cgroup: fix cgroup_create() error handling path

ae7f164a09 ("cgroup: move cgroup->subsys[] assignment to
online_css()") moved cgroup->subsys[] assignements later in
cgroup_create() but didn't update error handling path accordingly
leading to the following oops and leaking later css's after an
online_css() failure.  The oops is from cgroup destruction path being
invoked on the partially constructed cgroup which is not ready to
handle empty slots in cgrp->subsys[] array.

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
  IP: [<ffffffff810eeaa8>] cgroup_destroy_locked+0x118/0x2f0
  PGD a780a067 PUD aadbe067 PMD 0
  Oops: 0000 [#1] SMP
  Modules linked in:
  CPU: 6 PID: 7360 Comm: mkdir Not tainted 3.13.0-rc2+ #69
  Hardware name:
  task: ffff8800b9dbec00 ti: ffff8800a781a000 task.ti: ffff8800a781a000
  RIP: 0010:[<ffffffff810eeaa8>]  [<ffffffff810eeaa8>] cgroup_destroy_locked+0x118/0x2f0
  RSP: 0018:ffff8800a781bd98  EFLAGS: 00010282
  RAX: ffff880586903878 RBX: ffff880586903800 RCX: ffff880586903820
  RDX: ffff880586903860 RSI: ffff8800a781bdb0 RDI: ffff880586903820
  RBP: ffff8800a781bde8 R08: ffff88060e0b8048 R09: ffffffff811d7bc1
  R10: 000000000000008c R11: 0000000000000001 R12: ffff8800a72286c0
  R13: 0000000000000000 R14: ffffffff81cf7a40 R15: 0000000000000001
  FS:  00007f60ecda57a0(0000) GS:ffff8806272c0000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000000000000008 CR3: 00000000a7a03000 CR4: 00000000000007e0
  Stack:
   ffff880586903860 ffff880586903910 ffff8800a72286c0 ffff880586903820
   ffffffff81cf7a40 ffff880586903800 ffff88060e0b8018 ffffffff81cf7a40
   ffff8800b9dbec00 ffff8800b9dbf098 ffff8800a781bec8 ffffffff810ef5bf
  Call Trace:
   [<ffffffff810ef5bf>] cgroup_mkdir+0x55f/0x5f0
   [<ffffffff811c90ae>] vfs_mkdir+0xee/0x140
   [<ffffffff811cb07e>] SyS_mkdirat+0x6e/0xf0
   [<ffffffff811c6a19>] SyS_mkdir+0x19/0x20
   [<ffffffff8169e569>] system_call_fastpath+0x16/0x1b

This patch moves reference bumping inside online_css() loop, clears
css_ar[] as css's are brought online successfully, and updates
err_destroy path so that either a css is fully online and destroyed by
cgroup_destroy_locked() or the error path frees it.  This creates a
duplicate css free logic in the error path but it will be cleaned up
soon.

v2: Li pointed out that cgroup_destroy_locked() would do NULL-deref if
    invoked with a cgroup which doesn't have all css's populated.
    Update cgroup_destroy_locked() so that it skips NULL css's.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Reported-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: stable@vger.kernel.org # v3.12+

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 8b729c2..bcb1755 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4426,14 +4426,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
        list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
        root->number_of_cgroups++;
 
-       /* each css holds a ref to the cgroup's dentry and the parent css */
-       for_each_root_subsys(root, ss) {
-               struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
-
-               dget(dentry);
-               css_get(css->parent);
-       }
-
        /* hold a ref to the parent's dentry */
        dget(parent->dentry);
 
@@ -4445,6 +4437,13 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
                if (err)
                        goto err_destroy;
 
+               /* each css holds a ref to the cgroup's dentry and parent css */
+               dget(dentry);
+               css_get(css->parent);
+
+               /* mark it consumed for error path */
+               css_ar[ss->subsys_id] = NULL;
+
                if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
                    parent->parent) {
                        pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
@@ -4491,6 +4490,14 @@ err_free_cgrp:
        return err;
 
 err_destroy:
+       for_each_root_subsys(root, ss) {
+               struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
+
+               if (css) {
+                       percpu_ref_cancel_init(&css->refcnt);
+                       ss->css_free(css);
+               }
+       }
        cgroup_destroy_locked(cgrp);
        mutex_unlock(&cgroup_mutex);
        mutex_unlock(&dentry->d_inode->i_mutex);
@@ -4652,8 +4659,12 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
         * will be invoked to perform the rest of destruction once the
         * percpu refs of all css's are confirmed to be killed.
         */
-       for_each_root_subsys(cgrp->root, ss)
-               kill_css(cgroup_css(cgrp, ss));
+       for_each_root_subsys(cgrp->root, ss) {
+               struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
+
+               if (css)
+                       kill_css(css);
+       }
 
        /*
         * Mark @cgrp dead.  This prevents further task migration and child