1 files changed, 122 insertions, 70 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 87a3227e5179..bf345777ae9f 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -172,9 +172,60 @@ static inline int use_cpu_reloc(struct drm_i915_gem_object *obj)
 }
 
 static int
+relocate_entry_cpu(struct drm_i915_gem_object *obj,
+		   struct drm_i915_gem_relocation_entry *reloc)
+{
+	uint32_t page_offset = offset_in_page(reloc->offset);
+	char *vaddr;
+	int ret = -EINVAL;
+
+	ret = i915_gem_object_set_to_cpu_domain(obj, 1);
+	if (ret)
+		return ret;
+
+	vaddr = kmap_atomic(i915_gem_object_get_page(obj,
+				reloc->offset >> PAGE_SHIFT));
+	*(uint32_t *)(vaddr + page_offset) = reloc->delta;
+	kunmap_atomic(vaddr);
+
+	return 0;
+}
+
+static int
+relocate_entry_gtt(struct drm_i915_gem_object *obj,
+		   struct drm_i915_gem_relocation_entry *reloc)
+{
+	struct drm_device *dev = obj->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	uint32_t __iomem *reloc_entry;
+	void __iomem *reloc_page;
+	int ret = -EINVAL;
+
+	ret = i915_gem_object_set_to_gtt_domain(obj, true);
+	if (ret)
+		return ret;
+
+	ret = i915_gem_object_put_fence(obj);
+	if (ret)
+		return ret;
+
+	/* Map the page containing the relocation we're going to perform.  */
+	reloc->offset += i915_gem_obj_ggtt_offset(obj);
+	reloc_page = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
+			reloc->offset & PAGE_MASK);
+	reloc_entry = (uint32_t __iomem *)
+		(reloc_page + offset_in_page(reloc->offset));
+	iowrite32(reloc->delta, reloc_entry);
+	io_mapping_unmap_atomic(reloc_page);
+
+	return 0;
+}
+
+static int
 i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 				   struct eb_objects *eb,
-				   struct drm_i915_gem_relocation_entry *reloc)
+				   struct drm_i915_gem_relocation_entry *reloc,
+				   struct i915_address_space *vm)
 {
 	struct drm_device *dev = obj->base.dev;
 	struct drm_gem_object *target_obj;
@@ -188,7 +239,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 		return -ENOENT;
 
 	target_i915_obj = to_intel_bo(target_obj);
-	target_offset = target_i915_obj->gtt_offset;
+	target_offset = i915_gem_obj_ggtt_offset(target_i915_obj);
 
 	/* Sandybridge PPGTT errata: We need a global gtt mapping for MI and
 	 * pipe_control writes because the gpu doesn't properly redirect them
@@ -254,40 +305,13 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 		return -EFAULT;
 
 	reloc->delta += target_offset;
-	if (use_cpu_reloc(obj)) {
-		uint32_t page_offset = reloc->offset & ~PAGE_MASK;
-		char *vaddr;
-
-		ret = i915_gem_object_set_to_cpu_domain(obj, 1);
-		if (ret)
-			return ret;
-
-		vaddr = kmap_atomic(i915_gem_object_get_page(obj,
-							     reloc->offset >> PAGE_SHIFT));
-		*(uint32_t *)(vaddr + page_offset) = reloc->delta;
-		kunmap_atomic(vaddr);
-	} else {
-		struct drm_i915_private *dev_priv = dev->dev_private;
-		uint32_t __iomem *reloc_entry;
-		void __iomem *reloc_page;
-
-		ret = i915_gem_object_set_to_gtt_domain(obj, true);
-		if (ret)
-			return ret;
-
-		ret = i915_gem_object_put_fence(obj);
-		if (ret)
-			return ret;
+	if (use_cpu_reloc(obj))
+		ret = relocate_entry_cpu(obj, reloc);
+	else
+		ret = relocate_entry_gtt(obj, reloc);
 
-		/* Map the page containing the relocation we're going to perform.  */
-		reloc->offset += obj->gtt_offset;
-		reloc_page = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
-						      reloc->offset & PAGE_MASK);
-		reloc_entry = (uint32_t __iomem *)
-			(reloc_page + (reloc->offset & ~PAGE_MASK));
-		iowrite32(reloc->delta, reloc_entry);
-		io_mapping_unmap_atomic(reloc_page);
-	}
+	if (ret)
+		return ret;
 
 	/* and update the user's relocation entry */
 	reloc->presumed_offset = target_offset;
@@ -297,7 +321,8 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 
 static int
 i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj,
-				    struct eb_objects *eb)
+				    struct eb_objects *eb,
+				    struct i915_address_space *vm)
 {
 #define N_RELOC(x) ((x) / sizeof(struct drm_i915_gem_relocation_entry))
 	struct drm_i915_gem_relocation_entry stack_reloc[N_RELOC(512)];
@@ -321,7 +346,8 @@ i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj,
 		do {
 			u64 offset = r->presumed_offset;
 
-			ret = i915_gem_execbuffer_relocate_entry(obj, eb, r);
+			ret = i915_gem_execbuffer_relocate_entry(obj, eb, r,
+								 vm);
 			if (ret)
 				return ret;
 
@@ -344,13 +370,15 @@ i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj,
 static int
 i915_gem_execbuffer_relocate_object_slow(struct drm_i915_gem_object *obj,
 					 struct eb_objects *eb,
-					 struct drm_i915_gem_relocation_entry *relocs)
+					 struct drm_i915_gem_relocation_entry *relocs,
+					 struct i915_address_space *vm)
 {
 	const struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
 	int i, ret;
 
 	for (i = 0; i < entry->relocation_count; i++) {
-		ret = i915_gem_execbuffer_relocate_entry(obj, eb, &relocs[i]);
+		ret = i915_gem_execbuffer_relocate_entry(obj, eb, &relocs[i],
+							 vm);
 		if (ret)
 			return ret;
 	}
@@ -359,7 +387,8 @@ i915_gem_execbuffer_relocate_object_slow(struct drm_i915_gem_object *obj,
 }
 
 static int
-i915_gem_execbuffer_relocate(struct eb_objects *eb)
+i915_gem_execbuffer_relocate(struct eb_objects *eb,
+			     struct i915_address_space *vm)
 {
 	struct drm_i915_gem_object *obj;
 	int ret = 0;
@@ -373,7 +402,7 @@ i915_gem_execbuffer_relocate(struct eb_objects *eb)
 	 */
 	pagefault_disable();
 	list_for_each_entry(obj, &eb->objects, exec_list) {
-		ret = i915_gem_execbuffer_relocate_object(obj, eb);
+		ret = i915_gem_execbuffer_relocate_object(obj, eb, vm);
 		if (ret)
 			break;
 	}
@@ -395,6 +424,7 @@ need_reloc_mappable(struct drm_i915_gem_object *obj)
 static int
 i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj,
 				   struct intel_ring_buffer *ring,
+				   struct i915_address_space *vm,
 				   bool *need_reloc)
 {
 	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
@@ -409,7 +439,8 @@ i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj,
 		obj->tiling_mode != I915_TILING_NONE;
 	need_mappable = need_fence || need_reloc_mappable(obj);
 
-	ret = i915_gem_object_pin(obj, entry->alignment, need_mappable, false);
+	ret = i915_gem_object_pin(obj, vm, entry->alignment, need_mappable,
+				  false);
 	if (ret)
 		return ret;
 
@@ -436,8 +467,8 @@ i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj,
 		obj->has_aliasing_ppgtt_mapping = 1;
 	}
 
-	if (entry->offset != obj->gtt_offset) {
-		entry->offset = obj->gtt_offset;
+	if (entry->offset != i915_gem_obj_offset(obj, vm)) {
+		entry->offset = i915_gem_obj_offset(obj, vm);
 		*need_reloc = true;
 	}
 
@@ -458,7 +489,7 @@ i915_gem_execbuffer_unreserve_object(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_gem_exec_object2 *entry;
 
-	if (!obj->gtt_space)
+	if (!i915_gem_obj_bound_any(obj))
 		return;
 
 	entry = obj->exec_entry;
@@ -475,6 +506,7 @@ i915_gem_execbuffer_unreserve_object(struct drm_i915_gem_object *obj)
 static int
 i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 			    struct list_head *objects,
+			    struct i915_address_space *vm,
 			    bool *need_relocs)
 {
 	struct drm_i915_gem_object *obj;
@@ -529,31 +561,37 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 		list_for_each_entry(obj, objects, exec_list) {
 			struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
 			bool need_fence, need_mappable;
+			u32 obj_offset;
 
-			if (!obj->gtt_space)
+			if (!i915_gem_obj_bound(obj, vm))
 				continue;
 
+			obj_offset = i915_gem_obj_offset(obj, vm);
 			need_fence =
 				has_fenced_gpu_access &&
 				entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
 				obj->tiling_mode != I915_TILING_NONE;
 			need_mappable = need_fence || need_reloc_mappable(obj);
 
-			if ((entry->alignment && obj->gtt_offset & (entry->alignment - 1)) ||
+			WARN_ON((need_mappable || need_fence) &&
+				!i915_is_ggtt(vm));
+
+			if ((entry->alignment &&
+			     obj_offset & (entry->alignment - 1)) ||
 			    (need_mappable && !obj->map_and_fenceable))
-				ret = i915_gem_object_unbind(obj);
+				ret = i915_vma_unbind(i915_gem_obj_to_vma(obj, vm));
 			else
-				ret = i915_gem_execbuffer_reserve_object(obj, ring, need_relocs);
+				ret = i915_gem_execbuffer_reserve_object(obj, ring, vm, need_relocs);
 			if (ret)
 				goto err;
 		}
 
 		/* Bind fresh objects */
 		list_for_each_entry(obj, objects, exec_list) {
-			if (obj->gtt_space)
+			if (i915_gem_obj_bound(obj, vm))
 				continue;
 
-			ret = i915_gem_execbuffer_reserve_object(obj, ring, need_relocs);
+			ret = i915_gem_execbuffer_reserve_object(obj, ring, vm, need_relocs);
 			if (ret)
 				goto err;
 		}
@@ -577,7 +615,8 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 				  struct drm_file *file,
 				  struct intel_ring_buffer *ring,
 				  struct eb_objects *eb,
-				  struct drm_i915_gem_exec_object2 *exec)
+				  struct drm_i915_gem_exec_object2 *exec,
+				  struct i915_address_space *vm)
 {
 	struct drm_i915_gem_relocation_entry *reloc;
 	struct drm_i915_gem_object *obj;
@@ -661,14 +700,15 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 		goto err;
 
 	need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0;
-	ret = i915_gem_execbuffer_reserve(ring, &eb->objects, &need_relocs);
+	ret = i915_gem_execbuffer_reserve(ring, &eb->objects, vm, &need_relocs);
 	if (ret)
 		goto err;
 
 	list_for_each_entry(obj, &eb->objects, exec_list) {
 		int offset = obj->exec_entry - exec;
 		ret = i915_gem_execbuffer_relocate_object_slow(obj, eb,
-							       reloc + reloc_offset[offset]);
+							       reloc + reloc_offset[offset],
+							       vm);
 		if (ret)
 			goto err;
 	}
@@ -691,6 +731,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring,
 {
 	struct drm_i915_gem_object *obj;
 	uint32_t flush_domains = 0;
+	bool flush_chipset = false;
 	int ret;
 
 	list_for_each_entry(obj, objects, exec_list) {
@@ -699,12 +740,12 @@ i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring,
 			return ret;
 
 		if (obj->base.write_domain & I915_GEM_DOMAIN_CPU)
-			i915_gem_clflush_object(obj);
+			flush_chipset |= i915_gem_clflush_object(obj, false);
 
 		flush_domains |= obj->base.write_domain;
 	}
 
-	if (flush_domains & I915_GEM_DOMAIN_CPU)
+	if (flush_chipset)
 		i915_gem_chipset_flush(ring->dev);
 
 	if (flush_domains & I915_GEM_DOMAIN_GTT)
@@ -758,8 +799,10 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec,
 		if (!access_ok(VERIFY_WRITE, ptr, length))
 			return -EFAULT;
 
-		if (fault_in_multipages_readable(ptr, length))
-			return -EFAULT;
+		if (likely(!i915_prefault_disable)) {
+			if (fault_in_multipages_readable(ptr, length))
+				return -EFAULT;
+		}
 	}
 
 	return 0;
@@ -767,6 +810,7 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec,
 
 static void
 i915_gem_execbuffer_move_to_active(struct list_head *objects,
+				   struct i915_address_space *vm,
 				   struct intel_ring_buffer *ring)
 {
 	struct drm_i915_gem_object *obj;
@@ -781,6 +825,8 @@ i915_gem_execbuffer_move_to_active(struct list_head *objects,
 		obj->base.read_domains = obj->base.pending_read_domains;
 		obj->fenced_gpu_access = obj->pending_fenced_gpu_access;
 
+		/* FIXME: This lookup gets fixed later <-- danvet */
+		list_move_tail(&i915_gem_obj_to_vma(obj, vm)->mm_list, &vm->active_list);
 		i915_gem_object_move_to_active(obj, ring);
 		if (obj->base.write_domain) {
 			obj->dirty = 1;
@@ -835,7 +881,8 @@ static int
 i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		       struct drm_file *file,
 		       struct drm_i915_gem_execbuffer2 *args,
-		       struct drm_i915_gem_exec_object2 *exec)
+		       struct drm_i915_gem_exec_object2 *exec,
+		       struct i915_address_space *vm)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct eb_objects *eb;
@@ -872,7 +919,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		break;
 	case I915_EXEC_BSD:
 		ring = &dev_priv->ring[VCS];
-		if (ctx_id != 0) {
+		if (ctx_id != DEFAULT_CONTEXT_ID) {
 			DRM_DEBUG("Ring %s doesn't support contexts\n",
 				  ring->name);
 			return -EPERM;
@@ -880,7 +927,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		break;
 	case I915_EXEC_BLT:
 		ring = &dev_priv->ring[BCS];
-		if (ctx_id != 0) {
+		if (ctx_id != DEFAULT_CONTEXT_ID) {
 			DRM_DEBUG("Ring %s doesn't support contexts\n",
 				  ring->name);
 			return -EPERM;
@@ -888,7 +935,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		break;
 	case I915_EXEC_VEBOX:
 		ring = &dev_priv->ring[VECS];
-		if (ctx_id != 0) {
+		if (ctx_id != DEFAULT_CONTEXT_ID) {
 			DRM_DEBUG("Ring %s doesn't support contexts\n",
 				  ring->name);
 			return -EPERM;
@@ -972,7 +1019,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	if (ret)
 		goto pre_mutex_err;
 
-	if (dev_priv->mm.suspended) {
+	if (dev_priv->ums.mm_suspended) {
 		mutex_unlock(&dev->struct_mutex);
 		ret = -EBUSY;
 		goto pre_mutex_err;
@@ -997,17 +1044,17 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 
 	/* Move the objects en-masse into the GTT, evicting if necessary. */
 	need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0;
-	ret = i915_gem_execbuffer_reserve(ring, &eb->objects, &need_relocs);
+	ret = i915_gem_execbuffer_reserve(ring, &eb->objects, vm, &need_relocs);
 	if (ret)
 		goto err;
 
 	/* The objects are in their final locations, apply the relocations. */
 	if (need_relocs)
-		ret = i915_gem_execbuffer_relocate(eb);
+		ret = i915_gem_execbuffer_relocate(eb, vm);
 	if (ret) {
 		if (ret == -EFAULT) {
 			ret = i915_gem_execbuffer_relocate_slow(dev, args, file, ring,
-								eb, exec);
+								eb, exec, vm);
 			BUG_ON(!mutex_is_locked(&dev->struct_mutex));
 		}
 		if (ret)
@@ -1058,7 +1105,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 			goto err;
 	}
 
-	exec_start = batch_obj->gtt_offset + args->batch_start_offset;
+	exec_start = i915_gem_obj_offset(batch_obj, vm) +
+		args->batch_start_offset;
 	exec_len = args->batch_len;
 	if (cliprects) {
 		for (i = 0; i < args->num_cliprects; i++) {
@@ -1083,7 +1131,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 
 	trace_i915_gem_ring_dispatch(ring, intel_ring_get_seqno(ring), flags);
 
-	i915_gem_execbuffer_move_to_active(&eb->objects, ring);
+	i915_gem_execbuffer_move_to_active(&eb->objects, vm, ring);
 	i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
 
 err:
@@ -1104,6 +1152,7 @@ int
 i915_gem_execbuffer(struct drm_device *dev, void *data,
 		    struct drm_file *file)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_execbuffer *args = data;
 	struct drm_i915_gem_execbuffer2 exec2;
 	struct drm_i915_gem_exec_object *exec_list = NULL;
@@ -1159,7 +1208,8 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
 	exec2.flags = I915_EXEC_RENDER;
 	i915_execbuffer2_set_context_id(exec2, 0);
 
-	ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list);
+	ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list,
+				     &dev_priv->gtt.base);
 	if (!ret) {
 		/* Copy the new buffer offsets back to the user's exec list. */
 		for (i = 0; i < args->buffer_count; i++)
@@ -1185,6 +1235,7 @@ int
 i915_gem_execbuffer2(struct drm_device *dev, void *data,
 		     struct drm_file *file)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_execbuffer2 *args = data;
 	struct drm_i915_gem_exec_object2 *exec2_list = NULL;
 	int ret;
@@ -1215,7 +1266,8 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 		return -EFAULT;
 	}
 
-	ret = i915_gem_do_execbuffer(dev, data, file, args, exec2_list);
+	ret = i915_gem_do_execbuffer(dev, data, file, args, exec2_list,
+				     &dev_priv->gtt.base);
 	if (!ret) {
 		/* Copy the new buffer offsets back to the user's exec list. */
 		ret = copy_to_user(to_user_ptr(args->buffers_ptr),