blkcg: consolidate blkg creation in blkcg_bio_issue_check()
blkg (blkcg_gq) currently is created by blkcg policies invoking
blkg_lookup_create() which ends up repeating about the same code in
different policies. Theoretically, this can avoid the overhead of
looking and/or creating blkg's if blkcg is enabled but no policy is in
use; however, the cost of blkg lookup / creation is very low
especially if only the root blkcg is in use which is highly likely if
no blkcg policy is in active use - it boils down to a single very
predictable conditional and surrounding RCU protection.
This patch consolidates blkg creation to a new function
blkcg_bio_issue_check() which is called during bio issue from
generic_make_request_checks(). blkcg_bio_issue_check() is now the
only function which tries to create missing blkg's. The subsequent
policy and request_list operations just perform blkg_lookup() and if
missing falls back to the root.
* blk_get_rl() no longer tries to create blkg. It uses blkg_lookup()
instead of blkg_lookup_create().
* blk_throtl_bio() is now called from blkcg_bio_issue_check() with rcu
read locked and blkg already looked up. Both throtl_lookup_tg() and
throtl_lookup_create_tg() are dropped.
* cfq is similarly updated. cfq_lookup_create_cfqg() is replaced with
cfq_lookup_cfqg()which uses blkg_lookup().
This consolidates blkg handling and avoids unnecessary blkg creation
retries under memory pressure. In addition, this provides a common
bio entry point into blkcg where things like common accounting can be
performed.
v2: Build fixes for !CONFIG_CFQ_GROUP_IOSCHED and
!CONFIG_BLK_DEV_THROTTLING.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 52e637e..097c4a6 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -153,6 +153,7 @@
return NULL;
}
+EXPORT_SYMBOL_GPL(blkg_lookup_slowpath);
/*
* If @new_blkg is %NULL, this function tries to allocate a new one as
@@ -295,7 +296,6 @@
return blkg;
}
}
-EXPORT_SYMBOL_GPL(blkg_lookup_create);
static void blkg_destroy(struct blkcg_gq *blkg)
{
diff --git a/block/blk-core.c b/block/blk-core.c
index 627ed0c..140094f 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1889,8 +1889,8 @@
*/
create_io_context(GFP_ATOMIC, q->node);
- if (blk_throtl_bio(q, bio))
- return false; /* throttled, will be resubmitted later */
+ if (!blkcg_bio_issue_check(q, bio))
+ return false;
trace_block_bio_queue(q, bio);
return true;
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 900a777..29c22ed 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -182,11 +182,6 @@
return pd_to_blkg(&tg->pd);
}
-static inline struct throtl_grp *td_root_tg(struct throtl_data *td)
-{
- return blkg_to_tg(td->queue->root_blkg);
-}
-
/**
* sq_to_tg - return the throl_grp the specified service queue belongs to
* @sq: the throtl_service_queue of interest
@@ -449,39 +444,6 @@
}
}
-static struct throtl_grp *throtl_lookup_tg(struct throtl_data *td,
- struct blkcg *blkcg)
-{
- return blkg_to_tg(blkg_lookup(blkcg, td->queue));
-}
-
-static struct throtl_grp *throtl_lookup_create_tg(struct throtl_data *td,
- struct blkcg *blkcg)
-{
- struct request_queue *q = td->queue;
- struct throtl_grp *tg = NULL;
-
- /*
- * This is the common case when there are no blkcgs. Avoid lookup
- * in this case
- */
- if (blkcg == &blkcg_root) {
- tg = td_root_tg(td);
- } else {
- struct blkcg_gq *blkg;
-
- blkg = blkg_lookup_create(blkcg, q);
-
- /* if %NULL and @q is alive, fall back to root_tg */
- if (!IS_ERR(blkg))
- tg = blkg_to_tg(blkg);
- else
- tg = td_root_tg(td);
- }
-
- return tg;
-}
-
static struct throtl_grp *
throtl_rb_first(struct throtl_service_queue *parent_sq)
{
@@ -1403,46 +1365,26 @@
.pd_reset_stats_fn = throtl_pd_reset_stats,
};
-bool blk_throtl_bio(struct request_queue *q, struct bio *bio)
+bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
+ struct bio *bio)
{
- struct throtl_data *td = q->td;
struct throtl_qnode *qn = NULL;
- struct throtl_grp *tg;
+ struct throtl_grp *tg = blkg_to_tg(blkg ?: q->root_blkg);
struct throtl_service_queue *sq;
bool rw = bio_data_dir(bio);
- struct blkcg *blkcg;
bool throttled = false;
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
/* see throtl_charge_bio() */
- if (bio->bi_rw & REQ_THROTTLED)
+ if ((bio->bi_rw & REQ_THROTTLED) || !tg->has_rules[rw])
goto out;
- /*
- * 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 = bio_blkcg(bio);
- tg = throtl_lookup_tg(td, blkcg);
- if (tg) {
- if (!tg->has_rules[rw]) {
- throtl_update_dispatch_stats(tg_to_blkg(tg),
- bio->bi_iter.bi_size, bio->bi_rw);
- goto out_unlock_rcu;
- }
- }
-
- /*
- * Either group has not been allocated yet or it is not an unlimited
- * IO group
- */
spin_lock_irq(q->queue_lock);
if (unlikely(blk_queue_bypass(q)))
goto out_unlock;
- tg = throtl_lookup_create_tg(td, blkcg);
sq = &tg->service_queue;
while (true) {
@@ -1507,8 +1449,6 @@
out_unlock:
spin_unlock_irq(q->queue_lock);
-out_unlock_rcu:
- rcu_read_unlock();
out:
/*
* As multiple blk-throtls may stack in the same issue path, we
diff --git a/block/blk.h b/block/blk.h
index 026d959..d905b26 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -266,15 +266,10 @@
* Internal throttling interface
*/
#ifdef CONFIG_BLK_DEV_THROTTLING
-extern bool blk_throtl_bio(struct request_queue *q, struct bio *bio);
extern void blk_throtl_drain(struct request_queue *q);
extern int blk_throtl_init(struct request_queue *q);
extern void blk_throtl_exit(struct request_queue *q);
#else /* CONFIG_BLK_DEV_THROTTLING */
-static inline bool blk_throtl_bio(struct request_queue *q, struct bio *bio)
-{
- return false;
-}
static inline void blk_throtl_drain(struct request_queue *q) { }
static inline int blk_throtl_init(struct request_queue *q) { return 0; }
static inline void blk_throtl_exit(struct request_queue *q) { }
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index a4429b3..0994f3b 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1683,28 +1683,15 @@
cfqg_stats_reset(&cfqg->dead_stats);
}
-/*
- * Search for the cfq group current task belongs to. request_queue lock must
- * be held.
- */
-static struct cfq_group *cfq_lookup_create_cfqg(struct cfq_data *cfqd,
- struct blkcg *blkcg)
+static struct cfq_group *cfq_lookup_cfqg(struct cfq_data *cfqd,
+ struct blkcg *blkcg)
{
- struct request_queue *q = cfqd->queue;
- struct cfq_group *cfqg = NULL;
+ struct blkcg_gq *blkg;
- /* avoid lookup for the common case where there's no blkcg */
- if (blkcg == &blkcg_root) {
- cfqg = cfqd->root_group;
- } else {
- struct blkcg_gq *blkg;
-
- blkg = blkg_lookup_create(blkcg, q);
- if (!IS_ERR(blkg))
- cfqg = blkg_to_cfqg(blkg);
- }
-
- return cfqg;
+ blkg = blkg_lookup(blkcg, cfqd->queue);
+ if (likely(blkg))
+ return blkg_to_cfqg(blkg);
+ return NULL;
}
static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg)
@@ -2108,8 +2095,8 @@
{ } /* terminate */
};
#else /* GROUP_IOSCHED */
-static struct cfq_group *cfq_lookup_create_cfqg(struct cfq_data *cfqd,
- struct blkcg *blkcg)
+static struct cfq_group *cfq_lookup_cfqg(struct cfq_data *cfqd,
+ struct blkcg *blkcg)
{
return cfqd->root_group;
}
@@ -3716,7 +3703,7 @@
struct cfq_group *cfqg;
rcu_read_lock();
- cfqg = cfq_lookup_create_cfqg(cfqd, bio_blkcg(bio));
+ cfqg = cfq_lookup_cfqg(cfqd, bio_blkcg(bio));
if (!cfqg) {
cfqq = &cfqd->oom_cfqq;
goto out;
