Re: [PATCH] drm/xe/vf: Retry GuC state reset until timeout

["K V P, Satyanarayana" <satyanarayana.k.v.p@intel.com>]

On 31-Aug-26 2:51 PM, Lukasz Laguna wrote:
> Instead of using a fixed number of GuC state reset retries, keep
> retrying until timeout with sleeps between attempts.
>
> Signed-off-by: Lukasz Laguna <lukasz.laguna@intel.com>
> ---
>   drivers/gpu/drm/xe/xe_gt_sriov_vf.c | 12 +++++++++---
>   1 file changed, 9 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> index 37899fcf5b22..01873896f77b 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> @@ -31,6 +31,7 @@
>   #include "xe_lrc.h"
>   #include "xe_memirq.h"
>   #include "xe_mmio.h"
> +#include "xe_sleep.h"
>   #include "xe_sriov.h"
>   #include "xe_sriov_vf.h"
>   #include "xe_sriov_vf_ccs.h"
> @@ -86,18 +87,23 @@ static int guc_action_vf_reset(struct xe_guc *guc)
>   	return ret > 0 ? -EPROTO : ret;
>   }
>   
> -#define GUC_RESET_VF_STATE_RETRY_MAX	10
> +#define GUC_RESET_VF_STATE_TIMEOUT_MS	10000

How is this 10 seconds timeout derived? Do we have any references for this?

- Satya.

> +#define GUC_RESET_VF_STATE_SLEEP_MS	10
> +
>   static int vf_reset_guc_state(struct xe_gt *gt)
>   {
> -	unsigned int retry = GUC_RESET_VF_STATE_RETRY_MAX;
>   	struct xe_guc *guc = &gt->uc.guc;
> +	unsigned long jiffies_end;
>   	int err;
>   
> +	jiffies_end = jiffies + msecs_to_jiffies(GUC_RESET_VF_STATE_TIMEOUT_MS);
>   	do {
>   		err = guc_action_vf_reset(guc);
>   		if (!err || err != -ETIMEDOUT)
>   			break;
> -	} while (--retry);
> +
> +		xe_sleep_relaxed_ms(GUC_RESET_VF_STATE_SLEEP_MS);
> +	} while (time_before(jiffies, jiffies_end));
>   
>   	if (unlikely(err))
>   		xe_gt_sriov_err(gt, "Failed to reset GuC state (%pe)\n", ERR_PTR(err));