[PATCH v2] drm/amdgpu: Fix two reset triggered in a row

[Christian König]

Am 23.04.24 um 16:44 schrieb Yunxiang Li:
> Some times a hang GPU causes multiple reset source to schedule resets,
> if the second source schedule after we call
> amdgpu_device_stop_pending_resets they will be able to trigger an
> unnecessary reset.
>
> Move amdgpu_device_stop_pending_resets to after the reset is already
> done, since any reset scheduled after that point would be legitimate.
> Remove unnecessary and incorrect checks for amdgpu_in_reset that was
> kinda serving this purpose.
>
> Signed-off-by: Yunxiang Li <Yunxiang.Li at amd.com>

Looks really good to me of hand, especially that so many cases of using 
amdgpu_in_reset() are removed.

But I'm just not deeply into each component to fully judge everything here.

So only Acked-by: Christian König <christian.koenig at amd.com> for now, if 
you need a more in deep review please ping me.

Regards,
Christian.

> ---
> v2: instead of adding amdgpu_in_reset check, move when we cancel pending
> resets
>
>   drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 17 ++++++++---------
>   drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c   |  2 +-
>   drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c      |  2 +-
>   drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c      |  2 +-
>   drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c      |  2 +-
>   5 files changed, 12 insertions(+), 13 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index f8a34db5d9e3..28f6a1c38b17 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -5061,8 +5061,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
>   retry:
>   	amdgpu_amdkfd_pre_reset(adev);
>   
> -	amdgpu_device_stop_pending_resets(adev);
> -
>   	if (from_hypervisor)
>   		r = amdgpu_virt_request_full_gpu(adev, true);
>   	else
> @@ -5813,13 +5811,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
>   				  r, adev_to_drm(tmp_adev)->unique);
>   			tmp_adev->asic_reset_res = r;
>   		}
> -
> -		if (!amdgpu_sriov_vf(tmp_adev))
> -			/*
> -			* Drop all pending non scheduler resets. Scheduler resets
> -			* were already dropped during drm_sched_stop
> -			*/
> -			amdgpu_device_stop_pending_resets(tmp_adev);
>   	}
>   
>   	/* Actual ASIC resets if needed.*/
> @@ -5841,6 +5832,14 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
>   			goto retry;
>   	}
>   
> +	list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
> +		/*
> +		 * Drop all pending non scheduler resets. Scheduler resets
> +		 * were already dropped during drm_sched_stop
> +		 */
> +		amdgpu_device_stop_pending_resets(tmp_adev);
> +	}
> +
>   skip_hw_reset:
>   
>   	/* Post ASIC reset for all devs .*/
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
> index 54ab51a4ada7..c2385178d6b3 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
> @@ -597,7 +597,7 @@ static void amdgpu_virt_update_vf2pf_work_item(struct work_struct *work)
>   	if (ret) {
>   		adev->virt.vf2pf_update_retry_cnt++;
>   		if ((adev->virt.vf2pf_update_retry_cnt >= AMDGPU_VF2PF_UPDATE_MAX_RETRY_LIMIT) &&
> -		    amdgpu_sriov_runtime(adev) && !amdgpu_in_reset(adev)) {
> +		    amdgpu_sriov_runtime(adev)) {
>   			amdgpu_ras_set_fed(adev, true);
>   			if (amdgpu_reset_domain_schedule(adev->reset_domain,
>   							  &adev->virt.flr_work))
> diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
> index 0c7275bca8f7..c5ba9c4757a8 100644
> --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
> +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
> @@ -319,7 +319,7 @@ static int xgpu_ai_mailbox_rcv_irq(struct amdgpu_device *adev,
>   
>   	switch (event) {
>   		case IDH_FLR_NOTIFICATION:
> -		if (amdgpu_sriov_runtime(adev) && !amdgpu_in_reset(adev))
> +		if (amdgpu_sriov_runtime(adev))
>   			WARN_ONCE(!amdgpu_reset_domain_schedule(adev->reset_domain,
>   								&adev->virt.flr_work),
>   				  "Failed to queue work! at %s",
> diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
> index aba00d961627..fa9d1b02f391 100644
> --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
> @@ -358,7 +358,7 @@ static int xgpu_nv_mailbox_rcv_irq(struct amdgpu_device *adev,
>   
>   	switch (event) {
>   	case IDH_FLR_NOTIFICATION:
> -		if (amdgpu_sriov_runtime(adev) && !amdgpu_in_reset(adev))
> +		if (amdgpu_sriov_runtime(adev))
>   			WARN_ONCE(!amdgpu_reset_domain_schedule(adev->reset_domain,
>   				   &adev->virt.flr_work),
>   				  "Failed to queue work! at %s",
> diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
> index 59f53c743362..14a065516ae4 100644
> --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
> +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
> @@ -560,7 +560,7 @@ static int xgpu_vi_mailbox_rcv_irq(struct amdgpu_device *adev,
>   		r = xgpu_vi_mailbox_rcv_msg(adev, IDH_FLR_NOTIFICATION);
>   
>   		/* only handle FLR_NOTIFY now */
> -		if (!r && !amdgpu_in_reset(adev))
> +		if (!r)
>   			WARN_ONCE(!amdgpu_reset_domain_schedule(adev->reset_domain,
>   								&adev->virt.flr_work),
>   				  "Failed to queue work! at %s",