From: Tejun Heo <tj@kernel.org>
To: axboe@kernel.dk, vgoyal@redhat.com
Cc: ctalbott@google.com, rni@google.com,
linux-kernel@vger.kernel.org, Tejun Heo <tj@kernel.org>
Subject: [PATCH 18/36] blkcg: let blkio_group point to blkio_cgroup directly
Date: Tue, 21 Feb 2012 17:46:45 -0800 [thread overview]
Message-ID: <1329875223-5102-19-git-send-email-tj@kernel.org> (raw)
In-Reply-To: <1329875223-5102-1-git-send-email-tj@kernel.org>
Currently, blkg points to the associated blkcg via its css_id. This
unnecessarily complicates dereferencing blkcg. Let blkg hold a
reference to the associated blkcg and point directly to it and disable
css_id on blkio_subsys.
This change requires splitting blkiocg_destroy() into
blkiocg_pre_destroy() and blkiocg_destroy() so that all blkg's can be
destroyed and all the blkcg references held by them dropped during
cgroup removal.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
---
block/blk-cgroup.c | 43 ++++++++++++++++++++++++-------------------
block/blk-cgroup.h | 2 +-
block/blk-throttle.c | 3 +++
block/cfq-iosched.c | 4 ++++
4 files changed, 32 insertions(+), 20 deletions(-)
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 8742af3..803c3b1 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -37,6 +37,7 @@ static int blkiocg_can_attach(struct cgroup_subsys *, struct cgroup *,
struct cgroup_taskset *);
static void blkiocg_attach(struct cgroup_subsys *, struct cgroup *,
struct cgroup_taskset *);
+static int blkiocg_pre_destroy(struct cgroup_subsys *, struct cgroup *);
static void blkiocg_destroy(struct cgroup_subsys *, struct cgroup *);
static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *);
@@ -51,10 +52,10 @@ struct cgroup_subsys blkio_subsys = {
.create = blkiocg_create,
.can_attach = blkiocg_can_attach,
.attach = blkiocg_attach,
+ .pre_destroy = blkiocg_pre_destroy,
.destroy = blkiocg_destroy,
.populate = blkiocg_populate,
.subsys_id = blkio_subsys_id,
- .use_id = 1,
.module = THIS_MODULE,
};
EXPORT_SYMBOL_GPL(blkio_subsys);
@@ -442,6 +443,7 @@ struct blkio_group *blkg_lookup_create(struct blkio_cgroup *blkcg,
if (blkg)
return blkg;
+ /* blkg holds a reference to blkcg */
if (!css_tryget(&blkcg->css))
return ERR_PTR(-EINVAL);
@@ -463,15 +465,16 @@ struct blkio_group *blkg_lookup_create(struct blkio_cgroup *blkcg,
spin_lock_init(&new_blkg->stats_lock);
rcu_assign_pointer(new_blkg->q, q);
- new_blkg->blkcg_id = css_id(&blkcg->css);
+ new_blkg->blkcg = blkcg;
new_blkg->plid = plid;
cgroup_path(blkcg->css.cgroup, new_blkg->path,
sizeof(new_blkg->path));
+ } else {
+ css_put(&blkcg->css);
}
rcu_read_lock();
spin_lock_irq(q->queue_lock);
- css_put(&blkcg->css);
/* did bypass get turned on inbetween? */
if (unlikely(blk_queue_bypass(q)) && !for_root) {
@@ -500,6 +503,7 @@ out:
if (new_blkg) {
free_percpu(new_blkg->stats_cpu);
kfree(new_blkg);
+ css_put(&blkcg->css);
}
return blkg;
}
@@ -508,7 +512,6 @@ EXPORT_SYMBOL_GPL(blkg_lookup_create);
static void __blkiocg_del_blkio_group(struct blkio_group *blkg)
{
hlist_del_init_rcu(&blkg->blkcg_node);
- blkg->blkcg_id = 0;
}
/*
@@ -517,24 +520,17 @@ static void __blkiocg_del_blkio_group(struct blkio_group *blkg)
*/
int blkiocg_del_blkio_group(struct blkio_group *blkg)
{
- struct blkio_cgroup *blkcg;
+ struct blkio_cgroup *blkcg = blkg->blkcg;
unsigned long flags;
- struct cgroup_subsys_state *css;
int ret = 1;
- rcu_read_lock();
- css = css_lookup(&blkio_subsys, blkg->blkcg_id);
- if (css) {
- blkcg = container_of(css, struct blkio_cgroup, css);
- spin_lock_irqsave(&blkcg->lock, flags);
- if (!hlist_unhashed(&blkg->blkcg_node)) {
- __blkiocg_del_blkio_group(blkg);
- ret = 0;
- }
- spin_unlock_irqrestore(&blkcg->lock, flags);
+ spin_lock_irqsave(&blkcg->lock, flags);
+ if (!hlist_unhashed(&blkg->blkcg_node)) {
+ __blkiocg_del_blkio_group(blkg);
+ ret = 0;
}
+ spin_unlock_irqrestore(&blkcg->lock, flags);
- rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(blkiocg_del_blkio_group);
@@ -1376,7 +1372,8 @@ static int blkiocg_populate(struct cgroup_subsys *subsys, struct cgroup *cgroup)
ARRAY_SIZE(blkio_files));
}
-static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
+static int blkiocg_pre_destroy(struct cgroup_subsys *subsys,
+ struct cgroup *cgroup)
{
struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
unsigned long flags;
@@ -1385,6 +1382,7 @@ static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
struct blkio_policy_type *blkiop;
rcu_read_lock();
+
do {
spin_lock_irqsave(&blkcg->lock, flags);
@@ -1414,8 +1412,15 @@ static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
spin_unlock(&blkio_list_lock);
} while (1);
- free_css_id(&blkio_subsys, &blkcg->css);
rcu_read_unlock();
+
+ return 0;
+}
+
+static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
+{
+ struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
+
if (blkcg != &blkio_root_cgroup)
kfree(blkcg);
}
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 7ebecf6..ca1fc63 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -163,7 +163,7 @@ struct blkio_group {
/* Pointer to the associated request_queue, RCU protected */
struct request_queue __rcu *q;
struct hlist_node blkcg_node;
- unsigned short blkcg_id;
+ struct blkio_cgroup *blkcg;
/* Store cgroup path */
char path[128];
/* policy which owns this blk group */
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 52a4293..fe6a442 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -169,6 +169,9 @@ static void throtl_put_tg(struct throtl_grp *tg)
if (!atomic_dec_and_test(&tg->ref))
return;
+ /* release the extra blkcg reference this blkg has been holding */
+ css_put(&tg->blkg.blkcg->css);
+
/*
* 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
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index f67d109..9ef86fb 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1133,6 +1133,10 @@ static void cfq_put_cfqg(struct cfq_group *cfqg)
cfqg->ref--;
if (cfqg->ref)
return;
+
+ /* release the extra blkcg reference this blkg has been holding */
+ css_put(&cfqg->blkg.blkcg->css);
+
for_each_cfqg_st(cfqg, i, j, st)
BUG_ON(!RB_EMPTY_ROOT(&st->rb));
free_percpu(cfqg->blkg.stats_cpu);
--
1.7.7.3
next prev parent reply other threads:[~2012-02-22 1:52 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-02-22 1:46 [PATCHSET] blkcg: accumulated blkcg updates Tejun Heo
2012-02-22 1:46 ` [PATCH 01/36] block: blk-throttle should be drained regardless of q->elevator Tejun Heo
2012-02-22 1:46 ` [PATCH 02/36] blkcg: make CONFIG_BLK_CGROUP bool Tejun Heo
2012-02-22 1:46 ` [PATCH 03/36] cfq: don't register propio policy if !CONFIG_CFQ_GROUP_IOSCHED Tejun Heo
2012-02-22 1:46 ` [PATCH 04/36] elevator: clear auxiliary data earlier during elevator switch Tejun Heo
2012-02-22 1:46 ` [PATCH 05/36] elevator: make elevator_init_fn() return 0/-errno Tejun Heo
2012-02-22 1:46 ` [PATCH 06/36] block: implement blk_queue_bypass_start/end() Tejun Heo
2012-02-22 1:46 ` [PATCH 07/36] block: extend queue bypassing to cover blkcg policies Tejun Heo
2012-02-22 1:46 ` [PATCH 08/36] blkcg: shoot down blkio_groups on elevator switch Tejun Heo
2012-02-22 1:46 ` [PATCH 09/36] blkcg: move rcu_read_lock() outside of blkio_group get functions Tejun Heo
2012-02-22 1:46 ` [PATCH 10/36] blkcg: update blkg get functions take blkio_cgroup as parameter Tejun Heo
2012-02-22 1:46 ` [PATCH 11/36] blkcg: use q and plid instead of opaque void * for blkio_group association Tejun Heo
2012-02-22 1:46 ` [PATCH 12/36] blkcg: add blkio_policy[] array and allow one policy per policy ID Tejun Heo
2012-02-22 1:46 ` [PATCH 13/36] blkcg: use the usual get blkg path for root blkio_group Tejun Heo
2012-02-22 1:46 ` [PATCH 14/36] blkcg: factor out blkio_group creation Tejun Heo
2012-02-22 1:46 ` [PATCH 15/36] blkcg: don't allow or retain configuration of missing devices Tejun Heo
2012-02-22 1:46 ` [PATCH 16/36] blkcg: kill blkio_policy_node Tejun Heo
2012-02-22 1:46 ` [PATCH 17/36] blkcg: kill the mind-bending blkg->dev Tejun Heo
2012-02-22 1:46 ` Tejun Heo [this message]
2012-02-22 1:46 ` [PATCH 19/36] blkcg: add blkcg_{init|drain|exit}_queue() Tejun Heo
2012-02-22 1:46 ` [PATCH 20/36] blkcg: clear all request_queues on blkcg policy [un]registrations Tejun Heo
2012-02-22 1:46 ` [PATCH 21/36] blkcg: let blkcg core handle policy private data allocation Tejun Heo
2012-02-22 1:46 ` [PATCH 22/36] blkcg: move refcnt to blkcg core Tejun Heo
2012-02-22 1:46 ` [PATCH 23/36] blkcg: make blkg->pd an array and move configuration and stats into it Tejun Heo
2012-02-22 1:46 ` [PATCH 24/36] blkcg: don't use blkg->plid in stat related functions Tejun Heo
2012-02-22 1:46 ` [PATCH 25/36] blkcg: move per-queue blkg list heads and counters to queue and blkg Tejun Heo
2012-02-22 1:46 ` [PATCH 26/36] blkcg: let blkcg core manage per-queue blkg list and counter Tejun Heo
2012-02-22 1:46 ` [PATCH 27/36] blkcg: unify blkg's for blkcg policies Tejun Heo
2012-03-05 21:01 ` [PATCH UPDATED " Tejun Heo
2012-02-22 1:46 ` [PATCH 28/36] blkcg: use double locking instead of RCU for blkg synchronization Tejun Heo
2012-02-22 1:46 ` [PATCH 29/36] blkcg: drop unnecessary RCU locking Tejun Heo
2012-02-23 18:51 ` [PATCH UPDATED " Tejun Heo
2012-02-22 1:46 ` [PATCH 30/36] block: restructure get_request() Tejun Heo
2012-02-22 1:46 ` [PATCH 31/36] block: interface update for ioc/icq creation functions Tejun Heo
2012-02-22 1:46 ` [PATCH 32/36] block: ioc_task_link() can't fail Tejun Heo
2012-02-22 1:47 ` [PATCH 33/36] block: add io_context->active_ref Tejun Heo
2012-02-22 18:47 ` Vivek Goyal
2012-02-22 19:13 ` Tejun Heo
2012-02-23 18:20 ` Vivek Goyal
2012-02-22 1:47 ` [PATCH 34/36] block: implement bio_associate_current() Tejun Heo
2012-02-22 13:45 ` Jeff Moyer
2012-02-22 19:07 ` Tejun Heo
2012-02-22 19:33 ` Jeff Moyer
2012-02-22 19:37 ` Vivek Goyal
2012-02-22 19:41 ` Jeff Moyer
2012-02-22 1:47 ` [PATCH 35/36] block: make block cgroup policies follow bio task association Tejun Heo
2012-02-22 1:47 ` [PATCH 36/36] block: make blk-throttle preserve the issuing task on delayed bios Tejun Heo
2012-02-22 19:34 ` [PATCHSET] blkcg: accumulated blkcg updates Vivek Goyal
2012-02-22 22:04 ` Tejun Heo
2012-03-05 20:59 ` [PATCH 17.5] blkcg: skip blkg printing if q isn't associated with disk Tejun Heo
2012-03-05 21:07 ` [PATCHSET] blkcg: accumulated blkcg updates Tejun Heo
2012-03-05 21:08 ` Tejun Heo
2012-03-06 15:07 ` Vivek Goyal
2012-03-06 16:24 ` Vivek Goyal
2012-03-06 18:39 ` Vivek Goyal
2012-03-06 18:39 ` Vivek Goyal
2012-03-06 19:02 ` Vivek Goyal
2012-03-08 0:06 ` Tejun Heo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1329875223-5102-19-git-send-email-tj@kernel.org \
--to=tj@kernel.org \
--cc=axboe@kernel.dk \
--cc=ctalbott@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=rni@google.com \
--cc=vgoyal@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.