[PATCH] ovl: make private mounts longterm

[Miklos Szeredi]

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 <viro@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Miklos Szeredi <mszeredi@xxxxxxxxxx>
---
 fs/namespace.c        | 16 ++++++++++++++++
 fs/overlayfs/super.c  | 19 ++++++++++++++-----
 include/linux/mount.h |  2 ++
 3 files changed, 32 insertions(+), 5 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index a28e4db075ed..5d16d87b6b8b 100644
--- a/fs/namespace.c
+++ b/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_many(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_many);
+
 bool our_mnt(struct vfsmount *mnt)
 {
 	return check_mnt(real_mount(mnt));
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 60dfb27bc12b..a938dd2521b2 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -225,12 +225,21 @@ static void ovl_free_fs(struct ovl_fs *ofs)
 	dput(ofs->workbasedir);
 	if (ofs->upperdir_locked)
 		ovl_inuse_unlock(ofs->upper_mnt->mnt_root);
-	mntput(ofs->upper_mnt);
-	for (i = 1; i < ofs->numlayer; i++) {
-		iput(ofs->layers[i].trap);
-		mntput(ofs->layers[i].mnt);
+
+	if (!ofs->layers) {
+		/* Deal with partial setup */
+		kern_unmount(ofs->upper_mnt);
+	} else {
+		/* Hack!  Reuse ofs->layers as a mounts array */
+		struct vfsmount **mounts = (struct vfsmount **) ofs->layers;
+
+		for (i = 0; i < ofs->numlayer; i++) {
+			iput(ofs->layers[i].trap);
+			mounts[i] = ofs->layers[i].mnt;
+		}
+		kern_unmount_many(mounts, ofs->numlayer);
+		kfree(ofs->layers);
 	}
-	kfree(ofs->layers);
 	for (i = 0; i < ofs->numfs; i++)
 		free_anon_bdev(ofs->fs[i].pseudo_dev);
 	kfree(ofs->fs);
diff --git a/include/linux/mount.h b/include/linux/mount.h
index bf8cc4108b8f..e3e994bfcecb 100644
--- a/include/linux/mount.h
+++ b/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_many(struct vfsmount *mnt[], unsigned int num);
+
 #endif /* _LINUX_MOUNT_H */
-- 
2.21.1