Re: [PATCH v2 21/34] drm/xe/vf: Stop and flush CTs in VF post migration recovery

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

On 9/24/2025 3:15 AM, Matthew Brost wrote:
> Flushing CTs (i.e., progressing all pending G2H messages) gives VF
> post-migration recovery an accurate view of which H2G messages the GuC
> has processed, enabling the GuC submission state machine to correctly
> rebuild all state.
> 
> Also, stop all CT traffic, as the CT is not live during VF
> post-migration recovery.

this is what I was looking for, some comments below, but LGTM
> 
> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_gt_sriov_vf.c |  2 ++
>  drivers/gpu/drm/xe/xe_guc_ct.c      | 11 +++++++++++
>  drivers/gpu/drm/xe/xe_guc_ct.h      |  1 +
>  3 files changed, 14 insertions(+)
> 
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> index e79ab4a2a273..071c2c5e0d0a 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> @@ -23,6 +23,7 @@
>  #include "xe_gt_sriov_vf.h"
>  #include "xe_gt_sriov_vf_types.h"
>  #include "xe_guc.h"
> +#include "xe_guc_ct.h"
>  #include "xe_guc_hxg_helpers.h"
>  #include "xe_guc_relay.h"
>  #include "xe_guc_submit.h"
> @@ -1185,6 +1186,7 @@ static void vf_post_migration_shutdown(struct xe_gt *gt)
>  	gt->sriov.vf.migration.recovery_queued = false;
>  	spin_unlock_irq(&gt->sriov.vf.migration.lock);
>  
> +	xe_guc_ct_flush(&gt->uc.guc.ct);
>  	xe_guc_submit_pause(&gt->uc.guc);
>  }
>  
> diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
> index aa9fb08f7856..d4a132b81b86 100644
> --- a/drivers/gpu/drm/xe/xe_guc_ct.c
> +++ b/drivers/gpu/drm/xe/xe_guc_ct.c
> @@ -574,6 +574,17 @@ void xe_guc_ct_disable(struct xe_guc_ct *ct)
>  	stop_g2h_handler(ct);
>  }
>  
> +/**
> + * xe_guc_ct_flush - Flush all processing of G2H / H2G

Flush and stop ?

> + * @ct: the &xe_guc_ct
> + */
> +void xe_guc_ct_flush(struct xe_guc_ct *ct)
> +{

do we care about ct being not initialized yet?

> +	receive_g2h(ct);
> +	wake_up_all(&ct->g2h_fence_wq);

this is part of the guc_ct_change_state() called by below stop
isn't that sufficient ?

> +	xe_guc_ct_stop(ct);
> +}
> +
>  /**
>   * xe_guc_ct_stop - Set GuC to stopped state
>   * @ct: the &xe_guc_ct
> diff --git a/drivers/gpu/drm/xe/xe_guc_ct.h b/drivers/gpu/drm/xe/xe_guc_ct.h
> index d6c81325a76c..1e32a59817cc 100644
> --- a/drivers/gpu/drm/xe/xe_guc_ct.h
> +++ b/drivers/gpu/drm/xe/xe_guc_ct.h
> @@ -17,6 +17,7 @@ int xe_guc_ct_init_post_hwconfig(struct xe_guc_ct *ct);
>  int xe_guc_ct_enable(struct xe_guc_ct *ct);
>  void xe_guc_ct_disable(struct xe_guc_ct *ct);
>  void xe_guc_ct_stop(struct xe_guc_ct *ct);
> +void xe_guc_ct_flush(struct xe_guc_ct *ct);
>  void xe_guc_ct_fast_path(struct xe_guc_ct *ct);
>  
>  struct xe_guc_ct_snapshot *xe_guc_ct_snapshot_capture(struct xe_guc_ct *ct);