diff --git a/Documentation/vm/slub.rst b/Documentation/vm/slub.rst index 03f294a638bd..d3028554b1e9 100644 --- a/Documentation/vm/slub.rst +++ b/Documentation/vm/slub.rst @@ -181,7 +181,7 @@ SLUB Debug output Here is a sample of slub debug output:: ==================================================================== - BUG kmalloc-8: Redzone overwritten + BUG kmalloc-8: Right Redzone overwritten -------------------------------------------------------------------- INFO: 0xc90f6d28-0xc90f6d2b. First byte 0x00 instead of 0xcc @@ -189,10 +189,10 @@ Here is a sample of slub debug output:: INFO: Object 0xc90f6d20 @offset=3360 fp=0xc90f6d58 INFO: Allocated in get_modalias+0x61/0xf5 age=53 cpu=1 pid=554 - Bytes b4 0xc90f6d10: 00 00 00 00 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a ........ZZZZZZZZ - Object 0xc90f6d20: 31 30 31 39 2e 30 30 35 1019.005 - Redzone 0xc90f6d28: 00 cc cc cc . - Padding 0xc90f6d50: 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZ + Bytes b4 (0xc90f6d10): 00 00 00 00 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a ........ZZZZZZZZ + Object (0xc90f6d20): 31 30 31 39 2e 30 30 35 1019.005 + Redzone (0xc90f6d28): 00 cc cc cc . + Padding (0xc90f6d50): 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZ [<c010523d>] dump_trace+0x63/0x1eb [<c01053df>] show_trace_log_lvl+0x1a/0x2f diff --git a/Makefile b/Makefile index e0a252b64463..d2fe36db78ae 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 12 -SUBLEVEL = 12 +SUBLEVEL = 13 EXTRAVERSION = NAME = Frozen Wasteland @@ -913,11 +913,14 @@ CC_FLAGS_LTO += -fvisibility=hidden # Limit inlining across translation units to reduce binary size KBUILD_LDFLAGS += -mllvm -import-instr-limit=5 -# Check for frame size exceeding threshold during prolog/epilog insertion. +# Check for frame size exceeding threshold during prolog/epilog insertion +# when using lld < 13.0.0. ifneq ($(CONFIG_FRAME_WARN),0) +ifeq ($(shell test $(CONFIG_LLD_VERSION) -lt 130000; echo $$?),0) KBUILD_LDFLAGS += -plugin-opt=-warn-stack-size=$(CONFIG_FRAME_WARN) endif endif +endif ifdef CONFIG_LTO KBUILD_CFLAGS += -fno-lto $(CC_FLAGS_LTO) diff --git a/arch/arc/include/uapi/asm/sigcontext.h b/arch/arc/include/uapi/asm/sigcontext.h index 95f8a4380e11..7a5449dfcb29 100644 --- a/arch/arc/include/uapi/asm/sigcontext.h +++ b/arch/arc/include/uapi/asm/sigcontext.h @@ -18,6 +18,7 @@ */ struct sigcontext { struct user_regs_struct regs; + struct user_regs_arcv2 v2abi; }; #endif /* _ASM_ARC_SIGCONTEXT_H */ diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index fdbe06c98895..4868bdebf586 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -61,6 +61,41 @@ struct rt_sigframe { unsigned int sigret_magic; }; +static int save_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs) +{ + int err = 0; +#ifndef CONFIG_ISA_ARCOMPACT + struct user_regs_arcv2 v2abi; + + v2abi.r30 = regs->r30; +#ifdef CONFIG_ARC_HAS_ACCL_REGS + v2abi.r58 = regs->r58; + v2abi.r59 = regs->r59; +#else + v2abi.r58 = v2abi.r59 = 0; +#endif + err = __copy_to_user(&mctx->v2abi, &v2abi, sizeof(v2abi)); +#endif + return err; +} + +static int restore_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs) +{ + int err = 0; +#ifndef CONFIG_ISA_ARCOMPACT + struct user_regs_arcv2 v2abi; + + err = __copy_from_user(&v2abi, &mctx->v2abi, sizeof(v2abi)); + + regs->r30 = v2abi.r30; +#ifdef CONFIG_ARC_HAS_ACCL_REGS + regs->r58 = v2abi.r58; + regs->r59 = v2abi.r59; +#endif +#endif + return err; +} + static int stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs, sigset_t *set) @@ -94,6 +129,10 @@ stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs, err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), &uregs.scratch, sizeof(sf->uc.uc_mcontext.regs.scratch)); + + if (is_isa_arcv2()) + err |= save_arcv2_regs(&(sf->uc.uc_mcontext), regs); + err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t)); return err ? -EFAULT : 0; @@ -109,6 +148,10 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf) err |= __copy_from_user(&uregs.scratch, &(sf->uc.uc_mcontext.regs.scratch), sizeof(sf->uc.uc_mcontext.regs.scratch)); + + if (is_isa_arcv2()) + err |= restore_arcv2_regs(&(sf->uc.uc_mcontext), regs); + if (err) return -EFAULT; diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 766f064f00fb..167fde7f2fce 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2242,7 +2242,7 @@ unsigned long perf_instruction_pointer(struct pt_regs *regs) bool use_siar = regs_use_siar(regs); unsigned long siar = mfspr(SPRN_SIAR); - if (ppmu->flags & PPMU_P10_DD1) { + if (ppmu && (ppmu->flags & PPMU_P10_DD1)) { if (siar) return siar; else diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index d9522fc35ca5..4f116be9152f 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -54,11 +54,11 @@ config RISCV select GENERIC_TIME_VSYSCALL if MMU && 64BIT select HANDLE_DOMAIN_IRQ select HAVE_ARCH_AUDITSYSCALL - select HAVE_ARCH_JUMP_LABEL - select HAVE_ARCH_JUMP_LABEL_RELATIVE + select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL + select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL select HAVE_ARCH_KASAN if MMU && 64BIT select HAVE_ARCH_KASAN_VMALLOC if MMU && 64BIT - select HAVE_ARCH_KGDB + select HAVE_ARCH_KGDB if !XIP_KERNEL select HAVE_ARCH_KGDB_QXFER_PKT select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_SECCOMP_FILTER @@ -73,9 +73,9 @@ config RISCV select HAVE_GCC_PLUGINS select HAVE_GENERIC_VDSO if MMU && 64BIT select HAVE_IRQ_TIME_ACCOUNTING - select HAVE_KPROBES - select HAVE_KPROBES_ON_FTRACE - select HAVE_KRETPROBES + select HAVE_KPROBES if !XIP_KERNEL + select HAVE_KPROBES_ON_FTRACE if !XIP_KERNEL + select HAVE_KRETPROBES if !XIP_KERNEL select HAVE_PCI select HAVE_PERF_EVENTS select HAVE_PERF_REGS @@ -227,11 +227,11 @@ config ARCH_RV64I bool "RV64I" select 64BIT select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && GCC_VERSION >= 50000 - select HAVE_DYNAMIC_FTRACE if MMU && $(cc-option,-fpatchable-function-entry=8) + select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && $(cc-option,-fpatchable-function-entry=8) select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE - select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_GRAPH_TRACER - select HAVE_FUNCTION_TRACER + select HAVE_FUNCTION_TRACER if !XIP_KERNEL select SWIOTLB if MMU endchoice diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 12de7a9c85b3..9cc71ca9a88f 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -651,9 +651,9 @@ ENDPROC(stack_overflow) .Lcleanup_sie_mcck: larl %r13,.Lsie_entry slgr %r9,%r13 - larl %r13,.Lsie_skip + lghi %r13,.Lsie_skip - .Lsie_entry clgr %r9,%r13 - jh .Lcleanup_sie_int + jhe .Lcleanup_sie_int oi __LC_CPU_FLAGS+7, _CIF_MCCK_GUEST .Lcleanup_sie_int: BPENTER __SF_SIE_FLAGS(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index ceeba9f63172..fdee23ea4e17 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -578,10 +578,17 @@ static inline void switch_fpu_finish(struct fpu *new_fpu) * PKRU state is switched eagerly because it needs to be valid before we * return to userland e.g. for a copy_to_user() operation. */ - if (current->mm) { + if (!(current->flags & PF_KTHREAD)) { + /* + * If the PKRU bit in xsave.header.xfeatures is not set, + * then the PKRU component was in init state, which means + * XRSTOR will set PKRU to 0. If the bit is not set then + * get_xsave_addr() will return NULL because the PKRU value + * in memory is not valid. This means pkru_val has to be + * set to 0 and not to init_pkru_value. + */ pk = get_xsave_addr(&new_fpu->state.xsave, XFEATURE_PKRU); - if (pk) - pkru_val = pk->pkru; + pkru_val = pk ? pk->pkru : 0; } __write_pkru(pkru_val); } diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index a4ec65317a7f..ec3ae3054792 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -307,13 +307,17 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) return 0; } - if (!access_ok(buf, size)) - return -EACCES; + if (!access_ok(buf, size)) { + ret = -EACCES; + goto out; + } - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_set(current, NULL, - 0, sizeof(struct user_i387_ia32_struct), - NULL, buf) != 0; + if (!static_cpu_has(X86_FEATURE_FPU)) { + ret = fpregs_soft_set(current, NULL, 0, + sizeof(struct user_i387_ia32_struct), + NULL, buf); + goto out; + } if (use_xsave()) { struct _fpx_sw_bytes fx_sw_user; @@ -369,6 +373,25 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) fpregs_unlock(); return 0; } + + /* + * The above did an FPU restore operation, restricted to + * the user portion of the registers, and failed, but the + * microcode might have modified the FPU registers + * nevertheless. + * + * If the FPU registers do not belong to current, then + * invalidate the FPU register state otherwise the task might + * preempt current and return to user space with corrupted + * FPU registers. + * + * In case current owns the FPU registers then no further + * action is required. The fixup below will handle it + * correctly. + */ + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + __cpu_invalidate_fpregs_state(); + fpregs_unlock(); } else { /* @@ -377,7 +400,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) */ ret = __copy_from_user(&env, buf, sizeof(env)); if (ret) - goto err_out; + goto out; envp = &env; } @@ -405,16 +428,9 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) if (use_xsave() && !fx_only) { u64 init_bv = xfeatures_mask_user() & ~user_xfeatures; - if (using_compacted_format()) { - ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx); - } else { - ret = __copy_from_user(&fpu->state.xsave, buf_fx, state_size); - - if (!ret && state_size > offsetof(struct xregs_state, header)) - ret = validate_user_xstate_header(&fpu->state.xsave.header); - } + ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx); if (ret) - goto err_out; + goto out; sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures, fx_only); @@ -434,7 +450,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size); if (ret) { ret = -EFAULT; - goto err_out; + goto out; } sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures, @@ -452,7 +468,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) } else { ret = __copy_from_user(&fpu->state.fsave, buf_fx, state_size); if (ret) - goto err_out; + goto out; fpregs_lock(); ret = copy_kernel_to_fregs_err(&fpu->state.fsave); @@ -463,7 +479,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) fpregs_deactivate(fpu); fpregs_unlock(); -err_out: +out: if (ret) fpu__clear_user_states(fpu); return ret; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index fa023f3feb25..43013ac0fd4d 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1410,6 +1410,9 @@ int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, if (!apic_x2apic_mode(apic)) valid_reg_mask |= APIC_REG_MASK(APIC_ARBPRI); + if (alignment + len > 4) + return 1; + if (offset > 0x3f0 || !(valid_reg_mask & APIC_REG_MASK(offset))) return 1; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index cd0faa187674..676ec0d1e6be 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4726,9 +4726,33 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu) context->inject_page_fault = kvm_inject_page_fault; } +static union kvm_mmu_role kvm_calc_nested_mmu_role(struct kvm_vcpu *vcpu) +{ + union kvm_mmu_role role = kvm_calc_shadow_root_page_role_common(vcpu, false); + + /* + * Nested MMUs are used only for walking L2's gva->gpa, they never have + * shadow pages of their own and so "direct" has no meaning. Set it + * to "true" to try to detect bogus usage of the nested MMU. + */ + role.base.direct = true; + + if (!is_paging(vcpu)) + role.base.level = 0; + else if (is_long_mode(vcpu)) + role.base.level = is_la57_mode(vcpu) ? PT64_ROOT_5LEVEL : + PT64_ROOT_4LEVEL; + else if (is_pae(vcpu)) + role.base.level = PT32E_ROOT_LEVEL; + else + role.base.level = PT32_ROOT_LEVEL; + + return role; +} + static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) { - union kvm_mmu_role new_role = kvm_calc_mmu_role_common(vcpu, false); + union kvm_mmu_role new_role = kvm_calc_nested_mmu_role(vcpu); struct kvm_mmu *g_context = &vcpu->arch.nested_mmu; if (new_role.as_u64 == g_context->mmu_role.as_u64) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cf3720578429..a6ca7e657af2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6991,7 +6991,10 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags) { - emul_to_vcpu(ctxt)->arch.hflags = emul_flags; + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + + vcpu->arch.hflags = emul_flags; + kvm_mmu_reset_context(vcpu); } static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, @@ -8147,6 +8150,7 @@ void kvm_arch_exit(void) kvm_x86_ops.hardware_enable = NULL; kvm_mmu_module_exit(); free_percpu(user_return_msrs); + kmem_cache_destroy(x86_emulator_cache); kmem_cache_destroy(x86_fpu_cache); #ifdef CONFIG_KVM_XEN static_key_deferred_flush(&kvm_xen_enabled); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 9e5ccc56f8e0..356b746dfbe7 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -118,7 +118,9 @@ static void __ioremap_check_other(resource_size_t addr, struct ioremap_desc *des if (!IS_ENABLED(CONFIG_EFI)) return; - if (efi_mem_type(addr) == EFI_RUNTIME_SERVICES_DATA) + if (efi_mem_type(addr) == EFI_RUNTIME_SERVICES_DATA || + (efi_mem_type(addr) == EFI_BOOT_SERVICES_DATA && + efi_mem_attributes(addr) & EFI_MEMORY_RUNTIME)) desc->flags |= IORES_MAP_ENCRYPTED; } diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 5eb4dc2b97da..e94da744386f 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -254,7 +254,13 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi) /* make sure all non-reserved blocks are inside the limits */ bi->start = max(bi->start, low); - bi->end = min(bi->end, high); + + /* preserve info for non-RAM areas above 'max_pfn': */ + if (bi->end > high) { + numa_add_memblk_to(bi->nid, high, bi->end, + &numa_reserved_meminfo); + bi->end = high; + } /* and there's no empty block */ if (bi->start >= bi->end) diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 0c2827fd8c19..03b1b0334947 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -59,6 +59,7 @@ config DMA_OF #devices config ALTERA_MSGDMA tristate "Altera / Intel mSGDMA Engine" + depends on HAS_IOMEM select DMA_ENGINE help Enable support for Altera / Intel mSGDMA controller. diff --git a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c index 4ec909e0b810..4ae057922ef1 100644 --- a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c +++ b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c @@ -332,6 +332,7 @@ static int __cold dpaa2_qdma_setup(struct fsl_mc_device *ls_dev) } if (priv->dpdmai_attr.version.major > DPDMAI_VER_MAJOR) { + err = -EINVAL; dev_err(dev, "DPDMAI major version mismatch\n" "Found %u.%u, supported version is %u.%u\n", priv->dpdmai_attr.version.major, @@ -341,6 +342,7 @@ static int __cold dpaa2_qdma_setup(struct fsl_mc_device *ls_dev) } if (priv->dpdmai_attr.version.minor > DPDMAI_VER_MINOR) { + err = -EINVAL; dev_err(dev, "DPDMAI minor version mismatch\n" "Found %u.%u, supported version is %u.%u\n", priv->dpdmai_attr.version.major, @@ -475,6 +477,7 @@ static int __cold dpaa2_qdma_dpio_setup(struct dpaa2_qdma_priv *priv) ppriv->store = dpaa2_io_store_create(DPAA2_QDMA_STORE_SIZE, dev); if (!ppriv->store) { + err = -ENOMEM; dev_err(dev, "dpaa2_io_store_create() failed\n"); goto err_store; } diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 59f2104ffc77..eb41bb9df0fd 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -218,6 +218,7 @@ static int idxd_setup_engines(struct idxd_device *idxd) engine->idxd = idxd; device_initialize(&engine->conf_dev); engine->conf_dev.parent = &idxd->conf_dev; + engine->conf_dev.bus = &dsa_bus_type; engine->conf_dev.type = &idxd_engine_device_type; rc = dev_set_name(&engine->conf_dev, "engine%d.%d", idxd->id, engine->id); if (rc < 0) { @@ -718,6 +719,7 @@ module_init(idxd_init_module); static void __exit idxd_exit_module(void) { + idxd_unregister_driver(); pci_unregister_driver(&idxd_pci_driver); idxd_cdev_remove(); idxd_unregister_bus_type(); diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index fd8d2bc3be9f..110de8a60058 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -2694,13 +2694,15 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic( for (i = 0; i < len / period_len; i++) { desc = pl330_get_desc(pch); if (!desc) { + unsigned long iflags; + dev_err(pch->dmac->ddma.dev, "%s:%d Unable to fetch desc\n", __func__, __LINE__); if (!first) return NULL; - spin_lock_irqsave(&pl330->pool_lock, flags); + spin_lock_irqsave(&pl330->pool_lock, iflags); while (!list_empty(&first->node)) { desc = list_entry(first->node.next, @@ -2710,7 +2712,7 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic( list_move_tail(&first->node, &pl330->desc_pool); - spin_unlock_irqrestore(&pl330->pool_lock, flags); + spin_unlock_irqrestore(&pl330->pool_lock, iflags); return NULL; } diff --git a/drivers/dma/qcom/Kconfig b/drivers/dma/qcom/Kconfig index 365f94eb3b08..3f926a653bd8 100644 --- a/drivers/dma/qcom/Kconfig +++ b/drivers/dma/qcom/Kconfig @@ -33,6 +33,7 @@ config QCOM_GPI_DMA config QCOM_HIDMA_MGMT tristate "Qualcomm Technologies HIDMA Management support" + depends on HAS_IOMEM select DMA_ENGINE help Enable support for the Qualcomm Technologies HIDMA Management. diff --git a/drivers/dma/sf-pdma/Kconfig b/drivers/dma/sf-pdma/Kconfig index f8ffa02e279f..ba46a0a15a93 100644 --- a/drivers/dma/sf-pdma/Kconfig +++ b/drivers/dma/sf-pdma/Kconfig @@ -1,5 +1,6 @@ config SF_PDMA tristate "Sifive PDMA controller driver" + depends on HAS_IOMEM select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c index 265d7c07b348..e1827393143f 100644 --- a/drivers/dma/ste_dma40.c +++ b/drivers/dma/ste_dma40.c @@ -3675,6 +3675,9 @@ static int __init d40_probe(struct platform_device *pdev) kfree(base->lcla_pool.base_unaligned); + if (base->lcpa_base) + iounmap(base->lcpa_base); + if (base->phy_lcpa) release_mem_region(base->phy_lcpa, base->lcpa_size); diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c index 70b29bd079c9..ff7dfb3fdeb4 100644 --- a/drivers/dma/xilinx/xilinx_dpdma.c +++ b/drivers/dma/xilinx/xilinx_dpdma.c @@ -1459,7 +1459,7 @@ static void xilinx_dpdma_enable_irq(struct xilinx_dpdma_device *xdev) */ static void xilinx_dpdma_disable_irq(struct xilinx_dpdma_device *xdev) { - dpdma_write(xdev->reg, XILINX_DPDMA_IDS, XILINX_DPDMA_INTR_ERR_ALL); + dpdma_write(xdev->reg, XILINX_DPDMA_IDS, XILINX_DPDMA_INTR_ALL); dpdma_write(xdev->reg, XILINX_DPDMA_EIDS, XILINX_DPDMA_EINTR_ALL); } @@ -1596,6 +1596,26 @@ static struct dma_chan *of_dma_xilinx_xlate(struct of_phandle_args *dma_spec, return dma_get_slave_channel(&xdev->chan[chan_id]->vchan.chan); } +static void dpdma_hw_init(struct xilinx_dpdma_device *xdev) +{ + unsigned int i; + void __iomem *reg; + + /* Disable all interrupts */ + xilinx_dpdma_disable_irq(xdev); + + /* Stop all channels */ + for (i = 0; i < ARRAY_SIZE(xdev->chan); i++) { + reg = xdev->reg + XILINX_DPDMA_CH_BASE + + XILINX_DPDMA_CH_OFFSET * i; + dpdma_clr(reg, XILINX_DPDMA_CH_CNTL, XILINX_DPDMA_CH_CNTL_ENABLE); + } + + /* Clear the interrupt status registers */ + dpdma_write(xdev->reg, XILINX_DPDMA_ISR, XILINX_DPDMA_INTR_ALL); + dpdma_write(xdev->reg, XILINX_DPDMA_EISR, XILINX_DPDMA_EINTR_ALL); +} + static int xilinx_dpdma_probe(struct platform_device *pdev) { struct xilinx_dpdma_device *xdev; @@ -1622,6 +1642,8 @@ static int xilinx_dpdma_probe(struct platform_device *pdev) if (IS_ERR(xdev->reg)) return PTR_ERR(xdev->reg); + dpdma_hw_init(xdev); + xdev->irq = platform_get_irq(pdev, 0); if (xdev->irq < 0) { dev_err(xdev->dev, "failed to get platform irq\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 2342c5d216f9..72d23651501d 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -6769,8 +6769,12 @@ static int gfx_v10_0_kiq_init_register(struct amdgpu_ring *ring) if (ring->use_doorbell) { WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_LOWER, (adev->doorbell_index.kiq * 2) << 2); + /* If GC has entered CGPG, ringing doorbell > first page doesn't + * wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to workaround + * this issue. + */ WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER, - (adev->doorbell_index.userqueue_end * 2) << 2); + (adev->doorbell.size - 4)); } WREG32_SOC15(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index d2c020a91c0b..1fdfb7783404 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3623,8 +3623,12 @@ static int gfx_v9_0_kiq_init_register(struct amdgpu_ring *ring) if (ring->use_doorbell) { WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_LOWER, (adev->doorbell_index.kiq * 2) << 2); + /* If GC has entered CGPG, ringing doorbell > first page doesn't + * wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to workaround + * this issue. + */ WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER, - (adev->doorbell_index.userqueue_end * 2) << 2); + (adev->doorbell.size - 4)); } WREG32_SOC15_RLC(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL, diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index dfa9fdbe98da..06bb24d7a9fe 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -286,7 +286,7 @@ int radeon_uvd_resume(struct radeon_device *rdev) if (rdev->uvd.vcpu_bo == NULL) return -EINVAL; - memcpy(rdev->uvd.cpu_addr, rdev->uvd_fw->data, rdev->uvd_fw->size); + memcpy_toio((void __iomem *)rdev->uvd.cpu_addr, rdev->uvd_fw->data, rdev->uvd_fw->size); size = radeon_bo_size(rdev->uvd.vcpu_bo); size -= rdev->uvd_fw->size; @@ -294,7 +294,7 @@ int radeon_uvd_resume(struct radeon_device *rdev) ptr = rdev->uvd.cpu_addr; ptr += rdev->uvd_fw->size; - memset(ptr, 0, size); + memset_io((void __iomem *)ptr, 0, size); return 0; } diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c index bbdfd5e26ec8..f75fb157f2ff 100644 --- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c +++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c @@ -209,7 +209,7 @@ static int sun8i_dw_hdmi_bind(struct device *dev, struct device *master, goto err_disable_clk_tmds; } - ret = sun8i_hdmi_phy_probe(hdmi, phy_node); + ret = sun8i_hdmi_phy_get(hdmi, phy_node); of_node_put(phy_node); if (ret) { dev_err(dev, "Couldn't get the HDMI PHY\n"); @@ -242,7 +242,6 @@ static int sun8i_dw_hdmi_bind(struct device *dev, struct device *master, cleanup_encoder: drm_encoder_cleanup(encoder); - sun8i_hdmi_phy_remove(hdmi); err_disable_clk_tmds: clk_disable_unprepare(hdmi->clk_tmds); err_assert_ctrl_reset: @@ -263,7 +262,6 @@ static void sun8i_dw_hdmi_unbind(struct device *dev, struct device *master, struct sun8i_dw_hdmi *hdmi = dev_get_drvdata(dev); dw_hdmi_unbind(hdmi->hdmi); - sun8i_hdmi_phy_remove(hdmi); clk_disable_unprepare(hdmi->clk_tmds); reset_control_assert(hdmi->rst_ctrl); gpiod_set_value(hdmi->ddc_en, 0); @@ -320,7 +318,32 @@ static struct platform_driver sun8i_dw_hdmi_pltfm_driver = { .of_match_table = sun8i_dw_hdmi_dt_ids, }, }; -module_platform_driver(sun8i_dw_hdmi_pltfm_driver); + +static int __init sun8i_dw_hdmi_init(void) +{ + int ret; + + ret = platform_driver_register(&sun8i_dw_hdmi_pltfm_driver); + if (ret) + return ret; + + ret = platform_driver_register(&sun8i_hdmi_phy_driver); + if (ret) { + platform_driver_unregister(&sun8i_dw_hdmi_pltfm_driver); + return ret; + } + + return ret; +} + +static void __exit sun8i_dw_hdmi_exit(void) +{ + platform_driver_unregister(&sun8i_dw_hdmi_pltfm_driver); + platform_driver_unregister(&sun8i_hdmi_phy_driver); +} + +module_init(sun8i_dw_hdmi_init); +module_exit(sun8i_dw_hdmi_exit); MODULE_AUTHOR("Jernej Skrabec <jernej.skrabec@xxxxxxxx>"); MODULE_DESCRIPTION("Allwinner DW HDMI bridge"); diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h index d4b55af0592f..74f6ed0e2570 100644 --- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h +++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h @@ -195,14 +195,15 @@ struct sun8i_dw_hdmi { struct gpio_desc *ddc_en; }; +extern struct platform_driver sun8i_hdmi_phy_driver; + static inline struct sun8i_dw_hdmi * encoder_to_sun8i_dw_hdmi(struct drm_encoder *encoder) { return container_of(encoder, struct sun8i_dw_hdmi, encoder); } -int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node); -void sun8i_hdmi_phy_remove(struct sun8i_dw_hdmi *hdmi); +int sun8i_hdmi_phy_get(struct sun8i_dw_hdmi *hdmi, struct device_node *node); void sun8i_hdmi_phy_init(struct sun8i_hdmi_phy *phy); void sun8i_hdmi_phy_set_ops(struct sun8i_hdmi_phy *phy, diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c index 9994edf67509..c9239708d398 100644 --- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c +++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c @@ -5,6 +5,7 @@ #include <linux/delay.h> #include <linux/of_address.h> +#include <linux/of_platform.h> #include "sun8i_dw_hdmi.h" @@ -597,10 +598,30 @@ static const struct of_device_id sun8i_hdmi_phy_of_table[] = { { /* sentinel */ } }; -int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node) +int sun8i_hdmi_phy_get(struct sun8i_dw_hdmi *hdmi, struct device_node *node) +{ + struct platform_device *pdev = of_find_device_by_node(node); + struct sun8i_hdmi_phy *phy; + + if (!pdev) + return -EPROBE_DEFER; + + phy = platform_get_drvdata(pdev); + if (!phy) + return -EPROBE_DEFER; + + hdmi->phy = phy; + + put_device(&pdev->dev); + + return 0; +} + +static int sun8i_hdmi_phy_probe(struct platform_device *pdev) { const struct of_device_id *match; - struct device *dev = hdmi->dev; + struct device *dev = &pdev->dev; + struct device_node *node = dev->of_node; struct sun8i_hdmi_phy *phy; struct resource res; void __iomem *regs; @@ -704,7 +725,7 @@ int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node) clk_prepare_enable(phy->clk_phy); } - hdmi->phy = phy; + platform_set_drvdata(pdev, phy); return 0; @@ -728,9 +749,9 @@ int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node) return ret; } -void sun8i_hdmi_phy_remove(struct sun8i_dw_hdmi *hdmi) +static int sun8i_hdmi_phy_remove(struct platform_device *pdev) { - struct sun8i_hdmi_phy *phy = hdmi->phy; + struct sun8i_hdmi_phy *phy = platform_get_drvdata(pdev); clk_disable_unprepare(phy->clk_mod); clk_disable_unprepare(phy->clk_bus); @@ -744,4 +765,14 @@ void sun8i_hdmi_phy_remove(struct sun8i_dw_hdmi *hdmi) clk_put(phy->clk_pll1); clk_put(phy->clk_mod); clk_put(phy->clk_bus); + return 0; } + +struct platform_driver sun8i_hdmi_phy_driver = { + .probe = sun8i_hdmi_phy_probe, + .remove = sun8i_hdmi_phy_remove, + .driver = { + .name = "sun8i-hdmi-phy", + .of_match_table = sun8i_hdmi_phy_of_table, + }, +}; diff --git a/drivers/hwmon/scpi-hwmon.c b/drivers/hwmon/scpi-hwmon.c index 25aac40f2764..919877970ae3 100644 --- a/drivers/hwmon/scpi-hwmon.c +++ b/drivers/hwmon/scpi-hwmon.c @@ -99,6 +99,15 @@ scpi_show_sensor(struct device *dev, struct device_attribute *attr, char *buf) scpi_scale_reading(&value, sensor); + /* + * Temperature sensor values are treated as signed values based on + * observation even though that is not explicitly specified, and + * because an unsigned u64 temperature does not really make practical + * sense especially when the temperature is below zero degrees Celsius. + */ + if (sensor->info.class == TEMPERATURE) + return sprintf(buf, "%lld\n", (s64)value); + return sprintf(buf, "%llu\n", value); } diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 00404024d7cd..fea237838bb0 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -642,11 +642,45 @@ static inline void gic_handle_nmi(u32 irqnr, struct pt_regs *regs) nmi_exit(); } +static u32 do_read_iar(struct pt_regs *regs) +{ + u32 iar; + + if (gic_supports_nmi() && unlikely(!interrupts_enabled(regs))) { + u64 pmr; + + /* + * We were in a context with IRQs disabled. However, the + * entry code has set PMR to a value that allows any + * interrupt to be acknowledged, and not just NMIs. This can + * lead to surprising effects if the NMI has been retired in + * the meantime, and that there is an IRQ pending. The IRQ + * would then be taken in NMI context, something that nobody + * wants to debug twice. + * + * Until we sort this, drop PMR again to a level that will + * actually only allow NMIs before reading IAR, and then + * restore it to what it was. + */ + pmr = gic_read_pmr(); + gic_pmr_mask_irqs(); + isb(); + + iar = gic_read_iar(); + + gic_write_pmr(pmr); + } else { + iar = gic_read_iar(); + } + + return iar; +} + static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs) { u32 irqnr; - irqnr = gic_read_iar(); + irqnr = do_read_iar(regs); /* Check for special IDs first */ if ((irqnr >= 1020 && irqnr <= 1023)) diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index 1f649d178010..4484f9c079b7 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -82,6 +82,8 @@ struct mcba_priv { bool can_ka_first_pass; bool can_speed_check; atomic_t free_ctx_cnt; + void *rxbuf[MCBA_MAX_RX_URBS]; + dma_addr_t rxbuf_dma[MCBA_MAX_RX_URBS]; }; /* CAN frame */ @@ -633,6 +635,7 @@ static int mcba_usb_start(struct mcba_priv *priv) for (i = 0; i < MCBA_MAX_RX_URBS; i++) { struct urb *urb = NULL; u8 *buf; + dma_addr_t buf_dma; /* create a URB, and a buffer for it */ urb = usb_alloc_urb(0, GFP_KERNEL); @@ -642,7 +645,7 @@ static int mcba_usb_start(struct mcba_priv *priv) } buf = usb_alloc_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE, - GFP_KERNEL, &urb->transfer_dma); + GFP_KERNEL, &buf_dma); if (!buf) { netdev_err(netdev, "No memory left for USB buffer\n"); usb_free_urb(urb); @@ -661,11 +664,14 @@ static int mcba_usb_start(struct mcba_priv *priv) if (err) { usb_unanchor_urb(urb); usb_free_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE, - buf, urb->transfer_dma); + buf, buf_dma); usb_free_urb(urb); break; } + priv->rxbuf[i] = buf; + priv->rxbuf_dma[i] = buf_dma; + /* Drop reference, USB core will take care of freeing it */ usb_free_urb(urb); } @@ -708,7 +714,14 @@ static int mcba_usb_open(struct net_device *netdev) static void mcba_urb_unlink(struct mcba_priv *priv) { + int i; + usb_kill_anchored_urbs(&priv->rx_submitted); + + for (i = 0; i < MCBA_MAX_RX_URBS; ++i) + usb_free_coherent(priv->udev, MCBA_USB_RX_BUFF_SIZE, + priv->rxbuf[i], priv->rxbuf_dma[i]); + usb_kill_anchored_urbs(&priv->tx_submitted); } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 102f2c91fdb8..20f8012bbe04 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -236,36 +236,48 @@ static int ena_xdp_io_poll(struct napi_struct *napi, int budget) static int ena_xdp_tx_map_frame(struct ena_ring *xdp_ring, struct ena_tx_buffer *tx_info, struct xdp_frame *xdpf, - void **push_hdr, - u32 *push_len) + struct ena_com_tx_ctx *ena_tx_ctx) { struct ena_adapter *adapter = xdp_ring->adapter; struct ena_com_buf *ena_buf; - dma_addr_t dma = 0; + int push_len = 0; + dma_addr_t dma; + void *data; u32 size; tx_info->xdpf = xdpf; + data = tx_info->xdpf->data; size = tx_info->xdpf->len; - ena_buf = tx_info->bufs; - /* llq push buffer */ - *push_len = min_t(u32, size, xdp_ring->tx_max_header_size); - *push_hdr = tx_info->xdpf->data; + if (xdp_ring->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV) { + /* Designate part of the packet for LLQ */ + push_len = min_t(u32, size, xdp_ring->tx_max_header_size); + + ena_tx_ctx->push_header = data; + + size -= push_len; + data += push_len; + } + + ena_tx_ctx->header_len = push_len; - if (size - *push_len > 0) { + if (size > 0) { dma = dma_map_single(xdp_ring->dev, - *push_hdr + *push_len, - size - *push_len, + data, + size, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(xdp_ring->dev, dma))) goto error_report_dma_error; - tx_info->map_linear_data = 1; - tx_info->num_of_bufs = 1; - } + tx_info->map_linear_data = 0; - ena_buf->paddr = dma; - ena_buf->len = size; + ena_buf = tx_info->bufs; + ena_buf->paddr = dma; + ena_buf->len = size; + + ena_tx_ctx->ena_bufs = ena_buf; + ena_tx_ctx->num_bufs = tx_info->num_of_bufs = 1; + } return 0; @@ -274,10 +286,6 @@ static int ena_xdp_tx_map_frame(struct ena_ring *xdp_ring, &xdp_ring->syncp); netif_warn(adapter, tx_queued, adapter->netdev, "Failed to map xdp buff\n"); - xdp_return_frame_rx_napi(tx_info->xdpf); - tx_info->xdpf = NULL; - tx_info->num_of_bufs = 0; - return -EINVAL; } @@ -289,8 +297,6 @@ static int ena_xdp_xmit_frame(struct ena_ring *xdp_ring, struct ena_com_tx_ctx ena_tx_ctx = {}; struct ena_tx_buffer *tx_info; u16 next_to_use, req_id; - void *push_hdr; - u32 push_len; int rc; next_to_use = xdp_ring->next_to_use; @@ -298,15 +304,11 @@ static int ena_xdp_xmit_frame(struct ena_ring *xdp_ring, tx_info = &xdp_ring->tx_buffer_info[req_id]; tx_info->num_of_bufs = 0; - rc = ena_xdp_tx_map_frame(xdp_ring, tx_info, xdpf, &push_hdr, &push_len); + rc = ena_xdp_tx_map_frame(xdp_ring, tx_info, xdpf, &ena_tx_ctx); if (unlikely(rc)) goto error_drop_packet; - ena_tx_ctx.ena_bufs = tx_info->bufs; - ena_tx_ctx.push_header = push_hdr; - ena_tx_ctx.num_bufs = tx_info->num_of_bufs; ena_tx_ctx.req_id = req_id; - ena_tx_ctx.header_len = push_len; rc = ena_xmit_common(dev, xdp_ring, diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 9e02f8864593..5e90df42b201 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1849,6 +1849,7 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) free_netdev(netdev); out_pci_release: pci_release_mem_regions(pdev); + pci_disable_pcie_error_reporting(pdev); out_pci_disable: pci_disable_device(pdev); return err; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 027997c711ab..c118de27bc5c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -7295,7 +7295,7 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp) entries_sp = ctx->vnic_max_vnic_entries + ctx->qp_max_l2_entries + 2 * (extra_qps + ctx->qp_min_qp1_entries) + min; entries_sp = roundup(entries_sp, ctx->tqm_entries_multiple); - entries = ctx->qp_max_l2_entries + extra_qps + ctx->qp_min_qp1_entries; + entries = ctx->qp_max_l2_entries + 2 * (extra_qps + ctx->qp_min_qp1_entries); entries = roundup(entries, ctx->tqm_entries_multiple); entries = clamp_t(u32, entries, min, ctx->tqm_max_entries_per_ring); for (i = 0; i < ctx->tqm_fp_rings_count + 1; i++) { @@ -11573,6 +11573,8 @@ static void bnxt_fw_init_one_p3(struct bnxt *bp) bnxt_hwrm_coal_params_qcaps(bp); } +static int bnxt_probe_phy(struct bnxt *bp, bool fw_dflt); + static int bnxt_fw_init_one(struct bnxt *bp) { int rc; @@ -11587,6 +11589,9 @@ static int bnxt_fw_init_one(struct bnxt *bp) netdev_err(bp->dev, "Firmware init phase 2 failed\n"); return rc; } + rc = bnxt_probe_phy(bp, false); + if (rc) + return rc; rc = bnxt_approve_mac(bp, bp->dev->dev_addr, false); if (rc) return rc; @@ -12976,6 +12981,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) bnxt_hwrm_func_drv_unrgtr(bp); bnxt_free_hwrm_short_cmd_req(bp); bnxt_free_hwrm_resources(bp); + bnxt_ethtool_free(bp); kfree(bp->fw_health); bp->fw_health = NULL; bnxt_cleanup_pci(bp); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 61ea3ec5c3fc..83ed10ac8660 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -1337,13 +1337,27 @@ static int cxgb4_ethtool_flash_phy(struct net_device *netdev, return ret; } - spin_lock_bh(&adap->win0_lock); + /* We have to RESET the chip/firmware because we need the + * chip in uninitialized state for loading new PHY image. + * Otherwise, the running firmware will only store the PHY + * image in local RAM which will be lost after next reset. + */ + ret = t4_fw_reset(adap, adap->mbox, PIORSTMODE_F | PIORST_F); + if (ret < 0) { + dev_err(adap->pdev_dev, + "Set FW to RESET for flashing PHY FW failed. ret: %d\n", + ret); + return ret; + } + ret = t4_load_phy_fw(adap, MEMWIN_NIC, NULL, data, size); - spin_unlock_bh(&adap->win0_lock); - if (ret) - dev_err(adap->pdev_dev, "Failed to load PHY FW\n"); + if (ret < 0) { + dev_err(adap->pdev_dev, "Failed to load PHY FW. ret: %d\n", + ret); + return ret; + } - return ret; + return 0; } static int cxgb4_ethtool_flash_fw(struct net_device *netdev, @@ -1610,16 +1624,14 @@ static struct filter_entry *cxgb4_get_filter_entry(struct adapter *adap, u32 ftid) { struct tid_info *t = &adap->tids; - struct filter_entry *f; - if (ftid < t->nhpftids) - f = &adap->tids.hpftid_tab[ftid]; - else if (ftid < t->nftids) - f = &adap->tids.ftid_tab[ftid - t->nhpftids]; - else - f = lookup_tid(&adap->tids, ftid); + if (ftid >= t->hpftid_base && ftid < t->hpftid_base + t->nhpftids) + return &t->hpftid_tab[ftid - t->hpftid_base]; - return f; + if (ftid >= t->ftid_base && ftid < t->ftid_base + t->nftids) + return &t->ftid_tab[ftid - t->ftid_base]; + + return lookup_tid(t, ftid); } static void cxgb4_fill_filter_rule(struct ethtool_rx_flow_spec *fs, @@ -1826,6 +1838,11 @@ static int cxgb4_ntuple_del_filter(struct net_device *dev, filter_id = filter_info->loc_array[cmd->fs.location]; f = cxgb4_get_filter_entry(adapter, filter_id); + if (f->fs.prio) + filter_id -= adapter->tids.hpftid_base; + else if (!f->fs.hash) + filter_id -= (adapter->tids.ftid_base - adapter->tids.nhpftids); + ret = cxgb4_flow_rule_destroy(dev, f->fs.tc_prio, &f->fs, filter_id); if (ret) goto err; @@ -1885,6 +1902,11 @@ static int cxgb4_ntuple_set_filter(struct net_device *netdev, filter_info = &adapter->ethtool_filters->port[pi->port_id]; + if (fs.prio) + tid += adapter->tids.hpftid_base; + else if (!fs.hash) + tid += (adapter->tids.ftid_base - adapter->tids.nhpftids); + filter_info->loc_array[cmd->fs.location] = tid; set_bit(cmd->fs.location, filter_info->bmap); filter_info->in_use++; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index e664e05b9f02..5fbc087268db 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -198,7 +198,7 @@ static void set_nat_params(struct adapter *adap, struct filter_entry *f, WORD_MASK, f->fs.nat_lip[3] | f->fs.nat_lip[2] << 8 | f->fs.nat_lip[1] << 16 | - (u64)f->fs.nat_lip[0] << 25, 1); + (u64)f->fs.nat_lip[0] << 24, 1); } } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 1f601de02e70..762113a04dde 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -4424,10 +4424,8 @@ static int adap_init0_phy(struct adapter *adap) /* Load PHY Firmware onto adapter. */ - spin_lock_bh(&adap->win0_lock); ret = t4_load_phy_fw(adap, MEMWIN_NIC, phy_info->phy_fw_version, (u8 *)phyf->data, phyf->size); - spin_unlock_bh(&adap->win0_lock); if (ret < 0) dev_err(adap->pdev_dev, "PHY Firmware transfer error %d\n", -ret); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 80882cfc370f..601853bb34c9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -3060,16 +3060,19 @@ int t4_read_flash(struct adapter *adapter, unsigned int addr, * @addr: the start address to write * @n: length of data to write in bytes * @data: the data to write + * @byte_oriented: whether to store data as bytes or as words * * Writes up to a page of data (256 bytes) to the serial flash starting * at the given address. All the data must be written to the same page. + * If @byte_oriented is set the write data is stored as byte stream + * (i.e. matches what on disk), otherwise in big-endian. */ static int t4_write_flash(struct adapter *adapter, unsigned int addr, - unsigned int n, const u8 *data) + unsigned int n, const u8 *data, bool byte_oriented) { - int ret; - u32 buf[64]; unsigned int i, c, left, val, offset = addr & 0xff; + u32 buf[64]; + int ret; if (addr >= adapter->params.sf_size || offset + n > SF_PAGE_SIZE) return -EINVAL; @@ -3080,10 +3083,14 @@ static int t4_write_flash(struct adapter *adapter, unsigned int addr, (ret = sf1_write(adapter, 4, 1, 1, val)) != 0) goto unlock; - for (left = n; left; left -= c) { + for (left = n; left; left -= c, data += c) { c = min(left, 4U); - for (val = 0, i = 0; i < c; ++i) - val = (val << 8) + *data++; + for (val = 0, i = 0; i < c; ++i) { + if (byte_oriented) + val = (val << 8) + data[i]; + else + val = (val << 8) + data[c - i - 1]; + } ret = sf1_write(adapter, c, c != left, 1, val); if (ret) @@ -3096,7 +3103,8 @@ static int t4_write_flash(struct adapter *adapter, unsigned int addr, t4_write_reg(adapter, SF_OP_A, 0); /* unlock SF */ /* Read the page to verify the write succeeded */ - ret = t4_read_flash(adapter, addr & ~0xff, ARRAY_SIZE(buf), buf, 1); + ret = t4_read_flash(adapter, addr & ~0xff, ARRAY_SIZE(buf), buf, + byte_oriented); if (ret) return ret; @@ -3692,7 +3700,7 @@ int t4_load_fw(struct adapter *adap, const u8 *fw_data, unsigned int size) */ memcpy(first_page, fw_data, SF_PAGE_SIZE); ((struct fw_hdr *)first_page)->fw_ver = cpu_to_be32(0xffffffff); - ret = t4_write_flash(adap, fw_start, SF_PAGE_SIZE, first_page); + ret = t4_write_flash(adap, fw_start, SF_PAGE_SIZE, first_page, true); if (ret) goto out; @@ -3700,14 +3708,14 @@ int t4_load_fw(struct adapter *adap, const u8 *fw_data, unsigned int size) for (size -= SF_PAGE_SIZE; size; size -= SF_PAGE_SIZE) { addr += SF_PAGE_SIZE; fw_data += SF_PAGE_SIZE; - ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, fw_data); + ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, fw_data, true); if (ret) goto out; } - ret = t4_write_flash(adap, - fw_start + offsetof(struct fw_hdr, fw_ver), - sizeof(hdr->fw_ver), (const u8 *)&hdr->fw_ver); + ret = t4_write_flash(adap, fw_start + offsetof(struct fw_hdr, fw_ver), + sizeof(hdr->fw_ver), (const u8 *)&hdr->fw_ver, + true); out: if (ret) dev_err(adap->pdev_dev, "firmware download failed, error %d\n", @@ -3812,9 +3820,11 @@ int t4_load_phy_fw(struct adapter *adap, int win, /* Copy the supplied PHY Firmware image to the adapter memory location * allocated by the adapter firmware. */ + spin_lock_bh(&adap->win0_lock); ret = t4_memory_rw(adap, win, mtype, maddr, phy_fw_size, (__be32 *)phy_fw_data, T4_MEMORY_WRITE); + spin_unlock_bh(&adap->win0_lock); if (ret) return ret; @@ -10208,7 +10218,7 @@ int t4_load_cfg(struct adapter *adap, const u8 *cfg_data, unsigned int size) n = size - i; else n = SF_PAGE_SIZE; - ret = t4_write_flash(adap, addr, n, cfg_data); + ret = t4_write_flash(adap, addr, n, cfg_data, true); if (ret) goto out; @@ -10677,13 +10687,14 @@ int t4_load_boot(struct adapter *adap, u8 *boot_data, for (size -= SF_PAGE_SIZE; size; size -= SF_PAGE_SIZE) { addr += SF_PAGE_SIZE; boot_data += SF_PAGE_SIZE; - ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, boot_data); + ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, boot_data, + false); if (ret) goto out; } ret = t4_write_flash(adap, boot_sector, SF_PAGE_SIZE, - (const u8 *)header); + (const u8 *)header, false); out: if (ret) @@ -10758,7 +10769,7 @@ int t4_load_bootcfg(struct adapter *adap, const u8 *cfg_data, unsigned int size) for (i = 0; i < size; i += SF_PAGE_SIZE) { n = min_t(u32, size - i, SF_PAGE_SIZE); - ret = t4_write_flash(adap, addr, n, cfg_data); + ret = t4_write_flash(adap, addr, n, cfg_data, false); if (ret) goto out; @@ -10770,7 +10781,8 @@ int t4_load_bootcfg(struct adapter *adap, const u8 *cfg_data, unsigned int size) for (i = 0; i < npad; i++) { u8 data = 0; - ret = t4_write_flash(adap, cfg_addr + size + i, 1, &data); + ret = t4_write_flash(adap, cfg_addr + size + i, 1, &data, + false); if (ret) goto out; } diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c index 46b0dbab8aad..7c992172933b 100644 --- a/drivers/net/ethernet/ec_bhf.c +++ b/drivers/net/ethernet/ec_bhf.c @@ -576,10 +576,12 @@ static void ec_bhf_remove(struct pci_dev *dev) struct ec_bhf_priv *priv = netdev_priv(net_dev); unregister_netdev(net_dev); - free_netdev(net_dev); pci_iounmap(dev, priv->dma_io); pci_iounmap(dev, priv->io); + + free_netdev(net_dev); + pci_release_regions(dev); pci_clear_master(dev); pci_disable_device(dev); diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index b6eba29d8e99..7968568bbe21 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -5897,6 +5897,7 @@ static int be_probe(struct pci_dev *pdev, const struct pci_device_id *pdev_id) unmap_bars: be_unmap_pci_bars(adapter); free_netdev: + pci_disable_pcie_error_reporting(pdev); free_netdev(netdev); rel_reg: pci_release_regions(pdev); diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 1753807cbf97..d71eac7e1924 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -215,15 +215,13 @@ static u64 fec_ptp_read(const struct cyclecounter *cc) { struct fec_enet_private *fep = container_of(cc, struct fec_enet_private, cc); - const struct platform_device_id *id_entry = - platform_get_device_id(fep->pdev); u32 tempval; tempval = readl(fep->hwp + FEC_ATIME_CTRL); tempval |= FEC_T_CTRL_CAPTURE; writel(tempval, fep->hwp + FEC_ATIME_CTRL); - if (id_entry->driver_data & FEC_QUIRK_BUG_CAPTURE) + if (fep->quirks & FEC_QUIRK_BUG_CAPTURE) udelay(1); return readl(fep->hwp + FEC_ATIME); @@ -604,6 +602,10 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx) fep->ptp_caps.enable = fec_ptp_enable; fep->cycle_speed = clk_get_rate(fep->clk_ptp); + if (!fep->cycle_speed) { + fep->cycle_speed = NSEC_PER_SEC; + dev_err(&fep->pdev->dev, "clk_ptp clock rate is zero\n"); + } fep->ptp_inc = NSEC_PER_SEC / fep->cycle_speed; spin_lock_init(&fep->tmreg_lock); diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 27e439853c3b..55432ea360ad 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1715,12 +1715,13 @@ int ice_vsi_cfg_rxqs(struct ice_vsi *vsi) * ice_vsi_cfg_txqs - Configure the VSI for Tx * @vsi: the VSI being configured * @rings: Tx ring array to be configured + * @count: number of Tx ring array elements * * Return 0 on success and a negative value on error * Configure the Tx VSI for operation. */ static int -ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings) +ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings, u16 count) { struct ice_aqc_add_tx_qgrp *qg_buf; u16 q_idx = 0; @@ -1732,7 +1733,7 @@ ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings) qg_buf->num_txqs = 1; - for (q_idx = 0; q_idx < vsi->num_txq; q_idx++) { + for (q_idx = 0; q_idx < count; q_idx++) { err = ice_vsi_cfg_txq(vsi, rings[q_idx], qg_buf); if (err) goto err_cfg_txqs; @@ -1752,7 +1753,7 @@ ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings) */ int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi) { - return ice_vsi_cfg_txqs(vsi, vsi->tx_rings); + return ice_vsi_cfg_txqs(vsi, vsi->tx_rings, vsi->num_txq); } /** @@ -1767,7 +1768,7 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) int ret; int i; - ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings); + ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings, vsi->num_xdp_txq); if (ret) return ret; @@ -1965,17 +1966,18 @@ int ice_vsi_stop_all_rx_rings(struct ice_vsi *vsi) * @rst_src: reset source * @rel_vmvf_num: Relative ID of VF/VM * @rings: Tx ring array to be stopped + * @count: number of Tx ring array elements */ static int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, - u16 rel_vmvf_num, struct ice_ring **rings) + u16 rel_vmvf_num, struct ice_ring **rings, u16 count) { u16 q_idx; if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS) return -EINVAL; - for (q_idx = 0; q_idx < vsi->num_txq; q_idx++) { + for (q_idx = 0; q_idx < count; q_idx++) { struct ice_txq_meta txq_meta = { }; int status; @@ -2003,7 +2005,7 @@ int ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, u16 rel_vmvf_num) { - return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings); + return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings, vsi->num_txq); } /** @@ -2012,7 +2014,7 @@ ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, */ int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi) { - return ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0, vsi->xdp_rings); + return ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0, vsi->xdp_rings, vsi->num_xdp_txq); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index d821c687f239..b61cd84be97f 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2554,6 +2554,20 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, return (ret || xdp_ring_err) ? -ENOMEM : 0; } +/** + * ice_xdp_safe_mode - XDP handler for safe mode + * @dev: netdevice + * @xdp: XDP command + */ +static int ice_xdp_safe_mode(struct net_device __always_unused *dev, + struct netdev_bpf *xdp) +{ + NL_SET_ERR_MSG_MOD(xdp->extack, + "Please provide working DDP firmware package in order to use XDP\n" + "Refer to Documentation/networking/device_drivers/ethernet/intel/ice.rst"); + return -EOPNOTSUPP; +} + /** * ice_xdp - implements XDP handler * @dev: netdevice @@ -6805,6 +6819,7 @@ static const struct net_device_ops ice_netdev_safe_mode_ops = { .ndo_change_mtu = ice_change_mtu, .ndo_get_stats64 = ice_get_stats64, .ndo_tx_timeout = ice_tx_timeout, + .ndo_bpf = ice_xdp_safe_mode, }; static const struct net_device_ops ice_netdev_ops = { diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index 135ba5b6ae98..072075bc60ee 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -154,6 +154,7 @@ static int xrx200_close(struct net_device *net_dev) static int xrx200_alloc_skb(struct xrx200_chan *ch) { + struct sk_buff *skb = ch->skb[ch->dma.desc]; dma_addr_t mapping; int ret = 0; @@ -168,6 +169,7 @@ static int xrx200_alloc_skb(struct xrx200_chan *ch) XRX200_DMA_DATA_LEN, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(ch->priv->dev, mapping))) { dev_kfree_skb_any(ch->skb[ch->dma.desc]); + ch->skb[ch->dma.desc] = skb; ret = -ENOMEM; goto skip; } @@ -198,7 +200,6 @@ static int xrx200_hw_receive(struct xrx200_chan *ch) ch->dma.desc %= LTQ_DESC_NUM; if (ret) { - ch->skb[ch->dma.desc] = skb; net_dev->stats.rx_dropped++; netdev_err(net_dev, "failed to allocate new rx buffer\n"); return ret; @@ -352,8 +353,8 @@ static irqreturn_t xrx200_dma_irq(int irq, void *ptr) struct xrx200_chan *ch = ptr; if (napi_schedule_prep(&ch->napi)) { - __napi_schedule(&ch->napi); ltq_dma_disable_irq(&ch->dma); + __napi_schedule(&ch->napi); } ltq_dma_ack_irq(&ch->dma); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index 9153c9bda96f..897853a68cd0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -306,6 +306,7 @@ int mlx5_attach_device(struct mlx5_core_dev *dev) int ret = 0, i; mutex_lock(&mlx5_intf_mutex); + priv->flags &= ~MLX5_PRIV_FLAGS_DETACH; for (i = 0; i < ARRAY_SIZE(mlx5_adev_devices); i++) { if (!priv->adev[i]) { bool is_supported = false; @@ -323,6 +324,16 @@ int mlx5_attach_device(struct mlx5_core_dev *dev) } } else { adev = &priv->adev[i]->adev; + + /* Pay attention that this is not PCI driver that + * mlx5_core_dev is connected, but auxiliary driver. + * + * Here we can race of module unload with devlink + * reload, but we don't need to take extra lock because + * we are holding global mlx5_intf_mutex. + */ + if (!adev->dev.driver) + continue; adrv = to_auxiliary_drv(adev->dev.driver); if (adrv->resume) @@ -353,6 +364,10 @@ void mlx5_detach_device(struct mlx5_core_dev *dev) continue; adev = &priv->adev[i]->adev; + /* Auxiliary driver was unbind manually through sysfs */ + if (!adev->dev.driver) + goto skip_suspend; + adrv = to_auxiliary_drv(adev->dev.driver); if (adrv->suspend) { @@ -360,9 +375,11 @@ void mlx5_detach_device(struct mlx5_core_dev *dev) continue; } +skip_suspend: del_adev(&priv->adev[i]->adev); priv->adev[i] = NULL; } + priv->flags |= MLX5_PRIV_FLAGS_DETACH; mutex_unlock(&mlx5_intf_mutex); } @@ -451,6 +468,8 @@ int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev) struct mlx5_priv *priv = &dev->priv; lockdep_assert_held(&mlx5_intf_mutex); + if (priv->flags & MLX5_PRIV_FLAGS_DETACH) + return 0; delete_drivers(dev); if (priv->flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c index be0ee03de721..2e9bee4e5209 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c @@ -129,10 +129,9 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) work); struct mlx5e_neigh_hash_entry *nhe = update_work->nhe; struct neighbour *n = update_work->n; + struct mlx5e_encap_entry *e = NULL; bool neigh_connected, same_dev; - struct mlx5e_encap_entry *e; unsigned char ha[ETH_ALEN]; - struct mlx5e_priv *priv; u8 nud_state, dead; rtnl_lock(); @@ -156,14 +155,12 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) if (!same_dev) goto out; - list_for_each_entry(e, &nhe->encap_list, encap_list) { - if (!mlx5e_encap_take(e)) - continue; + /* mlx5e_get_next_init_encap() releases previous encap before returning + * the next one. + */ + while ((e = mlx5e_get_next_init_encap(nhe, e)) != NULL) + mlx5e_rep_update_flows(netdev_priv(e->out_dev), e, neigh_connected, ha); - priv = netdev_priv(e->out_dev); - mlx5e_rep_update_flows(priv, e, neigh_connected, ha); - mlx5e_encap_put(priv, e); - } out: rtnl_unlock(); mlx5e_release_neigh_update_work(update_work); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index 96ba027dbef3..9992f94f794b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -93,13 +93,9 @@ void mlx5e_rep_update_flows(struct mlx5e_priv *priv, ASSERT_RTNL(); - /* wait for encap to be fully initialized */ - wait_for_completion(&e->res_ready); - mutex_lock(&esw->offloads.encap_tbl_lock); encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID); - if (e->compl_result < 0 || (encap_connected == neigh_connected && - ether_addr_equal(e->h_dest, ha))) + if (encap_connected == neigh_connected && ether_addr_equal(e->h_dest, ha)) goto unlock; mlx5e_take_all_encap_flows(e, &flow_list); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 1560fcbf4ac7..a17d79effa27 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -250,9 +250,12 @@ static void mlx5e_take_all_route_decap_flows(struct mlx5e_route_entry *r, mlx5e_take_tmp_flow(flow, flow_list, 0); } +typedef bool (match_cb)(struct mlx5e_encap_entry *); + static struct mlx5e_encap_entry * -mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe, - struct mlx5e_encap_entry *e) +mlx5e_get_next_matching_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e, + match_cb match) { struct mlx5e_encap_entry *next = NULL; @@ -287,7 +290,7 @@ mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe, /* wait for encap to be fully initialized */ wait_for_completion(&next->res_ready); /* continue searching if encap entry is not in valid state after completion */ - if (!(next->flags & MLX5_ENCAP_ENTRY_VALID)) { + if (!match(next)) { e = next; goto retry; } @@ -295,6 +298,30 @@ mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe, return next; } +static bool mlx5e_encap_valid(struct mlx5e_encap_entry *e) +{ + return e->flags & MLX5_ENCAP_ENTRY_VALID; +} + +static struct mlx5e_encap_entry * +mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e) +{ + return mlx5e_get_next_matching_encap(nhe, e, mlx5e_encap_valid); +} + +static bool mlx5e_encap_initialized(struct mlx5e_encap_entry *e) +{ + return e->compl_result >= 0; +} + +struct mlx5e_encap_entry * +mlx5e_get_next_init_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e) +{ + return mlx5e_get_next_matching_encap(nhe, e, mlx5e_encap_initialized); +} + void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) { struct mlx5e_neigh *m_neigh = &nhe->m_neigh; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 3d45341e2216..26f7fab109d9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -532,9 +532,6 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv) struct mlx5_core_dev *mdev = priv->mdev; struct net_device *netdev = priv->netdev; - if (!priv->ipsec) - return; - if (!(mlx5_accel_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_ESP) || !MLX5_CAP_ETH(mdev, swp)) { mlx5_core_dbg(mdev, "mlx5e: ESP and SWP offload not supported\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 99dc9f2beed5..16b8f5245032 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5168,22 +5168,15 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) } if (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev)) { - netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; - netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; - netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM; - netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; + netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL; + netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL; } if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_GRE)) { - netdev->hw_features |= NETIF_F_GSO_GRE | - NETIF_F_GSO_GRE_CSUM; - netdev->hw_enc_features |= NETIF_F_GSO_GRE | - NETIF_F_GSO_GRE_CSUM; - netdev->gso_partial_features |= NETIF_F_GSO_GRE | - NETIF_F_GSO_GRE_CSUM; + netdev->hw_features |= NETIF_F_GSO_GRE; + netdev->hw_enc_features |= NETIF_F_GSO_GRE; + netdev->gso_partial_features |= NETIF_F_GSO_GRE; } if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_IPIP)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index b633f669ea57..b3b8e44540a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -4622,7 +4622,7 @@ static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, list_for_each_entry_safe(hpe, tmp, &init_wait_list, dead_peer_wait_list) { wait_for_completion(&hpe->res_ready); if (!IS_ERR_OR_NULL(hpe->hp) && hpe->peer_vhca_id == peer_vhca_id) - hpe->hp->pair->peer_gone = true; + mlx5_core_hairpin_clear_dead_peer(hpe->hp->pair); mlx5e_hairpin_put(priv, hpe); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 25c091795bcd..17027536efba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -178,6 +178,9 @@ void mlx5e_take_all_encap_flows(struct mlx5e_encap_entry *e, struct list_head *f void mlx5e_put_flow_list(struct mlx5e_priv *priv, struct list_head *flow_list); struct mlx5e_neigh_hash_entry; +struct mlx5e_encap_entry * +mlx5e_get_next_init_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e); void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe); void mlx5e_tc_reoffload_flows_work(struct work_struct *work); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 1fa9c18563da..31c6a3b91f4a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -136,7 +136,7 @@ static int mlx5_eq_comp_int(struct notifier_block *nb, eqe = next_eqe_sw(eq); if (!eqe) - return 0; + goto out; do { struct mlx5_core_cq *cq; @@ -161,6 +161,8 @@ static int mlx5_eq_comp_int(struct notifier_block *nb, ++eq->cons_index; } while ((++num_eqes < MLX5_EQ_POLLING_BUDGET) && (eqe = next_eqe_sw(eq))); + +out: eq_update_ci(eq, 1); if (cqn != -1) @@ -248,9 +250,9 @@ static int mlx5_eq_async_int(struct notifier_block *nb, ++eq->cons_index; } while ((++num_eqes < MLX5_EQ_POLLING_BUDGET) && (eqe = next_eqe_sw(eq))); - eq_update_ci(eq, 1); out: + eq_update_ci(eq, 1); mlx5_eq_async_int_unlock(eq_async, recovery, &flags); return unlikely(recovery) ? num_eqes : 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 2c6d95900e3c..a3edeea4ddd7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1308,6 +1308,12 @@ int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, u16 vport_num, goto err_vhca_mapping; } + /* External controller host PF has factory programmed MAC. + * Read it from the device. + */ + if (mlx5_core_is_ecpf(esw->dev) && vport_num == MLX5_VPORT_PF) + mlx5_query_nic_vport_mac_address(esw->dev, vport_num, true, vport->info.mac); + esw_vport_change_handle_locked(vport); esw->enabled_vports++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index efb93d63e54c..58b8f75d7a01 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1157,7 +1157,7 @@ static int mlx5_load(struct mlx5_core_dev *dev) err = mlx5_core_set_hca_defaults(dev); if (err) { mlx5_core_err(dev, "Failed to set hca defaults\n"); - goto err_sriov; + goto err_set_hca; } mlx5_vhca_event_start(dev); @@ -1190,6 +1190,7 @@ static int mlx5_load(struct mlx5_core_dev *dev) mlx5_sf_hw_table_destroy(dev); err_vhca: mlx5_vhca_event_stop(dev); +err_set_hca: mlx5_cleanup_fs(dev); err_fs: mlx5_accel_tls_cleanup(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 50af84e76fb6..174f71ed5280 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -54,7 +54,7 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index); mkey->iova = MLX5_GET64(mkc, mkc, start_addr); mkey->size = MLX5_GET64(mkc, mkc, len); - mkey->key |= mlx5_idx_to_mkey(mkey_index); + mkey->key = (u32)mlx5_mkey_variant(mkey->key) | mlx5_idx_to_mkey(mkey_index); mkey->pd = MLX5_GET(mkc, mkc, pd); init_waitqueue_head(&mkey->wait); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c index 8e0dddc6383f..2389239acadc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c @@ -156,6 +156,9 @@ void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) { int err; + if (!MLX5_CAP_GEN(dev, roce)) + return; + err = mlx5_nic_vport_enable_roce(dev); if (err) { mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c index 90b524c59f3c..c4139f4648bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c @@ -153,6 +153,7 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_ sf_index = event->function_id - MLX5_CAP_GEN(table->dev, sf_base_id); sf_dev = xa_load(&table->devices, sf_index); switch (event->new_vhca_state) { + case MLX5_VHCA_STATE_INVALID: case MLX5_VHCA_STATE_ALLOCATED: if (sf_dev) mlx5_sf_dev_del(table->dev, sf_dev, sf_index); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c index f146c618a78e..46ef45fa9167 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -712,7 +712,11 @@ static int dr_ste_v1_set_action_decap_l3_list(void *data, if (hw_action_sz / DR_STE_ACTION_DOUBLE_SZ < DR_STE_DECAP_L3_ACTION_NUM) return -EINVAL; - memcpy(padded_data, data, data_sz); + inline_data_sz = + MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v1, inline_data); + + /* Add an alignment padding */ + memcpy(padded_data + data_sz % inline_data_sz, data, data_sz); /* Remove L2L3 outer headers */ MLX5_SET(ste_single_action_remove_header_v1, hw_action, action_id, @@ -724,32 +728,34 @@ static int dr_ste_v1_set_action_decap_l3_list(void *data, hw_action += DR_STE_ACTION_DOUBLE_SZ; used_actions++; /* Remove and NOP are a single double action */ - inline_data_sz = - MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v1, inline_data); + /* Point to the last dword of the header */ + data_ptr += (data_sz / inline_data_sz) * inline_data_sz; - /* Add the new header inline + 2 extra bytes */ + /* Add the new header using inline action 4Byte at a time, the header + * is added in reversed order to the beginning of the packet to avoid + * incorrect parsing by the HW. Since header is 14B or 18B an extra + * two bytes are padded and later removed. + */ for (i = 0; i < data_sz / inline_data_sz + 1; i++) { void *addr_inline; MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, action_id, DR_STE_V1_ACTION_ID_INSERT_INLINE); /* The hardware expects here offset to words (2 bytes) */ - MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, start_offset, - i * 2); + MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, start_offset, 0); /* Copy bytes one by one to avoid endianness problem */ addr_inline = MLX5_ADDR_OF(ste_double_action_insert_with_inline_v1, hw_action, inline_data); - memcpy(addr_inline, data_ptr, inline_data_sz); + memcpy(addr_inline, data_ptr - i * inline_data_sz, inline_data_sz); hw_action += DR_STE_ACTION_DOUBLE_SZ; - data_ptr += inline_data_sz; used_actions++; } - /* Remove 2 extra bytes */ + /* Remove first 2 extra bytes */ MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE); - MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, start_offset, data_sz / 2); + MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, start_offset, 0); /* The hardware expects here size in words (2 bytes) */ MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, remove_size, 1); used_actions++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index 612b0ac31db2..9737565cd8d4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -124,10 +124,11 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action); static inline bool mlx5dr_is_supported(struct mlx5_core_dev *dev) { - return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) || - (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) && - (MLX5_CAP_GEN(dev, steering_format_version) <= - MLX5_STEERING_FORMAT_CONNECTX_6DX)); + return MLX5_CAP_GEN(dev, roce) && + (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) || + (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) && + (MLX5_CAP_GEN(dev, steering_format_version) <= + MLX5_STEERING_FORMAT_CONNECTX_6DX))); } /* buddy functions & structure */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c index 01cc00ad8acf..b6931bbe52d2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c @@ -424,6 +424,15 @@ static int mlx5_hairpin_pair_queues(struct mlx5_hairpin *hp) return err; } +static void mlx5_hairpin_unpair_peer_sq(struct mlx5_hairpin *hp) +{ + int i; + + for (i = 0; i < hp->num_channels; i++) + mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY, + MLX5_SQC_STATE_RST, 0, 0); +} + static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp) { int i; @@ -432,13 +441,9 @@ static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp) for (i = 0; i < hp->num_channels; i++) mlx5_hairpin_modify_rq(hp->func_mdev, hp->rqn[i], MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_RST, 0, 0); - /* unset peer SQs */ - if (hp->peer_gone) - return; - for (i = 0; i < hp->num_channels; i++) - mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY, - MLX5_SQC_STATE_RST, 0, 0); + if (!hp->peer_gone) + mlx5_hairpin_unpair_peer_sq(hp); } struct mlx5_hairpin * @@ -485,3 +490,16 @@ void mlx5_core_hairpin_destroy(struct mlx5_hairpin *hp) mlx5_hairpin_destroy_queues(hp); kfree(hp); } + +void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp) +{ + int i; + + mlx5_hairpin_unpair_peer_sq(hp); + + /* destroy peer SQ */ + for (i = 0; i < hp->num_channels; i++) + mlx5_core_destroy_sq(hp->peer_mdev, hp->sqn[i]); + + hp->peer_gone = true; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index e05c5c0f3ae1..7d21fbb9192f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -465,8 +465,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, void *in; int err; - if (!vport) - return -EINVAL; if (!MLX5_CAP_GEN(mdev, vport_group_manager)) return -EACCES; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c index bf85ce9835d7..42e4437ac3c1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c @@ -708,7 +708,8 @@ mlxsw_thermal_module_tz_init(struct mlxsw_thermal_module *module_tz) MLXSW_THERMAL_TRIP_MASK, module_tz, &mlxsw_thermal_module_ops, - NULL, 0, 0); + NULL, 0, + module_tz->parent->polling_delay); if (IS_ERR(module_tz->tzdev)) { err = PTR_ERR(module_tz->tzdev); return err; @@ -830,7 +831,8 @@ mlxsw_thermal_gearbox_tz_init(struct mlxsw_thermal_module *gearbox_tz) MLXSW_THERMAL_TRIP_MASK, gearbox_tz, &mlxsw_thermal_gearbox_ops, - NULL, 0, 0); + NULL, 0, + gearbox_tz->parent->polling_delay); if (IS_ERR(gearbox_tz->tzdev)) return PTR_ERR(gearbox_tz->tzdev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index c4adc7f740d3..769386971ac3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -3863,7 +3863,7 @@ MLXSW_ITEM32(reg, qeec, max_shaper_bs, 0x1C, 0, 6); #define MLXSW_REG_QEEC_HIGHEST_SHAPER_BS 25 #define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP1 5 #define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP2 11 -#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3 5 +#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3 11 static inline void mlxsw_reg_qeec_pack(char *payload, u8 local_port, enum mlxsw_reg_qeec_hr hr, u8 index, diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 46e5c9136bac..0c4c976548c8 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -378,6 +378,7 @@ static u32 ocelot_read_eq_avail(struct ocelot *ocelot, int port) int ocelot_port_flush(struct ocelot *ocelot, int port) { + unsigned int pause_ena; int err, val; /* Disable dequeuing from the egress queues */ @@ -386,6 +387,7 @@ int ocelot_port_flush(struct ocelot *ocelot, int port) QSYS_PORT_MODE, port); /* Disable flow control */ + ocelot_fields_read(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, &pause_ena); ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, 0); /* Disable priority flow control */ @@ -421,6 +423,9 @@ int ocelot_port_flush(struct ocelot *ocelot, int port) /* Clear flushing again. */ ocelot_rmw_gix(ocelot, 0, REW_PORT_CFG_FLUSH_ENA, REW_PORT_CFG, port); + /* Re-enable flow control */ + ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, pause_ena); + return err; } EXPORT_SYMBOL(ocelot_port_flush); diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 7e6bac85495d..344ea1143454 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -1602,6 +1602,8 @@ netxen_nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) free_netdev(netdev); err_out_free_res: + if (NX_IS_REVISION_P3(pdev->revision)) + pci_disable_pcie_error_reporting(pdev); pci_release_regions(pdev); err_out_disable_pdev: diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 96b947fde646..3beafc60747e 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -2690,6 +2690,7 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) kfree(ahw); err_out_free_res: + pci_disable_pcie_error_reporting(pdev); pci_release_regions(pdev); err_out_disable_pdev: diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 41fbd2ceeede..ab1e0fcccabb 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -126,24 +126,24 @@ static void rmnet_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { struct rmnet_priv *priv = netdev_priv(dev); - struct rmnet_vnd_stats total_stats; + struct rmnet_vnd_stats total_stats = { }; struct rmnet_pcpu_stats *pcpu_ptr; + struct rmnet_vnd_stats snapshot; unsigned int cpu, start; - memset(&total_stats, 0, sizeof(struct rmnet_vnd_stats)); - for_each_possible_cpu(cpu) { pcpu_ptr = per_cpu_ptr(priv->pcpu_stats, cpu); do { start = u64_stats_fetch_begin_irq(&pcpu_ptr->syncp); - total_stats.rx_pkts += pcpu_ptr->stats.rx_pkts; - total_stats.rx_bytes += pcpu_ptr->stats.rx_bytes; - total_stats.tx_pkts += pcpu_ptr->stats.tx_pkts; - total_stats.tx_bytes += pcpu_ptr->stats.tx_bytes; + snapshot = pcpu_ptr->stats; /* struct assignment */ } while (u64_stats_fetch_retry_irq(&pcpu_ptr->syncp, start)); - total_stats.tx_drops += pcpu_ptr->stats.tx_drops; + total_stats.rx_pkts += snapshot.rx_pkts; + total_stats.rx_bytes += snapshot.rx_bytes; + total_stats.tx_pkts += snapshot.tx_pkts; + total_stats.tx_bytes += snapshot.tx_bytes; + total_stats.tx_drops += snapshot.tx_drops; } s->rx_packets = total_stats.rx_pkts; @@ -354,4 +354,4 @@ int rmnet_vnd_update_dev_mtu(struct rmnet_port *port, } return 0; -} \ No newline at end of file +} diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h index b70d44ac0990..3c73453725f9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h @@ -76,10 +76,10 @@ enum power_event { #define LPI_CTRL_STATUS_TLPIEN 0x00000001 /* Transmit LPI Entry */ /* GMAC HW ADDR regs */ -#define GMAC_ADDR_HIGH(reg) (((reg > 15) ? 0x00000800 : 0x00000040) + \ - (reg * 8)) -#define GMAC_ADDR_LOW(reg) (((reg > 15) ? 0x00000804 : 0x00000044) + \ - (reg * 8)) +#define GMAC_ADDR_HIGH(reg) ((reg > 15) ? 0x00000800 + (reg - 16) * 8 : \ + 0x00000040 + (reg * 8)) +#define GMAC_ADDR_LOW(reg) ((reg > 15) ? 0x00000804 + (reg - 16) * 8 : \ + 0x00000044 + (reg * 8)) #define GMAC_MAX_PERFECT_ADDRESSES 1 #define GMAC_PCS_BASE 0x000000c0 /* PCS register base */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 6dc9f10414e4..7e6bead6429c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -622,6 +622,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) void stmmac_remove_config_dt(struct platform_device *pdev, struct plat_stmmacenet_data *plat) { + clk_disable_unprepare(plat->stmmac_clk); + clk_disable_unprepare(plat->pclk); of_node_put(plat->phy_node); of_node_put(plat->mdio_node); } diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 030185301014..01bb36e7cff0 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -849,7 +849,7 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) smp_mb(); /* Space might have just been freed - check again */ - if (temac_check_tx_bd_space(lp, num_frag)) + if (temac_check_tx_bd_space(lp, num_frag + 1)) return NETDEV_TX_BUSY; netif_wake_queue(ndev); @@ -876,7 +876,6 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_OK; } cur_p->phys = cpu_to_be32(skb_dma_addr); - ptr_to_txbd((void *)skb, cur_p); for (ii = 0; ii < num_frag; ii++) { if (++lp->tx_bd_tail >= lp->tx_bd_num) @@ -915,6 +914,11 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) } cur_p->app0 |= cpu_to_be32(STS_CTRL_APP0_EOP); + /* Mark last fragment with skb address, so it can be consumed + * in temac_start_xmit_done() + */ + ptr_to_txbd((void *)skb, cur_p); + tail_p = lp->tx_bd_p + sizeof(*lp->tx_bd_v) * lp->tx_bd_tail; lp->tx_bd_tail++; if (lp->tx_bd_tail >= lp->tx_bd_num) diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 17be2bb2985c..920e9f888cc3 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -799,6 +799,7 @@ static void mkiss_close(struct tty_struct *tty) ax->tty = NULL; unregister_netdev(ax->dev); + free_netdev(ax->dev); } /* Perform I/O control on an active ax25 channel. */ diff --git a/drivers/net/mhi/net.c b/drivers/net/mhi/net.c index f59960876083..8e7f8728998f 100644 --- a/drivers/net/mhi/net.c +++ b/drivers/net/mhi/net.c @@ -49,7 +49,7 @@ static int mhi_ndo_stop(struct net_device *ndev) return 0; } -static int mhi_ndo_xmit(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t mhi_ndo_xmit(struct sk_buff *skb, struct net_device *ndev) { struct mhi_net_dev *mhi_netdev = netdev_priv(ndev); const struct mhi_net_proto *proto = mhi_netdev->proto; diff --git a/drivers/net/usb/cdc_eem.c b/drivers/net/usb/cdc_eem.c index 0eeec80bec31..e4a570366646 100644 --- a/drivers/net/usb/cdc_eem.c +++ b/drivers/net/usb/cdc_eem.c @@ -123,10 +123,10 @@ static struct sk_buff *eem_tx_fixup(struct usbnet *dev, struct sk_buff *skb, } skb2 = skb_copy_expand(skb, EEM_HEAD, ETH_FCS_LEN + padlen, flags); + dev_kfree_skb_any(skb); if (!skb2) return NULL; - dev_kfree_skb_any(skb); skb = skb2; done: diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 8acf30115428..dc3d84b43e4e 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -1902,7 +1902,7 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb) static const struct driver_info cdc_ncm_info = { .description = "CDC NCM", .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET - | FLAG_LINK_INTR, + | FLAG_LINK_INTR | FLAG_ETHER, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 76ed79bb1e3f..5281291711af 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -1483,7 +1483,7 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf) ret = smsc75xx_wait_ready(dev, 0); if (ret < 0) { netdev_warn(dev->net, "device not ready in smsc75xx_bind\n"); - goto err; + goto free_pdata; } smsc75xx_init_mac_address(dev); @@ -1492,7 +1492,7 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf) ret = smsc75xx_reset(dev); if (ret < 0) { netdev_warn(dev->net, "smsc75xx_reset error %d\n", ret); - goto err; + goto cancel_work; } dev->net->netdev_ops = &smsc75xx_netdev_ops; @@ -1503,8 +1503,11 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf) dev->net->max_mtu = MAX_SINGLE_PACKET_SIZE; return 0; -err: +cancel_work: + cancel_work_sync(&pdata->set_multicast); +free_pdata: kfree(pdata); + dev->data[0] = 0; return ret; } @@ -1515,7 +1518,6 @@ static void smsc75xx_unbind(struct usbnet *dev, struct usb_interface *intf) cancel_work_sync(&pdata->set_multicast); netif_dbg(dev, ifdown, dev->net, "free pdata\n"); kfree(pdata); - pdata = NULL; dev->data[0] = 0; } } diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 503e2fd7ce51..28a6c4cfe9b8 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1183,9 +1183,6 @@ static int vrf_dev_init(struct net_device *dev) dev->flags = IFF_MASTER | IFF_NOARP; - /* MTU is irrelevant for VRF device; set to 64k similar to lo */ - dev->mtu = 64 * 1024; - /* similarly, oper state is irrelevant; set to up to avoid confusion */ dev->operstate = IF_OPER_UP; netdev_lockdep_set_classes(dev); @@ -1685,7 +1682,8 @@ static void vrf_setup(struct net_device *dev) * which breaks networking. */ dev->min_mtu = IPV6_MIN_MTU; - dev->max_mtu = ETH_MAX_MTU; + dev->max_mtu = IP6_MAX_MTU; + dev->mtu = dev->max_mtu; } static int vrf_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index 051b48bd7985..e3f5e7ab7606 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -514,7 +514,7 @@ static int advk_pcie_wait_pio(struct advk_pcie *pcie) udelay(PIO_RETRY_DELAY); } - dev_err(dev, "config read/write timed out\n"); + dev_err(dev, "PIO read/write transfer time out\n"); return -ETIMEDOUT; } @@ -657,6 +657,35 @@ static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus, return true; } +static bool advk_pcie_pio_is_running(struct advk_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + + /* + * Trying to start a new PIO transfer when previous has not completed + * cause External Abort on CPU which results in kernel panic: + * + * SError Interrupt on CPU0, code 0xbf000002 -- SError + * Kernel panic - not syncing: Asynchronous SError Interrupt + * + * Functions advk_pcie_rd_conf() and advk_pcie_wr_conf() are protected + * by raw_spin_lock_irqsave() at pci_lock_config() level to prevent + * concurrent calls at the same time. But because PIO transfer may take + * about 1.5s when link is down or card is disconnected, it means that + * advk_pcie_wait_pio() does not always have to wait for completion. + * + * Some versions of ARM Trusted Firmware handles this External Abort at + * EL3 level and mask it to prevent kernel panic. Relevant TF-A commit: + * https://git.trustedfirmware.org/TF-A/trusted-firmware-a.git/commit/?id=3c7dcdac5c50 + */ + if (advk_readl(pcie, PIO_START)) { + dev_err(dev, "Previous PIO read/write transfer is still running\n"); + return true; + } + + return false; +} + static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where, int size, u32 *val) { @@ -673,9 +702,10 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, return pci_bridge_emul_conf_read(&pcie->bridge, where, size, val); - /* Start PIO */ - advk_writel(pcie, 0, PIO_START); - advk_writel(pcie, 1, PIO_ISR); + if (advk_pcie_pio_is_running(pcie)) { + *val = 0xffffffff; + return PCIBIOS_SET_FAILED; + } /* Program the control register */ reg = advk_readl(pcie, PIO_CTRL); @@ -694,7 +724,8 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, /* Program the data strobe */ advk_writel(pcie, 0xf, PIO_WR_DATA_STRB); - /* Start the transfer */ + /* Clear PIO DONE ISR and start the transfer */ + advk_writel(pcie, 1, PIO_ISR); advk_writel(pcie, 1, PIO_START); ret = advk_pcie_wait_pio(pcie); @@ -734,9 +765,8 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn, if (where % size) return PCIBIOS_SET_FAILED; - /* Start PIO */ - advk_writel(pcie, 0, PIO_START); - advk_writel(pcie, 1, PIO_ISR); + if (advk_pcie_pio_is_running(pcie)) + return PCIBIOS_SET_FAILED; /* Program the control register */ reg = advk_readl(pcie, PIO_CTRL); @@ -763,7 +793,8 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn, /* Program the data strobe */ advk_writel(pcie, data_strobe, PIO_WR_DATA_STRB); - /* Start the transfer */ + /* Clear PIO DONE ISR and start the transfer */ + advk_writel(pcie, 1, PIO_ISR); advk_writel(pcie, 1, PIO_START); ret = advk_pcie_wait_pio(pcie); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 653660e3ba9e..7bf76bca888d 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3558,6 +3558,18 @@ static void quirk_no_bus_reset(struct pci_dev *dev) dev->dev_flags |= PCI_DEV_FLAGS_NO_BUS_RESET; } +/* + * Some NVIDIA GPU devices do not work with bus reset, SBR needs to be + * prevented for those affected devices. + */ +static void quirk_nvidia_no_bus_reset(struct pci_dev *dev) +{ + if ((dev->device & 0xffc0) == 0x2340) + quirk_no_bus_reset(dev); +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, + quirk_nvidia_no_bus_reset); + /* * Some Atheros AR9xxx and QCA988x chips do not behave after a bus reset. * The device will throw a Link Down error on AER-capable systems and @@ -3578,6 +3590,16 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x0034, quirk_no_bus_reset); */ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CAVIUM, 0xa100, quirk_no_bus_reset); +/* + * Some TI KeyStone C667X devices do not support bus/hot reset. The PCIESS + * automatically disables LTSSM when Secondary Bus Reset is received and + * the device stops working. Prevent bus reset for these devices. With + * this change, the device can be assigned to VMs with VFIO, but it will + * leak state between VMs. Reference + * https://e2e.ti.com/support/processors/f/791/t/954382 + */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TI, 0xb005, quirk_no_bus_reset); + static void quirk_no_pm_reset(struct pci_dev *dev) { /* @@ -3913,6 +3935,69 @@ static int delay_250ms_after_flr(struct pci_dev *dev, int probe) return 0; } +#define PCI_DEVICE_ID_HINIC_VF 0x375E +#define HINIC_VF_FLR_TYPE 0x1000 +#define HINIC_VF_FLR_CAP_BIT (1UL << 30) +#define HINIC_VF_OP 0xE80 +#define HINIC_VF_FLR_PROC_BIT (1UL << 18) +#define HINIC_OPERATION_TIMEOUT 15000 /* 15 seconds */ + +/* Device-specific reset method for Huawei Intelligent NIC virtual functions */ +static int reset_hinic_vf_dev(struct pci_dev *pdev, int probe) +{ + unsigned long timeout; + void __iomem *bar; + u32 val; + + if (probe) + return 0; + + bar = pci_iomap(pdev, 0, 0); + if (!bar) + return -ENOTTY; + + /* Get and check firmware capabilities */ + val = ioread32be(bar + HINIC_VF_FLR_TYPE); + if (!(val & HINIC_VF_FLR_CAP_BIT)) { + pci_iounmap(pdev, bar); + return -ENOTTY; + } + + /* Set HINIC_VF_FLR_PROC_BIT for the start of FLR */ + val = ioread32be(bar + HINIC_VF_OP); + val = val | HINIC_VF_FLR_PROC_BIT; + iowrite32be(val, bar + HINIC_VF_OP); + + pcie_flr(pdev); + + /* + * The device must recapture its Bus and Device Numbers after FLR + * in order generate Completions. Issue a config write to let the + * device capture this information. + */ + pci_write_config_word(pdev, PCI_VENDOR_ID, 0); + + /* Firmware clears HINIC_VF_FLR_PROC_BIT when reset is complete */ + timeout = jiffies + msecs_to_jiffies(HINIC_OPERATION_TIMEOUT); + do { + val = ioread32be(bar + HINIC_VF_OP); + if (!(val & HINIC_VF_FLR_PROC_BIT)) + goto reset_complete; + msleep(20); + } while (time_before(jiffies, timeout)); + + val = ioread32be(bar + HINIC_VF_OP); + if (!(val & HINIC_VF_FLR_PROC_BIT)) + goto reset_complete; + + pci_warn(pdev, "Reset dev timeout, FLR ack reg: %#010x\n", val); + +reset_complete: + pci_iounmap(pdev, bar); + + return 0; +} + static const struct pci_dev_reset_methods pci_dev_reset_methods[] = { { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82599_SFP_VF, reset_intel_82599_sfp_virtfn }, @@ -3924,6 +4009,8 @@ static const struct pci_dev_reset_methods pci_dev_reset_methods[] = { { PCI_VENDOR_ID_INTEL, 0x0953, delay_250ms_after_flr }, { PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID, reset_chelsio_generic_dev }, + { PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HINIC_VF, + reset_hinic_vf_dev }, { 0 } }; @@ -4764,6 +4851,8 @@ static const struct pci_dev_acs_enabled { { PCI_VENDOR_ID_AMPERE, 0xE00A, pci_quirk_xgene_acs }, { PCI_VENDOR_ID_AMPERE, 0xE00B, pci_quirk_xgene_acs }, { PCI_VENDOR_ID_AMPERE, 0xE00C, pci_quirk_xgene_acs }, + /* Broadcom multi-function device */ + { PCI_VENDOR_ID_BROADCOM, 0x16D7, pci_quirk_mf_endpoint_acs }, { PCI_VENDOR_ID_BROADCOM, 0xD714, pci_quirk_brcm_acs }, /* Amazon Annapurna Labs */ { PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031, pci_quirk_al_acs }, @@ -5165,7 +5254,8 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0422, quirk_no_ext_tags); static void quirk_amd_harvest_no_ats(struct pci_dev *pdev) { if ((pdev->device == 0x7312 && pdev->revision != 0x00) || - (pdev->device == 0x7340 && pdev->revision != 0xc5)) + (pdev->device == 0x7340 && pdev->revision != 0xc5) || + (pdev->device == 0x7341 && pdev->revision != 0x00)) return; if (pdev->device == 0x15d8) { @@ -5192,6 +5282,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_amd_harvest_no_ats); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7312, quirk_amd_harvest_no_ats); /* AMD Navi14 dGPU */ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7341, quirk_amd_harvest_no_ats); /* AMD Raven platform iGPU */ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x15d8, quirk_amd_harvest_no_ats); #endif /* CONFIG_PCI_ATS */ diff --git a/drivers/phy/mediatek/phy-mtk-tphy.c b/drivers/phy/mediatek/phy-mtk-tphy.c index cdbcc49f7115..731c483a04de 100644 --- a/drivers/phy/mediatek/phy-mtk-tphy.c +++ b/drivers/phy/mediatek/phy-mtk-tphy.c @@ -949,6 +949,8 @@ static int mtk_phy_init(struct phy *phy) break; default: dev_err(tphy->dev, "incompatible PHY type\n"); + clk_disable_unprepare(instance->ref_clk); + clk_disable_unprepare(instance->da_ref_clk); return -EINVAL; } diff --git a/drivers/pinctrl/ralink/pinctrl-rt2880.c b/drivers/pinctrl/ralink/pinctrl-rt2880.c index 1f4bca854add..a9b511c7e850 100644 --- a/drivers/pinctrl/ralink/pinctrl-rt2880.c +++ b/drivers/pinctrl/ralink/pinctrl-rt2880.c @@ -127,7 +127,7 @@ static int rt2880_pmx_group_enable(struct pinctrl_dev *pctrldev, if (p->groups[group].enabled) { dev_err(p->dev, "%s is already enabled\n", p->groups[group].name); - return -EBUSY; + return 0; } p->groups[group].enabled = 1; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 61f1c91c62de..3390168ac079 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -8808,6 +8808,7 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_Q_LNV3('N', '2', 'O', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (2nd gen) */ TPACPI_Q_LNV3('N', '2', 'V', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (3nd gen) */ TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL), /* P15 (1st gen) / P15v (1st gen) */ + TPACPI_Q_LNV3('N', '3', '2', TPACPI_FAN_2CTL), /* X1 Carbon (9th gen) */ }; static int __init fan_init(struct ibm_init_struct *iibm) diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 03a246e60fd9..21c4c34c52d8 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -63,7 +63,7 @@ static void enqueue_external_timestamp(struct timestamp_event_queue *queue, spin_unlock_irqrestore(&queue->lock, flags); } -s32 scaled_ppm_to_ppb(long ppm) +long scaled_ppm_to_ppb(long ppm) { /* * The 'freq' field in the 'struct timex' is in parts per @@ -80,7 +80,7 @@ s32 scaled_ppm_to_ppb(long ppm) s64 ppb = 1 + ppm; ppb *= 125; ppb >>= 13; - return (s32) ppb; + return (long) ppb; } EXPORT_SYMBOL(scaled_ppm_to_ppb); @@ -138,7 +138,7 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx) delta = ktime_to_ns(kt); err = ops->adjtime(ops, delta); } else if (tx->modes & ADJ_FREQUENCY) { - s32 ppb = scaled_ppm_to_ppb(tx->freq); + long ppb = scaled_ppm_to_ppb(tx->freq); if (ppb > ops->max_adj || ppb < -ops->max_adj) return -ERANGE; if (ops->adjfine) diff --git a/drivers/regulator/cros-ec-regulator.c b/drivers/regulator/cros-ec-regulator.c index eb3fc1db4edc..c4754f3cf233 100644 --- a/drivers/regulator/cros-ec-regulator.c +++ b/drivers/regulator/cros-ec-regulator.c @@ -225,8 +225,9 @@ static int cros_ec_regulator_probe(struct platform_device *pdev) drvdata->dev = devm_regulator_register(dev, &drvdata->desc, &cfg); if (IS_ERR(drvdata->dev)) { + ret = PTR_ERR(drvdata->dev); dev_err(&pdev->dev, "Failed to register regulator: %d\n", ret); - return PTR_ERR(drvdata->dev); + return ret; } platform_set_drvdata(pdev, drvdata); diff --git a/drivers/regulator/mt6315-regulator.c b/drivers/regulator/mt6315-regulator.c index 9edc34981ee0..6b8be52c3772 100644 --- a/drivers/regulator/mt6315-regulator.c +++ b/drivers/regulator/mt6315-regulator.c @@ -59,7 +59,7 @@ static const struct linear_range mt_volt_range1[] = { REGULATOR_LINEAR_RANGE(0, 0, 0xbf, 6250), }; -static unsigned int mt6315_map_mode(u32 mode) +static unsigned int mt6315_map_mode(unsigned int mode) { switch (mode) { case MT6315_BUCK_MODE_AUTO: diff --git a/drivers/regulator/rt4801-regulator.c b/drivers/regulator/rt4801-regulator.c index 2055a9cb13ba..7a87788d3f09 100644 --- a/drivers/regulator/rt4801-regulator.c +++ b/drivers/regulator/rt4801-regulator.c @@ -66,7 +66,7 @@ static int rt4801_enable(struct regulator_dev *rdev) struct gpio_descs *gpios = priv->enable_gpios; int id = rdev_get_id(rdev), ret; - if (gpios->ndescs <= id) { + if (!gpios || gpios->ndescs <= id) { dev_warn(&rdev->dev, "no dedicated gpio can control\n"); goto bypass_gpio; } @@ -88,7 +88,7 @@ static int rt4801_disable(struct regulator_dev *rdev) struct gpio_descs *gpios = priv->enable_gpios; int id = rdev_get_id(rdev); - if (gpios->ndescs <= id) { + if (!gpios || gpios->ndescs <= id) { dev_warn(&rdev->dev, "no dedicated gpio can control\n"); goto bypass_gpio; } diff --git a/drivers/regulator/rtmv20-regulator.c b/drivers/regulator/rtmv20-regulator.c index 5adc552dffd5..4bca64de0f67 100644 --- a/drivers/regulator/rtmv20-regulator.c +++ b/drivers/regulator/rtmv20-regulator.c @@ -27,6 +27,7 @@ #define RTMV20_REG_LDIRQ 0x30 #define RTMV20_REG_LDSTAT 0x40 #define RTMV20_REG_LDMASK 0x50 +#define RTMV20_MAX_REGS (RTMV20_REG_LDMASK + 1) #define RTMV20_VID_MASK GENMASK(7, 4) #define RICHTEK_VID 0x80 @@ -313,6 +314,7 @@ static const struct regmap_config rtmv20_regmap_config = { .val_bits = 8, .cache_type = REGCACHE_RBTREE, .max_register = RTMV20_REG_LDMASK, + .num_reg_defaults_raw = RTMV20_MAX_REGS, .writeable_reg = rtmv20_is_accessible_reg, .readable_reg = rtmv20_is_accessible_reg, diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index ecefc25eff0c..337353c9655e 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -135,12 +135,13 @@ static struct ap_queue_status ap_sm_recv(struct ap_queue *aq) { struct ap_queue_status status; struct ap_message *ap_msg; + bool found = false; status = ap_dqap(aq->qid, &aq->reply->psmid, aq->reply->msg, aq->reply->len); switch (status.response_code) { case AP_RESPONSE_NORMAL: - aq->queue_count--; + aq->queue_count = max_t(int, 0, aq->queue_count - 1); if (aq->queue_count > 0) mod_timer(&aq->timeout, jiffies + aq->request_timeout); @@ -150,8 +151,14 @@ static struct ap_queue_status ap_sm_recv(struct ap_queue *aq) list_del_init(&ap_msg->list); aq->pendingq_count--; ap_msg->receive(aq, ap_msg, aq->reply); + found = true; break; } + if (!found) { + AP_DBF_WARN("%s unassociated reply psmid=0x%016llx on 0x%02x.%04x\n", + __func__, aq->reply->psmid, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + } fallthrough; case AP_RESPONSE_NO_PENDING_REPLY: if (!status.queue_empty || aq->queue_count <= 0) @@ -232,7 +239,7 @@ static enum ap_sm_wait ap_sm_write(struct ap_queue *aq) ap_msg->flags & AP_MSG_FLAG_SPECIAL); switch (status.response_code) { case AP_RESPONSE_NORMAL: - aq->queue_count++; + aq->queue_count = max_t(int, 1, aq->queue_count + 1); if (aq->queue_count == 1) mod_timer(&aq->timeout, jiffies + aq->request_timeout); list_move_tail(&ap_msg->list, &aq->pendingq); diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c index 2786470a5201..4f24f6392212 100644 --- a/drivers/spi/spi-stm32-qspi.c +++ b/drivers/spi/spi-stm32-qspi.c @@ -293,7 +293,7 @@ static int stm32_qspi_wait_cmd(struct stm32_qspi *qspi, int err = 0; if (!op->data.nbytes) - return stm32_qspi_wait_nobusy(qspi); + goto wait_nobusy; if (readl_relaxed(qspi->io_base + QSPI_SR) & SR_TCF) goto out; @@ -314,6 +314,9 @@ static int stm32_qspi_wait_cmd(struct stm32_qspi *qspi, out: /* clear flags */ writel_relaxed(FCR_CTCF | FCR_CTEF, qspi->io_base + QSPI_FCR); +wait_nobusy: + if (!err) + err = stm32_qspi_wait_nobusy(qspi); return err; } diff --git a/drivers/spi/spi-zynq-qspi.c b/drivers/spi/spi-zynq-qspi.c index 2765289028fa..68193db8b2e3 100644 --- a/drivers/spi/spi-zynq-qspi.c +++ b/drivers/spi/spi-zynq-qspi.c @@ -678,14 +678,14 @@ static int zynq_qspi_probe(struct platform_device *pdev) xqspi->irq = platform_get_irq(pdev, 0); if (xqspi->irq <= 0) { ret = -ENXIO; - goto remove_master; + goto clk_dis_all; } ret = devm_request_irq(&pdev->dev, xqspi->irq, zynq_qspi_irq, 0, pdev->name, xqspi); if (ret != 0) { ret = -ENXIO; dev_err(&pdev->dev, "request_irq failed\n"); - goto remove_master; + goto clk_dis_all; } ret = of_property_read_u32(np, "num-cs", @@ -693,8 +693,9 @@ static int zynq_qspi_probe(struct platform_device *pdev) if (ret < 0) { ctlr->num_chipselect = 1; } else if (num_cs > ZYNQ_QSPI_MAX_NUM_CS) { + ret = -EINVAL; dev_err(&pdev->dev, "only 2 chip selects are available\n"); - goto remove_master; + goto clk_dis_all; } else { ctlr->num_chipselect = num_cs; } diff --git a/drivers/staging/hikey9xx/hi6421v600-regulator.c b/drivers/staging/hikey9xx/hi6421v600-regulator.c index f6a14e9c3cbf..e10fe3058176 100644 --- a/drivers/staging/hikey9xx/hi6421v600-regulator.c +++ b/drivers/staging/hikey9xx/hi6421v600-regulator.c @@ -83,7 +83,7 @@ static const unsigned int ldo34_voltages[] = { .owner = THIS_MODULE, \ .volt_table = vtable, \ .n_voltages = ARRAY_SIZE(vtable), \ - .vsel_mask = (1 << (ARRAY_SIZE(vtable) - 1)) - 1, \ + .vsel_mask = ARRAY_SIZE(vtable) - 1, \ .vsel_reg = vreg, \ .enable_reg = ereg, \ .enable_mask = emask, \ diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c index cbec65e5a464..62ea47f9fee5 100644 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c +++ b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c @@ -2579,7 +2579,7 @@ static int rtw_cfg80211_add_monitor_if(struct adapter *padapter, char *name, str mon_wdev->iftype = NL80211_IFTYPE_MONITOR; mon_ndev->ieee80211_ptr = mon_wdev; - ret = register_netdevice(mon_ndev); + ret = cfg80211_register_netdevice(mon_ndev); if (ret) { goto out; } @@ -2661,7 +2661,7 @@ static int cfg80211_rtw_del_virtual_intf(struct wiphy *wiphy, adapter = rtw_netdev_priv(ndev); pwdev_priv = adapter_wdev_data(adapter); - unregister_netdevice(ndev); + cfg80211_unregister_netdevice(ndev); if (ndev == pwdev_priv->pmon_ndev) { pwdev_priv->pmon_ndev = NULL; diff --git a/drivers/usb/chipidea/usbmisc_imx.c b/drivers/usb/chipidea/usbmisc_imx.c index 4545b23bda3f..bac0f5458cab 100644 --- a/drivers/usb/chipidea/usbmisc_imx.c +++ b/drivers/usb/chipidea/usbmisc_imx.c @@ -686,6 +686,16 @@ static int imx7d_charger_secondary_detection(struct imx_usbmisc_data *data) int val; unsigned long flags; + /* Clear VDATSRCENB0 to disable VDP_SRC and IDM_SNK required by BC 1.2 spec */ + spin_lock_irqsave(&usbmisc->lock, flags); + val = readl(usbmisc->base + MX7D_USB_OTG_PHY_CFG2); + val &= ~MX7D_USB_OTG_PHY_CFG2_CHRG_VDATSRCENB0; + writel(val, usbmisc->base + MX7D_USB_OTG_PHY_CFG2); + spin_unlock_irqrestore(&usbmisc->lock, flags); + + /* TVDMSRC_DIS */ + msleep(20); + /* VDM_SRC is connected to D- and IDP_SINK is connected to D+ */ spin_lock_irqsave(&usbmisc->lock, flags); val = readl(usbmisc->base + MX7D_USB_OTG_PHY_CFG2); @@ -695,7 +705,8 @@ static int imx7d_charger_secondary_detection(struct imx_usbmisc_data *data) usbmisc->base + MX7D_USB_OTG_PHY_CFG2); spin_unlock_irqrestore(&usbmisc->lock, flags); - usleep_range(1000, 2000); + /* TVDMSRC_ON */ + msleep(40); /* * Per BC 1.2, check voltage of D+: @@ -798,7 +809,8 @@ static int imx7d_charger_primary_detection(struct imx_usbmisc_data *data) usbmisc->base + MX7D_USB_OTG_PHY_CFG2); spin_unlock_irqrestore(&usbmisc->lock, flags); - usleep_range(1000, 2000); + /* TVDPSRC_ON */ + msleep(40); /* Check if D- is less than VDAT_REF to determine an SDP per BC 1.2 */ val = readl(usbmisc->base + MX7D_USB_OTG_PHY_STATUS); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 13fe37fbbd2c..6ebb8bd92e9d 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -40,6 +40,8 @@ #define USB_VENDOR_GENESYS_LOGIC 0x05e3 #define USB_VENDOR_SMSC 0x0424 #define USB_PRODUCT_USB5534B 0x5534 +#define USB_VENDOR_CYPRESS 0x04b4 +#define USB_PRODUCT_CY7C65632 0x6570 #define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND 0x01 #define HUB_QUIRK_DISABLE_AUTOSUSPEND 0x02 @@ -5644,6 +5646,11 @@ static const struct usb_device_id hub_id_table[] = { .idProduct = USB_PRODUCT_USB5534B, .bInterfaceClass = USB_CLASS_HUB, .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND}, + { .match_flags = USB_DEVICE_ID_MATCH_VENDOR + | USB_DEVICE_ID_MATCH_PRODUCT, + .idVendor = USB_VENDOR_CYPRESS, + .idProduct = USB_PRODUCT_CY7C65632, + .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND}, { .match_flags = USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_INT_CLASS, .idVendor = USB_VENDOR_GENESYS_LOGIC, diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 126f0e10b3ef..0022039bc235 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1657,8 +1657,8 @@ static int dwc3_remove(struct platform_device *pdev) pm_runtime_get_sync(&pdev->dev); - dwc3_debugfs_exit(dwc); dwc3_core_exit_mode(dwc); + dwc3_debugfs_exit(dwc); dwc3_core_exit(dwc); dwc3_ulpi_exit(dwc); diff --git a/drivers/usb/dwc3/debug.h b/drivers/usb/dwc3/debug.h index 8ab394942360..74d9c2c38193 100644 --- a/drivers/usb/dwc3/debug.h +++ b/drivers/usb/dwc3/debug.h @@ -413,9 +413,12 @@ static inline const char *dwc3_gadget_generic_cmd_status_string(int status) #ifdef CONFIG_DEBUG_FS +extern void dwc3_debugfs_create_endpoint_dir(struct dwc3_ep *dep); extern void dwc3_debugfs_init(struct dwc3 *d); extern void dwc3_debugfs_exit(struct dwc3 *d); #else +static inline void dwc3_debugfs_create_endpoint_dir(struct dwc3_ep *dep) +{ } static inline void dwc3_debugfs_init(struct dwc3 *d) { } static inline void dwc3_debugfs_exit(struct dwc3 *d) diff --git a/drivers/usb/dwc3/debugfs.c b/drivers/usb/dwc3/debugfs.c index 5da4f6082d93..3ebe3e6c284d 100644 --- a/drivers/usb/dwc3/debugfs.c +++ b/drivers/usb/dwc3/debugfs.c @@ -890,30 +890,14 @@ static void dwc3_debugfs_create_endpoint_files(struct dwc3_ep *dep, } } -static void dwc3_debugfs_create_endpoint_dir(struct dwc3_ep *dep, - struct dentry *parent) +void dwc3_debugfs_create_endpoint_dir(struct dwc3_ep *dep) { struct dentry *dir; - dir = debugfs_create_dir(dep->name, parent); + dir = debugfs_create_dir(dep->name, dep->dwc->root); dwc3_debugfs_create_endpoint_files(dep, dir); } -static void dwc3_debugfs_create_endpoint_dirs(struct dwc3 *dwc, - struct dentry *parent) -{ - int i; - - for (i = 0; i < dwc->num_eps; i++) { - struct dwc3_ep *dep = dwc->eps[i]; - - if (!dep) - continue; - - dwc3_debugfs_create_endpoint_dir(dep, parent); - } -} - void dwc3_debugfs_init(struct dwc3 *dwc) { struct dentry *root; @@ -944,7 +928,6 @@ void dwc3_debugfs_init(struct dwc3 *dwc) &dwc3_testmode_fops); debugfs_create_file("link_state", 0644, root, dwc, &dwc3_link_state_fops); - dwc3_debugfs_create_endpoint_dirs(dwc, root); } } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 1f9454e0d447..755ab6fc0791 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2719,6 +2719,8 @@ static int dwc3_gadget_init_endpoint(struct dwc3 *dwc, u8 epnum) INIT_LIST_HEAD(&dep->started_list); INIT_LIST_HEAD(&dep->cancelled_list); + dwc3_debugfs_create_endpoint_dir(dep); + return 0; } @@ -2762,6 +2764,7 @@ static void dwc3_gadget_free_endpoints(struct dwc3 *dwc) list_del(&dep->endpoint.ep_list); } + debugfs_remove_recursive(debugfs_lookup(dep->name, dwc->root)); kfree(dep); } } diff --git a/fs/afs/main.c b/fs/afs/main.c index b2975256dadb..179004b15566 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -203,8 +203,8 @@ static int __init afs_init(void) goto error_fs; afs_proc_symlink = proc_symlink("fs/afs", NULL, "../self/net/afs"); - if (IS_ERR(afs_proc_symlink)) { - ret = PTR_ERR(afs_proc_symlink); + if (!afs_proc_symlink) { + ret = -ENOMEM; goto error_proc; } diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index a7d9e147dee6..595fd083c4ad 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2347,16 +2347,16 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache) spin_lock(&sinfo->lock); spin_lock(&cache->lock); if (!--cache->ro) { - num_bytes = cache->length - cache->reserved - - cache->pinned - cache->bytes_super - - cache->zone_unusable - cache->used; - sinfo->bytes_readonly -= num_bytes; if (btrfs_is_zoned(cache->fs_info)) { /* Migrate zone_unusable bytes back */ cache->zone_unusable = cache->alloc_offset - cache->used; sinfo->bytes_zone_unusable += cache->zone_unusable; sinfo->bytes_readonly -= cache->zone_unusable; } + num_bytes = cache->length - cache->reserved - + cache->pinned - cache->bytes_super - + cache->zone_unusable - cache->used; + sinfo->bytes_readonly -= num_bytes; list_del_init(&cache->ro_list); } spin_unlock(&cache->lock); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index c63d0a7f7ba4..527c972b562d 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -738,6 +738,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, __SetPageUptodate(page); error = huge_add_to_page_cache(page, mapping, index); if (unlikely(error)) { + restore_reserve_on_error(h, &pseudo_vma, addr, page); put_page(page); mutex_unlock(&hugetlb_fault_mutex_table[hash]); goto out; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 9e0c1afac8bd..c175523b0a2c 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -378,7 +378,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, info_type, fanotify_info_name(info), info->name_len, buf, count); if (ret < 0) - return ret; + goto out_close_fd; buf += ret; count -= ret; @@ -426,7 +426,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, fanotify_event_object_fh(event), info_type, dot, dot_len, buf, count); if (ret < 0) - return ret; + goto out_close_fd; buf += ret; count -= ret; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index cccd1aab69dd..5dae4187210d 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -145,6 +145,7 @@ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); bool isolate_huge_page(struct page *page, struct list_head *list); +int get_hwpoison_huge_page(struct page *page, bool *hugetlb); void putback_active_hugepage(struct page *page); void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason); void free_huge_page(struct page *page); @@ -330,6 +331,11 @@ static inline bool isolate_huge_page(struct page *page, struct list_head *list) return false; } +static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb) +{ + return 0; +} + static inline void putback_active_hugepage(struct page *page) { } @@ -591,6 +597,8 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address); int huge_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); +void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, + unsigned long address, struct page *page); /* arch callback */ int __init __alloc_bootmem_huge_page(struct hstate *h); diff --git a/include/linux/mfd/rohm-bd70528.h b/include/linux/mfd/rohm-bd70528.h index a57af878fd0c..4a5966475a35 100644 --- a/include/linux/mfd/rohm-bd70528.h +++ b/include/linux/mfd/rohm-bd70528.h @@ -26,9 +26,7 @@ struct bd70528_data { struct mutex rtc_timer_lock; }; -#define BD70528_BUCK_VOLTS 17 -#define BD70528_BUCK_VOLTS 17 -#define BD70528_BUCK_VOLTS 17 +#define BD70528_BUCK_VOLTS 0x10 #define BD70528_LDO_VOLTS 0x20 #define BD70528_REG_BUCK1_EN 0x0F diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 133967c40214..6a31bbba1b6f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -541,6 +541,10 @@ struct mlx5_core_roce { enum { MLX5_PRIV_FLAGS_DISABLE_IB_ADEV = 1 << 0, MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV = 1 << 1, + /* Set during device detach to block any further devices + * creation/deletion on drivers rescan. Unset during device attach. + */ + MLX5_PRIV_FLAGS_DETACH = 1 << 2, }; struct mlx5_adev { diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h index 028f442530cf..60ffeb6b67ae 100644 --- a/include/linux/mlx5/transobj.h +++ b/include/linux/mlx5/transobj.h @@ -85,4 +85,5 @@ mlx5_core_hairpin_create(struct mlx5_core_dev *func_mdev, struct mlx5_hairpin_params *params); void mlx5_core_hairpin_destroy(struct mlx5_hairpin *pair); +void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp); #endif /* __TRANSOBJ_H__ */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5aacc1c10a45..8f0fb62e8975 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -445,13 +445,6 @@ struct mm_struct { */ atomic_t has_pinned; - /** - * @write_protect_seq: Locked when any thread is write - * protecting pages mapped by this mm to enforce a later COW, - * for instance during page table copying for fork(). - */ - seqcount_t write_protect_seq; - #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* PTE page table pages */ #endif @@ -460,6 +453,18 @@ struct mm_struct { spinlock_t page_table_lock; /* Protects page tables and some * counters */ + /* + * With some kernel config, the current mmap_lock's offset + * inside 'mm_struct' is at 0x120, which is very optimal, as + * its two hot fields 'count' and 'owner' sit in 2 different + * cachelines, and when mmap_lock is highly contended, both + * of the 2 fields will be accessed frequently, current layout + * will help to reduce cache bouncing. + * + * So please be careful with adding new fields before + * mmap_lock, which can easily push the 2 fields into one + * cacheline. + */ struct rw_semaphore mmap_lock; struct list_head mmlist; /* List of maybe swapped mm's. These @@ -480,7 +485,15 @@ struct mm_struct { unsigned long stack_vm; /* VM_STACK */ unsigned long def_flags; + /** + * @write_protect_seq: Locked when any thread is write + * protecting pages mapped by this mm to enforce a later COW, + * for instance during page table copying for fork(). + */ + seqcount_t write_protect_seq; + spinlock_t arg_lock; /* protect the below fields */ + unsigned long start_code, end_code, start_data, end_data; unsigned long start_brk, brk, start_stack; unsigned long arg_start, arg_end, env_start, env_end; diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 0d47fd33b228..51d7f1b8b32a 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -235,7 +235,7 @@ extern int ptp_clock_index(struct ptp_clock *ptp); * @ppm: Parts per million, but with a 16 bit binary fractional field */ -extern s32 scaled_ppm_to_ppb(long ppm); +extern long scaled_ppm_to_ppb(long ppm); /** * ptp_find_pin() - obtain the pin index of a given auxiliary function diff --git a/include/linux/socket.h b/include/linux/socket.h index 385894b4a8bb..42222a84167f 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -438,6 +438,4 @@ extern int __sys_socketpair(int family, int type, int protocol, int __user *usockvec); extern int __sys_shutdown_sock(struct socket *sock, int how); extern int __sys_shutdown(int fd, int how); - -extern struct ns_common *get_net_ns(struct ns_common *ns); #endif /* _LINUX_SOCKET_H */ diff --git a/include/linux/swapops.h b/include/linux/swapops.h index d9b7c9132c2f..6430a94c6981 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -23,6 +23,16 @@ #define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) #define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) +/* Clear all flags but only keep swp_entry_t related information */ +static inline pte_t pte_swp_clear_flags(pte_t pte) +{ + if (pte_swp_soft_dirty(pte)) + pte = pte_swp_clear_soft_dirty(pte); + if (pte_swp_uffd_wp(pte)) + pte = pte_swp_clear_uffd_wp(pte); + return pte; +} + /* * Store a type+offset into a swp_entry_t in an arch-independent format */ @@ -66,10 +76,7 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte) { swp_entry_t arch_entry; - if (pte_swp_soft_dirty(pte)) - pte = pte_swp_clear_soft_dirty(pte); - if (pte_swp_uffd_wp(pte)) - pte = pte_swp_clear_uffd_wp(pte); + pte = pte_swp_clear_flags(pte); arch_entry = __pte_to_swp_entry(pte); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 2d1d629e5d14..a5ca18cfdb6f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6388,7 +6388,12 @@ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw, /** * ieee80211_parse_tx_radiotap - Sanity-check and parse the radiotap header - * of injected frames + * of injected frames. + * + * To accurately parse and take into account rate and retransmission fields, + * you must initialize the chandef field in the ieee80211_tx_info structure + * of the skb before calling this function. + * * @skb: packet injected by userspace * @dev: the &struct device of this 802.11 device */ diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index dcaee24a4d87..14b6f7f44532 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -197,6 +197,8 @@ struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid); void net_ns_barrier(void); + +struct ns_common *get_net_ns(struct ns_common *ns); #else /* CONFIG_NET_NS */ #include <linux/sched.h> #include <linux/nsproxy.h> @@ -216,6 +218,11 @@ static inline void net_ns_get_ownership(const struct net *net, } static inline void net_ns_barrier(void) {} + +static inline struct ns_common *get_net_ns(struct ns_common *ns) +{ + return ERR_PTR(-EINVAL); +} #endif /* CONFIG_NET_NS */ diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 7d6687618d80..d1b327036ae4 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -289,6 +289,9 @@ struct sockaddr_in { /* Address indicating an error return. */ #define INADDR_NONE ((unsigned long int) 0xffffffff) +/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */ +#define INADDR_DUMMY ((unsigned long int) 0xc0000008) + /* Network number for local host loopback. */ #define IN_LOOPBACKNET 127 diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9e600767803b..2423b4e918b9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5937,6 +5937,27 @@ struct bpf_sanitize_info { bool mask_to_left; }; +static struct bpf_verifier_state * +sanitize_speculative_path(struct bpf_verifier_env *env, + const struct bpf_insn *insn, + u32 next_idx, u32 curr_idx) +{ + struct bpf_verifier_state *branch; + struct bpf_reg_state *regs; + + branch = push_stack(env, next_idx, curr_idx, true); + if (branch && insn) { + regs = branch->frame[branch->curframe]->regs; + if (BPF_SRC(insn->code) == BPF_K) { + mark_reg_unknown(env, regs, insn->dst_reg); + } else if (BPF_SRC(insn->code) == BPF_X) { + mark_reg_unknown(env, regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->src_reg); + } + } + return branch; +} + static int sanitize_ptr_alu(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, @@ -6020,12 +6041,26 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, tmp = *dst_reg; *dst_reg = *ptr_reg; } - ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true); + ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1, + env->insn_idx); if (!ptr_is_dst_reg && ret) *dst_reg = tmp; return !ret ? REASON_STACK : 0; } +static void sanitize_mark_insn_seen(struct bpf_verifier_env *env) +{ + struct bpf_verifier_state *vstate = env->cur_state; + + /* If we simulate paths under speculation, we don't update the + * insn as 'seen' such that when we verify unreachable paths in + * the non-speculative domain, sanitize_dead_code() can still + * rewrite/sanitize them. + */ + if (!vstate->speculative) + env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; +} + static int sanitize_err(struct bpf_verifier_env *env, const struct bpf_insn *insn, int reason, const struct bpf_reg_state *off_reg, @@ -8204,14 +8239,28 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, if (err) return err; } + if (pred == 1) { - /* only follow the goto, ignore fall-through */ + /* Only follow the goto, ignore fall-through. If needed, push + * the fall-through branch for simulation under speculative + * execution. + */ + if (!env->bypass_spec_v1 && + !sanitize_speculative_path(env, insn, *insn_idx + 1, + *insn_idx)) + return -EFAULT; *insn_idx += insn->off; return 0; } else if (pred == 0) { - /* only follow fall-through branch, since - * that's where the program will go + /* Only follow the fall-through branch, since that's where the + * program will go. If needed, push the goto branch for + * simulation under speculative execution. */ + if (!env->bypass_spec_v1 && + !sanitize_speculative_path(env, insn, + *insn_idx + insn->off + 1, + *insn_idx)) + return -EFAULT; return 0; } @@ -10060,7 +10109,7 @@ static int do_check(struct bpf_verifier_env *env) } regs = cur_regs(env); - env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; + sanitize_mark_insn_seen(env); prev_insn_idx = env->insn_idx; if (class == BPF_ALU || class == BPF_ALU64) { @@ -10285,7 +10334,7 @@ static int do_check(struct bpf_verifier_env *env) return err; env->insn_idx++; - env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; + sanitize_mark_insn_seen(env); } else { verbose(env, "invalid BPF_LD mode\n"); return -EINVAL; @@ -10784,6 +10833,7 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, { struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data; struct bpf_insn *insn = new_prog->insnsi; + u32 old_seen = old_data[off].seen; u32 prog_len; int i; @@ -10804,7 +10854,8 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, memcpy(new_data + off + cnt - 1, old_data + off, sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); for (i = off; i < off + cnt - 1; i++) { - new_data[i].seen = env->pass_cnt; + /* Expand insni[off]'s seen count to the patched range. */ + new_data[i].seen = old_seen; new_data[i].zext_dst = insn_has_def32(env, insn + i); } env->insn_aux_data = new_data; @@ -12060,6 +12111,9 @@ static void free_states(struct bpf_verifier_env *env) * insn_aux_data was touched. These variables are compared to clear temporary * data from failed pass. For testing and experiments do_check_common() can be * run multiple times even when prior attempt to verify is unsuccessful. + * + * Note that special handling is needed on !env->bypass_spec_v1 if this is + * ever called outside of error path with subsequent program rejection. */ static void sanitize_insn_aux_data(struct bpf_verifier_env *env) { diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 825284baaf46..684a6061a13a 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -464,6 +464,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); VMCOREINFO_STRUCT_SIZE(mem_section); VMCOREINFO_OFFSET(mem_section, section_mem_map); + VMCOREINFO_NUMBER(SECTION_SIZE_BITS); VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS); #endif VMCOREINFO_STRUCT_SIZE(page); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 487312a5ceab..47fcc3fe9dc5 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3760,11 +3760,17 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s */ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { + /* + * cfs_rq->avg.period_contrib can be used for both cfs_rq and se. + * See ___update_load_avg() for details. + */ + u32 divider = get_pelt_divider(&cfs_rq->avg); + dequeue_load_avg(cfs_rq, se); sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg); - sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum); + cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider; sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg); - sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum); + cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider; add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f2d4ee80feb3..7c8151d74faf 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2198,9 +2198,6 @@ struct saved_cmdlines_buffer { }; static struct saved_cmdlines_buffer *savedcmd; -/* temporary disable recording */ -static atomic_t trace_record_taskinfo_disabled __read_mostly; - static inline char *get_saved_cmdlines(int idx) { return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN]; @@ -2486,8 +2483,6 @@ static bool tracing_record_taskinfo_skip(int flags) { if (unlikely(!(flags & (TRACE_RECORD_CMDLINE | TRACE_RECORD_TGID)))) return true; - if (atomic_read(&trace_record_taskinfo_disabled) || !tracing_is_on()) - return true; if (!__this_cpu_read(trace_taskinfo_save)) return true; return false; @@ -3742,9 +3737,6 @@ static void *s_start(struct seq_file *m, loff_t *pos) return ERR_PTR(-EBUSY); #endif - if (!iter->snapshot) - atomic_inc(&trace_record_taskinfo_disabled); - if (*pos != iter->pos) { iter->ent = NULL; iter->cpu = 0; @@ -3787,9 +3779,6 @@ static void s_stop(struct seq_file *m, void *p) return; #endif - if (!iter->snapshot) - atomic_dec(&trace_record_taskinfo_disabled); - trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); } diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index c1637f90c8a3..4702efb00ff2 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -115,9 +115,9 @@ u64 notrace trace_clock_global(void) prev_time = READ_ONCE(trace_clock_struct.prev_time); now = sched_clock_cpu(this_cpu); - /* Make sure that now is always greater than prev_time */ + /* Make sure that now is always greater than or equal to prev_time */ if ((s64)(now - prev_time) < 0) - now = prev_time + 1; + now = prev_time; /* * If in an NMI context then dont risk lockups and simply return @@ -131,7 +131,7 @@ u64 notrace trace_clock_global(void) /* Reread prev_time in case it was already updated */ prev_time = READ_ONCE(trace_clock_struct.prev_time); if ((s64)(now - prev_time) < 0) - now = prev_time + 1; + now = prev_time; trace_clock_struct.prev_time = now; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ce63ec0187c5..3da4817190f3 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2127,12 +2127,18 @@ static void return_unused_surplus_pages(struct hstate *h, * be restored when a newly allocated huge page must be freed. It is * to be called after calling vma_needs_reservation to determine if a * reservation exists. + * + * vma_del_reservation is used in error paths where an entry in the reserve + * map was created during huge page allocation and must be removed. It is to + * be called after calling vma_needs_reservation to determine if a reservation + * exists. */ enum vma_resv_mode { VMA_NEEDS_RESV, VMA_COMMIT_RESV, VMA_END_RESV, VMA_ADD_RESV, + VMA_DEL_RESV, }; static long __vma_reservation_common(struct hstate *h, struct vm_area_struct *vma, unsigned long addr, @@ -2176,11 +2182,21 @@ static long __vma_reservation_common(struct hstate *h, ret = region_del(resv, idx, idx + 1); } break; + case VMA_DEL_RESV: + if (vma->vm_flags & VM_MAYSHARE) { + region_abort(resv, idx, idx + 1, 1); + ret = region_del(resv, idx, idx + 1); + } else { + ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); + /* region_add calls of range 1 should never fail. */ + VM_BUG_ON(ret < 0); + } + break; default: BUG(); } - if (vma->vm_flags & VM_MAYSHARE) + if (vma->vm_flags & VM_MAYSHARE || mode == VMA_DEL_RESV) return ret; else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && ret >= 0) { /* @@ -2229,25 +2245,39 @@ static long vma_add_reservation(struct hstate *h, return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV); } +static long vma_del_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) +{ + return __vma_reservation_common(h, vma, addr, VMA_DEL_RESV); +} + /* - * This routine is called to restore a reservation on error paths. In the - * specific error paths, a huge page was allocated (via alloc_huge_page) - * and is about to be freed. If a reservation for the page existed, - * alloc_huge_page would have consumed the reservation and set - * HPageRestoreReserve in the newly allocated page. When the page is freed - * via free_huge_page, the global reservation count will be incremented if - * HPageRestoreReserve is set. However, free_huge_page can not adjust the - * reserve map. Adjust the reserve map here to be consistent with global - * reserve count adjustments to be made by free_huge_page. + * This routine is called to restore reservation information on error paths. + * It should ONLY be called for pages allocated via alloc_huge_page(), and + * the hugetlb mutex should remain held when calling this routine. + * + * It handles two specific cases: + * 1) A reservation was in place and the page consumed the reservation. + * HPageRestoreReserve is set in the page. + * 2) No reservation was in place for the page, so HPageRestoreReserve is + * not set. However, alloc_huge_page always updates the reserve map. + * + * In case 1, free_huge_page later in the error path will increment the + * global reserve count. But, free_huge_page does not have enough context + * to adjust the reservation map. This case deals primarily with private + * mappings. Adjust the reserve map here to be consistent with global + * reserve count adjustments to be made by free_huge_page. Make sure the + * reserve map indicates there is a reservation present. + * + * In case 2, simply undo reserve map modifications done by alloc_huge_page. */ -static void restore_reserve_on_error(struct hstate *h, - struct vm_area_struct *vma, unsigned long address, - struct page *page) +void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, + unsigned long address, struct page *page) { - if (unlikely(HPageRestoreReserve(page))) { - long rc = vma_needs_reservation(h, vma, address); + long rc = vma_needs_reservation(h, vma, address); - if (unlikely(rc < 0)) { + if (HPageRestoreReserve(page)) { + if (unlikely(rc < 0)) /* * Rare out of memory condition in reserve map * manipulation. Clear HPageRestoreReserve so that @@ -2260,16 +2290,57 @@ static void restore_reserve_on_error(struct hstate *h, * accounting of reserve counts. */ ClearHPageRestoreReserve(page); - } else if (rc) { - rc = vma_add_reservation(h, vma, address); - if (unlikely(rc < 0)) + else if (rc) + (void)vma_add_reservation(h, vma, address); + else + vma_end_reservation(h, vma, address); + } else { + if (!rc) { + /* + * This indicates there is an entry in the reserve map + * added by alloc_huge_page. We know it was added + * before the alloc_huge_page call, otherwise + * HPageRestoreReserve would be set on the page. + * Remove the entry so that a subsequent allocation + * does not consume a reservation. + */ + rc = vma_del_reservation(h, vma, address); + if (rc < 0) /* - * See above comment about rare out of - * memory condition. + * VERY rare out of memory condition. Since + * we can not delete the entry, set + * HPageRestoreReserve so that the reserve + * count will be incremented when the page + * is freed. This reserve will be consumed + * on a subsequent allocation. */ - ClearHPageRestoreReserve(page); + SetHPageRestoreReserve(page); + } else if (rc < 0) { + /* + * Rare out of memory condition from + * vma_needs_reservation call. Memory allocation is + * only attempted if a new entry is needed. Therefore, + * this implies there is not an entry in the + * reserve map. + * + * For shared mappings, no entry in the map indicates + * no reservation. We are done. + */ + if (!(vma->vm_flags & VM_MAYSHARE)) + /* + * For private mappings, no entry indicates + * a reservation is present. Since we can + * not add an entry, set SetHPageRestoreReserve + * on the page so reserve count will be + * incremented when freed. This reserve will + * be consumed on a subsequent allocation. + */ + SetHPageRestoreReserve(page); } else - vma_end_reservation(h, vma, address); + /* + * No reservation present, do nothing + */ + vma_end_reservation(h, vma, address); } } @@ -3886,6 +3957,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); if (!pte_same(src_pte_old, entry)) { + restore_reserve_on_error(h, vma, addr, + new); put_page(new); /* dst_entry won't change as in child */ goto again; @@ -4820,6 +4893,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, if (vm_shared) unlock_page(page); out_release_nounlock: + restore_reserve_on_error(h, dst_vma, dst_addr, page); put_page(page); goto out; } @@ -5664,6 +5738,21 @@ bool isolate_huge_page(struct page *page, struct list_head *list) return ret; } +int get_hwpoison_huge_page(struct page *page, bool *hugetlb) +{ + int ret = 0; + + *hugetlb = false; + spin_lock_irq(&hugetlb_lock); + if (PageHeadHuge(page)) { + *hugetlb = true; + if (HPageFreed(page) || HPageMigratable(page)) + ret = get_page_unless_zero(page); + } + spin_unlock_irq(&hugetlb_lock); + return ret; +} + void putback_active_hugepage(struct page *page) { spin_lock(&hugetlb_lock); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index bd3945446d47..704d05057d8c 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -949,6 +949,17 @@ static int page_action(struct page_state *ps, struct page *p, return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY; } +/* + * Return true if a page type of a given page is supported by hwpoison + * mechanism (while handling could fail), otherwise false. This function + * does not return true for hugetlb or device memory pages, so it's assumed + * to be called only in the context where we never have such pages. + */ +static inline bool HWPoisonHandlable(struct page *page) +{ + return PageLRU(page) || __PageMovable(page); +} + /** * __get_hwpoison_page() - Get refcount for memory error handling: * @page: raw error page (hit by memory error) @@ -959,8 +970,22 @@ static int page_action(struct page_state *ps, struct page *p, static int __get_hwpoison_page(struct page *page) { struct page *head = compound_head(page); + int ret = 0; + bool hugetlb = false; + + ret = get_hwpoison_huge_page(head, &hugetlb); + if (hugetlb) + return ret; - if (!PageHuge(head) && PageTransHuge(head)) { + /* + * This check prevents from calling get_hwpoison_unless_zero() + * for any unsupported type of page in order to reduce the risk of + * unexpected races caused by taking a page refcount. + */ + if (!HWPoisonHandlable(head)) + return 0; + + if (PageTransHuge(head)) { /* * Non anonymous thp exists only in allocation/free time. We * can't handle such a case correctly, so let's give it up. @@ -1017,7 +1042,7 @@ static int get_any_page(struct page *p, unsigned long flags) ret = -EIO; } } else { - if (PageHuge(p) || PageLRU(p) || __PageMovable(p)) { + if (PageHuge(p) || HWPoisonHandlable(p)) { ret = 1; } else { /* @@ -1527,7 +1552,12 @@ int memory_failure(unsigned long pfn, int flags) return 0; } - if (!PageTransTail(p) && !PageLRU(p)) + /* + * __munlock_pagevec may clear a writeback page's LRU flag without + * page_lock. We need wait writeback completion for this page or it + * may trigger vfs BUG while evict inode. + */ + if (!PageTransTail(p) && !PageLRU(p) && !PageWriteback(p)) goto identify_page_state; /* diff --git a/mm/slab_common.c b/mm/slab_common.c index 88e833986332..ba2f4b01920f 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -89,8 +89,7 @@ EXPORT_SYMBOL(kmem_cache_size); #ifdef CONFIG_DEBUG_VM static int kmem_cache_sanity_check(const char *name, unsigned int size) { - if (!name || in_interrupt() || size < sizeof(void *) || - size > KMALLOC_MAX_SIZE) { + if (!name || in_interrupt() || size > KMALLOC_MAX_SIZE) { pr_err("kmem_cache_create(%s) integrity check failed\n", name); return -EINVAL; } diff --git a/mm/slub.c b/mm/slub.c index 3021ce9bf1b3..602f9712ab53 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -15,6 +15,7 @@ #include <linux/module.h> #include <linux/bit_spinlock.h> #include <linux/interrupt.h> +#include <linux/swab.h> #include <linux/bitops.h> #include <linux/slab.h> #include "slab.h" @@ -710,15 +711,15 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) p, p - addr, get_freepointer(s, p)); if (s->flags & SLAB_RED_ZONE) - print_section(KERN_ERR, "Redzone ", p - s->red_left_pad, + print_section(KERN_ERR, "Redzone ", p - s->red_left_pad, s->red_left_pad); else if (p > addr + 16) print_section(KERN_ERR, "Bytes b4 ", p - 16, 16); - print_section(KERN_ERR, "Object ", p, + print_section(KERN_ERR, "Object ", p, min_t(unsigned int, s->object_size, PAGE_SIZE)); if (s->flags & SLAB_RED_ZONE) - print_section(KERN_ERR, "Redzone ", p + s->object_size, + print_section(KERN_ERR, "Redzone ", p + s->object_size, s->inuse - s->object_size); off = get_info_end(s); @@ -730,7 +731,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) if (off != size_from_object(s)) /* Beginning of the filler is the free pointer */ - print_section(KERN_ERR, "Padding ", p + off, + print_section(KERN_ERR, "Padding ", p + off, size_from_object(s) - off); dump_stack(); @@ -907,11 +908,11 @@ static int check_object(struct kmem_cache *s, struct page *page, u8 *endobject = object + s->object_size; if (s->flags & SLAB_RED_ZONE) { - if (!check_bytes_and_report(s, page, object, "Redzone", + if (!check_bytes_and_report(s, page, object, "Left Redzone", object - s->red_left_pad, val, s->red_left_pad)) return 0; - if (!check_bytes_and_report(s, page, object, "Redzone", + if (!check_bytes_and_report(s, page, object, "Right Redzone", endobject, val, s->inuse - s->object_size)) return 0; } else { @@ -926,7 +927,7 @@ static int check_object(struct kmem_cache *s, struct page *page, if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) && (!check_bytes_and_report(s, page, p, "Poison", p, POISON_FREE, s->object_size - 1) || - !check_bytes_and_report(s, page, p, "Poison", + !check_bytes_and_report(s, page, p, "End Poison", p + s->object_size - 1, POISON_END, 1))) return 0; /* @@ -3687,7 +3688,6 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) { slab_flags_t flags = s->flags; unsigned int size = s->object_size; - unsigned int freepointer_area; unsigned int order; /* @@ -3696,13 +3696,6 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * the possible location of the free pointer. */ size = ALIGN(size, sizeof(void *)); - /* - * This is the area of the object where a freepointer can be - * safely written. If redzoning adds more to the inuse size, we - * can't use that portion for writing the freepointer, so - * s->offset must be limited within this for the general case. - */ - freepointer_area = size; #ifdef CONFIG_SLUB_DEBUG /* @@ -3728,19 +3721,21 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) /* * With that we have determined the number of bytes in actual use - * by the object. This is the potential offset to the free pointer. + * by the object and redzoning. */ s->inuse = size; - if (((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) || - s->ctor)) { + if ((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) || + ((flags & SLAB_RED_ZONE) && s->object_size < sizeof(void *)) || + s->ctor) { /* * Relocate free pointer after the object if it is not * permitted to overwrite the first word of the object on * kmem_cache_free. * * This is the case if we do RCU, have a constructor or - * destructor or are poisoning the objects. + * destructor, are poisoning the objects, or are + * redzoning an object smaller than sizeof(void *). * * The assumption that s->offset >= s->inuse means free * pointer is outside of the object is used in the @@ -3749,13 +3744,13 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) */ s->offset = size; size += sizeof(void *); - } else if (freepointer_area > sizeof(void *)) { + } else { /* * Store freelist pointer near middle of object to keep * it away from the edges of the object to avoid small * sized over/underflows from neighboring allocations. */ - s->offset = ALIGN(freepointer_area / 2, sizeof(void *)); + s->offset = ALIGN_DOWN(s->object_size / 2, sizeof(void *)); } #ifdef CONFIG_SLUB_DEBUG diff --git a/mm/swapfile.c b/mm/swapfile.c index 084a5b9a18e5..2097648df212 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1900,7 +1900,7 @@ unsigned int count_swap_pages(int type, int free) static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { - return pte_same(pte_swp_clear_soft_dirty(pte), swp_pte); + return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index a5e313cd6f44..b9dd150f6f01 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -409,8 +409,10 @@ static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet) if (WARN_ON(!forw_packet->if_outgoing)) return; - if (WARN_ON(forw_packet->if_outgoing->soft_iface != soft_iface)) + if (forw_packet->if_outgoing->soft_iface != soft_iface) { + pr_warn("%s: soft interface switch for queued OGM\n", __func__); return; + } if (forw_packet->if_incoming->if_status != BATADV_IF_ACTIVE) return; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index af3430c2d6ea..660dec6785ad 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -90,8 +90,8 @@ struct bridge_mcast_stats { #endif struct br_tunnel_info { - __be64 tunnel_id; - struct metadata_dst *tunnel_dst; + __be64 tunnel_id; + struct metadata_dst __rcu *tunnel_dst; }; /* private vlan flags */ diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c index 169e005fbda2..debe16720278 100644 --- a/net/bridge/br_vlan_tunnel.c +++ b/net/bridge/br_vlan_tunnel.c @@ -41,26 +41,33 @@ static struct net_bridge_vlan *br_vlan_tunnel_lookup(struct rhashtable *tbl, br_vlan_tunnel_rht_params); } +static void vlan_tunnel_info_release(struct net_bridge_vlan *vlan) +{ + struct metadata_dst *tdst = rtnl_dereference(vlan->tinfo.tunnel_dst); + + WRITE_ONCE(vlan->tinfo.tunnel_id, 0); + RCU_INIT_POINTER(vlan->tinfo.tunnel_dst, NULL); + dst_release(&tdst->dst); +} + void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan) { - if (!vlan->tinfo.tunnel_dst) + if (!rcu_access_pointer(vlan->tinfo.tunnel_dst)) return; rhashtable_remove_fast(&vg->tunnel_hash, &vlan->tnode, br_vlan_tunnel_rht_params); - vlan->tinfo.tunnel_id = 0; - dst_release(&vlan->tinfo.tunnel_dst->dst); - vlan->tinfo.tunnel_dst = NULL; + vlan_tunnel_info_release(vlan); } static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan, u32 tun_id) { - struct metadata_dst *metadata = NULL; + struct metadata_dst *metadata = rtnl_dereference(vlan->tinfo.tunnel_dst); __be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id)); int err; - if (vlan->tinfo.tunnel_dst) + if (metadata) return -EEXIST; metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY, @@ -69,8 +76,8 @@ static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, return -EINVAL; metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_BRIDGE; - vlan->tinfo.tunnel_dst = metadata; - vlan->tinfo.tunnel_id = key; + rcu_assign_pointer(vlan->tinfo.tunnel_dst, metadata); + WRITE_ONCE(vlan->tinfo.tunnel_id, key); err = rhashtable_lookup_insert_fast(&vg->tunnel_hash, &vlan->tnode, br_vlan_tunnel_rht_params); @@ -79,9 +86,7 @@ static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, return 0; out: - dst_release(&vlan->tinfo.tunnel_dst->dst); - vlan->tinfo.tunnel_dst = NULL; - vlan->tinfo.tunnel_id = 0; + vlan_tunnel_info_release(vlan); return err; } @@ -182,12 +187,15 @@ int br_handle_ingress_vlan_tunnel(struct sk_buff *skb, int br_handle_egress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan *vlan) { + struct metadata_dst *tunnel_dst; + __be64 tunnel_id; int err; - if (!vlan || !vlan->tinfo.tunnel_id) + if (!vlan) return 0; - if (unlikely(!skb_vlan_tag_present(skb))) + tunnel_id = READ_ONCE(vlan->tinfo.tunnel_id); + if (!tunnel_id || unlikely(!skb_vlan_tag_present(skb))) return 0; skb_dst_drop(skb); @@ -195,7 +203,9 @@ int br_handle_egress_vlan_tunnel(struct sk_buff *skb, if (err) return err; - skb_dst_set(skb, dst_clone(&vlan->tinfo.tunnel_dst->dst)); + tunnel_dst = rcu_dereference(vlan->tinfo.tunnel_dst); + if (tunnel_dst && dst_hold_safe(&tunnel_dst->dst)) + skb_dst_set(skb, &tunnel_dst->dst); return 0; } diff --git a/net/can/bcm.c b/net/can/bcm.c index 909b9e684e04..f3e4d9528fa3 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -125,7 +125,7 @@ struct bcm_sock { struct sock sk; int bound; int ifindex; - struct notifier_block notifier; + struct list_head notifier; struct list_head rx_ops; struct list_head tx_ops; unsigned long dropped_usr_msgs; @@ -133,6 +133,10 @@ struct bcm_sock { char procname [32]; /* inode number in decimal with \0 */ }; +static LIST_HEAD(bcm_notifier_list); +static DEFINE_SPINLOCK(bcm_notifier_lock); +static struct bcm_sock *bcm_busy_notifier; + static inline struct bcm_sock *bcm_sk(const struct sock *sk) { return (struct bcm_sock *)sk; @@ -402,6 +406,7 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) if (!op->count && (op->flags & TX_COUNTEVT)) { /* create notification to user */ + memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = TX_EXPIRED; msg_head.flags = op->flags; msg_head.count = op->count; @@ -439,6 +444,7 @@ static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data) /* this element is not throttled anymore */ data->flags &= (BCM_CAN_FLAGS_MASK|RX_RECV); + memset(&head, 0, sizeof(head)); head.opcode = RX_CHANGED; head.flags = op->flags; head.count = op->count; @@ -560,6 +566,7 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) } /* create notification to user */ + memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = RX_TIMEOUT; msg_head.flags = op->flags; msg_head.count = op->count; @@ -1378,20 +1385,15 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) /* * notification handler for netdevice status changes */ -static int bcm_notifier(struct notifier_block *nb, unsigned long msg, - void *ptr) +static void bcm_notify(struct bcm_sock *bo, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct bcm_sock *bo = container_of(nb, struct bcm_sock, notifier); struct sock *sk = &bo->sk; struct bcm_op *op; int notify_enodev = 0; if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return; switch (msg) { @@ -1426,7 +1428,28 @@ static int bcm_notifier(struct notifier_block *nb, unsigned long msg, sk->sk_error_report(sk); } } +} +static int bcm_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(bcm_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + + spin_lock(&bcm_notifier_lock); + list_for_each_entry(bcm_busy_notifier, &bcm_notifier_list, notifier) { + spin_unlock(&bcm_notifier_lock); + bcm_notify(bcm_busy_notifier, msg, dev); + spin_lock(&bcm_notifier_lock); + } + bcm_busy_notifier = NULL; + spin_unlock(&bcm_notifier_lock); return NOTIFY_DONE; } @@ -1446,9 +1469,9 @@ static int bcm_init(struct sock *sk) INIT_LIST_HEAD(&bo->rx_ops); /* set notifier */ - bo->notifier.notifier_call = bcm_notifier; - - register_netdevice_notifier(&bo->notifier); + spin_lock(&bcm_notifier_lock); + list_add_tail(&bo->notifier, &bcm_notifier_list); + spin_unlock(&bcm_notifier_lock); return 0; } @@ -1471,7 +1494,14 @@ static int bcm_release(struct socket *sock) /* remove bcm_ops, timer, rx_unregister(), etc. */ - unregister_netdevice_notifier(&bo->notifier); + spin_lock(&bcm_notifier_lock); + while (bcm_busy_notifier == bo) { + spin_unlock(&bcm_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&bcm_notifier_lock); + } + list_del(&bo->notifier); + spin_unlock(&bcm_notifier_lock); lock_sock(sk); @@ -1692,6 +1722,10 @@ static struct pernet_operations canbcm_pernet_ops __read_mostly = { .exit = canbcm_pernet_exit, }; +static struct notifier_block canbcm_notifier = { + .notifier_call = bcm_notifier +}; + static int __init bcm_module_init(void) { int err; @@ -1705,12 +1739,14 @@ static int __init bcm_module_init(void) } register_pernet_subsys(&canbcm_pernet_ops); + register_netdevice_notifier(&canbcm_notifier); return 0; } static void __exit bcm_module_exit(void) { can_proto_unregister(&bcm_can_proto); + unregister_netdevice_notifier(&canbcm_notifier); unregister_pernet_subsys(&canbcm_pernet_ops); } diff --git a/net/can/isotp.c b/net/can/isotp.c index 253b24417c8e..be6183f8ca11 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -143,10 +143,14 @@ struct isotp_sock { u32 force_tx_stmin; u32 force_rx_stmin; struct tpcon rx, tx; - struct notifier_block notifier; + struct list_head notifier; wait_queue_head_t wait; }; +static LIST_HEAD(isotp_notifier_list); +static DEFINE_SPINLOCK(isotp_notifier_lock); +static struct isotp_sock *isotp_busy_notifier; + static inline struct isotp_sock *isotp_sk(const struct sock *sk) { return (struct isotp_sock *)sk; @@ -1013,7 +1017,14 @@ static int isotp_release(struct socket *sock) /* wait for complete transmission of current pdu */ wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); - unregister_netdevice_notifier(&so->notifier); + spin_lock(&isotp_notifier_lock); + while (isotp_busy_notifier == so) { + spin_unlock(&isotp_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&isotp_notifier_lock); + } + list_del(&so->notifier); + spin_unlock(&isotp_notifier_lock); lock_sock(sk); @@ -1317,21 +1328,16 @@ static int isotp_getsockopt(struct socket *sock, int level, int optname, return 0; } -static int isotp_notifier(struct notifier_block *nb, unsigned long msg, - void *ptr) +static void isotp_notify(struct isotp_sock *so, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct isotp_sock *so = container_of(nb, struct isotp_sock, notifier); struct sock *sk = &so->sk; if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return; if (so->ifindex != dev->ifindex) - return NOTIFY_DONE; + return; switch (msg) { case NETDEV_UNREGISTER: @@ -1357,7 +1363,28 @@ static int isotp_notifier(struct notifier_block *nb, unsigned long msg, sk->sk_error_report(sk); break; } +} +static int isotp_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(isotp_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + + spin_lock(&isotp_notifier_lock); + list_for_each_entry(isotp_busy_notifier, &isotp_notifier_list, notifier) { + spin_unlock(&isotp_notifier_lock); + isotp_notify(isotp_busy_notifier, msg, dev); + spin_lock(&isotp_notifier_lock); + } + isotp_busy_notifier = NULL; + spin_unlock(&isotp_notifier_lock); return NOTIFY_DONE; } @@ -1394,8 +1421,9 @@ static int isotp_init(struct sock *sk) init_waitqueue_head(&so->wait); - so->notifier.notifier_call = isotp_notifier; - register_netdevice_notifier(&so->notifier); + spin_lock(&isotp_notifier_lock); + list_add_tail(&so->notifier, &isotp_notifier_list); + spin_unlock(&isotp_notifier_lock); return 0; } @@ -1442,6 +1470,10 @@ static const struct can_proto isotp_can_proto = { .prot = &isotp_proto, }; +static struct notifier_block canisotp_notifier = { + .notifier_call = isotp_notifier +}; + static __init int isotp_module_init(void) { int err; @@ -1451,6 +1483,8 @@ static __init int isotp_module_init(void) err = can_proto_register(&isotp_can_proto); if (err < 0) pr_err("can: registration of isotp protocol failed\n"); + else + register_netdevice_notifier(&canisotp_notifier); return err; } @@ -1458,6 +1492,7 @@ static __init int isotp_module_init(void) static __exit void isotp_module_exit(void) { can_proto_unregister(&isotp_can_proto); + unregister_netdevice_notifier(&canisotp_notifier); } module_init(isotp_module_init); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index e09d087ba240..c3946c355882 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -330,6 +330,9 @@ static void j1939_session_skb_drop_old(struct j1939_session *session) if ((do_skcb->offset + do_skb->len) < offset_start) { __skb_unlink(do_skb, &session->skb_queue); + /* drop ref taken in j1939_session_skb_queue() */ + skb_unref(do_skb); + kfree_skb(do_skb); } spin_unlock_irqrestore(&session->skb_queue.lock, flags); @@ -349,12 +352,13 @@ void j1939_session_skb_queue(struct j1939_session *session, skcb->flags |= J1939_ECU_LOCAL_SRC; + skb_get(skb); skb_queue_tail(&session->skb_queue, skb); } static struct -sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session, - unsigned int offset_start) +sk_buff *j1939_session_skb_get_by_offset(struct j1939_session *session, + unsigned int offset_start) { struct j1939_priv *priv = session->priv; struct j1939_sk_buff_cb *do_skcb; @@ -371,6 +375,10 @@ sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session, skb = do_skb; } } + + if (skb) + skb_get(skb); + spin_unlock_irqrestore(&session->skb_queue.lock, flags); if (!skb) @@ -381,12 +389,12 @@ sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session, return skb; } -static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) +static struct sk_buff *j1939_session_skb_get(struct j1939_session *session) { unsigned int offset_start; offset_start = session->pkt.dpo * 7; - return j1939_session_skb_find_by_offset(session, offset_start); + return j1939_session_skb_get_by_offset(session, offset_start); } /* see if we are receiver @@ -776,7 +784,7 @@ static int j1939_session_tx_dat(struct j1939_session *session) int ret = 0; u8 dat[8]; - se_skb = j1939_session_skb_find_by_offset(session, session->pkt.tx * 7); + se_skb = j1939_session_skb_get_by_offset(session, session->pkt.tx * 7); if (!se_skb) return -ENOBUFS; @@ -801,7 +809,8 @@ static int j1939_session_tx_dat(struct j1939_session *session) netdev_err_once(priv->ndev, "%s: 0x%p: requested data outside of queued buffer: offset %i, len %i, pkt.tx: %i\n", __func__, session, skcb->offset, se_skb->len , session->pkt.tx); - return -EOVERFLOW; + ret = -EOVERFLOW; + goto out_free; } if (!len) { @@ -835,6 +844,12 @@ static int j1939_session_tx_dat(struct j1939_session *session) if (pkt_done) j1939_tp_set_rxtimeout(session, 250); + out_free: + if (ret) + kfree_skb(se_skb); + else + consume_skb(se_skb); + return ret; } @@ -1007,7 +1022,7 @@ static int j1939_xtp_txnext_receiver(struct j1939_session *session) static int j1939_simple_txnext(struct j1939_session *session) { struct j1939_priv *priv = session->priv; - struct sk_buff *se_skb = j1939_session_skb_find(session); + struct sk_buff *se_skb = j1939_session_skb_get(session); struct sk_buff *skb; int ret; @@ -1015,8 +1030,10 @@ static int j1939_simple_txnext(struct j1939_session *session) return 0; skb = skb_clone(se_skb, GFP_ATOMIC); - if (!skb) - return -ENOMEM; + if (!skb) { + ret = -ENOMEM; + goto out_free; + } can_skb_set_owner(skb, se_skb->sk); @@ -1024,12 +1041,18 @@ static int j1939_simple_txnext(struct j1939_session *session) ret = j1939_send_one(priv, skb); if (ret) - return ret; + goto out_free; j1939_sk_errqueue(session, J1939_ERRQUEUE_SCHED); j1939_sk_queue_activate_next(session); - return 0; + out_free: + if (ret) + kfree_skb(se_skb); + else + consume_skb(se_skb); + + return ret; } static bool j1939_session_deactivate_locked(struct j1939_session *session) @@ -1170,9 +1193,10 @@ static void j1939_session_completed(struct j1939_session *session) struct sk_buff *skb; if (!session->transmission) { - skb = j1939_session_skb_find(session); + skb = j1939_session_skb_get(session); /* distribute among j1939 receivers */ j1939_sk_recv(session->priv, skb); + consume_skb(skb); } j1939_session_deactivate_activate_next(session); @@ -1744,7 +1768,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, { struct j1939_priv *priv = session->priv; struct j1939_sk_buff_cb *skcb; - struct sk_buff *se_skb; + struct sk_buff *se_skb = NULL; const u8 *dat; u8 *tpdat; int offset; @@ -1786,7 +1810,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, goto out_session_cancel; } - se_skb = j1939_session_skb_find_by_offset(session, packet * 7); + se_skb = j1939_session_skb_get_by_offset(session, packet * 7); if (!se_skb) { netdev_warn(priv->ndev, "%s: 0x%p: no skb found\n", __func__, session); @@ -1848,11 +1872,13 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, j1939_tp_set_rxtimeout(session, 250); } session->last_cmd = 0xff; + consume_skb(se_skb); j1939_session_put(session); return; out_session_cancel: + kfree_skb(se_skb); j1939_session_timers_cancel(session); j1939_session_cancel(session, J1939_XTP_ABORT_FAULT); j1939_session_put(session); diff --git a/net/can/raw.c b/net/can/raw.c index 139d9471ddcf..ac96fc210025 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -83,7 +83,7 @@ struct raw_sock { struct sock sk; int bound; int ifindex; - struct notifier_block notifier; + struct list_head notifier; int loopback; int recv_own_msgs; int fd_frames; @@ -95,6 +95,10 @@ struct raw_sock { struct uniqframe __percpu *uniq; }; +static LIST_HEAD(raw_notifier_list); +static DEFINE_SPINLOCK(raw_notifier_lock); +static struct raw_sock *raw_busy_notifier; + /* Return pointer to store the extra msg flags for raw_recvmsg(). * We use the space of one unsigned int beyond the 'struct sockaddr_can' * in skb->cb. @@ -263,21 +267,16 @@ static int raw_enable_allfilters(struct net *net, struct net_device *dev, return err; } -static int raw_notifier(struct notifier_block *nb, - unsigned long msg, void *ptr) +static void raw_notify(struct raw_sock *ro, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct raw_sock *ro = container_of(nb, struct raw_sock, notifier); struct sock *sk = &ro->sk; if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return; if (ro->ifindex != dev->ifindex) - return NOTIFY_DONE; + return; switch (msg) { case NETDEV_UNREGISTER: @@ -305,7 +304,28 @@ static int raw_notifier(struct notifier_block *nb, sk->sk_error_report(sk); break; } +} + +static int raw_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(raw_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + spin_lock(&raw_notifier_lock); + list_for_each_entry(raw_busy_notifier, &raw_notifier_list, notifier) { + spin_unlock(&raw_notifier_lock); + raw_notify(raw_busy_notifier, msg, dev); + spin_lock(&raw_notifier_lock); + } + raw_busy_notifier = NULL; + spin_unlock(&raw_notifier_lock); return NOTIFY_DONE; } @@ -334,9 +354,9 @@ static int raw_init(struct sock *sk) return -ENOMEM; /* set notifier */ - ro->notifier.notifier_call = raw_notifier; - - register_netdevice_notifier(&ro->notifier); + spin_lock(&raw_notifier_lock); + list_add_tail(&ro->notifier, &raw_notifier_list); + spin_unlock(&raw_notifier_lock); return 0; } @@ -351,7 +371,14 @@ static int raw_release(struct socket *sock) ro = raw_sk(sk); - unregister_netdevice_notifier(&ro->notifier); + spin_lock(&raw_notifier_lock); + while (raw_busy_notifier == ro) { + spin_unlock(&raw_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&raw_notifier_lock); + } + list_del(&ro->notifier); + spin_unlock(&raw_notifier_lock); lock_sock(sk); @@ -889,6 +916,10 @@ static const struct can_proto raw_can_proto = { .prot = &raw_proto, }; +static struct notifier_block canraw_notifier = { + .notifier_call = raw_notifier +}; + static __init int raw_module_init(void) { int err; @@ -898,6 +929,8 @@ static __init int raw_module_init(void) err = can_proto_register(&raw_can_proto); if (err < 0) pr_err("can: registration of raw protocol failed\n"); + else + register_netdevice_notifier(&canraw_notifier); return err; } @@ -905,6 +938,7 @@ static __init int raw_module_init(void) static __exit void raw_module_exit(void) { can_proto_unregister(&raw_can_proto); + unregister_netdevice_notifier(&canraw_notifier); } module_init(raw_module_init); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 43b6ac4c4439..cc8dafb25d61 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -641,6 +641,18 @@ void __put_net(struct net *net) } EXPORT_SYMBOL_GPL(__put_net); +/** + * get_net_ns - increment the refcount of the network namespace + * @ns: common namespace (net) + * + * Returns the net's common namespace. + */ +struct ns_common *get_net_ns(struct ns_common *ns) +{ + return &get_net(container_of(ns, struct net, ns))->ns; +} +EXPORT_SYMBOL_GPL(get_net_ns); + struct net *get_net_ns_by_fd(int fd) { struct file *file; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 9ad046917b34..2123427883ba 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4833,10 +4833,12 @@ static int rtnl_bridge_notify(struct net_device *dev) if (err < 0) goto errout; - if (!skb->len) { - err = -EINVAL; + /* Notification info is only filled for bridge ports, not the bridge + * device itself. Therefore, a zero notification length is valid and + * should not result in an error. + */ + if (!skb->len) goto errout; - } rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return 0; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c421c8f80925..7997d99afbd8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1252,6 +1252,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) struct sock *sk = skb->sk; struct sk_buff_head *q; unsigned long flags; + bool is_zerocopy; u32 lo, hi; u16 len; @@ -1266,6 +1267,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) len = uarg->len; lo = uarg->id; hi = uarg->id + len - 1; + is_zerocopy = uarg->zerocopy; serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); @@ -1273,7 +1275,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY; serr->ee.ee_data = hi; serr->ee.ee_info = lo; - if (!uarg->zerocopy) + if (!is_zerocopy) serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED; q = &sk->sk_error_queue; diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index c3a5489964cd..9908b922cce8 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -328,6 +328,8 @@ static int strset_reply_size(const struct ethnl_req_info *req_base, int len = 0; int ret; + len += nla_total_size(0); /* ETHTOOL_A_STRSET_STRINGSETS */ + for (i = 0; i < ETH_SS_COUNT; i++) { const struct strset_info *set_info = &data->sets[i]; diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index bfaf327e9d12..e0480c6cebaa 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -472,6 +472,7 @@ void cipso_v4_doi_free(struct cipso_v4_doi *doi_def) kfree(doi_def->map.std->lvl.local); kfree(doi_def->map.std->cat.cipso); kfree(doi_def->map.std->cat.local); + kfree(doi_def->map.std); break; } kfree(doi_def); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 616e2dc1c8fa..cd65d3146c30 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -759,6 +759,13 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, icmp_param.data_len = room; icmp_param.head_len = sizeof(struct icmphdr); + /* if we don't have a source address at this point, fall back to the + * dummy address instead of sending out a packet with a source address + * of 0.0.0.0 + */ + if (!fl4.saddr) + fl4.saddr = htonl(INADDR_DUMMY); + icmp_push_reply(&icmp_param, &fl4, &ipc, &rt); ende: ip_rt_put(rt); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 7b272bbed2b4..6b3c558a4f23 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1801,6 +1801,7 @@ void ip_mc_destroy_dev(struct in_device *in_dev) while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { in_dev->mc_list = i->next_rcu; in_dev->mc_count--; + ip_mc_clear_src(i); ip_ma_put(i); } } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d635b4f32d34..09506203156d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2081,6 +2081,19 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, return err; } +/* get device for dst_alloc with local routes */ +static struct net_device *ip_rt_get_dev(struct net *net, + const struct fib_result *res) +{ + struct fib_nh_common *nhc = res->fi ? res->nhc : NULL; + struct net_device *dev = NULL; + + if (nhc) + dev = l3mdev_master_dev_rcu(nhc->nhc_dev); + + return dev ? : net->loopback_dev; +} + /* * NOTE. We drop all the packets that has local source * addresses, because every properly looped back packet @@ -2237,7 +2250,7 @@ out: return err; } } - rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev, + rth = rt_dst_alloc(ip_rt_get_dev(net, res), flags | RTCF_LOCAL, res->type, IN_DEV_ORCONF(in_dev, NOPOLICY), false); if (!rth) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c586a6bb8c6d..3dd340679d09 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2576,6 +2576,9 @@ void udp_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); bool slow = lock_sock_fast(sk); + + /* protects from races with udp_abort() */ + sock_set_flag(sk, SOCK_DEAD); udp_flush_pending_frames(sk); unlock_sock_fast(sk, slow); if (static_branch_unlikely(&udp_encap_needed_key)) { @@ -2826,10 +2829,17 @@ int udp_abort(struct sock *sk, int err) { lock_sock(sk); + /* udp{v6}_destroy_sock() sets it under the sk lock, avoid racing + * with close() + */ + if (sock_flag(sk, SOCK_DEAD)) + goto out; + sk->sk_err = err; sk->sk_error_report(sk); __udp_disconnect(sk, 0); +out: release_sock(sk); return 0; diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index e204163c7036..92f3235fa287 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -135,6 +135,17 @@ void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs, } EXPORT_SYMBOL_GPL(nft_fib6_eval_type); +static bool nft_fib_v6_skip_icmpv6(const struct sk_buff *skb, u8 next, const struct ipv6hdr *iph) +{ + if (likely(next != IPPROTO_ICMPV6)) + return false; + + if (ipv6_addr_type(&iph->saddr) != IPV6_ADDR_ANY) + return false; + + return ipv6_addr_type(&iph->daddr) & IPV6_ADDR_LINKLOCAL; +} + void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { @@ -163,10 +174,13 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif, iph); - if (nft_hook(pkt) == NF_INET_PRE_ROUTING && - nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { - nft_fib_store_result(dest, priv, nft_in(pkt)); - return; + if (nft_hook(pkt) == NF_INET_PRE_ROUTING || + nft_hook(pkt) == NF_INET_INGRESS) { + if (nft_fib_is_loopback(pkt->skb, nft_in(pkt)) || + nft_fib_v6_skip_icmpv6(pkt->skb, pkt->tprot, iph)) { + nft_fib_store_result(dest, priv, nft_in(pkt)); + return; + } } *dest = 0; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index d25e5a9252fd..29288f134d7a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1597,6 +1597,9 @@ void udpv6_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); lock_sock(sk); + + /* protects from races with udp_abort() */ + sock_set_flag(sk, SOCK_DEAD); udp_v6_flush_pending_frames(sk); release_sock(sk); diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 5296898875ff..223fbcafd6fc 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -4,7 +4,7 @@ * * Copyright 2007 Johannes Berg <johannes@xxxxxxxxxxxxxxxx> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2018 - 2019 Intel Corporation + * Copyright (C) 2018 - 2019, 2021 Intel Corporation */ #include <linux/debugfs.h> @@ -387,10 +387,17 @@ static ssize_t reset_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct ieee80211_local *local = file->private_data; + int ret; rtnl_lock(); + wiphy_lock(local->hw.wiphy); __ieee80211_suspend(&local->hw, NULL); - __ieee80211_resume(&local->hw); + ret = __ieee80211_resume(&local->hw); + wiphy_unlock(local->hw.wiphy); + + if (ret) + cfg80211_shutdown_all_interfaces(local->hw.wiphy); + rtnl_unlock(); return count; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 6f8885766cba..6ebfd484e61d 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -475,14 +475,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do GFP_KERNEL); } - /* APs need special treatment */ if (sdata->vif.type == NL80211_IFTYPE_AP) { - struct ieee80211_sub_if_data *vlan, *tmpsdata; - - /* down all dependent devices, that is VLANs */ - list_for_each_entry_safe(vlan, tmpsdata, &sdata->u.ap.vlans, - u.vlan.list) - dev_close(vlan->dev); WARN_ON(!list_empty(&sdata->u.ap.vlans)); } else if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { /* remove all packets in parent bc_buf pointing to this dev */ @@ -640,6 +633,15 @@ static int ieee80211_stop(struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + /* close all dependent VLAN interfaces before locking wiphy */ + if (sdata->vif.type == NL80211_IFTYPE_AP) { + struct ieee80211_sub_if_data *vlan, *tmpsdata; + + list_for_each_entry_safe(vlan, tmpsdata, &sdata->u.ap.vlans, + u.vlan.list) + dev_close(vlan->dev); + } + wiphy_lock(sdata->local->hw.wiphy); ieee80211_do_stop(sdata, true); wiphy_unlock(sdata->local->hw.wiphy); @@ -1589,6 +1591,9 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, switch (sdata->vif.type) { case NL80211_IFTYPE_AP: + if (!list_empty(&sdata->u.ap.vlans)) + return -EBUSY; + break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_OCB: diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 0331f3a3c40e..9dd741b68f26 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -252,6 +252,7 @@ static void ieee80211_restart_work(struct work_struct *work) struct ieee80211_local *local = container_of(work, struct ieee80211_local, restart_work); struct ieee80211_sub_if_data *sdata; + int ret; /* wait for scan work complete */ flush_workqueue(local->workqueue); @@ -294,8 +295,12 @@ static void ieee80211_restart_work(struct work_struct *work) /* wait for all packet processing to be done */ synchronize_net(); - ieee80211_reconfig(local); + ret = ieee80211_reconfig(local); wiphy_unlock(local->hw.wiphy); + + if (ret) + cfg80211_shutdown_all_interfaces(local->hw.wiphy); + rtnl_unlock(); } diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index ecad9b10984f..e627a11844a9 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -1516,7 +1516,7 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, (info->control.flags & IEEE80211_TX_CTRL_PORT_CTRL_PROTO)) return; - if (time_is_before_jiffies(mi->sample_time)) + if (time_is_after_jiffies(mi->sample_time)) return; mi->sample_time = jiffies + MINSTREL_SAMPLE_INTERVAL; diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index d4cc9ac2d703..6b50cb5e0e3c 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -251,13 +251,24 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) struct ieee80211_mgmt *mgmt = (void *)skb->data; struct ieee80211_bss *bss; struct ieee80211_channel *channel; + size_t min_hdr_len = offsetof(struct ieee80211_mgmt, + u.probe_resp.variable); + + if (!ieee80211_is_probe_resp(mgmt->frame_control) && + !ieee80211_is_beacon(mgmt->frame_control) && + !ieee80211_is_s1g_beacon(mgmt->frame_control)) + return; if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { - if (skb->len < 15) - return; - } else if (skb->len < 24 || - (!ieee80211_is_probe_resp(mgmt->frame_control) && - !ieee80211_is_beacon(mgmt->frame_control))) + if (ieee80211_is_s1g_short_beacon(mgmt->frame_control)) + min_hdr_len = offsetof(struct ieee80211_ext, + u.s1g_short_beacon.variable); + else + min_hdr_len = offsetof(struct ieee80211_ext, + u.s1g_beacon); + } + + if (skb->len < min_hdr_len) return; sdata1 = rcu_dereference(local->scan_sdata); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 28422d687096..d33dc4e02371 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2002,6 +2002,26 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, ieee80211_tx(sdata, sta, skb, false); } +static bool ieee80211_validate_radiotap_len(struct sk_buff *skb) +{ + struct ieee80211_radiotap_header *rthdr = + (struct ieee80211_radiotap_header *)skb->data; + + /* check for not even having the fixed radiotap header part */ + if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header))) + return false; /* too short to be possibly valid */ + + /* is it a header version we can trust to find length from? */ + if (unlikely(rthdr->it_version)) + return false; /* only version 0 is supported */ + + /* does the skb contain enough to deliver on the alleged length? */ + if (unlikely(skb->len < ieee80211_get_radiotap_len(skb->data))) + return false; /* skb too short for claimed rt header extent */ + + return true; +} + bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, struct net_device *dev) { @@ -2010,8 +2030,6 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, struct ieee80211_radiotap_header *rthdr = (struct ieee80211_radiotap_header *) skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_supported_band *sband = - local->hw.wiphy->bands[info->band]; int ret = ieee80211_radiotap_iterator_init(&iterator, rthdr, skb->len, NULL); u16 txflags; @@ -2024,17 +2042,8 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, u8 vht_mcs = 0, vht_nss = 0; int i; - /* check for not even having the fixed radiotap header part */ - if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header))) - return false; /* too short to be possibly valid */ - - /* is it a header version we can trust to find length from? */ - if (unlikely(rthdr->it_version)) - return false; /* only version 0 is supported */ - - /* does the skb contain enough to deliver on the alleged length? */ - if (unlikely(skb->len < ieee80211_get_radiotap_len(skb->data))) - return false; /* skb too short for claimed rt header extent */ + if (!ieee80211_validate_radiotap_len(skb)) + return false; info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | IEEE80211_TX_CTL_DONTFRAG; @@ -2174,6 +2183,9 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, return false; if (rate_found) { + struct ieee80211_supported_band *sband = + local->hw.wiphy->bands[info->band]; + info->control.flags |= IEEE80211_TX_CTRL_RATE_INJECT; for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { @@ -2187,7 +2199,7 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, } else if (rate_flags & IEEE80211_TX_RC_VHT_MCS) { ieee80211_rate_set_vht(info->control.rates, vht_mcs, vht_nss); - } else { + } else if (sband) { for (i = 0; i < sband->n_bitrates; i++) { if (rate * 5 != sband->bitrates[i].bitrate) continue; @@ -2224,8 +2236,8 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS | IEEE80211_TX_CTL_INJECTED; - /* Sanity-check and process the injection radiotap header */ - if (!ieee80211_parse_tx_radiotap(skb, dev)) + /* Sanity-check the length of the radiotap header */ + if (!ieee80211_validate_radiotap_len(skb)) goto fail; /* we now know there is a radiotap header with a length we can use */ @@ -2339,6 +2351,14 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, ieee80211_select_queue_80211(sdata, skb, hdr); skb_set_queue_mapping(skb, ieee80211_ac_from_tid(skb->priority)); + /* + * Process the radiotap header. This will now take into account the + * selected chandef above to accurately set injection rates and + * retransmissions. + */ + if (!ieee80211_parse_tx_radiotap(skb, dev)) + goto fail_rcu; + /* remove the injection radiotap header */ skb_pull(skb, len_rthdr); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index c0fa526a45b4..53755a05f73b 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2186,8 +2186,6 @@ static void ieee80211_handle_reconfig_failure(struct ieee80211_local *local) list_for_each_entry(ctx, &local->chanctx_list, list) ctx->driver_present = false; mutex_unlock(&local->chanctx_mtx); - - cfg80211_shutdown_all_interfaces(local->hw.wiphy); } static void ieee80211_assign_chanctx(struct ieee80211_local *local, diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 8848a9e2a95b..47d90cf31f12 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -337,6 +337,8 @@ void mptcp_get_options(const struct sk_buff *skb, length--; continue; default: + if (length < 2) + return; opsize = *ptr++; if (opsize < 2) /* "silly options" */ return; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 225b98821517..d8187ac06539 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -287,11 +287,13 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, /* try to fetch required memory from subflow */ if (!sk_rmem_schedule(sk, skb, skb->truesize)) { - if (ssk->sk_forward_alloc < skb->truesize) - goto drop; - __sk_mem_reclaim(ssk, skb->truesize); - if (!sk_rmem_schedule(sk, skb, skb->truesize)) + int amount = sk_mem_pages(skb->truesize) << SK_MEM_QUANTUM_SHIFT; + + if (ssk->sk_forward_alloc < amount) goto drop; + + ssk->sk_forward_alloc -= amount; + sk->sk_forward_alloc += amount; } /* the skb map_seq accounts for the skb offset: @@ -687,18 +689,22 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) /* In most cases we will be able to lock the mptcp socket. If its already * owned, we need to defer to the work queue to avoid ABBA deadlock. */ -static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) +static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; unsigned int moved = 0; if (inet_sk_state_load(sk) == TCP_CLOSE) - return; - - mptcp_data_lock(sk); + return false; __mptcp_move_skbs_from_subflow(msk, ssk, &moved); __mptcp_ofo_queue(msk); + if (unlikely(ssk->sk_err)) { + if (!sock_owned_by_user(sk)) + __mptcp_error_report(sk); + else + set_bit(MPTCP_ERROR_REPORT, &msk->flags); + } /* If the moves have caught up with the DATA_FIN sequence number * it's time to ack the DATA_FIN and change socket state, but @@ -707,7 +713,7 @@ static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) */ if (mptcp_pending_data_fin(sk, NULL)) mptcp_schedule_work(sk); - mptcp_data_unlock(sk); + return moved > 0; } void mptcp_data_ready(struct sock *sk, struct sock *ssk) @@ -715,7 +721,6 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(sk); int sk_rbuf, ssk_rbuf; - bool wake; /* The peer can send data while we are shutting down this * subflow at msk destruction time, but we must avoid enqueuing @@ -724,28 +729,22 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) if (unlikely(subflow->disposable)) return; - /* move_skbs_to_msk below can legitly clear the data_avail flag, - * but we will need later to properly woke the reader, cache its - * value - */ - wake = subflow->data_avail == MPTCP_SUBFLOW_DATA_AVAIL; - if (wake) - set_bit(MPTCP_DATA_READY, &msk->flags); - ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf); sk_rbuf = READ_ONCE(sk->sk_rcvbuf); if (unlikely(ssk_rbuf > sk_rbuf)) sk_rbuf = ssk_rbuf; - /* over limit? can't append more skbs to msk */ + /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) - goto wake; - - move_skbs_to_msk(msk, ssk); + return; -wake: - if (wake) + /* Wake-up the reader only for in-sequence data */ + mptcp_data_lock(sk); + if (move_skbs_to_msk(msk, ssk)) { + set_bit(MPTCP_DATA_READY, &msk->flags); sk->sk_data_ready(sk); + } + mptcp_data_unlock(sk); } void __mptcp_flush_join_list(struct mptcp_sock *msk) @@ -848,7 +847,7 @@ static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk) sock_owned_by_me(sk); mptcp_for_each_subflow(msk, subflow) { - if (subflow->data_avail) + if (READ_ONCE(subflow->data_avail)) return mptcp_subflow_tcp_sock(subflow); } @@ -1939,6 +1938,9 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); mptcp_data_unlock(sk); tcp_cleanup_rbuf(ssk, moved); + + if (unlikely(ssk->sk_err)) + __mptcp_error_report(sk); unlock_sock_fast(ssk, slowpath); } while (!done); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index e21a5bc36cf0..14e89e4bd4a8 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -372,7 +372,6 @@ mptcp_subflow_rsk(const struct request_sock *rsk) enum mptcp_data_avail { MPTCP_SUBFLOW_NODATA, MPTCP_SUBFLOW_DATA_AVAIL, - MPTCP_SUBFLOW_OOO_DATA }; struct mptcp_delegated_action { diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 8425cd393bf3..d6d8ad4f918e 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -754,10 +754,10 @@ static u64 expand_seq(u64 old_seq, u16 old_data_len, u64 seq) return seq | ((old_seq + old_data_len + 1) & GENMASK_ULL(63, 32)); } -static void warn_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) +static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) { - WARN_ONCE(1, "Bad mapping: ssn=%d map_seq=%d map_data_len=%d", - ssn, subflow->map_subflow_seq, subflow->map_data_len); + pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d", + ssn, subflow->map_subflow_seq, subflow->map_data_len); } static bool skb_is_fully_mapped(struct sock *ssk, struct sk_buff *skb) @@ -782,13 +782,13 @@ static bool validate_mapping(struct sock *ssk, struct sk_buff *skb) /* Mapping covers data later in the subflow stream, * currently unsupported. */ - warn_bad_map(subflow, ssn); + dbg_bad_map(subflow, ssn); return false; } if (unlikely(!before(ssn, subflow->map_subflow_seq + subflow->map_data_len))) { /* Mapping does covers past subflow data, invalid */ - warn_bad_map(subflow, ssn + skb->len); + dbg_bad_map(subflow, ssn); return false; } return true; @@ -974,7 +974,7 @@ static bool subflow_check_data_avail(struct sock *ssk) pr_debug("msk=%p ssk=%p data_avail=%d skb=%p", subflow->conn, ssk, subflow->data_avail, skb_peek(&ssk->sk_receive_queue)); if (!skb_peek(&ssk->sk_receive_queue)) - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); if (subflow->data_avail) return true; @@ -1012,18 +1012,13 @@ static bool subflow_check_data_avail(struct sock *ssk) ack_seq = mptcp_subflow_get_mapped_dsn(subflow); pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack, ack_seq); - if (ack_seq == old_ack) { - subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL; - break; - } else if (after64(ack_seq, old_ack)) { - subflow->data_avail = MPTCP_SUBFLOW_OOO_DATA; - break; + if (unlikely(before64(ack_seq, old_ack))) { + mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); + continue; } - /* only accept in-sequence mapping. Old values are spurious - * retransmission - */ - mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); + break; } return true; @@ -1038,10 +1033,9 @@ static bool subflow_check_data_avail(struct sock *ssk) * subflow_error_report() will introduce the appropriate barriers */ ssk->sk_err = EBADMSG; - ssk->sk_error_report(ssk); tcp_set_state(ssk, TCP_CLOSE); tcp_send_active_reset(ssk, GFP_ATOMIC); - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); return false; } @@ -1051,7 +1045,7 @@ static bool subflow_check_data_avail(struct sock *ssk) subflow->map_seq = READ_ONCE(msk->ack_seq); subflow->map_data_len = skb->len; subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset; - subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL; + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); return true; } @@ -1063,7 +1057,7 @@ bool mptcp_subflow_data_available(struct sock *sk) if (subflow->map_valid && mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) { subflow->map_valid = 0; - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); pr_debug("Done with mapping: seq=%u data_len=%u", subflow->map_subflow_seq, @@ -1091,41 +1085,6 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space) *full_space = tcp_full_space(sk); } -static void subflow_data_ready(struct sock *sk) -{ - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - u16 state = 1 << inet_sk_state_load(sk); - struct sock *parent = subflow->conn; - struct mptcp_sock *msk; - - msk = mptcp_sk(parent); - if (state & TCPF_LISTEN) { - /* MPJ subflow are removed from accept queue before reaching here, - * avoid stray wakeups - */ - if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue)) - return; - - set_bit(MPTCP_DATA_READY, &msk->flags); - parent->sk_data_ready(parent); - return; - } - - WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && - !subflow->mp_join && !(state & TCPF_CLOSE)); - - if (mptcp_subflow_data_available(sk)) - mptcp_data_ready(parent, sk); -} - -static void subflow_write_space(struct sock *ssk) -{ - struct sock *sk = mptcp_subflow_ctx(ssk)->conn; - - mptcp_propagate_sndbuf(sk, ssk); - mptcp_write_space(sk); -} - void __mptcp_error_report(struct sock *sk) { struct mptcp_subflow_context *subflow; @@ -1166,6 +1125,43 @@ static void subflow_error_report(struct sock *ssk) mptcp_data_unlock(sk); } +static void subflow_data_ready(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + u16 state = 1 << inet_sk_state_load(sk); + struct sock *parent = subflow->conn; + struct mptcp_sock *msk; + + msk = mptcp_sk(parent); + if (state & TCPF_LISTEN) { + /* MPJ subflow are removed from accept queue before reaching here, + * avoid stray wakeups + */ + if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue)) + return; + + set_bit(MPTCP_DATA_READY, &msk->flags); + parent->sk_data_ready(parent); + return; + } + + WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && + !subflow->mp_join && !(state & TCPF_CLOSE)); + + if (mptcp_subflow_data_available(sk)) + mptcp_data_ready(parent, sk); + else if (unlikely(sk->sk_err)) + subflow_error_report(sk); +} + +static void subflow_write_space(struct sock *ssk) +{ + struct sock *sk = mptcp_subflow_ctx(ssk)->conn; + + mptcp_propagate_sndbuf(sk, ssk); + mptcp_write_space(sk); +} + static struct inet_connection_sock_af_ops * subflow_default_af_ops(struct sock *sk) { @@ -1474,6 +1470,8 @@ static void subflow_state_change(struct sock *sk) */ if (mptcp_subflow_data_available(sk)) mptcp_data_ready(parent, sk); + else if (unlikely(sk->sk_err)) + subflow_error_report(sk); subflow_sched_work_if_closed(mptcp_sk(parent), sk); diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index b100c04a0e43..3d6d49420db8 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -31,6 +31,9 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, int length = (th->doff * 4) - sizeof(*th); u8 buf[40], *ptr; + if (unlikely(length < 0)) + return false; + ptr = skb_header_pointer(skb, doff + sizeof(*th), length, buf); if (ptr == NULL) return false; @@ -47,6 +50,8 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, length--; continue; default: + if (length < 2) + return true; opsize = *ptr++; if (opsize < 2) return true; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 31016c144c48..9d5ea2352965 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4317,13 +4317,44 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, err = nf_tables_set_alloc_name(&ctx, set, name); kfree(name); if (err < 0) - goto err_set_alloc_name; + goto err_set_name; + + udata = NULL; + if (udlen) { + udata = set->data + size; + nla_memcpy(udata, nla[NFTA_SET_USERDATA], udlen); + } + + INIT_LIST_HEAD(&set->bindings); + set->table = table; + write_pnet(&set->net, net); + set->ops = ops; + set->ktype = ktype; + set->klen = desc.klen; + set->dtype = dtype; + set->objtype = objtype; + set->dlen = desc.dlen; + set->flags = flags; + set->size = desc.size; + set->policy = policy; + set->udlen = udlen; + set->udata = udata; + set->timeout = timeout; + set->gc_int = gc_int; + + set->field_count = desc.field_count; + for (i = 0; i < desc.field_count; i++) + set->field_len[i] = desc.field_len[i]; + + err = ops->init(set, &desc, nla); + if (err < 0) + goto err_set_init; if (nla[NFTA_SET_EXPR]) { expr = nft_set_elem_expr_alloc(&ctx, set, nla[NFTA_SET_EXPR]); if (IS_ERR(expr)) { err = PTR_ERR(expr); - goto err_set_alloc_name; + goto err_set_expr_alloc; } set->exprs[0] = expr; set->num_exprs++; @@ -4334,74 +4365,44 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (!(flags & NFT_SET_EXPR)) { err = -EINVAL; - goto err_set_alloc_name; + goto err_set_expr_alloc; } i = 0; nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) { if (i == NFT_SET_EXPR_MAX) { err = -E2BIG; - goto err_set_init; + goto err_set_expr_alloc; } if (nla_type(tmp) != NFTA_LIST_ELEM) { err = -EINVAL; - goto err_set_init; + goto err_set_expr_alloc; } expr = nft_set_elem_expr_alloc(&ctx, set, tmp); if (IS_ERR(expr)) { err = PTR_ERR(expr); - goto err_set_init; + goto err_set_expr_alloc; } set->exprs[i++] = expr; set->num_exprs++; } } - udata = NULL; - if (udlen) { - udata = set->data + size; - nla_memcpy(udata, nla[NFTA_SET_USERDATA], udlen); - } - - INIT_LIST_HEAD(&set->bindings); - set->table = table; - write_pnet(&set->net, net); - set->ops = ops; - set->ktype = ktype; - set->klen = desc.klen; - set->dtype = dtype; - set->objtype = objtype; - set->dlen = desc.dlen; - set->flags = flags; - set->size = desc.size; - set->policy = policy; - set->udlen = udlen; - set->udata = udata; - set->timeout = timeout; - set->gc_int = gc_int; set->handle = nf_tables_alloc_handle(table); - set->field_count = desc.field_count; - for (i = 0; i < desc.field_count; i++) - set->field_len[i] = desc.field_len[i]; - - err = ops->init(set, &desc, nla); - if (err < 0) - goto err_set_init; - err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) - goto err_set_trans; + goto err_set_expr_alloc; list_add_tail_rcu(&set->list, &table->sets); table->use++; return 0; -err_set_trans: - ops->destroy(set); -err_set_init: +err_set_expr_alloc: for (i = 0; i < set->num_exprs; i++) nft_expr_destroy(&ctx, set->exprs[i]); -err_set_alloc_name: + + ops->destroy(set); +err_set_init: kfree(set->name); err_set_name: kvfree(set); diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 1e4fb568fa84..24f10bf7d8a3 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -435,7 +435,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) struct qrtr_sock *ipc; struct sk_buff *skb; struct qrtr_cb *cb; - unsigned int size; + size_t size; unsigned int ver; size_t hdrlen; diff --git a/net/rds/recv.c b/net/rds/recv.c index aba4afe4dfed..967d115f97ef 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -714,7 +714,7 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, if (rds_cmsg_recv(inc, msg, rs)) { ret = -EFAULT; - goto out; + break; } rds_recvmsg_zcookie(rs, msg); diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index ba7f57cb41c3..143786d8cde0 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -904,14 +904,19 @@ static int tcf_ct_act_nat(struct sk_buff *skb, } err = ct_nat_execute(skb, ct, ctinfo, range, maniptype); - if (err == NF_ACCEPT && - ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) { - if (maniptype == NF_NAT_MANIP_SRC) - maniptype = NF_NAT_MANIP_DST; - else - maniptype = NF_NAT_MANIP_SRC; - - err = ct_nat_execute(skb, ct, ctinfo, range, maniptype); + if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) { + if (ct->status & IPS_SRC_NAT) { + if (maniptype == NF_NAT_MANIP_SRC) + maniptype = NF_NAT_MANIP_DST; + else + maniptype = NF_NAT_MANIP_SRC; + + err = ct_nat_execute(skb, ct, ctinfo, range, + maniptype); + } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { + err = ct_nat_execute(skb, ct, ctinfo, NULL, + NF_NAT_MANIP_SRC); + } } return err; #else diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 7d37638ee1c7..5c15968b5155 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -943,7 +943,7 @@ static struct tcphdr *cake_get_tcphdr(const struct sk_buff *skb, } tcph = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); - if (!tcph) + if (!tcph || tcph->doff < 5) return NULL; return skb_header_pointer(skb, offset, @@ -967,6 +967,8 @@ static const void *cake_get_tcpopt(const struct tcphdr *tcph, length--; continue; } + if (length < 2) + break; opsize = *ptr++; if (opsize < 2 || opsize > length) break; @@ -1104,6 +1106,8 @@ static bool cake_tcph_may_drop(const struct tcphdr *tcph, length--; continue; } + if (length < 2) + break; opsize = *ptr++; if (opsize < 2 || opsize > length) break; diff --git a/net/socket.c b/net/socket.c index 84a8049c2b09..03259cb919f7 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1072,19 +1072,6 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, * what to do with it - that's up to the protocol still. */ -/** - * get_net_ns - increment the refcount of the network namespace - * @ns: common namespace (net) - * - * Returns the net's common namespace. - */ - -struct ns_common *get_net_ns(struct ns_common *ns) -{ - return &get_net(container_of(ns, struct net, ns))->ns; -} -EXPORT_SYMBOL_GPL(get_net_ns); - static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct socket *sock; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5a31307ceb76..5d1192ceb139 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -535,12 +535,14 @@ static void unix_release_sock(struct sock *sk, int embrion) u->path.mnt = NULL; state = sk->sk_state; sk->sk_state = TCP_CLOSE; + + skpair = unix_peer(sk); + unix_peer(sk) = NULL; + unix_state_unlock(sk); wake_up_interruptible_all(&u->peer_wait); - skpair = unix_peer(sk); - if (skpair != NULL) { if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) { unix_state_lock(skpair); @@ -555,7 +557,6 @@ static void unix_release_sock(struct sock *sk, int embrion) unix_dgram_peer_wake_disconnect(sk, skpair); sock_put(skpair); /* It may now die */ - unix_peer(sk) = NULL; } /* Try to flush out this socket. Throw out buffers at least */ diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 2eee93985ab0..af590ae606b6 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -28,7 +28,7 @@ $(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.hex) @$(kecho) " GEN $@" @(echo '#include "reg.h"'; \ echo 'const u8 shipped_regdb_certs[] = {'; \ - cat $^ ; \ + echo | cat - $^ ; \ echo '};'; \ echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);'; \ ) > $@ diff --git a/net/wireless/core.c b/net/wireless/core.c index 589ee5a69a2e..0e364f32794d 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1339,6 +1339,11 @@ void cfg80211_register_wdev(struct cfg80211_registered_device *rdev, rdev->devlist_generation++; wdev->registered = true; + if (wdev->netdev && + sysfs_create_link(&wdev->netdev->dev.kobj, &rdev->wiphy.dev.kobj, + "phy80211")) + pr_err("failed to add phy80211 symlink to netdev!\n"); + nl80211_notify_iface(rdev, wdev, NL80211_CMD_NEW_INTERFACE); } @@ -1364,14 +1369,6 @@ int cfg80211_register_netdevice(struct net_device *dev) if (ret) goto out; - if (sysfs_create_link(&dev->dev.kobj, &rdev->wiphy.dev.kobj, - "phy80211")) { - pr_err("failed to add phy80211 symlink to netdev!\n"); - unregister_netdevice(dev); - ret = -EINVAL; - goto out; - } - cfg80211_register_wdev(rdev, wdev); ret = 0; out: diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index a95c79d18349..a817d8e3e4b3 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -324,6 +324,7 @@ void cfg80211_pmsr_complete(struct wireless_dev *wdev, gfp_t gfp) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct cfg80211_pmsr_request *tmp, *prev, *to_free = NULL; struct sk_buff *msg; void *hdr; @@ -354,9 +355,20 @@ void cfg80211_pmsr_complete(struct wireless_dev *wdev, nlmsg_free(msg); free_request: spin_lock_bh(&wdev->pmsr_lock); - list_del(&req->list); + /* + * cfg80211_pmsr_process_abort() may have already moved this request + * to the free list, and will free it later. In this case, don't free + * it here. + */ + list_for_each_entry_safe(tmp, prev, &wdev->pmsr_list, list) { + if (tmp == req) { + list_del(&req->list); + to_free = req; + break; + } + } spin_unlock_bh(&wdev->pmsr_lock); - kfree(req); + kfree(to_free); } EXPORT_SYMBOL_GPL(cfg80211_pmsr_complete); diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index 9b959e3b09c6..0c3f05c9be27 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -133,6 +133,10 @@ static int wiphy_resume(struct device *dev) if (rdev->wiphy.registered && rdev->ops->resume) ret = rdev_resume(rdev); wiphy_unlock(&rdev->wiphy); + + if (ret) + cfg80211_shutdown_all_interfaces(&rdev->wiphy); + rtnl_unlock(); return ret; diff --git a/sound/soc/codecs/rt5659.c b/sound/soc/codecs/rt5659.c index 91a4ef7f620c..a9b079d56fd6 100644 --- a/sound/soc/codecs/rt5659.c +++ b/sound/soc/codecs/rt5659.c @@ -2433,13 +2433,18 @@ static int set_dmic_power(struct snd_soc_dapm_widget *w, return 0; } -static const struct snd_soc_dapm_widget rt5659_dapm_widgets[] = { +static const struct snd_soc_dapm_widget rt5659_particular_dapm_widgets[] = { SND_SOC_DAPM_SUPPLY("LDO2", RT5659_PWR_ANLG_3, RT5659_PWR_LDO2_BIT, 0, NULL, 0), - SND_SOC_DAPM_SUPPLY("PLL", RT5659_PWR_ANLG_3, RT5659_PWR_PLL_BIT, 0, - NULL, 0), + SND_SOC_DAPM_SUPPLY("MICBIAS1", RT5659_PWR_ANLG_2, RT5659_PWR_MB1_BIT, + 0, NULL, 0), SND_SOC_DAPM_SUPPLY("Mic Det Power", RT5659_PWR_VOL, RT5659_PWR_MIC_DET_BIT, 0, NULL, 0), +}; + +static const struct snd_soc_dapm_widget rt5659_dapm_widgets[] = { + SND_SOC_DAPM_SUPPLY("PLL", RT5659_PWR_ANLG_3, RT5659_PWR_PLL_BIT, 0, + NULL, 0), SND_SOC_DAPM_SUPPLY("Mono Vref", RT5659_PWR_ANLG_1, RT5659_PWR_VREF3_BIT, 0, NULL, 0), @@ -2464,8 +2469,6 @@ static const struct snd_soc_dapm_widget rt5659_dapm_widgets[] = { RT5659_ADC_MONO_R_ASRC_SFT, 0, NULL, 0), /* Input Side */ - SND_SOC_DAPM_SUPPLY("MICBIAS1", RT5659_PWR_ANLG_2, RT5659_PWR_MB1_BIT, - 0, NULL, 0), SND_SOC_DAPM_SUPPLY("MICBIAS2", RT5659_PWR_ANLG_2, RT5659_PWR_MB2_BIT, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("MICBIAS3", RT5659_PWR_ANLG_2, RT5659_PWR_MB3_BIT, @@ -3660,10 +3663,23 @@ static int rt5659_set_bias_level(struct snd_soc_component *component, static int rt5659_probe(struct snd_soc_component *component) { + struct snd_soc_dapm_context *dapm = + snd_soc_component_get_dapm(component); struct rt5659_priv *rt5659 = snd_soc_component_get_drvdata(component); rt5659->component = component; + switch (rt5659->pdata.jd_src) { + case RT5659_JD_HDA_HEADER: + break; + + default: + snd_soc_dapm_new_controls(dapm, + rt5659_particular_dapm_widgets, + ARRAY_SIZE(rt5659_particular_dapm_widgets)); + break; + } + return 0; } diff --git a/sound/soc/codecs/rt5682-sdw.c b/sound/soc/codecs/rt5682-sdw.c index b49f1e16125d..d1dd7f720ba4 100644 --- a/sound/soc/codecs/rt5682-sdw.c +++ b/sound/soc/codecs/rt5682-sdw.c @@ -462,7 +462,8 @@ static int rt5682_io_init(struct device *dev, struct sdw_slave *slave) regmap_update_bits(rt5682->regmap, RT5682_CBJ_CTRL_2, RT5682_EXT_JD_SRC, RT5682_EXT_JD_SRC_MANUAL); - regmap_write(rt5682->regmap, RT5682_CBJ_CTRL_1, 0xd042); + regmap_write(rt5682->regmap, RT5682_CBJ_CTRL_1, 0xd142); + regmap_update_bits(rt5682->regmap, RT5682_CBJ_CTRL_5, 0x0700, 0x0600); regmap_update_bits(rt5682->regmap, RT5682_CBJ_CTRL_3, RT5682_CBJ_IN_BUF_EN, RT5682_CBJ_IN_BUF_EN); regmap_update_bits(rt5682->regmap, RT5682_SAR_IL_CMD_1, diff --git a/sound/soc/codecs/tas2562.h b/sound/soc/codecs/tas2562.h index 81866aeb3fbf..55b2a1f52ca3 100644 --- a/sound/soc/codecs/tas2562.h +++ b/sound/soc/codecs/tas2562.h @@ -57,13 +57,13 @@ #define TAS2562_TDM_CFG0_RAMPRATE_MASK BIT(5) #define TAS2562_TDM_CFG0_RAMPRATE_44_1 BIT(5) #define TAS2562_TDM_CFG0_SAMPRATE_MASK GENMASK(3, 1) -#define TAS2562_TDM_CFG0_SAMPRATE_7305_8KHZ 0x0 -#define TAS2562_TDM_CFG0_SAMPRATE_14_7_16KHZ 0x1 -#define TAS2562_TDM_CFG0_SAMPRATE_22_05_24KHZ 0x2 -#define TAS2562_TDM_CFG0_SAMPRATE_29_4_32KHZ 0x3 -#define TAS2562_TDM_CFG0_SAMPRATE_44_1_48KHZ 0x4 -#define TAS2562_TDM_CFG0_SAMPRATE_88_2_96KHZ 0x5 -#define TAS2562_TDM_CFG0_SAMPRATE_176_4_192KHZ 0x6 +#define TAS2562_TDM_CFG0_SAMPRATE_7305_8KHZ (0x0 << 1) +#define TAS2562_TDM_CFG0_SAMPRATE_14_7_16KHZ (0x1 << 1) +#define TAS2562_TDM_CFG0_SAMPRATE_22_05_24KHZ (0x2 << 1) +#define TAS2562_TDM_CFG0_SAMPRATE_29_4_32KHZ (0x3 << 1) +#define TAS2562_TDM_CFG0_SAMPRATE_44_1_48KHZ (0x4 << 1) +#define TAS2562_TDM_CFG0_SAMPRATE_88_2_96KHZ (0x5 << 1) +#define TAS2562_TDM_CFG0_SAMPRATE_176_4_192KHZ (0x6 << 1) #define TAS2562_TDM_CFG2_RIGHT_JUSTIFY BIT(6) diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c index f62f81ceab0d..9dcbe5d5a428 100644 --- a/sound/soc/fsl/fsl-asoc-card.c +++ b/sound/soc/fsl/fsl-asoc-card.c @@ -732,6 +732,7 @@ static int fsl_asoc_card_probe(struct platform_device *pdev) /* Initialize sound card */ priv->pdev = pdev; priv->card.dev = &pdev->dev; + priv->card.owner = THIS_MODULE; ret = snd_soc_of_parse_card_name(&priv->card, "model"); if (ret) { snprintf(priv->name, sizeof(priv->name), "%s-audio", diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index 936384a94f25..74d3d8c58608 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -93,8 +93,30 @@ static void lpass_cpu_daiops_shutdown(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct lpass_data *drvdata = snd_soc_dai_get_drvdata(dai); + struct lpaif_i2sctl *i2sctl = drvdata->i2sctl; + unsigned int id = dai->driver->id; clk_disable_unprepare(drvdata->mi2s_osr_clk[dai->driver->id]); + /* + * Ensure LRCLK is disabled even in device node validation. + * Will not impact if disabled in lpass_cpu_daiops_trigger() + * suspend. + */ + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + regmap_fields_write(i2sctl->spken, id, LPAIF_I2SCTL_SPKEN_DISABLE); + else + regmap_fields_write(i2sctl->micen, id, LPAIF_I2SCTL_MICEN_DISABLE); + + /* + * BCLK may not be enabled if lpass_cpu_daiops_prepare is called before + * lpass_cpu_daiops_shutdown. It's paired with the clk_enable in + * lpass_cpu_daiops_prepare. + */ + if (drvdata->mi2s_was_prepared[dai->driver->id]) { + drvdata->mi2s_was_prepared[dai->driver->id] = false; + clk_disable(drvdata->mi2s_bit_clk[dai->driver->id]); + } + clk_unprepare(drvdata->mi2s_bit_clk[dai->driver->id]); } @@ -275,6 +297,18 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: + /* + * Ensure lpass BCLK/LRCLK is enabled during + * device resume as lpass_cpu_daiops_prepare() is not called + * after the device resumes. We don't check mi2s_was_prepared before + * enable/disable BCLK in trigger events because: + * 1. These trigger events are paired, so the BCLK + * enable_count is balanced. + * 2. the BCLK can be shared (ex: headset and headset mic), + * we need to increase the enable_count so that we don't + * turn off the shared BCLK while other devices are using + * it. + */ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { ret = regmap_fields_write(i2sctl->spken, id, LPAIF_I2SCTL_SPKEN_ENABLE); @@ -296,6 +330,10 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: + /* + * To ensure lpass BCLK/LRCLK is disabled during + * device suspend. + */ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { ret = regmap_fields_write(i2sctl->spken, id, LPAIF_I2SCTL_SPKEN_DISABLE); @@ -315,12 +353,53 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, return ret; } +static int lpass_cpu_daiops_prepare(struct snd_pcm_substream *substream, + struct snd_soc_dai *dai) +{ + struct lpass_data *drvdata = snd_soc_dai_get_drvdata(dai); + struct lpaif_i2sctl *i2sctl = drvdata->i2sctl; + unsigned int id = dai->driver->id; + int ret; + + /* + * Ensure lpass BCLK/LRCLK is enabled bit before playback/capture + * data flow starts. This allows other codec to have some delay before + * the data flow. + * (ex: to drop start up pop noise before capture starts). + */ + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + ret = regmap_fields_write(i2sctl->spken, id, LPAIF_I2SCTL_SPKEN_ENABLE); + else + ret = regmap_fields_write(i2sctl->micen, id, LPAIF_I2SCTL_MICEN_ENABLE); + + if (ret) { + dev_err(dai->dev, "error writing to i2sctl reg: %d\n", ret); + return ret; + } + + /* + * Check mi2s_was_prepared before enabling BCLK as lpass_cpu_daiops_prepare can + * be called multiple times. It's paired with the clk_disable in + * lpass_cpu_daiops_shutdown. + */ + if (!drvdata->mi2s_was_prepared[dai->driver->id]) { + ret = clk_enable(drvdata->mi2s_bit_clk[id]); + if (ret) { + dev_err(dai->dev, "error in enabling mi2s bit clk: %d\n", ret); + return ret; + } + drvdata->mi2s_was_prepared[dai->driver->id] = true; + } + return 0; +} + const struct snd_soc_dai_ops asoc_qcom_lpass_cpu_dai_ops = { .set_sysclk = lpass_cpu_daiops_set_sysclk, .startup = lpass_cpu_daiops_startup, .shutdown = lpass_cpu_daiops_shutdown, .hw_params = lpass_cpu_daiops_hw_params, .trigger = lpass_cpu_daiops_trigger, + .prepare = lpass_cpu_daiops_prepare, }; EXPORT_SYMBOL_GPL(asoc_qcom_lpass_cpu_dai_ops); diff --git a/sound/soc/qcom/lpass.h b/sound/soc/qcom/lpass.h index 83b2e08ade06..7f72214404ba 100644 --- a/sound/soc/qcom/lpass.h +++ b/sound/soc/qcom/lpass.h @@ -67,6 +67,10 @@ struct lpass_data { /* MI2S SD lines to use for playback/capture */ unsigned int mi2s_playback_sd_mode[LPASS_MAX_MI2S_PORTS]; unsigned int mi2s_capture_sd_mode[LPASS_MAX_MI2S_PORTS]; + + /* The state of MI2S prepare dai_ops was called */ + bool mi2s_was_prepared[LPASS_MAX_MI2S_PORTS]; + int hdmi_port_enable; /* low-power audio interface (LPAIF) registers */ diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index 7d6687618d80..d1b327036ae4 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -289,6 +289,9 @@ struct sockaddr_in { /* Address indicating an error return. */ #define INADDR_NONE ((unsigned long int) 0xffffffff) +/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */ +#define INADDR_DUMMY ((unsigned long int) 0xc0000008) + /* Network number for local host loopback. */ #define IN_LOOPBACKNET 127 diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 007fe5d59438..fe2bec500bf6 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -928,7 +928,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, goto out_put_ctx; } if (xsk->fd == umem->fd) - umem->rx_ring_setup_done = true; + umem->tx_ring_setup_done = true; } err = xsk_get_mmap_offsets(xsk->fd, &off); diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 385894b4a8bb..42222a84167f 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -438,6 +438,4 @@ extern int __sys_socketpair(int family, int type, int protocol, int __user *usockvec); extern int __sys_shutdown_sock(struct socket *sock, int how); extern int __sys_shutdown(int fd, int how); - -extern struct ns_common *get_net_ns(struct ns_common *ns); #endif /* _LINUX_SOCKET_H */ diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 26c990e32378..939aed36e0c2 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -162,10 +162,10 @@ static bool contains_event(struct evsel **metric_events, int num_events, return false; } -static bool evsel_same_pmu(struct evsel *ev1, struct evsel *ev2) +static bool evsel_same_pmu_or_none(struct evsel *ev1, struct evsel *ev2) { if (!ev1->pmu_name || !ev2->pmu_name) - return false; + return true; return !strcmp(ev1->pmu_name, ev2->pmu_name); } @@ -288,7 +288,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, */ if (!has_constraint && ev->leader != metric_events[i]->leader && - evsel_same_pmu(ev->leader, metric_events[i]->leader)) + evsel_same_pmu_or_none(ev->leader, metric_events[i]->leader)) break; if (!strcmp(metric_events[i]->name, ev->name)) { set_bit(ev->idx, evlist_used); @@ -1072,16 +1072,18 @@ static int metricgroup__add_metric_sys_event_iter(struct pmu_event *pe, ret = add_metric(d->metric_list, pe, d->metric_no_group, &m, NULL, d->ids); if (ret) - return ret; + goto out; ret = resolve_metric(d->metric_no_group, d->metric_list, NULL, d->ids); if (ret) - return ret; + goto out; *(d->has_match) = true; - return *d->ret; +out: + *(d->ret) = ret; + return ret; } static int metricgroup__add_metric(const char *metric, bool metric_no_group, diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 2b5707738609..6fad54c7ecb4 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -1384,12 +1384,37 @@ ipv4_rt_replace() ipv4_rt_replace_mpath } +# checks that cached input route on VRF port is deleted +# when VRF is deleted +ipv4_local_rt_cache() +{ + run_cmd "ip addr add 10.0.0.1/32 dev lo" + run_cmd "ip netns add test-ns" + run_cmd "ip link add veth-outside type veth peer name veth-inside" + run_cmd "ip link add vrf-100 type vrf table 1100" + run_cmd "ip link set veth-outside master vrf-100" + run_cmd "ip link set veth-inside netns test-ns" + run_cmd "ip link set veth-outside up" + run_cmd "ip link set vrf-100 up" + run_cmd "ip route add 10.1.1.1/32 dev veth-outside table 1100" + run_cmd "ip netns exec test-ns ip link set veth-inside up" + run_cmd "ip netns exec test-ns ip addr add 10.1.1.1/32 dev veth-inside" + run_cmd "ip netns exec test-ns ip route add 10.0.0.1/32 dev veth-inside" + run_cmd "ip netns exec test-ns ip route add default via 10.0.0.1" + run_cmd "ip netns exec test-ns ping 10.0.0.1 -c 1 -i 1" + run_cmd "ip link delete vrf-100" + + # if we do not hang test is a success + log_test $? 0 "Cached route removed from VRF port device" +} + ipv4_route_test() { route_setup ipv4_rt_add ipv4_rt_replace + ipv4_local_rt_cache route_cleanup } diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 65b3b983efc2..8763706b0d04 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -197,9 +197,6 @@ ip -net "$ns4" link set ns4eth3 up ip -net "$ns4" route add default via 10.0.3.2 ip -net "$ns4" route add default via dead:beef:3::2 -# use TCP syn cookies, even if no flooding was detected. -ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2 - set_ethtool_flags() { local ns="$1" local dev="$2" @@ -711,6 +708,14 @@ for sender in $ns1 $ns2 $ns3 $ns4;do exit $ret fi + # ns1<->ns2 is not subject to reordering/tc delays. Use it to test + # mptcp syncookie support. + if [ $sender = $ns1 ]; then + ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2 + else + ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=1 + fi + run_tests "$ns2" $sender 10.0.1.2 run_tests "$ns2" $sender dead:beef:1::2 run_tests "$ns2" $sender 10.0.2.1