[PATCH 6/8] vfs: Make sys_sync writeout also block device inodes

[Jan Kara <jack@suse.cz>]

In case block device does not have filesystem mounted on it, sys_sync will just
ignore it and doesn't writeout its dirty pages. This is because writeback code
avoids writing inodes from superblock without backing device and
blockdev_superblock is such a superblock.  Since it's unexpected that sync
doesn't writeout dirty data for block devices be nice to users and change the
behavior to do so. So now we iterate over all block devices on blockdev_super
instead of iterating over all superblocks when syncing block devices.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/sync.c |   58 +++++++++++++++++++++++++++++++++++++++++++++++++++-------
 1 files changed, 51 insertions(+), 7 deletions(-)

diff --git a/fs/sync.c b/fs/sync.c
index e62a57b..ccaaa1b 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -86,10 +86,54 @@ static void sync_fs_one_sb(struct super_block *sb, void *arg)
 		sb->s_op->sync_fs(sb, *(int *)arg);
 }
 
-static void sync_blkdev_one_sb(struct super_block *sb, void *arg)
+/*
+ * We go through all existing block devices so that even devices without
+ * filesystem mounted are synced.
+ */
+static void sync_all_bdevs(int wait)
 {
-	if (!(sb->s_flags & MS_RDONLY))
-		__sync_blockdev(sb->s_bdev, *(int *)arg);
+	struct inode *inode, *old_inode = NULL;
+
+	spin_lock(&inode_sb_list_lock);
+	list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) {
+		struct address_space *mapping = inode->i_mapping;
+
+		spin_lock(&inode->i_lock);
+		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) ||
+		    mapping->nrpages == 0) {
+			spin_unlock(&inode->i_lock);
+			continue;
+		}
+		__iget(inode);
+		spin_unlock(&inode->i_lock);
+		spin_unlock(&inode_sb_list_lock);
+		/*
+		 * We hold a reference to 'inode' so it couldn't have been
+		 * removed from s_inodes list while we dropped the
+		 * inode_sb_list_lock.  We cannot iput the inode now as we can
+		 * be holding the last reference and we cannot iput it under
+		 * inode_sb_list_lock. So we keep the reference and iput it
+		 * later.
+		 */
+		iput(old_inode);
+		old_inode = inode;
+
+		__sync_blockdev(I_BDEV(inode), wait);
+
+		spin_lock(&inode_sb_list_lock);
+	}
+	spin_unlock(&inode_sb_list_lock);
+	iput(old_inode);
+}
+
+static void flush_one_bdev(struct block_device *bdev, void *arg)
+{
+	__sync_blockdev(bdev, 0);
+}
+
+static void sync_one_bdev(struct block_device *bdev, void *arg)
+{
+	sync_blockdev(bdev);
 }
 
 /*
@@ -103,10 +147,10 @@ SYSCALL_DEFINE0(sync)
 	wakeup_flusher_threads(0, WB_REASON_SYNC);
 	iterate_supers(writeback_inodes_one_sb, NULL);
 	iterate_supers(sync_fs_one_sb, &nowait);
-	iterate_supers(sync_blkdev_one_sb, &nowait);
+	iterate_bdevs(flush_one_bdev, NULL);
 	iterate_supers(sync_inodes_one_sb, NULL);
 	iterate_supers(sync_fs_one_sb, &wait);
-	iterate_supers(sync_blkdev_one_sb, &wait);
+	iterate_bdevs(sync_one_bdev, NULL);
 	if (unlikely(laptop_mode))
 		laptop_sync_completion();
 	return 0;
@@ -122,10 +166,10 @@ static void do_sync_work(struct work_struct *work)
 	 */
 	iterate_supers(sync_inodes_one_sb, &nowait);
 	iterate_supers(sync_fs_one_sb, &nowait);
-	iterate_supers(sync_blkdev_one_sb, &nowait);
+	sync_all_bdevs(nowait);
 	iterate_supers(sync_inodes_one_sb, &nowait);
 	iterate_supers(sync_fs_one_sb, &nowait);
-	iterate_supers(sync_blkdev_one_sb, &nowait);
+	sync_all_bdevs(nowait);
 	printk("Emergency Sync complete\n");
 	kfree(work);
 }
-- 
1.7.1