drm/amdkfd: fix cp hang in eviction

The cp hang occurs in OCL conformance test only on supermicro
platform which has 40 cores and the test generates 40 threads.
The root cause is race condition in non-protected flags.

The fix is to add flags of is_evicted and is_active(init_mqd())
into protected area.

Signed-off-by: Eric Huang <JinhuiEric.Huang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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 584748c23f14a68da105b563bccf83ce4011f09d..e6a4288bfaa6ab5824ca672653875c49144be803 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1157,12 +1157,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 
        mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type(
                        q->properties.type)];
-       /*
-        * Eviction state logic: mark all queues as evicted, even ones
-        * not currently active. Restoring inactive queues later only
-        * updates the is_evicted flag but is a no-op otherwise.
-        */
-       q->properties.is_evicted = !!qpd->evicted;
+
        if (q->properties.type == KFD_QUEUE_TYPE_SDMA ||
                q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)
                dqm->asic_ops.init_sdma_vm(dqm, q, qpd);
@@ -1173,9 +1168,16 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
                retval = -ENOMEM;
                goto out_deallocate_doorbell;
        }
+
+       dqm_lock(dqm);
+       /*
+        * Eviction state logic: mark all queues as evicted, even ones
+        * not currently active. Restoring inactive queues later only
+        * updates the is_evicted flag but is a no-op otherwise.
+        */
+       q->properties.is_evicted = !!qpd->evicted;
        mqd_mgr->init_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj,
                                &q->gart_mqd_addr, &q->properties);
-       dqm_lock(dqm);
 
        list_add(&q->list, &qpd->queues_list);
        qpd->queue_count++;