| Message ID | 20170522220755.12400-2-michal.winiarski@intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Tue, May 23, 2017 at 12:07:49AM +0200, Michał Winiarski wrote: > If port[0] is occupied and we're trying to dequeue request from > different context, we will inevitably hit BUG_ON in port_assign. > Let's skip it - similar to what we're doing in execlists counterpart. > > Fixes: 77f0d0e925e8a0 ("drm/i915/execlists: Pack the count into the low bits of the port.request") > Cc: Chris Wilson <chris@chris-wilson.co.uk> > Cc: Michał Wajdeczko <michal.wajdeczko@intel.com> > Cc: Mika Kuoppala <mika.kuoppala@intel.com> > Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> > Signed-off-by: Michał Winiarski <michal.winiarski@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Can you split out the first two and resend with a CI prefix + a guc enabling patch? Let's get this fixed first. -Chris
diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c index 777f48e..e6e0c6e 100644 --- a/drivers/gpu/drm/i915/i915_guc_submission.c +++ b/drivers/gpu/drm/i915/i915_guc_submission.c @@ -681,7 +681,8 @@ static bool i915_guc_dequeue(struct intel_engine_cs *engine) goto done; } - port_assign(port, last); + if (submit) + port_assign(port, last); port++; }
If port[0] is occupied and we're trying to dequeue request from different context, we will inevitably hit BUG_ON in port_assign. Let's skip it - similar to what we're doing in execlists counterpart. Fixes: 77f0d0e925e8a0 ("drm/i915/execlists: Pack the count into the low bits of the port.request") Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Michał Wajdeczko <michal.wajdeczko@intel.com> Cc: Mika Kuoppala <mika.kuoppala@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Michał Winiarski <michal.winiarski@intel.com> --- drivers/gpu/drm/i915/i915_guc_submission.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)