On 25/11/2019 11:25, Chris Wilson wrote:
I rushed a last minute correction to cancel_port_requests() to prevent
the snooping of *execlists->active as the inflight array was being
updated, without noticing we iterated the inflight array starting from
active! Oops.
Fixes: 331bf9059157 ("drm/i915/gt: Mark the execlists->active as the primary
volatile access")
Signed-off-by: Chris Wilson <ch...@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuopp...@linux.intel.com>
---
drivers/gpu/drm/i915/gt/intel_lrc.c | 16 +++++++---------
1 file changed, 7 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c
b/drivers/gpu/drm/i915/gt/intel_lrc.c
index e533ff7ba334..6090357a00fa 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2007,19 +2007,17 @@ static void execlists_dequeue(struct intel_engine_cs
*engine)
static void
cancel_port_requests(struct intel_engine_execlists * const execlists)
{
- struct i915_request * const *port, *rq;
+ struct i915_request * const *port;
- for (port = execlists->pending; (rq = *port); port++)
- execlists_schedule_out(rq);
+ for (port = execlists->pending; *port; port++)
+ execlists_schedule_out(*port);
memset(execlists->pending, 0, sizeof(execlists->pending));
/* Mark the end of active before we overwrite *active */
- WRITE_ONCE(execlists->active, execlists->pending);
-
- for (port = execlists->active; (rq = *port); port++)
- execlists_schedule_out(rq);
- execlists->active =
- memset(execlists->inflight, 0, sizeof(execlists->inflight));
+ for (port = xchg(&execlists->active, execlists->pending); *port; port++)
+ execlists_schedule_out(*port);
+ WRITE_ONCE(execlists->active,
+ memset(execlists->inflight, 0, sizeof(execlists->inflight)));
}
static inline void
Reviewed-by: Tvrtko Ursulin <tvrtko.ursu...@intel.com>
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
