dax: move writeback calls into the filesystems

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@linux.intel.com> Signed-off-by: Jan Kara <jack@suse.cz> Cc: Al Viro <viro@ftp.linux.org.uk> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Jens Axboe <axboe@fb.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
author: Ross Zwisler <ross.zwisler@linux.intel.com> 2016-02-26 18:19:55 -0500
committer: Linus Torvalds <torvalds@linux-foundation.org> 2016-02-27 13:28:52 -0500
commit: 7f6d5b529b7dfe2fca30cbf4bc81e16575090025 (patch)
tree: 3dce0ed231dadcd470db83c1762a701004c1616b /fs
parent: 20a90f58997245749c2bdfaea9e51f785ec90d0b (diff)
5 files changed, 35 insertions, 6 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 31c6d1090f11..826b164a4b5b 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1697,13 +1697,24 @@ 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 9a173dd8c4a3..711172450da6 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -484,11 +484,10 @@ 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,
+int dax_writeback_mapping_range(struct address_space *mapping,
-                loff_t end)
+                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;
@@ -499,8 +498,11 @@ 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;
+        if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
-        end_index = end >> PAGE_CACHE_SHIFT;
+                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 4467cbd75f24..6bd58e6ff038 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -876,6 +876,14 @@ 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/inode.c b/fs/ext4/inode.c
index 5708e689e63d..aee960b1af34 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2478,6 +2478,10 @@ 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 fc20518e2398..a9ebabfe7587 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1208,6 +1208,10 @@ 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);
 }
author	Ross Zwisler <ross.zwisler@linux.intel.com>	2016-02-26 18:19:55 -0500
committer	Linus Torvalds <torvalds@linux-foundation.org>	2016-02-27 13:28:52 -0500
commit	7f6d5b529b7dfe2fca30cbf4bc81e16575090025 (patch)
tree	3dce0ed231dadcd470db83c1762a701004c1616b /fs
parent	20a90f58997245749c2bdfaea9e51f785ec90d0b (diff)