[CI 4/7] drm/i915: Uninterruptibly drain the timelines on unwedging

[Chris Wilson <chris@chris-wilson.co.uk>]

On wedging, we mark all executing requests as complete and all pending
requests completed as soon as they are ready. Before unwedging though we
wish to flush those pending requests prior to restoring default
execution, and so we must wait. Do so uninterruptibly as we do not provide
the EINTR gracefully back to userspace in this case but persists in
keeping the permanently wedged state without restarting the syscall.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
---
 drivers/gpu/drm/i915/i915_reset.c | 28 ++++++++--------------------
 1 file changed, 8 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reset.c b/drivers/gpu/drm/i915/i915_reset.c
index 64f26e17243a..c4fcb450bd80 100644
--- a/drivers/gpu/drm/i915/i915_reset.c
+++ b/drivers/gpu/drm/i915/i915_reset.c
@@ -862,7 +862,6 @@ bool i915_gem_unset_wedged(struct drm_i915_private *i915)
 {
 	struct i915_gpu_error *error = &i915->gpu_error;
 	struct i915_timeline *tl;
-	bool ret = false;
 
 	if (!test_bit(I915_WEDGED, &error->flags))
 		return true;
@@ -887,30 +886,20 @@ bool i915_gem_unset_wedged(struct drm_i915_private *i915)
 	mutex_lock(&i915->gt.timelines.mutex);
 	list_for_each_entry(tl, &i915->gt.timelines.active_list, link) {
 		struct i915_request *rq;
-		long timeout;
 
 		rq = i915_active_request_get_unlocked(&tl->last_request);
 		if (!rq)
 			continue;
 
 		/*
-		 * We can't use our normal waiter as we want to
-		 * avoid recursively trying to handle the current
-		 * reset. The basic dma_fence_default_wait() installs
-		 * a callback for dma_fence_signal(), which is
-		 * triggered by our nop handler (indirectly, the
-		 * callback enables the signaler thread which is
-		 * woken by the nop_submit_request() advancing the seqno
-		 * and when the seqno passes the fence, the signaler
-		 * then signals the fence waking us up).
+		 * All internal dependencies (i915_requests) will have
+		 * been flushed by the set-wedge, but we may be stuck waiting
+		 * for external fences. These should all be capped to 10s
+		 * (I915_FENCE_TIMEOUT) so this wait should not be unbounded
+		 * in the worst case.
 		 */
-		timeout = dma_fence_default_wait(&rq->fence, true,
-						 MAX_SCHEDULE_TIMEOUT);
+		dma_fence_default_wait(&rq->fence, false, MAX_SCHEDULE_TIMEOUT);
 		i915_request_put(rq);
-		if (timeout < 0) {
-			mutex_unlock(&i915->gt.timelines.mutex);
-			goto unlock;
-		}
 	}
 	mutex_unlock(&i915->gt.timelines.mutex);
 
@@ -931,11 +920,10 @@ bool i915_gem_unset_wedged(struct drm_i915_private *i915)
 
 	smp_mb__before_atomic(); /* complete takeover before enabling execbuf */
 	clear_bit(I915_WEDGED, &i915->gpu_error.flags);
-	ret = true;
-unlock:
+
 	mutex_unlock(&i915->gpu_error.wedge_mutex);
 
-	return ret;
+	return true;
 }
 
 static int do_reset(struct drm_i915_private *i915, unsigned int stalled_mask)
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx