summaryrefslogtreecommitdiff
path: root/kernel/cgroup.c
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2014-02-12 09:29:50 -0500
committerTejun Heo <tj@kernel.org>2014-02-12 09:29:50 -0500
commit776f02fa4e1ad70557c0318c70ce928e0642bee0 (patch)
treef2080066461b0ef75a964a8ef2b9a2243d7b5389 /kernel/cgroup.c
parent3c9c825b8b50de7dbb015e6bfc04bb2da79364d9 (diff)
cgroup: remove cgroupfs_root->refcnt
Currently, cgroupfs_root and its ->top_cgroup are separated reference counted and the latter's is ignored. There's no reason to do this separately. This patch removes cgroupfs_root->refcnt and destroys cgroupfs_root when the top_cgroup is released. * cgroup_put() updated to ignore cgroup_is_dead() test for top cgroups. cgroup_free_fn() updated to handle root destruction when releasing a top cgroup. * As root destruction is now bounced through cgroup destruction, it is asynchronous. Update cgroup_mount() so that it waits for pending release which is currently implemented using msleep(). Converting this to proper wait_queue isn't hard but likely unnecessary. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Li Zefan <lizefan@huawei.com>
Diffstat (limited to 'kernel/cgroup.c')
-rw-r--r--kernel/cgroup.c86
1 files changed, 38 insertions, 48 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index cffdb6e2ad08..03845c5d082b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -53,6 +53,7 @@
#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
#include <linux/flex_array.h> /* used in cgroup_attach_task */
#include <linux/kthread.h>
+#include <linux/delay.h>
#include <linux/atomic.h>
@@ -728,37 +729,16 @@ static void cgroup_free_root(struct cgroupfs_root *root)
}
}
-static void cgroup_get_root(struct cgroupfs_root *root)
-{
- /*
- * The caller must ensure that @root is alive, which can be
- * achieved by holding a ref on one of the member cgroups or
- * following a registered reference to @root while holding
- * cgroup_tree_mutex.
- */
- WARN_ON_ONCE(atomic_read(&root->refcnt) <= 0);
- atomic_inc(&root->refcnt);
-}
-
-static void cgroup_put_root(struct cgroupfs_root *root)
+static void cgroup_destroy_root(struct cgroupfs_root *root)
{
struct cgroup *cgrp = &root->top_cgroup;
struct cgrp_cset_link *link, *tmp_link;
int ret;
- /*
- * @root's refcnt reaching zero and its deregistration should be
- * atomic w.r.t. cgroup_tree_mutex. This ensures that
- * cgroup_get_root() is safe to invoke if @root is registered.
- */
mutex_lock(&cgroup_tree_mutex);
- if (!atomic_dec_and_test(&root->refcnt)) {
- mutex_unlock(&cgroup_tree_mutex);
- return;
- }
mutex_lock(&cgroup_mutex);
- BUG_ON(atomic_read(&root->nr_cgrps) != 1);
+ BUG_ON(atomic_read(&root->nr_cgrps));
BUG_ON(!list_empty(&cgrp->children));
/* Rebind all subsystems back to the default hierarchy */
@@ -929,21 +909,24 @@ static void cgroup_free_fn(struct work_struct *work)
struct cgroup *cgrp = container_of(work, struct cgroup, destroy_work);
atomic_dec(&cgrp->root->nr_cgrps);
-
- /*
- * We get a ref to the parent, and put the ref when this cgroup is
- * being freed, so it's guaranteed that the parent won't be
- * destroyed before its children.
- */
- cgroup_put(cgrp->parent);
-
- /* put the root reference that we took when we created the cgroup */
- cgroup_put_root(cgrp->root);
-
cgroup_pidlist_destroy_all(cgrp);
- kernfs_put(cgrp->kn);
- kfree(cgrp);
+ if (cgrp->parent) {
+ /*
+ * We get a ref to the parent, and put the ref when this
+ * cgroup is being freed, so it's guaranteed that the
+ * parent won't be destroyed before its children.
+ */
+ cgroup_put(cgrp->parent);
+ kernfs_put(cgrp->kn);
+ kfree(cgrp);
+ } else {
+ /*
+ * This is top cgroup's refcnt reaching zero, which
+ * indicates that the root should be released.
+ */
+ cgroup_destroy_root(cgrp->root);
+ }
}
static void cgroup_free_rcu(struct rcu_head *head)
@@ -965,7 +948,7 @@ static void cgroup_put(struct cgroup *cgrp)
{
if (!atomic_dec_and_test(&cgrp->refcnt))
return;
- if (WARN_ON_ONCE(!cgroup_is_dead(cgrp)))
+ if (WARN_ON_ONCE(cgrp->parent && !cgroup_is_dead(cgrp)))
return;
/*
@@ -1356,7 +1339,6 @@ static void init_cgroup_root(struct cgroupfs_root *root)
{
struct cgroup *cgrp = &root->top_cgroup;
- atomic_set(&root->refcnt, 1);
INIT_LIST_HEAD(&root->root_list);
atomic_set(&root->nr_cgrps, 1);
cgrp->root = root;
@@ -1485,7 +1467,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
struct cgroup_sb_opts opts;
struct dentry *dentry;
int ret;
-
+retry:
mutex_lock(&cgroup_tree_mutex);
mutex_lock(&cgroup_mutex);
@@ -1531,7 +1513,21 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
}
}
- cgroup_get_root(root);
+ /*
+ * A root's lifetime is governed by its top cgroup. Zero
+ * ref indicate that the root is being destroyed. Wait for
+ * destruction to complete so that the subsystems are free.
+ * We can use wait_queue for the wait but this path is
+ * super cold. Let's just sleep for a bit and retry.
+ */
+ if (!atomic_inc_not_zero(&root->top_cgroup.refcnt)) {
+ mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
+ msleep(10);
+ goto retry;
+ }
+
+ ret = 0;
goto out_unlock;
}
@@ -1558,7 +1554,7 @@ out_unlock:
dentry = kernfs_mount(fs_type, flags, root->kf_root);
if (IS_ERR(dentry))
- cgroup_put_root(root);
+ cgroup_put(&root->top_cgroup);
return dentry;
}
@@ -1567,7 +1563,7 @@ static void cgroup_kill_sb(struct super_block *sb)
struct kernfs_root *kf_root = kernfs_root_from_sb(sb);
struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
- cgroup_put_root(root);
+ cgroup_put(&root->top_cgroup);
kernfs_kill_sb(sb);
}
@@ -3708,12 +3704,6 @@ static long cgroup_create(struct cgroup *parent, const char *name,
/* allocation complete, commit to creation */
list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
atomic_inc(&root->nr_cgrps);
-
- /*
- * Grab a reference on the root and parent so that they don't get
- * deleted while there are child cgroups.
- */
- cgroup_get_root(root);
cgroup_get(parent);
/*