[Intel-gfx] [PATCH v2] drm/i915/gt: Protect execlists_hold/unhold from new waiters

[Mika Kuoppala]

Chris Wilson <chris at chris-wilson.co.uk> writes:

> As we may add new waiters to a request as it is being run, we need to
> mark the list iteration as being safe for concurrent addition.
>
> v2: Mika spotted that we used the same trick for signalers_list, so warn
> the compiler about the lockless walk there as well.
>
> Fixes: 32ff621fd744 ("drm/i915/gt: Allow temporary suspension of inflight requests")
> Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> Cc: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
> Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>

Reviewed-by: Mika Kuoppala <mika.kuoppala at linux.intel.com>

> ---
>  drivers/gpu/drm/i915/gt/intel_lrc.c   | 11 ++++++++---
>  drivers/gpu/drm/i915/i915_scheduler.c |  2 +-
>  2 files changed, 9 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
> index b350e01d86d2..ed1e4d883d47 100644
> --- a/drivers/gpu/drm/i915/gt/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
> @@ -1620,6 +1620,11 @@ last_active(const struct intel_engine_execlists *execlists)
>  				     &(rq__)->sched.waiters_list, \
>  				     wait_link)
>  
> +#define for_each_signaler(p__, rq__) \
> +	list_for_each_entry_lockless(p__, \
> +				     &(rq__)->sched.signalers_list, \
> +				     signal_link)
> +
>  static void defer_request(struct i915_request *rq, struct list_head * const pl)
>  {
>  	LIST_HEAD(list);
> @@ -2378,7 +2383,7 @@ static void __execlists_hold(struct i915_request *rq)
>  		list_move_tail(&rq->sched.link, &rq->engine->active.hold);
>  		i915_request_set_hold(rq);
>  
> -		list_for_each_entry(p, &rq->sched.waiters_list, wait_link) {
> +		for_each_waiter(p, rq) {
>  			struct i915_request *w =
>  				container_of(p->waiter, typeof(*w), sched);
>  
> @@ -2464,7 +2469,7 @@ static bool hold_request(const struct i915_request *rq)
>  	 * If one of our ancestors is on hold, we must also be on hold,
>  	 * otherwise we will bypass it and execute before it.
>  	 */
> -	list_for_each_entry(p, &rq->sched.signalers_list, signal_link) {
> +	for_each_signaler(p, rq) {
>  		const struct i915_request *s =
>  			container_of(p->signaler, typeof(*s), sched);
>  
> @@ -2496,7 +2501,7 @@ static void __execlists_unhold(struct i915_request *rq)
>  		RQ_TRACE(rq, "hold release\n");
>  
>  		/* Also release any children on this engine that are ready */
> -		list_for_each_entry(p, &rq->sched.waiters_list, wait_link) {
> +		for_each_waiter(p, rq) {
>  			struct i915_request *w =
>  				container_of(p->waiter, typeof(*w), sched);
>  
> diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
> index 9cbd31443eb0..a9666df1d842 100644
> --- a/drivers/gpu/drm/i915/i915_scheduler.c
> +++ b/drivers/gpu/drm/i915/i915_scheduler.c
> @@ -432,7 +432,7 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
>  		    !node_started(signal))
>  			node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN;
>  
> -		list_add(&dep->signal_link, &node->signalers_list);
> +		list_add_rcu(&dep->signal_link, &node->signalers_list);
>  		list_add_rcu(&dep->wait_link, &signal->waiters_list);
>  
>  		/*
> -- 
> 2.25.0