diff options
77 files changed, 726 insertions, 245 deletions
diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst index 100bfd227265..13ea0cc0a3fa 100644 --- a/Documentation/driver-api/dma-buf.rst +++ b/Documentation/driver-api/dma-buf.rst @@ -179,7 +179,7 @@ DMA Fence uABI/Sync File :internal: Indefinite DMA Fences -~~~~~~~~~~~~~~~~~~~~ +~~~~~~~~~~~~~~~~~~~~~ At various times &dma_fence with an indefinite time until dma_fence_wait() finishes have been proposed. Examples include: @@ -882,10 +882,6 @@ KBUILD_CFLAGS_KERNEL += -ffunction-sections -fdata-sections LDFLAGS_vmlinux += --gc-sections endif -ifdef CONFIG_LIVEPATCH -KBUILD_CFLAGS += $(call cc-option, -flive-patching=inline-clone) -endif - ifdef CONFIG_SHADOW_CALL_STACK CC_FLAGS_SCS := -fsanitize=shadow-call-stack KBUILD_CFLAGS += $(CC_FLAGS_SCS) diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 1699a8e309ef..58564d82a3a2 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -316,9 +316,9 @@ out: * name of the dma-buf if the same piece of memory is used for multiple * purpose between different devices. * - * @dmabuf [in] dmabuf buffer that will be renamed. - * @buf: [in] A piece of userspace memory that contains the name of - * the dma-buf. + * @dmabuf: [in] dmabuf buffer that will be renamed. + * @buf: [in] A piece of userspace memory that contains the name of + * the dma-buf. * * Returns 0 on success. If the dma-buf buffer is already attached to * devices, return -EBUSY. diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c index 3d123502ff12..7d129e68ac70 100644 --- a/drivers/dma-buf/dma-fence-chain.c +++ b/drivers/dma-buf/dma-fence-chain.c @@ -222,6 +222,7 @@ EXPORT_SYMBOL(dma_fence_chain_ops); * @chain: the chain node to initialize * @prev: the previous fence * @fence: the current fence + * @seqno: the sequence number to use for the fence chain * * Initialize a new chain node and either start a new chain or add the node to * the existing chain of the previous fence. diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 68325678f5ef..b18c5ac2934d 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -14956,12 +14956,6 @@ static int intel_atomic_check(struct drm_device *dev, if (dev_priv->wm.distrust_bios_wm) any_ms = true; - if (any_ms) { - ret = intel_modeset_checks(state); - if (ret) - goto fail; - } - intel_fbc_choose_crtc(dev_priv, state); ret = calc_watermark_data(state); if (ret) @@ -14976,6 +14970,10 @@ static int intel_atomic_check(struct drm_device *dev, goto fail; if (any_ms) { + ret = intel_modeset_checks(state); + if (ret) + goto fail; + ret = intel_modeset_calc_cdclk(state); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 6b4ec66cb558..446e76e95c38 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -45,6 +45,13 @@ struct eb_vma_array { struct eb_vma vma[]; }; +enum { + FORCE_CPU_RELOC = 1, + FORCE_GTT_RELOC, + FORCE_GPU_RELOC, +#define DBG_FORCE_RELOC 0 /* choose one of the above! */ +}; + #define __EXEC_OBJECT_HAS_PIN BIT(31) #define __EXEC_OBJECT_HAS_FENCE BIT(30) #define __EXEC_OBJECT_NEEDS_MAP BIT(29) @@ -253,6 +260,8 @@ struct i915_execbuffer { */ struct reloc_cache { struct drm_mm_node node; /** temporary GTT binding */ + unsigned long vaddr; /** Current kmap address */ + unsigned long page; /** Currently mapped page index */ unsigned int gen; /** Cached value of INTEL_GEN */ bool use_64bit_reloc : 1; bool has_llc : 1; @@ -596,6 +605,23 @@ eb_add_vma(struct i915_execbuffer *eb, } } +static inline int use_cpu_reloc(const struct reloc_cache *cache, + const struct drm_i915_gem_object *obj) +{ + if (!i915_gem_object_has_struct_page(obj)) + return false; + + if (DBG_FORCE_RELOC == FORCE_CPU_RELOC) + return true; + + if (DBG_FORCE_RELOC == FORCE_GTT_RELOC) + return false; + + return (cache->has_llc || + obj->cache_dirty || + obj->cache_level != I915_CACHE_NONE); +} + static int eb_reserve_vma(const struct i915_execbuffer *eb, struct eb_vma *ev, u64 pin_flags) @@ -926,6 +952,8 @@ relocation_target(const struct drm_i915_gem_relocation_entry *reloc, static void reloc_cache_init(struct reloc_cache *cache, struct drm_i915_private *i915) { + cache->page = -1; + cache->vaddr = 0; /* Must be a variable in the struct to allow GCC to unroll. */ cache->gen = INTEL_GEN(i915); cache->has_llc = HAS_LLC(i915); @@ -937,6 +965,25 @@ static void reloc_cache_init(struct reloc_cache *cache, cache->target = NULL; } +static inline void *unmask_page(unsigned long p) +{ + return (void *)(uintptr_t)(p & PAGE_MASK); +} + +static inline unsigned int unmask_flags(unsigned long p) +{ + return p & ~PAGE_MASK; +} + +#define KMAP 0x4 /* after CLFLUSH_FLAGS */ + +static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache) +{ + struct drm_i915_private *i915 = + container_of(cache, struct i915_execbuffer, reloc_cache)->i915; + return &i915->ggtt; +} + #define RELOC_TAIL 4 static int reloc_gpu_chain(struct reloc_cache *cache) @@ -1049,6 +1096,181 @@ static int reloc_gpu_flush(struct reloc_cache *cache) return err; } +static void reloc_cache_reset(struct reloc_cache *cache) +{ + void *vaddr; + + if (!cache->vaddr) + return; + + vaddr = unmask_page(cache->vaddr); + if (cache->vaddr & KMAP) { + if (cache->vaddr & CLFLUSH_AFTER) + mb(); + + kunmap_atomic(vaddr); + i915_gem_object_finish_access((struct drm_i915_gem_object *)cache->node.mm); + } else { + struct i915_ggtt *ggtt = cache_to_ggtt(cache); + + intel_gt_flush_ggtt_writes(ggtt->vm.gt); + io_mapping_unmap_atomic((void __iomem *)vaddr); + + if (drm_mm_node_allocated(&cache->node)) { + ggtt->vm.clear_range(&ggtt->vm, + cache->node.start, + cache->node.size); + mutex_lock(&ggtt->vm.mutex); + drm_mm_remove_node(&cache->node); + mutex_unlock(&ggtt->vm.mutex); + } else { + i915_vma_unpin((struct i915_vma *)cache->node.mm); + } + } + + cache->vaddr = 0; + cache->page = -1; +} + +static void *reloc_kmap(struct drm_i915_gem_object *obj, + struct reloc_cache *cache, + unsigned long page) +{ + void *vaddr; + + if (cache->vaddr) { + kunmap_atomic(unmask_page(cache->vaddr)); + } else { + unsigned int flushes; + int err; + + err = i915_gem_object_prepare_write(obj, &flushes); + if (err) + return ERR_PTR(err); + + BUILD_BUG_ON(KMAP & CLFLUSH_FLAGS); + BUILD_BUG_ON((KMAP | CLFLUSH_FLAGS) & PAGE_MASK); + + cache->vaddr = flushes | KMAP; + cache->node.mm = (void *)obj; + if (flushes) + mb(); + } + + vaddr = kmap_atomic(i915_gem_object_get_dirty_page(obj, page)); + cache->vaddr = unmask_flags(cache->vaddr) | (unsigned long)vaddr; + cache->page = page; + + return vaddr; +} + +static void *reloc_iomap(struct drm_i915_gem_object *obj, + struct reloc_cache *cache, + unsigned long page) +{ + struct i915_ggtt *ggtt = cache_to_ggtt(cache); + unsigned long offset; + void *vaddr; + + if (cache->vaddr) { + intel_gt_flush_ggtt_writes(ggtt->vm.gt); + io_mapping_unmap_atomic((void __force __iomem *) unmask_page(cache->vaddr)); + } else { + struct i915_vma *vma; + int err; + + if (i915_gem_object_is_tiled(obj)) + return ERR_PTR(-EINVAL); + + if (use_cpu_reloc(cache, obj)) + return NULL; + + i915_gem_object_lock(obj); + err = i915_gem_object_set_to_gtt_domain(obj, true); + i915_gem_object_unlock(obj); + if (err) + return ERR_PTR(err); + + vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, + PIN_MAPPABLE | + PIN_NONBLOCK /* NOWARN */ | + PIN_NOEVICT); + if (IS_ERR(vma)) { + memset(&cache->node, 0, sizeof(cache->node)); + mutex_lock(&ggtt->vm.mutex); + err = drm_mm_insert_node_in_range + (&ggtt->vm.mm, &cache->node, + PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE, + 0, ggtt->mappable_end, + DRM_MM_INSERT_LOW); + mutex_unlock(&ggtt->vm.mutex); + if (err) /* no inactive aperture space, use cpu reloc */ + return NULL; + } else { + cache->node.start = vma->node.start; + cache->node.mm = (void *)vma; + } + } + + offset = cache->node.start; + if (drm_mm_node_allocated(&cache->node)) { + ggtt->vm.insert_page(&ggtt->vm, + i915_gem_object_get_dma_address(obj, page), + offset, I915_CACHE_NONE, 0); + } else { + offset += page << PAGE_SHIFT; + } + + vaddr = (void __force *)io_mapping_map_atomic_wc(&ggtt->iomap, + offset); + cache->page = page; + cache->vaddr = (unsigned long)vaddr; + + return vaddr; +} + +static void *reloc_vaddr(struct drm_i915_gem_object *obj, + struct reloc_cache *cache, + unsigned long page) +{ + void *vaddr; + + if (cache->page == page) { + vaddr = unmask_page(cache->vaddr); + } else { + vaddr = NULL; + if ((cache->vaddr & KMAP) == 0) + vaddr = reloc_iomap(obj, cache, page); + if (!vaddr) + vaddr = reloc_kmap(obj, cache, page); + } + + return vaddr; +} + +static void clflush_write32(u32 *addr, u32 value, unsigned int flushes) +{ + if (unlikely(flushes & (CLFLUSH_BEFORE | CLFLUSH_AFTER))) { + if (flushes & CLFLUSH_BEFORE) { + clflushopt(addr); + mb(); + } + + *addr = value; + + /* + * Writes to the same cacheline are serialised by the CPU + * (including clflush). On the write path, we only require + * that it hits memory in an orderly fashion and place + * mb barriers at the start and end of the relocation phase + * to ensure ordering of clflush wrt to the system. + */ + if (flushes & CLFLUSH_AFTER) + clflushopt(addr); + } else + *addr = value; +} + static int reloc_move_to_gpu(struct i915_request *rq, struct i915_vma *vma) { struct drm_i915_gem_object *obj = vma->obj; @@ -1214,6 +1436,17 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb, return cmd; } +static inline bool use_reloc_gpu(struct i915_vma *vma) +{ + if (DBG_FORCE_RELOC == FORCE_GPU_RELOC) + return true; + + if (DBG_FORCE_RELOC) + return false; + + return !dma_resv_test_signaled_rcu(vma->resv, true); +} + static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset) { struct page *page; @@ -1228,10 +1461,10 @@ static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset) return addr + offset_in_page(offset); } -static int __reloc_entry_gpu(struct i915_execbuffer *eb, - struct i915_vma *vma, - u64 offset, - u64 target_addr) +static bool __reloc_entry_gpu(struct i915_execbuffer *eb, + struct i915_vma *vma, + u64 offset, + u64 target_addr) { const unsigned int gen = eb->reloc_cache.gen; unsigned int len; @@ -1247,7 +1480,7 @@ static int __reloc_entry_gpu(struct i915_execbuffer *eb, batch = reloc_gpu(eb, vma, len); if (IS_ERR(batch)) - return PTR_ERR(batch); + return false; addr = gen8_canonical_addr(vma->node.start + offset); if (gen >= 8) { @@ -1296,21 +1529,55 @@ static int __reloc_entry_gpu(struct i915_execbuffer *eb, *batch++ = target_addr; } - return 0; + return true; +} + +static bool reloc_entry_gpu(struct i915_execbuffer *eb, + struct i915_vma *vma, + u64 offset, + u64 target_addr) +{ + if (eb->reloc_cache.vaddr) + return false; + + if (!use_reloc_gpu(vma)) + return false; + + return __reloc_entry_gpu(eb, vma, offset, target_addr); } static u64 -relocate_entry(struct i915_execbuffer *eb, - struct i915_vma *vma, +relocate_entry(struct i915_vma *vma, const struct drm_i915_gem_relocation_entry *reloc, + struct i915_execbuffer *eb, const struct i915_vma *target) { u64 target_addr = relocation_target(reloc, target); - int err; - - err = __reloc_entry_gpu(eb, vma, reloc->offset, target_addr); - if (err) - return err; + u64 offset = reloc->offset; + + if (!reloc_entry_gpu(eb, vma, offset, target_addr)) { + bool wide = eb->reloc_cache.use_64bit_reloc; + void *vaddr; + +repeat: + vaddr = reloc_vaddr(vma->obj, + &eb->reloc_cache, + offset >> PAGE_SHIFT); + if (IS_ERR(vaddr)) + return PTR_ERR(vaddr); + + GEM_BUG_ON(!IS_ALIGNED(offset, sizeof(u32))); + clflush_write32(vaddr + offset_in_page(offset), + lower_32_bits(target_addr), + eb->reloc_cache.vaddr); + + if (wide) { + offset += sizeof(u32); + target_addr >>= 32; + wide = false; + goto repeat; + } + } return target->node.start | UPDATE; } @@ -1375,7 +1642,8 @@ eb_relocate_entry(struct i915_execbuffer *eb, * If the relocation already has the right value in it, no * more work needs to be done. */ - if (gen8_canonical_addr(target->vma->node.start) == reloc->presumed_offset) + if (!DBG_FORCE_RELOC && + gen8_canonical_addr(target->vma->node.start) == reloc->presumed_offset) return 0; /* Check that the relocation address is valid... */ @@ -1407,7 +1675,7 @@ eb_relocate_entry(struct i915_execbuffer *eb, ev->flags &= ~EXEC_OBJECT_ASYNC; /* and update the user's relocation entry */ - return relocate_entry(eb, ev->vma, reloc, target->vma); + return relocate_entry(ev->vma, reloc, eb, target->vma); } static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev) @@ -1445,8 +1713,10 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev) * this is bad and so lockdep complains vehemently. */ copied = __copy_from_user(r, urelocs, count * sizeof(r[0])); - if (unlikely(copied)) - return -EFAULT; + if (unlikely(copied)) { + remain = -EFAULT; + goto out; + } remain -= count; do { @@ -1454,7 +1724,8 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev) if (likely(offset == 0)) { } else if ((s64)offset < 0) { - return (int)offset; + remain = (int)offset; + goto out; } else { /* * Note that reporting an error now @@ -1484,8 +1755,9 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev) } while (r++, --count); urelocs += ARRAY_SIZE(stack); } while (remain); - - return 0; +out: + reloc_cache_reset(&eb->reloc_cache); + return remain; } static int eb_relocate(struct i915_execbuffer *eb) @@ -2392,7 +2664,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, eb.i915 = i915; eb.file = file; eb.args = args; - if (!(args->flags & I915_EXEC_NO_RELOC)) + if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC)) args->flags |= __EXEC_HAS_RELOC; eb.exec = exec; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index e5b9276d254c..9cf4ad78ece6 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -258,6 +258,10 @@ struct page * i915_gem_object_get_page(struct drm_i915_gem_object *obj, unsigned int n); +struct page * +i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, + unsigned int n); + dma_addr_t i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj, unsigned long n, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index d15ff6748a50..e8a083743e09 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -548,6 +548,20 @@ i915_gem_object_get_page(struct drm_i915_gem_object *obj, unsigned int n) return nth_page(sg_page(sg), offset); } +/* Like i915_gem_object_get_page(), but mark the returned page dirty */ +struct page * +i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, + unsigned int n) +{ + struct page *page; + + page = i915_gem_object_get_page(obj, n); + if (!obj->mm.dirty) + set_page_dirty(page); + + return page; +} + dma_addr_t i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj, unsigned long n, diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c index 57c14d3340cd..a49016f8ee0d 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c @@ -37,14 +37,20 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb, return err; /* 8-Byte aligned */ - err = __reloc_entry_gpu(eb, vma, offsets[0] * sizeof(u32), 0); - if (err) + if (!__reloc_entry_gpu(eb, vma, + offsets[0] * sizeof(u32), + 0)) { + err = -EIO; goto unpin_vma; + } /* !8-Byte aligned */ - err = __reloc_entry_gpu(eb, vma, offsets[1] * sizeof(u32), 1); - if (err) + if (!__reloc_entry_gpu(eb, vma, + offsets[1] * sizeof(u32), + 1)) { + err = -EIO; goto unpin_vma; + } /* Skip to the end of the cmd page */ i = PAGE_SIZE / sizeof(u32) - RELOC_TAIL - 1; @@ -54,9 +60,12 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb, eb->reloc_cache.rq_size += i; /* Force batch chaining */ - err = __reloc_entry_gpu(eb, vma, offsets[2] * sizeof(u32), 2); - if (err) + if (!__reloc_entry_gpu(eb, vma, + offsets[2] * sizeof(u32), + 2)) { + err = -EIO; goto unpin_vma; + } GEM_BUG_ON(!eb->reloc_cache.rq); rq = i915_request_get(eb->reloc_cache.rq); diff --git a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c index ada990a7f911..b7074161ccf0 100644 --- a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c +++ b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c @@ -673,7 +673,7 @@ static void ingenic_drm_unbind_all(void *d) component_unbind_all(priv->dev, &priv->drm); } -static int ingenic_drm_bind(struct device *dev) +static int ingenic_drm_bind(struct device *dev, bool has_components) { struct platform_device *pdev = to_platform_device(dev); const struct jz_soc_info *soc_info; @@ -808,7 +808,7 @@ static int ingenic_drm_bind(struct device *dev) return ret; } - if (IS_ENABLED(CONFIG_DRM_INGENIC_IPU)) { + if (IS_ENABLED(CONFIG_DRM_INGENIC_IPU) && has_components) { ret = component_bind_all(dev, drm); if (ret) { if (ret != -EPROBE_DEFER) @@ -939,6 +939,11 @@ err_pixclk_disable: return ret; } +static int ingenic_drm_bind_with_components(struct device *dev) +{ + return ingenic_drm_bind(dev, true); +} + static int compare_of(struct device *dev, void *data) { return dev->of_node == data; @@ -957,7 +962,7 @@ static void ingenic_drm_unbind(struct device *dev) } static const struct component_master_ops ingenic_master_ops = { - .bind = ingenic_drm_bind, + .bind = ingenic_drm_bind_with_components, .unbind = ingenic_drm_unbind, }; @@ -968,16 +973,15 @@ static int ingenic_drm_probe(struct platform_device *pdev) struct device_node *np; if (!IS_ENABLED(CONFIG_DRM_INGENIC_IPU)) - return ingenic_drm_bind(dev); + return ingenic_drm_bind(dev, false); /* IPU is at port address 8 */ np = of_graph_get_remote_node(dev->of_node, 8, 0); - if (!np) { - dev_err(dev, "Unable to get IPU node\n"); - return -EINVAL; - } + if (!np) + return ingenic_drm_bind(dev, false); drm_of_component_match_add(dev, &match, compare_of, np); + of_node_put(np); return component_master_add_with_match(dev, &ingenic_master_ops, match); } diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c index 6021f8d9efd1..48fa49f69d6d 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c @@ -164,6 +164,11 @@ static int a2xx_hw_init(struct msm_gpu *gpu) if (ret) return ret; + gpu_write(gpu, REG_AXXX_CP_RB_CNTL, + MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + + gpu_write(gpu, REG_AXXX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova)); + /* NOTE: PM4/micro-engine firmware registers look to be the same * for a2xx and a3xx.. we could possibly push that part down to * adreno_gpu base class. Or push both PM4 and PFP but diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index 0a5ea9f56cb8..f6471145a7a6 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -211,6 +211,16 @@ static int a3xx_hw_init(struct msm_gpu *gpu) if (ret) return ret; + /* + * Use the default ringbuffer size and block size but disable the RPTR + * shadow + */ + gpu_write(gpu, REG_AXXX_CP_RB_CNTL, + MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + + /* Set the ringbuffer address */ + gpu_write(gpu, REG_AXXX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova)); + /* setup access protection: */ gpu_write(gpu, REG_A3XX_CP_PROTECT_CTRL, 0x00000007); diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index b9b26b2bf9c5..954753600625 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -267,6 +267,16 @@ static int a4xx_hw_init(struct msm_gpu *gpu) if (ret) return ret; + /* + * Use the default ringbuffer size and block size but disable the RPTR + * shadow + */ + gpu_write(gpu, REG_A4XX_CP_RB_CNTL, + MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + + /* Set the ringbuffer address */ + gpu_write(gpu, REG_A4XX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova)); + /* Load PM4: */ ptr = (uint32_t *)(adreno_gpu->fw[ADRENO_FW_PM4]->data); len = adreno_gpu->fw[ADRENO_FW_PM4]->size / 4; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 84a5d9c1f2a2..91726da82ed6 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -703,8 +703,6 @@ static int a5xx_hw_init(struct msm_gpu *gpu) if (ret) return ret; - a5xx_preempt_hw_init(gpu); - if (!adreno_is_a510(adreno_gpu)) a5xx_gpmu_ucode_init(gpu); @@ -712,6 +710,15 @@ static int a5xx_hw_init(struct msm_gpu *gpu) if (ret) return ret; + /* Set the ringbuffer address */ + gpu_write64(gpu, REG_A5XX_CP_RB_BASE, REG_A5XX_CP_RB_BASE_HI, + gpu->rb[0]->iova); + + gpu_write(gpu, REG_A5XX_CP_RB_CNTL, + MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + + a5xx_preempt_hw_init(gpu); + /* Disable the interrupts through the initial bringup stage */ gpu_write(gpu, REG_A5XX_RBBM_INT_0_MASK, A5XX_INT_MASK); @@ -1511,7 +1518,8 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) check_speed_bin(&pdev->dev); - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 4); + /* Restricting nr_rings to 1 to temporarily disable preemption */ + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); if (ret) { a5xx_destroy(&(a5xx_gpu->base.base)); return ERR_PTR(ret); diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h index 54868d4e3958..1e5b1a15a70f 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h @@ -31,6 +31,7 @@ struct a5xx_gpu { struct msm_ringbuffer *next_ring; struct drm_gem_object *preempt_bo[MSM_GPU_MAX_RINGS]; + struct drm_gem_object *preempt_counters_bo[MSM_GPU_MAX_RINGS]; struct a5xx_preempt_record *preempt[MSM_GPU_MAX_RINGS]; uint64_t preempt_iova[MSM_GPU_MAX_RINGS]; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c index 9cf9353a7ff1..9f3fe177b00e 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -226,19 +226,31 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu, struct adreno_gpu *adreno_gpu = &a5xx_gpu->base; struct msm_gpu *gpu = &adreno_gpu->base; struct a5xx_preempt_record *ptr; - struct drm_gem_object *bo = NULL; - u64 iova = 0; + void *counters; + struct drm_gem_object *bo = NULL, *counters_bo = NULL; + u64 iova = 0, counters_iova = 0; ptr = msm_gem_kernel_new(gpu->dev, A5XX_PREEMPT_RECORD_SIZE + A5XX_PREEMPT_COUNTER_SIZE, - MSM_BO_UNCACHED, gpu->aspace, &bo, &iova); + MSM_BO_UNCACHED | MSM_BO_MAP_PRIV, gpu->aspace, &bo, &iova); if (IS_ERR(ptr)) return PTR_ERR(ptr); + /* The buffer to store counters needs to be unprivileged */ + counters = msm_gem_kernel_new(gpu->dev, + A5XX_PREEMPT_COUNTER_SIZE, + MSM_BO_UNCACHED, gpu->aspace, &counters_bo, &counters_iova); + if (IS_ERR(counters)) { + msm_gem_kernel_put(bo, gpu->aspace, true); + return PTR_ERR(counters); + } + msm_gem_object_set_name(bo, "preempt"); + msm_gem_object_set_name(counters_bo, "preempt_counters"); a5xx_gpu->preempt_bo[ring->id] = bo; + a5xx_gpu->preempt_counters_bo[ring->id] = counters_bo; a5xx_gpu->preempt_iova[ring->id] = iova; a5xx_gpu->preempt[ring->id] = ptr; @@ -249,7 +261,7 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu, ptr->data = 0; ptr->cntl = MSM_GPU_RB_CNTL_DEFAULT; ptr->rptr_addr = rbmemptr(ring, rptr); - ptr->counter = iova + A5XX_PREEMPT_RECORD_SIZE; + ptr->counter = counters_iova; return 0; } @@ -260,8 +272,11 @@ void a5xx_preempt_fini(struct msm_gpu *gpu) struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); int i; - for (i = 0; i < gpu->nr_rings; i++) + for (i = 0; i < gpu->nr_rings; i++) { msm_gem_kernel_put(a5xx_gpu->preempt_bo[i], gpu->aspace, true); + msm_gem_kernel_put(a5xx_gpu->preempt_counters_bo[i], + gpu->aspace, true); + } } void a5xx_preempt_init(struct msm_gpu *gpu) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 3966abd523cc..66a95e22b7b3 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -678,7 +678,8 @@ static int a6xx_hw_init(struct msm_gpu *gpu) A6XX_PROTECT_RDONLY(0x980, 0x4)); gpu_write(gpu, REG_A6XX_CP_PROTECT(25), A6XX_PROTECT_RW(0xa630, 0x0)); - if (adreno_is_a650(adreno_gpu)) { + /* Enable expanded apriv for targets that support it */ + if (gpu->hw_apriv) { gpu_write(gpu, REG_A6XX_CP_APRIV_CNTL, (1 << 6) | (1 << 5) | (1 << 3) | (1 << 2) | (1 << 1)); } @@ -694,6 +695,13 @@ static int a6xx_hw_init(struct msm_gpu *gpu) if (ret) goto out; + /* Set the ringbuffer address */ + gpu_write64(gpu, REG_A6XX_CP_RB_BASE, REG_A6XX_CP_RB_BASE_HI, + gpu->rb[0]->iova); + + gpu_write(gpu, REG_A6XX_CP_RB_CNTL, + MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + /* Always come up on rb 0 */ a6xx_gpu->cur_ring = gpu->rb[0]; @@ -1056,6 +1064,9 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) adreno_gpu->registers = NULL; adreno_gpu->reg_offsets = a6xx_register_offsets; + if (adreno_is_a650(adreno_gpu)) + adreno_gpu->base.hw_apriv = true; + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); if (ret) { a6xx_destroy(&(a6xx_gpu->base.base)); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 288141fe4c58..862dd35b27d3 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -400,26 +400,6 @@ int adreno_hw_init(struct msm_gpu *gpu) ring->memptrs->rptr = 0; } - /* - * Setup REG_CP_RB_CNTL. The same value is used across targets (with - * the excpetion of A430 that disables the RPTR shadow) - the cacluation - * for the ringbuffer size and block size is moved to msm_gpu.h for the - * pre-processor to deal with and the A430 variant is ORed in here - */ - adreno_gpu_write(adreno_gpu, REG_ADRENO_CP_RB_CNTL, - MSM_GPU_RB_CNTL_DEFAULT | - (adreno_is_a430(adreno_gpu) ? AXXX_CP_RB_CNTL_NO_UPDATE : 0)); - - /* Setup ringbuffer address - use ringbuffer[0] for GPU init */ - adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_BASE, - REG_ADRENO_CP_RB_BASE_HI, gpu->rb[0]->iova); - - if (!adreno_is_a430(adreno_gpu)) { - adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_RPTR_ADDR, - REG_ADRENO_CP_RB_RPTR_ADDR_HI, - rbmemptr(gpu->rb[0], rptr)); - } - return 0; } @@ -427,11 +407,8 @@ int adreno_hw_init(struct msm_gpu *gpu) static uint32_t get_rptr(struct adreno_gpu *adreno_gpu, struct msm_ringbuffer *ring) { - if (adreno_is_a430(adreno_gpu)) - return ring->memptrs->rptr = adreno_gpu_read( - adreno_gpu, REG_ADRENO_CP_RB_RPTR); - else - return ring->memptrs->rptr; + return ring->memptrs->rptr = adreno_gpu_read( + adreno_gpu, REG_ADRENO_CP_RB_RPTR); } struct msm_ringbuffer *adreno_active_ring(struct msm_gpu *gpu) diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index d5645472b25d..57ddc9438351 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -908,7 +908,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, memptrs = msm_gem_kernel_new(drm, sizeof(struct msm_rbmemptrs) * nr_rings, - MSM_BO_UNCACHED, gpu->aspace, &gpu->memptrs_bo, + check_apriv(gpu, MSM_BO_UNCACHED), gpu->aspace, &gpu->memptrs_bo, &memptrs_iova); if (IS_ERR(memptrs)) { diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 0db117a7339b..37cffac4cbe3 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -15,6 +15,7 @@ #include "msm_drv.h" #include "msm_fence.h" #include "msm_ringbuffer.h" +#include "msm_gem.h" struct msm_gem_submit; struct msm_gpu_perfcntr; @@ -139,6 +140,8 @@ struct msm_gpu { } devfreq; struct msm_gpu_state *crashstate; + /* True if the hardware supports expanded apriv (a650 and newer) */ + bool hw_apriv; }; /* It turns out that all targets use the same ringbuffer size */ @@ -327,4 +330,12 @@ static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu) mutex_unlock(&gpu->dev->struct_mutex); } +/* + * Simple macro to semi-cleanly add the MAP_PRIV flag for targets that can + * support expanded privileges + */ +#define check_apriv(gpu, flags) \ + (((gpu)->hw_apriv ? MSM_BO_MAP_PRIV : 0) | (flags)) + + #endif /* __MSM_GPU_H__ */ diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index 39ecb5a18431..935bf9b1d941 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -27,8 +27,8 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id, ring->id = id; ring->start = msm_gem_kernel_new(gpu->dev, MSM_GPU_RINGBUFFER_SZ, - MSM_BO_WC | MSM_BO_GPU_READONLY, gpu->aspace, &ring->bo, - &ring->iova); + check_apriv(gpu, MSM_BO_WC | MSM_BO_GPU_READONLY), + gpu->aspace, &ring->bo, &ring->iova); if (IS_ERR(ring->start)) { ret = PTR_ERR(ring->start); diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c index 072ea113e6be..ed5d86617802 100644 --- a/drivers/gpu/drm/sun4i/sun4i_backend.c +++ b/drivers/gpu/drm/sun4i/sun4i_backend.c @@ -589,8 +589,7 @@ static int sun4i_backend_atomic_check(struct sunxi_engine *engine, /* We can't have an alpha plane at the lowest position */ if (!backend->quirks->supports_lowest_plane_alpha && - (plane_states[0]->fb->format->has_alpha || - (plane_states[0]->alpha != DRM_BLEND_ALPHA_OPAQUE))) + (plane_states[0]->alpha != DRM_BLEND_ALPHA_OPAQUE)) return -EINVAL; for (i = 1; i < num_planes; i++) { @@ -995,7 +994,6 @@ static const struct sun4i_backend_quirks sun6i_backend_quirks = { static const struct sun4i_backend_quirks sun7i_backend_quirks = { .needs_output_muxing = true, - .supports_lowest_plane_alpha = true, }; static const struct sun4i_backend_quirks sun8i_a33_backend_quirks = { diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index ced9a8287dd8..e40c542254f6 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -1433,14 +1433,18 @@ static int sun8i_r40_tcon_tv_set_mux(struct sun4i_tcon *tcon, if (IS_ENABLED(CONFIG_DRM_SUN8I_TCON_TOP) && encoder->encoder_type == DRM_MODE_ENCODER_TMDS) { ret = sun8i_tcon_top_set_hdmi_src(&pdev->dev, id); - if (ret) + if (ret) { + put_device(&pdev->dev); return ret; + } } if (IS_ENABLED(CONFIG_DRM_SUN8I_TCON_TOP)) { ret = sun8i_tcon_top_de_config(&pdev->dev, tcon->id, id); - if (ret) + if (ret) { + put_device(&pdev->dev); return ret; + } } return 0; diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c index 7f13f4d715bf..de8a11abd66a 100644 --- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c @@ -889,7 +889,7 @@ static int sun6i_dsi_dcs_write_long(struct sun6i_dsi *dsi, regmap_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(0), sun6i_dsi_dcs_build_pkt_hdr(dsi, msg)); - bounce = kzalloc(msg->tx_len + sizeof(crc), GFP_KERNEL); + bounce = kzalloc(ALIGN(msg->tx_len + sizeof(crc), 4), GFP_KERNEL); if (!bounce) return -ENOMEM; @@ -900,7 +900,7 @@ static int sun6i_dsi_dcs_write_long(struct sun6i_dsi *dsi, memcpy((u8 *)bounce + msg->tx_len, &crc, sizeof(crc)); len += sizeof(crc); - regmap_bulk_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(1), bounce, len); + regmap_bulk_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(1), bounce, DIV_ROUND_UP(len, 4)); regmap_write(dsi->regs, SUN6I_DSI_CMD_CTL_REG, len + 4 - 1); kfree(bounce); diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c index 22c8c5375d0d..c0147af6a840 100644 --- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c +++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c @@ -211,7 +211,7 @@ static int sun8i_vi_layer_update_coord(struct sun8i_mixer *mixer, int channel, return 0; } -static bool sun8i_vi_layer_get_csc_mode(const struct drm_format_info *format) +static u32 sun8i_vi_layer_get_csc_mode(const struct drm_format_info *format) { if (!format->is_yuv) return SUN8I_CSC_MODE_OFF; diff --git a/drivers/gpu/drm/tve200/tve200_display.c b/drivers/gpu/drm/tve200/tve200_display.c index d733bbc4ac0e..17ff24d999d1 100644 --- a/drivers/gpu/drm/tve200/tve200_display.c +++ b/drivers/gpu/drm/tve200/tve200_display.c @@ -14,6 +14,7 @@ #include <linux/version.h> #include <linux/dma-buf.h> #include <linux/of_graph.h> +#include <linux/delay.h> #include <drm/drm_fb_cma_helper.h> #include <drm/drm_fourcc.h> @@ -130,9 +131,25 @@ static void tve200_display_enable(struct drm_simple_display_pipe *pipe, struct drm_connector *connector = priv->connector; u32 format = fb->format->format; u32 ctrl1 = 0; + int retries; clk_prepare_enable(priv->clk); + /* Reset the TVE200 and wait for it to come back online */ + writel(TVE200_CTRL_4_RESET, priv->regs + TVE200_CTRL_4); + for (retries = 0; retries < 5; retries++) { + usleep_range(30000, 50000); + if (readl(priv->regs + TVE200_CTRL_4) & TVE200_CTRL_4_RESET) + continue; + else + break; + } + if (retries == 5 && + readl(priv->regs + TVE200_CTRL_4) & TVE200_CTRL_4_RESET) { + dev_err(drm->dev, "can't get hardware out of reset\n"); + return; + } + /* Function 1 */ ctrl1 |= TVE200_CTRL_CSMODE; /* Interlace mode for CCIR656: parameterize? */ @@ -230,8 +247,9 @@ static void tve200_display_disable(struct drm_simple_display_pipe *pipe) drm_crtc_vblank_off(crtc); - /* Disable and Power Down */ + /* Disable put into reset and Power Down */ writel(0, priv->regs + TVE200_CTRL); + writel(TVE200_CTRL_4_RESET, priv->regs + TVE200_CTRL_4); clk_disable_unprepare(priv->clk); } @@ -279,6 +297,8 @@ static int tve200_display_enable_vblank(struct drm_simple_display_pipe *pipe) struct drm_device *drm = crtc->dev; struct tve200_drm_dev_private *priv = drm->dev_private; + /* Clear any IRQs and enable */ + writel(0xFF, priv->regs + TVE200_INT_CLR); writel(TVE200_INT_V_STATUS, priv->regs + TVE200_INT_EN); return 0; } diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index af55b334be2f..afd0f9200f90 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -97,9 +97,6 @@ static void virtio_gpu_crtc_mode_set_nofb(struct drm_crtc *crtc) static void virtio_gpu_crtc_atomic_enable(struct drm_crtc *crtc, struct drm_crtc_state *old_state) { - struct virtio_gpu_output *output = drm_crtc_to_virtio_gpu_output(crtc); - - output->enabled = true; } static void virtio_gpu_crtc_atomic_disable(struct drm_crtc *crtc, @@ -111,7 +108,6 @@ static void virtio_gpu_crtc_atomic_disable(struct drm_crtc *crtc, virtio_gpu_cmd_set_scanout(vgdev, output->index, 0, 0, 0, 0, 0); virtio_gpu_notify(vgdev); - output->enabled = false; } static int virtio_gpu_crtc_atomic_check(struct drm_crtc *crtc, @@ -123,6 +119,17 @@ static int virtio_gpu_crtc_atomic_check(struct drm_crtc *crtc, static void virtio_gpu_crtc_atomic_flush(struct drm_crtc *crtc, struct drm_crtc_state *old_state) { + struct virtio_gpu_output *output = drm_crtc_to_virtio_gpu_output(crtc); + + /* + * virtio-gpu can't do modeset and plane update operations + * independent from each other. So the actual modeset happens + * in the plane update callback, and here we just check + * whenever we must force the modeset. + */ + if (drm_atomic_crtc_needs_modeset(crtc->state)) { + output->needs_modeset = true; + } } static const struct drm_crtc_helper_funcs virtio_gpu_crtc_helper_funcs = { diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 9ff9f4ac0522..fbc04272db4f 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -137,7 +137,7 @@ struct virtio_gpu_output { struct edid *edid; int cur_x; int cur_y; - bool enabled; + bool needs_modeset; }; #define drm_crtc_to_virtio_gpu_output(x) \ container_of(x, struct virtio_gpu_output, crtc) diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index e83651b7747d..842f8b61aa89 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -151,7 +151,13 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev, if (ret < 0) return -EINVAL; - shmem->pages = drm_gem_shmem_get_pages_sgt(&bo->base.base); + /* + * virtio_gpu uses drm_gem_shmem_get_sg_table instead of + * drm_gem_shmem_get_pages_sgt because virtio has it's own set of + * dma-ops. This is discouraged for other drivers, but should be fine + * since virtio_gpu doesn't support dma-buf import from other devices. + */ + shmem->pages = drm_gem_shmem_get_sg_table(&bo->base.base); if (!shmem->pages) { drm_gem_shmem_unpin(&bo->base.base); return -EINVAL; diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c index 52d24179bcec..6a311cd93440 100644 --- a/drivers/gpu/drm/virtio/virtgpu_plane.c +++ b/drivers/gpu/drm/virtio/virtgpu_plane.c @@ -142,7 +142,7 @@ static void virtio_gpu_primary_plane_update(struct drm_plane *plane, if (WARN_ON(!output)) return; - if (!plane->state->fb || !output->enabled) { + if (!plane->state->fb || !output->crtc.state->active) { DRM_DEBUG("nofb\n"); virtio_gpu_cmd_set_scanout(vgdev, output->index, 0, plane->state->src_w >> 16, @@ -163,7 +163,9 @@ static void virtio_gpu_primary_plane_update(struct drm_plane *plane, plane->state->src_w != old_state->src_w || plane->state->src_h != old_state->src_h || plane->state->src_x != old_state->src_x || - plane->state->src_y != old_state->src_y) { + plane->state->src_y != old_state->src_y || + output->needs_modeset) { + output->needs_modeset = false; DRM_DEBUG("handle 0x%x, crtc %dx%d+%d+%d, src %dx%d+%d+%d\n", bo->hw_res_handle, plane->state->crtc_w, plane->state->crtc_h, diff --git a/drivers/gpu/drm/xlnx/Kconfig b/drivers/gpu/drm/xlnx/Kconfig index aa6cd889bd11..b52c6cdfc0b8 100644 --- a/drivers/gpu/drm/xlnx/Kconfig +++ b/drivers/gpu/drm/xlnx/Kconfig @@ -2,6 +2,7 @@ config DRM_ZYNQMP_DPSUB tristate "ZynqMP DisplayPort Controller Driver" depends on ARCH_ZYNQMP || COMPILE_TEST depends on COMMON_CLK && DRM && OF + depends on DMADEVICES select DMA_ENGINE select DRM_GEM_CMA_HELPER select DRM_KMS_CMA_HELPER diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c index 513825e424bf..a92fc3f90bb5 100644 --- a/drivers/infiniband/core/cq.c +++ b/drivers/infiniband/core/cq.c @@ -379,7 +379,7 @@ static int ib_alloc_cqs(struct ib_device *dev, unsigned int nr_cqes, { LIST_HEAD(tmp_list); unsigned int nr_cqs, i; - struct ib_cq *cq; + struct ib_cq *cq, *n; int ret; if (poll_ctx > IB_POLL_LAST_POOL_TYPE) { @@ -412,7 +412,7 @@ static int ib_alloc_cqs(struct ib_device *dev, unsigned int nr_cqes, return 0; out_free_cqs: - list_for_each_entry(cq, &tmp_list, pool_entry) { + list_for_each_entry_safe(cq, n, &tmp_list, pool_entry) { cq->shared = false; ib_free_cq(cq); } diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 3096e73797b7..307886737646 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1801,7 +1801,7 @@ int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width) dev_put(netdev); - if (!rc) { + if (!rc && lksettings.base.speed != (u32)SPEED_UNKNOWN) { netdev_speed = lksettings.base.speed; } else { netdev_speed = SPEED_1000; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 5ee272d27aaa..1d7a9ca5240c 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -752,12 +752,6 @@ static int bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp) gsi_sqp = rdev->gsi_ctx.gsi_sqp; gsi_sah = rdev->gsi_ctx.gsi_sah; - /* remove from active qp list */ - mutex_lock(&rdev->qp_lock); - list_del(&gsi_sqp->list); - mutex_unlock(&rdev->qp_lock); - atomic_dec(&rdev->qp_count); - ibdev_dbg(&rdev->ibdev, "Destroy the shadow AH\n"); bnxt_qplib_destroy_ah(&rdev->qplib_res, &gsi_sah->qplib_ah, @@ -772,6 +766,12 @@ static int bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp) } bnxt_qplib_free_qp_res(&rdev->qplib_res, &gsi_sqp->qplib_qp); + /* remove from active qp list */ + mutex_lock(&rdev->qp_lock); + list_del(&gsi_sqp->list); + mutex_unlock(&rdev->qp_lock); + atomic_dec(&rdev->qp_count); + kfree(rdev->gsi_ctx.sqp_tbl); kfree(gsi_sah); kfree(gsi_sqp); @@ -792,11 +792,6 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata) unsigned int flags; int rc; - mutex_lock(&rdev->qp_lock); - list_del(&qp->list); - mutex_unlock(&rdev->qp_lock); - atomic_dec(&rdev->qp_count); - bnxt_qplib_flush_cqn_wq(&qp->qplib_qp); rc = bnxt_qplib_destroy_qp(&rdev->qplib_res, &qp->qplib_qp); @@ -819,6 +814,11 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata) goto sh_fail; } + mutex_lock(&rdev->qp_lock); + list_del(&qp->list); + mutex_unlock(&rdev->qp_lock); + atomic_dec(&rdev->qp_count); + ib_umem_release(qp->rumem); ib_umem_release(qp->sumem); @@ -3264,6 +3264,19 @@ static void bnxt_re_process_res_rawqp1_wc(struct ib_wc *wc, wc->wc_flags |= IB_WC_GRH; } +static bool bnxt_re_check_if_vlan_valid(struct bnxt_re_dev *rdev, + u16 vlan_id) +{ + /* + * Check if the vlan is configured in the host. If not configured, it + * can be a transparent VLAN. So dont report the vlan id. + */ + if (!__vlan_find_dev_deep_rcu(rdev->netdev, + htons(ETH_P_8021Q), vlan_id)) + return false; + return true; +} + static bool bnxt_re_is_vlan_pkt(struct bnxt_qplib_cqe *orig_cqe, u16 *vid, u8 *sl) { @@ -3332,9 +3345,11 @@ static void bnxt_re_process_res_shadow_qp_wc(struct bnxt_re_qp *gsi_sqp, wc->src_qp = orig_cqe->src_qp; memcpy(wc->smac, orig_cqe->smac, ETH_ALEN); if (bnxt_re_is_vlan_pkt(orig_cqe, &vlan_id, &sl)) { - wc->vlan_id = vlan_id; - wc->sl = sl; - wc->wc_flags |= IB_WC_WITH_VLAN; + if (bnxt_re_check_if_vlan_valid(rdev, vlan_id)) { + wc->vlan_id = vlan_id; + wc->sl = sl; + wc->wc_flags |= IB_WC_WITH_VLAN; + } } wc->port_num = 1; wc->vendor_err = orig_cqe->status; diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 17ac8b7c5710..53aee5a42ab8 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -1009,7 +1009,6 @@ static void bnxt_re_free_res(struct bnxt_re_dev *rdev) static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev) { struct bnxt_re_ring_attr rattr = {}; - struct bnxt_qplib_ctx *qplib_ctx; int num_vec_created = 0; int rc = 0, i; u8 type; @@ -1032,13 +1031,11 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev) if (rc) goto dealloc_res; - qplib_ctx = &rdev->qplib_ctx; for (i = 0; i < rdev->num_msix - 1; i++) { struct bnxt_qplib_nq *nq; nq = &rdev->nq[i]; - nq->hwq.max_elements = (qplib_ctx->cq_count + - qplib_ctx->srqc_count + 2); + nq->hwq.max_elements = BNXT_QPLIB_NQE_MAX_CNT; rc = bnxt_qplib_alloc_nq(&rdev->qplib_res, &rdev->nq[i]); if (rc) { ibdev_err(&rdev->ibdev, "Alloc Failed NQ%d rc:%#x", diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index d60e3dcea087..f78da54a0bc5 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -818,6 +818,7 @@ int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) u16 cmd_flags = 0; u32 qp_flags = 0; u8 pg_sz_lvl; + u32 tbl_indx; int rc; RCFW_CMD_PREP(req, CREATE_QP1, cmd_flags); @@ -907,8 +908,9 @@ int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) rq->dbinfo.db = qp->dpi->dbr; rq->dbinfo.max_slot = bnxt_qplib_set_rq_max_slot(rq->wqe_size); } - rcfw->qp_tbl[qp->id].qp_id = qp->id; - rcfw->qp_tbl[qp->id].qp_handle = (void *)qp; + tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw); + rcfw->qp_tbl[tbl_indx].qp_id = qp->id; + rcfw->qp_tbl[tbl_indx].qp_handle = (void *)qp; return 0; @@ -935,10 +937,10 @@ static void bnxt_qplib_init_psn_ptr(struct bnxt_qplib_qp *qp, int size) sq = &qp->sq; hwq = &sq->hwq; + /* First psn entry */ fpsne = (u64)bnxt_qplib_get_qe(hwq, hwq->depth, &psn_pg); if (!IS_ALIGNED(fpsne, PAGE_SIZE)) - indx_pad = ALIGN(fpsne, PAGE_SIZE) / size; - + indx_pad = (fpsne & ~PAGE_MASK) / size; hwq->pad_pgofft = indx_pad; hwq->pad_pg = (u64 *)psn_pg; hwq->pad_stride = size; @@ -959,6 +961,7 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) u16 cmd_flags = 0; u32 qp_flags = 0; u8 pg_sz_lvl; + u32 tbl_indx; u16 nsge; RCFW_CMD_PREP(req, CREATE_QP, cmd_flags); @@ -1111,8 +1114,9 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) rq->dbinfo.db = qp->dpi->dbr; rq->dbinfo.max_slot = bnxt_qplib_set_rq_max_slot(rq->wqe_size); } - rcfw->qp_tbl[qp->id].qp_id = qp->id; - rcfw->qp_tbl[qp->id].qp_handle = (void *)qp; + tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw); + rcfw->qp_tbl[tbl_indx].qp_id = qp->id; + rcfw->qp_tbl[tbl_indx].qp_handle = (void *)qp; return 0; fail: @@ -1457,10 +1461,12 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res, struct cmdq_destroy_qp req; struct creq_destroy_qp_resp resp; u16 cmd_flags = 0; + u32 tbl_indx; int rc; - rcfw->qp_tbl[qp->id].qp_id = BNXT_QPLIB_QP_ID_INVALID; - rcfw->qp_tbl[qp->id].qp_handle = NULL; + tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw); + rcfw->qp_tbl[tbl_indx].qp_id = BNXT_QPLIB_QP_ID_INVALID; + rcfw->qp_tbl[tbl_indx].qp_handle = NULL; RCFW_CMD_PREP(req, DESTROY_QP, cmd_flags); @@ -1468,8 +1474,8 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res, rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, NULL, 0); if (rc) { - rcfw->qp_tbl[qp->id].qp_id = qp->id; - rcfw->qp_tbl[qp->id].qp_handle = qp; + rcfw->qp_tbl[tbl_indx].qp_id = qp->id; + rcfw->qp_tbl[tbl_indx].qp_handle = qp; return rc; } diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 4e211162acee..f7736e34ac64 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -307,14 +307,15 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw, __le16 mcookie; u16 cookie; int rc = 0; - u32 qp_id; + u32 qp_id, tbl_indx; pdev = rcfw->pdev; switch (qp_event->event) { case CREQ_QP_EVENT_EVENT_QP_ERROR_NOTIFICATION: err_event = (struct creq_qp_error_notification *)qp_event; qp_id = le32_to_cpu(err_event->xid); - qp = rcfw->qp_tbl[qp_id].qp_handle; + tbl_indx = map_qp_id_to_tbl_indx(qp_id, rcfw); + qp = rcfw->qp_tbl[tbl_indx].qp_handle; dev_dbg(&pdev->dev, "Received QP error notification\n"); dev_dbg(&pdev->dev, "qpid 0x%x, req_err=0x%x, resp_err=0x%x\n", @@ -615,8 +616,9 @@ int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res, cmdq->bmap_size = bmap_size; - rcfw->qp_tbl_size = qp_tbl_sz; - rcfw->qp_tbl = kcalloc(qp_tbl_sz, sizeof(struct bnxt_qplib_qp_node), + /* Allocate one extra to hold the QP1 entries */ + rcfw->qp_tbl_size = qp_tbl_sz + 1; + rcfw->qp_tbl = kcalloc(rcfw->qp_tbl_size, sizeof(struct bnxt_qplib_qp_node), GFP_KERNEL); if (!rcfw->qp_tbl) goto fail; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h index 157387636d00..5f2f0a5a3560 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h @@ -216,4 +216,9 @@ int bnxt_qplib_deinit_rcfw(struct bnxt_qplib_rcfw *rcfw); int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw, struct bnxt_qplib_ctx *ctx, int is_virtfn); void bnxt_qplib_mark_qp_error(void *qp_handle); +static inline u32 map_qp_id_to_tbl_indx(u32 qid, struct bnxt_qplib_rcfw *rcfw) +{ + /* Last index of the qp_tbl is for QP1 ie. qp_tbl_size - 1*/ + return (qid == 1) ? rcfw->qp_tbl_size - 1 : qid % rcfw->qp_tbl_size - 2; +} #endif /* __BNXT_QPLIB_RCFW_H__ */ diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 4cd475ea97a2..64d44f51db4b 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -149,7 +149,7 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw, attr->max_inline_data = le32_to_cpu(sb->max_inline_data); attr->l2_db_size = (sb->l2_db_space_size + 1) * (0x01 << RCFW_DBR_BASE_PAGE_SHIFT); - attr->max_sgid = le32_to_cpu(sb->max_gid); + attr->max_sgid = BNXT_QPLIB_NUM_GIDS_SUPPORTED; bnxt_qplib_query_version(rcfw, attr->fw_ver); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h index 6404f0da1051..967890cd81f2 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h @@ -47,6 +47,7 @@ struct bnxt_qplib_dev_attr { #define FW_VER_ARR_LEN 4 u8 fw_ver[FW_VER_ARR_LEN]; +#define BNXT_QPLIB_NUM_GIDS_SUPPORTED 256 u16 max_sgid; u16 max_mrw; u32 max_qp; diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 5e7910a517da..bd4f975e7f9a 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -784,7 +784,8 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port, props->ip_gids = true; props->gid_tbl_len = mdev->dev->caps.gid_table_len[port]; props->max_msg_sz = mdev->dev->caps.max_msg_sz; - props->pkey_tbl_len = 1; + if (mdev->dev->caps.pkey_table_len[port]) + props->pkey_tbl_len = 1; props->max_mtu = IB_MTU_4096; props->max_vl_num = 2; props->state = IB_PORT_DOWN; diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index 907203afbd99..77f2c7cd1216 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -40,6 +40,8 @@ MODULE_AUTHOR("Bob Pearson, Frank Zago, John Groves, Kamal Heib"); MODULE_DESCRIPTION("Soft RDMA transport"); MODULE_LICENSE("Dual BSD/GPL"); +bool rxe_initialized; + /* free resources for a rxe device all objects created for this device must * have been destroyed */ @@ -315,6 +317,7 @@ static int __init rxe_module_init(void) return err; rdma_link_register(&rxe_link_ops); + rxe_initialized = true; pr_info("loaded\n"); return 0; } @@ -326,6 +329,7 @@ static void __exit rxe_module_exit(void) rxe_net_exit(); rxe_cache_exit(); + rxe_initialized = false; pr_info("unloaded\n"); } diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h index fb07eed9e402..cae1b0a24c85 100644 --- a/drivers/infiniband/sw/rxe/rxe.h +++ b/drivers/infiniband/sw/rxe/rxe.h @@ -67,6 +67,8 @@ #define RXE_ROCE_V2_SPORT (0xc000) +extern bool rxe_initialized; + static inline u32 rxe_crc32(struct rxe_dev *rxe, u32 crc, void *next, size_t len) { diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c index cdd811a45120..ce24144de16a 100644 --- a/drivers/infiniband/sw/rxe/rxe_mr.c +++ b/drivers/infiniband/sw/rxe/rxe_mr.c @@ -205,6 +205,7 @@ int rxe_mem_init_user(struct rxe_pd *pd, u64 start, vaddr = page_address(sg_page_iter_page(&sg_iter)); if (!vaddr) { pr_warn("null vaddr\n"); + ib_umem_release(umem); err = -ENOMEM; goto err1; } diff --git a/drivers/infiniband/sw/rxe/rxe_sysfs.c b/drivers/infiniband/sw/rxe/rxe_sysfs.c index ccda5f5a3bc0..2af31d421bfc 100644 --- a/drivers/infiniband/sw/rxe/rxe_sysfs.c +++ b/drivers/infiniband/sw/rxe/rxe_sysfs.c @@ -61,6 +61,11 @@ static int rxe_param_set_add(const char *val, const struct kernel_param *kp) struct net_device *ndev; struct rxe_dev *exists; + if (!rxe_initialized) { + pr_err("Module parameters are not supported, use rdma link add or rxe_cfg\n"); + return -EAGAIN; + } + len = sanitize_arg(val, intf, sizeof(intf)); if (!len) { pr_err("add: invalid interface name\n"); diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 658939e5c34a..8522e9a3e914 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -1056,7 +1056,7 @@ static ssize_t parent_show(struct device *device, struct rxe_dev *rxe = rdma_device_to_drv_device(device, struct rxe_dev, ib_dev); - return snprintf(buf, 16, "%s\n", rxe_parent_name(rxe, 1)); + return scnprintf(buf, PAGE_SIZE, "%s\n", rxe_parent_name(rxe, 1)); } static DEVICE_ATTR_RO(parent); diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index e86acda3cf8c..695f701dc43d 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -140,15 +140,15 @@ isert_alloc_rx_descriptors(struct isert_conn *isert_conn) rx_desc = isert_conn->rx_descs; for (i = 0; i < ISERT_QP_MAX_RECV_DTOS; i++, rx_desc++) { - dma_addr = ib_dma_map_single(ib_dev, (void *)rx_desc, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + dma_addr = ib_dma_map_single(ib_dev, rx_desc->buf, + ISER_RX_SIZE, DMA_FROM_DEVICE); if (ib_dma_mapping_error(ib_dev, dma_addr)) goto dma_map_fail; rx_desc->dma_addr = dma_addr; rx_sg = &rx_desc->rx_sg; - rx_sg->addr = rx_desc->dma_addr; + rx_sg->addr = rx_desc->dma_addr + isert_get_hdr_offset(rx_desc); rx_sg->length = ISER_RX_PAYLOAD_SIZE; rx_sg->lkey = device->pd->local_dma_lkey; rx_desc->rx_cqe.done = isert_recv_done; @@ -160,7 +160,7 @@ dma_map_fail: rx_desc = isert_conn->rx_descs; for (j = 0; j < i; j++, rx_desc++) { ib_dma_unmap_single(ib_dev, rx_desc->dma_addr, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ISER_RX_SIZE, DMA_FROM_DEVICE); } kfree(isert_conn->rx_descs); isert_conn->rx_descs = NULL; @@ -181,7 +181,7 @@ isert_free_rx_descriptors(struct isert_conn *isert_conn) rx_desc = isert_conn->rx_descs; for (i = 0; i < ISERT_QP_MAX_RECV_DTOS; i++, rx_desc++) { ib_dma_unmap_single(ib_dev, rx_desc->dma_addr, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ISER_RX_SIZE, DMA_FROM_DEVICE); } kfree(isert_conn->rx_descs); @@ -299,10 +299,9 @@ isert_free_login_buf(struct isert_conn *isert_conn) ISER_RX_PAYLOAD_SIZE, DMA_TO_DEVICE); kfree(isert_conn->login_rsp_buf); - ib_dma_unmap_single(ib_dev, isert_conn->login_req_dma, - ISER_RX_PAYLOAD_SIZE, - DMA_FROM_DEVICE); - kfree(isert_conn->login_req_buf); + ib_dma_unmap_single(ib_dev, isert_conn->login_desc->dma_addr, + ISER_RX_SIZE, DMA_FROM_DEVICE); + kfree(isert_conn->login_desc); } static int @@ -311,25 +310,25 @@ isert_alloc_login_buf(struct isert_conn *isert_conn, { int ret; - isert_conn->login_req_buf = kzalloc(sizeof(*isert_conn->login_req_buf), + isert_conn->login_desc = kzalloc(sizeof(*isert_conn->login_desc), GFP_KERNEL); - if (!isert_conn->login_req_buf) + if (!isert_conn->login_desc) return -ENOMEM; - isert_conn->login_req_dma = ib_dma_map_single(ib_dev, - isert_conn->login_req_buf, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); - ret = ib_dma_mapping_error(ib_dev, isert_conn->login_req_dma); + isert_conn->login_desc->dma_addr = ib_dma_map_single(ib_dev, + isert_conn->login_desc->buf, + ISER_RX_SIZE, DMA_FROM_DEVICE); + ret = ib_dma_mapping_error(ib_dev, isert_conn->login_desc->dma_addr); if (ret) { - isert_err("login_req_dma mapping error: %d\n", ret); - isert_conn->login_req_dma = 0; - goto out_free_login_req_buf; + isert_err("login_desc dma mapping error: %d\n", ret); + isert_conn->login_desc->dma_addr = 0; + goto out_free_login_desc; } isert_conn->login_rsp_buf = kzalloc(ISER_RX_PAYLOAD_SIZE, GFP_KERNEL); if (!isert_conn->login_rsp_buf) { ret = -ENOMEM; - goto out_unmap_login_req_buf; + goto out_unmap_login_desc; } isert_conn->login_rsp_dma = ib_dma_map_single(ib_dev, @@ -346,11 +345,11 @@ isert_alloc_login_buf(struct isert_conn *isert_conn, out_free_login_rsp_buf: kfree(isert_conn->login_rsp_buf); -out_unmap_login_req_buf: - ib_dma_unmap_single(ib_dev, isert_conn->login_req_dma, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); -out_free_login_req_buf: - kfree(isert_conn->login_req_buf); +out_unmap_login_desc: + ib_dma_unmap_single(ib_dev, isert_conn->login_desc->dma_addr, + ISER_RX_SIZE, DMA_FROM_DEVICE); +out_free_login_desc: + kfree(isert_conn->login_desc); return ret; } @@ -476,7 +475,7 @@ isert_connect_release(struct isert_conn *isert_conn) if (isert_conn->qp) isert_destroy_qp(isert_conn); - if (isert_conn->login_req_buf) + if (isert_conn->login_desc) isert_free_login_buf(isert_conn); isert_device_put(device); @@ -862,17 +861,18 @@ isert_login_post_recv(struct isert_conn *isert_conn) int ret; memset(&sge, 0, sizeof(struct ib_sge)); - sge.addr = isert_conn->login_req_dma; + sge.addr = isert_conn->login_desc->dma_addr + + isert_get_hdr_offset(isert_conn->login_desc); sge.length = ISER_RX_PAYLOAD_SIZE; sge.lkey = isert_conn->device->pd->local_dma_lkey; isert_dbg("Setup sge: addr: %llx length: %d 0x%08x\n", sge.addr, sge.length, sge.lkey); - isert_conn->login_req_buf->rx_cqe.done = isert_login_recv_done; + isert_conn->login_desc->rx_cqe.done = isert_login_recv_done; memset(&rx_wr, 0, sizeof(struct ib_recv_wr)); - rx_wr.wr_cqe = &isert_conn->login_req_buf->rx_cqe; + rx_wr.wr_cqe = &isert_conn->login_desc->rx_cqe; rx_wr.sg_list = &sge; rx_wr.num_sge = 1; @@ -949,7 +949,7 @@ post_send: static void isert_rx_login_req(struct isert_conn *isert_conn) { - struct iser_rx_desc *rx_desc = isert_conn->login_req_buf; + struct iser_rx_desc *rx_desc = isert_conn->login_desc; int rx_buflen = isert_conn->login_req_len; struct iscsi_conn *conn = isert_conn->conn; struct iscsi_login *login = conn->conn_login; @@ -961,7 +961,7 @@ isert_rx_login_req(struct isert_conn *isert_conn) if (login->first_request) { struct iscsi_login_req *login_req = - (struct iscsi_login_req *)&rx_desc->iscsi_header; + (struct iscsi_login_req *)isert_get_iscsi_hdr(rx_desc); /* * Setup the initial iscsi_login values from the leading * login request PDU. @@ -980,13 +980,13 @@ isert_rx_login_req(struct isert_conn *isert_conn) login->tsih = be16_to_cpu(login_req->tsih); } - memcpy(&login->req[0], (void *)&rx_desc->iscsi_header, ISCSI_HDR_LEN); + memcpy(&login->req[0], isert_get_iscsi_hdr(rx_desc), ISCSI_HDR_LEN); size = min(rx_buflen, MAX_KEY_VALUE_PAIRS); isert_dbg("Using login payload size: %d, rx_buflen: %d " "MAX_KEY_VALUE_PAIRS: %d\n", size, rx_buflen, MAX_KEY_VALUE_PAIRS); - memcpy(login->req_buf, &rx_desc->data[0], size); + memcpy(login->req_buf, isert_get_data(rx_desc), size); if (login->first_request) { complete(&isert_conn->login_comp); @@ -1051,14 +1051,15 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn, if (imm_data_len != data_len) { sg_nents = max(1UL, DIV_ROUND_UP(imm_data_len, PAGE_SIZE)); sg_copy_from_buffer(cmd->se_cmd.t_data_sg, sg_nents, - &rx_desc->data[0], imm_data_len); + isert_get_data(rx_desc), imm_data_len); isert_dbg("Copy Immediate sg_nents: %u imm_data_len: %d\n", sg_nents, imm_data_len); } else { sg_init_table(&isert_cmd->sg, 1); cmd->se_cmd.t_data_sg = &isert_cmd->sg; cmd->se_cmd.t_data_nents = 1; - sg_set_buf(&isert_cmd->sg, &rx_desc->data[0], imm_data_len); + sg_set_buf(&isert_cmd->sg, isert_get_data(rx_desc), + imm_data_len); isert_dbg("Transfer Immediate imm_data_len: %d\n", imm_data_len); } @@ -1127,9 +1128,9 @@ isert_handle_iscsi_dataout(struct isert_conn *isert_conn, } isert_dbg("Copying DataOut: sg_start: %p, sg_off: %u " "sg_nents: %u from %p %u\n", sg_start, sg_off, - sg_nents, &rx_desc->data[0], unsol_data_len); + sg_nents, isert_get_data(rx_desc), unsol_data_len); - sg_copy_from_buffer(sg_start, sg_nents, &rx_desc->data[0], + sg_copy_from_buffer(sg_start, sg_nents, isert_get_data(rx_desc), unsol_data_len); rc = iscsit_check_dataout_payload(cmd, hdr, false); @@ -1188,7 +1189,7 @@ isert_handle_text_cmd(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd } cmd->text_in_ptr = text_in; - memcpy(cmd->text_in_ptr, &rx_desc->data[0], payload_length); + memcpy(cmd->text_in_ptr, isert_get_data(rx_desc), payload_length); return iscsit_process_text_cmd(conn, cmd, hdr); } @@ -1198,7 +1199,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc, uint32_t read_stag, uint64_t read_va, uint32_t write_stag, uint64_t write_va) { - struct iscsi_hdr *hdr = &rx_desc->iscsi_header; + struct iscsi_hdr *hdr = isert_get_iscsi_hdr(rx_desc); struct iscsi_conn *conn = isert_conn->conn; struct iscsi_cmd *cmd; struct isert_cmd *isert_cmd; @@ -1296,8 +1297,8 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc) struct isert_conn *isert_conn = wc->qp->qp_context; struct ib_device *ib_dev = isert_conn->cm_id->device; struct iser_rx_desc *rx_desc = cqe_to_rx_desc(wc->wr_cqe); - struct iscsi_hdr *hdr = &rx_desc->iscsi_header; - struct iser_ctrl *iser_ctrl = &rx_desc->iser_header; + struct iscsi_hdr *hdr = isert_get_iscsi_hdr(rx_desc); + struct iser_ctrl *iser_ctrl = isert_get_iser_hdr(rx_desc); uint64_t read_va = 0, write_va = 0; uint32_t read_stag = 0, write_stag = 0; @@ -1311,7 +1312,7 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc) rx_desc->in_use = true; ib_dma_sync_single_for_cpu(ib_dev, rx_desc->dma_addr, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ISER_RX_SIZE, DMA_FROM_DEVICE); isert_dbg("DMA: 0x%llx, iSCSI opcode: 0x%02x, ITT: 0x%08x, flags: 0x%02x dlen: %d\n", rx_desc->dma_addr, hdr->opcode, hdr->itt, hdr->flags, @@ -1346,7 +1347,7 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc) read_stag, read_va, write_stag, write_va); ib_dma_sync_single_for_device(ib_dev, rx_desc->dma_addr, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ISER_RX_SIZE, DMA_FROM_DEVICE); } static void @@ -1360,8 +1361,8 @@ isert_login_recv_done(struct ib_cq *cq, struct ib_wc *wc) return; } - ib_dma_sync_single_for_cpu(ib_dev, isert_conn->login_req_dma, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ib_dma_sync_single_for_cpu(ib_dev, isert_conn->login_desc->dma_addr, + ISER_RX_SIZE, DMA_FROM_DEVICE); isert_conn->login_req_len = wc->byte_len - ISER_HEADERS_LEN; @@ -1376,8 +1377,8 @@ isert_login_recv_done(struct ib_cq *cq, struct ib_wc *wc) complete(&isert_conn->login_req_comp); mutex_unlock(&isert_conn->mutex); - ib_dma_sync_single_for_device(ib_dev, isert_conn->login_req_dma, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ib_dma_sync_single_for_device(ib_dev, isert_conn->login_desc->dma_addr, + ISER_RX_SIZE, DMA_FROM_DEVICE); } static void diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h index c55f7d9bfced..7fee4a65e181 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.h +++ b/drivers/infiniband/ulp/isert/ib_isert.h @@ -59,9 +59,11 @@ ISERT_MAX_TX_MISC_PDUS + \ ISERT_MAX_RX_MISC_PDUS) -#define ISER_RX_PAD_SIZE (ISCSI_DEF_MAX_RECV_SEG_LEN + 4096 - \ - (ISER_RX_PAYLOAD_SIZE + sizeof(u64) + sizeof(struct ib_sge) + \ - sizeof(struct ib_cqe) + sizeof(bool))) +/* + * RX size is default of 8k plus headers, but data needs to align to + * 512 boundary, so use 1024 to have the extra space for alignment. + */ +#define ISER_RX_SIZE (ISCSI_DEF_MAX_RECV_SEG_LEN + 1024) /* Maximum support is 16MB I/O size */ #define ISCSI_ISER_MAX_SG_TABLESIZE 4096 @@ -81,21 +83,41 @@ enum iser_conn_state { }; struct iser_rx_desc { - struct iser_ctrl iser_header; - struct iscsi_hdr iscsi_header; - char data[ISCSI_DEF_MAX_RECV_SEG_LEN]; + char buf[ISER_RX_SIZE]; u64 dma_addr; struct ib_sge rx_sg; struct ib_cqe rx_cqe; bool in_use; - char pad[ISER_RX_PAD_SIZE]; -} __packed; +}; static inline struct iser_rx_desc *cqe_to_rx_desc(struct ib_cqe *cqe) { return container_of(cqe, struct iser_rx_desc, rx_cqe); } +static void *isert_get_iser_hdr(struct iser_rx_desc *desc) +{ + return PTR_ALIGN(desc->buf + ISER_HEADERS_LEN, 512) - ISER_HEADERS_LEN; +} + +static size_t isert_get_hdr_offset(struct iser_rx_desc *desc) +{ + return isert_get_iser_hdr(desc) - (void *)desc->buf; +} + +static void *isert_get_iscsi_hdr(struct iser_rx_desc *desc) +{ + return isert_get_iser_hdr(desc) + sizeof(struct iser_ctrl); +} + +static void *isert_get_data(struct iser_rx_desc *desc) +{ + void *data = isert_get_iser_hdr(desc) + ISER_HEADERS_LEN; + + WARN_ON((uintptr_t)data & 511); + return data; +} + struct iser_tx_desc { struct iser_ctrl iser_header; struct iscsi_hdr iscsi_header; @@ -142,9 +164,8 @@ struct isert_conn { u32 responder_resources; u32 initiator_depth; bool pi_support; - struct iser_rx_desc *login_req_buf; + struct iser_rx_desc *login_desc; char *login_rsp_buf; - u64 login_req_dma; int login_req_len; u64 login_rsp_dma; struct iser_rx_desc *rx_descs; diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c b/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c index 3d7877534bcc..cf6a2be61695 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c @@ -152,13 +152,6 @@ static struct attribute_group rtrs_srv_stats_attr_group = { .attrs = rtrs_srv_stats_attrs, }; -static void rtrs_srv_dev_release(struct device *dev) -{ - struct rtrs_srv *srv = container_of(dev, struct rtrs_srv, dev); - - kfree(srv); -} - static int rtrs_srv_create_once_sysfs_root_folders(struct rtrs_srv_sess *sess) { struct rtrs_srv *srv = sess->srv; @@ -172,7 +165,6 @@ static int rtrs_srv_create_once_sysfs_root_folders(struct rtrs_srv_sess *sess) goto unlock; } srv->dev.class = rtrs_dev_class; - srv->dev.release = rtrs_srv_dev_release; err = dev_set_name(&srv->dev, "%s", sess->s.sessname); if (err) goto unlock; @@ -182,16 +174,16 @@ static int rtrs_srv_create_once_sysfs_root_folders(struct rtrs_srv_sess *sess) * sysfs files are created */ dev_set_uevent_suppress(&srv->dev, true); - err = device_register(&srv->dev); + err = device_add(&srv->dev); if (err) { - pr_err("device_register(): %d\n", err); + pr_err("device_add(): %d\n", err); goto put; } srv->kobj_paths = kobject_create_and_add("paths", &srv->dev.kobj); if (!srv->kobj_paths) { err = -ENOMEM; pr_err("kobject_create_and_add(): %d\n", err); - device_unregister(&srv->dev); + device_del(&srv->dev); goto unlock; } dev_set_uevent_suppress(&srv->dev, false); @@ -216,7 +208,7 @@ rtrs_srv_destroy_once_sysfs_root_folders(struct rtrs_srv_sess *sess) kobject_del(srv->kobj_paths); kobject_put(srv->kobj_paths); mutex_unlock(&srv->paths_mutex); - device_unregister(&srv->dev); + device_del(&srv->dev); } else { mutex_unlock(&srv->paths_mutex); } diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c index a219bd1bdbc2..28f6414dfa3d 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c @@ -1319,6 +1319,13 @@ static int rtrs_srv_get_next_cq_vector(struct rtrs_srv_sess *sess) return sess->cur_cq_vector; } +static void rtrs_srv_dev_release(struct device *dev) +{ + struct rtrs_srv *srv = container_of(dev, struct rtrs_srv, dev); + + kfree(srv); +} + static struct rtrs_srv *__alloc_srv(struct rtrs_srv_ctx *ctx, const uuid_t *paths_uuid) { @@ -1336,6 +1343,8 @@ static struct rtrs_srv *__alloc_srv(struct rtrs_srv_ctx *ctx, uuid_copy(&srv->paths_uuid, paths_uuid); srv->queue_depth = sess_queue_depth; srv->ctx = ctx; + device_initialize(&srv->dev); + srv->dev.release = rtrs_srv_dev_release; srv->chunks = kcalloc(srv->queue_depth, sizeof(*srv->chunks), GFP_KERNEL); diff --git a/drivers/rapidio/Kconfig b/drivers/rapidio/Kconfig index e4c422d806be..b9f8514909bf 100644 --- a/drivers/rapidio/Kconfig +++ b/drivers/rapidio/Kconfig @@ -37,7 +37,7 @@ config RAPIDIO_ENABLE_RX_TX_PORTS config RAPIDIO_DMA_ENGINE bool "DMA Engine support for RapidIO" depends on RAPIDIO - select DMADEVICES + depends on DMADEVICES select DMA_ENGINE help Say Y here if you want to use DMA Engine frameork for RapidIO data diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c index d8cbc9c0e766..e67abb184a8a 100644 --- a/drivers/scsi/libfc/fc_disc.c +++ b/drivers/scsi/libfc/fc_disc.c @@ -634,8 +634,6 @@ free_fp: fc_frame_free(fp); out: kref_put(&rdata->kref, fc_rport_destroy); - if (!IS_ERR(fp)) - fc_frame_free(fp); } /** diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index 6a521ba7a616..a4887985aad6 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -209,7 +209,10 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc) task->num_scatter = si; } - task->data_dir = qc->dma_dir; + if (qc->tf.protocol == ATA_PROT_NODATA) + task->data_dir = DMA_NONE; + else + task->data_dir = qc->dma_dir; task->scatter = qc->sg; task->ata_task.retry_count = 1; task->task_state_flags = SAS_TASK_STATE_PENDING; diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 6aae61d6ee16..b60945182db8 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -3517,6 +3517,9 @@ lpfc_issue_els_rdf(struct lpfc_vport *vport, uint8_t retry) FC_TLV_DESC_LENGTH_FROM_SZ(prdf->reg_d1)); prdf->reg_d1.reg_desc.count = cpu_to_be32(ELS_RDF_REG_TAG_CNT); prdf->reg_d1.desc_tags[0] = cpu_to_be32(ELS_DTAG_LNK_INTEGRITY); + prdf->reg_d1.desc_tags[1] = cpu_to_be32(ELS_DTAG_DELIVERY); + prdf->reg_d1.desc_tags[2] = cpu_to_be32(ELS_DTAG_PEER_CONGEST); + prdf->reg_d1.desc_tags[3] = cpu_to_be32(ELS_DTAG_CONGESTION); lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD, "Issue RDF: did:x%x", @@ -4656,7 +4659,9 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, out: if (ndlp && NLP_CHK_NODE_ACT(ndlp) && shost) { spin_lock_irq(shost->host_lock); - ndlp->nlp_flag &= ~(NLP_ACC_REGLOGIN | NLP_RM_DFLT_RPI); + if (mbox) + ndlp->nlp_flag &= ~NLP_ACC_REGLOGIN; + ndlp->nlp_flag &= ~NLP_RM_DFLT_RPI; spin_unlock_irq(shost->host_lock); /* If the node is not being used by another discovery thread, diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h index c4ba8273a63f..12e4e76233e6 100644 --- a/drivers/scsi/lpfc/lpfc_hw4.h +++ b/drivers/scsi/lpfc/lpfc_hw4.h @@ -4800,7 +4800,7 @@ struct send_frame_wqe { uint32_t fc_hdr_wd5; /* word 15 */ }; -#define ELS_RDF_REG_TAG_CNT 1 +#define ELS_RDF_REG_TAG_CNT 4 struct lpfc_els_rdf_reg_desc { struct fc_df_desc_fpin_reg reg_desc; /* descriptor header */ __be32 desc_tags[ELS_RDF_REG_TAG_CNT]; diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index c69725999315..ca25e54bb782 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -11376,7 +11376,6 @@ lpfc_irq_clear_aff(struct lpfc_hba_eq_hdl *eqhdl) { cpumask_clear(&eqhdl->aff_mask); irq_clear_status_flags(eqhdl->irq, IRQ_NO_BALANCING); - irq_set_affinity_hint(eqhdl->irq, &eqhdl->aff_mask); } /** diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h index 20adec4387f0..c657abf22b75 100644 --- a/drivers/scsi/lpfc/lpfc_version.h +++ b/drivers/scsi/lpfc/lpfc_version.h @@ -20,7 +20,7 @@ * included with this package. * *******************************************************************/ -#define LPFC_DRIVER_VERSION "12.8.0.3" +#define LPFC_DRIVER_VERSION "12.8.0.4" #define LPFC_DRIVER_NAME "lpfc" /* Used for SLI 2/3 */ diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index 883cccb59c2d..b0c01cf0428f 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -3689,7 +3689,7 @@ int megasas_irqpoll(struct irq_poll *irqpoll, int budget) instance = irq_ctx->instance; if (irq_ctx->irq_line_enable) { - disable_irq(irq_ctx->os_irq); + disable_irq_nosync(irq_ctx->os_irq); irq_ctx->irq_line_enable = false; } diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 5730f32496b6..8062bd99add8 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -1733,7 +1733,7 @@ _base_irqpoll(struct irq_poll *irqpoll, int budget) reply_q = container_of(irqpoll, struct adapter_reply_queue, irqpoll); if (reply_q->irq_line_enable) { - disable_irq(reply_q->os_irq); + disable_irq_nosync(reply_q->os_irq); reply_q->irq_line_enable = false; } num_entries = _base_process_reply_queue(reply_q); diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c index 337e79d6837f..9889bab7d31c 100644 --- a/drivers/scsi/pm8001/pm8001_sas.c +++ b/drivers/scsi/pm8001/pm8001_sas.c @@ -818,7 +818,7 @@ pm8001_exec_internal_task_abort(struct pm8001_hba_info *pm8001_ha, res = pm8001_tag_alloc(pm8001_ha, &ccb_tag); if (res) - return res; + goto ex_err; ccb = &pm8001_ha->ccb_info[ccb_tag]; ccb->device = pm8001_dev; ccb->ccb_tag = ccb_tag; diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 1bc090d8a71b..a165120d2976 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -1626,7 +1626,7 @@ typedef struct { */ uint8_t firmware_options[2]; - uint16_t frame_payload_size; + __le16 frame_payload_size; __le16 max_iocb_allocation; __le16 execution_throttle; uint8_t retry_count; diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 507919d4ab36..0bd04a62af83 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -4603,18 +4603,18 @@ qla2x00_nvram_config(scsi_qla_host_t *vha) nv->firmware_options[1] = BIT_7 | BIT_5; nv->add_firmware_options[0] = BIT_5; nv->add_firmware_options[1] = BIT_5 | BIT_4; - nv->frame_payload_size = 2048; + nv->frame_payload_size = cpu_to_le16(2048); nv->special_options[1] = BIT_7; } else if (IS_QLA2200(ha)) { nv->firmware_options[0] = BIT_2 | BIT_1; nv->firmware_options[1] = BIT_7 | BIT_5; nv->add_firmware_options[0] = BIT_5; nv->add_firmware_options[1] = BIT_5 | BIT_4; - nv->frame_payload_size = 1024; + nv->frame_payload_size = cpu_to_le16(1024); } else if (IS_QLA2100(ha)) { nv->firmware_options[0] = BIT_3 | BIT_1; nv->firmware_options[1] = BIT_5; - nv->frame_payload_size = 1024; + nv->frame_payload_size = cpu_to_le16(1024); } nv->max_iocb_allocation = cpu_to_le16(256); diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index cd045dc75a58..7b56fe9f1062 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1389,14 +1389,27 @@ static u32 iscsit_do_crypto_hash_sg( sg = cmd->first_data_sg; page_off = cmd->first_data_sg_off; + if (data_length && page_off) { + struct scatterlist first_sg; + u32 len = min_t(u32, data_length, sg->length - page_off); + + sg_init_table(&first_sg, 1); + sg_set_page(&first_sg, sg_page(sg), len, sg->offset + page_off); + + ahash_request_set_crypt(hash, &first_sg, NULL, len); + crypto_ahash_update(hash); + + data_length -= len; + sg = sg_next(sg); + } + while (data_length) { - u32 cur_len = min_t(u32, data_length, (sg->length - page_off)); + u32 cur_len = min_t(u32, data_length, sg->length); ahash_request_set_crypt(hash, sg, NULL, cur_len); crypto_ahash_update(hash); data_length -= cur_len; - page_off = 0; /* iscsit_map_iovec has already checked for invalid sg pointers */ sg = sg_next(sg); } diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 85748e338858..893d1b406c29 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -1149,7 +1149,7 @@ void iscsit_free_conn(struct iscsi_conn *conn) } void iscsi_target_login_sess_out(struct iscsi_conn *conn, - struct iscsi_np *np, bool zero_tsih, bool new_sess) + bool zero_tsih, bool new_sess) { if (!new_sess) goto old_sess_out; @@ -1167,7 +1167,6 @@ void iscsi_target_login_sess_out(struct iscsi_conn *conn, conn->sess = NULL; old_sess_out: - iscsi_stop_login_thread_timer(np); /* * If login negotiation fails check if the Time2Retain timer * needs to be restarted. @@ -1407,8 +1406,9 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) new_sess_out: new_sess = true; old_sess_out: + iscsi_stop_login_thread_timer(np); tpg_np = conn->tpg_np; - iscsi_target_login_sess_out(conn, np, zero_tsih, new_sess); + iscsi_target_login_sess_out(conn, zero_tsih, new_sess); new_sess = false; if (tpg) { diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h index 3b8e3639ff5d..fc95e6150253 100644 --- a/drivers/target/iscsi/iscsi_target_login.h +++ b/drivers/target/iscsi/iscsi_target_login.h @@ -22,8 +22,7 @@ extern int iscsit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32); extern void iscsit_free_conn(struct iscsi_conn *); extern int iscsit_start_kthreads(struct iscsi_conn *); extern void iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8); -extern void iscsi_target_login_sess_out(struct iscsi_conn *, struct iscsi_np *, - bool, bool); +extern void iscsi_target_login_sess_out(struct iscsi_conn *, bool, bool); extern int iscsi_target_login_thread(void *); extern void iscsi_handle_login_thread_timeout(struct timer_list *t); diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index f88a52fec889..8b40f10976ff 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -535,12 +535,11 @@ static bool iscsi_target_sk_check_and_clear(struct iscsi_conn *conn, unsigned in static void iscsi_target_login_drop(struct iscsi_conn *conn, struct iscsi_login *login) { - struct iscsi_np *np = login->np; bool zero_tsih = login->zero_tsih; iscsi_remove_failed_auth_entry(conn); iscsi_target_nego_release(conn); - iscsi_target_login_sess_out(conn, np, zero_tsih, true); + iscsi_target_login_sess_out(conn, zero_tsih, true); } struct conn_timeout { diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index ed2bca0fce92..73683e58a08d 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -3550,6 +3550,9 @@ static int check_direct_IO(struct inode *inode, struct iov_iter *iter, unsigned long align = offset | iov_iter_alignment(iter); struct block_device *bdev = inode->i_sb->s_bdev; + if (iov_iter_rw(iter) == READ && offset >= i_size_read(inode)) + return 1; + if (align & blocksize_mask) { if (bdev) blkbits = blksize_bits(bdev_logical_block_size(bdev)); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 3ad7bdbda5ca..cb1b5b61a1da 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -2373,6 +2373,9 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi, if (unlikely(nid >= nm_i->max_nid)) nid = 0; + if (unlikely(nid % NAT_ENTRY_PER_BLOCK)) + nid = NAT_BLOCK_OFFSET(nid) * NAT_ENTRY_PER_BLOCK; + /* Enough entries */ if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK) return 0; diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index a65d357f89a9..e247a5ef3713 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -799,7 +799,7 @@ static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, if (__is_large_section(sbi)) { unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); - unsigned short valid_blocks = + block_t valid_blocks = get_valid_blocks(sbi, segno, true); f2fs_bug_on(sbi, unlikely(!valid_blocks || @@ -815,7 +815,7 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, enum dirty_type dirty_type) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); - unsigned short valid_blocks; + block_t valid_blocks; if (test_and_clear_bit(segno, dirty_i->dirty_segmap[dirty_type])) dirty_i->nr_dirty[dirty_type]--; @@ -4316,8 +4316,8 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi) struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); struct free_segmap_info *free_i = FREE_I(sbi); unsigned int segno = 0, offset = 0, secno; - unsigned short valid_blocks; - unsigned short blks_per_sec = BLKS_PER_SEC(sbi); + block_t valid_blocks; + block_t blks_per_sec = BLKS_PER_SEC(sbi); while (1) { /* find dirty segment based on free segmap */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f8946b9468ef..6e95c85fe395 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3293,8 +3293,10 @@ static int _nfs4_do_setattr(struct inode *inode, /* Servers should only apply open mode checks for file size changes */ truncate = (arg->iap->ia_valid & ATTR_SIZE) ? true : false; - if (!truncate) + if (!truncate) { + nfs4_inode_make_writeable(inode); goto zero_stateid; + } if (nfs4_copy_delegation_stateid(inode, FMODE_WRITE, &arg->stateid, &delegation_cred)) { /* Use that stateid */ @@ -7298,7 +7300,12 @@ int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, err = nfs4_set_lock_state(state, fl); if (err != 0) return err; - err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW); + do { + err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW); + if (err != -NFS4ERR_DELAY) + break; + ssleep(1); + } while (err == -NFS4ERR_DELAY); return nfs4_handle_delegation_recall_error(server, state, stateid, fl, err); } diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index bb4b680e8455..3110c77230c7 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -4,7 +4,6 @@ menu "GCOV-based kernel profiling" config GCOV_KERNEL bool "Enable gcov-based kernel profiling" depends on DEBUG_FS - depends on !CC_IS_GCC || GCC_VERSION < 100000 select CONSTRUCTORS if !UML default n help diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index 908fdf5098c3..53c67c87f141 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -19,7 +19,9 @@ #include <linux/vmalloc.h> #include "gcov.h" -#if (__GNUC__ >= 7) +#if (__GNUC__ >= 10) +#define GCOV_COUNTERS 8 +#elif (__GNUC__ >= 7) #define GCOV_COUNTERS 9 #elif (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1) #define GCOV_COUNTERS 10 diff --git a/kernel/padata.c b/kernel/padata.c index 16cb894dc272..d4d3ba6e1728 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -215,12 +215,13 @@ int padata_do_parallel(struct padata_shell *ps, padata->pd = pd; padata->cb_cpu = *cb_cpu; - rcu_read_unlock_bh(); - spin_lock(&padata_works_lock); padata->seq_nr = ++pd->seq_nr; pw = padata_work_alloc(); spin_unlock(&padata_works_lock); + + rcu_read_unlock_bh(); + if (pw) { padata_work_init(pw, padata_parallel_worker, padata, 0); queue_work(pinst->parallel_wq, &pw->pw_work); diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index c27123e6ba80..4a67685c83eb 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -982,8 +982,8 @@ static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, p = xdr_inline_decode(xdr, len); if (unlikely(p == NULL)) goto out_fail; - dprintk("RPC: %5u RPCB_%s reply: %s\n", req->rq_task->tk_pid, - req->rq_task->tk_msg.rpc_proc->p_name, (char *)p); + dprintk("RPC: %5u RPCB_%s reply: %*pE\n", req->rq_task->tk_pid, + req->rq_task->tk_msg.rpc_proc->p_name, len, (char *)p); if (rpc_uaddr2sockaddr(req->rq_xprt->xprt_net, (char *)p, len, sap, sizeof(address)) == 0) diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 3f86d039875c..ad6e2e4994ce 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -933,6 +933,8 @@ static void rpcrdma_req_reset(struct rpcrdma_req *req) rpcrdma_regbuf_dma_unmap(req->rl_sendbuf); rpcrdma_regbuf_dma_unmap(req->rl_recvbuf); + + frwr_reset(req); } /* ASSUMPTION: the rb_allreqs list is stable for the duration, diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile index 7656c7ce79d9..0e73a16874c4 100644 --- a/tools/testing/selftests/timers/Makefile +++ b/tools/testing/selftests/timers/Makefile @@ -13,6 +13,7 @@ DESTRUCTIVE_TESTS = alarmtimer-suspend valid-adjtimex adjtick change_skew \ TEST_GEN_PROGS_EXTENDED = $(DESTRUCTIVE_TESTS) +TEST_FILES := settings include ../lib.mk diff --git a/tools/testing/selftests/timers/settings b/tools/testing/selftests/timers/settings new file mode 100644 index 000000000000..e7b9417537fb --- /dev/null +++ b/tools/testing/selftests/timers/settings @@ -0,0 +1 @@ +timeout=0 |