Re: [PATCH v2 25/34] drm/xe/vf: Abort VF post migration recovery on failure

["Lis, Tomasz" <tomasz.lis@intel.com>]

[-- Attachment #1: Type: text/plain, Size: 3533 bytes --]


On 9/24/2025 3:15 AM, Matthew Brost wrote:
> If VF post-migration recovery fails, the device is wedged. However,
> submission queues still need to be enabled for proper cleanup. In such
> cases, call into the GuC submission backend to restart all queues that
> were previously paused.
>
> Signed-off-by: Matthew Brost<matthew.brost@intel.com>
> ---
>   drivers/gpu/drm/xe/xe_gt_sriov_vf.c | 10 ++++++++++
>   drivers/gpu/drm/xe/xe_guc_submit.c  | 20 ++++++++++++++++++++
>   drivers/gpu/drm/xe/xe_guc_submit.h  |  1 +
>   3 files changed, 31 insertions(+)
>
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> index 34e57f44fbf4..a987560de2c7 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> @@ -1224,6 +1224,15 @@ static void vf_post_migration_kickstart(struct xe_gt *gt)
>   	xe_guc_submit_unpause(&gt->uc.guc);
>   }
>   
> +static void vf_post_migration_abort(struct xe_gt *gt)
> +{
> +	spin_lock_irq(&gt->sriov.vf.migration.lock);
> +	WRITE_ONCE(gt->sriov.vf.migration.recovery_inprogress, false);
> +	spin_unlock_irq(&gt->sriov.vf.migration.lock);
> +
> +	xe_guc_submit_pause_abort(&gt->uc.guc);
> +}
> +
>   static int vf_post_migration_notify_resfix_done(struct xe_gt *gt)
>   {
>   	bool skip_resfix = false;
> @@ -1280,6 +1289,7 @@ static void vf_post_migration_recovery(struct xe_gt *gt)
>   	xe_gt_sriov_notice(gt, "migration recovery ended\n");
>   	return;
>   fail:
> +	vf_post_migration_abort(gt);
>   	xe_pm_runtime_put(xe);
>   	xe_gt_sriov_err(gt, "migration recovery failed (%pe)\n", ERR_PTR(err));
>   	xe_device_declare_wedged(xe);

We could alter the order here to make sure all queues have cleanup 
triggered. Now only the ones which were previously killed/banned/wedged 
have that.

Not sure if it would bring any benefits though.

> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
> index 52b86cab4ec5..8bee65dd9ca6 100644
> --- a/drivers/gpu/drm/xe/xe_guc_submit.c
> +++ b/drivers/gpu/drm/xe/xe_guc_submit.c
> @@ -2345,6 +2345,26 @@ void xe_guc_submit_unpause(struct xe_guc *guc)
>   	wake_up_all(&guc->ct.wq);
>   }
>   
> +/**
> + * xe_guc_submit_abort - Avort all paused submission task on given GuC.

typo - Avort

-Tomasz

> + * @guc: the &xe_guc struct instance whose scheduler is to be aborted
> + */
> +void xe_guc_submit_pause_abort(struct xe_guc *guc)
> +{
> +	struct xe_exec_queue *q;
> +	unsigned long index;
> +
> +	mutex_lock(&guc->submission_state.lock);
> +	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
> +		struct xe_gpu_scheduler *sched = &q->guc->sched;
> +
> +		xe_sched_submission_start(sched);
> +		if (exec_queue_killed_or_banned_or_wedged(q))
> +			xe_guc_exec_queue_trigger_cleanup(q);
> +	}
> +	mutex_unlock(&guc->submission_state.lock);
> +}
> +
>   static struct xe_exec_queue *
>   g2h_exec_queue_lookup(struct xe_guc *guc, u32 guc_id)
>   {
> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
> index f535fe3895e5..fe82c317048e 100644
> --- a/drivers/gpu/drm/xe/xe_guc_submit.h
> +++ b/drivers/gpu/drm/xe/xe_guc_submit.h
> @@ -22,6 +22,7 @@ void xe_guc_submit_stop(struct xe_guc *guc);
>   int xe_guc_submit_start(struct xe_guc *guc);
>   void xe_guc_submit_pause(struct xe_guc *guc);
>   void xe_guc_submit_unpause(struct xe_guc *guc);
> +void xe_guc_submit_pause_abort(struct xe_guc *guc);
>   void xe_guc_submit_wedge(struct xe_guc *guc);
>   
>   int xe_guc_read_stopped(struct xe_guc *guc);

[-- Attachment #2: Type: text/html, Size: 4286 bytes --]