_map_close; prot->recvmsg = udp_bpf_recvmsg; + prot->sock_is_readable = sk_msg_is_readable; } static void udp_bpf_check_v6_needs_rebuild(struct proto *ops) diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index a4212a333d61..15ac08d111ea 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -672,7 +672,7 @@ ieee80211_mesh_update_bss_params(struct ieee80211_sub_if_data *sdata, u8 *ie, u8 ie_len) { struct ieee80211_supported_band *sband; - const u8 *cap; + const struct element *cap; const struct ieee80211_he_operation *he_oper = NULL; sband = ieee80211_get_sband(sdata); @@ -687,9 +687,10 @@ ieee80211_mesh_update_bss_params(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.he_support = true; - cap = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION, ie, ie_len); - if (cap && cap[1] >= ieee80211_he_oper_size(&cap[3])) - he_oper = (void *)(cap + 3); + cap = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_OPERATION, ie, ie_len); + if (cap && cap->datalen >= 1 + sizeof(*he_oper) && + cap->datalen >= 1 + ieee80211_he_oper_size(cap->data + 1)) + he_oper = (void *)(cap->data + 1); if (he_oper) sdata->vif.bss_conf.he_oper.params = diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 422f4acfb3e6..7c3420afb1a0 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -485,11 +485,11 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, mpext = mptcp_get_ext(skb); data_len = mpext ? mpext->data_len : 0; - /* we will check ext_copy.data_len in mptcp_write_options() to + /* we will check ops->data_len in mptcp_write_options() to * discriminate between TCPOLEN_MPTCP_MPC_ACK_DATA and * TCPOLEN_MPTCP_MPC_ACK */ - opts->ext_copy.data_len = data_len; + opts->data_len = data_len; opts->suboptions = OPTION_MPTCP_MPC_ACK; opts->sndr_key = subflow->local_key; opts->rcvr_key = subflow->remote_key; @@ -505,9 +505,9 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, len = TCPOLEN_MPTCP_MPC_ACK_DATA; if (opts->csum_reqd) { /* we need to propagate more info to csum the pseudo hdr */ - opts->ext_copy.data_seq = mpext->data_seq; - opts->ext_copy.subflow_seq = mpext->subflow_seq; - opts->ext_copy.csum = mpext->csum; + opts->data_seq = mpext->data_seq; + opts->subflow_seq = mpext->subflow_seq; + opts->csum = mpext->csum; len += TCPOLEN_MPTCP_DSS_CHECKSUM; } *size = ALIGN(len, 4); @@ -1223,7 +1223,7 @@ static void mptcp_set_rwin(const struct tcp_sock *tp) WRITE_ONCE(msk->rcv_wnd_sent, ack_seq); } -static u16 mptcp_make_csum(const struct mptcp_ext *mpext) +static u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __sum16 sum) { struct csum_pseudo_header header; __wsum csum; @@ -1233,15 +1233,21 @@ static u16 mptcp_make_csum(const struct mptcp_ext *mpext) * always the 64-bit value, irrespective of what length is used in the * DSS option itself. */ - header.data_seq = cpu_to_be64(mpext->data_seq); - header.subflow_seq = htonl(mpext->subflow_seq); - header.data_len = htons(mpext->data_len); + header.data_seq = cpu_to_be64(data_seq); + header.subflow_seq = htonl(subflow_seq); + header.data_len = htons(data_len); header.csum = 0; - csum = csum_partial(&header, sizeof(header), ~csum_unfold(mpext->csum)); + csum = csum_partial(&header, sizeof(header), ~csum_unfold(sum)); return (__force u16)csum_fold(csum); } +static u16 mptcp_make_csum(const struct mptcp_ext *mpext) +{ + return __mptcp_make_csum(mpext->data_seq, mpext->subflow_seq, mpext->data_len, + mpext->csum); +} + void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts) { @@ -1332,7 +1338,7 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, len = TCPOLEN_MPTCP_MPC_SYN; } else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions) { len = TCPOLEN_MPTCP_MPC_SYNACK; - } else if (opts->ext_copy.data_len) { + } else if (opts->data_len) { len = TCPOLEN_MPTCP_MPC_ACK_DATA; if (opts->csum_reqd) len += TCPOLEN_MPTCP_DSS_CHECKSUM; @@ -1361,14 +1367,17 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, put_unaligned_be64(opts->rcvr_key, ptr); ptr += 2; - if (!opts->ext_copy.data_len) + if (!opts->data_len) goto mp_capable_done; if (opts->csum_reqd) { - put_unaligned_be32(opts->ext_copy.data_len << 16 | - mptcp_make_csum(&opts->ext_copy), ptr); + put_unaligned_be32(opts->data_len << 16 | + __mptcp_make_csum(opts->data_seq, + opts->subflow_seq, + opts->data_len, + opts->csum), ptr); } else { - put_unaligned_be32(opts->ext_copy.data_len << 16 | + put_unaligned_be32(opts->data_len << 16 | TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); } ptr += 1; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 32df65f68c12..fb3da4d8f4a3 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -156,6 +156,12 @@ static enum sctp_disposition __sctp_sf_do_9_1_abort( void *arg, struct sctp_cmd_seq *commands); +static enum sctp_disposition +__sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, void *arg, + struct sctp_cmd_seq *commands); + /* Small helper function that checks if the chunk length * is of the appropriate length. The 'required_length' argument * is set to be the size of a specific chunk we are testing. @@ -337,6 +343,14 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net, if (!chunk->singleton) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Make sure that the INIT chunk has a valid length. + * Normally, this would cause an ABORT with a Protocol Violation + * error, but since we don't have an association, we'll + * just discard the packet. + */ + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* If the packet is an OOTB packet which is temporarily on the * control endpoint, respond with an ABORT. */ @@ -351,14 +365,6 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net, if (chunk->sctp_hdr->vtag != 0) return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); - /* Make sure that the INIT chunk has a valid length. - * Normally, this would cause an ABORT with a Protocol Violation - * error, but since we don't have an association, we'll - * just discard the packet. - */ - if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - /* If the INIT is coming toward a closing socket, we'll send back * and ABORT. Essentially, this catches the race of INIT being * backloged to the socket at the same time as the user issues close(). @@ -704,6 +710,9 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, struct sock *sk; int error = 0; + if (asoc && !sctp_vtag_verify(chunk, asoc)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* If the packet is an OOTB packet which is temporarily on the * control endpoint, respond with an ABORT. */ @@ -718,7 +727,8 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, * in sctp_unpack_cookie(). */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, + commands); /* If the endpoint is not listening or if the number of associations * on the TCP-style socket exceed the max backlog, respond with an @@ -1524,20 +1534,16 @@ static enum sctp_disposition sctp_sf_do_unexpected_init( if (!chunk->singleton) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Make sure that the INIT chunk has a valid length. */ + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* 3.1 A packet containing an INIT chunk MUST have a zero Verification * Tag. */ if (chunk->sctp_hdr->vtag != 0) return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); - /* Make sure that the INIT chunk has a valid length. - * In this case, we generate a protocol violation since we have - * an association established. - */ - if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) - return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, - commands); - if (SCTP_INPUT_CB(chunk->skb)->encap_port != chunk->transport->encap_port) return sctp_sf_new_encap_port(net, ep, asoc, type, arg, commands); @@ -1882,9 +1888,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_a( * its peer. */ if (sctp_state(asoc, SHUTDOWN_ACK_SENT)) { - disposition = sctp_sf_do_9_2_reshutack(net, ep, asoc, - SCTP_ST_CHUNK(chunk->chunk_hdr->type), - chunk, commands); + disposition = __sctp_sf_do_9_2_reshutack(net, ep, asoc, + SCTP_ST_CHUNK(chunk->chunk_hdr->type), + chunk, commands); if (SCTP_DISPOSITION_NOMEM == disposition) goto nomem; @@ -2202,9 +2208,11 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( * enough for the chunk header. Cookie length verification is * done later. */ - if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) - return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, - commands); + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) { + if (!sctp_vtag_verify(chunk, asoc)) + asoc = NULL; + return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); + } /* "Decode" the chunk. We have no optional parameters so we * are in good shape. @@ -2341,7 +2349,7 @@ enum sctp_disposition sctp_sf_shutdown_pending_abort( */ if (SCTP_ADDR_DEL == sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); if (!sctp_err_chunk_valid(chunk)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); @@ -2387,7 +2395,7 @@ enum sctp_disposition sctp_sf_shutdown_sent_abort( */ if (SCTP_ADDR_DEL == sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); if (!sctp_err_chunk_valid(chunk)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); @@ -2657,7 +2665,7 @@ enum sctp_disposition sctp_sf_do_9_1_abort( */ if (SCTP_ADDR_DEL == sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); if (!sctp_err_chunk_valid(chunk)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); @@ -2970,13 +2978,11 @@ enum sctp_disposition sctp_sf_do_9_2_shut_ctsn( * that belong to this association, it should discard the INIT chunk and * retransmit the SHUTDOWN ACK chunk. */ -enum sctp_disposition sctp_sf_do_9_2_reshutack( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const union sctp_subtype type, - void *arg, - struct sctp_cmd_seq *commands) +static enum sctp_disposition +__sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_chunk *reply; @@ -3010,6 +3016,26 @@ nomem: return SCTP_DISPOSITION_NOMEM; } +enum sctp_disposition +sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, void *arg, + struct sctp_cmd_seq *commands) +{ + struct sctp_chunk *chunk = arg; + + if (!chunk->singleton) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + + if (chunk->sctp_hdr->vtag != 0) + return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); + + return __sctp_sf_do_9_2_reshutack(net, ep, asoc, type, arg, commands); +} + /* * sctp_sf_do_ecn_cwr * @@ -3662,6 +3688,9 @@ enum sctp_disposition sctp_sf_ootb(struct net *net, SCTP_INC_STATS(net, SCTP_MIB_OUTOFBLUES); + if (asoc && !sctp_vtag_verify(chunk, asoc)) + asoc = NULL; + ch = (struct sctp_chunkhdr *)chunk->chunk_hdr; do { /* Report violation if the chunk is less then minimal */ @@ -3777,12 +3806,6 @@ static enum sctp_disposition sctp_sf_shut_8_4_5( SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); - /* If the chunk length is invalid, we don't want to process - * the reset of the packet. - */ - if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - /* We need to discard the rest of the packet to prevent * potential boomming attacks from additional bundled chunks. * This is documented in SCTP Threats ID. @@ -3810,6 +3833,9 @@ enum sctp_disposition sctp_sf_do_8_5_1_E_sa(struct net *net, { struct sctp_chunk *chunk = arg; + if (!sctp_vtag_verify(chunk, asoc)) + asoc = NULL; + /* Make sure that the SHUTDOWN_ACK chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, @@ -3845,6 +3871,11 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net, return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } + /* Make sure that the ASCONF ADDIP chunk has a valid length. */ + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_addip_chunk))) + return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, + commands); + /* ADD-IP: Section 4.1.1 * This chunk MUST be sent in an authenticated way by using * the mechanism defined in [I-D.ietf-tsvwg-sctp-auth]. If this chunk @@ -3853,13 +3884,7 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net, */ if (!asoc->peer.asconf_capable || (!net->sctp.addip_noauth && !chunk->auth)) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, - commands); - - /* Make sure that the ASCONF ADDIP chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_addip_chunk))) - return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, - commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); hdr = (struct sctp_addiphdr *)chunk->skb->data; serial = ntohl(hdr->serial); @@ -3988,6 +4013,12 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net, return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } + /* Make sure that the ADDIP chunk has a valid length. */ + if (!sctp_chunk_length_valid(asconf_ack, + sizeof(struct sctp_addip_chunk))) + return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, + commands); + /* ADD-IP, Section 4.1.2: * This chunk MUST be sent in an authenticated way by using * the mechanism defined in [I-D.ietf-tsvwg-sctp-auth]. If this chunk @@ -3996,14 +4027,7 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net, */ if (!asoc->peer.asconf_capable || (!net->sctp.addip_noauth && !asconf_ack->auth)) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, - commands); - - /* Make sure that the ADDIP chunk has a valid length. */ - if (!sctp_chunk_length_valid(asconf_ack, - sizeof(struct sctp_addip_chunk))) - return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, - commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); addip_hdr = (struct sctp_addiphdr *)asconf_ack->skb->data; rcvd_serial = ntohl(addip_hdr->serial); @@ -4575,6 +4599,9 @@ enum sctp_disposition sctp_sf_discard_chunk(struct net *net, { struct sctp_chunk *chunk = arg; + if (asoc && !sctp_vtag_verify(chunk, asoc)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Make sure that the chunk has a valid length. * Since we don't know the chunk type, we use a general * chunkhdr structure to make a comparison. @@ -4642,6 +4669,9 @@ enum sctp_disposition sctp_sf_violation(struct net *net, { struct sctp_chunk *chunk = arg; + if (!sctp_vtag_verify(chunk, asoc)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Make sure that the chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, @@ -6348,6 +6378,7 @@ static struct sctp_packet *sctp_ootb_pkt_new( * yet. */ switch (chunk->chunk_hdr->type) { + case SCTP_CID_INIT: case SCTP_CID_INIT_ACK: { struct sctp_initack_chunk *initack; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 5e50e007a7da..8dc34388b2c1 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1185,7 +1185,7 @@ static void smc_connect_work(struct work_struct *work) if (smc->clcsock->sk->sk_err) { smc->sk.sk_err = smc->clcsock->sk->sk_err; } else if ((1 << smc->clcsock->sk->sk_state) & - (TCPF_SYN_SENT | TCP_SYN_RECV)) { + (TCPF_SYN_SENT | TCPF_SYN_RECV)) { rc = sk_stream_wait_connect(smc->clcsock->sk, &timeo); if ((rc == -EPIPE) && ((1 << smc->clcsock->sk->sk_state) & diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index a9623c952007..b102680296b8 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -2154,7 +2154,7 @@ void smc_llc_link_active(struct smc_link *link) link->smcibdev->ibdev->name, link->ibport); link->state = SMC_LNK_ACTIVE; if (link->lgr->llc_testlink_time) { - link->llc_testlink_time = link->lgr->llc_testlink_time * HZ; + link->llc_testlink_time = link->lgr->llc_testlink_time; schedule_delayed_work(&link->llc_testlink_wrk, link->llc_testlink_time); } diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index c9391d38de85..dc60c32bb70d 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -2285,43 +2285,53 @@ static bool tipc_crypto_key_rcv(struct tipc_crypto *rx, struct tipc_msg *hdr) u16 key_gen = msg_key_gen(hdr); u16 size = msg_data_sz(hdr); u8 *data = msg_data(hdr); + unsigned int keylen; + + /* Verify whether the size can exist in the packet */ + if (unlikely(size < sizeof(struct tipc_aead_key) + TIPC_AEAD_KEYLEN_MIN)) { + pr_debug("%s: message data size is too small\n", rx->name); + goto exit; + } + + keylen = ntohl(*((__be32 *)(data + TIPC_AEAD_ALG_NAME))); + + /* Verify the supplied size values */ + if (unlikely(size != keylen + sizeof(struct tipc_aead_key) || + keylen > TIPC_AEAD_KEY_SIZE_MAX)) { + pr_debug("%s: invalid MSG_CRYPTO key size\n", rx->name); + goto exit; + } spin_lock(&rx->lock); if (unlikely(rx->skey || (key_gen == rx->key_gen && rx->key.keys))) { pr_err("%s: key existed <%p>, gen %d vs %d\n", rx->name, rx->skey, key_gen, rx->key_gen); - goto exit; + goto exit_unlock; } /* Allocate memory for the key */ skey = kmalloc(size, GFP_ATOMIC); if (unlikely(!skey)) { pr_err("%s: unable to allocate memory for skey\n", rx->name); - goto exit; + goto exit_unlock; } /* Copy key from msg data */ - skey->keylen = ntohl(*((__be32 *)(data + TIPC_AEAD_ALG_NAME))); + skey->keylen = keylen; memcpy(skey->alg_name, data, TIPC_AEAD_ALG_NAME); memcpy(skey->key, data + TIPC_AEAD_ALG_NAME + sizeof(__be32), skey->keylen); - /* Sanity check */ - if (unlikely(size != tipc_aead_key_size(skey))) { - kfree(skey); - skey = NULL; - goto exit; - } - rx->key_gen = key_gen; rx->skey_mode = msg_key_mode(hdr); rx->skey = skey; rx->nokey = 0; mb(); /* for nokey flag */ -exit: +exit_unlock: spin_unlock(&rx->lock); +exit: /* Schedule the key attaching on this crypto */ if (likely(skey && queue_delayed_work(tx->wq, &rx->work, 0))) return true; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 278192ee133e..acfba9f1ba72 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -769,12 +769,12 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE]; prot[TLS_BASE][TLS_SW].recvmsg = tls_sw_recvmsg; - prot[TLS_BASE][TLS_SW].stream_memory_read = tls_sw_stream_read; + prot[TLS_BASE][TLS_SW].sock_is_readable = tls_sw_sock_is_readable; prot[TLS_BASE][TLS_SW].close = tls_sk_proto_close; prot[TLS_SW][TLS_SW] = prot[TLS_SW][TLS_BASE]; prot[TLS_SW][TLS_SW].recvmsg = tls_sw_recvmsg; - prot[TLS_SW][TLS_SW].stream_memory_read = tls_sw_stream_read; + prot[TLS_SW][TLS_SW].sock_is_readable = tls_sw_sock_is_readable; prot[TLS_SW][TLS_SW].close = tls_sk_proto_close; #ifdef CONFIG_TLS_DEVICE diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 4147bb2e7057..d81564078557 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -35,6 +35,7 @@ * SOFTWARE. */ +#include <linux/bug.h> #include <linux/sched/signal.h> #include <linux/module.h> #include <linux/splice.h> @@ -43,6 +44,14 @@ #include <net/strparser.h> #include <net/tls.h> +noinline void tls_err_abort(struct sock *sk, int err) +{ + WARN_ON_ONCE(err >= 0); + /* sk->sk_err should contain a positive error code. */ + sk->sk_err = -err; + sk_error_report(sk); +} + static int __skb_nsg(struct sk_buff *skb, int offset, int len, unsigned int recursion_level) { @@ -419,7 +428,7 @@ int tls_tx_records(struct sock *sk, int flags) tx_err: if (rc < 0 && rc != -EAGAIN) - tls_err_abort(sk, EBADMSG); + tls_err_abort(sk, -EBADMSG); return rc; } @@ -450,7 +459,7 @@ static void tls_encrypt_done(struct crypto_async_request *req, int err) /* If err is already set on socket, return the same code */ if (sk->sk_err) { - ctx->async_wait.err = sk->sk_err; + ctx->async_wait.err = -sk->sk_err; } else { ctx->async_wait.err = err; tls_err_abort(sk, err); @@ -769,7 +778,7 @@ static int tls_push_record(struct sock *sk, int flags, msg_pl->sg.size + prot->tail_size, i); if (rc < 0) { if (rc != -EINPROGRESS) { - tls_err_abort(sk, EBADMSG); + tls_err_abort(sk, -EBADMSG); if (split) { tls_ctx->pending_open_record_frags = true; tls_merge_open_record(sk, rec, tmp, orig_end); @@ -1839,7 +1848,7 @@ int tls_sw_recvmsg(struct sock *sk, err = decrypt_skb_update(sk, skb, &msg->msg_iter, &chunk, &zc, async_capable); if (err < 0 && err != -EINPROGRESS) { - tls_err_abort(sk, EBADMSG); + tls_err_abort(sk, -EBADMSG); goto recv_end; } @@ -2019,7 +2028,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, } if (err < 0) { - tls_err_abort(sk, EBADMSG); + tls_err_abort(sk, -EBADMSG); goto splice_read_end; } ctx->decrypted = 1; @@ -2038,7 +2047,7 @@ splice_read_end: return copied ? : err; } -bool tls_sw_stream_read(const struct sock *sk) +bool tls_sw_sock_is_readable(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 89f9e85ae970..78e08e82c08c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -3052,6 +3052,8 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa /* readable? */ if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; + if (sk_is_readable(sk)) + mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) && @@ -3091,6 +3093,8 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, /* readable? */ if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; + if (sk_is_readable(sk)) + mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ if (sk->sk_type == SOCK_SEQPACKET) { diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c index b927e2baae50..452376c6f419 100644 --- a/net/unix/unix_bpf.c +++ b/net/unix/unix_bpf.c @@ -102,6 +102,7 @@ static void unix_dgram_bpf_rebuild_protos(struct proto *prot, const struct proto *prot = *base; prot->close = sock_map_close; prot->recvmsg = unix_bpf_recvmsg; + prot->sock_is_readable = sk_msg_is_readable; } static void unix_stream_bpf_rebuild_protos(struct proto *prot, @@ -110,6 +111,7 @@ static void unix_stream_bpf_rebuild_protos(struct proto *prot, *prot = *base; prot->close = sock_map_close; prot->recvmsg = unix_bpf_recvmsg; + prot->sock_is_readable = sk_msg_is_readable; prot->unhash = sock_map_unhash; } diff --git a/net/wireless/core.c b/net/wireless/core.c index 45be124a98f1..eb297e1015e0 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -524,6 +524,7 @@ use_default_name: INIT_WORK(&rdev->propagate_cac_done_wk, cfg80211_propagate_cac_done_wk); INIT_WORK(&rdev->mgmt_registrations_update_wk, cfg80211_mgmt_registrations_update_wk); + spin_lock_init(&rdev->mgmt_registrations_lock); #ifdef CONFIG_CFG80211_DEFAULT_PS rdev->wiphy.flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT; @@ -1289,7 +1290,6 @@ void cfg80211_init_wdev(struct wireless_dev *wdev) INIT_LIST_HEAD(&wdev->event_list); spin_lock_init(&wdev->event_lock); INIT_LIST_HEAD(&wdev->mgmt_registrations); - spin_lock_init(&wdev->mgmt_registrations_lock); INIT_LIST_HEAD(&wdev->pmsr_list); spin_lock_init(&wdev->pmsr_lock); INIT_WORK(&wdev->pmsr_free_wk, cfg80211_pmsr_free_wk); diff --git a/net/wireless/core.h b/net/wireless/core.h index b35d0db12f1d..1720abf36f92 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -100,6 +100,8 @@ struct cfg80211_registered_device { struct work_struct propagate_cac_done_wk; struct work_struct mgmt_registrations_update_wk; + /* lock for all wdev lists */ + spinlock_t mgmt_registrations_lock; /* must be last because of the way we do wiphy_priv(), * and it should at least be aligned to NETDEV_ALIGN */ diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 3aa69b375a10..783acd2c4211 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -452,9 +452,9 @@ static void cfg80211_mgmt_registrations_update(struct wireless_dev *wdev) lockdep_assert_held(&rdev->wiphy.mtx); - spin_lock_bh(&wdev->mgmt_registrations_lock); + spin_lock_bh(&rdev->mgmt_registrations_lock); if (!wdev->mgmt_registrations_need_update) { - spin_unlock_bh(&wdev->mgmt_registrations_lock); + spin_unlock_bh(&rdev->mgmt_registrations_lock); return; } @@ -479,7 +479,7 @@ static void cfg80211_mgmt_registrations_update(struct wireless_dev *wdev) rcu_read_unlock(); wdev->mgmt_registrations_need_update = 0; - spin_unlock_bh(&wdev->mgmt_registrations_lock); + spin_unlock_bh(&rdev->mgmt_registrations_lock); rdev_update_mgmt_frame_registrations(rdev, wdev, &upd); } @@ -503,6 +503,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, int match_len, bool multicast_rx, struct netlink_ext_ack *extack) { + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_mgmt_registration *reg, *nreg; int err = 0; u16 mgmt_type; @@ -548,7 +549,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, if (!nreg) return -ENOMEM; - spin_lock_bh(&wdev->mgmt_registrations_lock); + spin_lock_bh(&rdev->mgmt_registrations_lock); list_for_each_entry(reg, &wdev->mgmt_registrations, list) { int mlen = min(match_len, reg->match_len); @@ -583,7 +584,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, list_add(&nreg->list, &wdev->mgmt_registrations); } wdev->mgmt_registrations_need_update = 1; - spin_unlock_bh(&wdev->mgmt_registrations_lock); + spin_unlock_bh(&rdev->mgmt_registrations_lock); cfg80211_mgmt_registrations_update(wdev); @@ -591,7 +592,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, out: kfree(nreg); - spin_unlock_bh(&wdev->mgmt_registrations_lock); + spin_unlock_bh(&rdev->mgmt_registrations_lock); return err; } @@ -602,7 +603,7 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid) struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); struct cfg80211_mgmt_registration *reg, *tmp; - spin_lock_bh(&wdev->mgmt_registrations_lock); + spin_lock_bh(&rdev->mgmt_registrations_lock); list_for_each_entry_safe(reg, tmp, &wdev->mgmt_registrations, list) { if (reg->nlportid != nlportid) @@ -615,7 +616,7 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid) schedule_work(&rdev->mgmt_registrations_update_wk); } - spin_unlock_bh(&wdev->mgmt_registrations_lock); + spin_unlock_bh(&rdev->mgmt_registrations_lock); if (nlportid && rdev->crit_proto_nlportid == nlportid) { rdev->crit_proto_nlportid = 0; @@ -628,15 +629,16 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid) void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev) { + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_mgmt_registration *reg, *tmp; - spin_lock_bh(&wdev->mgmt_registrations_lock); + spin_lock_bh(&rdev->mgmt_registrations_lock); list_for_each_entry_safe(reg, tmp, &wdev->mgmt_registrations, list) { list_del(®->list); kfree(reg); } wdev->mgmt_registrations_need_update = 1; - spin_unlock_bh(&wdev->mgmt_registrations_lock); + spin_unlock_bh(&rdev->mgmt_registrations_lock); cfg80211_mgmt_registrations_update(wdev); } @@ -784,7 +786,7 @@ bool cfg80211_rx_mgmt_khz(struct wireless_dev *wdev, int freq, int sig_dbm, data = buf + ieee80211_hdrlen(mgmt->frame_control); data_len = len - ieee80211_hdrlen(mgmt->frame_control); - spin_lock_bh(&wdev->mgmt_registrations_lock); + spin_lock_bh(&rdev->mgmt_registrations_lock); list_for_each_entry(reg, &wdev->mgmt_registrations, list) { if (reg->frame_type != ftype) @@ -808,7 +810,7 @@ bool cfg80211_rx_mgmt_khz(struct wireless_dev *wdev, int freq, int sig_dbm, break; } - spin_unlock_bh(&wdev->mgmt_registrations_lock); + spin_unlock_bh(&rdev->mgmt_registrations_lock); trace_cfg80211_return_bool(result); return result; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index e4f79b23f7f6..22e92be61938 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -418,14 +418,17 @@ cfg80211_add_nontrans_list(struct cfg80211_bss *trans_bss, } ssid_len = ssid[1]; ssid = ssid + 2; - rcu_read_unlock(); /* check if nontrans_bss is in the list */ list_for_each_entry(bss, &trans_bss->nontrans_list, nontrans_list) { - if (is_bss(bss, nontrans_bss->bssid, ssid, ssid_len)) + if (is_bss(bss, nontrans_bss->bssid, ssid, ssid_len)) { + rcu_read_unlock(); return 0; + } } + rcu_read_unlock(); + /* add to the list */ list_add_tail(&nontrans_bss->nontrans_list, &trans_bss->nontrans_list); return 0; diff --git a/net/wireless/util.c b/net/wireless/util.c index 2991f711491a..5ff1f8726faf 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1030,14 +1030,14 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, !(rdev->wiphy.interface_modes & (1 << ntype))) return -EOPNOTSUPP; - /* if it's part of a bridge, reject changing type to station/ibss */ - if (netif_is_bridge_port(dev) && - (ntype == NL80211_IFTYPE_ADHOC || - ntype == NL80211_IFTYPE_STATION || - ntype == NL80211_IFTYPE_P2P_CLIENT)) - return -EBUSY; - if (ntype != otype) { + /* if it's part of a bridge, reject changing type to station/ibss */ + if (netif_is_bridge_port(dev) && + (ntype == NL80211_IFTYPE_ADHOC || + ntype == NL80211_IFTYPE_STATION || + ntype == NL80211_IFTYPE_P2P_CLIENT)) + return -EBUSY; + dev->ieee80211_ptr->use_4addr = false; dev->ieee80211_ptr->mesh_id_up_len = 0; wdev_lock(dev->ieee80211_ptr); diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 5c5979046523..d88bb65b74cc 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -949,7 +949,6 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, int err, n; u32 key; char b; - int retries = 100; zero_verdict_count(verd_mapfd); @@ -1002,17 +1001,11 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, goto close_peer1; if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close_peer1: xclose(p1); @@ -1571,7 +1564,6 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd, const char *log_prefix = redir_mode_str(mode); int c0, c1, p0, p1; unsigned int pass; - int retries = 100; int err, n; int sfd[2]; u32 key; @@ -1606,17 +1598,11 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close: xclose(c1); @@ -1748,7 +1734,6 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd, const char *log_prefix = redir_mode_str(mode); int c0, c1, p0, p1; unsigned int pass; - int retries = 100; int err, n; u32 key; char b; @@ -1781,17 +1766,11 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close_cli1: xclose(c1); @@ -1841,7 +1820,6 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd, const char *log_prefix = redir_mode_str(mode); int c0, c1, p0, p1; unsigned int pass; - int retries = 100; int err, n; int sfd[2]; u32 key; @@ -1876,17 +1854,11 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close_cli1: xclose(c1); @@ -1932,7 +1904,6 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd, int sfd[2]; u32 key; char b; - int retries = 100; zero_verdict_count(verd_mapfd); @@ -1963,17 +1934,11 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close: xclose(c1); diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh index ade79ef08de3..071a33d10c20 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh @@ -6,7 +6,9 @@ ALL_TESTS=" test_root + test_port_tbf test_etsprio + test_etsprio_port_tbf " NUM_NETIFS=1 lib_dir=$(dirname $0)/../../../net/forwarding @@ -221,6 +223,12 @@ test_root() do_test_combinations 1 0 } +test_port_tbf() +{ + with_tbf 1: root \ + do_test_combinations 8 1 +} + do_test_etsprio() { local parent=$1; shift @@ -264,6 +272,12 @@ test_etsprio() do_test_etsprio root "" } +test_etsprio_port_tbf() +{ + with_tbf 1: root \ + do_test_etsprio "parent 1:1" "-TBF" +} + cleanup() { tc qdisc del dev $h1 root &>/dev/null diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 8e67a252b672..3313566ce906 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -445,10 +445,13 @@ cleanup() ip -netns ${NSA} link set dev ${NSA_DEV} down ip -netns ${NSA} link del dev ${NSA_DEV} + ip netns pids ${NSA} | xargs kill 2>/dev/null ip netns del ${NSA} fi + ip netns pids ${NSB} | xargs kill 2>/dev/null ip netns del ${NSB} + ip netns pids ${NSC} | xargs kill 2>/dev/null ip netns del ${NSC} >/dev/null 2>&1 } diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh b/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh index 8bd85da1905a..75a37c189ef3 100644 --- a/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh +++ b/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh @@ -4,9 +4,12 @@ ALL_TESTS=" ping_ipv4 tbf_test + tbf_root_test " source $lib_dir/sch_tbf_core.sh +QDISC_TYPE=${QDISC% *} + tbf_test_one() { local bs=$1; shift @@ -22,6 +25,8 @@ tbf_test_one() tbf_test() { + log_info "Testing root-$QDISC_TYPE-tbf" + # This test is used for both ETS and PRIO. Even though we only need two # bands, PRIO demands a minimum of three. tc qdisc add dev $swp2 root handle 10: $QDISC 3 priomap 2 1 0 @@ -29,6 +34,29 @@ tbf_test() tc qdisc del dev $swp2 root } +tbf_root_test() +{ + local bs=128K + + log_info "Testing root-tbf-$QDISC_TYPE" + + tc qdisc replace dev $swp2 root handle 1: \ + tbf rate 400Mbit burst $bs limit 1M + tc qdisc replace dev $swp2 parent 1:1 handle 10: \ + $QDISC 3 priomap 2 1 0 + tc qdisc replace dev $swp2 parent 10:3 handle 103: \ + bfifo limit 1M + tc qdisc replace dev $swp2 parent 10:2 handle 102: \ + bfifo limit 1M + tc qdisc replace dev $swp2 parent 10:1 handle 101: \ + bfifo limit 1M + + do_tbf_test 10 400 $bs + do_tbf_test 11 400 $bs + + tc qdisc del dev $swp2 root +} + trap cleanup EXIT setup_prepare |