[PATCH 3/3] drm/xe/guc: Cancel ongoing H2G requests when stopping CT

[Cavitt, Jonathan]

> 
> -----Original Message-----
From: Intel-xe <intel-xe-bounces at lists.freedesktop.org> On Behalf Of Michal Wajdeczko
Sent: Wednesday, July 9, 2025 10:41 AM
To: intel-xe at lists.freedesktop.org
Cc: Wajdeczko, Michal <Michal.Wajdeczko at intel.com>; Brost, Matthew <matthew.brost at intel.com>
Subject: [PATCH 3/3] drm/xe/guc: Cancel ongoing H2G requests when stopping CT
> 
> Once we have started a GT reset sequence, which includes stopping
> GuC CTB communication, we should also cancel all onging H2G send-
> recv requests, as either GuC is already dead, or due to imminent
> reset GuC will not be able to reply, or due to internal cleanup
> we will loose pending fences. With this we will report dedicated
> -ECANCELED error instead of misleading -ETIME.
> 
> Signed-off-by: Michal Wajdeczko <michal.wajdeczko at intel.com>
> Cc: Matthew Brost <matthew.brost at intel.com>

s/onging/ongoing
s/loose/lose

And also, are we certain that reporting -ECANCELED here won't result
in some test failure due to expecting -ETIME in this failure case?  I'd
not expect so, but I'd like to be certain before proceeding.
Otherwise, though:
Reviewed-by: Jonathan Cavitt <jonathan.cavitt at intel.com>
-Jonathan Cavitt

> ---
>  drivers/gpu/drm/xe/xe_guc_ct.c | 24 ++++++++++++++++++++++++
>  1 file changed, 24 insertions(+)
> 
> diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
> index 17e5870baf33..b6acccfcd351 100644
> --- a/drivers/gpu/drm/xe/xe_guc_ct.c
> +++ b/drivers/gpu/drm/xe/xe_guc_ct.c
> @@ -85,6 +85,7 @@ struct g2h_fence {
>  	u16 error;
>  	u16 hint;
>  	u16 reason;
> +	bool cancel;
>  	bool retry;
>  	bool fail;
>  	bool done;
> @@ -103,6 +104,13 @@ static void g2h_fence_init(struct g2h_fence *g2h_fence, u32 *response_buffer)
>  	g2h_fence->seqno = ~0x0;
>  }
>  
> +static void g2h_fence_cancel(struct g2h_fence *g2h_fence)
> +{
> +	g2h_fence->cancel = true;
> +	g2h_fence->fail = true;
> +	g2h_fence->done = true;
> +}
> +
>  static bool g2h_fence_needs_alloc(struct g2h_fence *g2h_fence)
>  {
>  	return g2h_fence->seqno == ~0x0;
> @@ -388,6 +396,8 @@ static void guc_ct_change_state(struct xe_guc_ct *ct,
>  				enum xe_guc_ct_state state)
>  {
>  	struct xe_gt *gt = ct_to_gt(ct);
> +	struct g2h_fence *g2h_fence;
> +	unsigned long idx;
>  
>  	mutex_lock(&ct->lock);		/* Serialise dequeue_one_g2h() */
>  	spin_lock_irq(&ct->fast_lock);	/* Serialise CT fast-path */
> @@ -406,6 +416,14 @@ static void guc_ct_change_state(struct xe_guc_ct *ct,
>  
>  	spin_unlock_irq(&ct->fast_lock);
>  
> +	/* cancel all in-flight send-recv requests */
> +	xa_for_each(&ct->fence_lookup, idx, g2h_fence)
> +		g2h_fence_cancel(g2h_fence);
> +
> +	/* make sure guc_ct_send_recv() will see g2h_fence changes */
> +	smp_mb();
> +	wake_up_all(&ct->g2h_fence_wq);
> +
>  	/*
>  	 * Lockdep doesn't like this under the fast lock and he destroy only
>  	 * needs to be serialized with the send path which ct lock provides.
> @@ -1098,6 +1116,11 @@ static int guc_ct_send_recv(struct xe_guc_ct *ct, const u32 *action, u32 len,
>  		goto retry;
>  	}
>  	if (g2h_fence.fail) {
> +		if (g2h_fence.cancel) {
> +			xe_gt_dbg(gt, "H2G request %#x canceled!\n", action[0]);
> +			ret = -ECANCELED;
> +			goto unlock;
> +		}
>  		xe_gt_err(gt, "H2G request %#x failed: error %#x hint %#x\n",
>  			  action[0], g2h_fence.error, g2h_fence.hint);
>  		ret = -EIO;
> @@ -1106,6 +1129,7 @@ static int guc_ct_send_recv(struct xe_guc_ct *ct, const u32 *action, u32 len,
>  	if (ret > 0)
>  		ret = response_buffer ? g2h_fence.response_len : g2h_fence.response_data;
>  
> +unlock:
>  	mutex_unlock(&ct->lock);
>  
>  	return ret;
> -- 
> 2.47.1
> 
>