drm/amdkfd: Remove queue node when destroy queue failed

HWS may hang in the middle of destroy queue, remove the queue from the
process queue list so it won't be freed again in the future

Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 3045aebdc3f7a081f6b8076ecd815b073ee0351c..d65ce0436b31ba45ca9ef303b3970f7e5fc42dc6 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -241,7 +241,8 @@ int pqm_create_queue(struct process_queue_manager *pqm,
        }
 
        if (retval != 0) {
-               pr_err("DQM create queue failed\n");
+               pr_err("Pasid %d DQM create queue %d failed. ret %d\n",
+                       pqm->process->pasid, type, retval);
                goto err_create_queue;
        }
 
@@ -319,8 +320,11 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
                dqm = pqn->q->device->dqm;
                retval = dqm->ops.destroy_queue(dqm, &pdd->qpd, pqn->q);
                if (retval) {
-                       pr_debug("Destroy queue failed, returned %d\n", retval);
-                       goto err_destroy_queue;
+                       pr_err("Pasid %d destroy queue %d failed, ret %d\n",
+                               pqm->process->pasid,
+                               pqn->q->properties.queue_id, retval);
+                       if (retval != -ETIME)
+                               goto err_destroy_queue;
                }
                uninit_queue(pqn->q);
        }