[PATCH v3 1/2] drm/xe: introduce xe_gt_reset and xe_gt_wait_for_reset

[Nirmoy Das]

On 12/11/2024 12:17 PM, Maciej Patelczyk wrote:
> Add synchronous version gt reset as there are few places where it
> is expected.
> Also add a wait helper to wait until gt reset is done.
>
> Signed-off-by: Maciej Patelczyk <maciej.patelczyk at intel.com>
> Reviewed-by: Lucas De Marchi <lucas.demarchi at intel.com>

Patch 2 needs this so the same fixes should be applies here too

Fixes: f3bc5bb4d53d ("drm/xe: Allow userspace to configure CCS mode")
Cc: <stable at vger.kernel.org> # v6.8+
Reviewed-by: Nirmoy Das <nirmoy.das at intel.com>

> ---
>  drivers/gpu/drm/xe/tests/xe_bo.c   |  7 +++----
>  drivers/gpu/drm/xe/tests/xe_mocs.c |  3 +--
>  drivers/gpu/drm/xe/xe_gt.h         | 25 +++++++++++++++++++++++++
>  drivers/gpu/drm/xe/xe_gt_debugfs.c |  4 +---
>  4 files changed, 30 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/tests/xe_bo.c b/drivers/gpu/drm/xe/tests/xe_bo.c
> index c9ec7a313c6b..a1af45e06189 100644
> --- a/drivers/gpu/drm/xe/tests/xe_bo.c
> +++ b/drivers/gpu/drm/xe/tests/xe_bo.c
> @@ -264,10 +264,9 @@ static int evict_test_run_tile(struct xe_device *xe, struct xe_tile *tile, struc
>  		 * however seems quite fragile not to also restart the GT. Try
>  		 * to do that here by triggering a GT reset.
>  		 */
> -		for_each_gt(__gt, xe, id) {
> -			xe_gt_reset_async(__gt);
> -			flush_work(&__gt->reset.worker);
> -		}
> +		for_each_gt(__gt, xe, id)
> +			xe_gt_reset(__gt);
> +
>  		if (err) {
>  			KUNIT_FAIL(test, "restore kernel err=%pe\n",
>  				   ERR_PTR(err));
> diff --git a/drivers/gpu/drm/xe/tests/xe_mocs.c b/drivers/gpu/drm/xe/tests/xe_mocs.c
> index 6f9b7a266b41..2698e433c6fa 100644
> --- a/drivers/gpu/drm/xe/tests/xe_mocs.c
> +++ b/drivers/gpu/drm/xe/tests/xe_mocs.c
> @@ -162,8 +162,7 @@ static int mocs_reset_test_run_device(struct xe_device *xe)
>  		if (flags & HAS_LNCF_MOCS)
>  			read_l3cc_table(gt, &mocs.table);
>  
> -		xe_gt_reset_async(gt);
> -		flush_work(&gt->reset.worker);
> +		xe_gt_reset(gt);
>  
>  		kunit_info(test, "mocs_reset_test after reset\n");
>  		if (flags & HAS_GLOBAL_MOCS)
> diff --git a/drivers/gpu/drm/xe/xe_gt.h b/drivers/gpu/drm/xe/xe_gt.h
> index 82b9b7f82fca..eb2946963420 100644
> --- a/drivers/gpu/drm/xe/xe_gt.h
> +++ b/drivers/gpu/drm/xe/xe_gt.h
> @@ -56,6 +56,31 @@ void xe_gt_sanitize(struct xe_gt *gt);
>  int xe_gt_sanitize_freq(struct xe_gt *gt);
>  void xe_gt_remove(struct xe_gt *gt);
>  
> +/**
> + * xe_gt_wait_for_reset - wait for gt's async reset to finalize.
> + * @gt: GT structure
> + * Return:
> + * %true if it waited for the work to finish execution,
> + * %false if there was no scheduled reset or it was done.
> + */
> +static inline bool xe_gt_wait_for_reset(struct xe_gt *gt)
> +{
> +	return flush_work(&gt->reset.worker);
> +}
> +
> +/**
> + * xe_gt_reset - perform synchronous reset
> + * @gt: GT structure
> + * Return:
> + * %true if it waited for the reset to finish,
> + * %false if there was no scheduled reset.
> + */
> +static inline bool xe_gt_reset(struct xe_gt *gt)
> +{
> +	xe_gt_reset_async(gt);
> +	return xe_gt_wait_for_reset(gt);
> +}
> +
>  /**
>   * xe_gt_any_hw_engine_by_reset_domain - scan the list of engines and return the
>   * first that matches the same reset domain as @class
> diff --git a/drivers/gpu/drm/xe/xe_gt_debugfs.c b/drivers/gpu/drm/xe/xe_gt_debugfs.c
> index 3e8c351a0eab..e7792858b1e4 100644
> --- a/drivers/gpu/drm/xe/xe_gt_debugfs.c
> +++ b/drivers/gpu/drm/xe/xe_gt_debugfs.c
> @@ -132,11 +132,9 @@ static int force_reset(struct xe_gt *gt, struct drm_printer *p)
>  static int force_reset_sync(struct xe_gt *gt, struct drm_printer *p)
>  {
>  	xe_pm_runtime_get(gt_to_xe(gt));
> -	xe_gt_reset_async(gt);
> +	xe_gt_reset(gt);
>  	xe_pm_runtime_put(gt_to_xe(gt));
>  
> -	flush_work(&gt->reset.worker);
> -
>  	return 0;
>  }
>