1 files changed, 50 insertions, 8 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 7868fc3c0bc5..70776aec2562 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1648,10 +1648,13 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
                          int flags, const char *unused_dev_name,
                          void *data)
 {
+        struct super_block *pinned_sb = NULL;
+        struct cgroup_subsys *ss;
         struct cgroup_root *root;
         struct cgroup_sb_opts opts;
         struct dentry *dentry;
         int ret;
+        int i;
         bool new_sb;
 
         /*
@@ -1677,6 +1680,27 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
                 goto out_unlock;
         }
 
+        /*
+         * Destruction of cgroup root is asynchronous, so subsystems may
+         * still be dying after the previous unmount.  Let's drain the
+         * dying subsystems.  We just need to ensure that the ones
+         * unmounted previously finish dying and don't care about new ones
+         * starting.  Testing ref liveliness is good enough.
+         */
+        for_each_subsys(ss, i) {
+                if (!(opts.subsys_mask & (1 << i)) ||
+                    ss->root == &cgrp_dfl_root)
+                        continue;
+
+                if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) {
+                        mutex_unlock(&cgroup_mutex);
+                        msleep(10);
+                        ret = restart_syscall();
+                        goto out_free;
+                }
+                cgroup_put(&ss->root->cgrp);
+        }
+
         for_each_root(root) {
                 bool name_match = false;
 
@@ -1717,15 +1741,23 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
                 }
 
                 /*
-                 * A root's lifetime is governed by its root cgroup.
-                 * tryget_live failure 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.
+                 * We want to reuse @root whose lifetime is governed by its
+                 * ->cgrp.  Let's check whether @root is alive and keep it
+                 * that way.  As cgroup_kill_sb() can happen anytime, we
+                 * want to block it by pinning the sb so that @root doesn't
+                 * get killed before mount is complete.
+                 *
+                 * With the sb pinned, tryget_live can reliably indicate
+                 * whether @root can be reused.  If it's being killed,
+                 * drain it.  We can use wait_queue for the wait but this
+                 * path is super cold.  Let's just sleep a bit and retry.
                  */
-                if (!percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
+                pinned_sb = kernfs_pin_sb(root->kf_root, NULL);
+                if (IS_ERR(pinned_sb) ||
+                    !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
                         mutex_unlock(&cgroup_mutex);
+                        if (!IS_ERR_OR_NULL(pinned_sb))
+                                deactivate_super(pinned_sb);
                         msleep(10);
                         ret = restart_syscall();
                         goto out_free;
@@ -1770,6 +1802,16 @@ out_free:
                                 CGROUP_SUPER_MAGIC, &new_sb);
         if (IS_ERR(dentry) || !new_sb)
                 cgroup_put(&root->cgrp);
+
+        /*
+         * If @pinned_sb, we're reusing an existing root and holding an
+         * extra ref on its sb.  Mount is complete.  Put the extra ref.
+         */
+        if (pinned_sb) {
+                WARN_ON(new_sb);
+                deactivate_super(pinned_sb);
+        }
+
         return dentry;
 }
 
@@ -3328,7 +3370,7 @@ bool css_has_online_children(struct cgroup_subsys_state *css)
 
         rcu_read_lock();
         css_for_each_child(child, css) {
-                if (css->flags & CSS_ONLINE) {
+                if (child->flags & CSS_ONLINE) {
                         ret = true;
                         break;
                 }