Re: [PATCH 06/27] drm/i915/guc: Workaround reset G2H is received after schedule done G2H

[Daniele Ceraolo Spurio <daniele.ceraolospurio@xxxxxxxxx>]

On 8/25/2021 8:23 PM, Matthew Brost wrote:
> If the context is reset as a result of the request cancellation the
> context reset G2H is received after schedule disable done G2H which is
> the wrong order. The schedule disable done G2H release the waiting
> request cancellation code which resubmits the context. This races
> with the context reset G2H which also wants to resubmit the context but
> in this case it really should be a NOP as request cancellation code owns
> the resubmit. Use some clever tricks of checking the context state to
> seal this race until the GuC firmware is fixed.
>
> v2:
>   (Checkpatch)
>    - Fix typos
> v3:
>   (Daniele)
>    - State that is a bug in the GuC firmware
>
> Fixes: 62eaf0ae217d ("drm/i915/guc: Support request cancellation")
> Signed-off-by: Matthew Brost <matthew.brost@xxxxxxxxx>
> Cc: <stable@xxxxxxxxxxxxxxx>

Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@xxxxxxxxx>

Daniele

> ---
>   .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 41 ++++++++++++++++---
>   1 file changed, 35 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> index d94e7e1a876f..592b421e1429 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> @@ -831,17 +831,33 @@ __unwind_incomplete_requests(struct intel_context *ce)
>   static void __guc_reset_context(struct intel_context *ce, bool stalled)
>   {
>   	struct i915_request *rq;
> +	unsigned long flags;
>   	u32 head;
> +	bool skip = false;
>   
>   	intel_context_get(ce);
>   
>   	/*
> -	 * GuC will implicitly mark the context as non-schedulable
> -	 * when it sends the reset notification. Make sure our state
> -	 * reflects this change. The context will be marked enabled
> -	 * on resubmission.
> +	 * GuC will implicitly mark the context as non-schedulable when it sends
> +	 * the reset notification. Make sure our state reflects this change. The
> +	 * context will be marked enabled on resubmission.
> +	 *
> +	 * XXX: If the context is reset as a result of the request cancellation
> +	 * this G2H is received after the schedule disable complete G2H which is
> +	 * wrong as this creates a race between the request cancellation code
> +	 * re-submitting the context and this G2H handler. This is a bug in the
> +	 * GuC but can be worked around in the meantime but converting this to a
> +	 * NOP if a pending enable is in flight as this indicates that a request
> +	 * cancellation has occurred.
>   	 */
> -	clr_context_enabled(ce);
> +	spin_lock_irqsave(&ce->guc_state.lock, flags);
> +	if (likely(!context_pending_enable(ce)))
> +		clr_context_enabled(ce);
> +	else
> +		skip = true;
> +	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> +	if (unlikely(skip))
> +		goto out_put;
>   
>   	rq = intel_context_find_active_request(ce);
>   	if (!rq) {
> @@ -860,6 +876,7 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled)
>   out_replay:
>   	guc_reset_state(ce, head, stalled);
>   	__unwind_incomplete_requests(ce);
> +out_put:
>   	intel_context_put(ce);
>   }
>   
> @@ -1604,6 +1621,13 @@ static void guc_context_cancel_request(struct intel_context *ce,
>   			guc_reset_state(ce, intel_ring_wrap(ce->ring, rq->head),
>   					true);
>   		}
> +
> +		/*
> +		 * XXX: Racey if context is reset, see comment in
> +		 * __guc_reset_context().
> +		 */
> +		flush_work(&ce_to_guc(ce)->ct.requests.worker);
> +
>   		guc_context_unblock(ce);
>   	}
>   }
> @@ -2718,7 +2742,12 @@ static void guc_handle_context_reset(struct intel_guc *guc,
>   {
>   	trace_intel_context_reset(ce);
>   
> -	if (likely(!intel_context_is_banned(ce))) {
> +	/*
> +	 * XXX: Racey if request cancellation has occurred, see comment in
> +	 * __guc_reset_context().
> +	 */
> +	if (likely(!intel_context_is_banned(ce) &&
> +		   !context_blocked(ce))) {
>   		capture_error_state(guc, ce);
>   		guc_context_replay(ce);
>   	}