On 07/03/2017 20:58, Chris Wilson wrote:
To avoid waiting for work from other invalidate-range threads where
not required, only wait on the userptr cancel workqueue if we have added
some work to it.
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Michał Winiarski <michal.winiarski@xxxxxxxxx>
Cc: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gem_userptr.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 6ef05d5b884d..dc9bf5282071 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -145,7 +145,8 @@ static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
del_object(mo);
spin_unlock(&mn->lock);
- flush_workqueue(mn->wq);
+ if (!list_empty(&cancelled))
+ flush_workqueue(mn->wq);
}
static const struct mmu_notifier_ops i915_gem_userptr_notifier = {
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
