linux-kernel - [PATCH v2 5/6] cgroup: remove synchronize_rcu() from cgroup

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <5100D54E.7010602@huawei.com>
Date:	Thu, 24 Jan 2013 14:31:42 +0800
From:	Li Zefan <lizefan@...wei.com>
To:	Tejun Heo <tj@...nel.org>
CC:	Andrew Morton <akpm@...ux-foundation.org>,
	Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...nel.org>,
	LKML <linux-kernel@...r.kernel.org>,
	Cgroups <cgroups@...r.kernel.org>
Subject: [PATCH v2 5/6] cgroup: remove synchronize_rcu() from cgroup_diput()

Free cgroup via call_rcu(). The actual work is done through
workqueue.

Signed-off-by: Li Zefan <lizefan@...wei.com>
---

v2: move INIT_WORK() from cgroup_create() to init_cgroup_housekeeping()

---
 include/linux/cgroup.h |  1 +
 kernel/cgroup.c        | 72 ++++++++++++++++++++++++++++++--------------------
 2 files changed, 44 insertions(+), 29 deletions(-)

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 8118a31..900af59 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -203,6 +203,7 @@ struct cgroup {
 
 	/* For RCU-protected deletion */
 	struct rcu_head rcu_head;
+	struct work_struct free_work;
 
 	/* List of events which userspace want to receive */
 	struct list_head event_list;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index a39e2b0..f18b0d9 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -852,12 +852,52 @@ static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb)
 	return inode;
 }
 
+static void cgroup_free_fn(struct work_struct *work)
+{
+	struct cgroup *cgrp = container_of(work, struct cgroup, free_work);
+	struct cgroup_subsys *ss;
+
+	mutex_lock(&cgroup_mutex);
+	/*
+	 * Release the subsystem state objects.
+	 */
+	for_each_subsys(cgrp->root, ss)
+		ss->css_free(cgrp);
+
+	cgrp->root->number_of_cgroups--;
+	mutex_unlock(&cgroup_mutex);
+
+	/*
+	 * Drop the active superblock reference that we took when we
+	 * created the cgroup
+	 */
+	deactivate_super(cgrp->root->sb);
+
+	/*
+	 * if we're getting rid of the cgroup, refcount should ensure
+	 * that there are no pidlists left.
+	 */
+	BUG_ON(!list_empty(&cgrp->pidlists));
+
+	simple_xattrs_free(&cgrp->xattrs);
+
+	ida_simple_remove(&cgrp->root->cgroup_ida, cgrp->id);
+	kfree(cgrp);
+}
+
+static void cgroup_free_rcu(struct rcu_head *head)
+{
+	struct cgroup *cgrp = container_of(head, struct cgroup, rcu_head);
+
+	schedule_work(&cgrp->free_work);
+}
+
 static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 {
 	/* is dentry a directory ? if so, kfree() associated cgroup */
 	if (S_ISDIR(inode->i_mode)) {
 		struct cgroup *cgrp = dentry->d_fsdata;
-		struct cgroup_subsys *ss;
+
 		BUG_ON(!(cgroup_is_removed(cgrp)));
 		/* It's possible for external users to be holding css
 		 * reference counts on a cgroup; css_put() needs to
@@ -865,34 +905,7 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 		 * the reference count in order to know if it needs to
 		 * queue the cgroup to be handled by the release
 		 * agent */
-		synchronize_rcu();
-
-		mutex_lock(&cgroup_mutex);
-		/*
-		 * Release the subsystem state objects.
-		 */
-		for_each_subsys(cgrp->root, ss)
-			ss->css_free(cgrp);
-
-		cgrp->root->number_of_cgroups--;
-		mutex_unlock(&cgroup_mutex);
-
-		/*
-		 * Drop the active superblock reference that we took when we
-		 * created the cgroup
-		 */
-		deactivate_super(cgrp->root->sb);
-
-		/*
-		 * if we're getting rid of the cgroup, refcount should ensure
-		 * that there are no pidlists left.
-		 */
-		BUG_ON(!list_empty(&cgrp->pidlists));
-
-		simple_xattrs_free(&cgrp->xattrs);
-
-		ida_simple_remove(&cgrp->root->cgroup_ida, cgrp->id);
-		kfree(cgrp);
+		call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
 	} else {
 		struct cfent *cfe = __d_cfe(dentry);
 		struct cgroup *cgrp = dentry->d_parent->d_fsdata;
@@ -1391,6 +1404,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	INIT_LIST_HEAD(&cgrp->allcg_node);
 	INIT_LIST_HEAD(&cgrp->release_list);
 	INIT_LIST_HEAD(&cgrp->pidlists);
+	INIT_WORK(&cgrp->free_work, cgroup_free_fn);
 	mutex_init(&cgrp->pidlist_mutex);
 	INIT_LIST_HEAD(&cgrp->event_list);
 	spin_lock_init(&cgrp->event_list_lock);
-- 
1.8.0.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/