cgroups: add a per-subsystem hierarchy_mutex

These patches introduce new locking/refcount support for cgroups to
reduce the need for subsystems to call cgroup_lock(). This will
ultimately allow the atomicity of cgroup_rmdir() (which was removed
recently) to be restored.

These three patches give:

1/3 - introduce a per-subsystem hierarchy_mutex which a subsystem can
     use to prevent changes to its own cgroup tree

2/3 - use hierarchy_mutex in place of calling cgroup_lock() in the
     memory controller

3/3 - introduce a css_tryget() function similar to the one recently
      proposed by Kamezawa, but avoiding spurious refcount failures in
      the event of a race between a css_tryget() and an unsuccessful
      cgroup_rmdir()

Future patches will likely involve:

- using hierarchy mutex in place of cgroup_lock() in more subsystems
 where appropriate

- restoring the atomicity of cgroup_rmdir() with respect to cgroup_create()

This patch:

Add a hierarchy_mutex to the cgroup_subsys object that protects changes to
the hierarchy observed by that subsystem.  It is taken by the cgroup
subsystem (in addition to cgroup_mutex) for the following operations:

- linking a cgroup into that subsystem's cgroup tree
- unlinking a cgroup from that subsystem's cgroup tree
- moving the subsystem to/from a hierarchy (including across the
  bind() callback)

Thus if the subsystem holds its own hierarchy_mutex, it can safely
traverse its own hierarchy.

Signed-off-by: Paul Menage <menage@google.com>
Tested-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 52 insertions, 4 deletions

diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 60287e9e9d2..e33ee74eee7 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -528,7 +528,7 @@ example in cpusets, no task may attach before 'cpus' and 'mems' are set
 up.
 
 void bind(struct cgroup_subsys *ss, struct cgroup *root)
-(cgroup_mutex held by caller)
+(cgroup_mutex and ss->hierarchy_mutex held by caller)
 
 Called when a cgroup subsystem is rebound to a different hierarchy
 and root cgroup. Currently this will only involve movement between
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 73d1c730c3c..ce1c1f34c30 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -340,8 +340,23 @@ struct cgroup_subsys {
 #define MAX_CGROUP_TYPE_NAMELEN 32
 	const char *name;
 
-	struct cgroupfs_root *root;
+	/*
+	 * Protects sibling/children links of cgroups in this
+	 * hierarchy, plus protects which hierarchy (or none) the
+	 * subsystem is a part of (i.e. root/sibling).  To avoid
+	 * potential deadlocks, the following operations should not be
+	 * undertaken while holding any hierarchy_mutex:
+	 *
+	 * - allocating memory
+	 * - initiating hotplug events
+	 */
+	struct mutex hierarchy_mutex;
 
+	/*
+	 * Link to parent, and list entry in parent's children.
+	 * Protected by this->hierarchy_mutex and cgroup_lock()
+	 */
+	struct cgroupfs_root *root;
 	struct list_head sibling;
 };
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 83ea4f524be..8b6379cdf63 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -722,23 +722,26 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 			BUG_ON(cgrp->subsys[i]);
 			BUG_ON(!dummytop->subsys[i]);
 			BUG_ON(dummytop->subsys[i]->cgroup != dummytop);
+			mutex_lock(&ss->hierarchy_mutex);
 			cgrp->subsys[i] = dummytop->subsys[i];
 			cgrp->subsys[i]->cgroup = cgrp;
 			list_move(&ss->sibling, &root->subsys_list);
 			ss->root = root;
 			if (ss->bind)
 				ss->bind(ss, cgrp);
-
+			mutex_unlock(&ss->hierarchy_mutex);
 		} else if (bit & removed_bits) {
 			/* We're removing this subsystem */
 			BUG_ON(cgrp->subsys[i] != dummytop->subsys[i]);
 			BUG_ON(cgrp->subsys[i]->cgroup != cgrp);
+			mutex_lock(&ss->hierarchy_mutex);
 			if (ss->bind)
 				ss->bind(ss, dummytop);
 			dummytop->subsys[i]->cgroup = dummytop;
 			cgrp->subsys[i] = NULL;
 			subsys[i]->root = &rootnode;
 			list_move(&ss->sibling, &rootnode.subsys_list);
+			mutex_unlock(&ss->hierarchy_mutex);
 		} else if (bit & final_bits) {
 			/* Subsystem state should already exist */
 			BUG_ON(!cgrp->subsys[i]);
@@ -2338,6 +2341,29 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
 	cgrp->subsys[ss->subsys_id] = css;
 }
 
+static void cgroup_lock_hierarchy(struct cgroupfs_root *root)
+{
+	/* We need to take each hierarchy_mutex in a consistent order */
+	int i;
+
+	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+		struct cgroup_subsys *ss = subsys[i];
+		if (ss->root == root)
+			mutex_lock_nested(&ss->hierarchy_mutex, i);
+	}
+}
+
+static void cgroup_unlock_hierarchy(struct cgroupfs_root *root)
+{
+	int i;
+
+	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+		struct cgroup_subsys *ss = subsys[i];
+		if (ss->root == root)
+			mutex_unlock(&ss->hierarchy_mutex);
+	}
+}
+
 /*
  * cgroup_create - create a cgroup
  * @parent: cgroup that will be parent of the new cgroup
@@ -2386,7 +2412,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 		init_cgroup_css(css, ss, cgrp);
 	}
 
+	cgroup_lock_hierarchy(root);
 	list_add(&cgrp->sibling, &cgrp->parent->children);
+	cgroup_unlock_hierarchy(root);
 	root->number_of_cgroups++;
 
 	err = cgroup_create_dir(cgrp, dentry, mode);
@@ -2504,8 +2532,12 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	if (!list_empty(&cgrp->release_list))
 		list_del(&cgrp->release_list);
 	spin_unlock(&release_list_lock);
-	/* delete my sibling from parent->children */
+
+	cgroup_lock_hierarchy(cgrp->root);
+	/* delete this cgroup from parent->children */
 	list_del(&cgrp->sibling);
+	cgroup_unlock_hierarchy(cgrp->root);
+
 	spin_lock(&cgrp->dentry->d_lock);
 	d = dget(cgrp->dentry);
 	spin_unlock(&d->d_lock);
@@ -2547,6 +2579,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	 * need to invoke fork callbacks here. */
 	BUG_ON(!list_empty(&init_task.tasks));
 
+	mutex_init(&ss->hierarchy_mutex);
 	ss->active = 1;
 }