[PATCH] dax: move writeback calls into the filesystems

[Ross Zwisler]

Previously calls to dax_writeback_mapping_range() for all DAX filesystems
(ext2, ext4 & xfs) were centralized in filemap_write_and_wait_range().
dax_writeback_mapping_range() needs a struct block_device, and it used to
get that from inode->i_sb->s_bdev.  This is correct for normal inodes
mounted on ext2, ext4 and XFS filesystems, but is incorrect for DAX raw
block devices and for XFS real-time files.

Instead, call dax_writeback_mapping_range() directly from the filesystem
->writepages function so that it can supply us with a valid block
device. This also fixes DAX code to properly flush caches in response to
sync(2).

Signed-off-by: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
Signed-off-by: Jan Kara <jack@xxxxxxx>
---
 fs/block_dev.c      | 13 ++++++++++++-
 fs/dax.c            | 12 +++++++-----
 fs/ext2/inode.c     |  8 ++++++++
 fs/ext4/fsync.c     |  1 -
 fs/ext4/inode.c     |  4 ++++
 fs/xfs/xfs_aops.c   |  5 +++++
 include/linux/dax.h |  7 +++++--
 mm/filemap.c        | 12 ++++--------
 8 files changed, 45 insertions(+), 17 deletions(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 39b3a174a425..271d38aa6cbb 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1693,13 +1693,24 @@ static int blkdev_releasepage(struct page *page, gfp_t wait)
 	return try_to_free_buffers(page);
 }
 
+static int blkdev_writepages(struct address_space *mapping,
+			     struct writeback_control *wbc)
+{
+	if (dax_mapping(mapping)) {
+		struct block_device *bdev = I_BDEV(mapping->host);
+
+		return dax_writeback_mapping_range(mapping, bdev, wbc);
+	}
+	return generic_writepages(mapping, wbc);
+}
+
 static const struct address_space_operations def_blk_aops = {
 	.readpage	= blkdev_readpage,
 	.readpages	= blkdev_readpages,
 	.writepage	= blkdev_writepage,
 	.write_begin	= blkdev_write_begin,
 	.write_end	= blkdev_write_end,
-	.writepages	= generic_writepages,
+	.writepages	= blkdev_writepages,
 	.releasepage	= blkdev_releasepage,
 	.direct_IO	= blkdev_direct_IO,
 	.is_dirty_writeback = buffer_check_dirty_writeback,
diff --git a/fs/dax.c b/fs/dax.c
index fc2e3141138b..2f4965214783 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -485,11 +485,10 @@ static int dax_writeback_one(struct block_device *bdev,
  * end]. This is required by data integrity operations to ensure file data is
  * on persistent storage prior to completion of the operation.
  */
-int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
-		loff_t end)
+int dax_writeback_mapping_range(struct address_space *mapping,
+		struct block_device *bdev, struct writeback_control *wbc)
 {
 	struct inode *inode = mapping->host;
-	struct block_device *bdev = inode->i_sb->s_bdev;
 	pgoff_t start_index, end_index, pmd_index;
 	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
@@ -500,8 +499,11 @@ int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
 	if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
 		return -EIO;
 
-	start_index = start >> PAGE_CACHE_SHIFT;
-	end_index = end >> PAGE_CACHE_SHIFT;
+	if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
+		return 0;
+
+	start_index = wbc->range_start >> PAGE_CACHE_SHIFT;
+	end_index = wbc->range_end >> PAGE_CACHE_SHIFT;
 	pmd_index = DAX_PMD_INDEX(start_index);
 
 	rcu_read_lock();
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 338eefda70c6..ee05e945f40c 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -874,6 +874,14 @@ ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 static int
 ext2_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
+#ifdef CONFIG_FS_DAX
+	if (dax_mapping(mapping)) {
+		return dax_writeback_mapping_range(mapping,
+						   mapping->host->i_sb->s_bdev,
+						   wbc);
+	}
+#endif
+
 	return mpage_writepages(mapping, wbc, ext2_get_block);
 }
 
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 8850254136ae..b7136227d0f8 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -83,7 +83,6 @@ static int ext4_sync_parent(struct inode *inode)
  * What we do is just kick off a commit and wait on it.  This will snapshot the
  * inode to disk.
  */
-
 int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct inode *inode = file->f_mapping->host;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 83bc8bfb3bea..19989c12187a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2450,6 +2450,10 @@ static int ext4_writepages(struct address_space *mapping,
 
 	trace_ext4_writepages(inode, wbc);
 
+	if (dax_mapping(mapping))
+		return dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
+						   wbc);
+
 	/*
 	 * No pages to write? This is mainly a kludge to avoid starting
 	 * a transaction for special inodes like journal inode on last iput()
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 379c089fb051..fd0839278442 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1208,6 +1208,11 @@ xfs_vm_writepages(
 	struct writeback_control *wbc)
 {
 	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
+	if (dax_mapping(mapping)) {
+		return dax_writeback_mapping_range(mapping,
+				xfs_find_bdev_for_inode(mapping->host), wbc);
+	}
+
 	return generic_writepages(mapping, wbc);
 }
 
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 818e45078929..05d7d043d3bd 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -52,6 +52,9 @@ static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);
 }
-int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
-		loff_t end);
+
+struct writeback_control;
+
+int dax_writeback_mapping_range(struct address_space *mapping,
+		struct block_device *bdev, struct writeback_control *wbc);
 #endif
diff --git a/mm/filemap.c b/mm/filemap.c
index bc943867d68c..af3eec1a8c5e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -446,7 +446,8 @@ int filemap_write_and_wait(struct address_space *mapping)
 {
 	int err = 0;
 
-	if (mapping->nrpages) {
+	if ((!dax_mapping(mapping) && mapping->nrpages) ||
+	    (dax_mapping(mapping) && mapping->nrexceptional)) {
 		err = filemap_fdatawrite(mapping);
 		/*
 		 * Even if the above returned error, the pages may be
@@ -482,13 +483,8 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 {
 	int err = 0;
 
-	if (dax_mapping(mapping) && mapping->nrexceptional) {
-		err = dax_writeback_mapping_range(mapping, lstart, lend);
-		if (err)
-			return err;
-	}
-
-	if (mapping->nrpages) {
+	if ((!dax_mapping(mapping) && mapping->nrpages) ||
+	    (dax_mapping(mapping) && mapping->nrexceptional)) {
 		err = __filemap_fdatawrite_range(mapping, lstart, lend,
 						 WB_SYNC_ALL);
 		/* See comment of filemap_write_and_wait() */
-- 
2.6.2


--LQksG6bCIzRHxTLp--