Commit b3b9f24f authored by Dennis Zhou (Facebook)'s avatar Dennis Zhou (Facebook) Committed by Jens Axboe

blkcg: change blkg reference counting to use percpu_ref

Now that every bio is associated with a blkg, this puts the use of
blkg_get, blkg_try_get, and blkg_put on the hot path. This switches over
the refcnt in blkg to use percpu_ref.
Signed-off-by: default avatarDennis Zhou <dennisszhou@gmail.com>
Acked-by: default avatarTejun Heo <tj@kernel.org>
Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
parent e2b09899
......@@ -84,6 +84,37 @@ static void blkg_free(struct blkcg_gq *blkg)
kfree(blkg);
}
static void __blkg_release(struct rcu_head *rcu)
{
struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head);
percpu_ref_exit(&blkg->refcnt);
/* release the blkcg and parent blkg refs this blkg has been holding */
css_put(&blkg->blkcg->css);
if (blkg->parent)
blkg_put(blkg->parent);
wb_congested_put(blkg->wb_congested);
blkg_free(blkg);
}
/*
* A group is RCU protected, 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 accesses to only values
* local to groups like group stats and group rate limits.
*/
static void blkg_release(struct percpu_ref *ref)
{
struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt);
call_rcu(&blkg->rcu_head, __blkg_release);
}
/**
* blkg_alloc - allocate a blkg
* @blkcg: block cgroup the new blkg is associated with
......@@ -110,7 +141,6 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
blkg->q = q;
INIT_LIST_HEAD(&blkg->q_node);
blkg->blkcg = blkcg;
atomic_set(&blkg->refcnt, 1);
/* root blkg uses @q->root_rl, init rl only for !root blkgs */
if (blkcg != &blkcg_root) {
......@@ -217,6 +247,11 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
blkg_get(blkg->parent);
}
ret = percpu_ref_init(&blkg->refcnt, blkg_release, 0,
GFP_NOWAIT | __GFP_NOWARN);
if (ret)
goto err_cancel_ref;
/* invoke per-policy init */
for (i = 0; i < BLKCG_MAX_POLS; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
......@@ -249,6 +284,8 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
blkg_put(blkg);
return ERR_PTR(ret);
err_cancel_ref:
percpu_ref_exit(&blkg->refcnt);
err_put_congested:
wb_congested_put(wb_congested);
err_put_css:
......@@ -387,7 +424,7 @@ static void blkg_destroy(struct blkcg_gq *blkg)
* Put the reference taken at the time of creation so that when all
* queues are gone, group can be destroyed.
*/
blkg_put(blkg);
percpu_ref_kill(&blkg->refcnt);
}
/**
......@@ -414,29 +451,6 @@ static void blkg_destroy_all(struct request_queue *q)
q->root_rl.blkg = NULL;
}
/*
* A group is RCU protected, 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 accesses to only values
* local to groups like group stats and group rate limits.
*/
void __blkg_release_rcu(struct rcu_head *rcu_head)
{
struct blkcg_gq *blkg = container_of(rcu_head, struct blkcg_gq, rcu_head);
/* release the blkcg and parent blkg refs this blkg has been holding */
css_put(&blkg->blkcg->css);
if (blkg->parent)
blkg_put(blkg->parent);
wb_congested_put(blkg->wb_congested);
blkg_free(blkg);
}
EXPORT_SYMBOL_GPL(__blkg_release_rcu);
/*
* The next function used by blk_queue_for_each_rl(). It's a bit tricky
* because the root blkg uses @q->root_rl instead of its own rl.
......
......@@ -126,7 +126,7 @@ struct blkcg_gq {
struct request_list rl;
/* reference count */
atomic_t refcnt;
struct percpu_ref refcnt;
/* is this blkg online? protected by both blkcg and q locks */
bool online;
......@@ -490,8 +490,7 @@ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
*/
static inline void blkg_get(struct blkcg_gq *blkg)
{
WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0);
atomic_inc(&blkg->refcnt);
percpu_ref_get(&blkg->refcnt);
}
/**
......@@ -503,7 +502,7 @@ static inline void blkg_get(struct blkcg_gq *blkg)
*/
static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg)
{
if (atomic_inc_not_zero(&blkg->refcnt))
if (percpu_ref_tryget(&blkg->refcnt))
return blkg;
return NULL;
}
......@@ -517,23 +516,19 @@ static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg)
*/
static inline struct blkcg_gq *blkg_try_get_closest(struct blkcg_gq *blkg)
{
while (!atomic_inc_not_zero(&blkg->refcnt))
while (!percpu_ref_tryget(&blkg->refcnt))
blkg = blkg->parent;
return blkg;
}
void __blkg_release_rcu(struct rcu_head *rcu);
/**
* blkg_put - put a blkg reference
* @blkg: blkg to put
*/
static inline void blkg_put(struct blkcg_gq *blkg)
{
WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0);
if (atomic_dec_and_test(&blkg->refcnt))
call_rcu(&blkg->rcu_head, __blkg_release_rcu);
percpu_ref_put(&blkg->refcnt);
}
/**
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment