[RFC v2 8/8] drm/amd/virt: Drop concurrent GPU reset protection for SRIOV

[Liu, Monk]

[AMD Official Use Only]

@Chen, Horace @Chen, JingWen @Deng, Emily

Please take a review on Andrey's patch 

Thanks 
-------------------------------------------------------------------
Monk Liu | Cloud GPU & Virtualization Solution | AMD
-------------------------------------------------------------------
we are hiring software manager for CVS core team
-------------------------------------------------------------------

-----Original Message-----
From: Koenig, Christian <Christian.Koenig at amd.com> 
Sent: Thursday, December 23, 2021 4:42 PM
To: Grodzovsky, Andrey <Andrey.Grodzovsky at amd.com>; dri-devel at lists.freedesktop.org; amd-gfx at lists.freedesktop.org
Cc: daniel at ffwll.ch; Liu, Monk <Monk.Liu at amd.com>; Chen, Horace <Horace.Chen at amd.com>
Subject: Re: [RFC v2 8/8] drm/amd/virt: Drop concurrent GPU reset protection for SRIOV

Am 22.12.21 um 23:14 schrieb Andrey Grodzovsky:
> Since now flr work is serialized against  GPU resets there is no need 
> for this.
>
> Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky at amd.com>

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

> ---
>   drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 11 -----------
>   drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | 11 -----------
>   2 files changed, 22 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c 
> b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
> index 487cd654b69e..7d59a66e3988 100644
> --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
> +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
> @@ -248,15 +248,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
>   	struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt);
>   	int timeout = AI_MAILBOX_POLL_FLR_TIMEDOUT;
>   
> -	/* block amdgpu_gpu_recover till msg FLR COMPLETE received,
> -	 * otherwise the mailbox msg will be ruined/reseted by
> -	 * the VF FLR.
> -	 */
> -	if (!down_write_trylock(&adev->reset_sem))
> -		return;
> -
>   	amdgpu_virt_fini_data_exchange(adev);
> -	atomic_set(&adev->in_gpu_reset, 1);
>   
>   	xgpu_ai_mailbox_trans_msg(adev, IDH_READY_TO_RESET, 0, 0, 0);
>   
> @@ -269,9 +261,6 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
>   	} while (timeout > 1);
>   
>   flr_done:
> -	atomic_set(&adev->in_gpu_reset, 0);
> -	up_write(&adev->reset_sem);
> -
>   	/* Trigger recovery for world switch failure if no TDR */
>   	if (amdgpu_device_should_recover_gpu(adev)
>   		&& (!amdgpu_device_has_job_running(adev) || diff --git 
> a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c 
> b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
> index e3869067a31d..f82c066c8e8d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
> @@ -277,15 +277,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
>   	struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt);
>   	int timeout = NV_MAILBOX_POLL_FLR_TIMEDOUT;
>   
> -	/* block amdgpu_gpu_recover till msg FLR COMPLETE received,
> -	 * otherwise the mailbox msg will be ruined/reseted by
> -	 * the VF FLR.
> -	 */
> -	if (!down_write_trylock(&adev->reset_sem))
> -		return;
> -
>   	amdgpu_virt_fini_data_exchange(adev);
> -	atomic_set(&adev->in_gpu_reset, 1);
>   
>   	xgpu_nv_mailbox_trans_msg(adev, IDH_READY_TO_RESET, 0, 0, 0);
>   
> @@ -298,9 +290,6 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
>   	} while (timeout > 1);
>   
>   flr_done:
> -	atomic_set(&adev->in_gpu_reset, 0);
> -	up_write(&adev->reset_sem);
> -
>   	/* Trigger recovery for world switch failure if no TDR */
>   	if (amdgpu_device_should_recover_gpu(adev)
>   		&& (!amdgpu_device_has_job_running(adev) ||