[PATCH 2/3] drm/amdkfd: avoid HMM change cause circular lock dependency v2

Christian König ckoenig.leichtzumerken at gmail.com
Tue Feb 5 11:42:51 UTC 2019


Am 04.02.19 um 19:23 schrieb Yang, Philip:
> 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)

In general this sounds correct to me, but apart from that I don't know 
the code well enough to fully judge.

>
> Change-Id: I2ec09a47571f6b4c8eaef93f22c0a600f5f70153
> Signed-off-by: Philip Yang <Philip.Yang at amd.com>

Acked-by: Christian König <christian.koenig at amd.com>

> ---
>   .../drm/amd/amdkfd/kfd_device_queue_manager.c | 32 ++++++++++---------
>   1 file 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 8372556b52eb..efe0d3c0215b 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
> @@ -1156,21 +1156,17 @@ 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 =
> @@ -1181,6 +1177,9 @@ 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));
>   
> @@ -1188,6 +1187,7 @@ 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
> @@ -1196,9 +1196,7 @@ 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,
> @@ -1206,6 +1204,8 @@ 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) {
> @@ -1233,9 +1233,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
>   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;
>   }
>   
> @@ -1398,8 +1396,6 @@ 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
> @@ -1410,6 +1406,9 @@ 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:
> @@ -1631,7 +1630,11 @@ 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));
> @@ -1645,7 +1648,6 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
>   	}
>   
>   out:
> -	dqm_unlock(dqm);
>   	return retval;
>   }
>   



More information about the amd-gfx mailing list