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-& |