When testing reset, we wait for 1s on the main thread for the hang to
start. Meanwhile, we continue submitting requests on all the background
threads, and we may have more threads than cores and so potentially
starve the waiter from being woken within the timeout. As the hang
timeout and the active timeouts are the same, it is hard to distinguish
which caused the timeout. Bump the active thread timeouts to 5s,
compared to the 1s timeout for the hang, so that we preferentially
report the hang timing out, while hopefully ensuring that we do at least
wake up the hang thread first before declaring the background active
timeout.

Signed-off-by: Chris Wilson <ch...@chris-wilson.co.uk>
---
 .../gpu/drm/i915/selftests/intel_hangcheck.c  | 48 +++++++++++++------
 1 file changed, 34 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c 
b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 438e0b045a2c..f1dc42a171c8 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -560,6 +560,30 @@ struct active_engine {
 #define TEST_SELF      BIT(2)
 #define TEST_PRIORITY  BIT(3)
 
+static int active_request_put(struct i915_request *rq)
+{
+       int err = 0;
+
+       if (!rq)
+               return 0;
+
+       if (i915_request_wait(rq, 0, 5 * HZ) < 0) {
+               GEM_TRACE("%s timed out waiting for completion of fence 
%llx:%d, seqno %d.\n",
+                         rq->engine->name,
+                         rq->fence.context,
+                         rq->fence.seqno,
+                         i915_request_global_seqno(rq));
+               GEM_TRACE_DUMP();
+
+               i915_gem_set_wedged(rq->i915);
+               err = -EIO;
+       }
+
+       i915_request_put(rq);
+
+       return err;
+}
+
 static int active_engine(void *data)
 {
        I915_RND_STATE(prng);
@@ -608,24 +632,20 @@ static int active_engine(void *data)
                i915_request_add(new);
                mutex_unlock(&engine->i915->drm.struct_mutex);
 
-               if (old) {
-                       if (i915_request_wait(old, 0, HZ) < 0) {
-                               GEM_TRACE("%s timed out.\n", engine->name);
-                               GEM_TRACE_DUMP();
-
-                               i915_gem_set_wedged(engine->i915);
-                               i915_request_put(old);
-                               err = -EIO;
-                               break;
-                       }
-                       i915_request_put(old);
-               }
+               err = active_request_put(old);
+               if (err)
+                       break;
 
                cond_resched();
        }
 
-       for (count = 0; count < ARRAY_SIZE(rq); count++)
-               i915_request_put(rq[count]);
+       for (count = 0; count < ARRAY_SIZE(rq); count++) {
+               int err__ = active_request_put(rq[count]);
+
+               /* Keep the first error */
+               if (!err)
+                       err = err__;
+       }
 
 err_file:
        mock_file_free(engine->i915, file);
-- 
2.17.0

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

Reply via email to