Since we can retire requests from multiple paths, we cannot assume that
i915_gem_retire_requests() is the sole path on which we can transition
to gt.active_requests == 0. A consequence of this is that we would skip
the function if we had already retired all the requests and not
scheduled the idle worker.
This is fallout from changing the routine from considering active_engines
(over which it was the only consumer) to active_requests.
Fixes: 28176ef4cfa5 ("drm/i915: Reserve space in the global seqno during request allocation")
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gem_request.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index b9b5253cf3cd..2b763026b4c1 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -763,6 +763,8 @@ static void i915_gem_mark_busy(const struct intel_engine_cs *engine)
if (dev_priv->gt.awake)
return;
+ GEM_BUG_ON(!dev_priv->gt.active_requests);
+
intel_runtime_pm_get_noresume(dev_priv);
dev_priv->gt.awake = true;
@@ -1143,11 +1145,9 @@ void i915_gem_retire_requests(struct drm_i915_private *dev_priv)
lockdep_assert_held(&dev_priv->drm.struct_mutex);
- if (!dev_priv->gt.active_requests)
+ if (!dev_priv->gt.awake)
return;
- GEM_BUG_ON(!dev_priv->gt.awake);
-
for_each_engine(engine, dev_priv, id)
engine_retire_requests(engine);
--
2.10.2
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
