Re: [PATCH v4 9/9] drm/amdgpu: add lock in kfd_process_dequeue_from_device

[Felix Kuehling <felix.kuehling@amd.com>]

On 2024-06-04 21:33, Yunxiang Li wrote:
> We need to take the reset domain lock before talking to MES. While in
> this case we can take the lock inside the mes helper. We can't do so for
> most other mes helpers since they are used during reset. So for
> consistency sake we add the lock here.
>
> Signed-off-by: Yunxiang Li <Yunxiang.Li@amd.com>

Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>


> ---
>   drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 9 +++++++--
>   1 file changed, 7 insertions(+), 2 deletions(-)
>
> 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 86ea610b16f3..21f5a1fb3bf8 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
> @@ -28,6 +28,7 @@
>   #include "kfd_priv.h"
>   #include "kfd_kernel_queue.h"
>   #include "amdgpu_amdkfd.h"
> +#include "amdgpu_reset.h"
>   
>   static inline struct process_queue_node *get_queue_by_qid(
>   			struct process_queue_manager *pqm, unsigned int qid)
> @@ -87,8 +88,12 @@ void kfd_process_dequeue_from_device(struct kfd_process_device *pdd)
>   		return;
>   
>   	dev->dqm->ops.process_termination(dev->dqm, &pdd->qpd);
> -	if (dev->kfd->shared_resources.enable_mes)
> -		amdgpu_mes_flush_shader_debugger(dev->adev, pdd->proc_ctx_gpu_addr);
> +	if (dev->kfd->shared_resources.enable_mes &&
> +	    down_read_trylock(&dev->adev->reset_domain->sem)) {
> +		amdgpu_mes_flush_shader_debugger(dev->adev,
> +						 pdd->proc_ctx_gpu_addr);
> +		up_read(&dev->adev->reset_domain->sem);
> +	}
>   	pdd->already_dequeued = true;
>   }
>