drm/i915: Record the in-flight requests at the time of a hang

Being able to tally the list of outstanding requests with the sequence
of commands in the ringbuffer is often useful evidence with respect to
driver corruption.

Note that since this is the umpteenth per-ring data structure to be added
to the error state, I've coallesced the nearby loops (the ringbuffer and
batchbuffer) into a single structure along with the list of requests.  A
later task would be to refactor the ring register state into the same
structure.

v2: Fix pretty printing of requests so that they are parsed correctly by
intel_error_decode and use the 0x%08x format for seqno for consistency

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

1 files changed, 12 insertions, 5 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0e4c073..5622ec8 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -174,11 +174,18 @@ struct drm_i915_error_state {
 	u32 faddr[I915_NUM_RINGS];
 	u64 fence[I915_MAX_NUM_FENCES];
 	struct timeval time;
-	struct drm_i915_error_object {
-		int page_count;
-		u32 gtt_offset;
-		u32 *pages[0];
-	} *ringbuffer[I915_NUM_RINGS], *batchbuffer[I915_NUM_RINGS];
+	struct drm_i915_error_ring {
+		struct drm_i915_error_object {
+			int page_count;
+			u32 gtt_offset;
+			u32 *pages[0];
+		} *ringbuffer, *batchbuffer;
+		struct drm_i915_error_request {
+			long jiffies;
+			u32 seqno;
+		} *requests;
+		int num_requests;
+	} ring[I915_NUM_RINGS];
 	struct drm_i915_error_buffer {
 		u32 size;
 		u32 name;