ovl: make private mounts longterm

Overlayfs is using clone_private_mount() to create internal mounts for
underlying layers.  These are used for operations requiring a path, such as
dentry_open().

Since these private mounts are not in any namespace they are treated as
short term, "detached" mounts and mntput() involves taking the global
mount_lock, which can result in serious cacheline pingpong.

Make these private mounts longterm instead, which trade the penalty on
mntput() for a slightly longer shutdown time due to an added RCU grace
period when putting these mounts.

Introduce a new helper kern_unmount_many() that can take care of multiple
longterm mounts with a single RCU grace period.

Cc: Al Viro <[email protected]>
Signed-off-by: Miklos Szeredi <[email protected]>

Author: Miklos Szeredi

Documentation/filesystems/porting.rst

@@ -858,3 +858,10 @@ be misspelled d_alloc_anon().
 [should've been added in 2016] stale comment in finish_open() nonwithstanding,
 failure exits in ->atomic_open() instances should *NOT* fput() the file,
 no matter what.  Everything is handled by the caller.
+
+---
+
+**mandatory**
+
+clone_private_mount() returns a longterm mount now, so the proper destructor of
+its result is kern_unmount() or kern_unmount_array().

fs/namespace.c

@@ -1879,6 +1879,9 @@ struct vfsmount *clone_private_mount(const struct path *path)
 	if (IS_ERR(new_mnt))
 		return ERR_CAST(new_mnt);
 
+	/* Longterm mount to be removed by kern_unmount*() */
+	new_mnt->mnt_ns = MNT_NS_INTERNAL;
+
 	return &new_mnt->mnt;
 }
 EXPORT_SYMBOL_GPL(clone_private_mount);
@@ -3804,6 +3807,19 @@ void kern_unmount(struct vfsmount *mnt)
 }
 EXPORT_SYMBOL(kern_unmount);
 
+void kern_unmount_array(struct vfsmount *mnt[], unsigned int num)
+{
+	unsigned int i;
+
+	for (i = 0; i < num; i++)
+		if (mnt[i])
+			real_mount(mnt[i])->mnt_ns = NULL;
+	synchronize_rcu_expedited();
+	for (i = 0; i < num; i++)
+		mntput(mnt[i]);
+}
+EXPORT_SYMBOL(kern_unmount_array);
+
 bool our_mnt(struct vfsmount *mnt)
 {
 	return check_mnt(real_mount(mnt));

fs/overlayfs/super.c

@@ -211,6 +211,7 @@ static void ovl_destroy_inode(struct inode *inode)
 
 static void ovl_free_fs(struct ovl_fs *ofs)
 {
+	struct vfsmount **mounts;
 	unsigned i;
 
 	iput(ofs->workbasedir_trap);
@@ -224,10 +225,14 @@ static void ovl_free_fs(struct ovl_fs *ofs)
 	dput(ofs->workbasedir);
 	if (ofs->upperdir_locked)
 		ovl_inuse_unlock(ovl_upper_mnt(ofs)->mnt_root);
+
+	/* Hack!  Reuse ofs->layers as a vfsmount array before freeing it */
+	mounts = (struct vfsmount **) ofs->layers;
 	for (i = 0; i < ofs->numlayer; i++) {
 		iput(ofs->layers[i].trap);
-		mntput(ofs->layers[i].mnt);
+		mounts[i] = ofs->layers[i].mnt;
 	}
+	kern_unmount_array(mounts, ofs->numlayer);
 	kfree(ofs->layers);
 	for (i = 0; i < ofs->numfs; i++)
 		free_anon_bdev(ofs->fs[i].pseudo_dev);

include/linux/mount.h

@@ -109,4 +109,6 @@ extern unsigned int sysctl_mount_max;
 
 extern bool path_is_mountpoint(const struct path *path);
 
+extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num);
+
 #endif /* _LINUX_MOUNT_H */