diff --git a/Makefile b/Makefile index 30600e309c73..e16d2e58ed4b 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 4 -SUBLEVEL = 15 +SUBLEVEL = 16 EXTRAVERSION = NAME = Kleptomaniac Octopus diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 15b75005bc34..3fa1b962dc27 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -600,8 +600,11 @@ extern void slb_set_size(u16 size); * */ #define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 2) + +// The + 2 accounts for INVALID_REGION and 1 more to avoid overlap with kernel #define MIN_USER_CONTEXT (MAX_KERNEL_CTX_CNT + MAX_VMALLOC_CTX_CNT + \ - MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT) + MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT + 2) + /* * For platforms that support on 65bit VA we limit the context bits */ diff --git a/arch/powerpc/include/asm/xive-regs.h b/arch/powerpc/include/asm/xive-regs.h index f2dfcd50a2d3..33aee7490cbb 100644 --- a/arch/powerpc/include/asm/xive-regs.h +++ b/arch/powerpc/include/asm/xive-regs.h @@ -39,6 +39,7 @@ #define XIVE_ESB_VAL_P 0x2 #define XIVE_ESB_VAL_Q 0x1 +#define XIVE_ESB_INVALID 0xFF /* * Thread Management (aka "TM") registers diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index f5fadbd2533a..9651ca061828 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -972,12 +972,21 @@ static int xive_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state which, bool *state) { struct xive_irq_data *xd = irq_data_get_irq_handler_data(data); + u8 pq; switch (which) { case IRQCHIP_STATE_ACTIVE: - *state = !xd->stale_p && - (xd->saved_p || - !!(xive_esb_read(xd, XIVE_ESB_GET) & XIVE_ESB_VAL_P)); + pq = xive_esb_read(xd, XIVE_ESB_GET); + + /* + * The esb value being all 1's means we couldn't get + * the PQ state of the interrupt through mmio. It may + * happen, for example when querying a PHB interrupt + * while the PHB is in an error state. We consider the + * interrupt to be inactive in that case. + */ + *state = (pq != XIVE_ESB_INVALID) && !xd->stale_p && + (xd->saved_p || !!(pq & XIVE_ESB_VAL_P)); return 0; default: return -EINVAL; diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c index 2bbab0230aeb..d287837ed755 100644 --- a/drivers/atm/firestream.c +++ b/drivers/atm/firestream.c @@ -912,6 +912,7 @@ static int fs_open(struct atm_vcc *atm_vcc) } if (!to) { printk ("No more free channels for FS50..\n"); + kfree(vcc); return -EBUSY; } vcc->channo = dev->channo; @@ -922,6 +923,7 @@ static int fs_open(struct atm_vcc *atm_vcc) if (((DO_DIRECTION(rxtp) && dev->atm_vccs[vcc->channo])) || ( DO_DIRECTION(txtp) && test_bit (vcc->channo, dev->tx_inuse))) { printk ("Channel is in use for FS155.\n"); + kfree(vcc); return -EBUSY; } } @@ -935,6 +937,7 @@ static int fs_open(struct atm_vcc *atm_vcc) tc, sizeof (struct fs_transmit_config)); if (!tc) { fs_dprintk (FS_DEBUG_OPEN, "fs: can't alloc transmit_config.\n"); + kfree(vcc); return -ENOMEM; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_busy.c b/drivers/gpu/drm/i915/gem/i915_gem_busy.c index 3d4f5775a4ba..25235ef630c1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_busy.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_busy.c @@ -9,16 +9,16 @@ #include "i915_gem_ioctls.h" #include "i915_gem_object.h" -static __always_inline u32 __busy_read_flag(u8 id) +static __always_inline u32 __busy_read_flag(u16 id) { - if (id == (u8)I915_ENGINE_CLASS_INVALID) + if (id == (u16)I915_ENGINE_CLASS_INVALID) return 0xffff0000u; GEM_BUG_ON(id >= 16); return 0x10000u << id; } -static __always_inline u32 __busy_write_id(u8 id) +static __always_inline u32 __busy_write_id(u16 id) { /* * The uABI guarantees an active writer is also amongst the read @@ -29,14 +29,14 @@ static __always_inline u32 __busy_write_id(u8 id) * last_read - hence we always set both read and write busy for * last_write. */ - if (id == (u8)I915_ENGINE_CLASS_INVALID) + if (id == (u16)I915_ENGINE_CLASS_INVALID) return 0xffffffffu; return (id + 1) | __busy_read_flag(id); } static __always_inline unsigned int -__busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u8 id)) +__busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u16 id)) { const struct i915_request *rq; @@ -57,7 +57,7 @@ __busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u8 id)) return 0; /* Beware type-expansion follies! */ - BUILD_BUG_ON(!typecheck(u8, rq->engine->uabi_class)); + BUILD_BUG_ON(!typecheck(u16, rq->engine->uabi_class)); return flag(rq->engine->uabi_class); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index abfbac49b8e8..968d9b2705d0 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -427,7 +427,7 @@ struct get_pages_work { static struct sg_table * __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj, - struct page **pvec, int num_pages) + struct page **pvec, unsigned long num_pages) { unsigned int max_segment = i915_sg_segment_size(); struct sg_table *st; @@ -473,9 +473,10 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work) { struct get_pages_work *work = container_of(_work, typeof(*work), work); struct drm_i915_gem_object *obj = work->obj; - const int npages = obj->base.size >> PAGE_SHIFT; + const unsigned long npages = obj->base.size >> PAGE_SHIFT; + unsigned long pinned; struct page **pvec; - int pinned, ret; + int ret; ret = -ENOMEM; pinned = 0; @@ -578,7 +579,7 @@ __i915_gem_userptr_get_pages_schedule(struct drm_i915_gem_object *obj) static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) { - const int num_pages = obj->base.size >> PAGE_SHIFT; + const unsigned long num_pages = obj->base.size >> PAGE_SHIFT; struct mm_struct *mm = obj->userptr.mm->mm; struct page **pvec; struct sg_table *pages; diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 9dd8c299cb2d..798e1b024406 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -300,8 +300,8 @@ struct intel_engine_cs { u8 class; u8 instance; - u8 uabi_class; - u8 uabi_instance; + u16 uabi_class; + u16 uabi_instance; u32 context_size; u32 mmio_base; diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index b1a7a8b9b46a..f614646ed3f9 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -1178,6 +1178,7 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt, pd = i915_pd_entry(pdp, gen8_pd_index(idx, 2)); vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1))); do { + GEM_BUG_ON(iter->sg->length < I915_GTT_PAGE_SIZE); vaddr[gen8_pd_index(idx, 0)] = pte_encode | iter->dma; iter->dma += I915_GTT_PAGE_SIZE; @@ -1657,6 +1658,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm, vaddr = kmap_atomic_px(i915_pt_entry(pd, act_pt)); do { + GEM_BUG_ON(iter.sg->length < I915_GTT_PAGE_SIZE); vaddr[act_pte] = pte_encode | GEN6_PTE_ADDR_ENCODE(iter.dma); iter.dma += I915_GTT_PAGE_SIZE; diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index 1c67ac434e10..5906c80c4b2c 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -78,8 +78,10 @@ static int panfrost_ioctl_get_param(struct drm_device *ddev, void *data, struct static int panfrost_ioctl_create_bo(struct drm_device *dev, void *data, struct drm_file *file) { + struct panfrost_file_priv *priv = file->driver_priv; struct panfrost_gem_object *bo; struct drm_panfrost_create_bo *args = data; + struct panfrost_gem_mapping *mapping; if (!args->size || args->pad || (args->flags & ~(PANFROST_BO_NOEXEC | PANFROST_BO_HEAP))) @@ -95,7 +97,14 @@ static int panfrost_ioctl_create_bo(struct drm_device *dev, void *data, if (IS_ERR(bo)) return PTR_ERR(bo); - args->offset = bo->node.start << PAGE_SHIFT; + mapping = panfrost_gem_mapping_get(bo, priv); + if (!mapping) { + drm_gem_object_put_unlocked(&bo->base.base); + return -EINVAL; + } + + args->offset = mapping->mmnode.start << PAGE_SHIFT; + panfrost_gem_mapping_put(mapping); return 0; } @@ -119,6 +128,11 @@ panfrost_lookup_bos(struct drm_device *dev, struct drm_panfrost_submit *args, struct panfrost_job *job) { + struct panfrost_file_priv *priv = file_priv->driver_priv; + struct panfrost_gem_object *bo; + unsigned int i; + int ret; + job->bo_count = args->bo_handle_count; if (!job->bo_count) @@ -130,9 +144,32 @@ panfrost_lookup_bos(struct drm_device *dev, if (!job->implicit_fences) return -ENOMEM; - return drm_gem_objects_lookup(file_priv, - (void __user *)(uintptr_t)args->bo_handles, - job->bo_count, &job->bos); + ret = drm_gem_objects_lookup(file_priv, + (void __user *)(uintptr_t)args->bo_handles, + job->bo_count, &job->bos); + if (ret) + return ret; + + job->mappings = kvmalloc_array(job->bo_count, + sizeof(struct panfrost_gem_mapping *), + GFP_KERNEL | __GFP_ZERO); + if (!job->mappings) + return -ENOMEM; + + for (i = 0; i < job->bo_count; i++) { + struct panfrost_gem_mapping *mapping; + + bo = to_panfrost_bo(job->bos[i]); + mapping = panfrost_gem_mapping_get(bo, priv); + if (!mapping) { + ret = -EINVAL; + break; + } + + job->mappings[i] = mapping; + } + + return ret; } /** @@ -320,7 +357,9 @@ out: static int panfrost_ioctl_get_bo_offset(struct drm_device *dev, void *data, struct drm_file *file_priv) { + struct panfrost_file_priv *priv = file_priv->driver_priv; struct drm_panfrost_get_bo_offset *args = data; + struct panfrost_gem_mapping *mapping; struct drm_gem_object *gem_obj; struct panfrost_gem_object *bo; @@ -331,18 +370,26 @@ static int panfrost_ioctl_get_bo_offset(struct drm_device *dev, void *data, } bo = to_panfrost_bo(gem_obj); - args->offset = bo->node.start << PAGE_SHIFT; - + mapping = panfrost_gem_mapping_get(bo, priv); drm_gem_object_put_unlocked(gem_obj); + + if (!mapping) + return -EINVAL; + + args->offset = mapping->mmnode.start << PAGE_SHIFT; + panfrost_gem_mapping_put(mapping); return 0; } static int panfrost_ioctl_madvise(struct drm_device *dev, void *data, struct drm_file *file_priv) { + struct panfrost_file_priv *priv = file_priv->driver_priv; struct drm_panfrost_madvise *args = data; struct panfrost_device *pfdev = dev->dev_private; struct drm_gem_object *gem_obj; + struct panfrost_gem_object *bo; + int ret = 0; gem_obj = drm_gem_object_lookup(file_priv, args->handle); if (!gem_obj) { @@ -350,22 +397,48 @@ static int panfrost_ioctl_madvise(struct drm_device *dev, void *data, return -ENOENT; } + bo = to_panfrost_bo(gem_obj); + mutex_lock(&pfdev->shrinker_lock); + mutex_lock(&bo->mappings.lock); + if (args->madv == PANFROST_MADV_DONTNEED) { + struct panfrost_gem_mapping *first; + + first = list_first_entry(&bo->mappings.list, + struct panfrost_gem_mapping, + node); + + /* + * If we want to mark the BO purgeable, there must be only one + * user: the caller FD. + * We could do something smarter and mark the BO purgeable only + * when all its users have marked it purgeable, but globally + * visible/shared BOs are likely to never be marked purgeable + * anyway, so let's not bother. + */ + if (!list_is_singular(&bo->mappings.list) || + WARN_ON_ONCE(first->mmu != &priv->mmu)) { + ret = -EINVAL; + goto out_unlock_mappings; + } + } + args->retained = drm_gem_shmem_madvise(gem_obj, args->madv); if (args->retained) { - struct panfrost_gem_object *bo = to_panfrost_bo(gem_obj); - if (args->madv == PANFROST_MADV_DONTNEED) list_add_tail(&bo->base.madv_list, &pfdev->shrinker_list); else if (args->madv == PANFROST_MADV_WILLNEED) list_del_init(&bo->base.madv_list); } + +out_unlock_mappings: + mutex_unlock(&bo->mappings.lock); mutex_unlock(&pfdev->shrinker_lock); drm_gem_object_put_unlocked(gem_obj); - return 0; + return ret; } int panfrost_unstable_ioctl_check(void) diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c index 92a95210a899..77c3a3855c68 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem.c @@ -29,6 +29,12 @@ static void panfrost_gem_free_object(struct drm_gem_object *obj) list_del_init(&bo->base.madv_list); mutex_unlock(&pfdev->shrinker_lock); + /* + * If we still have mappings attached to the BO, there's a problem in + * our refcounting. + */ + WARN_ON_ONCE(!list_empty(&bo->mappings.list)); + if (bo->sgts) { int i; int n_sgt = bo->base.base.size / SZ_2M; @@ -46,6 +52,69 @@ static void panfrost_gem_free_object(struct drm_gem_object *obj) drm_gem_shmem_free_object(obj); } +struct panfrost_gem_mapping * +panfrost_gem_mapping_get(struct panfrost_gem_object *bo, + struct panfrost_file_priv *priv) +{ + struct panfrost_gem_mapping *iter, *mapping = NULL; + + mutex_lock(&bo->mappings.lock); + list_for_each_entry(iter, &bo->mappings.list, node) { + if (iter->mmu == &priv->mmu) { + kref_get(&iter->refcount); + mapping = iter; + break; + } + } + mutex_unlock(&bo->mappings.lock); + + return mapping; +} + +static void +panfrost_gem_teardown_mapping(struct panfrost_gem_mapping *mapping) +{ + struct panfrost_file_priv *priv; + + if (mapping->active) + panfrost_mmu_unmap(mapping); + + priv = container_of(mapping->mmu, struct panfrost_file_priv, mmu); + spin_lock(&priv->mm_lock); + if (drm_mm_node_allocated(&mapping->mmnode)) + drm_mm_remove_node(&mapping->mmnode); + spin_unlock(&priv->mm_lock); +} + +static void panfrost_gem_mapping_release(struct kref *kref) +{ + struct panfrost_gem_mapping *mapping; + + mapping = container_of(kref, struct panfrost_gem_mapping, refcount); + + panfrost_gem_teardown_mapping(mapping); + drm_gem_object_put_unlocked(&mapping->obj->base.base); + kfree(mapping); +} + +void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping) +{ + if (!mapping) + return; + + kref_put(&mapping->refcount, panfrost_gem_mapping_release); +} + +void panfrost_gem_teardown_mappings(struct panfrost_gem_object *bo) +{ + struct panfrost_gem_mapping *mapping; + + mutex_lock(&bo->mappings.lock); + list_for_each_entry(mapping, &bo->mappings.list, node) + panfrost_gem_teardown_mapping(mapping); + mutex_unlock(&bo->mappings.lock); +} + int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv) { int ret; @@ -54,6 +123,16 @@ int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv) struct panfrost_gem_object *bo = to_panfrost_bo(obj); unsigned long color = bo->noexec ? PANFROST_BO_NOEXEC : 0; struct panfrost_file_priv *priv = file_priv->driver_priv; + struct panfrost_gem_mapping *mapping; + + mapping = kzalloc(sizeof(*mapping), GFP_KERNEL); + if (!mapping) + return -ENOMEM; + + INIT_LIST_HEAD(&mapping->node); + kref_init(&mapping->refcount); + drm_gem_object_get(obj); + mapping->obj = bo; /* * Executable buffers cannot cross a 16MB boundary as the program @@ -66,37 +145,48 @@ int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv) else align = size >= SZ_2M ? SZ_2M >> PAGE_SHIFT : 0; - bo->mmu = &priv->mmu; + mapping->mmu = &priv->mmu; spin_lock(&priv->mm_lock); - ret = drm_mm_insert_node_generic(&priv->mm, &bo->node, + ret = drm_mm_insert_node_generic(&priv->mm, &mapping->mmnode, size >> PAGE_SHIFT, align, color, 0); spin_unlock(&priv->mm_lock); if (ret) - return ret; + goto err; if (!bo->is_heap) { - ret = panfrost_mmu_map(bo); - if (ret) { - spin_lock(&priv->mm_lock); - drm_mm_remove_node(&bo->node); - spin_unlock(&priv->mm_lock); - } + ret = panfrost_mmu_map(mapping); + if (ret) + goto err; } + + mutex_lock(&bo->mappings.lock); + WARN_ON(bo->base.madv != PANFROST_MADV_WILLNEED); + list_add_tail(&mapping->node, &bo->mappings.list); + mutex_unlock(&bo->mappings.lock); + +err: + if (ret) + panfrost_gem_mapping_put(mapping); return ret; } void panfrost_gem_close(struct drm_gem_object *obj, struct drm_file *file_priv) { - struct panfrost_gem_object *bo = to_panfrost_bo(obj); struct panfrost_file_priv *priv = file_priv->driver_priv; + struct panfrost_gem_object *bo = to_panfrost_bo(obj); + struct panfrost_gem_mapping *mapping = NULL, *iter; - if (bo->is_mapped) - panfrost_mmu_unmap(bo); + mutex_lock(&bo->mappings.lock); + list_for_each_entry(iter, &bo->mappings.list, node) { + if (iter->mmu == &priv->mmu) { + mapping = iter; + list_del(&iter->node); + break; + } + } + mutex_unlock(&bo->mappings.lock); - spin_lock(&priv->mm_lock); - if (drm_mm_node_allocated(&bo->node)) - drm_mm_remove_node(&bo->node); - spin_unlock(&priv->mm_lock); + panfrost_gem_mapping_put(mapping); } static int panfrost_gem_pin(struct drm_gem_object *obj) @@ -136,6 +226,8 @@ struct drm_gem_object *panfrost_gem_create_object(struct drm_device *dev, size_t if (!obj) return NULL; + INIT_LIST_HEAD(&obj->mappings.list); + mutex_init(&obj->mappings.lock); obj->base.base.funcs = &panfrost_gem_funcs; return &obj->base.base; diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h index 4b17e7308764..ca1bc9019600 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.h +++ b/drivers/gpu/drm/panfrost/panfrost_gem.h @@ -13,23 +13,46 @@ struct panfrost_gem_object { struct drm_gem_shmem_object base; struct sg_table *sgts; - struct panfrost_mmu *mmu; - struct drm_mm_node node; - bool is_mapped :1; + /* + * Use a list for now. If searching a mapping ever becomes the + * bottleneck, we should consider using an RB-tree, or even better, + * let the core store drm_gem_object_mapping entries (where we + * could place driver specific data) instead of drm_gem_object ones + * in its drm_file->object_idr table. + * + * struct drm_gem_object_mapping { + * struct drm_gem_object *obj; + * void *driver_priv; + * }; + */ + struct { + struct list_head list; + struct mutex lock; + } mappings; + bool noexec :1; bool is_heap :1; }; +struct panfrost_gem_mapping { + struct list_head node; + struct kref refcount; + struct panfrost_gem_object *obj; + struct drm_mm_node mmnode; + struct panfrost_mmu *mmu; + bool active :1; +}; + static inline struct panfrost_gem_object *to_panfrost_bo(struct drm_gem_object *obj) { return container_of(to_drm_gem_shmem_obj(obj), struct panfrost_gem_object, base); } -static inline -struct panfrost_gem_object *drm_mm_node_to_panfrost_bo(struct drm_mm_node *node) +static inline struct panfrost_gem_mapping * +drm_mm_node_to_panfrost_mapping(struct drm_mm_node *node) { - return container_of(node, struct panfrost_gem_object, node); + return container_of(node, struct panfrost_gem_mapping, mmnode); } struct drm_gem_object *panfrost_gem_create_object(struct drm_device *dev, size_t size); @@ -49,6 +72,12 @@ int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv); void panfrost_gem_close(struct drm_gem_object *obj, struct drm_file *file_priv); +struct panfrost_gem_mapping * +panfrost_gem_mapping_get(struct panfrost_gem_object *bo, + struct panfrost_file_priv *priv); +void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping); +void panfrost_gem_teardown_mappings(struct panfrost_gem_object *bo); + void panfrost_gem_shrinker_init(struct drm_device *dev); void panfrost_gem_shrinker_cleanup(struct drm_device *dev); diff --git a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c index 458f0fa68111..f5dd7b29bc95 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c @@ -39,11 +39,12 @@ panfrost_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc static bool panfrost_gem_purge(struct drm_gem_object *obj) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); + struct panfrost_gem_object *bo = to_panfrost_bo(obj); if (!mutex_trylock(&shmem->pages_lock)) return false; - panfrost_mmu_unmap(to_panfrost_bo(obj)); + panfrost_gem_teardown_mappings(bo); drm_gem_shmem_purge_locked(obj); mutex_unlock(&shmem->pages_lock); diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index 21f34d44aac2..bbb0c5e3ca6f 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -269,9 +269,20 @@ static void panfrost_job_cleanup(struct kref *ref) dma_fence_put(job->done_fence); dma_fence_put(job->render_done_fence); - if (job->bos) { + if (job->mappings) { for (i = 0; i < job->bo_count; i++) + panfrost_gem_mapping_put(job->mappings[i]); + kvfree(job->mappings); + } + + if (job->bos) { + struct panfrost_gem_object *bo; + + for (i = 0; i < job->bo_count; i++) { + bo = to_panfrost_bo(job->bos[i]); drm_gem_object_put_unlocked(job->bos[i]); + } + kvfree(job->bos); } diff --git a/drivers/gpu/drm/panfrost/panfrost_job.h b/drivers/gpu/drm/panfrost/panfrost_job.h index 62454128a792..bbd3ba97ff67 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.h +++ b/drivers/gpu/drm/panfrost/panfrost_job.h @@ -32,6 +32,7 @@ struct panfrost_job { /* Exclusive fences we have taken from the BOs to wait for */ struct dma_fence **implicit_fences; + struct panfrost_gem_mapping **mappings; struct drm_gem_object **bos; u32 bo_count; diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index a3ed64a1f15e..763cfca886a7 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -269,14 +269,15 @@ static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu, return 0; } -int panfrost_mmu_map(struct panfrost_gem_object *bo) +int panfrost_mmu_map(struct panfrost_gem_mapping *mapping) { + struct panfrost_gem_object *bo = mapping->obj; struct drm_gem_object *obj = &bo->base.base; struct panfrost_device *pfdev = to_panfrost_device(obj->dev); struct sg_table *sgt; int prot = IOMMU_READ | IOMMU_WRITE; - if (WARN_ON(bo->is_mapped)) + if (WARN_ON(mapping->active)) return 0; if (bo->noexec) @@ -286,25 +287,28 @@ int panfrost_mmu_map(struct panfrost_gem_object *bo) if (WARN_ON(IS_ERR(sgt))) return PTR_ERR(sgt); - mmu_map_sg(pfdev, bo->mmu, bo->node.start << PAGE_SHIFT, prot, sgt); - bo->is_mapped = true; + mmu_map_sg(pfdev, mapping->mmu, mapping->mmnode.start << PAGE_SHIFT, + prot, sgt); + mapping->active = true; return 0; } -void panfrost_mmu_unmap(struct panfrost_gem_object *bo) +void panfrost_mmu_unmap(struct panfrost_gem_mapping *mapping) { + struct panfrost_gem_object *bo = mapping->obj; struct drm_gem_object *obj = &bo->base.base; struct panfrost_device *pfdev = to_panfrost_device(obj->dev); - struct io_pgtable_ops *ops = bo->mmu->pgtbl_ops; - u64 iova = bo->node.start << PAGE_SHIFT; - size_t len = bo->node.size << PAGE_SHIFT; + struct io_pgtable_ops *ops = mapping->mmu->pgtbl_ops; + u64 iova = mapping->mmnode.start << PAGE_SHIFT; + size_t len = mapping->mmnode.size << PAGE_SHIFT; size_t unmapped_len = 0; - if (WARN_ON(!bo->is_mapped)) + if (WARN_ON(!mapping->active)) return; - dev_dbg(pfdev->dev, "unmap: as=%d, iova=%llx, len=%zx", bo->mmu->as, iova, len); + dev_dbg(pfdev->dev, "unmap: as=%d, iova=%llx, len=%zx", + mapping->mmu->as, iova, len); while (unmapped_len < len) { size_t unmapped_page; @@ -318,8 +322,9 @@ void panfrost_mmu_unmap(struct panfrost_gem_object *bo) unmapped_len += pgsize; } - panfrost_mmu_flush_range(pfdev, bo->mmu, bo->node.start << PAGE_SHIFT, len); - bo->is_mapped = false; + panfrost_mmu_flush_range(pfdev, mapping->mmu, + mapping->mmnode.start << PAGE_SHIFT, len); + mapping->active = false; } static void mmu_tlb_inv_context_s1(void *cookie) @@ -394,10 +399,10 @@ void panfrost_mmu_pgtable_free(struct panfrost_file_priv *priv) free_io_pgtable_ops(mmu->pgtbl_ops); } -static struct panfrost_gem_object * -addr_to_drm_mm_node(struct panfrost_device *pfdev, int as, u64 addr) +static struct panfrost_gem_mapping * +addr_to_mapping(struct panfrost_device *pfdev, int as, u64 addr) { - struct panfrost_gem_object *bo = NULL; + struct panfrost_gem_mapping *mapping = NULL; struct panfrost_file_priv *priv; struct drm_mm_node *node; u64 offset = addr >> PAGE_SHIFT; @@ -418,8 +423,9 @@ found_mmu: drm_mm_for_each_node(node, &priv->mm) { if (offset >= node->start && offset < (node->start + node->size)) { - bo = drm_mm_node_to_panfrost_bo(node); - drm_gem_object_get(&bo->base.base); + mapping = drm_mm_node_to_panfrost_mapping(node); + + kref_get(&mapping->refcount); break; } } @@ -427,7 +433,7 @@ found_mmu: spin_unlock(&priv->mm_lock); out: spin_unlock(&pfdev->as_lock); - return bo; + return mapping; } #define NUM_FAULT_PAGES (SZ_2M / PAGE_SIZE) @@ -436,28 +442,30 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, u64 addr) { int ret, i; + struct panfrost_gem_mapping *bomapping; struct panfrost_gem_object *bo; struct address_space *mapping; pgoff_t page_offset; struct sg_table *sgt; struct page **pages; - bo = addr_to_drm_mm_node(pfdev, as, addr); - if (!bo) + bomapping = addr_to_mapping(pfdev, as, addr); + if (!bomapping) return -ENOENT; + bo = bomapping->obj; if (!bo->is_heap) { dev_WARN(pfdev->dev, "matching BO is not heap type (GPU VA = %llx)", - bo->node.start << PAGE_SHIFT); + bomapping->mmnode.start << PAGE_SHIFT); ret = -EINVAL; goto err_bo; } - WARN_ON(bo->mmu->as != as); + WARN_ON(bomapping->mmu->as != as); /* Assume 2MB alignment and size multiple */ addr &= ~((u64)SZ_2M - 1); page_offset = addr >> PAGE_SHIFT; - page_offset -= bo->node.start; + page_offset -= bomapping->mmnode.start; mutex_lock(&bo->base.pages_lock); @@ -509,13 +517,14 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, goto err_map; } - mmu_map_sg(pfdev, bo->mmu, addr, IOMMU_WRITE | IOMMU_READ | IOMMU_NOEXEC, sgt); + mmu_map_sg(pfdev, bomapping->mmu, addr, + IOMMU_WRITE | IOMMU_READ | IOMMU_NOEXEC, sgt); - bo->is_mapped = true; + bomapping->active = true; dev_dbg(pfdev->dev, "mapped page fault @ AS%d %llx", as, addr); - drm_gem_object_put_unlocked(&bo->base.base); + panfrost_gem_mapping_put(bomapping); return 0; diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.h b/drivers/gpu/drm/panfrost/panfrost_mmu.h index 7c5b6775ae23..44fc2edf63ce 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.h +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.h @@ -4,12 +4,12 @@ #ifndef __PANFROST_MMU_H__ #define __PANFROST_MMU_H__ -struct panfrost_gem_object; +struct panfrost_gem_mapping; struct panfrost_file_priv; struct panfrost_mmu; -int panfrost_mmu_map(struct panfrost_gem_object *bo); -void panfrost_mmu_unmap(struct panfrost_gem_object *bo); +int panfrost_mmu_map(struct panfrost_gem_mapping *mapping); +void panfrost_mmu_unmap(struct panfrost_gem_mapping *mapping); int panfrost_mmu_init(struct panfrost_device *pfdev); void panfrost_mmu_fini(struct panfrost_device *pfdev); diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c index 2c04e858c50a..684820448be3 100644 --- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c +++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c @@ -25,7 +25,7 @@ #define V4_SHADERS_PER_COREGROUP 4 struct panfrost_perfcnt { - struct panfrost_gem_object *bo; + struct panfrost_gem_mapping *mapping; size_t bosize; void *buf; struct panfrost_file_priv *user; @@ -49,7 +49,7 @@ static int panfrost_perfcnt_dump_locked(struct panfrost_device *pfdev) int ret; reinit_completion(&pfdev->perfcnt->dump_comp); - gpuva = pfdev->perfcnt->bo->node.start << PAGE_SHIFT; + gpuva = pfdev->perfcnt->mapping->mmnode.start << PAGE_SHIFT; gpu_write(pfdev, GPU_PERFCNT_BASE_LO, gpuva); gpu_write(pfdev, GPU_PERFCNT_BASE_HI, gpuva >> 32); gpu_write(pfdev, GPU_INT_CLEAR, @@ -89,17 +89,22 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev, if (IS_ERR(bo)) return PTR_ERR(bo); - perfcnt->bo = to_panfrost_bo(&bo->base); - /* Map the perfcnt buf in the address space attached to file_priv. */ - ret = panfrost_gem_open(&perfcnt->bo->base.base, file_priv); + ret = panfrost_gem_open(&bo->base, file_priv); if (ret) goto err_put_bo; + perfcnt->mapping = panfrost_gem_mapping_get(to_panfrost_bo(&bo->base), + user); + if (!perfcnt->mapping) { + ret = -EINVAL; + goto err_close_bo; + } + perfcnt->buf = drm_gem_shmem_vmap(&bo->base); if (IS_ERR(perfcnt->buf)) { ret = PTR_ERR(perfcnt->buf); - goto err_close_bo; + goto err_put_mapping; } /* @@ -154,12 +159,17 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev, if (panfrost_has_hw_issue(pfdev, HW_ISSUE_8186)) gpu_write(pfdev, GPU_PRFCNT_TILER_EN, 0xffffffff); + /* The BO ref is retained by the mapping. */ + drm_gem_object_put_unlocked(&bo->base); + return 0; err_vunmap: - drm_gem_shmem_vunmap(&perfcnt->bo->base.base, perfcnt->buf); + drm_gem_shmem_vunmap(&bo->base, perfcnt->buf); +err_put_mapping: + panfrost_gem_mapping_put(perfcnt->mapping); err_close_bo: - panfrost_gem_close(&perfcnt->bo->base.base, file_priv); + panfrost_gem_close(&bo->base, file_priv); err_put_bo: drm_gem_object_put_unlocked(&bo->base); return ret; @@ -182,11 +192,11 @@ static int panfrost_perfcnt_disable_locked(struct panfrost_device *pfdev, GPU_PERFCNT_CFG_MODE(GPU_PERFCNT_CFG_MODE_OFF)); perfcnt->user = NULL; - drm_gem_shmem_vunmap(&perfcnt->bo->base.base, perfcnt->buf); + drm_gem_shmem_vunmap(&perfcnt->mapping->obj->base.base, perfcnt->buf); perfcnt->buf = NULL; - panfrost_gem_close(&perfcnt->bo->base.base, file_priv); - drm_gem_object_put_unlocked(&perfcnt->bo->base.base); - perfcnt->bo = NULL; + panfrost_gem_close(&perfcnt->mapping->obj->base.base, file_priv); + panfrost_gem_mapping_put(perfcnt->mapping); + perfcnt->mapping = NULL; pm_runtime_mark_last_busy(pfdev->dev); pm_runtime_put_autosuspend(pfdev->dev); diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c index 6c64d50c9aae..01c2eeb02aa9 100644 --- a/drivers/hwmon/adt7475.c +++ b/drivers/hwmon/adt7475.c @@ -294,9 +294,10 @@ static inline u16 volt2reg(int channel, long volt, u8 bypass_attn) long reg; if (bypass_attn & (1 << channel)) - reg = (volt * 1024) / 2250; + reg = DIV_ROUND_CLOSEST(volt * 1024, 2250); else - reg = (volt * r[1] * 1024) / ((r[0] + r[1]) * 2250); + reg = DIV_ROUND_CLOSEST(volt * r[1] * 1024, + (r[0] + r[1]) * 2250); return clamp_val(reg, 0, 1023) & (0xff << 2); } diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index 1f3b30b085b9..d018b20089ec 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -51,6 +51,7 @@ struct hwmon_device_attribute { #define to_hwmon_attr(d) \ container_of(d, struct hwmon_device_attribute, dev_attr) +#define to_dev_attr(a) container_of(a, struct device_attribute, attr) /* * Thermal zone information @@ -58,7 +59,7 @@ struct hwmon_device_attribute { * also provides the sensor index. */ struct hwmon_thermal_data { - struct hwmon_device *hwdev; /* Reference to hwmon device */ + struct device *dev; /* Reference to hwmon device */ int index; /* sensor index */ }; @@ -95,9 +96,27 @@ static const struct attribute_group *hwmon_dev_attr_groups[] = { NULL }; +static void hwmon_free_attrs(struct attribute **attrs) +{ + int i; + + for (i = 0; attrs[i]; i++) { + struct device_attribute *dattr = to_dev_attr(attrs[i]); + struct hwmon_device_attribute *hattr = to_hwmon_attr(dattr); + + kfree(hattr); + } + kfree(attrs); +} + static void hwmon_dev_release(struct device *dev) { - kfree(to_hwmon_device(dev)); + struct hwmon_device *hwdev = to_hwmon_device(dev); + + if (hwdev->group.attrs) + hwmon_free_attrs(hwdev->group.attrs); + kfree(hwdev->groups); + kfree(hwdev); } static struct class hwmon_class = { @@ -119,11 +138,11 @@ static DEFINE_IDA(hwmon_ida); static int hwmon_thermal_get_temp(void *data, int *temp) { struct hwmon_thermal_data *tdata = data; - struct hwmon_device *hwdev = tdata->hwdev; + struct hwmon_device *hwdev = to_hwmon_device(tdata->dev); int ret; long t; - ret = hwdev->chip->ops->read(&hwdev->dev, hwmon_temp, hwmon_temp_input, + ret = hwdev->chip->ops->read(tdata->dev, hwmon_temp, hwmon_temp_input, tdata->index, &t); if (ret < 0) return ret; @@ -137,8 +156,7 @@ static const struct thermal_zone_of_device_ops hwmon_thermal_ops = { .get_temp = hwmon_thermal_get_temp, }; -static int hwmon_thermal_add_sensor(struct device *dev, - struct hwmon_device *hwdev, int index) +static int hwmon_thermal_add_sensor(struct device *dev, int index) { struct hwmon_thermal_data *tdata; struct thermal_zone_device *tzd; @@ -147,10 +165,10 @@ static int hwmon_thermal_add_sensor(struct device *dev, if (!tdata) return -ENOMEM; - tdata->hwdev = hwdev; + tdata->dev = dev; tdata->index = index; - tzd = devm_thermal_zone_of_sensor_register(&hwdev->dev, index, tdata, + tzd = devm_thermal_zone_of_sensor_register(dev, index, tdata, &hwmon_thermal_ops); /* * If CONFIG_THERMAL_OF is disabled, this returns -ENODEV, @@ -162,8 +180,7 @@ static int hwmon_thermal_add_sensor(struct device *dev, return 0; } #else -static int hwmon_thermal_add_sensor(struct device *dev, - struct hwmon_device *hwdev, int index) +static int hwmon_thermal_add_sensor(struct device *dev, int index) { return 0; } @@ -250,8 +267,7 @@ static bool is_string_attr(enum hwmon_sensor_types type, u32 attr) (type == hwmon_fan && attr == hwmon_fan_label); } -static struct attribute *hwmon_genattr(struct device *dev, - const void *drvdata, +static struct attribute *hwmon_genattr(const void *drvdata, enum hwmon_sensor_types type, u32 attr, int index, @@ -279,7 +295,7 @@ static struct attribute *hwmon_genattr(struct device *dev, if ((mode & 0222) && !ops->write) return ERR_PTR(-EINVAL); - hattr = devm_kzalloc(dev, sizeof(*hattr), GFP_KERNEL); + hattr = kzalloc(sizeof(*hattr), GFP_KERNEL); if (!hattr) return ERR_PTR(-ENOMEM); @@ -492,8 +508,7 @@ static int hwmon_num_channel_attrs(const struct hwmon_channel_info *info) return n; } -static int hwmon_genattrs(struct device *dev, - const void *drvdata, +static int hwmon_genattrs(const void *drvdata, struct attribute **attrs, const struct hwmon_ops *ops, const struct hwmon_channel_info *info) @@ -519,7 +534,7 @@ static int hwmon_genattrs(struct device *dev, attr_mask &= ~BIT(attr); if (attr >= template_size) return -EINVAL; - a = hwmon_genattr(dev, drvdata, info->type, attr, i, + a = hwmon_genattr(drvdata, info->type, attr, i, templates[attr], ops); if (IS_ERR(a)) { if (PTR_ERR(a) != -ENOENT) @@ -533,8 +548,7 @@ static int hwmon_genattrs(struct device *dev, } static struct attribute ** -__hwmon_create_attrs(struct device *dev, const void *drvdata, - const struct hwmon_chip_info *chip) +__hwmon_create_attrs(const void *drvdata, const struct hwmon_chip_info *chip) { int ret, i, aindex = 0, nattrs = 0; struct attribute **attrs; @@ -545,15 +559,17 @@ __hwmon_create_attrs(struct device *dev, const void *drvdata, if (nattrs == 0) return ERR_PTR(-EINVAL); - attrs = devm_kcalloc(dev, nattrs + 1, sizeof(*attrs), GFP_KERNEL); + attrs = kcalloc(nattrs + 1, sizeof(*attrs), GFP_KERNEL); if (!attrs) return ERR_PTR(-ENOMEM); for (i = 0; chip->info[i]; i++) { - ret = hwmon_genattrs(dev, drvdata, &attrs[aindex], chip->ops, + ret = hwmon_genattrs(drvdata, &attrs[aindex], chip->ops, chip->info[i]); - if (ret < 0) + if (ret < 0) { + hwmon_free_attrs(attrs); return ERR_PTR(ret); + } aindex += ret; } @@ -595,14 +611,13 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, for (i = 0; groups[i]; i++) ngroups++; - hwdev->groups = devm_kcalloc(dev, ngroups, sizeof(*groups), - GFP_KERNEL); + hwdev->groups = kcalloc(ngroups, sizeof(*groups), GFP_KERNEL); if (!hwdev->groups) { err = -ENOMEM; goto free_hwmon; } - attrs = __hwmon_create_attrs(dev, drvdata, chip); + attrs = __hwmon_create_attrs(drvdata, chip); if (IS_ERR(attrs)) { err = PTR_ERR(attrs); goto free_hwmon; @@ -647,8 +662,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, hwmon_temp_input, j)) continue; if (info[i]->config[j] & HWMON_T_INPUT) { - err = hwmon_thermal_add_sensor(dev, - hwdev, j); + err = hwmon_thermal_add_sensor(hdev, j); if (err) { device_unregister(hdev); /* @@ -667,7 +681,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, return hdev; free_hwmon: - kfree(hwdev); + hwmon_dev_release(hdev); ida_remove: ida_simple_remove(&hwmon_ida, id); return ERR_PTR(err); diff --git a/drivers/hwmon/nct7802.c b/drivers/hwmon/nct7802.c index f3dd2a17bd42..2e97e56c72c7 100644 --- a/drivers/hwmon/nct7802.c +++ b/drivers/hwmon/nct7802.c @@ -23,8 +23,8 @@ static const u8 REG_VOLTAGE[5] = { 0x09, 0x0a, 0x0c, 0x0d, 0x0e }; static const u8 REG_VOLTAGE_LIMIT_LSB[2][5] = { - { 0x40, 0x00, 0x42, 0x44, 0x46 }, - { 0x3f, 0x00, 0x41, 0x43, 0x45 }, + { 0x46, 0x00, 0x40, 0x42, 0x44 }, + { 0x45, 0x00, 0x3f, 0x41, 0x43 }, }; static const u8 REG_VOLTAGE_LIMIT_MSB[5] = { 0x48, 0x00, 0x47, 0x47, 0x48 }; @@ -58,6 +58,8 @@ static const u8 REG_VOLTAGE_LIMIT_MSB_SHIFT[2][5] = { struct nct7802_data { struct regmap *regmap; struct mutex access_lock; /* for multi-byte read and write operations */ + u8 in_status; + struct mutex in_alarm_lock; }; static ssize_t temp_type_show(struct device *dev, @@ -368,6 +370,66 @@ static ssize_t in_store(struct device *dev, struct device_attribute *attr, return err ? : count; } +static ssize_t in_alarm_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr); + struct nct7802_data *data = dev_get_drvdata(dev); + int volt, min, max, ret; + unsigned int val; + + mutex_lock(&data->in_alarm_lock); + + /* + * The SMI Voltage status register is the only register giving a status + * for voltages. A bit is set for each input crossing a threshold, in + * both direction, but the "inside" or "outside" limits info is not + * available. Also this register is cleared on read. + * Note: this is not explicitly spelled out in the datasheet, but + * from experiment. + * To deal with this we use a status cache with one validity bit and + * one status bit for each input. Validity is cleared at startup and + * each time the register reports a change, and the status is processed + * by software based on current input value and limits. + */ + ret = regmap_read(data->regmap, 0x1e, &val); /* SMI Voltage status */ + if (ret < 0) + goto abort; + + /* invalidate cached status for all inputs crossing a threshold */ + data->in_status &= ~((val & 0x0f) << 4); + + /* if cached status for requested input is invalid, update it */ + if (!(data->in_status & (0x10 << sattr->index))) { + ret = nct7802_read_voltage(data, sattr->nr, 0); + if (ret < 0) + goto abort; + volt = ret; + + ret = nct7802_read_voltage(data, sattr->nr, 1); + if (ret < 0) + goto abort; + min = ret; + + ret = nct7802_read_voltage(data, sattr->nr, 2); + if (ret < 0) + goto abort; + max = ret; + + if (volt < min || volt > max) + data->in_status |= (1 << sattr->index); + else + data->in_status &= ~(1 << sattr->index); + + data->in_status |= 0x10 << sattr->index; + } + + ret = sprintf(buf, "%u\n", !!(data->in_status & (1 << sattr->index))); +abort: + mutex_unlock(&data->in_alarm_lock); + return ret; +} + static ssize_t temp_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -660,7 +722,7 @@ static const struct attribute_group nct7802_temp_group = { static SENSOR_DEVICE_ATTR_2_RO(in0_input, in, 0, 0); static SENSOR_DEVICE_ATTR_2_RW(in0_min, in, 0, 1); static SENSOR_DEVICE_ATTR_2_RW(in0_max, in, 0, 2); -static SENSOR_DEVICE_ATTR_2_RO(in0_alarm, alarm, 0x1e, 3); +static SENSOR_DEVICE_ATTR_2_RO(in0_alarm, in_alarm, 0, 3); static SENSOR_DEVICE_ATTR_2_RW(in0_beep, beep, 0x5a, 3); static SENSOR_DEVICE_ATTR_2_RO(in1_input, in, 1, 0); @@ -668,19 +730,19 @@ static SENSOR_DEVICE_ATTR_2_RO(in1_input, in, 1, 0); static SENSOR_DEVICE_ATTR_2_RO(in2_input, in, 2, 0); static SENSOR_DEVICE_ATTR_2_RW(in2_min, in, 2, 1); static SENSOR_DEVICE_ATTR_2_RW(in2_max, in, 2, 2); -static SENSOR_DEVICE_ATTR_2_RO(in2_alarm, alarm, 0x1e, 0); +static SENSOR_DEVICE_ATTR_2_RO(in2_alarm, in_alarm, 2, 0); static SENSOR_DEVICE_ATTR_2_RW(in2_beep, beep, 0x5a, 0); static SENSOR_DEVICE_ATTR_2_RO(in3_input, in, 3, 0); static SENSOR_DEVICE_ATTR_2_RW(in3_min, in, 3, 1); static SENSOR_DEVICE_ATTR_2_RW(in3_max, in, 3, 2); -static SENSOR_DEVICE_ATTR_2_RO(in3_alarm, alarm, 0x1e, 1); +static SENSOR_DEVICE_ATTR_2_RO(in3_alarm, in_alarm, 3, 1); static SENSOR_DEVICE_ATTR_2_RW(in3_beep, beep, 0x5a, 1); static SENSOR_DEVICE_ATTR_2_RO(in4_input, in, 4, 0); static SENSOR_DEVICE_ATTR_2_RW(in4_min, in, 4, 1); static SENSOR_DEVICE_ATTR_2_RW(in4_max, in, 4, 2); -static SENSOR_DEVICE_ATTR_2_RO(in4_alarm, alarm, 0x1e, 2); +static SENSOR_DEVICE_ATTR_2_RO(in4_alarm, in_alarm, 4, 2); static SENSOR_DEVICE_ATTR_2_RW(in4_beep, beep, 0x5a, 2); static struct attribute *nct7802_in_attrs[] = { @@ -1011,6 +1073,7 @@ static int nct7802_probe(struct i2c_client *client, return PTR_ERR(data->regmap); mutex_init(&data->access_lock); + mutex_init(&data->in_alarm_lock); ret = nct7802_init_chip(data); if (ret < 0) diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index a1a035270cab..b273e421e910 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -2575,17 +2575,6 @@ isert_wait4logout(struct isert_conn *isert_conn) } } -static void -isert_wait4cmds(struct iscsi_conn *conn) -{ - isert_info("iscsi_conn %p\n", conn); - - if (conn->sess) { - target_sess_cmd_list_set_waiting(conn->sess->se_sess); - target_wait_for_sess_cmds(conn->sess->se_sess); - } -} - /** * isert_put_unsol_pending_cmds() - Drop commands waiting for * unsolicitate dataout @@ -2633,7 +2622,6 @@ static void isert_wait_conn(struct iscsi_conn *conn) ib_drain_qp(isert_conn->qp); isert_put_unsol_pending_cmds(conn); - isert_wait4cmds(conn); isert_wait4logout(isert_conn); queue_work(isert_release_wq, &isert_conn->release_work); diff --git a/drivers/input/misc/keyspan_remote.c b/drivers/input/misc/keyspan_remote.c index 83368f1e7c4e..4650f4a94989 100644 --- a/drivers/input/misc/keyspan_remote.c +++ b/drivers/input/misc/keyspan_remote.c @@ -336,7 +336,8 @@ static int keyspan_setup(struct usb_device* dev) int retval = 0; retval = usb_control_msg(dev, usb_sndctrlpipe(dev, 0), - 0x11, 0x40, 0x5601, 0x0, NULL, 0, 0); + 0x11, 0x40, 0x5601, 0x0, NULL, 0, + USB_CTRL_SET_TIMEOUT); if (retval) { dev_dbg(&dev->dev, "%s - failed to set bit rate due to error: %d\n", __func__, retval); @@ -344,7 +345,8 @@ static int keyspan_setup(struct usb_device* dev) } retval = usb_control_msg(dev, usb_sndctrlpipe(dev, 0), - 0x44, 0x40, 0x0, 0x0, NULL, 0, 0); + 0x44, 0x40, 0x0, 0x0, NULL, 0, + USB_CTRL_SET_TIMEOUT); if (retval) { dev_dbg(&dev->dev, "%s - failed to set resume sensitivity due to error: %d\n", __func__, retval); @@ -352,7 +354,8 @@ static int keyspan_setup(struct usb_device* dev) } retval = usb_control_msg(dev, usb_sndctrlpipe(dev, 0), - 0x22, 0x40, 0x0, 0x0, NULL, 0, 0); + 0x22, 0x40, 0x0, 0x0, NULL, 0, + USB_CTRL_SET_TIMEOUT); if (retval) { dev_dbg(&dev->dev, "%s - failed to turn receive on due to error: %d\n", __func__, retval); diff --git a/drivers/input/misc/pm8xxx-vibrator.c b/drivers/input/misc/pm8xxx-vibrator.c index ecd762f93732..53ad25eaf1a2 100644 --- a/drivers/input/misc/pm8xxx-vibrator.c +++ b/drivers/input/misc/pm8xxx-vibrator.c @@ -90,7 +90,7 @@ static int pm8xxx_vib_set(struct pm8xxx_vib *vib, bool on) if (regs->enable_mask) rc = regmap_update_bits(vib->regmap, regs->enable_addr, - on ? regs->enable_mask : 0, val); + regs->enable_mask, on ? ~0 : 0); return rc; } diff --git a/drivers/input/rmi4/rmi_smbus.c b/drivers/input/rmi4/rmi_smbus.c index b313c579914f..2407ea43de59 100644 --- a/drivers/input/rmi4/rmi_smbus.c +++ b/drivers/input/rmi4/rmi_smbus.c @@ -163,6 +163,7 @@ static int rmi_smb_write_block(struct rmi_transport_dev *xport, u16 rmiaddr, /* prepare to write next block of bytes */ cur_len -= SMB_MAX_COUNT; databuff += SMB_MAX_COUNT; + rmiaddr += SMB_MAX_COUNT; } exit: mutex_unlock(&rmi_smb->page_mutex); @@ -214,6 +215,7 @@ static int rmi_smb_read_block(struct rmi_transport_dev *xport, u16 rmiaddr, /* prepare to read next block of bytes */ cur_len -= SMB_MAX_COUNT; databuff += SMB_MAX_COUNT; + rmiaddr += SMB_MAX_COUNT; } retval = 0; diff --git a/drivers/input/tablet/aiptek.c b/drivers/input/tablet/aiptek.c index 2ca586fb914f..06d0ffef4a17 100644 --- a/drivers/input/tablet/aiptek.c +++ b/drivers/input/tablet/aiptek.c @@ -1802,14 +1802,14 @@ aiptek_probe(struct usb_interface *intf, const struct usb_device_id *id) input_set_abs_params(inputdev, ABS_WHEEL, AIPTEK_WHEEL_MIN, AIPTEK_WHEEL_MAX - 1, 0, 0); /* Verify that a device really has an endpoint */ - if (intf->altsetting[0].desc.bNumEndpoints < 1) { + if (intf->cur_altsetting->desc.bNumEndpoints < 1) { dev_err(&intf->dev, "interface has %d endpoints, but must have minimum 1\n", - intf->altsetting[0].desc.bNumEndpoints); + intf->cur_altsetting->desc.bNumEndpoints); err = -EINVAL; goto fail3; } - endpoint = &intf->altsetting[0].endpoint[0].desc; + endpoint = &intf->cur_altsetting->endpoint[0].desc; /* Go set up our URB, which is called when the tablet receives * input. diff --git a/drivers/input/tablet/gtco.c b/drivers/input/tablet/gtco.c index 35031228a6d0..799c94dda651 100644 --- a/drivers/input/tablet/gtco.c +++ b/drivers/input/tablet/gtco.c @@ -875,18 +875,14 @@ static int gtco_probe(struct usb_interface *usbinterface, } /* Sanity check that a device has an endpoint */ - if (usbinterface->altsetting[0].desc.bNumEndpoints < 1) { + if (usbinterface->cur_altsetting->desc.bNumEndpoints < 1) { dev_err(&usbinterface->dev, "Invalid number of endpoints\n"); error = -EINVAL; goto err_free_urb; } - /* - * The endpoint is always altsetting 0, we know this since we know - * this device only has one interrupt endpoint - */ - endpoint = &usbinterface->altsetting[0].endpoint[0].desc; + endpoint = &usbinterface->cur_altsetting->endpoint[0].desc; /* Some debug */ dev_dbg(&usbinterface->dev, "gtco # interfaces: %d\n", usbinterface->num_altsetting); @@ -973,7 +969,7 @@ static int gtco_probe(struct usb_interface *usbinterface, input_dev->dev.parent = &usbinterface->dev; /* Setup the URB, it will be posted later on open of input device */ - endpoint = &usbinterface->altsetting[0].endpoint[0].desc; + endpoint = &usbinterface->cur_altsetting->endpoint[0].desc; usb_fill_int_urb(gtco->urbinfo, udev, diff --git a/drivers/input/tablet/pegasus_notetaker.c b/drivers/input/tablet/pegasus_notetaker.c index a1f3a0cb197e..38f087404f7a 100644 --- a/drivers/input/tablet/pegasus_notetaker.c +++ b/drivers/input/tablet/pegasus_notetaker.c @@ -275,7 +275,7 @@ static int pegasus_probe(struct usb_interface *intf, return -ENODEV; /* Sanity check that the device has an endpoint */ - if (intf->altsetting[0].desc.bNumEndpoints < 1) { + if (intf->cur_altsetting->desc.bNumEndpoints < 1) { dev_err(&intf->dev, "Invalid number of endpoints\n"); return -EINVAL; } diff --git a/drivers/input/touchscreen/sun4i-ts.c b/drivers/input/touchscreen/sun4i-ts.c index 0af0fe8c40d7..742a7e96c1b5 100644 --- a/drivers/input/touchscreen/sun4i-ts.c +++ b/drivers/input/touchscreen/sun4i-ts.c @@ -237,6 +237,7 @@ static int sun4i_ts_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct device_node *np = dev->of_node; struct device *hwmon; + struct thermal_zone_device *thermal; int error; u32 reg; bool ts_attached; @@ -355,7 +356,10 @@ static int sun4i_ts_probe(struct platform_device *pdev) if (IS_ERR(hwmon)) return PTR_ERR(hwmon); - devm_thermal_zone_of_sensor_register(ts->dev, 0, ts, &sun4i_ts_tz_ops); + thermal = devm_thermal_zone_of_sensor_register(ts->dev, 0, ts, + &sun4i_ts_tz_ops); + if (IS_ERR(thermal)) + return PTR_ERR(thermal); writel(TEMP_IRQ_EN(1), ts->base + TP_INT_FIFOC); diff --git a/drivers/input/touchscreen/sur40.c b/drivers/input/touchscreen/sur40.c index 3fd3e862269b..2e2ea5719c90 100644 --- a/drivers/input/touchscreen/sur40.c +++ b/drivers/input/touchscreen/sur40.c @@ -653,7 +653,7 @@ static int sur40_probe(struct usb_interface *interface, int error; /* Check if we really have the right interface. */ - iface_desc = &interface->altsetting[0]; + iface_desc = interface->cur_altsetting; if (iface_desc->desc.bInterfaceClass != 0xFF) return -ENODEV; diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 568c52317757..483f7bc379fa 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1655,27 +1655,39 @@ static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, static void init_iommu_perf_ctr(struct amd_iommu *iommu) { struct pci_dev *pdev = iommu->dev; - u64 val = 0xabcd, val2 = 0; + u64 val = 0xabcd, val2 = 0, save_reg = 0; if (!iommu_feature(iommu, FEATURE_PC)) return; amd_iommu_pc_present = true; + /* save the value to restore, if writable */ + if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, false)) + goto pc_false; + /* Check if the performance counters can be written to */ if ((iommu_pc_get_set_reg(iommu, 0, 0, 0, &val, true)) || (iommu_pc_get_set_reg(iommu, 0, 0, 0, &val2, false)) || - (val != val2)) { - pci_err(pdev, "Unable to write to IOMMU perf counter.\n"); - amd_iommu_pc_present = false; - return; - } + (val != val2)) + goto pc_false; + + /* restore */ + if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, true)) + goto pc_false; pci_info(pdev, "IOMMU performance counters supported\n"); val = readl(iommu->mmio_base + MMIO_CNTR_CONF_OFFSET); iommu->max_banks = (u8) ((val >> 12) & 0x3f); iommu->max_counters = (u8) ((val >> 7) & 0xf); + + return; + +pc_false: + pci_err(pdev, "Unable to read/write to IOMMU perf counter.\n"); + amd_iommu_pc_present = false; + return; } static ssize_t amd_iommu_show_cap(struct device *dev, diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index e84c5dfe146f..dd5db856dcaf 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5132,7 +5132,8 @@ static void dmar_remove_one_dev_info(struct device *dev) spin_lock_irqsave(&device_domain_lock, flags); info = dev->archdata.iommu; - if (info) + if (info && info != DEFER_DEVICE_DOMAIN_INFO + && info != DUMMY_DEVICE_DOMAIN_INFO) __dmar_remove_one_dev_info(info); spin_unlock_irqrestore(&device_domain_lock, flags); } diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c index a5c73f3d5f79..2bf74595610f 100644 --- a/drivers/leds/leds-gpio.c +++ b/drivers/leds/leds-gpio.c @@ -151,9 +151,14 @@ static struct gpio_leds_priv *gpio_leds_create(struct platform_device *pdev) struct gpio_led led = {}; const char *state = NULL; + /* + * Acquire gpiod from DT with uninitialized label, which + * will be updated after LED class device is registered, + * Only then the final LED name is known. + */ led.gpiod = devm_fwnode_get_gpiod_from_child(dev, NULL, child, GPIOD_ASIS, - led.name); + NULL); if (IS_ERR(led.gpiod)) { fwnode_handle_put(child); return ERR_CAST(led.gpiod); @@ -186,6 +191,9 @@ static struct gpio_leds_priv *gpio_leds_create(struct platform_device *pdev) fwnode_handle_put(child); return ERR_PTR(ret); } + /* Set gpiod label to match the corresponding LED name. */ + gpiod_set_consumer_name(led_dat->gpiod, + led_dat->cdev.dev->kobj.name); priv->num_leds++; } diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 21bb96ce4cd6..58868d7129eb 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1605,12 +1605,12 @@ static int v4l_s_fmt(const struct v4l2_ioctl_ops *ops, case V4L2_BUF_TYPE_VBI_CAPTURE: if (unlikely(!ops->vidioc_s_fmt_vbi_cap)) break; - CLEAR_AFTER_FIELD(p, fmt.vbi); + CLEAR_AFTER_FIELD(p, fmt.vbi.flags); return ops->vidioc_s_fmt_vbi_cap(file, fh, arg); case V4L2_BUF_TYPE_SLICED_VBI_CAPTURE: if (unlikely(!ops->vidioc_s_fmt_sliced_vbi_cap)) break; - CLEAR_AFTER_FIELD(p, fmt.sliced); + CLEAR_AFTER_FIELD(p, fmt.sliced.io_size); return ops->vidioc_s_fmt_sliced_vbi_cap(file, fh, arg); case V4L2_BUF_TYPE_VIDEO_OUTPUT: if (unlikely(!ops->vidioc_s_fmt_vid_out)) @@ -1636,22 +1636,22 @@ static int v4l_s_fmt(const struct v4l2_ioctl_ops *ops, case V4L2_BUF_TYPE_VBI_OUTPUT: if (unlikely(!ops->vidioc_s_fmt_vbi_out)) break; - CLEAR_AFTER_FIELD(p, fmt.vbi); + CLEAR_AFTER_FIELD(p, fmt.vbi.flags); return ops->vidioc_s_fmt_vbi_out(file, fh, arg); case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT: if (unlikely(!ops->vidioc_s_fmt_sliced_vbi_out)) break; - CLEAR_AFTER_FIELD(p, fmt.sliced); + CLEAR_AFTER_FIELD(p, fmt.sliced.io_size); return ops->vidioc_s_fmt_sliced_vbi_out(file, fh, arg); case V4L2_BUF_TYPE_SDR_CAPTURE: if (unlikely(!ops->vidioc_s_fmt_sdr_cap)) break; - CLEAR_AFTER_FIELD(p, fmt.sdr); + CLEAR_AFTER_FIELD(p, fmt.sdr.buffersize); return ops->vidioc_s_fmt_sdr_cap(file, fh, arg); case V4L2_BUF_TYPE_SDR_OUTPUT: if (unlikely(!ops->vidioc_s_fmt_sdr_out)) break; - CLEAR_AFTER_FIELD(p, fmt.sdr); + CLEAR_AFTER_FIELD(p, fmt.sdr.buffersize); return ops->vidioc_s_fmt_sdr_out(file, fh, arg); case V4L2_BUF_TYPE_META_CAPTURE: if (unlikely(!ops->vidioc_s_fmt_meta_cap)) @@ -1707,12 +1707,12 @@ static int v4l_try_fmt(const struct v4l2_ioctl_ops *ops, case V4L2_BUF_TYPE_VBI_CAPTURE: if (unlikely(!ops->vidioc_try_fmt_vbi_cap)) break; - CLEAR_AFTER_FIELD(p, fmt.vbi); + CLEAR_AFTER_FIELD(p, fmt.vbi.flags); return ops->vidioc_try_fmt_vbi_cap(file, fh, arg); case V4L2_BUF_TYPE_SLICED_VBI_CAPTURE: if (unlikely(!ops->vidioc_try_fmt_sliced_vbi_cap)) break; - CLEAR_AFTER_FIELD(p, fmt.sliced); + CLEAR_AFTER_FIELD(p, fmt.sliced.io_size); return ops->vidioc_try_fmt_sliced_vbi_cap(file, fh, arg); case V4L2_BUF_TYPE_VIDEO_OUTPUT: if (unlikely(!ops->vidioc_try_fmt_vid_out)) @@ -1738,22 +1738,22 @@ static int v4l_try_fmt(const struct v4l2_ioctl_ops *ops, case V4L2_BUF_TYPE_VBI_OUTPUT: if (unlikely(!ops->vidioc_try_fmt_vbi_out)) break; - CLEAR_AFTER_FIELD(p, fmt.vbi); + CLEAR_AFTER_FIELD(p, fmt.vbi.flags); return ops->vidioc_try_fmt_vbi_out(file, fh, arg); case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT: if (unlikely(!ops->vidioc_try_fmt_sliced_vbi_out)) break; - CLEAR_AFTER_FIELD(p, fmt.sliced); + CLEAR_AFTER_FIELD(p, fmt.sliced.io_size); return ops->vidioc_try_fmt_sliced_vbi_out(file, fh, arg); case V4L2_BUF_TYPE_SDR_CAPTURE: if (unlikely(!ops->vidioc_try_fmt_sdr_cap)) break; - CLEAR_AFTER_FIELD(p, fmt.sdr); + CLEAR_AFTER_FIELD(p, fmt.sdr.buffersize); return ops->vidioc_try_fmt_sdr_cap(file, fh, arg); case V4L2_BUF_TYPE_SDR_OUTPUT: if (unlikely(!ops->vidioc_try_fmt_sdr_out)) break; - CLEAR_AFTER_FIELD(p, fmt.sdr); + CLEAR_AFTER_FIELD(p, fmt.sdr.buffersize); return ops->vidioc_try_fmt_sdr_out(file, fh, arg); case V4L2_BUF_TYPE_META_CAPTURE: if (unlikely(!ops->vidioc_try_fmt_meta_cap)) diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 7bc950520fd9..403ac44a7378 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -386,7 +386,7 @@ static void tegra_sdhci_reset(struct sdhci_host *host, u8 mask) misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_DDR50; if (soc_data->nvquirks & NVQUIRK_ENABLE_SDR104) misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_SDR104; - if (soc_data->nvquirks & SDHCI_MISC_CTRL_ENABLE_SDR50) + if (soc_data->nvquirks & NVQUIRK_ENABLE_SDR50) clk_ctrl |= SDHCI_CLOCK_CTRL_SDR50_TUNING_OVERRIDE; } diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 5f9df2dbde06..4478b94d4791 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -3902,11 +3902,13 @@ int sdhci_setup_host(struct sdhci_host *host) if (host->ops->get_min_clock) mmc->f_min = host->ops->get_min_clock(host); else if (host->version >= SDHCI_SPEC_300) { - if (host->clk_mul) { - mmc->f_min = (host->max_clk * host->clk_mul) / 1024; + if (host->clk_mul) max_clk = host->max_clk * host->clk_mul; - } else - mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_300; + /* + * Divided Clock Mode minimum clock rate is always less than + * Programmable Clock Mode minimum clock rate. + */ + mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_300; } else mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_200; diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c index bb90757ecace..4cbb764c9822 100644 --- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -236,6 +236,22 @@ static void sdhci_am654_write_b(struct sdhci_host *host, u8 val, int reg) writeb(val, host->ioaddr + reg); } +static int sdhci_am654_execute_tuning(struct mmc_host *mmc, u32 opcode) +{ + struct sdhci_host *host = mmc_priv(mmc); + int err = sdhci_execute_tuning(mmc, opcode); + + if (err) + return err; + /* + * Tuning data remains in the buffer after tuning. + * Do a command and data reset to get rid of it + */ + sdhci_reset(host, SDHCI_RESET_CMD | SDHCI_RESET_DATA); + + return 0; +} + static struct sdhci_ops sdhci_am654_ops = { .get_max_clock = sdhci_pltfm_clk_get_max_clock, .get_timeout_clock = sdhci_pltfm_clk_get_max_clock, @@ -249,8 +265,7 @@ static struct sdhci_ops sdhci_am654_ops = { static const struct sdhci_pltfm_data sdhci_am654_pdata = { .ops = &sdhci_am654_ops, - .quirks = SDHCI_QUIRK_INVERTED_WRITE_PROTECT | - SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, + .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, }; @@ -272,8 +287,7 @@ static struct sdhci_ops sdhci_j721e_8bit_ops = { static const struct sdhci_pltfm_data sdhci_j721e_8bit_pdata = { .ops = &sdhci_j721e_8bit_ops, - .quirks = SDHCI_QUIRK_INVERTED_WRITE_PROTECT | - SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, + .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, }; @@ -295,8 +309,7 @@ static struct sdhci_ops sdhci_j721e_4bit_ops = { static const struct sdhci_pltfm_data sdhci_j721e_4bit_pdata = { .ops = &sdhci_j721e_4bit_ops, - .quirks = SDHCI_QUIRK_INVERTED_WRITE_PROTECT | - SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, + .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, }; @@ -480,6 +493,8 @@ static int sdhci_am654_probe(struct platform_device *pdev) goto pm_runtime_put; } + host->mmc_host_ops.execute_tuning = sdhci_am654_execute_tuning; + ret = sdhci_am654_init(host); if (ret) goto pm_runtime_put; diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index 2e57122f02fb..2f5c287eac95 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -344,9 +344,16 @@ static void slcan_transmit(struct work_struct *work) */ static void slcan_write_wakeup(struct tty_struct *tty) { - struct slcan *sl = tty->disc_data; + struct slcan *sl; + + rcu_read_lock(); + sl = rcu_dereference(tty->disc_data); + if (!sl) + goto out; schedule_work(&sl->tx_work); +out: + rcu_read_unlock(); } /* Send a can_frame to a TTY queue. */ @@ -644,10 +651,11 @@ static void slcan_close(struct tty_struct *tty) return; spin_lock_bh(&sl->lock); - tty->disc_data = NULL; + rcu_assign_pointer(tty->disc_data, NULL); sl->tty = NULL; spin_unlock_bh(&sl->lock); + synchronize_rcu(); flush_work(&sl->tx_work); /* Flush network side */ diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 1de51811fcb4..8f909d57501f 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2164,8 +2164,8 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv, DMA_END_ADDR); /* Initialize Tx NAPI */ - netif_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll, - NAPI_POLL_WEIGHT); + netif_tx_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll, + NAPI_POLL_WEIGHT); } /* Initialize a RDMA ring */ diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 58f89f6a040f..97ff8608f0ab 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -2448,6 +2448,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) if (!is_offload(adapter)) return -EOPNOTSUPP; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; if (!(adapter->flags & FULL_INIT_DONE)) return -EIO; /* need the memory controllers */ if (copy_from_user(&t, useraddr, sizeof(t))) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index 778dab1af8fc..f260dd96873b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -180,7 +180,7 @@ mlx5e_ktls_tx_post_param_wqes(struct mlx5e_txqsq *sq, struct tx_sync_info { u64 rcd_sn; - s32 sync_len; + u32 sync_len; int nr_frags; skb_frag_t frags[MAX_SKB_FRAGS]; }; @@ -193,13 +193,14 @@ enum mlx5e_ktls_sync_retval { static enum mlx5e_ktls_sync_retval tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx, - u32 tcp_seq, struct tx_sync_info *info) + u32 tcp_seq, int datalen, struct tx_sync_info *info) { struct tls_offload_context_tx *tx_ctx = priv_tx->tx_ctx; enum mlx5e_ktls_sync_retval ret = MLX5E_KTLS_SYNC_DONE; struct tls_record_info *record; int remaining, i = 0; unsigned long flags; + bool ends_before; spin_lock_irqsave(&tx_ctx->lock, flags); record = tls_get_record(tx_ctx, tcp_seq, &info->rcd_sn); @@ -209,9 +210,21 @@ tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx, goto out; } - if (unlikely(tcp_seq < tls_record_start_seq(record))) { - ret = tls_record_is_start_marker(record) ? - MLX5E_KTLS_SYNC_SKIP_NO_DATA : MLX5E_KTLS_SYNC_FAIL; + /* There are the following cases: + * 1. packet ends before start marker: bypass offload. + * 2. packet starts before start marker and ends after it: drop, + * not supported, breaks contract with kernel. + * 3. packet ends before tls record info starts: drop, + * this packet was already acknowledged and its record info + * was released. + */ + ends_before = before(tcp_seq + datalen, tls_record_start_seq(record)); + + if (unlikely(tls_record_is_start_marker(record))) { + ret = ends_before ? MLX5E_KTLS_SYNC_SKIP_NO_DATA : MLX5E_KTLS_SYNC_FAIL; + goto out; + } else if (ends_before) { + ret = MLX5E_KTLS_SYNC_FAIL; goto out; } @@ -337,7 +350,7 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx, u8 num_wqebbs; int i = 0; - ret = tx_sync_info_get(priv_tx, seq, &info); + ret = tx_sync_info_get(priv_tx, seq, datalen, &info); if (unlikely(ret != MLX5E_KTLS_SYNC_DONE)) { if (ret == MLX5E_KTLS_SYNC_SKIP_NO_DATA) { stats->tls_skip_no_sync_data++; @@ -351,14 +364,6 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx, goto err_out; } - if (unlikely(info.sync_len < 0)) { - if (likely(datalen <= -info.sync_len)) - return MLX5E_KTLS_SYNC_DONE; - - stats->tls_drop_bypass_req++; - goto err_out; - } - stats->tls_ooo++; tx_post_resync_params(sq, priv_tx, info.rcd_sn); @@ -378,8 +383,6 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx, if (unlikely(contig_wqebbs_room < num_wqebbs)) mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room); - tx_post_resync_params(sq, priv_tx, info.rcd_sn); - for (; i < info.nr_frags; i++) { unsigned int orig_fsz, frag_offset = 0, n = 0; skb_frag_t *f = &info.frags[i]; @@ -455,12 +458,18 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev, enum mlx5e_ktls_sync_retval ret = mlx5e_ktls_tx_handle_ooo(priv_tx, sq, datalen, seq); - if (likely(ret == MLX5E_KTLS_SYNC_DONE)) + switch (ret) { + case MLX5E_KTLS_SYNC_DONE: *wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi); - else if (ret == MLX5E_KTLS_SYNC_FAIL) + break; + case MLX5E_KTLS_SYNC_SKIP_NO_DATA: + if (likely(!skb->decrypted)) + goto out; + WARN_ON_ONCE(1); + /* fall-through */ + default: /* MLX5E_KTLS_SYNC_FAIL */ goto err_out; - else /* ret == MLX5E_KTLS_SYNC_SKIP_NO_DATA */ - goto out; + } } priv_tx->expected_seq = seq + datalen; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 96711e34d248..1f9107d83848 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3951,6 +3951,13 @@ static int apply_police_params(struct mlx5e_priv *priv, u32 rate, u32 rate_mbps; int err; + vport_num = rpriv->rep->vport; + if (vport_num >= MLX5_VPORT_ECPF) { + NL_SET_ERR_MSG_MOD(extack, + "Ingress rate limit is supported only for Eswitch ports connected to VFs"); + return -EOPNOTSUPP; + } + esw = priv->mdev->priv.eswitch; /* rate is given in bytes/sec. * First convert to bits/sec and then round to the nearest mbit/secs. @@ -3959,8 +3966,6 @@ static int apply_police_params(struct mlx5e_priv *priv, u32 rate, * 1 mbit/sec. */ rate_mbps = rate ? max_t(u32, (rate * 8 + 500000) / 1000000, 1) : 0; - vport_num = rpriv->rep->vport; - err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps); if (err) NL_SET_ERR_MSG_MOD(extack, "failed applying action to hardware"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 9004a07e457a..5acfdea3a75a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -858,7 +858,7 @@ out: */ #define ESW_SIZE (16 * 1024 * 1024) const unsigned int ESW_POOLS[4] = { 4 * 1024 * 1024, 1 * 1024 * 1024, - 64 * 1024, 4 * 1024 }; + 64 * 1024, 128 }; static int get_sz_from_pool(struct mlx5_eswitch *esw) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 051ab845b501..c96a0e501007 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1569,6 +1569,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x101d) }, /* ConnectX-6 Dx */ { PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF}, /* ConnectX Family mlx5Gen Virtual Function */ { PCI_VDEVICE(MELLANOX, 0x101f) }, /* ConnectX-6 LX */ + { PCI_VDEVICE(MELLANOX, 0x1021) }, /* ConnectX-7 */ { PCI_VDEVICE(MELLANOX, 0xa2d2) }, /* BlueField integrated ConnectX-5 network controller */ { PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF}, /* BlueField integrated ConnectX-5 network controller VF */ { PCI_VDEVICE(MELLANOX, 0xa2d6) }, /* BlueField-2 integrated ConnectX-6 Dx network controller */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index 51803eef13dd..c7f10d4f8f8d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2019 Mellanox Technologies. */ +#include #include "dr_types.h" #define QUEUE_SIZE 128 @@ -729,7 +730,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, if (!in) goto err_cqwq; - vector = smp_processor_id() % mlx5_comp_vectors_count(mdev); + vector = raw_smp_processor_id() % mlx5_comp_vectors_count(mdev); err = mlx5_vector2eqn(mdev, vector, &eqn, &irqn); if (err) { kvfree(in); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 3d587d0bdbbe..1e32e2443f73 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -352,26 +352,16 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { list_for_each_entry(dst, &fte->node.children, node.list) { enum mlx5_flow_destination_type type = dst->dest_attr.type; - u32 id; if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { err = -ENOSPC; goto free_actions; } - switch (type) { - case MLX5_FLOW_DESTINATION_TYPE_COUNTER: - id = dst->dest_attr.counter_id; + if (type == MLX5_FLOW_DESTINATION_TYPE_COUNTER) + continue; - tmp_action = - mlx5dr_action_create_flow_counter(id); - if (!tmp_action) { - err = -ENOMEM; - goto free_actions; - } - fs_dr_actions[fs_dr_num_actions++] = tmp_action; - actions[num_actions++] = tmp_action; - break; + switch (type) { case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE: tmp_action = create_ft_action(dev, dst); if (!tmp_action) { @@ -397,6 +387,32 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, } } + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { + list_for_each_entry(dst, &fte->node.children, node.list) { + u32 id; + + if (dst->dest_attr.type != + MLX5_FLOW_DESTINATION_TYPE_COUNTER) + continue; + + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -ENOSPC; + goto free_actions; + } + + id = dst->dest_attr.counter_id; + tmp_action = + mlx5dr_action_create_flow_counter(id); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + } + } + params.match_sz = match_sz; params.match_buf = (u64 *)fte->val; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 150b3a144b83..3d3cca596116 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -25,6 +26,7 @@ struct mlxsw_sp_acl { struct mlxsw_sp_fid *dummy_fid; struct rhashtable ruleset_ht; struct list_head rules; + struct mutex rules_lock; /* Protects rules list */ struct { struct delayed_work dw; unsigned long interval; /* ms */ @@ -701,7 +703,9 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp, goto err_ruleset_block_bind; } + mutex_lock(&mlxsw_sp->acl->rules_lock); list_add_tail(&rule->list, &mlxsw_sp->acl->rules); + mutex_unlock(&mlxsw_sp->acl->rules_lock); block->rule_count++; block->egress_blocker_rule_count += rule->rulei->egress_bind_blocker; return 0; @@ -723,7 +727,9 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp, block->egress_blocker_rule_count -= rule->rulei->egress_bind_blocker; ruleset->ht_key.block->rule_count--; + mutex_lock(&mlxsw_sp->acl->rules_lock); list_del(&rule->list); + mutex_unlock(&mlxsw_sp->acl->rules_lock); if (!ruleset->ht_key.chain_index && mlxsw_sp_acl_ruleset_is_singular(ruleset)) mlxsw_sp_acl_ruleset_block_unbind(mlxsw_sp, ruleset, @@ -783,19 +789,18 @@ static int mlxsw_sp_acl_rules_activity_update(struct mlxsw_sp_acl *acl) struct mlxsw_sp_acl_rule *rule; int err; - /* Protect internal structures from changes */ - rtnl_lock(); + mutex_lock(&acl->rules_lock); list_for_each_entry(rule, &acl->rules, list) { err = mlxsw_sp_acl_rule_activity_update(acl->mlxsw_sp, rule); if (err) goto err_rule_update; } - rtnl_unlock(); + mutex_unlock(&acl->rules_lock); return 0; err_rule_update: - rtnl_unlock(); + mutex_unlock(&acl->rules_lock); return err; } @@ -880,6 +885,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp) acl->dummy_fid = fid; INIT_LIST_HEAD(&acl->rules); + mutex_init(&acl->rules_lock); err = mlxsw_sp_acl_tcam_init(mlxsw_sp, &acl->tcam); if (err) goto err_acl_ops_init; @@ -892,6 +898,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp) return 0; err_acl_ops_init: + mutex_destroy(&acl->rules_lock); mlxsw_sp_fid_put(fid); err_fid_get: rhashtable_destroy(&acl->ruleset_ht); @@ -908,6 +915,7 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp) cancel_delayed_work_sync(&mlxsw_sp->acl->rule_activity_update.dw); mlxsw_sp_acl_tcam_fini(mlxsw_sp, &acl->tcam); + mutex_destroy(&acl->rules_lock); WARN_ON(!list_empty(&acl->rules)); mlxsw_sp_fid_put(acl->dummy_fid); rhashtable_destroy(&acl->ruleset_ht); diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index 1c14c051ee52..63e7a058b7c6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -299,22 +299,17 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb, u64 len; int err; + if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) { + this_cpu_inc(mlxsw_sx_port->pcpu_stats->tx_dropped); + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + memset(skb->cb, 0, sizeof(struct mlxsw_skb_cb)); if (mlxsw_core_skb_transmit_busy(mlxsw_sx->core, &tx_info)) return NETDEV_TX_BUSY; - if (unlikely(skb_headroom(skb) < MLXSW_TXHDR_LEN)) { - struct sk_buff *skb_orig = skb; - - skb = skb_realloc_headroom(skb, MLXSW_TXHDR_LEN); - if (!skb) { - this_cpu_inc(mlxsw_sx_port->pcpu_stats->tx_dropped); - dev_kfree_skb_any(skb_orig); - return NETDEV_TX_OK; - } - dev_consume_skb_any(skb_orig); - } mlxsw_sx_txhdr_construct(skb, &tx_info); /* TX header is consumed by HW on the way so we shouldn't count its * bytes as being sent. diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c index b339125b2f09..05e760444a92 100644 --- a/drivers/net/ethernet/natsemi/sonic.c +++ b/drivers/net/ethernet/natsemi/sonic.c @@ -64,6 +64,8 @@ static int sonic_open(struct net_device *dev) netif_dbg(lp, ifup, dev, "%s: initializing sonic driver\n", __func__); + spin_lock_init(&lp->lock); + for (i = 0; i < SONIC_NUM_RRS; i++) { struct sk_buff *skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2); if (skb == NULL) { @@ -114,6 +116,24 @@ static int sonic_open(struct net_device *dev) return 0; } +/* Wait for the SONIC to become idle. */ +static void sonic_quiesce(struct net_device *dev, u16 mask) +{ + struct sonic_local * __maybe_unused lp = netdev_priv(dev); + int i; + u16 bits; + + for (i = 0; i < 1000; ++i) { + bits = SONIC_READ(SONIC_CMD) & mask; + if (!bits) + return; + if (irqs_disabled() || in_interrupt()) + udelay(20); + else + usleep_range(100, 200); + } + WARN_ONCE(1, "command deadline expired! 0x%04x\n", bits); +} /* * Close the SONIC device @@ -130,6 +150,9 @@ static int sonic_close(struct net_device *dev) /* * stop the SONIC, disable interrupts */ + SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS); + sonic_quiesce(dev, SONIC_CR_ALL); + SONIC_WRITE(SONIC_IMR, 0); SONIC_WRITE(SONIC_ISR, 0x7fff); SONIC_WRITE(SONIC_CMD, SONIC_CR_RST); @@ -169,6 +192,9 @@ static void sonic_tx_timeout(struct net_device *dev) * put the Sonic into software-reset mode and * disable all interrupts before releasing DMA buffers */ + SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS); + sonic_quiesce(dev, SONIC_CR_ALL); + SONIC_WRITE(SONIC_IMR, 0); SONIC_WRITE(SONIC_ISR, 0x7fff); SONIC_WRITE(SONIC_CMD, SONIC_CR_RST); @@ -206,8 +232,6 @@ static void sonic_tx_timeout(struct net_device *dev) * wake the tx queue * Concurrently with all of this, the SONIC is potentially writing to * the status flags of the TDs. - * Until some mutual exclusion is added, this code will not work with SMP. However, - * MIPS Jazz machines and m68k Macs were all uni-processor machines. */ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) @@ -215,7 +239,8 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) struct sonic_local *lp = netdev_priv(dev); dma_addr_t laddr; int length; - int entry = lp->next_tx; + int entry; + unsigned long flags; netif_dbg(lp, tx_queued, dev, "%s: skb=%p\n", __func__, skb); @@ -237,6 +262,10 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } + spin_lock_irqsave(&lp->lock, flags); + + entry = lp->next_tx; + sonic_tda_put(dev, entry, SONIC_TD_STATUS, 0); /* clear status */ sonic_tda_put(dev, entry, SONIC_TD_FRAG_COUNT, 1); /* single fragment */ sonic_tda_put(dev, entry, SONIC_TD_PKTSIZE, length); /* length of packet */ @@ -246,10 +275,6 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) sonic_tda_put(dev, entry, SONIC_TD_LINK, sonic_tda_get(dev, entry, SONIC_TD_LINK) | SONIC_EOL); - /* - * Must set tx_skb[entry] only after clearing status, and - * before clearing EOL and before stopping queue - */ wmb(); lp->tx_len[entry] = length; lp->tx_laddr[entry] = laddr; @@ -272,6 +297,8 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) SONIC_WRITE(SONIC_CMD, SONIC_CR_TXP); + spin_unlock_irqrestore(&lp->lock, flags); + return NETDEV_TX_OK; } @@ -284,15 +311,28 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) struct net_device *dev = dev_id; struct sonic_local *lp = netdev_priv(dev); int status; + unsigned long flags; + + /* The lock has two purposes. Firstly, it synchronizes sonic_interrupt() + * with sonic_send_packet() so that the two functions can share state. + * Secondly, it makes sonic_interrupt() re-entrant, as that is required + * by macsonic which must use two IRQs with different priority levels. + */ + spin_lock_irqsave(&lp->lock, flags); + + status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT; + if (!status) { + spin_unlock_irqrestore(&lp->lock, flags); - if (!(status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT)) return IRQ_NONE; + } do { + SONIC_WRITE(SONIC_ISR, status); /* clear the interrupt(s) */ + if (status & SONIC_INT_PKTRX) { netif_dbg(lp, intr, dev, "%s: packet rx\n", __func__); sonic_rx(dev); /* got packet(s) */ - SONIC_WRITE(SONIC_ISR, SONIC_INT_PKTRX); /* clear the interrupt */ } if (status & SONIC_INT_TXDN) { @@ -300,11 +340,12 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) int td_status; int freed_some = 0; - /* At this point, cur_tx is the index of a TD that is one of: - * unallocated/freed (status set & tx_skb[entry] clear) - * allocated and sent (status set & tx_skb[entry] set ) - * allocated and not yet sent (status clear & tx_skb[entry] set ) - * still being allocated by sonic_send_packet (status clear & tx_skb[entry] clear) + /* The state of a Transmit Descriptor may be inferred + * from { tx_skb[entry], td_status } as follows. + * { clear, clear } => the TD has never been used + * { set, clear } => the TD was handed to SONIC + * { set, set } => the TD was handed back + * { clear, set } => the TD is available for re-use */ netif_dbg(lp, intr, dev, "%s: tx done\n", __func__); @@ -313,18 +354,19 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) if ((td_status = sonic_tda_get(dev, entry, SONIC_TD_STATUS)) == 0) break; - if (td_status & 0x0001) { + if (td_status & SONIC_TCR_PTX) { lp->stats.tx_packets++; lp->stats.tx_bytes += sonic_tda_get(dev, entry, SONIC_TD_PKTSIZE); } else { - lp->stats.tx_errors++; - if (td_status & 0x0642) + if (td_status & (SONIC_TCR_EXD | + SONIC_TCR_EXC | SONIC_TCR_BCM)) lp->stats.tx_aborted_errors++; - if (td_status & 0x0180) + if (td_status & + (SONIC_TCR_NCRS | SONIC_TCR_CRLS)) lp->stats.tx_carrier_errors++; - if (td_status & 0x0020) + if (td_status & SONIC_TCR_OWC) lp->stats.tx_window_errors++; - if (td_status & 0x0004) + if (td_status & SONIC_TCR_FU) lp->stats.tx_fifo_errors++; } @@ -346,7 +388,6 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) if (freed_some || lp->tx_skb[entry] == NULL) netif_wake_queue(dev); /* The ring is no longer full */ lp->cur_tx = entry; - SONIC_WRITE(SONIC_ISR, SONIC_INT_TXDN); /* clear the interrupt */ } /* @@ -355,42 +396,37 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) if (status & SONIC_INT_RFO) { netif_dbg(lp, rx_err, dev, "%s: rx fifo overrun\n", __func__); - lp->stats.rx_fifo_errors++; - SONIC_WRITE(SONIC_ISR, SONIC_INT_RFO); /* clear the interrupt */ } if (status & SONIC_INT_RDE) { netif_dbg(lp, rx_err, dev, "%s: rx descriptors exhausted\n", __func__); - lp->stats.rx_dropped++; - SONIC_WRITE(SONIC_ISR, SONIC_INT_RDE); /* clear the interrupt */ } if (status & SONIC_INT_RBAE) { netif_dbg(lp, rx_err, dev, "%s: rx buffer area exceeded\n", __func__); - lp->stats.rx_dropped++; - SONIC_WRITE(SONIC_ISR, SONIC_INT_RBAE); /* clear the interrupt */ } /* counter overruns; all counters are 16bit wide */ - if (status & SONIC_INT_FAE) { + if (status & SONIC_INT_FAE) lp->stats.rx_frame_errors += 65536; - SONIC_WRITE(SONIC_ISR, SONIC_INT_FAE); /* clear the interrupt */ - } - if (status & SONIC_INT_CRC) { + if (status & SONIC_INT_CRC) lp->stats.rx_crc_errors += 65536; - SONIC_WRITE(SONIC_ISR, SONIC_INT_CRC); /* clear the interrupt */ - } - if (status & SONIC_INT_MP) { + if (status & SONIC_INT_MP) lp->stats.rx_missed_errors += 65536; - SONIC_WRITE(SONIC_ISR, SONIC_INT_MP); /* clear the interrupt */ - } /* transmit error */ if (status & SONIC_INT_TXER) { - if (SONIC_READ(SONIC_TCR) & SONIC_TCR_FU) - netif_dbg(lp, tx_err, dev, "%s: tx fifo underrun\n", - __func__); - SONIC_WRITE(SONIC_ISR, SONIC_INT_TXER); /* clear the interrupt */ + u16 tcr = SONIC_READ(SONIC_TCR); + + netif_dbg(lp, tx_err, dev, "%s: TXER intr, TCR %04x\n", + __func__, tcr); + + if (tcr & (SONIC_TCR_EXD | SONIC_TCR_EXC | + SONIC_TCR_FU | SONIC_TCR_BCM)) { + /* Aborted transmission. Try again. */ + netif_stop_queue(dev); + SONIC_WRITE(SONIC_CMD, SONIC_CR_TXP); + } } /* bus retry */ @@ -400,107 +436,164 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) /* ... to help debug DMA problems causing endless interrupts. */ /* Bounce the eth interface to turn on the interrupt again. */ SONIC_WRITE(SONIC_IMR, 0); - SONIC_WRITE(SONIC_ISR, SONIC_INT_BR); /* clear the interrupt */ } - /* load CAM done */ - if (status & SONIC_INT_LCD) - SONIC_WRITE(SONIC_ISR, SONIC_INT_LCD); /* clear the interrupt */ - } while((status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT)); + status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT; + } while (status); + + spin_unlock_irqrestore(&lp->lock, flags); + return IRQ_HANDLED; } +/* Return the array index corresponding to a given Receive Buffer pointer. */ +static int index_from_addr(struct sonic_local *lp, dma_addr_t addr, + unsigned int last) +{ + unsigned int i = last; + + do { + i = (i + 1) & SONIC_RRS_MASK; + if (addr == lp->rx_laddr[i]) + return i; + } while (i != last); + + return -ENOENT; +} + +/* Allocate and map a new skb to be used as a receive buffer. */ +static bool sonic_alloc_rb(struct net_device *dev, struct sonic_local *lp, + struct sk_buff **new_skb, dma_addr_t *new_addr) +{ + *new_skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2); + if (!*new_skb) + return false; + + if (SONIC_BUS_SCALE(lp->dma_bitmode) == 2) + skb_reserve(*new_skb, 2); + + *new_addr = dma_map_single(lp->device, skb_put(*new_skb, SONIC_RBSIZE), + SONIC_RBSIZE, DMA_FROM_DEVICE); + if (!*new_addr) { + dev_kfree_skb(*new_skb); + *new_skb = NULL; + return false; + } + + return true; +} + +/* Place a new receive resource in the Receive Resource Area and update RWP. */ +static void sonic_update_rra(struct net_device *dev, struct sonic_local *lp, + dma_addr_t old_addr, dma_addr_t new_addr) +{ + unsigned int entry = sonic_rr_entry(dev, SONIC_READ(SONIC_RWP)); + unsigned int end = sonic_rr_entry(dev, SONIC_READ(SONIC_RRP)); + u32 buf; + + /* The resources in the range [RRP, RWP) belong to the SONIC. This loop + * scans the other resources in the RRA, those in the range [RWP, RRP). + */ + do { + buf = (sonic_rra_get(dev, entry, SONIC_RR_BUFADR_H) << 16) | + sonic_rra_get(dev, entry, SONIC_RR_BUFADR_L); + + if (buf == old_addr) + break; + + entry = (entry + 1) & SONIC_RRS_MASK; + } while (entry != end); + + WARN_ONCE(buf != old_addr, "failed to find resource!\n"); + + sonic_rra_put(dev, entry, SONIC_RR_BUFADR_H, new_addr >> 16); + sonic_rra_put(dev, entry, SONIC_RR_BUFADR_L, new_addr & 0xffff); + + entry = (entry + 1) & SONIC_RRS_MASK; + + SONIC_WRITE(SONIC_RWP, sonic_rr_addr(dev, entry)); +} + /* * We have a good packet(s), pass it/them up the network stack. */ static void sonic_rx(struct net_device *dev) { struct sonic_local *lp = netdev_priv(dev); - int status; int entry = lp->cur_rx; + int prev_entry = lp->eol_rx; + bool rbe = false; while (sonic_rda_get(dev, entry, SONIC_RD_IN_USE) == 0) { - struct sk_buff *used_skb; - struct sk_buff *new_skb; - dma_addr_t new_laddr; - u16 bufadr_l; - u16 bufadr_h; - int pkt_len; - - status = sonic_rda_get(dev, entry, SONIC_RD_STATUS); - if (status & SONIC_RCR_PRX) { - /* Malloc up new buffer. */ - new_skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2); - if (new_skb == NULL) { - lp->stats.rx_dropped++; + u16 status = sonic_rda_get(dev, entry, SONIC_RD_STATUS); + + /* If the RD has LPKT set, the chip has finished with the RB */ + if ((status & SONIC_RCR_PRX) && (status & SONIC_RCR_LPKT)) { + struct sk_buff *new_skb; + dma_addr_t new_laddr; + u32 addr = (sonic_rda_get(dev, entry, + SONIC_RD_PKTPTR_H) << 16) | + sonic_rda_get(dev, entry, SONIC_RD_PKTPTR_L); + int i = index_from_addr(lp, addr, entry); + + if (i < 0) { + WARN_ONCE(1, "failed to find buffer!\n"); break; } - /* provide 16 byte IP header alignment unless DMA requires otherwise */ - if(SONIC_BUS_SCALE(lp->dma_bitmode) == 2) - skb_reserve(new_skb, 2); - - new_laddr = dma_map_single(lp->device, skb_put(new_skb, SONIC_RBSIZE), - SONIC_RBSIZE, DMA_FROM_DEVICE); - if (!new_laddr) { - dev_kfree_skb(new_skb); - printk(KERN_ERR "%s: Failed to map rx buffer, dropping packet.\n", dev->name); + + if (sonic_alloc_rb(dev, lp, &new_skb, &new_laddr)) { + struct sk_buff *used_skb = lp->rx_skb[i]; + int pkt_len; + + /* Pass the used buffer up the stack */ + dma_unmap_single(lp->device, addr, SONIC_RBSIZE, + DMA_FROM_DEVICE); + + pkt_len = sonic_rda_get(dev, entry, + SONIC_RD_PKTLEN); + skb_trim(used_skb, pkt_len); + used_skb->protocol = eth_type_trans(used_skb, + dev); + netif_rx(used_skb); + lp->stats.rx_packets++; + lp->stats.rx_bytes += pkt_len; + + lp->rx_skb[i] = new_skb; + lp->rx_laddr[i] = new_laddr; + } else { + /* Failed to obtain a new buffer so re-use it */ + new_laddr = addr; lp->stats.rx_dropped++; - break; } - - /* now we have a new skb to replace it, pass the used one up the stack */ - dma_unmap_single(lp->device, lp->rx_laddr[entry], SONIC_RBSIZE, DMA_FROM_DEVICE); - used_skb = lp->rx_skb[entry]; - pkt_len = sonic_rda_get(dev, entry, SONIC_RD_PKTLEN); - skb_trim(used_skb, pkt_len); - used_skb->protocol = eth_type_trans(used_skb, dev); - netif_rx(used_skb); - lp->stats.rx_packets++; - lp->stats.rx_bytes += pkt_len; - - /* and insert the new skb */ - lp->rx_laddr[entry] = new_laddr; - lp->rx_skb[entry] = new_skb; - - bufadr_l = (unsigned long)new_laddr & 0xffff; - bufadr_h = (unsigned long)new_laddr >> 16; - sonic_rra_put(dev, entry, SONIC_RR_BUFADR_L, bufadr_l); - sonic_rra_put(dev, entry, SONIC_RR_BUFADR_H, bufadr_h); - } else { - /* This should only happen, if we enable accepting broken packets. */ - lp->stats.rx_errors++; - if (status & SONIC_RCR_FAER) - lp->stats.rx_frame_errors++; - if (status & SONIC_RCR_CRCR) - lp->stats.rx_crc_errors++; - } - if (status & SONIC_RCR_LPKT) { - /* - * this was the last packet out of the current receive buffer - * give the buffer back to the SONIC + /* If RBE is already asserted when RWP advances then + * it's safe to clear RBE after processing this packet. */ - lp->cur_rwp += SIZEOF_SONIC_RR * SONIC_BUS_SCALE(lp->dma_bitmode); - if (lp->cur_rwp >= lp->rra_end) lp->cur_rwp = lp->rra_laddr & 0xffff; - SONIC_WRITE(SONIC_RWP, lp->cur_rwp); - if (SONIC_READ(SONIC_ISR) & SONIC_INT_RBE) { - netif_dbg(lp, rx_err, dev, "%s: rx buffer exhausted\n", - __func__); - SONIC_WRITE(SONIC_ISR, SONIC_INT_RBE); /* clear the flag */ - } - } else - printk(KERN_ERR "%s: rx desc without RCR_LPKT. Shouldn't happen !?\n", - dev->name); + rbe = rbe || SONIC_READ(SONIC_ISR) & SONIC_INT_RBE; + sonic_update_rra(dev, lp, addr, new_laddr); + } /* * give back the descriptor */ - sonic_rda_put(dev, entry, SONIC_RD_LINK, - sonic_rda_get(dev, entry, SONIC_RD_LINK) | SONIC_EOL); + sonic_rda_put(dev, entry, SONIC_RD_STATUS, 0); sonic_rda_put(dev, entry, SONIC_RD_IN_USE, 1); - sonic_rda_put(dev, lp->eol_rx, SONIC_RD_LINK, - sonic_rda_get(dev, lp->eol_rx, SONIC_RD_LINK) & ~SONIC_EOL); - lp->eol_rx = entry; - lp->cur_rx = entry = (entry + 1) & SONIC_RDS_MASK; + + prev_entry = entry; + entry = (entry + 1) & SONIC_RDS_MASK; + } + + lp->cur_rx = entry; + + if (prev_entry != lp->eol_rx) { + /* Advance the EOL flag to put descriptors back into service */ + sonic_rda_put(dev, prev_entry, SONIC_RD_LINK, SONIC_EOL | + sonic_rda_get(dev, prev_entry, SONIC_RD_LINK)); + sonic_rda_put(dev, lp->eol_rx, SONIC_RD_LINK, ~SONIC_EOL & + sonic_rda_get(dev, lp->eol_rx, SONIC_RD_LINK)); + lp->eol_rx = prev_entry; } + + if (rbe) + SONIC_WRITE(SONIC_ISR, SONIC_INT_RBE); /* * If any worth-while packets have been received, netif_rx() * has done a mark_bh(NET_BH) for us and will work on them @@ -550,6 +643,8 @@ static void sonic_multicast_list(struct net_device *dev) (netdev_mc_count(dev) > 15)) { rcr |= SONIC_RCR_AMC; } else { + unsigned long flags; + netif_dbg(lp, ifup, dev, "%s: mc_count %d\n", __func__, netdev_mc_count(dev)); sonic_set_cam_enable(dev, 1); /* always enable our own address */ @@ -563,9 +658,14 @@ static void sonic_multicast_list(struct net_device *dev) i++; } SONIC_WRITE(SONIC_CDC, 16); - /* issue Load CAM command */ SONIC_WRITE(SONIC_CDP, lp->cda_laddr & 0xffff); + + /* LCAM and TXP commands can't be used simultaneously */ + spin_lock_irqsave(&lp->lock, flags); + sonic_quiesce(dev, SONIC_CR_TXP); SONIC_WRITE(SONIC_CMD, SONIC_CR_LCAM); + sonic_quiesce(dev, SONIC_CR_LCAM); + spin_unlock_irqrestore(&lp->lock, flags); } } @@ -580,7 +680,6 @@ static void sonic_multicast_list(struct net_device *dev) */ static int sonic_init(struct net_device *dev) { - unsigned int cmd; struct sonic_local *lp = netdev_priv(dev); int i; @@ -592,12 +691,16 @@ static int sonic_init(struct net_device *dev) SONIC_WRITE(SONIC_ISR, 0x7fff); SONIC_WRITE(SONIC_CMD, SONIC_CR_RST); + /* While in reset mode, clear CAM Enable register */ + SONIC_WRITE(SONIC_CE, 0); + /* * clear software reset flag, disable receiver, clear and * enable interrupts, then completely initialize the SONIC */ SONIC_WRITE(SONIC_CMD, 0); - SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS); + SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS | SONIC_CR_STP); + sonic_quiesce(dev, SONIC_CR_ALL); /* * initialize the receive resource area @@ -615,15 +718,10 @@ static int sonic_init(struct net_device *dev) } /* initialize all RRA registers */ - lp->rra_end = (lp->rra_laddr + SONIC_NUM_RRS * SIZEOF_SONIC_RR * - SONIC_BUS_SCALE(lp->dma_bitmode)) & 0xffff; - lp->cur_rwp = (lp->rra_laddr + (SONIC_NUM_RRS - 1) * SIZEOF_SONIC_RR * - SONIC_BUS_SCALE(lp->dma_bitmode)) & 0xffff; - - SONIC_WRITE(SONIC_RSA, lp->rra_laddr & 0xffff); - SONIC_WRITE(SONIC_REA, lp->rra_end); - SONIC_WRITE(SONIC_RRP, lp->rra_laddr & 0xffff); - SONIC_WRITE(SONIC_RWP, lp->cur_rwp); + SONIC_WRITE(SONIC_RSA, sonic_rr_addr(dev, 0)); + SONIC_WRITE(SONIC_REA, sonic_rr_addr(dev, SONIC_NUM_RRS)); + SONIC_WRITE(SONIC_RRP, sonic_rr_addr(dev, 0)); + SONIC_WRITE(SONIC_RWP, sonic_rr_addr(dev, SONIC_NUM_RRS - 1)); SONIC_WRITE(SONIC_URRA, lp->rra_laddr >> 16); SONIC_WRITE(SONIC_EOBC, (SONIC_RBSIZE >> 1) - (lp->dma_bitmode ? 2 : 1)); @@ -631,14 +729,7 @@ static int sonic_init(struct net_device *dev) netif_dbg(lp, ifup, dev, "%s: issuing RRRA command\n", __func__); SONIC_WRITE(SONIC_CMD, SONIC_CR_RRRA); - i = 0; - while (i++ < 100) { - if (SONIC_READ(SONIC_CMD) & SONIC_CR_RRRA) - break; - } - - netif_dbg(lp, ifup, dev, "%s: status=%x, i=%d\n", __func__, - SONIC_READ(SONIC_CMD), i); + sonic_quiesce(dev, SONIC_CR_RRRA); /* * Initialize the receive descriptors so that they @@ -713,28 +804,17 @@ static int sonic_init(struct net_device *dev) * load the CAM */ SONIC_WRITE(SONIC_CMD, SONIC_CR_LCAM); - - i = 0; - while (i++ < 100) { - if (SONIC_READ(SONIC_ISR) & SONIC_INT_LCD) - break; - } - netif_dbg(lp, ifup, dev, "%s: CMD=%x, ISR=%x, i=%d\n", __func__, - SONIC_READ(SONIC_CMD), SONIC_READ(SONIC_ISR), i); + sonic_quiesce(dev, SONIC_CR_LCAM); /* * enable receiver, disable loopback * and enable all interrupts */ - SONIC_WRITE(SONIC_CMD, SONIC_CR_RXEN | SONIC_CR_STP); SONIC_WRITE(SONIC_RCR, SONIC_RCR_DEFAULT); SONIC_WRITE(SONIC_TCR, SONIC_TCR_DEFAULT); SONIC_WRITE(SONIC_ISR, 0x7fff); SONIC_WRITE(SONIC_IMR, SONIC_IMR_DEFAULT); - - cmd = SONIC_READ(SONIC_CMD); - if ((cmd & SONIC_CR_RXEN) == 0 || (cmd & SONIC_CR_STP) == 0) - printk(KERN_ERR "sonic_init: failed, status=%x\n", cmd); + SONIC_WRITE(SONIC_CMD, SONIC_CR_RXEN); netif_dbg(lp, ifup, dev, "%s: new status=%x\n", __func__, SONIC_READ(SONIC_CMD)); diff --git a/drivers/net/ethernet/natsemi/sonic.h b/drivers/net/ethernet/natsemi/sonic.h index 2b27f7049acb..1df6d2f06cc4 100644 --- a/drivers/net/ethernet/natsemi/sonic.h +++ b/drivers/net/ethernet/natsemi/sonic.h @@ -110,6 +110,9 @@ #define SONIC_CR_TXP 0x0002 #define SONIC_CR_HTX 0x0001 +#define SONIC_CR_ALL (SONIC_CR_LCAM | SONIC_CR_RRRA | \ + SONIC_CR_RXEN | SONIC_CR_TXP) + /* * SONIC data configuration bits */ @@ -175,6 +178,7 @@ #define SONIC_TCR_NCRS 0x0100 #define SONIC_TCR_CRLS 0x0080 #define SONIC_TCR_EXC 0x0040 +#define SONIC_TCR_OWC 0x0020 #define SONIC_TCR_PMB 0x0008 #define SONIC_TCR_FU 0x0004 #define SONIC_TCR_BCM 0x0002 @@ -274,8 +278,9 @@ #define SONIC_NUM_RDS SONIC_NUM_RRS /* number of receive descriptors */ #define SONIC_NUM_TDS 16 /* number of transmit descriptors */ -#define SONIC_RDS_MASK (SONIC_NUM_RDS-1) -#define SONIC_TDS_MASK (SONIC_NUM_TDS-1) +#define SONIC_RRS_MASK (SONIC_NUM_RRS - 1) +#define SONIC_RDS_MASK (SONIC_NUM_RDS - 1) +#define SONIC_TDS_MASK (SONIC_NUM_TDS - 1) #define SONIC_RBSIZE 1520 /* size of one resource buffer */ @@ -312,8 +317,6 @@ struct sonic_local { u32 rda_laddr; /* logical DMA address of RDA */ dma_addr_t rx_laddr[SONIC_NUM_RRS]; /* logical DMA addresses of rx skbuffs */ dma_addr_t tx_laddr[SONIC_NUM_TDS]; /* logical DMA addresses of tx skbuffs */ - unsigned int rra_end; - unsigned int cur_rwp; unsigned int cur_rx; unsigned int cur_tx; /* first unacked transmit packet */ unsigned int eol_rx; @@ -322,6 +325,7 @@ struct sonic_local { int msg_enable; struct device *device; /* generic device */ struct net_device_stats stats; + spinlock_t lock; }; #define TX_TIMEOUT (3 * HZ) @@ -344,30 +348,30 @@ static void sonic_msg_init(struct net_device *dev); as far as we can tell. */ /* OpenBSD calls this "SWO". I'd like to think that sonic_buf_put() is a much better name. */ -static inline void sonic_buf_put(void* base, int bitmode, +static inline void sonic_buf_put(u16 *base, int bitmode, int offset, __u16 val) { if (bitmode) #ifdef __BIG_ENDIAN - ((__u16 *) base + (offset*2))[1] = val; + __raw_writew(val, base + (offset * 2) + 1); #else - ((__u16 *) base + (offset*2))[0] = val; + __raw_writew(val, base + (offset * 2) + 0); #endif else - ((__u16 *) base)[offset] = val; + __raw_writew(val, base + (offset * 1) + 0); } -static inline __u16 sonic_buf_get(void* base, int bitmode, +static inline __u16 sonic_buf_get(u16 *base, int bitmode, int offset) { if (bitmode) #ifdef __BIG_ENDIAN - return ((volatile __u16 *) base + (offset*2))[1]; + return __raw_readw(base + (offset * 2) + 1); #else - return ((volatile __u16 *) base + (offset*2))[0]; + return __raw_readw(base + (offset * 2) + 0); #endif else - return ((volatile __u16 *) base)[offset]; + return __raw_readw(base + (offset * 1) + 0); } /* Inlines that you should actually use for reading/writing DMA buffers */ @@ -447,6 +451,22 @@ static inline __u16 sonic_rra_get(struct net_device* dev, int entry, (entry * SIZEOF_SONIC_RR) + offset); } +static inline u16 sonic_rr_addr(struct net_device *dev, int entry) +{ + struct sonic_local *lp = netdev_priv(dev); + + return lp->rra_laddr + + entry * SIZEOF_SONIC_RR * SONIC_BUS_SCALE(lp->dma_bitmode); +} + +static inline u16 sonic_rr_entry(struct net_device *dev, u16 addr) +{ + struct sonic_local *lp = netdev_priv(dev); + + return (addr - (u16)lp->rra_laddr) / (SIZEOF_SONIC_RR * + SONIC_BUS_SCALE(lp->dma_bitmode)); +} + static const char version[] = "sonic.c:v0.92 20.9.98 tsbogend@alpha.franken.de\n"; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index f6222ada6818..9b3ba98726d7 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -804,19 +804,21 @@ static struct sock *gtp_encap_enable_socket(int fd, int type, return NULL; } - if (sock->sk->sk_protocol != IPPROTO_UDP) { + sk = sock->sk; + if (sk->sk_protocol != IPPROTO_UDP || + sk->sk_type != SOCK_DGRAM || + (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)) { pr_debug("socket fd=%d not UDP\n", fd); sk = ERR_PTR(-EINVAL); goto out_sock; } - lock_sock(sock->sk); - if (sock->sk->sk_user_data) { + lock_sock(sk); + if (sk->sk_user_data) { sk = ERR_PTR(-EBUSY); goto out_rel_sock; } - sk = sock->sk; sock_hold(sk); tuncfg.sk_user_data = gtp; diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index 2a91c192659f..61d7e0d1d77d 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -452,9 +452,16 @@ static void slip_transmit(struct work_struct *work) */ static void slip_write_wakeup(struct tty_struct *tty) { - struct slip *sl = tty->disc_data; + struct slip *sl; + + rcu_read_lock(); + sl = rcu_dereference(tty->disc_data); + if (!sl) + goto out; schedule_work(&sl->tx_work); +out: + rcu_read_unlock(); } static void sl_tx_timeout(struct net_device *dev) @@ -882,10 +889,11 @@ static void slip_close(struct tty_struct *tty) return; spin_lock_bh(&sl->lock); - tty->disc_data = NULL; + rcu_assign_pointer(tty->disc_data, NULL); sl->tty = NULL; spin_unlock_bh(&sl->lock); + synchronize_rcu(); flush_work(&sl->tx_work); /* VSV = very important to remove timers */ diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 16564ebcde50..69f553a028ee 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1936,6 +1936,10 @@ drop: if (ret != XDP_PASS) { rcu_read_unlock(); local_bh_enable(); + if (frags) { + tfile->napi.skb = NULL; + mutex_unlock(&tfile->napi_mutex); + } return total_len; } } diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index c232f1612083..0170a441208a 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -3668,6 +3669,19 @@ static void lan78xx_tx_timeout(struct net_device *net) tasklet_schedule(&dev->bh); } +static netdev_features_t lan78xx_features_check(struct sk_buff *skb, + struct net_device *netdev, + netdev_features_t features) +{ + if (skb->len + TX_OVERHEAD > MAX_SINGLE_PACKET_SIZE) + features &= ~NETIF_F_GSO_MASK; + + features = vlan_features_check(skb, features); + features = vxlan_features_check(skb, features); + + return features; +} + static const struct net_device_ops lan78xx_netdev_ops = { .ndo_open = lan78xx_open, .ndo_stop = lan78xx_stop, @@ -3681,6 +3695,7 @@ static const struct net_device_ops lan78xx_netdev_ops = { .ndo_set_features = lan78xx_set_features, .ndo_vlan_rx_add_vid = lan78xx_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = lan78xx_vlan_rx_kill_vid, + .ndo_features_check = lan78xx_features_check, }; static void lan78xx_stat_monitor(struct timer_list *t) diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c index f43c06569ea1..c4c8f1b62e1e 100644 --- a/drivers/net/wireless/cisco/airo.c +++ b/drivers/net/wireless/cisco/airo.c @@ -7790,16 +7790,8 @@ static int readrids(struct net_device *dev, aironet_ioctl *comp) { case AIROGVLIST: ridcode = RID_APLIST; break; case AIROGDRVNAM: ridcode = RID_DRVNAME; break; case AIROGEHTENC: ridcode = RID_ETHERENCAP; break; - case AIROGWEPKTMP: ridcode = RID_WEP_TEMP; - /* Only super-user can read WEP keys */ - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - break; - case AIROGWEPKNV: ridcode = RID_WEP_PERM; - /* Only super-user can read WEP keys */ - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - break; + case AIROGWEPKTMP: ridcode = RID_WEP_TEMP; break; + case AIROGWEPKNV: ridcode = RID_WEP_PERM; break; case AIROGSTAT: ridcode = RID_STATUS; break; case AIROGSTATSD32: ridcode = RID_STATSDELTA; break; case AIROGSTATSC32: ridcode = RID_STATS; break; @@ -7813,7 +7805,13 @@ static int readrids(struct net_device *dev, aironet_ioctl *comp) { return -EINVAL; } - if ((iobuf = kmalloc(RIDSIZE, GFP_KERNEL)) == NULL) + if (ridcode == RID_WEP_TEMP || ridcode == RID_WEP_PERM) { + /* Only super-user can read WEP keys */ + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + } + + if ((iobuf = kzalloc(RIDSIZE, GFP_KERNEL)) == NULL) return -ENOMEM; PC4500_readrid(ai,ridcode,iobuf,RIDSIZE, 1); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h index 60aff2ecec12..58df25e2fb32 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h @@ -154,5 +154,6 @@ #define IWL_MVM_D3_DEBUG false #define IWL_MVM_USE_TWT false #define IWL_MVM_AMPDU_CONSEC_DROPS_DELBA 10 +#define IWL_MVM_USE_NSSN_SYNC 0 #endif /* __MVM_CONSTANTS_H */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index d31f96c3f925..49aeab7c27a2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -742,6 +742,20 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm) return ret; } +static void iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb, + struct ieee80211_sta *sta) +{ + if (likely(sta)) { + if (likely(iwl_mvm_tx_skb_sta(mvm, skb, sta) == 0)) + return; + } else { + if (likely(iwl_mvm_tx_skb_non_sta(mvm, skb) == 0)) + return; + } + + ieee80211_free_txskb(mvm->hw, skb); +} + static void iwl_mvm_mac_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control, struct sk_buff *skb) @@ -785,14 +799,7 @@ static void iwl_mvm_mac_tx(struct ieee80211_hw *hw, } } - if (sta) { - if (iwl_mvm_tx_skb(mvm, skb, sta)) - goto drop; - return; - } - - if (iwl_mvm_tx_skb_non_sta(mvm, skb)) - goto drop; + iwl_mvm_tx_skb(mvm, skb, sta); return; drop: ieee80211_free_txskb(hw, skb); @@ -842,10 +849,7 @@ void iwl_mvm_mac_itxq_xmit(struct ieee80211_hw *hw, struct ieee80211_txq *txq) break; } - if (!txq->sta) - iwl_mvm_tx_skb_non_sta(mvm, skb); - else - iwl_mvm_tx_skb(mvm, skb, txq->sta); + iwl_mvm_tx_skb(mvm, skb, txq->sta); } } while (atomic_dec_return(&mvmtxq->tx_request)); rcu_read_unlock(); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 5ca50f39a023..5f1ecbb6fb71 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -1508,8 +1508,8 @@ int __must_check iwl_mvm_send_cmd_status(struct iwl_mvm *mvm, int __must_check iwl_mvm_send_cmd_pdu_status(struct iwl_mvm *mvm, u32 id, u16 len, const void *data, u32 *status); -int iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb, - struct ieee80211_sta *sta); +int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb, + struct ieee80211_sta *sta); int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb); void iwl_mvm_set_tx_cmd(struct iwl_mvm *mvm, struct sk_buff *skb, struct iwl_tx_cmd *tx_cmd, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 77b03b757193..a6e2a30eb310 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -514,14 +514,17 @@ static bool iwl_mvm_is_sn_less(u16 sn1, u16 sn2, u16 buffer_size) static void iwl_mvm_sync_nssn(struct iwl_mvm *mvm, u8 baid, u16 nssn) { - struct iwl_mvm_rss_sync_notif notif = { - .metadata.type = IWL_MVM_RXQ_NSSN_SYNC, - .metadata.sync = 0, - .nssn_sync.baid = baid, - .nssn_sync.nssn = nssn, - }; - - iwl_mvm_sync_rx_queues_internal(mvm, (void *)¬if, sizeof(notif)); + if (IWL_MVM_USE_NSSN_SYNC) { + struct iwl_mvm_rss_sync_notif notif = { + .metadata.type = IWL_MVM_RXQ_NSSN_SYNC, + .metadata.sync = 0, + .nssn_sync.baid = baid, + .nssn_sync.nssn = nssn, + }; + + iwl_mvm_sync_rx_queues_internal(mvm, (void *)¬if, + sizeof(notif)); + } } #define RX_REORDER_BUF_TIMEOUT_MQ (HZ / 10) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index fcafa22ec6ce..8aa567d7912c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -1220,7 +1220,7 @@ static int iwl_mvm_legacy_config_scan(struct iwl_mvm *mvm) cmd_size = sizeof(struct iwl_scan_config_v2); else cmd_size = sizeof(struct iwl_scan_config_v1); - cmd_size += num_channels; + cmd_size += mvm->fw->ucode_capa.n_scan_channels; cfg = kzalloc(cmd_size, GFP_KERNEL); if (!cfg) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index e3b2a2bf3863..d9d82f6b5e87 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -1151,7 +1151,7 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb, if (WARN_ONCE(txq_id == IWL_MVM_INVALID_QUEUE, "Invalid TXQ id")) { iwl_trans_free_tx_cmd(mvm->trans, dev_cmd); spin_unlock(&mvmsta->lock); - return 0; + return -1; } if (!iwl_mvm_has_new_tx_api(mvm)) { @@ -1203,8 +1203,8 @@ drop: return -1; } -int iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb, - struct ieee80211_sta *sta) +int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb, + struct ieee80211_sta *sta) { struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); struct ieee80211_tx_info info; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c index 041dd75ac72b..64c74acadb99 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c @@ -1537,13 +1537,13 @@ out: napi = &rxq->napi; if (napi->poll) { + napi_gro_flush(napi, false); + if (napi->rx_count) { netif_receive_skb_list(&napi->rx_list); INIT_LIST_HEAD(&napi->rx_list); napi->rx_count = 0; } - - napi_gro_flush(napi, false); } iwl_pcie_rxq_restock(trans, rxq); diff --git a/drivers/net/wireless/marvell/libertas/cfg.c b/drivers/net/wireless/marvell/libertas/cfg.c index 57edfada0665..c9401c121a14 100644 --- a/drivers/net/wireless/marvell/libertas/cfg.c +++ b/drivers/net/wireless/marvell/libertas/cfg.c @@ -273,6 +273,10 @@ add_ie_rates(u8 *tlv, const u8 *ie, int *nrates) int hw, ap, ap_max = ie[1]; u8 hw_rate; + if (ap_max > MAX_RATES) { + lbs_deb_assoc("invalid rates\n"); + return tlv; + } /* Advance past IE header */ ie += 2; @@ -1717,6 +1721,9 @@ static int lbs_ibss_join_existing(struct lbs_private *priv, struct cmd_ds_802_11_ad_hoc_join cmd; u8 preamble = RADIO_PREAMBLE_SHORT; int ret = 0; + int hw, i; + u8 rates_max; + u8 *rates; /* TODO: set preamble based on scan result */ ret = lbs_set_radio(priv, preamble, 1); @@ -1775,9 +1782,12 @@ static int lbs_ibss_join_existing(struct lbs_private *priv, if (!rates_eid) { lbs_add_rates(cmd.bss.rates); } else { - int hw, i; - u8 rates_max = rates_eid[1]; - u8 *rates = cmd.bss.rates; + rates_max = rates_eid[1]; + if (rates_max > MAX_RATES) { + lbs_deb_join("invalid rates"); + goto out; + } + rates = cmd.bss.rates; for (hw = 0; hw < ARRAY_SIZE(lbs_rates); hw++) { u8 hw_rate = lbs_rates[hw].bitrate / 5; for (i = 0; i < rates_max; i++) { diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 308f744393eb..1593b8494ebb 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5021,18 +5021,25 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0422, quirk_no_ext_tags); #ifdef CONFIG_PCI_ATS /* - * Some devices have a broken ATS implementation causing IOMMU stalls. - * Don't use ATS for those devices. + * Some devices require additional driver setup to enable ATS. Don't use + * ATS for those devices as ATS will be enabled before the driver has had a + * chance to load and configure the device. */ -static void quirk_no_ats(struct pci_dev *pdev) +static void quirk_amd_harvest_no_ats(struct pci_dev *pdev) { - pci_info(pdev, "disabling ATS (broken on this device)\n"); + if (pdev->device == 0x7340 && pdev->revision != 0xc5) + return; + + pci_info(pdev, "disabling ATS\n"); pdev->ats_cap = 0; } /* AMD Stoney platform GPU */ -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_no_ats); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_amd_harvest_no_ats); +/* AMD Iceland dGPU */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_amd_harvest_no_ats); +/* AMD Navi14 dGPU */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats); #endif /* CONFIG_PCI_ATS */ /* Freescale PCIe doesn't support MSI in RC mode */ diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c index 44d7f50bbc82..d936e7aa74c4 100644 --- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c +++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c @@ -49,6 +49,7 @@ .padown_offset = SPT_PAD_OWN, \ .padcfglock_offset = SPT_PADCFGLOCK, \ .hostown_offset = SPT_HOSTSW_OWN, \ + .is_offset = SPT_GPI_IS, \ .ie_offset = SPT_GPI_IE, \ .pin_base = (s), \ .npins = ((e) - (s) + 1), \ diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index f194ffc4699e..c070cb2a6a5b 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -4151,9 +4151,6 @@ int iscsit_close_connection( iscsit_stop_nopin_response_timer(conn); iscsit_stop_nopin_timer(conn); - if (conn->conn_transport->iscsit_wait_conn) - conn->conn_transport->iscsit_wait_conn(conn); - /* * During Connection recovery drop unacknowledged out of order * commands for this connection, and prepare the other commands @@ -4239,6 +4236,9 @@ int iscsit_close_connection( target_sess_cmd_list_set_waiting(sess->se_sess); target_wait_for_sess_cmds(sess->se_sess); + if (conn->conn_transport->iscsit_wait_conn) + conn->conn_transport->iscsit_wait_conn(conn); + ahash_request_free(conn->conn_tx_hash); if (conn->conn_rx_hash) { struct crypto_ahash *tfm; diff --git a/fs/afs/cell.c b/fs/afs/cell.c index fd5133e26a38..78ba5f932287 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -134,8 +134,17 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, _leave(" = -ENAMETOOLONG"); return ERR_PTR(-ENAMETOOLONG); } - if (namelen == 5 && memcmp(name, "@cell", 5) == 0) + + /* Prohibit cell names that contain unprintable chars, '/' and '@' or + * that begin with a dot. This also precludes "@cell". + */ + if (name[0] == '.') return ERR_PTR(-EINVAL); + for (i = 0; i < namelen; i++) { + char ch = name[i]; + if (!isprint(ch) || ch == '/' || ch == '@') + return ERR_PTR(-EINVAL); + } _enter("%*.*s,%s", namelen, namelen, name, addresses); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index a5163296d9d9..ee02a742fff5 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -708,8 +708,10 @@ void ceph_mdsc_release_request(struct kref *kref) /* avoid calling iput_final() in mds dispatch threads */ ceph_async_iput(req->r_inode); } - if (req->r_parent) + if (req->r_parent) { ceph_put_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN); + ceph_async_iput(req->r_parent); + } ceph_async_iput(req->r_target_inode); if (req->r_dentry) dput(req->r_dentry); @@ -2670,8 +2672,10 @@ int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir, /* take CAP_PIN refs for r_inode, r_parent, r_old_dentry */ if (req->r_inode) ceph_get_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN); - if (req->r_parent) + if (req->r_parent) { ceph_get_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN); + ihold(req->r_parent); + } if (req->r_old_dentry_dir) ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir), CEPH_CAP_PIN); diff --git a/fs/io_uring.c b/fs/io_uring.c index b1c9ad1fb9e1..709671faaed6 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3716,12 +3716,6 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, wake_up(&ctx->sqo_wait); submitted = to_submit; } else if (to_submit) { - if (current->mm != ctx->sqo_mm || - current_cred() != ctx->creds) { - ret = -EPERM; - goto out; - } - to_submit = min(to_submit, ctx->sq_entries); mutex_lock(&ctx->uring_lock); diff --git a/fs/namei.c b/fs/namei.c index 671c3c1a3425..e81521c87f98 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1001,7 +1001,8 @@ static int may_linkat(struct path *link) * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory * should be allowed, or not, on files that already * exist. - * @dir: the sticky parent directory + * @dir_mode: mode bits of directory + * @dir_uid: owner of directory * @inode: the inode of the file to open * * Block an O_CREAT open of a FIFO (or a regular file) when: @@ -1017,18 +1018,18 @@ static int may_linkat(struct path *link) * * Returns 0 if the open is allowed, -ve on error. */ -static int may_create_in_sticky(struct dentry * const dir, +static int may_create_in_sticky(umode_t dir_mode, kuid_t dir_uid, struct inode * const inode) { if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) || (!sysctl_protected_regular && S_ISREG(inode->i_mode)) || - likely(!(dir->d_inode->i_mode & S_ISVTX)) || - uid_eq(inode->i_uid, dir->d_inode->i_uid) || + likely(!(dir_mode & S_ISVTX)) || + uid_eq(inode->i_uid, dir_uid) || uid_eq(current_fsuid(), inode->i_uid)) return 0; - if (likely(dir->d_inode->i_mode & 0002) || - (dir->d_inode->i_mode & 0020 && + if (likely(dir_mode & 0002) || + (dir_mode & 0020 && ((sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) || (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode))))) { return -EACCES; @@ -3248,6 +3249,8 @@ static int do_last(struct nameidata *nd, struct file *file, const struct open_flags *op) { struct dentry *dir = nd->path.dentry; + kuid_t dir_uid = dir->d_inode->i_uid; + umode_t dir_mode = dir->d_inode->i_mode; int open_flag = op->open_flag; bool will_truncate = (open_flag & O_TRUNC) != 0; bool got_write = false; @@ -3383,7 +3386,7 @@ finish_open: error = -EISDIR; if (d_is_dir(nd->path.dentry)) goto out; - error = may_create_in_sticky(dir, + error = may_create_in_sticky(dir_mode, dir_uid, d_backing_inode(nd->path.dentry)); if (unlikely(error)) goto out; diff --git a/fs/readdir.c b/fs/readdir.c index d26d5ea4de7b..de2eceffdee8 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -102,10 +102,14 @@ EXPORT_SYMBOL(iterate_dir); * filename length, and the above "soft error" worry means * that it's probably better left alone until we have that * issue clarified. + * + * Note the PATH_MAX check - it's arbitrary but the real + * kernel limit on a possible path component, not NAME_MAX, + * which is the technical standard limit. */ static int verify_dirent_name(const char *name, int len) { - if (!len) + if (len <= 0 || len >= PATH_MAX) return -EIO; if (memchr(name, '/', len)) return -EIO; @@ -206,7 +210,7 @@ struct linux_dirent { struct getdents_callback { struct dir_context ctx; struct linux_dirent __user * current_dir; - struct linux_dirent __user * previous; + int prev_reclen; int count; int error; }; @@ -214,12 +218,13 @@ struct getdents_callback { static int filldir(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { - struct linux_dirent __user * dirent; + struct linux_dirent __user *dirent, *prev; struct getdents_callback *buf = container_of(ctx, struct getdents_callback, ctx); unsigned long d_ino; int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2, sizeof(long)); + int prev_reclen; buf->error = verify_dirent_name(name, namlen); if (unlikely(buf->error)) @@ -232,28 +237,24 @@ static int filldir(struct dir_context *ctx, const char *name, int namlen, buf->error = -EOVERFLOW; return -EOVERFLOW; } - dirent = buf->previous; - if (dirent && signal_pending(current)) + prev_reclen = buf->prev_reclen; + if (prev_reclen && signal_pending(current)) return -EINTR; - - /* - * Note! This range-checks 'previous' (which may be NULL). - * The real range was checked in getdents - */ - if (!user_access_begin(dirent, sizeof(*dirent))) - goto efault; - if (dirent) - unsafe_put_user(offset, &dirent->d_off, efault_end); dirent = buf->current_dir; + prev = (void __user *) dirent - prev_reclen; + if (!user_access_begin(prev, reclen + prev_reclen)) + goto efault; + + /* This might be 'dirent->d_off', but if so it will get overwritten */ + unsafe_put_user(offset, &prev->d_off, efault_end); unsafe_put_user(d_ino, &dirent->d_ino, efault_end); unsafe_put_user(reclen, &dirent->d_reclen, efault_end); unsafe_put_user(d_type, (char __user *) dirent + reclen - 1, efault_end); unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); user_access_end(); - buf->previous = dirent; - dirent = (void __user *)dirent + reclen; - buf->current_dir = dirent; + buf->current_dir = (void __user *)dirent + reclen; + buf->prev_reclen = reclen; buf->count -= reclen; return 0; efault_end: @@ -267,7 +268,6 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, struct linux_dirent __user *, dirent, unsigned int, count) { struct fd f; - struct linux_dirent __user * lastdirent; struct getdents_callback buf = { .ctx.actor = filldir, .count = count, @@ -285,8 +285,10 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, error = iterate_dir(f.file, &buf.ctx); if (error >= 0) error = buf.error; - lastdirent = buf.previous; - if (lastdirent) { + if (buf.prev_reclen) { + struct linux_dirent __user * lastdirent; + lastdirent = (void __user *)buf.current_dir - buf.prev_reclen; + if (put_user(buf.ctx.pos, &lastdirent->d_off)) error = -EFAULT; else @@ -299,7 +301,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, struct getdents_callback64 { struct dir_context ctx; struct linux_dirent64 __user * current_dir; - struct linux_dirent64 __user * previous; + int prev_reclen; int count; int error; }; @@ -307,11 +309,12 @@ struct getdents_callback64 { static int filldir64(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { - struct linux_dirent64 __user *dirent; + struct linux_dirent64 __user *dirent, *prev; struct getdents_callback64 *buf = container_of(ctx, struct getdents_callback64, ctx); int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1, sizeof(u64)); + int prev_reclen; buf->error = verify_dirent_name(name, namlen); if (unlikely(buf->error)) @@ -319,30 +322,27 @@ static int filldir64(struct dir_context *ctx, const char *name, int namlen, buf->error = -EINVAL; /* only used if we fail.. */ if (reclen > buf->count) return -EINVAL; - dirent = buf->previous; - if (dirent && signal_pending(current)) + prev_reclen = buf->prev_reclen; + if (prev_reclen && signal_pending(current)) return -EINTR; - - /* - * Note! This range-checks 'previous' (which may be NULL). - * The real range was checked in getdents - */ - if (!user_access_begin(dirent, sizeof(*dirent))) - goto efault; - if (dirent) - unsafe_put_user(offset, &dirent->d_off, efault_end); dirent = buf->current_dir; + prev = (void __user *)dirent - prev_reclen; + if (!user_access_begin(prev, reclen + prev_reclen)) + goto efault; + + /* This might be 'dirent->d_off', but if so it will get overwritten */ + unsafe_put_user(offset, &prev->d_off, efault_end); unsafe_put_user(ino, &dirent->d_ino, efault_end); unsafe_put_user(reclen, &dirent->d_reclen, efault_end); unsafe_put_user(d_type, &dirent->d_type, efault_end); unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); user_access_end(); - buf->previous = dirent; - dirent = (void __user *)dirent + reclen; - buf->current_dir = dirent; + buf->prev_reclen = reclen; + buf->current_dir = (void __user *)dirent + reclen; buf->count -= reclen; return 0; + efault_end: user_access_end(); efault: @@ -354,7 +354,6 @@ int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, unsigned int count) { struct fd f; - struct linux_dirent64 __user * lastdirent; struct getdents_callback64 buf = { .ctx.actor = filldir64, .count = count, @@ -372,9 +371,11 @@ int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, error = iterate_dir(f.file, &buf.ctx); if (error >= 0) error = buf.error; - lastdirent = buf.previous; - if (lastdirent) { + if (buf.prev_reclen) { + struct linux_dirent64 __user * lastdirent; typeof(lastdirent->d_off) d_off = buf.ctx.pos; + + lastdirent = (void __user *) buf.current_dir - buf.prev_reclen; if (__put_user(d_off, &lastdirent->d_off)) error = -EFAULT; else diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 13f09706033a..f8fde9fa479c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3666,6 +3666,8 @@ int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); int dev_change_net_namespace(struct net_device *, struct net *, const char *); int __dev_set_mtu(struct net_device *, int); +int dev_validate_mtu(struct net_device *dev, int mtu, + struct netlink_ext_ack *extack); int dev_set_mtu_ext(struct net_device *dev, int mtu, struct netlink_ext_ack *extack); int dev_set_mtu(struct net_device *, int); diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 9bc255a8461b..77336f4c4b1c 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -445,13 +445,6 @@ ip6addrptr(const struct sk_buff *skb, bool src, struct in6_addr *addr) sizeof(*addr)); } -/* Calculate the bytes required to store the inclusive range of a-b */ -static inline int -bitmap_bytes(u32 a, u32 b) -{ - return 4 * ((((b - a + 8) / 8) + 3) / 4); -} - /* How often should the gc be run by default */ #define IPSET_GC_TIME (3 * 60) diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index cf09ab37b45b..851425c3178f 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -31,7 +31,7 @@ struct nfnetlink_subsystem { const struct nfnl_callback *cb; /* callback for individual types */ struct module *owner; int (*commit)(struct net *net, struct sk_buff *skb); - int (*abort)(struct net *net, struct sk_buff *skb); + int (*abort)(struct net *net, struct sk_buff *skb, bool autoload); void (*cleanup)(struct net *net); bool (*valid_genid)(struct net *net, u32 genid); }; diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index 286fd960896f..a1a8d45adb42 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -7,6 +7,7 @@ struct netns_nftables { struct list_head tables; struct list_head commit_list; + struct list_head module_list; struct mutex commit_mutex; unsigned int base_seq; u8 gencursor; diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h index 9a0e8af21310..a5ccfa67bc5c 100644 --- a/include/trace/events/xen.h +++ b/include/trace/events/xen.h @@ -66,7 +66,11 @@ TRACE_EVENT(xen_mc_callback, TP_PROTO(xen_mc_callback_fn_t fn, void *data), TP_ARGS(fn, data), TP_STRUCT__entry( - __field(xen_mc_callback_fn_t, fn) + /* + * Use field_struct to avoid is_signed_type() + * comparison of a function pointer. + */ + __field_struct(xen_mc_callback_fn_t, fn) __field(void *, data) ), TP_fast_assign( diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 26b9168321e7..d65f2d5ab694 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1147,24 +1147,24 @@ void free_basic_memory_bitmaps(void) void clear_free_pages(void) { -#ifdef CONFIG_PAGE_POISONING_ZERO struct memory_bitmap *bm = free_pages_map; unsigned long pfn; if (WARN_ON(!(free_pages_map))) return; - memory_bm_position_reset(bm); - pfn = memory_bm_next_pfn(bm); - while (pfn != BM_END_OF_MAP) { - if (pfn_valid(pfn)) - clear_highpage(pfn_to_page(pfn)); - + if (IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) || want_init_on_free()) { + memory_bm_position_reset(bm); pfn = memory_bm_next_pfn(bm); + while (pfn != BM_END_OF_MAP) { + if (pfn_valid(pfn)) + clear_highpage(pfn_to_page(pfn)); + + pfn = memory_bm_next_pfn(bm); + } + memory_bm_position_reset(bm); + pr_info("free pages cleared after restore\n"); } - memory_bm_position_reset(bm); - pr_info("free pages cleared after restore\n"); -#endif /* PAGE_POISONING_ZERO */ } /** diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index bcb72f102613..341aab32c946 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9270,6 +9270,11 @@ __init static int tracing_set_default_clock(void) { /* sched_clock_stable() is determined in late_initcall */ if (!trace_boot_clock && !sched_clock_stable()) { + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warn("Can not set tracing clock due to lockdown\n"); + return -EPERM; + } + printk(KERN_WARNING "Unstable clock detected, switching default tracing clock to \"global\"\n" "If you want to keep using the local clock, then add:\n" diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index c2783915600c..205692181e7b 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -116,6 +116,7 @@ struct hist_field { struct ftrace_event_field *field; unsigned long flags; hist_field_fn_t fn; + unsigned int ref; unsigned int size; unsigned int offset; unsigned int is_signed; @@ -1766,11 +1767,13 @@ static struct hist_field *find_var(struct hist_trigger_data *hist_data, struct event_trigger_data *test; struct hist_field *hist_field; + lockdep_assert_held(&event_mutex); + hist_field = find_var_field(hist_data, var_name); if (hist_field) return hist_field; - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { test_data = test->private_data; hist_field = find_var_field(test_data, var_name); @@ -1820,7 +1823,9 @@ static struct hist_field *find_file_var(struct trace_event_file *file, struct event_trigger_data *test; struct hist_field *hist_field; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { test_data = test->private_data; hist_field = find_var_field(test_data, var_name); @@ -2423,8 +2428,16 @@ static int contains_operator(char *str) return field_op; } +static void get_hist_field(struct hist_field *hist_field) +{ + hist_field->ref++; +} + static void __destroy_hist_field(struct hist_field *hist_field) { + if (--hist_field->ref > 1) + return; + kfree(hist_field->var.name); kfree(hist_field->name); kfree(hist_field->type); @@ -2466,6 +2479,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, if (!hist_field) return NULL; + hist_field->ref = 1; + hist_field->hist_data = hist_data; if (flags & HIST_FIELD_FL_EXPR || flags & HIST_FIELD_FL_ALIAS) @@ -2661,6 +2676,17 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data, { unsigned long flags = HIST_FIELD_FL_VAR_REF; struct hist_field *ref_field; + int i; + + /* Check if the variable already exists */ + for (i = 0; i < hist_data->n_var_refs; i++) { + ref_field = hist_data->var_refs[i]; + if (ref_field->var.idx == var_field->var.idx && + ref_field->var.hist_data == var_field->hist_data) { + get_hist_field(ref_field); + return ref_field; + } + } ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL); if (ref_field) { @@ -3115,7 +3141,9 @@ static char *find_trigger_filter(struct hist_trigger_data *hist_data, { struct event_trigger_data *test; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (test->private_data == hist_data) return test->filter_str; @@ -3166,9 +3194,11 @@ find_compatible_hist(struct hist_trigger_data *target_hist_data, struct event_trigger_data *test; unsigned int n_keys; + lockdep_assert_held(&event_mutex); + n_keys = target_hist_data->n_fields - target_hist_data->n_vals; - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { hist_data = test->private_data; @@ -5528,7 +5558,7 @@ static int hist_show(struct seq_file *m, void *v) goto out_unlock; } - list_for_each_entry_rcu(data, &event_file->triggers, list) { + list_for_each_entry(data, &event_file->triggers, list) { if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) hist_trigger_show(m, data, n++); } @@ -5921,7 +5951,9 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops, if (hist_data->attrs->name && !named_data) goto new; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (!hist_trigger_match(data, test, named_data, false)) continue; @@ -6005,10 +6037,12 @@ static bool have_hist_trigger_match(struct event_trigger_data *data, struct event_trigger_data *test, *named_data = NULL; bool match = false; + lockdep_assert_held(&event_mutex); + if (hist_data->attrs->name) named_data = find_named_trigger(hist_data->attrs->name); - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (hist_trigger_match(data, test, named_data, false)) { match = true; @@ -6026,10 +6060,12 @@ static bool hist_trigger_check_refs(struct event_trigger_data *data, struct hist_trigger_data *hist_data = data->private_data; struct event_trigger_data *test, *named_data = NULL; + lockdep_assert_held(&event_mutex); + if (hist_data->attrs->name) named_data = find_named_trigger(hist_data->attrs->name); - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (!hist_trigger_match(data, test, named_data, false)) continue; @@ -6051,10 +6087,12 @@ static void hist_unregister_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *test, *named_data = NULL; bool unregistered = false; + lockdep_assert_held(&event_mutex); + if (hist_data->attrs->name) named_data = find_named_trigger(hist_data->attrs->name); - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (!hist_trigger_match(data, test, named_data, false)) continue; @@ -6080,7 +6118,9 @@ static bool hist_file_check_refs(struct trace_event_file *file) struct hist_trigger_data *hist_data; struct event_trigger_data *test; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { hist_data = test->private_data; if (check_var_refs(hist_data)) @@ -6323,7 +6363,8 @@ hist_enable_trigger(struct event_trigger_data *data, void *rec, struct enable_trigger_data *enable_data = data->private_data; struct event_trigger_data *test; - list_for_each_entry_rcu(test, &enable_data->file->triggers, list) { + list_for_each_entry_rcu(test, &enable_data->file->triggers, list, + lockdep_is_held(&event_mutex)) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (enable_data->enable) test->paused = false; diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 2cd53ca21b51..40106fff06a4 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -501,7 +501,9 @@ void update_cond_flag(struct trace_event_file *file) struct event_trigger_data *data; bool set_cond = false; - list_for_each_entry_rcu(data, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(data, &file->triggers, list) { if (data->filter || event_command_post_trigger(data->cmd_ops) || event_command_needs_rec(data->cmd_ops)) { set_cond = true; @@ -536,7 +538,9 @@ static int register_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *test; int ret = 0; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == data->cmd_ops->trigger_type) { ret = -EEXIST; goto out; @@ -581,7 +585,9 @@ static void unregister_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *data; bool unregistered = false; - list_for_each_entry_rcu(data, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(data, &file->triggers, list) { if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) { unregistered = true; list_del_rcu(&data->list); @@ -1497,7 +1503,9 @@ int event_enable_register_trigger(char *glob, struct event_trigger_data *test; int ret = 0; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { test_enable_data = test->private_data; if (test_enable_data && (test->cmd_ops->trigger_type == @@ -1537,7 +1545,9 @@ void event_enable_unregister_trigger(char *glob, struct event_trigger_data *data; bool unregistered = false; - list_for_each_entry_rcu(data, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(data, &file->triggers, list) { enable_data = data->private_data; if (enable_data && (data->cmd_ops->trigger_type == diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 7f890262c8a3..3e5f9c7d939c 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -290,7 +290,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, INIT_HLIST_NODE(&tk->rp.kp.hlist); INIT_LIST_HEAD(&tk->rp.kp.list); - ret = trace_probe_init(&tk->tp, event, group); + ret = trace_probe_init(&tk->tp, event, group, 0); if (ret < 0) goto error; diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 905b10af5d5c..bba18cf44a30 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -984,7 +984,7 @@ void trace_probe_cleanup(struct trace_probe *tp) } int trace_probe_init(struct trace_probe *tp, const char *event, - const char *group) + const char *group, size_t event_data_size) { struct trace_event_call *call; int ret = 0; @@ -992,7 +992,8 @@ int trace_probe_init(struct trace_probe *tp, const char *event, if (!event || !group) return -EINVAL; - tp->event = kzalloc(sizeof(struct trace_probe_event), GFP_KERNEL); + tp->event = kzalloc(sizeof(struct trace_probe_event) + event_data_size, + GFP_KERNEL); if (!tp->event) return -ENOMEM; diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 4ee703728aec..03e4e180058d 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -230,6 +230,7 @@ struct trace_probe_event { struct trace_event_call call; struct list_head files; struct list_head probes; + char data[0]; }; struct trace_probe { @@ -322,7 +323,7 @@ static inline bool trace_probe_has_single_file(struct trace_probe *tp) } int trace_probe_init(struct trace_probe *tp, const char *event, - const char *group); + const char *group, size_t event_data_size); void trace_probe_cleanup(struct trace_probe *tp); int trace_probe_append(struct trace_probe *tp, struct trace_probe *to); void trace_probe_unlink(struct trace_probe *tp); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 352073d36585..f66e202fec13 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -60,7 +60,6 @@ static struct dyn_event_operations trace_uprobe_ops = { */ struct trace_uprobe { struct dyn_event devent; - struct trace_uprobe_filter filter; struct uprobe_consumer consumer; struct path path; struct inode *inode; @@ -264,6 +263,14 @@ process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest, } NOKPROBE_SYMBOL(process_fetch_insn) +static struct trace_uprobe_filter * +trace_uprobe_get_filter(struct trace_uprobe *tu) +{ + struct trace_probe_event *event = tu->tp.event; + + return (struct trace_uprobe_filter *)&event->data[0]; +} + static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter) { rwlock_init(&filter->rwlock); @@ -351,7 +358,8 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) if (!tu) return ERR_PTR(-ENOMEM); - ret = trace_probe_init(&tu->tp, event, group); + ret = trace_probe_init(&tu->tp, event, group, + sizeof(struct trace_uprobe_filter)); if (ret < 0) goto error; @@ -359,7 +367,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) tu->consumer.handler = uprobe_dispatcher; if (is_ret) tu->consumer.ret_handler = uretprobe_dispatcher; - init_trace_uprobe_filter(&tu->filter); + init_trace_uprobe_filter(trace_uprobe_get_filter(tu)); return tu; error: @@ -1067,13 +1075,14 @@ static void __probe_event_disable(struct trace_probe *tp) struct trace_probe *pos; struct trace_uprobe *tu; + tu = container_of(tp, struct trace_uprobe, tp); + WARN_ON(!uprobe_filter_is_empty(trace_uprobe_get_filter(tu))); + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); if (!tu->inode) continue; - WARN_ON(!uprobe_filter_is_empty(&tu->filter)); - uprobe_unregister(tu->inode, tu->offset, &tu->consumer); tu->inode = NULL; } @@ -1108,7 +1117,7 @@ static int probe_event_enable(struct trace_event_call *call, } tu = container_of(tp, struct trace_uprobe, tp); - WARN_ON(!uprobe_filter_is_empty(&tu->filter)); + WARN_ON(!uprobe_filter_is_empty(trace_uprobe_get_filter(tu))); if (enabled) return 0; @@ -1205,39 +1214,39 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) } static inline bool -uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event) +trace_uprobe_filter_event(struct trace_uprobe_filter *filter, + struct perf_event *event) { - return __uprobe_perf_filter(&tu->filter, event->hw.target->mm); + return __uprobe_perf_filter(filter, event->hw.target->mm); } -static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event) +static bool trace_uprobe_filter_remove(struct trace_uprobe_filter *filter, + struct perf_event *event) { bool done; - write_lock(&tu->filter.rwlock); + write_lock(&filter->rwlock); if (event->hw.target) { list_del(&event->hw.tp_list); - done = tu->filter.nr_systemwide || + done = filter->nr_systemwide || (event->hw.target->flags & PF_EXITING) || - uprobe_filter_event(tu, event); + trace_uprobe_filter_event(filter, event); } else { - tu->filter.nr_systemwide--; - done = tu->filter.nr_systemwide; + filter->nr_systemwide--; + done = filter->nr_systemwide; } - write_unlock(&tu->filter.rwlock); - - if (!done) - return uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); + write_unlock(&filter->rwlock); - return 0; + return done; } -static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) +/* This returns true if the filter always covers target mm */ +static bool trace_uprobe_filter_add(struct trace_uprobe_filter *filter, + struct perf_event *event) { bool done; - int err; - write_lock(&tu->filter.rwlock); + write_lock(&filter->rwlock); if (event->hw.target) { /* * event->parent != NULL means copy_process(), we can avoid @@ -1247,28 +1256,21 @@ static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) * attr.enable_on_exec means that exec/mmap will install the * breakpoints we need. */ - done = tu->filter.nr_systemwide || + done = filter->nr_systemwide || event->parent || event->attr.enable_on_exec || - uprobe_filter_event(tu, event); - list_add(&event->hw.tp_list, &tu->filter.perf_events); + trace_uprobe_filter_event(filter, event); + list_add(&event->hw.tp_list, &filter->perf_events); } else { - done = tu->filter.nr_systemwide; - tu->filter.nr_systemwide++; + done = filter->nr_systemwide; + filter->nr_systemwide++; } - write_unlock(&tu->filter.rwlock); + write_unlock(&filter->rwlock); - err = 0; - if (!done) { - err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); - if (err) - uprobe_perf_close(tu, event); - } - return err; + return done; } -static int uprobe_perf_multi_call(struct trace_event_call *call, - struct perf_event *event, - int (*op)(struct trace_uprobe *tu, struct perf_event *event)) +static int uprobe_perf_close(struct trace_event_call *call, + struct perf_event *event) { struct trace_probe *pos, *tp; struct trace_uprobe *tu; @@ -1278,25 +1280,59 @@ static int uprobe_perf_multi_call(struct trace_event_call *call, if (WARN_ON_ONCE(!tp)) return -ENODEV; + tu = container_of(tp, struct trace_uprobe, tp); + if (trace_uprobe_filter_remove(trace_uprobe_get_filter(tu), event)) + return 0; + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); - ret = op(tu, event); + ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); if (ret) break; } return ret; } + +static int uprobe_perf_open(struct trace_event_call *call, + struct perf_event *event) +{ + struct trace_probe *pos, *tp; + struct trace_uprobe *tu; + int err = 0; + + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return -ENODEV; + + tu = container_of(tp, struct trace_uprobe, tp); + if (trace_uprobe_filter_add(trace_uprobe_get_filter(tu), event)) + return 0; + + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { + err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); + if (err) { + uprobe_perf_close(call, event); + break; + } + } + + return err; +} + static bool uprobe_perf_filter(struct uprobe_consumer *uc, enum uprobe_filter_ctx ctx, struct mm_struct *mm) { + struct trace_uprobe_filter *filter; struct trace_uprobe *tu; int ret; tu = container_of(uc, struct trace_uprobe, consumer); - read_lock(&tu->filter.rwlock); - ret = __uprobe_perf_filter(&tu->filter, mm); - read_unlock(&tu->filter.rwlock); + filter = trace_uprobe_get_filter(tu); + + read_lock(&filter->rwlock); + ret = __uprobe_perf_filter(filter, mm); + read_unlock(&filter->rwlock); return ret; } @@ -1419,10 +1455,10 @@ trace_uprobe_register(struct trace_event_call *event, enum trace_reg type, return 0; case TRACE_REG_PERF_OPEN: - return uprobe_perf_multi_call(event, data, uprobe_perf_open); + return uprobe_perf_open(event, data); case TRACE_REG_PERF_CLOSE: - return uprobe_perf_multi_call(event, data, uprobe_perf_close); + return uprobe_perf_close(event, data); #endif default: diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index dccb95af6003..706020b06617 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -30,13 +30,6 @@ static inline long do_strncpy_from_user(char *dst, const char __user *src, const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long res = 0; - /* - * Truncate 'max' to the user-specified limit, so that - * we only have one limit we need to check in the loop - */ - if (max > count) - max = count; - if (IS_UNALIGNED(src, dst)) goto byte_at_a_time; @@ -114,6 +107,13 @@ long strncpy_from_user(char *dst, const char __user *src, long count) unsigned long max = max_addr - src_addr; long retval; + /* + * Truncate 'max' to the user-specified limit, so that + * we only have one limit we need to check in the loop + */ + if (max > count) + max = count; + kasan_check_write(dst, count); check_object_size(dst, count, false); if (user_access_begin(src, max)) { diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index 6c0005d5dd5c..41670d4a5816 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -26,13 +26,6 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long align, res = 0; unsigned long c; - /* - * Truncate 'max' to the user-specified limit, so that - * we only have one limit we need to check in the loop - */ - if (max > count) - max = count; - /* * Do everything aligned. But that means that we * need to also expand the maximum.. @@ -109,6 +102,13 @@ long strnlen_user(const char __user *str, long count) unsigned long max = max_addr - src_addr; long retval; + /* + * Truncate 'max' to the user-specified limit, so that + * we only have one limit we need to check in the loop + */ + if (max > count) + max = count; + if (user_access_begin(str, max)) { retval = do_strnlen_user(str, count, max); user_access_end(); diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 7df4f7f395bf..03c3f42966ce 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -2,6 +2,7 @@ /* * test_xarray.c: Test the XArray API * Copyright (c) 2017-2018 Microsoft Corporation + * Copyright (c) 2019-2020 Oracle * Author: Matthew Wilcox */ @@ -902,28 +903,34 @@ static noinline void check_store_iter(struct xarray *xa) XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_multi_find(struct xarray *xa) +static noinline void check_multi_find_1(struct xarray *xa, unsigned order) { #ifdef CONFIG_XARRAY_MULTI + unsigned long multi = 3 << order; + unsigned long next = 4 << order; unsigned long index; - xa_store_order(xa, 12, 2, xa_mk_value(12), GFP_KERNEL); - XA_BUG_ON(xa, xa_store_index(xa, 16, GFP_KERNEL) != NULL); + xa_store_order(xa, multi, order, xa_mk_value(multi), GFP_KERNEL); + XA_BUG_ON(xa, xa_store_index(xa, next, GFP_KERNEL) != NULL); + XA_BUG_ON(xa, xa_store_index(xa, next + 1, GFP_KERNEL) != NULL); index = 0; XA_BUG_ON(xa, xa_find(xa, &index, ULONG_MAX, XA_PRESENT) != - xa_mk_value(12)); - XA_BUG_ON(xa, index != 12); - index = 13; + xa_mk_value(multi)); + XA_BUG_ON(xa, index != multi); + index = multi + 1; XA_BUG_ON(xa, xa_find(xa, &index, ULONG_MAX, XA_PRESENT) != - xa_mk_value(12)); - XA_BUG_ON(xa, (index < 12) || (index >= 16)); + xa_mk_value(multi)); + XA_BUG_ON(xa, (index < multi) || (index >= next)); XA_BUG_ON(xa, xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT) != - xa_mk_value(16)); - XA_BUG_ON(xa, index != 16); - - xa_erase_index(xa, 12); - xa_erase_index(xa, 16); + xa_mk_value(next)); + XA_BUG_ON(xa, index != next); + XA_BUG_ON(xa, xa_find_after(xa, &index, next, XA_PRESENT) != NULL); + XA_BUG_ON(xa, index != next); + + xa_erase_index(xa, multi); + xa_erase_index(xa, next); + xa_erase_index(xa, next + 1); XA_BUG_ON(xa, !xa_empty(xa)); #endif } @@ -1046,12 +1053,33 @@ static noinline void check_find_3(struct xarray *xa) xa_destroy(xa); } +static noinline void check_find_4(struct xarray *xa) +{ + unsigned long index = 0; + void *entry; + + xa_store_index(xa, ULONG_MAX, GFP_KERNEL); + + entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT); + XA_BUG_ON(xa, entry != xa_mk_index(ULONG_MAX)); + + entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT); + XA_BUG_ON(xa, entry); + + xa_erase_index(xa, ULONG_MAX); +} + static noinline void check_find(struct xarray *xa) { + unsigned i; + check_find_1(xa); check_find_2(xa); check_find_3(xa); - check_multi_find(xa); + check_find_4(xa); + + for (i = 2; i < 10; i++) + check_multi_find_1(xa, i); check_multi_find_2(xa); } diff --git a/lib/xarray.c b/lib/xarray.c index 1237c213f52b..47e17d46e5f8 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0+ /* * XArray implementation - * Copyright (c) 2017 Microsoft Corporation + * Copyright (c) 2017-2018 Microsoft Corporation + * Copyright (c) 2018-2020 Oracle * Author: Matthew Wilcox */ @@ -1081,6 +1082,8 @@ void *xas_find(struct xa_state *xas, unsigned long max) if (xas_error(xas)) return NULL; + if (xas->xa_index > max) + return set_bounds(xas); if (!xas->xa_node) { xas->xa_index = 1; @@ -1150,6 +1153,8 @@ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) if (xas_error(xas)) return NULL; + if (xas->xa_index > max) + goto max; if (!xas->xa_node) { xas->xa_index = 1; @@ -1824,6 +1829,17 @@ void *xa_find(struct xarray *xa, unsigned long *indexp, } EXPORT_SYMBOL(xa_find); +static bool xas_sibling(struct xa_state *xas) +{ + struct xa_node *node = xas->xa_node; + unsigned long mask; + + if (!node) + return false; + mask = (XA_CHUNK_SIZE << node->shift) - 1; + return (xas->xa_index & mask) > (xas->xa_offset << node->shift); +} + /** * xa_find_after() - Search the XArray for a present entry. * @xa: XArray. @@ -1847,21 +1863,20 @@ void *xa_find_after(struct xarray *xa, unsigned long *indexp, XA_STATE(xas, xa, *indexp + 1); void *entry; + if (xas.xa_index == 0) + return NULL; + rcu_read_lock(); for (;;) { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); - if (xas.xa_node == XAS_BOUNDS) + + if (xas_invalid(&xas)) break; - if (xas.xa_shift) { - if (xas.xa_index & ((1UL << xas.xa_shift) - 1)) - continue; - } else { - if (xas.xa_offset < (xas.xa_index & XA_CHUNK_MASK)) - continue; - } + if (xas_sibling(&xas)) + continue; if (!xas_retry(&xas, entry)) break; } diff --git a/net/core/dev.c b/net/core/dev.c index 3098c90d60e2..82325d3d1371 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5270,9 +5270,29 @@ static void flush_all_backlogs(void) put_online_cpus(); } +/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ +static void gro_normal_list(struct napi_struct *napi) +{ + if (!napi->rx_count) + return; + netif_receive_skb_list_internal(&napi->rx_list); + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; +} + +/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, + * pass the whole batch up to the stack. + */ +static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb) +{ + list_add_tail(&skb->list, &napi->rx_list); + if (++napi->rx_count >= gro_normal_batch) + gro_normal_list(napi); +} + INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int)); INDIRECT_CALLABLE_DECLARE(int ipv6_gro_complete(struct sk_buff *, int)); -static int napi_gro_complete(struct sk_buff *skb) +static int napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) { struct packet_offload *ptype; __be16 type = skb->protocol; @@ -5305,7 +5325,8 @@ static int napi_gro_complete(struct sk_buff *skb) } out: - return netif_receive_skb_internal(skb); + gro_normal_one(napi, skb); + return NET_RX_SUCCESS; } static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, @@ -5318,7 +5339,7 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) return; skb_list_del_init(skb); - napi_gro_complete(skb); + napi_gro_complete(napi, skb); napi->gro_hash[index].count--; } @@ -5421,7 +5442,7 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow) } } -static void gro_flush_oldest(struct list_head *head) +static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head) { struct sk_buff *oldest; @@ -5437,7 +5458,7 @@ static void gro_flush_oldest(struct list_head *head) * SKB to the chain. */ skb_list_del_init(oldest); - napi_gro_complete(oldest); + napi_gro_complete(napi, oldest); } INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *, @@ -5513,7 +5534,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (pp) { skb_list_del_init(pp); - napi_gro_complete(pp); + napi_gro_complete(napi, pp); napi->gro_hash[hash].count--; } @@ -5524,7 +5545,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff goto normal; if (unlikely(napi->gro_hash[hash].count >= MAX_GRO_SKBS)) { - gro_flush_oldest(gro_head); + gro_flush_oldest(napi, gro_head); } else { napi->gro_hash[hash].count++; } @@ -5672,26 +5693,6 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi) } EXPORT_SYMBOL(napi_get_frags); -/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ -static void gro_normal_list(struct napi_struct *napi) -{ - if (!napi->rx_count) - return; - netif_receive_skb_list_internal(&napi->rx_list); - INIT_LIST_HEAD(&napi->rx_list); - napi->rx_count = 0; -} - -/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, - * pass the whole batch up to the stack. - */ -static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb) -{ - list_add_tail(&skb->list, &napi->rx_list); - if (++napi->rx_count >= gro_normal_batch) - gro_normal_list(napi); -} - static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, gro_result_t ret) @@ -5979,8 +5980,6 @@ bool napi_complete_done(struct napi_struct *n, int work_done) NAPIF_STATE_IN_BUSY_POLL))) return false; - gro_normal_list(n); - if (n->gro_bitmask) { unsigned long timeout = 0; @@ -5996,6 +5995,9 @@ bool napi_complete_done(struct napi_struct *n, int work_done) hrtimer_start(&n->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); } + + gro_normal_list(n); + if (unlikely(!list_empty(&n->poll_list))) { /* If n->poll_list is not empty, we need to mask irqs */ local_irq_save(flags); @@ -6327,8 +6329,6 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) goto out_unlock; } - gro_normal_list(n); - if (n->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. @@ -6336,6 +6336,8 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) napi_gro_flush(n, HZ >= 1000); } + gro_normal_list(n); + /* Some drivers may have called napi_schedule * prior to exhausting their budget. */ @@ -7973,6 +7975,22 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu) } EXPORT_SYMBOL(__dev_set_mtu); +int dev_validate_mtu(struct net_device *dev, int new_mtu, + struct netlink_ext_ack *extack) +{ + /* MTU must be positive, and in range */ + if (new_mtu < 0 || new_mtu < dev->min_mtu) { + NL_SET_ERR_MSG(extack, "mtu less than device minimum"); + return -EINVAL; + } + + if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { + NL_SET_ERR_MSG(extack, "mtu greater than device maximum"); + return -EINVAL; + } + return 0; +} + /** * dev_set_mtu_ext - Change maximum transfer unit * @dev: device @@ -7989,16 +8007,9 @@ int dev_set_mtu_ext(struct net_device *dev, int new_mtu, if (new_mtu == dev->mtu) return 0; - /* MTU must be positive, and in range */ - if (new_mtu < 0 || new_mtu < dev->min_mtu) { - NL_SET_ERR_MSG(extack, "mtu less than device minimum"); - return -EINVAL; - } - - if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { - NL_SET_ERR_MSG(extack, "mtu greater than device maximum"); - return -EINVAL; - } + err = dev_validate_mtu(dev, new_mtu, extack); + if (err) + return err; if (!netif_device_present(dev)) return -ENODEV; @@ -9073,8 +9084,10 @@ int register_netdevice(struct net_device *dev) goto err_uninit; ret = netdev_register_kobject(dev); - if (ret) + if (ret) { + dev->reg_state = NETREG_UNREGISTERED; goto err_uninit; + } dev->reg_state = NETREG_REGISTERED; __netdev_update_features(dev); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e4ec575c1fba..944acb1a9f29 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2959,8 +2959,17 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, dev->rtnl_link_ops = ops; dev->rtnl_link_state = RTNL_LINK_INITIALIZING; - if (tb[IFLA_MTU]) - dev->mtu = nla_get_u32(tb[IFLA_MTU]); + if (tb[IFLA_MTU]) { + u32 mtu = nla_get_u32(tb[IFLA_MTU]); + int err; + + err = dev_validate_mtu(dev, mtu, extack); + if (err) { + free_netdev(dev); + return ERR_PTR(err); + } + dev->mtu = mtu; + } if (tb[IFLA_ADDRESS]) { memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]), nla_len(tb[IFLA_ADDRESS])); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 3866d7e20c07..ded2d5227678 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -594,8 +594,6 @@ EXPORT_SYMBOL_GPL(sk_psock_destroy); void sk_psock_drop(struct sock *sk, struct sk_psock *psock) { - sock_owned_by_me(sk); - sk_psock_cork_free(psock); sk_psock_zap_ingress(psock); diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index d40de84a637f..754d84b217f0 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -191,7 +191,7 @@ void hsr_debugfs_term(struct hsr_priv *priv); void hsr_debugfs_create_root(void); void hsr_debugfs_remove_root(void); #else -static inline void void hsr_debugfs_rename(struct net_device *dev) +static inline void hsr_debugfs_rename(struct net_device *dev) { } static inline void hsr_debugfs_init(struct hsr_priv *priv, diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 0e4a7cf6bc87..e2e219c7854a 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -57,6 +57,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head, if (!x) goto out_reset; + skb->mark = xfrm_smark_get(skb->mark, x); + sp->xvec[sp->len++] = x; sp->olen++; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 1ab2fb6bb37d..f12fa8da6127 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2175,6 +2175,12 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, int count = cb->args[2]; t_key key = cb->args[3]; + /* First time here, count and key are both always 0. Count > 0 + * and key == 0 means the dump has wrapped around and we are done. + */ + if (count && !key) + return skb->len; + while ((l = leaf_walk_rcu(&tp, key)) != NULL) { int err; diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 30fa771d382a..dcc79ff54b41 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -662,8 +662,8 @@ static const struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = { [FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, }, [FOU_ATTR_LOCAL_V4] = { .type = NLA_U32, }, [FOU_ATTR_PEER_V4] = { .type = NLA_U32, }, - [FOU_ATTR_LOCAL_V6] = { .type = sizeof(struct in6_addr), }, - [FOU_ATTR_PEER_V6] = { .type = sizeof(struct in6_addr), }, + [FOU_ATTR_LOCAL_V6] = { .len = sizeof(struct in6_addr), }, + [FOU_ATTR_PEER_V6] = { .len = sizeof(struct in6_addr), }, [FOU_ATTR_PEER_PORT] = { .type = NLA_U16, }, [FOU_ATTR_IFINDEX] = { .type = NLA_S32, }, }; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 0fe2a5d3e258..74e1d964a615 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -1236,10 +1236,8 @@ int ip_tunnel_init(struct net_device *dev) iph->version = 4; iph->ihl = 5; - if (tunnel->collect_md) { - dev->features |= NETIF_F_NETNS_LOCAL; + if (tunnel->collect_md) netif_keep_dst(dev); - } return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_init); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 84115577d3dc..3640e8563a10 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2520,6 +2520,7 @@ static void tcp_rtx_queue_purge(struct sock *sk) { struct rb_node *p = rb_first(&sk->tcp_rtx_queue); + tcp_sk(sk)->highest_sack = NULL; while (p) { struct sk_buff *skb = rb_to_skb(p); diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index a6545ef0d27b..6c4d79baff26 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -779,8 +779,7 @@ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs) * bandwidth sample. Delivered is in packets and interval_us in uS and * ratio will be <<1 for most connections. So delivered is first scaled. */ - bw = (u64)rs->delivered * BW_UNIT; - do_div(bw, rs->interval_us); + bw = div64_long((u64)rs->delivered * BW_UNIT, rs->interval_us); /* If this sample is application-limited, it is likely to have a very * low delivered count that represents application behavior rather than diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 59b78ce2ce2e..6f7155d91313 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3164,6 +3164,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, tp->retransmit_skb_hint = NULL; if (unlikely(skb == tp->lost_skb_hint)) tp->lost_skb_hint = NULL; + tcp_highest_sack_replace(sk, skb, next); tcp_rtx_queue_unlink_and_free(skb, sk); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e4ba915c4bb5..660b24fe041e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3231,6 +3231,7 @@ int tcp_send_synack(struct sock *sk) if (!nskb) return -ENOMEM; INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor); + tcp_highest_sack_replace(sk, skb, nskb); tcp_rtx_queue_unlink_and_free(skb, sk); __skb_header_release(nskb); tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 7aa4e77161f6..7ae7065758bd 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1368,7 +1368,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, if (likely(partial)) { up->forward_deficit += size; size = up->forward_deficit; - if (size < (sk->sk_rcvbuf >> 2)) + if (size < (sk->sk_rcvbuf >> 2) && + !skb_queue_empty(&up->reader_queue)) return; } else { size += up->forward_deficit; diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index e31626ffccd1..fd535053245b 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -79,6 +79,8 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head, if (!x) goto out_reset; + skb->mark = xfrm_smark_get(skb->mark, x); + sp->xvec[sp->len++] = x; sp->olen++; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 189de56f5e36..9ec05a1df5e1 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1466,7 +1466,6 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) dev->mtu -= 8; if (tunnel->parms.collect_md) { - dev->features |= NETIF_F_NETNS_LOCAL; netif_keep_dst(dev); } ip6gre_tnl_init_features(dev); @@ -1894,7 +1893,6 @@ static void ip6gre_tap_setup(struct net_device *dev) dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; - dev->features |= NETIF_F_NETNS_LOCAL; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); @@ -2197,7 +2195,6 @@ static void ip6erspan_tap_setup(struct net_device *dev) dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; - dev->features |= NETIF_F_NETNS_LOCAL; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 2f376dbc37d5..b5dd20c4599b 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1877,10 +1877,8 @@ static int ip6_tnl_dev_init(struct net_device *dev) if (err) return err; ip6_tnl_link_config(t); - if (t->parms.collect_md) { - dev->features |= NETIF_F_NETNS_LOCAL; + if (t->parms.collect_md) netif_keep_dst(dev); - } return 0; } diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index e70567446f28..802eebf8ac4b 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -23,6 +23,7 @@ #include #include #include +#include #ifdef CONFIG_IPV6_SEG6_HMAC #include #endif @@ -135,7 +136,8 @@ static bool decap_and_validate(struct sk_buff *skb, int proto) skb_reset_network_header(skb); skb_reset_transport_header(skb); - skb->encapsulation = 0; + if (iptunnel_pull_offloads(skb)) + return false; return true; } diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index e1f271a1b2c1..bfd4b42ba305 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -75,7 +75,7 @@ mtype_flush(struct ip_set *set) if (set->extensions & IPSET_EXT_DESTROY) mtype_ext_cleanup(set); - memset(map->members, 0, map->memsize); + bitmap_zero(map->members, map->elements); set->elements = 0; set->ext_size = 0; } diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index 11ff9d4a7006..d934384f31ad 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -37,7 +37,7 @@ MODULE_ALIAS("ip_set_bitmap:ip"); /* Type structure */ struct bitmap_ip { - void *members; /* the set members */ + unsigned long *members; /* the set members */ u32 first_ip; /* host byte order, included in range */ u32 last_ip; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ @@ -220,7 +220,7 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map, u32 first_ip, u32 last_ip, u32 elements, u32 hosts, u8 netmask) { - map->members = ip_set_alloc(map->memsize); + map->members = bitmap_zalloc(elements, GFP_KERNEL | __GFP_NOWARN); if (!map->members) return false; map->first_ip = first_ip; @@ -310,7 +310,7 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], if (!map) return -ENOMEM; - map->memsize = bitmap_bytes(0, elements - 1); + map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_ip; if (!init_map_ip(set, map, first_ip, last_ip, elements, hosts, netmask)) { diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 1d4e63326e68..e8532783b43a 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -42,7 +42,7 @@ enum { /* Type structure */ struct bitmap_ipmac { - void *members; /* the set members */ + unsigned long *members; /* the set members */ u32 first_ip; /* host byte order, included in range */ u32 last_ip; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ @@ -299,7 +299,7 @@ static bool init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map, u32 first_ip, u32 last_ip, u32 elements) { - map->members = ip_set_alloc(map->memsize); + map->members = bitmap_zalloc(elements, GFP_KERNEL | __GFP_NOWARN); if (!map->members) return false; map->first_ip = first_ip; @@ -360,7 +360,7 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[], if (!map) return -ENOMEM; - map->memsize = bitmap_bytes(0, elements - 1); + map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_ipmac; if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) { kfree(map); diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 704a0dda1609..e3ac914fff1a 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -30,7 +30,7 @@ MODULE_ALIAS("ip_set_bitmap:port"); /* Type structure */ struct bitmap_port { - void *members; /* the set members */ + unsigned long *members; /* the set members */ u16 first_port; /* host byte order, included in range */ u16 last_port; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ @@ -204,7 +204,7 @@ static bool init_map_port(struct ip_set *set, struct bitmap_port *map, u16 first_port, u16 last_port) { - map->members = ip_set_alloc(map->memsize); + map->members = bitmap_zalloc(map->elements, GFP_KERNEL | __GFP_NOWARN); if (!map->members) return false; map->first_port = first_port; @@ -244,7 +244,7 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[], return -ENOMEM; map->elements = elements; - map->memsize = bitmap_bytes(0, map->elements); + map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_port; if (!init_map_port(set, map, first_port, last_port)) { kfree(map); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 9fefd0150091..23544842b692 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -488,48 +488,71 @@ static inline u64 nf_tables_alloc_handle(struct nft_table *table) static const struct nft_chain_type *chain_type[NFPROTO_NUMPROTO][NFT_CHAIN_T_MAX]; +static const struct nft_chain_type * +__nft_chain_type_get(u8 family, enum nft_chain_types type) +{ + if (family >= NFPROTO_NUMPROTO || + type >= NFT_CHAIN_T_MAX) + return NULL; + + return chain_type[family][type]; +} + static const struct nft_chain_type * __nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family) { + const struct nft_chain_type *type; int i; for (i = 0; i < NFT_CHAIN_T_MAX; i++) { - if (chain_type[family][i] != NULL && - !nla_strcmp(nla, chain_type[family][i]->name)) - return chain_type[family][i]; + type = __nft_chain_type_get(family, i); + if (!type) + continue; + if (!nla_strcmp(nla, type->name)) + return type; } return NULL; } -/* - * Loading a module requires dropping mutex that guards the transaction. - * A different client might race to start a new transaction meanwhile. Zap the - * list of pending transaction and then restore it once the mutex is grabbed - * again. Users of this function return EAGAIN which implicitly triggers the - * transaction abort path to clean up the list of pending transactions. - */ +struct nft_module_request { + struct list_head list; + char module[MODULE_NAME_LEN]; + bool done; +}; + #ifdef CONFIG_MODULES -static void nft_request_module(struct net *net, const char *fmt, ...) +static int nft_request_module(struct net *net, const char *fmt, ...) { char module_name[MODULE_NAME_LEN]; - LIST_HEAD(commit_list); + struct nft_module_request *req; va_list args; int ret; - list_splice_init(&net->nft.commit_list, &commit_list); - va_start(args, fmt); ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); va_end(args); if (ret >= MODULE_NAME_LEN) - return; + return 0; - mutex_unlock(&net->nft.commit_mutex); - request_module("%s", module_name); - mutex_lock(&net->nft.commit_mutex); + list_for_each_entry(req, &net->nft.module_list, list) { + if (!strcmp(req->module, module_name)) { + if (req->done) + return 0; - WARN_ON_ONCE(!list_empty(&net->nft.commit_list)); - list_splice(&commit_list, &net->nft.commit_list); + /* A request to load this module already exists. */ + return -EAGAIN; + } + } + + req = kmalloc(sizeof(*req), GFP_KERNEL); + if (!req) + return -ENOMEM; + + req->done = false; + strlcpy(req->module, module_name, MODULE_NAME_LEN); + list_add_tail(&req->list, &net->nft.module_list); + + return -EAGAIN; } #endif @@ -553,10 +576,9 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla, lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (autoload) { - nft_request_module(net, "nft-chain-%u-%.*s", family, - nla_len(nla), (const char *)nla_data(nla)); - type = __nf_tables_chain_type_lookup(nla, family); - if (type != NULL) + if (nft_request_module(net, "nft-chain-%u-%.*s", family, + nla_len(nla), + (const char *)nla_data(nla)) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -1095,11 +1117,8 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx) void nft_register_chain_type(const struct nft_chain_type *ctype) { - if (WARN_ON(ctype->family >= NFPROTO_NUMPROTO)) - return; - nfnl_lock(NFNL_SUBSYS_NFTABLES); - if (WARN_ON(chain_type[ctype->family][ctype->type] != NULL)) { + if (WARN_ON(__nft_chain_type_get(ctype->family, ctype->type))) { nfnl_unlock(NFNL_SUBSYS_NFTABLES); return; } @@ -1551,7 +1570,10 @@ static int nft_chain_parse_hook(struct net *net, hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])); hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY])); - type = chain_type[family][NFT_CHAIN_T_DEFAULT]; + type = __nft_chain_type_get(family, NFT_CHAIN_T_DEFAULT); + if (!type) + return -EOPNOTSUPP; + if (nla[NFTA_CHAIN_TYPE]) { type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE], family, autoload); @@ -2060,9 +2082,8 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family, static int nft_expr_type_request_module(struct net *net, u8 family, struct nlattr *nla) { - nft_request_module(net, "nft-expr-%u-%.*s", family, - nla_len(nla), (char *)nla_data(nla)); - if (__nft_expr_type_get(family, nla)) + if (nft_request_module(net, "nft-expr-%u-%.*s", family, + nla_len(nla), (char *)nla_data(nla)) == -EAGAIN) return -EAGAIN; return 0; @@ -2088,9 +2109,9 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net, if (nft_expr_type_request_module(net, family, nla) == -EAGAIN) return ERR_PTR(-EAGAIN); - nft_request_module(net, "nft-expr-%.*s", - nla_len(nla), (char *)nla_data(nla)); - if (__nft_expr_type_get(family, nla)) + if (nft_request_module(net, "nft-expr-%.*s", + nla_len(nla), + (char *)nla_data(nla)) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -2181,9 +2202,10 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx, err = PTR_ERR(ops); #ifdef CONFIG_MODULES if (err == -EAGAIN) - nft_expr_type_request_module(ctx->net, - ctx->family, - tb[NFTA_EXPR_NAME]); + if (nft_expr_type_request_module(ctx->net, + ctx->family, + tb[NFTA_EXPR_NAME]) != -EAGAIN) + err = -ENOENT; #endif goto err1; } @@ -3020,8 +3042,7 @@ nft_select_set_ops(const struct nft_ctx *ctx, lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (list_empty(&nf_tables_set_types)) { - nft_request_module(ctx->net, "nft-set"); - if (!list_empty(&nf_tables_set_types)) + if (nft_request_module(ctx->net, "nft-set") == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -5147,8 +5168,7 @@ nft_obj_type_get(struct net *net, u32 objtype) lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { - nft_request_module(net, "nft-obj-%u", objtype); - if (__nft_obj_type_get(objtype)) + if (nft_request_module(net, "nft-obj-%u", objtype) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -5764,8 +5784,7 @@ nft_flowtable_type_get(struct net *net, u8 family) lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { - nft_request_module(net, "nf-flowtable-%u", family); - if (__nft_flowtable_type_get(family)) + if (nft_request_module(net, "nf-flowtable-%u", family) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -6712,6 +6731,18 @@ static void nft_chain_del(struct nft_chain *chain) list_del_rcu(&chain->list); } +static void nf_tables_module_autoload_cleanup(struct net *net) +{ + struct nft_module_request *req, *next; + + WARN_ON_ONCE(!list_empty(&net->nft.commit_list)); + list_for_each_entry_safe(req, next, &net->nft.module_list, list) { + WARN_ON_ONCE(!req->done); + list_del(&req->list); + kfree(req); + } +} + static void nf_tables_commit_release(struct net *net) { struct nft_trans *trans; @@ -6724,6 +6755,7 @@ static void nf_tables_commit_release(struct net *net) * to prevent expensive synchronize_rcu() in commit phase. */ if (list_empty(&net->nft.commit_list)) { + nf_tables_module_autoload_cleanup(net); mutex_unlock(&net->nft.commit_mutex); return; } @@ -6738,6 +6770,7 @@ static void nf_tables_commit_release(struct net *net) list_splice_tail_init(&net->nft.commit_list, &nf_tables_destroy_list); spin_unlock(&nf_tables_destroy_list_lock); + nf_tables_module_autoload_cleanup(net); mutex_unlock(&net->nft.commit_mutex); schedule_work(&trans_destroy_work); @@ -6929,6 +6962,26 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) return 0; } +static void nf_tables_module_autoload(struct net *net) +{ + struct nft_module_request *req, *next; + LIST_HEAD(module_list); + + list_splice_init(&net->nft.module_list, &module_list); + mutex_unlock(&net->nft.commit_mutex); + list_for_each_entry_safe(req, next, &module_list, list) { + if (req->done) { + list_del(&req->list); + kfree(req); + } else { + request_module("%s", req->module); + req->done = true; + } + } + mutex_lock(&net->nft.commit_mutex); + list_splice(&module_list, &net->nft.module_list); +} + static void nf_tables_abort_release(struct nft_trans *trans) { switch (trans->msg_type) { @@ -6958,7 +7011,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) kfree(trans); } -static int __nf_tables_abort(struct net *net) +static int __nf_tables_abort(struct net *net, bool autoload) { struct nft_trans *trans, *next; struct nft_trans_elem *te; @@ -7080,6 +7133,11 @@ static int __nf_tables_abort(struct net *net) nf_tables_abort_release(trans); } + if (autoload) + nf_tables_module_autoload(net); + else + nf_tables_module_autoload_cleanup(net); + return 0; } @@ -7088,9 +7146,9 @@ static void nf_tables_cleanup(struct net *net) nft_validate_state_update(net, NFT_VALIDATE_SKIP); } -static int nf_tables_abort(struct net *net, struct sk_buff *skb) +static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload) { - int ret = __nf_tables_abort(net); + int ret = __nf_tables_abort(net, autoload); mutex_unlock(&net->nft.commit_mutex); @@ -7685,6 +7743,7 @@ static int __net_init nf_tables_init_net(struct net *net) { INIT_LIST_HEAD(&net->nft.tables); INIT_LIST_HEAD(&net->nft.commit_list); + INIT_LIST_HEAD(&net->nft.module_list); mutex_init(&net->nft.commit_mutex); net->nft.base_seq = 1; net->nft.validate_state = NFT_VALIDATE_SKIP; @@ -7696,7 +7755,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) { mutex_lock(&net->nft.commit_mutex); if (!list_empty(&net->nft.commit_list)) - __nf_tables_abort(net); + __nf_tables_abort(net, false); __nft_release_tables(net); mutex_unlock(&net->nft.commit_mutex); WARN_ON_ONCE(!list_empty(&net->nft.tables)); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 4abbb452cf6c..99127e2d95a8 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -476,7 +476,7 @@ ack: } done: if (status & NFNL_BATCH_REPLAY) { - ss->abort(net, oskb); + ss->abort(net, oskb, true); nfnl_err_reset(&err_list); kfree_skb(skb); module_put(ss->owner); @@ -487,11 +487,11 @@ done: status |= NFNL_BATCH_REPLAY; goto done; } else if (err) { - ss->abort(net, oskb); + ss->abort(net, oskb, false); netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL); } } else { - ss->abort(net, oskb); + ss->abort(net, oskb, false); } if (ss->cleanup) ss->cleanup(net); diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index f54d6ae15bb1..b42247aa48a9 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -61,6 +61,9 @@ static int nft_osf_init(const struct nft_ctx *ctx, int err; u8 ttl; + if (!tb[NFTA_OSF_DREG]) + return -EINVAL; + if (tb[NFTA_OSF_TTL]) { ttl = nla_get_u8(tb[NFTA_OSF_TTL]); if (ttl > 2) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 76e0d122616a..c2cdd0fc2e70 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2055,9 +2055,8 @@ replay: &chain_info)); mutex_unlock(&chain->filter_chain_lock); - tp_new = tcf_proto_create(nla_data(tca[TCA_KIND]), - protocol, prio, chain, rtnl_held, - extack); + tp_new = tcf_proto_create(name, protocol, prio, chain, + rtnl_held, extack); if (IS_ERR(tp_new)) { err = PTR_ERR(tp_new); goto errout_tp; diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 8f2ad706784d..d0140a92694a 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -263,12 +263,12 @@ static int tcf_em_validate(struct tcf_proto *tp, } em->data = (unsigned long) v; } + em->datalen = data_len; } } em->matchid = em_hdr->matchid; em->flags = em_hdr->flags; - em->datalen = data_len; em->net = net; err = 0; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index a80920f261ca..41e9c2932b34 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -793,7 +793,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk, psock = sk_psock_get(sk); if (!psock || !policy) { err = tls_push_record(sk, flags, record_type); - if (err) { + if (err && err != -EINPROGRESS) { *copied -= sk_msg_free(sk, msg); tls_free_open_rec(sk); } @@ -819,7 +819,7 @@ more_data: switch (psock->eval) { case __SK_PASS: err = tls_push_record(sk, flags, record_type); - if (err < 0) { + if (err && err != -EINPROGRESS) { *copied -= sk_msg_free(sk, msg); tls_free_open_rec(sk); goto out_err; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 6aee9f5e8e71..256f3e97d1f3 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -760,6 +760,10 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, if (sk->sk_state == TCP_ESTABLISHED) goto out; + rc = -EALREADY; /* Do nothing if call is already in progress */ + if (sk->sk_state == TCP_SYN_SENT) + goto out; + sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; @@ -806,7 +810,7 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, /* Now the loop */ rc = -EINPROGRESS; if (sk->sk_state != TCP_ESTABLISHED && (flags & O_NONBLOCK)) - goto out_put_neigh; + goto out; rc = x25_wait_for_connection_establishment(sk); if (rc) diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index 612268eabef4..7225107a9aaf 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -38,6 +38,10 @@ #define R_AARCH64_ABS64 257 #endif +#define R_ARM_PC24 1 +#define R_ARM_THM_CALL 10 +#define R_ARM_CALL 28 + static int fd_map; /* File descriptor for file being modified. */ static int mmap_failed; /* Boolean flag. */ static char gpfx; /* prefix for global symbol name (sometimes '_') */ @@ -418,6 +422,18 @@ static char const *already_has_rel_mcount = "success"; /* our work here is done! #define RECORD_MCOUNT_64 #include "recordmcount.h" +static int arm_is_fake_mcount(Elf32_Rel const *rp) +{ + switch (ELF32_R_TYPE(w(rp->r_info))) { + case R_ARM_THM_CALL: + case R_ARM_CALL: + case R_ARM_PC24: + return 0; + } + + return 1; +} + /* 64-bit EM_MIPS has weird ELF64_Rela.r_info. * http://techpubs.sgi.com/library/manuals/4000/007-4658-001/pdf/007-4658-001.pdf * We interpret Table 29 Relocation Operation (Elf64_Rel, Elf64_Rela) [p.40] @@ -523,6 +539,7 @@ static int do_file(char const *const fname) altmcount = "__gnu_mcount_nc"; make_nop = make_nop_arm; rel_type_nop = R_ARM_NONE; + is_fake_mcount32 = arm_is_fake_mcount; gpfx = 0; break; case EM_AARCH64: