summaryrefslogtreecommitdiffstats
path: root/fs/namespace.c
diff options
context:
space:
mode:
authorAl Viro <viro@zeniv.linux.org.uk>2020-01-11 10:44:29 -0500
committerAl Viro <viro@zeniv.linux.org.uk>2020-02-27 14:40:43 -0500
commit26df6034fdb211857e069e7b07d25a368da646df (patch)
tree92fb71e1251c745948fb0af18956795d957c115f /fs/namespace.c
parent8f11538ebe984e5434eeda4c7183d165cddb5936 (diff)
downloadlinux-26df6034fdb211857e069e7b07d25a368da646df.tar.bz2
fix automount/automount race properly
Protection against automount/automount races (two threads hitting the same referral point at the same time) is based upon do_add_mount() prevention of identical overmounts - trying to overmount the root of mounted tree with the same tree fails with -EBUSY. It's unreliable (the other thread might've mounted something on top of the automount it has triggered) *and* causes no end of headache for follow_automount() and its caller, since finish_automount() behaves like do_new_mount() - if the mountpoint to be is overmounted, it mounts on top what's overmounting it. It's not only wrong (we want to go into what's overmounting the automount point and quietly discard what we planned to mount there), it introduces the possibility of original parent mount getting dropped. That's what 8aef18845266 (VFS: Fix vfsmount overput on simultaneous automount) deals with, but it can't do anything about the reliability of conflict detection - if something had been overmounted the other thread's automount (e.g. that other thread having stepped into automount in mount(2)), we don't get that -EBUSY and the result is referral point under automounted NFS under explicit overmount under another copy of automounted NFS What we need is finish_automount() *NOT* digging into overmounts - if it finds one, it should just quietly discard the thing it was asked to mount. And don't bother with actually crossing into the results of finish_automount() - the same loop that calls follow_automount() will do that just fine on the next iteration. IOW, instead of calling lock_mount() have finish_automount() do it manually, _without_ the "move into overmount and retry" part. And leave crossing into the results to the caller of follow_automount(), which simplifies it a lot. Moral: if you end up with a lot of glue working around the calling conventions of something, perhaps these calling conventions are simply wrong... Fixes: 8aef18845266 (VFS: Fix vfsmount overput on simultaneous automount) Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Diffstat (limited to 'fs/namespace.c')
-rw-r--r--fs/namespace.c40
1 files changed, 33 insertions, 7 deletions
diff --git a/fs/namespace.c b/fs/namespace.c
index dcd015fafe01..777c3116e62e 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2823,6 +2823,7 @@ static int do_new_mount(struct path *path, const char *fstype, int sb_flags,
int finish_automount(struct vfsmount *m, struct path *path)
{
+ struct dentry *dentry = path->dentry;
struct mount *mnt = real_mount(m);
struct mountpoint *mp;
int err;
@@ -2832,21 +2833,46 @@ int finish_automount(struct vfsmount *m, struct path *path)
BUG_ON(mnt_get_count(mnt) < 2);
if (m->mnt_sb == path->mnt->mnt_sb &&
- m->mnt_root == path->dentry) {
+ m->mnt_root == dentry) {
err = -ELOOP;
- goto fail;
+ goto discard;
}
- mp = lock_mount(path);
+ /*
+ * we don't want to use lock_mount() - in this case finding something
+ * that overmounts our mountpoint to be means "quitely drop what we've
+ * got", not "try to mount it on top".
+ */
+ inode_lock(dentry->d_inode);
+ namespace_lock();
+ if (unlikely(cant_mount(dentry))) {
+ err = -ENOENT;
+ goto discard_locked;
+ }
+ rcu_read_lock();
+ if (unlikely(__lookup_mnt(path->mnt, dentry))) {
+ rcu_read_unlock();
+ err = 0;
+ goto discard_locked;
+ }
+ rcu_read_unlock();
+ mp = get_mountpoint(dentry);
if (IS_ERR(mp)) {
err = PTR_ERR(mp);
- goto fail;
+ goto discard_locked;
}
+
err = do_add_mount(mnt, mp, path, path->mnt->mnt_flags | MNT_SHRINKABLE);
unlock_mount(mp);
- if (!err)
- return 0;
-fail:
+ if (unlikely(err))
+ goto discard;
+ mntput(m);
+ return 0;
+
+discard_locked:
+ namespace_unlock();
+ inode_unlock(dentry->d_inode);
+discard:
/* remove m from any expiration list it may be on */
if (!list_empty(&mnt->mnt_expire)) {
namespace_lock();