[Intel-gfx] [PATCH] drm/i915/selftests: Try to recover from a wedged GPU during reset tests

[Chris Wilson]

If we see the seqno stop progressing, we abandon the test for fear that
the GPU died following the reset. However, during test teardown we still
wait for the GPU to idle before continuing, but we have already
confirmed that the GPU is dead. Furthermore, since we are inside a reset
test, we have disabled the hangchecker, and so there is no safety net and
we wait indefinitely. Detect the stuck GPU and declare it wedged as a
state of emergency so we can escape.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Jari Tahvanainen <jari.tahvanainen at intel.com>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
---
 drivers/gpu/drm/i915/selftests/intel_hangcheck.c | 25 +++++++++++++++++++-----
 1 file changed, 20 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 02e52a146ed8..913fe752f6b4 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -165,6 +165,7 @@ static int emit_recurse_batch(struct hang *h,
 		*batch++ = lower_32_bits(vma->node.start);
 	}
 	*batch++ = MI_BATCH_BUFFER_END; /* not reached */
+	wmb();
 
 	flags = 0;
 	if (INTEL_GEN(vm->i915) <= 5)
@@ -621,7 +622,12 @@ static int igt_wait_reset(void *arg)
 	__i915_add_request(rq, true);
 
 	if (!wait_for_hang(&h, rq)) {
-		pr_err("Failed to start request %x\n", rq->fence.seqno);
+		pr_err("Failed to start request %x, at %x\n",
+		       rq->fence.seqno, hws_seqno(&h, rq));
+
+		i915_reset(i915, 0);
+		i915_gem_set_wedged(i915);
+
 		err = -EIO;
 		goto out_rq;
 	}
@@ -708,10 +714,14 @@ static int igt_reset_queue(void *arg)
 			__i915_add_request(rq, true);
 
 			if (!wait_for_hang(&h, prev)) {
-				pr_err("Failed to start request %x\n",
-				       prev->fence.seqno);
+				pr_err("Failed to start request %x, at %x\n",
+				       rq->fence.seqno, hws_seqno(&h, rq));
 				i915_gem_request_put(rq);
 				i915_gem_request_put(prev);
+
+				i915_reset(i915, 0);
+				i915_gem_set_wedged(i915);
+
 				err = -EIO;
 				goto fini;
 			}
@@ -806,7 +816,12 @@ static int igt_handle_error(void *arg)
 	__i915_add_request(rq, true);
 
 	if (!wait_for_hang(&h, rq)) {
-		pr_err("Failed to start request %x\n", rq->fence.seqno);
+		pr_err("Failed to start request %x, at %x\n",
+		       rq->fence.seqno, hws_seqno(&h, rq));
+
+		i915_reset(i915, 0);
+		i915_gem_set_wedged(i915);
+
 		err = -EIO;
 		goto err_request;
 	}
@@ -843,8 +858,8 @@ static int igt_handle_error(void *arg)
 int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_global_reset), /* attempt to recover GPU first */
 		SUBTEST(igt_hang_sanitycheck),
-		SUBTEST(igt_global_reset),
 		SUBTEST(igt_reset_engine),
 		SUBTEST(igt_reset_active_engines),
 		SUBTEST(igt_wait_reset),
-- 
2.14.1