9 files changed, 401 insertions, 60 deletions

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_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index d0bdb6d447ed..ef755dd5e68f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -439,29 +439,36 @@ static bool __cancel_engine(struct intel_engine_cs *engine)
 	return __reset_engine(engine);
 }
 
-static struct intel_engine_cs *__active_engine(struct i915_request *rq)
+static bool
+__active_engine(struct i915_request *rq, struct intel_engine_cs **active)
 {
 	struct intel_engine_cs *engine, *locked;
+	bool ret = false;
 
 	/*
 	 * Serialise with __i915_request_submit() so that it sees
 	 * is-banned?, or we know the request is already inflight.
+	 *
+	 * Note that rq->engine is unstable, and so we double
+	 * check that we have acquired the lock on the final engine.
 	 */
 	locked = READ_ONCE(rq->engine);
 	spin_lock_irq(&locked->active.lock);
 	while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
 		spin_unlock(&locked->active.lock);
-		spin_lock(&engine->active.lock);
 		locked = engine;
+		spin_lock(&locked->active.lock);
 	}
 
-	engine = NULL;
-	if (i915_request_is_active(rq) && rq->fence.error != -EIO)
-		engine = rq->engine;
+	if (!i915_request_completed(rq)) {
+		if (i915_request_is_active(rq) && rq->fence.error != -EIO)
+			*active = locked;
+		ret = true;
+	}
 
 	spin_unlock_irq(&locked->active.lock);
 
-	return engine;
+	return ret;
 }
 
 static struct intel_engine_cs *active_engine(struct intel_context *ce)
@@ -472,17 +479,16 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce)
 	if (!ce->timeline)
 		return NULL;
 
-	mutex_lock(&ce->timeline->mutex);
-	list_for_each_entry_reverse(rq, &ce->timeline->requests, link) {
-		if (i915_request_completed(rq))
-			break;
+	rcu_read_lock();
+	list_for_each_entry_rcu(rq, &ce->timeline->requests, link) {
+		if (i915_request_is_active(rq) && i915_request_completed(rq))
+			continue;
 
 		/* Check with the backend if the request is inflight */
-		engine = __active_engine(rq);
-		if (engine)
+		if (__active_engine(rq, &engine))
 			break;
 	}
-	mutex_unlock(&ce->timeline->mutex);
+	rcu_read_unlock();
 
 	return engine;
 }
@@ -713,6 +719,7 @@ __create_context(struct drm_i915_private *i915)
 	ctx->i915 = i915;
 	ctx->sched.priority = I915_USER_PRIORITY(I915_PRIORITY_NORMAL);
 	mutex_init(&ctx->mutex);
+	INIT_LIST_HEAD(&ctx->link);
 
 	spin_lock_init(&ctx->stale.lock);
 	INIT_LIST_HEAD(&ctx->stale.engines);
@@ -740,10 +747,6 @@ __create_context(struct drm_i915_private *i915)
 	for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
 		ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
 
-	spin_lock(&i915->gem.contexts.lock);
-	list_add_tail(&ctx->link, &i915->gem.contexts.list);
-	spin_unlock(&i915->gem.contexts.lock);
-
 	return ctx;
 
 err_free:
@@ -931,6 +934,7 @@ static int gem_context_register(struct i915_gem_context *ctx,
 				struct drm_i915_file_private *fpriv,
 				u32 *id)
 {
+	struct drm_i915_private *i915 = ctx->i915;
 	struct i915_address_space *vm;
 	int ret;
 
@@ -949,8 +953,16 @@ static int gem_context_register(struct i915_gem_context *ctx,
 	/* And finally expose ourselves to userspace via the idr */
 	ret = xa_alloc(&fpriv->context_xa, id, ctx, xa_limit_32b, GFP_KERNEL);
 	if (ret)
-		put_pid(fetch_and_zero(&ctx->pid));
+		goto err_pid;
+
+	spin_lock(&i915->gem.contexts.lock);
+	list_add_tail(&ctx->link, &i915->gem.contexts.list);
+	spin_unlock(&i915->gem.contexts.lock);
+
+	return 0;
 
+err_pid:
+	put_pid(fetch_and_zero(&ctx->pid));
 	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/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 24322ef08aa4..9eeaca957a7e 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2060,6 +2060,14 @@ static inline void clear_ports(struct i915_request **ports, int count)
 	memset_p((void **)ports, NULL, count);
 }
 
+static inline void
+copy_ports(struct i915_request **dst, struct i915_request **src, int count)
+{
+	/* A memcpy_p() would be very useful here! */
+	while (count--)
+		WRITE_ONCE(*dst++, *src++); /* avoid write tearing */
+}
+
 static void execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -2648,10 +2656,9 @@ static void process_csb(struct intel_engine_cs *engine)
 
 			/* switch pending to inflight */
 			GEM_BUG_ON(!assert_pending_valid(execlists, "promote"));
-			memcpy(execlists->inflight,
-			       execlists->pending,
-			       execlists_num_ports(execlists) *
-			       sizeof(*execlists->pending));
+			copy_ports(execlists->inflight,
+				   execlists->pending,
+				   execlists_num_ports(execlists));
 			smp_wmb(); /* complete the seqlock */
 			WRITE_ONCE(execlists->active, execlists->inflight);
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 0b2fe55e6194..781a6783affe 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -388,17 +388,38 @@ static bool __request_in_flight(const struct i915_request *signal)
 	 * As we know that there are always preemption points between
 	 * requests, we know that only the currently executing request
 	 * may be still active even though we have cleared the flag.
-	 * However, we can't rely on our tracking of ELSP[0] to known
+	 * However, we can't rely on our tracking of ELSP[0] to know
 	 * which request is currently active and so maybe stuck, as
 	 * the tracking maybe an event behind. Instead assume that
 	 * if the context is still inflight, then it is still active
 	 * even if the active flag has been cleared.
+	 *
+	 * To further complicate matters, if there a pending promotion, the HW
+	 * may either perform a context switch to the second inflight execlists,
+	 * or it may switch to the pending set of execlists. In the case of the
+	 * latter, it may send the ACK and we process the event copying the
+	 * pending[] over top of inflight[], _overwriting_ our *active. Since
+	 * this implies the HW is arbitrating and not struck in *active, we do
+	 * not worry about complete accuracy, but we do require no read/write
+	 * tearing of the pointer [the read of the pointer must be valid, even
+	 * as the array is being overwritten, for which we require the writes
+	 * to avoid tearing.]
+	 *
+	 * Note that the read of *execlists->active may race with the promotion
+	 * of execlists->pending[] to execlists->inflight[], overwritting
+	 * the value at *execlists->active. This is fine. The promotion implies
+	 * that we received an ACK from the HW, and so the context is not
+	 * stuck -- if we do not see ourselves in *active, the inflight status
+	 * is valid. If instead we see ourselves being copied into *active,
+	 * we are inflight and may signal the callback.
 	 */
 	if (!intel_context_inflight(signal->context))
 		return false;
 
 	rcu_read_lock();
-	for (port = __engine_active(signal->engine); (rq = *port); port++) {
+	for (port = __engine_active(signal->engine);
+	     (rq = READ_ONCE(*port)); /* may race with promotion of pending[] */
+	     port++) {
 		if (rq->context == signal->context) {
 			inflight = i915_seqno_passed(rq->fence.seqno,
 						     signal->fence.seqno);
diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c
index 295b9829e2da..4cd2038cbe35 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence.c
@@ -164,9 +164,13 @@ static void __i915_sw_fence_wake_up_all(struct i915_sw_fence *fence,
 
 		do {
 			list_for_each_entry_safe(pos, next, &x->head, entry) {
-				pos->func(pos,
-					  TASK_NORMAL, fence->error,
-					  &extra);
+				int wake_flags;
+
+				wake_flags = fence->error;
+				if (pos->func == autoremove_wake_function)
+					wake_flags = 0;
+
+				pos->func(pos, TASK_NORMAL, wake_flags, &extra);
 			}
 
 			if (list_empty(&extra))