drm/i915/selftests: Try to recover from a wedged GPU during reset tests

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@chris-wilson.co.uk>
Cc: Jari Tahvanainen <jari.tahvanainen@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170915130929.18892-1-chris@chris-wilson.co.uk
Tested-by: Jari Tahvanainen <jari.tahvanainen@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>

diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 02e52a146ed86e0c67587070fed32cfe053f5897..377c1de766ce3c53d8eba827f0f34f312fd3240d 100644 (file)
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -621,7 +621,12 @@ 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 +713,14 @@ 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",
+                                      prev->fence.seqno, hws_seqno(&h, prev));
                                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 +815,12 @@ 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 +857,8 @@ err_unlock:
 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),