drm/amdkfd: avoid HMM change cause circular lock

There is circular lock between gfx and kfd path with HMM change:
lock(dqm) -> bo::reserve -> amdgpu_mn_lock

To avoid this, move init/unint_mqd() out of lock(dqm), to remove nested
locking between mmap_sem and bo::reserve. The locking order
is: bo::reserve -> amdgpu_mn_lock(p->mn)

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 17 insertions, 15 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 d6fe75245d05..cf6b57627842 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1161,21 +1161,17 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	int retval;
 	struct mqd_manager *mqd_mgr;
 
-	retval = 0;
-
-	dqm_lock(dqm);
-
 	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
 		pr_warn("Can't create new usermode queue because %d queues were already created\n",
 				dqm->total_queue_count);
 		retval = -EPERM;
-		goto out_unlock;
+		goto out;
 	}
 
 	if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
 		retval = allocate_sdma_queue(dqm, &q->sdma_id);
 		if (retval)
-			goto out_unlock;
+			goto out;
 		q->properties.sdma_queue_id =
 			q->sdma_id / get_num_sdma_engines(dqm);
 		q->properties.sdma_engine_id =
@@ -1189,6 +1185,9 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	if (retval)
 		goto out_deallocate_sdma_queue;
 
+	/* Do init_mqd before dqm_lock(dqm) to avoid circular locking order:
+	 * lock(dqm) -> bo::reserve
+	 */
 	mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
 
@@ -1196,6 +1195,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 		retval = -ENOMEM;
 		goto out_deallocate_doorbell;
 	}
+
 	/*
 	 * Eviction state logic: we only mark active queues as evicted
 	 * to avoid the overhead of restoring inactive queues later
@@ -1204,9 +1204,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 		q->properties.is_evicted = (q->properties.queue_size > 0 &&
 					    q->properties.queue_percent > 0 &&
 					    q->properties.queue_address != 0);
-
 	dqm->asic_ops.init_sdma_vm(dqm, q, qpd);
-
 	q->properties.tba_addr = qpd->tba_addr;
 	q->properties.tma_addr = qpd->tma_addr;
 	retval = mqd_mgr->init_mqd(mqd_mgr, &q->mqd, &q->mqd_mem_obj,
@@ -1214,6 +1212,8 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	if (retval)
 		goto out_deallocate_doorbell;
 
+	dqm_lock(dqm);
+
 	list_add(&q->list, &qpd->queues_list);
 	qpd->queue_count++;
 	if (q->properties.is_active) {
@@ -1241,9 +1241,7 @@ out_deallocate_doorbell:
 out_deallocate_sdma_queue:
 	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
 		deallocate_sdma_queue(dqm, q->sdma_id);
-out_unlock:
-	dqm_unlock(dqm);
-
+out:
 	return retval;
 }
 
@@ -1406,8 +1404,6 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 			qpd->reset_wavefronts = true;
 	}
 
-	mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
-
 	/*
 	 * Unconditionally decrement this counter, regardless of the queue's
 	 * type
@@ -1418,6 +1414,9 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 
 	dqm_unlock(dqm);
 
+	/* Do uninit_mqd after dqm_unlock(dqm) to avoid circular locking */
+	mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
+
 	return retval;
 
 failed:
@@ -1641,7 +1640,11 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 		qpd->reset_wavefronts = false;
 	}
 
-	/* lastly, free mqd resources */
+	dqm_unlock(dqm);
+
+	/* Lastly, free mqd resources.
+	 * Do uninit_mqd() after dqm_unlock to avoid circular locking.
+	 */
 	list_for_each_entry_safe(q, next, &qpd->queues_list, list) {
 		mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
@@ -1655,7 +1658,6 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 	}
 
 out:
-	dqm_unlock(dqm);
 	return retval;
 }