blk-throttle: add upgrade logic for LIMIT_LOW state

When queue is in LIMIT_LOW state and all cgroups with low limit cross
the bps/iops limitation, we will upgrade queue's state to
LIMIT_MAX. To determine if a cgroup exceeds its limitation, we check if
the cgroup has pending request. Since cgroup is throttled according to
the limit, pending request means the cgroup reaches the limit.

If a cgroup has limit set for both read and write, we consider the
combination of them for upgrade. The reason is read IO and write IO can
interfere with each other. If we do the upgrade based in one direction
IO, the other direction IO could be severly harmed.

For a cgroup hierarchy, there are two cases. Children has lower low
limit than parent. Parent's low limit is meaningless. If children's
bps/iops cross low limit, we can upgrade queue state. The other case is
children has higher low limit than parent. Children's low limit is
meaningless. As long as parent's bps/iops (which is a sum of childrens
bps/iops) cross low limit, we can upgrade queue state.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

block/blk-throttle.c

@@ -457,6 +457,7 @@ static void blk_throtl_update_limit_valid(struct throtl_data *td)
 	td->limit_valid[LIMIT_LOW] = low_valid;
 }
 
+static void throtl_upgrade_state(struct throtl_data *td);
 static void throtl_pd_offline(struct blkg_policy_data *pd)
 {
 	struct throtl_grp *tg = pd_to_tg(pd);
@@ -468,9 +469,8 @@ static void throtl_pd_offline(struct blkg_policy_data *pd)
 
 	blk_throtl_update_limit_valid(tg->td);
 
-	if (tg->td->limit_index == LIMIT_LOW &&
+	if (!tg->td->limit_valid[tg->td->limit_index])
-	    !tg->td->limit_valid[LIMIT_LOW])
+		throtl_upgrade_state(tg->td);
-		tg->td->limit_index = LIMIT_MAX;
 }
 
 static void throtl_pd_free(struct blkg_policy_data *pd)
@@ -1081,6 +1081,8 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq)
 	return nr_disp;
 }
 
+static bool throtl_can_upgrade(struct throtl_data *td,
+	struct throtl_grp *this_tg);
 /**
  * throtl_pending_timer_fn - timer function for service_queue->pending_timer
  * @arg: the throtl_service_queue being serviced
@@ -1107,6 +1109,9 @@ static void throtl_pending_timer_fn(unsigned long arg)
 	int ret;
 
 	spin_lock_irq(q->queue_lock);
+	if (throtl_can_upgrade(td, NULL))
+		throtl_upgrade_state(td);
+
 again:
 	parent_sq = sq->parent_sq;
 	dispatched = false;
@@ -1522,6 +1527,87 @@ static struct blkcg_policy blkcg_policy_throtl = {
 	.pd_free_fn		= throtl_pd_free,
 };
 
+static bool throtl_tg_can_upgrade(struct throtl_grp *tg)
+{
+	struct throtl_service_queue *sq = &tg->service_queue;
+	bool read_limit, write_limit;
+
+	/*
+	 * if cgroup reaches low limit (if low limit is 0, the cgroup always
+	 * reaches), it's ok to upgrade to next limit
+	 */
+	read_limit = tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW];
+	write_limit = tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW];
+	if (!read_limit && !write_limit)
+		return true;
+	if (read_limit && sq->nr_queued[READ] &&
+	    (!write_limit || sq->nr_queued[WRITE]))
+		return true;
+	if (write_limit && sq->nr_queued[WRITE] &&
+	    (!read_limit || sq->nr_queued[READ]))
+		return true;
+	return false;
+}
+
+static bool throtl_hierarchy_can_upgrade(struct throtl_grp *tg)
+{
+	while (true) {
+		if (throtl_tg_can_upgrade(tg))
+			return true;
+		tg = sq_to_tg(tg->service_queue.parent_sq);
+		if (!tg || !tg_to_blkg(tg)->parent)
+			return false;
+	}
+	return false;
+}
+
+static bool throtl_can_upgrade(struct throtl_data *td,
+	struct throtl_grp *this_tg)
+{
+	struct cgroup_subsys_state *pos_css;
+	struct blkcg_gq *blkg;
+
+	if (td->limit_index != LIMIT_LOW)
+		return false;
+
+	rcu_read_lock();
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
+		struct throtl_grp *tg = blkg_to_tg(blkg);
+
+		if (tg == this_tg)
+			continue;
+		if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children))
+			continue;
+		if (!throtl_hierarchy_can_upgrade(tg)) {
+			rcu_read_unlock();
+			return false;
+		}
+	}
+	rcu_read_unlock();
+	return true;
+}
+
+static void throtl_upgrade_state(struct throtl_data *td)
+{
+	struct cgroup_subsys_state *pos_css;
+	struct blkcg_gq *blkg;
+
+	td->limit_index = LIMIT_MAX;
+	rcu_read_lock();
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
+		struct throtl_grp *tg = blkg_to_tg(blkg);
+		struct throtl_service_queue *sq = &tg->service_queue;
+
+		tg->disptime = jiffies - 1;
+		throtl_select_dispatch(sq);
+		throtl_schedule_next_dispatch(sq, false);
+	}
+	rcu_read_unlock();
+	throtl_select_dispatch(&td->service_queue);
+	throtl_schedule_next_dispatch(&td->service_queue, false);
+	queue_work(kthrotld_workqueue, &td->dispatch_work);
+}
+
 bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 		    struct bio *bio)
 {
@@ -1544,14 +1630,20 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 
 	sq = &tg->service_queue;
 
+again:
 	while (true) {
 		/* throtl is FIFO - if bios are already queued, should queue */
 		if (sq->nr_queued[rw])
 			break;
 
 		/* if above limits, break to queue */
-		if (!tg_may_dispatch(tg, bio, NULL))
+		if (!tg_may_dispatch(tg, bio, NULL)) {
+			if (throtl_can_upgrade(tg->td, tg)) {
+				throtl_upgrade_state(tg->td);
+				goto again;
+			}
 			break;
+		}
 
 		/* within limits, let's charge and dispatch directly */
 		throtl_charge_bio(tg, bio);