Merge tag 'amd-drm-next-6.15-2025-03-07' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amdgpu:
- Fix spelling typos
- RAS updates
- VCN 5.0.1 updates
- SubVP fixes
- DCN 4.0.1 fixes
- MSO DPCD fixes
- DIO encoder refactor
- PCON fixes
- Misc cleanups
- DMCUB fixes
- USB4 DP fixes
- DM cleanups
- Backlight cleanups and fixes
- Support platform backlight curves
- Misc code cleanups
- SMU 14 fixes
- JPEG 4.0.3 reset updates
- SR-IOV fixes
- SVM fixes
- GC 12 DCC fixes
- DC DCE 6.x fix
- Hiberation fix

amdkfd:
- Fix possible NULL pointer in queue validation
- Remove unnecessary CP domain validation
- SDMA queue reset support
- Add per process flags

radeon:
- Fix spelling typos
- RS400 hyperZ fix

UAPI:
- Add KFD per process flags for setting precision
  Proposed user space: https://github.com/ROCm/ROCR-Runtime/commit/2a64fa5e06e80e0af36df4ce0c76ae52eeec0a9d

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250307211051.1880472-1-alexander.deucher@amd.com

1 files changed, 24 insertions, 6 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 1899c601c95c..1d26be3c6d9d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -130,29 +130,47 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 		amdgpu_vm_put_task_info(ti);
 	}
 
-	dma_fence_set_error(&s_job->s_fence->finished, -ETIME);
-
 	/* attempt a per ring reset */
-	if (amdgpu_gpu_recovery &&
-	    ring->funcs->reset) {
+	if (unlikely(adev->debug_disable_gpu_ring_reset)) {
+		dev_err(adev->dev, "Ring reset disabled by debug mask\n");
+	} else if (amdgpu_gpu_recovery && ring->funcs->reset) {
+		bool is_guilty;
+
 		dev_err(adev->dev, "Starting %s ring reset\n", s_job->sched->name);
 		/* stop the scheduler, but don't mess with the
 		 * bad job yet because if ring reset fails
 		 * we'll fall back to full GPU reset.
 		 */
 		drm_sched_wqueue_stop(&ring->sched);
+
+		/* for engine resets, we need to reset the engine,
+		 * but individual queues may be unaffected.
+		 * check here to make sure the accounting is correct.
+		 */
+		if (ring->funcs->is_guilty)
+			is_guilty = ring->funcs->is_guilty(ring);
+		else
+			is_guilty = true;
+
+		if (is_guilty)
+			dma_fence_set_error(&s_job->s_fence->finished, -ETIME);
+
 		r = amdgpu_ring_reset(ring, job->vmid);
 		if (!r) {
 			if (amdgpu_ring_sched_ready(ring))
 				drm_sched_stop(&ring->sched, s_job);
-			atomic_inc(&ring->adev->gpu_reset_counter);
-			amdgpu_fence_driver_force_completion(ring);
+			if (is_guilty) {
+				atomic_inc(&ring->adev->gpu_reset_counter);
+				amdgpu_fence_driver_force_completion(ring);
+			}
 			if (amdgpu_ring_sched_ready(ring))
 				drm_sched_start(&ring->sched, 0);
+			dev_err(adev->dev, "Ring %s reset succeeded\n", ring->sched.name);
 			goto exit;
 		}
 		dev_err(adev->dev, "Ring %s reset failure\n", ring->sched.name);
 	}
+	dma_fence_set_error(&s_job->s_fence->finished, -ETIME);
 
 	if (amdgpu_device_should_recover_gpu(ring->adev)) {
 		struct amdgpu_reset_context reset_context;