proc: Fix proc_sys_prune_dcache to hold a sb reference

Andrei Vagin writes:
FYI: This bug has been reproduced on 4.11.7
> BUG: Dentry ffff895a3dd01240{i=4e7c09a,n=lo}  still in use (1) [unmount of proc proc]
> ------------[ cut here ]------------
> WARNING: CPU: 1 PID: 13588 at fs/dcache.c:1445 umount_check+0x6e/0x80
> CPU: 1 PID: 13588 Comm: kworker/1:1 Not tainted 4.11.7-200.fc25.x86_64 #1
> Hardware name: CompuLab sbc-flt1/fitlet, BIOS SBCFLT_0.08.04 06/27/2015
> Workqueue: events proc_cleanup_work
> Call Trace:
>  dump_stack+0x63/0x86
>  __warn+0xcb/0xf0
>  warn_slowpath_null+0x1d/0x20
>  umount_check+0x6e/0x80
>  d_walk+0xc6/0x270
>  ? dentry_free+0x80/0x80
>  do_one_tree+0x26/0x40
>  shrink_dcache_for_umount+0x2d/0x90
>  generic_shutdown_super+0x1f/0xf0
>  kill_anon_super+0x12/0x20
>  proc_kill_sb+0x40/0x50
>  deactivate_locked_super+0x43/0x70
>  deactivate_super+0x5a/0x60
>  cleanup_mnt+0x3f/0x90
>  mntput_no_expire+0x13b/0x190
>  kern_unmount+0x3e/0x50
>  pid_ns_release_proc+0x15/0x20
>  proc_cleanup_work+0x15/0x20
>  process_one_work+0x197/0x450
>  worker_thread+0x4e/0x4a0
>  kthread+0x109/0x140
>  ? process_one_work+0x450/0x450
>  ? kthread_park+0x90/0x90
>  ret_from_fork+0x2c/0x40
> ---[ end trace e1c109611e5d0b41 ]---
> VFS: Busy inodes after unmount of proc. Self-destruct in 5 seconds.  Have a nice day...
> BUG: unable to handle kernel NULL pointer dereference at           (null)
> IP: _raw_spin_lock+0xc/0x30
> PGD 0

Fix this by taking a reference to the super block in proc_sys_prune_dcache.

The superblock reference is the core of the fix however the sysctl_inodes
list is converted to a hlist so that hlist_del_init_rcu may be used.  This
allows proc_sys_prune_dache to remove inodes the sysctl_inodes list, while
not causing problems for proc_sys_evict_inode when if it later choses to
remove the inode from the sysctl_inodes list.  Removing inodes from the
sysctl_inodes list allows proc_sys_prune_dcache to have a progress
guarantee, while still being able to drop all locks.  The fact that
head->unregistering is set in start_unregistering ensures that no more
inodes will be added to the the sysctl_inodes list.

Previously the code did a dance where it delayed calling iput until the
next entry in the list was being considered to ensure the inode remained on
the sysctl_inodes list until the next entry was walked to.  The structure
of the loop in this patch does not need that so is much easier to
understand and maintain.

Cc: stable@vger.kernel.org
Reported-by: Andrei Vagin <avagin@gmail.com>
Tested-by: Andrei Vagin <avagin@openvz.org>
Fixes: ace0c791e6c3 ("proc/sysctl: Don't grab i_lock under sysctl_lock.")
Fixes: d6cffbbe9a7e ("proc/sysctl: prune stale dentries during unregistering")
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

1 files changed, 30 insertions, 13 deletions

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 67985a7233c2..9bf06e2b1284 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -191,7 +191,7 @@ static void init_header(struct ctl_table_header *head,
 	head->set = set;
 	head->parent = NULL;
 	head->node = node;
-	INIT_LIST_HEAD(&head->inodes);
+	INIT_HLIST_HEAD(&head->inodes);
 	if (node) {
 		struct ctl_table *entry;
 		for (entry = table; entry->procname; entry++, node++)
@@ -261,25 +261,42 @@ static void unuse_table(struct ctl_table_header *p)
 			complete(p->unregistering);
 }
 
-/* called under sysctl_lock */
 static void proc_sys_prune_dcache(struct ctl_table_header *head)
 {
-	struct inode *inode, *prev = NULL;
+	struct inode *inode;
 	struct proc_inode *ei;
+	struct hlist_node *node;
+	struct super_block *sb;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(ei, &head->inodes, sysctl_inodes) {
-		inode = igrab(&ei->vfs_inode);
-		if (inode) {
-			rcu_read_unlock();
-			iput(prev);
-			prev = inode;
-			d_prune_aliases(inode);
+	for (;;) {
+		node = hlist_first_rcu(&head->inodes);
+		if (!node)
+			break;
+		ei = hlist_entry(node, struct proc_inode, sysctl_inodes);
+		spin_lock(&sysctl_lock);
+		hlist_del_init_rcu(&ei->sysctl_inodes);
+		spin_unlock(&sysctl_lock);
+
+		inode = &ei->vfs_inode;
+		sb = inode->i_sb;
+		if (!atomic_inc_not_zero(&sb->s_active))
+			continue;
+		inode = igrab(inode);
+		rcu_read_unlock();
+		if (unlikely(!inode)) {
+			deactivate_super(sb);
 			rcu_read_lock();
+			continue;
 		}
+
+		d_prune_aliases(inode);
+		iput(inode);
+		deactivate_super(sb);
+
+		rcu_read_lock();
 	}
 	rcu_read_unlock();
-	iput(prev);
 }
 
 /* called under sysctl_lock, will reacquire if has to wait */
@@ -461,7 +478,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
 	}
 	ei->sysctl = head;
 	ei->sysctl_entry = table;
-	list_add_rcu(&ei->sysctl_inodes, &head->inodes);
+	hlist_add_head_rcu(&ei->sysctl_inodes, &head->inodes);
 	head->count++;
 	spin_unlock(&sysctl_lock);
 
@@ -489,7 +506,7 @@ out:
 void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head)
 {
 	spin_lock(&sysctl_lock);
-	list_del_rcu(&PROC_I(inode)->sysctl_inodes);
+	hlist_del_init_rcu(&PROC_I(inode)->sysctl_inodes);
 	if (!--head->count)
 		kfree_rcu(head, rcu);
 	spin_unlock(&sysctl_lock);