mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-08-31 11:41:29 -04:00
drm/radeon: restore hardware polling in fence_is_signaled to fix performance regression
Commit527ba26e50("drm/radeon: delete radeon_fence_process in is_signaled, no deadlock") removed the hardware polling from radeon_fence_is_signaled() to fix a self-deadlock caused by wake_up_all(&rdev->fence_queue) being called with the fence queue lock held. However, removing the polling entirely causes significant performance regression (e.g. glxgears FPS drop) because the fence signaled check becomes purely passive — it only reads the cached last_seq without probing the GPU, so completed GPU work is not detected in time, causing unnecessary CPU stalls in sync-heavy workloads. Fix this by calling radeon_fence_activity() directly instead of radeon_fence_process(). radeon_fence_activity() reads the hardware fence counter and updates last_seq via atomic ops without calling wake_up_all(), thus avoiding the deadlock while restoring timely fence detection. Fixes:527ba26e50("drm/radeon: delete radeon_fence_process in is_signaled, no deadlock") Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Wang Jiang <jiangwang@kylinos.cn> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> (cherry picked from commitf59ad4cca2) Cc: stable@vger.kernel.org
This commit is contained in:
@@ -360,6 +360,13 @@ static bool radeon_fence_is_signaled(struct dma_fence *f)
|
||||
if (atomic64_read(&rdev->fence_drv[ring].last_seq) >= seq)
|
||||
return true;
|
||||
|
||||
if (down_read_trylock(&rdev->exclusive_lock)) {
|
||||
radeon_fence_activity(rdev, ring);
|
||||
up_read(&rdev->exclusive_lock);
|
||||
|
||||
if (atomic64_read(&rdev->fence_drv[ring].last_seq) >= seq)
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user