cgroups: make cgroup_path() RCU-safe
Fix races between /proc/sched_debug by freeing cgroup objects via an RCU
callback. Thus any cgroup reference obtained from an RCU-safe source will
remain valid during the RCU section. Since dentries are also RCU-safe,
this allows us to traverse up the tree safely.
Additionally, make cgroup_path() check for a NULL cgrp->dentry to avoid
trying to report a path for a partially-created cgroup.
[lizf@cn.fujitsu.com: call deactive_super() in cgroup_diput()]
Signed-off-by: Paul Menage <menage@google.com>
Reviewed-by: Li Zefan <lizf@cn.fujitsu.com>
Tested-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index f68dfd8d..73d1c73 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -116,7 +116,7 @@
struct list_head children; /* my children */
struct cgroup *parent; /* my parent */
- struct dentry *dentry; /* cgroup fs entry */
+ struct dentry *dentry; /* cgroup fs entry, RCU protected */
/* Private pointers for each registered subsystem */
struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
@@ -145,6 +145,9 @@
int pids_use_count;
/* Length of the current tasks_pids array */
int pids_length;
+
+ /* For RCU-protected deletion */
+ struct rcu_head rcu_head;
};
/* A css_set is a structure holding pointers to a set of
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index cb7c72b..83ea4f5 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -271,7 +271,7 @@
rcu_read_lock();
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
- struct cgroup *cgrp = cg->subsys[i]->cgroup;
+ struct cgroup *cgrp = rcu_dereference(cg->subsys[i]->cgroup);
if (atomic_dec_and_test(&cgrp->count) &&
notify_on_release(cgrp)) {
if (taskexit)
@@ -594,6 +594,13 @@
return;
}
+static void free_cgroup_rcu(struct rcu_head *obj)
+{
+ struct cgroup *cgrp = container_of(obj, struct cgroup, rcu_head);
+
+ kfree(cgrp);
+}
+
static void cgroup_diput(struct dentry *dentry, struct inode *inode)
{
/* is dentry a directory ? if so, kfree() associated cgroup */
@@ -619,11 +626,13 @@
cgrp->root->number_of_cgroups--;
mutex_unlock(&cgroup_mutex);
- /* Drop the active superblock reference that we took when we
- * created the cgroup */
+ /*
+ * Drop the active superblock reference that we took when we
+ * created the cgroup
+ */
deactivate_super(cgrp->root->sb);
- kfree(cgrp);
+ call_rcu(&cgrp->rcu_head, free_cgroup_rcu);
}
iput(inode);
}
@@ -1134,14 +1143,16 @@
* @buf: the buffer to write the path into
* @buflen: the length of the buffer
*
- * Called with cgroup_mutex held. Writes path of cgroup into buf.
- * Returns 0 on success, -errno on error.
+ * Called with cgroup_mutex held or else with an RCU-protected cgroup
+ * reference. Writes path of cgroup into buf. Returns 0 on success,
+ * -errno on error.
*/
int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
{
char *start;
+ struct dentry *dentry = rcu_dereference(cgrp->dentry);
- if (cgrp == dummytop) {
+ if (!dentry || cgrp == dummytop) {
/*
* Inactive subsystems have no dentry for their root
* cgroup
@@ -1154,13 +1165,14 @@
*--start = '\0';
for (;;) {
- int len = cgrp->dentry->d_name.len;
+ int len = dentry->d_name.len;
if ((start -= len) < buf)
return -ENAMETOOLONG;
memcpy(start, cgrp->dentry->d_name.name, len);
cgrp = cgrp->parent;
if (!cgrp)
break;
+ dentry = rcu_dereference(cgrp->dentry);
if (!cgrp->parent)
continue;
if (--start < buf)
@@ -1663,7 +1675,7 @@
if (!error) {
dentry->d_fsdata = cgrp;
inc_nlink(parent->d_inode);
- cgrp->dentry = dentry;
+ rcu_assign_pointer(cgrp->dentry, dentry);
dget(dentry);
}
dput(dentry);