Re: [Intel-gfx] [PATCH 13/27] drm/i915/guc: Ensure GuC schedule operations do not operate on child contexts

[John Harrison <john.c.harrison@intel.com>]

On 8/20/2021 15:44, Matthew Brost wrote:
> In GuC parent-child contexts the parent context controls the scheduling,
> ensure only the parent does the scheduling operations.
>
> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> ---
>   .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 24 ++++++++++++++-----
>   1 file changed, 18 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 dbcb9ab28a9a..00d54bb00bfb 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> @@ -320,6 +320,12 @@ static void decr_context_committed_requests(struct intel_context *ce)
>   	GEM_BUG_ON(ce->guc_state.number_committed_requests < 0);
>   }
>   
> +static struct intel_context *
> +request_to_scheduling_context(struct i915_request *rq)
> +{
> +	return intel_context_to_parent(rq->context);
> +}
> +
>   static bool context_guc_id_invalid(struct intel_context *ce)
>   {
>   	return ce->guc_id.id == GUC_INVALID_LRC_ID;
> @@ -1684,6 +1690,7 @@ static void __guc_context_sched_disable(struct intel_guc *guc,
>   
>   	GEM_BUG_ON(guc_id == GUC_INVALID_LRC_ID);
>   
> +	GEM_BUG_ON(intel_context_is_child(ce));
>   	trace_intel_context_sched_disable(ce);
>   
>   	guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action),
> @@ -1898,6 +1905,8 @@ static void guc_context_sched_disable(struct intel_context *ce)
>   	u16 guc_id;
>   	bool enabled;
>   
> +	GEM_BUG_ON(intel_context_is_child(ce));
> +
>   	if (submission_disabled(guc) || context_guc_id_invalid(ce) ||
>   	    !lrc_desc_registered(guc, ce->guc_id.id)) {
>   		spin_lock_irqsave(&ce->guc_state.lock, flags);
> @@ -2286,6 +2295,8 @@ static void guc_signal_context_fence(struct intel_context *ce)
>   {
>   	unsigned long flags;
>   
> +	GEM_BUG_ON(intel_context_is_child(ce));
> +
>   	spin_lock_irqsave(&ce->guc_state.lock, flags);
>   	clr_context_wait_for_deregister_to_register(ce);
>   	__guc_signal_context_fence(ce);
> @@ -2315,7 +2326,7 @@ static void guc_context_init(struct intel_context *ce)
>   
>   static int guc_request_alloc(struct i915_request *rq)
>   {
> -	struct intel_context *ce = rq->context;
> +	struct intel_context *ce = request_to_scheduling_context(rq);
>   	struct intel_guc *guc = ce_to_guc(ce);
>   	unsigned long flags;
>   	int ret;
> @@ -2358,11 +2369,12 @@ static int guc_request_alloc(struct i915_request *rq)
>   	 * exhausted and return -EAGAIN to the user indicating that they can try
>   	 * again in the future.
>   	 *
> -	 * There is no need for a lock here as the timeline mutex ensures at
> -	 * most one context can be executing this code path at once. The
> -	 * guc_id_ref is incremented once for every request in flight and
> -	 * decremented on each retire. When it is zero, a lock around the
> -	 * increment (in pin_guc_id) is needed to seal a race with unpin_guc_id.
> +	 * There is no need for a lock here as the timeline mutex (or
> +	 * parallel_submit mutex in the case of multi-lrc) ensures at most one
> +	 * context can be executing this code path at once. The guc_id_ref is
Isn't that now two? One uni-LRC holding the timeline mutex and one 
multi-LRC holding the parallel submit mutex?

John.

> +	 * incremented once for every request in flight and decremented on each
> +	 * retire. When it is zero, a lock around the increment (in pin_guc_id)
> +	 * is needed to seal a race with unpin_guc_id.
>   	 */
>   	if (atomic_add_unless(&ce->guc_id.ref, 1, 0))
>   		goto out;