1 files changed, 67 insertions, 29 deletions

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index be185886e4fc..a18b2a244706 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -221,6 +221,8 @@ static void remove_from_engine(struct i915_request *rq)
 		locked = engine;
 	}
 	list_del_init(&rq->sched.link);
+	clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
+	clear_bit(I915_FENCE_FLAG_HOLD, &rq->fence.flags);
 	spin_unlock_irq(&locked->active.lock);
 }
 
@@ -273,7 +275,7 @@ bool i915_request_retire(struct i915_request *rq)
 	spin_unlock_irq(&rq->lock);
 
 	remove_from_client(rq);
-	list_del(&rq->link);
+	list_del_rcu(&rq->link);
 
 	intel_context_exit(rq->context);
 	intel_context_unpin(rq->context);
@@ -408,8 +410,10 @@ bool __i915_request_submit(struct i915_request *request)
 xfer:	/* We may be recursing from the signal callback of another i915 fence */
 	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
 
-	if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags))
+	if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags)) {
 		list_move_tail(&request->sched.link, &engine->active.requests);
+		clear_bit(I915_FENCE_FLAG_PQUEUE, &request->fence.flags);
+	}
 
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) &&
 	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) &&
@@ -523,19 +527,31 @@ submit_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 	return NOTIFY_DONE;
 }
 
+static void irq_semaphore_cb(struct irq_work *wrk)
+{
+	struct i915_request *rq =
+		container_of(wrk, typeof(*rq), semaphore_work);
+
+	i915_schedule_bump_priority(rq, I915_PRIORITY_NOSEMAPHORE);
+	i915_request_put(rq);
+}
+
 static int __i915_sw_fence_call
 semaphore_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 {
-	struct i915_request *request =
-		container_of(fence, typeof(*request), semaphore);
+	struct i915_request *rq = container_of(fence, typeof(*rq), semaphore);
 
 	switch (state) {
 	case FENCE_COMPLETE:
-		i915_schedule_bump_priority(request, I915_PRIORITY_NOSEMAPHORE);
+		if (!(READ_ONCE(rq->sched.attr.priority) & I915_PRIORITY_NOSEMAPHORE)) {
+			i915_request_get(rq);
+			init_irq_work(&rq->semaphore_work, irq_semaphore_cb);
+			irq_work_queue(&rq->semaphore_work);
+		}
 		break;
 
 	case FENCE_FREE:
-		i915_request_put(request);
+		i915_request_put(rq);
 		break;
 	}
 
@@ -591,6 +607,8 @@ static void __i915_request_ctor(void *arg)
 	i915_sw_fence_init(&rq->submit, submit_notify);
 	i915_sw_fence_init(&rq->semaphore, semaphore_notify);
 
+	dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, 0, 0);
+
 	rq->file_priv = NULL;
 	rq->capture_list = NULL;
 
@@ -649,25 +667,30 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 		}
 	}
 
-	ret = intel_timeline_get_seqno(tl, rq, &seqno);
-	if (ret)
-		goto err_free;
-
 	rq->i915 = ce->engine->i915;
 	rq->context = ce;
 	rq->engine = ce->engine;
 	rq->ring = ce->ring;
 	rq->execution_mask = ce->engine->mask;
 
+	kref_init(&rq->fence.refcount);
+	rq->fence.flags = 0;
+	rq->fence.error = 0;
+	INIT_LIST_HEAD(&rq->fence.cb_list);
+
+	ret = intel_timeline_get_seqno(tl, rq, &seqno);
+	if (ret)
+		goto err_free;
+
+	rq->fence.context = tl->fence_context;
+	rq->fence.seqno = seqno;
+
 	RCU_INIT_POINTER(rq->timeline, tl);
 	RCU_INIT_POINTER(rq->hwsp_cacheline, tl->hwsp_cacheline);
 	rq->hwsp_seqno = tl->hwsp_seqno;
 
 	rq->rcustate = get_state_synchronize_rcu(); /* acts as smp_mb() */
 
-	dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock,
-		       tl->fence_context, seqno);
-
 	/* We bump the ref for the fence chain */
 	i915_sw_fence_reinit(&i915_request_get(rq)->submit);
 	i915_sw_fence_reinit(&i915_request_get(rq)->semaphore);
@@ -710,6 +733,8 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq->infix = rq->ring->emit; /* end of header; start of user payload */
 
 	intel_context_mark_active(ce);
+	list_add_tail_rcu(&rq->link, &tl->requests);
+
 	return rq;
 
 err_unwind:
@@ -763,16 +788,26 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 	struct dma_fence *fence;
 	int err;
 
-	GEM_BUG_ON(i915_request_timeline(rq) ==
-		   rcu_access_pointer(signal->timeline));
+	if (i915_request_timeline(rq) == rcu_access_pointer(signal->timeline))
+		return 0;
+
+	if (i915_request_started(signal))
+		return 0;
 
 	fence = NULL;
 	rcu_read_lock();
 	spin_lock_irq(&signal->lock);
-	if (!i915_request_started(signal) &&
-	    !list_is_first(&signal->link,
-			   &rcu_dereference(signal->timeline)->requests)) {
-		struct i915_request *prev = list_prev_entry(signal, link);
+	do {
+		struct list_head *pos = READ_ONCE(signal->link.prev);
+		struct i915_request *prev;
+
+		/* Confirm signal has not been retired, the link is valid */
+		if (unlikely(i915_request_started(signal)))
+			break;
+
+		/* Is signal the earliest request on its timeline? */
+		if (pos == &rcu_dereference(signal->timeline)->requests)
+			break;
 
 		/*
 		 * Peek at the request before us in the timeline. That
@@ -780,20 +815,25 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 		 * after acquiring a reference to it, confirm that it is
 		 * still part of the signaler's timeline.
 		 */
-		if (i915_request_get_rcu(prev)) {
-			if (list_next_entry(prev, link) == signal)
-				fence = &prev->fence;
-			else
-				i915_request_put(prev);
+		prev = list_entry(pos, typeof(*prev), link);
+		if (!i915_request_get_rcu(prev))
+			break;
+
+		/* After the strong barrier, confirm prev is still attached */
+		if (unlikely(READ_ONCE(prev->link.next) != &signal->link)) {
+			i915_request_put(prev);
+			break;
 		}
-	}
+
+		fence = &prev->fence;
+	} while (0);
 	spin_unlock_irq(&signal->lock);
 	rcu_read_unlock();
 	if (!fence)
 		return 0;
 
 	err = 0;
-	if (intel_timeline_sync_is_later(i915_request_timeline(rq), fence))
+	if (!intel_timeline_sync_is_later(i915_request_timeline(rq), fence))
 		err = i915_sw_fence_await_dma_fence(&rq->submit,
 						    fence, 0,
 						    I915_FENCE_GFP);
@@ -1231,8 +1271,6 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 							 0);
 	}
 
-	list_add_tail(&rq->link, &timeline->requests);
-
 	/*
 	 * Make sure that no request gazumped us - if it was allocated after
 	 * our i915_request_alloc() and called __i915_request_add() before
@@ -1292,9 +1330,9 @@ void __i915_request_queue(struct i915_request *rq,
 	 * decide whether to preempt the entire chain so that it is ready to
 	 * run at the earliest possible convenience.
 	 */
-	i915_sw_fence_commit(&rq->semaphore);
 	if (attr && rq->engine->schedule)
 		rq->engine->schedule(rq, attr);
+	i915_sw_fence_commit(&rq->semaphore);
 	i915_sw_fence_commit(&rq->submit);
 }