drm/i915: add batch bo to i915_add_request()

In order to track down a batch buffer and context which
caused the ring to hang, store reference to bo into the request struct.
Request can also cause gpu to hang after the batch in the flush section
in the ring. To detect this add start of the flush portion offset into the
request.

v2: Included comment about request vs batch_obj lifetimes (Chris Wilson)

Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

3 files changed, 25 insertions, 6 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 425200bc1e4..5ce3751ddb3 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1362,12 +1362,18 @@ struct drm_i915_gem_request {
 	/** GEM sequence number associated with this request. */
 	uint32_t seqno;
 
-	/** Postion in the ringbuffer of the end of the request */
+	/** Position in the ringbuffer of the start of the request */
+	u32 head;
+
+	/** Position in the ringbuffer of the end of the request */
 	u32 tail;
 
 	/** Context related to this request */
 	struct i915_hw_context *ctx;
 
+	/** Batch buffer related to this request if any */
+	struct drm_i915_gem_object *batch_obj;
+
 	/** Time at which this request was emitted, in jiffies. */
 	unsigned long emitted_jiffies;
 
@@ -1758,9 +1764,10 @@ int __must_check i915_gpu_idle(struct drm_device *dev);
 int __must_check i915_gem_idle(struct drm_device *dev);
 int __i915_add_request(struct intel_ring_buffer *ring,
 		       struct drm_file *file,
+		       struct drm_i915_gem_object *batch_obj,
 		       u32 *seqno);
 #define i915_add_request(ring, seqno) \
-	__i915_add_request(ring, NULL, seqno);
+	__i915_add_request(ring, NULL, NULL, seqno);
 int __must_check i915_wait_seqno(struct intel_ring_buffer *ring,
 				 uint32_t seqno);
 int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 38e20875c25..dc32faecd9f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2002,14 +2002,16 @@ i915_gem_get_seqno(struct drm_device *dev, u32 *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
@@ -2041,8 +2043,17 @@ int __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);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index d79ac7aa55d..87a3227e517 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -796,13 +796,14 @@ i915_gem_execbuffer_move_to_active(struct list_head *objects,
 static void
 i915_gem_execbuffer_retire_commands(struct drm_device *dev,
 				    struct drm_file *file,
-				    struct intel_ring_buffer *ring)
+				    struct intel_ring_buffer *ring,
+				    struct drm_i915_gem_object *obj)
 {
 	/* Unconditionally force add_request to emit a full flush. */
 	ring->gpu_caches_dirty = true;
 
 	/* Add a breadcrumb for the completion of the batch buffer */
-	(void)__i915_add_request(ring, file, NULL);
+	(void)__i915_add_request(ring, file, obj, NULL);
 }
 
 static int
@@ -1083,7 +1084,7 @@ 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_retire_commands(dev, file, ring);
+	i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
 
 err:
 	eb_destroy(eb);