Re: [PATCH v3] drm/xe/xe_guc_ct: Exit CT submission fence wait on GT reset

[Matthew Brost <matthew.brost@intel.com>]

On Tue, Jan 06, 2026 at 08:55:34PM +0000, Jonathan Cavitt wrote:
> It's possible if unlikely that the GuC could be reset in the time
> between performing a guc_ct_send and the G2H fence completing in
> guc_ct_send_recv.  Exit early if this is occurs.
> 
> v2: Rebase
> 
> v3: goto retry_same_fence if ct is not alive (Stuart)
> 
> Suggested-by: Stuart Summers <stuart.summers@intel.com>
> Signed-off-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_guc_ct.c | 14 +++++++++-----
>  1 file changed, 9 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
> index dfbf76037b04..0bdcbe6503a7 100644
> --- a/drivers/gpu/drm/xe/xe_guc_ct.c
> +++ b/drivers/gpu/drm/xe/xe_guc_ct.c
> @@ -1238,6 +1238,10 @@ int xe_guc_ct_send_g2h_handler(struct xe_guc_ct *ct, const u32 *action, u32 len)
>  	return ret;
>  }
>  
> +#define ct_alive(ct)    \
> +	(xe_guc_ct_enabled(ct) && !ct->ctbs.h2g.info.broken && \
> +	 !ct->ctbs.g2h.info.broken)
> +
>  /*
>   * Check if a GT reset is in progress or will occur and if GT reset brought the
>   * CT back up. Randomly picking 5 seconds for an upper limit to do a GT a reset.
> @@ -1247,12 +1251,8 @@ static bool retry_failure(struct xe_guc_ct *ct, int ret)
>  	if (!(ret == -EDEADLK || ret == -EPIPE || ret == -ENODEV))
>  		return false;
>  
> -#define ct_alive(ct)	\
> -	(xe_guc_ct_enabled(ct) && !ct->ctbs.h2g.info.broken && \
> -	 !ct->ctbs.g2h.info.broken)
>  	if (!wait_event_interruptible_timeout(ct->wq, ct_alive(ct), HZ * 5))
>  		return false;
> -#undef ct_alive
>  
>  	return true;
>  }
> @@ -1304,7 +1304,11 @@ static int guc_ct_send_recv(struct xe_guc_ct *ct, const u32 *action, u32 len,
>  	/* READ_ONCEs pairs with WRITE_ONCEs in parse_g2h_response
>  	 * and g2h_fence_cancel.
>  	 */
> -	ret = wait_event_timeout(ct->g2h_fence_wq, READ_ONCE(g2h_fence.done), HZ);
> +	ret = wait_event_timeout(ct->g2h_fence_wq, !ct_alive(ct) ||
> +				 READ_ONCE(g2h_fence.done), HZ);
> +	if (!ct_alive(ct))

I think you only want to do this if no_fail is set, but again that is
dead code and likely doesn't even work as is. I don't handle the device
wedging nor does this patch, so either case could live lock.

Matt

> +		goto retry_same_fence;
> +
>  	if (!ret) {
>  		LNL_FLUSH_WORK(&ct->g2h_worker);
>  		if (READ_ONCE(g2h_fence.done)) {
> -- 
> 2.43.0
>