[PATCH 14/27] drm/amdgpu/sdma6: re-emit unprocessed state on ring reset

[Alex Deucher]

Re-emit the unprocessed state after resetting the queue.

Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 29 ++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
index 595e90a5274ea..00c7f440a6ba0 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
@@ -1537,11 +1537,23 @@ static int sdma_v6_0_ring_preempt_ib(struct amdgpu_ring *ring)
 	return r;
 }
 
+static bool sdma_v6_0_is_queue_selected(struct amdgpu_device *adev,
+					u32 instance_id)
+{
+	/* we always use queue0 for KGD */
+	u32 context_status = RREG32(sdma_v6_0_get_reg_offset(adev, instance_id,
+							     regSDMA0_QUEUE0_CONTEXT_STATUS));
+
+	/* Check if the SELECTED bit is set */
+	return (context_status & SDMA0_QUEUE0_CONTEXT_STATUS__SELECTED_MASK) != 0;
+}
+
 static int sdma_v6_0_reset_queue(struct amdgpu_ring *ring,
 				 unsigned int vmid,
 				 struct amdgpu_fence *guilty_fence)
 {
 	struct amdgpu_device *adev = ring->adev;
+	bool is_guilty;
 	int i, r;
 
 	if (amdgpu_sriov_vf(adev))
@@ -1557,6 +1569,10 @@ static int sdma_v6_0_reset_queue(struct amdgpu_ring *ring,
 		return -EINVAL;
 	}
 
+	is_guilty = sdma_v6_0_is_queue_selected(adev, i);
+
+	amdgpu_ring_backup_unprocessed_commands(ring, is_guilty ? guilty_fence : NULL);
+
 	r = amdgpu_mes_reset_legacy_queue(adev, ring, vmid, true);
 	if (r)
 		return r;
@@ -1564,8 +1580,17 @@ static int sdma_v6_0_reset_queue(struct amdgpu_ring *ring,
 	r = sdma_v6_0_gfx_resume_instance(adev, i, true);
 	if (r)
 		return r;
-	amdgpu_fence_driver_force_completion(ring);
-	atomic_inc(&ring->adev->gpu_reset_counter);
+
+	if (is_guilty) {
+		/* signal the fence of the bad job */
+		amdgpu_fence_driver_guilty_force_completion(guilty_fence);
+		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