vfs: protect remounting superblock read-only

Currently remouting superblock read-only is racy in a major way.

With the per mount read-only infrastructure it is now possible to
prevent most races, which this patch attempts.

Before starting the remount read-only, iterate through all mounts
belonging to the superblock and if none of them have any pending
writes, set sb->s_readonly_remount.  This indicates that remount is in
progress and no further write requests are allowed.  If the remount
succeeds set MS_RDONLY and reset s_readonly_remount.

If the remounting is unsuccessful just reset s_readonly_remount.
This can result in transient EROFS errors, despite the fact the
remount failed.  Unfortunately hodling off writes is difficult as
remount itself may touch the filesystem (e.g. through load_nls())
which would deadlock.

A later patch deals with delayed writes due to nlink going to zero.

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Tested-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 39 insertions, 1 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index 145217b..98ebc78 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -273,6 +273,15 @@ static unsigned int mnt_get_writers(struct mount *mnt)
 #endif
 }
 
+static int mnt_is_readonly(struct vfsmount *mnt)
+{
+	if (mnt->mnt_sb->s_readonly_remount)
+		return 1;
+	/* Order wrt setting s_flags/s_readonly_remount in do_remount() */
+	smp_rmb();
+	return __mnt_is_readonly(mnt);
+}
+
 /*
  * Most r/o checks on a fs are for operations that take
  * discrete amounts of time, like a write() or unlink().
@@ -312,7 +321,7 @@ int mnt_want_write(struct vfsmount *m)
 	 * MNT_WRITE_HOLD is cleared.
 	 */
 	smp_rmb();
-	if (__mnt_is_readonly(m)) {
+	if (mnt_is_readonly(m)) {
 		mnt_dec_writers(mnt);
 		ret = -EROFS;
 		goto out;
@@ -435,6 +444,35 @@ static void __mnt_unmake_readonly(struct mount *mnt)
 	br_write_unlock(vfsmount_lock);
 }
 
+int sb_prepare_remount_readonly(struct super_block *sb)
+{
+	struct mount *mnt;
+	int err = 0;
+
+	br_write_lock(vfsmount_lock);
+	list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) {
+		if (!(mnt->mnt.mnt_flags & MNT_READONLY)) {
+			mnt->mnt.mnt_flags |= MNT_WRITE_HOLD;
+			smp_mb();
+			if (mnt_get_writers(mnt) > 0) {
+				err = -EBUSY;
+				break;
+			}
+		}
+	}
+	if (!err) {
+		sb->s_readonly_remount = 1;
+		smp_wmb();
+	}
+	list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) {
+		if (mnt->mnt.mnt_flags & MNT_WRITE_HOLD)
+			mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD;
+	}
+	br_write_unlock(vfsmount_lock);
+
+	return err;
+}
+
 static void free_vfsmnt(struct mount *mnt)
 {
 	kfree(mnt->mnt_devname);