As a precaution against the driver fouling up and missing a hang leaving
the caller in an indefinite wait, manually inspect for a GPU hang if we
timeout whilst waiting for a seqno.
v2: To avoid issues with multiple clients running hangchecks
concurrently or in very rapid succession, make sure we only reactivate
the hangcheck timer if we find it idle whilst waiting.
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
drivers/gpu/drm/i915/i915_gem.c | 13 ++++++++-----
1 file changed, 8 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0d878c1..dc382eb 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1096,7 +1096,6 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
struct timespec before, now, wait_time={1,0};
unsigned long timeout_jiffies;
long end;
- bool wait_forever = true;
int ret;
if (i915_seqno_passed(ring->get_seqno(ring, true), seqno))
@@ -1104,10 +1103,8 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
trace_i915_gem_request_wait_begin(ring, seqno);
- if (timeout != NULL) {
+ if (timeout != NULL)
wait_time = *timeout;
- wait_forever = false;
- }
timeout_jiffies = timespec_to_jiffies(&wait_time);
@@ -1129,6 +1126,12 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
else
end = wait_event_timeout(ring->irq_queue, EXIT_COND,
timeout_jiffies);
+ /* Be paranoid and check that we haven't missed a GPU hang */
+ if (end == 0 &&
+ i915_enable_hangcheck &&
+ !timer_pending(&dev_priv->gpu_error.hangcheck_timer))
+ mod_timer(&dev_priv->gpu_error.hangcheck_timer,
+ round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES));
/* We need to check whether any gpu reset happened in between
* the caller grabbing the seqno and now ... */
@@ -1140,7 +1143,7 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
ret = i915_gem_check_wedge(&dev_priv->gpu_error, interruptible);
if (ret)
end = ret;
- } while (end == 0 && wait_forever);
+ } while (end == 0 && timeout == NULL);
getrawmonotonic(&now);
--
1.7.10.4
