diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index f2040d46f095..ff4ba249a26f 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4092,6 +4092,23 @@ expediting. Set to zero to disable automatic expediting. + ssbd= [ARM64,HW] + Speculative Store Bypass Disable control + + On CPUs that are vulnerable to the Speculative + Store Bypass vulnerability and offer a + firmware based mitigation, this parameter + indicates how the mitigation should be used: + + force-on: Unconditionally enable mitigation for + for both kernel and userspace + force-off: Unconditionally disable mitigation for + for both kernel and userspace + kernel: Always enable mitigation in the + kernel, and offer a prctl interface + to allow userspace to register its + interest in being mitigated too. + stack_guard_gap= [MM] override the default stack gap protection. The value is in page units and it defines how many pages prior diff --git a/Makefile b/Makefile index 7cc36fe18dbb..693fde3aa317 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 17 -SUBLEVEL = 8 +SUBLEVEL = 9 EXTRAVERSION = NAME = Merciless Moray diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index c7c28c885a19..7001fb871429 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -315,6 +315,18 @@ static inline bool kvm_arm_harden_branch_predictor(void) return false; } +#define KVM_SSBD_UNKNOWN -1 +#define KVM_SSBD_FORCE_DISABLE 0 +#define KVM_SSBD_KERNEL 1 +#define KVM_SSBD_FORCE_ENABLE 2 +#define KVM_SSBD_MITIGATED 3 + +static inline int kvm_arm_have_ssbd(void) +{ + /* No way to detect it yet, pretend it is not there. */ + return KVM_SSBD_UNKNOWN; +} + static inline void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu) {} diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index f675162663f0..d2eb24eccf8f 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -335,6 +335,11 @@ static inline int kvm_map_vectors(void) return 0; } +static inline int hyp_map_aux_data(void) +{ + return 0; +} + #define kvm_phys_to_vttbr(addr) (addr) #endif /* !__ASSEMBLY__ */ diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index b5030e1a41d8..5539fba892ce 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -1928,7 +1928,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) /* there are 2 passes here */ bpf_jit_dump(prog->len, image_size, 2, ctx.target); - set_memory_ro((unsigned long)header, header->pages); + bpf_jit_binary_lock_ro(header); prog->bpf_func = (void *)ctx.target; prog->jited = 1; prog->jited_len = image_size; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index eb2cf4938f6d..b2103b4df467 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -938,6 +938,15 @@ config HARDEN_EL2_VECTORS If unsure, say Y. +config ARM64_SSBD + bool "Speculative Store Bypass Disable" if EXPERT + default y + help + This enables mitigation of the bypassing of previous stores + by speculative loads. + + If unsure, say Y. + menuconfig ARMV8_DEPRECATED bool "Emulate deprecated/obsolete ARMv8 instructions" depends on COMPAT diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index bc51b72fafd4..8a699c708fc9 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -48,7 +48,8 @@ #define ARM64_HAS_CACHE_IDC 27 #define ARM64_HAS_CACHE_DIC 28 #define ARM64_HW_DBM 29 +#define ARM64_SSBD 30 -#define ARM64_NCAPS 30 +#define ARM64_NCAPS 31 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 09b0f2a80c8f..55bc1f073bfb 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -537,6 +537,28 @@ static inline u64 read_zcr_features(void) return zcr; } +#define ARM64_SSBD_UNKNOWN -1 +#define ARM64_SSBD_FORCE_DISABLE 0 +#define ARM64_SSBD_KERNEL 1 +#define ARM64_SSBD_FORCE_ENABLE 2 +#define ARM64_SSBD_MITIGATED 3 + +static inline int arm64_get_ssbd_state(void) +{ +#ifdef CONFIG_ARM64_SSBD + extern int ssbd_state; + return ssbd_state; +#else + return ARM64_SSBD_UNKNOWN; +#endif +} + +#ifdef CONFIG_ARM64_SSBD +void arm64_set_ssbd_mitigation(bool state); +#else +static inline void arm64_set_ssbd_mitigation(bool state) {} +#endif + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index f6648a3e4152..d4fbb1356c4c 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -33,6 +33,9 @@ #define KVM_ARM64_DEBUG_DIRTY_SHIFT 0 #define KVM_ARM64_DEBUG_DIRTY (1 << KVM_ARM64_DEBUG_DIRTY_SHIFT) +#define VCPU_WORKAROUND_2_FLAG_SHIFT 0 +#define VCPU_WORKAROUND_2_FLAG (_AC(1, UL) << VCPU_WORKAROUND_2_FLAG_SHIFT) + /* Translate a kernel address of @sym into its equivalent linear mapping */ #define kvm_ksym_ref(sym) \ ({ \ @@ -71,14 +74,37 @@ extern u32 __kvm_get_mdcr_el2(void); extern u32 __init_stage2_translation(void); +/* Home-grown __this_cpu_{ptr,read} variants that always work at HYP */ +#define __hyp_this_cpu_ptr(sym) \ + ({ \ + void *__ptr = hyp_symbol_addr(sym); \ + __ptr += read_sysreg(tpidr_el2); \ + (typeof(&sym))__ptr; \ + }) + +#define __hyp_this_cpu_read(sym) \ + ({ \ + *__hyp_this_cpu_ptr(sym); \ + }) + #else /* __ASSEMBLY__ */ -.macro get_host_ctxt reg, tmp - adr_l \reg, kvm_host_cpu_state +.macro hyp_adr_this_cpu reg, sym, tmp + adr_l \reg, \sym mrs \tmp, tpidr_el2 add \reg, \reg, \tmp .endm +.macro hyp_ldr_this_cpu reg, sym, tmp + adr_l \reg, \sym + mrs \tmp, tpidr_el2 + ldr \reg, [\reg, \tmp] +.endm + +.macro get_host_ctxt reg, tmp + hyp_adr_this_cpu \reg, kvm_host_cpu_state, \tmp +.endm + .macro get_vcpu_ptr vcpu, ctxt get_host_ctxt \ctxt, \vcpu ldr \vcpu, [\ctxt, #HOST_CONTEXT_VCPU] diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 469de8acd06f..95d8a0e15b5f 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -216,6 +216,9 @@ struct kvm_vcpu_arch { /* Exception Information */ struct kvm_vcpu_fault_info fault; + /* State of various workarounds, see kvm_asm.h for bit assignment */ + u64 workaround_flags; + /* Guest debug state */ u64 debug_flags; @@ -452,6 +455,29 @@ static inline bool kvm_arm_harden_branch_predictor(void) return cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR); } +#define KVM_SSBD_UNKNOWN -1 +#define KVM_SSBD_FORCE_DISABLE 0 +#define KVM_SSBD_KERNEL 1 +#define KVM_SSBD_FORCE_ENABLE 2 +#define KVM_SSBD_MITIGATED 3 + +static inline int kvm_arm_have_ssbd(void) +{ + switch (arm64_get_ssbd_state()) { + case ARM64_SSBD_FORCE_DISABLE: + return KVM_SSBD_FORCE_DISABLE; + case ARM64_SSBD_KERNEL: + return KVM_SSBD_KERNEL; + case ARM64_SSBD_FORCE_ENABLE: + return KVM_SSBD_FORCE_ENABLE; + case ARM64_SSBD_MITIGATED: + return KVM_SSBD_MITIGATED; + case ARM64_SSBD_UNKNOWN: + default: + return KVM_SSBD_UNKNOWN; + } +} + void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu); void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 6128992c2ded..e3b2ad7dd40a 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -473,6 +473,30 @@ static inline int kvm_map_vectors(void) } #endif +#ifdef CONFIG_ARM64_SSBD +DECLARE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required); + +static inline int hyp_map_aux_data(void) +{ + int cpu, err; + + for_each_possible_cpu(cpu) { + u64 *ptr; + + ptr = per_cpu_ptr(&arm64_ssbd_callback_required, cpu); + err = create_hyp_mappings(ptr, ptr + 1, PAGE_HYP); + if (err) + return err; + } + return 0; +} +#else +static inline int hyp_map_aux_data(void) +{ + return 0; +} +#endif + #define kvm_phys_to_vttbr(addr) phys_to_ttbr(addr) #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 740aa03c5f0d..cbcf11b5e637 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -94,6 +94,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define TIF_32BIT 22 /* 32bit process */ #define TIF_SVE 23 /* Scalable Vector Extension in use */ #define TIF_SVE_VL_INHERIT 24 /* Inherit sve_vl_onexec across exec */ +#define TIF_SSBD 25 /* Wants SSB mitigation */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index bf825f38d206..0025f8691046 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -54,6 +54,7 @@ arm64-obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o arm64-obj-$(CONFIG_CRASH_DUMP) += crash_dump.o arm64-obj-$(CONFIG_ARM_SDE_INTERFACE) += sdei.o +arm64-obj-$(CONFIG_ARM64_SSBD) += ssbd.o obj-y += $(arm64-obj-y) vdso/ probes/ obj-m += $(arm64-obj-m) diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 5bdda651bd05..323aeb5f2fe6 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -136,6 +136,7 @@ int main(void) #ifdef CONFIG_KVM_ARM_HOST DEFINE(VCPU_CONTEXT, offsetof(struct kvm_vcpu, arch.ctxt)); DEFINE(VCPU_FAULT_DISR, offsetof(struct kvm_vcpu, arch.fault.disr_el1)); + DEFINE(VCPU_WORKAROUND_FLAGS, offsetof(struct kvm_vcpu, arch.workaround_flags)); DEFINE(CPU_GP_REGS, offsetof(struct kvm_cpu_context, gp_regs)); DEFINE(CPU_USER_PT_REGS, offsetof(struct kvm_regs, regs)); DEFINE(CPU_FP_REGS, offsetof(struct kvm_regs, fp_regs)); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index e4a1182deff7..2b9a31a6a16a 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -232,6 +232,178 @@ enable_smccc_arch_workaround_1(const struct arm64_cpu_capabilities *entry) } #endif /* CONFIG_HARDEN_BRANCH_PREDICTOR */ +#ifdef CONFIG_ARM64_SSBD +DEFINE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required); + +int ssbd_state __read_mostly = ARM64_SSBD_KERNEL; + +static const struct ssbd_options { + const char *str; + int state; +} ssbd_options[] = { + { "force-on", ARM64_SSBD_FORCE_ENABLE, }, + { "force-off", ARM64_SSBD_FORCE_DISABLE, }, + { "kernel", ARM64_SSBD_KERNEL, }, +}; + +static int __init ssbd_cfg(char *buf) +{ + int i; + + if (!buf || !buf[0]) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(ssbd_options); i++) { + int len = strlen(ssbd_options[i].str); + + if (strncmp(buf, ssbd_options[i].str, len)) + continue; + + ssbd_state = ssbd_options[i].state; + return 0; + } + + return -EINVAL; +} +early_param("ssbd", ssbd_cfg); + +void __init arm64_update_smccc_conduit(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, + int nr_inst) +{ + u32 insn; + + BUG_ON(nr_inst != 1); + + switch (psci_ops.conduit) { + case PSCI_CONDUIT_HVC: + insn = aarch64_insn_get_hvc_value(); + break; + case PSCI_CONDUIT_SMC: + insn = aarch64_insn_get_smc_value(); + break; + default: + return; + } + + *updptr = cpu_to_le32(insn); +} + +void __init arm64_enable_wa2_handling(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, + int nr_inst) +{ + BUG_ON(nr_inst != 1); + /* + * Only allow mitigation on EL1 entry/exit and guest + * ARCH_WORKAROUND_2 handling if the SSBD state allows it to + * be flipped. + */ + if (arm64_get_ssbd_state() == ARM64_SSBD_KERNEL) + *updptr = cpu_to_le32(aarch64_insn_gen_nop()); +} + +void arm64_set_ssbd_mitigation(bool state) +{ + switch (psci_ops.conduit) { + case PSCI_CONDUIT_HVC: + arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL); + break; + + case PSCI_CONDUIT_SMC: + arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL); + break; + + default: + WARN_ON_ONCE(1); + break; + } +} + +static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, + int scope) +{ + struct arm_smccc_res res; + bool required = true; + s32 val; + + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + + if (psci_ops.smccc_version == SMCCC_VERSION_1_0) { + ssbd_state = ARM64_SSBD_UNKNOWN; + return false; + } + + switch (psci_ops.conduit) { + case PSCI_CONDUIT_HVC: + arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_2, &res); + break; + + case PSCI_CONDUIT_SMC: + arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_2, &res); + break; + + default: + ssbd_state = ARM64_SSBD_UNKNOWN; + return false; + } + + val = (s32)res.a0; + + switch (val) { + case SMCCC_RET_NOT_SUPPORTED: + ssbd_state = ARM64_SSBD_UNKNOWN; + return false; + + case SMCCC_RET_NOT_REQUIRED: + pr_info_once("%s mitigation not required\n", entry->desc); + ssbd_state = ARM64_SSBD_MITIGATED; + return false; + + case SMCCC_RET_SUCCESS: + required = true; + break; + + case 1: /* Mitigation not required on this CPU */ + required = false; + break; + + default: + WARN_ON(1); + return false; + } + + switch (ssbd_state) { + case ARM64_SSBD_FORCE_DISABLE: + pr_info_once("%s disabled from command-line\n", entry->desc); + arm64_set_ssbd_mitigation(false); + required = false; + break; + + case ARM64_SSBD_KERNEL: + if (required) { + __this_cpu_write(arm64_ssbd_callback_required, 1); + arm64_set_ssbd_mitigation(true); + } + break; + + case ARM64_SSBD_FORCE_ENABLE: + pr_info_once("%s forced from command-line\n", entry->desc); + arm64_set_ssbd_mitigation(true); + required = true; + break; + + default: + WARN_ON(1); + break; + } + + return required; +} +#endif /* CONFIG_ARM64_SSBD */ + #define CAP_MIDR_RANGE(model, v_min, r_min, v_max, r_max) \ .matches = is_affected_midr_range, \ .midr_range = MIDR_RANGE(model, v_min, r_min, v_max, r_max) @@ -487,6 +659,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors), }, +#endif +#ifdef CONFIG_ARM64_SSBD + { + .desc = "Speculative Store Bypass Disable", + .capability = ARM64_SSBD, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = has_ssbd_mitigation, + }, #endif { } diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index ec2ee720e33e..28ad8799406f 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -18,6 +18,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/arm-smccc.h> #include <linux/init.h> #include <linux/linkage.h> @@ -137,6 +138,25 @@ alternative_else_nop_endif add \dst, \dst, #(\sym - .entry.tramp.text) .endm + // This macro corrupts x0-x3. It is the caller's duty + // to save/restore them if required. + .macro apply_ssbd, state, targ, tmp1, tmp2 +#ifdef CONFIG_ARM64_SSBD +alternative_cb arm64_enable_wa2_handling + b \targ +alternative_cb_end + ldr_this_cpu \tmp2, arm64_ssbd_callback_required, \tmp1 + cbz \tmp2, \targ + ldr \tmp2, [tsk, #TSK_TI_FLAGS] + tbnz \tmp2, #TIF_SSBD, \targ + mov w0, #ARM_SMCCC_ARCH_WORKAROUND_2 + mov w1, #\state +alternative_cb arm64_update_smccc_conduit + nop // Patched to SMC/HVC #0 +alternative_cb_end +#endif + .endm + .macro kernel_entry, el, regsize = 64 .if \regsize == 32 mov w0, w0 // zero upper 32 bits of x0 @@ -163,6 +183,14 @@ alternative_else_nop_endif ldr x19, [tsk, #TSK_TI_FLAGS] // since we can unmask debug disable_step_tsk x19, x20 // exceptions when scheduling. + apply_ssbd 1, 1f, x22, x23 + +#ifdef CONFIG_ARM64_SSBD + ldp x0, x1, [sp, #16 * 0] + ldp x2, x3, [sp, #16 * 1] +#endif +1: + mov x29, xzr // fp pointed to user-space .else add x21, sp, #S_FRAME_SIZE @@ -303,6 +331,8 @@ alternative_if ARM64_WORKAROUND_845719 alternative_else_nop_endif #endif 3: + apply_ssbd 0, 5f, x0, x1 +5: .endif msr elr_el1, x21 // set up the return data diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 1ec5f28c39fc..6b2686d54411 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -313,6 +313,17 @@ int swsusp_arch_suspend(void) sleep_cpu = -EINVAL; __cpu_suspend_exit(); + + /* + * Just in case the boot kernel did turn the SSBD + * mitigation off behind our back, let's set the state + * to what we expect it to be. + */ + switch (arm64_get_ssbd_state()) { + case ARM64_SSBD_FORCE_ENABLE: + case ARM64_SSBD_KERNEL: + arm64_set_ssbd_mitigation(true); + } } local_daif_restore(flags); diff --git a/arch/arm64/kernel/ssbd.c b/arch/arm64/kernel/ssbd.c new file mode 100644 index 000000000000..3432e5ef9f41 --- /dev/null +++ b/arch/arm64/kernel/ssbd.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2018 ARM Ltd, All Rights Reserved. + */ + +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/thread_info.h> + +#include <asm/cpufeature.h> + +/* + * prctl interface for SSBD + * FIXME: Drop the below ifdefery once merged in 4.18. + */ +#ifdef PR_SPEC_STORE_BYPASS +static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl) +{ + int state = arm64_get_ssbd_state(); + + /* Unsupported */ + if (state == ARM64_SSBD_UNKNOWN) + return -EINVAL; + + /* Treat the unaffected/mitigated state separately */ + if (state == ARM64_SSBD_MITIGATED) { + switch (ctrl) { + case PR_SPEC_ENABLE: + return -EPERM; + case PR_SPEC_DISABLE: + case PR_SPEC_FORCE_DISABLE: + return 0; + } + } + + /* + * Things are a bit backward here: the arm64 internal API + * *enables the mitigation* when the userspace API *disables + * speculation*. So much fun. + */ + switch (ctrl) { + case PR_SPEC_ENABLE: + /* If speculation is force disabled, enable is not allowed */ + if (state == ARM64_SSBD_FORCE_ENABLE || + task_spec_ssb_force_disable(task)) + return -EPERM; + task_clear_spec_ssb_disable(task); + clear_tsk_thread_flag(task, TIF_SSBD); + break; + case PR_SPEC_DISABLE: + if (state == ARM64_SSBD_FORCE_DISABLE) + return -EPERM; + task_set_spec_ssb_disable(task); + set_tsk_thread_flag(task, TIF_SSBD); + break; + case PR_SPEC_FORCE_DISABLE: + if (state == ARM64_SSBD_FORCE_DISABLE) + return -EPERM; + task_set_spec_ssb_disable(task); + task_set_spec_ssb_force_disable(task); + set_tsk_thread_flag(task, TIF_SSBD); + break; + default: + return -ERANGE; + } + + return 0; +} + +int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, + unsigned long ctrl) +{ + switch (which) { + case PR_SPEC_STORE_BYPASS: + return ssbd_prctl_set(task, ctrl); + default: + return -ENODEV; + } +} + +static int ssbd_prctl_get(struct task_struct *task) +{ + switch (arm64_get_ssbd_state()) { + case ARM64_SSBD_UNKNOWN: + return -EINVAL; + case ARM64_SSBD_FORCE_ENABLE: + return PR_SPEC_DISABLE; + case ARM64_SSBD_KERNEL: + if (task_spec_ssb_force_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; + if (task_spec_ssb_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_DISABLE; + return PR_SPEC_PRCTL | PR_SPEC_ENABLE; + case ARM64_SSBD_FORCE_DISABLE: + return PR_SPEC_ENABLE; + default: + return PR_SPEC_NOT_AFFECTED; + } +} + +int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) +{ + switch (which) { + case PR_SPEC_STORE_BYPASS: + return ssbd_prctl_get(task); + default: + return -ENODEV; + } +} +#endif /* PR_SPEC_STORE_BYPASS */ diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index a307b9e13392..70c283368b64 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -62,6 +62,14 @@ void notrace __cpu_suspend_exit(void) */ if (hw_breakpoint_restore) hw_breakpoint_restore(cpu); + + /* + * On resume, firmware implementing dynamic mitigation will + * have turned the mitigation on. If the user has forcefully + * disabled it, make sure their wishes are obeyed. + */ + if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) + arm64_set_ssbd_mitigation(false); } /* diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index bffece27b5c1..05d836979032 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -106,8 +106,44 @@ el1_hvc_guest: */ ldr x1, [sp] // Guest's x0 eor w1, w1, #ARM_SMCCC_ARCH_WORKAROUND_1 + cbz w1, wa_epilogue + + /* ARM_SMCCC_ARCH_WORKAROUND_2 handling */ + eor w1, w1, #(ARM_SMCCC_ARCH_WORKAROUND_1 ^ \ + ARM_SMCCC_ARCH_WORKAROUND_2) cbnz w1, el1_trap - mov x0, x1 + +#ifdef CONFIG_ARM64_SSBD +alternative_cb arm64_enable_wa2_handling + b wa2_end +alternative_cb_end + get_vcpu_ptr x2, x0 + ldr x0, [x2, #VCPU_WORKAROUND_FLAGS] + + // Sanitize the argument and update the guest flags + ldr x1, [sp, #8] // Guest's x1 + clz w1, w1 // Murphy's device: + lsr w1, w1, #5 // w1 = !!w1 without using + eor w1, w1, #1 // the flags... + bfi x0, x1, #VCPU_WORKAROUND_2_FLAG_SHIFT, #1 + str x0, [x2, #VCPU_WORKAROUND_FLAGS] + + /* Check that we actually need to perform the call */ + hyp_ldr_this_cpu x0, arm64_ssbd_callback_required, x2 + cbz x0, wa2_end + + mov w0, #ARM_SMCCC_ARCH_WORKAROUND_2 + smc #0 + + /* Don't leak data from the SMC call */ + mov x3, xzr +wa2_end: + mov x2, xzr + mov x1, xzr +#endif + +wa_epilogue: + mov x0, xzr add sp, sp, #16 eret diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index d9645236e474..c50cedc447f1 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -15,6 +15,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/arm-smccc.h> #include <linux/types.h> #include <linux/jump_label.h> #include <uapi/linux/psci.h> @@ -389,6 +390,39 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) return false; } +static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu) +{ + if (!cpus_have_const_cap(ARM64_SSBD)) + return false; + + return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG); +} + +static void __hyp_text __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_ARM64_SSBD + /* + * The host runs with the workaround always present. If the + * guest wants it disabled, so be it... + */ + if (__needs_ssbd_off(vcpu) && + __hyp_this_cpu_read(arm64_ssbd_callback_required)) + arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 0, NULL); +#endif +} + +static void __hyp_text __set_host_arch_workaround_state(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_ARM64_SSBD + /* + * If the guest has disabled the workaround, bring it back on. + */ + if (__needs_ssbd_off(vcpu) && + __hyp_this_cpu_read(arm64_ssbd_callback_required)) + arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 1, NULL); +#endif +} + /* Switch to the guest for VHE systems running in EL2 */ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) { @@ -409,6 +443,8 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) sysreg_restore_guest_state_vhe(guest_ctxt); __debug_switch_to_guest(vcpu); + __set_guest_arch_workaround_state(vcpu); + do { /* Jump in the fire! */ exit_code = __guest_enter(vcpu, host_ctxt); @@ -416,6 +452,8 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) /* And we're baaack! */ } while (fixup_guest_exit(vcpu, &exit_code)); + __set_host_arch_workaround_state(vcpu); + fp_enabled = fpsimd_enabled_vhe(); sysreg_save_guest_state_vhe(guest_ctxt); @@ -465,6 +503,8 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) __sysreg_restore_state_nvhe(guest_ctxt); __debug_switch_to_guest(vcpu); + __set_guest_arch_workaround_state(vcpu); + do { /* Jump in the fire! */ exit_code = __guest_enter(vcpu, host_ctxt); @@ -472,6 +512,8 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) /* And we're baaack! */ } while (fixup_guest_exit(vcpu, &exit_code)); + __set_host_arch_workaround_state(vcpu); + fp_enabled = __fpsimd_enabled_nvhe(); __sysreg_save_state_nvhe(guest_ctxt); diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 3256b9228e75..a74311beda35 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -122,6 +122,10 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) /* Reset PMU */ kvm_pmu_vcpu_reset(vcpu); + /* Default workaround setup is enabled (if supported) */ + if (kvm_arm_have_ssbd() == KVM_SSBD_KERNEL) + vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG; + /* Reset timer */ return kvm_timer_vcpu_reset(vcpu); } diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 219faaec51df..990770f9e76b 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -46,6 +46,65 @@ #define _ASM_SI __ASM_REG(si) #define _ASM_DI __ASM_REG(di) +#ifndef __x86_64__ +/* 32 bit */ + +#define _ASM_ARG1 _ASM_AX +#define _ASM_ARG2 _ASM_DX +#define _ASM_ARG3 _ASM_CX + +#define _ASM_ARG1L eax +#define _ASM_ARG2L edx +#define _ASM_ARG3L ecx + +#define _ASM_ARG1W ax +#define _ASM_ARG2W dx +#define _ASM_ARG3W cx + +#define _ASM_ARG1B al +#define _ASM_ARG2B dl +#define _ASM_ARG3B cl + +#else +/* 64 bit */ + +#define _ASM_ARG1 _ASM_DI +#define _ASM_ARG2 _ASM_SI +#define _ASM_ARG3 _ASM_DX +#define _ASM_ARG4 _ASM_CX +#define _ASM_ARG5 r8 +#define _ASM_ARG6 r9 + +#define _ASM_ARG1Q rdi +#define _ASM_ARG2Q rsi +#define _ASM_ARG3Q rdx +#define _ASM_ARG4Q rcx +#define _ASM_ARG5Q r8 +#define _ASM_ARG6Q r9 + +#define _ASM_ARG1L edi +#define _ASM_ARG2L esi +#define _ASM_ARG3L edx +#define _ASM_ARG4L ecx +#define _ASM_ARG5L r8d +#define _ASM_ARG6L r9d + +#define _ASM_ARG1W di +#define _ASM_ARG2W si +#define _ASM_ARG3W dx +#define _ASM_ARG4W cx +#define _ASM_ARG5W r8w +#define _ASM_ARG6W r9w + +#define _ASM_ARG1B dil +#define _ASM_ARG2B sil +#define _ASM_ARG3B dl +#define _ASM_ARG4B cl +#define _ASM_ARG5B r8b +#define _ASM_ARG6B r9b + +#endif + /* * Macros to generate condition code outputs from inline assembly, * The output operand must be type "bool". diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 89f08955fff7..c4fc17220df9 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -13,7 +13,7 @@ * Interrupt control: */ -static inline unsigned long native_save_fl(void) +extern inline unsigned long native_save_fl(void) { unsigned long flags; diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 02d6f5cf4e70..8824d01c0c35 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -61,6 +61,7 @@ obj-y += alternative.o i8253.o hw_breakpoint.o obj-y += tsc.o tsc_msr.o io_delay.o rtc.o obj-y += pci-iommu_table.o obj-y += resource.o +obj-y += irqflags.o obj-y += process.o obj-y += fpu/ diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S new file mode 100644 index 000000000000..ddeeaac8adda --- /dev/null +++ b/arch/x86/kernel/irqflags.S @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <asm/asm.h> +#include <asm/export.h> +#include <linux/linkage.h> + +/* + * unsigned long native_save_fl(void) + */ +ENTRY(native_save_fl) + pushf + pop %_ASM_AX + ret +ENDPROC(native_save_fl) +EXPORT_SYMBOL(native_save_fl) + +/* + * void native_restore_fl(unsigned long flags) + * %eax/%rdi: flags + */ +ENTRY(native_restore_fl) + push %_ASM_ARG1 + popf + ret +ENDPROC(native_restore_fl) +EXPORT_SYMBOL(native_restore_fl) diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 92fd433c50b9..1bbec387d289 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -85,7 +85,7 @@ config KVM_AMD_SEV def_bool y bool "AMD Secure Encrypted Virtualization (SEV) support" depends on KVM_AMD && X86_64 - depends on CRYPTO_DEV_CCP && CRYPTO_DEV_CCP_DD && CRYPTO_DEV_SP_PSP + depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m) ---help--- Provides support for launching Encrypted VMs on AMD processors. diff --git a/block/blk-core.c b/block/blk-core.c index b559b9d4f1a2..47ab2d9d02d9 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2392,7 +2392,9 @@ blk_qc_t generic_make_request(struct bio *bio) if (bio->bi_opf & REQ_NOWAIT) flags = BLK_MQ_REQ_NOWAIT; - if (blk_queue_enter(q, flags) < 0) { + if (bio_flagged(bio, BIO_QUEUE_ENTERED)) + blk_queue_enter_live(q); + else if (blk_queue_enter(q, flags) < 0) { if (!blk_queue_dying(q) && (bio->bi_opf & REQ_NOWAIT)) bio_wouldblock_error(bio); else diff --git a/block/blk-merge.c b/block/blk-merge.c index 782940c65d8a..481dc02668f9 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -210,6 +210,16 @@ void blk_queue_split(struct request_queue *q, struct bio **bio) /* there isn't chance to merge the splitted bio */ split->bi_opf |= REQ_NOMERGE; + /* + * Since we're recursing into make_request here, ensure + * that we mark this bio as already having entered the queue. + * If not, and the queue is going away, we can get stuck + * forever on waiting for the queue reference to drop. But + * that will never happen, as we're already holding a + * reference to it. + */ + bio_set_flag(*bio, BIO_QUEUE_ENTERED); + bio_chain(split, *bio); trace_block_split(q, split, (*bio)->bi_iter.bi_sector); generic_make_request(*bio); diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 7846c0c20cfe..b52a14fc3bae 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -1156,8 +1156,10 @@ int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags, /* make one iovec available as scatterlist */ err = af_alg_make_sg(&rsgl->sgl, &msg->msg_iter, seglen); - if (err < 0) + if (err < 0) { + rsgl->sg_num_bytes = 0; return err; + } /* chain the new scatterlist with previous one */ if (areq->last_rsgl) diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c index a8d2eb0ceb8d..2c288d1f42bb 100644 --- a/drivers/atm/zatm.c +++ b/drivers/atm/zatm.c @@ -1483,6 +1483,8 @@ static int zatm_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg) return -EFAULT; if (pool < 0 || pool > ZATM_LAST_POOL) return -EINVAL; + pool = array_index_nospec(pool, + ZATM_LAST_POOL + 1); if (copy_from_user(&info, &((struct zatm_pool_req __user *) arg)->info, sizeof(info))) return -EFAULT; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 69716a7ea993..95a516ac6c39 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -5736,7 +5736,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) dev->num_ports = max(MLX5_CAP_GEN(mdev, num_ports), MLX5_CAP_GEN(mdev, num_vhca_ports)); - if (MLX5_VPORT_MANAGER(mdev) && + if (MLX5_ESWITCH_MANAGER(mdev) && mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) { dev->rep = mlx5_ib_vport_rep(mdev->priv.eswitch, 0); diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 567ee54504bc..5e5022fa1d04 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1897,13 +1897,19 @@ static int alx_resume(struct device *dev) struct pci_dev *pdev = to_pci_dev(dev); struct alx_priv *alx = pci_get_drvdata(pdev); struct alx_hw *hw = &alx->hw; + int err; alx_reset_phy(hw); if (!netif_running(alx->dev)) return 0; netif_device_attach(alx->dev); - return __alx_open(alx, true); + + rtnl_lock(); + err = __alx_open(alx, true); + rtnl_unlock(); + + return err; } static SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume); diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index b4c9268100bb..068f991395dc 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -3732,6 +3732,8 @@ static int at91ether_init(struct platform_device *pdev) int err; u32 reg; + bp->queues[0].bp = bp; + dev->netdev_ops = &at91ether_netdev_ops; dev->ethtool_ops = &macb_ethtool_ops; diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c index 2220c771092b..678835136bf8 100644 --- a/drivers/net/ethernet/cadence/macb_ptp.c +++ b/drivers/net/ethernet/cadence/macb_ptp.c @@ -170,10 +170,7 @@ static int gem_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) if (delta > TSU_NSEC_MAX_VAL) { gem_tsu_get_time(&bp->ptp_clock_info, &now); - if (sign) - now = timespec64_sub(now, then); - else - now = timespec64_add(now, then); + now = timespec64_add(now, then); gem_tsu_set_time(&bp->ptp_clock_info, (const struct timespec64 *)&now); diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 2edfdbdaae48..b25fd543b6f0 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -51,6 +51,7 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/uaccess.h> +#include <linux/nospec.h> #include "common.h" #include "cxgb3_ioctl.h" @@ -2268,6 +2269,7 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) if (t.qset_idx >= nqsets) return -EINVAL; + t.qset_idx = array_index_nospec(t.qset_idx, nqsets); q = &adapter->params.sge.qset[q1 + t.qset_idx]; t.rspq_size = q->rspq_size; diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 8a8b12b720ef..454e57ef047a 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1920,7 +1920,7 @@ static int enic_open(struct net_device *netdev) { struct enic *enic = netdev_priv(netdev); unsigned int i; - int err; + int err, ret; err = enic_request_intr(enic); if (err) { @@ -1977,10 +1977,9 @@ static int enic_open(struct net_device *netdev) err_out_free_rq: for (i = 0; i < enic->rq_count; i++) { - err = vnic_rq_disable(&enic->rq[i]); - if (err) - return err; - vnic_rq_clean(&enic->rq[i], enic_free_rq_buf); + ret = vnic_rq_disable(&enic->rq[i]); + if (!ret) + vnic_rq_clean(&enic->rq[i], enic_free_rq_buf); } enic_dev_notify_unset(enic); err_out_free_intr: diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c index e2e5cdc7119c..4c0f7eda1166 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c @@ -439,6 +439,7 @@ static void rx_free_irq(struct hinic_rxq *rxq) { struct hinic_rq *rq = rxq->rq; + irq_set_affinity_hint(rq->irq, NULL); free_irq(rq->irq, rxq); rx_del_napi(rxq); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index f174c72480ab..8d3522c94c3f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2199,9 +2199,10 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, return true; } -#define I40E_XDP_PASS 0 -#define I40E_XDP_CONSUMED 1 -#define I40E_XDP_TX 2 +#define I40E_XDP_PASS 0 +#define I40E_XDP_CONSUMED BIT(0) +#define I40E_XDP_TX BIT(1) +#define I40E_XDP_REDIR BIT(2) static int i40e_xmit_xdp_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring); @@ -2235,7 +2236,7 @@ static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring, break; case XDP_REDIRECT: err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? I40E_XDP_TX : I40E_XDP_CONSUMED; + result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED; break; default: bpf_warn_invalid_xdp_action(act); @@ -2298,7 +2299,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) unsigned int total_rx_bytes = 0, total_rx_packets = 0; struct sk_buff *skb = rx_ring->skb; u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); - bool failure = false, xdp_xmit = false; + unsigned int xdp_xmit = 0; + bool failure = false; struct xdp_buff xdp; xdp.rxq = &rx_ring->xdp_rxq; @@ -2359,8 +2361,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) } if (IS_ERR(skb)) { - if (PTR_ERR(skb) == -I40E_XDP_TX) { - xdp_xmit = true; + unsigned int xdp_res = -PTR_ERR(skb); + + if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) { + xdp_xmit |= xdp_res; i40e_rx_buffer_flip(rx_ring, rx_buffer, size); } else { rx_buffer->pagecnt_bias++; @@ -2414,12 +2418,14 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) total_rx_packets++; } - if (xdp_xmit) { + if (xdp_xmit & I40E_XDP_REDIR) + xdp_do_flush_map(); + + if (xdp_xmit & I40E_XDP_TX) { struct i40e_ring *xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index]; i40e_xdp_ring_update_tail(xdp_ring); - xdp_do_flush_map(); } rx_ring->skb = skb; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 2ecd55856c50..a820a6cd831a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2257,9 +2257,10 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, return skb; } -#define IXGBE_XDP_PASS 0 -#define IXGBE_XDP_CONSUMED 1 -#define IXGBE_XDP_TX 2 +#define IXGBE_XDP_PASS 0 +#define IXGBE_XDP_CONSUMED BIT(0) +#define IXGBE_XDP_TX BIT(1) +#define IXGBE_XDP_REDIR BIT(2) static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, struct xdp_buff *xdp); @@ -2288,7 +2289,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, case XDP_REDIRECT: err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); if (!err) - result = IXGBE_XDP_TX; + result = IXGBE_XDP_REDIR; else result = IXGBE_XDP_CONSUMED; break; @@ -2348,7 +2349,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, unsigned int mss = 0; #endif /* IXGBE_FCOE */ u16 cleaned_count = ixgbe_desc_unused(rx_ring); - bool xdp_xmit = false; + unsigned int xdp_xmit = 0; struct xdp_buff xdp; xdp.rxq = &rx_ring->xdp_rxq; @@ -2391,8 +2392,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, } if (IS_ERR(skb)) { - if (PTR_ERR(skb) == -IXGBE_XDP_TX) { - xdp_xmit = true; + unsigned int xdp_res = -PTR_ERR(skb); + + if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) { + xdp_xmit |= xdp_res; ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size); } else { rx_buffer->pagecnt_bias++; @@ -2464,7 +2467,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, total_rx_packets++; } - if (xdp_xmit) { + if (xdp_xmit & IXGBE_XDP_REDIR) + xdp_do_flush_map(); + + if (xdp_xmit & IXGBE_XDP_TX) { struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; /* Force memory writes to complete before letting h/w @@ -2472,8 +2478,6 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, */ wmb(); writel(ring->next_to_use, ring->tail); - - xdp_do_flush_map(); } u64_stats_update_begin(&rx_ring->syncp); diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 17a904cc6a5e..0ad2f3f7da85 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1932,7 +1932,7 @@ static int mvneta_rx_swbm(struct mvneta_port *pp, int rx_todo, rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE); index = rx_desc - rxq->descs; data = rxq->buf_virt_addr[index]; - phys_addr = rx_desc->buf_phys_addr; + phys_addr = rx_desc->buf_phys_addr - pp->rx_offset_correction; if (!mvneta_rxq_desc_is_first_last(rx_status) || (rx_status & MVNETA_RXD_ERR_SUMMARY)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 21cd1703a862..33ab34dc6d96 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -803,6 +803,7 @@ static void cmd_work_handler(struct work_struct *work) unsigned long flags; bool poll_cmd = ent->polling; int alloc_ret; + int cmd_mode; sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); @@ -849,6 +850,7 @@ static void cmd_work_handler(struct work_struct *work) set_signature(ent, !cmd->checksum_disabled); dump_command(dev, ent, 1); ent->ts1 = ktime_get_ns(); + cmd_mode = cmd->mode; if (ent->callback) schedule_delayed_work(&ent->cb_timeout_work, cb_timeout); @@ -873,7 +875,7 @@ static void cmd_work_handler(struct work_struct *work) iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell); mmiowb(); /* if not in polling don't use ent after this point */ - if (cmd->mode == CMD_MODE_POLLING || poll_cmd) { + if (cmd_mode == CMD_MODE_POLLING || poll_cmd) { poll_timeout(ent); /* make sure we read the descriptor after ownership is SW */ rmb(); @@ -1274,7 +1276,7 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf, { struct mlx5_core_dev *dev = filp->private_data; struct mlx5_cmd_debug *dbg = &dev->cmd.dbg; - char outlen_str[8]; + char outlen_str[8] = {0}; int outlen; void *ptr; int err; @@ -1289,8 +1291,6 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf, if (copy_from_user(outlen_str, buf, count)) return -EFAULT; - outlen_str[7] = 0; - err = sscanf(outlen_str, "%d", &outlen); if (err < 0) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b29c1d93f058..d3a1a2281e77 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2612,7 +2612,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) mlx5e_activate_channels(&priv->channels); netif_tx_start_all_queues(priv->netdev); - if (MLX5_VPORT_MANAGER(priv->mdev)) + if (MLX5_ESWITCH_MANAGER(priv->mdev)) mlx5e_add_sqs_fwd_rules(priv); mlx5e_wait_channels_min_rx_wqes(&priv->channels); @@ -2623,7 +2623,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) { mlx5e_redirect_rqts_to_drop(priv); - if (MLX5_VPORT_MANAGER(priv->mdev)) + if (MLX5_ESWITCH_MANAGER(priv->mdev)) mlx5e_remove_sqs_fwd_rules(priv); /* FIXME: This is a W/A only for tx timeout watch dog false alarm when @@ -4315,7 +4315,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) mlx5e_set_netdev_dev_addr(netdev); #if IS_ENABLED(CONFIG_MLX5_ESWITCH) - if (MLX5_VPORT_MANAGER(mdev)) + if (MLX5_ESWITCH_MANAGER(mdev)) netdev->switchdev_ops = &mlx5e_switchdev_ops; #endif @@ -4465,7 +4465,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) mlx5e_enable_async_events(priv); - if (MLX5_VPORT_MANAGER(priv->mdev)) + if (MLX5_ESWITCH_MANAGER(priv->mdev)) mlx5e_register_vport_reps(priv); if (netdev->reg_state != NETREG_REGISTERED) @@ -4500,7 +4500,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) queue_work(priv->wq, &priv->set_rx_mode_work); - if (MLX5_VPORT_MANAGER(priv->mdev)) + if (MLX5_ESWITCH_MANAGER(priv->mdev)) mlx5e_unregister_vport_reps(priv); mlx5e_disable_async_events(priv); @@ -4684,7 +4684,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev) return NULL; #ifdef CONFIG_MLX5_ESWITCH - if (MLX5_VPORT_MANAGER(mdev)) { + if (MLX5_ESWITCH_MANAGER(mdev)) { rpriv = mlx5e_alloc_nic_rep_priv(mdev); if (!rpriv) { mlx5_core_warn(mdev, "Failed to alloc NIC rep priv data\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 876c3e4c6193..286565862341 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -790,7 +790,7 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep; - if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager)) + if (!MLX5_ESWITCH_MANAGER(priv->mdev)) return false; rep = rpriv->rep; @@ -804,8 +804,12 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv) { struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct mlx5_eswitch_rep *rep = rpriv->rep; + struct mlx5_eswitch_rep *rep; + if (!MLX5_ESWITCH_MANAGER(priv->mdev)) + return false; + + rep = rpriv->rep; if (rep && rep->vport != FDB_UPLINK_VPORT) return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 1352d13eedb3..c3a18ddf5dba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1604,7 +1604,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) if (!ESW_ALLOWED(esw)) return 0; - if (!MLX5_CAP_GEN(esw->dev, eswitch_flow_table) || + if (!MLX5_ESWITCH_MANAGER(esw->dev) || !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) { esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 35e256eb2f6e..2feb33dcad2f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -983,8 +983,8 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink) if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) return -EOPNOTSUPP; - if (!MLX5_CAP_GEN(dev, vport_group_manager)) - return -EOPNOTSUPP; + if(!MLX5_ESWITCH_MANAGER(dev)) + return -EPERM; if (dev->priv.eswitch->mode == SRIOV_NONE) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index c39c1692e674..bd0ffc347bd7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -32,6 +32,7 @@ #include <linux/mutex.h> #include <linux/mlx5/driver.h> +#include <linux/mlx5/eswitch.h> #include "mlx5_core.h" #include "fs_core.h" @@ -2631,7 +2632,7 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) goto err; } - if (MLX5_CAP_GEN(dev, eswitch_flow_table)) { + if (MLX5_ESWITCH_MANAGER(dev)) { if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, ft_support)) { err = init_fdb_root_ns(steering); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index afd9f4fa22f4..41ad24f0de2c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -32,6 +32,7 @@ #include <linux/mlx5/driver.h> #include <linux/mlx5/cmd.h> +#include <linux/mlx5/eswitch.h> #include <linux/module.h> #include "mlx5_core.h" #include "../../mlxfw/mlxfw.h" @@ -159,13 +160,13 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) } if (MLX5_CAP_GEN(dev, vport_group_manager) && - MLX5_CAP_GEN(dev, eswitch_flow_table)) { + MLX5_ESWITCH_MANAGER(dev)) { err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH_FLOW_TABLE); if (err) return err; } - if (MLX5_CAP_GEN(dev, eswitch_flow_table)) { + if (MLX5_ESWITCH_MANAGER(dev)) { err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c index 7cb67122e8b5..98359559c77e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c @@ -33,6 +33,7 @@ #include <linux/etherdevice.h> #include <linux/mlx5/driver.h> #include <linux/mlx5/mlx5_ifc.h> +#include <linux/mlx5/eswitch.h> #include "mlx5_core.h" #include "lib/mpfs.h" @@ -98,7 +99,7 @@ int mlx5_mpfs_init(struct mlx5_core_dev *dev) int l2table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table); struct mlx5_mpfs *mpfs; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return 0; mpfs = kzalloc(sizeof(*mpfs), GFP_KERNEL); @@ -122,7 +123,7 @@ void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev) { struct mlx5_mpfs *mpfs = dev->priv.mpfs; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return; WARN_ON(!hlist_empty(mpfs->hash)); @@ -137,7 +138,7 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) u32 index; int err; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return 0; mutex_lock(&mpfs->lock); @@ -179,7 +180,7 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) int err = 0; u32 index; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return 0; mutex_lock(&mpfs->lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index fa9d0760dd36..31a9cbd85689 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -701,7 +701,7 @@ EXPORT_SYMBOL_GPL(mlx5_query_port_prio_tc); static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in, int inlen) { - u32 out[MLX5_ST_SZ_DW(qtct_reg)]; + u32 out[MLX5_ST_SZ_DW(qetc_reg)]; if (!MLX5_CAP_GEN(mdev, ets)) return -EOPNOTSUPP; @@ -713,7 +713,7 @@ static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in, static int mlx5_query_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *out, int outlen) { - u32 in[MLX5_ST_SZ_DW(qtct_reg)]; + u32 in[MLX5_ST_SZ_DW(qetc_reg)]; if (!MLX5_CAP_GEN(mdev, ets)) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 2a8b529ce6dd..a0674962f02c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -88,6 +88,9 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) return -EBUSY; } + if (!MLX5_ESWITCH_MANAGER(dev)) + goto enable_vfs_hca; + err = mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY); if (err) { mlx5_core_warn(dev, @@ -95,6 +98,7 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) return err; } +enable_vfs_hca: for (vf = 0; vf < num_vfs; vf++) { err = mlx5_core_enable_hca(dev, vf + 1); if (err) { @@ -140,7 +144,8 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev) } out: - mlx5_eswitch_disable_sriov(dev->priv.eswitch); + if (MLX5_ESWITCH_MANAGER(dev)) + mlx5_eswitch_disable_sriov(dev->priv.eswitch); if (mlx5_wait_for_vf_pages(dev)) mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index 35fb31f682af..1a781281c57a 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -194,6 +194,9 @@ static int nfp_bpf_setup_tc_block(struct net_device *netdev, if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) return -EOPNOTSUPP; + if (tcf_block_shared(f->block)) + return -EOPNOTSUPP; + switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index 91935405f586..84f7a5dbea9d 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -123,6 +123,20 @@ nfp_flower_compile_mac(struct nfp_flower_mac_mpls *frame, NFP_FLOWER_MASK_MPLS_Q; frame->mpls_lse = cpu_to_be32(t_mpls); + } else if (dissector_uses_key(flow->dissector, + FLOW_DISSECTOR_KEY_BASIC)) { + /* Check for mpls ether type and set NFP_FLOWER_MASK_MPLS_Q + * bit, which indicates an mpls ether type but without any + * mpls fields. + */ + struct flow_dissector_key_basic *key_basic; + + key_basic = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_BASIC, + flow->key); + if (key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_UC) || + key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_MC)) + frame->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q); } } diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 114d2ab02a38..4de30d0f9491 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -264,6 +264,14 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, case cpu_to_be16(ETH_P_ARP): return -EOPNOTSUPP; + case cpu_to_be16(ETH_P_MPLS_UC): + case cpu_to_be16(ETH_P_MPLS_MC): + if (!(key_layer & NFP_FLOWER_LAYER_MAC)) { + key_layer |= NFP_FLOWER_LAYER_MAC; + key_size += sizeof(struct nfp_flower_mac_mpls); + } + break; + /* Will be included in layer 2. */ case cpu_to_be16(ETH_P_8021Q): break; @@ -593,6 +601,9 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev, if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) return -EOPNOTSUPP; + if (tcf_block_shared(f->block)) + return -EOPNOTSUPP; + switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index 449777f21237..e82986df9b8e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -700,9 +700,9 @@ qed_dcbx_get_local_lldp_params(struct qed_hwfn *p_hwfn, p_local = &p_hwfn->p_dcbx_info->lldp_local[LLDP_NEAREST_BRIDGE]; memcpy(params->lldp_local.local_chassis_id, p_local->local_chassis_id, - ARRAY_SIZE(p_local->local_chassis_id)); + sizeof(p_local->local_chassis_id)); memcpy(params->lldp_local.local_port_id, p_local->local_port_id, - ARRAY_SIZE(p_local->local_port_id)); + sizeof(p_local->local_port_id)); } static void @@ -714,9 +714,9 @@ qed_dcbx_get_remote_lldp_params(struct qed_hwfn *p_hwfn, p_remote = &p_hwfn->p_dcbx_info->lldp_remote[LLDP_NEAREST_BRIDGE]; memcpy(params->lldp_remote.peer_chassis_id, p_remote->peer_chassis_id, - ARRAY_SIZE(p_remote->peer_chassis_id)); + sizeof(p_remote->peer_chassis_id)); memcpy(params->lldp_remote.peer_port_id, p_remote->peer_port_id, - ARRAY_SIZE(p_remote->peer_port_id)); + sizeof(p_remote->peer_port_id)); } static int diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index d2ad5e92c74f..5644b24d85b0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -1789,7 +1789,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params) DP_INFO(p_hwfn, "Failed to update driver state\n"); rc = qed_mcp_ov_update_eswitch(p_hwfn, p_hwfn->p_main_ptt, - QED_OV_ESWITCH_VEB); + QED_OV_ESWITCH_NONE); if (rc) DP_INFO(p_hwfn, "Failed to update eswitch mode\n"); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 7870ae2a6f7e..261f21d6b0b0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -780,6 +780,14 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev, /* We want a minimum of one slowpath and one fastpath vector per hwfn */ cdev->int_params.in.min_msix_cnt = cdev->num_hwfns * 2; + if (is_kdump_kernel()) { + DP_INFO(cdev, + "Kdump kernel: Limit the max number of requested MSI-X vectors to %hd\n", + cdev->int_params.in.min_msix_cnt); + cdev->int_params.in.num_vectors = + cdev->int_params.in.min_msix_cnt; + } + rc = qed_set_int_mode(cdev, false); if (rc) { DP_ERR(cdev, "qed_slowpath_setup_int ERR\n"); diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index 5acb91b3564c..419c681ea2be 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -4400,6 +4400,8 @@ static void qed_sriov_enable_qid_config(struct qed_hwfn *hwfn, static int qed_sriov_enable(struct qed_dev *cdev, int num) { struct qed_iov_vf_init_params params; + struct qed_hwfn *hwfn; + struct qed_ptt *ptt; int i, j, rc; if (num >= RESC_NUM(&cdev->hwfns[0], QED_VPORT)) { @@ -4412,8 +4414,8 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num) /* Initialize HW for VF access */ for_each_hwfn(cdev, j) { - struct qed_hwfn *hwfn = &cdev->hwfns[j]; - struct qed_ptt *ptt = qed_ptt_acquire(hwfn); + hwfn = &cdev->hwfns[j]; + ptt = qed_ptt_acquire(hwfn); /* Make sure not to use more than 16 queues per VF */ params.num_queues = min_t(int, @@ -4449,6 +4451,19 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num) goto err; } + hwfn = QED_LEADING_HWFN(cdev); + ptt = qed_ptt_acquire(hwfn); + if (!ptt) { + DP_ERR(hwfn, "Failed to acquire ptt\n"); + rc = -EBUSY; + goto err; + } + + rc = qed_mcp_ov_update_eswitch(hwfn, ptt, QED_OV_ESWITCH_VEB); + if (rc) + DP_INFO(cdev, "Failed to update eswitch mode\n"); + qed_ptt_release(hwfn, ptt); + return num; err: diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c index 02adb513f475..013ff567283c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c @@ -337,8 +337,14 @@ int qede_ptp_get_ts_info(struct qede_dev *edev, struct ethtool_ts_info *info) { struct qede_ptp *ptp = edev->ptp; - if (!ptp) - return -EIO; + if (!ptp) { + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + info->phc_index = -1; + + return 0; + } info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | SOF_TIMESTAMPING_RX_SOFTWARE | diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c index c72adf8b52ea..9165e2b0c590 100644 --- a/drivers/net/ethernet/sfc/farch.c +++ b/drivers/net/ethernet/sfc/farch.c @@ -2794,6 +2794,7 @@ int efx_farch_filter_table_probe(struct efx_nic *efx) if (!state) return -ENOMEM; efx->filter_state = state; + init_rwsem(&state->lock); table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP]; table->id = EFX_FARCH_FILTER_TABLE_RX_IP; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index b65e2d144698..1e1cc5256eca 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -927,6 +927,7 @@ static void stmmac_check_pcs_mode(struct stmmac_priv *priv) static int stmmac_init_phy(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + u32 tx_cnt = priv->plat->tx_queues_to_use; struct phy_device *phydev; char phy_id_fmt[MII_BUS_ID_SIZE + 3]; char bus_id[MII_BUS_ID_SIZE]; @@ -967,6 +968,15 @@ static int stmmac_init_phy(struct net_device *dev) phydev->advertising &= ~(SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full); + /* + * Half-duplex mode not supported with multiqueue + * half-duplex can only works with single queue + */ + if (tx_cnt > 1) + phydev->supported &= ~(SUPPORTED_1000baseT_Half | + SUPPORTED_100baseT_Half | + SUPPORTED_10baseT_Half); + /* * Broken HW is sometimes missing the pull-up resistor on the * MDIO line, which results in reads to non-existent devices returning diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index 7a16d40a72d1..b9221fc1674d 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -60,8 +60,7 @@ #include <linux/sungem_phy.h> #include "sungem.h" -/* Stripping FCS is causing problems, disabled for now */ -#undef STRIP_FCS +#define STRIP_FCS #define DEFAULT_MSG (NETIF_MSG_DRV | \ NETIF_MSG_PROBE | \ @@ -435,7 +434,7 @@ static int gem_rxmac_reset(struct gem *gp) writel(desc_dma & 0xffffffff, gp->regs + RXDMA_DBLOW); writel(RX_RING_SIZE - 4, gp->regs + RXDMA_KICK); val = (RXDMA_CFG_BASE | (RX_OFFSET << 10) | - ((14 / 2) << 13) | RXDMA_CFG_FTHRESH_128); + (ETH_HLEN << 13) | RXDMA_CFG_FTHRESH_128); writel(val, gp->regs + RXDMA_CFG); if (readl(gp->regs + GREG_BIFCFG) & GREG_BIFCFG_M66EN) writel(((5 & RXDMA_BLANK_IPKTS) | @@ -760,7 +759,6 @@ static int gem_rx(struct gem *gp, int work_to_do) struct net_device *dev = gp->dev; int entry, drops, work_done = 0; u32 done; - __sum16 csum; if (netif_msg_rx_status(gp)) printk(KERN_DEBUG "%s: rx interrupt, done: %d, rx_new: %d\n", @@ -855,9 +853,13 @@ static int gem_rx(struct gem *gp, int work_to_do) skb = copy_skb; } - csum = (__force __sum16)htons((status & RXDCTRL_TCPCSUM) ^ 0xffff); - skb->csum = csum_unfold(csum); - skb->ip_summed = CHECKSUM_COMPLETE; + if (likely(dev->features & NETIF_F_RXCSUM)) { + __sum16 csum; + + csum = (__force __sum16)htons((status & RXDCTRL_TCPCSUM) ^ 0xffff); + skb->csum = csum_unfold(csum); + skb->ip_summed = CHECKSUM_COMPLETE; + } skb->protocol = eth_type_trans(skb, gp->dev); napi_gro_receive(&gp->napi, skb); @@ -1761,7 +1763,7 @@ static void gem_init_dma(struct gem *gp) writel(0, gp->regs + TXDMA_KICK); val = (RXDMA_CFG_BASE | (RX_OFFSET << 10) | - ((14 / 2) << 13) | RXDMA_CFG_FTHRESH_128); + (ETH_HLEN << 13) | RXDMA_CFG_FTHRESH_128); writel(val, gp->regs + RXDMA_CFG); writel(desc_dma >> 32, gp->regs + RXDMA_DBHI); @@ -2985,8 +2987,8 @@ static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, dev); /* We can do scatter/gather and HW checksum */ - dev->hw_features = NETIF_F_SG | NETIF_F_HW_CSUM; - dev->features |= dev->hw_features | NETIF_F_RXCSUM; + dev->hw_features = NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM; + dev->features = dev->hw_features; if (pci_using_dac) dev->features |= NETIF_F_HIGHDMA; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index b919e89a9b93..4b3986dda52e 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -474,7 +474,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 960f06141472..eaeee3201e8f 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -211,7 +211,7 @@ int netvsc_recv_callback(struct net_device *net, void netvsc_channel_cb(void *context); int netvsc_poll(struct napi_struct *napi, int budget); -void rndis_set_subchannel(struct work_struct *w); +int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev); int rndis_filter_open(struct netvsc_device *nvdev); int rndis_filter_close(struct netvsc_device *nvdev); struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 04f611e6f678..c418113c6b20 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -66,6 +66,41 @@ void netvsc_switch_datapath(struct net_device *ndev, bool vf) VM_PKT_DATA_INBAND, 0); } +/* Worker to setup sub channels on initial setup + * Initial hotplug event occurs in softirq context + * and can't wait for channels. + */ +static void netvsc_subchan_work(struct work_struct *w) +{ + struct netvsc_device *nvdev = + container_of(w, struct netvsc_device, subchan_work); + struct rndis_device *rdev; + int i, ret; + + /* Avoid deadlock with device removal already under RTNL */ + if (!rtnl_trylock()) { + schedule_work(w); + return; + } + + rdev = nvdev->extension; + if (rdev) { + ret = rndis_set_subchannel(rdev->ndev, nvdev); + if (ret == 0) { + netif_device_attach(rdev->ndev); + } else { + /* fallback to only primary channel */ + for (i = 1; i < nvdev->num_chn; i++) + netif_napi_del(&nvdev->chan_table[i].napi); + + nvdev->max_chn = 1; + nvdev->num_chn = 1; + } + } + + rtnl_unlock(); +} + static struct netvsc_device *alloc_net_device(void) { struct netvsc_device *net_device; @@ -82,7 +117,7 @@ static struct netvsc_device *alloc_net_device(void) init_completion(&net_device->channel_init_wait); init_waitqueue_head(&net_device->subchan_open); - INIT_WORK(&net_device->subchan_work, rndis_set_subchannel); + INIT_WORK(&net_device->subchan_work, netvsc_subchan_work); return net_device; } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index eb8dccd24abf..82c3c8e200f0 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -905,8 +905,20 @@ static int netvsc_attach(struct net_device *ndev, if (IS_ERR(nvdev)) return PTR_ERR(nvdev); - /* Note: enable and attach happen when sub-channels setup */ + if (nvdev->num_chn > 1) { + ret = rndis_set_subchannel(ndev, nvdev); + + /* if unavailable, just proceed with one queue */ + if (ret) { + nvdev->max_chn = 1; + nvdev->num_chn = 1; + } + } + + /* In any case device is now ready */ + netif_device_attach(ndev); + /* Note: enable and attach happen when sub-channels setup */ netif_carrier_off(ndev); if (netif_running(ndev)) { @@ -2064,6 +2076,9 @@ static int netvsc_probe(struct hv_device *dev, memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN); + if (nvdev->num_chn > 1) + schedule_work(&nvdev->subchan_work); + /* hw_features computed in rndis_netdev_set_hwcaps() */ net->features = net->hw_features | NETIF_F_HIGHDMA | NETIF_F_SG | diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index e7ca5b5f39ed..f362cda85425 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1061,29 +1061,15 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc) * This breaks overlap of processing the host message for the * new primary channel with the initialization of sub-channels. */ -void rndis_set_subchannel(struct work_struct *w) +int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev) { - struct netvsc_device *nvdev - = container_of(w, struct netvsc_device, subchan_work); struct nvsp_message *init_packet = &nvdev->channel_init_pkt; - struct net_device_context *ndev_ctx; - struct rndis_device *rdev; - struct net_device *ndev; - struct hv_device *hv_dev; + struct net_device_context *ndev_ctx = netdev_priv(ndev); + struct hv_device *hv_dev = ndev_ctx->device_ctx; + struct rndis_device *rdev = nvdev->extension; int i, ret; - if (!rtnl_trylock()) { - schedule_work(w); - return; - } - - rdev = nvdev->extension; - if (!rdev) - goto unlock; /* device was removed */ - - ndev = rdev->ndev; - ndev_ctx = netdev_priv(ndev); - hv_dev = ndev_ctx->device_ctx; + ASSERT_RTNL(); memset(init_packet, 0, sizeof(struct nvsp_message)); init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL; @@ -1099,13 +1085,13 @@ void rndis_set_subchannel(struct work_struct *w) VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); if (ret) { netdev_err(ndev, "sub channel allocate send failed: %d\n", ret); - goto failed; + return ret; } wait_for_completion(&nvdev->channel_init_wait); if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) { netdev_err(ndev, "sub channel request failed\n"); - goto failed; + return -EIO; } nvdev->num_chn = 1 + @@ -1124,21 +1110,7 @@ void rndis_set_subchannel(struct work_struct *w) for (i = 0; i < VRSS_SEND_TAB_SIZE; i++) ndev_ctx->tx_table[i] = i % nvdev->num_chn; - netif_device_attach(ndev); - rtnl_unlock(); - return; - -failed: - /* fallback to only primary channel */ - for (i = 1; i < nvdev->num_chn; i++) - netif_napi_del(&nvdev->chan_table[i].napi); - - nvdev->max_chn = 1; - nvdev->num_chn = 1; - - netif_device_attach(ndev); -unlock: - rtnl_unlock(); + return 0; } static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device, @@ -1329,21 +1301,12 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, netif_napi_add(net, &net_device->chan_table[i].napi, netvsc_poll, NAPI_POLL_WEIGHT); - if (net_device->num_chn > 1) - schedule_work(&net_device->subchan_work); + return net_device; out: - /* if unavailable, just proceed with one queue */ - if (ret) { - net_device->max_chn = 1; - net_device->num_chn = 1; - } - - /* No sub channels, device is ready */ - if (net_device->num_chn == 1) - netif_device_attach(net); - - return net_device; + /* setting up multiple channels failed */ + net_device->max_chn = 1; + net_device->num_chn = 1; err_dev_remv: rndis_filter_device_remove(dev, net_device); diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 4377c26f714d..6641fd5355e0 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -594,7 +594,8 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, ipvlan->phy_dev = phy_dev; ipvlan->dev = dev; ipvlan->sfeatures = IPVLAN_FEATURES; - ipvlan_adjust_mtu(ipvlan, phy_dev); + if (!tb[IFLA_MTU]) + ipvlan_adjust_mtu(ipvlan, phy_dev); INIT_LIST_HEAD(&ipvlan->addrs); spin_lock_init(&ipvlan->addrs_lock); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 0867f7275852..8a76c1e5de8d 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -3193,6 +3193,7 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) pkt_cnt = 0; count = 0; length = 0; + spin_lock_irqsave(&tqp->lock, flags); for (skb = tqp->next; pkt_cnt < tqp->qlen; skb = skb->next) { if (skb_is_gso(skb)) { if (pkt_cnt) { @@ -3201,7 +3202,8 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) } count = 1; length = skb->len - TX_OVERHEAD; - skb2 = skb_dequeue(tqp); + __skb_unlink(skb, tqp); + spin_unlock_irqrestore(&tqp->lock, flags); goto gso_skb; } @@ -3210,6 +3212,7 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) skb_totallen = skb->len + roundup(skb_totallen, sizeof(u32)); pkt_cnt++; } + spin_unlock_irqrestore(&tqp->lock, flags); /* copy to a single skb */ skb = alloc_skb(skb_totallen, GFP_ATOMIC); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 094680871687..04c22f508ed9 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1246,6 +1246,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ + {QMI_FIXED_INTF(0x413c, 0x81d7, 1)}, /* Dell Wireless 5821e */ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */ {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 86f7196f9d91..2a58607a6aea 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3962,7 +3962,8 @@ static int rtl8152_close(struct net_device *netdev) #ifdef CONFIG_PM_SLEEP unregister_pm_notifier(&tp->pm_notifier); #endif - napi_disable(&tp->napi); + if (!test_bit(RTL8152_UNPLUG, &tp->flags)) + napi_disable(&tp->napi); clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); cancel_delayed_work_sync(&tp->schedule); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 8c7207535179..11a3915e92e9 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -50,6 +50,10 @@ module_param(napi_tx, bool, 0644); /* Amount of XDP headroom to prepend to packets for use by xdp_adjust_head */ #define VIRTIO_XDP_HEADROOM 256 +/* Separating two types of XDP xmit */ +#define VIRTIO_XDP_TX BIT(0) +#define VIRTIO_XDP_REDIR BIT(1) + /* RX packet size EWMA. The average packet size is used to determine the packet * buffer size when refilling RX rings. As the entire RX ring may be refilled * at once, the weight is chosen so that the EWMA will be insensitive to short- @@ -547,7 +551,7 @@ static struct sk_buff *receive_small(struct net_device *dev, struct receive_queue *rq, void *buf, void *ctx, unsigned int len, - bool *xdp_xmit) + unsigned int *xdp_xmit) { struct sk_buff *skb; struct bpf_prog *xdp_prog; @@ -615,14 +619,14 @@ static struct sk_buff *receive_small(struct net_device *dev, trace_xdp_exception(vi->dev, xdp_prog, act); goto err_xdp; } - *xdp_xmit = true; + *xdp_xmit |= VIRTIO_XDP_TX; rcu_read_unlock(); goto xdp_xmit; case XDP_REDIRECT: err = xdp_do_redirect(dev, &xdp, xdp_prog); if (err) goto err_xdp; - *xdp_xmit = true; + *xdp_xmit |= VIRTIO_XDP_REDIR; rcu_read_unlock(); goto xdp_xmit; default: @@ -684,7 +688,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, void *buf, void *ctx, unsigned int len, - bool *xdp_xmit) + unsigned int *xdp_xmit) { struct virtio_net_hdr_mrg_rxbuf *hdr = buf; u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); @@ -772,7 +776,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, put_page(xdp_page); goto err_xdp; } - *xdp_xmit = true; + *xdp_xmit |= VIRTIO_XDP_REDIR; if (unlikely(xdp_page != page)) put_page(page); rcu_read_unlock(); @@ -784,7 +788,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, put_page(xdp_page); goto err_xdp; } - *xdp_xmit = true; + *xdp_xmit |= VIRTIO_XDP_TX; if (unlikely(xdp_page != page)) put_page(page); rcu_read_unlock(); @@ -893,7 +897,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, } static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq, - void *buf, unsigned int len, void **ctx, bool *xdp_xmit) + void *buf, unsigned int len, void **ctx, + unsigned int *xdp_xmit) { struct net_device *dev = vi->dev; struct sk_buff *skb; @@ -1186,7 +1191,8 @@ static void refill_work(struct work_struct *work) } } -static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit) +static int virtnet_receive(struct receive_queue *rq, int budget, + unsigned int *xdp_xmit) { struct virtnet_info *vi = rq->vq->vdev->priv; unsigned int len, received = 0, bytes = 0; @@ -1275,7 +1281,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget) struct virtnet_info *vi = rq->vq->vdev->priv; struct send_queue *sq; unsigned int received, qp; - bool xdp_xmit = false; + unsigned int xdp_xmit = 0; virtnet_poll_cleantx(rq); @@ -1285,12 +1291,14 @@ static int virtnet_poll(struct napi_struct *napi, int budget) if (received < budget) virtqueue_napi_complete(napi, rq->vq, received); - if (xdp_xmit) { + if (xdp_xmit & VIRTIO_XDP_REDIR) + xdp_do_flush_map(); + + if (xdp_xmit & VIRTIO_XDP_TX) { qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id(); sq = &vi->sq[qp]; virtqueue_kick(sq->vq); - xdp_do_flush_map(); } return received; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index fab7a4db249e..4b170599fa5e 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -623,9 +623,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk, flush = 0; out: - skb_gro_remcsum_cleanup(skb, &grc); - skb->remcsum_offload = 0; - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c index 762a29cdf7ad..b23983737011 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.c +++ b/drivers/net/wireless/realtek/rtlwifi/base.c @@ -485,18 +485,21 @@ static void _rtl_init_deferred_work(struct ieee80211_hw *hw) } -void rtl_deinit_deferred_work(struct ieee80211_hw *hw) +void rtl_deinit_deferred_work(struct ieee80211_hw *hw, bool ips_wq) { struct rtl_priv *rtlpriv = rtl_priv(hw); del_timer_sync(&rtlpriv->works.watchdog_timer); - cancel_delayed_work(&rtlpriv->works.watchdog_wq); - cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq); - cancel_delayed_work(&rtlpriv->works.ps_work); - cancel_delayed_work(&rtlpriv->works.ps_rfon_wq); - cancel_delayed_work(&rtlpriv->works.fwevt_wq); - cancel_delayed_work(&rtlpriv->works.c2hcmd_wq); + cancel_delayed_work_sync(&rtlpriv->works.watchdog_wq); + if (ips_wq) + cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq); + else + cancel_delayed_work_sync(&rtlpriv->works.ips_nic_off_wq); + cancel_delayed_work_sync(&rtlpriv->works.ps_work); + cancel_delayed_work_sync(&rtlpriv->works.ps_rfon_wq); + cancel_delayed_work_sync(&rtlpriv->works.fwevt_wq); + cancel_delayed_work_sync(&rtlpriv->works.c2hcmd_wq); } EXPORT_SYMBOL_GPL(rtl_deinit_deferred_work); diff --git a/drivers/net/wireless/realtek/rtlwifi/base.h b/drivers/net/wireless/realtek/rtlwifi/base.h index acc924635818..92b8cad6b563 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.h +++ b/drivers/net/wireless/realtek/rtlwifi/base.h @@ -121,7 +121,7 @@ void rtl_init_rfkill(struct ieee80211_hw *hw); void rtl_deinit_rfkill(struct ieee80211_hw *hw); void rtl_watch_dog_timer_callback(struct timer_list *t); -void rtl_deinit_deferred_work(struct ieee80211_hw *hw); +void rtl_deinit_deferred_work(struct ieee80211_hw *hw, bool ips_wq); bool rtl_action_proc(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx); int rtlwifi_rate_mapping(struct ieee80211_hw *hw, bool isht, diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c index cfea57efa7f4..4bf7967590ca 100644 --- a/drivers/net/wireless/realtek/rtlwifi/core.c +++ b/drivers/net/wireless/realtek/rtlwifi/core.c @@ -130,7 +130,6 @@ static void rtl_fw_do_work(const struct firmware *firmware, void *context, firmware->size); rtlpriv->rtlhal.wowlan_fwsize = firmware->size; } - rtlpriv->rtlhal.fwsize = firmware->size; release_firmware(firmware); } @@ -196,7 +195,7 @@ static void rtl_op_stop(struct ieee80211_hw *hw) /* reset sec info */ rtl_cam_reset_sec_info(hw); - rtl_deinit_deferred_work(hw); + rtl_deinit_deferred_work(hw, false); } rtlpriv->intf_ops->adapter_stop(hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c index 57bb8f049e59..4dc3e3122f5d 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.c +++ b/drivers/net/wireless/realtek/rtlwifi/pci.c @@ -2375,7 +2375,7 @@ void rtl_pci_disconnect(struct pci_dev *pdev) ieee80211_unregister_hw(hw); rtlmac->mac80211_registered = 0; } else { - rtl_deinit_deferred_work(hw); + rtl_deinit_deferred_work(hw, false); rtlpriv->intf_ops->adapter_stop(hw); } rtlpriv->cfg->ops->disable_interrupt(hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/ps.c b/drivers/net/wireless/realtek/rtlwifi/ps.c index 71af24e2e051..479a4cfc245d 100644 --- a/drivers/net/wireless/realtek/rtlwifi/ps.c +++ b/drivers/net/wireless/realtek/rtlwifi/ps.c @@ -71,7 +71,7 @@ bool rtl_ps_disable_nic(struct ieee80211_hw *hw) struct rtl_priv *rtlpriv = rtl_priv(hw); /*<1> Stop all timer */ - rtl_deinit_deferred_work(hw); + rtl_deinit_deferred_work(hw, true); /*<2> Disable Interrupt */ rtlpriv->cfg->ops->disable_interrupt(hw); @@ -292,7 +292,7 @@ void rtl_ips_nic_on(struct ieee80211_hw *hw) struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw)); enum rf_pwrstate rtstate; - cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq); + cancel_delayed_work_sync(&rtlpriv->works.ips_nic_off_wq); mutex_lock(&rtlpriv->locks.ips_mutex); if (ppsc->inactiveps) { diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c index ce3103bb8ebb..6771b2742b78 100644 --- a/drivers/net/wireless/realtek/rtlwifi/usb.c +++ b/drivers/net/wireless/realtek/rtlwifi/usb.c @@ -1132,7 +1132,7 @@ void rtl_usb_disconnect(struct usb_interface *intf) ieee80211_unregister_hw(hw); rtlmac->mac80211_registered = 0; } else { - rtl_deinit_deferred_work(hw); + rtl_deinit_deferred_work(hw, false); rtlpriv->intf_ops->adapter_stop(hw); } /*deinit rfkill */ diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 4dd0668003e7..1d5082d30187 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1810,7 +1810,7 @@ static int talk_to_netback(struct xenbus_device *dev, err = xen_net_read_mac(dev, info->netdev->dev_addr); if (err) { xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename); - goto out; + goto out_unlocked; } rtnl_lock(); @@ -1925,6 +1925,7 @@ static int talk_to_netback(struct xenbus_device *dev, xennet_destroy_queues(info); out: rtnl_unlock(); +out_unlocked: device_unregister(&dev->dev); return err; } @@ -1950,10 +1951,6 @@ static int xennet_connect(struct net_device *dev) /* talk_to_netback() sets the correct number of queues */ num_queues = dev->real_num_tx_queues; - rtnl_lock(); - netdev_update_features(dev); - rtnl_unlock(); - if (dev->reg_state == NETREG_UNINITIALIZED) { err = register_netdev(dev); if (err) { @@ -1963,6 +1960,10 @@ static int xennet_connect(struct net_device *dev) } } + rtnl_lock(); + netdev_update_features(dev); + rtnl_unlock(); + /* * All public and private state should now be sane. Get * ready to start sending and receiving packets and give the driver diff --git a/drivers/pci/host/pci-hyperv.c b/drivers/pci/host/pci-hyperv.c index da4b457a14e0..4690814cfc51 100644 --- a/drivers/pci/host/pci-hyperv.c +++ b/drivers/pci/host/pci-hyperv.c @@ -1077,6 +1077,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) struct pci_bus *pbus; struct pci_dev *pdev; struct cpumask *dest; + unsigned long flags; struct compose_comp_ctxt comp; struct tran_int_desc *int_desc; struct { @@ -1168,14 +1169,15 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) * the channel callback directly when channel->target_cpu is * the current CPU. When the higher level interrupt code * calls us with interrupt enabled, let's add the - * local_bh_disable()/enable() to avoid race. + * local_irq_save()/restore() to avoid race: + * hv_pci_onchannelcallback() can also run in tasklet. */ - local_bh_disable(); + local_irq_save(flags); if (hbus->hdev->channel->target_cpu == smp_processor_id()) hv_pci_onchannelcallback(hbus); - local_bh_enable(); + local_irq_restore(flags); if (hpdev->state == hv_pcichild_ejecting) { dev_err_once(&hbus->hdev->device, diff --git a/drivers/pinctrl/mediatek/pinctrl-mt7622.c b/drivers/pinctrl/mediatek/pinctrl-mt7622.c index 06e8406c4440..9dc7cf211da0 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt7622.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt7622.c @@ -1411,7 +1411,7 @@ static struct pinctrl_desc mtk_desc = { static int mtk_gpio_get(struct gpio_chip *chip, unsigned int gpio) { - struct mtk_pinctrl *hw = dev_get_drvdata(chip->parent); + struct mtk_pinctrl *hw = gpiochip_get_data(chip); int value, err; err = mtk_hw_get_value(hw, gpio, PINCTRL_PIN_REG_DI, &value); @@ -1423,7 +1423,7 @@ static int mtk_gpio_get(struct gpio_chip *chip, unsigned int gpio) static void mtk_gpio_set(struct gpio_chip *chip, unsigned int gpio, int value) { - struct mtk_pinctrl *hw = dev_get_drvdata(chip->parent); + struct mtk_pinctrl *hw = gpiochip_get_data(chip); mtk_hw_set_value(hw, gpio, PINCTRL_PIN_REG_DO, !!value); } @@ -1463,11 +1463,20 @@ static int mtk_build_gpiochip(struct mtk_pinctrl *hw, struct device_node *np) if (ret < 0) return ret; - ret = gpiochip_add_pin_range(chip, dev_name(hw->dev), 0, 0, - chip->ngpio); - if (ret < 0) { - gpiochip_remove(chip); - return ret; + /* Just for backward compatible for these old pinctrl nodes without + * "gpio-ranges" property. Otherwise, called directly from a + * DeviceTree-supported pinctrl driver is DEPRECATED. + * Please see Section 2.1 of + * Documentation/devicetree/bindings/gpio/gpio.txt on how to + * bind pinctrl and gpio drivers via the "gpio-ranges" property. + */ + if (!of_find_property(np, "gpio-ranges", NULL)) { + ret = gpiochip_add_pin_range(chip, dev_name(hw->dev), 0, 0, + chip->ngpio); + if (ret < 0) { + gpiochip_remove(chip); + return ret; + } } return 0; @@ -1561,7 +1570,7 @@ static int mtk_pinctrl_probe(struct platform_device *pdev) err = mtk_build_groups(hw); if (err) { dev_err(&pdev->dev, "Failed to build groups\n"); - return 0; + return err; } /* Setup functions descriptions per SoC types */ diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a77970.c b/drivers/pinctrl/sh-pfc/pfc-r8a77970.c index b1bb7263532b..049b374aa4ae 100644 --- a/drivers/pinctrl/sh-pfc/pfc-r8a77970.c +++ b/drivers/pinctrl/sh-pfc/pfc-r8a77970.c @@ -22,12 +22,12 @@ #include "sh_pfc.h" #define CPU_ALL_PORT(fn, sfx) \ - PORT_GP_CFG_22(0, fn, sfx, SH_PFC_PIN_CFG_DRIVE_STRENGTH), \ - PORT_GP_CFG_28(1, fn, sfx, SH_PFC_PIN_CFG_DRIVE_STRENGTH), \ - PORT_GP_CFG_17(2, fn, sfx, SH_PFC_PIN_CFG_DRIVE_STRENGTH), \ - PORT_GP_CFG_17(3, fn, sfx, SH_PFC_PIN_CFG_DRIVE_STRENGTH), \ - PORT_GP_CFG_6(4, fn, sfx, SH_PFC_PIN_CFG_DRIVE_STRENGTH), \ - PORT_GP_CFG_15(5, fn, sfx, SH_PFC_PIN_CFG_DRIVE_STRENGTH) + PORT_GP_22(0, fn, sfx), \ + PORT_GP_28(1, fn, sfx), \ + PORT_GP_17(2, fn, sfx), \ + PORT_GP_17(3, fn, sfx), \ + PORT_GP_6(4, fn, sfx), \ + PORT_GP_15(5, fn, sfx) /* * F_() : just information * FM() : macro for FN_xxx / xxx_MARK diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 78b98b3e7efa..b7f75339683e 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -831,6 +831,17 @@ struct qeth_trap_id { /*some helper functions*/ #define QETH_CARD_IFNAME(card) (((card)->dev)? (card)->dev->name : "") +static inline void qeth_scrub_qdio_buffer(struct qdio_buffer *buf, + unsigned int elements) +{ + unsigned int i; + + for (i = 0; i < elements; i++) + memset(&buf->element[i], 0, sizeof(struct qdio_buffer_element)); + buf->element[14].sflags = 0; + buf->element[15].sflags = 0; +} + /** * qeth_get_elements_for_range() - find number of SBALEs to cover range. * @start: Start of the address range. diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index dffd820731f2..b2eebcffd502 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -73,9 +73,6 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *queue, struct qeth_qdio_out_buffer *buf, enum iucv_tx_notify notification); static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf); -static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue, - struct qeth_qdio_out_buffer *buf, - enum qeth_qdio_buffer_states newbufstate); static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *, int); struct workqueue_struct *qeth_wq; @@ -488,6 +485,7 @@ static void qeth_qdio_handle_aob(struct qeth_card *card, struct qaob *aob; struct qeth_qdio_out_buffer *buffer; enum iucv_tx_notify notification; + unsigned int i; aob = (struct qaob *) phys_to_virt(phys_aob_addr); QETH_CARD_TEXT(card, 5, "haob"); @@ -512,10 +510,18 @@ static void qeth_qdio_handle_aob(struct qeth_card *card, qeth_notify_skbs(buffer->q, buffer, notification); buffer->aob = NULL; - qeth_clear_output_buffer(buffer->q, buffer, - QETH_QDIO_BUF_HANDLED_DELAYED); + /* Free dangling allocations. The attached skbs are handled by + * qeth_cleanup_handled_pending(). + */ + for (i = 0; + i < aob->sb_count && i < QETH_MAX_BUFFER_ELEMENTS(card); + i++) { + if (aob->sba[i] && buffer->is_header[i]) + kmem_cache_free(qeth_core_header_cache, + (void *) aob->sba[i]); + } + atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED); - /* from here on: do not touch buffer anymore */ qdio_release_aob(aob); } @@ -3759,6 +3765,10 @@ void qeth_qdio_output_handler(struct ccw_device *ccwdev, QETH_CARD_TEXT(queue->card, 5, "aob"); QETH_CARD_TEXT_(queue->card, 5, "%lx", virt_to_phys(buffer->aob)); + + /* prepare the queue slot for re-use: */ + qeth_scrub_qdio_buffer(buffer->buffer, + QETH_MAX_BUFFER_ELEMENTS(card)); if (qeth_init_qdio_out_buf(queue, bidx)) { QETH_CARD_TEXT(card, 2, "outofbuf"); qeth_schedule_recovery(card); @@ -4835,7 +4845,7 @@ int qeth_vm_request_mac(struct qeth_card *card) goto out; } - ccw_device_get_id(CARD_RDEV(card), &id); + ccw_device_get_id(CARD_DDEV(card), &id); request->resp_buf_len = sizeof(*response); request->resp_version = DIAG26C_VERSION2; request->op_code = DIAG26C_GET_MAC; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index b8079f2a65b3..16dc8b83ca6f 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -141,7 +141,7 @@ static int qeth_l2_send_setmac(struct qeth_card *card, __u8 *mac) static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac) { - enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ? + enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ? IPA_CMD_SETGMAC : IPA_CMD_SETVMAC; int rc; @@ -158,7 +158,7 @@ static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac) static int qeth_l2_remove_mac(struct qeth_card *card, u8 *mac) { - enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ? + enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ? IPA_CMD_DELGMAC : IPA_CMD_DELVMAC; int rc; @@ -523,27 +523,34 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p) return -ERESTARTSYS; } + /* avoid racing against concurrent state change: */ + if (!mutex_trylock(&card->conf_mutex)) + return -EAGAIN; + if (!qeth_card_hw_is_reachable(card)) { ether_addr_copy(dev->dev_addr, addr->sa_data); - return 0; + goto out_unlock; } /* don't register the same address twice */ if (ether_addr_equal_64bits(dev->dev_addr, addr->sa_data) && (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED)) - return 0; + goto out_unlock; /* add the new address, switch over, drop the old */ rc = qeth_l2_send_setmac(card, addr->sa_data); if (rc) - return rc; + goto out_unlock; ether_addr_copy(old_addr, dev->dev_addr); ether_addr_copy(dev->dev_addr, addr->sa_data); if (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED) qeth_l2_remove_mac(card, old_addr); card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED; - return 0; + +out_unlock: + mutex_unlock(&card->conf_mutex); + return rc; } static void qeth_promisc_to_bridge(struct qeth_card *card) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index eeaf6739215f..dd4eb986f693 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1219,7 +1219,8 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) if (ubufs) vhost_net_ubuf_put_wait_and_free(ubufs); err_ubufs: - sockfd_put(sock); + if (sock) + sockfd_put(sock); err_vq: mutex_unlock(&vq->mutex); err: diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index 26f6b4f41ce6..00458e985cc3 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -148,6 +148,15 @@ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param) cmd); goto out; } + } else { + unsigned int inr = _IOC_NR(cmd); + + if (inr == AUTOFS_DEV_IOCTL_OPENMOUNT_CMD || + inr == AUTOFS_DEV_IOCTL_REQUESTER_CMD || + inr == AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD) { + err = -EINVAL; + goto out; + } } err = 0; @@ -284,7 +293,8 @@ static int autofs_dev_ioctl_openmount(struct file *fp, dev_t devid; int err, fd; - /* param->path has already been checked */ + /* param->path has been checked in validate_dev_ioctl() */ + if (!param->openmount.devid) return -EINVAL; @@ -446,10 +456,7 @@ static int autofs_dev_ioctl_requester(struct file *fp, dev_t devid; int err = -ENOENT; - if (param->size <= AUTOFS_DEV_IOCTL_SIZE) { - err = -EINVAL; - goto out; - } + /* param->path has been checked in validate_dev_ioctl() */ devid = sbi->sb->s_dev; @@ -534,10 +541,7 @@ static int autofs_dev_ioctl_ismountpoint(struct file *fp, unsigned int devid, magic; int err = -ENOENT; - if (param->size <= AUTOFS_DEV_IOCTL_SIZE) { - err = -EINVAL; - goto out; - } + /* param->path has been checked in validate_dev_ioctl() */ name = param->path; type = param->ismountpoint.in.type; diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c index 7e288d97adcb..9fed1c05f1f4 100644 --- a/fs/reiserfs/prints.c +++ b/fs/reiserfs/prints.c @@ -76,83 +76,99 @@ static char *le_type(struct reiserfs_key *key) } /* %k */ -static void sprintf_le_key(char *buf, struct reiserfs_key *key) +static int scnprintf_le_key(char *buf, size_t size, struct reiserfs_key *key) { if (key) - sprintf(buf, "[%d %d %s %s]", le32_to_cpu(key->k_dir_id), - le32_to_cpu(key->k_objectid), le_offset(key), - le_type(key)); + return scnprintf(buf, size, "[%d %d %s %s]", + le32_to_cpu(key->k_dir_id), + le32_to_cpu(key->k_objectid), le_offset(key), + le_type(key)); else - sprintf(buf, "[NULL]"); + return scnprintf(buf, size, "[NULL]"); } /* %K */ -static void sprintf_cpu_key(char *buf, struct cpu_key *key) +static int scnprintf_cpu_key(char *buf, size_t size, struct cpu_key *key) { if (key) - sprintf(buf, "[%d %d %s %s]", key->on_disk_key.k_dir_id, - key->on_disk_key.k_objectid, reiserfs_cpu_offset(key), - cpu_type(key)); + return scnprintf(buf, size, "[%d %d %s %s]", + key->on_disk_key.k_dir_id, + key->on_disk_key.k_objectid, + reiserfs_cpu_offset(key), cpu_type(key)); else - sprintf(buf, "[NULL]"); + return scnprintf(buf, size, "[NULL]"); } -static void sprintf_de_head(char *buf, struct reiserfs_de_head *deh) +static int scnprintf_de_head(char *buf, size_t size, + struct reiserfs_de_head *deh) { if (deh) - sprintf(buf, - "[offset=%d dir_id=%d objectid=%d location=%d state=%04x]", - deh_offset(deh), deh_dir_id(deh), deh_objectid(deh), - deh_location(deh), deh_state(deh)); + return scnprintf(buf, size, + "[offset=%d dir_id=%d objectid=%d location=%d state=%04x]", + deh_offset(deh), deh_dir_id(deh), + deh_objectid(deh), deh_location(deh), + deh_state(deh)); else - sprintf(buf, "[NULL]"); + return scnprintf(buf, size, "[NULL]"); } -static void sprintf_item_head(char *buf, struct item_head *ih) +static int scnprintf_item_head(char *buf, size_t size, struct item_head *ih) { if (ih) { - strcpy(buf, - (ih_version(ih) == KEY_FORMAT_3_6) ? "*3.6* " : "*3.5*"); - sprintf_le_key(buf + strlen(buf), &(ih->ih_key)); - sprintf(buf + strlen(buf), ", item_len %d, item_location %d, " - "free_space(entry_count) %d", - ih_item_len(ih), ih_location(ih), ih_free_space(ih)); + char *p = buf; + char * const end = buf + size; + + p += scnprintf(p, end - p, "%s", + (ih_version(ih) == KEY_FORMAT_3_6) ? + "*3.6* " : "*3.5*"); + + p += scnprintf_le_key(p, end - p, &ih->ih_key); + + p += scnprintf(p, end - p, + ", item_len %d, item_location %d, free_space(entry_count) %d", + ih_item_len(ih), ih_location(ih), + ih_free_space(ih)); + return p - buf; } else - sprintf(buf, "[NULL]"); + return scnprintf(buf, size, "[NULL]"); } -static void sprintf_direntry(char *buf, struct reiserfs_dir_entry *de) +static int scnprintf_direntry(char *buf, size_t size, + struct reiserfs_dir_entry *de) { char name[20]; memcpy(name, de->de_name, de->de_namelen > 19 ? 19 : de->de_namelen); name[de->de_namelen > 19 ? 19 : de->de_namelen] = 0; - sprintf(buf, "\"%s\"==>[%d %d]", name, de->de_dir_id, de->de_objectid); + return scnprintf(buf, size, "\"%s\"==>[%d %d]", + name, de->de_dir_id, de->de_objectid); } -static void sprintf_block_head(char *buf, struct buffer_head *bh) +static int scnprintf_block_head(char *buf, size_t size, struct buffer_head *bh) { - sprintf(buf, "level=%d, nr_items=%d, free_space=%d rdkey ", - B_LEVEL(bh), B_NR_ITEMS(bh), B_FREE_SPACE(bh)); + return scnprintf(buf, size, + "level=%d, nr_items=%d, free_space=%d rdkey ", + B_LEVEL(bh), B_NR_ITEMS(bh), B_FREE_SPACE(bh)); } -static void sprintf_buffer_head(char *buf, struct buffer_head *bh) +static int scnprintf_buffer_head(char *buf, size_t size, struct buffer_head *bh) { - sprintf(buf, - "dev %pg, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)", - bh->b_bdev, bh->b_size, - (unsigned long long)bh->b_blocknr, atomic_read(&(bh->b_count)), - bh->b_state, bh->b_page, - buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE", - buffer_dirty(bh) ? "DIRTY" : "CLEAN", - buffer_locked(bh) ? "LOCKED" : "UNLOCKED"); + return scnprintf(buf, size, + "dev %pg, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)", + bh->b_bdev, bh->b_size, + (unsigned long long)bh->b_blocknr, + atomic_read(&(bh->b_count)), + bh->b_state, bh->b_page, + buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE", + buffer_dirty(bh) ? "DIRTY" : "CLEAN", + buffer_locked(bh) ? "LOCKED" : "UNLOCKED"); } -static void sprintf_disk_child(char *buf, struct disk_child *dc) +static int scnprintf_disk_child(char *buf, size_t size, struct disk_child *dc) { - sprintf(buf, "[dc_number=%d, dc_size=%u]", dc_block_number(dc), - dc_size(dc)); + return scnprintf(buf, size, "[dc_number=%d, dc_size=%u]", + dc_block_number(dc), dc_size(dc)); } static char *is_there_reiserfs_struct(char *fmt, int *what) @@ -189,55 +205,60 @@ static void prepare_error_buf(const char *fmt, va_list args) char *fmt1 = fmt_buf; char *k; char *p = error_buf; + char * const end = &error_buf[sizeof(error_buf)]; int what; spin_lock(&error_lock); - strcpy(fmt1, fmt); + if (WARN_ON(strscpy(fmt_buf, fmt, sizeof(fmt_buf)) < 0)) { + strscpy(error_buf, "format string too long", end - error_buf); + goto out_unlock; + } while ((k = is_there_reiserfs_struct(fmt1, &what)) != NULL) { *k = 0; - p += vsprintf(p, fmt1, args); + p += vscnprintf(p, end - p, fmt1, args); switch (what) { case 'k': - sprintf_le_key(p, va_arg(args, struct reiserfs_key *)); + p += scnprintf_le_key(p, end - p, + va_arg(args, struct reiserfs_key *)); break; case 'K': - sprintf_cpu_key(p, va_arg(args, struct cpu_key *)); + p += scnprintf_cpu_key(p, end - p, + va_arg(args, struct cpu_key *)); break; case 'h': - sprintf_item_head(p, va_arg(args, struct item_head *)); + p += scnprintf_item_head(p, end - p, + va_arg(args, struct item_head *)); break; case 't': - sprintf_direntry(p, - va_arg(args, - struct reiserfs_dir_entry *)); + p += scnprintf_direntry(p, end - p, + va_arg(args, struct reiserfs_dir_entry *)); break; case 'y': - sprintf_disk_child(p, - va_arg(args, struct disk_child *)); + p += scnprintf_disk_child(p, end - p, + va_arg(args, struct disk_child *)); break; case 'z': - sprintf_block_head(p, - va_arg(args, struct buffer_head *)); + p += scnprintf_block_head(p, end - p, + va_arg(args, struct buffer_head *)); break; case 'b': - sprintf_buffer_head(p, - va_arg(args, struct buffer_head *)); + p += scnprintf_buffer_head(p, end - p, + va_arg(args, struct buffer_head *)); break; case 'a': - sprintf_de_head(p, - va_arg(args, - struct reiserfs_de_head *)); + p += scnprintf_de_head(p, end - p, + va_arg(args, struct reiserfs_de_head *)); break; } - p += strlen(p); fmt1 = k + 2; } - vsprintf(p, fmt1, args); + p += vscnprintf(p, end - p, fmt1, args); +out_unlock: spin_unlock(&error_lock); } diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index a031897fca76..ca1d2cc2cdfa 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -80,6 +80,11 @@ ARM_SMCCC_SMC_32, \ 0, 0x8000) +#define ARM_SMCCC_ARCH_WORKAROUND_2 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0x7fff) + #ifndef __ASSEMBLY__ #include <linux/linkage.h> @@ -291,5 +296,10 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, */ #define arm_smccc_1_1_hvc(...) __arm_smccc_1_1(SMCCC_HVC_INST, __VA_ARGS__) +/* Return codes defined in ARM DEN 0070A */ +#define SMCCC_RET_SUCCESS 0 +#define SMCCC_RET_NOT_SUPPORTED -1 +#define SMCCC_RET_NOT_REQUIRED -2 + #endif /*__ASSEMBLY__*/ #endif /*__LINUX_ARM_SMCCC_H*/ diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index 0c27515d2cf6..8124815eb121 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -214,6 +214,7 @@ struct atmphy_ops { struct atm_skb_data { struct atm_vcc *vcc; /* ATM VCC */ unsigned long atm_options; /* ATM layer options */ + unsigned int acct_truesize; /* truesize accounted to vcc */ }; #define VCC_HTABLE_SIZE 32 @@ -241,6 +242,20 @@ void vcc_insert_socket(struct sock *sk); void atm_dev_release_vccs(struct atm_dev *dev); +static inline void atm_account_tx(struct atm_vcc *vcc, struct sk_buff *skb) +{ + /* + * Because ATM skbs may not belong to a sock (and we don't + * necessarily want to), skb->truesize may be adjusted, + * escaping the hack in pskb_expand_head() which avoids + * doing so for some cases. So stash the value of truesize + * at the time we accounted it, and atm_pop_raw() can use + * that value later, in case it changes. + */ + refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + ATM_SKB(skb)->acct_truesize = skb->truesize; + ATM_SKB(skb)->atm_options = vcc->atm_options; +} static inline void atm_force_charge(struct atm_vcc *vcc,int truesize) { diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 0bd432a4d7bd..24251762c20c 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -22,7 +22,6 @@ struct dentry; */ enum wb_state { WB_registered, /* bdi_register() was done */ - WB_shutting_down, /* wb_shutdown() in progress */ WB_writeback_running, /* Writeback is in progress */ WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */ WB_start_all, /* nr_pages == 0 (all) work pending */ @@ -189,6 +188,7 @@ struct backing_dev_info { #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct rb_root cgwb_congested_tree; /* their congested states */ + struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ #else struct bdi_writeback_congested *wb_congested; #endif diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 17b18b91ebac..1602bf4ab4cd 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -186,6 +186,8 @@ struct bio { * throttling rules. Don't do it again. */ #define BIO_TRACE_COMPLETION 10 /* bio_endio() should trace the final completion * of this bio. */ +#define BIO_QUEUE_ENTERED 11 /* can use blk_queue_enter_live() */ + /* See BVEC_POOL_OFFSET below before adding new flags */ /* diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index b4bf73f5e38f..f1fa516bcf51 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -65,6 +65,18 @@ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) #endif +/* + * Feature detection for gnu_inline (gnu89 extern inline semantics). Either + * __GNUC_STDC_INLINE__ is defined (not using gnu89 extern inline semantics, + * and we opt in to the gnu89 semantics), or __GNUC_STDC_INLINE__ is not + * defined so the gnu89 semantics are the default. + */ +#ifdef __GNUC_STDC_INLINE__ +# define __gnu_inline __attribute__((gnu_inline)) +#else +# define __gnu_inline +#endif + /* * Force always-inline if the user requests it so via the .config, * or if gcc is too old. @@ -72,19 +84,22 @@ * -Wunused-function. This turns out to avoid the need for complex #ifdef * directives. Suppress the warning in clang as well by using "unused" * function attribute, which is redundant but not harmful for gcc. + * Prefer gnu_inline, so that extern inline functions do not emit an + * externally visible function. This makes extern inline behave as per gnu89 + * semantics rather than c99. This prevents multiple symbol definition errors + * of extern inline functions at link time. + * A lot of inline functions can cause havoc with function tracing. */ #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4) -#define inline inline __attribute__((always_inline,unused)) notrace -#define __inline__ __inline__ __attribute__((always_inline,unused)) notrace -#define __inline __inline __attribute__((always_inline,unused)) notrace +#define inline \ + inline __attribute__((always_inline, unused)) notrace __gnu_inline #else -/* A lot of inline functions can cause havoc with function tracing */ -#define inline inline __attribute__((unused)) notrace -#define __inline__ __inline__ __attribute__((unused)) notrace -#define __inline __inline __attribute__((unused)) notrace +#define inline inline __attribute__((unused)) notrace __gnu_inline #endif +#define __inline__ inline +#define __inline inline #define __always_inline inline __attribute__((always_inline)) #define noinline __attribute__((noinline)) diff --git a/include/linux/filter.h b/include/linux/filter.h index fc4e8f91b03d..b49658f9001e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -453,15 +453,16 @@ struct sock_fprog_kern { }; struct bpf_binary_header { - unsigned int pages; - u8 image[]; + u32 pages; + /* Some arches need word alignment for their instructions */ + u8 image[] __aligned(4); }; struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ jit_requested:1,/* archs need to JIT the prog */ - locked:1, /* Program image locked? */ + undo_set_mem:1, /* Passed set_memory_ro() checkpoint */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ @@ -644,50 +645,27 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, const u32 size_default) #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) -#ifdef CONFIG_ARCH_HAS_SET_MEMORY -static inline void bpf_prog_lock_ro(struct bpf_prog *fp) -{ - fp->locked = 1; - WARN_ON_ONCE(set_memory_ro((unsigned long)fp, fp->pages)); -} - -static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) -{ - if (fp->locked) { - WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages)); - /* In case set_memory_rw() fails, we want to be the first - * to crash here instead of some random place later on. - */ - fp->locked = 0; - } -} - -static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) -{ - WARN_ON_ONCE(set_memory_ro((unsigned long)hdr, hdr->pages)); -} - -static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) -{ - WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages)); -} -#else static inline void bpf_prog_lock_ro(struct bpf_prog *fp) { + fp->undo_set_mem = 1; + set_memory_ro((unsigned long)fp, fp->pages); } static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) { + if (fp->undo_set_mem) + set_memory_rw((unsigned long)fp, fp->pages); } static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { + set_memory_ro((unsigned long)hdr, hdr->pages); } static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) { + set_memory_rw((unsigned long)hdr, hdr->pages); } -#endif /* CONFIG_ARCH_HAS_SET_MEMORY */ static inline struct bpf_binary_header * bpf_jit_binary_hdr(const struct bpf_prog *fp) diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index d3c9db492b30..fab5121ffb8f 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -8,6 +8,8 @@ #include <linux/mlx5/driver.h> +#define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager) + enum { SRIOV_NONE, SRIOV_LEGACY, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1aad455538f4..5b662ea2e32a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -905,7 +905,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 vnic_env_queue_counters[0x1]; u8 ets[0x1]; u8 nic_flow_table[0x1]; - u8 eswitch_flow_table[0x1]; + u8 eswitch_manager[0x1]; u8 device_memory[0x1]; u8 mcam_reg[0x1]; u8 pcam_reg[0x1]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cf44503ea81a..5ad916d31471 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2735,11 +2735,31 @@ static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, if (PTR_ERR(pp) != -EINPROGRESS) NAPI_GRO_CB(skb)->flush |= flush; } +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff **pp, + int flush, + struct gro_remcsum *grc) +{ + if (PTR_ERR(pp) != -EINPROGRESS) { + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; + } +} #else static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) { NAPI_GRO_CB(skb)->flush |= flush; } +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff **pp, + int flush, + struct gro_remcsum *grc) +{ + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; +} #endif static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index e828d31be5da..3b4fbf690957 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -111,6 +111,11 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, { } +static inline bool tcf_block_shared(struct tcf_block *block) +{ + return false; +} + static inline struct Qdisc *tcf_block_q(struct tcf_block *block) { return NULL; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6ef6746a7871..78509e3f68da 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1513,6 +1513,17 @@ static int bpf_check_tail_call(const struct bpf_prog *fp) return 0; } +static void bpf_prog_select_func(struct bpf_prog *fp) +{ +#ifndef CONFIG_BPF_JIT_ALWAYS_ON + u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1); + + fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1]; +#else + fp->bpf_func = __bpf_prog_ret0_warn; +#endif +} + /** * bpf_prog_select_runtime - select exec runtime for BPF program * @fp: bpf_prog populated with internal BPF program @@ -1523,13 +1534,13 @@ static int bpf_check_tail_call(const struct bpf_prog *fp) */ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) { -#ifndef CONFIG_BPF_JIT_ALWAYS_ON - u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1); + /* In case of BPF to BPF calls, verifier did all the prep + * work with regards to JITing, etc. + */ + if (fp->bpf_func) + goto finalize; - fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1]; -#else - fp->bpf_func = __bpf_prog_ret0_warn; -#endif + bpf_prog_select_func(fp); /* eBPF JITs can rewrite the program in case constant * blinding is active. However, in case of error during @@ -1550,6 +1561,8 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) if (*err) return fp; } + +finalize: bpf_prog_lock_ro(fp); /* The tail call compatibility check can only be done at diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 95a84b2f10ce..fc7ee4357381 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -112,6 +112,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); static int bpf_tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); +static void bpf_tcp_close(struct sock *sk, long timeout); static inline struct smap_psock *smap_psock_sk(const struct sock *sk) { @@ -133,7 +134,42 @@ static bool bpf_tcp_stream_read(const struct sock *sk) return !empty; } -static struct proto tcp_bpf_proto; +enum { + SOCKMAP_IPV4, + SOCKMAP_IPV6, + SOCKMAP_NUM_PROTS, +}; + +enum { + SOCKMAP_BASE, + SOCKMAP_TX, + SOCKMAP_NUM_CONFIGS, +}; + +static struct proto *saved_tcpv6_prot __read_mostly; +static DEFINE_SPINLOCK(tcpv6_prot_lock); +static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS]; +static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS], + struct proto *base) +{ + prot[SOCKMAP_BASE] = *base; + prot[SOCKMAP_BASE].close = bpf_tcp_close; + prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg; + prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read; + + prot[SOCKMAP_TX] = prot[SOCKMAP_BASE]; + prot[SOCKMAP_TX].sendmsg = bpf_tcp_sendmsg; + prot[SOCKMAP_TX].sendpage = bpf_tcp_sendpage; +} + +static void update_sk_prot(struct sock *sk, struct smap_psock *psock) +{ + int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4; + int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE; + + sk->sk_prot = &bpf_tcp_prots[family][conf]; +} + static int bpf_tcp_init(struct sock *sk) { struct smap_psock *psock; @@ -153,14 +189,17 @@ static int bpf_tcp_init(struct sock *sk) psock->save_close = sk->sk_prot->close; psock->sk_proto = sk->sk_prot; - if (psock->bpf_tx_msg) { - tcp_bpf_proto.sendmsg = bpf_tcp_sendmsg; - tcp_bpf_proto.sendpage = bpf_tcp_sendpage; - tcp_bpf_proto.recvmsg = bpf_tcp_recvmsg; - tcp_bpf_proto.stream_memory_read = bpf_tcp_stream_read; + /* Build IPv6 sockmap whenever the address of tcpv6_prot changes */ + if (sk->sk_family == AF_INET6 && + unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) { + spin_lock_bh(&tcpv6_prot_lock); + if (likely(sk->sk_prot != saved_tcpv6_prot)) { + build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot); + smp_store_release(&saved_tcpv6_prot, sk->sk_prot); + } + spin_unlock_bh(&tcpv6_prot_lock); } - - sk->sk_prot = &tcp_bpf_proto; + update_sk_prot(sk, psock); rcu_read_unlock(); return 0; } @@ -432,7 +471,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) while (sg[i].length) { free += sg[i].length; sk_mem_uncharge(sk, sg[i].length); - put_page(sg_page(&sg[i])); + if (!md->skb) + put_page(sg_page(&sg[i])); sg[i].length = 0; sg[i].page_link = 0; sg[i].offset = 0; @@ -441,6 +481,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) if (i == MAX_SKB_FRAGS) i = 0; } + if (md->skb) + consume_skb(md->skb); return free; } @@ -1070,8 +1112,7 @@ static void bpf_tcp_msg_add(struct smap_psock *psock, static int bpf_tcp_ulp_register(void) { - tcp_bpf_proto = tcp_prot; - tcp_bpf_proto.close = bpf_tcp_close; + build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot); /* Once BPF TX ULP is registered it is never unregistered. It * will be in the ULP list for the lifetime of the system. Doing * duplicate registers is not a problem. diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 016ef9025827..74fa60b4b438 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1328,9 +1328,7 @@ static int bpf_prog_load(union bpf_attr *attr) if (err < 0) goto free_used_maps; - /* eBPF program is ready to be JITed */ - if (!prog->bpf_func) - prog = bpf_prog_select_runtime(prog, &err); + prog = bpf_prog_select_runtime(prog, &err); if (err < 0) goto free_used_maps; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 56212edd6f23..1b586f31cbfd 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5349,6 +5349,10 @@ static int jit_subprogs(struct bpf_verifier_env *env) if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) continue; + /* Upon error here we cannot fall back to interpreter but + * need a hard reject of the program. Thus -EFAULT is + * propagated in any case. + */ subprog = find_subprog(env, i + insn->imm + 1); if (subprog < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", @@ -5369,7 +5373,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) func = kzalloc(sizeof(prog) * (env->subprog_cnt + 1), GFP_KERNEL); if (!func) - return -ENOMEM; + goto out_undo_insn; for (i = 0; i <= env->subprog_cnt; i++) { subprog_start = subprog_end; @@ -5424,7 +5428,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) tmp = bpf_int_jit_compile(func[i]); if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) { verbose(env, "JIT doesn't support bpf-to-bpf calls\n"); - err = -EFAULT; + err = -ENOTSUPP; goto out_free; } cond_resched(); @@ -5466,6 +5470,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) if (func[i]) bpf_jit_free(func[i]); kfree(func); +out_undo_insn: /* cleanup main prog to be interpreted */ prog->jit_requested = 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { @@ -5492,6 +5497,8 @@ static int fixup_call_args(struct bpf_verifier_env *env) err = jit_subprogs(env); if (err == 0) return 0; + if (err == -EFAULT) + return err; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON for (i = 0; i < prog->len; i++, insn++) { diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 8fe3ebd6ac00..048d0651aa98 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -359,15 +359,8 @@ static void wb_shutdown(struct bdi_writeback *wb) spin_lock_bh(&wb->work_lock); if (!test_and_clear_bit(WB_registered, &wb->state)) { spin_unlock_bh(&wb->work_lock); - /* - * Wait for wb shutdown to finish if someone else is just - * running wb_shutdown(). Otherwise we could proceed to wb / - * bdi destruction before wb_shutdown() is finished. - */ - wait_on_bit(&wb->state, WB_shutting_down, TASK_UNINTERRUPTIBLE); return; } - set_bit(WB_shutting_down, &wb->state); spin_unlock_bh(&wb->work_lock); cgwb_remove_from_bdi_list(wb); @@ -379,12 +372,6 @@ static void wb_shutdown(struct bdi_writeback *wb) mod_delayed_work(bdi_wq, &wb->dwork, 0); flush_delayed_work(&wb->dwork); WARN_ON(!list_empty(&wb->work_list)); - /* - * Make sure bit gets cleared after shutdown is finished. Matches with - * the barrier provided by test_and_clear_bit() above. - */ - smp_wmb(); - clear_and_wake_up_bit(WB_shutting_down, &wb->state); } static void wb_exit(struct bdi_writeback *wb) @@ -508,10 +495,12 @@ static void cgwb_release_workfn(struct work_struct *work) struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); + mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb); css_put(wb->memcg_css); css_put(wb->blkcg_css); + mutex_unlock(&wb->bdi->cgwb_release_mutex); fprop_local_destroy_percpu(&wb->memcg_completions); percpu_ref_exit(&wb->refcnt); @@ -697,6 +686,7 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); bdi->cgwb_congested_tree = RB_ROOT; + mutex_init(&bdi->cgwb_release_mutex); ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); if (!ret) { @@ -717,7 +707,10 @@ static void cgwb_bdi_unregister(struct backing_dev_info *bdi) spin_lock_irq(&cgwb_lock); radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) cgwb_kill(*slot); + spin_unlock_irq(&cgwb_lock); + mutex_lock(&bdi->cgwb_release_mutex); + spin_lock_irq(&cgwb_lock); while (!list_empty(&bdi->wb_list)) { wb = list_first_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); @@ -726,6 +719,7 @@ static void cgwb_bdi_unregister(struct backing_dev_info *bdi) spin_lock_irq(&cgwb_lock); } spin_unlock_irq(&cgwb_lock); + mutex_unlock(&bdi->cgwb_release_mutex); } /** diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 5505ee6ebdbe..d3a5ec02e64c 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -688,7 +688,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } diff --git a/net/atm/br2684.c b/net/atm/br2684.c index fd94bea36ee8..82c8d33bd8ba 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -252,8 +252,7 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev, ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc; pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, atmvcc, atmvcc->dev); - refcount_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc); - ATM_SKB(skb)->atm_options = atmvcc->atm_options; + atm_account_tx(atmvcc, skb); dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; diff --git a/net/atm/clip.c b/net/atm/clip.c index f07dbc632222..0edebf8decc0 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -381,8 +381,7 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb, memcpy(here, llc_oui, sizeof(llc_oui)); ((__be16 *) here)[3] = skb->protocol; } - refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); - ATM_SKB(skb)->atm_options = vcc->atm_options; + atm_account_tx(vcc, skb); entry->vccs->last_use = jiffies; pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, vcc, vcc->dev); old = xchg(&entry->vccs->xoff, 1); /* assume XOFF ... */ diff --git a/net/atm/common.c b/net/atm/common.c index fc78a0508ae1..a7a68e509628 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -630,10 +630,9 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size) goto out; } pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize); - refcount_add(skb->truesize, &sk->sk_wmem_alloc); + atm_account_tx(vcc, skb); skb->dev = NULL; /* for paths shared with net_device interfaces */ - ATM_SKB(skb)->atm_options = vcc->atm_options; if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) { kfree_skb(skb); error = -EFAULT; diff --git a/net/atm/lec.c b/net/atm/lec.c index 3138a869b5c0..19ad2fd04983 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -182,9 +182,8 @@ lec_send(struct atm_vcc *vcc, struct sk_buff *skb) struct net_device *dev = skb->dev; ATM_SKB(skb)->vcc = vcc; - ATM_SKB(skb)->atm_options = vcc->atm_options; + atm_account_tx(vcc, skb); - refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); if (vcc->send(vcc, skb) < 0) { dev->stats.tx_dropped++; return; diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 31e0dcb970f8..44ddcdd5fd35 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -555,8 +555,7 @@ static int send_via_shortcut(struct sk_buff *skb, struct mpoa_client *mpc) sizeof(struct llc_snap_hdr)); } - refcount_add(skb->truesize, &sk_atm(entry->shortcut)->sk_wmem_alloc); - ATM_SKB(skb)->atm_options = entry->shortcut->atm_options; + atm_account_tx(entry->shortcut, skb); entry->shortcut->send(entry->shortcut, skb); entry->packets_fwded++; mpc->in_ops->put(entry); diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index 21d9d341a619..af8c4b38b746 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -350,8 +350,7 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb) return 1; } - refcount_add(skb->truesize, &sk_atm(ATM_SKB(skb)->vcc)->sk_wmem_alloc); - ATM_SKB(skb)->atm_options = ATM_SKB(skb)->vcc->atm_options; + atm_account_tx(vcc, skb); pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, ATM_SKB(skb)->vcc, ATM_SKB(skb)->vcc->dev); ret = ATM_SKB(skb)->vcc->send(ATM_SKB(skb)->vcc, skb) diff --git a/net/atm/raw.c b/net/atm/raw.c index ee10e8d46185..b3ba44aab0ee 100644 --- a/net/atm/raw.c +++ b/net/atm/raw.c @@ -35,8 +35,8 @@ static void atm_pop_raw(struct atm_vcc *vcc, struct sk_buff *skb) struct sock *sk = sk_atm(vcc); pr_debug("(%d) %d -= %d\n", - vcc->vci, sk_wmem_alloc_get(sk), skb->truesize); - WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)); + vcc->vci, sk_wmem_alloc_get(sk), ATM_SKB(skb)->acct_truesize); + WARN_ON(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize, &sk->sk_wmem_alloc)); dev_kfree_skb_any(skb); sk->sk_write_space(sk); } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 499123afcab5..9d37d91b34e5 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -396,6 +396,12 @@ ebt_check_watcher(struct ebt_entry_watcher *w, struct xt_tgchk_param *par, watcher = xt_request_find_target(NFPROTO_BRIDGE, w->u.name, 0); if (IS_ERR(watcher)) return PTR_ERR(watcher); + + if (watcher->family != NFPROTO_BRIDGE) { + module_put(watcher->me); + return -ENOENT; + } + w->u.watcher = watcher; par->target = watcher; @@ -717,6 +723,13 @@ ebt_check_entry(struct ebt_entry *e, struct net *net, goto cleanup_watchers; } + /* Reject UNSPEC, xtables verdicts/return values are incompatible */ + if (target->family != NFPROTO_BRIDGE) { + module_put(target->me); + ret = -ENOENT; + goto cleanup_watchers; + } + t->u.target = target; if (t->u.target == &ebt_standard_target) { if (gap < sizeof(struct ebt_standard_target)) { diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index a04e1e88bf3a..50537ff961a7 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -285,16 +285,9 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) if (ifr->ifr_qlen < 0) return -EINVAL; if (dev->tx_queue_len ^ ifr->ifr_qlen) { - unsigned int orig_len = dev->tx_queue_len; - - dev->tx_queue_len = ifr->ifr_qlen; - err = call_netdevice_notifiers( - NETDEV_CHANGE_TX_QUEUE_LEN, dev); - err = notifier_to_errno(err); - if (err) { - dev->tx_queue_len = orig_len; + err = dev_change_tx_queue_len(dev, ifr->ifr_qlen); + if (err) return err; - } } return 0; diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 8b5ba6dffac7..12877a1514e7 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -600,7 +600,7 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk, { struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); struct dccp_sock *dp = dccp_sk(sk); - ktime_t now = ktime_get_real(); + ktime_t now = ktime_get(); s64 delta = 0; switch (fbtype) { @@ -625,15 +625,14 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk, case CCID3_FBACK_PERIODIC: delta = ktime_us_delta(now, hc->rx_tstamp_last_feedback); if (delta <= 0) - DCCP_BUG("delta (%ld) <= 0", (long)delta); - else - hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta); + delta = 1; + hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta); break; default: return; } - ccid3_pr_debug("Interval %ldusec, X_recv=%u, 1/p=%u\n", (long)delta, + ccid3_pr_debug("Interval %lldusec, X_recv=%u, 1/p=%u\n", delta, hc->rx_x_recv, hc->rx_pinv); hc->rx_tstamp_last_feedback = now; @@ -680,7 +679,8 @@ static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb) static u32 ccid3_first_li(struct sock *sk) { struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); - u32 x_recv, p, delta; + u32 x_recv, p; + s64 delta; u64 fval; if (hc->rx_rtt == 0) { @@ -688,7 +688,9 @@ static u32 ccid3_first_li(struct sock *sk) hc->rx_rtt = DCCP_FALLBACK_RTT; } - delta = ktime_to_us(net_timedelta(hc->rx_tstamp_last_feedback)); + delta = ktime_us_delta(ktime_get(), hc->rx_tstamp_last_feedback); + if (delta <= 0) + delta = 1; x_recv = scaled_div32(hc->rx_bytes_recv, delta); if (x_recv == 0) { /* would also trigger divide-by-zero */ DCCP_WARN("X_recv==0\n"); diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 40c851693f77..0c9478b91fa5 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -86,35 +86,39 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) opt++; kdebug("options: '%s'", opt); do { + int opt_len, opt_nlen; const char *eq; - int opt_len, opt_nlen, opt_vlen, tmp; + char optval[128]; next_opt = memchr(opt, '#', end - opt) ?: end; opt_len = next_opt - opt; - if (opt_len <= 0 || opt_len > 128) { + if (opt_len <= 0 || opt_len > sizeof(optval)) { pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n", opt_len); return -EINVAL; } - eq = memchr(opt, '=', opt_len) ?: end; - opt_nlen = eq - opt; - eq++; - opt_vlen = next_opt - eq; /* will be -1 if no value */ + eq = memchr(opt, '=', opt_len); + if (eq) { + opt_nlen = eq - opt; + eq++; + memcpy(optval, eq, next_opt - eq); + optval[next_opt - eq] = '\0'; + } else { + opt_nlen = opt_len; + optval[0] = '\0'; + } - tmp = opt_vlen >= 0 ? opt_vlen : 0; - kdebug("option '%*.*s' val '%*.*s'", - opt_nlen, opt_nlen, opt, tmp, tmp, eq); + kdebug("option '%*.*s' val '%s'", + opt_nlen, opt_nlen, opt, optval); /* see if it's an error number representing a DNS error * that's to be recorded as the result in this key */ if (opt_nlen == sizeof(DNS_ERRORNO_OPTION) - 1 && memcmp(opt, DNS_ERRORNO_OPTION, opt_nlen) == 0) { kdebug("dns error number option"); - if (opt_vlen <= 0) - goto bad_option_value; - ret = kstrtoul(eq, 10, &derrno); + ret = kstrtoul(optval, 10, &derrno); if (ret < 0) goto bad_option_value; diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 1540db65241a..c9ec1603666b 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -448,9 +448,7 @@ static struct sk_buff **gue_gro_receive(struct sock *sk, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; - skb_gro_remcsum_cleanup(skb, &grc); - skb->remcsum_offload = 0; + skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 1859c473b21a..6a7d980105f6 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -223,7 +223,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 31ff46daae97..3647167c8fa3 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -243,9 +243,9 @@ static inline int compute_score(struct sock *sk, struct net *net, bool dev_match = (sk->sk_bound_dev_if == dif || sk->sk_bound_dev_if == sdif); - if (exact_dif && !dev_match) + if (!dev_match) return -1; - if (sk->sk_bound_dev_if && dev_match) + if (sk->sk_bound_dev_if) score += 4; } if (sk->sk_incoming_cpu == raw_smp_processor_id()) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 4b195bac8ac0..2f600f261690 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -263,8 +263,9 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, ipv4.sysctl_tcp_fastopen); struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) }; struct tcp_fastopen_context *ctxt; - int ret; u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */ + __le32 key[4]; + int ret, i; tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL); if (!tbl.data) @@ -273,11 +274,14 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, rcu_read_lock(); ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx); if (ctxt) - memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH); + memcpy(key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH); else - memset(user_key, 0, sizeof(user_key)); + memset(key, 0, sizeof(key)); rcu_read_unlock(); + for (i = 0; i < ARRAY_SIZE(key); i++) + user_key[i] = le32_to_cpu(key[i]); + snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x", user_key[0], user_key[1], user_key[2], user_key[3]); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); @@ -288,13 +292,17 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, ret = -EINVAL; goto bad_key; } - tcp_fastopen_reset_cipher(net, NULL, user_key, + + for (i = 0; i < ARRAY_SIZE(user_key); i++) + key[i] = cpu_to_le32(user_key[i]); + + tcp_fastopen_reset_cipher(net, NULL, key, TCP_FASTOPEN_KEY_LENGTH); } bad_key: pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n", - user_key[0], user_key[1], user_key[2], user_key[3], + user_key[0], user_key[1], user_key[2], user_key[3], (char *)tbl.data, ret); kfree(tbl.data); return ret; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e51c644484dc..1f25ebab25d2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3149,6 +3149,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, if (tcp_is_reno(tp)) { tcp_remove_reno_sacks(sk, pkts_acked); + + /* If any of the cumulatively ACKed segments was + * retransmitted, non-SACK case cannot confirm that + * progress was due to original transmission due to + * lack of TCPCB_SACKED_ACKED bits even if some of + * the packets may have been never retransmitted. + */ + if (flag & FLAG_RETRANS_DATA_ACKED) + flag &= ~FLAG_ORIG_SACK_ACKED; } else { int delta; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index ea6e6e7df0ee..cde2719fcb89 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -295,7 +295,7 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } EXPORT_SYMBOL(udp_gro_receive); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 2febe26de6a1..595ad408dba0 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -113,9 +113,9 @@ static inline int compute_score(struct sock *sk, struct net *net, bool dev_match = (sk->sk_bound_dev_if == dif || sk->sk_bound_dev_if == sdif); - if (exact_dif && !dev_match) + if (!dev_match) return -1; - if (sk->sk_bound_dev_if && dev_match) + if (sk->sk_bound_dev_if) score++; } if (sk->sk_incoming_cpu == raw_smp_processor_id()) diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 5e0332014c17..eeb4d3098ff4 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -585,6 +585,8 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) fq->q.meat == fq->q.len && nf_ct_frag6_reasm(fq, skb, dev)) ret = 0; + else + skb_dst_drop(skb); out_unlock: spin_unlock_bh(&fq->q.lock); diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index 33fb35cbfac1..558fe8cc6d43 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -373,7 +373,7 @@ static int seg6_hmac_init_algo(void) return -ENOMEM; for_each_possible_cpu(cpu) { - tfm = crypto_alloc_shash(algo->name, 0, GFP_KERNEL); + tfm = crypto_alloc_shash(algo->name, 0, 0); if (IS_ERR(tfm)) return PTR_ERR(tfm); p_tfm = per_cpu_ptr(algo->tfms, cpu); diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 3057e453bf31..83918119ceb8 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -371,6 +371,7 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc) tbl->counter = 1; tbl->dead = false; tbl->svc = svc; + atomic_set(&tbl->entries, 0); /* * Hook periodic timer for garbage collection diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 92adc04557ed..bc2bc5eebcb8 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -534,6 +534,7 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc) tbl->counter = 1; tbl->dead = false; tbl->svc = svc; + atomic_set(&tbl->entries, 0); /* * Hook periodic timer for garbage collection diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 2ceefa183cee..6a196e438b6c 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -752,11 +752,14 @@ int nfc_llcp_send_ui_frame(struct nfc_llcp_sock *sock, u8 ssap, u8 dsap, pr_debug("Fragment %zd bytes remaining %zd", frag_len, remaining_len); - pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, MSG_DONTWAIT, + pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, 0, frag_len + LLCP_HEADER_SIZE, &err); if (pdu == NULL) { - pr_err("Could not allocate PDU\n"); - continue; + pr_err("Could not allocate PDU (error=%d)\n", err); + len -= remaining_len; + if (len == 0) + len = err; + break; } pdu = llcp_add_header(pdu, dsap, ssap, LLCP_PDU_UI); diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index 9696ef96b719..1a30e165eeb4 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -104,7 +104,7 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, __skb_pull(skb, nsh_len); skb_reset_mac_header(skb); - skb_reset_mac_len(skb); + skb->mac_len = proto == htons(ETH_P_TEB) ? ETH_HLEN : 0; skb->protocol = proto; features &= NETIF_F_SG; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 38d132d007ba..cb0f02785749 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2294,6 +2294,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (po->stats.stats1.tp_drops) status |= TP_STATUS_LOSING; } + + if (do_vnet && + virtio_net_hdr_from_skb(skb, h.raw + macoff - + sizeof(struct virtio_net_hdr), + vio_le(), true, 0)) + goto drop_n_account; + po->stats.stats1.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; @@ -2301,15 +2308,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } spin_unlock(&sk->sk_receive_queue.lock); - if (do_vnet) { - if (virtio_net_hdr_from_skb(skb, h.raw + macoff - - sizeof(struct virtio_net_hdr), - vio_le(), true, 0)) { - spin_lock(&sk->sk_receive_queue.lock); - goto drop_n_account; - } - } - skb_copy_bits(skb, 0, h.raw + macoff, snaplen); if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp))) diff --git a/net/rds/loop.c b/net/rds/loop.c index f2bf78de5688..dac6218a460e 100644 --- a/net/rds/loop.c +++ b/net/rds/loop.c @@ -193,4 +193,5 @@ struct rds_transport rds_loop_transport = { .inc_copy_to_user = rds_message_inc_copy_to_user, .inc_free = rds_loop_inc_free, .t_name = "loopback", + .t_type = RDS_TRANS_LOOP, }; diff --git a/net/rds/rds.h b/net/rds/rds.h index b04c333d9d1c..f2272fb8cd45 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -479,6 +479,11 @@ struct rds_notifier { int n_status; }; +/* Available as part of RDS core, so doesn't need to participate + * in get_preferred transport etc + */ +#define RDS_TRANS_LOOP 3 + /** * struct rds_transport - transport specific behavioural hooks * diff --git a/net/rds/recv.c b/net/rds/recv.c index dc67458b52f0..192ac6f78ded 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -103,6 +103,11 @@ static void rds_recv_rcvbuf_delta(struct rds_sock *rs, struct sock *sk, rds_stats_add(s_recv_bytes_added_to_socket, delta); else rds_stats_add(s_recv_bytes_removed_from_socket, -delta); + + /* loop transport doesn't send/recv congestion updates */ + if (rs->rs_transport->t_type == RDS_TRANS_LOOP) + return; + now_congested = rs->rs_rcv_bytes > rds_sk_rcvbuf(rs); rdsdebug("rs %p (%pI4:%u) recv bytes %d buf %d " diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 8527cfdc446d..20d7d36b2fc9 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -415,7 +415,8 @@ static void tcf_ife_cleanup(struct tc_action *a) spin_unlock_bh(&ife->tcf_lock); p = rcu_dereference_protected(ife->params, 1); - kfree_rcu(p, rcu); + if (p) + kfree_rcu(p, rcu); } /* under ife->tcf_lock for existing action */ @@ -516,8 +517,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, saddr = nla_data(tb[TCA_IFE_SMAC]); } - ife->tcf_action = parm->action; - if (parm->flags & IFE_ENCODE) { if (daddr) ether_addr_copy(p->eth_dst, daddr); @@ -543,10 +542,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, NULL, NULL); if (err) { metadata_parse_err: - if (exists) - tcf_idr_release(*a, bind); if (ret == ACT_P_CREATED) - _tcf_ife_cleanup(*a); + tcf_idr_release(*a, bind); if (exists) spin_unlock_bh(&ife->tcf_lock); @@ -567,7 +564,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, err = use_all_metadata(ife); if (err) { if (ret == ACT_P_CREATED) - _tcf_ife_cleanup(*a); + tcf_idr_release(*a, bind); if (exists) spin_unlock_bh(&ife->tcf_lock); @@ -576,6 +573,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } } + ife->tcf_action = parm->action; if (exists) spin_unlock_bh(&ife->tcf_lock); diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c index c98a61e980ba..9c4c2bb547d7 100644 --- a/net/sched/sch_blackhole.c +++ b/net/sched/sch_blackhole.c @@ -21,7 +21,7 @@ static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { qdisc_drop(skb, sch, to_free); - return NET_XMIT_SUCCESS; + return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; } static struct sk_buff *blackhole_dequeue(struct Qdisc *sch) diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 092bebc70048..7afd66949a91 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -35,7 +35,6 @@ struct _strp_msg { */ struct strp_msg strp; int accum_len; - int early_eaten; }; static inline struct _strp_msg *_strp_msg(struct sk_buff *skb) @@ -115,20 +114,6 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, head = strp->skb_head; if (head) { /* Message already in progress */ - - stm = _strp_msg(head); - if (unlikely(stm->early_eaten)) { - /* Already some number of bytes on the receive sock - * data saved in skb_head, just indicate they - * are consumed. - */ - eaten = orig_len <= stm->early_eaten ? - orig_len : stm->early_eaten; - stm->early_eaten -= eaten; - - return eaten; - } - if (unlikely(orig_offset)) { /* Getting data with a non-zero offset when a message is * in progress is not expected. If it does happen, we @@ -297,9 +282,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, } stm->accum_len += cand_len; + eaten += cand_len; strp->need_bytes = stm->strp.full_len - stm->accum_len; - stm->early_eaten = cand_len; STRP_STATS_ADD(strp->stats.bytes, cand_len); desc->count = 0; /* Stop reading socket */ break; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 5fe29121b9a8..9a7f91232de8 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -440,7 +440,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) ret = tls_push_record(sk, msg->msg_flags, record_type); if (!ret) continue; - if (ret == -EAGAIN) + if (ret < 0) goto send_end; copied -= try_to_copy; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 8e03bd3f3668..5d3cce9e8744 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -201,7 +201,7 @@ virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt) return -ENODEV; } - if (le32_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid) + if (le64_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid) return virtio_transport_send_pkt_loopback(vsock, pkt); if (pkt->reply) diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index a4c1b76240df..2d9b4795edb2 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -1490,6 +1490,10 @@ static int init_hyp_mode(void) } } + err = hyp_map_aux_data(); + if (err) + kvm_err("Cannot map host auxilary data: %d\n", err); + return 0; out_err: diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index c4762bef13c6..c95ab4c5a475 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -405,7 +405,7 @@ static int kvm_psci_call(struct kvm_vcpu *vcpu) int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) { u32 func_id = smccc_get_function(vcpu); - u32 val = PSCI_RET_NOT_SUPPORTED; + u32 val = SMCCC_RET_NOT_SUPPORTED; u32 feature; switch (func_id) { @@ -417,7 +417,21 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) switch(feature) { case ARM_SMCCC_ARCH_WORKAROUND_1: if (kvm_arm_harden_branch_predictor()) - val = 0; + val = SMCCC_RET_SUCCESS; + break; + case ARM_SMCCC_ARCH_WORKAROUND_2: + switch (kvm_arm_have_ssbd()) { + case KVM_SSBD_FORCE_DISABLE: + case KVM_SSBD_UNKNOWN: + break; + case KVM_SSBD_KERNEL: + val = SMCCC_RET_SUCCESS; + break; + case KVM_SSBD_FORCE_ENABLE: + case KVM_SSBD_MITIGATED: + val = SMCCC_RET_NOT_REQUIRED; + break; + } break; } break;