summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c')
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c11
1 files changed, 10 insertions, 1 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 76359c6a3f3a..2d91027e2a74 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -2312,7 +2312,7 @@ static int reset_hung_queues_sdma(struct device_queue_manager *dqm)
continue;
/* Reset engine and check. */
- if (amdgpu_sdma_reset_engine(dqm->dev->adev, i) ||
+ if (amdgpu_sdma_reset_engine(dqm->dev->adev, i, false) ||
dqm->dev->kfd2kgd->hqd_sdma_get_doorbell(dqm->dev->adev, i, j) ||
!set_sdma_queue_as_reset(dqm, doorbell_off)) {
r = -ENOTRECOVERABLE;
@@ -2339,9 +2339,18 @@ reset_fail:
static int reset_queues_on_hws_hang(struct device_queue_manager *dqm, bool is_sdma)
{
+ struct amdgpu_device *adev = dqm->dev->adev;
+
while (halt_if_hws_hang)
schedule();
+ if (adev->debug_disable_gpu_ring_reset) {
+ dev_info_once(adev->dev,
+ "%s queue hung, but ring reset disabled",
+ is_sdma ? "sdma" : "compute");
+
+ return -EPERM;
+ }
if (!amdgpu_gpu_recovery)
return -ENOTRECOVERABLE;