summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
diff options
context:
space:
mode:
authorChris Wilson2018-05-17 16:24:41 +0200
committerChris Wilson2018-05-19 13:50:59 +0200
commit39d3cc03e9ddd3c7b564acd07ba1691ba817837d (patch)
tree2c9524c0b5c33e909a57685216435353836a73ea /drivers/gpu/drm/i915/selftests/intel_hangcheck.c
parentdrm/i915: Allow init_breadcrumbs to be used from irq context (diff)
downloadkernel-qcow2-linux-39d3cc03e9ddd3c7b564acd07ba1691ba817837d.tar.gz
kernel-qcow2-linux-39d3cc03e9ddd3c7b564acd07ba1691ba817837d.tar.xz
kernel-qcow2-linux-39d3cc03e9ddd3c7b564acd07ba1691ba817837d.zip
drm/i915/selftests: Wait longer for the old active request
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 <chris@chris-wilson.co.uk> Link: https://patchwork.freedesktop.org/patch/msgid/20180517142442.16979-1-chris@chris-wilson.co.uk Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Diffstat (limited to 'drivers/gpu/drm/i915/selftests/intel_hangcheck.c')
-rw-r--r--drivers/gpu/drm/i915/selftests/intel_hangcheck.c48
1 files 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 2c4e77c050dc..2091e3a6a5be 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -563,6 +563,30 @@ 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);
@@ -611,24 +635,20 @@ 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);