Re: [PATCH] drm/xe: Add wait for completion after gt force reset

["Nilawar, Badal" <badal.nilawar@intel.com>]

I think title should be make sysfs  gt force reset synchronous.

On 14-12-2023 15:36, Karthik Poosa wrote:
> Wait for gt reset to complete before returning from force_reset
> sysfs call. Without this igt test freq_reset_multiple fails
> sporadically in case xe_guc_pc is not started.
> 
> Testcase: igt@xe_guc_pc@freq_reset_multiple
> Signed-off-by: Karthik Poosa <karthik.poosa@intel.com>
> ---
>   drivers/gpu/drm/xe/xe_gt.c         |  3 +++
>   drivers/gpu/drm/xe/xe_gt_debugfs.c | 10 ++++++++++
>   drivers/gpu/drm/xe/xe_gt_types.h   |  3 +++
>   3 files changed, 16 insertions(+)
> 
> diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
> index dfd9cf01a5d5..eb7552b6dfa5 100644
> --- a/drivers/gpu/drm/xe/xe_gt.c
> +++ b/drivers/gpu/drm/xe/xe_gt.c
> @@ -65,6 +65,7 @@ struct xe_gt *xe_gt_alloc(struct xe_tile *tile)
>   
>   	gt->tile = tile;
>   	gt->ordered_wq = alloc_ordered_workqueue("gt-ordered-wq", 0);
> +	init_completion(&gt->reset_done);
>   
>   	return gt;
>   }
> @@ -647,6 +648,8 @@ static int gt_reset(struct xe_gt *gt)
>   	xe_device_mem_access_put(gt_to_xe(gt));
>   	XE_WARN_ON(err);
>   
> +	complete(&gt->reset_done);
> +
>   	xe_gt_info(gt, "reset done\n");
>   
>   	return 0;
> diff --git a/drivers/gpu/drm/xe/xe_gt_debugfs.c b/drivers/gpu/drm/xe/xe_gt_debugfs.c
> index c4b67cf09f8f..49b30937a28b 100644
> --- a/drivers/gpu/drm/xe/xe_gt_debugfs.c
> +++ b/drivers/gpu/drm/xe/xe_gt_debugfs.c
> @@ -23,6 +23,8 @@
>   #include "xe_uc_debugfs.h"
>   #include "xe_wa.h"
>   
> +#define XE_GT_RESET_TIMEOUT_MS	(msecs_to_jiffies(5*1000))
> +
>   static struct xe_gt *node_to_gt(struct drm_info_node *node)
>   {
>   	return node->info_ent->data;
> @@ -58,9 +60,17 @@ static int hw_engines(struct seq_file *m, void *data)
>   static int force_reset(struct seq_file *m, void *data)
>   {
>   	struct xe_gt *gt = node_to_gt(m->private);
> +	struct xe_device *xe = gt_to_xe(gt);
> +	unsigned long timeout;
>   
This may not work when multiple processes tries gt reset simultaneously.
Check for reset in progress should be here.

Regards,
Badal
>   	xe_gt_reset_async(gt);
>   
> +	timeout = wait_for_completion_timeout(&gt->reset_done, XE_GT_RESET_TIMEOUT_MS);
> +	if (timeout == 0) {
> +		drm_err(&xe->drm, "gt reset timed out");
> +		return -ETIMEDOUT;
> +	}
> +
>   	return 0;
>   }
>   
> diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
> index f74684660475..6f2fb9e3cfea 100644
> --- a/drivers/gpu/drm/xe/xe_gt_types.h
> +++ b/drivers/gpu/drm/xe/xe_gt_types.h
> @@ -358,6 +358,9 @@ struct xe_gt {
>   		/** @oob: bitmap with active OOB workaroudns */
>   		unsigned long *oob;
>   	} wa_active;
> +
> +	/** @reset_done : Completion of GT reset */
> +	struct completion reset_done;
>   };
>   
>   #endif