From bab0557c8dca97b651a09a987337dbb55945d534 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 24 Dec 2020 13:55:40 +0000 Subject: [PATCH] drm/i915/gt: Remove virtual breadcrumb before transfer The issue with stale virtual breadcrumbs remain. Now we have the problem that if the irq-signaler is still referencing the stale breadcrumb as we transfer it to a new sibling, the list becomes spaghetti. This is a very small window, but that doesn't stop it being hit infrequently. To prevent the lists being tangled (the iterator starting on one engine's b->signalers but walking onto another list), always decouple the virtual breadcrumb on schedule-out and make sure that the walker has stepped out of the lists. Signed-off-by: Chris Wilson Reviewed-by: Matthew Brost Link: https://patchwork.freedesktop.org/patch/msgid/20201224135544.1713-5-chris@chris-wilson.co.uk --- drivers/gpu/drm/i915/gt/intel_breadcrumbs.c | 5 +++-- drivers/gpu/drm/i915/gt/intel_execlists_submission.c | 15 +++++++++++++++ 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index f96cd7d..8f7c859 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -451,15 +451,16 @@ void i915_request_cancel_breadcrumb(struct i915_request *rq) { struct intel_breadcrumbs *b = READ_ONCE(rq->engine)->breadcrumbs; struct intel_context *ce = rq->context; + unsigned long flags; bool release; if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) return; - spin_lock(&ce->signal_lock); + spin_lock_irqsave(&ce->signal_lock, flags); list_del_rcu(&rq->signal_link); release = remove_signaling_context(b, ce); - spin_unlock(&ce->signal_lock); + spin_unlock_irqrestore(&ce->signal_lock, flags); if (release) intel_context_put(ce); diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index b5f256b..1f6e9fe 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -581,6 +581,21 @@ static inline void execlists_schedule_in(struct i915_request *rq, int idx) static void kick_siblings(struct i915_request *rq, struct intel_context *ce) { struct virtual_engine *ve = container_of(ce, typeof(*ve), context); + struct intel_engine_cs *engine = rq->engine; + + /* Flush concurrent rcu iterators in signal_irq_work */ + if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags)) { + /* + * After this point, the rq may be transferred to a new + * sibling, so before we clear ce->inflight make sure that + * the context has been removed from the b->signalers and + * furthermore we need to make sure that the concurrent + * iterator in signal_irq_work is no longer following + * ce->signal_link. + */ + i915_request_cancel_breadcrumb(rq); + irq_work_sync(&engine->breadcrumbs->irq_work); + } if (READ_ONCE(ve->request)) tasklet_hi_schedule(&ve->base.execlists.tasklet); -- 2.7.4