drm/amdgpu: use scheduler fault instead of reset work

Signal a fault to the scheduler on an illegal instruction or register
access violation instead of kicking of the reset handler directly.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 7 insertions, 1 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 6fb3edaba0ec..415968dc6c87 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -1440,8 +1440,14 @@ static int sdma_v3_0_process_illegal_inst_irq(struct amdgpu_device *adev,
 					      struct amdgpu_irq_src *source,
 					      struct amdgpu_iv_entry *entry)
 {
+	u8 instance_id, queue_id;
+
 	DRM_ERROR("Illegal instruction in SDMA command stream\n");
-	schedule_work(&adev->reset_work);
+	instance_id = (entry->ring_id & 0x3) >> 0;
+	queue_id = (entry->ring_id & 0xc) >> 2;
+
+	if (instance_id <= 1 && queue_id == 0)
+		drm_sched_fault(&adev->sdma.instance[instance_id].ring.sched);
 	return 0;
 }