cgroup: make cgroup hold onto its kernfs_node

cgroup currently releases its kernfs_node when it gets removed.  While
not buggy, this makes cgroup->kn access rules complicated than
necessary and leads to things like get/put protection around
kernfs_remove() in cgroup_destroy_locked().  In addition, we want to
use kernfs_name/path() and friends but also want to be able to
determine a cgroup's name between removal and release.

This patch makes cgroup hold onto its kernfs_node until freed so that
cgroup->kn is always accessible.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index f4409715a2f59ca1798df2314ebcb0e33db45fb6..59dfb025f1ac66c8391838243d7fbbf7207c6aa4 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -957,6 +957,8 @@ static void cgroup_free_fn(struct work_struct *work)
 
        cgroup_pidlist_destroy_all(cgrp);
 
+       kernfs_put(cgrp->kn);
+
        kfree(rcu_dereference_raw(cgrp->name));
        kfree(cgrp);
 }
@@ -3786,6 +3788,12 @@ static long cgroup_create(struct cgroup *parent, const char *name_str,
        }
        cgrp->kn = kn;
 
+       /*
+        * This extra ref will be put in cgroup_free_fn() and guarantees
+        * that @cgrp->kn is always accessible.
+        */
+       kernfs_get(kn);
+
        cgrp->serial_nr = cgroup_serial_nr_next++;
 
        /* allocation complete, commit to creation */
@@ -3966,7 +3974,6 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 {
        struct cgroup *child;
        struct cgroup_subsys_state *css;
-       struct kernfs_node *kn;
        bool empty;
        int ssid;
 
@@ -4044,13 +4051,8 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
         * clearing of cgrp->kn->priv backpointer, which should happen
         * after all files under it have been removed.
         */
-       kn = cgrp->kn;
-       kernfs_get(kn);
-
-       kernfs_remove(cgrp->kn);
-
+       kernfs_remove(cgrp->kn);        /* @cgrp has an extra ref on its kn */
        RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL);
-       kernfs_put(kn);
 
        mutex_lock(&cgroup_mutex);