death to mnt_pinned

Rather than playing silly buggers with vfsmount refcounts, just have
acct_on() ask fs/namespace.c for internal clone of file->f_path.mnt
and replace it with said clone.  Then attach the pin to original
vfsmount.  Voila - the clone will be alive until the file gets closed,
making sure that underlying superblock remains active, etc., and
we can drop the original vfsmount, so that it's not kept busy.
If the file lives until the final mntput of the original vfsmount,
we'll notice that there's an fs_pin (one in bsd_acct_struct that
holds that file) and mnt_pin_kill() will take it out.  Since
->kill() is synchronous, we won't proceed past that point until
these files are closed (and private clones of our vfsmount are
gone), so we get the same ordering warranties we used to get.

mnt_pin()/mnt_unpin()/->mnt_pinned is gone now, and good riddance -
it never became usable outside of kernel/acct.c (and racy wrt
umount even there).

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

2 files changed, 9 insertions, 27 deletions

diff --git a/fs/mount.h b/fs/mount.h
index 0a2d1458681f..6740a6215529 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -55,7 +55,6 @@ struct mount {
 	int mnt_id;			/* mount identifier */
 	int mnt_group_id;		/* peer group identifier */
 	int mnt_expiry_mark;		/* true if marked for expiry */
-	int mnt_pinned;
 	struct hlist_head mnt_pins;
 	struct path mnt_ex_mountpoint;
 };
diff --git a/fs/namespace.c b/fs/namespace.c
index 0e4ce51c5277..65af9d0e0d67 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -937,7 +937,6 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 
 static void mntput_no_expire(struct mount *mnt)
 {
-put_again:
 	rcu_read_lock();
 	mnt_add_count(mnt, -1);
 	if (likely(mnt->mnt_ns)) { /* shouldn't be the last one */
@@ -950,14 +949,6 @@ put_again:
 		unlock_mount_hash();
 		return;
 	}
-	if (unlikely(mnt->mnt_pinned)) {
-		mnt_add_count(mnt, mnt->mnt_pinned + 1);
-		mnt->mnt_pinned = 0;
-		rcu_read_unlock();
-		unlock_mount_hash();
-		mnt_pin_kill(mnt);
-		goto put_again;
-	}
 	if (unlikely(mnt->mnt.mnt_flags & MNT_DOOMED)) {
 		rcu_read_unlock();
 		unlock_mount_hash();
@@ -980,6 +971,8 @@ put_again:
 	 * so mnt_get_writers() below is safe.
 	 */
 	WARN_ON(mnt_get_writers(mnt));
+	if (unlikely(mnt->mnt_pins.first))
+		mnt_pin_kill(mnt);
 	fsnotify_vfsmount_delete(&mnt->mnt);
 	dput(mnt->mnt.mnt_root);
 	deactivate_super(mnt->mnt.mnt_sb);
@@ -1007,25 +1000,15 @@ struct vfsmount *mntget(struct vfsmount *mnt)
 }
 EXPORT_SYMBOL(mntget);
 
-void mnt_pin(struct vfsmount *mnt)
+struct vfsmount *mnt_clone_internal(struct path *path)
 {
-	lock_mount_hash();
-	real_mount(mnt)->mnt_pinned++;
-	unlock_mount_hash();
-}
-EXPORT_SYMBOL(mnt_pin);
-
-void mnt_unpin(struct vfsmount *m)
-{
-	struct mount *mnt = real_mount(m);
-	lock_mount_hash();
-	if (mnt->mnt_pinned) {
-		mnt_add_count(mnt, 1);
-		mnt->mnt_pinned--;
-	}
-	unlock_mount_hash();
+	struct mount *p;
+	p = clone_mnt(real_mount(path->mnt), path->dentry, CL_PRIVATE);
+	if (IS_ERR(p))
+		return ERR_CAST(p);
+	p->mnt.mnt_flags |= MNT_INTERNAL;
+	return &p->mnt;
 }
-EXPORT_SYMBOL(mnt_unpin);
 
 static inline void mangle(struct seq_file *m, const char *s)
 {