ovl: implement volatile-specific fsync error behaviour

Overlayfs's volatile option allows the user to bypass all forced sync calls
to the upperdir filesystem. This comes at the cost of safety. We can never
ensure that the user's data is intact, but we can make a best effort to
expose whether or not the data is likely to be in a bad state.

The best way to handle this in the time being is that if an overlayfs's
upperdir experiences an error after a volatile mount occurs, that error
will be returned on fsync, fdatasync, sync, and syncfs. This is
contradictory to the traditional behaviour of VFS which fails the call
once, and only raises an error if a subsequent fsync error has occurred,
and been raised by the filesystem.

One awkward aspect of the patch is that we have to manually set the
superblock's errseq_t after the sync_fs callback as opposed to just
returning an error from syncfs. This is because the call chain looks
something like this:

sys_syncfs ->
	sync_filesystem ->
		__sync_filesystem ->
			/* The return value is ignored here
			sb->s_op->sync_fs(sb)
			_sync_blockdev
		/* Where the VFS fetches the error to raise to userspace */
		errseq_check_and_advance

Because of this we call errseq_set every time the sync_fs callback occurs.
Due to the nature of this seen / unseen dichotomy, if the upperdir is an
inconsistent state at the initial mount time, overlayfs will refuse to
mount, as overlayfs cannot get a snapshot of the upperdir's errseq that
will increment on error until the user calls syncfs.

Signed-off-by: Sargun Dhillon <sargun@sargun.me>
Suggested-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Fixes: c86243b090bc ("ovl: provide a mount option "volatile"")
Cc: stable@vger.kernel.org
Reviewed-by: Vivek Goyal <vgoyal@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

1 files changed, 27 insertions, 7 deletions

diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 82cd6d55a5a1..d58b8f2bf9d0 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -264,11 +264,20 @@ static int ovl_sync_fs(struct super_block *sb, int wait)
 	struct super_block *upper_sb;
 	int ret;
 
-	if (!ovl_upper_mnt(ofs))
-		return 0;
+	ret = ovl_sync_status(ofs);
+	/*
+	 * We have to always set the err, because the return value isn't
+	 * checked in syncfs, and instead indirectly return an error via
+	 * the sb's writeback errseq, which VFS inspects after this call.
+	 */
+	if (ret < 0) {
+		errseq_set(&sb->s_wb_err, -EIO);
+		return -EIO;
+	}
+
+	if (!ret)
+		return ret;
 
-	if (!ovl_should_sync(ofs))
-		return 0;
 	/*
 	 * Not called for sync(2) call or an emergency sync (SB_I_SKIP_SYNC).
 	 * All the super blocks will be iterated, including upper_sb.
@@ -1993,6 +2002,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_op = &ovl_super_operations;
 
 	if (ofs->config.upperdir) {
+		struct super_block *upper_sb;
+
 		if (!ofs->config.workdir) {
 			pr_err("missing 'workdir'\n");
 			goto out_err;
@@ -2002,6 +2013,16 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		if (err)
 			goto out_err;
 
+		upper_sb = ovl_upper_mnt(ofs)->mnt_sb;
+		if (!ovl_should_sync(ofs)) {
+			ofs->errseq = errseq_sample(&upper_sb->s_wb_err);
+			if (errseq_check(&upper_sb->s_wb_err, ofs->errseq)) {
+				err = -EIO;
+				pr_err("Cannot mount volatile when upperdir has an unseen error. Sync upperdir fs to clear state.\n");
+				goto out_err;
+			}
+		}
+
 		err = ovl_get_workdir(sb, ofs, &upperpath);
 		if (err)
 			goto out_err;
@@ -2009,9 +2030,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		if (!ofs->workdir)
 			sb->s_flags |= SB_RDONLY;
 
-		sb->s_stack_depth = ovl_upper_mnt(ofs)->mnt_sb->s_stack_depth;
-		sb->s_time_gran = ovl_upper_mnt(ofs)->mnt_sb->s_time_gran;
-
+		sb->s_stack_depth = upper_sb->s_stack_depth;
+		sb->s_time_gran = upper_sb->s_time_gran;
 	}
 	oe = ovl_get_lowerstack(sb, splitlower, numlower, ofs, layers);
 	err = PTR_ERR(oe);