1 files changed, 245 insertions, 93 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 9e35dafc5807..d9e2208cfe98 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -176,7 +176,7 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 
 	pinned = 0;
 	mutex_lock(&dev->struct_mutex);
-	list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list)
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list)
 		if (obj->pin_count)
 			pinned += obj->gtt_space->size;
 	mutex_unlock(&dev->struct_mutex);
@@ -956,7 +956,7 @@ i915_gem_check_olr(struct intel_ring_buffer *ring, u32 seqno)
 
 	ret = 0;
 	if (seqno == ring->outstanding_lazy_request)
-		ret = i915_add_request(ring, NULL, NULL);
+		ret = i915_add_request(ring, NULL);
 
 	return ret;
 }
@@ -1087,6 +1087,25 @@ i915_wait_seqno(struct intel_ring_buffer *ring, uint32_t seqno)
 			    interruptible, NULL);
 }
 
+static int
+i915_gem_object_wait_rendering__tail(struct drm_i915_gem_object *obj,
+				     struct intel_ring_buffer *ring)
+{
+	i915_gem_retire_requests_ring(ring);
+
+	/* Manually manage the write flush as we may have not yet
+	 * retired the buffer.
+	 *
+	 * Note that the last_write_seqno is always the earlier of
+	 * the two (read/write) seqno, so if we haved successfully waited,
+	 * we know we have passed the last write.
+	 */
+	obj->last_write_seqno = 0;
+	obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS;
+
+	return 0;
+}
+
 /**
  * Ensures that all rendering to the object has completed and the object is
  * safe to unbind from the GTT or access from the CPU.
@@ -1107,18 +1126,7 @@ i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj,
 	if (ret)
 		return ret;
 
-	i915_gem_retire_requests_ring(ring);
-
-	/* Manually manage the write flush as we may have not yet
-	 * retired the buffer.
-	 */
-	if (obj->last_write_seqno &&
-	    i915_seqno_passed(seqno, obj->last_write_seqno)) {
-		obj->last_write_seqno = 0;
-		obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS;
-	}
-
-	return 0;
+	return i915_gem_object_wait_rendering__tail(obj, ring);
 }
 
 /* A nonblocking variant of the above wait. This is a highly dangerous routine
@@ -1154,19 +1162,10 @@ i915_gem_object_wait_rendering__nonblocking(struct drm_i915_gem_object *obj,
 	mutex_unlock(&dev->struct_mutex);
 	ret = __wait_seqno(ring, seqno, reset_counter, true, NULL);
 	mutex_lock(&dev->struct_mutex);
+	if (ret)
+		return ret;
 
-	i915_gem_retire_requests_ring(ring);
-
-	/* Manually manage the write flush as we may have not yet
-	 * retired the buffer.
-	 */
-	if (obj->last_write_seqno &&
-	    i915_seqno_passed(seqno, obj->last_write_seqno)) {
-		obj->last_write_seqno = 0;
-		obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS;
-	}
-
-	return ret;
+	return i915_gem_object_wait_rendering__tail(obj, ring);
 }
 
 /**
@@ -1676,7 +1675,7 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
 	/* ->put_pages might need to allocate memory for the bit17 swizzle
 	 * array, hence protect them from being reaped by removing them from gtt
 	 * lists early. */
-	list_del(&obj->gtt_list);
+	list_del(&obj->global_list);
 
 	ops->put_pages(obj);
 	obj->pages = NULL;
@@ -1696,7 +1695,7 @@ __i915_gem_shrink(struct drm_i915_private *dev_priv, long target,
 
 	list_for_each_entry_safe(obj, next,
 				 &dev_priv->mm.unbound_list,
-				 gtt_list) {
+				 global_list) {
 		if ((i915_gem_object_is_purgeable(obj) || !purgeable_only) &&
 		    i915_gem_object_put_pages(obj) == 0) {
 			count += obj->base.size >> PAGE_SHIFT;
@@ -1733,7 +1732,8 @@ i915_gem_shrink_all(struct drm_i915_private *dev_priv)
 
 	i915_gem_evict_everything(dev_priv->dev);
 
-	list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, gtt_list)
+	list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list,
+				 global_list)
 		i915_gem_object_put_pages(obj);
 }
 
@@ -1867,7 +1867,7 @@ i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
 	if (ret)
 		return ret;
 
-	list_add_tail(&obj->gtt_list, &dev_priv->mm.unbound_list);
+	list_add_tail(&obj->global_list, &dev_priv->mm.unbound_list);
 	return 0;
 }
 
@@ -1880,6 +1880,10 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
 	u32 seqno = intel_ring_get_seqno(ring);
 
 	BUG_ON(ring == NULL);
+	if (obj->ring != ring && obj->last_write_seqno) {
+		/* Keep the seqno relative to the current ring */
+		obj->last_write_seqno = seqno;
+	}
 	obj->ring = ring;
 
 	/* Add a reference if we're newly entering the active list. */
@@ -2005,17 +2009,18 @@ i915_gem_get_seqno(struct drm_device *dev, u32 *seqno)
 	return 0;
 }
 
-int
-i915_add_request(struct intel_ring_buffer *ring,
-		 struct drm_file *file,
-		 u32 *out_seqno)
+int __i915_add_request(struct intel_ring_buffer *ring,
+		       struct drm_file *file,
+		       struct drm_i915_gem_object *obj,
+		       u32 *out_seqno)
 {
 	drm_i915_private_t *dev_priv = ring->dev->dev_private;
 	struct drm_i915_gem_request *request;
-	u32 request_ring_position;
+	u32 request_ring_position, request_start;
 	int was_empty;
 	int ret;
 
+	request_start = intel_ring_get_tail(ring);
 	/*
 	 * Emit any outstanding flushes - execbuf can fail to emit the flush
 	 * after having emitted the batchbuffer command. Hence we need to fix
@@ -2047,7 +2052,21 @@ i915_add_request(struct intel_ring_buffer *ring,
 
 	request->seqno = intel_ring_get_seqno(ring);
 	request->ring = ring;
+	request->head = request_start;
 	request->tail = request_ring_position;
+	request->ctx = ring->last_context;
+	request->batch_obj = obj;
+
+	/* Whilst this request exists, batch_obj will be on the
+	 * active_list, and so will hold the active reference. Only when this
+	 * request is retired will the the batch_obj be moved onto the
+	 * inactive_list and lose its active reference. Hence we do not need
+	 * to explicitly hold another reference here.
+	 */
+
+	if (request->ctx)
+		i915_gem_context_reference(request->ctx);
+
 	request->emitted_jiffies = jiffies;
 	was_empty = list_empty(&ring->request_list);
 	list_add_tail(&request->list, &ring->request_list);
@@ -2100,9 +2119,114 @@ i915_gem_request_remove_from_client(struct drm_i915_gem_request *request)
 	spin_unlock(&file_priv->mm.lock);
 }
 
+static bool i915_head_inside_object(u32 acthd, struct drm_i915_gem_object *obj)
+{
+	if (acthd >= obj->gtt_offset &&
+	    acthd < obj->gtt_offset + obj->base.size)
+		return true;
+
+	return false;
+}
+
+static bool i915_head_inside_request(const u32 acthd_unmasked,
+				     const u32 request_start,
+				     const u32 request_end)
+{
+	const u32 acthd = acthd_unmasked & HEAD_ADDR;
+
+	if (request_start < request_end) {
+		if (acthd >= request_start && acthd < request_end)
+			return true;
+	} else if (request_start > request_end) {
+		if (acthd >= request_start || acthd < request_end)
+			return true;
+	}
+
+	return false;
+}
+
+static bool i915_request_guilty(struct drm_i915_gem_request *request,
+				const u32 acthd, bool *inside)
+{
+	/* There is a possibility that unmasked head address
+	 * pointing inside the ring, matches the batch_obj address range.
+	 * However this is extremely unlikely.
+	 */
+
+	if (request->batch_obj) {
+		if (i915_head_inside_object(acthd, request->batch_obj)) {
+			*inside = true;
+			return true;
+		}
+	}
+
+	if (i915_head_inside_request(acthd, request->head, request->tail)) {
+		*inside = false;
+		return true;
+	}
+
+	return false;
+}
+
+static void i915_set_reset_status(struct intel_ring_buffer *ring,
+				  struct drm_i915_gem_request *request,
+				  u32 acthd)
+{
+	struct i915_ctx_hang_stats *hs = NULL;
+	bool inside, guilty;
+
+	/* Innocent until proven guilty */
+	guilty = false;
+
+	if (ring->hangcheck.action != wait &&
+	    i915_request_guilty(request, acthd, &inside)) {
+		DRM_ERROR("%s hung %s bo (0x%x ctx %d) at 0x%x\n",
+			  ring->name,
+			  inside ? "inside" : "flushing",
+			  request->batch_obj ?
+			  request->batch_obj->gtt_offset : 0,
+			  request->ctx ? request->ctx->id : 0,
+			  acthd);
+
+		guilty = true;
+	}
+
+	/* If contexts are disabled or this is the default context, use
+	 * file_priv->reset_state
+	 */
+	if (request->ctx && request->ctx->id != DEFAULT_CONTEXT_ID)
+		hs = &request->ctx->hang_stats;
+	else if (request->file_priv)
+		hs = &request->file_priv->hang_stats;
+
+	if (hs) {
+		if (guilty)
+			hs->batch_active++;
+		else
+			hs->batch_pending++;
+	}
+}
+
+static void i915_gem_free_request(struct drm_i915_gem_request *request)
+{
+	list_del(&request->list);
+	i915_gem_request_remove_from_client(request);
+
+	if (request->ctx)
+		i915_gem_context_unreference(request->ctx);
+
+	kfree(request);
+}
+
 static void i915_gem_reset_ring_lists(struct drm_i915_private *dev_priv,
 				      struct intel_ring_buffer *ring)
 {
+	u32 completed_seqno;
+	u32 acthd;
+
+	acthd = intel_ring_get_active_head(ring);
+	completed_seqno = ring->get_seqno(ring, false);
+
 	while (!list_empty(&ring->request_list)) {
 		struct drm_i915_gem_request *request;
 
@@ -2110,9 +2234,10 @@ static void i915_gem_reset_ring_lists(struct drm_i915_private *dev_priv,
 					   struct drm_i915_gem_request,
 					   list);
 
-		list_del(&request->list);
-		i915_gem_request_remove_from_client(request);
-		kfree(request);
+		if (request->seqno > completed_seqno)
+			i915_set_reset_status(ring, request, acthd);
+
+		i915_gem_free_request(request);
 	}
 
 	while (!list_empty(&ring->active_list)) {
@@ -2133,7 +2258,17 @@ void i915_gem_restore_fences(struct drm_device *dev)
 
 	for (i = 0; i < dev_priv->num_fence_regs; i++) {
 		struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i];
-		i915_gem_write_fence(dev, i, reg->obj);
+
+		/*
+		 * Commit delayed tiling changes if we have an object still
+		 * attached to the fence, otherwise just clear the fence.
+		 */
+		if (reg->obj) {
+			i915_gem_object_update_fence(reg->obj, reg,
+						     reg->obj->tiling_mode);
+		} else {
+			i915_gem_write_fence(dev, i, NULL);
+		}
 	}
 }
 
@@ -2193,9 +2328,7 @@ i915_gem_retire_requests_ring(struct intel_ring_buffer *ring)
 		 */
 		ring->last_retired_head = request->tail;
 
-		list_del(&request->list);
-		i915_gem_request_remove_from_client(request);
-		kfree(request);
+		i915_gem_free_request(request);
 	}
 
 	/* Move any buffers on the active list that are no longer referenced
@@ -2262,7 +2395,7 @@ i915_gem_retire_work_handler(struct work_struct *work)
 	idle = true;
 	for_each_ring(ring, dev_priv, i) {
 		if (ring->gpu_caches_dirty)
-			i915_add_request(ring, NULL, NULL);
+			i915_add_request(ring, NULL);
 
 		idle &= list_empty(&ring->request_list);
 	}
@@ -2494,9 +2627,10 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj)
 		obj->has_aliasing_ppgtt_mapping = 0;
 	}
 	i915_gem_gtt_finish_object(obj);
+	i915_gem_object_unpin_pages(obj);
 
 	list_del(&obj->mm_list);
-	list_move_tail(&obj->gtt_list, &dev_priv->mm.unbound_list);
+	list_move_tail(&obj->global_list, &dev_priv->mm.unbound_list);
 	/* Avoid an unnecessary call to unbind on rebind. */
 	obj->map_and_fenceable = true;
 
@@ -2533,7 +2667,6 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	int fence_reg;
 	int fence_pitch_shift;
-	uint64_t val;
 
 	if (INTEL_INFO(dev)->gen >= 6) {
 		fence_reg = FENCE_REG_SANDYBRIDGE_0;
@@ -2543,8 +2676,23 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
 		fence_pitch_shift = I965_FENCE_PITCH_SHIFT;
 	}
 
+	fence_reg += reg * 8;
+
+	/* To w/a incoherency with non-atomic 64-bit register updates,
+	 * we split the 64-bit update into two 32-bit writes. In order
+	 * for a partial fence not to be evaluated between writes, we
+	 * precede the update with write to turn off the fence register,
+	 * and only enable the fence as the last step.
+	 *
+	 * For extra levels of paranoia, we make sure each step lands
+	 * before applying the next step.
+	 */
+	I915_WRITE(fence_reg, 0);
+	POSTING_READ(fence_reg);
+
 	if (obj) {
 		u32 size = obj->gtt_space->size;
+		uint64_t val;
 
 		val = (uint64_t)((obj->gtt_offset + size - 4096) &
 				 0xfffff000) << 32;
@@ -2553,12 +2701,16 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
 		if (obj->tiling_mode == I915_TILING_Y)
 			val |= 1 << I965_FENCE_TILING_Y_SHIFT;
 		val |= I965_FENCE_REG_VALID;
-	} else
-		val = 0;
 
-	fence_reg += reg * 8;
-	I915_WRITE64(fence_reg, val);
-	POSTING_READ(fence_reg);
+		I915_WRITE(fence_reg + 4, val >> 32);
+		POSTING_READ(fence_reg + 4);
+
+		I915_WRITE(fence_reg + 0, val);
+		POSTING_READ(fence_reg);
+	} else {
+		I915_WRITE(fence_reg + 4, 0);
+		POSTING_READ(fence_reg + 4);
+	}
 }
 
 static void i915_write_fence_reg(struct drm_device *dev, int reg,
@@ -2653,6 +2805,10 @@ static void i915_gem_write_fence(struct drm_device *dev, int reg,
 	if (i915_gem_object_needs_mb(dev_priv->fence_regs[reg].obj))
 		mb();
 
+	WARN(obj && (!obj->stride || !obj->tiling_mode),
+	     "bogus fence setup with stride: 0x%x, tiling mode: %i\n",
+	     obj->stride, obj->tiling_mode);
+
 	switch (INTEL_INFO(dev)->gen) {
 	case 7:
 	case 6:
@@ -2676,35 +2832,17 @@ static inline int fence_number(struct drm_i915_private *dev_priv,
 	return fence - dev_priv->fence_regs;
 }
 
-static void i915_gem_write_fence__ipi(void *data)
-{
-	wbinvd();
-}
-
 static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj,
 					 struct drm_i915_fence_reg *fence,
 					 bool enable)
 {
-	struct drm_device *dev = obj->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int fence_reg = fence_number(dev_priv, fence);
-
-	/* In order to fully serialize access to the fenced region and
-	 * the update to the fence register we need to take extreme
-	 * measures on SNB+. In theory, the write to the fence register
-	 * flushes all memory transactions before, and coupled with the
-	 * mb() placed around the register write we serialise all memory
-	 * operations with respect to the changes in the tiler. Yet, on
-	 * SNB+ we need to take a step further and emit an explicit wbinvd()
-	 * on each processor in order to manually flush all memory
-	 * transactions before updating the fence register.
-	 */
-	if (HAS_LLC(obj->base.dev))
-		on_each_cpu(i915_gem_write_fence__ipi, NULL, 1);
-	i915_gem_write_fence(dev, fence_reg, enable ? obj : NULL);
+	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+	int reg = fence_number(dev_priv, fence);
+
+	i915_gem_write_fence(obj->base.dev, reg, enable ? obj : NULL);
 
 	if (enable) {
-		obj->fence_reg = fence_reg;
+		obj->fence_reg = reg;
 		fence->obj = obj;
 		list_move_tail(&fence->lru_list, &dev_priv->mm.fence_list);
 	} else {
@@ -2712,6 +2850,7 @@ static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj,
 		fence->obj = NULL;
 		list_del_init(&fence->lru_list);
 	}
+	obj->fence_dirty = false;
 }
 
 static int
@@ -2841,7 +2980,6 @@ i915_gem_object_get_fence(struct drm_i915_gem_object *obj)
 		return 0;
 
 	i915_gem_object_update_fence(obj, reg, enable);
-	obj->fence_dirty = false;
 
 	return 0;
 }
@@ -2883,7 +3021,7 @@ static void i915_gem_verify_gtt(struct drm_device *dev)
 	struct drm_i915_gem_object *obj;
 	int err = 0;
 
-	list_for_each_entry(obj, &dev_priv->mm.gtt_list, gtt_list) {
+	list_for_each_entry(obj, &dev_priv->mm.gtt_list, global_list) {
 		if (obj->gtt_space == NULL) {
 			printk(KERN_ERR "object found on GTT list with no space reserved\n");
 			err++;
@@ -2930,6 +3068,8 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 	struct drm_mm_node *node;
 	u32 size, fence_size, fence_alignment, unfenced_alignment;
 	bool mappable, fenceable;
+	size_t gtt_max = map_and_fenceable ?
+		dev_priv->gtt.mappable_end : dev_priv->gtt.total;
 	int ret;
 
 	fence_size = i915_gem_get_gtt_size(dev,
@@ -2956,9 +3096,11 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 	/* If the object is bigger than the entire aperture, reject it early
 	 * before evicting everything in a vain attempt to find space.
 	 */
-	if (obj->base.size >
-	    (map_and_fenceable ? dev_priv->gtt.mappable_end : dev_priv->gtt.total)) {
-		DRM_ERROR("Attempting to bind an object larger than the aperture\n");
+	if (obj->base.size > gtt_max) {
+		DRM_ERROR("Attempting to bind an object larger than the aperture: object=%zd > %s aperture=%zu\n",
+			  obj->base.size,
+			  map_and_fenceable ? "mappable" : "total",
+			  gtt_max);
 		return -E2BIG;
 	}
 
@@ -2974,14 +3116,10 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 		return -ENOMEM;
 	}
 
- search_free:
-	if (map_and_fenceable)
-		ret = drm_mm_insert_node_in_range_generic(&dev_priv->mm.gtt_space, node,
-							  size, alignment, obj->cache_level,
-							  0, dev_priv->gtt.mappable_end);
-	else
-		ret = drm_mm_insert_node_generic(&dev_priv->mm.gtt_space, node,
-						 size, alignment, obj->cache_level);
+search_free:
+	ret = drm_mm_insert_node_in_range_generic(&dev_priv->mm.gtt_space, node,
+						  size, alignment,
+						  obj->cache_level, 0, gtt_max);
 	if (ret) {
 		ret = i915_gem_evict_something(dev, size, alignment,
 					       obj->cache_level,
@@ -3007,7 +3145,7 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 		return ret;
 	}
 
-	list_move_tail(&obj->gtt_list, &dev_priv->mm.bound_list);
+	list_move_tail(&obj->global_list, &dev_priv->mm.bound_list);
 	list_add_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
 
 	obj->gtt_space = node;
@@ -3022,7 +3160,6 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 
 	obj->map_and_fenceable = mappable && fenceable;
 
-	i915_gem_object_unpin_pages(obj);
 	trace_i915_gem_object_bind(obj, map_and_fenceable);
 	i915_gem_verify_gtt(dev);
 	return 0;
@@ -3722,7 +3859,7 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 			  const struct drm_i915_gem_object_ops *ops)
 {
 	INIT_LIST_HEAD(&obj->mm_list);
-	INIT_LIST_HEAD(&obj->gtt_list);
+	INIT_LIST_HEAD(&obj->global_list);
 	INIT_LIST_HEAD(&obj->ring_list);
 	INIT_LIST_HEAD(&obj->exec_list);
 
@@ -3822,7 +3959,13 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 		dev_priv->mm.interruptible = was_interruptible;
 	}
 
-	obj->pages_pin_count = 0;
+	/* Stolen objects don't hold a ref, but do hold pin count. Fix that up
+	 * before progressing. */
+	if (obj->stolen)
+		i915_gem_object_unpin_pages(obj);
+
+	if (WARN_ON(obj->pages_pin_count))
+		obj->pages_pin_count = 0;
 	i915_gem_object_put_pages(obj);
 	i915_gem_object_free_mmap_offset(obj);
 	i915_gem_object_release_stolen(obj);
@@ -3973,12 +4116,21 @@ static int i915_gem_init_rings(struct drm_device *dev)
 			goto cleanup_bsd_ring;
 	}
 
+	if (HAS_VEBOX(dev)) {
+		ret = intel_init_vebox_ring_buffer(dev);
+		if (ret)
+			goto cleanup_blt_ring;
+	}
+
+
 	ret = i915_gem_set_seqno(dev, ((u32)~0 - 0x1000));
 	if (ret)
-		goto cleanup_blt_ring;
+		goto cleanup_vebox_ring;
 
 	return 0;
 
+cleanup_vebox_ring:
+	intel_cleanup_ring_buffer(&dev_priv->ring[VECS]);
 cleanup_blt_ring:
 	intel_cleanup_ring_buffer(&dev_priv->ring[BCS]);
 cleanup_bsd_ring:
@@ -4453,10 +4605,10 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
 	}
 
 	cnt = 0;
-	list_for_each_entry(obj, &dev_priv->mm.unbound_list, gtt_list)
+	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list)
 		if (obj->pages_pin_count == 0)
 			cnt += obj->base.size >> PAGE_SHIFT;
-	list_for_each_entry(obj, &dev_priv->mm.inactive_list, gtt_list)
+	list_for_each_entry(obj, &dev_priv->mm.inactive_list, mm_list)
 		if (obj->pin_count == 0 && obj->pages_pin_count == 0)
 			cnt += obj->base.size >> PAGE_SHIFT;