diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt index 405da11fc3e4..d11af52427b4 100644 --- a/Documentation/arm64/silicon-errata.txt +++ b/Documentation/arm64/silicon-errata.txt @@ -42,24 +42,26 @@ file acts as a registry of software workarounds in the Linux Kernel and will be updated when new workarounds are committed and backported to stable kernels. -| Implementor | Component | Erratum ID | Kconfig | -+----------------+-----------------+-----------------+-------------------------+ -| ARM | Cortex-A53 | #826319 | ARM64_ERRATUM_826319 | -| ARM | Cortex-A53 | #827319 | ARM64_ERRATUM_827319 | -| ARM | Cortex-A53 | #824069 | ARM64_ERRATUM_824069 | -| ARM | Cortex-A53 | #819472 | ARM64_ERRATUM_819472 | -| ARM | Cortex-A53 | #845719 | ARM64_ERRATUM_845719 | -| ARM | Cortex-A53 | #843419 | ARM64_ERRATUM_843419 | -| ARM | Cortex-A57 | #832075 | ARM64_ERRATUM_832075 | -| ARM | Cortex-A57 | #852523 | N/A | -| ARM | Cortex-A57 | #834220 | ARM64_ERRATUM_834220 | -| ARM | Cortex-A72 | #853709 | N/A | -| ARM | MMU-500 | #841119,#826419 | N/A | -| | | | | -| Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 | -| Cavium | ThunderX ITS | #23144 | CAVIUM_ERRATUM_23144 | -| Cavium | ThunderX GICv3 | #23154 | CAVIUM_ERRATUM_23154 | -| Cavium | ThunderX Core | #27456 | CAVIUM_ERRATUM_27456 | -| Cavium | ThunderX SMMUv2 | #27704 | N/A | -| | | | | -| Freescale/NXP | LS2080A/LS1043A | A-008585 | FSL_ERRATUM_A008585 | +| Implementor | Component | Erratum ID | Kconfig | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A53 | #826319 | ARM64_ERRATUM_826319 | +| ARM | Cortex-A53 | #827319 | ARM64_ERRATUM_827319 | +| ARM | Cortex-A53 | #824069 | ARM64_ERRATUM_824069 | +| ARM | Cortex-A53 | #819472 | ARM64_ERRATUM_819472 | +| ARM | Cortex-A53 | #845719 | ARM64_ERRATUM_845719 | +| ARM | Cortex-A53 | #843419 | ARM64_ERRATUM_843419 | +| ARM | Cortex-A57 | #832075 | ARM64_ERRATUM_832075 | +| ARM | Cortex-A57 | #852523 | N/A | +| ARM | Cortex-A57 | #834220 | ARM64_ERRATUM_834220 | +| ARM | Cortex-A72 | #853709 | N/A | +| ARM | MMU-500 | #841119,#826419 | N/A | +| | | | | +| Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 | +| Cavium | ThunderX ITS | #23144 | CAVIUM_ERRATUM_23144 | +| Cavium | ThunderX GICv3 | #23154 | CAVIUM_ERRATUM_23154 | +| Cavium | ThunderX Core | #27456 | CAVIUM_ERRATUM_27456 | +| Cavium | ThunderX SMMUv2 | #27704 | N/A | +| | | | | +| Freescale/NXP | LS2080A/LS1043A | A-008585 | FSL_ERRATUM_A008585 | +| | | | | +| Qualcomm Tech. | QDF2400 ITS | E0065 | QCOM_QDF2400_ERRATUM_0065 | diff --git a/Makefile b/Makefile index 8df819e31882..48e18096913f 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 10 -SUBLEVEL = 4 +SUBLEVEL = 5 EXTRAVERSION = NAME = Fearless Coyote diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 111742126897..51634f7f0aff 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -479,6 +479,16 @@ config CAVIUM_ERRATUM_27456 If unsure, say Y. +config QCOM_QDF2400_ERRATUM_0065 + bool "QDF2400 E0065: Incorrect GITS_TYPER.ITT_Entry_size" + default y + help + On Qualcomm Datacenter Technologies QDF2400 SoC, ITS hardware reports + ITE size incorrectly. The GITS_TYPER.ITT_Entry_size field should have + been indicated as 16Bytes (0xf), not 8Bytes (0x7). + + If unsure, say Y. + endmenu diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index 88e2f2b938f0..55889d057757 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -17,14 +17,62 @@ #include <asm/kvm_hyp.h> +static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm) +{ + u64 val; + + /* + * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and + * most TLB operations target EL2/EL0. In order to affect the + * guest TLBs (EL1/EL0), we need to change one of these two + * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so + * let's flip TGE before executing the TLB operation. + */ + write_sysreg(kvm->arch.vttbr, vttbr_el2); + val = read_sysreg(hcr_el2); + val &= ~HCR_TGE; + write_sysreg(val, hcr_el2); + isb(); +} + +static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm) +{ + write_sysreg(kvm->arch.vttbr, vttbr_el2); + isb(); +} + +static hyp_alternate_select(__tlb_switch_to_guest, + __tlb_switch_to_guest_nvhe, + __tlb_switch_to_guest_vhe, + ARM64_HAS_VIRT_HOST_EXTN); + +static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm) +{ + /* + * We're done with the TLB operation, let's restore the host's + * view of HCR_EL2. + */ + write_sysreg(0, vttbr_el2); + write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); +} + +static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm) +{ + write_sysreg(0, vttbr_el2); +} + +static hyp_alternate_select(__tlb_switch_to_host, + __tlb_switch_to_host_nvhe, + __tlb_switch_to_host_vhe, + ARM64_HAS_VIRT_HOST_EXTN); + void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) { dsb(ishst); /* Switch to requested VMID */ kvm = kern_hyp_va(kvm); - write_sysreg(kvm->arch.vttbr, vttbr_el2); - isb(); + __tlb_switch_to_guest()(kvm); /* * We could do so much better if we had the VA as well. @@ -45,7 +93,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) dsb(ish); isb(); - write_sysreg(0, vttbr_el2); + __tlb_switch_to_host()(kvm); } void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) @@ -54,14 +102,13 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) /* Switch to requested VMID */ kvm = kern_hyp_va(kvm); - write_sysreg(kvm->arch.vttbr, vttbr_el2); - isb(); + __tlb_switch_to_guest()(kvm); asm volatile("tlbi vmalls12e1is" : : ); dsb(ish); isb(); - write_sysreg(0, vttbr_el2); + __tlb_switch_to_host()(kvm); } void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) @@ -69,14 +116,13 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm); /* Switch to requested VMID */ - write_sysreg(kvm->arch.vttbr, vttbr_el2); - isb(); + __tlb_switch_to_guest()(kvm); asm volatile("tlbi vmalle1" : : ); dsb(nsh); isb(); - write_sysreg(0, vttbr_el2); + __tlb_switch_to_host()(kvm); } void __hyp_text __kvm_flush_vm_context(void) diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c index 9fa046d56eba..411994551afc 100644 --- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c +++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c @@ -52,7 +52,7 @@ static int crc32c_vpmsum_cra_init(struct crypto_tfm *tfm) { u32 *key = crypto_tfm_ctx(tfm); - *key = 0; + *key = ~0; return 0; } diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 1635c0c8df23..e07b36c5588a 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2100,8 +2100,8 @@ static int x86_pmu_event_init(struct perf_event *event) static void refresh_pce(void *ignored) { - if (current->mm) - load_mm_cr4(current->mm); + if (current->active_mm) + load_mm_cr4(current->active_mm); } static void x86_pmu_event_mapped(struct perf_event *event) diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 8af04afdfcb9..84c0f23ea644 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -727,7 +727,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) if (atomic_dec_and_test(&rdtgrp->waitcount) && (rdtgrp->flags & RDT_DELETED)) { kernfs_unbreak_active_protection(kn); - kernfs_put(kn); + kernfs_put(rdtgrp->kn); kfree(rdtgrp); } else { kernfs_unbreak_active_protection(kn); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 54a2372f5dbb..b5785c197e53 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -4,6 +4,7 @@ * Copyright (C) 2000 Andrea Arcangeli <andrea@xxxxxxx> SuSE */ +#define DISABLE_BRANCH_PROFILING #include <linux/init.h> #include <linux/linkage.h> #include <linux/types.h> diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 37e7cf544e51..62d55e34d373 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1310,6 +1310,8 @@ static int __init init_tsc_clocksource(void) * the refined calibration and directly register it as a clocksource. */ if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) { + if (boot_cpu_has(X86_FEATURE_ART)) + art_related_clocksource = &clocksource_tsc; clocksource_register_khz(&clocksource_tsc, tsc_khz); return 0; } diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index 23d15565d02a..919a7b78f945 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -80,19 +80,43 @@ static size_t regs_size(struct pt_regs *regs) return sizeof(*regs); } +#ifdef CONFIG_X86_32 +#define GCC_REALIGN_WORDS 3 +#else +#define GCC_REALIGN_WORDS 1 +#endif + static bool is_last_task_frame(struct unwind_state *state) { - unsigned long bp = (unsigned long)state->bp; - unsigned long regs = (unsigned long)task_pt_regs(state->task); + unsigned long *last_bp = (unsigned long *)task_pt_regs(state->task) - 2; + unsigned long *aligned_bp = last_bp - GCC_REALIGN_WORDS; /* * We have to check for the last task frame at two different locations * because gcc can occasionally decide to realign the stack pointer and - * change the offset of the stack frame by a word in the prologue of a - * function called by head/entry code. + * change the offset of the stack frame in the prologue of a function + * called by head/entry code. Examples: + * + * <start_secondary>: + * push %edi + * lea 0x8(%esp),%edi + * and $0xfffffff8,%esp + * pushl -0x4(%edi) + * push %ebp + * mov %esp,%ebp + * + * <x86_64_start_kernel>: + * lea 0x8(%rsp),%r10 + * and $0xfffffffffffffff0,%rsp + * pushq -0x8(%r10) + * push %rbp + * mov %rsp,%rbp + * + * Note that after aligning the stack, it pushes a duplicate copy of + * the return address before pushing the frame pointer. */ - return bp == regs - FRAME_HEADER_SIZE || - bp == regs - FRAME_HEADER_SIZE - sizeof(long); + return (state->bp == last_bp || + (state->bp == aligned_bp && *(aligned_bp+1) == *(last_bp+1))); } /* diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 0493c17b8a51..333362f992e4 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -1,3 +1,4 @@ +#define DISABLE_BRANCH_PROFILING #define pr_fmt(fmt) "kasan: " fmt #include <linux/bootmem.h> #include <linux/kasan.h> diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c index dce1af0ce85c..4721d50c4628 100644 --- a/drivers/crypto/s5p-sss.c +++ b/drivers/crypto/s5p-sss.c @@ -270,7 +270,7 @@ static void s5p_sg_copy_buf(void *buf, struct scatterlist *sg, scatterwalk_done(&walk, out, 0); } -static void s5p_aes_complete(struct s5p_aes_dev *dev, int err) +static void s5p_sg_done(struct s5p_aes_dev *dev) { if (dev->sg_dst_cpy) { dev_dbg(dev->dev, @@ -281,8 +281,11 @@ static void s5p_aes_complete(struct s5p_aes_dev *dev, int err) } s5p_free_sg_cpy(dev, &dev->sg_src_cpy); s5p_free_sg_cpy(dev, &dev->sg_dst_cpy); +} - /* holding a lock outside */ +/* Calls the completion. Cannot be called with dev->lock hold. */ +static void s5p_aes_complete(struct s5p_aes_dev *dev, int err) +{ dev->req->base.complete(&dev->req->base, err); dev->busy = false; } @@ -368,51 +371,44 @@ static int s5p_set_indata(struct s5p_aes_dev *dev, struct scatterlist *sg) } /* - * Returns true if new transmitting (output) data is ready and its - * address+length have to be written to device (by calling - * s5p_set_dma_outdata()). False otherwise. + * Returns -ERRNO on error (mapping of new data failed). + * On success returns: + * - 0 if there is no more data, + * - 1 if new transmitting (output) data is ready and its address+length + * have to be written to device (by calling s5p_set_dma_outdata()). */ -static bool s5p_aes_tx(struct s5p_aes_dev *dev) +static int s5p_aes_tx(struct s5p_aes_dev *dev) { - int err = 0; - bool ret = false; + int ret = 0; s5p_unset_outdata(dev); if (!sg_is_last(dev->sg_dst)) { - err = s5p_set_outdata(dev, sg_next(dev->sg_dst)); - if (err) - s5p_aes_complete(dev, err); - else - ret = true; - } else { - s5p_aes_complete(dev, err); - - dev->busy = true; - tasklet_schedule(&dev->tasklet); + ret = s5p_set_outdata(dev, sg_next(dev->sg_dst)); + if (!ret) + ret = 1; } return ret; } /* - * Returns true if new receiving (input) data is ready and its - * address+length have to be written to device (by calling - * s5p_set_dma_indata()). False otherwise. + * Returns -ERRNO on error (mapping of new data failed). + * On success returns: + * - 0 if there is no more data, + * - 1 if new receiving (input) data is ready and its address+length + * have to be written to device (by calling s5p_set_dma_indata()). */ -static bool s5p_aes_rx(struct s5p_aes_dev *dev) +static int s5p_aes_rx(struct s5p_aes_dev *dev/*, bool *set_dma*/) { - int err; - bool ret = false; + int ret = 0; s5p_unset_indata(dev); if (!sg_is_last(dev->sg_src)) { - err = s5p_set_indata(dev, sg_next(dev->sg_src)); - if (err) - s5p_aes_complete(dev, err); - else - ret = true; + ret = s5p_set_indata(dev, sg_next(dev->sg_src)); + if (!ret) + ret = 1; } return ret; @@ -422,33 +418,73 @@ static irqreturn_t s5p_aes_interrupt(int irq, void *dev_id) { struct platform_device *pdev = dev_id; struct s5p_aes_dev *dev = platform_get_drvdata(pdev); - bool set_dma_tx = false; - bool set_dma_rx = false; + int err_dma_tx = 0; + int err_dma_rx = 0; + bool tx_end = false; unsigned long flags; uint32_t status; + int err; spin_lock_irqsave(&dev->lock, flags); + /* + * Handle rx or tx interrupt. If there is still data (scatterlist did not + * reach end), then map next scatterlist entry. + * In case of such mapping error, s5p_aes_complete() should be called. + * + * If there is no more data in tx scatter list, call s5p_aes_complete() + * and schedule new tasklet. + */ status = SSS_READ(dev, FCINTSTAT); if (status & SSS_FCINTSTAT_BRDMAINT) - set_dma_rx = s5p_aes_rx(dev); - if (status & SSS_FCINTSTAT_BTDMAINT) - set_dma_tx = s5p_aes_tx(dev); + err_dma_rx = s5p_aes_rx(dev); + + if (status & SSS_FCINTSTAT_BTDMAINT) { + if (sg_is_last(dev->sg_dst)) + tx_end = true; + err_dma_tx = s5p_aes_tx(dev); + } SSS_WRITE(dev, FCINTPEND, status); - /* - * Writing length of DMA block (either receiving or transmitting) - * will start the operation immediately, so this should be done - * at the end (even after clearing pending interrupts to not miss the - * interrupt). - */ - if (set_dma_tx) - s5p_set_dma_outdata(dev, dev->sg_dst); - if (set_dma_rx) - s5p_set_dma_indata(dev, dev->sg_src); + if (err_dma_rx < 0) { + err = err_dma_rx; + goto error; + } + if (err_dma_tx < 0) { + err = err_dma_tx; + goto error; + } + + if (tx_end) { + s5p_sg_done(dev); + + spin_unlock_irqrestore(&dev->lock, flags); + + s5p_aes_complete(dev, 0); + dev->busy = true; + tasklet_schedule(&dev->tasklet); + } else { + /* + * Writing length of DMA block (either receiving or + * transmitting) will start the operation immediately, so this + * should be done at the end (even after clearing pending + * interrupts to not miss the interrupt). + */ + if (err_dma_tx == 1) + s5p_set_dma_outdata(dev, dev->sg_dst); + if (err_dma_rx == 1) + s5p_set_dma_indata(dev, dev->sg_src); + spin_unlock_irqrestore(&dev->lock, flags); + } + + return IRQ_HANDLED; + +error: + s5p_sg_done(dev); spin_unlock_irqrestore(&dev->lock, flags); + s5p_aes_complete(dev, err); return IRQ_HANDLED; } @@ -597,8 +633,9 @@ static void s5p_aes_crypt_start(struct s5p_aes_dev *dev, unsigned long mode) s5p_unset_indata(dev); indata_error: - s5p_aes_complete(dev, err); + s5p_sg_done(dev); spin_unlock_irqrestore(&dev->lock, flags); + s5p_aes_complete(dev, err); } static void s5p_tasklet_cb(unsigned long data) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 728ca3ea74d2..f02da12f2860 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1573,18 +1573,21 @@ static int i915_drm_resume(struct drm_device *dev) intel_opregion_setup(dev_priv); intel_init_pch_refclk(dev); - drm_mode_config_reset(dev); /* * Interrupts have to be enabled before any batches are run. If not the * GPU will hang. i915_gem_init_hw() will initiate batches to * update/restore the context. * + * drm_mode_config_reset() needs AUX interrupts. + * * Modeset enabling in intel_modeset_init_hw() also needs working * interrupts. */ intel_runtime_pm_enable_interrupts(dev_priv); + drm_mode_config_reset(dev); + mutex_lock(&dev->struct_mutex); if (i915_gem_init_hw(dev)) { DRM_ERROR("failed to re-initialize GPU, declaring wedged!\n"); diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 07ca71cabb2b..f914581b1729 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -3089,19 +3089,16 @@ static void ibx_hpd_irq_setup(struct drm_i915_private *dev_priv) I915_WRITE(PCH_PORT_HOTPLUG, hotplug); } -static void spt_hpd_irq_setup(struct drm_i915_private *dev_priv) +static void spt_hpd_detection_setup(struct drm_i915_private *dev_priv) { - u32 hotplug_irqs, hotplug, enabled_irqs; - - hotplug_irqs = SDE_HOTPLUG_MASK_SPT; - enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_spt); - - ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs); + u32 hotplug; /* Enable digital hotplug on the PCH */ hotplug = I915_READ(PCH_PORT_HOTPLUG); - hotplug |= PORTD_HOTPLUG_ENABLE | PORTC_HOTPLUG_ENABLE | - PORTB_HOTPLUG_ENABLE | PORTA_HOTPLUG_ENABLE; + hotplug |= PORTA_HOTPLUG_ENABLE | + PORTB_HOTPLUG_ENABLE | + PORTC_HOTPLUG_ENABLE | + PORTD_HOTPLUG_ENABLE; I915_WRITE(PCH_PORT_HOTPLUG, hotplug); hotplug = I915_READ(PCH_PORT_HOTPLUG2); @@ -3109,6 +3106,18 @@ static void spt_hpd_irq_setup(struct drm_i915_private *dev_priv) I915_WRITE(PCH_PORT_HOTPLUG2, hotplug); } +static void spt_hpd_irq_setup(struct drm_i915_private *dev_priv) +{ + u32 hotplug_irqs, enabled_irqs; + + hotplug_irqs = SDE_HOTPLUG_MASK_SPT; + enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_spt); + + ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs); + + spt_hpd_detection_setup(dev_priv); +} + static void ilk_hpd_irq_setup(struct drm_i915_private *dev_priv) { u32 hotplug_irqs, hotplug, enabled_irqs; @@ -3143,18 +3152,15 @@ static void ilk_hpd_irq_setup(struct drm_i915_private *dev_priv) ibx_hpd_irq_setup(dev_priv); } -static void bxt_hpd_irq_setup(struct drm_i915_private *dev_priv) +static void __bxt_hpd_detection_setup(struct drm_i915_private *dev_priv, + u32 enabled_irqs) { - u32 hotplug_irqs, hotplug, enabled_irqs; - - enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_bxt); - hotplug_irqs = BXT_DE_PORT_HOTPLUG_MASK; - - bdw_update_port_irq(dev_priv, hotplug_irqs, enabled_irqs); + u32 hotplug; hotplug = I915_READ(PCH_PORT_HOTPLUG); - hotplug |= PORTC_HOTPLUG_ENABLE | PORTB_HOTPLUG_ENABLE | - PORTA_HOTPLUG_ENABLE; + hotplug |= PORTA_HOTPLUG_ENABLE | + PORTB_HOTPLUG_ENABLE | + PORTC_HOTPLUG_ENABLE; DRM_DEBUG_KMS("Invert bit setting: hp_ctl:%x hp_port:%x\n", hotplug, enabled_irqs); @@ -3164,7 +3170,6 @@ static void bxt_hpd_irq_setup(struct drm_i915_private *dev_priv) * For BXT invert bit has to be set based on AOB design * for HPD detection logic, update it based on VBT fields. */ - if ((enabled_irqs & BXT_DE_PORT_HP_DDIA) && intel_bios_is_port_hpd_inverted(dev_priv, PORT_A)) hotplug |= BXT_DDIA_HPD_INVERT; @@ -3178,6 +3183,23 @@ static void bxt_hpd_irq_setup(struct drm_i915_private *dev_priv) I915_WRITE(PCH_PORT_HOTPLUG, hotplug); } +static void bxt_hpd_detection_setup(struct drm_i915_private *dev_priv) +{ + __bxt_hpd_detection_setup(dev_priv, BXT_DE_PORT_HOTPLUG_MASK); +} + +static void bxt_hpd_irq_setup(struct drm_i915_private *dev_priv) +{ + u32 hotplug_irqs, enabled_irqs; + + enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_bxt); + hotplug_irqs = BXT_DE_PORT_HOTPLUG_MASK; + + bdw_update_port_irq(dev_priv, hotplug_irqs, enabled_irqs); + + __bxt_hpd_detection_setup(dev_priv, enabled_irqs); +} + static void ibx_irq_postinstall(struct drm_device *dev) { struct drm_i915_private *dev_priv = to_i915(dev); @@ -3193,6 +3215,12 @@ static void ibx_irq_postinstall(struct drm_device *dev) gen5_assert_iir_is_zero(dev_priv, SDEIIR); I915_WRITE(SDEIMR, ~mask); + + if (HAS_PCH_IBX(dev_priv) || HAS_PCH_CPT(dev_priv) || + HAS_PCH_LPT(dev_priv)) + ; /* TODO: Enable HPD detection on older PCH platforms too */ + else + spt_hpd_detection_setup(dev_priv); } static void gen5_gt_irq_postinstall(struct drm_device *dev) @@ -3404,6 +3432,9 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) GEN5_IRQ_INIT(GEN8_DE_PORT_, ~de_port_masked, de_port_enables); GEN5_IRQ_INIT(GEN8_DE_MISC_, ~de_misc_masked, de_misc_masked); + + if (IS_BROXTON(dev_priv)) + bxt_hpd_detection_setup(dev_priv); } static int gen8_irq_postinstall(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 4daf7dda9cca..c3ab0240691a 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -4289,8 +4289,8 @@ static bool bxt_digital_port_connected(struct drm_i915_private *dev_priv, * * Return %true if @port is connected, %false otherwise. */ -static bool intel_digital_port_connected(struct drm_i915_private *dev_priv, - struct intel_digital_port *port) +bool intel_digital_port_connected(struct drm_i915_private *dev_priv, + struct intel_digital_port *port) { if (HAS_PCH_IBX(dev_priv)) return ibx_digital_port_connected(dev_priv, port); diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 03a2112004f9..a0af54bba85b 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1451,6 +1451,8 @@ bool intel_dp_read_dpcd(struct intel_dp *intel_dp); bool __intel_dp_read_desc(struct intel_dp *intel_dp, struct intel_dp_desc *desc); bool intel_dp_read_desc(struct intel_dp *intel_dp); +bool intel_digital_port_connected(struct drm_i915_private *dev_priv, + struct intel_digital_port *port); /* intel_dp_aux_backlight.c */ int intel_dp_aux_init_backlight_funcs(struct intel_connector *intel_connector); diff --git a/drivers/gpu/drm/i915/intel_lspcon.c b/drivers/gpu/drm/i915/intel_lspcon.c index daa523410953..12695616f673 100644 --- a/drivers/gpu/drm/i915/intel_lspcon.c +++ b/drivers/gpu/drm/i915/intel_lspcon.c @@ -100,6 +100,8 @@ static bool lspcon_probe(struct intel_lspcon *lspcon) static void lspcon_resume_in_pcon_wa(struct intel_lspcon *lspcon) { struct intel_dp *intel_dp = lspcon_to_intel_dp(lspcon); + struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); + struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); unsigned long start = jiffies; if (!lspcon->desc_valid) @@ -115,7 +117,8 @@ static void lspcon_resume_in_pcon_wa(struct intel_lspcon *lspcon) if (!__intel_dp_read_desc(intel_dp, &desc)) return; - if (!memcmp(&intel_dp->desc, &desc, sizeof(desc))) { + if (intel_digital_port_connected(dev_priv, dig_port) && + !memcmp(&intel_dp->desc, &desc, sizeof(desc))) { DRM_DEBUG_KMS("LSPCON recovering in PCON mode after %u ms\n", jiffies_to_msecs(jiffies - start)); return; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 69b040f47d56..519ff7a18b5b 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1597,6 +1597,14 @@ static void __maybe_unused its_enable_quirk_cavium_23144(void *data) its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_23144; } +static void __maybe_unused its_enable_quirk_qdf2400_e0065(void *data) +{ + struct its_node *its = data; + + /* On QDF2400, the size of the ITE is 16Bytes */ + its->ite_size = 16; +} + static const struct gic_quirk its_quirks[] = { #ifdef CONFIG_CAVIUM_ERRATUM_22375 { @@ -1614,6 +1622,14 @@ static const struct gic_quirk its_quirks[] = { .init = its_enable_quirk_cavium_23144, }, #endif +#ifdef CONFIG_QCOM_QDF2400_ERRATUM_0065 + { + .desc = "ITS: QDF2400 erratum 0065", + .iidr = 0x00001070, /* QDF2400 ITS rev 1.x */ + .mask = 0xffffffff, + .init = its_enable_quirk_qdf2400_e0065, + }, +#endif { } }; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 8029dd4912b6..644d2bf0c451 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4185,6 +4185,7 @@ void bond_setup(struct net_device *bond_dev) /* Initialize the device entry points */ ether_setup(bond_dev); + bond_dev->max_mtu = ETH_MAX_MTU; bond_dev->netdev_ops = &bond_netdev_ops; bond_dev->ethtool_ops = &bond_ethtool_ops; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index a7d16db5c4b2..937f37a5dcb2 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1323,7 +1323,7 @@ static int xgbe_read_ext_mii_regs(struct xgbe_prv_data *pdata, int addr, static int xgbe_set_ext_mii_mode(struct xgbe_prv_data *pdata, unsigned int port, enum xgbe_mdio_mode mode) { - unsigned int reg_val = 0; + unsigned int reg_val = XGMAC_IOREAD(pdata, MAC_MDIOCL22R); switch (mode) { case XGBE_MDIO_MODE_CL22: diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 1c87cc204075..742e5d1b5da4 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1131,12 +1131,12 @@ static void xgbe_stop(struct xgbe_prv_data *pdata) hw_if->disable_tx(pdata); hw_if->disable_rx(pdata); + phy_if->phy_stop(pdata); + xgbe_free_irqs(pdata); xgbe_napi_disable(pdata, 1); - phy_if->phy_stop(pdata); - hw_if->exit(pdata); channel = pdata->channel; @@ -2274,10 +2274,7 @@ static int xgbe_one_poll(struct napi_struct *napi, int budget) processed = xgbe_rx_poll(channel, budget); /* If we processed everything, we are done */ - if (processed < budget) { - /* Turn off polling */ - napi_complete_done(napi, processed); - + if ((processed < budget) && napi_complete_done(napi, processed)) { /* Enable Tx and Rx interrupts */ if (pdata->channel_irq_mode) xgbe_enable_rx_tx_int(pdata, channel); @@ -2319,10 +2316,7 @@ static int xgbe_all_poll(struct napi_struct *napi, int budget) } while ((processed < budget) && (processed != last_processed)); /* If we processed everything, we are done */ - if (processed < budget) { - /* Turn off polling */ - napi_complete_done(napi, processed); - + if ((processed < budget) && napi_complete_done(napi, processed)) { /* Enable Tx and Rx interrupts */ xgbe_enable_rx_tx_ints(pdata); } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 9d8c953083b4..e707c49cc55a 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -716,6 +716,8 @@ static void xgbe_phy_sfp_phy_settings(struct xgbe_prv_data *pdata) pdata->phy.duplex = DUPLEX_UNKNOWN; pdata->phy.autoneg = AUTONEG_ENABLE; pdata->phy.advertising = pdata->phy.supported; + + return; } pdata->phy.advertising &= ~ADVERTISED_Autoneg; @@ -875,6 +877,16 @@ static int xgbe_phy_find_phy_device(struct xgbe_prv_data *pdata) !phy_data->sfp_phy_avail) return 0; + /* Set the proper MDIO mode for the PHY */ + ret = pdata->hw_if.set_ext_mii_mode(pdata, phy_data->mdio_addr, + phy_data->phydev_mode); + if (ret) { + netdev_err(pdata->netdev, + "mdio port/clause not compatible (%u/%u)\n", + phy_data->mdio_addr, phy_data->phydev_mode); + return ret; + } + /* Create and connect to the PHY device */ phydev = get_phy_device(phy_data->mii, phy_data->mdio_addr, (phy_data->phydev_mode == XGBE_MDIO_MODE_CL45)); @@ -2722,6 +2734,18 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata) if (ret) return ret; + /* Set the proper MDIO mode for the re-driver */ + if (phy_data->redrv && !phy_data->redrv_if) { + ret = pdata->hw_if.set_ext_mii_mode(pdata, phy_data->redrv_addr, + XGBE_MDIO_MODE_CL22); + if (ret) { + netdev_err(pdata->netdev, + "redriver mdio port not compatible (%u)\n", + phy_data->redrv_addr); + return ret; + } + } + /* Start in highest supported mode */ xgbe_phy_set_mode(pdata, phy_data->start_mode); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index d5ecb8f53fd4..c69a1f827b65 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -803,6 +803,7 @@ int mlx5e_get_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode); +void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type); static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq, struct mlx5_wqe_ctrl_seg *ctrl, int bf_sz) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index bb67863aa361..6906deae06e0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1477,6 +1477,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev, MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS, enable); priv->params.rx_cqe_compress_def = enable; + mlx5e_set_rq_type_params(priv, priv->params.rq_wq_type); if (reset) err = mlx5e_open_locked(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index f14ca3385fdd..9d9c64927372 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -78,9 +78,10 @@ static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) MLX5_CAP_ETH(mdev, reg_umr_sq); } -static void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type) +void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type) { priv->params.rq_wq_type = rq_type; + priv->params.lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ; switch (priv->params.rq_wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: priv->params.log_rq_size = MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW; @@ -93,6 +94,10 @@ static void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type) break; default: /* MLX5_WQ_TYPE_LINKED_LIST */ priv->params.log_rq_size = MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE; + + /* Extra room needed for build_skb */ + priv->params.lro_wqe_sz -= MLX5_RX_HEADROOM + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); } priv->params.min_rx_wqes = mlx5_min_rx_wqes(priv->params.rq_wq_type, BIT(priv->params.log_rq_size)); @@ -3495,6 +3500,9 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev, cqe_compress_heuristic(link_speed, pci_bw); } + MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS, + priv->params.rx_cqe_compress_def); + mlx5e_set_rq_priv_params(priv); if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) priv->params.lro_en = true; @@ -3517,16 +3525,9 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev, mlx5e_build_default_indir_rqt(mdev, priv->params.indirection_rqt, MLX5E_INDIR_RQT_SIZE, profile->max_nch(mdev)); - priv->params.lro_wqe_sz = - MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - - /* Extra room needed for build_skb */ - MLX5_RX_HEADROOM - - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - /* Initialize pflags */ MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_BASED_MODER, priv->params.rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE); - MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS, priv->params.rx_cqe_compress_def); mutex_init(&priv->state_lock); @@ -3940,6 +3941,19 @@ static void mlx5e_register_vport_rep(struct mlx5_core_dev *mdev) } } +static void mlx5e_unregister_vport_rep(struct mlx5_core_dev *mdev) +{ + struct mlx5_eswitch *esw = mdev->priv.eswitch; + int total_vfs = MLX5_TOTAL_VPORTS(mdev); + int vport; + + if (!MLX5_CAP_GEN(mdev, vport_group_manager)) + return; + + for (vport = 1; vport < total_vfs; vport++) + mlx5_eswitch_unregister_vport_rep(esw, vport); +} + void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -3986,6 +4000,7 @@ static int mlx5e_attach(struct mlx5_core_dev *mdev, void *vpriv) return err; } + mlx5e_register_vport_rep(mdev); return 0; } @@ -3997,6 +4012,7 @@ static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv) if (!netif_device_present(netdev)) return; + mlx5e_unregister_vport_rep(mdev); mlx5e_detach_netdev(mdev, netdev); mlx5e_destroy_mdev_resources(mdev); } @@ -4015,8 +4031,6 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev) if (err) return NULL; - mlx5e_register_vport_rep(mdev); - if (MLX5_CAP_GEN(mdev, vport_group_manager)) ppriv = &esw->offloads.vport_reps[0]; @@ -4068,13 +4082,7 @@ void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv) static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv) { - struct mlx5_eswitch *esw = mdev->priv.eswitch; - int total_vfs = MLX5_TOTAL_VPORTS(mdev); struct mlx5e_priv *priv = vpriv; - int vport; - - for (vport = 1; vport < total_vfs; vport++) - mlx5_eswitch_unregister_vport_rep(esw, vport); unregister_netdev(priv->netdev); mlx5e_detach(mdev, vpriv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 06d5e6fecb0a..e3b88bbb9dcf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -92,19 +92,18 @@ static inline void mlx5e_cqes_update_owner(struct mlx5e_cq *cq, u32 cqcc, int n) static inline void mlx5e_decompress_cqe(struct mlx5e_rq *rq, struct mlx5e_cq *cq, u32 cqcc) { - u16 wqe_cnt_step; - cq->title.byte_cnt = cq->mini_arr[cq->mini_arr_idx].byte_cnt; cq->title.check_sum = cq->mini_arr[cq->mini_arr_idx].checksum; cq->title.op_own &= 0xf0; cq->title.op_own |= 0x01 & (cqcc >> cq->wq.log_sz); cq->title.wqe_counter = cpu_to_be16(cq->decmprs_wqe_counter); - wqe_cnt_step = - rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ? - mpwrq_get_cqe_consumed_strides(&cq->title) : 1; - cq->decmprs_wqe_counter = - (cq->decmprs_wqe_counter + wqe_cnt_step) & rq->wq.sz_m1; + if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) + cq->decmprs_wqe_counter += + mpwrq_get_cqe_consumed_strides(&cq->title); + else + cq->decmprs_wqe_counter = + (cq->decmprs_wqe_counter + 1) & rq->wq.sz_m1; } static inline void mlx5e_decompress_cqe_no_hash(struct mlx5e_rq *rq, @@ -172,6 +171,7 @@ void mlx5e_modify_rx_cqe_compression(struct mlx5e_priv *priv, bool val) mlx5e_close_locked(priv->netdev); MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS, val); + mlx5e_set_rq_type_params(priv, priv->params.rq_wq_type); if (was_opened) mlx5e_open_locked(priv->netdev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 9e494a446b7e..f17f906f1d3a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -496,30 +496,40 @@ static int mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, struct mlxsw_sp_prefix_usage *req_prefix_usage) { - struct mlxsw_sp_lpm_tree *lpm_tree; + struct mlxsw_sp_lpm_tree *lpm_tree = vr->lpm_tree; + struct mlxsw_sp_lpm_tree *new_tree; + int err; - if (mlxsw_sp_prefix_usage_eq(req_prefix_usage, - &vr->lpm_tree->prefix_usage)) + if (mlxsw_sp_prefix_usage_eq(req_prefix_usage, &lpm_tree->prefix_usage)) return 0; - lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage, + new_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage, vr->proto, false); - if (IS_ERR(lpm_tree)) { + if (IS_ERR(new_tree)) { /* We failed to get a tree according to the required * prefix usage. However, the current tree might be still good * for us if our requirement is subset of the prefixes used * in the tree. */ if (mlxsw_sp_prefix_usage_subset(req_prefix_usage, - &vr->lpm_tree->prefix_usage)) + &lpm_tree->prefix_usage)) return 0; - return PTR_ERR(lpm_tree); + return PTR_ERR(new_tree); } - mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr); - mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree); + /* Prevent packet loss by overwriting existing binding */ + vr->lpm_tree = new_tree; + err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr); + if (err) + goto err_tree_bind; + mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); + + return 0; + +err_tree_bind: vr->lpm_tree = lpm_tree; - return mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr); + mlxsw_sp_lpm_tree_put(mlxsw_sp, new_tree); + return err; } static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 45301cb98bc1..7074b40ebd7f 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -881,12 +881,14 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) info = &geneve->info; } + rcu_read_lock(); #if IS_ENABLED(CONFIG_IPV6) if (info->mode & IP_TUNNEL_INFO_IPV6) err = geneve6_xmit_skb(skb, dev, geneve, info); else #endif err = geneve_xmit_skb(skb, dev, geneve, info); + rcu_read_unlock(); if (likely(!err)) return NETDEV_TX_OK; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index bdc58567d10e..707321508c69 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2075,6 +2075,7 @@ static int team_dev_type_check_change(struct net_device *dev, static void team_setup(struct net_device *dev) { ether_setup(dev); + dev->max_mtu = ETH_MAX_MTU; dev->netdev_ops = &team_netdev_ops; dev->ethtool_ops = &team_ethtool_ops; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index bfabe180053e..cdf6339827e6 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -819,7 +819,18 @@ static void tun_net_uninit(struct net_device *dev) /* Net device open. */ static int tun_net_open(struct net_device *dev) { + struct tun_struct *tun = netdev_priv(dev); + int i; + netif_tx_start_all_queues(dev); + + for (i = 0; i < tun->numqueues; i++) { + struct tun_file *tfile; + + tfile = rtnl_dereference(tun->tfiles[i]); + tfile->socket.sk->sk_write_space(tfile->socket.sk); + } + return 0; } @@ -1101,9 +1112,10 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait) if (!skb_array_empty(&tfile->tx_array)) mask |= POLLIN | POLLRDNORM; - if (sock_writeable(sk) || - (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) && - sock_writeable(sk))) + if (tun->dev->flags & IFF_UP && + (sock_writeable(sk) || + (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) && + sock_writeable(sk)))) mask |= POLLOUT | POLLWRNORM; if (tun->dev->reg_state != NETREG_REGISTERED) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 454f907d419a..682aac0a2267 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -341,6 +341,7 @@ static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev) static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) { + int len = skb->len; netdev_tx_t ret = is_ip_tx_frame(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { @@ -348,7 +349,7 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) u64_stats_update_begin(&dstats->syncp); dstats->tx_pkts++; - dstats->tx_bytes += skb->len; + dstats->tx_bytes += len; u64_stats_update_end(&dstats->syncp); } else { this_cpu_inc(dev->dstats->tx_drps); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 30b04cf2bb1e..0e204f1a5072 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1992,7 +1992,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, const struct iphdr *old_iph = ip_hdr(skb); union vxlan_addr *dst; union vxlan_addr remote_ip, local_ip; - union vxlan_addr *src; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; __be16 src_port = 0, dst_port; @@ -2019,7 +2018,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port; vni = rdst->remote_vni; - src = &vxlan->cfg.saddr; + local_ip = vxlan->cfg.saddr; dst_cache = &rdst->dst_cache; md->gbp = skb->mark; ttl = vxlan->cfg.ttl; @@ -2052,7 +2051,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, dst = &remote_ip; dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port; vni = tunnel_id_to_key32(info->key.tun_id); - src = &local_ip; dst_cache = &info->dst_cache; if (info->options_len) md = ip_tunnel_info_opts(info); @@ -2064,6 +2062,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); + rcu_read_lock(); if (dst->sa.sa_family == AF_INET) { struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); struct rtable *rt; @@ -2072,7 +2071,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, rt = vxlan_get_route(vxlan, dev, sock4, skb, rdst ? rdst->remote_ifindex : 0, tos, dst->sin.sin_addr.s_addr, - &src->sin.sin_addr.s_addr, + &local_ip.sin.sin_addr.s_addr, dst_port, src_port, dst_cache, info); if (IS_ERR(rt)) { @@ -2086,7 +2085,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, dst_port, vni, &rt->dst, rt->rt_flags); if (err) - return; + goto out_unlock; } else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) { df = htons(IP_DF); } @@ -2099,7 +2098,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, if (err < 0) goto tx_error; - udp_tunnel_xmit_skb(rt, sock4->sock->sk, skb, src->sin.sin_addr.s_addr, + udp_tunnel_xmit_skb(rt, sock4->sock->sk, skb, local_ip.sin.sin_addr.s_addr, dst->sin.sin_addr.s_addr, tos, ttl, df, src_port, dst_port, xnet, !udp_sum); #if IS_ENABLED(CONFIG_IPV6) @@ -2109,7 +2108,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ndst = vxlan6_get_route(vxlan, dev, sock6, skb, rdst ? rdst->remote_ifindex : 0, tos, label, &dst->sin6.sin6_addr, - &src->sin6.sin6_addr, + &local_ip.sin6.sin6_addr, dst_port, src_port, dst_cache, info); if (IS_ERR(ndst)) { @@ -2125,7 +2124,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, dst_port, vni, ndst, rt6i_flags); if (err) - return; + goto out_unlock; } tos = ip_tunnel_ecn_encap(tos, old_iph, skb); @@ -2137,11 +2136,13 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto tx_error; udp_tunnel6_xmit_skb(ndst, sock6->sock->sk, skb, dev, - &src->sin6.sin6_addr, + &local_ip.sin6.sin6_addr, &dst->sin6.sin6_addr, tos, ttl, label, src_port, dst_port, !udp_sum); #endif } +out_unlock: + rcu_read_unlock(); return; drop: @@ -2150,6 +2151,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, return; tx_error: + rcu_read_unlock(); if (err == -ELOOP) dev->stats.collisions++; else if (err == -ENETUNREACH) @@ -2626,7 +2628,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[]) if (data[IFLA_VXLAN_ID]) { __u32 id = nla_get_u32(data[IFLA_VXLAN_ID]); - if (id >= VXLAN_VID_MASK) + if (id >= VXLAN_N_VID) return -ERANGE; } diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 61d042bbbf60..68449293c4b6 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -163,6 +163,7 @@ struct dccp_request_sock { __u64 dreq_isr; __u64 dreq_gsr; __be32 dreq_service; + spinlock_t dreq_lock; struct list_head dreq_featneg; __u32 dreq_timestamp_echo; __u32 dreq_timestamp_time; diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h index d08c63f3dd6f..0c5d5dd61b6a 100644 --- a/include/uapi/linux/packet_diag.h +++ b/include/uapi/linux/packet_diag.h @@ -64,7 +64,7 @@ struct packet_diag_mclist { __u32 pdmc_count; __u16 pdmc_type; __u16 pdmc_alen; - __u8 pdmc_addr[MAX_ADDR_LEN]; + __u8 pdmc_addr[32]; /* MAX_ADDR_LEN */ }; struct packet_diag_ring { diff --git a/kernel/futex.c b/kernel/futex.c index cdf365036141..dda00f03337d 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2813,7 +2813,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, { struct hrtimer_sleeper timeout, *to = NULL; struct rt_mutex_waiter rt_waiter; - struct rt_mutex *pi_mutex = NULL; struct futex_hash_bucket *hb; union futex_key key2 = FUTEX_KEY_INIT; struct futex_q q = futex_q_init; @@ -2897,6 +2896,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (q.pi_state && (q.pi_state->owner != current)) { spin_lock(q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); + if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) + rt_mutex_unlock(&q.pi_state->pi_mutex); /* * Drop the reference to the pi state which * the requeue_pi() code acquired for us. @@ -2905,6 +2906,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, spin_unlock(q.lock_ptr); } } else { + struct rt_mutex *pi_mutex; + /* * We have been woken up by futex_unlock_pi(), a timeout, or a * signal. futex_unlock_pi() will not destroy the lock_ptr nor @@ -2928,18 +2931,19 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (res) ret = (res < 0) ? res : 0; + /* + * If fixup_pi_state_owner() faulted and was unable to handle + * the fault, unlock the rt_mutex and return the fault to + * userspace. + */ + if (ret && rt_mutex_owner(pi_mutex) == current) + rt_mutex_unlock(pi_mutex); + /* Unqueue and drop the lock. */ unqueue_me_pi(&q); } - /* - * If fixup_pi_state_owner() faulted and was unable to handle the - * fault, unlock the rt_mutex and return the fault to userspace. - */ - if (ret == -EFAULT) { - if (pi_mutex && rt_mutex_owner(pi_mutex) == current) - rt_mutex_unlock(pi_mutex); - } else if (ret == -EINTR) { + if (ret == -EINTR) { /* * We've already been requeued, but cannot restart by calling * futex_lock_pi() directly. We could restart this syscall, but diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c index 1591f6b3539f..2bef4ab94003 100644 --- a/kernel/locking/rwsem-spinlock.c +++ b/kernel/locking/rwsem-spinlock.c @@ -216,10 +216,8 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state) */ if (sem->count == 0) break; - if (signal_pending_state(state, current)) { - ret = -EINTR; - goto out; - } + if (signal_pending_state(state, current)) + goto out_nolock; set_task_state(tsk, state); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); schedule(); @@ -227,12 +225,19 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state) } /* got the lock */ sem->count = -1; -out: list_del(&waiter.list); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); return ret; + +out_nolock: + list_del(&waiter.list); + if (!list_empty(&sem->wait_list)) + __rwsem_do_wake(sem, 1); + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + + return -EINTR; } void __sched __down_write(struct rw_semaphore *sem) diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 7cb41aee4c82..8498e3503605 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -186,8 +186,9 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb, /* Do not flood unicast traffic to ports that turn it off */ if (pkt_type == BR_PKT_UNICAST && !(p->flags & BR_FLOOD)) continue; + /* Do not flood if mc off, except for traffic we originate */ if (pkt_type == BR_PKT_MULTICAST && - !(p->flags & BR_MCAST_FLOOD)) + !(p->flags & BR_MCAST_FLOOD) && skb->dev != br->dev) continue; /* Do not flood to ports that enable proxy ARP */ diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 855b72fbe1da..267b46af407f 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -29,6 +29,7 @@ EXPORT_SYMBOL(br_should_route_hook); static int br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb) { + br_drop_fake_rtable(skb); return netif_receive_skb(skb); } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 95087e6e8258..fa87fbd62bb7 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -521,21 +521,6 @@ static unsigned int br_nf_pre_routing(void *priv, } -/* PF_BRIDGE/LOCAL_IN ************************************************/ -/* The packet is locally destined, which requires a real - * dst_entry, so detach the fake one. On the way up, the - * packet would pass through PRE_ROUTING again (which already - * took place when the packet entered the bridge), but we - * register an IPv4 PRE_ROUTING 'sabotage' hook that will - * prevent this from happening. */ -static unsigned int br_nf_local_in(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - br_drop_fake_rtable(skb); - return NF_ACCEPT; -} - /* PF_BRIDGE/FORWARD *************************************************/ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -908,12 +893,6 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = { .priority = NF_BR_PRI_BRNF, }, { - .hook = br_nf_local_in, - .pf = NFPROTO_BRIDGE, - .hooknum = NF_BR_LOCAL_IN, - .priority = NF_BR_PRI_BRNF, - }, - { .hook = br_nf_forward_ip, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, diff --git a/net/core/dev.c b/net/core/dev.c index 29101c98399f..fd6e2dfda45f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1696,27 +1696,54 @@ EXPORT_SYMBOL_GPL(net_dec_egress_queue); static struct static_key netstamp_needed __read_mostly; #ifdef HAVE_JUMP_LABEL static atomic_t netstamp_needed_deferred; +static atomic_t netstamp_wanted; static void netstamp_clear(struct work_struct *work) { int deferred = atomic_xchg(&netstamp_needed_deferred, 0); + int wanted; - while (deferred--) - static_key_slow_dec(&netstamp_needed); + wanted = atomic_add_return(deferred, &netstamp_wanted); + if (wanted > 0) + static_key_enable(&netstamp_needed); + else + static_key_disable(&netstamp_needed); } static DECLARE_WORK(netstamp_work, netstamp_clear); #endif void net_enable_timestamp(void) { +#ifdef HAVE_JUMP_LABEL + int wanted; + + while (1) { + wanted = atomic_read(&netstamp_wanted); + if (wanted <= 0) + break; + if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted + 1) == wanted) + return; + } + atomic_inc(&netstamp_needed_deferred); + schedule_work(&netstamp_work); +#else static_key_slow_inc(&netstamp_needed); +#endif } EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { #ifdef HAVE_JUMP_LABEL - /* net_disable_timestamp() can be called from non process context */ - atomic_inc(&netstamp_needed_deferred); + int wanted; + + while (1) { + wanted = atomic_read(&netstamp_wanted); + if (wanted <= 1) + break; + if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted - 1) == wanted) + return; + } + atomic_dec(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else static_key_slow_dec(&netstamp_needed); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index b0c04cf4851d..1004418d937e 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -952,7 +952,7 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) while (--i >= new_num) { struct kobject *kobj = &dev->_rx[i].kobj; - if (!list_empty(&dev_net(dev)->exit_list)) + if (!atomic_read(&dev_net(dev)->count)) kobj->uevent_suppress = 1; if (dev->sysfs_rx_queue_group) sysfs_remove_group(kobj, dev->sysfs_rx_queue_group); @@ -1370,7 +1370,7 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) while (--i >= new_num) { struct netdev_queue *queue = dev->_tx + i; - if (!list_empty(&dev_net(dev)->exit_list)) + if (!atomic_read(&dev_net(dev)->count)) queue->kobj.uevent_suppress = 1; #ifdef CONFIG_BQL sysfs_remove_group(&queue->kobj, &dql_group); @@ -1557,7 +1557,7 @@ void netdev_unregister_kobject(struct net_device *ndev) { struct device *dev = &(ndev->dev); - if (!list_empty(&dev_net(ndev)->exit_list)) + if (!atomic_read(&dev_net(ndev)->count)) dev_set_uevent_suppress(dev, 1); kobject_get(&dev->kobj); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 734c71468b01..aa3a13378c90 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3824,13 +3824,14 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, if (!skb_may_tx_timestamp(sk, false)) return; - /* take a reference to prevent skb_orphan() from freeing the socket */ - sock_hold(sk); - - *skb_hwtstamps(skb) = *hwtstamps; - __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND); - - sock_put(sk); + /* Take a reference to prevent skb_orphan() from freeing the socket, + * but only if the socket refcount is not zero. + */ + if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) { + *skb_hwtstamps(skb) = *hwtstamps; + __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND); + sock_put(sk); + } } EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); @@ -3889,7 +3890,7 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) { struct sock *sk = skb->sk; struct sock_exterr_skb *serr; - int err; + int err = 1; skb->wifi_acked_valid = 1; skb->wifi_acked = acked; @@ -3899,14 +3900,15 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS; - /* take a reference to prevent skb_orphan() from freeing the socket */ - sock_hold(sk); - - err = sock_queue_err_skb(sk, skb); + /* Take a reference to prevent skb_orphan() from freeing the socket, + * but only if the socket refcount is not zero. + */ + if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) { + err = sock_queue_err_skb(sk, skb); + sock_put(sk); + } if (err) kfree_skb(skb); - - sock_put(sk); } EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index f053198e730c..5e3a7302f774 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -749,6 +749,7 @@ static void ccid2_hc_tx_exit(struct sock *sk) for (i = 0; i < hc->tx_seqbufc; i++) kfree(hc->tx_seqbuf[i]); hc->tx_seqbufc = 0; + dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks); } static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) diff --git a/net/dccp/input.c b/net/dccp/input.c index 8fedc2d49770..4a05d7876850 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -577,6 +577,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, struct dccp_sock *dp = dccp_sk(sk); struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); const int old_state = sk->sk_state; + bool acceptable; int queued = 0; /* @@ -603,8 +604,13 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, */ if (sk->sk_state == DCCP_LISTEN) { if (dh->dccph_type == DCCP_PKT_REQUEST) { - if (inet_csk(sk)->icsk_af_ops->conn_request(sk, - skb) < 0) + /* It is possible that we process SYN packets from backlog, + * so we need to make sure to disable BH right there. + */ + local_bh_disable(); + acceptable = inet_csk(sk)->icsk_af_ops->conn_request(sk, skb) >= 0; + local_bh_enable(); + if (!acceptable) return 1; consume_skb(skb); return 0; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index d859a5c36e70..b0a1ba968ed5 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -289,7 +289,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) switch (type) { case ICMP_REDIRECT: - dccp_do_redirect(skb, sk); + if (!sock_owned_by_user(sk)) + dccp_do_redirect(skb, sk); goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index c4e879c02186..2f3e8bbe2cb9 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -122,10 +122,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); if (type == NDISC_REDIRECT) { - struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); + if (!sock_owned_by_user(sk)) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); - if (dst) - dst->ops->redirect(dst, sk, skb); + if (dst) + dst->ops->redirect(dst, sk, skb); + } goto out; } diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 53eddf99e4f6..39e7e2bca8db 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -122,6 +122,7 @@ struct sock *dccp_create_openreq_child(const struct sock *sk, /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ newsk->sk_destruct = NULL; + bh_unlock_sock(newsk); sk_free(newsk); return NULL; } @@ -145,6 +146,13 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, struct dccp_request_sock *dreq = dccp_rsk(req); bool own_req; + /* TCP/DCCP listeners became lockless. + * DCCP stores complex state in its request_sock, so we need + * a protection for them, now this code runs without being protected + * by the parent (listener) lock. + */ + spin_lock_bh(&dreq->dreq_lock); + /* Check for retransmitted REQUEST */ if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) { @@ -159,7 +167,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, inet_rtx_syn_ack(sk, req); } /* Network Duplicate, discard packet */ - return NULL; + goto out; } DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR; @@ -185,20 +193,20 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL, req, &own_req); - if (!child) - goto listen_overflow; - - return inet_csk_complete_hashdance(sk, child, req, own_req); + if (child) { + child = inet_csk_complete_hashdance(sk, child, req, own_req); + goto out; + } -listen_overflow: - dccp_pr_debug("listen_overflow!\n"); DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY; drop: if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET) req->rsk_ops->send_reset(sk, skb); inet_csk_reqsk_queue_drop(sk, req); - return NULL; +out: + spin_unlock_bh(&dreq->dreq_lock); + return child; } EXPORT_SYMBOL_GPL(dccp_check_req); @@ -249,6 +257,7 @@ int dccp_reqsk_init(struct request_sock *req, { struct dccp_request_sock *dreq = dccp_rsk(req); + spin_lock_init(&dreq->dreq_lock); inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport; inet_rsk(req)->ir_num = ntohs(dccp_hdr(skb)->dccph_dport); inet_rsk(req)->acked = 0; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f75069883f2b..4391da91789f 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1470,8 +1470,10 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff) int proto = iph->protocol; int err = -ENOSYS; - if (skb->encapsulation) + if (skb->encapsulation) { + skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IP)); skb_set_inner_network_header(skb, nhoff); + } csum_replace2(&iph->check, iph->tot_len, newlen); iph->tot_len = newlen; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 7db2ad2e82d3..b39a791f6756 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -319,7 +319,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, int ret, no_addr; struct fib_result res; struct flowi4 fl4; - struct net *net; + struct net *net = dev_net(dev); bool dev_match; fl4.flowi4_oif = 0; @@ -332,6 +332,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_flags = 0; + fl4.flowi4_uid = sock_net_uid(net, NULL); no_addr = idev->ifa_list == NULL; @@ -339,13 +340,12 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, trace_fib_validate_source(dev, &fl4); - net = dev_net(dev); if (fib_lookup(net, &fl4, &res, 0)) goto last_resort; if (res.type != RTN_UNICAST && (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev))) goto e_inval; - if (!rpf && !fib_num_tclassid_users(dev_net(dev)) && + if (!rpf && !fib_num_tclassid_users(net) && (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) goto last_resort; fib_combine_itag(itag, &res); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 709ffe67d1de..8976887dc83e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1858,6 +1858,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.flowi4_flags = 0; fl4.daddr = daddr; fl4.saddr = saddr; + fl4.flowi4_uid = sock_net_uid(net, NULL); err = fib_lookup(net, &fl4, &res, 0); if (err != 0) { if (!IN_DEV_FORWARD(in_dev)) @@ -1990,6 +1991,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, { int res; + tos &= IPTOS_RT_MASK; rcu_read_lock(); /* Multicast recognition logic is moved from route cache to here. diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 41dcbd568cbe..28777a0307c8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5916,9 +5916,15 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (th->syn) { if (th->fin) goto discard; - if (icsk->icsk_af_ops->conn_request(sk, skb) < 0) - return 1; + /* It is possible that we process SYN packets from backlog, + * so we need to make sure to disable BH right there. + */ + local_bh_disable(); + acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0; + local_bh_enable(); + if (!acceptable) + return 1; consume_skb(skb); return 0; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fe9da4fb96bf..bb629dc2bfb0 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -269,10 +269,13 @@ EXPORT_SYMBOL(tcp_v4_connect); */ void tcp_v4_mtu_reduced(struct sock *sk) { - struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); - u32 mtu = tcp_sk(sk)->mtu_info; + struct dst_entry *dst; + u32 mtu; + if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) + return; + mtu = tcp_sk(sk)->mtu_info; dst = inet_csk_update_pmtu(sk, mtu); if (!dst) return; @@ -418,7 +421,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) switch (type) { case ICMP_REDIRECT: - do_redirect(icmp_skb, sk); + if (!sock_owned_by_user(sk)) + do_redirect(icmp_skb, sk); goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 3705075f42c3..45d707569af6 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -249,7 +249,8 @@ void tcp_delack_timer_handler(struct sock *sk) sk_mem_reclaim_partial(sk); - if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) + if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || + !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) goto out; if (time_after(icsk->icsk_ack.timeout, jiffies)) { @@ -552,7 +553,8 @@ void tcp_write_timer_handler(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); int event; - if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending) + if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || + !icsk->icsk_pending) goto out; if (time_after(icsk->icsk_timeout, jiffies)) { diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index ef5485204522..8c88a37392d0 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -908,6 +908,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, ins = &rt->dst.rt6_next; iter = *ins; while (iter) { + if (iter->rt6i_metric > rt->rt6i_metric) + break; if (rt6_qualify_for_ecmp(iter)) { *ins = iter->dst.rt6_next; fib6_purge_rt(iter, fn, info->nl_net); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index fc7b4017ba24..33b04ec2744a 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -294,8 +294,10 @@ static int ipv6_gro_complete(struct sk_buff *skb, int nhoff) struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff); int err = -ENOSYS; - if (skb->encapsulation) + if (skb->encapsulation) { + skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6)); skb_set_inner_network_header(skb, nhoff); + } iph->payload_len = htons(skb->len - nhoff - sizeof(*iph)); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 7cebee58e55b..d57f4ee5ec29 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -767,13 +767,14 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, * Fragment the datagram. */ - *prevhdr = NEXTHDR_FRAGMENT; troom = rt->dst.dev->needed_tailroom; /* * Keep copying data until we run out. */ while (left > 0) { + u8 *fragnexthdr_offset; + len = left; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > mtu) @@ -818,6 +819,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, */ skb_copy_from_linear_data(skb, skb_network_header(frag), hlen); + fragnexthdr_offset = skb_network_header(frag); + fragnexthdr_offset += prevhdr - skb_network_header(skb); + *fragnexthdr_offset = NEXTHDR_FRAGMENT; + /* * Build fragment header. */ diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index d82042c8d8fd..733c63ef4b8a 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -692,6 +692,10 @@ vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p) u->link = p->link; u->i_key = p->i_key; u->o_key = p->o_key; + if (u->i_key) + u->i_flags |= GRE_KEY; + if (u->o_key) + u->o_flags |= GRE_KEY; u->proto = p->proto; memcpy(u->name, p->name, sizeof(u->name)); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 9948b5ce52da..986d4ca38832 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -589,6 +589,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb); + skb_orphan(skb); fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr, skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr)); if (fq == NULL) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4c60c6f71cd3..cfc232714139 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -382,10 +382,12 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); if (type == NDISC_REDIRECT) { - struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); + if (!sock_owned_by_user(sk)) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); - if (dst) - dst->ops->redirect(dst, sk, skb); + if (dst) + dst->ops->redirect(dst, sk, skb); + } goto out; } diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 28c21546d5b6..3ed30153a6f5 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -381,7 +381,7 @@ static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb) drop: IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS); kfree_skb(skb); - return -1; + return 0; } /* Userspace will call sendmsg() on the tunnel socket to send L2TP diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 5b77377e5a15..1309e2c34764 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -956,7 +956,8 @@ static void mpls_ifdown(struct net_device *dev, int event) /* fall through */ case NETDEV_CHANGE: nh->nh_flags |= RTNH_F_LINKDOWN; - ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1; + if (event != NETDEV_UNREGISTER) + ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1; break; } if (event == NETDEV_UNREGISTER) @@ -1696,6 +1697,7 @@ static void mpls_net_exit(struct net *net) for (index = 0; index < platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); RCU_INIT_POINTER(platform_label[index], NULL); + mpls_notify_route(net, index, rt, NULL, NULL); mpls_rt_free(rt); } rtnl_unlock(); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 54253ea5976e..919d66e083d1 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -367,7 +367,6 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, } else if (key->eth.type == htons(ETH_P_IPV6)) { enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; - skb_orphan(skb); memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); err = nf_ct_frag6_gather(net, skb, user); if (err) { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 70f5b6a4683c..c59fcc79ba32 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3082,7 +3082,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; - char name[15]; + char name[sizeof(uaddr->sa_data) + 1]; /* * Check legality @@ -3090,7 +3090,11 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, if (addr_len != sizeof(struct sockaddr)) return -EINVAL; - strlcpy(name, uaddr->sa_data, sizeof(name)); + /* uaddr->sa_data comes from the userspace, it's not guaranteed to be + * zero-terminated. + */ + memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data)); + name[sizeof(uaddr->sa_data)] = 0; return packet_do_bind(sk, name, 0, pkt_sk(sk)->num); } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index e10456ef6f7a..9b29b6115384 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -817,10 +817,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, goto out_module_put; err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops); - if (err < 0) + if (err <= 0) goto out_module_put; - if (err == 0) - goto noflush_out; nla_nest_end(skb, nest); @@ -837,7 +835,6 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, out_module_put: module_put(ops->owner); err_out: -noflush_out: kfree_skb(skb); return err; } diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index ab8062909962..f9bb43c25697 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -113,6 +113,9 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, if (ret < 0) return ret; + if (!tb[TCA_CONNMARK_PARMS]) + return -EINVAL; + parm = nla_data(tb[TCA_CONNMARK_PARMS]); if (!tcf_hash_check(tn, parm->index, a, bind)) { diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 3b7074e23024..c736627f8f4a 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -228,7 +228,6 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, return skb->len; nla_put_failure: - rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 616a9428e0c4..4ee4a33e34dc 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -199,6 +199,7 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp, sctp_scope_t scope, gfp_t gfp, int copy_flags) { struct sctp_sockaddr_entry *addr; + union sctp_addr laddr; int error = 0; rcu_read_lock(); @@ -220,7 +221,10 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp, !(copy_flags & SCTP_ADDR6_PEERSUPP))) continue; - if (sctp_bind_addr_state(bp, &addr->a) != -1) + laddr = addr->a; + /* also works for setting ipv6 address port */ + laddr.v4.sin_port = htons(bp->port); + if (sctp_bind_addr_state(bp, &laddr) != -1) continue; error = sctp_add_bind_addr(bp, &addr->a, sizeof(addr->a), diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 1b5d669e3029..d04a8b66098c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4734,6 +4734,12 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) if (!asoc) return -EINVAL; + /* If there is a thread waiting on more sndbuf space for + * sending on this asoc, it cannot be peeled. + */ + if (waitqueue_active(&asoc->wait)) + return -EBUSY; + /* An association cannot be branched off from an already peeled-off * socket, nor is this supported for tcp style sockets. */ @@ -7426,8 +7432,6 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, */ release_sock(sk); current_timeo = schedule_timeout(current_timeo); - if (sk != asoc->base.sk) - goto do_error; lock_sock(sk); *timeo_p = current_timeo; diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 41adf362936d..b5c279b22680 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -504,6 +504,7 @@ static int __init strp_mod_init(void) static void __exit strp_mod_exit(void) { + destroy_workqueue(strp_wq); } module_init(strp_mod_init); module_exit(strp_mod_exit);