Re: [PATCH] drm/i915/gt: Be defensive in the face of false CS events

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 




On 10/07/2020 13:16, Chris Wilson wrote:
If the HW throws a curve ball and reports either en event before it is
possible, or just a completely impossible event, we have to grin and
bear it. The first few events, we will likely not notice as we would be
expecting some event, but as soon as we stop expecting an event and yet
they still keep coming, then we enter into undefined state territory.
In which case, bail out, stop processing the events, and reset the
engine and our set of queued requests to recover.

The sporadic hangs and warnings will continue to plague CI, but at least
system stability should not be compromised.

Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2045
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
---
  drivers/gpu/drm/i915/gt/intel_lrc.c | 8 ++++++--
  1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index fbcfeaed6441..c86324d2d2bb 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2567,6 +2567,7 @@ static void process_csb(struct intel_engine_cs *engine)
  	tail = READ_ONCE(*execlists->csb_write);
  	if (unlikely(head == tail))
  		return;
+	execlists->csb_head = tail;

This deserves a comment...

/*
  	 * Hopefully paired with a wmb() in HW!
@@ -2613,6 +2614,9 @@ static void process_csb(struct intel_engine_cs *engine)
  		if (promote) {
  			struct i915_request * const *old = execlists->active;
+ if (GEM_WARN_ON(!*execlists->pending))
+				break;
+

... but why not continue? You think nothing good can come out of trying further and break simply expedites the hang? We have to be confident we can cope with any random i915 state caused by skipping maybe valid entries.

Conclusion will define what kind of comment to put above. "Assume we always consume all CSB entries, or things are really bad and we mark all as invalid upon finding first bad entry"?

Regards,

Tvrtko

  			ring_set_paused(engine, 0);
/* Point active to the new ELSP; prevent overwriting */
@@ -2635,7 +2639,8 @@ static void process_csb(struct intel_engine_cs *engine)
WRITE_ONCE(execlists->pending[0], NULL);
  		} else {
-			GEM_BUG_ON(!*execlists->active);
+			if (GEM_WARN_ON(!*execlists->active))
+				break;
/* port0 completed, advanced to port1 */
  			trace_ports(execlists, "completed", execlists->active);
@@ -2686,7 +2691,6 @@ static void process_csb(struct intel_engine_cs *engine)
  		}
  	} while (head != tail);
- execlists->csb_head = head;
  	set_timeslice(engine);
/*

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



[Index of Archives]     [AMD Graphics]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux