[PATCH v2 10/10] ovl: implement containerized syncfs for overlayfs

[Josef Bacik <josef@toxicpanda.com>]

From: Chengguang Xu <charliecgxu@tencent.com>

Now overlayfs can only sync own dirty inodes during syncfs,
so remove unnecessary sync_filesystem() on upper file system.

Call ->sync_fs() and write the block device of the upper filesystem
instead, which is what sync_filesystem() does after it has written the
inodes.  Do the same for a read-only remount.

With many containers on one upper filesystem, stopping one of them no
longer writes out the dirty data of all the others.

Signed-off-by: Chengguang Xu <charliecgxu@tencent.com>
[josef: everything after the first paragraph, no wait_sb_inodes() on the
 upper filesystem]
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
---
 fs/overlayfs/params.c | 14 +++-----------
 fs/overlayfs/super.c  | 28 ++++++++++++++++++++--------
 2 files changed, 23 insertions(+), 19 deletions(-)

diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c
index 5a15e5478a6b..43fe0b1ef11f 100644
--- a/fs/overlayfs/params.c
+++ b/fs/overlayfs/params.c
@@ -764,22 +764,14 @@ static int ovl_reconfigure(struct fs_context *fc)
 {
 	struct super_block *sb = fc->root->d_sb;
 	struct ovl_fs *ofs = OVL_FS(sb);
-	struct super_block *upper_sb;
-	int ret = 0;
 
 	if (!(fc->sb_flags & SB_RDONLY) && ovl_force_readonly(ofs))
 		return -EROFS;
 
-	if (fc->sb_flags & SB_RDONLY && !sb_rdonly(sb)) {
-		upper_sb = ovl_upper_mnt(ofs)->mnt_sb;
-		if (ovl_should_sync(ofs)) {
-			down_read(&upper_sb->s_umount);
-			ret = sync_filesystem(upper_sb);
-			up_read(&upper_sb->s_umount);
-		}
-	}
+	if (fc->sb_flags & SB_RDONLY && !sb_rdonly(sb) && ovl_should_sync(ofs))
+		return sync_filesystem(sb);
 
-	return ret;
+	return 0;
 }
 
 static const struct fs_context_operations ovl_context_ops = {
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 84258edb5530..361a3afa4ac8 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -15,6 +15,7 @@
 #include <linux/seq_file.h>
 #include <linux/posix_acl_xattr.h>
 #include <linux/exportfs.h>
+#include <linux/blkdev.h>
 #include <linux/pagemap.h>
 #include <linux/writeback.h>
 #include <linux/file.h>
@@ -271,18 +272,29 @@ static int ovl_sync_fs(struct super_block *sb, int wait)
 	/*
 	 * Not called for sync(2) call or an emergency sync (SB_I_SKIP_SYNC).
 	 * All the super blocks will be iterated, including upper_sb.
-	 *
-	 * If this is a syncfs(2) call, then we do need to call
-	 * sync_filesystem() on upper_sb, but enough if we do it when being
-	 * called with wait == 1.
 	 */
-	if (!wait)
-		return 0;
-
 	upper_sb = ovl_upper_mnt(ofs)->mnt_sb;
 
+	/*
+	 * sync_filesystem() has already written the dirty inodes of this
+	 * overlay through ovl_write_inode(), including the fake ones, see
+	 * ovl_upper_modified().  What is left are the last two steps of
+	 * sync_filesystem() on the upper filesystem.  Do not write the inodes
+	 * that others have dirtied there.
+	 */
 	down_read(&upper_sb->s_umount);
-	ret = sync_filesystem(upper_sb);
+	/* Like sync_filesystem(), do not call ->sync_fs() on a read-only sb */
+	ret = 0;
+	if (sb_rdonly(upper_sb))
+		goto out;
+
+	if (upper_sb->s_op->sync_fs)
+		ret = upper_sb->s_op->sync_fs(upper_sb, wait);
+	if (!ret && wait)
+		ret = sync_blockdev(upper_sb->s_bdev);
+	else if (!ret)
+		ret = sync_blockdev_nowait(upper_sb->s_bdev);
+out:
 	up_read(&upper_sb->s_umount);
 
 	return ret;

-- 
2.55.0