On 14/02/2017 09:54, Chris Wilson wrote:
Add ourselves to the gpu error waitqueue earllier on, even before we
determine we have to wait on the seqno. This is so that we can then
share the waitqueue between stages in subsequent patches.
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gem_request.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index f7ff3736797f..dcc0a7ab95dc 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -1081,6 +1081,9 @@ long i915_wait_request(struct drm_i915_gem_request *req,
trace_i915_gem_request_wait_begin(req);
+ if (flags & I915_WAIT_LOCKED)
+ add_wait_queue(errq, &reset);
+
if (!i915_sw_fence_done(&req->execute)) {
timeout = __i915_request_wait_for_execute(req, flags, timeout);
if (timeout < 0)
@@ -1096,9 +1099,6 @@ long i915_wait_request(struct drm_i915_gem_request *req,
goto complete;
set_current_state(state);
- if (flags & I915_WAIT_LOCKED)
- add_wait_queue(errq, &reset);
-
intel_wait_init(&wait, req->global_seqno);
if (intel_engine_add_wait(req->engine, &wait))
/* In order to check that we haven't missed the interrupt
@@ -1158,11 +1158,11 @@ long i915_wait_request(struct drm_i915_gem_request *req,
}
intel_engine_remove_wait(req->engine, &wait);
- if (flags & I915_WAIT_LOCKED)
- remove_wait_queue(errq, &reset);
__set_current_state(TASK_RUNNING);
complete:
+ if (flags & I915_WAIT_LOCKED)
+ remove_wait_queue(errq, &reset);
trace_i915_gem_request_wait_end(req);
return timeout;
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
