[PATCH 12/29] drm/amdgpu/gfx9.4.3: re-emit unprocessed state on kcq reset

Alex Deucher alexander.deucher at amd.com
Fri Jun 6 06:43:37 UTC 2025


Re-emit the unprocessed state after resetting the queue.

Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index d9eea11f52fec..637d261231898 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -3566,6 +3566,8 @@ static int gfx_v9_4_3_reset_kcq(struct amdgpu_ring *ring,
 	if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
 		return -EINVAL;
 
+	amdgpu_ring_backup_unprocessed_commands(ring, &job->hw_fence.base, true);
+
 	spin_lock_irqsave(&kiq->ring_lock, flags);
 
 	if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size)) {
@@ -3612,9 +3614,8 @@ static int gfx_v9_4_3_reset_kcq(struct amdgpu_ring *ring,
 	}
 	kiq->pmf->kiq_map_queues(kiq_ring, ring);
 	amdgpu_ring_commit(kiq_ring);
-	spin_unlock_irqrestore(&kiq->ring_lock, flags);
-
 	r = amdgpu_ring_test_ring(kiq_ring);
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 	if (r) {
 		dev_err(adev->dev, "fail to remap queue\n");
 		return r;
@@ -3623,9 +3624,16 @@ static int gfx_v9_4_3_reset_kcq(struct amdgpu_ring *ring,
 	r = amdgpu_ring_test_ring(ring);
 	if (r)
 		return r;
+
 	dma_fence_set_error(&job->base.s_fence->finished, -ETIME);
-	amdgpu_fence_driver_force_completion(ring);
+	/* signal the fence of the bad job */
+	amdgpu_fence_driver_guilty_force_completion(&job->hw_fence.base);
 	atomic_inc(&ring->adev->gpu_reset_counter);
+	r = amdgpu_ring_reemit_unprocessed_commands(ring);
+	if (r)
+		/* if we fail to reemit, force complete all fences */
+		amdgpu_fence_driver_force_completion(ring);
+
 	return 0;
 }
 
-- 
2.49.0



More information about the amd-gfx mailing list