Commit 12fdaf19 authored by Chris Wilson's avatar Chris Wilson

drm/i915/execlists: Keep virtual context alive until after we kick

The call to kick_siblings() dereferences the rq->context, so we should
not drop our local reference until afterwards!

v2: Stick to setting ce.inflight=NULL before kicking as this is what the
other threads will check to see if the context is ready for takeover.

Fixes: 22b7a426 ("drm/i915/execlists: Preempt-to-busy")
Signed-off-by: default avatarChris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: default avatarTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190621080729.2652-1-chris@chris-wilson.co.uk
parent b32fa811
...@@ -557,9 +557,6 @@ execlists_schedule_out(struct i915_request *rq) ...@@ -557,9 +557,6 @@ execlists_schedule_out(struct i915_request *rq)
intel_engine_context_out(ce->inflight); intel_engine_context_out(ce->inflight);
execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT); execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
ce->inflight = NULL;
intel_context_put(ce);
/* /*
* If this is part of a virtual engine, its next request may * If this is part of a virtual engine, its next request may
* have been blocked waiting for access to the active context. * have been blocked waiting for access to the active context.
...@@ -569,8 +566,11 @@ execlists_schedule_out(struct i915_request *rq) ...@@ -569,8 +566,11 @@ execlists_schedule_out(struct i915_request *rq)
* request before the tasklet runs and do not need to rebuild * request before the tasklet runs and do not need to rebuild
* each virtual tree and kick everyone again. * each virtual tree and kick everyone again.
*/ */
ce->inflight = NULL;
if (rq->engine != ce->engine) if (rq->engine != ce->engine)
kick_siblings(rq, ce); kick_siblings(rq, ce);
intel_context_put(ce);
} }
i915_request_put(rq); i915_request_put(rq);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment