Re: [PATCH v4 20/34] drm/xe/vf: Use GUC_HXG_TYPE_EVENT for GuC context register

[Michal Wajdeczko <michal.wajdeczko@intel.com>]

On 10/2/2025 7:53 AM, Matthew Brost wrote:
> The only case where the GuC submission backend cannot reason 100%
> correctly is when a GuC context is registered during VF post-migration
> recovery. In this scenario, it's possible that the GuC context register
> H2G is processed, but the immediately following schedule-enable H2G gets
> lost.
> 
> A double register is harmless when using `GUC_HXG_TYPE_EVENT`, as GuC
> simply drops the duplicate H2G. To keep things simple, use
> `GUC_HXG_TYPE_EVENT` for all context registrations on VFs.
> 
> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_guc_ct.c | 32 ++++++++++++++++++++++++--------
>  1 file changed, 24 insertions(+), 8 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
> index d0fde371fae3..d84de8544532 100644
> --- a/drivers/gpu/drm/xe/xe_guc_ct.c
> +++ b/drivers/gpu/drm/xe/xe_guc_ct.c
> @@ -736,6 +736,26 @@ static u16 next_ct_seqno(struct xe_guc_ct *ct, bool is_g2h_fence)
>  	return seqno;
>  }
>  
> +#define MAKE_ACTION(type, __action)				\
> +({								\
> +	FIELD_PREP(GUC_HXG_MSG_0_TYPE, type) |			\
> +	FIELD_PREP(GUC_HXG_EVENT_MSG_0_ACTION |			\
> +		   GUC_HXG_EVENT_MSG_0_DATA0, __action);	\
> +})
> +
> +static bool vf_action_can_safely_fail(struct xe_device *xe, u32 action)
> +{
> +	/*
> +	 * If we are VF resuming, we can't exactly track if a context

s/resuming/recovering

> +	 * registration has been completed in the GuC state machine, it is

well, we can (by looking at H2G if that was processed) but to "simplify" we don't

> +	 * harmless to resend as it will just fail silently if
> +	 * GUC_HXG_TYPE_EVENT is used.
> +	 */
> +	return IS_SRIOV_VF(xe) &&

maybe also:
		xe_gt_recovery_inprogress(gt) &&

to limit our trick to recovery only ?

> +		(action == XE_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC ||
> +		 action == XE_GUC_ACTION_REGISTER_CONTEXT);
> +}
> +
>  #define H2G_CT_HEADERS (GUC_CTB_HDR_LEN + 1) /* one DW CTB header and one DW HxG header */
>  
>  static int h2g_write(struct xe_guc_ct *ct, const u32 *action, u32 len,
> @@ -807,18 +827,14 @@ static int h2g_write(struct xe_guc_ct *ct, const u32 *action, u32 len,
>  		FIELD_PREP(GUC_CTB_MSG_0_NUM_DWORDS, len) |
>  		FIELD_PREP(GUC_CTB_MSG_0_FENCE, ct_fence_value);
>  	if (want_response) {
> -		cmd[1] =
> -			FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_REQUEST) |
> -			FIELD_PREP(GUC_HXG_EVENT_MSG_0_ACTION |
> -				   GUC_HXG_EVENT_MSG_0_DATA0, action[0]);
> +		cmd[1] = MAKE_ACTION(GUC_HXG_TYPE_REQUEST, action[0]);
> +	} else if (vf_action_can_safely_fail(xe, action[0])) {
> +		cmd[1] = MAKE_ACTION(GUC_HXG_TYPE_EVENT, action[0]);
>  	} else {
>  		fast_req_track(ct, ct_fence_value,
>  			       FIELD_GET(GUC_HXG_EVENT_MSG_0_ACTION, action[0]));
>  
> -		cmd[1] =
> -			FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_FAST_REQUEST) |
> -			FIELD_PREP(GUC_HXG_EVENT_MSG_0_ACTION |
> -				   GUC_HXG_EVENT_MSG_0_DATA0, action[0]);
> +		cmd[1] = MAKE_ACTION(GUC_HXG_TYPE_FAST_REQUEST, action[0]);
>  	}
>  
>  	/* H2G header in cmd[1] replaces action[0] so: */