drm/i915/gt: Protect execlists_hold/unhold from new waiters

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: 7de814b5692e ("drm/i915/gt: Allow temporary suspension of inflight requests")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200207110213.2734386-1-chris@chris-wilson.co.uk

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 9808244cb8feb6e354fbb8f5f941bc9340e88f09..77bd8d8c027eacc177b6ea7dd63a5f1bd93a57f9 100644 (file)
--- 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 34b654b4e58af2b7fb3eb22b4bcecd65c74c9e2f..e19a37a83397ef98870949c669c38849874d4cf6 100644 (file)
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -433,7 +433,7 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
                        node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN;
 
                /* All set, now publish. Beware the lockless walkers. */
-               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);
 
                /*