Commit 53b3f8f4 authored by Dennis Li's avatar Dennis Li Committed by Alex Deucher
Browse files

drm/amdgpu: refine codes to avoid reentering GPU recovery 



if other threads have holden the reset lock, recovery will
fail to try_lock. Therefore we introduce atomic hive->in_reset
and adev->in_gpu_reset, to avoid reentering GPU recovery.

v2:
drop "? true : false" in the definition of amdgpu_in_reset

Reviewed-by: default avatarHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: default avatarDennis Li <Dennis.Li@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent c9977dff

drivers/gpu/drm/amd/amdgpu/amdgpu.h

+5 −1
Original line number Diff line number Diff line
@@ -949,7 +949,7 @@ struct amdgpu_device { 
	bool                            in_suspend;

	bool				in_hibernate;



	bool                            in_gpu_reset;

	atomic_t 			in_gpu_reset;

	enum pp_mp1_state               mp1_state;

	struct mutex  lock_reset;

	struct amdgpu_doorbell_index doorbell_index;
@@ -1267,4 +1267,8 @@ static inline bool amdgpu_is_tmz(struct amdgpu_device *adev) 
       return adev->gmc.tmz_enabled;

}



static inline int amdgpu_in_reset(struct amdgpu_device *adev)

{

	return atomic_read(&adev->in_gpu_reset);

}

#endif

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c

+1 −1
Original line number Diff line number Diff line
@@ -542,7 +542,7 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd, 
	uint32_t temp;

	struct v10_compute_mqd *m = get_mqd(mqd);



	if (adev->in_gpu_reset)

	if (amdgpu_in_reset(adev))

		return -EIO;



#if 0

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c

+1 −1
Original line number Diff line number Diff line
@@ -423,7 +423,7 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd, 
	unsigned long flags, end_jiffies;

	int retry;



	if (adev->in_gpu_reset)

	if (amdgpu_in_reset(adev))

		return -EIO;



	acquire_queue(kgd, pipe_id, queue_id);

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c

+1 −1
Original line number Diff line number Diff line
@@ -419,7 +419,7 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd, 
	int retry;

	struct vi_mqd *m = get_mqd(mqd);



	if (adev->in_gpu_reset)

	if (amdgpu_in_reset(adev))

		return -EIO;



	acquire_queue(kgd, pipe_id, queue_id);

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c

+1 −1
Original line number Diff line number Diff line
@@ -552,7 +552,7 @@ int kgd_gfx_v9_hqd_destroy(struct kgd_dev *kgd, void *mqd, 
	uint32_t temp;

	struct v9_mqd *m = get_mqd(mqd);



	if (adev->in_gpu_reset)

	if (amdgpu_in_reset(adev))

		return -EIO;



	acquire_queue(kgd, pipe_id, queue_id);