Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/vapier...

[firefly-linux-kernel-4.4.55.git] / block / blk-throttle.c

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index b9412d1cea9e34a7fe74543dc4d883c5843ff8ec..a62be8d0dc1b34cfdf832947856669a8ee449a84 100644 (file)
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -78,6 +78,8 @@ struct throtl_grp {
 
        /* Some throttle limits got updated for the group */
        int limits_changed;
+
+       struct rcu_head rcu_head;
 };
 
 struct throtl_data
@@ -151,12 +153,31 @@ static inline struct throtl_grp *throtl_ref_get_tg(struct throtl_grp *tg)
        return tg;
 }
 
+static void throtl_free_tg(struct rcu_head *head)
+{
+       struct throtl_grp *tg;
+
+       tg = container_of(head, struct throtl_grp, rcu_head);
+       free_percpu(tg->blkg.stats_cpu);
+       kfree(tg);
+}
+
 static void throtl_put_tg(struct throtl_grp *tg)
 {
        BUG_ON(atomic_read(&tg->ref) <= 0);
        if (!atomic_dec_and_test(&tg->ref))
                return;
-       kfree(tg);
+
+       /*
+        * A group is freed in rcu manner. But having an rcu lock does not
+        * mean that one can access all the fields of blkg and assume these
+        * are valid. For example, don't try to follow throtl_data and
+        * request queue links.
+        *
+        * Having a reference to blkg under an rcu allows acess to only
+        * values local to groups like group stats and group rate limits
+        */
+       call_rcu(&tg->rcu_head, throtl_free_tg);
 }
 
 static void throtl_init_group(struct throtl_grp *tg)
@@ -208,6 +229,22 @@ __throtl_tg_fill_dev_details(struct throtl_data *td, struct throtl_grp *tg)
        }
 }
 
+/*
+ * Should be called with without queue lock held. Here queue lock will be
+ * taken rarely. It will be taken only once during life time of a group
+ * if need be
+ */
+static void
+throtl_tg_fill_dev_details(struct throtl_data *td, struct throtl_grp *tg)
+{
+       if (!tg || tg->blkg.dev)
+               return;
+
+       spin_lock_irq(td->queue->queue_lock);
+       __throtl_tg_fill_dev_details(td, tg);
+       spin_unlock_irq(td->queue->queue_lock);
+}
+
 static void throtl_init_add_tg_lists(struct throtl_data *td,
                        struct throtl_grp *tg, struct blkio_cgroup *blkcg)
 {
@@ -229,11 +266,19 @@ static void throtl_init_add_tg_lists(struct throtl_data *td,
 static struct throtl_grp *throtl_alloc_tg(struct throtl_data *td)
 {
        struct throtl_grp *tg = NULL;
+       int ret;
 
        tg = kzalloc_node(sizeof(*tg), GFP_ATOMIC, td->queue->node);
        if (!tg)
                return NULL;
 
+       ret = blkio_alloc_blkg_stats(&tg->blkg);
+
+       if (ret) {
+               kfree(tg);
+               return NULL;
+       }
+
        throtl_init_group(tg);
        return tg;
 }
@@ -637,6 +682,12 @@ static bool tg_with_in_bps_limit(struct throtl_data *td, struct throtl_grp *tg,
        return 0;
 }
 
+static bool tg_no_rule_group(struct throtl_grp *tg, bool rw) {
+       if (tg->bps[rw] == -1 && tg->iops[rw] == -1)
+               return 1;
+       return 0;
+}
+
 /*
  * Returns whether one can dispatch a bio or not. Also returns approx number
  * of jiffies to wait before this bio is with-in IO rate and can be dispatched
@@ -701,10 +752,6 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
        tg->bytes_disp[rw] += bio->bi_size;
        tg->io_disp[rw]++;
 
-       /*
-        * TODO: This will take blkg->stats_lock. Figure out a way
-        * to avoid this cost.
-        */
        blkiocg_update_dispatch_stats(&tg->blkg, bio->bi_size, rw, sync);
 }
 
@@ -1082,12 +1129,39 @@ int blk_throtl_bio(struct request_queue *q, struct bio **biop)
        struct throtl_grp *tg;
        struct bio *bio = *biop;
        bool rw = bio_data_dir(bio), update_disptime = true;
+       struct blkio_cgroup *blkcg;
 
        if (bio->bi_rw & REQ_THROTTLED) {
                bio->bi_rw &= ~REQ_THROTTLED;
                return 0;
        }
 
+       /*
+        * A throtl_grp pointer retrieved under rcu can be used to access
+        * basic fields like stats and io rates. If a group has no rules,
+        * just update the dispatch stats in lockless manner and return.
+        */
+
+       rcu_read_lock();
+       blkcg = task_blkio_cgroup(current);
+       tg = throtl_find_tg(td, blkcg);
+       if (tg) {
+               throtl_tg_fill_dev_details(td, tg);
+
+               if (tg_no_rule_group(tg, rw)) {
+                       blkiocg_update_dispatch_stats(&tg->blkg, bio->bi_size,
+                                       rw, bio->bi_rw & REQ_SYNC);
+                       rcu_read_unlock();
+                       return 0;
+               }
+       }
+       rcu_read_unlock();
+
+       /*
+        * Either group has not been allocated yet or it is not an unlimited
+        * IO group
+        */
+
        spin_lock_irq(q->queue_lock);
        tg = throtl_get_tg(td);