diff --git a/Makefile b/Makefile index 4442e9ea4b6d..5274f8ae6b44 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 18 -SUBLEVEL = 13 +SUBLEVEL = 14 EXTRAVERSION = NAME = Merciless Moray diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index 4674541eba3f..8ce6e7235915 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -241,6 +241,26 @@ int copy_thread(unsigned long clone_flags, task_thread_info(current)->thr_ptr; } + + /* + * setup usermode thread pointer #1: + * when child is picked by scheduler, __switch_to() uses @c_callee to + * populate usermode callee regs: this works (despite being in a kernel + * function) since special return path for child @ret_from_fork() + * ensures those regs are not clobbered all the way to RTIE to usermode + */ + c_callee->r25 = task_thread_info(p)->thr_ptr; + +#ifdef CONFIG_ARC_CURR_IN_REG + /* + * setup usermode thread pointer #2: + * however for this special use of r25 in kernel, __switch_to() sets + * r25 for kernel needs and only in the final return path is usermode + * r25 setup, from pt_regs->user_r25. So set that up as well + */ + c_regs->user_r25 = c_callee->r25; +#endif + return 0; } diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 8721fd004291..e1a1518a1ec7 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -9,6 +9,7 @@ extern void ppc_printk_progress(char *s, unsigned short hex); extern unsigned int rtas_data; extern unsigned long long memory_limit; +extern bool init_mem_is_free; extern unsigned long klimit; extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask); diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index e0d881ab304e..30cbcadb54d5 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -142,7 +142,7 @@ static inline int unmap_patch_area(unsigned long addr) return 0; } -int patch_instruction(unsigned int *addr, unsigned int instr) +static int do_patch_instruction(unsigned int *addr, unsigned int instr) { int err; unsigned int *patch_addr = NULL; @@ -182,12 +182,22 @@ int patch_instruction(unsigned int *addr, unsigned int instr) } #else /* !CONFIG_STRICT_KERNEL_RWX */ -int patch_instruction(unsigned int *addr, unsigned int instr) +static int do_patch_instruction(unsigned int *addr, unsigned int instr) { return raw_patch_instruction(addr, instr); } #endif /* CONFIG_STRICT_KERNEL_RWX */ + +int patch_instruction(unsigned int *addr, unsigned int instr) +{ + /* Make sure we aren't patching a freed init section */ + if (init_mem_is_free && init_section_contains(addr, 4)) { + pr_debug("Skipping init section patching addr: 0x%px\n", addr); + return 0; + } + return do_patch_instruction(addr, instr); +} NOKPROBE_SYMBOL(patch_instruction); int patch_branch(unsigned int *addr, unsigned long target, int flags) diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 5c8530d0c611..04ccb274a620 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -63,6 +63,7 @@ #endif unsigned long long memory_limit; +bool init_mem_is_free; #ifdef CONFIG_HIGHMEM pte_t *kmap_pte; @@ -396,6 +397,7 @@ void free_initmem(void) { ppc_md.progress = ppc_printk_progress; mark_initmem_nx(); + init_mem_is_free = true; free_initmem_default(POISON_FREE_INITMEM); } diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 9589878faf46..eb1ed9a7109d 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -72,7 +72,13 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \ -fno-omit-frame-pointer -foptimize-sibling-calls \ - -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO $(RETPOLINE_VDSO_CFLAGS) + -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO + +ifdef CONFIG_RETPOLINE +ifneq ($(RETPOLINE_VDSO_CFLAGS),) + CFL += $(RETPOLINE_VDSO_CFLAGS) +endif +endif $(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) @@ -144,7 +150,13 @@ KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector) KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) KBUILD_CFLAGS_32 += -fno-omit-frame-pointer KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING -KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS) + +ifdef CONFIG_RETPOLINE +ifneq ($(RETPOLINE_VDSO_CFLAGS),) + KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS) +endif +endif + $(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) $(obj)/vdso32.so.dbg: FORCE \ diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index f19856d95c60..e48ca3afa091 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -43,8 +43,9 @@ extern u8 hvclock_page notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; - asm("syscall" : "=a" (ret) : - "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory"); + asm ("syscall" : "=a" (ret), "=m" (*ts) : + "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : + "memory", "rcx", "r11"); return ret; } @@ -52,8 +53,9 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) { long ret; - asm("syscall" : "=a" (ret) : - "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory"); + asm ("syscall" : "=a" (ret), "=m" (*tv), "=m" (*tz) : + "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : + "memory", "rcx", "r11"); return ret; } @@ -64,13 +66,13 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; - asm( + asm ( "mov %%ebx, %%edx \n" - "mov %2, %%ebx \n" + "mov %[clock], %%ebx \n" "call __kernel_vsyscall \n" "mov %%edx, %%ebx \n" - : "=a" (ret) - : "0" (__NR_clock_gettime), "g" (clock), "c" (ts) + : "=a" (ret), "=m" (*ts) + : "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts) : "memory", "edx"); return ret; } @@ -79,13 +81,13 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) { long ret; - asm( + asm ( "mov %%ebx, %%edx \n" - "mov %2, %%ebx \n" + "mov %[tv], %%ebx \n" "call __kernel_vsyscall \n" "mov %%edx, %%ebx \n" - : "=a" (ret) - : "0" (__NR_gettimeofday), "g" (tv), "c" (tz) + : "=a" (ret), "=m" (*tv), "=m" (*tz) + : "0" (__NR_gettimeofday), [tv] "g" (tv), "c" (tz) : "memory", "edx"); return ret; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 97d41754769e..d02f0390c1c1 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -232,6 +232,17 @@ static u64 __read_mostly shadow_nonpresent_or_rsvd_mask; */ static const u64 shadow_nonpresent_or_rsvd_mask_len = 5; +/* + * In some cases, we need to preserve the GFN of a non-present or reserved + * SPTE when we usurp the upper five bits of the physical address space to + * defend against L1TF, e.g. for MMIO SPTEs. To preserve the GFN, we'll + * shift bits of the GFN that overlap with shadow_nonpresent_or_rsvd_mask + * left into the reserved bits, i.e. the GFN in the SPTE will be split into + * high and low parts. This mask covers the lower bits of the GFN. + */ +static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; + + static void mmu_spte_set(u64 *sptep, u64 spte); void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value) @@ -338,9 +349,7 @@ static bool is_mmio_spte(u64 spte) static gfn_t get_mmio_spte_gfn(u64 spte) { - u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask | - shadow_nonpresent_or_rsvd_mask; - u64 gpa = spte & ~mask; + u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask; gpa |= (spte >> shadow_nonpresent_or_rsvd_mask_len) & shadow_nonpresent_or_rsvd_mask; @@ -404,6 +413,8 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); static void kvm_mmu_reset_all_pte_masks(void) { + u8 low_phys_bits; + shadow_user_mask = 0; shadow_accessed_mask = 0; shadow_dirty_mask = 0; @@ -418,12 +429,17 @@ static void kvm_mmu_reset_all_pte_masks(void) * appropriate mask to guard against L1TF attacks. Otherwise, it is * assumed that the CPU is not vulnerable to L1TF. */ + low_phys_bits = boot_cpu_data.x86_phys_bits; if (boot_cpu_data.x86_phys_bits < - 52 - shadow_nonpresent_or_rsvd_mask_len) + 52 - shadow_nonpresent_or_rsvd_mask_len) { shadow_nonpresent_or_rsvd_mask = rsvd_bits(boot_cpu_data.x86_phys_bits - shadow_nonpresent_or_rsvd_mask_len, boot_cpu_data.x86_phys_bits - 1); + low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len; + } + shadow_nonpresent_or_rsvd_lower_gfn_mask = + GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT); } static int is_cpuid_PSE36(void) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index d0c3be353bb6..32721ef9652d 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -9826,15 +9826,16 @@ static void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) if (!lapic_in_kernel(vcpu)) return; + if (!flexpriority_enabled && + !cpu_has_vmx_virtualize_x2apic_mode()) + return; + /* Postpone execution until vmcs01 is the current VMCS. */ if (is_guest_mode(vcpu)) { to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true; return; } - if (!cpu_need_tpr_shadow(vcpu)) - return; - sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE); diff --git a/block/blk-mq.c b/block/blk-mq.c index 2f9e14361673..90e8058ae557 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1596,7 +1596,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) BUG_ON(!rq->q); if (rq->mq_ctx != this_ctx) { if (this_ctx) { - trace_block_unplug(this_q, depth, from_schedule); + trace_block_unplug(this_q, depth, !from_schedule); blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list, from_schedule); @@ -1616,7 +1616,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) * on 'ctx_list'. Do those. */ if (this_ctx) { - trace_block_unplug(this_q, depth, from_schedule); + trace_block_unplug(this_q, depth, !from_schedule); blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list, from_schedule); } diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 3f68e2919dc5..a690fd400260 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1713,8 +1713,10 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) dpm_wait_for_subordinate(dev, async); - if (async_error) + if (async_error) { + dev->power.direct_complete = false; goto Complete; + } /* * If a device configured to wake up the system from sleep states @@ -1726,6 +1728,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) pm_wakeup_event(dev, 0); if (pm_wakeup_pending()) { + dev->power.direct_complete = false; async_error = -EBUSY; goto Complete; } diff --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c index ec8a4376f74f..2fab18fae4fc 100644 --- a/drivers/clocksource/timer-atmel-pit.c +++ b/drivers/clocksource/timer-atmel-pit.c @@ -180,26 +180,29 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node) data->base = of_iomap(node, 0); if (!data->base) { pr_err("Could not map PIT address\n"); - return -ENXIO; + ret = -ENXIO; + goto exit; } data->mck = of_clk_get(node, 0); if (IS_ERR(data->mck)) { pr_err("Unable to get mck clk\n"); - return PTR_ERR(data->mck); + ret = PTR_ERR(data->mck); + goto exit; } ret = clk_prepare_enable(data->mck); if (ret) { pr_err("Unable to enable mck\n"); - return ret; + goto exit; } /* Get the interrupts property */ data->irq = irq_of_parse_and_map(node, 0); if (!data->irq) { pr_err("Unable to get IRQ from DT\n"); - return -EINVAL; + ret = -EINVAL; + goto exit; } /* @@ -227,7 +230,7 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node) ret = clocksource_register_hz(&data->clksrc, pit_rate); if (ret) { pr_err("Failed to register clocksource\n"); - return ret; + goto exit; } /* Set up irq handler */ @@ -236,7 +239,8 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node) "at91_tick", data); if (ret) { pr_err("Unable to setup IRQ\n"); - return ret; + clocksource_unregister(&data->clksrc); + goto exit; } /* Set up and register clockevents */ @@ -254,6 +258,10 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node) clockevents_register_device(&data->clkevt); return 0; + +exit: + kfree(data); + return ret; } TIMER_OF_DECLARE(at91sam926x_pit, "atmel,at91sam9260-pit", at91sam926x_pit_dt_init); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index 23d960ec1cf2..acad2999560c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -246,6 +246,8 @@ int amdgpu_vce_suspend(struct amdgpu_device *adev) { int i; + cancel_delayed_work_sync(&adev->vce.idle_work); + if (adev->vce.vcpu_bo == NULL) return 0; @@ -256,7 +258,6 @@ int amdgpu_vce_suspend(struct amdgpu_device *adev) if (i == AMDGPU_MAX_VCE_HANDLES) return 0; - cancel_delayed_work_sync(&adev->vce.idle_work); /* TODO: suspending running encoding sessions isn't supported */ return -EINVAL; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index bee49991c1ff..2dc3d1e28f3c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -151,11 +151,11 @@ int amdgpu_vcn_suspend(struct amdgpu_device *adev) unsigned size; void *ptr; + cancel_delayed_work_sync(&adev->vcn.idle_work); + if (adev->vcn.vcpu_bo == NULL) return 0; - cancel_delayed_work_sync(&adev->vcn.idle_work); - size = amdgpu_bo_size(adev->vcn.vcpu_bo); ptr = adev->vcn.cpu_addr; diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index d638c0fb3418..23a5643a4b98 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -566,14 +566,14 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, lessee_priv->is_master = 1; lessee_priv->authenticated = 1; - /* Hook up the fd */ - fd_install(fd, lessee_file); - /* Pass fd back to userspace */ DRM_DEBUG_LEASE("Returning fd %d id %d\n", fd, lessee->lessee_id); cl->fd = fd; cl->lessee_id = lessee->lessee_id; + /* Hook up the fd */ + fd_install(fd, lessee_file); + DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl succeeded\n"); return 0; diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index d4f4ce484529..8e71da403324 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -97,6 +97,8 @@ static int drm_syncobj_fence_get_or_add_callback(struct drm_syncobj *syncobj, { int ret; + WARN_ON(*fence); + *fence = drm_syncobj_fence_get(syncobj); if (*fence) return 1; @@ -744,6 +746,9 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) { for (i = 0; i < count; ++i) { + if (entries[i].fence) + continue; + drm_syncobj_fence_get_or_add_callback(syncobjs[i], &entries[i].fence, &entries[i].syncobj_cb, diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 5f437d1570fb..21863ddde63e 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1759,6 +1759,8 @@ static int ucma_close(struct inode *inode, struct file *filp) mutex_lock(&mut); if (!ctx->closing) { mutex_unlock(&mut); + ucma_put_ctx(ctx); + wait_for_completion(&ctx->comp); /* rdma_destroy_id ensures that no event handlers are * inflight for that id before releasing it. */ diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 69dddeab124c..5936de71883f 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -1455,8 +1455,8 @@ static int __load_mappings(struct dm_cache_metadata *cmd, if (hints_valid) { r = dm_array_cursor_next(&cmd->hint_cursor); if (r) { - DMERR("dm_array_cursor_next for hint failed"); - goto out; + dm_array_cursor_end(&cmd->hint_cursor); + hints_valid = false; } } diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 44df244807e5..a39ae8f45e32 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -3017,8 +3017,13 @@ static dm_cblock_t get_cache_dev_size(struct cache *cache) static bool can_resize(struct cache *cache, dm_cblock_t new_size) { - if (from_cblock(new_size) > from_cblock(cache->cache_size)) - return true; + if (from_cblock(new_size) > from_cblock(cache->cache_size)) { + if (cache->sized) { + DMERR("%s: unable to extend cache due to missing cache table reload", + cache_device_name(cache)); + return false; + } + } /* * We can't drop a dirty block when shrinking the cache. diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index d94ba6f72ff5..419362c2d8ac 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -806,19 +806,19 @@ static int parse_path_selector(struct dm_arg_set *as, struct priority_group *pg, } static int setup_scsi_dh(struct block_device *bdev, struct multipath *m, - const char *attached_handler_name, char **error) + const char **attached_handler_name, char **error) { struct request_queue *q = bdev_get_queue(bdev); int r; if (test_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags)) { retain: - if (attached_handler_name) { + if (*attached_handler_name) { /* * Clear any hw_handler_params associated with a * handler that isn't already attached. */ - if (m->hw_handler_name && strcmp(attached_handler_name, m->hw_handler_name)) { + if (m->hw_handler_name && strcmp(*attached_handler_name, m->hw_handler_name)) { kfree(m->hw_handler_params); m->hw_handler_params = NULL; } @@ -830,7 +830,8 @@ static int setup_scsi_dh(struct block_device *bdev, struct multipath *m, * handler instead of the original table passed in. */ kfree(m->hw_handler_name); - m->hw_handler_name = attached_handler_name; + m->hw_handler_name = *attached_handler_name; + *attached_handler_name = NULL; } } @@ -867,7 +868,7 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps struct pgpath *p; struct multipath *m = ti->private; struct request_queue *q; - const char *attached_handler_name; + const char *attached_handler_name = NULL; /* we need at least a path arg */ if (as->argc < 1) { @@ -890,7 +891,7 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps attached_handler_name = scsi_dh_attached_handler_name(q, GFP_KERNEL); if (attached_handler_name || m->hw_handler_name) { INIT_DELAYED_WORK(&p->activate_path, activate_path_work); - r = setup_scsi_dh(p->path.dev->bdev, m, attached_handler_name, &ti->error); + r = setup_scsi_dh(p->path.dev->bdev, m, &attached_handler_name, &ti->error); if (r) { dm_put_device(ti, p->path.dev); goto bad; @@ -905,6 +906,7 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps return p; bad: + kfree(attached_handler_name); free_pgpath(p); return ERR_PTR(r); } diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index abf9e884386c..f57f5de54206 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -235,7 +235,7 @@ int mmc_of_parse(struct mmc_host *host) host->caps |= MMC_CAP_NEEDS_POLL; ret = mmc_gpiod_request_cd(host, "cd", 0, true, - cd_debounce_delay_ms, + cd_debounce_delay_ms * 1000, &cd_gpio_invert); if (!ret) dev_info(host->parent, "Got CD GPIO\n"); diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c index 2a833686784b..86803a3a04dc 100644 --- a/drivers/mmc/core/slot-gpio.c +++ b/drivers/mmc/core/slot-gpio.c @@ -271,7 +271,7 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, if (debounce) { ret = gpiod_set_debounce(desc, debounce); if (ret < 0) - ctx->cd_debounce_delay_ms = debounce; + ctx->cd_debounce_delay_ms = debounce / 1000; } if (gpio_invert) diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c index 21eb3a598a86..bdaad6e93be5 100644 --- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c +++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c @@ -1619,10 +1619,10 @@ ath10k_wmi_tlv_op_gen_start_scan(struct ath10k *ar, bssid_len = arg->n_bssids * sizeof(struct wmi_mac_addr); ie_len = roundup(arg->ie_len, 4); len = (sizeof(*tlv) + sizeof(*cmd)) + - (arg->n_channels ? sizeof(*tlv) + chan_len : 0) + - (arg->n_ssids ? sizeof(*tlv) + ssid_len : 0) + - (arg->n_bssids ? sizeof(*tlv) + bssid_len : 0) + - (arg->ie_len ? sizeof(*tlv) + ie_len : 0); + sizeof(*tlv) + chan_len + + sizeof(*tlv) + ssid_len + + sizeof(*tlv) + bssid_len + + sizeof(*tlv) + ie_len; skb = ath10k_wmi_alloc_skb(ar, len); if (!skb) diff --git a/drivers/net/xen-netback/hash.c b/drivers/net/xen-netback/hash.c index 3c4c58b9fe76..3b6fb5b3bdb2 100644 --- a/drivers/net/xen-netback/hash.c +++ b/drivers/net/xen-netback/hash.c @@ -332,20 +332,22 @@ u32 xenvif_set_hash_mapping_size(struct xenvif *vif, u32 size) u32 xenvif_set_hash_mapping(struct xenvif *vif, u32 gref, u32 len, u32 off) { - u32 *mapping = &vif->hash.mapping[off]; + u32 *mapping = vif->hash.mapping; struct gnttab_copy copy_op = { .source.u.ref = gref, .source.domid = vif->domid, - .dest.u.gmfn = virt_to_gfn(mapping), .dest.domid = DOMID_SELF, - .dest.offset = xen_offset_in_page(mapping), - .len = len * sizeof(u32), + .len = len * sizeof(*mapping), .flags = GNTCOPY_source_gref }; - if ((off + len > vif->hash.size) || copy_op.len > XEN_PAGE_SIZE) + if ((off + len < off) || (off + len > vif->hash.size) || + len > XEN_PAGE_SIZE / sizeof(*mapping)) return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER; + copy_op.dest.u.gmfn = virt_to_gfn(mapping + off); + copy_op.dest.offset = xen_offset_in_page(mapping + off); + while (len-- != 0) if (mapping[off++] >= vif->num_queues) return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER; diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 722537e14848..41b49716ac75 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -771,6 +771,9 @@ static void __init of_unittest_parse_interrupts(void) struct of_phandle_args args; int i, rc; + if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC) + return; + np = of_find_node_by_path("/testcase-data/interrupts/interrupts0"); if (!np) { pr_err("missing testcase data\n"); @@ -845,6 +848,9 @@ static void __init of_unittest_parse_interrupts_extended(void) struct of_phandle_args args; int i, rc; + if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC) + return; + np = of_find_node_by_path("/testcase-data/interrupts/interrupts-extended0"); if (!np) { pr_err("missing testcase data\n"); @@ -1001,15 +1007,19 @@ static void __init of_unittest_platform_populate(void) pdev = of_find_device_by_node(np); unittest(pdev, "device 1 creation failed\n"); - irq = platform_get_irq(pdev, 0); - unittest(irq == -EPROBE_DEFER, "device deferred probe failed - %d\n", irq); + if (!(of_irq_workarounds & OF_IMAP_OLDWORLD_MAC)) { + irq = platform_get_irq(pdev, 0); + unittest(irq == -EPROBE_DEFER, + "device deferred probe failed - %d\n", irq); - /* Test that a parsing failure does not return -EPROBE_DEFER */ - np = of_find_node_by_path("/testcase-data/testcase-device2"); - pdev = of_find_device_by_node(np); - unittest(pdev, "device 2 creation failed\n"); - irq = platform_get_irq(pdev, 0); - unittest(irq < 0 && irq != -EPROBE_DEFER, "device parsing error failed - %d\n", irq); + /* Test that a parsing failure does not return -EPROBE_DEFER */ + np = of_find_node_by_path("/testcase-data/testcase-device2"); + pdev = of_find_device_by_node(np); + unittest(pdev, "device 2 creation failed\n"); + irq = platform_get_irq(pdev, 0); + unittest(irq < 0 && irq != -EPROBE_DEFER, + "device parsing error failed - %d\n", irq); + } np = of_find_node_by_path("/testcase-data/platform-tests"); unittest(np, "No testcase data in device tree\n"); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 0abe2865a3a5..c97ad905e7c9 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1125,12 +1125,12 @@ int pci_save_state(struct pci_dev *dev) EXPORT_SYMBOL(pci_save_state); static void pci_restore_config_dword(struct pci_dev *pdev, int offset, - u32 saved_val, int retry) + u32 saved_val, int retry, bool force) { u32 val; pci_read_config_dword(pdev, offset, &val); - if (val == saved_val) + if (!force && val == saved_val) return; for (;;) { @@ -1149,25 +1149,36 @@ static void pci_restore_config_dword(struct pci_dev *pdev, int offset, } static void pci_restore_config_space_range(struct pci_dev *pdev, - int start, int end, int retry) + int start, int end, int retry, + bool force) { int index; for (index = end; index >= start; index--) pci_restore_config_dword(pdev, 4 * index, pdev->saved_config_space[index], - retry); + retry, force); } static void pci_restore_config_space(struct pci_dev *pdev) { if (pdev->hdr_type == PCI_HEADER_TYPE_NORMAL) { - pci_restore_config_space_range(pdev, 10, 15, 0); + pci_restore_config_space_range(pdev, 10, 15, 0, false); /* Restore BARs before the command register. */ - pci_restore_config_space_range(pdev, 4, 9, 10); - pci_restore_config_space_range(pdev, 0, 3, 0); + pci_restore_config_space_range(pdev, 4, 9, 10, false); + pci_restore_config_space_range(pdev, 0, 3, 0, false); + } else if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE) { + pci_restore_config_space_range(pdev, 12, 15, 0, false); + + /* + * Force rewriting of prefetch registers to avoid S3 resume + * issues on Intel PCI bridges that occur when these + * registers are not explicitly written. + */ + pci_restore_config_space_range(pdev, 9, 11, 0, true); + pci_restore_config_space_range(pdev, 0, 8, 0, false); } else { - pci_restore_config_space_range(pdev, 0, 15, 0); + pci_restore_config_space_range(pdev, 0, 15, 0, false); } } diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index aba59521ad48..31d06f59c4e4 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1264,6 +1264,7 @@ static void tty_driver_remove_tty(struct tty_driver *driver, struct tty_struct * static int tty_reopen(struct tty_struct *tty) { struct tty_driver *driver = tty->driver; + int retval; if (driver->type == TTY_DRIVER_TYPE_PTY && driver->subtype == PTY_TYPE_MASTER) @@ -1277,10 +1278,14 @@ static int tty_reopen(struct tty_struct *tty) tty->count++; - if (!tty->ldisc) - return tty_ldisc_reinit(tty, tty->termios.c_line); + if (tty->ldisc) + return 0; - return 0; + retval = tty_ldisc_reinit(tty, tty->termios.c_line); + if (retval) + tty->count--; + + return retval; } /** diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index f8ee32d9843a..84f52774810a 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1514,6 +1514,7 @@ static void acm_disconnect(struct usb_interface *intf) { struct acm *acm = usb_get_intfdata(intf); struct tty_struct *tty; + int i; /* sibling interface is already cleaning up */ if (!acm) @@ -1544,6 +1545,11 @@ static void acm_disconnect(struct usb_interface *intf) tty_unregister_device(acm_tty_driver, acm->minor); + usb_free_urb(acm->ctrlurb); + for (i = 0; i < ACM_NW; i++) + usb_free_urb(acm->wb[i].urb); + for (i = 0; i < acm->rx_buflimit; i++) + usb_free_urb(acm->read_urbs[i]); acm_write_buffers_free(acm); usb_free_coherent(acm->dev, acm->ctrlsize, acm->ctrl_buffer, acm->ctrl_dma); acm_read_buffers_free(acm); diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c index 7334da9e9779..71d0d33c3286 100644 --- a/drivers/usb/host/xhci-mtk.c +++ b/drivers/usb/host/xhci-mtk.c @@ -642,10 +642,10 @@ static int __maybe_unused xhci_mtk_resume(struct device *dev) xhci_mtk_host_enable(mtk); xhci_dbg(xhci, "%s: restart port polling\n", __func__); - set_bit(HCD_FLAG_POLL_RH, &hcd->flags); - usb_hcd_poll_rh_status(hcd); set_bit(HCD_FLAG_POLL_RH, &xhci->shared_hcd->flags); usb_hcd_poll_rh_status(xhci->shared_hcd); + set_bit(HCD_FLAG_POLL_RH, &hcd->flags); + usb_hcd_poll_rh_status(hcd); return 0; } diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 6372edf339d9..722860eb5a91 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -185,6 +185,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) } if (pdev->vendor == PCI_VENDOR_ID_INTEL && (pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) xhci->quirks |= XHCI_MISSING_CAS; diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 0215b70c4efc..e72ad9f81c73 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -561,6 +561,9 @@ static void option_instat_callback(struct urb *urb); /* Interface is reserved */ #define RSVD(ifnum) ((BIT(ifnum) & 0xff) << 0) +/* Interface must have two endpoints */ +#define NUMEP2 BIT(16) + static const struct usb_device_id option_ids[] = { { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) }, @@ -1081,8 +1084,9 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(4) }, { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96), .driver_info = RSVD(4) }, - { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06), - .driver_info = RSVD(4) | RSVD(5) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff), + .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003), @@ -1999,6 +2003,13 @@ static int option_probe(struct usb_serial *serial, if (device_flags & RSVD(iface_desc->bInterfaceNumber)) return -ENODEV; + /* + * Allow matching on bNumEndpoints for devices whose interface numbers + * can change (e.g. Quectel EP06). + */ + if (device_flags & NUMEP2 && iface_desc->bNumEndpoints != 2) + return -ENODEV; + /* Store the device flags so we can use them during attach. */ usb_set_serial_data(serial, (void *)device_flags); diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c index 40864c2bd9dc..4d0273508043 100644 --- a/drivers/usb/serial/usb-serial-simple.c +++ b/drivers/usb/serial/usb-serial-simple.c @@ -84,7 +84,8 @@ DEVICE(moto_modem, MOTO_IDS); /* Motorola Tetra driver */ #define MOTOROLA_TETRA_IDS() \ - { USB_DEVICE(0x0cad, 0x9011) } /* Motorola Solutions TETRA PEI */ + { USB_DEVICE(0x0cad, 0x9011) }, /* Motorola Solutions TETRA PEI */ \ + { USB_DEVICE(0x0cad, 0x9012) } /* MTP6550 */ DEVICE(motorola_tetra, MOTOROLA_TETRA_IDS); /* Novatel Wireless GPS driver */ diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c index ef69273074ba..a3edb20ea4c3 100644 --- a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c +++ b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c @@ -496,6 +496,9 @@ static int omapfb_memory_read(struct fb_info *fbi, if (!access_ok(VERIFY_WRITE, mr->buffer, mr->buffer_size)) return -EFAULT; + if (mr->w > 4096 || mr->h > 4096) + return -EINVAL; + if (mr->w * mr->h * 3 > mr->buffer_size) return -EINVAL; @@ -509,7 +512,7 @@ static int omapfb_memory_read(struct fb_info *fbi, mr->x, mr->y, mr->w, mr->h); if (r > 0) { - if (copy_to_user(mr->buffer, buf, mr->buffer_size)) + if (copy_to_user(mr->buffer, buf, r)) r = -EFAULT; } diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 9f1c96caebda..782e7243c5c0 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -746,6 +746,7 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr, crc_offset = le32_to_cpu((*cp_block)->checksum_offset); if (crc_offset > (blk_size - sizeof(__le32))) { + f2fs_put_page(*cp_page, 1); f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc_offset: %zu", crc_offset); return -EINVAL; @@ -753,6 +754,7 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr, crc = cur_cp_crc(*cp_block); if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) { + f2fs_put_page(*cp_page, 1); f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value"); return -EINVAL; } @@ -772,14 +774,14 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi, err = get_checkpoint_version(sbi, cp_addr, &cp_block, &cp_page_1, version); if (err) - goto invalid_cp1; + return NULL; pre_version = *version; cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1; err = get_checkpoint_version(sbi, cp_addr, &cp_block, &cp_page_2, version); if (err) - goto invalid_cp2; + goto invalid_cp; cur_version = *version; if (cur_version == pre_version) { @@ -787,9 +789,8 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi, f2fs_put_page(cp_page_2, 1); return cp_page_1; } -invalid_cp2: f2fs_put_page(cp_page_2, 1); -invalid_cp1: +invalid_cp: f2fs_put_page(cp_page_1, 1); return NULL; } diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index bbd1e357c23d..f4fd2e72add4 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -898,8 +898,22 @@ static struct platform_driver ramoops_driver = { }, }; -static void ramoops_register_dummy(void) +static inline void ramoops_unregister_dummy(void) { + platform_device_unregister(dummy); + dummy = NULL; + + kfree(dummy_data); + dummy_data = NULL; +} + +static void __init ramoops_register_dummy(void) +{ + /* + * Prepare a dummy platform data structure to carry the module + * parameters. If mem_size isn't set, then there are no module + * parameters, and we can skip this. + */ if (!mem_size) return; @@ -932,21 +946,28 @@ static void ramoops_register_dummy(void) if (IS_ERR(dummy)) { pr_info("could not create platform device: %ld\n", PTR_ERR(dummy)); + dummy = NULL; + ramoops_unregister_dummy(); } } static int __init ramoops_init(void) { + int ret; + ramoops_register_dummy(); - return platform_driver_register(&ramoops_driver); + ret = platform_driver_register(&ramoops_driver); + if (ret != 0) + ramoops_unregister_dummy(); + + return ret; } late_initcall(ramoops_init); static void __exit ramoops_exit(void) { platform_driver_unregister(&ramoops_driver); - platform_device_unregister(dummy); - kfree(dummy_data); + ramoops_unregister_dummy(); } module_exit(ramoops_exit); diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index c5466c70d620..2a82aeeacba5 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1929,6 +1929,9 @@ static struct ubi_volume_desc *open_ubi(const char *name, int mode) int dev, vol; char *endptr; + if (!name || !*name) + return ERR_PTR(-EINVAL); + /* First, try to open using the device node path method */ ubi = ubi_open_volume_path(name, mode); if (!IS_ERR(ubi)) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 36fa6a2a82e3..4ee95d8c8413 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -140,6 +140,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write); struct page *follow_huge_pd(struct vm_area_struct *vma, @@ -170,6 +172,18 @@ static inline unsigned long hugetlb_total_pages(void) return 0; } +static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, + pte_t *ptep) +{ + return 0; +} + +static inline void adjust_range_if_pmd_sharing_possible( + struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} + #define follow_hugetlb_page(m,v,p,vs,a,b,i,w,n) ({ BUG(); 0; }) #define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL) #define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; }) diff --git a/include/linux/mm.h b/include/linux/mm.h index 68a5121694ef..40ad93bc9548 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2463,6 +2463,12 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, return vma; } +static inline bool range_in_vma(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + return (vma && vma->vm_start <= start && end <= vma->vm_end); +} + #ifdef CONFIG_MMU pgprot_t vm_get_page_prot(unsigned long vm_flags); void vma_set_page_prot(struct vm_area_struct *vma); diff --git a/kernel/events/core.c b/kernel/events/core.c index c7b3e34811ec..ae22d93701db 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3940,6 +3940,12 @@ int perf_event_read_local(struct perf_event *event, u64 *value, goto out; } + /* If this is a pinned event it must be running on this CPU */ + if (event->attr.pinned && event->oncpu != smp_processor_id()) { + ret = -EBUSY; + goto out; + } + /* * If the event is currently on this CPU, its either a per-task event, * or local to this CPU. Furthermore it means its ACTIVE (otherwise diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 25346bd99364..571875b37453 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2929,7 +2929,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) else page_add_file_rmap(new, true); set_pmd_at(mm, mmun_start, pvmw->pmd, pmde); - if (vma->vm_flags & VM_LOCKED) + if ((vma->vm_flags & VM_LOCKED) && !PageDoubleMap(new)) mlock_vma_page(new); update_mmu_cache_pmd(vma, address, pvmw->pmd); } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3103099f64fd..f469315a6a0f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4556,12 +4556,40 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr) /* * check on proper vm_flags and page table alignment */ - if (vma->vm_flags & VM_MAYSHARE && - vma->vm_start <= base && end <= vma->vm_end) + if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end)) return true; return false; } +/* + * Determine if start,end range within vma could be mapped by shared pmd. + * If yes, adjust start and end to cover range associated with possible + * shared pmd mappings. + */ +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ + unsigned long check_addr = *start; + + if (!(vma->vm_flags & VM_MAYSHARE)) + return; + + for (check_addr = *start; check_addr < *end; check_addr += PUD_SIZE) { + unsigned long a_start = check_addr & PUD_MASK; + unsigned long a_end = a_start + PUD_SIZE; + + /* + * If sharing is possible, adjust start/end if necessary. + */ + if (range_in_vma(vma, a_start, a_end)) { + if (a_start < *start) + *start = a_start; + if (a_end > *end) + *end = a_end; + } + } +} + /* * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the @@ -4659,6 +4687,11 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) { return 0; } + +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} #define want_pmd_share() (0) #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ diff --git a/mm/migrate.c b/mm/migrate.c index 8c0af0f7cab1..2a55289ee9f1 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -275,6 +275,9 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new)) mlock_vma_page(new); + if (PageTransHuge(page) && PageMlocked(page)) + clear_page_mlock(page); + /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, pvmw.address, pvmw.pte); } diff --git a/mm/rmap.c b/mm/rmap.c index eb477809a5c0..1e79fac3186b 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1362,11 +1362,21 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } /* - * We have to assume the worse case ie pmd for invalidation. Note that - * the page can not be free in this function as call of try_to_unmap() - * must hold a reference on the page. + * For THP, we have to assume the worse case ie pmd for invalidation. + * For hugetlb, it could be much worse if we need to do pud + * invalidation in the case of pmd sharing. + * + * Note that the page can not be free in this function as call of + * try_to_unmap() must hold a reference on the page. */ end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page))); + if (PageHuge(page)) { + /* + * If sharing is possible, start and end will be adjusted + * accordingly. + */ + adjust_range_if_pmd_sharing_possible(vma, &start, &end); + } mmu_notifier_invalidate_range_start(vma->vm_mm, start, end); while (page_vma_mapped_walk(&pvmw)) { @@ -1409,6 +1419,32 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); address = pvmw.address; + if (PageHuge(page)) { + if (huge_pmd_unshare(mm, &address, pvmw.pte)) { + /* + * huge_pmd_unshare unmapped an entire PMD + * page. There is no way of knowing exactly + * which PMDs may be cached for this mm, so + * we must flush them all. start/end were + * already adjusted above to cover this range. + */ + flush_cache_range(vma, start, end); + flush_tlb_range(vma, start, end); + mmu_notifier_invalidate_range(mm, start, end); + + /* + * The ref count of the PMD page was dropped + * which is part of the way map counting + * is done for shared PMDs. Return 'true' + * here. When there is no other sharing, + * huge_pmd_unshare returns false and we will + * unmap the actual page and drop map count + * to zero. + */ + page_vma_mapped_walk_done(&pvmw); + break; + } + } if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && diff --git a/mm/vmstat.c b/mm/vmstat.c index 8ba0870ecddd..55a5bb1d773d 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1275,6 +1275,9 @@ const char * const vmstat_text[] = { #ifdef CONFIG_SMP "nr_tlb_remote_flush", "nr_tlb_remote_flush_received", +#else + "", /* nr_tlb_remote_flush */ + "", /* nr_tlb_remote_flush_received */ #endif /* CONFIG_SMP */ "nr_tlb_local_flush_all", "nr_tlb_local_flush_one", diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index aa082b71d2e4..c6bbe5b56378 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -427,7 +427,7 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: /* Keys without a station are used for TX only */ - if (key->sta && test_sta_flag(key->sta, WLAN_STA_MFP)) + if (sta && test_sta_flag(sta, WLAN_STA_MFP)) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; case NL80211_IFTYPE_ADHOC: diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 555e389b7dfa..5d22c058ae23 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1756,7 +1756,8 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, if (local->ops->wake_tx_queue && type != NL80211_IFTYPE_AP_VLAN && - type != NL80211_IFTYPE_MONITOR) + (type != NL80211_IFTYPE_MONITOR || + (params->flags & MONITOR_FLAG_ACTIVE))) txq_size += sizeof(struct txq_info) + local->hw.txq_data_size; diff --git a/net/rds/ib.h b/net/rds/ib.h index a6f4d7d68e95..83ff7c18d691 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -371,7 +371,7 @@ void rds_ib_mr_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc); int rds_ib_recv_init(void); void rds_ib_recv_exit(void); int rds_ib_recv_path(struct rds_conn_path *conn); -int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic); +int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic, gfp_t gfp); void rds_ib_recv_free_caches(struct rds_ib_connection *ic); void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp); void rds_ib_inc_free(struct rds_incoming *inc); diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index f1684ae6abfd..6a909ea9e8fb 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -949,7 +949,7 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp) if (!ic) return -ENOMEM; - ret = rds_ib_recv_alloc_caches(ic); + ret = rds_ib_recv_alloc_caches(ic, gfp); if (ret) { kfree(ic); return ret; diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index b4e421aa9727..918d2e676b9b 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -98,12 +98,12 @@ static void rds_ib_cache_xfer_to_ready(struct rds_ib_refill_cache *cache) } } -static int rds_ib_recv_alloc_cache(struct rds_ib_refill_cache *cache) +static int rds_ib_recv_alloc_cache(struct rds_ib_refill_cache *cache, gfp_t gfp) { struct rds_ib_cache_head *head; int cpu; - cache->percpu = alloc_percpu(struct rds_ib_cache_head); + cache->percpu = alloc_percpu_gfp(struct rds_ib_cache_head, gfp); if (!cache->percpu) return -ENOMEM; @@ -118,13 +118,13 @@ static int rds_ib_recv_alloc_cache(struct rds_ib_refill_cache *cache) return 0; } -int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic) +int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic, gfp_t gfp) { int ret; - ret = rds_ib_recv_alloc_cache(&ic->i_cache_incs); + ret = rds_ib_recv_alloc_cache(&ic->i_cache_incs, gfp); if (!ret) { - ret = rds_ib_recv_alloc_cache(&ic->i_cache_frags); + ret = rds_ib_recv_alloc_cache(&ic->i_cache_frags, gfp); if (ret) free_percpu(ic->i_cache_incs.percpu); } diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index a2f76743c73a..82f665728382 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -185,6 +185,7 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, return -ENOMEM; buf->sk = msg->dst_sk; + __tipc_dump_start(&cb, msg->net); do { int rem; @@ -216,6 +217,7 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, err = 0; err_out: + tipc_dump_done(&cb); kfree_skb(buf); if (err == -EMSGSIZE) { diff --git a/net/tipc/socket.c b/net/tipc/socket.c index bdb4a9a5a83a..093e16d1b770 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -3233,7 +3233,7 @@ int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb, struct netlink_callback *cb, struct tipc_sock *tsk)) { - struct rhashtable_iter *iter = (void *)cb->args[0]; + struct rhashtable_iter *iter = (void *)cb->args[4]; struct tipc_sock *tsk; int err; @@ -3269,8 +3269,14 @@ EXPORT_SYMBOL(tipc_nl_sk_walk); int tipc_dump_start(struct netlink_callback *cb) { - struct rhashtable_iter *iter = (void *)cb->args[0]; - struct net *net = sock_net(cb->skb->sk); + return __tipc_dump_start(cb, sock_net(cb->skb->sk)); +} +EXPORT_SYMBOL(tipc_dump_start); + +int __tipc_dump_start(struct netlink_callback *cb, struct net *net) +{ + /* tipc_nl_name_table_dump() uses cb->args[0...3]. */ + struct rhashtable_iter *iter = (void *)cb->args[4]; struct tipc_net *tn = tipc_net(net); if (!iter) { @@ -3278,17 +3284,16 @@ int tipc_dump_start(struct netlink_callback *cb) if (!iter) return -ENOMEM; - cb->args[0] = (long)iter; + cb->args[4] = (long)iter; } rhashtable_walk_enter(&tn->sk_rht, iter); return 0; } -EXPORT_SYMBOL(tipc_dump_start); int tipc_dump_done(struct netlink_callback *cb) { - struct rhashtable_iter *hti = (void *)cb->args[0]; + struct rhashtable_iter *hti = (void *)cb->args[4]; rhashtable_walk_exit(hti); kfree(hti); diff --git a/net/tipc/socket.h b/net/tipc/socket.h index d43032e26532..5e575f205afe 100644 --- a/net/tipc/socket.h +++ b/net/tipc/socket.h @@ -69,5 +69,6 @@ int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb, struct netlink_callback *cb, struct tipc_sock *tsk)); int tipc_dump_start(struct netlink_callback *cb); +int __tipc_dump_start(struct netlink_callback *cb, struct net *net); int tipc_dump_done(struct netlink_callback *cb); #endif diff --git a/tools/testing/selftests/x86/test_vdso.c b/tools/testing/selftests/x86/test_vdso.c index 235259011704..35edd61d1663 100644 --- a/tools/testing/selftests/x86/test_vdso.c +++ b/tools/testing/selftests/x86/test_vdso.c @@ -17,6 +17,7 @@ #include <errno.h> #include <sched.h> #include <stdbool.h> +#include <limits.h> #ifndef SYS_getcpu # ifdef __x86_64__ @@ -31,6 +32,14 @@ int nerrs = 0; +typedef int (*vgettime_t)(clockid_t, struct timespec *); + +vgettime_t vdso_clock_gettime; + +typedef long (*vgtod_t)(struct timeval *tv, struct timezone *tz); + +vgtod_t vdso_gettimeofday; + typedef long (*getcpu_t)(unsigned *, unsigned *, void *); getcpu_t vgetcpu; @@ -95,6 +104,15 @@ static void fill_function_pointers() printf("Warning: failed to find getcpu in vDSO\n"); vgetcpu = (getcpu_t) vsyscall_getcpu(); + + vdso_clock_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime"); + if (!vdso_clock_gettime) + printf("Warning: failed to find clock_gettime in vDSO\n"); + + vdso_gettimeofday = (vgtod_t)dlsym(vdso, "__vdso_gettimeofday"); + if (!vdso_gettimeofday) + printf("Warning: failed to find gettimeofday in vDSO\n"); + } static long sys_getcpu(unsigned * cpu, unsigned * node, @@ -103,6 +121,16 @@ static long sys_getcpu(unsigned * cpu, unsigned * node, return syscall(__NR_getcpu, cpu, node, cache); } +static inline int sys_clock_gettime(clockid_t id, struct timespec *ts) +{ + return syscall(__NR_clock_gettime, id, ts); +} + +static inline int sys_gettimeofday(struct timeval *tv, struct timezone *tz) +{ + return syscall(__NR_gettimeofday, tv, tz); +} + static void test_getcpu(void) { printf("[RUN]\tTesting getcpu...\n"); @@ -155,10 +183,154 @@ static void test_getcpu(void) } } +static bool ts_leq(const struct timespec *a, const struct timespec *b) +{ + if (a->tv_sec != b->tv_sec) + return a->tv_sec < b->tv_sec; + else + return a->tv_nsec <= b->tv_nsec; +} + +static bool tv_leq(const struct timeval *a, const struct timeval *b) +{ + if (a->tv_sec != b->tv_sec) + return a->tv_sec < b->tv_sec; + else + return a->tv_usec <= b->tv_usec; +} + +static char const * const clocknames[] = { + [0] = "CLOCK_REALTIME", + [1] = "CLOCK_MONOTONIC", + [2] = "CLOCK_PROCESS_CPUTIME_ID", + [3] = "CLOCK_THREAD_CPUTIME_ID", + [4] = "CLOCK_MONOTONIC_RAW", + [5] = "CLOCK_REALTIME_COARSE", + [6] = "CLOCK_MONOTONIC_COARSE", + [7] = "CLOCK_BOOTTIME", + [8] = "CLOCK_REALTIME_ALARM", + [9] = "CLOCK_BOOTTIME_ALARM", + [10] = "CLOCK_SGI_CYCLE", + [11] = "CLOCK_TAI", +}; + +static void test_one_clock_gettime(int clock, const char *name) +{ + struct timespec start, vdso, end; + int vdso_ret, end_ret; + + printf("[RUN]\tTesting clock_gettime for clock %s (%d)...\n", name, clock); + + if (sys_clock_gettime(clock, &start) < 0) { + if (errno == EINVAL) { + vdso_ret = vdso_clock_gettime(clock, &vdso); + if (vdso_ret == -EINVAL) { + printf("[OK]\tNo such clock.\n"); + } else { + printf("[FAIL]\tNo such clock, but __vdso_clock_gettime returned %d\n", vdso_ret); + nerrs++; + } + } else { + printf("[WARN]\t clock_gettime(%d) syscall returned error %d\n", clock, errno); + } + return; + } + + vdso_ret = vdso_clock_gettime(clock, &vdso); + end_ret = sys_clock_gettime(clock, &end); + + if (vdso_ret != 0 || end_ret != 0) { + printf("[FAIL]\tvDSO returned %d, syscall errno=%d\n", + vdso_ret, errno); + nerrs++; + return; + } + + printf("\t%llu.%09ld %llu.%09ld %llu.%09ld\n", + (unsigned long long)start.tv_sec, start.tv_nsec, + (unsigned long long)vdso.tv_sec, vdso.tv_nsec, + (unsigned long long)end.tv_sec, end.tv_nsec); + + if (!ts_leq(&start, &vdso) || !ts_leq(&vdso, &end)) { + printf("[FAIL]\tTimes are out of sequence\n"); + nerrs++; + } +} + +static void test_clock_gettime(void) +{ + for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]); + clock++) { + test_one_clock_gettime(clock, clocknames[clock]); + } + + /* Also test some invalid clock ids */ + test_one_clock_gettime(-1, "invalid"); + test_one_clock_gettime(INT_MIN, "invalid"); + test_one_clock_gettime(INT_MAX, "invalid"); +} + +static void test_gettimeofday(void) +{ + struct timeval start, vdso, end; + struct timezone sys_tz, vdso_tz; + int vdso_ret, end_ret; + + if (!vdso_gettimeofday) + return; + + printf("[RUN]\tTesting gettimeofday...\n"); + + if (sys_gettimeofday(&start, &sys_tz) < 0) { + printf("[FAIL]\tsys_gettimeofday failed (%d)\n", errno); + nerrs++; + return; + } + + vdso_ret = vdso_gettimeofday(&vdso, &vdso_tz); + end_ret = sys_gettimeofday(&end, NULL); + + if (vdso_ret != 0 || end_ret != 0) { + printf("[FAIL]\tvDSO returned %d, syscall errno=%d\n", + vdso_ret, errno); + nerrs++; + return; + } + + printf("\t%llu.%06ld %llu.%06ld %llu.%06ld\n", + (unsigned long long)start.tv_sec, start.tv_usec, + (unsigned long long)vdso.tv_sec, vdso.tv_usec, + (unsigned long long)end.tv_sec, end.tv_usec); + + if (!tv_leq(&start, &vdso) || !tv_leq(&vdso, &end)) { + printf("[FAIL]\tTimes are out of sequence\n"); + nerrs++; + } + + if (sys_tz.tz_minuteswest == vdso_tz.tz_minuteswest && + sys_tz.tz_dsttime == vdso_tz.tz_dsttime) { + printf("[OK]\ttimezones match: minuteswest=%d, dsttime=%d\n", + sys_tz.tz_minuteswest, sys_tz.tz_dsttime); + } else { + printf("[FAIL]\ttimezones do not match\n"); + nerrs++; + } + + /* And make sure that passing NULL for tz doesn't crash. */ + vdso_gettimeofday(&vdso, NULL); +} + int main(int argc, char **argv) { fill_function_pointers(); + test_clock_gettime(); + test_gettimeofday(); + + /* + * Test getcpu() last so that, if something goes wrong setting affinity, + * we still run the other tests. + */ test_getcpu(); return nerrs ? 1 : 0;